Mercurial > hg > compact-paper
changeset 32054:616e788321cc stable 4.2-rc
freeze: merge default into stable for 4.2 code freeze
| author | Augie Fackler <augie@google.com> |
|---|---|
| date | Tue, 18 Apr 2017 12:24:34 -0400 |
| parents | 52902059edc7 (current diff) ed42e00a5c4e (diff) |
| children | f64ac87d82f9 |
| files | contrib/hgperf contrib/python-zstandard/c-ext/dictparams.c contrib/python-zstandard/tests/test_cffi.py contrib/python-zstandard/tests/test_roundtrip.py mercurial/dispatch.py tests/test-ssh.t |
| diffstat | 445 files changed, 35348 insertions(+), 10166 deletions(-) [+] |
line wrap: on
line diff
--- a/Makefile Tue Apr 18 11:22:42 2017 -0400 +++ b/Makefile Tue Apr 18 12:24:34 2017 -0400 @@ -159,10 +159,21 @@ # Packaging targets osx: + rm -rf build/mercurial /usr/bin/python2.7 setup.py install --optimize=1 \ --root=build/mercurial/ --prefix=/usr/local/ \ --install-lib=/Library/Python/2.7/site-packages/ make -C doc all install DESTDIR="$(PWD)/build/mercurial/" + # install zsh completions - this location appears to be + # searched by default as of macOS Sierra. + install -d build/mercurial/usr/local/share/zsh/site-functions/ + install -m 0644 contrib/zsh_completion build/mercurial/usr/local/share/zsh/site-functions/hg + # install bash completions - there doesn't appear to be a + # place that's searched by default for bash, so we'll follow + # the lead of Apple's git install and just put it in a + # location of our own. + install -d build/mercurial/usr/local/hg/contrib/ + install -m 0644 contrib/bash_completion build/mercurial/usr/local/hg/contrib/hg-completion.bash mkdir -p $${OUTPUTDIR:-dist} HGVER=$$((cat build/mercurial/Library/Python/2.7/site-packages/mercurial/__version__.py; echo 'print(version)') | python) && \ OSXVER=$$(sw_vers -productVersion | cut -d. -f1,2) && \ @@ -262,5 +273,9 @@ .PHONY: help all local build doc cleanbutpackages clean install install-bin \ install-doc install-home install-home-bin install-home-doc \ dist dist-notests check tests check-code update-pot \ - osx fedora20 docker-fedora20 fedora21 docker-fedora21 \ + osx deb ppa docker-debian-jessie \ + docker-ubuntu-trusty docker-ubuntu-trusty-ppa \ + docker-ubuntu-xenial docker-ubuntu-xenial-ppa \ + docker-ubuntu-yakkety docker-ubuntu-yakkety-ppa \ + fedora20 docker-fedora20 fedora21 docker-fedora21 \ centos5 docker-centos5 centos6 docker-centos6 centos7 docker-centos7
--- a/contrib/check-code.py Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/check-code.py Tue Apr 18 12:24:34 2017 -0400 @@ -100,7 +100,7 @@ testpats = [ [ - (r'pushd|popd', "don't use 'pushd' or 'popd', use 'cd'"), + (r'\b(push|pop)d\b', "don't use 'pushd' or 'popd', use 'cd'"), (r'\W\$?\(\([^\)\n]*\)\)', "don't use (()) or $(()), use 'expr'"), (r'grep.*-q', "don't use 'grep -q', redirect to /dev/null"), (r'(?<!hg )grep.* -a', "don't use 'grep -a', use in-line python"), @@ -190,8 +190,10 @@ (r'^ .*: largefile \S+ not available from file:.*/.*[^)]$', winglobmsg), (r'^ .*file://\$TESTTMP', 'write "file:/*/$TESTTMP" + (glob) to match on windows too'), - (r'^ [^$>].*27\.0\.0\.1.*[^)]$', - 'use (glob) to match localhost IP on hosts without 127.0.0.1 too'), + (r'^ [^$>].*27\.0\.0\.1', + 'use $LOCALIP not an explicit loopback address'), + (r'^ [^$>].*\$LOCALIP.*[^)]$', + 'mark $LOCALIP output lines with (glob) to help tests in BSD jails'), (r'^ (cat|find): .*: No such file or directory', 'use test -f to test for file existence'), (r'^ diff -[^ -]*p', @@ -210,8 +212,8 @@ ], # warnings [ - (r'^ (?!.*127\.0\.0\.1)[^*?/\n]* \(glob\)$', - "glob match with no glob string (?, *, /, and 127.0.0.1)"), + (r'^ (?!.*\$LOCALIP)[^*?/\n]* \(glob\)$', + "glob match with no glob string (?, *, /, and $LOCALIP)"), ] ] @@ -237,7 +239,7 @@ (r'lambda\s*\(.*,.*\)', "tuple parameter unpacking not available in Python 3+"), (r'(?<!def)\s+(cmp)\(', "cmp is not available in Python 3+"), - (r'\breduce\s*\(.*', "reduce is not available in Python 3+"), + (r'(?<!\.)\breduce\s*\(.*', "reduce is not available in Python 3+"), (r'\bdict\(.*=', 'dict() is different in Py2 and 3 and is slower than {}', 'dict-from-generator'), (r'\.has_key\b', "dict.has_key is not available in Python 3+"), @@ -318,7 +320,7 @@ 'legacy exception syntax; use "as" instead of ","'), (r':\n( )*( ){1,3}[^ ]', "must indent 4 spaces"), (r'release\(.*wlock, .*lock\)', "wrong lock release order"), - (r'\b__bool__\b', "__bool__ should be __nonzero__ in Python 2"), + (r'\bdef\s+__bool__\b', "__bool__ should be __nonzero__ in Python 2"), (r'os\.path\.join\(.*, *(""|\'\')\)', "use pathutil.normasprefix(path) instead of os.path.join(path, '')"), (r'\s0[0-7]+\b', 'legacy octal syntax; use "0o" prefix instead of "0"'), @@ -330,13 +332,15 @@ (r'^import cStringIO', "don't use cStringIO.StringIO, use util.stringio"), (r'^import urllib', "don't use urllib, use util.urlreq/util.urlerr"), (r'^import SocketServer', "don't use SockerServer, use util.socketserver"), - (r'^import urlparse', "don't use urlparse, use util.urlparse"), + (r'^import urlparse', "don't use urlparse, use util.urlreq"), (r'^import xmlrpclib', "don't use xmlrpclib, use util.xmlrpclib"), (r'^import cPickle', "don't use cPickle, use util.pickle"), (r'^import pickle', "don't use pickle, use util.pickle"), (r'^import httplib', "don't use httplib, use util.httplib"), (r'^import BaseHTTPServer', "use util.httpserver instead"), (r'\.next\(\)', "don't use .next(), use next(...)"), + (r'([a-z]*).revision\(\1\.node\(', + "don't convert rev to node before passing to revision(nodeorrev)"), # rules depending on implementation of repquote() (r' x+[xpqo%APM][\'"]\n\s+[\'"]x', @@ -371,6 +375,13 @@ (?P=quote))""", reppython), ] +# extension non-filter patterns +pyextnfpats = [ + [(r'^"""\n?[A-Z]', "don't capitalize docstring title")], + # warnings + [], +] + txtfilters = [] txtpats = [ @@ -480,6 +491,7 @@ checks = [ ('python', r'.*\.(py|cgi)$', r'^#!.*python', pyfilters, pypats), + ('python', r'.*hgext.*\.py$', '', [], pyextnfpats), ('python 3', r'.*(hgext|mercurial).*(?<!pycompat)\.py', '', pyfilters, py3pats), ('test script', r'(.*/)?test-[^.~]*$', '', testfilters, testpats), @@ -661,7 +673,7 @@ return result def main(): - parser = optparse.OptionParser("%prog [options] [files]") + parser = optparse.OptionParser("%prog [options] [files | -]") parser.add_option("-w", "--warnings", action="store_true", help="include warning-level checks") parser.add_option("-p", "--per-file", type="int", @@ -679,6 +691,9 @@ if len(args) == 0: check = glob.glob("*") + elif args == ['-']: + # read file list from stdin + check = sys.stdin.read().splitlines() else: check = args
--- a/contrib/chg/chg.c Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/chg/chg.c Tue Apr 18 12:24:34 2017 -0400 @@ -128,6 +128,24 @@ abortmsg("insecure sockdir %s", sockdir); } +/* + * Check if a socket directory exists and is only owned by the current user. + * Return 1 if so, 0 if not. This is used to check if XDG_RUNTIME_DIR can be + * used or not. According to the specification [1], XDG_RUNTIME_DIR should be + * ignored if the directory is not owned by the user with mode 0700. + * [1]: https://standards.freedesktop.org/basedir-spec/basedir-spec-latest.html + */ +static int checkruntimedir(const char *sockdir) +{ + struct stat st; + int r = lstat(sockdir, &st); + if (r < 0) /* ex. does not exist */ + return 0; + if (!S_ISDIR(st.st_mode)) /* ex. is a file, not a directory */ + return 0; + return st.st_uid == geteuid() && (st.st_mode & 0777) == 0700; +} + static void getdefaultsockdir(char sockdir[], size_t size) { /* by default, put socket file in secure directory @@ -135,7 +153,7 @@ * (permission of socket file may be ignored on some Unices) */ const char *runtimedir = getenv("XDG_RUNTIME_DIR"); int r; - if (runtimedir) { + if (runtimedir && checkruntimedir(runtimedir)) { r = snprintf(sockdir, size, "%s/chg", runtimedir); } else { const char *tmpdir = getenv("TMPDIR"); @@ -429,11 +447,11 @@ } setupsignalhandler(hgc_peerpid(hgc), hgc_peerpgid(hgc)); + atexit(waitpager); int exitcode = hgc_runcommand(hgc, argv + 1, argc - 1); restoresignalhandler(); hgc_close(hgc); freecmdserveropts(&opts); - waitpager(); return exitcode; }
--- a/contrib/chg/hgclient.c Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/chg/hgclient.c Tue Apr 18 12:24:34 2017 -0400 @@ -252,7 +252,7 @@ ctx->datasize = sizeof(r_n); writeblock(hgc); } else if (strcmp(args[0], "pager") == 0) { - setuppager(args[1]); + setuppager(args[1], args + 3); if (hgc->capflags & CAP_ATTACHIO) attachio(hgc); /* unblock the server */
--- a/contrib/chg/procutil.c Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/chg/procutil.c Tue Apr 18 12:24:34 2017 -0400 @@ -91,11 +91,15 @@ struct sigaction sa; memset(&sa, 0, sizeof(sa)); + + /* deadly signals meant to be sent to a process group: + * - SIGHUP: usually generated by the kernel, when termination of a + * process causes that process group to become orphaned + * - SIGINT: usually generated by the terminal */ sa.sa_handler = forwardsignaltogroup; sa.sa_flags = SA_RESTART; if (sigemptyset(&sa.sa_mask) < 0) goto error; - if (sigaction(SIGHUP, &sa, NULL) < 0) goto error; if (sigaction(SIGINT, &sa, NULL) < 0) @@ -111,6 +115,11 @@ sa.sa_flags = SA_RESTART; if (sigaction(SIGWINCH, &sa, NULL) < 0) goto error; + /* forward user-defined signals */ + if (sigaction(SIGUSR1, &sa, NULL) < 0) + goto error; + if (sigaction(SIGUSR2, &sa, NULL) < 0) + goto error; /* propagate job control requests to worker */ sa.sa_handler = forwardsignal; sa.sa_flags = SA_RESTART; @@ -168,7 +177,7 @@ /* This implementation is based on hgext/pager.py (post 369741ef7253) * Return 0 if pager is not started, or pid of the pager */ -pid_t setuppager(const char *pagercmd) +pid_t setuppager(const char *pagercmd, const char *envp[]) { assert(pagerpid == 0); if (!pagercmd) @@ -196,7 +205,8 @@ close(pipefds[0]); close(pipefds[1]); - int r = execlp("/bin/sh", "/bin/sh", "-c", pagercmd, NULL); + int r = execle("/bin/sh", "/bin/sh", "-c", pagercmd, NULL, + envp); if (r < 0) { abortmsgerrno("cannot start pager '%s'", pagercmd); }
--- a/contrib/chg/procutil.h Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/chg/procutil.h Tue Apr 18 12:24:34 2017 -0400 @@ -15,7 +15,7 @@ void restoresignalhandler(void); void setupsignalhandler(pid_t pid, pid_t pgid); -pid_t setuppager(const char *pagercmd); +pid_t setuppager(const char *pagercmd, const char *envp[]); void waitpager(void); #endif /* PROCUTIL_H_ */
--- a/contrib/hgperf Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/hgperf Tue Apr 18 12:24:34 2017 -0400 @@ -55,17 +55,15 @@ import mercurial.util import mercurial.dispatch -import time - def timer(func, title=None): results = [] - begin = time.time() + begin = mercurial.util.timer() count = 0 while True: ostart = os.times() - cstart = time.time() + cstart = mercurial.util.timer() r = func() - cstop = time.time() + cstop = mercurial.util.timer() ostop = os.times() count += 1 a, b = ostart, ostop
--- a/contrib/memory.py Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/memory.py Tue Apr 18 12:24:34 2017 -0400 @@ -12,7 +12,6 @@ ''' from __future__ import absolute_import -import atexit def memusage(ui): """Report memory usage of the current process.""" @@ -29,4 +28,4 @@ for k, v in result.iteritems()]) + "\n") def extsetup(ui): - atexit.register(memusage, ui) + ui.atexit(memusage, ui)
--- a/contrib/perf.py Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/perf.py Tue Apr 18 12:24:34 2017 -0400 @@ -20,6 +20,7 @@ from __future__ import absolute_import import functools +import gc import os import random import sys @@ -66,6 +67,16 @@ setattr(util, 'safehasattr', safehasattr) # for "historical portability": +# define util.timer forcibly, because util.timer has been available +# since ae5d60bb70c9 +if safehasattr(time, 'perf_counter'): + util.timer = time.perf_counter +elif os.name == 'nt': + util.timer = time.clock +else: + util.timer = time.time + +# for "historical portability": # use locally defined empty option list, if formatteropts isn't # available, because commands.formatteropts has been available since # 3.2 (or 7a7eed5176a4), even though formatting itself has been @@ -164,6 +175,7 @@ self.hexfunc = node.short def __nonzero__(self): return False + __bool__ = __nonzero__ def startitem(self): pass def data(self, **data): @@ -189,14 +201,15 @@ func() def _timer(fm, func, title=None): + gc.collect() results = [] - begin = time.time() + begin = util.timer() count = 0 while True: ostart = os.times() - cstart = time.time() + cstart = util.timer() r = func() - cstop = time.time() + cstop = util.timer() ostop = os.times() count += 1 a, b = ostart, ostop @@ -993,6 +1006,26 @@ node = r.lookup(rev) rev = r.rev(node) + def getrawchunks(data, chain): + start = r.start + length = r.length + inline = r._inline + iosize = r._io.size + buffer = util.buffer + offset = start(chain[0]) + + chunks = [] + ladd = chunks.append + + for rev in chain: + chunkstart = start(rev) + if inline: + chunkstart += (rev + 1) * iosize + chunklength = length(rev) + ladd(buffer(data, chunkstart - offset, chunklength)) + + return chunks + def dodeltachain(rev): if not cache: r.clearcaches() @@ -1003,24 +1036,15 @@ r.clearcaches() r._chunkraw(chain[0], chain[-1]) - def dodecompress(data, chain): + def dorawchunks(data, chain): if not cache: r.clearcaches() - - start = r.start - length = r.length - inline = r._inline - iosize = r._io.size - buffer = util.buffer - offset = start(chain[0]) + getrawchunks(data, chain) - for rev in chain: - chunkstart = start(rev) - if inline: - chunkstart += (rev + 1) * iosize - chunklength = length(rev) - b = buffer(data, chunkstart - offset, chunklength) - r.decompress(b) + def dodecompress(chunks): + decomp = r.decompress + for chunk in chunks: + decomp(chunk) def dopatch(text, bins): if not cache: @@ -1039,6 +1063,7 @@ chain = r._deltachain(rev)[0] data = r._chunkraw(chain[0], chain[-1])[1] + rawchunks = getrawchunks(data, chain) bins = r._chunks(chain) text = str(bins[0]) bins = bins[1:] @@ -1048,7 +1073,8 @@ (lambda: dorevision(), 'full'), (lambda: dodeltachain(rev), 'deltachain'), (lambda: doread(chain), 'read'), - (lambda: dodecompress(data, chain), 'decompress'), + (lambda: dorawchunks(data, chain), 'rawchunks'), + (lambda: dodecompress(rawchunks), 'decompress'), (lambda: dopatch(text, bins), 'patch'), (lambda: dohash(text), 'hash'), ] @@ -1256,6 +1282,17 @@ timer(fn, title=title) fm.end() +@command('perfwrite', formatteropts) +def perfwrite(ui, repo, **opts): + """microbenchmark ui.write + """ + timer, fm = gettimer(ui, opts) + def write(): + for i in range(100000): + ui.write(('Testing write performance\n')) + timer(write) + fm.end() + def uisetup(ui): if (util.safehasattr(cmdutil, 'openrevlog') and not util.safehasattr(commands, 'debugrevlogopts')):
--- a/contrib/python-zstandard/NEWS.rst Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/python-zstandard/NEWS.rst Tue Apr 18 12:24:34 2017 -0400 @@ -1,6 +1,66 @@ Version History =============== +0.8.1 (released 2017-04-08) +--------------------------- + +* Add #includes so compilation on OS X and BSDs works (#20). + +0.8.0 (released 2017-03-08) +--------------------------- + +* CompressionParameters now has a estimated_compression_context_size() method. + zstd.estimate_compression_context_size() is now deprecated and slated for + removal. +* Implemented a lot of fuzzing tests. +* CompressionParameters instances now perform extra validation by calling + ZSTD_checkCParams() at construction time. +* multi_compress_to_buffer() API for compressing multiple inputs as a + single operation, as efficiently as possible. +* ZSTD_CStream instances are now used across multiple operations on + ZstdCompressor instances, resulting in much better performance for + APIs that do streaming. +* ZSTD_DStream instances are now used across multiple operations on + ZstdDecompressor instances, resulting in much better performance for + APIs that do streaming. +* train_dictionary() now releases the GIL. +* Support for training dictionaries using the COVER algorithm. +* multi_decompress_to_buffer() API for decompressing multiple frames as a + single operation, as efficiently as possible. +* Support for multi-threaded compression. +* Disable deprecation warnings when compiling CFFI module. +* Fixed memory leak in train_dictionary(). +* Removed DictParameters type. +* train_dictionary() now accepts keyword arguments instead of a + DictParameters instance to control dictionary generation. + +0.7.0 (released 2017-02-07) +--------------------------- + +* Added zstd.get_frame_parameters() to obtain info about a zstd frame. +* Added ZstdDecompressor.decompress_content_dict_chain() for efficient + decompression of *content-only dictionary chains*. +* CFFI module fully implemented; all tests run against both C extension and + CFFI implementation. +* Vendored version of zstd updated to 1.1.3. +* Use ZstdDecompressor.decompress() now uses ZSTD_createDDict_byReference() + to avoid extra memory allocation of dict data. +* Add function names to error messages (by using ":name" in PyArg_Parse* + functions). +* Reuse decompression context across operations. Previously, we created a + new ZSTD_DCtx for each decompress(). This was measured to slow down + decompression by 40-200MB/s. The API guarantees say ZstdDecompressor + is not thread safe. So we reuse the ZSTD_DCtx across operations and make + things faster in the process. +* ZstdCompressor.write_to()'s compress() and flush() methods now return number + of bytes written. +* ZstdDecompressor.write_to()'s write() method now returns the number of bytes + written to the underlying output object. +* CompressionParameters instances now expose their values as attributes. +* CompressionParameters instances no longer are subscriptable nor behave + as tuples (backwards incompatible). Use attributes to obtain values. +* DictParameters instances now expose their values as attributes. + 0.6.0 (released 2017-01-14) ---------------------------
--- a/contrib/python-zstandard/README.rst Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/python-zstandard/README.rst Tue Apr 18 12:24:34 2017 -0400 @@ -4,10 +4,11 @@ This project provides Python bindings for interfacing with the `Zstandard <http://www.zstd.net>`_ compression library. A C extension -and CFFI interface is provided. +and CFFI interface are provided. -The primary goal of the extension is to provide a Pythonic interface to -the underlying C API. This means exposing most of the features and flexibility +The primary goal of the project is to provide a rich interface to the +underlying C API through a Pythonic interface while not sacrificing +performance. This means exposing most of the features and flexibility of the C API while not sacrificing usability or safety that Python provides. The canonical home for this project is @@ -19,15 +20,24 @@ ================ The project is officially in beta state. The author is reasonably satisfied -with the current API and that functionality works as advertised. There -may be some backwards incompatible changes before 1.0. Though the author -does not intend to make any major changes to the Python API. +that functionality works as advertised. **There will be some backwards +incompatible changes before 1.0, probably in the 0.9 release.** This may +involve renaming the main module from *zstd* to *zstandard* and renaming +various types and methods. Pin the package version to prevent unwanted +breakage when this change occurs! + +This project is vendored and distributed with Mercurial 4.1, where it is +used in a production capacity. There is continuous integration for Python versions 2.6, 2.7, and 3.3+ on Linux x86_x64 and Windows x86 and x86_64. The author is reasonably confident the extension is stable and works as advertised on these platforms. +The CFFI bindings are mostly feature complete. Where a feature is implemented +in CFFI, unit tests run against both C extension and CFFI implementation to +ensure behavior parity. + Expected Changes ---------------- @@ -43,19 +53,27 @@ There should be an API that accepts an object that conforms to the buffer interface and returns an iterator over compressed or decompressed output. +There should be an API that exposes an ``io.RawIOBase`` interface to +compressor and decompressor streams, like how ``gzip.GzipFile`` from +the standard library works (issue 13). + The author is on the fence as to whether to support the extremely low level compression and decompression APIs. It could be useful to support compression without the framing headers. But the author doesn't believe it a high priority at this time. -The CFFI bindings are half-baked and need to be finished. +There will likely be a refactoring of the module names. Currently, +``zstd`` is a C extension and ``zstd_cffi`` is the CFFI interface. +This means that all code for the C extension must be implemented in +C. ``zstd`` may be converted to a Python module so code can be reused +between CFFI and C and so not all code in the C extension has to be C. Requirements ============ -This extension is designed to run with Python 2.6, 2.7, 3.3, 3.4, and 3.5 -on common platforms (Linux, Windows, and OS X). Only x86_64 is currently -well-tested as an architecture. +This extension is designed to run with Python 2.6, 2.7, 3.3, 3.4, 3.5, and +3.6 on common platforms (Linux, Windows, and OS X). Only x86_64 is +currently well-tested as an architecture. Installing ========== @@ -106,15 +124,11 @@ Comparison to Other Python Bindings =================================== -https://pypi.python.org/pypi/zstd is an alternative Python binding to +https://pypi.python.org/pypi/zstd is an alternate Python binding to Zstandard. At the time this was written, the latest release of that -package (1.0.0.2) had the following significant differences from this package: - -* It only exposes the simple API for compression and decompression operations. - This extension exposes the streaming API, dictionary training, and more. -* It adds a custom framing header to compressed data and there is no way to - disable it. This means that data produced with that module cannot be used by - other Zstandard implementations. +package (1.1.2) only exposed the simple APIs for compression and decompression. +This package exposes much more of the zstd API, including streaming and +dictionary compression. This package also has CFFI support. Bundling of Zstandard Source Code ================================= @@ -151,10 +165,13 @@ $ tox Tests use the ``hypothesis`` Python package to perform fuzzing. If you -don't have it, those tests won't run. +don't have it, those tests won't run. Since the fuzzing tests take longer +to execute than normal tests, you'll need to opt in to running them by +setting the ``ZSTD_SLOW_TESTS`` environment variable. This is set +automatically when using ``tox``. -There is also an experimental CFFI module. You need the ``cffi`` Python -package installed to build and test that. +The ``cffi`` Python package needs to be installed in order to build the CFFI +bindings. If it isn't present, the CFFI bindings won't be built. To create a virtualenv with all development dependencies, do something like the following:: @@ -171,8 +188,16 @@ API === -The compiled C extension provides a ``zstd`` Python module. This module -exposes the following interfaces. +The compiled C extension provides a ``zstd`` Python module. The CFFI +bindings provide a ``zstd_cffi`` module. Both provide an identical API +interface. The types, functions, and attributes exposed by these modules +are documented in the sections below. + +.. note:: + + The documentation in this section makes references to various zstd + concepts and functionality. The ``Concepts`` section below explains + these concepts in more detail. ZstdCompressor -------------- @@ -208,6 +233,14 @@ Whether to write the dictionary ID into the compressed data. Defaults to True. The dictionary ID is only written if a dictionary is being used. +threads + Enables and sets the number of threads to use for multi-threaded compression + operations. Defaults to 0, which means to use single-threaded compression. + Negative values will resolve to the number of logical CPUs in the system. + Read below for more info on multi-threaded compression. This argument only + controls thread count for operations that operate on individual pieces of + data. APIs that spawn multiple threads for working on multiple pieces of + data have their own ``threads`` argument. Unless specified otherwise, assume that no two methods of ``ZstdCompressor`` instances can be called from multiple Python threads simultaneously. In other @@ -221,6 +254,8 @@ cctx = zstd.ZstdCompressor() compressed = cctx.compress(b'data to compress') +The ``data`` argument can be any object that implements the *buffer protocol*. + Unless ``compression_params`` or ``dict_data`` are passed to the ``ZstdCompressor``, each invocation of ``compress()`` will calculate the optimal compression parameters for the configured compression ``level`` and @@ -260,6 +295,10 @@ compressor's internal state into the output object. This may result in 0 or more ``write()`` calls to the output object. +Both ``write()`` and ``flush()`` return the number of bytes written to the +object's ``write()``. In many cases, small inputs do not accumulate enough +data to cause a write and ``write()`` will return ``0``. + If the size of the data being fed to this streaming compressor is known, you can declare it before compression begins:: @@ -406,6 +445,42 @@ data = cobj.compress(b'foobar') data = cobj.flush() +Batch Compression API +^^^^^^^^^^^^^^^^^^^^^ + +(Experimental. Not yet supported in CFFI bindings.) + +``multi_compress_to_buffer(data, [threads=0])`` performs compression of multiple +inputs as a single operation. + +Data to be compressed can be passed as a ``BufferWithSegmentsCollection``, a +``BufferWithSegments``, or a list containing byte like objects. Each element of +the container will be compressed individually using the configured parameters +on the ``ZstdCompressor`` instance. + +The ``threads`` argument controls how many threads to use for compression. The +default is ``0`` which means to use a single thread. Negative values use the +number of logical CPUs in the machine. + +The function returns a ``BufferWithSegmentsCollection``. This type represents +N discrete memory allocations, eaching holding 1 or more compressed frames. + +Output data is written to shared memory buffers. This means that unlike +regular Python objects, a reference to *any* object within the collection +keeps the shared buffer and therefore memory backing it alive. This can have +undesirable effects on process memory usage. + +The API and behavior of this function is experimental and will likely change. +Known deficiencies include: + +* If asked to use multiple threads, it will always spawn that many threads, + even if the input is too small to use them. It should automatically lower + the thread count when the extra threads would just add overhead. +* The buffer allocation strategy is fixed. There is room to make it dynamic, + perhaps even to allow one output buffer per input, facilitating a variation + of the API to return a list without the adverse effects of shared memory + buffers. + ZstdDecompressor ---------------- @@ -476,6 +551,10 @@ the decompressor by calling ``write(data)`` and decompressed output is written to the output object by calling its ``write(data)`` method. +Calls to ``write()`` will return the number of bytes written to the output +object. Not all inputs will result in bytes being written, so return values +of ``0`` are possible. + The size of chunks being ``write()`` to the destination can be specified:: dctx = zstd.ZstdDecompressor() @@ -576,64 +655,155 @@ data = dobj.decompress(compressed_chunk_0) data = dobj.decompress(compressed_chunk_1) -Choosing an API ---------------- +Batch Decompression API +^^^^^^^^^^^^^^^^^^^^^^^ + +(Experimental. Not yet supported in CFFI bindings.) + +``multi_decompress_to_buffer()`` performs decompression of multiple +frames as a single operation and returns a ``BufferWithSegmentsCollection`` +containing decompressed data for all inputs. -Various forms of compression and decompression APIs are provided because each -are suitable for different use cases. +Compressed frames can be passed to the function as a ``BufferWithSegments``, +a ``BufferWithSegmentsCollection``, or as a list containing objects that +conform to the buffer protocol. For best performance, pass a +``BufferWithSegmentsCollection`` or a ``BufferWithSegments``, as +minimal input validation will be done for that type. If calling from +Python (as opposed to C), constructing one of these instances may add +overhead cancelling out the performance overhead of validation for list +inputs. + +The decompressed size of each frame must be discoverable. It can either be +embedded within the zstd frame (``write_content_size=True`` argument to +``ZstdCompressor``) or passed in via the ``decompressed_sizes`` argument. + +The ``decompressed_sizes`` argument is an object conforming to the buffer +protocol which holds an array of 64-bit unsigned integers in the machine's +native format defining the decompressed sizes of each frame. If this argument +is passed, it avoids having to scan each frame for its decompressed size. +This frame scanning can add noticeable overhead in some scenarios. -The simple/one-shot APIs are useful for small data, when the decompressed -data size is known (either recorded in the zstd frame header via -``write_content_size`` or known via an out-of-band mechanism, such as a file -size). +The ``threads`` argument controls the number of threads to use to perform +decompression operations. The default (``0``) or the value ``1`` means to +use a single thread. Negative values use the number of logical CPUs in the +machine. + +.. note:: + + It is possible to pass a ``mmap.mmap()`` instance into this function by + wrapping it with a ``BufferWithSegments`` instance (which will define the + offsets of frames within the memory mapped region). + +This function is logically equivalent to performing ``dctx.decompress()`` +on each input frame and returning the result. -A limitation of the simple APIs is that input or output data must fit in memory. -And unless using advanced tricks with Python *buffer objects*, both input and -output must fit in memory simultaneously. +This function exists to perform decompression on multiple frames as fast +as possible by having as little overhead as possible. Since decompression is +performed as a single operation and since the decompressed output is stored in +a single buffer, extra memory allocations, Python objects, and Python function +calls are avoided. This is ideal for scenarios where callers need to access +decompressed data for multiple frames. -Another limitation is that compression or decompression is performed as a single -operation. So if you feed large input, it could take a long time for the -function to return. +Currently, the implementation always spawns multiple threads when requested, +even if the amount of work to do is small. In the future, it will be smarter +about avoiding threads and their associated overhead when the amount of +work to do is small. + +Content-Only Dictionary Chain Decompression +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +``decompress_content_dict_chain(frames)`` performs decompression of a list of +zstd frames produced using chained *content-only* dictionary compression. Such +a list of frames is produced by compressing discrete inputs where each +non-initial input is compressed with a *content-only* dictionary consisting +of the content of the previous input. + +For example, say you have the following inputs:: -The streaming APIs do not have the limitations of the simple API. The cost to -this is they are more complex to use than a single function call. + inputs = [b'input 1', b'input 2', b'input 3'] + +The zstd frame chain consists of: + +1. ``b'input 1'`` compressed in standalone/discrete mode +2. ``b'input 2'`` compressed using ``b'input 1'`` as a *content-only* dictionary +3. ``b'input 3'`` compressed using ``b'input 2'`` as a *content-only* dictionary + +Each zstd frame **must** have the content size written. + +The following Python code can be used to produce a *content-only dictionary +chain*:: -The streaming APIs put the caller in control of compression and decompression -behavior by allowing them to directly control either the input or output side -of the operation. + def make_chain(inputs): + frames = [] + + # First frame is compressed in standalone/discrete mode. + zctx = zstd.ZstdCompressor(write_content_size=True) + frames.append(zctx.compress(inputs[0])) -With the streaming input APIs, the caller feeds data into the compressor or -decompressor as they see fit. Output data will only be written after the caller -has explicitly written data. + # Subsequent frames use the previous fulltext as a content-only dictionary + for i, raw in enumerate(inputs[1:]): + dict_data = zstd.ZstdCompressionDict(inputs[i]) + zctx = zstd.ZstdCompressor(write_content_size=True, dict_data=dict_data) + frames.append(zctx.compress(raw)) + + return frames + +``decompress_content_dict_chain()`` returns the uncompressed data of the last +element in the input chain. -With the streaming output APIs, the caller consumes output from the compressor -or decompressor as they see fit. The compressor or decompressor will only -consume data from the source when the caller is ready to receive it. +It is possible to implement *content-only dictionary chain* decompression +on top of other Python APIs. However, this function will likely be significantly +faster, especially for long input chains, as it avoids the overhead of +instantiating and passing around intermediate objects between C and Python. + +Multi-Threaded Compression +-------------------------- + +``ZstdCompressor`` accepts a ``threads`` argument that controls the number +of threads to use for compression. The way this works is that input is split +into segments and each segment is fed into a worker pool for compression. Once +a segment is compressed, it is flushed/appended to the output. + +The segment size for multi-threaded compression is chosen from the window size +of the compressor. This is derived from the ``window_log`` attribute of a +``CompressionParameters`` instance. By default, segment sizes are in the 1+MB +range. -One end of the streaming APIs involves a file-like object that must -``write()`` output data or ``read()`` input data. Depending on what the -backing storage for these objects is, those operations may not complete quickly. -For example, when streaming compressed data to a file, the ``write()`` into -a streaming compressor could result in a ``write()`` to the filesystem, which -may take a long time to finish due to slow I/O on the filesystem. So, there -may be overhead in streaming APIs beyond the compression and decompression -operations. +If multi-threaded compression is requested and the input is smaller than the +configured segment size, only a single compression thread will be used. If the +input is smaller than the segment size multiplied by the thread pool size or +if data cannot be delivered to the compressor fast enough, not all requested +compressor threads may be active simultaneously. + +Compared to non-multi-threaded compression, multi-threaded compression has +higher per-operation overhead. This includes extra memory operations, +thread creation, lock acquisition, etc. + +Due to the nature of multi-threaded compression using *N* compression +*states*, the output from multi-threaded compression will likely be larger +than non-multi-threaded compression. The difference is usually small. But +there is a CPU/wall time versus size trade off that may warrant investigation. + +Output from multi-threaded compression does not require any special handling +on the decompression side. In other words, any zstd decompressor should be able +to consume data produced with multi-threaded compression. Dictionary Creation and Management ---------------------------------- -Zstandard allows *dictionaries* to be used when compressing and -decompressing data. The idea is that if you are compressing a lot of similar -data, you can precompute common properties of that data (such as recurring -byte sequences) to achieve better compression ratios. - -In Python, compression dictionaries are represented as the -``ZstdCompressionDict`` type. +Compression dictionaries are represented as the ``ZstdCompressionDict`` type. Instances can be constructed from bytes:: dict_data = zstd.ZstdCompressionDict(data) +It is possible to construct a dictionary from *any* data. Unless the +data begins with a magic header, the dictionary will be treated as +*content-only*. *Content-only* dictionaries allow compression operations +that follow to reference raw data within the content. For one use of +*content-only* dictionaries, see +``ZstdDecompressor.decompress_content_dict_chain()``. + More interestingly, instances can be created by *training* on sample data:: dict_data = zstd.train_dictionary(size, samples) @@ -673,6 +843,88 @@ dict_data = zstd.train_dictionary(size, samples) raw_data = dict_data.as_bytes() +The following named arguments to ``train_dictionary`` can also be used +to further control dictionary generation. + +selectivity + Integer selectivity level. Default is 9. Larger values yield more data in + dictionary. +level + Integer compression level. Default is 6. +dict_id + Integer dictionary ID for the produced dictionary. Default is 0, which + means to use a random value. +notifications + Controls writing of informational messages to ``stderr``. ``0`` (the + default) means to write nothing. ``1`` writes errors. ``2`` writes + progression info. ``3`` writes more details. And ``4`` writes all info. + +Cover Dictionaries +^^^^^^^^^^^^^^^^^^ + +An alternate dictionary training mechanism named *cover* is also available. +More details about this training mechanism are available in the paper +*Effective Construction of Relative Lempel-Ziv Dictionaries* (authors: +Liao, Petri, Moffat, Wirth). + +To use this mechanism, use ``zstd.train_cover_dictionary()`` instead of +``zstd.train_dictionary()``. The function behaves nearly the same except +its arguments are different and the returned dictionary will contain ``k`` +and ``d`` attributes reflecting the parameters to the cover algorithm. + +.. note:: + + The ``k`` and ``d`` attributes are only populated on dictionary + instances created by this function. If a ``ZstdCompressionDict`` is + constructed from raw bytes data, the ``k`` and ``d`` attributes will + be ``0``. + +The segment and dmer size parameters to the cover algorithm can either be +specified manually or you can ask ``train_cover_dictionary()`` to try +multiple values and pick the best one, where *best* means the smallest +compressed data size. + +In manual mode, the ``k`` and ``d`` arguments must be specified or a +``ZstdError`` will be raised. + +In automatic mode (triggered by specifying ``optimize=True``), ``k`` +and ``d`` are optional. If a value isn't specified, then default values for +both are tested. The ``steps`` argument can control the number of steps +through ``k`` values. The ``level`` argument defines the compression level +that will be used when testing the compressed size. And ``threads`` can +specify the number of threads to use for concurrent operation. + +This function takes the following arguments: + +dict_size + Target size in bytes of the dictionary to generate. +samples + A list of bytes holding samples the dictionary will be trained from. +k + Parameter to cover algorithm defining the segment size. A reasonable range + is [16, 2048+]. +d + Parameter to cover algorithm defining the dmer size. A reasonable range is + [6, 16]. ``d`` must be less than or equal to ``k``. +dict_id + Integer dictionary ID for the produced dictionary. Default is 0, which uses + a random value. +optimize + When true, test dictionary generation with multiple parameters. +level + Integer target compression level when testing compression with + ``optimize=True``. Default is 1. +steps + Number of steps through ``k`` values to perform when ``optimize=True``. + Default is 32. +threads + Number of threads to use when ``optimize=True``. Default is 0, which means + to use a single thread. A negative value can be specified to use as many + threads as there are detected logical CPUs. +notifications + Controls writing of informational messages to ``stderr``. See the + documentation for ``train_dictionary()`` for more. + Explicit Compression Parameters ------------------------------- @@ -700,19 +952,57 @@ cctx = zstd.ZstdCompressor(compression_params=params) -The members of the ``CompressionParameters`` tuple are as follows:: +The members/attributes of ``CompressionParameters`` instances are as follows:: -* 0 - Window log -* 1 - Chain log -* 2 - Hash log -* 3 - Search log -* 4 - Search length -* 5 - Target length -* 6 - Strategy (one of the ``zstd.STRATEGY_`` constants) +* window_log +* chain_log +* hash_log +* search_log +* search_length +* target_length +* strategy + +This is the order the arguments are passed to the constructor if not using +named arguments. You'll need to read the Zstandard documentation for what these parameters do. +Frame Inspection +---------------- + +Data emitted from zstd compression is encapsulated in a *frame*. This frame +begins with a 4 byte *magic number* header followed by 2 to 14 bytes describing +the frame in more detail. For more info, see +https://github.com/facebook/zstd/blob/master/doc/zstd_compression_format.md. + +``zstd.get_frame_parameters(data)`` parses a zstd *frame* header from a bytes +instance and return a ``FrameParameters`` object describing the frame. + +Depending on which fields are present in the frame and their values, the +length of the frame parameters varies. If insufficient bytes are passed +in to fully parse the frame parameters, ``ZstdError`` is raised. To ensure +frame parameters can be parsed, pass in at least 18 bytes. + +``FrameParameters`` instances have the following attributes: + +content_size + Integer size of original, uncompressed content. This will be ``0`` if the + original content size isn't written to the frame (controlled with the + ``write_content_size`` argument to ``ZstdCompressor``) or if the input + content size was ``0``. + +window_size + Integer size of maximum back-reference distance in compressed data. + +dict_id + Integer of dictionary ID used for compression. ``0`` if no dictionary + ID was used or if the dictionary ID was ``0``. + +has_checksum + Bool indicating whether a 4 byte content checksum is stored at the end + of the frame. + Misc Functionality ------------------ @@ -776,19 +1066,293 @@ TARGETLENGTH_MAX Maximum value for compression parameter STRATEGY_FAST - Compression strategory + Compression strategy STRATEGY_DFAST - Compression strategory + Compression strategy STRATEGY_GREEDY - Compression strategory + Compression strategy STRATEGY_LAZY - Compression strategory + Compression strategy STRATEGY_LAZY2 - Compression strategory + Compression strategy STRATEGY_BTLAZY2 - Compression strategory + Compression strategy STRATEGY_BTOPT - Compression strategory + Compression strategy + +Performance Considerations +-------------------------- + +The ``ZstdCompressor`` and ``ZstdDecompressor`` types maintain state to a +persistent compression or decompression *context*. Reusing a ``ZstdCompressor`` +or ``ZstdDecompressor`` instance for multiple operations is faster than +instantiating a new ``ZstdCompressor`` or ``ZstdDecompressor`` for each +operation. The differences are magnified as the size of data decreases. For +example, the difference between *context* reuse and non-reuse for 100,000 +100 byte inputs will be significant (possiby over 10x faster to reuse contexts) +whereas 10 1,000,000 byte inputs will be more similar in speed (because the +time spent doing compression dwarfs time spent creating new *contexts*). + +Buffer Types +------------ + +The API exposes a handful of custom types for interfacing with memory buffers. +The primary goal of these types is to facilitate efficient multi-object +operations. + +The essential idea is to have a single memory allocation provide backing +storage for multiple logical objects. This has 2 main advantages: fewer +allocations and optimal memory access patterns. This avoids having to allocate +a Python object for each logical object and furthermore ensures that access of +data for objects can be sequential (read: fast) in memory. + +BufferWithSegments +^^^^^^^^^^^^^^^^^^ + +The ``BufferWithSegments`` type represents a memory buffer containing N +discrete items of known lengths (segments). It is essentially a fixed size +memory address and an array of 2-tuples of ``(offset, length)`` 64-bit +unsigned native endian integers defining the byte offset and length of each +segment within the buffer. + +Instances behave like containers. + +``len()`` returns the number of segments within the instance. + +``o[index]`` or ``__getitem__`` obtains a ``BufferSegment`` representing an +individual segment within the backing buffer. That returned object references +(not copies) memory. This means that iterating all objects doesn't copy +data within the buffer. + +The ``.size`` attribute contains the total size in bytes of the backing +buffer. + +Instances conform to the buffer protocol. So a reference to the backing bytes +can be obtained via ``memoryview(o)``. A *copy* of the backing bytes can also +be obtained via ``.tobytes()``. + +The ``.segments`` attribute exposes the array of ``(offset, length)`` for +segments within the buffer. It is a ``BufferSegments`` type. + +BufferSegment +^^^^^^^^^^^^^ + +The ``BufferSegment`` type represents a segment within a ``BufferWithSegments``. +It is essentially a reference to N bytes within a ``BufferWithSegments``. + +``len()`` returns the length of the segment in bytes. + +``.offset`` contains the byte offset of this segment within its parent +``BufferWithSegments`` instance. + +The object conforms to the buffer protocol. ``.tobytes()`` can be called to +obtain a ``bytes`` instance with a copy of the backing bytes. + +BufferSegments +^^^^^^^^^^^^^^ + +This type represents an array of ``(offset, length)`` integers defining segments +within a ``BufferWithSegments``. + +The array members are 64-bit unsigned integers using host/native bit order. + +Instances conform to the buffer protocol. + +BufferWithSegmentsCollection +^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +The ``BufferWithSegmentsCollection`` type represents a virtual spanning view +of multiple ``BufferWithSegments`` instances. + +Instances are constructed from 1 or more ``BufferWithSegments`` instances. The +resulting object behaves like an ordered sequence whose members are the +segments within each ``BufferWithSegments``. + +``len()`` returns the number of segments within all ``BufferWithSegments`` +instances. + +``o[index]`` and ``__getitem__(index)`` return the ``BufferSegment`` at +that offset as if all ``BufferWithSegments`` instances were a single +entity. + +If the object is composed of 2 ``BufferWithSegments`` instances with the +first having 2 segments and the second have 3 segments, then ``b[0]`` +and ``b[1]`` access segments in the first object and ``b[2]``, ``b[3]``, +and ``b[4]`` access segments from the second. + +Choosing an API +=============== + +There are multiple APIs for performing compression and decompression. This is +because different applications have different needs and the library wants to +facilitate optimal use in as many use cases as possible. + +From a high-level, APIs are divided into *one-shot* and *streaming*. See +the ``Concepts`` section for a description of how these are different at +the C layer. + +The *one-shot* APIs are useful for small data, where the input or output +size is known. (The size can come from a buffer length, file size, or +stored in the zstd frame header.) A limitation of the *one-shot* APIs is that +input and output must fit in memory simultaneously. For say a 4 GB input, +this is often not feasible. + +The *one-shot* APIs also perform all work as a single operation. So, if you +feed it large input, it could take a long time for the function to return. + +The streaming APIs do not have the limitations of the simple API. But the +price you pay for this flexibility is that they are more complex than a +single function call. + +The streaming APIs put the caller in control of compression and decompression +behavior by allowing them to directly control either the input or output side +of the operation. + +With the *streaming input*, *compressor*, and *decompressor* APIs, the caller +has full control over the input to the compression or decompression stream. +They can directly choose when new data is operated on. + +With the *streaming ouput* APIs, the caller has full control over the output +of the compression or decompression stream. It can choose when to receive +new data. + +When using the *streaming* APIs that operate on file-like or stream objects, +it is important to consider what happens in that object when I/O is requested. +There is potential for long pauses as data is read or written from the +underlying stream (say from interacting with a filesystem or network). This +could add considerable overhead. + +Concepts +======== + +It is important to have a basic understanding of how Zstandard works in order +to optimally use this library. In addition, there are some low-level Python +concepts that are worth explaining to aid understanding. This section aims to +provide that knowledge. + +Zstandard Frames and Compression Format +--------------------------------------- + +Compressed zstandard data almost always exists within a container called a +*frame*. (For the technically curious, see the +`specification <https://github.com/facebook/zstd/blob/3bee41a70eaf343fbcae3637b3f6edbe52f35ed8/doc/zstd_compression_format.md>_.) + +The frame contains a header and optional trailer. The header contains a +magic number to self-identify as a zstd frame and a description of the +compressed data that follows. + +Among other things, the frame *optionally* contains the size of the +decompressed data the frame represents, a 32-bit checksum of the +decompressed data (to facilitate verification during decompression), +and the ID of the dictionary used to compress the data. + +Storing the original content size in the frame (``write_content_size=True`` +to ``ZstdCompressor``) is important for performance in some scenarios. Having +the decompressed size stored there (or storing it elsewhere) allows +decompression to perform a single memory allocation that is exactly sized to +the output. This is faster than continuously growing a memory buffer to hold +output. + +Compression and Decompression Contexts +-------------------------------------- + +In order to perform a compression or decompression operation with the zstd +C API, you need what's called a *context*. A context essentially holds +configuration and state for a compression or decompression operation. For +example, a compression context holds the configured compression level. + +Contexts can be reused for multiple operations. Since creating and +destroying contexts is not free, there are performance advantages to +reusing contexts. + +The ``ZstdCompressor`` and ``ZstdDecompressor`` types are essentially +wrappers around these contexts in the zstd C API. + +One-shot And Streaming Operations +--------------------------------- + +A compression or decompression operation can either be performed as a +single *one-shot* operation or as a continuous *streaming* operation. + +In one-shot mode (the *simple* APIs provided by the Python interface), +**all** input is handed to the compressor or decompressor as a single buffer +and **all** output is returned as a single buffer. + +In streaming mode, input is delivered to the compressor or decompressor as +a series of chunks via multiple function calls. Likewise, output is +obtained in chunks as well. + +Streaming operations require an additional *stream* object to be created +to track the operation. These are logical extensions of *context* +instances. + +There are advantages and disadvantages to each mode of operation. There +are scenarios where certain modes can't be used. See the +``Choosing an API`` section for more. + +Dictionaries +------------ + +A compression *dictionary* is essentially data used to seed the compressor +state so it can achieve better compression. The idea is that if you are +compressing a lot of similar pieces of data (e.g. JSON documents or anything +sharing similar structure), then you can find common patterns across multiple +objects then leverage those common patterns during compression and +decompression operations to achieve better compression ratios. + +Dictionary compression is generally only useful for small inputs - data no +larger than a few kilobytes. The upper bound on this range is highly dependent +on the input data and the dictionary. + +Python Buffer Protocol +---------------------- + +Many functions in the library operate on objects that implement Python's +`buffer protocol <https://docs.python.org/3.6/c-api/buffer.html>`_. + +The *buffer protocol* is an internal implementation detail of a Python +type that allows instances of that type (objects) to be exposed as a raw +pointer (or buffer) in the C API. In other words, it allows objects to be +exposed as an array of bytes. + +From the perspective of the C API, objects implementing the *buffer protocol* +all look the same: they are just a pointer to a memory address of a defined +length. This allows the C API to be largely type agnostic when accessing their +data. This allows custom types to be passed in without first converting them +to a specific type. + +Many Python types implement the buffer protocol. These include ``bytes`` +(``str`` on Python 2), ``bytearray``, ``array.array``, ``io.BytesIO``, +``mmap.mmap``, and ``memoryview``. + +``python-zstandard`` APIs that accept objects conforming to the buffer +protocol require that the buffer is *C contiguous* and has a single +dimension (``ndim==1``). This is usually the case. An example of where it +is not is a Numpy matrix type. + +Requiring Output Sizes for Non-Streaming Decompression APIs +----------------------------------------------------------- + +Non-streaming decompression APIs require that either the output size is +explicitly defined (either in the zstd frame header or passed into the +function) or that a max output size is specified. This restriction is for +your safety. + +The *one-shot* decompression APIs store the decompressed result in a +single buffer. This means that a buffer needs to be pre-allocated to hold +the result. If the decompressed size is not known, then there is no universal +good default size to use. Any default will fail or will be highly sub-optimal +in some scenarios (it will either be too small or will put stress on the +memory allocator to allocate a too large block). + +A *helpful* API may retry decompression with buffers of increasing size. +While useful, there are obvious performance disadvantages, namely redoing +decompression N times until it works. In addition, there is a security +concern. Say the input came from highly compressible data, like 1 GB of the +same byte value. The output size could be several magnitudes larger than the +input size. An input of <100KB could decompress to >1GB. Without a bounds +restriction on the decompressed size, certain inputs could exhaust all system +memory. That's not good and is why the maximum output size is limited. Note on Zstandard's *Experimental* API ======================================
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/contrib/python-zstandard/c-ext/bufferutil.c Tue Apr 18 12:24:34 2017 -0400 @@ -0,0 +1,770 @@ +/** +* Copyright (c) 2017-present, Gregory Szorc +* All rights reserved. +* +* This software may be modified and distributed under the terms +* of the BSD license. See the LICENSE file for details. +*/ + +#include "python-zstandard.h" + +extern PyObject* ZstdError; + +PyDoc_STRVAR(BufferWithSegments__doc__, +"BufferWithSegments - A memory buffer holding known sub-segments.\n" +"\n" +"This type represents a contiguous chunk of memory containing N discrete\n" +"items within sub-segments of that memory.\n" +"\n" +"Segments within the buffer are stored as an array of\n" +"``(offset, length)`` pairs, where each element is an unsigned 64-bit\n" +"integer using the host/native bit order representation.\n" +"\n" +"The type exists to facilitate operations against N>1 items without the\n" +"overhead of Python object creation and management.\n" +); + +static void BufferWithSegments_dealloc(ZstdBufferWithSegments* self) { + /* Backing memory is either canonically owned by a Py_buffer or by us. */ + if (self->parent.buf) { + PyBuffer_Release(&self->parent); + } + else if (self->useFree) { + free(self->data); + } + else { + PyMem_Free(self->data); + } + + self->data = NULL; + + if (self->useFree) { + free(self->segments); + } + else { + PyMem_Free(self->segments); + } + + self->segments = NULL; + + PyObject_Del(self); +} + +static int BufferWithSegments_init(ZstdBufferWithSegments* self, PyObject* args, PyObject* kwargs) { + static char* kwlist[] = { + "data", + "segments", + NULL + }; + + Py_buffer segments; + Py_ssize_t segmentCount; + Py_ssize_t i; + + memset(&self->parent, 0, sizeof(self->parent)); + +#if PY_MAJOR_VERSION >= 3 + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "y*y*:BufferWithSegments", +#else + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "s*s*:BufferWithSegments", +#endif + kwlist, &self->parent, &segments)) { + return -1; + } + + if (!PyBuffer_IsContiguous(&self->parent, 'C') || self->parent.ndim > 1) { + PyErr_SetString(PyExc_ValueError, "data buffer should be contiguous and have a single dimension"); + goto except; + } + + if (!PyBuffer_IsContiguous(&segments, 'C') || segments.ndim > 1) { + PyErr_SetString(PyExc_ValueError, "segments buffer should be contiguous and have a single dimension"); + goto except; + } + + if (segments.len % sizeof(BufferSegment)) { + PyErr_Format(PyExc_ValueError, "segments array size is not a multiple of %lu", + sizeof(BufferSegment)); + goto except; + } + + segmentCount = segments.len / sizeof(BufferSegment); + + /* Validate segments data, as blindly trusting it could lead to arbitrary + memory access. */ + for (i = 0; i < segmentCount; i++) { + BufferSegment* segment = &((BufferSegment*)(segments.buf))[i]; + + if (segment->offset + segment->length > (unsigned long long)self->parent.len) { + PyErr_SetString(PyExc_ValueError, "offset within segments array references memory outside buffer"); + goto except; + return -1; + } + } + + /* Make a copy of the segments data. It is cheap to do so and is a guard + against caller changing offsets, which has security implications. */ + self->segments = PyMem_Malloc(segments.len); + if (!self->segments) { + PyErr_NoMemory(); + goto except; + } + + memcpy(self->segments, segments.buf, segments.len); + PyBuffer_Release(&segments); + + self->data = self->parent.buf; + self->dataSize = self->parent.len; + self->segmentCount = segmentCount; + + return 0; + +except: + PyBuffer_Release(&self->parent); + PyBuffer_Release(&segments); + return -1; +}; + +/** + * Construct a BufferWithSegments from existing memory and offsets. + * + * Ownership of the backing memory and BufferSegments will be transferred to + * the created object and freed when the BufferWithSegments is destroyed. + */ +ZstdBufferWithSegments* BufferWithSegments_FromMemory(void* data, unsigned long long dataSize, + BufferSegment* segments, Py_ssize_t segmentsSize) { + ZstdBufferWithSegments* result = NULL; + Py_ssize_t i; + + if (NULL == data) { + PyErr_SetString(PyExc_ValueError, "data is NULL"); + return NULL; + } + + if (NULL == segments) { + PyErr_SetString(PyExc_ValueError, "segments is NULL"); + return NULL; + } + + for (i = 0; i < segmentsSize; i++) { + BufferSegment* segment = &segments[i]; + + if (segment->offset + segment->length > dataSize) { + PyErr_SetString(PyExc_ValueError, "offset in segments overflows buffer size"); + return NULL; + } + } + + result = PyObject_New(ZstdBufferWithSegments, &ZstdBufferWithSegmentsType); + if (NULL == result) { + return NULL; + } + + result->useFree = 0; + + memset(&result->parent, 0, sizeof(result->parent)); + result->data = data; + result->dataSize = dataSize; + result->segments = segments; + result->segmentCount = segmentsSize; + + return result; +} + +static Py_ssize_t BufferWithSegments_length(ZstdBufferWithSegments* self) { + return self->segmentCount; +} + +static ZstdBufferSegment* BufferWithSegments_item(ZstdBufferWithSegments* self, Py_ssize_t i) { + ZstdBufferSegment* result = NULL; + + if (i < 0) { + PyErr_SetString(PyExc_IndexError, "offset must be non-negative"); + return NULL; + } + + if (i >= self->segmentCount) { + PyErr_Format(PyExc_IndexError, "offset must be less than %zd", self->segmentCount); + return NULL; + } + + result = (ZstdBufferSegment*)PyObject_CallObject((PyObject*)&ZstdBufferSegmentType, NULL); + if (NULL == result) { + return NULL; + } + + result->parent = (PyObject*)self; + Py_INCREF(self); + + result->data = (char*)self->data + self->segments[i].offset; + result->dataSize = self->segments[i].length; + result->offset = self->segments[i].offset; + + return result; +} + +#if PY_MAJOR_VERSION >= 3 +static int BufferWithSegments_getbuffer(ZstdBufferWithSegments* self, Py_buffer* view, int flags) { + return PyBuffer_FillInfo(view, (PyObject*)self, self->data, self->dataSize, 1, flags); +} +#else +static Py_ssize_t BufferWithSegments_getreadbuffer(ZstdBufferWithSegments* self, Py_ssize_t segment, void **ptrptr) { + if (segment != 0) { + PyErr_SetString(PyExc_ValueError, "segment number must be 0"); + return -1; + } + + *ptrptr = self->data; + return self->dataSize; +} + +static Py_ssize_t BufferWithSegments_getsegcount(ZstdBufferWithSegments* self, Py_ssize_t* len) { + if (len) { + *len = 1; + } + + return 1; +} +#endif + +PyDoc_STRVAR(BufferWithSegments_tobytes__doc__, +"Obtain a bytes instance for this buffer.\n" +); + +static PyObject* BufferWithSegments_tobytes(ZstdBufferWithSegments* self) { + return PyBytes_FromStringAndSize(self->data, self->dataSize); +} + +PyDoc_STRVAR(BufferWithSegments_segments__doc__, +"Obtain a BufferSegments describing segments in this sintance.\n" +); + +static ZstdBufferSegments* BufferWithSegments_segments(ZstdBufferWithSegments* self) { + ZstdBufferSegments* result = (ZstdBufferSegments*)PyObject_CallObject((PyObject*)&ZstdBufferSegmentsType, NULL); + if (NULL == result) { + return NULL; + } + + result->parent = (PyObject*)self; + Py_INCREF(self); + result->segments = self->segments; + result->segmentCount = self->segmentCount; + + return result; +} + +static PySequenceMethods BufferWithSegments_sq = { + (lenfunc)BufferWithSegments_length, /* sq_length */ + 0, /* sq_concat */ + 0, /* sq_repeat */ + (ssizeargfunc)BufferWithSegments_item, /* sq_item */ + 0, /* sq_ass_item */ + 0, /* sq_contains */ + 0, /* sq_inplace_concat */ + 0 /* sq_inplace_repeat */ +}; + +static PyBufferProcs BufferWithSegments_as_buffer = { +#if PY_MAJOR_VERSION >= 3 + (getbufferproc)BufferWithSegments_getbuffer, /* bf_getbuffer */ + 0 /* bf_releasebuffer */ +#else + (readbufferproc)BufferWithSegments_getreadbuffer, /* bf_getreadbuffer */ + 0, /* bf_getwritebuffer */ + (segcountproc)BufferWithSegments_getsegcount, /* bf_getsegcount */ + 0 /* bf_getcharbuffer */ +#endif +}; + +static PyMethodDef BufferWithSegments_methods[] = { + { "segments", (PyCFunction)BufferWithSegments_segments, + METH_NOARGS, BufferWithSegments_segments__doc__ }, + { "tobytes", (PyCFunction)BufferWithSegments_tobytes, + METH_NOARGS, BufferWithSegments_tobytes__doc__ }, + { NULL, NULL } +}; + +static PyMemberDef BufferWithSegments_members[] = { + { "size", T_ULONGLONG, offsetof(ZstdBufferWithSegments, dataSize), + READONLY, "total size of the buffer in bytes" }, + { NULL } +}; + +PyTypeObject ZstdBufferWithSegmentsType = { + PyVarObject_HEAD_INIT(NULL, 0) + "zstd.BufferWithSegments", /* tp_name */ + sizeof(ZstdBufferWithSegments),/* tp_basicsize */ + 0, /* tp_itemsize */ + (destructor)BufferWithSegments_dealloc, /* tp_dealloc */ + 0, /* tp_print */ + 0, /* tp_getattr */ + 0, /* tp_setattr */ + 0, /* tp_compare */ + 0, /* tp_repr */ + 0, /* tp_as_number */ + &BufferWithSegments_sq, /* tp_as_sequence */ + 0, /* tp_as_mapping */ + 0, /* tp_hash */ + 0, /* tp_call */ + 0, /* tp_str */ + 0, /* tp_getattro */ + 0, /* tp_setattro */ + &BufferWithSegments_as_buffer, /* tp_as_buffer */ + Py_TPFLAGS_DEFAULT, /* tp_flags */ + BufferWithSegments__doc__, /* tp_doc */ + 0, /* tp_traverse */ + 0, /* tp_clear */ + 0, /* tp_richcompare */ + 0, /* tp_weaklistoffset */ + 0, /* tp_iter */ + 0, /* tp_iternext */ + BufferWithSegments_methods, /* tp_methods */ + BufferWithSegments_members, /* tp_members */ + 0, /* tp_getset */ + 0, /* tp_base */ + 0, /* tp_dict */ + 0, /* tp_descr_get */ + 0, /* tp_descr_set */ + 0, /* tp_dictoffset */ + (initproc)BufferWithSegments_init, /* tp_init */ + 0, /* tp_alloc */ + PyType_GenericNew, /* tp_new */ +}; + +PyDoc_STRVAR(BufferSegments__doc__, +"BufferSegments - Represents segments/offsets within a BufferWithSegments\n" +); + +static void BufferSegments_dealloc(ZstdBufferSegments* self) { + Py_CLEAR(self->parent); + PyObject_Del(self); +} + +#if PY_MAJOR_VERSION >= 3 +static int BufferSegments_getbuffer(ZstdBufferSegments* self, Py_buffer* view, int flags) { + return PyBuffer_FillInfo(view, (PyObject*)self, + (void*)self->segments, self->segmentCount * sizeof(BufferSegment), + 1, flags); +} +#else +static Py_ssize_t BufferSegments_getreadbuffer(ZstdBufferSegments* self, Py_ssize_t segment, void **ptrptr) { + if (segment != 0) { + PyErr_SetString(PyExc_ValueError, "segment number must be 0"); + return -1; + } + + *ptrptr = (void*)self->segments; + return self->segmentCount * sizeof(BufferSegment); +} + +static Py_ssize_t BufferSegments_getsegcount(ZstdBufferSegments* self, Py_ssize_t* len) { + if (len) { + *len = 1; + } + + return 1; +} +#endif + +static PyBufferProcs BufferSegments_as_buffer = { +#if PY_MAJOR_VERSION >= 3 + (getbufferproc)BufferSegments_getbuffer, + 0 +#else + (readbufferproc)BufferSegments_getreadbuffer, + 0, + (segcountproc)BufferSegments_getsegcount, + 0 +#endif +}; + +PyTypeObject ZstdBufferSegmentsType = { + PyVarObject_HEAD_INIT(NULL, 0) + "zstd.BufferSegments", /* tp_name */ + sizeof(ZstdBufferSegments),/* tp_basicsize */ + 0, /* tp_itemsize */ + (destructor)BufferSegments_dealloc, /* tp_dealloc */ + 0, /* tp_print */ + 0, /* tp_getattr */ + 0, /* tp_setattr */ + 0, /* tp_compare */ + 0, /* tp_repr */ + 0, /* tp_as_number */ + 0, /* tp_as_sequence */ + 0, /* tp_as_mapping */ + 0, /* tp_hash */ + 0, /* tp_call */ + 0, /* tp_str */ + 0, /* tp_getattro */ + 0, /* tp_setattro */ + &BufferSegments_as_buffer, /* tp_as_buffer */ + Py_TPFLAGS_DEFAULT, /* tp_flags */ + BufferSegments__doc__, /* tp_doc */ + 0, /* tp_traverse */ + 0, /* tp_clear */ + 0, /* tp_richcompare */ + 0, /* tp_weaklistoffset */ + 0, /* tp_iter */ + 0, /* tp_iternext */ + 0, /* tp_methods */ + 0, /* tp_members */ + 0, /* tp_getset */ + 0, /* tp_base */ + 0, /* tp_dict */ + 0, /* tp_descr_get */ + 0, /* tp_descr_set */ + 0, /* tp_dictoffset */ + 0, /* tp_init */ + 0, /* tp_alloc */ + PyType_GenericNew, /* tp_new */ +}; + +PyDoc_STRVAR(BufferSegment__doc__, + "BufferSegment - Represents a segment within a BufferWithSegments\n" +); + +static void BufferSegment_dealloc(ZstdBufferSegment* self) { + Py_CLEAR(self->parent); + PyObject_Del(self); +} + +static Py_ssize_t BufferSegment_length(ZstdBufferSegment* self) { + return self->dataSize; +} + +#if PY_MAJOR_VERSION >= 3 +static int BufferSegment_getbuffer(ZstdBufferSegment* self, Py_buffer* view, int flags) { + return PyBuffer_FillInfo(view, (PyObject*)self, + self->data, self->dataSize, 1, flags); +} +#else +static Py_ssize_t BufferSegment_getreadbuffer(ZstdBufferSegment* self, Py_ssize_t segment, void **ptrptr) { + if (segment != 0) { + PyErr_SetString(PyExc_ValueError, "segment number must be 0"); + return -1; + } + + *ptrptr = self->data; + return self->dataSize; +} + +static Py_ssize_t BufferSegment_getsegcount(ZstdBufferSegment* self, Py_ssize_t* len) { + if (len) { + *len = 1; + } + + return 1; +} +#endif + +PyDoc_STRVAR(BufferSegment_tobytes__doc__, +"Obtain a bytes instance for this segment.\n" +); + +static PyObject* BufferSegment_tobytes(ZstdBufferSegment* self) { + return PyBytes_FromStringAndSize(self->data, self->dataSize); +} + +static PySequenceMethods BufferSegment_sq = { + (lenfunc)BufferSegment_length, /* sq_length */ + 0, /* sq_concat */ + 0, /* sq_repeat */ + 0, /* sq_item */ + 0, /* sq_ass_item */ + 0, /* sq_contains */ + 0, /* sq_inplace_concat */ + 0 /* sq_inplace_repeat */ +}; + +static PyBufferProcs BufferSegment_as_buffer = { +#if PY_MAJOR_VERSION >= 3 + (getbufferproc)BufferSegment_getbuffer, + 0 +#else + (readbufferproc)BufferSegment_getreadbuffer, + 0, + (segcountproc)BufferSegment_getsegcount, + 0 +#endif +}; + +static PyMethodDef BufferSegment_methods[] = { + { "tobytes", (PyCFunction)BufferSegment_tobytes, + METH_NOARGS, BufferSegment_tobytes__doc__ }, + { NULL, NULL } +}; + +static PyMemberDef BufferSegment_members[] = { + { "offset", T_ULONGLONG, offsetof(ZstdBufferSegment, offset), READONLY, + "offset of segment within parent buffer" }, + { NULL } +}; + +PyTypeObject ZstdBufferSegmentType = { + PyVarObject_HEAD_INIT(NULL, 0) + "zstd.BufferSegment", /* tp_name */ + sizeof(ZstdBufferSegment),/* tp_basicsize */ + 0, /* tp_itemsize */ + (destructor)BufferSegment_dealloc, /* tp_dealloc */ + 0, /* tp_print */ + 0, /* tp_getattr */ + 0, /* tp_setattr */ + 0, /* tp_compare */ + 0, /* tp_repr */ + 0, /* tp_as_number */ + &BufferSegment_sq, /* tp_as_sequence */ + 0, /* tp_as_mapping */ + 0, /* tp_hash */ + 0, /* tp_call */ + 0, /* tp_str */ + 0, /* tp_getattro */ + 0, /* tp_setattro */ + &BufferSegment_as_buffer, /* tp_as_buffer */ + Py_TPFLAGS_DEFAULT, /* tp_flags */ + BufferSegment__doc__, /* tp_doc */ + 0, /* tp_traverse */ + 0, /* tp_clear */ + 0, /* tp_richcompare */ + 0, /* tp_weaklistoffset */ + 0, /* tp_iter */ + 0, /* tp_iternext */ + BufferSegment_methods, /* tp_methods */ + BufferSegment_members, /* tp_members */ + 0, /* tp_getset */ + 0, /* tp_base */ + 0, /* tp_dict */ + 0, /* tp_descr_get */ + 0, /* tp_descr_set */ + 0, /* tp_dictoffset */ + 0, /* tp_init */ + 0, /* tp_alloc */ + PyType_GenericNew, /* tp_new */ +}; + +PyDoc_STRVAR(BufferWithSegmentsCollection__doc__, +"Represents a collection of BufferWithSegments.\n" +); + +static void BufferWithSegmentsCollection_dealloc(ZstdBufferWithSegmentsCollection* self) { + Py_ssize_t i; + + if (self->firstElements) { + PyMem_Free(self->firstElements); + self->firstElements = NULL; + } + + if (self->buffers) { + for (i = 0; i < self->bufferCount; i++) { + Py_CLEAR(self->buffers[i]); + } + + PyMem_Free(self->buffers); + self->buffers = NULL; + } + + PyObject_Del(self); +} + +static int BufferWithSegmentsCollection_init(ZstdBufferWithSegmentsCollection* self, PyObject* args) { + Py_ssize_t size; + Py_ssize_t i; + Py_ssize_t offset = 0; + + size = PyTuple_Size(args); + if (-1 == size) { + return -1; + } + + if (0 == size) { + PyErr_SetString(PyExc_ValueError, "must pass at least 1 argument"); + return -1; + } + + for (i = 0; i < size; i++) { + PyObject* item = PyTuple_GET_ITEM(args, i); + if (!PyObject_TypeCheck(item, &ZstdBufferWithSegmentsType)) { + PyErr_SetString(PyExc_TypeError, "arguments must be BufferWithSegments instances"); + return -1; + } + + if (0 == ((ZstdBufferWithSegments*)item)->segmentCount || + 0 == ((ZstdBufferWithSegments*)item)->dataSize) { + PyErr_SetString(PyExc_ValueError, "ZstdBufferWithSegments cannot be empty"); + return -1; + } + } + + self->buffers = PyMem_Malloc(size * sizeof(ZstdBufferWithSegments*)); + if (NULL == self->buffers) { + PyErr_NoMemory(); + return -1; + } + + self->firstElements = PyMem_Malloc(size * sizeof(Py_ssize_t)); + if (NULL == self->firstElements) { + PyMem_Free(self->buffers); + self->buffers = NULL; + PyErr_NoMemory(); + return -1; + } + + self->bufferCount = size; + + for (i = 0; i < size; i++) { + ZstdBufferWithSegments* item = (ZstdBufferWithSegments*)PyTuple_GET_ITEM(args, i); + + self->buffers[i] = item; + Py_INCREF(item); + + if (i > 0) { + self->firstElements[i - 1] = offset; + } + + offset += item->segmentCount; + } + + self->firstElements[size - 1] = offset; + + return 0; +} + +static PyObject* BufferWithSegmentsCollection_size(ZstdBufferWithSegmentsCollection* self) { + Py_ssize_t i; + Py_ssize_t j; + unsigned long long size = 0; + + for (i = 0; i < self->bufferCount; i++) { + for (j = 0; j < self->buffers[i]->segmentCount; j++) { + size += self->buffers[i]->segments[j].length; + } + } + + return PyLong_FromUnsignedLongLong(size); +} + +Py_ssize_t BufferWithSegmentsCollection_length(ZstdBufferWithSegmentsCollection* self) { + return self->firstElements[self->bufferCount - 1]; +} + +static ZstdBufferSegment* BufferWithSegmentsCollection_item(ZstdBufferWithSegmentsCollection* self, Py_ssize_t i) { + Py_ssize_t bufferOffset; + + if (i < 0) { + PyErr_SetString(PyExc_IndexError, "offset must be non-negative"); + return NULL; + } + + if (i >= BufferWithSegmentsCollection_length(self)) { + PyErr_Format(PyExc_IndexError, "offset must be less than %zd", + BufferWithSegmentsCollection_length(self)); + return NULL; + } + + for (bufferOffset = 0; bufferOffset < self->bufferCount; bufferOffset++) { + Py_ssize_t offset = 0; + + if (i < self->firstElements[bufferOffset]) { + if (bufferOffset > 0) { + offset = self->firstElements[bufferOffset - 1]; + } + + return BufferWithSegments_item(self->buffers[bufferOffset], i - offset); + } + } + + PyErr_SetString(ZstdError, "error resolving segment; this should not happen"); + return NULL; +} + +static PySequenceMethods BufferWithSegmentsCollection_sq = { + (lenfunc)BufferWithSegmentsCollection_length, /* sq_length */ + 0, /* sq_concat */ + 0, /* sq_repeat */ + (ssizeargfunc)BufferWithSegmentsCollection_item, /* sq_item */ + 0, /* sq_ass_item */ + 0, /* sq_contains */ + 0, /* sq_inplace_concat */ + 0 /* sq_inplace_repeat */ +}; + +static PyMethodDef BufferWithSegmentsCollection_methods[] = { + { "size", (PyCFunction)BufferWithSegmentsCollection_size, + METH_NOARGS, PyDoc_STR("total size in bytes of all segments") }, + { NULL, NULL } +}; + +PyTypeObject ZstdBufferWithSegmentsCollectionType = { + PyVarObject_HEAD_INIT(NULL, 0) + "zstd.BufferWithSegmentsCollection", /* tp_name */ + sizeof(ZstdBufferWithSegmentsCollection),/* tp_basicsize */ + 0, /* tp_itemsize */ + (destructor)BufferWithSegmentsCollection_dealloc, /* tp_dealloc */ + 0, /* tp_print */ + 0, /* tp_getattr */ + 0, /* tp_setattr */ + 0, /* tp_compare */ + 0, /* tp_repr */ + 0, /* tp_as_number */ + &BufferWithSegmentsCollection_sq, /* tp_as_sequence */ + 0, /* tp_as_mapping */ + 0, /* tp_hash */ + 0, /* tp_call */ + 0, /* tp_str */ + 0, /* tp_getattro */ + 0, /* tp_setattro */ + 0, /* tp_as_buffer */ + Py_TPFLAGS_DEFAULT, /* tp_flags */ + BufferWithSegmentsCollection__doc__, /* tp_doc */ + 0, /* tp_traverse */ + 0, /* tp_clear */ + 0, /* tp_richcompare */ + 0, /* tp_weaklistoffset */ + /* TODO implement iterator for performance. */ + 0, /* tp_iter */ + 0, /* tp_iternext */ + BufferWithSegmentsCollection_methods, /* tp_methods */ + 0, /* tp_members */ + 0, /* tp_getset */ + 0, /* tp_base */ + 0, /* tp_dict */ + 0, /* tp_descr_get */ + 0, /* tp_descr_set */ + 0, /* tp_dictoffset */ + (initproc)BufferWithSegmentsCollection_init, /* tp_init */ + 0, /* tp_alloc */ + PyType_GenericNew, /* tp_new */ +}; + +void bufferutil_module_init(PyObject* mod) { + Py_TYPE(&ZstdBufferWithSegmentsType) = &PyType_Type; + if (PyType_Ready(&ZstdBufferWithSegmentsType) < 0) { + return; + } + + Py_INCREF(&ZstdBufferWithSegmentsType); + PyModule_AddObject(mod, "BufferWithSegments", (PyObject*)&ZstdBufferWithSegmentsType); + + Py_TYPE(&ZstdBufferSegmentsType) = &PyType_Type; + if (PyType_Ready(&ZstdBufferSegmentsType) < 0) { + return; + } + + Py_INCREF(&ZstdBufferSegmentsType); + PyModule_AddObject(mod, "BufferSegments", (PyObject*)&ZstdBufferSegmentsType); + + Py_TYPE(&ZstdBufferSegmentType) = &PyType_Type; + if (PyType_Ready(&ZstdBufferSegmentType) < 0) { + return; + } + + Py_INCREF(&ZstdBufferSegmentType); + PyModule_AddObject(mod, "BufferSegment", (PyObject*)&ZstdBufferSegmentType); + + Py_TYPE(&ZstdBufferWithSegmentsCollectionType) = &PyType_Type; + if (PyType_Ready(&ZstdBufferWithSegmentsCollectionType) < 0) { + return; + } + + Py_INCREF(&ZstdBufferWithSegmentsCollectionType); + PyModule_AddObject(mod, "BufferWithSegmentsCollection", (PyObject*)&ZstdBufferWithSegmentsCollectionType); +}
--- a/contrib/python-zstandard/c-ext/compressiondict.c Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/python-zstandard/c-ext/compressiondict.c Tue Apr 18 12:24:34 2017 -0400 @@ -11,45 +11,48 @@ extern PyObject* ZstdError; ZstdCompressionDict* train_dictionary(PyObject* self, PyObject* args, PyObject* kwargs) { - static char *kwlist[] = { "dict_size", "samples", "parameters", NULL }; + static char* kwlist[] = { + "dict_size", + "samples", + "selectivity", + "level", + "notifications", + "dict_id", + NULL + }; size_t capacity; PyObject* samples; Py_ssize_t samplesLen; - PyObject* parameters = NULL; + unsigned selectivity = 0; + int level = 0; + unsigned notifications = 0; + unsigned dictID = 0; ZDICT_params_t zparams; Py_ssize_t sampleIndex; Py_ssize_t sampleSize; PyObject* sampleItem; size_t zresult; - void* sampleBuffer; + void* sampleBuffer = NULL; void* sampleOffset; size_t samplesSize = 0; - size_t* sampleSizes; - void* dict; - ZstdCompressionDict* result; + size_t* sampleSizes = NULL; + void* dict = NULL; + ZstdCompressionDict* result = NULL; - if (!PyArg_ParseTupleAndKeywords(args, kwargs, "nO!|O!", kwlist, + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "nO!|IiII:train_dictionary", + kwlist, &capacity, &PyList_Type, &samples, - (PyObject*)&DictParametersType, ¶meters)) { + &selectivity, &level, ¬ifications, &dictID)) { return NULL; } - /* Validate parameters first since it is easiest. */ - zparams.selectivityLevel = 0; - zparams.compressionLevel = 0; - zparams.notificationLevel = 0; - zparams.dictID = 0; - zparams.reserved[0] = 0; - zparams.reserved[1] = 0; + memset(&zparams, 0, sizeof(zparams)); - if (parameters) { - /* TODO validate data ranges */ - zparams.selectivityLevel = PyLong_AsUnsignedLong(PyTuple_GetItem(parameters, 0)); - zparams.compressionLevel = PyLong_AsLong(PyTuple_GetItem(parameters, 1)); - zparams.notificationLevel = PyLong_AsUnsignedLong(PyTuple_GetItem(parameters, 2)); - zparams.dictID = PyLong_AsUnsignedLong(PyTuple_GetItem(parameters, 3)); - } + zparams.selectivityLevel = selectivity; + zparams.compressionLevel = level; + zparams.notificationLevel = notifications; + zparams.dictID = dictID; /* Figure out the size of the raw samples */ samplesLen = PyList_Size(samples); @@ -57,7 +60,6 @@ sampleItem = PyList_GetItem(samples, sampleIndex); if (!PyBytes_Check(sampleItem)) { PyErr_SetString(PyExc_ValueError, "samples must be bytes"); - /* TODO probably need to perform DECREF here */ return NULL; } samplesSize += PyBytes_GET_SIZE(sampleItem); @@ -68,13 +70,12 @@ sampleBuffer = PyMem_Malloc(samplesSize); if (!sampleBuffer) { PyErr_NoMemory(); - return NULL; + goto finally; } sampleSizes = PyMem_Malloc(samplesLen * sizeof(size_t)); if (!sampleSizes) { - PyMem_Free(sampleBuffer); PyErr_NoMemory(); - return NULL; + goto finally; } sampleOffset = sampleBuffer; @@ -89,33 +90,168 @@ dict = PyMem_Malloc(capacity); if (!dict) { - PyMem_Free(sampleSizes); - PyMem_Free(sampleBuffer); PyErr_NoMemory(); - return NULL; + goto finally; } + /* TODO consider using dup2() to redirect zstd's stderr writing to a buffer */ + Py_BEGIN_ALLOW_THREADS zresult = ZDICT_trainFromBuffer_advanced(dict, capacity, sampleBuffer, sampleSizes, (unsigned int)samplesLen, zparams); + Py_END_ALLOW_THREADS if (ZDICT_isError(zresult)) { PyErr_Format(ZstdError, "Cannot train dict: %s", ZDICT_getErrorName(zresult)); PyMem_Free(dict); - PyMem_Free(sampleSizes); - PyMem_Free(sampleBuffer); - return NULL; + goto finally; } result = PyObject_New(ZstdCompressionDict, &ZstdCompressionDictType); if (!result) { - return NULL; + goto finally; } result->dictData = dict; result->dictSize = zresult; + result->d = 0; + result->k = 0; + +finally: + PyMem_Free(sampleBuffer); + PyMem_Free(sampleSizes); + return result; } +ZstdCompressionDict* train_cover_dictionary(PyObject* self, PyObject* args, PyObject* kwargs) { + static char* kwlist[] = { + "dict_size", + "samples", + "k", + "d", + "notifications", + "dict_id", + "level", + "optimize", + "steps", + "threads", + NULL + }; + + size_t capacity; + PyObject* samples; + unsigned k = 0; + unsigned d = 0; + unsigned notifications = 0; + unsigned dictID = 0; + int level = 0; + PyObject* optimize = NULL; + unsigned steps = 0; + int threads = 0; + COVER_params_t params; + Py_ssize_t samplesLen; + Py_ssize_t i; + size_t samplesSize = 0; + void* sampleBuffer = NULL; + size_t* sampleSizes = NULL; + void* sampleOffset; + Py_ssize_t sampleSize; + void* dict = NULL; + size_t zresult; + ZstdCompressionDict* result = NULL; + + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "nO!|IIIIiOIi:train_cover_dictionary", + kwlist, &capacity, &PyList_Type, &samples, + &k, &d, ¬ifications, &dictID, &level, &optimize, &steps, &threads)) { + return NULL; + } + + if (threads < 0) { + threads = cpu_count(); + } + + memset(¶ms, 0, sizeof(params)); + params.k = k; + params.d = d; + params.steps = steps; + params.nbThreads = threads; + params.notificationLevel = notifications; + params.dictID = dictID; + params.compressionLevel = level; + + /* Figure out total size of input samples. */ + samplesLen = PyList_Size(samples); + for (i = 0; i < samplesLen; i++) { + PyObject* sampleItem = PyList_GET_ITEM(samples, i); + + if (!PyBytes_Check(sampleItem)) { + PyErr_SetString(PyExc_ValueError, "samples must be bytes"); + return NULL; + } + samplesSize += PyBytes_GET_SIZE(sampleItem); + } + + sampleBuffer = PyMem_Malloc(samplesSize); + if (!sampleBuffer) { + PyErr_NoMemory(); + goto finally; + } + + sampleSizes = PyMem_Malloc(samplesLen * sizeof(size_t)); + if (!sampleSizes) { + PyErr_NoMemory(); + goto finally; + } + + sampleOffset = sampleBuffer; + for (i = 0; i < samplesLen; i++) { + PyObject* sampleItem = PyList_GET_ITEM(samples, i); + sampleSize = PyBytes_GET_SIZE(sampleItem); + sampleSizes[i] = sampleSize; + memcpy(sampleOffset, PyBytes_AS_STRING(sampleItem), sampleSize); + sampleOffset = (char*)sampleOffset + sampleSize; + } + + dict = PyMem_Malloc(capacity); + if (!dict) { + PyErr_NoMemory(); + goto finally; + } + + Py_BEGIN_ALLOW_THREADS + if (optimize && PyObject_IsTrue(optimize)) { + zresult = COVER_optimizeTrainFromBuffer(dict, capacity, + sampleBuffer, sampleSizes, (unsigned)samplesLen, ¶ms); + } + else { + zresult = COVER_trainFromBuffer(dict, capacity, + sampleBuffer, sampleSizes, (unsigned)samplesLen, params); + } + Py_END_ALLOW_THREADS + + if (ZDICT_isError(zresult)) { + PyMem_Free(dict); + PyErr_Format(ZstdError, "cannot train dict: %s", ZDICT_getErrorName(zresult)); + goto finally; + } + + result = PyObject_New(ZstdCompressionDict, &ZstdCompressionDictType); + if (!result) { + PyMem_Free(dict); + goto finally; + } + + result->dictData = dict; + result->dictSize = zresult; + result->d = params.d; + result->k = params.k; + +finally: + PyMem_Free(sampleBuffer); + PyMem_Free(sampleSizes); + + return result; +} PyDoc_STRVAR(ZstdCompressionDict__doc__, "ZstdCompressionDict(data) - Represents a computed compression dictionary\n" @@ -133,10 +269,11 @@ self->dictSize = 0; #if PY_MAJOR_VERSION >= 3 - if (!PyArg_ParseTuple(args, "y#", &source, &sourceSize)) { + if (!PyArg_ParseTuple(args, "y#:ZstdCompressionDict", #else - if (!PyArg_ParseTuple(args, "s#", &source, &sourceSize)) { + if (!PyArg_ParseTuple(args, "s#:ZstdCompressionDict", #endif + &source, &sourceSize)) { return -1; } @@ -179,6 +316,14 @@ { NULL, NULL } }; +static PyMemberDef ZstdCompressionDict_members[] = { + { "k", T_UINT, offsetof(ZstdCompressionDict, k), READONLY, + "segment size" }, + { "d", T_UINT, offsetof(ZstdCompressionDict, d), READONLY, + "dmer size" }, + { NULL } +}; + static Py_ssize_t ZstdCompressionDict_length(ZstdCompressionDict* self) { return self->dictSize; } @@ -223,7 +368,7 @@ 0, /* tp_iter */ 0, /* tp_iternext */ ZstdCompressionDict_methods, /* tp_methods */ - 0, /* tp_members */ + ZstdCompressionDict_members, /* tp_members */ 0, /* tp_getset */ 0, /* tp_base */ 0, /* tp_dict */
--- a/contrib/python-zstandard/c-ext/compressionparams.c Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/python-zstandard/c-ext/compressionparams.c Tue Apr 18 12:24:34 2017 -0400 @@ -25,7 +25,8 @@ ZSTD_compressionParameters params; CompressionParametersObject* result; - if (!PyArg_ParseTuple(args, "i|Kn", &compressionLevel, &sourceSize, &dictSize)) { + if (!PyArg_ParseTuple(args, "i|Kn:get_compression_parameters", + &compressionLevel, &sourceSize, &dictSize)) { return NULL; } @@ -47,12 +48,108 @@ return result; } +static int CompressionParameters_init(CompressionParametersObject* self, PyObject* args, PyObject* kwargs) { + static char* kwlist[] = { + "window_log", + "chain_log", + "hash_log", + "search_log", + "search_length", + "target_length", + "strategy", + NULL + }; + + unsigned windowLog; + unsigned chainLog; + unsigned hashLog; + unsigned searchLog; + unsigned searchLength; + unsigned targetLength; + unsigned strategy; + ZSTD_compressionParameters params; + size_t zresult; + + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "IIIIIII:CompressionParameters", + kwlist, &windowLog, &chainLog, &hashLog, &searchLog, &searchLength, + &targetLength, &strategy)) { + return -1; + } + + if (windowLog < ZSTD_WINDOWLOG_MIN || windowLog > ZSTD_WINDOWLOG_MAX) { + PyErr_SetString(PyExc_ValueError, "invalid window log value"); + return -1; + } + + if (chainLog < ZSTD_CHAINLOG_MIN || chainLog > ZSTD_CHAINLOG_MAX) { + PyErr_SetString(PyExc_ValueError, "invalid chain log value"); + return -1; + } + + if (hashLog < ZSTD_HASHLOG_MIN || hashLog > ZSTD_HASHLOG_MAX) { + PyErr_SetString(PyExc_ValueError, "invalid hash log value"); + return -1; + } + + if (searchLog < ZSTD_SEARCHLOG_MIN || searchLog > ZSTD_SEARCHLOG_MAX) { + PyErr_SetString(PyExc_ValueError, "invalid search log value"); + return -1; + } + + if (searchLength < ZSTD_SEARCHLENGTH_MIN || searchLength > ZSTD_SEARCHLENGTH_MAX) { + PyErr_SetString(PyExc_ValueError, "invalid search length value"); + return -1; + } + + if (targetLength < ZSTD_TARGETLENGTH_MIN || targetLength > ZSTD_TARGETLENGTH_MAX) { + PyErr_SetString(PyExc_ValueError, "invalid target length value"); + return -1; + } + + if (strategy < ZSTD_fast || strategy > ZSTD_btopt) { + PyErr_SetString(PyExc_ValueError, "invalid strategy value"); + return -1; + } + + self->windowLog = windowLog; + self->chainLog = chainLog; + self->hashLog = hashLog; + self->searchLog = searchLog; + self->searchLength = searchLength; + self->targetLength = targetLength; + self->strategy = strategy; + + ztopy_compression_parameters(self, ¶ms); + zresult = ZSTD_checkCParams(params); + + if (ZSTD_isError(zresult)) { + PyErr_Format(PyExc_ValueError, "invalid compression parameters: %s", + ZSTD_getErrorName(zresult)); + return -1; + } + + return 0; +} + +PyDoc_STRVAR(CompressionParameters_estimated_compression_context_size__doc__, +"Estimate the size in bytes of a compression context for compression parameters\n" +); + +PyObject* CompressionParameters_estimated_compression_context_size(CompressionParametersObject* self) { + ZSTD_compressionParameters params; + + ztopy_compression_parameters(self, ¶ms); + + return PyLong_FromSize_t(ZSTD_estimateCCtxSize(params)); +} + PyObject* estimate_compression_context_size(PyObject* self, PyObject* args) { CompressionParametersObject* params; ZSTD_compressionParameters zparams; PyObject* result; - if (!PyArg_ParseTuple(args, "O!", &CompressionParametersType, ¶ms)) { + if (!PyArg_ParseTuple(args, "O!:estimate_compression_context_size", + &CompressionParametersType, ¶ms)) { return NULL; } @@ -64,113 +161,43 @@ PyDoc_STRVAR(CompressionParameters__doc__, "CompressionParameters: low-level control over zstd compression"); -static PyObject* CompressionParameters_new(PyTypeObject* subtype, PyObject* args, PyObject* kwargs) { - CompressionParametersObject* self; - unsigned windowLog; - unsigned chainLog; - unsigned hashLog; - unsigned searchLog; - unsigned searchLength; - unsigned targetLength; - unsigned strategy; - - if (!PyArg_ParseTuple(args, "IIIIIII", &windowLog, &chainLog, &hashLog, &searchLog, - &searchLength, &targetLength, &strategy)) { - return NULL; - } - - if (windowLog < ZSTD_WINDOWLOG_MIN || windowLog > ZSTD_WINDOWLOG_MAX) { - PyErr_SetString(PyExc_ValueError, "invalid window log value"); - return NULL; - } - - if (chainLog < ZSTD_CHAINLOG_MIN || chainLog > ZSTD_CHAINLOG_MAX) { - PyErr_SetString(PyExc_ValueError, "invalid chain log value"); - return NULL; - } - - if (hashLog < ZSTD_HASHLOG_MIN || hashLog > ZSTD_HASHLOG_MAX) { - PyErr_SetString(PyExc_ValueError, "invalid hash log value"); - return NULL; - } - - if (searchLog < ZSTD_SEARCHLOG_MIN || searchLog > ZSTD_SEARCHLOG_MAX) { - PyErr_SetString(PyExc_ValueError, "invalid search log value"); - return NULL; - } - - if (searchLength < ZSTD_SEARCHLENGTH_MIN || searchLength > ZSTD_SEARCHLENGTH_MAX) { - PyErr_SetString(PyExc_ValueError, "invalid search length value"); - return NULL; - } - - if (targetLength < ZSTD_TARGETLENGTH_MIN || targetLength > ZSTD_TARGETLENGTH_MAX) { - PyErr_SetString(PyExc_ValueError, "invalid target length value"); - return NULL; - } - - if (strategy < ZSTD_fast || strategy > ZSTD_btopt) { - PyErr_SetString(PyExc_ValueError, "invalid strategy value"); - return NULL; - } - - self = (CompressionParametersObject*)subtype->tp_alloc(subtype, 1); - if (!self) { - return NULL; - } - - self->windowLog = windowLog; - self->chainLog = chainLog; - self->hashLog = hashLog; - self->searchLog = searchLog; - self->searchLength = searchLength; - self->targetLength = targetLength; - self->strategy = strategy; - - return (PyObject*)self; -} - static void CompressionParameters_dealloc(PyObject* self) { PyObject_Del(self); } -static Py_ssize_t CompressionParameters_length(PyObject* self) { - return 7; -} - -static PyObject* CompressionParameters_item(PyObject* o, Py_ssize_t i) { - CompressionParametersObject* self = (CompressionParametersObject*)o; +static PyMethodDef CompressionParameters_methods[] = { + { + "estimated_compression_context_size", + (PyCFunction)CompressionParameters_estimated_compression_context_size, + METH_NOARGS, + CompressionParameters_estimated_compression_context_size__doc__ + }, + { NULL, NULL } +}; - switch (i) { - case 0: - return PyLong_FromLong(self->windowLog); - case 1: - return PyLong_FromLong(self->chainLog); - case 2: - return PyLong_FromLong(self->hashLog); - case 3: - return PyLong_FromLong(self->searchLog); - case 4: - return PyLong_FromLong(self->searchLength); - case 5: - return PyLong_FromLong(self->targetLength); - case 6: - return PyLong_FromLong(self->strategy); - default: - PyErr_SetString(PyExc_IndexError, "index out of range"); - return NULL; - } -} - -static PySequenceMethods CompressionParameters_sq = { - CompressionParameters_length, /* sq_length */ - 0, /* sq_concat */ - 0, /* sq_repeat */ - CompressionParameters_item, /* sq_item */ - 0, /* sq_ass_item */ - 0, /* sq_contains */ - 0, /* sq_inplace_concat */ - 0 /* sq_inplace_repeat */ +static PyMemberDef CompressionParameters_members[] = { + { "window_log", T_UINT, + offsetof(CompressionParametersObject, windowLog), READONLY, + "window log" }, + { "chain_log", T_UINT, + offsetof(CompressionParametersObject, chainLog), READONLY, + "chain log" }, + { "hash_log", T_UINT, + offsetof(CompressionParametersObject, hashLog), READONLY, + "hash log" }, + { "search_log", T_UINT, + offsetof(CompressionParametersObject, searchLog), READONLY, + "search log" }, + { "search_length", T_UINT, + offsetof(CompressionParametersObject, searchLength), READONLY, + "search length" }, + { "target_length", T_UINT, + offsetof(CompressionParametersObject, targetLength), READONLY, + "target length" }, + { "strategy", T_INT, + offsetof(CompressionParametersObject, strategy), READONLY, + "strategy" }, + { NULL } }; PyTypeObject CompressionParametersType = { @@ -185,7 +212,7 @@ 0, /* tp_compare */ 0, /* tp_repr */ 0, /* tp_as_number */ - &CompressionParameters_sq, /* tp_as_sequence */ + 0, /* tp_as_sequence */ 0, /* tp_as_mapping */ 0, /* tp_hash */ 0, /* tp_call */ @@ -193,7 +220,7 @@ 0, /* tp_getattro */ 0, /* tp_setattro */ 0, /* tp_as_buffer */ - Py_TPFLAGS_DEFAULT, /* tp_flags */ + Py_TPFLAGS_DEFAULT | Py_TPFLAGS_BASETYPE, /* tp_flags */ CompressionParameters__doc__, /* tp_doc */ 0, /* tp_traverse */ 0, /* tp_clear */ @@ -201,17 +228,17 @@ 0, /* tp_weaklistoffset */ 0, /* tp_iter */ 0, /* tp_iternext */ - 0, /* tp_methods */ - 0, /* tp_members */ + CompressionParameters_methods, /* tp_methods */ + CompressionParameters_members, /* tp_members */ 0, /* tp_getset */ 0, /* tp_base */ 0, /* tp_dict */ 0, /* tp_descr_get */ 0, /* tp_descr_set */ 0, /* tp_dictoffset */ - 0, /* tp_init */ + (initproc)CompressionParameters_init, /* tp_init */ 0, /* tp_alloc */ - CompressionParameters_new, /* tp_new */ + PyType_GenericNew, /* tp_new */ }; void compressionparams_module_init(PyObject* mod) { @@ -220,7 +247,7 @@ return; } - Py_IncRef((PyObject*)&CompressionParametersType); + Py_INCREF(&CompressionParametersType); PyModule_AddObject(mod, "CompressionParameters", (PyObject*)&CompressionParametersType); }
--- a/contrib/python-zstandard/c-ext/compressionwriter.c Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/python-zstandard/c-ext/compressionwriter.c Tue Apr 18 12:24:34 2017 -0400 @@ -18,11 +18,6 @@ Py_XDECREF(self->compressor); Py_XDECREF(self->writer); - if (self->cstream) { - ZSTD_freeCStream(self->cstream); - self->cstream = NULL; - } - PyObject_Del(self); } @@ -32,9 +27,15 @@ return NULL; } - self->cstream = CStream_from_ZstdCompressor(self->compressor, self->sourceSize); - if (!self->cstream) { - return NULL; + if (self->compressor->mtcctx) { + if (init_mtcstream(self->compressor, self->sourceSize)) { + return NULL; + } + } + else { + if (0 != init_cstream(self->compressor, self->sourceSize)) { + return NULL; + } } self->entered = 1; @@ -52,14 +53,14 @@ ZSTD_outBuffer output; PyObject* res; - if (!PyArg_ParseTuple(args, "OOO", &exc_type, &exc_value, &exc_tb)) { + if (!PyArg_ParseTuple(args, "OOO:__exit__", &exc_type, &exc_value, &exc_tb)) { return NULL; } self->entered = 0; - if (self->cstream && exc_type == Py_None && exc_value == Py_None && - exc_tb == Py_None) { + if ((self->compressor->cstream || self->compressor->mtcctx) && exc_type == Py_None + && exc_value == Py_None && exc_tb == Py_None) { output.dst = PyMem_Malloc(self->outSize); if (!output.dst) { @@ -69,7 +70,12 @@ output.pos = 0; while (1) { - zresult = ZSTD_endStream(self->cstream, &output); + if (self->compressor->mtcctx) { + zresult = ZSTDMT_endStream(self->compressor->mtcctx, &output); + } + else { + zresult = ZSTD_endStream(self->compressor->cstream, &output); + } if (ZSTD_isError(zresult)) { PyErr_Format(ZstdError, "error ending compression stream: %s", ZSTD_getErrorName(zresult)); @@ -95,21 +101,19 @@ } PyMem_Free(output.dst); - ZSTD_freeCStream(self->cstream); - self->cstream = NULL; } Py_RETURN_FALSE; } static PyObject* ZstdCompressionWriter_memory_size(ZstdCompressionWriter* self) { - if (!self->cstream) { + if (!self->compressor->cstream) { PyErr_SetString(ZstdError, "cannot determine size of an inactive compressor; " "call when a context manager is active"); return NULL; } - return PyLong_FromSize_t(ZSTD_sizeof_CStream(self->cstream)); + return PyLong_FromSize_t(ZSTD_sizeof_CStream(self->compressor->cstream)); } static PyObject* ZstdCompressionWriter_write(ZstdCompressionWriter* self, PyObject* args) { @@ -119,11 +123,12 @@ ZSTD_inBuffer input; ZSTD_outBuffer output; PyObject* res; + Py_ssize_t totalWrite = 0; #if PY_MAJOR_VERSION >= 3 - if (!PyArg_ParseTuple(args, "y#", &source, &sourceSize)) { + if (!PyArg_ParseTuple(args, "y#:write", &source, &sourceSize)) { #else - if (!PyArg_ParseTuple(args, "s#", &source, &sourceSize)) { + if (!PyArg_ParseTuple(args, "s#:write", &source, &sourceSize)) { #endif return NULL; } @@ -146,7 +151,13 @@ while ((ssize_t)input.pos < sourceSize) { Py_BEGIN_ALLOW_THREADS - zresult = ZSTD_compressStream(self->cstream, &output, &input); + if (self->compressor->mtcctx) { + zresult = ZSTDMT_compressStream(self->compressor->mtcctx, + &output, &input); + } + else { + zresult = ZSTD_compressStream(self->compressor->cstream, &output, &input); + } Py_END_ALLOW_THREADS if (ZSTD_isError(zresult)) { @@ -164,20 +175,21 @@ #endif output.dst, output.pos); Py_XDECREF(res); + totalWrite += output.pos; } output.pos = 0; } PyMem_Free(output.dst); - /* TODO return bytes written */ - Py_RETURN_NONE; + return PyLong_FromSsize_t(totalWrite); } static PyObject* ZstdCompressionWriter_flush(ZstdCompressionWriter* self, PyObject* args) { size_t zresult; ZSTD_outBuffer output; PyObject* res; + Py_ssize_t totalWrite = 0; if (!self->entered) { PyErr_SetString(ZstdError, "flush must be called from an active context manager"); @@ -193,7 +205,12 @@ while (1) { Py_BEGIN_ALLOW_THREADS - zresult = ZSTD_flushStream(self->cstream, &output); + if (self->compressor->mtcctx) { + zresult = ZSTDMT_flushStream(self->compressor->mtcctx, &output); + } + else { + zresult = ZSTD_flushStream(self->compressor->cstream, &output); + } Py_END_ALLOW_THREADS if (ZSTD_isError(zresult)) { @@ -215,14 +232,14 @@ #endif output.dst, output.pos); Py_XDECREF(res); + totalWrite += output.pos; } output.pos = 0; } PyMem_Free(output.dst); - /* TODO return bytes written */ - Py_RETURN_NONE; + return PyLong_FromSsize_t(totalWrite); } static PyMethodDef ZstdCompressionWriter_methods[] = {
--- a/contrib/python-zstandard/c-ext/compressobj.c Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/python-zstandard/c-ext/compressobj.c Tue Apr 18 12:24:34 2017 -0400 @@ -18,11 +18,6 @@ PyMem_Free(self->output.dst); self->output.dst = NULL; - if (self->cstream) { - ZSTD_freeCStream(self->cstream); - self->cstream = NULL; - } - Py_XDECREF(self->compressor); PyObject_Del(self); @@ -42,9 +37,9 @@ } #if PY_MAJOR_VERSION >= 3 - if (!PyArg_ParseTuple(args, "y#", &source, &sourceSize)) { + if (!PyArg_ParseTuple(args, "y#:compress", &source, &sourceSize)) { #else - if (!PyArg_ParseTuple(args, "s#", &source, &sourceSize)) { + if (!PyArg_ParseTuple(args, "s#:compress", &source, &sourceSize)) { #endif return NULL; } @@ -55,7 +50,13 @@ while ((ssize_t)input.pos < sourceSize) { Py_BEGIN_ALLOW_THREADS - zresult = ZSTD_compressStream(self->cstream, &self->output, &input); + if (self->compressor->mtcctx) { + zresult = ZSTDMT_compressStream(self->compressor->mtcctx, + &self->output, &input); + } + else { + zresult = ZSTD_compressStream(self->compressor->cstream, &self->output, &input); + } Py_END_ALLOW_THREADS if (ZSTD_isError(zresult)) { @@ -98,7 +99,7 @@ PyObject* result = NULL; Py_ssize_t resultSize = 0; - if (!PyArg_ParseTuple(args, "|i", &flushMode)) { + if (!PyArg_ParseTuple(args, "|i:flush", &flushMode)) { return NULL; } @@ -118,7 +119,12 @@ /* The output buffer is of size ZSTD_CStreamOutSize(), which is guaranteed to hold a full block. */ Py_BEGIN_ALLOW_THREADS - zresult = ZSTD_flushStream(self->cstream, &self->output); + if (self->compressor->mtcctx) { + zresult = ZSTDMT_flushStream(self->compressor->mtcctx, &self->output); + } + else { + zresult = ZSTD_flushStream(self->compressor->cstream, &self->output); + } Py_END_ALLOW_THREADS if (ZSTD_isError(zresult)) { @@ -150,7 +156,12 @@ self->finished = 1; while (1) { - zresult = ZSTD_endStream(self->cstream, &self->output); + if (self->compressor->mtcctx) { + zresult = ZSTDMT_endStream(self->compressor->mtcctx, &self->output); + } + else { + zresult = ZSTD_endStream(self->compressor->cstream, &self->output); + } if (ZSTD_isError(zresult)) { PyErr_Format(ZstdError, "error ending compression stream: %s", ZSTD_getErrorName(zresult)); @@ -182,9 +193,6 @@ } } - ZSTD_freeCStream(self->cstream); - self->cstream = NULL; - if (result) { return result; }
--- a/contrib/python-zstandard/c-ext/compressor.c Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/python-zstandard/c-ext/compressor.c Tue Apr 18 12:24:34 2017 -0400 @@ -7,16 +7,21 @@ */ #include "python-zstandard.h" +#include "pool.h" extern PyObject* ZstdError; -int populate_cdict(ZstdCompressor* compressor, void* dictData, size_t dictSize, ZSTD_parameters* zparams) { +int populate_cdict(ZstdCompressor* compressor, ZSTD_parameters* zparams) { ZSTD_customMem zmem; - assert(!compressor->cdict); + + if (compressor->cdict || !compressor->dict || !compressor->dict->dictData) { + return 0; + } + Py_BEGIN_ALLOW_THREADS memset(&zmem, 0, sizeof(zmem)); compressor->cdict = ZSTD_createCDict_advanced(compressor->dict->dictData, - compressor->dict->dictSize, *zparams, zmem); + compressor->dict->dictSize, 1, *zparams, zmem); Py_END_ALLOW_THREADS if (!compressor->cdict) { @@ -28,22 +33,32 @@ } /** -* Initialize a zstd CStream from a ZstdCompressor instance. -* -* Returns a ZSTD_CStream on success or NULL on failure. If NULL, a Python -* exception will be set. -*/ -ZSTD_CStream* CStream_from_ZstdCompressor(ZstdCompressor* compressor, Py_ssize_t sourceSize) { - ZSTD_CStream* cstream; + * Ensure the ZSTD_CStream on a ZstdCompressor instance is initialized. + * + * Returns 0 on success. Other value on failure. Will set a Python exception + * on failure. + */ +int init_cstream(ZstdCompressor* compressor, unsigned long long sourceSize) { ZSTD_parameters zparams; void* dictData = NULL; size_t dictSize = 0; size_t zresult; - cstream = ZSTD_createCStream(); - if (!cstream) { - PyErr_SetString(ZstdError, "cannot create CStream"); - return NULL; + if (compressor->cstream) { + zresult = ZSTD_resetCStream(compressor->cstream, sourceSize); + if (ZSTD_isError(zresult)) { + PyErr_Format(ZstdError, "could not reset CStream: %s", + ZSTD_getErrorName(zresult)); + return -1; + } + + return 0; + } + + compressor->cstream = ZSTD_createCStream(); + if (!compressor->cstream) { + PyErr_SetString(ZstdError, "could not create CStream"); + return -1; } if (compressor->dict) { @@ -63,15 +78,51 @@ zparams.fParams = compressor->fparams; - zresult = ZSTD_initCStream_advanced(cstream, dictData, dictSize, zparams, sourceSize); + zresult = ZSTD_initCStream_advanced(compressor->cstream, dictData, dictSize, + zparams, sourceSize); if (ZSTD_isError(zresult)) { - ZSTD_freeCStream(cstream); + ZSTD_freeCStream(compressor->cstream); + compressor->cstream = NULL; PyErr_Format(ZstdError, "cannot init CStream: %s", ZSTD_getErrorName(zresult)); - return NULL; + return -1; } - return cstream; + return 0;; +} + +int init_mtcstream(ZstdCompressor* compressor, Py_ssize_t sourceSize) { + size_t zresult; + void* dictData = NULL; + size_t dictSize = 0; + ZSTD_parameters zparams; + + assert(compressor->mtcctx); + + if (compressor->dict) { + dictData = compressor->dict->dictData; + dictSize = compressor->dict->dictSize; + } + + memset(&zparams, 0, sizeof(zparams)); + if (compressor->cparams) { + ztopy_compression_parameters(compressor->cparams, &zparams.cParams); + } + else { + zparams.cParams = ZSTD_getCParams(compressor->compressionLevel, sourceSize, dictSize); + } + + zparams.fParams = compressor->fparams; + + zresult = ZSTDMT_initCStream_advanced(compressor->mtcctx, dictData, dictSize, + zparams, sourceSize); + + if (ZSTD_isError(zresult)) { + PyErr_Format(ZstdError, "cannot init CStream: %s", ZSTD_getErrorName(zresult)); + return -1; + } + + return 0; } PyDoc_STRVAR(ZstdCompressor__doc__, @@ -103,6 +154,11 @@ " Determines whether the dictionary ID will be written into the compressed\n" " data. Defaults to True. Only adds content to the compressed data if\n" " a dictionary is being used.\n" +"threads\n" +" Number of threads to use to compress data concurrently. When set,\n" +" compression operations are performed on multiple threads. The default\n" +" value (0) disables multi-threaded compression. A value of ``-1`` means to\n" +" set the number of threads to the number of detected logical CPUs.\n" ); static int ZstdCompressor_init(ZstdCompressor* self, PyObject* args, PyObject* kwargs) { @@ -113,6 +169,7 @@ "write_checksum", "write_content_size", "write_dict_id", + "threads", NULL }; @@ -122,16 +179,12 @@ PyObject* writeChecksum = NULL; PyObject* writeContentSize = NULL; PyObject* writeDictID = NULL; + int threads = 0; - self->cctx = NULL; - self->dict = NULL; - self->cparams = NULL; - self->cdict = NULL; - - if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|iO!O!OOO", kwlist, - &level, &ZstdCompressionDictType, &dict, + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|iO!O!OOOi:ZstdCompressor", + kwlist, &level, &ZstdCompressionDictType, &dict, &CompressionParametersType, ¶ms, - &writeChecksum, &writeContentSize, &writeDictID)) { + &writeChecksum, &writeContentSize, &writeDictID, &threads)) { return -1; } @@ -146,12 +199,27 @@ return -1; } + if (threads < 0) { + threads = cpu_count(); + } + + self->threads = threads; + /* We create a ZSTD_CCtx for reuse among multiple operations to reduce the overhead of each compression operation. */ - self->cctx = ZSTD_createCCtx(); - if (!self->cctx) { - PyErr_NoMemory(); - return -1; + if (threads) { + self->mtcctx = ZSTDMT_createCCtx(threads); + if (!self->mtcctx) { + PyErr_NoMemory(); + return -1; + } + } + else { + self->cctx = ZSTD_createCCtx(); + if (!self->cctx) { + PyErr_NoMemory(); + return -1; + } } self->compressionLevel = level; @@ -182,6 +250,11 @@ } static void ZstdCompressor_dealloc(ZstdCompressor* self) { + if (self->cstream) { + ZSTD_freeCStream(self->cstream); + self->cstream = NULL; + } + Py_XDECREF(self->cparams); Py_XDECREF(self->dict); @@ -195,6 +268,11 @@ self->cctx = NULL; } + if (self->mtcctx) { + ZSTDMT_freeCCtx(self->mtcctx); + self->mtcctx = NULL; + } + PyObject_Del(self); } @@ -229,7 +307,6 @@ Py_ssize_t sourceSize = 0; size_t inSize = ZSTD_CStreamInSize(); size_t outSize = ZSTD_CStreamOutSize(); - ZSTD_CStream* cstream; ZSTD_inBuffer input; ZSTD_outBuffer output; Py_ssize_t totalRead = 0; @@ -243,8 +320,8 @@ PyObject* totalReadPy; PyObject* totalWritePy; - if (!PyArg_ParseTupleAndKeywords(args, kwargs, "OO|nkk", kwlist, &source, &dest, &sourceSize, - &inSize, &outSize)) { + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "OO|nkk:copy_stream", kwlist, + &source, &dest, &sourceSize, &inSize, &outSize)) { return NULL; } @@ -261,10 +338,17 @@ /* Prevent free on uninitialized memory in finally. */ output.dst = NULL; - cstream = CStream_from_ZstdCompressor(self, sourceSize); - if (!cstream) { - res = NULL; - goto finally; + if (self->mtcctx) { + if (init_mtcstream(self, sourceSize)) { + res = NULL; + goto finally; + } + } + else { + if (0 != init_cstream(self, sourceSize)) { + res = NULL; + goto finally; + } } output.dst = PyMem_Malloc(outSize); @@ -300,7 +384,12 @@ while (input.pos < input.size) { Py_BEGIN_ALLOW_THREADS - zresult = ZSTD_compressStream(cstream, &output, &input); + if (self->mtcctx) { + zresult = ZSTDMT_compressStream(self->mtcctx, &output, &input); + } + else { + zresult = ZSTD_compressStream(self->cstream, &output, &input); + } Py_END_ALLOW_THREADS if (ZSTD_isError(zresult)) { @@ -325,7 +414,12 @@ /* We've finished reading. Now flush the compressor stream. */ while (1) { - zresult = ZSTD_endStream(cstream, &output); + if (self->mtcctx) { + zresult = ZSTDMT_endStream(self->mtcctx, &output); + } + else { + zresult = ZSTD_endStream(self->cstream, &output); + } if (ZSTD_isError(zresult)) { PyErr_Format(ZstdError, "error ending compression stream: %s", ZSTD_getErrorName(zresult)); @@ -350,24 +444,17 @@ } } - ZSTD_freeCStream(cstream); - cstream = NULL; - totalReadPy = PyLong_FromSsize_t(totalRead); totalWritePy = PyLong_FromSsize_t(totalWrite); res = PyTuple_Pack(2, totalReadPy, totalWritePy); - Py_DecRef(totalReadPy); - Py_DecRef(totalWritePy); + Py_DECREF(totalReadPy); + Py_DECREF(totalWritePy); finally: if (output.dst) { PyMem_Free(output.dst); } - if (cstream) { - ZSTD_freeCStream(cstream); - } - return res; } @@ -402,14 +489,26 @@ ZSTD_parameters zparams; #if PY_MAJOR_VERSION >= 3 - if (!PyArg_ParseTupleAndKeywords(args, kwargs, "y#|O", + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "y#|O:compress", #else - if (!PyArg_ParseTupleAndKeywords(args, kwargs, "s#|O", + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "s#|O:compress", #endif kwlist, &source, &sourceSize, &allowEmpty)) { return NULL; } + if (self->threads && self->dict) { + PyErr_SetString(ZstdError, + "compress() cannot be used with both dictionaries and multi-threaded compression"); + return NULL; + } + + if (self->threads && self->cparams) { + PyErr_SetString(ZstdError, + "compress() cannot be used with both compression parameters and multi-threaded compression"); + return NULL; + } + /* Limitation in zstd C API doesn't let decompression side distinguish between content size of 0 and unknown content size. This can make round tripping via Python difficult. Until this is fixed, require a flag @@ -456,24 +555,28 @@ https://github.com/facebook/zstd/issues/358 contains more info. We could potentially add an argument somewhere to control this behavior. */ - if (dictData && !self->cdict) { - if (populate_cdict(self, dictData, dictSize, &zparams)) { - Py_DECREF(output); - return NULL; - } + if (0 != populate_cdict(self, &zparams)) { + Py_DECREF(output); + return NULL; } Py_BEGIN_ALLOW_THREADS - /* By avoiding ZSTD_compress(), we don't necessarily write out content - size. This means the argument to ZstdCompressor to control frame - parameters is honored. */ - if (self->cdict) { - zresult = ZSTD_compress_usingCDict(self->cctx, dest, destSize, - source, sourceSize, self->cdict); + if (self->mtcctx) { + zresult = ZSTDMT_compressCCtx(self->mtcctx, dest, destSize, + source, sourceSize, self->compressionLevel); } else { - zresult = ZSTD_compress_advanced(self->cctx, dest, destSize, - source, sourceSize, dictData, dictSize, zparams); + /* By avoiding ZSTD_compress(), we don't necessarily write out content + size. This means the argument to ZstdCompressor to control frame + parameters is honored. */ + if (self->cdict) { + zresult = ZSTD_compress_usingCDict(self->cctx, dest, destSize, + source, sourceSize, self->cdict); + } + else { + zresult = ZSTD_compress_advanced(self->cctx, dest, destSize, + source, sourceSize, dictData, dictSize, zparams); + } } Py_END_ALLOW_THREADS @@ -507,19 +610,28 @@ Py_ssize_t inSize = 0; size_t outSize = ZSTD_CStreamOutSize(); - ZstdCompressionObj* result = PyObject_New(ZstdCompressionObj, &ZstdCompressionObjType); + ZstdCompressionObj* result = NULL; + + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|n:compressobj", kwlist, &inSize)) { + return NULL; + } + + result = (ZstdCompressionObj*)PyObject_CallObject((PyObject*)&ZstdCompressionObjType, NULL); if (!result) { return NULL; } - if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|n", kwlist, &inSize)) { - return NULL; + if (self->mtcctx) { + if (init_mtcstream(self, inSize)) { + Py_DECREF(result); + return NULL; + } } - - result->cstream = CStream_from_ZstdCompressor(self, inSize); - if (!result->cstream) { - Py_DECREF(result); - return NULL; + else { + if (0 != init_cstream(self, inSize)) { + Py_DECREF(result); + return NULL; + } } result->output.dst = PyMem_Malloc(outSize); @@ -529,13 +641,9 @@ return NULL; } result->output.size = outSize; - result->output.pos = 0; - result->compressor = self; Py_INCREF(result->compressor); - result->finished = 0; - return result; } @@ -574,24 +682,15 @@ size_t outSize = ZSTD_CStreamOutSize(); ZstdCompressorIterator* result; - if (!PyArg_ParseTupleAndKeywords(args, kwargs, "O|nkk", kwlist, &reader, &sourceSize, - &inSize, &outSize)) { + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "O|nkk:read_from", kwlist, + &reader, &sourceSize, &inSize, &outSize)) { return NULL; } - result = PyObject_New(ZstdCompressorIterator, &ZstdCompressorIteratorType); + result = (ZstdCompressorIterator*)PyObject_CallObject((PyObject*)&ZstdCompressorIteratorType, NULL); if (!result) { return NULL; } - - result->compressor = NULL; - result->reader = NULL; - result->buffer = NULL; - result->cstream = NULL; - result->input.src = NULL; - result->output.dst = NULL; - result->readResult = NULL; - if (PyObject_HasAttrString(reader, "read")) { result->reader = reader; Py_INCREF(result->reader); @@ -608,7 +707,6 @@ goto except; } - result->bufferOffset = 0; sourceSize = result->buffer->len; } else { @@ -621,9 +719,16 @@ Py_INCREF(result->compressor); result->sourceSize = sourceSize; - result->cstream = CStream_from_ZstdCompressor(self, sourceSize); - if (!result->cstream) { - goto except; + + if (self->mtcctx) { + if (init_mtcstream(self, sourceSize)) { + goto except; + } + } + else { + if (0 != init_cstream(self, sourceSize)) { + goto except; + } } result->inSize = inSize; @@ -635,26 +740,12 @@ goto except; } result->output.size = outSize; - result->output.pos = 0; - - result->input.src = NULL; - result->input.size = 0; - result->input.pos = 0; - - result->finishedInput = 0; - result->finishedOutput = 0; goto finally; except: - if (result->cstream) { - ZSTD_freeCStream(result->cstream); - result->cstream = NULL; - } - - Py_DecRef((PyObject*)result->compressor); - Py_DecRef(result->reader); - + Py_XDECREF(result->compressor); + Py_XDECREF(result->reader); Py_DECREF(result); result = NULL; @@ -693,8 +784,8 @@ Py_ssize_t sourceSize = 0; size_t outSize = ZSTD_CStreamOutSize(); - if (!PyArg_ParseTupleAndKeywords(args, kwargs, "O|nk", kwlist, &writer, &sourceSize, - &outSize)) { + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "O|nk:write_to", kwlist, + &writer, &sourceSize, &outSize)) { return NULL; } @@ -703,7 +794,7 @@ return NULL; } - result = PyObject_New(ZstdCompressionWriter, &ZstdCompressionWriterType); + result = (ZstdCompressionWriter*)PyObject_CallObject((PyObject*)&ZstdCompressionWriterType, NULL); if (!result) { return NULL; } @@ -715,11 +806,671 @@ Py_INCREF(result->writer); result->sourceSize = sourceSize; - result->outSize = outSize; - result->entered = 0; - result->cstream = NULL; + return result; +} + +typedef struct { + void* sourceData; + size_t sourceSize; +} DataSource; + +typedef struct { + DataSource* sources; + Py_ssize_t sourcesSize; + unsigned long long totalSourceSize; +} DataSources; + +typedef struct { + void* dest; + Py_ssize_t destSize; + BufferSegment* segments; + Py_ssize_t segmentsSize; +} DestBuffer; + +typedef enum { + WorkerError_none = 0, + WorkerError_zstd = 1, + WorkerError_no_memory = 2, +} WorkerError; + +/** + * Holds state for an individual worker performing multi_compress_to_buffer work. + */ +typedef struct { + /* Used for compression. */ + ZSTD_CCtx* cctx; + ZSTD_CDict* cdict; + int cLevel; + CompressionParametersObject* cParams; + ZSTD_frameParameters fParams; + + /* What to compress. */ + DataSource* sources; + Py_ssize_t sourcesSize; + Py_ssize_t startOffset; + Py_ssize_t endOffset; + unsigned long long totalSourceSize; + + /* Result storage. */ + DestBuffer* destBuffers; + Py_ssize_t destCount; + + /* Error tracking. */ + WorkerError error; + size_t zresult; + Py_ssize_t errorOffset; +} WorkerState; + +static void compress_worker(WorkerState* state) { + Py_ssize_t inputOffset = state->startOffset; + Py_ssize_t remainingItems = state->endOffset - state->startOffset + 1; + Py_ssize_t currentBufferStartOffset = state->startOffset; + size_t zresult; + ZSTD_parameters zparams; + void* newDest; + size_t allocationSize; + size_t boundSize; + Py_ssize_t destOffset = 0; + DataSource* sources = state->sources; + DestBuffer* destBuffer; + + assert(!state->destBuffers); + assert(0 == state->destCount); + + if (state->cParams) { + ztopy_compression_parameters(state->cParams, &zparams.cParams); + } + + zparams.fParams = state->fParams; + + /* + * The total size of the compressed data is unknown until we actually + * compress data. That means we can't pre-allocate the exact size we need. + * + * There is a cost to every allocation and reallocation. So, it is in our + * interest to minimize the number of allocations. + * + * There is also a cost to too few allocations. If allocations are too + * large they may fail. If buffers are shared and all inputs become + * irrelevant at different lifetimes, then a reference to one segment + * in the buffer will keep the entire buffer alive. This leads to excessive + * memory usage. + * + * Our current strategy is to assume a compression ratio of 16:1 and + * allocate buffers of that size, rounded up to the nearest power of 2 + * (because computers like round numbers). That ratio is greater than what + * most inputs achieve. This is by design: we don't want to over-allocate. + * But we don't want to under-allocate and lead to too many buffers either. + */ + + state->destCount = 1; + + state->destBuffers = calloc(1, sizeof(DestBuffer)); + if (NULL == state->destBuffers) { + state->error = WorkerError_no_memory; + return; + } + + destBuffer = &state->destBuffers[state->destCount - 1]; + + /* + * Rather than track bounds and grow the segments buffer, allocate space + * to hold remaining items then truncate when we're done with it. + */ + destBuffer->segments = calloc(remainingItems, sizeof(BufferSegment)); + if (NULL == destBuffer->segments) { + state->error = WorkerError_no_memory; + return; + } + + destBuffer->segmentsSize = remainingItems; + + allocationSize = roundpow2(state->totalSourceSize >> 4); + + /* If the maximum size of the output is larger than that, round up. */ + boundSize = ZSTD_compressBound(sources[inputOffset].sourceSize); + + if (boundSize > allocationSize) { + allocationSize = roundpow2(boundSize); + } + + destBuffer->dest = malloc(allocationSize); + if (NULL == destBuffer->dest) { + state->error = WorkerError_no_memory; + return; + } + + destBuffer->destSize = allocationSize; + + for (inputOffset = state->startOffset; inputOffset <= state->endOffset; inputOffset++) { + void* source = sources[inputOffset].sourceData; + size_t sourceSize = sources[inputOffset].sourceSize; + size_t destAvailable; + void* dest; + + destAvailable = destBuffer->destSize - destOffset; + boundSize = ZSTD_compressBound(sourceSize); + + /* + * Not enough space in current buffer to hold largest compressed output. + * So allocate and switch to a new output buffer. + */ + if (boundSize > destAvailable) { + /* + * The downsizing of the existing buffer is optional. It should be cheap + * (unlike growing). So we just do it. + */ + if (destAvailable) { + newDest = realloc(destBuffer->dest, destOffset); + if (NULL == newDest) { + state->error = WorkerError_no_memory; + return; + } + + destBuffer->dest = newDest; + destBuffer->destSize = destOffset; + } + + /* Truncate segments buffer. */ + newDest = realloc(destBuffer->segments, + (inputOffset - currentBufferStartOffset + 1) * sizeof(BufferSegment)); + if (NULL == newDest) { + state->error = WorkerError_no_memory; + return; + } + + destBuffer->segments = newDest; + destBuffer->segmentsSize = inputOffset - currentBufferStartOffset; + + /* Grow space for new struct. */ + /* TODO consider over-allocating so we don't do this every time. */ + newDest = realloc(state->destBuffers, (state->destCount + 1) * sizeof(DestBuffer)); + if (NULL == newDest) { + state->error = WorkerError_no_memory; + return; + } + + state->destBuffers = newDest; + state->destCount++; + + destBuffer = &state->destBuffers[state->destCount - 1]; + + /* Don't take any chances with non-NULL pointers. */ + memset(destBuffer, 0, sizeof(DestBuffer)); + + /** + * We could dynamically update allocation size based on work done so far. + * For now, keep is simple. + */ + allocationSize = roundpow2(state->totalSourceSize >> 4); + + if (boundSize > allocationSize) { + allocationSize = roundpow2(boundSize); + } + + destBuffer->dest = malloc(allocationSize); + if (NULL == destBuffer->dest) { + state->error = WorkerError_no_memory; + return; + } + + destBuffer->destSize = allocationSize; + destAvailable = allocationSize; + destOffset = 0; + + destBuffer->segments = calloc(remainingItems, sizeof(BufferSegment)); + if (NULL == destBuffer->segments) { + state->error = WorkerError_no_memory; + return; + } + + destBuffer->segmentsSize = remainingItems; + currentBufferStartOffset = inputOffset; + } + + dest = (char*)destBuffer->dest + destOffset; + + if (state->cdict) { + zresult = ZSTD_compress_usingCDict(state->cctx, dest, destAvailable, + source, sourceSize, state->cdict); + } + else { + if (!state->cParams) { + zparams.cParams = ZSTD_getCParams(state->cLevel, sourceSize, 0); + } + + zresult = ZSTD_compress_advanced(state->cctx, dest, destAvailable, + source, sourceSize, NULL, 0, zparams); + } + + if (ZSTD_isError(zresult)) { + state->error = WorkerError_zstd; + state->zresult = zresult; + state->errorOffset = inputOffset; + break; + } + + destBuffer->segments[inputOffset - currentBufferStartOffset].offset = destOffset; + destBuffer->segments[inputOffset - currentBufferStartOffset].length = zresult; + + destOffset += zresult; + remainingItems--; + } + + if (destBuffer->destSize > destOffset) { + newDest = realloc(destBuffer->dest, destOffset); + if (NULL == newDest) { + state->error = WorkerError_no_memory; + return; + } + + destBuffer->dest = newDest; + destBuffer->destSize = destOffset; + } +} + +ZstdBufferWithSegmentsCollection* compress_from_datasources(ZstdCompressor* compressor, + DataSources* sources, unsigned int threadCount) { + ZSTD_parameters zparams; + unsigned long long bytesPerWorker; + POOL_ctx* pool = NULL; + WorkerState* workerStates = NULL; + Py_ssize_t i; + unsigned long long workerBytes = 0; + Py_ssize_t workerStartOffset = 0; + size_t currentThread = 0; + int errored = 0; + Py_ssize_t segmentsCount = 0; + Py_ssize_t segmentIndex; + PyObject* segmentsArg = NULL; + ZstdBufferWithSegments* buffer; + ZstdBufferWithSegmentsCollection* result = NULL; + + assert(sources->sourcesSize > 0); + assert(sources->totalSourceSize > 0); + assert(threadCount >= 1); + + /* More threads than inputs makes no sense. */ + threadCount = sources->sourcesSize < threadCount ? (unsigned int)sources->sourcesSize + : threadCount; + + /* TODO lower thread count when input size is too small and threads would add + overhead. */ + + /* + * When dictionaries are used, parameters are derived from the size of the + * first element. + * + * TODO come up with a better mechanism. + */ + memset(&zparams, 0, sizeof(zparams)); + if (compressor->cparams) { + ztopy_compression_parameters(compressor->cparams, &zparams.cParams); + } + else { + zparams.cParams = ZSTD_getCParams(compressor->compressionLevel, + sources->sources[0].sourceSize, + compressor->dict ? compressor->dict->dictSize : 0); + } + + zparams.fParams = compressor->fparams; + + if (0 != populate_cdict(compressor, &zparams)) { + return NULL; + } + + workerStates = PyMem_Malloc(threadCount * sizeof(WorkerState)); + if (NULL == workerStates) { + PyErr_NoMemory(); + goto finally; + } + + memset(workerStates, 0, threadCount * sizeof(WorkerState)); + + if (threadCount > 1) { + pool = POOL_create(threadCount, 1); + if (NULL == pool) { + PyErr_SetString(ZstdError, "could not initialize zstd thread pool"); + goto finally; + } + } + + bytesPerWorker = sources->totalSourceSize / threadCount; + + for (i = 0; i < threadCount; i++) { + workerStates[i].cctx = ZSTD_createCCtx(); + if (!workerStates[i].cctx) { + PyErr_NoMemory(); + goto finally; + } + + workerStates[i].cdict = compressor->cdict; + workerStates[i].cLevel = compressor->compressionLevel; + workerStates[i].cParams = compressor->cparams; + workerStates[i].fParams = compressor->fparams; + + workerStates[i].sources = sources->sources; + workerStates[i].sourcesSize = sources->sourcesSize; + } + + Py_BEGIN_ALLOW_THREADS + for (i = 0; i < sources->sourcesSize; i++) { + workerBytes += sources->sources[i].sourceSize; + + /* + * The last worker/thread needs to handle all remaining work. Don't + * trigger it prematurely. Defer to the block outside of the loop + * to run the last worker/thread. But do still process this loop + * so workerBytes is correct. + */ + if (currentThread == threadCount - 1) { + continue; + } + + if (workerBytes >= bytesPerWorker) { + assert(currentThread < threadCount); + workerStates[currentThread].totalSourceSize = workerBytes; + workerStates[currentThread].startOffset = workerStartOffset; + workerStates[currentThread].endOffset = i; + + if (threadCount > 1) { + POOL_add(pool, (POOL_function)compress_worker, &workerStates[currentThread]); + } + else { + compress_worker(&workerStates[currentThread]); + } + + currentThread++; + workerStartOffset = i + 1; + workerBytes = 0; + } + } + + if (workerBytes) { + assert(currentThread < threadCount); + workerStates[currentThread].totalSourceSize = workerBytes; + workerStates[currentThread].startOffset = workerStartOffset; + workerStates[currentThread].endOffset = sources->sourcesSize - 1; + + if (threadCount > 1) { + POOL_add(pool, (POOL_function)compress_worker, &workerStates[currentThread]); + } + else { + compress_worker(&workerStates[currentThread]); + } + } + + if (threadCount > 1) { + POOL_free(pool); + pool = NULL; + } + + Py_END_ALLOW_THREADS + + for (i = 0; i < threadCount; i++) { + switch (workerStates[i].error) { + case WorkerError_no_memory: + PyErr_NoMemory(); + errored = 1; + break; + + case WorkerError_zstd: + PyErr_Format(ZstdError, "error compressing item %zd: %s", + workerStates[i].errorOffset, ZSTD_getErrorName(workerStates[i].zresult)); + errored = 1; + break; + default: + ; + } + + if (errored) { + break; + } + + } + + if (errored) { + goto finally; + } + + segmentsCount = 0; + for (i = 0; i < threadCount; i++) { + WorkerState* state = &workerStates[i]; + segmentsCount += state->destCount; + } + + segmentsArg = PyTuple_New(segmentsCount); + if (NULL == segmentsArg) { + goto finally; + } + + segmentIndex = 0; + + for (i = 0; i < threadCount; i++) { + Py_ssize_t j; + WorkerState* state = &workerStates[i]; + + for (j = 0; j < state->destCount; j++) { + DestBuffer* destBuffer = &state->destBuffers[j]; + buffer = BufferWithSegments_FromMemory(destBuffer->dest, destBuffer->destSize, + destBuffer->segments, destBuffer->segmentsSize); + + if (NULL == buffer) { + goto finally; + } + + /* Tell instance to use free() instsead of PyMem_Free(). */ + buffer->useFree = 1; + + /* + * BufferWithSegments_FromMemory takes ownership of the backing memory. + * Unset it here so it doesn't get freed below. + */ + destBuffer->dest = NULL; + destBuffer->segments = NULL; + + PyTuple_SET_ITEM(segmentsArg, segmentIndex++, (PyObject*)buffer); + } + } + + result = (ZstdBufferWithSegmentsCollection*)PyObject_CallObject( + (PyObject*)&ZstdBufferWithSegmentsCollectionType, segmentsArg); + +finally: + Py_CLEAR(segmentsArg); + + if (pool) { + POOL_free(pool); + } + + if (workerStates) { + Py_ssize_t j; + + for (i = 0; i < threadCount; i++) { + WorkerState state = workerStates[i]; + + if (state.cctx) { + ZSTD_freeCCtx(state.cctx); + } + + /* malloc() is used in worker thread. */ + + for (j = 0; j < state.destCount; j++) { + if (state.destBuffers) { + free(state.destBuffers[j].dest); + free(state.destBuffers[j].segments); + } + } + + + free(state.destBuffers); + } + + PyMem_Free(workerStates); + } + + return result; +} + +PyDoc_STRVAR(ZstdCompressor_multi_compress_to_buffer__doc__, +"Compress multiple pieces of data as a single operation\n" +"\n" +"Receives a ``BufferWithSegmentsCollection``, a ``BufferWithSegments``, or\n" +"a list of bytes like objects holding data to compress.\n" +"\n" +"Returns a ``BufferWithSegmentsCollection`` holding compressed data.\n" +"\n" +"This function is optimized to perform multiple compression operations as\n" +"as possible with as little overhead as possbile.\n" +); + +static ZstdBufferWithSegmentsCollection* ZstdCompressor_multi_compress_to_buffer(ZstdCompressor* self, PyObject* args, PyObject* kwargs) { + static char* kwlist[] = { + "data", + "threads", + NULL + }; + + PyObject* data; + int threads = 0; + Py_buffer* dataBuffers = NULL; + DataSources sources; + Py_ssize_t i; + Py_ssize_t sourceCount = 0; + ZstdBufferWithSegmentsCollection* result = NULL; + + if (self->mtcctx) { + PyErr_SetString(ZstdError, + "function cannot be called on ZstdCompressor configured for multi-threaded compression"); + return NULL; + } + + memset(&sources, 0, sizeof(sources)); + + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "O|i:multi_compress_to_buffer", kwlist, + &data, &threads)) { + return NULL; + } + + if (threads < 0) { + threads = cpu_count(); + } + + if (threads < 2) { + threads = 1; + } + + if (PyObject_TypeCheck(data, &ZstdBufferWithSegmentsType)) { + ZstdBufferWithSegments* buffer = (ZstdBufferWithSegments*)data; + + sources.sources = PyMem_Malloc(buffer->segmentCount * sizeof(DataSource)); + if (NULL == sources.sources) { + PyErr_NoMemory(); + goto finally; + } + + for (i = 0; i < buffer->segmentCount; i++) { + sources.sources[i].sourceData = (char*)buffer->data + buffer->segments[i].offset; + sources.sources[i].sourceSize = buffer->segments[i].length; + sources.totalSourceSize += buffer->segments[i].length; + } + + sources.sourcesSize = buffer->segmentCount; + } + else if (PyObject_TypeCheck(data, &ZstdBufferWithSegmentsCollectionType)) { + Py_ssize_t j; + Py_ssize_t offset = 0; + ZstdBufferWithSegments* buffer; + ZstdBufferWithSegmentsCollection* collection = (ZstdBufferWithSegmentsCollection*)data; + + sourceCount = BufferWithSegmentsCollection_length(collection); + + sources.sources = PyMem_Malloc(sourceCount * sizeof(DataSource)); + if (NULL == sources.sources) { + PyErr_NoMemory(); + goto finally; + } + + for (i = 0; i < collection->bufferCount; i++) { + buffer = collection->buffers[i]; + + for (j = 0; j < buffer->segmentCount; j++) { + sources.sources[offset].sourceData = (char*)buffer->data + buffer->segments[j].offset; + sources.sources[offset].sourceSize = buffer->segments[j].length; + sources.totalSourceSize += buffer->segments[j].length; + + offset++; + } + } + + sources.sourcesSize = sourceCount; + } + else if (PyList_Check(data)) { + sourceCount = PyList_GET_SIZE(data); + + sources.sources = PyMem_Malloc(sourceCount * sizeof(DataSource)); + if (NULL == sources.sources) { + PyErr_NoMemory(); + goto finally; + } + + /* + * It isn't clear whether the address referred to by Py_buffer.buf + * is still valid after PyBuffer_Release. We we hold a reference to all + * Py_buffer instances for the duration of the operation. + */ + dataBuffers = PyMem_Malloc(sourceCount * sizeof(Py_buffer)); + if (NULL == dataBuffers) { + PyErr_NoMemory(); + goto finally; + } + + memset(dataBuffers, 0, sourceCount * sizeof(Py_buffer)); + + for (i = 0; i < sourceCount; i++) { + if (0 != PyObject_GetBuffer(PyList_GET_ITEM(data, i), + &dataBuffers[i], PyBUF_CONTIG_RO)) { + PyErr_Clear(); + PyErr_Format(PyExc_TypeError, "item %zd not a bytes like object", i); + goto finally; + } + + sources.sources[i].sourceData = dataBuffers[i].buf; + sources.sources[i].sourceSize = dataBuffers[i].len; + sources.totalSourceSize += dataBuffers[i].len; + } + + sources.sourcesSize = sourceCount; + } + else { + PyErr_SetString(PyExc_TypeError, "argument must be list of BufferWithSegments"); + goto finally; + } + + if (0 == sources.sourcesSize) { + PyErr_SetString(PyExc_ValueError, "no source elements found"); + goto finally; + } + + if (0 == sources.totalSourceSize) { + PyErr_SetString(PyExc_ValueError, "source elements are empty"); + goto finally; + } + + result = compress_from_datasources(self, &sources, threads); + +finally: + PyMem_Free(sources.sources); + + if (dataBuffers) { + for (i = 0; i < sourceCount; i++) { + PyBuffer_Release(&dataBuffers[i]); + } + + PyMem_Free(dataBuffers); + } return result; } @@ -735,6 +1486,8 @@ METH_VARARGS | METH_KEYWORDS, ZstdCompressor_read_from__doc__ }, { "write_to", (PyCFunction)ZstdCompressor_write_to, METH_VARARGS | METH_KEYWORDS, ZstdCompressor_write_to___doc__ }, + { "multi_compress_to_buffer", (PyCFunction)ZstdCompressor_multi_compress_to_buffer, + METH_VARARGS | METH_KEYWORDS, ZstdCompressor_multi_compress_to_buffer__doc__ }, { NULL, NULL } };
--- a/contrib/python-zstandard/c-ext/compressoriterator.c Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/python-zstandard/c-ext/compressoriterator.c Tue Apr 18 12:24:34 2017 -0400 @@ -27,11 +27,6 @@ self->buffer = NULL; } - if (self->cstream) { - ZSTD_freeCStream(self->cstream); - self->cstream = NULL; - } - if (self->output.dst) { PyMem_Free(self->output.dst); self->output.dst = NULL; @@ -63,7 +58,14 @@ /* If we have data left in the input, consume it. */ if (self->input.pos < self->input.size) { Py_BEGIN_ALLOW_THREADS - zresult = ZSTD_compressStream(self->cstream, &self->output, &self->input); + if (self->compressor->mtcctx) { + zresult = ZSTDMT_compressStream(self->compressor->mtcctx, + &self->output, &self->input); + } + else { + zresult = ZSTD_compressStream(self->compressor->cstream, &self->output, + &self->input); + } Py_END_ALLOW_THREADS /* Release the Python object holding the input buffer. */ @@ -128,7 +130,12 @@ /* EOF */ if (0 == readSize) { - zresult = ZSTD_endStream(self->cstream, &self->output); + if (self->compressor->mtcctx) { + zresult = ZSTDMT_endStream(self->compressor->mtcctx, &self->output); + } + else { + zresult = ZSTD_endStream(self->compressor->cstream, &self->output); + } if (ZSTD_isError(zresult)) { PyErr_Format(ZstdError, "error ending compression stream: %s", ZSTD_getErrorName(zresult)); @@ -152,7 +159,13 @@ self->input.pos = 0; Py_BEGIN_ALLOW_THREADS - zresult = ZSTD_compressStream(self->cstream, &self->output, &self->input); + if (self->compressor->mtcctx) { + zresult = ZSTDMT_compressStream(self->compressor->mtcctx, &self->output, + &self->input); + } + else { + zresult = ZSTD_compressStream(self->compressor->cstream, &self->output, &self->input); + } Py_END_ALLOW_THREADS /* The input buffer currently points to memory managed by Python
--- a/contrib/python-zstandard/c-ext/constants.c Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/python-zstandard/c-ext/constants.c Tue Apr 18 12:24:34 2017 -0400 @@ -41,7 +41,7 @@ PyTuple_SetItem(zstdVersion, 0, PyLong_FromLong(ZSTD_VERSION_MAJOR)); PyTuple_SetItem(zstdVersion, 1, PyLong_FromLong(ZSTD_VERSION_MINOR)); PyTuple_SetItem(zstdVersion, 2, PyLong_FromLong(ZSTD_VERSION_RELEASE)); - Py_IncRef(zstdVersion); + Py_INCREF(zstdVersion); PyModule_AddObject(mod, "ZSTD_VERSION", zstdVersion); frameHeader = PyBytes_FromStringAndSize(frame_header, sizeof(frame_header));
--- a/contrib/python-zstandard/c-ext/decompressionwriter.c Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/python-zstandard/c-ext/decompressionwriter.c Tue Apr 18 12:24:34 2017 -0400 @@ -18,11 +18,6 @@ Py_XDECREF(self->decompressor); Py_XDECREF(self->writer); - if (self->dstream) { - ZSTD_freeDStream(self->dstream); - self->dstream = NULL; - } - PyObject_Del(self); } @@ -32,8 +27,7 @@ return NULL; } - self->dstream = DStream_from_ZstdDecompressor(self->decompressor); - if (!self->dstream) { + if (0 != init_dstream(self->decompressor)) { return NULL; } @@ -46,22 +40,17 @@ static PyObject* ZstdDecompressionWriter_exit(ZstdDecompressionWriter* self, PyObject* args) { self->entered = 0; - if (self->dstream) { - ZSTD_freeDStream(self->dstream); - self->dstream = NULL; - } - Py_RETURN_FALSE; } static PyObject* ZstdDecompressionWriter_memory_size(ZstdDecompressionWriter* self) { - if (!self->dstream) { + if (!self->decompressor->dstream) { PyErr_SetString(ZstdError, "cannot determine size of inactive decompressor; " "call when context manager is active"); return NULL; } - return PyLong_FromSize_t(ZSTD_sizeof_DStream(self->dstream)); + return PyLong_FromSize_t(ZSTD_sizeof_DStream(self->decompressor->dstream)); } static PyObject* ZstdDecompressionWriter_write(ZstdDecompressionWriter* self, PyObject* args) { @@ -71,11 +60,12 @@ ZSTD_inBuffer input; ZSTD_outBuffer output; PyObject* res; + Py_ssize_t totalWrite = 0; #if PY_MAJOR_VERSION >= 3 - if (!PyArg_ParseTuple(args, "y#", &source, &sourceSize)) { + if (!PyArg_ParseTuple(args, "y#:write", &source, &sourceSize)) { #else - if (!PyArg_ParseTuple(args, "s#", &source, &sourceSize)) { + if (!PyArg_ParseTuple(args, "s#:write", &source, &sourceSize)) { #endif return NULL; } @@ -85,6 +75,8 @@ return NULL; } + assert(self->decompressor->dstream); + output.dst = PyMem_Malloc(self->outSize); if (!output.dst) { return PyErr_NoMemory(); @@ -98,7 +90,7 @@ while ((ssize_t)input.pos < sourceSize) { Py_BEGIN_ALLOW_THREADS - zresult = ZSTD_decompressStream(self->dstream, &output, &input); + zresult = ZSTD_decompressStream(self->decompressor->dstream, &output, &input); Py_END_ALLOW_THREADS if (ZSTD_isError(zresult)) { @@ -116,15 +108,15 @@ #endif output.dst, output.pos); Py_XDECREF(res); + totalWrite += output.pos; output.pos = 0; } } PyMem_Free(output.dst); - /* TODO return bytes written */ - Py_RETURN_NONE; - } + return PyLong_FromSsize_t(totalWrite); +} static PyMethodDef ZstdDecompressionWriter_methods[] = { { "__enter__", (PyCFunction)ZstdDecompressionWriter_enter, METH_NOARGS,
--- a/contrib/python-zstandard/c-ext/decompressobj.c Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/python-zstandard/c-ext/decompressobj.c Tue Apr 18 12:24:34 2017 -0400 @@ -15,11 +15,6 @@ ); static void DecompressionObj_dealloc(ZstdDecompressionObj* self) { - if (self->dstream) { - ZSTD_freeDStream(self->dstream); - self->dstream = NULL; - } - Py_XDECREF(self->decompressor); PyObject_Del(self); @@ -35,15 +30,18 @@ PyObject* result = NULL; Py_ssize_t resultSize = 0; + /* Constructor should ensure stream is populated. */ + assert(self->decompressor->dstream); + if (self->finished) { PyErr_SetString(ZstdError, "cannot use a decompressobj multiple times"); return NULL; } #if PY_MAJOR_VERSION >= 3 - if (!PyArg_ParseTuple(args, "y#", + if (!PyArg_ParseTuple(args, "y#:decompress", #else - if (!PyArg_ParseTuple(args, "s#", + if (!PyArg_ParseTuple(args, "s#:decompress", #endif &source, &sourceSize)) { return NULL; @@ -64,7 +62,7 @@ /* Read input until exhausted. */ while (input.pos < input.size) { Py_BEGIN_ALLOW_THREADS - zresult = ZSTD_decompressStream(self->dstream, &output, &input); + zresult = ZSTD_decompressStream(self->decompressor->dstream, &output, &input); Py_END_ALLOW_THREADS if (ZSTD_isError(zresult)) { @@ -106,8 +104,7 @@ goto finally; except: - Py_DecRef(result); - result = NULL; + Py_CLEAR(result); finally: PyMem_Free(output.dst);
--- a/contrib/python-zstandard/c-ext/decompressor.c Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/python-zstandard/c-ext/decompressor.c Tue Apr 18 12:24:34 2017 -0400 @@ -7,19 +7,37 @@ */ #include "python-zstandard.h" +#include "pool.h" extern PyObject* ZstdError; -ZSTD_DStream* DStream_from_ZstdDecompressor(ZstdDecompressor* decompressor) { - ZSTD_DStream* dstream; +/** + * Ensure the ZSTD_DStream on a ZstdDecompressor is initialized and reset. + * + * This should be called before starting a decompression operation with a + * ZSTD_DStream on a ZstdDecompressor. + */ +int init_dstream(ZstdDecompressor* decompressor) { void* dictData = NULL; size_t dictSize = 0; size_t zresult; - dstream = ZSTD_createDStream(); - if (!dstream) { + /* Simple case of dstream already exists. Just reset it. */ + if (decompressor->dstream) { + zresult = ZSTD_resetDStream(decompressor->dstream); + if (ZSTD_isError(zresult)) { + PyErr_Format(ZstdError, "could not reset DStream: %s", + ZSTD_getErrorName(zresult)); + return -1; + } + + return 0; + } + + decompressor->dstream = ZSTD_createDStream(); + if (!decompressor->dstream) { PyErr_SetString(ZstdError, "could not create DStream"); - return NULL; + return -1; } if (decompressor->dict) { @@ -28,19 +46,23 @@ } if (dictData) { - zresult = ZSTD_initDStream_usingDict(dstream, dictData, dictSize); + zresult = ZSTD_initDStream_usingDict(decompressor->dstream, dictData, dictSize); } else { - zresult = ZSTD_initDStream(dstream); + zresult = ZSTD_initDStream(decompressor->dstream); } if (ZSTD_isError(zresult)) { + /* Don't leave a reference to an invalid object. */ + ZSTD_freeDStream(decompressor->dstream); + decompressor->dstream = NULL; + PyErr_Format(ZstdError, "could not initialize DStream: %s", ZSTD_getErrorName(zresult)); - return NULL; + return -1; } - return dstream; + return 0; } PyDoc_STRVAR(Decompressor__doc__, @@ -59,23 +81,19 @@ ZstdCompressionDict* dict = NULL; - self->refdctx = NULL; + self->dctx = NULL; self->dict = NULL; self->ddict = NULL; - if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|O!", kwlist, + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|O!:ZstdDecompressor", kwlist, &ZstdCompressionDictType, &dict)) { return -1; } - /* Instead of creating a ZSTD_DCtx for every decompression operation, - we create an instance at object creation time and recycle it via - ZSTD_copyDCTx() on each use. This means each use is a malloc+memcpy - instead of a malloc+init. */ /* TODO lazily initialize the reference ZSTD_DCtx on first use since not instances of ZstdDecompressor will use a ZSTD_DCtx. */ - self->refdctx = ZSTD_createDCtx(); - if (!self->refdctx) { + self->dctx = ZSTD_createDCtx(); + if (!self->dctx) { PyErr_NoMemory(); goto except; } @@ -88,26 +106,32 @@ return 0; except: - if (self->refdctx) { - ZSTD_freeDCtx(self->refdctx); - self->refdctx = NULL; + if (self->dctx) { + ZSTD_freeDCtx(self->dctx); + self->dctx = NULL; } return -1; } static void Decompressor_dealloc(ZstdDecompressor* self) { - if (self->refdctx) { - ZSTD_freeDCtx(self->refdctx); - } - - Py_XDECREF(self->dict); + Py_CLEAR(self->dict); if (self->ddict) { ZSTD_freeDDict(self->ddict); self->ddict = NULL; } + if (self->dstream) { + ZSTD_freeDStream(self->dstream); + self->dstream = NULL; + } + + if (self->dctx) { + ZSTD_freeDCtx(self->dctx); + self->dctx = NULL; + } + PyObject_Del(self); } @@ -136,7 +160,6 @@ PyObject* dest; size_t inSize = ZSTD_DStreamInSize(); size_t outSize = ZSTD_DStreamOutSize(); - ZSTD_DStream* dstream; ZSTD_inBuffer input; ZSTD_outBuffer output; Py_ssize_t totalRead = 0; @@ -150,8 +173,8 @@ PyObject* totalReadPy; PyObject* totalWritePy; - if (!PyArg_ParseTupleAndKeywords(args, kwargs, "OO|kk", kwlist, &source, - &dest, &inSize, &outSize)) { + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "OO|kk:copy_stream", kwlist, + &source, &dest, &inSize, &outSize)) { return NULL; } @@ -168,8 +191,7 @@ /* Prevent free on uninitialized memory in finally. */ output.dst = NULL; - dstream = DStream_from_ZstdDecompressor(self); - if (!dstream) { + if (0 != init_dstream(self)) { res = NULL; goto finally; } @@ -207,7 +229,7 @@ while (input.pos < input.size) { Py_BEGIN_ALLOW_THREADS - zresult = ZSTD_decompressStream(dstream, &output, &input); + zresult = ZSTD_decompressStream(self->dstream, &output, &input); Py_END_ALLOW_THREADS if (ZSTD_isError(zresult)) { @@ -234,24 +256,17 @@ /* Source stream is exhausted. Finish up. */ - ZSTD_freeDStream(dstream); - dstream = NULL; - totalReadPy = PyLong_FromSsize_t(totalRead); totalWritePy = PyLong_FromSsize_t(totalWrite); res = PyTuple_Pack(2, totalReadPy, totalWritePy); - Py_DecRef(totalReadPy); - Py_DecRef(totalWritePy); + Py_DECREF(totalReadPy); + Py_DECREF(totalWritePy); - finally: +finally: if (output.dst) { PyMem_Free(output.dst); } - if (dstream) { - ZSTD_freeDStream(dstream); - } - return res; } @@ -291,28 +306,19 @@ unsigned long long decompressedSize; size_t destCapacity; PyObject* result = NULL; - ZSTD_DCtx* dctx = NULL; void* dictData = NULL; size_t dictSize = 0; size_t zresult; #if PY_MAJOR_VERSION >= 3 - if (!PyArg_ParseTupleAndKeywords(args, kwargs, "y#|n", kwlist, + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "y#|n:decompress", #else - if (!PyArg_ParseTupleAndKeywords(args, kwargs, "s#|n", kwlist, + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "s#|n:decompress", #endif - &source, &sourceSize, &maxOutputSize)) { + kwlist, &source, &sourceSize, &maxOutputSize)) { return NULL; } - dctx = PyMem_Malloc(ZSTD_sizeof_DCtx(self->refdctx)); - if (!dctx) { - PyErr_NoMemory(); - return NULL; - } - - ZSTD_copyDCtx(dctx, self->refdctx); - if (self->dict) { dictData = self->dict->dictData; dictSize = self->dict->dictSize; @@ -320,12 +326,12 @@ if (dictData && !self->ddict) { Py_BEGIN_ALLOW_THREADS - self->ddict = ZSTD_createDDict(dictData, dictSize); + self->ddict = ZSTD_createDDict_byReference(dictData, dictSize); Py_END_ALLOW_THREADS if (!self->ddict) { PyErr_SetString(ZstdError, "could not create decompression dict"); - goto except; + return NULL; } } @@ -335,7 +341,7 @@ if (0 == maxOutputSize) { PyErr_SetString(ZstdError, "input data invalid or missing content size " "in frame header"); - goto except; + return NULL; } else { result = PyBytes_FromStringAndSize(NULL, maxOutputSize); @@ -348,45 +354,39 @@ } if (!result) { - goto except; + return NULL; } Py_BEGIN_ALLOW_THREADS if (self->ddict) { - zresult = ZSTD_decompress_usingDDict(dctx, PyBytes_AsString(result), destCapacity, + zresult = ZSTD_decompress_usingDDict(self->dctx, + PyBytes_AsString(result), destCapacity, source, sourceSize, self->ddict); } else { - zresult = ZSTD_decompressDCtx(dctx, PyBytes_AsString(result), destCapacity, source, sourceSize); + zresult = ZSTD_decompressDCtx(self->dctx, + PyBytes_AsString(result), destCapacity, source, sourceSize); } Py_END_ALLOW_THREADS if (ZSTD_isError(zresult)) { PyErr_Format(ZstdError, "decompression error: %s", ZSTD_getErrorName(zresult)); - goto except; + Py_DECREF(result); + return NULL; } else if (decompressedSize && zresult != decompressedSize) { PyErr_Format(ZstdError, "decompression error: decompressed %zu bytes; expected %llu", zresult, decompressedSize); - goto except; + Py_DECREF(result); + return NULL; } else if (zresult < destCapacity) { if (_PyBytes_Resize(&result, zresult)) { - goto except; + Py_DECREF(result); + return NULL; } } - goto finally; - -except: - Py_DecRef(result); - result = NULL; - -finally: - if (dctx) { - PyMem_FREE(dctx); - } - return result; } @@ -401,22 +401,19 @@ ); static ZstdDecompressionObj* Decompressor_decompressobj(ZstdDecompressor* self) { - ZstdDecompressionObj* result = PyObject_New(ZstdDecompressionObj, &ZstdDecompressionObjType); + ZstdDecompressionObj* result = (ZstdDecompressionObj*)PyObject_CallObject((PyObject*)&ZstdDecompressionObjType, NULL); if (!result) { return NULL; } - result->dstream = DStream_from_ZstdDecompressor(self); - if (!result->dstream) { - Py_DecRef((PyObject*)result); + if (0 != init_dstream(self)) { + Py_DECREF(result); return NULL; } result->decompressor = self; Py_INCREF(result->decompressor); - result->finished = 0; - return result; } @@ -455,8 +452,8 @@ ZstdDecompressorIterator* result; size_t skipBytes = 0; - if (!PyArg_ParseTupleAndKeywords(args, kwargs, "O|kkk", kwlist, &reader, - &inSize, &outSize, &skipBytes)) { + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "O|kkk:read_from", kwlist, + &reader, &inSize, &outSize, &skipBytes)) { return NULL; } @@ -466,18 +463,11 @@ return NULL; } - result = PyObject_New(ZstdDecompressorIterator, &ZstdDecompressorIteratorType); + result = (ZstdDecompressorIterator*)PyObject_CallObject((PyObject*)&ZstdDecompressorIteratorType, NULL); if (!result) { return NULL; } - result->decompressor = NULL; - result->reader = NULL; - result->buffer = NULL; - result->dstream = NULL; - result->input.src = NULL; - result->output.dst = NULL; - if (PyObject_HasAttrString(reader, "read")) { result->reader = reader; Py_INCREF(result->reader); @@ -494,8 +484,6 @@ if (0 != PyObject_GetBuffer(reader, result->buffer, PyBUF_CONTIG_RO)) { goto except; } - - result->bufferOffset = 0; } else { PyErr_SetString(PyExc_ValueError, @@ -510,8 +498,7 @@ result->outSize = outSize; result->skipBytes = skipBytes; - result->dstream = DStream_from_ZstdDecompressor(self); - if (!result->dstream) { + if (0 != init_dstream(self)) { goto except; } @@ -520,33 +507,18 @@ PyErr_NoMemory(); goto except; } - result->input.size = 0; - result->input.pos = 0; - - result->output.dst = NULL; - result->output.size = 0; - result->output.pos = 0; - - result->readCount = 0; - result->finishedInput = 0; - result->finishedOutput = 0; goto finally; except: - if (result->reader) { - Py_DECREF(result->reader); - result->reader = NULL; - } + Py_CLEAR(result->reader); if (result->buffer) { PyBuffer_Release(result->buffer); - Py_DECREF(result->buffer); - result->buffer = NULL; + Py_CLEAR(result->buffer); } - Py_DECREF(result); - result = NULL; + Py_CLEAR(result); finally: @@ -577,7 +549,8 @@ size_t outSize = ZSTD_DStreamOutSize(); ZstdDecompressionWriter* result; - if (!PyArg_ParseTupleAndKeywords(args, kwargs, "O|k", kwlist, &writer, &outSize)) { + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "O|k:write_to", kwlist, + &writer, &outSize)) { return NULL; } @@ -586,7 +559,7 @@ return NULL; } - result = PyObject_New(ZstdDecompressionWriter, &ZstdDecompressionWriterType); + result = (ZstdDecompressionWriter*)PyObject_CallObject((PyObject*)&ZstdDecompressionWriterType, NULL); if (!result) { return NULL; } @@ -599,8 +572,939 @@ result->outSize = outSize; - result->entered = 0; - result->dstream = NULL; + return result; +} + +PyDoc_STRVAR(Decompressor_decompress_content_dict_chain__doc__, +"Decompress a series of chunks using the content dictionary chaining technique\n" +); + +static PyObject* Decompressor_decompress_content_dict_chain(PyObject* self, PyObject* args, PyObject* kwargs) { + static char* kwlist[] = { + "frames", + NULL + }; + + PyObject* chunks; + Py_ssize_t chunksLen; + Py_ssize_t chunkIndex; + char parity = 0; + PyObject* chunk; + char* chunkData; + Py_ssize_t chunkSize; + ZSTD_DCtx* dctx = NULL; + size_t zresult; + ZSTD_frameParams frameParams; + void* buffer1 = NULL; + size_t buffer1Size = 0; + size_t buffer1ContentSize = 0; + void* buffer2 = NULL; + size_t buffer2Size = 0; + size_t buffer2ContentSize = 0; + void* destBuffer = NULL; + PyObject* result = NULL; + + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "O!:decompress_content_dict_chain", + kwlist, &PyList_Type, &chunks)) { + return NULL; + } + + chunksLen = PyList_Size(chunks); + if (!chunksLen) { + PyErr_SetString(PyExc_ValueError, "empty input chain"); + return NULL; + } + + /* The first chunk should not be using a dictionary. We handle it specially. */ + chunk = PyList_GetItem(chunks, 0); + if (!PyBytes_Check(chunk)) { + PyErr_SetString(PyExc_ValueError, "chunk 0 must be bytes"); + return NULL; + } + + /* We require that all chunks be zstd frames and that they have content size set. */ + PyBytes_AsStringAndSize(chunk, &chunkData, &chunkSize); + zresult = ZSTD_getFrameParams(&frameParams, (void*)chunkData, chunkSize); + if (ZSTD_isError(zresult)) { + PyErr_SetString(PyExc_ValueError, "chunk 0 is not a valid zstd frame"); + return NULL; + } + else if (zresult) { + PyErr_SetString(PyExc_ValueError, "chunk 0 is too small to contain a zstd frame"); + return NULL; + } + + if (0 == frameParams.frameContentSize) { + PyErr_SetString(PyExc_ValueError, "chunk 0 missing content size in frame"); + return NULL; + } + + dctx = ZSTD_createDCtx(); + if (!dctx) { + PyErr_NoMemory(); + goto finally; + } + + buffer1Size = frameParams.frameContentSize; + buffer1 = PyMem_Malloc(buffer1Size); + if (!buffer1) { + goto finally; + } + + Py_BEGIN_ALLOW_THREADS + zresult = ZSTD_decompressDCtx(dctx, buffer1, buffer1Size, chunkData, chunkSize); + Py_END_ALLOW_THREADS + if (ZSTD_isError(zresult)) { + PyErr_Format(ZstdError, "could not decompress chunk 0: %s", ZSTD_getErrorName(zresult)); + goto finally; + } + + buffer1ContentSize = zresult; + + /* Special case of a simple chain. */ + if (1 == chunksLen) { + result = PyBytes_FromStringAndSize(buffer1, buffer1Size); + goto finally; + } + + /* This should ideally look at next chunk. But this is slightly simpler. */ + buffer2Size = frameParams.frameContentSize; + buffer2 = PyMem_Malloc(buffer2Size); + if (!buffer2) { + goto finally; + } + + /* For each subsequent chunk, use the previous fulltext as a content dictionary. + Our strategy is to have 2 buffers. One holds the previous fulltext (to be + used as a content dictionary) and the other holds the new fulltext. The + buffers grow when needed but never decrease in size. This limits the + memory allocator overhead. + */ + for (chunkIndex = 1; chunkIndex < chunksLen; chunkIndex++) { + chunk = PyList_GetItem(chunks, chunkIndex); + if (!PyBytes_Check(chunk)) { + PyErr_Format(PyExc_ValueError, "chunk %zd must be bytes", chunkIndex); + goto finally; + } + + PyBytes_AsStringAndSize(chunk, &chunkData, &chunkSize); + zresult = ZSTD_getFrameParams(&frameParams, (void*)chunkData, chunkSize); + if (ZSTD_isError(zresult)) { + PyErr_Format(PyExc_ValueError, "chunk %zd is not a valid zstd frame", chunkIndex); + goto finally; + } + else if (zresult) { + PyErr_Format(PyExc_ValueError, "chunk %zd is too small to contain a zstd frame", chunkIndex); + goto finally; + } + + if (0 == frameParams.frameContentSize) { + PyErr_Format(PyExc_ValueError, "chunk %zd missing content size in frame", chunkIndex); + goto finally; + } + + parity = chunkIndex % 2; + + /* This could definitely be abstracted to reduce code duplication. */ + if (parity) { + /* Resize destination buffer to hold larger content. */ + if (buffer2Size < frameParams.frameContentSize) { + buffer2Size = frameParams.frameContentSize; + destBuffer = PyMem_Realloc(buffer2, buffer2Size); + if (!destBuffer) { + goto finally; + } + buffer2 = destBuffer; + } + + Py_BEGIN_ALLOW_THREADS + zresult = ZSTD_decompress_usingDict(dctx, buffer2, buffer2Size, + chunkData, chunkSize, buffer1, buffer1ContentSize); + Py_END_ALLOW_THREADS + if (ZSTD_isError(zresult)) { + PyErr_Format(ZstdError, "could not decompress chunk %zd: %s", + chunkIndex, ZSTD_getErrorName(zresult)); + goto finally; + } + buffer2ContentSize = zresult; + } + else { + if (buffer1Size < frameParams.frameContentSize) { + buffer1Size = frameParams.frameContentSize; + destBuffer = PyMem_Realloc(buffer1, buffer1Size); + if (!destBuffer) { + goto finally; + } + buffer1 = destBuffer; + } + + Py_BEGIN_ALLOW_THREADS + zresult = ZSTD_decompress_usingDict(dctx, buffer1, buffer1Size, + chunkData, chunkSize, buffer2, buffer2ContentSize); + Py_END_ALLOW_THREADS + if (ZSTD_isError(zresult)) { + PyErr_Format(ZstdError, "could not decompress chunk %zd: %s", + chunkIndex, ZSTD_getErrorName(zresult)); + goto finally; + } + buffer1ContentSize = zresult; + } + } + + result = PyBytes_FromStringAndSize(parity ? buffer2 : buffer1, + parity ? buffer2ContentSize : buffer1ContentSize); + +finally: + if (buffer2) { + PyMem_Free(buffer2); + } + if (buffer1) { + PyMem_Free(buffer1); + } + + if (dctx) { + ZSTD_freeDCtx(dctx); + } + + return result; +} + +typedef struct { + void* sourceData; + size_t sourceSize; + unsigned long long destSize; +} FramePointer; + +typedef struct { + FramePointer* frames; + Py_ssize_t framesSize; + unsigned long long compressedSize; +} FrameSources; + +typedef struct { + void* dest; + Py_ssize_t destSize; + BufferSegment* segments; + Py_ssize_t segmentsSize; +} DestBuffer; + +typedef enum { + WorkerError_none = 0, + WorkerError_zstd = 1, + WorkerError_memory = 2, + WorkerError_sizeMismatch = 3, + WorkerError_unknownSize = 4, +} WorkerError; + +typedef struct { + /* Source records and length */ + FramePointer* framePointers; + /* Which records to process. */ + Py_ssize_t startOffset; + Py_ssize_t endOffset; + unsigned long long totalSourceSize; + + /* Compression state and settings. */ + ZSTD_DCtx* dctx; + ZSTD_DDict* ddict; + int requireOutputSizes; + + /* Output storage. */ + DestBuffer* destBuffers; + Py_ssize_t destCount; + + /* Item that error occurred on. */ + Py_ssize_t errorOffset; + /* If an error occurred. */ + WorkerError error; + /* result from zstd decompression operation */ + size_t zresult; +} WorkerState; + +static void decompress_worker(WorkerState* state) { + size_t allocationSize; + DestBuffer* destBuffer; + Py_ssize_t frameIndex; + Py_ssize_t localOffset = 0; + Py_ssize_t currentBufferStartIndex = state->startOffset; + Py_ssize_t remainingItems = state->endOffset - state->startOffset + 1; + void* tmpBuf; + Py_ssize_t destOffset = 0; + FramePointer* framePointers = state->framePointers; + size_t zresult; + unsigned long long totalOutputSize = 0; + + assert(NULL == state->destBuffers); + assert(0 == state->destCount); + assert(state->endOffset - state->startOffset >= 0); + + /* + * We need to allocate a buffer to hold decompressed data. How we do this + * depends on what we know about the output. The following scenarios are + * possible: + * + * 1. All structs defining frames declare the output size. + * 2. The decompressed size is embedded within the zstd frame. + * 3. The decompressed size is not stored anywhere. + * + * For now, we only support #1 and #2. + */ + + /* Resolve ouput segments. */ + for (frameIndex = state->startOffset; frameIndex <= state->endOffset; frameIndex++) { + FramePointer* fp = &framePointers[frameIndex]; + + if (0 == fp->destSize) { + fp->destSize = ZSTD_getDecompressedSize(fp->sourceData, fp->sourceSize); + if (0 == fp->destSize && state->requireOutputSizes) { + state->error = WorkerError_unknownSize; + state->errorOffset = frameIndex; + return; + } + } + + totalOutputSize += fp->destSize; + } + + state->destBuffers = calloc(1, sizeof(DestBuffer)); + if (NULL == state->destBuffers) { + state->error = WorkerError_memory; + return; + } + + state->destCount = 1; + + destBuffer = &state->destBuffers[state->destCount - 1]; + + assert(framePointers[state->startOffset].destSize > 0); /* For now. */ + + allocationSize = roundpow2(state->totalSourceSize); + + if (framePointers[state->startOffset].destSize > allocationSize) { + allocationSize = roundpow2(framePointers[state->startOffset].destSize); + } + + destBuffer->dest = malloc(allocationSize); + if (NULL == destBuffer->dest) { + state->error = WorkerError_memory; + return; + } + + destBuffer->destSize = allocationSize; + + destBuffer->segments = calloc(remainingItems, sizeof(BufferSegment)); + if (NULL == destBuffer->segments) { + /* Caller will free state->dest as part of cleanup. */ + state->error = WorkerError_memory; + return; + } + + destBuffer->segmentsSize = remainingItems; + + for (frameIndex = state->startOffset; frameIndex <= state->endOffset; frameIndex++) { + const void* source = framePointers[frameIndex].sourceData; + const size_t sourceSize = framePointers[frameIndex].sourceSize; + void* dest; + const size_t decompressedSize = framePointers[frameIndex].destSize; + size_t destAvailable = destBuffer->destSize - destOffset; + + assert(decompressedSize > 0); /* For now. */ + + /* + * Not enough space in current buffer. Finish current before and allocate and + * switch to a new one. + */ + if (decompressedSize > destAvailable) { + /* + * Shrinking the destination buffer is optional. But it should be cheap, + * so we just do it. + */ + if (destAvailable) { + tmpBuf = realloc(destBuffer->dest, destOffset); + if (NULL == tmpBuf) { + state->error = WorkerError_memory; + return; + } + + destBuffer->dest = tmpBuf; + destBuffer->destSize = destOffset; + } + + /* Truncate segments buffer. */ + tmpBuf = realloc(destBuffer->segments, + (frameIndex - currentBufferStartIndex) * sizeof(BufferSegment)); + if (NULL == tmpBuf) { + state->error = WorkerError_memory; + return; + } + + destBuffer->segments = tmpBuf; + destBuffer->segmentsSize = frameIndex - currentBufferStartIndex; + + /* Grow space for new DestBuffer. */ + tmpBuf = realloc(state->destBuffers, (state->destCount + 1) * sizeof(DestBuffer)); + if (NULL == tmpBuf) { + state->error = WorkerError_memory; + return; + } + + state->destBuffers = tmpBuf; + state->destCount++; + + destBuffer = &state->destBuffers[state->destCount - 1]; + + /* Don't take any chances will non-NULL pointers. */ + memset(destBuffer, 0, sizeof(DestBuffer)); + + allocationSize = roundpow2(state->totalSourceSize); + + if (decompressedSize > allocationSize) { + allocationSize = roundpow2(decompressedSize); + } + + destBuffer->dest = malloc(allocationSize); + if (NULL == destBuffer->dest) { + state->error = WorkerError_memory; + return; + } + + destBuffer->destSize = allocationSize; + destAvailable = allocationSize; + destOffset = 0; + localOffset = 0; + + destBuffer->segments = calloc(remainingItems, sizeof(BufferSegment)); + if (NULL == destBuffer->segments) { + state->error = WorkerError_memory; + return; + } + + destBuffer->segmentsSize = remainingItems; + currentBufferStartIndex = frameIndex; + } + + dest = (char*)destBuffer->dest + destOffset; + + if (state->ddict) { + zresult = ZSTD_decompress_usingDDict(state->dctx, dest, decompressedSize, + source, sourceSize, state->ddict); + } + else { + zresult = ZSTD_decompressDCtx(state->dctx, dest, decompressedSize, + source, sourceSize); + } + + if (ZSTD_isError(zresult)) { + state->error = WorkerError_zstd; + state->zresult = zresult; + state->errorOffset = frameIndex; + return; + } + else if (zresult != decompressedSize) { + state->error = WorkerError_sizeMismatch; + state->zresult = zresult; + state->errorOffset = frameIndex; + return; + } + + destBuffer->segments[localOffset].offset = destOffset; + destBuffer->segments[localOffset].length = decompressedSize; + destOffset += zresult; + localOffset++; + remainingItems--; + } + + if (destBuffer->destSize > destOffset) { + tmpBuf = realloc(destBuffer->dest, destOffset); + if (NULL == tmpBuf) { + state->error = WorkerError_memory; + return; + } + + destBuffer->dest = tmpBuf; + destBuffer->destSize = destOffset; + } +} + +ZstdBufferWithSegmentsCollection* decompress_from_framesources(ZstdDecompressor* decompressor, FrameSources* frames, + unsigned int threadCount) { + void* dictData = NULL; + size_t dictSize = 0; + Py_ssize_t i = 0; + int errored = 0; + Py_ssize_t segmentsCount; + ZstdBufferWithSegments* bws = NULL; + PyObject* resultArg = NULL; + Py_ssize_t resultIndex; + ZstdBufferWithSegmentsCollection* result = NULL; + FramePointer* framePointers = frames->frames; + unsigned long long workerBytes = 0; + int currentThread = 0; + Py_ssize_t workerStartOffset = 0; + POOL_ctx* pool = NULL; + WorkerState* workerStates = NULL; + unsigned long long bytesPerWorker; + + /* Caller should normalize 0 and negative values to 1 or larger. */ + assert(threadCount >= 1); + + /* More threads than inputs makes no sense under any conditions. */ + threadCount = frames->framesSize < threadCount ? (unsigned int)frames->framesSize + : threadCount; + + /* TODO lower thread count if input size is too small and threads would just + add overhead. */ + + if (decompressor->dict) { + dictData = decompressor->dict->dictData; + dictSize = decompressor->dict->dictSize; + } + + if (dictData && !decompressor->ddict) { + Py_BEGIN_ALLOW_THREADS + decompressor->ddict = ZSTD_createDDict_byReference(dictData, dictSize); + Py_END_ALLOW_THREADS + + if (!decompressor->ddict) { + PyErr_SetString(ZstdError, "could not create decompression dict"); + return NULL; + } + } + + /* If threadCount==1, we don't start a thread pool. But we do leverage the + same API for dispatching work. */ + workerStates = PyMem_Malloc(threadCount * sizeof(WorkerState)); + if (NULL == workerStates) { + PyErr_NoMemory(); + goto finally; + } + + memset(workerStates, 0, threadCount * sizeof(WorkerState)); + + if (threadCount > 1) { + pool = POOL_create(threadCount, 1); + if (NULL == pool) { + PyErr_SetString(ZstdError, "could not initialize zstd thread pool"); + goto finally; + } + } + + bytesPerWorker = frames->compressedSize / threadCount; + + for (i = 0; i < threadCount; i++) { + workerStates[i].dctx = ZSTD_createDCtx(); + if (NULL == workerStates[i].dctx) { + PyErr_NoMemory(); + goto finally; + } + + ZSTD_copyDCtx(workerStates[i].dctx, decompressor->dctx); + + workerStates[i].ddict = decompressor->ddict; + workerStates[i].framePointers = framePointers; + workerStates[i].requireOutputSizes = 1; + } + + Py_BEGIN_ALLOW_THREADS + /* There are many ways to split work among workers. + + For now, we take a simple approach of splitting work so each worker + gets roughly the same number of input bytes. This will result in more + starvation than running N>threadCount jobs. But it avoids complications + around state tracking, which could involve extra locking. + */ + for (i = 0; i < frames->framesSize; i++) { + workerBytes += frames->frames[i].sourceSize; + + /* + * The last worker/thread needs to handle all remaining work. Don't + * trigger it prematurely. Defer to the block outside of the loop. + * (But still process this loop so workerBytes is correct. + */ + if (currentThread == threadCount - 1) { + continue; + } + + if (workerBytes >= bytesPerWorker) { + workerStates[currentThread].startOffset = workerStartOffset; + workerStates[currentThread].endOffset = i; + workerStates[currentThread].totalSourceSize = workerBytes; + + if (threadCount > 1) { + POOL_add(pool, (POOL_function)decompress_worker, &workerStates[currentThread]); + } + else { + decompress_worker(&workerStates[currentThread]); + } + currentThread++; + workerStartOffset = i + 1; + workerBytes = 0; + } + } + + if (workerBytes) { + workerStates[currentThread].startOffset = workerStartOffset; + workerStates[currentThread].endOffset = frames->framesSize - 1; + workerStates[currentThread].totalSourceSize = workerBytes; + + if (threadCount > 1) { + POOL_add(pool, (POOL_function)decompress_worker, &workerStates[currentThread]); + } + else { + decompress_worker(&workerStates[currentThread]); + } + } + + if (threadCount > 1) { + POOL_free(pool); + pool = NULL; + } + Py_END_ALLOW_THREADS + + for (i = 0; i < threadCount; i++) { + switch (workerStates[i].error) { + case WorkerError_none: + break; + + case WorkerError_zstd: + PyErr_Format(ZstdError, "error decompressing item %zd: %s", + workerStates[i].errorOffset, ZSTD_getErrorName(workerStates[i].zresult)); + errored = 1; + break; + + case WorkerError_memory: + PyErr_NoMemory(); + errored = 1; + break; + + case WorkerError_sizeMismatch: + PyErr_Format(ZstdError, "error decompressing item %zd: decompressed %zu bytes; expected %llu", + workerStates[i].errorOffset, workerStates[i].zresult, + framePointers[workerStates[i].errorOffset].destSize); + errored = 1; + break; + + case WorkerError_unknownSize: + PyErr_Format(PyExc_ValueError, "could not determine decompressed size of item %zd", + workerStates[i].errorOffset); + errored = 1; + break; + + default: + PyErr_Format(ZstdError, "unhandled error type: %d; this is a bug", + workerStates[i].error); + errored = 1; + break; + } + + if (errored) { + break; + } + } + + if (errored) { + goto finally; + } + + segmentsCount = 0; + for (i = 0; i < threadCount; i++) { + segmentsCount += workerStates[i].destCount; + } + + resultArg = PyTuple_New(segmentsCount); + if (NULL == resultArg) { + goto finally; + } + + resultIndex = 0; + + for (i = 0; i < threadCount; i++) { + Py_ssize_t bufferIndex; + WorkerState* state = &workerStates[i]; + + for (bufferIndex = 0; bufferIndex < state->destCount; bufferIndex++) { + DestBuffer* destBuffer = &state->destBuffers[bufferIndex]; + + bws = BufferWithSegments_FromMemory(destBuffer->dest, destBuffer->destSize, + destBuffer->segments, destBuffer->segmentsSize); + if (NULL == bws) { + goto finally; + } + + /* + * Memory for buffer and segments was allocated using malloc() in worker + * and the memory is transferred to the BufferWithSegments instance. So + * tell instance to use free() and NULL the reference in the state struct + * so it isn't freed below. + */ + bws->useFree = 1; + destBuffer->dest = NULL; + destBuffer->segments = NULL; + + PyTuple_SET_ITEM(resultArg, resultIndex++, (PyObject*)bws); + } + } + + result = (ZstdBufferWithSegmentsCollection*)PyObject_CallObject( + (PyObject*)&ZstdBufferWithSegmentsCollectionType, resultArg); + +finally: + Py_CLEAR(resultArg); + + if (workerStates) { + for (i = 0; i < threadCount; i++) { + Py_ssize_t bufferIndex; + WorkerState* state = &workerStates[i]; + + if (state->dctx) { + ZSTD_freeDCtx(state->dctx); + } + + for (bufferIndex = 0; bufferIndex < state->destCount; bufferIndex++) { + if (state->destBuffers) { + /* + * Will be NULL if memory transfered to a BufferWithSegments. + * Otherwise it is left over after an error occurred. + */ + free(state->destBuffers[bufferIndex].dest); + free(state->destBuffers[bufferIndex].segments); + } + } + + free(state->destBuffers); + } + + PyMem_Free(workerStates); + } + + POOL_free(pool); + + return result; +} + +PyDoc_STRVAR(Decompressor_multi_decompress_to_buffer__doc__, +"Decompress multiple frames to output buffers\n" +"\n" +"Receives a ``BufferWithSegments``, a ``BufferWithSegmentsCollection`` or a\n" +"list of bytes-like objects. Each item in the passed collection should be a\n" +"compressed zstd frame.\n" +"\n" +"Unless ``decompressed_sizes`` is specified, the content size *must* be\n" +"written into the zstd frame header. If ``decompressed_sizes`` is specified,\n" +"it is an object conforming to the buffer protocol that represents an array\n" +"of 64-bit unsigned integers in the machine's native format. Specifying\n" +"``decompressed_sizes`` avoids a pre-scan of each frame to determine its\n" +"output size.\n" +"\n" +"Returns a ``BufferWithSegmentsCollection`` containing the decompressed\n" +"data. All decompressed data is allocated in a single memory buffer. The\n" +"``BufferWithSegments`` instance tracks which objects are at which offsets\n" +"and their respective lengths.\n" +"\n" +"The ``threads`` argument controls how many threads to use for operations.\n" +"Negative values will use the same number of threads as logical CPUs on the\n" +"machine.\n" +); + +static ZstdBufferWithSegmentsCollection* Decompressor_multi_decompress_to_buffer(ZstdDecompressor* self, PyObject* args, PyObject* kwargs) { + static char* kwlist[] = { + "frames", + "decompressed_sizes", + "threads", + NULL + }; + + PyObject* frames; + Py_buffer frameSizes; + int threads = 0; + Py_ssize_t frameCount; + Py_buffer* frameBuffers = NULL; + FramePointer* framePointers = NULL; + unsigned long long* frameSizesP = NULL; + unsigned long long totalInputSize = 0; + FrameSources frameSources; + ZstdBufferWithSegmentsCollection* result = NULL; + Py_ssize_t i; + + memset(&frameSizes, 0, sizeof(frameSizes)); + +#if PY_MAJOR_VERSION >= 3 + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "O|y*i:multi_decompress_to_buffer", +#else + if (!PyArg_ParseTupleAndKeywords(args, kwargs, "O|s*i:multi_decompress_to_buffer", +#endif + kwlist, &frames, &frameSizes, &threads)) { + return NULL; + } + + if (frameSizes.buf) { + if (!PyBuffer_IsContiguous(&frameSizes, 'C') || frameSizes.ndim > 1) { + PyErr_SetString(PyExc_ValueError, "decompressed_sizes buffer should be contiguous and have a single dimension"); + goto finally; + } + + frameSizesP = (unsigned long long*)frameSizes.buf; + } + + if (threads < 0) { + threads = cpu_count(); + } + + if (threads < 2) { + threads = 1; + } + + if (PyObject_TypeCheck(frames, &ZstdBufferWithSegmentsType)) { + ZstdBufferWithSegments* buffer = (ZstdBufferWithSegments*)frames; + frameCount = buffer->segmentCount; + + if (frameSizes.buf && frameSizes.len != frameCount * (Py_ssize_t)sizeof(unsigned long long)) { + PyErr_Format(PyExc_ValueError, "decompressed_sizes size mismatch; expected %zd, got %zd", + frameCount * sizeof(unsigned long long), frameSizes.len); + goto finally; + } + + framePointers = PyMem_Malloc(frameCount * sizeof(FramePointer)); + if (!framePointers) { + PyErr_NoMemory(); + goto finally; + } + + for (i = 0; i < frameCount; i++) { + void* sourceData; + unsigned long long sourceSize; + unsigned long long decompressedSize = 0; + + if (buffer->segments[i].offset + buffer->segments[i].length > buffer->dataSize) { + PyErr_Format(PyExc_ValueError, "item %zd has offset outside memory area", i); + goto finally; + } + + sourceData = (char*)buffer->data + buffer->segments[i].offset; + sourceSize = buffer->segments[i].length; + totalInputSize += sourceSize; + + if (frameSizesP) { + decompressedSize = frameSizesP[i]; + } + + framePointers[i].sourceData = sourceData; + framePointers[i].sourceSize = sourceSize; + framePointers[i].destSize = decompressedSize; + } + } + else if (PyObject_TypeCheck(frames, &ZstdBufferWithSegmentsCollectionType)) { + Py_ssize_t offset = 0; + ZstdBufferWithSegments* buffer; + ZstdBufferWithSegmentsCollection* collection = (ZstdBufferWithSegmentsCollection*)frames; + + frameCount = BufferWithSegmentsCollection_length(collection); + + if (frameSizes.buf && frameSizes.len != frameCount) { + PyErr_Format(PyExc_ValueError, + "decompressed_sizes size mismatch; expected %zd; got %zd", + frameCount * sizeof(unsigned long long), frameSizes.len); + goto finally; + } + + framePointers = PyMem_Malloc(frameCount * sizeof(FramePointer)); + if (NULL == framePointers) { + PyErr_NoMemory(); + goto finally; + } + + /* Iterate the data structure directly because it is faster. */ + for (i = 0; i < collection->bufferCount; i++) { + Py_ssize_t segmentIndex; + buffer = collection->buffers[i]; + + for (segmentIndex = 0; segmentIndex < buffer->segmentCount; segmentIndex++) { + if (buffer->segments[segmentIndex].offset + buffer->segments[segmentIndex].length > buffer->dataSize) { + PyErr_Format(PyExc_ValueError, "item %zd has offset outside memory area", + offset); + goto finally; + } + + totalInputSize += buffer->segments[segmentIndex].length; + + framePointers[offset].sourceData = (char*)buffer->data + buffer->segments[segmentIndex].offset; + framePointers[offset].sourceSize = buffer->segments[segmentIndex].length; + framePointers[offset].destSize = frameSizesP ? frameSizesP[offset] : 0; + + offset++; + } + } + } + else if (PyList_Check(frames)) { + frameCount = PyList_GET_SIZE(frames); + + if (frameSizes.buf && frameSizes.len != frameCount * (Py_ssize_t)sizeof(unsigned long long)) { + PyErr_Format(PyExc_ValueError, "decompressed_sizes size mismatch; expected %zd, got %zd", + frameCount * sizeof(unsigned long long), frameSizes.len); + goto finally; + } + + framePointers = PyMem_Malloc(frameCount * sizeof(FramePointer)); + if (!framePointers) { + PyErr_NoMemory(); + goto finally; + } + + /* + * It is not clear whether Py_buffer.buf is still valid after + * PyBuffer_Release. So, we hold a reference to all Py_buffer instances + * for the duration of the operation. + */ + frameBuffers = PyMem_Malloc(frameCount * sizeof(Py_buffer)); + if (NULL == frameBuffers) { + PyErr_NoMemory(); + goto finally; + } + + memset(frameBuffers, 0, frameCount * sizeof(Py_buffer)); + + /* Do a pass to assemble info about our input buffers and output sizes. */ + for (i = 0; i < frameCount; i++) { + if (0 != PyObject_GetBuffer(PyList_GET_ITEM(frames, i), + &frameBuffers[i], PyBUF_CONTIG_RO)) { + PyErr_Clear(); + PyErr_Format(PyExc_TypeError, "item %zd not a bytes like object", i); + goto finally; + } + + totalInputSize += frameBuffers[i].len; + + framePointers[i].sourceData = frameBuffers[i].buf; + framePointers[i].sourceSize = frameBuffers[i].len; + framePointers[i].destSize = frameSizesP ? frameSizesP[i] : 0; + } + } + else { + PyErr_SetString(PyExc_TypeError, "argument must be list or BufferWithSegments"); + goto finally; + } + + /* We now have an array with info about our inputs and outputs. Feed it into + our generic decompression function. */ + frameSources.frames = framePointers; + frameSources.framesSize = frameCount; + frameSources.compressedSize = totalInputSize; + + result = decompress_from_framesources(self, &frameSources, threads); + +finally: + if (frameSizes.buf) { + PyBuffer_Release(&frameSizes); + } + PyMem_Free(framePointers); + + if (frameBuffers) { + for (i = 0; i < frameCount; i++) { + PyBuffer_Release(&frameBuffers[i]); + } + + PyMem_Free(frameBuffers); + } return result; } @@ -616,6 +1520,10 @@ Decompressor_read_from__doc__ }, { "write_to", (PyCFunction)Decompressor_write_to, METH_VARARGS | METH_KEYWORDS, Decompressor_write_to__doc__ }, + { "decompress_content_dict_chain", (PyCFunction)Decompressor_decompress_content_dict_chain, + METH_VARARGS | METH_KEYWORDS, Decompressor_decompress_content_dict_chain__doc__ }, + { "multi_decompress_to_buffer", (PyCFunction)Decompressor_multi_decompress_to_buffer, + METH_VARARGS | METH_KEYWORDS, Decompressor_multi_decompress_to_buffer__doc__ }, { NULL, NULL } };
--- a/contrib/python-zstandard/c-ext/decompressoriterator.c Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/python-zstandard/c-ext/decompressoriterator.c Tue Apr 18 12:24:34 2017 -0400 @@ -26,11 +26,6 @@ self->buffer = NULL; } - if (self->dstream) { - ZSTD_freeDStream(self->dstream); - self->dstream = NULL; - } - if (self->input.src) { PyMem_Free((void*)self->input.src); self->input.src = NULL; @@ -50,6 +45,8 @@ DecompressorIteratorResult result; size_t oldInputPos = self->input.pos; + assert(self->decompressor->dstream); + result.chunk = NULL; chunk = PyBytes_FromStringAndSize(NULL, self->outSize); @@ -63,7 +60,7 @@ self->output.pos = 0; Py_BEGIN_ALLOW_THREADS - zresult = ZSTD_decompressStream(self->dstream, &self->output, &self->input); + zresult = ZSTD_decompressStream(self->decompressor->dstream, &self->output, &self->input); Py_END_ALLOW_THREADS /* We're done with the pointer. Nullify to prevent anyone from getting a @@ -160,7 +157,7 @@ PyErr_SetString(PyExc_ValueError, "skip_bytes larger than first input chunk; " "this scenario is currently unsupported"); - Py_DecRef(readResult); + Py_XDECREF(readResult); return NULL; } @@ -179,7 +176,7 @@ else if (!self->readCount) { self->finishedInput = 1; self->finishedOutput = 1; - Py_DecRef(readResult); + Py_XDECREF(readResult); PyErr_SetString(PyExc_StopIteration, "empty input"); return NULL; } @@ -188,7 +185,7 @@ } /* We've copied the data managed by memory. Discard the Python object. */ - Py_DecRef(readResult); + Py_XDECREF(readResult); } result = read_decompressor_iterator(self);
--- a/contrib/python-zstandard/c-ext/dictparams.c Tue Apr 18 11:22:42 2017 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,125 +0,0 @@ -/** -* Copyright (c) 2016-present, Gregory Szorc -* All rights reserved. -* -* This software may be modified and distributed under the terms -* of the BSD license. See the LICENSE file for details. -*/ - -#include "python-zstandard.h" - -PyDoc_STRVAR(DictParameters__doc__, -"DictParameters: low-level control over dictionary generation"); - -static PyObject* DictParameters_new(PyTypeObject* subtype, PyObject* args, PyObject* kwargs) { - DictParametersObject* self; - unsigned selectivityLevel; - int compressionLevel; - unsigned notificationLevel; - unsigned dictID; - - if (!PyArg_ParseTuple(args, "IiII", &selectivityLevel, &compressionLevel, - ¬ificationLevel, &dictID)) { - return NULL; - } - - self = (DictParametersObject*)subtype->tp_alloc(subtype, 1); - if (!self) { - return NULL; - } - - self->selectivityLevel = selectivityLevel; - self->compressionLevel = compressionLevel; - self->notificationLevel = notificationLevel; - self->dictID = dictID; - - return (PyObject*)self; -} - -static void DictParameters_dealloc(PyObject* self) { - PyObject_Del(self); -} - -static Py_ssize_t DictParameters_length(PyObject* self) { - return 4; -} - -static PyObject* DictParameters_item(PyObject* o, Py_ssize_t i) { - DictParametersObject* self = (DictParametersObject*)o; - - switch (i) { - case 0: - return PyLong_FromLong(self->selectivityLevel); - case 1: - return PyLong_FromLong(self->compressionLevel); - case 2: - return PyLong_FromLong(self->notificationLevel); - case 3: - return PyLong_FromLong(self->dictID); - default: - PyErr_SetString(PyExc_IndexError, "index out of range"); - return NULL; - } -} - -static PySequenceMethods DictParameters_sq = { - DictParameters_length, /* sq_length */ - 0, /* sq_concat */ - 0, /* sq_repeat */ - DictParameters_item, /* sq_item */ - 0, /* sq_ass_item */ - 0, /* sq_contains */ - 0, /* sq_inplace_concat */ - 0 /* sq_inplace_repeat */ -}; - -PyTypeObject DictParametersType = { - PyVarObject_HEAD_INIT(NULL, 0) - "DictParameters", /* tp_name */ - sizeof(DictParametersObject), /* tp_basicsize */ - 0, /* tp_itemsize */ - (destructor)DictParameters_dealloc, /* tp_dealloc */ - 0, /* tp_print */ - 0, /* tp_getattr */ - 0, /* tp_setattr */ - 0, /* tp_compare */ - 0, /* tp_repr */ - 0, /* tp_as_number */ - &DictParameters_sq, /* tp_as_sequence */ - 0, /* tp_as_mapping */ - 0, /* tp_hash */ - 0, /* tp_call */ - 0, /* tp_str */ - 0, /* tp_getattro */ - 0, /* tp_setattro */ - 0, /* tp_as_buffer */ - Py_TPFLAGS_DEFAULT, /* tp_flags */ - DictParameters__doc__, /* tp_doc */ - 0, /* tp_traverse */ - 0, /* tp_clear */ - 0, /* tp_richcompare */ - 0, /* tp_weaklistoffset */ - 0, /* tp_iter */ - 0, /* tp_iternext */ - 0, /* tp_methods */ - 0, /* tp_members */ - 0, /* tp_getset */ - 0, /* tp_base */ - 0, /* tp_dict */ - 0, /* tp_descr_get */ - 0, /* tp_descr_set */ - 0, /* tp_dictoffset */ - 0, /* tp_init */ - 0, /* tp_alloc */ - DictParameters_new, /* tp_new */ -}; - -void dictparams_module_init(PyObject* mod) { - Py_TYPE(&DictParametersType) = &PyType_Type; - if (PyType_Ready(&DictParametersType) < 0) { - return; - } - - Py_IncRef((PyObject*)&DictParametersType); - PyModule_AddObject(mod, "DictParameters", (PyObject*)&DictParametersType); -}
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/contrib/python-zstandard/c-ext/frameparams.c Tue Apr 18 12:24:34 2017 -0400 @@ -0,0 +1,132 @@ +/** +* Copyright (c) 2017-present, Gregory Szorc +* All rights reserved. +* +* This software may be modified and distributed under the terms +* of the BSD license. See the LICENSE file for details. +*/ + +#include "python-zstandard.h" + +extern PyObject* ZstdError; + +PyDoc_STRVAR(FrameParameters__doc__, + "FrameParameters: information about a zstd frame"); + +FrameParametersObject* get_frame_parameters(PyObject* self, PyObject* args) { + const char* source; + Py_ssize_t sourceSize; + ZSTD_frameParams params; + FrameParametersObject* result = NULL; + size_t zresult; + +#if PY_MAJOR_VERSION >= 3 + if (!PyArg_ParseTuple(args, "y#:get_frame_parameters", +#else + if (!PyArg_ParseTuple(args, "s#:get_frame_parameters", +#endif + &source, &sourceSize)) { + return NULL; + } + + /* Needed for Python 2 to reject unicode */ + if (!PyBytes_Check(PyTuple_GET_ITEM(args, 0))) { + PyErr_SetString(PyExc_TypeError, "argument must be bytes"); + return NULL; + } + + zresult = ZSTD_getFrameParams(¶ms, (void*)source, sourceSize); + + if (ZSTD_isError(zresult)) { + PyErr_Format(ZstdError, "cannot get frame parameters: %s", ZSTD_getErrorName(zresult)); + return NULL; + } + + if (zresult) { + PyErr_Format(ZstdError, "not enough data for frame parameters; need %zu bytes", zresult); + return NULL; + } + + result = PyObject_New(FrameParametersObject, &FrameParametersType); + if (!result) { + return NULL; + } + + result->frameContentSize = params.frameContentSize; + result->windowSize = params.windowSize; + result->dictID = params.dictID; + result->checksumFlag = params.checksumFlag ? 1 : 0; + + return result; +} + +static void FrameParameters_dealloc(PyObject* self) { + PyObject_Del(self); +} + +static PyMemberDef FrameParameters_members[] = { + { "content_size", T_ULONGLONG, + offsetof(FrameParametersObject, frameContentSize), READONLY, + "frame content size" }, + { "window_size", T_UINT, + offsetof(FrameParametersObject, windowSize), READONLY, + "window size" }, + { "dict_id", T_UINT, + offsetof(FrameParametersObject, dictID), READONLY, + "dictionary ID" }, + { "has_checksum", T_BOOL, + offsetof(FrameParametersObject, checksumFlag), READONLY, + "checksum flag" }, + { NULL } +}; + +PyTypeObject FrameParametersType = { + PyVarObject_HEAD_INIT(NULL, 0) + "FrameParameters", /* tp_name */ + sizeof(FrameParametersObject), /* tp_basicsize */ + 0, /* tp_itemsize */ + (destructor)FrameParameters_dealloc, /* tp_dealloc */ + 0, /* tp_print */ + 0, /* tp_getattr */ + 0, /* tp_setattr */ + 0, /* tp_compare */ + 0, /* tp_repr */ + 0, /* tp_as_number */ + 0, /* tp_as_sequence */ + 0, /* tp_as_mapping */ + 0, /* tp_hash */ + 0, /* tp_call */ + 0, /* tp_str */ + 0, /* tp_getattro */ + 0, /* tp_setattro */ + 0, /* tp_as_buffer */ + Py_TPFLAGS_DEFAULT, /* tp_flags */ + FrameParameters__doc__, /* tp_doc */ + 0, /* tp_traverse */ + 0, /* tp_clear */ + 0, /* tp_richcompare */ + 0, /* tp_weaklistoffset */ + 0, /* tp_iter */ + 0, /* tp_iternext */ + 0, /* tp_methods */ + FrameParameters_members, /* tp_members */ + 0, /* tp_getset */ + 0, /* tp_base */ + 0, /* tp_dict */ + 0, /* tp_descr_get */ + 0, /* tp_descr_set */ + 0, /* tp_dictoffset */ + 0, /* tp_init */ + 0, /* tp_alloc */ + 0, /* tp_new */ +}; + +void frameparams_module_init(PyObject* mod) { + Py_TYPE(&FrameParametersType) = &PyType_Type; + if (PyType_Ready(&FrameParametersType) < 0) { + return; + } + + Py_INCREF(&FrameParametersType); + PyModule_AddObject(mod, "FrameParameters", (PyObject*)&FrameParametersType); +}
--- a/contrib/python-zstandard/c-ext/python-zstandard.h Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/python-zstandard/c-ext/python-zstandard.h Tue Apr 18 12:24:34 2017 -0400 @@ -8,20 +8,27 @@ #define PY_SSIZE_T_CLEAN #include <Python.h> +#include "structmember.h" #define ZSTD_STATIC_LINKING_ONLY #define ZDICT_STATIC_LINKING_ONLY #include "mem.h" #include "zstd.h" #include "zdict.h" +#include "zstdmt_compress.h" -#define PYTHON_ZSTANDARD_VERSION "0.6.0" +#define PYTHON_ZSTANDARD_VERSION "0.8.1" typedef enum { compressorobj_flush_finish, compressorobj_flush_block, } CompressorObj_Flush; +/* + Represents a CompressionParameters type. + + This type is basically a wrapper around ZSTD_compressionParameters. +*/ typedef struct { PyObject_HEAD unsigned windowLog; @@ -35,34 +42,70 @@ extern PyTypeObject CompressionParametersType; +/* + Represents a FrameParameters type. + + This type is basically a wrapper around ZSTD_frameParams. +*/ typedef struct { PyObject_HEAD - unsigned selectivityLevel; - int compressionLevel; - unsigned notificationLevel; + unsigned long long frameContentSize; + unsigned windowSize; unsigned dictID; -} DictParametersObject; + char checksumFlag; +} FrameParametersObject; + +extern PyTypeObject FrameParametersType; -extern PyTypeObject DictParametersType; +/* + Represents a ZstdCompressionDict type. + Instances hold data used for a zstd compression dictionary. +*/ typedef struct { PyObject_HEAD + /* Pointer to dictionary data. Owned by self. */ void* dictData; + /* Size of dictionary data. */ size_t dictSize; + /* k parameter for cover dictionaries. Only populated by train_cover_dict(). */ + unsigned k; + /* d parameter for cover dictionaries. Only populated by train_cover_dict(). */ + unsigned d; } ZstdCompressionDict; extern PyTypeObject ZstdCompressionDictType; +/* + Represents a ZstdCompressor type. +*/ typedef struct { PyObject_HEAD + /* Configured compression level. Should be always set. */ int compressionLevel; + /* Number of threads to use for operations. */ + unsigned int threads; + /* Pointer to compression dictionary to use. NULL if not using dictionary + compression. */ ZstdCompressionDict* dict; + /* Compression context to use. Populated during object construction. NULL + if using multi-threaded compression. */ ZSTD_CCtx* cctx; + /* Multi-threaded compression context to use. Populated during object + construction. NULL if not using multi-threaded compression. */ + ZSTDMT_CCtx* mtcctx; + /* Digest compression dictionary. NULL initially. Populated on first use. */ ZSTD_CDict* cdict; + /* Low-level compression parameter control. NULL unless passed to + constructor. Takes precedence over `compressionLevel` if defined. */ CompressionParametersObject* cparams; + /* Controls zstd frame options. */ ZSTD_frameParameters fparams; + /* Holds state for streaming compression. Shared across all invocation. + Populated on first use. */ + ZSTD_CStream* cstream; } ZstdCompressor; extern PyTypeObject ZstdCompressorType; @@ -71,7 +114,6 @@ PyObject_HEAD ZstdCompressor* compressor; - ZSTD_CStream* cstream; ZSTD_outBuffer output; int finished; } ZstdCompressionObj; @@ -85,7 +127,6 @@ PyObject* writer; Py_ssize_t sourceSize; size_t outSize; - ZSTD_CStream* cstream; int entered; } ZstdCompressionWriter; @@ -102,7 +143,6 @@ size_t inSize; size_t outSize; - ZSTD_CStream* cstream; ZSTD_inBuffer input; ZSTD_outBuffer output; int finishedOutput; @@ -115,10 +155,11 @@ typedef struct { PyObject_HEAD - ZSTD_DCtx* refdctx; + ZSTD_DCtx* dctx; ZstdCompressionDict* dict; ZSTD_DDict* ddict; + ZSTD_DStream* dstream; } ZstdDecompressor; extern PyTypeObject ZstdDecompressorType; @@ -127,7 +168,6 @@ PyObject_HEAD ZstdDecompressor* decompressor; - ZSTD_DStream* dstream; int finished; } ZstdDecompressionObj; @@ -139,7 +179,6 @@ ZstdDecompressor* decompressor; PyObject* writer; size_t outSize; - ZSTD_DStream* dstream; int entered; } ZstdDecompressionWriter; @@ -155,7 +194,6 @@ size_t inSize; size_t outSize; size_t skipBytes; - ZSTD_DStream* dstream; ZSTD_inBuffer input; ZSTD_outBuffer output; Py_ssize_t readCount; @@ -170,9 +208,78 @@ PyObject* chunk; } DecompressorIteratorResult; +typedef struct { + unsigned long long offset; + unsigned long long length; +} BufferSegment; + +typedef struct { + PyObject_HEAD + + PyObject* parent; + BufferSegment* segments; + Py_ssize_t segmentCount; +} ZstdBufferSegments; + +extern PyTypeObject ZstdBufferSegmentsType; + +typedef struct { + PyObject_HEAD + + PyObject* parent; + void* data; + Py_ssize_t dataSize; + unsigned long long offset; +} ZstdBufferSegment; + +extern PyTypeObject ZstdBufferSegmentType; + +typedef struct { + PyObject_HEAD + + Py_buffer parent; + void* data; + unsigned long long dataSize; + BufferSegment* segments; + Py_ssize_t segmentCount; + int useFree; +} ZstdBufferWithSegments; + +extern PyTypeObject ZstdBufferWithSegmentsType; + +/** + * An ordered collection of BufferWithSegments exposed as a squashed collection. + * + * This type provides a virtual view spanning multiple BufferWithSegments + * instances. It allows multiple instances to be "chained" together and + * exposed as a single collection. e.g. if there are 2 buffers holding + * 10 segments each, then o[14] will access the 5th segment in the 2nd buffer. + */ +typedef struct { + PyObject_HEAD + + /* An array of buffers that should be exposed through this instance. */ + ZstdBufferWithSegments** buffers; + /* Number of elements in buffers array. */ + Py_ssize_t bufferCount; + /* Array of first offset in each buffer instance. 0th entry corresponds + to number of elements in the 0th buffer. 1st entry corresponds to the + sum of elements in 0th and 1st buffers. */ + Py_ssize_t* firstElements; +} ZstdBufferWithSegmentsCollection; + +extern PyTypeObject ZstdBufferWithSegmentsCollectionType; + void ztopy_compression_parameters(CompressionParametersObject* params, ZSTD_compressionParameters* zparams); CompressionParametersObject* get_compression_parameters(PyObject* self, PyObject* args); +FrameParametersObject* get_frame_parameters(PyObject* self, PyObject* args); PyObject* estimate_compression_context_size(PyObject* self, PyObject* args); -ZSTD_CStream* CStream_from_ZstdCompressor(ZstdCompressor* compressor, Py_ssize_t sourceSize); -ZSTD_DStream* DStream_from_ZstdDecompressor(ZstdDecompressor* decompressor); +int init_cstream(ZstdCompressor* compressor, unsigned long long sourceSize); +int init_mtcstream(ZstdCompressor* compressor, Py_ssize_t sourceSize); +int init_dstream(ZstdDecompressor* decompressor); ZstdCompressionDict* train_dictionary(PyObject* self, PyObject* args, PyObject* kwargs); +ZstdCompressionDict* train_cover_dictionary(PyObject* self, PyObject* args, PyObject* kwargs); +ZstdBufferWithSegments* BufferWithSegments_FromMemory(void* data, unsigned long long dataSize, BufferSegment* segments, Py_ssize_t segmentsSize); +Py_ssize_t BufferWithSegmentsCollection_length(ZstdBufferWithSegmentsCollection*); +int cpu_count(void); +size_t roundpow2(size_t);
--- a/contrib/python-zstandard/make_cffi.py Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/python-zstandard/make_cffi.py Tue Apr 18 12:24:34 2017 -0400 @@ -9,6 +9,7 @@ import cffi import distutils.ccompiler import os +import re import subprocess import tempfile @@ -19,17 +20,28 @@ 'common/entropy_common.c', 'common/error_private.c', 'common/fse_decompress.c', + 'common/pool.c', + 'common/threading.c', 'common/xxhash.c', 'common/zstd_common.c', 'compress/fse_compress.c', 'compress/huf_compress.c', 'compress/zstd_compress.c', + 'compress/zstdmt_compress.c', 'decompress/huf_decompress.c', 'decompress/zstd_decompress.c', + 'dictBuilder/cover.c', 'dictBuilder/divsufsort.c', 'dictBuilder/zdict.c', )] +# Headers whose preprocessed output will be fed into cdef(). +HEADERS = [os.path.join(HERE, 'zstd', *p) for p in ( + ('zstd.h',), + ('compress', 'zstdmt_compress.h'), + ('dictBuilder', 'zdict.h'), +)] + INCLUDE_DIRS = [os.path.join(HERE, d) for d in ( 'zstd', 'zstd/common', @@ -53,56 +65,123 @@ args.extend([ '-E', '-DZSTD_STATIC_LINKING_ONLY', + '-DZDICT_STATIC_LINKING_ONLY', ]) elif compiler.compiler_type == 'msvc': args = [compiler.cc] args.extend([ '/EP', '/DZSTD_STATIC_LINKING_ONLY', + '/DZDICT_STATIC_LINKING_ONLY', ]) else: raise Exception('unsupported compiler type: %s' % compiler.compiler_type) -# zstd.h includes <stddef.h>, which is also included by cffi's boilerplate. -# This can lead to duplicate declarations. So we strip this include from the -# preprocessor invocation. - -with open(os.path.join(HERE, 'zstd', 'zstd.h'), 'rb') as fh: - lines = [l for l in fh if not l.startswith(b'#include <stddef.h>')] - -fd, input_file = tempfile.mkstemp(suffix='.h') -os.write(fd, b''.join(lines)) -os.close(fd) +def preprocess(path): + with open(path, 'rb') as fh: + lines = [] + for l in fh: + # zstd.h includes <stddef.h>, which is also included by cffi's + # boilerplate. This can lead to duplicate declarations. So we strip + # this include from the preprocessor invocation. + # + # The same things happens for including zstd.h, so give it the same + # treatment. + # + # We define ZSTD_STATIC_LINKING_ONLY, which is redundant with the inline + # #define in zstdmt_compress.h and results in a compiler warning. So drop + # the inline #define. + if l.startswith((b'#include <stddef.h>', + b'#include "zstd.h"', + b'#define ZSTD_STATIC_LINKING_ONLY')): + continue -args.append(input_file) + # ZSTDLIB_API may not be defined if we dropped zstd.h. It isn't + # important so just filter it out. + if l.startswith(b'ZSTDLIB_API'): + l = l[len(b'ZSTDLIB_API '):] + + lines.append(l) + + fd, input_file = tempfile.mkstemp(suffix='.h') + os.write(fd, b''.join(lines)) + os.close(fd) -try: - process = subprocess.Popen(args, stdout=subprocess.PIPE) - output = process.communicate()[0] - ret = process.poll() - if ret: - raise Exception('preprocessor exited with error') -finally: - os.unlink(input_file) + try: + process = subprocess.Popen(args + [input_file], stdout=subprocess.PIPE) + output = process.communicate()[0] + ret = process.poll() + if ret: + raise Exception('preprocessor exited with error') -def normalize_output(): + return output + finally: + os.unlink(input_file) + + +def normalize_output(output): lines = [] for line in output.splitlines(): # CFFI's parser doesn't like __attribute__ on UNIX compilers. if line.startswith(b'__attribute__ ((visibility ("default"))) '): line = line[len(b'__attribute__ ((visibility ("default"))) '):] + if line.startswith(b'__attribute__((deprecated('): + continue + elif b'__declspec(deprecated(' in line: + continue + lines.append(line) return b'\n'.join(lines) + ffi = cffi.FFI() +# *_DISABLE_DEPRECATE_WARNINGS prevents the compiler from emitting a warning +# when cffi uses the function. Since we statically link against zstd, even +# if we use the deprecated functions it shouldn't be a huge problem. ffi.set_source('_zstd_cffi', ''' +#include "mem.h" #define ZSTD_STATIC_LINKING_ONLY #include "zstd.h" +#define ZDICT_STATIC_LINKING_ONLY +#define ZDICT_DISABLE_DEPRECATE_WARNINGS +#include "zdict.h" +#include "zstdmt_compress.h" ''', sources=SOURCES, include_dirs=INCLUDE_DIRS) -ffi.cdef(normalize_output().decode('latin1')) +DEFINE = re.compile(b'^\\#define ([a-zA-Z0-9_]+) ') + +sources = [] + +# Feed normalized preprocessor output for headers into the cdef parser. +for header in HEADERS: + preprocessed = preprocess(header) + sources.append(normalize_output(preprocessed)) + + # #define's are effectively erased as part of going through preprocessor. + # So perform a manual pass to re-add those to the cdef source. + with open(header, 'rb') as fh: + for line in fh: + line = line.strip() + m = DEFINE.match(line) + if not m: + continue + + if m.group(1) == b'ZSTD_STATIC_LINKING_ONLY': + continue + + # The parser doesn't like some constants with complex values. + if m.group(1) in (b'ZSTD_LIB_VERSION', b'ZSTD_VERSION_STRING'): + continue + + # The ... is magic syntax by the cdef parser to resolve the + # value at compile time. + sources.append(m.group(0) + b' ...') + +cdeflines = b'\n'.join(sources).splitlines() +cdeflines = [l for l in cdeflines if l.strip()] +ffi.cdef(b'\n'.join(cdeflines).decode('latin1')) if __name__ == '__main__': ffi.compile()
--- a/contrib/python-zstandard/setup.py Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/python-zstandard/setup.py Tue Apr 18 12:24:34 2017 -0400 @@ -25,10 +25,15 @@ # facilitate reuse in other projects. extensions = [setup_zstd.get_c_extension(SUPPORT_LEGACY, 'zstd')] +install_requires = [] + if cffi: import make_cffi extensions.append(make_cffi.ffi.distutils_extension()) + # Need change in 1.8 for ffi.from_buffer() behavior. + install_requires.append('cffi>=1.8') + version = None with open('c-ext/python-zstandard.h', 'r') as fh: @@ -62,8 +67,10 @@ 'Programming Language :: Python :: 3.3', 'Programming Language :: Python :: 3.4', 'Programming Language :: Python :: 3.5', + 'Programming Language :: Python :: 3.6', ], keywords='zstandard zstd compression', ext_modules=extensions, test_suite='tests', + install_requires=install_requires, )
--- a/contrib/python-zstandard/setup_zstd.py Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/python-zstandard/setup_zstd.py Tue Apr 18 12:24:34 2017 -0400 @@ -12,18 +12,23 @@ 'common/entropy_common.c', 'common/error_private.c', 'common/fse_decompress.c', + 'common/pool.c', + 'common/threading.c', 'common/xxhash.c', 'common/zstd_common.c', 'compress/fse_compress.c', 'compress/huf_compress.c', 'compress/zstd_compress.c', + 'compress/zstdmt_compress.c', 'decompress/huf_decompress.c', 'decompress/zstd_decompress.c', + 'dictBuilder/cover.c', 'dictBuilder/divsufsort.c', 'dictBuilder/zdict.c', )] zstd_sources_legacy = ['zstd/%s' % p for p in ( + 'deprecated/zbuff_common.c', 'deprecated/zbuff_compress.c', 'deprecated/zbuff_decompress.c', 'legacy/zstd_v01.c', @@ -51,6 +56,7 @@ ext_sources = [ 'zstd.c', + 'c-ext/bufferutil.c', 'c-ext/compressiondict.c', 'c-ext/compressobj.c', 'c-ext/compressor.c', @@ -62,7 +68,7 @@ 'c-ext/decompressor.c', 'c-ext/decompressoriterator.c', 'c-ext/decompressionwriter.c', - 'c-ext/dictparams.c', + 'c-ext/frameparams.c', ] zstd_depends = [ @@ -84,8 +90,13 @@ depends = [os.path.join(root, p) for p in zstd_depends] + extra_args = ['-DZSTD_MULTITHREAD'] + + if support_legacy: + extra_args.append('-DZSTD_LEGACY_SUPPORT=1') + # TODO compile with optimizations. return Extension(name, sources, include_dirs=include_dirs, depends=depends, - extra_compile_args=["-DZSTD_LEGACY_SUPPORT=1"] if support_legacy else []) + extra_compile_args=extra_args)
--- a/contrib/python-zstandard/tests/common.py Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/python-zstandard/tests/common.py Tue Apr 18 12:24:34 2017 -0400 @@ -1,4 +1,51 @@ +import inspect import io +import os +import types + + +def make_cffi(cls): + """Decorator to add CFFI versions of each test method.""" + + try: + import zstd_cffi + except ImportError: + return cls + + # If CFFI version is available, dynamically construct test methods + # that use it. + + for attr in dir(cls): + fn = getattr(cls, attr) + if not inspect.ismethod(fn) and not inspect.isfunction(fn): + continue + + if not fn.__name__.startswith('test_'): + continue + + name = '%s_cffi' % fn.__name__ + + # Replace the "zstd" symbol with the CFFI module instance. Then copy + # the function object and install it in a new attribute. + if isinstance(fn, types.FunctionType): + globs = dict(fn.__globals__) + globs['zstd'] = zstd_cffi + new_fn = types.FunctionType(fn.__code__, globs, name, + fn.__defaults__, fn.__closure__) + new_method = new_fn + else: + globs = dict(fn.__func__.func_globals) + globs['zstd'] = zstd_cffi + new_fn = types.FunctionType(fn.__func__.func_code, globs, name, + fn.__func__.func_defaults, + fn.__func__.func_closure) + new_method = types.UnboundMethodType(new_fn, fn.im_self, + fn.im_class) + + setattr(cls, name, new_method) + + return cls + class OpCountingBytesIO(io.BytesIO): def __init__(self, *args, **kwargs): @@ -13,3 +60,29 @@ def write(self, data): self._write_count += 1 return super(OpCountingBytesIO, self).write(data) + + +_source_files = [] + + +def random_input_data(): + """Obtain the raw content of source files. + + This is used for generating "random" data to feed into fuzzing, since it is + faster than random content generation. + """ + if _source_files: + return _source_files + + for root, dirs, files in os.walk(os.path.dirname(__file__)): + dirs[:] = list(sorted(dirs)) + for f in sorted(files): + try: + with open(os.path.join(root, f), 'rb') as fh: + data = fh.read() + if data: + _source_files.append(data) + except OSError: + pass + + return _source_files
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/contrib/python-zstandard/tests/test_buffer_util.py Tue Apr 18 12:24:34 2017 -0400 @@ -0,0 +1,112 @@ +import struct + +try: + import unittest2 as unittest +except ImportError: + import unittest + +import zstd + +ss = struct.Struct('=QQ') + + +class TestBufferWithSegments(unittest.TestCase): + def test_arguments(self): + with self.assertRaises(TypeError): + zstd.BufferWithSegments() + + with self.assertRaises(TypeError): + zstd.BufferWithSegments(b'foo') + + # Segments data should be a multiple of 16. + with self.assertRaisesRegexp(ValueError, 'segments array size is not a multiple of 16'): + zstd.BufferWithSegments(b'foo', b'\x00\x00') + + def test_invalid_offset(self): + with self.assertRaisesRegexp(ValueError, 'offset within segments array references memory'): + zstd.BufferWithSegments(b'foo', ss.pack(0, 4)) + + def test_invalid_getitem(self): + b = zstd.BufferWithSegments(b'foo', ss.pack(0, 3)) + + with self.assertRaisesRegexp(IndexError, 'offset must be non-negative'): + test = b[-10] + + with self.assertRaisesRegexp(IndexError, 'offset must be less than 1'): + test = b[1] + + with self.assertRaisesRegexp(IndexError, 'offset must be less than 1'): + test = b[2] + + def test_single(self): + b = zstd.BufferWithSegments(b'foo', ss.pack(0, 3)) + self.assertEqual(len(b), 1) + self.assertEqual(b.size, 3) + self.assertEqual(b.tobytes(), b'foo') + + self.assertEqual(len(b[0]), 3) + self.assertEqual(b[0].offset, 0) + self.assertEqual(b[0].tobytes(), b'foo') + + def test_multiple(self): + b = zstd.BufferWithSegments(b'foofooxfooxy', b''.join([ss.pack(0, 3), + ss.pack(3, 4), + ss.pack(7, 5)])) + self.assertEqual(len(b), 3) + self.assertEqual(b.size, 12) + self.assertEqual(b.tobytes(), b'foofooxfooxy') + + self.assertEqual(b[0].tobytes(), b'foo') + self.assertEqual(b[1].tobytes(), b'foox') + self.assertEqual(b[2].tobytes(), b'fooxy') + + +class TestBufferWithSegmentsCollection(unittest.TestCase): + def test_empty_constructor(self): + with self.assertRaisesRegexp(ValueError, 'must pass at least 1 argument'): + zstd.BufferWithSegmentsCollection() + + def test_argument_validation(self): + with self.assertRaisesRegexp(TypeError, 'arguments must be BufferWithSegments'): + zstd.BufferWithSegmentsCollection(None) + + with self.assertRaisesRegexp(TypeError, 'arguments must be BufferWithSegments'): + zstd.BufferWithSegmentsCollection(zstd.BufferWithSegments(b'foo', ss.pack(0, 3)), + None) + + with self.assertRaisesRegexp(ValueError, 'ZstdBufferWithSegments cannot be empty'): + zstd.BufferWithSegmentsCollection(zstd.BufferWithSegments(b'', b'')) + + def test_length(self): + b1 = zstd.BufferWithSegments(b'foo', ss.pack(0, 3)) + b2 = zstd.BufferWithSegments(b'barbaz', b''.join([ss.pack(0, 3), + ss.pack(3, 3)])) + + c = zstd.BufferWithSegmentsCollection(b1) + self.assertEqual(len(c), 1) + self.assertEqual(c.size(), 3) + + c = zstd.BufferWithSegmentsCollection(b2) + self.assertEqual(len(c), 2) + self.assertEqual(c.size(), 6) + + c = zstd.BufferWithSegmentsCollection(b1, b2) + self.assertEqual(len(c), 3) + self.assertEqual(c.size(), 9) + + def test_getitem(self): + b1 = zstd.BufferWithSegments(b'foo', ss.pack(0, 3)) + b2 = zstd.BufferWithSegments(b'barbaz', b''.join([ss.pack(0, 3), + ss.pack(3, 3)])) + + c = zstd.BufferWithSegmentsCollection(b1, b2) + + with self.assertRaisesRegexp(IndexError, 'offset must be less than 3'): + c[3] + + with self.assertRaisesRegexp(IndexError, 'offset must be less than 3'): + c[4] + + self.assertEqual(c[0].tobytes(), b'foo') + self.assertEqual(c[1].tobytes(), b'bar') + self.assertEqual(c[2].tobytes(), b'baz')
--- a/contrib/python-zstandard/tests/test_cffi.py Tue Apr 18 11:22:42 2017 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,35 +0,0 @@ -import io - -try: - import unittest2 as unittest -except ImportError: - import unittest - -import zstd - -try: - import zstd_cffi -except ImportError: - raise unittest.SkipTest('cffi version of zstd not available') - - -class TestCFFIWriteToToCDecompressor(unittest.TestCase): - def test_simple(self): - orig = io.BytesIO() - orig.write(b'foo') - orig.write(b'bar') - orig.write(b'foobar' * 16384) - - dest = io.BytesIO() - cctx = zstd_cffi.ZstdCompressor() - with cctx.write_to(dest) as compressor: - compressor.write(orig.getvalue()) - - uncompressed = io.BytesIO() - dctx = zstd.ZstdDecompressor() - with dctx.write_to(uncompressed) as decompressor: - decompressor.write(dest.getvalue()) - - self.assertEqual(uncompressed.getvalue(), orig.getvalue()) - -
--- a/contrib/python-zstandard/tests/test_compressor.py Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/python-zstandard/tests/test_compressor.py Tue Apr 18 12:24:34 2017 -0400 @@ -10,7 +10,10 @@ import zstd -from .common import OpCountingBytesIO +from .common import ( + make_cffi, + OpCountingBytesIO, +) if sys.version_info[0] >= 3: @@ -19,6 +22,13 @@ next = lambda it: it.next() +def multithreaded_chunk_size(level, source_size=0): + params = zstd.get_compression_parameters(level, source_size) + + return 1 << (params.window_log + 2) + + +@make_cffi class TestCompressor(unittest.TestCase): def test_level_bounds(self): with self.assertRaises(ValueError): @@ -28,18 +38,35 @@ zstd.ZstdCompressor(level=23) +@make_cffi class TestCompressor_compress(unittest.TestCase): - def test_compress_empty(self): - cctx = zstd.ZstdCompressor(level=1) - cctx.compress(b'') + def test_multithreaded_unsupported(self): + samples = [] + for i in range(128): + samples.append(b'foo' * 64) + samples.append(b'bar' * 64) + + d = zstd.train_dictionary(8192, samples) - cctx = zstd.ZstdCompressor(level=22) - cctx.compress(b'') + cctx = zstd.ZstdCompressor(dict_data=d, threads=2) + + with self.assertRaisesRegexp(zstd.ZstdError, 'compress\(\) cannot be used with both dictionaries and multi-threaded compression'): + cctx.compress(b'foo') + + params = zstd.get_compression_parameters(3) + cctx = zstd.ZstdCompressor(compression_params=params, threads=2) + with self.assertRaisesRegexp(zstd.ZstdError, 'compress\(\) cannot be used with both compression parameters and multi-threaded compression'): + cctx.compress(b'foo') def test_compress_empty(self): cctx = zstd.ZstdCompressor(level=1) - self.assertEqual(cctx.compress(b''), - b'\x28\xb5\x2f\xfd\x00\x48\x01\x00\x00') + result = cctx.compress(b'') + self.assertEqual(result, b'\x28\xb5\x2f\xfd\x00\x48\x01\x00\x00') + params = zstd.get_frame_parameters(result) + self.assertEqual(params.content_size, 0) + self.assertEqual(params.window_size, 524288) + self.assertEqual(params.dict_id, 0) + self.assertFalse(params.has_checksum, 0) # TODO should be temporary until https://github.com/facebook/zstd/issues/506 # is fixed. @@ -59,6 +86,13 @@ self.assertEqual(len(result), 999) self.assertEqual(result[0:4], b'\x28\xb5\x2f\xfd') + # This matches the test for read_from() below. + cctx = zstd.ZstdCompressor(level=1) + result = cctx.compress(b'f' * zstd.COMPRESSION_RECOMMENDED_INPUT_SIZE + b'o') + self.assertEqual(result, b'\x28\xb5\x2f\xfd\x00\x40\x54\x00\x00' + b'\x10\x66\x66\x01\x00\xfb\xff\x39\xc0' + b'\x02\x09\x00\x00\x6f') + def test_write_checksum(self): cctx = zstd.ZstdCompressor(level=1) no_checksum = cctx.compress(b'foobar') @@ -67,6 +101,12 @@ self.assertEqual(len(with_checksum), len(no_checksum) + 4) + no_params = zstd.get_frame_parameters(no_checksum) + with_params = zstd.get_frame_parameters(with_checksum) + + self.assertFalse(no_params.has_checksum) + self.assertTrue(with_params.has_checksum) + def test_write_content_size(self): cctx = zstd.ZstdCompressor(level=1) no_size = cctx.compress(b'foobar' * 256) @@ -75,6 +115,11 @@ self.assertEqual(len(with_size), len(no_size) + 1) + no_params = zstd.get_frame_parameters(no_size) + with_params = zstd.get_frame_parameters(with_size) + self.assertEqual(no_params.content_size, 0) + self.assertEqual(with_params.content_size, 1536) + def test_no_dict_id(self): samples = [] for i in range(128): @@ -92,6 +137,11 @@ self.assertEqual(len(with_dict_id), len(no_dict_id) + 4) + no_params = zstd.get_frame_parameters(no_dict_id) + with_params = zstd.get_frame_parameters(with_dict_id) + self.assertEqual(no_params.dict_id, 0) + self.assertEqual(with_params.dict_id, 1584102229) + def test_compress_dict_multiple(self): samples = [] for i in range(128): @@ -106,7 +156,23 @@ for i in range(32): cctx.compress(b'foo bar foobar foo bar foobar') + def test_multithreaded(self): + chunk_size = multithreaded_chunk_size(1) + source = b''.join([b'x' * chunk_size, b'y' * chunk_size]) + cctx = zstd.ZstdCompressor(level=1, threads=2) + compressed = cctx.compress(source) + + params = zstd.get_frame_parameters(compressed) + self.assertEqual(params.content_size, chunk_size * 2) + self.assertEqual(params.dict_id, 0) + self.assertFalse(params.has_checksum) + + dctx = zstd.ZstdDecompressor() + self.assertEqual(dctx.decompress(compressed), source) + + +@make_cffi class TestCompressor_compressobj(unittest.TestCase): def test_compressobj_empty(self): cctx = zstd.ZstdCompressor(level=1) @@ -127,6 +193,12 @@ self.assertEqual(len(result), 999) self.assertEqual(result[0:4], b'\x28\xb5\x2f\xfd') + params = zstd.get_frame_parameters(result) + self.assertEqual(params.content_size, 0) + self.assertEqual(params.window_size, 1048576) + self.assertEqual(params.dict_id, 0) + self.assertFalse(params.has_checksum) + def test_write_checksum(self): cctx = zstd.ZstdCompressor(level=1) cobj = cctx.compressobj() @@ -135,6 +207,15 @@ cobj = cctx.compressobj() with_checksum = cobj.compress(b'foobar') + cobj.flush() + no_params = zstd.get_frame_parameters(no_checksum) + with_params = zstd.get_frame_parameters(with_checksum) + self.assertEqual(no_params.content_size, 0) + self.assertEqual(with_params.content_size, 0) + self.assertEqual(no_params.dict_id, 0) + self.assertEqual(with_params.dict_id, 0) + self.assertFalse(no_params.has_checksum) + self.assertTrue(with_params.has_checksum) + self.assertEqual(len(with_checksum), len(no_checksum) + 4) def test_write_content_size(self): @@ -145,6 +226,15 @@ cobj = cctx.compressobj(size=len(b'foobar' * 256)) with_size = cobj.compress(b'foobar' * 256) + cobj.flush() + no_params = zstd.get_frame_parameters(no_size) + with_params = zstd.get_frame_parameters(with_size) + self.assertEqual(no_params.content_size, 0) + self.assertEqual(with_params.content_size, 1536) + self.assertEqual(no_params.dict_id, 0) + self.assertEqual(with_params.dict_id, 0) + self.assertFalse(no_params.has_checksum) + self.assertFalse(with_params.has_checksum) + self.assertEqual(len(with_size), len(no_size) + 1) def test_compress_after_finished(self): @@ -186,7 +276,32 @@ header = trailing[0:3] self.assertEqual(header, b'\x01\x00\x00') + def test_multithreaded(self): + source = io.BytesIO() + source.write(b'a' * 1048576) + source.write(b'b' * 1048576) + source.write(b'c' * 1048576) + source.seek(0) + cctx = zstd.ZstdCompressor(level=1, threads=2) + cobj = cctx.compressobj() + + chunks = [] + while True: + d = source.read(8192) + if not d: + break + + chunks.append(cobj.compress(d)) + + chunks.append(cobj.flush()) + + compressed = b''.join(chunks) + + self.assertEqual(len(compressed), 295) + + +@make_cffi class TestCompressor_copy_stream(unittest.TestCase): def test_no_read(self): source = object() @@ -229,6 +344,12 @@ self.assertEqual(r, 255 * 16384) self.assertEqual(w, 999) + params = zstd.get_frame_parameters(dest.getvalue()) + self.assertEqual(params.content_size, 0) + self.assertEqual(params.window_size, 1048576) + self.assertEqual(params.dict_id, 0) + self.assertFalse(params.has_checksum) + def test_write_checksum(self): source = io.BytesIO(b'foobar') no_checksum = io.BytesIO() @@ -244,6 +365,15 @@ self.assertEqual(len(with_checksum.getvalue()), len(no_checksum.getvalue()) + 4) + no_params = zstd.get_frame_parameters(no_checksum.getvalue()) + with_params = zstd.get_frame_parameters(with_checksum.getvalue()) + self.assertEqual(no_params.content_size, 0) + self.assertEqual(with_params.content_size, 0) + self.assertEqual(no_params.dict_id, 0) + self.assertEqual(with_params.dict_id, 0) + self.assertFalse(no_params.has_checksum) + self.assertTrue(with_params.has_checksum) + def test_write_content_size(self): source = io.BytesIO(b'foobar' * 256) no_size = io.BytesIO() @@ -268,6 +398,15 @@ self.assertEqual(len(with_size.getvalue()), len(no_size.getvalue()) + 1) + no_params = zstd.get_frame_parameters(no_size.getvalue()) + with_params = zstd.get_frame_parameters(with_size.getvalue()) + self.assertEqual(no_params.content_size, 0) + self.assertEqual(with_params.content_size, 1536) + self.assertEqual(no_params.dict_id, 0) + self.assertEqual(with_params.dict_id, 0) + self.assertFalse(no_params.has_checksum) + self.assertFalse(with_params.has_checksum) + def test_read_write_size(self): source = OpCountingBytesIO(b'foobarfoobar') dest = OpCountingBytesIO() @@ -279,6 +418,36 @@ self.assertEqual(source._read_count, len(source.getvalue()) + 1) self.assertEqual(dest._write_count, len(dest.getvalue())) + def test_multithreaded(self): + source = io.BytesIO() + source.write(b'a' * 1048576) + source.write(b'b' * 1048576) + source.write(b'c' * 1048576) + source.seek(0) + + dest = io.BytesIO() + cctx = zstd.ZstdCompressor(threads=2) + r, w = cctx.copy_stream(source, dest) + self.assertEqual(r, 3145728) + self.assertEqual(w, 295) + + params = zstd.get_frame_parameters(dest.getvalue()) + self.assertEqual(params.content_size, 0) + self.assertEqual(params.dict_id, 0) + self.assertFalse(params.has_checksum) + + # Writing content size and checksum works. + cctx = zstd.ZstdCompressor(threads=2, write_content_size=True, + write_checksum=True) + dest = io.BytesIO() + source.seek(0) + cctx.copy_stream(source, dest, size=len(source.getvalue())) + + params = zstd.get_frame_parameters(dest.getvalue()) + self.assertEqual(params.content_size, 3145728) + self.assertEqual(params.dict_id, 0) + self.assertTrue(params.has_checksum) + def compress(data, level): buffer = io.BytesIO() @@ -288,18 +457,25 @@ return buffer.getvalue() +@make_cffi class TestCompressor_write_to(unittest.TestCase): def test_empty(self): - self.assertEqual(compress(b'', 1), - b'\x28\xb5\x2f\xfd\x00\x48\x01\x00\x00') + result = compress(b'', 1) + self.assertEqual(result, b'\x28\xb5\x2f\xfd\x00\x48\x01\x00\x00') + + params = zstd.get_frame_parameters(result) + self.assertEqual(params.content_size, 0) + self.assertEqual(params.window_size, 524288) + self.assertEqual(params.dict_id, 0) + self.assertFalse(params.has_checksum) def test_multiple_compress(self): buffer = io.BytesIO() cctx = zstd.ZstdCompressor(level=5) with cctx.write_to(buffer) as compressor: - compressor.write(b'foo') - compressor.write(b'bar') - compressor.write(b'x' * 8192) + self.assertEqual(compressor.write(b'foo'), 0) + self.assertEqual(compressor.write(b'bar'), 0) + self.assertEqual(compressor.write(b'x' * 8192), 0) result = buffer.getvalue() self.assertEqual(result, @@ -318,11 +494,23 @@ buffer = io.BytesIO() cctx = zstd.ZstdCompressor(level=9, dict_data=d) with cctx.write_to(buffer) as compressor: - compressor.write(b'foo') - compressor.write(b'bar') - compressor.write(b'foo' * 16384) + self.assertEqual(compressor.write(b'foo'), 0) + self.assertEqual(compressor.write(b'bar'), 0) + self.assertEqual(compressor.write(b'foo' * 16384), 634) compressed = buffer.getvalue() + + params = zstd.get_frame_parameters(compressed) + self.assertEqual(params.content_size, 0) + self.assertEqual(params.window_size, 1024) + self.assertEqual(params.dict_id, d.dict_id()) + self.assertFalse(params.has_checksum) + + self.assertEqual(compressed[0:32], + b'\x28\xb5\x2f\xfd\x03\x00\x55\x7b\x6b\x5e\x54\x00' + b'\x00\x00\x02\xfc\xf4\xa5\xba\x23\x3f\x85\xb3\x54' + b'\x00\x00\x18\x6f\x6f\x66\x01\x00') + h = hashlib.sha1(compressed).hexdigest() self.assertEqual(h, '1c5bcd25181bcd8c1a73ea8773323e0056129f92') @@ -332,11 +520,18 @@ buffer = io.BytesIO() cctx = zstd.ZstdCompressor(compression_params=params) with cctx.write_to(buffer) as compressor: - compressor.write(b'foo') - compressor.write(b'bar') - compressor.write(b'foobar' * 16384) + self.assertEqual(compressor.write(b'foo'), 0) + self.assertEqual(compressor.write(b'bar'), 0) + self.assertEqual(compressor.write(b'foobar' * 16384), 0) compressed = buffer.getvalue() + + params = zstd.get_frame_parameters(compressed) + self.assertEqual(params.content_size, 0) + self.assertEqual(params.window_size, 1048576) + self.assertEqual(params.dict_id, 0) + self.assertFalse(params.has_checksum) + h = hashlib.sha1(compressed).hexdigest() self.assertEqual(h, '1ae31f270ed7de14235221a604b31ecd517ebd99') @@ -344,12 +539,21 @@ no_checksum = io.BytesIO() cctx = zstd.ZstdCompressor(level=1) with cctx.write_to(no_checksum) as compressor: - compressor.write(b'foobar') + self.assertEqual(compressor.write(b'foobar'), 0) with_checksum = io.BytesIO() cctx = zstd.ZstdCompressor(level=1, write_checksum=True) with cctx.write_to(with_checksum) as compressor: - compressor.write(b'foobar') + self.assertEqual(compressor.write(b'foobar'), 0) + + no_params = zstd.get_frame_parameters(no_checksum.getvalue()) + with_params = zstd.get_frame_parameters(with_checksum.getvalue()) + self.assertEqual(no_params.content_size, 0) + self.assertEqual(with_params.content_size, 0) + self.assertEqual(no_params.dict_id, 0) + self.assertEqual(with_params.dict_id, 0) + self.assertFalse(no_params.has_checksum) + self.assertTrue(with_params.has_checksum) self.assertEqual(len(with_checksum.getvalue()), len(no_checksum.getvalue()) + 4) @@ -358,12 +562,12 @@ no_size = io.BytesIO() cctx = zstd.ZstdCompressor(level=1) with cctx.write_to(no_size) as compressor: - compressor.write(b'foobar' * 256) + self.assertEqual(compressor.write(b'foobar' * 256), 0) with_size = io.BytesIO() cctx = zstd.ZstdCompressor(level=1, write_content_size=True) with cctx.write_to(with_size) as compressor: - compressor.write(b'foobar' * 256) + self.assertEqual(compressor.write(b'foobar' * 256), 0) # Source size is not known in streaming mode, so header not # written. @@ -373,7 +577,16 @@ # Declaring size will write the header. with_size = io.BytesIO() with cctx.write_to(with_size, size=len(b'foobar' * 256)) as compressor: - compressor.write(b'foobar' * 256) + self.assertEqual(compressor.write(b'foobar' * 256), 0) + + no_params = zstd.get_frame_parameters(no_size.getvalue()) + with_params = zstd.get_frame_parameters(with_size.getvalue()) + self.assertEqual(no_params.content_size, 0) + self.assertEqual(with_params.content_size, 1536) + self.assertEqual(no_params.dict_id, 0) + self.assertEqual(with_params.dict_id, 0) + self.assertFalse(no_params.has_checksum) + self.assertFalse(with_params.has_checksum) self.assertEqual(len(with_size.getvalue()), len(no_size.getvalue()) + 1) @@ -390,12 +603,21 @@ with_dict_id = io.BytesIO() cctx = zstd.ZstdCompressor(level=1, dict_data=d) with cctx.write_to(with_dict_id) as compressor: - compressor.write(b'foobarfoobar') + self.assertEqual(compressor.write(b'foobarfoobar'), 0) cctx = zstd.ZstdCompressor(level=1, dict_data=d, write_dict_id=False) no_dict_id = io.BytesIO() with cctx.write_to(no_dict_id) as compressor: - compressor.write(b'foobarfoobar') + self.assertEqual(compressor.write(b'foobarfoobar'), 0) + + no_params = zstd.get_frame_parameters(no_dict_id.getvalue()) + with_params = zstd.get_frame_parameters(with_dict_id.getvalue()) + self.assertEqual(no_params.content_size, 0) + self.assertEqual(with_params.content_size, 0) + self.assertEqual(no_params.dict_id, 0) + self.assertEqual(with_params.dict_id, d.dict_id()) + self.assertFalse(no_params.has_checksum) + self.assertFalse(with_params.has_checksum) self.assertEqual(len(with_dict_id.getvalue()), len(no_dict_id.getvalue()) + 4) @@ -412,9 +634,9 @@ cctx = zstd.ZstdCompressor(level=3) dest = OpCountingBytesIO() with cctx.write_to(dest, write_size=1) as compressor: - compressor.write(b'foo') - compressor.write(b'bar') - compressor.write(b'foobar') + self.assertEqual(compressor.write(b'foo'), 0) + self.assertEqual(compressor.write(b'bar'), 0) + self.assertEqual(compressor.write(b'foobar'), 0) self.assertEqual(len(dest.getvalue()), dest._write_count) @@ -422,15 +644,15 @@ cctx = zstd.ZstdCompressor(level=3) dest = OpCountingBytesIO() with cctx.write_to(dest) as compressor: - compressor.write(b'foo') + self.assertEqual(compressor.write(b'foo'), 0) self.assertEqual(dest._write_count, 0) - compressor.flush() + self.assertEqual(compressor.flush(), 12) self.assertEqual(dest._write_count, 1) - compressor.write(b'bar') + self.assertEqual(compressor.write(b'bar'), 0) self.assertEqual(dest._write_count, 1) - compressor.flush() + self.assertEqual(compressor.flush(), 6) self.assertEqual(dest._write_count, 2) - compressor.write(b'baz') + self.assertEqual(compressor.write(b'baz'), 0) self.assertEqual(dest._write_count, 3) @@ -438,10 +660,10 @@ cctx = zstd.ZstdCompressor(level=3, write_checksum=True) dest = OpCountingBytesIO() with cctx.write_to(dest) as compressor: - compressor.write(b'foobar' * 8192) + self.assertEqual(compressor.write(b'foobar' * 8192), 0) count = dest._write_count offset = dest.tell() - compressor.flush() + self.assertEqual(compressor.flush(), 23) self.assertGreater(dest._write_count, count) self.assertGreater(dest.tell(), offset) offset = dest.tell() @@ -455,19 +677,33 @@ header = trailing[0:3] self.assertEqual(header, b'\x01\x00\x00') + def test_multithreaded(self): + dest = io.BytesIO() + cctx = zstd.ZstdCompressor(threads=2) + with cctx.write_to(dest) as compressor: + compressor.write(b'a' * 1048576) + compressor.write(b'b' * 1048576) + compressor.write(b'c' * 1048576) + self.assertEqual(len(dest.getvalue()), 295) + + +@make_cffi class TestCompressor_read_from(unittest.TestCase): def test_type_validation(self): cctx = zstd.ZstdCompressor() # Object with read() works. - cctx.read_from(io.BytesIO()) + for chunk in cctx.read_from(io.BytesIO()): + pass # Buffer protocol works. - cctx.read_from(b'foobar') + for chunk in cctx.read_from(b'foobar'): + pass with self.assertRaisesRegexp(ValueError, 'must pass an object with a read'): - cctx.read_from(True) + for chunk in cctx.read_from(True): + pass def test_read_empty(self): cctx = zstd.ZstdCompressor(level=1) @@ -521,6 +757,12 @@ # We should get the same output as the one-shot compression mechanism. self.assertEqual(b''.join(chunks), cctx.compress(source.getvalue())) + params = zstd.get_frame_parameters(b''.join(chunks)) + self.assertEqual(params.content_size, 0) + self.assertEqual(params.window_size, 262144) + self.assertEqual(params.dict_id, 0) + self.assertFalse(params.has_checksum) + # Now check the buffer protocol. it = cctx.read_from(source.getvalue()) chunks = list(it) @@ -534,3 +776,130 @@ self.assertEqual(len(chunk), 1) self.assertEqual(source._read_count, len(source.getvalue()) + 1) + + def test_multithreaded(self): + source = io.BytesIO() + source.write(b'a' * 1048576) + source.write(b'b' * 1048576) + source.write(b'c' * 1048576) + source.seek(0) + + cctx = zstd.ZstdCompressor(threads=2) + + compressed = b''.join(cctx.read_from(source)) + self.assertEqual(len(compressed), 295) + + +class TestCompressor_multi_compress_to_buffer(unittest.TestCase): + def test_multithreaded_unsupported(self): + cctx = zstd.ZstdCompressor(threads=2) + + with self.assertRaisesRegexp(zstd.ZstdError, 'function cannot be called on ZstdCompressor configured for multi-threaded compression'): + cctx.multi_compress_to_buffer([b'foo']) + + def test_invalid_inputs(self): + cctx = zstd.ZstdCompressor() + + with self.assertRaises(TypeError): + cctx.multi_compress_to_buffer(True) + + with self.assertRaises(TypeError): + cctx.multi_compress_to_buffer((1, 2)) + + with self.assertRaisesRegexp(TypeError, 'item 0 not a bytes like object'): + cctx.multi_compress_to_buffer([u'foo']) + + def test_empty_input(self): + cctx = zstd.ZstdCompressor() + + with self.assertRaisesRegexp(ValueError, 'no source elements found'): + cctx.multi_compress_to_buffer([]) + + with self.assertRaisesRegexp(ValueError, 'source elements are empty'): + cctx.multi_compress_to_buffer([b'', b'', b'']) + + def test_list_input(self): + cctx = zstd.ZstdCompressor(write_content_size=True, write_checksum=True) + + original = [b'foo' * 12, b'bar' * 6] + frames = [cctx.compress(c) for c in original] + b = cctx.multi_compress_to_buffer(original) + + self.assertIsInstance(b, zstd.BufferWithSegmentsCollection) + + self.assertEqual(len(b), 2) + self.assertEqual(b.size(), 44) + + self.assertEqual(b[0].tobytes(), frames[0]) + self.assertEqual(b[1].tobytes(), frames[1]) + + def test_buffer_with_segments_input(self): + cctx = zstd.ZstdCompressor(write_content_size=True, write_checksum=True) + + original = [b'foo' * 4, b'bar' * 6] + frames = [cctx.compress(c) for c in original] + + offsets = struct.pack('=QQQQ', 0, len(original[0]), + len(original[0]), len(original[1])) + segments = zstd.BufferWithSegments(b''.join(original), offsets) + + result = cctx.multi_compress_to_buffer(segments) + + self.assertEqual(len(result), 2) + self.assertEqual(result.size(), 47) + + self.assertEqual(result[0].tobytes(), frames[0]) + self.assertEqual(result[1].tobytes(), frames[1]) + + def test_buffer_with_segments_collection_input(self): + cctx = zstd.ZstdCompressor(write_content_size=True, write_checksum=True) + + original = [ + b'foo1', + b'foo2' * 2, + b'foo3' * 3, + b'foo4' * 4, + b'foo5' * 5, + ] + + frames = [cctx.compress(c) for c in original] + + b = b''.join([original[0], original[1]]) + b1 = zstd.BufferWithSegments(b, struct.pack('=QQQQ', + 0, len(original[0]), + len(original[0]), len(original[1]))) + b = b''.join([original[2], original[3], original[4]]) + b2 = zstd.BufferWithSegments(b, struct.pack('=QQQQQQ', + 0, len(original[2]), + len(original[2]), len(original[3]), + len(original[2]) + len(original[3]), len(original[4]))) + + c = zstd.BufferWithSegmentsCollection(b1, b2) + + result = cctx.multi_compress_to_buffer(c) + + self.assertEqual(len(result), len(frames)) + + for i, frame in enumerate(frames): + self.assertEqual(result[i].tobytes(), frame) + + def test_multiple_threads(self): + # threads argument will cause multi-threaded ZSTD APIs to be used, which will + # make output different. + refcctx = zstd.ZstdCompressor(write_content_size=True, write_checksum=True) + reference = [refcctx.compress(b'x' * 64), refcctx.compress(b'y' * 64)] + + cctx = zstd.ZstdCompressor(write_content_size=True, write_checksum=True) + + frames = [] + frames.extend(b'x' * 64 for i in range(256)) + frames.extend(b'y' * 64 for i in range(256)) + + result = cctx.multi_compress_to_buffer(frames, threads=-1) + + self.assertEqual(len(result), 512) + for i in range(512): + if i < 256: + self.assertEqual(result[i].tobytes(), reference[0]) + else: + self.assertEqual(result[i].tobytes(), reference[1])
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/contrib/python-zstandard/tests/test_compressor_fuzzing.py Tue Apr 18 12:24:34 2017 -0400 @@ -0,0 +1,143 @@ +import io +import os + +try: + import unittest2 as unittest +except ImportError: + import unittest + +try: + import hypothesis + import hypothesis.strategies as strategies +except ImportError: + raise unittest.SkipTest('hypothesis not available') + +import zstd + +from . common import ( + make_cffi, + random_input_data, +) + + +@unittest.skipUnless('ZSTD_SLOW_TESTS' in os.environ, 'ZSTD_SLOW_TESTS not set') +@make_cffi +class TestCompressor_write_to_fuzzing(unittest.TestCase): + @hypothesis.given(original=strategies.sampled_from(random_input_data()), + level=strategies.integers(min_value=1, max_value=5), + write_size=strategies.integers(min_value=1, max_value=1048576)) + def test_write_size_variance(self, original, level, write_size): + refctx = zstd.ZstdCompressor(level=level) + ref_frame = refctx.compress(original) + + cctx = zstd.ZstdCompressor(level=level) + b = io.BytesIO() + with cctx.write_to(b, size=len(original), write_size=write_size) as compressor: + compressor.write(original) + + self.assertEqual(b.getvalue(), ref_frame) + + +@unittest.skipUnless('ZSTD_SLOW_TESTS' in os.environ, 'ZSTD_SLOW_TESTS not set') +@make_cffi +class TestCompressor_copy_stream_fuzzing(unittest.TestCase): + @hypothesis.given(original=strategies.sampled_from(random_input_data()), + level=strategies.integers(min_value=1, max_value=5), + read_size=strategies.integers(min_value=1, max_value=1048576), + write_size=strategies.integers(min_value=1, max_value=1048576)) + def test_read_write_size_variance(self, original, level, read_size, write_size): + refctx = zstd.ZstdCompressor(level=level) + ref_frame = refctx.compress(original) + + cctx = zstd.ZstdCompressor(level=level) + source = io.BytesIO(original) + dest = io.BytesIO() + + cctx.copy_stream(source, dest, size=len(original), read_size=read_size, + write_size=write_size) + + self.assertEqual(dest.getvalue(), ref_frame) + + +@unittest.skipUnless('ZSTD_SLOW_TESTS' in os.environ, 'ZSTD_SLOW_TESTS not set') +@make_cffi +class TestCompressor_compressobj_fuzzing(unittest.TestCase): + @hypothesis.given(original=strategies.sampled_from(random_input_data()), + level=strategies.integers(min_value=1, max_value=5), + chunk_sizes=strategies.streaming( + strategies.integers(min_value=1, max_value=4096))) + def test_random_input_sizes(self, original, level, chunk_sizes): + chunk_sizes = iter(chunk_sizes) + + refctx = zstd.ZstdCompressor(level=level) + ref_frame = refctx.compress(original) + + cctx = zstd.ZstdCompressor(level=level) + cobj = cctx.compressobj(size=len(original)) + + chunks = [] + i = 0 + while True: + chunk_size = next(chunk_sizes) + source = original[i:i + chunk_size] + if not source: + break + + chunks.append(cobj.compress(source)) + i += chunk_size + + chunks.append(cobj.flush()) + + self.assertEqual(b''.join(chunks), ref_frame) + + +@unittest.skipUnless('ZSTD_SLOW_TESTS' in os.environ, 'ZSTD_SLOW_TESTS not set') +@make_cffi +class TestCompressor_read_from_fuzzing(unittest.TestCase): + @hypothesis.given(original=strategies.sampled_from(random_input_data()), + level=strategies.integers(min_value=1, max_value=5), + read_size=strategies.integers(min_value=1, max_value=4096), + write_size=strategies.integers(min_value=1, max_value=4096)) + def test_read_write_size_variance(self, original, level, read_size, write_size): + refcctx = zstd.ZstdCompressor(level=level) + ref_frame = refcctx.compress(original) + + source = io.BytesIO(original) + + cctx = zstd.ZstdCompressor(level=level) + chunks = list(cctx.read_from(source, size=len(original), read_size=read_size, + write_size=write_size)) + + self.assertEqual(b''.join(chunks), ref_frame) + + +@unittest.skipUnless('ZSTD_SLOW_TESTS' in os.environ, 'ZSTD_SLOW_TESTS not set') +class TestCompressor_multi_compress_to_buffer_fuzzing(unittest.TestCase): + @hypothesis.given(original=strategies.lists(strategies.sampled_from(random_input_data()), + min_size=1, max_size=1024), + threads=strategies.integers(min_value=1, max_value=8), + use_dict=strategies.booleans()) + def test_data_equivalence(self, original, threads, use_dict): + kwargs = {} + + # Use a content dictionary because it is cheap to create. + if use_dict: + kwargs['dict_data'] = zstd.ZstdCompressionDict(original[0]) + + cctx = zstd.ZstdCompressor(level=1, + write_content_size=True, + write_checksum=True, + **kwargs) + + result = cctx.multi_compress_to_buffer(original, threads=-1) + + self.assertEqual(len(result), len(original)) + + # The frame produced via the batch APIs may not be bit identical to that + # produced by compress() because compression parameters are adjusted + # from the first input in batch mode. So the only thing we can do is + # verify the decompressed data matches the input. + dctx = zstd.ZstdDecompressor(**kwargs) + + for i, frame in enumerate(result): + self.assertEqual(dctx.decompress(frame), original[i])
--- a/contrib/python-zstandard/tests/test_data_structures.py Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/python-zstandard/tests/test_data_structures.py Tue Apr 18 12:24:34 2017 -0400 @@ -1,18 +1,16 @@ -import io - try: import unittest2 as unittest except ImportError: import unittest -try: - import hypothesis - import hypothesis.strategies as strategies -except ImportError: - hypothesis = None - import zstd +from . common import ( + make_cffi, +) + + +@make_cffi class TestCompressionParameters(unittest.TestCase): def test_init_bad_arg_type(self): with self.assertRaises(TypeError): @@ -26,7 +24,7 @@ zstd.CHAINLOG_MIN, zstd.HASHLOG_MIN, zstd.SEARCHLOG_MIN, - zstd.SEARCHLENGTH_MIN, + zstd.SEARCHLENGTH_MIN + 1, zstd.TARGETLENGTH_MIN, zstd.STRATEGY_FAST) @@ -34,7 +32,7 @@ zstd.CHAINLOG_MAX, zstd.HASHLOG_MAX, zstd.SEARCHLOG_MAX, - zstd.SEARCHLENGTH_MAX, + zstd.SEARCHLENGTH_MAX - 1, zstd.TARGETLENGTH_MAX, zstd.STRATEGY_BTOPT) @@ -42,66 +40,84 @@ p = zstd.get_compression_parameters(1) self.assertIsInstance(p, zstd.CompressionParameters) - self.assertEqual(p[0], 19) + self.assertEqual(p.window_log, 19) + + def test_members(self): + p = zstd.CompressionParameters(10, 6, 7, 4, 5, 8, 1) + self.assertEqual(p.window_log, 10) + self.assertEqual(p.chain_log, 6) + self.assertEqual(p.hash_log, 7) + self.assertEqual(p.search_log, 4) + self.assertEqual(p.search_length, 5) + self.assertEqual(p.target_length, 8) + self.assertEqual(p.strategy, 1) + + def test_estimated_compression_context_size(self): + p = zstd.CompressionParameters(20, 16, 17, 1, 5, 16, zstd.STRATEGY_DFAST) + + # 32-bit has slightly different values from 64-bit. + self.assertAlmostEqual(p.estimated_compression_context_size(), 1287076, + delta=110) + -if hypothesis: - s_windowlog = strategies.integers(min_value=zstd.WINDOWLOG_MIN, - max_value=zstd.WINDOWLOG_MAX) - s_chainlog = strategies.integers(min_value=zstd.CHAINLOG_MIN, - max_value=zstd.CHAINLOG_MAX) - s_hashlog = strategies.integers(min_value=zstd.HASHLOG_MIN, - max_value=zstd.HASHLOG_MAX) - s_searchlog = strategies.integers(min_value=zstd.SEARCHLOG_MIN, - max_value=zstd.SEARCHLOG_MAX) - s_searchlength = strategies.integers(min_value=zstd.SEARCHLENGTH_MIN, - max_value=zstd.SEARCHLENGTH_MAX) - s_targetlength = strategies.integers(min_value=zstd.TARGETLENGTH_MIN, - max_value=zstd.TARGETLENGTH_MAX) - s_strategy = strategies.sampled_from((zstd.STRATEGY_FAST, - zstd.STRATEGY_DFAST, - zstd.STRATEGY_GREEDY, - zstd.STRATEGY_LAZY, - zstd.STRATEGY_LAZY2, - zstd.STRATEGY_BTLAZY2, - zstd.STRATEGY_BTOPT)) +@make_cffi +class TestFrameParameters(unittest.TestCase): + def test_invalid_type(self): + with self.assertRaises(TypeError): + zstd.get_frame_parameters(None) + + with self.assertRaises(TypeError): + zstd.get_frame_parameters(u'foobarbaz') + + def test_invalid_input_sizes(self): + with self.assertRaisesRegexp(zstd.ZstdError, 'not enough data for frame'): + zstd.get_frame_parameters(b'') + + with self.assertRaisesRegexp(zstd.ZstdError, 'not enough data for frame'): + zstd.get_frame_parameters(zstd.FRAME_HEADER) + + def test_invalid_frame(self): + with self.assertRaisesRegexp(zstd.ZstdError, 'Unknown frame descriptor'): + zstd.get_frame_parameters(b'foobarbaz') - class TestCompressionParametersHypothesis(unittest.TestCase): - @hypothesis.given(s_windowlog, s_chainlog, s_hashlog, s_searchlog, - s_searchlength, s_targetlength, s_strategy) - def test_valid_init(self, windowlog, chainlog, hashlog, searchlog, - searchlength, targetlength, strategy): - p = zstd.CompressionParameters(windowlog, chainlog, hashlog, - searchlog, searchlength, - targetlength, strategy) - self.assertEqual(tuple(p), - (windowlog, chainlog, hashlog, searchlog, - searchlength, targetlength, strategy)) + def test_attributes(self): + params = zstd.get_frame_parameters(zstd.FRAME_HEADER + b'\x00\x00') + self.assertEqual(params.content_size, 0) + self.assertEqual(params.window_size, 1024) + self.assertEqual(params.dict_id, 0) + self.assertFalse(params.has_checksum) + + # Lowest 2 bits indicate a dictionary and length. Here, the dict id is 1 byte. + params = zstd.get_frame_parameters(zstd.FRAME_HEADER + b'\x01\x00\xff') + self.assertEqual(params.content_size, 0) + self.assertEqual(params.window_size, 1024) + self.assertEqual(params.dict_id, 255) + self.assertFalse(params.has_checksum) + + # Lowest 3rd bit indicates if checksum is present. + params = zstd.get_frame_parameters(zstd.FRAME_HEADER + b'\x04\x00') + self.assertEqual(params.content_size, 0) + self.assertEqual(params.window_size, 1024) + self.assertEqual(params.dict_id, 0) + self.assertTrue(params.has_checksum) - # Verify we can instantiate a compressor with the supplied values. - # ZSTD_checkCParams moves the goal posts on us from what's advertised - # in the constants. So move along with them. - if searchlength == zstd.SEARCHLENGTH_MIN and strategy in (zstd.STRATEGY_FAST, zstd.STRATEGY_GREEDY): - searchlength += 1 - p = zstd.CompressionParameters(windowlog, chainlog, hashlog, - searchlog, searchlength, - targetlength, strategy) - elif searchlength == zstd.SEARCHLENGTH_MAX and strategy != zstd.STRATEGY_FAST: - searchlength -= 1 - p = zstd.CompressionParameters(windowlog, chainlog, hashlog, - searchlog, searchlength, - targetlength, strategy) + # Upper 2 bits indicate content size. + params = zstd.get_frame_parameters(zstd.FRAME_HEADER + b'\x40\x00\xff\x00') + self.assertEqual(params.content_size, 511) + self.assertEqual(params.window_size, 1024) + self.assertEqual(params.dict_id, 0) + self.assertFalse(params.has_checksum) - cctx = zstd.ZstdCompressor(compression_params=p) - with cctx.write_to(io.BytesIO()): - pass + # Window descriptor is 2nd byte after frame header. + params = zstd.get_frame_parameters(zstd.FRAME_HEADER + b'\x00\x40') + self.assertEqual(params.content_size, 0) + self.assertEqual(params.window_size, 262144) + self.assertEqual(params.dict_id, 0) + self.assertFalse(params.has_checksum) - @hypothesis.given(s_windowlog, s_chainlog, s_hashlog, s_searchlog, - s_searchlength, s_targetlength, s_strategy) - def test_estimate_compression_context_size(self, windowlog, chainlog, - hashlog, searchlog, - searchlength, targetlength, - strategy): - p = zstd.CompressionParameters(windowlog, chainlog, hashlog, - searchlog, searchlength, - targetlength, strategy) - size = zstd.estimate_compression_context_size(p) + # Set multiple things. + params = zstd.get_frame_parameters(zstd.FRAME_HEADER + b'\x45\x40\x0f\x10\x00') + self.assertEqual(params.content_size, 272) + self.assertEqual(params.window_size, 262144) + self.assertEqual(params.dict_id, 15) + self.assertTrue(params.has_checksum)
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/contrib/python-zstandard/tests/test_data_structures_fuzzing.py Tue Apr 18 12:24:34 2017 -0400 @@ -0,0 +1,79 @@ +import io +import os + +try: + import unittest2 as unittest +except ImportError: + import unittest + +try: + import hypothesis + import hypothesis.strategies as strategies +except ImportError: + raise unittest.SkipTest('hypothesis not available') + +import zstd + +from .common import ( + make_cffi, +) + + +s_windowlog = strategies.integers(min_value=zstd.WINDOWLOG_MIN, + max_value=zstd.WINDOWLOG_MAX) +s_chainlog = strategies.integers(min_value=zstd.CHAINLOG_MIN, + max_value=zstd.CHAINLOG_MAX) +s_hashlog = strategies.integers(min_value=zstd.HASHLOG_MIN, + max_value=zstd.HASHLOG_MAX) +s_searchlog = strategies.integers(min_value=zstd.SEARCHLOG_MIN, + max_value=zstd.SEARCHLOG_MAX) +s_searchlength = strategies.integers(min_value=zstd.SEARCHLENGTH_MIN, + max_value=zstd.SEARCHLENGTH_MAX) +s_targetlength = strategies.integers(min_value=zstd.TARGETLENGTH_MIN, + max_value=zstd.TARGETLENGTH_MAX) +s_strategy = strategies.sampled_from((zstd.STRATEGY_FAST, + zstd.STRATEGY_DFAST, + zstd.STRATEGY_GREEDY, + zstd.STRATEGY_LAZY, + zstd.STRATEGY_LAZY2, + zstd.STRATEGY_BTLAZY2, + zstd.STRATEGY_BTOPT)) + + +@make_cffi +@unittest.skipUnless('ZSTD_SLOW_TESTS' in os.environ, 'ZSTD_SLOW_TESTS not set') +class TestCompressionParametersHypothesis(unittest.TestCase): + @hypothesis.given(s_windowlog, s_chainlog, s_hashlog, s_searchlog, + s_searchlength, s_targetlength, s_strategy) + def test_valid_init(self, windowlog, chainlog, hashlog, searchlog, + searchlength, targetlength, strategy): + # ZSTD_checkCParams moves the goal posts on us from what's advertised + # in the constants. So move along with them. + if searchlength == zstd.SEARCHLENGTH_MIN and strategy in (zstd.STRATEGY_FAST, zstd.STRATEGY_GREEDY): + searchlength += 1 + elif searchlength == zstd.SEARCHLENGTH_MAX and strategy != zstd.STRATEGY_FAST: + searchlength -= 1 + + p = zstd.CompressionParameters(windowlog, chainlog, hashlog, + searchlog, searchlength, + targetlength, strategy) + + cctx = zstd.ZstdCompressor(compression_params=p) + with cctx.write_to(io.BytesIO()): + pass + + @hypothesis.given(s_windowlog, s_chainlog, s_hashlog, s_searchlog, + s_searchlength, s_targetlength, s_strategy) + def test_estimate_compression_context_size(self, windowlog, chainlog, + hashlog, searchlog, + searchlength, targetlength, + strategy): + if searchlength == zstd.SEARCHLENGTH_MIN and strategy in (zstd.STRATEGY_FAST, zstd.STRATEGY_GREEDY): + searchlength += 1 + elif searchlength == zstd.SEARCHLENGTH_MAX and strategy != zstd.STRATEGY_FAST: + searchlength -= 1 + + p = zstd.CompressionParameters(windowlog, chainlog, hashlog, + searchlog, searchlength, + targetlength, strategy) + size = zstd.estimate_compression_context_size(p)
--- a/contrib/python-zstandard/tests/test_decompressor.py Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/python-zstandard/tests/test_decompressor.py Tue Apr 18 12:24:34 2017 -0400 @@ -10,7 +10,10 @@ import zstd -from .common import OpCountingBytesIO +from .common import ( + make_cffi, + OpCountingBytesIO, +) if sys.version_info[0] >= 3: @@ -19,6 +22,7 @@ next = lambda it: it.next() +@make_cffi class TestDecompressor_decompress(unittest.TestCase): def test_empty_input(self): dctx = zstd.ZstdDecompressor() @@ -45,7 +49,7 @@ compressed = cctx.compress(b'foobar') dctx = zstd.ZstdDecompressor() - decompressed = dctx.decompress(compressed) + decompressed = dctx.decompress(compressed) self.assertEqual(decompressed, b'foobar') def test_max_output_size(self): @@ -119,6 +123,7 @@ self.assertEqual(decompressed, sources[i]) +@make_cffi class TestDecompressor_copy_stream(unittest.TestCase): def test_no_read(self): source = object() @@ -180,6 +185,7 @@ self.assertEqual(dest._write_count, len(dest.getvalue())) +@make_cffi class TestDecompressor_decompressobj(unittest.TestCase): def test_simple(self): data = zstd.ZstdCompressor(level=1).compress(b'foobar') @@ -207,6 +213,7 @@ return buffer.getvalue() +@make_cffi class TestDecompressor_write_to(unittest.TestCase): def test_empty_roundtrip(self): cctx = zstd.ZstdCompressor() @@ -256,14 +263,14 @@ buffer = io.BytesIO() cctx = zstd.ZstdCompressor(dict_data=d) with cctx.write_to(buffer) as compressor: - compressor.write(orig) + self.assertEqual(compressor.write(orig), 1544) compressed = buffer.getvalue() buffer = io.BytesIO() dctx = zstd.ZstdDecompressor(dict_data=d) with dctx.write_to(buffer) as decompressor: - decompressor.write(compressed) + self.assertEqual(decompressor.write(compressed), len(orig)) self.assertEqual(buffer.getvalue(), orig) @@ -286,11 +293,11 @@ c = s.pack(c) decompressor.write(c) - self.assertEqual(dest.getvalue(), b'foobarfoobar') self.assertEqual(dest._write_count, len(dest.getvalue())) +@make_cffi class TestDecompressor_read_from(unittest.TestCase): def test_type_validation(self): dctx = zstd.ZstdDecompressor() @@ -302,7 +309,7 @@ dctx.read_from(b'foobar') with self.assertRaisesRegexp(ValueError, 'must pass an object with a read'): - dctx.read_from(True) + b''.join(dctx.read_from(True)) def test_empty_input(self): dctx = zstd.ZstdDecompressor() @@ -351,7 +358,7 @@ dctx = zstd.ZstdDecompressor() with self.assertRaisesRegexp(ValueError, 'skip_bytes must be smaller than read_size'): - dctx.read_from(b'', skip_bytes=1, read_size=1) + b''.join(dctx.read_from(b'', skip_bytes=1, read_size=1)) with self.assertRaisesRegexp(ValueError, 'skip_bytes larger than first input chunk'): b''.join(dctx.read_from(b'foobar', skip_bytes=10)) @@ -476,3 +483,259 @@ self.assertEqual(len(chunk), 1) self.assertEqual(source._read_count, len(source.getvalue())) + + +@make_cffi +class TestDecompressor_content_dict_chain(unittest.TestCase): + def test_bad_inputs_simple(self): + dctx = zstd.ZstdDecompressor() + + with self.assertRaises(TypeError): + dctx.decompress_content_dict_chain(b'foo') + + with self.assertRaises(TypeError): + dctx.decompress_content_dict_chain((b'foo', b'bar')) + + with self.assertRaisesRegexp(ValueError, 'empty input chain'): + dctx.decompress_content_dict_chain([]) + + with self.assertRaisesRegexp(ValueError, 'chunk 0 must be bytes'): + dctx.decompress_content_dict_chain([u'foo']) + + with self.assertRaisesRegexp(ValueError, 'chunk 0 must be bytes'): + dctx.decompress_content_dict_chain([True]) + + with self.assertRaisesRegexp(ValueError, 'chunk 0 is too small to contain a zstd frame'): + dctx.decompress_content_dict_chain([zstd.FRAME_HEADER]) + + with self.assertRaisesRegexp(ValueError, 'chunk 0 is not a valid zstd frame'): + dctx.decompress_content_dict_chain([b'foo' * 8]) + + no_size = zstd.ZstdCompressor().compress(b'foo' * 64) + + with self.assertRaisesRegexp(ValueError, 'chunk 0 missing content size in frame'): + dctx.decompress_content_dict_chain([no_size]) + + # Corrupt first frame. + frame = zstd.ZstdCompressor(write_content_size=True).compress(b'foo' * 64) + frame = frame[0:12] + frame[15:] + with self.assertRaisesRegexp(zstd.ZstdError, 'could not decompress chunk 0'): + dctx.decompress_content_dict_chain([frame]) + + def test_bad_subsequent_input(self): + initial = zstd.ZstdCompressor(write_content_size=True).compress(b'foo' * 64) + + dctx = zstd.ZstdDecompressor() + + with self.assertRaisesRegexp(ValueError, 'chunk 1 must be bytes'): + dctx.decompress_content_dict_chain([initial, u'foo']) + + with self.assertRaisesRegexp(ValueError, 'chunk 1 must be bytes'): + dctx.decompress_content_dict_chain([initial, None]) + + with self.assertRaisesRegexp(ValueError, 'chunk 1 is too small to contain a zstd frame'): + dctx.decompress_content_dict_chain([initial, zstd.FRAME_HEADER]) + + with self.assertRaisesRegexp(ValueError, 'chunk 1 is not a valid zstd frame'): + dctx.decompress_content_dict_chain([initial, b'foo' * 8]) + + no_size = zstd.ZstdCompressor().compress(b'foo' * 64) + + with self.assertRaisesRegexp(ValueError, 'chunk 1 missing content size in frame'): + dctx.decompress_content_dict_chain([initial, no_size]) + + # Corrupt second frame. + cctx = zstd.ZstdCompressor(write_content_size=True, dict_data=zstd.ZstdCompressionDict(b'foo' * 64)) + frame = cctx.compress(b'bar' * 64) + frame = frame[0:12] + frame[15:] + + with self.assertRaisesRegexp(zstd.ZstdError, 'could not decompress chunk 1'): + dctx.decompress_content_dict_chain([initial, frame]) + + def test_simple(self): + original = [ + b'foo' * 64, + b'foobar' * 64, + b'baz' * 64, + b'foobaz' * 64, + b'foobarbaz' * 64, + ] + + chunks = [] + chunks.append(zstd.ZstdCompressor(write_content_size=True).compress(original[0])) + for i, chunk in enumerate(original[1:]): + d = zstd.ZstdCompressionDict(original[i]) + cctx = zstd.ZstdCompressor(dict_data=d, write_content_size=True) + chunks.append(cctx.compress(chunk)) + + for i in range(1, len(original)): + chain = chunks[0:i] + expected = original[i - 1] + dctx = zstd.ZstdDecompressor() + decompressed = dctx.decompress_content_dict_chain(chain) + self.assertEqual(decompressed, expected) + + +# TODO enable for CFFI +class TestDecompressor_multi_decompress_to_buffer(unittest.TestCase): + def test_invalid_inputs(self): + dctx = zstd.ZstdDecompressor() + + with self.assertRaises(TypeError): + dctx.multi_decompress_to_buffer(True) + + with self.assertRaises(TypeError): + dctx.multi_decompress_to_buffer((1, 2)) + + with self.assertRaisesRegexp(TypeError, 'item 0 not a bytes like object'): + dctx.multi_decompress_to_buffer([u'foo']) + + with self.assertRaisesRegexp(ValueError, 'could not determine decompressed size of item 0'): + dctx.multi_decompress_to_buffer([b'foobarbaz']) + + def test_list_input(self): + cctx = zstd.ZstdCompressor(write_content_size=True) + + original = [b'foo' * 4, b'bar' * 6] + frames = [cctx.compress(d) for d in original] + + dctx = zstd.ZstdDecompressor() + result = dctx.multi_decompress_to_buffer(frames) + + self.assertEqual(len(result), len(frames)) + self.assertEqual(result.size(), sum(map(len, original))) + + for i, data in enumerate(original): + self.assertEqual(result[i].tobytes(), data) + + self.assertEqual(result[0].offset, 0) + self.assertEqual(len(result[0]), 12) + self.assertEqual(result[1].offset, 12) + self.assertEqual(len(result[1]), 18) + + def test_list_input_frame_sizes(self): + cctx = zstd.ZstdCompressor(write_content_size=False) + + original = [b'foo' * 4, b'bar' * 6, b'baz' * 8] + frames = [cctx.compress(d) for d in original] + sizes = struct.pack('=' + 'Q' * len(original), *map(len, original)) + + dctx = zstd.ZstdDecompressor() + result = dctx.multi_decompress_to_buffer(frames, decompressed_sizes=sizes) + + self.assertEqual(len(result), len(frames)) + self.assertEqual(result.size(), sum(map(len, original))) + + for i, data in enumerate(original): + self.assertEqual(result[i].tobytes(), data) + + def test_buffer_with_segments_input(self): + cctx = zstd.ZstdCompressor(write_content_size=True) + + original = [b'foo' * 4, b'bar' * 6] + frames = [cctx.compress(d) for d in original] + + dctx = zstd.ZstdDecompressor() + + segments = struct.pack('=QQQQ', 0, len(frames[0]), len(frames[0]), len(frames[1])) + b = zstd.BufferWithSegments(b''.join(frames), segments) + + result = dctx.multi_decompress_to_buffer(b) + + self.assertEqual(len(result), len(frames)) + self.assertEqual(result[0].offset, 0) + self.assertEqual(len(result[0]), 12) + self.assertEqual(result[1].offset, 12) + self.assertEqual(len(result[1]), 18) + + def test_buffer_with_segments_sizes(self): + cctx = zstd.ZstdCompressor(write_content_size=False) + original = [b'foo' * 4, b'bar' * 6, b'baz' * 8] + frames = [cctx.compress(d) for d in original] + sizes = struct.pack('=' + 'Q' * len(original), *map(len, original)) + + segments = struct.pack('=QQQQQQ', 0, len(frames[0]), + len(frames[0]), len(frames[1]), + len(frames[0]) + len(frames[1]), len(frames[2])) + b = zstd.BufferWithSegments(b''.join(frames), segments) + + dctx = zstd.ZstdDecompressor() + result = dctx.multi_decompress_to_buffer(b, decompressed_sizes=sizes) + + self.assertEqual(len(result), len(frames)) + self.assertEqual(result.size(), sum(map(len, original))) + + for i, data in enumerate(original): + self.assertEqual(result[i].tobytes(), data) + + def test_buffer_with_segments_collection_input(self): + cctx = zstd.ZstdCompressor(write_content_size=True) + + original = [ + b'foo0' * 2, + b'foo1' * 3, + b'foo2' * 4, + b'foo3' * 5, + b'foo4' * 6, + ] + + frames = cctx.multi_compress_to_buffer(original) + + # Check round trip. + dctx = zstd.ZstdDecompressor() + decompressed = dctx.multi_decompress_to_buffer(frames, threads=3) + + self.assertEqual(len(decompressed), len(original)) + + for i, data in enumerate(original): + self.assertEqual(data, decompressed[i].tobytes()) + + # And a manual mode. + b = b''.join([frames[0].tobytes(), frames[1].tobytes()]) + b1 = zstd.BufferWithSegments(b, struct.pack('=QQQQ', + 0, len(frames[0]), + len(frames[0]), len(frames[1]))) + + b = b''.join([frames[2].tobytes(), frames[3].tobytes(), frames[4].tobytes()]) + b2 = zstd.BufferWithSegments(b, struct.pack('=QQQQQQ', + 0, len(frames[2]), + len(frames[2]), len(frames[3]), + len(frames[2]) + len(frames[3]), len(frames[4]))) + + c = zstd.BufferWithSegmentsCollection(b1, b2) + + dctx = zstd.ZstdDecompressor() + decompressed = dctx.multi_decompress_to_buffer(c) + + self.assertEqual(len(decompressed), 5) + for i in range(5): + self.assertEqual(decompressed[i].tobytes(), original[i]) + + def test_multiple_threads(self): + cctx = zstd.ZstdCompressor(write_content_size=True) + + frames = [] + frames.extend(cctx.compress(b'x' * 64) for i in range(256)) + frames.extend(cctx.compress(b'y' * 64) for i in range(256)) + + dctx = zstd.ZstdDecompressor() + result = dctx.multi_decompress_to_buffer(frames, threads=-1) + + self.assertEqual(len(result), len(frames)) + self.assertEqual(result.size(), 2 * 64 * 256) + self.assertEqual(result[0].tobytes(), b'x' * 64) + self.assertEqual(result[256].tobytes(), b'y' * 64) + + def test_item_failure(self): + cctx = zstd.ZstdCompressor(write_content_size=True) + frames = [cctx.compress(b'x' * 128), cctx.compress(b'y' * 128)] + + frames[1] = frames[1] + b'extra' + + dctx = zstd.ZstdDecompressor() + + with self.assertRaisesRegexp(zstd.ZstdError, 'error decompressing item 1: Src size incorrect'): + dctx.multi_decompress_to_buffer(frames) + + with self.assertRaisesRegexp(zstd.ZstdError, 'error decompressing item 1: Src size incorrect'): + dctx.multi_decompress_to_buffer(frames, threads=2)
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/contrib/python-zstandard/tests/test_decompressor_fuzzing.py Tue Apr 18 12:24:34 2017 -0400 @@ -0,0 +1,151 @@ +import io +import os + +try: + import unittest2 as unittest +except ImportError: + import unittest + +try: + import hypothesis + import hypothesis.strategies as strategies +except ImportError: + raise unittest.SkipTest('hypothesis not available') + +import zstd + +from . common import ( + make_cffi, + random_input_data, +) + + +@unittest.skipUnless('ZSTD_SLOW_TESTS' in os.environ, 'ZSTD_SLOW_TESTS not set') +@make_cffi +class TestDecompressor_write_to_fuzzing(unittest.TestCase): + @hypothesis.given(original=strategies.sampled_from(random_input_data()), + level=strategies.integers(min_value=1, max_value=5), + write_size=strategies.integers(min_value=1, max_value=8192), + input_sizes=strategies.streaming( + strategies.integers(min_value=1, max_value=4096))) + def test_write_size_variance(self, original, level, write_size, input_sizes): + input_sizes = iter(input_sizes) + + cctx = zstd.ZstdCompressor(level=level) + frame = cctx.compress(original) + + dctx = zstd.ZstdDecompressor() + source = io.BytesIO(frame) + dest = io.BytesIO() + + with dctx.write_to(dest, write_size=write_size) as decompressor: + while True: + chunk = source.read(next(input_sizes)) + if not chunk: + break + + decompressor.write(chunk) + + self.assertEqual(dest.getvalue(), original) + + +@unittest.skipUnless('ZSTD_SLOW_TESTS' in os.environ, 'ZSTD_SLOW_TESTS not set') +@make_cffi +class TestDecompressor_copy_stream_fuzzing(unittest.TestCase): + @hypothesis.given(original=strategies.sampled_from(random_input_data()), + level=strategies.integers(min_value=1, max_value=5), + read_size=strategies.integers(min_value=1, max_value=8192), + write_size=strategies.integers(min_value=1, max_value=8192)) + def test_read_write_size_variance(self, original, level, read_size, write_size): + cctx = zstd.ZstdCompressor(level=level) + frame = cctx.compress(original) + + source = io.BytesIO(frame) + dest = io.BytesIO() + + dctx = zstd.ZstdDecompressor() + dctx.copy_stream(source, dest, read_size=read_size, write_size=write_size) + + self.assertEqual(dest.getvalue(), original) + + +@unittest.skipUnless('ZSTD_SLOW_TESTS' in os.environ, 'ZSTD_SLOW_TESTS not set') +@make_cffi +class TestDecompressor_decompressobj_fuzzing(unittest.TestCase): + @hypothesis.given(original=strategies.sampled_from(random_input_data()), + level=strategies.integers(min_value=1, max_value=5), + chunk_sizes=strategies.streaming( + strategies.integers(min_value=1, max_value=4096))) + def test_random_input_sizes(self, original, level, chunk_sizes): + chunk_sizes = iter(chunk_sizes) + + cctx = zstd.ZstdCompressor(level=level) + frame = cctx.compress(original) + + source = io.BytesIO(frame) + + dctx = zstd.ZstdDecompressor() + dobj = dctx.decompressobj() + + chunks = [] + while True: + chunk = source.read(next(chunk_sizes)) + if not chunk: + break + + chunks.append(dobj.decompress(chunk)) + + self.assertEqual(b''.join(chunks), original) + + +@unittest.skipUnless('ZSTD_SLOW_TESTS' in os.environ, 'ZSTD_SLOW_TESTS not set') +@make_cffi +class TestDecompressor_read_from_fuzzing(unittest.TestCase): + @hypothesis.given(original=strategies.sampled_from(random_input_data()), + level=strategies.integers(min_value=1, max_value=5), + read_size=strategies.integers(min_value=1, max_value=4096), + write_size=strategies.integers(min_value=1, max_value=4096)) + def test_read_write_size_variance(self, original, level, read_size, write_size): + cctx = zstd.ZstdCompressor(level=level) + frame = cctx.compress(original) + + source = io.BytesIO(frame) + + dctx = zstd.ZstdDecompressor() + chunks = list(dctx.read_from(source, read_size=read_size, write_size=write_size)) + + self.assertEqual(b''.join(chunks), original) + + +@unittest.skipUnless('ZSTD_SLOW_TESTS' in os.environ, 'ZSTD_SLOW_TESTS not set') +class TestDecompressor_multi_decompress_to_buffer_fuzzing(unittest.TestCase): + @hypothesis.given(original=strategies.lists(strategies.sampled_from(random_input_data()), + min_size=1, max_size=1024), + threads=strategies.integers(min_value=1, max_value=8), + use_dict=strategies.booleans()) + def test_data_equivalence(self, original, threads, use_dict): + kwargs = {} + if use_dict: + kwargs['dict_data'] = zstd.ZstdCompressionDict(original[0]) + + cctx = zstd.ZstdCompressor(level=1, + write_content_size=True, + write_checksum=True, + **kwargs) + + frames_buffer = cctx.multi_compress_to_buffer(original, threads=-1) + + dctx = zstd.ZstdDecompressor(**kwargs) + + result = dctx.multi_decompress_to_buffer(frames_buffer) + + self.assertEqual(len(result), len(original)) + for i, frame in enumerate(result): + self.assertEqual(frame.tobytes(), original[i]) + + frames_list = [f.tobytes() for f in frames_buffer] + result = dctx.multi_decompress_to_buffer(frames_list) + + self.assertEqual(len(result), len(original)) + for i, frame in enumerate(result): + self.assertEqual(frame.tobytes(), original[i])
--- a/contrib/python-zstandard/tests/test_estimate_sizes.py Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/python-zstandard/tests/test_estimate_sizes.py Tue Apr 18 12:24:34 2017 -0400 @@ -5,7 +5,12 @@ import zstd +from . common import ( + make_cffi, +) + +@make_cffi class TestSizes(unittest.TestCase): def test_decompression_size(self): size = zstd.estimate_decompression_context_size()
--- a/contrib/python-zstandard/tests/test_module_attributes.py Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/python-zstandard/tests/test_module_attributes.py Tue Apr 18 12:24:34 2017 -0400 @@ -7,9 +7,15 @@ import zstd +from . common import ( + make_cffi, +) + + +@make_cffi class TestModuleAttributes(unittest.TestCase): def test_version(self): - self.assertEqual(zstd.ZSTD_VERSION, (1, 1, 2)) + self.assertEqual(zstd.ZSTD_VERSION, (1, 1, 3)) def test_constants(self): self.assertEqual(zstd.MAX_COMPRESSION_LEVEL, 22) @@ -45,4 +51,4 @@ ) for a in attrs: - self.assertTrue(hasattr(zstd, a)) + self.assertTrue(hasattr(zstd, a), a)
--- a/contrib/python-zstandard/tests/test_roundtrip.py Tue Apr 18 11:22:42 2017 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,64 +0,0 @@ -import io - -try: - import unittest2 as unittest -except ImportError: - import unittest - -try: - import hypothesis - import hypothesis.strategies as strategies -except ImportError: - raise unittest.SkipTest('hypothesis not available') - -import zstd - - -compression_levels = strategies.integers(min_value=1, max_value=22) - - -class TestRoundTrip(unittest.TestCase): - @hypothesis.given(strategies.binary(), compression_levels) - def test_compress_write_to(self, data, level): - """Random data from compress() roundtrips via write_to.""" - cctx = zstd.ZstdCompressor(level=level) - compressed = cctx.compress(data) - - buffer = io.BytesIO() - dctx = zstd.ZstdDecompressor() - with dctx.write_to(buffer) as decompressor: - decompressor.write(compressed) - - self.assertEqual(buffer.getvalue(), data) - - @hypothesis.given(strategies.binary(), compression_levels) - def test_compressor_write_to_decompressor_write_to(self, data, level): - """Random data from compressor write_to roundtrips via write_to.""" - compress_buffer = io.BytesIO() - decompressed_buffer = io.BytesIO() - - cctx = zstd.ZstdCompressor(level=level) - with cctx.write_to(compress_buffer) as compressor: - compressor.write(data) - - dctx = zstd.ZstdDecompressor() - with dctx.write_to(decompressed_buffer) as decompressor: - decompressor.write(compress_buffer.getvalue()) - - self.assertEqual(decompressed_buffer.getvalue(), data) - - @hypothesis.given(strategies.binary(average_size=1048576)) - @hypothesis.settings(perform_health_check=False) - def test_compressor_write_to_decompressor_write_to_larger(self, data): - compress_buffer = io.BytesIO() - decompressed_buffer = io.BytesIO() - - cctx = zstd.ZstdCompressor(level=5) - with cctx.write_to(compress_buffer) as compressor: - compressor.write(data) - - dctx = zstd.ZstdDecompressor() - with dctx.write_to(decompressed_buffer) as decompressor: - decompressor.write(compress_buffer.getvalue()) - - self.assertEqual(decompressed_buffer.getvalue(), data)
--- a/contrib/python-zstandard/tests/test_train_dictionary.py Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/python-zstandard/tests/test_train_dictionary.py Tue Apr 18 12:24:34 2017 -0400 @@ -7,6 +7,9 @@ import zstd +from . common import ( + make_cffi, +) if sys.version_info[0] >= 3: int_type = int @@ -14,6 +17,7 @@ int_type = long +@make_cffi class TestTrainDictionary(unittest.TestCase): def test_no_args(self): with self.assertRaises(TypeError): @@ -44,3 +48,63 @@ data = d.as_bytes() self.assertEqual(data[0:4], b'\x37\xa4\x30\xec') + + def test_set_dict_id(self): + samples = [] + for i in range(128): + samples.append(b'foo' * 64) + samples.append(b'foobar' * 64) + + d = zstd.train_dictionary(8192, samples, dict_id=42) + self.assertEqual(d.dict_id(), 42) + + +@make_cffi +class TestTrainCoverDictionary(unittest.TestCase): + def test_no_args(self): + with self.assertRaises(TypeError): + zstd.train_cover_dictionary() + + def test_bad_args(self): + with self.assertRaises(TypeError): + zstd.train_cover_dictionary(8192, u'foo') + + with self.assertRaises(ValueError): + zstd.train_cover_dictionary(8192, [u'foo']) + + def test_basic(self): + samples = [] + for i in range(128): + samples.append(b'foo' * 64) + samples.append(b'foobar' * 64) + + d = zstd.train_cover_dictionary(8192, samples, k=64, d=16) + self.assertIsInstance(d.dict_id(), int_type) + + data = d.as_bytes() + self.assertEqual(data[0:4], b'\x37\xa4\x30\xec') + + self.assertEqual(d.k, 64) + self.assertEqual(d.d, 16) + + def test_set_dict_id(self): + samples = [] + for i in range(128): + samples.append(b'foo' * 64) + samples.append(b'foobar' * 64) + + d = zstd.train_cover_dictionary(8192, samples, k=64, d=16, + dict_id=42) + self.assertEqual(d.dict_id(), 42) + + def test_optimize(self): + samples = [] + for i in range(128): + samples.append(b'foo' * 64) + samples.append(b'foobar' * 64) + + d = zstd.train_cover_dictionary(8192, samples, optimize=True, + threads=-1, steps=1, d=16) + + self.assertEqual(d.k, 16) + self.assertEqual(d.d, 16)
--- a/contrib/python-zstandard/zstd.c Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/python-zstandard/zstd.c Tue Apr 18 12:24:34 2017 -0400 @@ -8,6 +8,14 @@ /* A Python C extension for Zstandard. */ +#if defined(_WIN32) +#define WIN32_LEAN_AND_MEAN +#include <Windows.h> +#elif defined(__APPLE__) || defined(__OpenBSD__) || defined(__FreeBSD__) || defined(__NetBSD__) || defined(__DragonFly__) +#include <sys/types.h> +#include <sys/sysctl.h> +#endif + #include "python-zstandard.h" PyObject *ZstdError; @@ -34,6 +42,11 @@ "Obtains a ``CompressionParameters`` instance from a compression level and\n" "optional input size and dictionary size"); +PyDoc_STRVAR(get_frame_parameters__doc__, +"get_frame_parameters(data)\n" +"\n" +"Obtains a ``FrameParameters`` instance by parsing data.\n"); + PyDoc_STRVAR(train_dictionary__doc__, "train_dictionary(dict_size, samples)\n" "\n" @@ -44,25 +57,42 @@ "\n" "The raw dictionary content will be returned\n"); +PyDoc_STRVAR(train_cover_dictionary__doc__, +"train_cover_dictionary(dict_size, samples, k=None, d=None, notifications=0, dict_id=0, level=0)\n" +"\n" +"Train a dictionary from sample data using the COVER algorithm.\n" +"\n" +"This behaves like ``train_dictionary()`` except a different algorithm is\n" +"used to create the dictionary. The algorithm has 2 parameters: ``k`` and\n" +"``d``. These control the *segment size* and *dmer size*. A reasonable range\n" +"for ``k`` is ``[16, 2048+]``. A reasonable range for ``d`` is ``[6, 16]``.\n" +"``d`` must be less than or equal to ``k``.\n" +); + static char zstd_doc[] = "Interface to zstandard"; static PyMethodDef zstd_methods[] = { + /* TODO remove since it is a method on CompressionParameters. */ { "estimate_compression_context_size", (PyCFunction)estimate_compression_context_size, METH_VARARGS, estimate_compression_context_size__doc__ }, { "estimate_decompression_context_size", (PyCFunction)estimate_decompression_context_size, METH_NOARGS, estimate_decompression_context_size__doc__ }, { "get_compression_parameters", (PyCFunction)get_compression_parameters, METH_VARARGS, get_compression_parameters__doc__ }, + { "get_frame_parameters", (PyCFunction)get_frame_parameters, + METH_VARARGS, get_frame_parameters__doc__ }, { "train_dictionary", (PyCFunction)train_dictionary, METH_VARARGS | METH_KEYWORDS, train_dictionary__doc__ }, + { "train_cover_dictionary", (PyCFunction)train_cover_dictionary, + METH_VARARGS | METH_KEYWORDS, train_cover_dictionary__doc__ }, { NULL, NULL } }; +void bufferutil_module_init(PyObject* mod); void compressobj_module_init(PyObject* mod); void compressor_module_init(PyObject* mod); void compressionparams_module_init(PyObject* mod); void constants_module_init(PyObject* mod); -void dictparams_module_init(PyObject* mod); void compressiondict_module_init(PyObject* mod); void compressionwriter_module_init(PyObject* mod); void compressoriterator_module_init(PyObject* mod); @@ -70,6 +100,7 @@ void decompressobj_module_init(PyObject* mod); void decompressionwriter_module_init(PyObject* mod); void decompressoriterator_module_init(PyObject* mod); +void frameparams_module_init(PyObject* mod); void zstd_module_init(PyObject* m) { /* python-zstandard relies on unstable zstd C API features. This means @@ -87,13 +118,13 @@ We detect this mismatch here and refuse to load the module if this scenario is detected. */ - if (ZSTD_VERSION_NUMBER != 10102 || ZSTD_versionNumber() != 10102) { + if (ZSTD_VERSION_NUMBER != 10103 || ZSTD_versionNumber() != 10103) { PyErr_SetString(PyExc_ImportError, "zstd C API mismatch; Python bindings not compiled against expected zstd version"); return; } + bufferutil_module_init(m); compressionparams_module_init(m); - dictparams_module_init(m); compressiondict_module_init(m); compressobj_module_init(m); compressor_module_init(m); @@ -104,6 +135,7 @@ decompressobj_module_init(m); decompressionwriter_module_init(m); decompressoriterator_module_init(m); + frameparams_module_init(m); } #if PY_MAJOR_VERSION >= 3 @@ -134,3 +166,48 @@ } } #endif + +/* Attempt to resolve the number of CPUs in the system. */ +int cpu_count() { + int count = 0; + +#if defined(_WIN32) + SYSTEM_INFO si; + si.dwNumberOfProcessors = 0; + GetSystemInfo(&si); + count = si.dwNumberOfProcessors; +#elif defined(__APPLE__) + int num; + size_t size = sizeof(int); + + if (0 == sysctlbyname("hw.logicalcpu", &num, &size, NULL, 0)) { + count = num; + } +#elif defined(__linux__) + count = sysconf(_SC_NPROCESSORS_ONLN); +#elif defined(__OpenBSD__) || defined(__FreeBSD__) || defined(__NetBSD__) || defined(__DragonFly__) + int mib[2]; + size_t len = sizeof(count); + mib[0] = CTL_HW; + mib[1] = HW_NCPU; + if (0 != sysctl(mib, 2, &count, &len, NULL, 0)) { + count = 0; + } +#elif defined(__hpux) + count = mpctl(MPC_GETNUMSPUS, NULL, NULL); +#endif + + return count; +} + +size_t roundpow2(size_t i) { + i--; + i |= i >> 1; + i |= i >> 2; + i |= i >> 4; + i |= i >> 8; + i |= i >> 16; + i++; + + return i; +}
--- a/contrib/python-zstandard/zstd/common/mem.h Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/python-zstandard/zstd/common/mem.h Tue Apr 18 12:24:34 2017 -0400 @@ -39,7 +39,7 @@ #endif /* code only tested on 32 and 64 bits systems */ -#define MEM_STATIC_ASSERT(c) { enum { XXH_static_assert = 1/(int)(!!(c)) }; } +#define MEM_STATIC_ASSERT(c) { enum { MEM_static_assert = 1/(int)(!!(c)) }; } MEM_STATIC void MEM_check(void) { MEM_STATIC_ASSERT((sizeof(size_t)==4) || (sizeof(size_t)==8)); }
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/contrib/python-zstandard/zstd/common/pool.c Tue Apr 18 12:24:34 2017 -0400 @@ -0,0 +1,194 @@ +/** + * Copyright (c) 2016-present, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under the BSD-style license found in the + * LICENSE file in the root directory of this source tree. An additional grant + * of patent rights can be found in the PATENTS file in the same directory. + */ + + +/* ====== Dependencies ======= */ +#include <stddef.h> /* size_t */ +#include <stdlib.h> /* malloc, calloc, free */ +#include "pool.h" + +/* ====== Compiler specifics ====== */ +#if defined(_MSC_VER) +# pragma warning(disable : 4204) /* disable: C4204: non-constant aggregate initializer */ +#endif + + +#ifdef ZSTD_MULTITHREAD + +#include "threading.h" /* pthread adaptation */ + +/* A job is a function and an opaque argument */ +typedef struct POOL_job_s { + POOL_function function; + void *opaque; +} POOL_job; + +struct POOL_ctx_s { + /* Keep track of the threads */ + pthread_t *threads; + size_t numThreads; + + /* The queue is a circular buffer */ + POOL_job *queue; + size_t queueHead; + size_t queueTail; + size_t queueSize; + /* The mutex protects the queue */ + pthread_mutex_t queueMutex; + /* Condition variable for pushers to wait on when the queue is full */ + pthread_cond_t queuePushCond; + /* Condition variables for poppers to wait on when the queue is empty */ + pthread_cond_t queuePopCond; + /* Indicates if the queue is shutting down */ + int shutdown; +}; + +/* POOL_thread() : + Work thread for the thread pool. + Waits for jobs and executes them. + @returns : NULL on failure else non-null. +*/ +static void* POOL_thread(void* opaque) { + POOL_ctx* const ctx = (POOL_ctx*)opaque; + if (!ctx) { return NULL; } + for (;;) { + /* Lock the mutex and wait for a non-empty queue or until shutdown */ + pthread_mutex_lock(&ctx->queueMutex); + while (ctx->queueHead == ctx->queueTail && !ctx->shutdown) { + pthread_cond_wait(&ctx->queuePopCond, &ctx->queueMutex); + } + /* empty => shutting down: so stop */ + if (ctx->queueHead == ctx->queueTail) { + pthread_mutex_unlock(&ctx->queueMutex); + return opaque; + } + /* Pop a job off the queue */ + { POOL_job const job = ctx->queue[ctx->queueHead]; + ctx->queueHead = (ctx->queueHead + 1) % ctx->queueSize; + /* Unlock the mutex, signal a pusher, and run the job */ + pthread_mutex_unlock(&ctx->queueMutex); + pthread_cond_signal(&ctx->queuePushCond); + job.function(job.opaque); + } + } + /* Unreachable */ +} + +POOL_ctx *POOL_create(size_t numThreads, size_t queueSize) { + POOL_ctx *ctx; + /* Check the parameters */ + if (!numThreads || !queueSize) { return NULL; } + /* Allocate the context and zero initialize */ + ctx = (POOL_ctx *)calloc(1, sizeof(POOL_ctx)); + if (!ctx) { return NULL; } + /* Initialize the job queue. + * It needs one extra space since one space is wasted to differentiate empty + * and full queues. + */ + ctx->queueSize = queueSize + 1; + ctx->queue = (POOL_job *)malloc(ctx->queueSize * sizeof(POOL_job)); + ctx->queueHead = 0; + ctx->queueTail = 0; + pthread_mutex_init(&ctx->queueMutex, NULL); + pthread_cond_init(&ctx->queuePushCond, NULL); + pthread_cond_init(&ctx->queuePopCond, NULL); + ctx->shutdown = 0; + /* Allocate space for the thread handles */ + ctx->threads = (pthread_t *)malloc(numThreads * sizeof(pthread_t)); + ctx->numThreads = 0; + /* Check for errors */ + if (!ctx->threads || !ctx->queue) { POOL_free(ctx); return NULL; } + /* Initialize the threads */ + { size_t i; + for (i = 0; i < numThreads; ++i) { + if (pthread_create(&ctx->threads[i], NULL, &POOL_thread, ctx)) { + ctx->numThreads = i; + POOL_free(ctx); + return NULL; + } } + ctx->numThreads = numThreads; + } + return ctx; +} + +/*! POOL_join() : + Shutdown the queue, wake any sleeping threads, and join all of the threads. +*/ +static void POOL_join(POOL_ctx *ctx) { + /* Shut down the queue */ + pthread_mutex_lock(&ctx->queueMutex); + ctx->shutdown = 1; + pthread_mutex_unlock(&ctx->queueMutex); + /* Wake up sleeping threads */ + pthread_cond_broadcast(&ctx->queuePushCond); + pthread_cond_broadcast(&ctx->queuePopCond); + /* Join all of the threads */ + { size_t i; + for (i = 0; i < ctx->numThreads; ++i) { + pthread_join(ctx->threads[i], NULL); + } } +} + +void POOL_free(POOL_ctx *ctx) { + if (!ctx) { return; } + POOL_join(ctx); + pthread_mutex_destroy(&ctx->queueMutex); + pthread_cond_destroy(&ctx->queuePushCond); + pthread_cond_destroy(&ctx->queuePopCond); + if (ctx->queue) free(ctx->queue); + if (ctx->threads) free(ctx->threads); + free(ctx); +} + +void POOL_add(void *ctxVoid, POOL_function function, void *opaque) { + POOL_ctx *ctx = (POOL_ctx *)ctxVoid; + if (!ctx) { return; } + + pthread_mutex_lock(&ctx->queueMutex); + { POOL_job const job = {function, opaque}; + /* Wait until there is space in the queue for the new job */ + size_t newTail = (ctx->queueTail + 1) % ctx->queueSize; + while (ctx->queueHead == newTail && !ctx->shutdown) { + pthread_cond_wait(&ctx->queuePushCond, &ctx->queueMutex); + newTail = (ctx->queueTail + 1) % ctx->queueSize; + } + /* The queue is still going => there is space */ + if (!ctx->shutdown) { + ctx->queue[ctx->queueTail] = job; + ctx->queueTail = newTail; + } + } + pthread_mutex_unlock(&ctx->queueMutex); + pthread_cond_signal(&ctx->queuePopCond); +} + +#else /* ZSTD_MULTITHREAD not defined */ +/* No multi-threading support */ + +/* We don't need any data, but if it is empty malloc() might return NULL. */ +struct POOL_ctx_s { + int data; +}; + +POOL_ctx *POOL_create(size_t numThreads, size_t queueSize) { + (void)numThreads; + (void)queueSize; + return (POOL_ctx *)malloc(sizeof(POOL_ctx)); +} + +void POOL_free(POOL_ctx *ctx) { + if (ctx) free(ctx); +} + +void POOL_add(void *ctx, POOL_function function, void *opaque) { + (void)ctx; + function(opaque); +} + +#endif /* ZSTD_MULTITHREAD */
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/contrib/python-zstandard/zstd/common/pool.h Tue Apr 18 12:24:34 2017 -0400 @@ -0,0 +1,56 @@ +/** + * Copyright (c) 2016-present, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under the BSD-style license found in the + * LICENSE file in the root directory of this source tree. An additional grant + * of patent rights can be found in the PATENTS file in the same directory. + */ +#ifndef POOL_H +#define POOL_H + +#if defined (__cplusplus) +extern "C" { +#endif + + +#include <stddef.h> /* size_t */ + +typedef struct POOL_ctx_s POOL_ctx; + +/*! POOL_create() : + Create a thread pool with at most `numThreads` threads. + `numThreads` must be at least 1. + The maximum number of queued jobs before blocking is `queueSize`. + `queueSize` must be at least 1. + @return : The POOL_ctx pointer on success else NULL. +*/ +POOL_ctx *POOL_create(size_t numThreads, size_t queueSize); + +/*! POOL_free() : + Free a thread pool returned by POOL_create(). +*/ +void POOL_free(POOL_ctx *ctx); + +/*! POOL_function : + The function type that can be added to a thread pool. +*/ +typedef void (*POOL_function)(void *); +/*! POOL_add_function : + The function type for a generic thread pool add function. +*/ +typedef void (*POOL_add_function)(void *, POOL_function, void *); + +/*! POOL_add() : + Add the job `function(opaque)` to the thread pool. + Possibly blocks until there is room in the queue. + Note : The function may be executed asynchronously, so `opaque` must live until the function has been completed. +*/ +void POOL_add(void *ctx, POOL_function function, void *opaque); + + +#if defined (__cplusplus) +} +#endif + +#endif
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/contrib/python-zstandard/zstd/common/threading.c Tue Apr 18 12:24:34 2017 -0400 @@ -0,0 +1,79 @@ + +/** + * Copyright (c) 2016 Tino Reichardt + * All rights reserved. + * + * This source code is licensed under the BSD-style license found in the + * LICENSE file in the root directory of this source tree. An additional grant + * of patent rights can be found in the PATENTS file in the same directory. + * + * You can contact the author at: + * - zstdmt source repository: https://github.com/mcmilk/zstdmt + */ + +/** + * This file will hold wrapper for systems, which do not support pthreads + */ + +/* ====== Compiler specifics ====== */ +#if defined(_MSC_VER) +# pragma warning(disable : 4206) /* disable: C4206: translation unit is empty (when ZSTD_MULTITHREAD is not defined) */ +#endif + + +#if defined(ZSTD_MULTITHREAD) && defined(_WIN32) + +/** + * Windows minimalist Pthread Wrapper, based on : + * http://www.cse.wustl.edu/~schmidt/win32-cv-1.html + */ + + +/* === Dependencies === */ +#include <process.h> +#include <errno.h> +#include "threading.h" + + +/* === Implementation === */ + +static unsigned __stdcall worker(void *arg) +{ + pthread_t* const thread = (pthread_t*) arg; + thread->arg = thread->start_routine(thread->arg); + return 0; +} + +int pthread_create(pthread_t* thread, const void* unused, + void* (*start_routine) (void*), void* arg) +{ + (void)unused; + thread->arg = arg; + thread->start_routine = start_routine; + thread->handle = (HANDLE) _beginthreadex(NULL, 0, worker, thread, 0, NULL); + + if (!thread->handle) + return errno; + else + return 0; +} + +int _pthread_join(pthread_t * thread, void **value_ptr) +{ + DWORD result; + + if (!thread->handle) return 0; + + result = WaitForSingleObject(thread->handle, INFINITE); + switch (result) { + case WAIT_OBJECT_0: + if (value_ptr) *value_ptr = thread->arg; + return 0; + case WAIT_ABANDONED: + return EINVAL; + default: + return GetLastError(); + } +} + +#endif /* ZSTD_MULTITHREAD */
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/contrib/python-zstandard/zstd/common/threading.h Tue Apr 18 12:24:34 2017 -0400 @@ -0,0 +1,104 @@ + +/** + * Copyright (c) 2016 Tino Reichardt + * All rights reserved. + * + * This source code is licensed under the BSD-style license found in the + * LICENSE file in the root directory of this source tree. An additional grant + * of patent rights can be found in the PATENTS file in the same directory. + * + * You can contact the author at: + * - zstdmt source repository: https://github.com/mcmilk/zstdmt + */ + +#ifndef THREADING_H_938743 +#define THREADING_H_938743 + +#if defined (__cplusplus) +extern "C" { +#endif + +#if defined(ZSTD_MULTITHREAD) && defined(_WIN32) + +/** + * Windows minimalist Pthread Wrapper, based on : + * http://www.cse.wustl.edu/~schmidt/win32-cv-1.html + */ +#ifdef WINVER +# undef WINVER +#endif +#define WINVER 0x0600 + +#ifdef _WIN32_WINNT +# undef _WIN32_WINNT +#endif +#define _WIN32_WINNT 0x0600 + +#ifndef WIN32_LEAN_AND_MEAN +# define WIN32_LEAN_AND_MEAN +#endif + +#include <windows.h> + +/* mutex */ +#define pthread_mutex_t CRITICAL_SECTION +#define pthread_mutex_init(a,b) InitializeCriticalSection((a)) +#define pthread_mutex_destroy(a) DeleteCriticalSection((a)) +#define pthread_mutex_lock(a) EnterCriticalSection((a)) +#define pthread_mutex_unlock(a) LeaveCriticalSection((a)) + +/* condition variable */ +#define pthread_cond_t CONDITION_VARIABLE +#define pthread_cond_init(a, b) InitializeConditionVariable((a)) +#define pthread_cond_destroy(a) /* No delete */ +#define pthread_cond_wait(a, b) SleepConditionVariableCS((a), (b), INFINITE) +#define pthread_cond_signal(a) WakeConditionVariable((a)) +#define pthread_cond_broadcast(a) WakeAllConditionVariable((a)) + +/* pthread_create() and pthread_join() */ +typedef struct { + HANDLE handle; + void* (*start_routine)(void*); + void* arg; +} pthread_t; + +int pthread_create(pthread_t* thread, const void* unused, + void* (*start_routine) (void*), void* arg); + +#define pthread_join(a, b) _pthread_join(&(a), (b)) +int _pthread_join(pthread_t* thread, void** value_ptr); + +/** + * add here more wrappers as required + */ + + +#elif defined(ZSTD_MULTITHREAD) /* posix assumed ; need a better detection mathod */ +/* === POSIX Systems === */ +# include <pthread.h> + +#else /* ZSTD_MULTITHREAD not defined */ +/* No multithreading support */ + +#define pthread_mutex_t int /* #define rather than typedef, as sometimes pthread support is implicit, resulting in duplicated symbols */ +#define pthread_mutex_init(a,b) +#define pthread_mutex_destroy(a) +#define pthread_mutex_lock(a) +#define pthread_mutex_unlock(a) + +#define pthread_cond_t int +#define pthread_cond_init(a,b) +#define pthread_cond_destroy(a) +#define pthread_cond_wait(a,b) +#define pthread_cond_signal(a) +#define pthread_cond_broadcast(a) + +/* do not use pthread_t */ + +#endif /* ZSTD_MULTITHREAD */ + +#if defined (__cplusplus) +} +#endif + +#endif /* THREADING_H_938743 */
--- a/contrib/python-zstandard/zstd/common/zstd_common.c Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/python-zstandard/zstd/common/zstd_common.c Tue Apr 18 12:24:34 2017 -0400 @@ -43,10 +43,6 @@ * provides error code string from enum */ const char* ZSTD_getErrorString(ZSTD_ErrorCode code) { return ERR_getErrorName(code); } -/* --- ZBUFF Error Management (deprecated) --- */ -unsigned ZBUFF_isError(size_t errorCode) { return ERR_isError(errorCode); } -const char* ZBUFF_getErrorName(size_t errorCode) { return ERR_getErrorName(errorCode); } - /*=************************************************************** * Custom allocator
--- a/contrib/python-zstandard/zstd/common/zstd_errors.h Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/python-zstandard/zstd/common/zstd_errors.h Tue Apr 18 12:24:34 2017 -0400 @@ -18,6 +18,20 @@ #include <stddef.h> /* size_t */ +/* ===== ZSTDERRORLIB_API : control library symbols visibility ===== */ +#if defined(__GNUC__) && (__GNUC__ >= 4) +# define ZSTDERRORLIB_VISIBILITY __attribute__ ((visibility ("default"))) +#else +# define ZSTDERRORLIB_VISIBILITY +#endif +#if defined(ZSTD_DLL_EXPORT) && (ZSTD_DLL_EXPORT==1) +# define ZSTDERRORLIB_API __declspec(dllexport) ZSTDERRORLIB_VISIBILITY +#elif defined(ZSTD_DLL_IMPORT) && (ZSTD_DLL_IMPORT==1) +# define ZSTDERRORLIB_API __declspec(dllimport) ZSTDERRORLIB_VISIBILITY /* It isn't required but allows to generate better code, saving a function pointer load from the IAT and an indirect jump.*/ +#else +# define ZSTDERRORLIB_API ZSTDERRORLIB_VISIBILITY +#endif + /*-**************************************** * error codes list ******************************************/ @@ -49,8 +63,8 @@ /*! ZSTD_getErrorCode() : convert a `size_t` function result into a `ZSTD_ErrorCode` enum type, which can be used to compare directly with enum list published into "error_public.h" */ -ZSTD_ErrorCode ZSTD_getErrorCode(size_t functionResult); -const char* ZSTD_getErrorString(ZSTD_ErrorCode code); +ZSTDERRORLIB_API ZSTD_ErrorCode ZSTD_getErrorCode(size_t functionResult); +ZSTDERRORLIB_API const char* ZSTD_getErrorString(ZSTD_ErrorCode code); #if defined (__cplusplus)
--- a/contrib/python-zstandard/zstd/common/zstd_internal.h Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/python-zstandard/zstd/common/zstd_internal.h Tue Apr 18 12:24:34 2017 -0400 @@ -267,4 +267,13 @@ } +/* hidden functions */ + +/* ZSTD_invalidateRepCodes() : + * ensures next compression will not use repcodes from previous block. + * Note : only works with regular variant; + * do not use with extDict variant ! */ +void ZSTD_invalidateRepCodes(ZSTD_CCtx* cctx); + + #endif /* ZSTD_CCOMMON_H_MODULE */
--- a/contrib/python-zstandard/zstd/compress/zstd_compress.c Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/python-zstandard/zstd/compress/zstd_compress.c Tue Apr 18 12:24:34 2017 -0400 @@ -51,8 +51,7 @@ /*-************************************* * Context memory management ***************************************/ -struct ZSTD_CCtx_s -{ +struct ZSTD_CCtx_s { const BYTE* nextSrc; /* next block here to continue on current prefix */ const BYTE* base; /* All regular indexes relative to this position */ const BYTE* dictBase; /* extDict indexes relative to this position */ @@ -61,10 +60,11 @@ U32 nextToUpdate; /* index from which to continue dictionary update */ U32 nextToUpdate3; /* index from which to continue dictionary update */ U32 hashLog3; /* dispatch table : larger == faster, more memory */ - U32 loadedDictEnd; + U32 loadedDictEnd; /* index of end of dictionary */ + U32 forceWindow; /* force back-references to respect limit of 1<<wLog, even for dictionary */ ZSTD_compressionStage_e stage; U32 rep[ZSTD_REP_NUM]; - U32 savedRep[ZSTD_REP_NUM]; + U32 repToConfirm[ZSTD_REP_NUM]; U32 dictID; ZSTD_parameters params; void* workSpace; @@ -101,7 +101,7 @@ cctx = (ZSTD_CCtx*) ZSTD_malloc(sizeof(ZSTD_CCtx), customMem); if (!cctx) return NULL; memset(cctx, 0, sizeof(ZSTD_CCtx)); - memcpy(&(cctx->customMem), &customMem, sizeof(customMem)); + cctx->customMem = customMem; return cctx; } @@ -119,6 +119,15 @@ return sizeof(*cctx) + cctx->workSpaceSize; } +size_t ZSTD_setCCtxParameter(ZSTD_CCtx* cctx, ZSTD_CCtxParameter param, unsigned value) +{ + switch(param) + { + case ZSTD_p_forceWindow : cctx->forceWindow = value>0; cctx->loadedDictEnd = 0; return 0; + default: return ERROR(parameter_unknown); + } +} + const seqStore_t* ZSTD_getSeqStore(const ZSTD_CCtx* ctx) /* hidden interface */ { return &(ctx->seqStore); @@ -318,6 +327,14 @@ } } +/* ZSTD_invalidateRepCodes() : + * ensures next compression will not use repcodes from previous block. + * Note : only works with regular variant; + * do not use with extDict variant ! */ +void ZSTD_invalidateRepCodes(ZSTD_CCtx* cctx) { + int i; + for (i=0; i<ZSTD_REP_NUM; i++) cctx->rep[i] = 0; +} /*! ZSTD_copyCCtx() : * Duplicate an existing context `srcCCtx` into another one `dstCCtx`. @@ -735,12 +752,19 @@ if ((size_t)(op-ostart) >= maxCSize) return 0; } /* confirm repcodes */ - { int i; for (i=0; i<ZSTD_REP_NUM; i++) zc->rep[i] = zc->savedRep[i]; } + { int i; for (i=0; i<ZSTD_REP_NUM; i++) zc->rep[i] = zc->repToConfirm[i]; } return op - ostart; } +#if 0 /* for debug */ +# define STORESEQ_DEBUG +#include <stdio.h> /* fprintf */ +U32 g_startDebug = 0; +const BYTE* g_start = NULL; +#endif + /*! ZSTD_storeSeq() : Store a sequence (literal length, literals, offset code and match length code) into seqStore_t. `offsetCode` : distance to match, or 0 == repCode. @@ -748,13 +772,14 @@ */ MEM_STATIC void ZSTD_storeSeq(seqStore_t* seqStorePtr, size_t litLength, const void* literals, U32 offsetCode, size_t matchCode) { -#if 0 /* for debug */ - static const BYTE* g_start = NULL; - const U32 pos = (U32)((const BYTE*)literals - g_start); - if (g_start==NULL) g_start = (const BYTE*)literals; - //if ((pos > 1) && (pos < 50000)) - printf("Cpos %6u :%5u literals & match %3u bytes at distance %6u \n", - pos, (U32)litLength, (U32)matchCode+MINMATCH, (U32)offsetCode); +#ifdef STORESEQ_DEBUG + if (g_startDebug) { + const U32 pos = (U32)((const BYTE*)literals - g_start); + if (g_start==NULL) g_start = (const BYTE*)literals; + if ((pos > 1895000) && (pos < 1895300)) + fprintf(stderr, "Cpos %6u :%5u literals & match %3u bytes at distance %6u \n", + pos, (U32)litLength, (U32)matchCode+MINMATCH, (U32)offsetCode); + } #endif /* copy Literals */ ZSTD_wildcopy(seqStorePtr->lit, literals, litLength); @@ -1004,8 +1029,8 @@ } } } /* save reps for next block */ - cctx->savedRep[0] = offset_1 ? offset_1 : offsetSaved; - cctx->savedRep[1] = offset_2 ? offset_2 : offsetSaved; + cctx->repToConfirm[0] = offset_1 ? offset_1 : offsetSaved; + cctx->repToConfirm[1] = offset_2 ? offset_2 : offsetSaved; /* Last Literals */ { size_t const lastLLSize = iend - anchor; @@ -1119,7 +1144,7 @@ } } } /* save reps for next block */ - ctx->savedRep[0] = offset_1; ctx->savedRep[1] = offset_2; + ctx->repToConfirm[0] = offset_1; ctx->repToConfirm[1] = offset_2; /* Last Literals */ { size_t const lastLLSize = iend - anchor; @@ -1273,8 +1298,8 @@ } } } /* save reps for next block */ - cctx->savedRep[0] = offset_1 ? offset_1 : offsetSaved; - cctx->savedRep[1] = offset_2 ? offset_2 : offsetSaved; + cctx->repToConfirm[0] = offset_1 ? offset_1 : offsetSaved; + cctx->repToConfirm[1] = offset_2 ? offset_2 : offsetSaved; /* Last Literals */ { size_t const lastLLSize = iend - anchor; @@ -1423,7 +1448,7 @@ } } } /* save reps for next block */ - ctx->savedRep[0] = offset_1; ctx->savedRep[1] = offset_2; + ctx->repToConfirm[0] = offset_1; ctx->repToConfirm[1] = offset_2; /* Last Literals */ { size_t const lastLLSize = iend - anchor; @@ -1955,8 +1980,8 @@ } } /* Save reps for next block */ - ctx->savedRep[0] = offset_1 ? offset_1 : savedOffset; - ctx->savedRep[1] = offset_2 ? offset_2 : savedOffset; + ctx->repToConfirm[0] = offset_1 ? offset_1 : savedOffset; + ctx->repToConfirm[1] = offset_2 ? offset_2 : savedOffset; /* Last Literals */ { size_t const lastLLSize = iend - anchor; @@ -2150,7 +2175,7 @@ } } /* Save reps for next block */ - ctx->savedRep[0] = offset_1; ctx->savedRep[1] = offset_2; + ctx->repToConfirm[0] = offset_1; ctx->repToConfirm[1] = offset_2; /* Last Literals */ { size_t const lastLLSize = iend - anchor; @@ -2409,12 +2434,14 @@ cctx->nextSrc = ip + srcSize; - { size_t const cSize = frame ? + if (srcSize) { + size_t const cSize = frame ? ZSTD_compress_generic (cctx, dst, dstCapacity, src, srcSize, lastFrameChunk) : ZSTD_compressBlock_internal (cctx, dst, dstCapacity, src, srcSize); if (ZSTD_isError(cSize)) return cSize; return cSize + fhSize; - } + } else + return fhSize; } @@ -2450,7 +2477,7 @@ zc->dictBase = zc->base; zc->base += ip - zc->nextSrc; zc->nextToUpdate = zc->dictLimit; - zc->loadedDictEnd = (U32)(iend - zc->base); + zc->loadedDictEnd = zc->forceWindow ? 0 : (U32)(iend - zc->base); zc->nextSrc = iend; if (srcSize <= HASH_READ_SIZE) return 0; @@ -2557,9 +2584,9 @@ } if (dictPtr+12 > dictEnd) return ERROR(dictionary_corrupted); - cctx->rep[0] = MEM_readLE32(dictPtr+0); if (cctx->rep[0] >= dictSize) return ERROR(dictionary_corrupted); - cctx->rep[1] = MEM_readLE32(dictPtr+4); if (cctx->rep[1] >= dictSize) return ERROR(dictionary_corrupted); - cctx->rep[2] = MEM_readLE32(dictPtr+8); if (cctx->rep[2] >= dictSize) return ERROR(dictionary_corrupted); + cctx->rep[0] = MEM_readLE32(dictPtr+0); if (cctx->rep[0] == 0 || cctx->rep[0] >= dictSize) return ERROR(dictionary_corrupted); + cctx->rep[1] = MEM_readLE32(dictPtr+4); if (cctx->rep[1] == 0 || cctx->rep[1] >= dictSize) return ERROR(dictionary_corrupted); + cctx->rep[2] = MEM_readLE32(dictPtr+8); if (cctx->rep[2] == 0 || cctx->rep[2] >= dictSize) return ERROR(dictionary_corrupted); dictPtr += 12; { U32 offcodeMax = MaxOff; @@ -2594,7 +2621,6 @@ } } - /*! ZSTD_compressBegin_internal() : * @return : 0, or an error code */ static size_t ZSTD_compressBegin_internal(ZSTD_CCtx* cctx, @@ -2626,9 +2652,9 @@ } -size_t ZSTD_compressBegin(ZSTD_CCtx* zc, int compressionLevel) +size_t ZSTD_compressBegin(ZSTD_CCtx* cctx, int compressionLevel) { - return ZSTD_compressBegin_usingDict(zc, NULL, 0, compressionLevel); + return ZSTD_compressBegin_usingDict(cctx, NULL, 0, compressionLevel); } @@ -2733,7 +2759,8 @@ /* ===== Dictionary API ===== */ struct ZSTD_CDict_s { - void* dictContent; + void* dictBuffer; + const void* dictContent; size_t dictContentSize; ZSTD_CCtx* refContext; }; /* typedef'd tp ZSTD_CDict within "zstd.h" */ @@ -2741,39 +2768,45 @@ size_t ZSTD_sizeof_CDict(const ZSTD_CDict* cdict) { if (cdict==NULL) return 0; /* support sizeof on NULL */ - return ZSTD_sizeof_CCtx(cdict->refContext) + cdict->dictContentSize; + return ZSTD_sizeof_CCtx(cdict->refContext) + (cdict->dictBuffer ? cdict->dictContentSize : 0) + sizeof(*cdict); } -ZSTD_CDict* ZSTD_createCDict_advanced(const void* dict, size_t dictSize, ZSTD_parameters params, ZSTD_customMem customMem) +ZSTD_CDict* ZSTD_createCDict_advanced(const void* dictBuffer, size_t dictSize, unsigned byReference, + ZSTD_parameters params, ZSTD_customMem customMem) { if (!customMem.customAlloc && !customMem.customFree) customMem = defaultCustomMem; if (!customMem.customAlloc || !customMem.customFree) return NULL; { ZSTD_CDict* const cdict = (ZSTD_CDict*) ZSTD_malloc(sizeof(ZSTD_CDict), customMem); - void* const dictContent = ZSTD_malloc(dictSize, customMem); ZSTD_CCtx* const cctx = ZSTD_createCCtx_advanced(customMem); - if (!dictContent || !cdict || !cctx) { - ZSTD_free(dictContent, customMem); + if (!cdict || !cctx) { ZSTD_free(cdict, customMem); ZSTD_free(cctx, customMem); return NULL; } - if (dictSize) { - memcpy(dictContent, dict, dictSize); + if ((byReference) || (!dictBuffer) || (!dictSize)) { + cdict->dictBuffer = NULL; + cdict->dictContent = dictBuffer; + } else { + void* const internalBuffer = ZSTD_malloc(dictSize, customMem); + if (!internalBuffer) { ZSTD_free(cctx, customMem); ZSTD_free(cdict, customMem); return NULL; } + memcpy(internalBuffer, dictBuffer, dictSize); + cdict->dictBuffer = internalBuffer; + cdict->dictContent = internalBuffer; } - { size_t const errorCode = ZSTD_compressBegin_advanced(cctx, dictContent, dictSize, params, 0); + + { size_t const errorCode = ZSTD_compressBegin_advanced(cctx, cdict->dictContent, dictSize, params, 0); if (ZSTD_isError(errorCode)) { - ZSTD_free(dictContent, customMem); + ZSTD_free(cdict->dictBuffer, customMem); + ZSTD_free(cctx, customMem); ZSTD_free(cdict, customMem); - ZSTD_free(cctx, customMem); return NULL; } } - cdict->dictContent = dictContent; + cdict->refContext = cctx; cdict->dictContentSize = dictSize; - cdict->refContext = cctx; return cdict; } } @@ -2783,7 +2816,15 @@ ZSTD_customMem const allocator = { NULL, NULL, NULL }; ZSTD_parameters params = ZSTD_getParams(compressionLevel, 0, dictSize); params.fParams.contentSizeFlag = 1; - return ZSTD_createCDict_advanced(dict, dictSize, params, allocator); + return ZSTD_createCDict_advanced(dict, dictSize, 0, params, allocator); +} + +ZSTD_CDict* ZSTD_createCDict_byReference(const void* dict, size_t dictSize, int compressionLevel) +{ + ZSTD_customMem const allocator = { NULL, NULL, NULL }; + ZSTD_parameters params = ZSTD_getParams(compressionLevel, 0, dictSize); + params.fParams.contentSizeFlag = 1; + return ZSTD_createCDict_advanced(dict, dictSize, 1, params, allocator); } size_t ZSTD_freeCDict(ZSTD_CDict* cdict) @@ -2791,7 +2832,7 @@ if (cdict==NULL) return 0; /* support free on NULL */ { ZSTD_customMem const cMem = cdict->refContext->customMem; ZSTD_freeCCtx(cdict->refContext); - ZSTD_free(cdict->dictContent, cMem); + ZSTD_free(cdict->dictBuffer, cMem); ZSTD_free(cdict, cMem); return 0; } @@ -2801,7 +2842,7 @@ return ZSTD_getParamsFromCCtx(cdict->refContext); } -size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict, U64 pledgedSrcSize) +size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict, unsigned long long pledgedSrcSize) { if (cdict->dictContentSize) CHECK_F(ZSTD_copyCCtx(cctx, cdict->refContext, pledgedSrcSize)) else CHECK_F(ZSTD_compressBegin_advanced(cctx, NULL, 0, cdict->refContext->params, pledgedSrcSize)); @@ -2900,7 +2941,7 @@ size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pledgedSrcSize) { - if (zcs->inBuffSize==0) return ERROR(stage_wrong); /* zcs has not been init at least once */ + if (zcs->inBuffSize==0) return ERROR(stage_wrong); /* zcs has not been init at least once => can't reset */ if (zcs->cdict) CHECK_F(ZSTD_compressBegin_usingCDict(zcs->cctx, zcs->cdict, pledgedSrcSize)) else CHECK_F(ZSTD_compressBegin_advanced(zcs->cctx, NULL, 0, zcs->params, pledgedSrcSize)); @@ -2937,9 +2978,9 @@ if (zcs->outBuff == NULL) return ERROR(memory_allocation); } - if (dict) { + if (dict && dictSize >= 8) { ZSTD_freeCDict(zcs->cdictLocal); - zcs->cdictLocal = ZSTD_createCDict_advanced(dict, dictSize, params, zcs->customMem); + zcs->cdictLocal = ZSTD_createCDict_advanced(dict, dictSize, 0, params, zcs->customMem); if (zcs->cdictLocal == NULL) return ERROR(memory_allocation); zcs->cdict = zcs->cdictLocal; } else zcs->cdict = NULL; @@ -2956,6 +2997,7 @@ ZSTD_parameters const params = ZSTD_getParamsFromCDict(cdict); size_t const initError = ZSTD_initCStream_advanced(zcs, NULL, 0, params, 0); zcs->cdict = cdict; + zcs->cctx->dictID = params.fParams.noDictIDFlag ? 0 : cdict->refContext->dictID; return initError; } @@ -2967,7 +3009,8 @@ size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigned long long pledgedSrcSize) { - ZSTD_parameters const params = ZSTD_getParams(compressionLevel, pledgedSrcSize, 0); + ZSTD_parameters params = ZSTD_getParams(compressionLevel, pledgedSrcSize, 0); + if (pledgedSrcSize) params.fParams.contentSizeFlag = 1; return ZSTD_initCStream_advanced(zcs, NULL, 0, params, pledgedSrcSize); }
--- a/contrib/python-zstandard/zstd/compress/zstd_opt.h Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/python-zstandard/zstd/compress/zstd_opt.h Tue Apr 18 12:24:34 2017 -0400 @@ -38,7 +38,7 @@ ssPtr->cachedLiterals = NULL; ssPtr->cachedPrice = ssPtr->cachedLitLength = 0; - ssPtr->staticPrices = 0; + ssPtr->staticPrices = 0; if (ssPtr->litLengthSum == 0) { if (srcSize <= 1024) ssPtr->staticPrices = 1; @@ -56,7 +56,7 @@ for (u=0; u<=MaxLit; u++) { ssPtr->litFreq[u] = 1 + (ssPtr->litFreq[u]>>ZSTD_FREQ_DIV); - ssPtr->litSum += ssPtr->litFreq[u]; + ssPtr->litSum += ssPtr->litFreq[u]; } for (u=0; u<=MaxLL; u++) ssPtr->litLengthFreq[u] = 1; @@ -634,7 +634,7 @@ } } /* for (cur=0; cur < last_pos; ) */ /* Save reps for next block */ - { int i; for (i=0; i<ZSTD_REP_NUM; i++) ctx->savedRep[i] = rep[i]; } + { int i; for (i=0; i<ZSTD_REP_NUM; i++) ctx->repToConfirm[i] = rep[i]; } /* Last Literals */ { size_t const lastLLSize = iend - anchor; @@ -825,7 +825,7 @@ match_num = ZSTD_BtGetAllMatches_selectMLS_extDict(ctx, inr, iend, maxSearches, mls, matches, minMatch); - if (match_num > 0 && matches[match_num-1].len > sufficient_len) { + if (match_num > 0 && (matches[match_num-1].len > sufficient_len || cur + matches[match_num-1].len >= ZSTD_OPT_NUM)) { best_mlen = matches[match_num-1].len; best_off = matches[match_num-1].off; last_pos = cur + 1; @@ -835,7 +835,7 @@ /* set prices using matches at position = cur */ for (u = 0; u < match_num; u++) { mlen = (u>0) ? matches[u-1].len+1 : best_mlen; - best_mlen = (cur + matches[u].len < ZSTD_OPT_NUM) ? matches[u].len : ZSTD_OPT_NUM - cur; + best_mlen = matches[u].len; while (mlen <= best_mlen) { if (opt[cur].mlen == 1) { @@ -907,7 +907,7 @@ } } /* for (cur=0; cur < last_pos; ) */ /* Save reps for next block */ - { int i; for (i=0; i<ZSTD_REP_NUM; i++) ctx->savedRep[i] = rep[i]; } + { int i; for (i=0; i<ZSTD_REP_NUM; i++) ctx->repToConfirm[i] = rep[i]; } /* Last Literals */ { size_t lastLLSize = iend - anchor;
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/contrib/python-zstandard/zstd/compress/zstdmt_compress.c Tue Apr 18 12:24:34 2017 -0400 @@ -0,0 +1,740 @@ +/** + * Copyright (c) 2016-present, Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under the BSD-style license found in the + * LICENSE file in the root directory of this source tree. An additional grant + * of patent rights can be found in the PATENTS file in the same directory. + */ + + +/* ====== Tuning parameters ====== */ +#define ZSTDMT_NBTHREADS_MAX 128 + + +/* ====== Compiler specifics ====== */ +#if defined(_MSC_VER) +# pragma warning(disable : 4204) /* disable: C4204: non-constant aggregate initializer */ +#endif + + +/* ====== Dependencies ====== */ +#include <stdlib.h> /* malloc */ +#include <string.h> /* memcpy */ +#include "pool.h" /* threadpool */ +#include "threading.h" /* mutex */ +#include "zstd_internal.h" /* MIN, ERROR, ZSTD_*, ZSTD_highbit32 */ +#include "zstdmt_compress.h" +#define XXH_STATIC_LINKING_ONLY /* XXH64_state_t */ +#include "xxhash.h" + + +/* ====== Debug ====== */ +#if 0 + +# include <stdio.h> +# include <unistd.h> +# include <sys/times.h> + static unsigned g_debugLevel = 3; +# define DEBUGLOGRAW(l, ...) if (l<=g_debugLevel) { fprintf(stderr, __VA_ARGS__); } +# define DEBUGLOG(l, ...) if (l<=g_debugLevel) { fprintf(stderr, __FILE__ ": "); fprintf(stderr, __VA_ARGS__); fprintf(stderr, " \n"); } + +# define DEBUG_PRINTHEX(l,p,n) { \ + unsigned debug_u; \ + for (debug_u=0; debug_u<(n); debug_u++) \ + DEBUGLOGRAW(l, "%02X ", ((const unsigned char*)(p))[debug_u]); \ + DEBUGLOGRAW(l, " \n"); \ +} + +static unsigned long long GetCurrentClockTimeMicroseconds() +{ + static clock_t _ticksPerSecond = 0; + if (_ticksPerSecond <= 0) _ticksPerSecond = sysconf(_SC_CLK_TCK); + + struct tms junk; clock_t newTicks = (clock_t) times(&junk); + return ((((unsigned long long)newTicks)*(1000000))/_ticksPerSecond); +} + +#define MUTEX_WAIT_TIME_DLEVEL 5 +#define PTHREAD_MUTEX_LOCK(mutex) \ +if (g_debugLevel>=MUTEX_WAIT_TIME_DLEVEL) { \ + unsigned long long beforeTime = GetCurrentClockTimeMicroseconds(); \ + pthread_mutex_lock(mutex); \ + unsigned long long afterTime = GetCurrentClockTimeMicroseconds(); \ + unsigned long long elapsedTime = (afterTime-beforeTime); \ + if (elapsedTime > 1000) { /* or whatever threshold you like; I'm using 1 millisecond here */ \ + DEBUGLOG(MUTEX_WAIT_TIME_DLEVEL, "Thread took %llu microseconds to acquire mutex %s \n", \ + elapsedTime, #mutex); \ + } \ +} else pthread_mutex_lock(mutex); + +#else + +# define DEBUGLOG(l, ...) {} /* disabled */ +# define PTHREAD_MUTEX_LOCK(m) pthread_mutex_lock(m) +# define DEBUG_PRINTHEX(l,p,n) {} + +#endif + + +/* ===== Buffer Pool ===== */ + +typedef struct buffer_s { + void* start; + size_t size; +} buffer_t; + +static const buffer_t g_nullBuffer = { NULL, 0 }; + +typedef struct ZSTDMT_bufferPool_s { + unsigned totalBuffers; + unsigned nbBuffers; + buffer_t bTable[1]; /* variable size */ +} ZSTDMT_bufferPool; + +static ZSTDMT_bufferPool* ZSTDMT_createBufferPool(unsigned nbThreads) +{ + unsigned const maxNbBuffers = 2*nbThreads + 2; + ZSTDMT_bufferPool* const bufPool = (ZSTDMT_bufferPool*)calloc(1, sizeof(ZSTDMT_bufferPool) + (maxNbBuffers-1) * sizeof(buffer_t)); + if (bufPool==NULL) return NULL; + bufPool->totalBuffers = maxNbBuffers; + bufPool->nbBuffers = 0; + return bufPool; +} + +static void ZSTDMT_freeBufferPool(ZSTDMT_bufferPool* bufPool) +{ + unsigned u; + if (!bufPool) return; /* compatibility with free on NULL */ + for (u=0; u<bufPool->totalBuffers; u++) + free(bufPool->bTable[u].start); + free(bufPool); +} + +/* assumption : invocation from main thread only ! */ +static buffer_t ZSTDMT_getBuffer(ZSTDMT_bufferPool* pool, size_t bSize) +{ + if (pool->nbBuffers) { /* try to use an existing buffer */ + buffer_t const buf = pool->bTable[--(pool->nbBuffers)]; + size_t const availBufferSize = buf.size; + if ((availBufferSize >= bSize) & (availBufferSize <= 10*bSize)) /* large enough, but not too much */ + return buf; + free(buf.start); /* size conditions not respected : scratch this buffer and create a new one */ + } + /* create new buffer */ + { buffer_t buffer; + void* const start = malloc(bSize); + if (start==NULL) bSize = 0; + buffer.start = start; /* note : start can be NULL if malloc fails ! */ + buffer.size = bSize; + return buffer; + } +} + +/* store buffer for later re-use, up to pool capacity */ +static void ZSTDMT_releaseBuffer(ZSTDMT_bufferPool* pool, buffer_t buf) +{ + if (buf.start == NULL) return; /* release on NULL */ + if (pool->nbBuffers < pool->totalBuffers) { + pool->bTable[pool->nbBuffers++] = buf; /* store for later re-use */ + return; + } + /* Reached bufferPool capacity (should not happen) */ + free(buf.start); +} + + +/* ===== CCtx Pool ===== */ + +typedef struct { + unsigned totalCCtx; + unsigned availCCtx; + ZSTD_CCtx* cctx[1]; /* variable size */ +} ZSTDMT_CCtxPool; + +/* assumption : CCtxPool invocation only from main thread */ + +/* note : all CCtx borrowed from the pool should be released back to the pool _before_ freeing the pool */ +static void ZSTDMT_freeCCtxPool(ZSTDMT_CCtxPool* pool) +{ + unsigned u; + for (u=0; u<pool->totalCCtx; u++) + ZSTD_freeCCtx(pool->cctx[u]); /* note : compatible with free on NULL */ + free(pool); +} + +/* ZSTDMT_createCCtxPool() : + * implies nbThreads >= 1 , checked by caller ZSTDMT_createCCtx() */ +static ZSTDMT_CCtxPool* ZSTDMT_createCCtxPool(unsigned nbThreads) +{ + ZSTDMT_CCtxPool* const cctxPool = (ZSTDMT_CCtxPool*) calloc(1, sizeof(ZSTDMT_CCtxPool) + (nbThreads-1)*sizeof(ZSTD_CCtx*)); + if (!cctxPool) return NULL; + cctxPool->totalCCtx = nbThreads; + cctxPool->availCCtx = 1; /* at least one cctx for single-thread mode */ + cctxPool->cctx[0] = ZSTD_createCCtx(); + if (!cctxPool->cctx[0]) { ZSTDMT_freeCCtxPool(cctxPool); return NULL; } + DEBUGLOG(1, "cctxPool created, with %u threads", nbThreads); + return cctxPool; +} + +static ZSTD_CCtx* ZSTDMT_getCCtx(ZSTDMT_CCtxPool* pool) +{ + if (pool->availCCtx) { + pool->availCCtx--; + return pool->cctx[pool->availCCtx]; + } + return ZSTD_createCCtx(); /* note : can be NULL, when creation fails ! */ +} + +static void ZSTDMT_releaseCCtx(ZSTDMT_CCtxPool* pool, ZSTD_CCtx* cctx) +{ + if (cctx==NULL) return; /* compatibility with release on NULL */ + if (pool->availCCtx < pool->totalCCtx) + pool->cctx[pool->availCCtx++] = cctx; + else + /* pool overflow : should not happen, since totalCCtx==nbThreads */ + ZSTD_freeCCtx(cctx); +} + + +/* ===== Thread worker ===== */ + +typedef struct { + buffer_t buffer; + size_t filled; +} inBuff_t; + +typedef struct { + ZSTD_CCtx* cctx; + buffer_t src; + const void* srcStart; + size_t srcSize; + size_t dictSize; + buffer_t dstBuff; + size_t cSize; + size_t dstFlushed; + unsigned firstChunk; + unsigned lastChunk; + unsigned jobCompleted; + unsigned jobScanned; + pthread_mutex_t* jobCompleted_mutex; + pthread_cond_t* jobCompleted_cond; + ZSTD_parameters params; + ZSTD_CDict* cdict; + unsigned long long fullFrameSize; +} ZSTDMT_jobDescription; + +/* ZSTDMT_compressChunk() : POOL_function type */ +void ZSTDMT_compressChunk(void* jobDescription) +{ + ZSTDMT_jobDescription* const job = (ZSTDMT_jobDescription*)jobDescription; + const void* const src = (const char*)job->srcStart + job->dictSize; + buffer_t const dstBuff = job->dstBuff; + DEBUGLOG(3, "job (first:%u) (last:%u) : dictSize %u, srcSize %u", job->firstChunk, job->lastChunk, (U32)job->dictSize, (U32)job->srcSize); + if (job->cdict) { + size_t const initError = ZSTD_compressBegin_usingCDict(job->cctx, job->cdict, job->fullFrameSize); + if (job->cdict) DEBUGLOG(3, "using CDict "); + if (ZSTD_isError(initError)) { job->cSize = initError; goto _endJob; } + } else { + size_t const initError = ZSTD_compressBegin_advanced(job->cctx, job->srcStart, job->dictSize, job->params, job->fullFrameSize); + if (ZSTD_isError(initError)) { job->cSize = initError; goto _endJob; } + ZSTD_setCCtxParameter(job->cctx, ZSTD_p_forceWindow, 1); + } + if (!job->firstChunk) { /* flush frame header */ + size_t const hSize = ZSTD_compressContinue(job->cctx, dstBuff.start, dstBuff.size, src, 0); + if (ZSTD_isError(hSize)) { job->cSize = hSize; goto _endJob; } + ZSTD_invalidateRepCodes(job->cctx); + } + + DEBUGLOG(4, "Compressing : "); + DEBUG_PRINTHEX(4, job->srcStart, 12); + job->cSize = (job->lastChunk) ? /* last chunk signal */ + ZSTD_compressEnd (job->cctx, dstBuff.start, dstBuff.size, src, job->srcSize) : + ZSTD_compressContinue(job->cctx, dstBuff.start, dstBuff.size, src, job->srcSize); + DEBUGLOG(3, "compressed %u bytes into %u bytes (first:%u) (last:%u)", (unsigned)job->srcSize, (unsigned)job->cSize, job->firstChunk, job->lastChunk); + +_endJob: + PTHREAD_MUTEX_LOCK(job->jobCompleted_mutex); + job->jobCompleted = 1; + job->jobScanned = 0; + pthread_cond_signal(job->jobCompleted_cond); + pthread_mutex_unlock(job->jobCompleted_mutex); +} + + +/* ------------------------------------------ */ +/* ===== Multi-threaded compression ===== */ +/* ------------------------------------------ */ + +struct ZSTDMT_CCtx_s { + POOL_ctx* factory; + ZSTDMT_bufferPool* buffPool; + ZSTDMT_CCtxPool* cctxPool; + pthread_mutex_t jobCompleted_mutex; + pthread_cond_t jobCompleted_cond; + size_t targetSectionSize; + size_t marginSize; + size_t inBuffSize; + size_t dictSize; + size_t targetDictSize; + inBuff_t inBuff; + ZSTD_parameters params; + XXH64_state_t xxhState; + unsigned nbThreads; + unsigned jobIDMask; + unsigned doneJobID; + unsigned nextJobID; + unsigned frameEnded; + unsigned allJobsCompleted; + unsigned overlapRLog; + unsigned long long frameContentSize; + size_t sectionSize; + ZSTD_CDict* cdict; + ZSTD_CStream* cstream; + ZSTDMT_jobDescription jobs[1]; /* variable size (must lies at the end) */ +}; + +ZSTDMT_CCtx *ZSTDMT_createCCtx(unsigned nbThreads) +{ + ZSTDMT_CCtx* cctx; + U32 const minNbJobs = nbThreads + 2; + U32 const nbJobsLog2 = ZSTD_highbit32(minNbJobs) + 1; + U32 const nbJobs = 1 << nbJobsLog2; + DEBUGLOG(5, "nbThreads : %u ; minNbJobs : %u ; nbJobsLog2 : %u ; nbJobs : %u \n", + nbThreads, minNbJobs, nbJobsLog2, nbJobs); + if ((nbThreads < 1) | (nbThreads > ZSTDMT_NBTHREADS_MAX)) return NULL; + cctx = (ZSTDMT_CCtx*) calloc(1, sizeof(ZSTDMT_CCtx) + nbJobs*sizeof(ZSTDMT_jobDescription)); + if (!cctx) return NULL; + cctx->nbThreads = nbThreads; + cctx->jobIDMask = nbJobs - 1; + cctx->allJobsCompleted = 1; + cctx->sectionSize = 0; + cctx->overlapRLog = 3; + cctx->factory = POOL_create(nbThreads, 1); + cctx->buffPool = ZSTDMT_createBufferPool(nbThreads); + cctx->cctxPool = ZSTDMT_createCCtxPool(nbThreads); + if (!cctx->factory | !cctx->buffPool | !cctx->cctxPool) { /* one object was not created */ + ZSTDMT_freeCCtx(cctx); + return NULL; + } + if (nbThreads==1) { + cctx->cstream = ZSTD_createCStream(); + if (!cctx->cstream) { + ZSTDMT_freeCCtx(cctx); return NULL; + } } + pthread_mutex_init(&cctx->jobCompleted_mutex, NULL); /* Todo : check init function return */ + pthread_cond_init(&cctx->jobCompleted_cond, NULL); + DEBUGLOG(4, "mt_cctx created, for %u threads \n", nbThreads); + return cctx; +} + +/* ZSTDMT_releaseAllJobResources() : + * Ensure all workers are killed first. */ +static void ZSTDMT_releaseAllJobResources(ZSTDMT_CCtx* mtctx) +{ + unsigned jobID; + for (jobID=0; jobID <= mtctx->jobIDMask; jobID++) { + ZSTDMT_releaseBuffer(mtctx->buffPool, mtctx->jobs[jobID].dstBuff); + mtctx->jobs[jobID].dstBuff = g_nullBuffer; + ZSTDMT_releaseBuffer(mtctx->buffPool, mtctx->jobs[jobID].src); + mtctx->jobs[jobID].src = g_nullBuffer; + ZSTDMT_releaseCCtx(mtctx->cctxPool, mtctx->jobs[jobID].cctx); + mtctx->jobs[jobID].cctx = NULL; + } + memset(mtctx->jobs, 0, (mtctx->jobIDMask+1)*sizeof(ZSTDMT_jobDescription)); + ZSTDMT_releaseBuffer(mtctx->buffPool, mtctx->inBuff.buffer); + mtctx->inBuff.buffer = g_nullBuffer; + mtctx->allJobsCompleted = 1; +} + +size_t ZSTDMT_freeCCtx(ZSTDMT_CCtx* mtctx) +{ + if (mtctx==NULL) return 0; /* compatible with free on NULL */ + POOL_free(mtctx->factory); + if (!mtctx->allJobsCompleted) ZSTDMT_releaseAllJobResources(mtctx); /* stop workers first */ + ZSTDMT_freeBufferPool(mtctx->buffPool); /* release job resources into pools first */ + ZSTDMT_freeCCtxPool(mtctx->cctxPool); + ZSTD_freeCDict(mtctx->cdict); + ZSTD_freeCStream(mtctx->cstream); + pthread_mutex_destroy(&mtctx->jobCompleted_mutex); + pthread_cond_destroy(&mtctx->jobCompleted_cond); + free(mtctx); + return 0; +} + +size_t ZSTDMT_setMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSDTMT_parameter parameter, unsigned value) +{ + switch(parameter) + { + case ZSTDMT_p_sectionSize : + mtctx->sectionSize = value; + return 0; + case ZSTDMT_p_overlapSectionLog : + DEBUGLOG(4, "ZSTDMT_p_overlapSectionLog : %u", value); + mtctx->overlapRLog = (value >= 9) ? 0 : 9 - value; + return 0; + default : + return ERROR(compressionParameter_unsupported); + } +} + + +/* ------------------------------------------ */ +/* ===== Multi-threaded compression ===== */ +/* ------------------------------------------ */ + +size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* mtctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + int compressionLevel) +{ + ZSTD_parameters params = ZSTD_getParams(compressionLevel, srcSize, 0); + size_t const chunkTargetSize = (size_t)1 << (params.cParams.windowLog + 2); + unsigned const nbChunksMax = (unsigned)(srcSize / chunkTargetSize) + (srcSize < chunkTargetSize) /* min 1 */; + unsigned nbChunks = MIN(nbChunksMax, mtctx->nbThreads); + size_t const proposedChunkSize = (srcSize + (nbChunks-1)) / nbChunks; + size_t const avgChunkSize = ((proposedChunkSize & 0x1FFFF) < 0xFFFF) ? proposedChunkSize + 0xFFFF : proposedChunkSize; /* avoid too small last block */ + size_t remainingSrcSize = srcSize; + const char* const srcStart = (const char*)src; + size_t frameStartPos = 0; + + DEBUGLOG(3, "windowLog : %2u => chunkTargetSize : %u bytes ", params.cParams.windowLog, (U32)chunkTargetSize); + DEBUGLOG(2, "nbChunks : %2u (chunkSize : %u bytes) ", nbChunks, (U32)avgChunkSize); + params.fParams.contentSizeFlag = 1; + + if (nbChunks==1) { /* fallback to single-thread mode */ + ZSTD_CCtx* const cctx = mtctx->cctxPool->cctx[0]; + return ZSTD_compressCCtx(cctx, dst, dstCapacity, src, srcSize, compressionLevel); + } + + { unsigned u; + for (u=0; u<nbChunks; u++) { + size_t const chunkSize = MIN(remainingSrcSize, avgChunkSize); + size_t const dstBufferCapacity = u ? ZSTD_compressBound(chunkSize) : dstCapacity; + buffer_t const dstAsBuffer = { dst, dstCapacity }; + buffer_t const dstBuffer = u ? ZSTDMT_getBuffer(mtctx->buffPool, dstBufferCapacity) : dstAsBuffer; + ZSTD_CCtx* const cctx = ZSTDMT_getCCtx(mtctx->cctxPool); + + if ((cctx==NULL) || (dstBuffer.start==NULL)) { + mtctx->jobs[u].cSize = ERROR(memory_allocation); /* job result */ + mtctx->jobs[u].jobCompleted = 1; + nbChunks = u+1; + break; /* let's wait for previous jobs to complete, but don't start new ones */ + } + + mtctx->jobs[u].srcStart = srcStart + frameStartPos; + mtctx->jobs[u].srcSize = chunkSize; + mtctx->jobs[u].fullFrameSize = srcSize; + mtctx->jobs[u].params = params; + mtctx->jobs[u].dstBuff = dstBuffer; + mtctx->jobs[u].cctx = cctx; + mtctx->jobs[u].firstChunk = (u==0); + mtctx->jobs[u].lastChunk = (u==nbChunks-1); + mtctx->jobs[u].jobCompleted = 0; + mtctx->jobs[u].jobCompleted_mutex = &mtctx->jobCompleted_mutex; + mtctx->jobs[u].jobCompleted_cond = &mtctx->jobCompleted_cond; + + DEBUGLOG(3, "posting job %u (%u bytes)", u, (U32)chunkSize); + DEBUG_PRINTHEX(3, mtctx->jobs[u].srcStart, 12); + POOL_add(mtctx->factory, ZSTDMT_compressChunk, &mtctx->jobs[u]); + + frameStartPos += chunkSize; + remainingSrcSize -= chunkSize; + } } + /* note : since nbChunks <= nbThreads, all jobs should be running immediately in parallel */ + + { unsigned chunkID; + size_t error = 0, dstPos = 0; + for (chunkID=0; chunkID<nbChunks; chunkID++) { + DEBUGLOG(3, "waiting for chunk %u ", chunkID); + PTHREAD_MUTEX_LOCK(&mtctx->jobCompleted_mutex); + while (mtctx->jobs[chunkID].jobCompleted==0) { + DEBUGLOG(4, "waiting for jobCompleted signal from chunk %u", chunkID); + pthread_cond_wait(&mtctx->jobCompleted_cond, &mtctx->jobCompleted_mutex); + } + pthread_mutex_unlock(&mtctx->jobCompleted_mutex); + DEBUGLOG(3, "ready to write chunk %u ", chunkID); + + ZSTDMT_releaseCCtx(mtctx->cctxPool, mtctx->jobs[chunkID].cctx); + mtctx->jobs[chunkID].cctx = NULL; + mtctx->jobs[chunkID].srcStart = NULL; + { size_t const cSize = mtctx->jobs[chunkID].cSize; + if (ZSTD_isError(cSize)) error = cSize; + if ((!error) && (dstPos + cSize > dstCapacity)) error = ERROR(dstSize_tooSmall); + if (chunkID) { /* note : chunk 0 is already written directly into dst */ + if (!error) memcpy((char*)dst + dstPos, mtctx->jobs[chunkID].dstBuff.start, cSize); + ZSTDMT_releaseBuffer(mtctx->buffPool, mtctx->jobs[chunkID].dstBuff); + mtctx->jobs[chunkID].dstBuff = g_nullBuffer; + } + dstPos += cSize ; + } + } + if (!error) DEBUGLOG(3, "compressed size : %u ", (U32)dstPos); + return error ? error : dstPos; + } + +} + + +/* ====================================== */ +/* ======= Streaming API ======= */ +/* ====================================== */ + +static void ZSTDMT_waitForAllJobsCompleted(ZSTDMT_CCtx* zcs) { + while (zcs->doneJobID < zcs->nextJobID) { + unsigned const jobID = zcs->doneJobID & zcs->jobIDMask; + PTHREAD_MUTEX_LOCK(&zcs->jobCompleted_mutex); + while (zcs->jobs[jobID].jobCompleted==0) { + DEBUGLOG(4, "waiting for jobCompleted signal from chunk %u", zcs->doneJobID); /* we want to block when waiting for data to flush */ + pthread_cond_wait(&zcs->jobCompleted_cond, &zcs->jobCompleted_mutex); + } + pthread_mutex_unlock(&zcs->jobCompleted_mutex); + zcs->doneJobID++; + } +} + + +static size_t ZSTDMT_initCStream_internal(ZSTDMT_CCtx* zcs, + const void* dict, size_t dictSize, unsigned updateDict, + ZSTD_parameters params, unsigned long long pledgedSrcSize) +{ + ZSTD_customMem const cmem = { NULL, NULL, NULL }; + DEBUGLOG(3, "Started new compression, with windowLog : %u", params.cParams.windowLog); + if (zcs->nbThreads==1) return ZSTD_initCStream_advanced(zcs->cstream, dict, dictSize, params, pledgedSrcSize); + if (zcs->allJobsCompleted == 0) { /* previous job not correctly finished */ + ZSTDMT_waitForAllJobsCompleted(zcs); + ZSTDMT_releaseAllJobResources(zcs); + zcs->allJobsCompleted = 1; + } + zcs->params = params; + if (updateDict) { + ZSTD_freeCDict(zcs->cdict); zcs->cdict = NULL; + if (dict && dictSize) { + zcs->cdict = ZSTD_createCDict_advanced(dict, dictSize, 0, params, cmem); + if (zcs->cdict == NULL) return ERROR(memory_allocation); + } } + zcs->frameContentSize = pledgedSrcSize; + zcs->targetDictSize = (zcs->overlapRLog>=9) ? 0 : (size_t)1 << (zcs->params.cParams.windowLog - zcs->overlapRLog); + DEBUGLOG(4, "overlapRLog : %u ", zcs->overlapRLog); + DEBUGLOG(3, "overlap Size : %u KB", (U32)(zcs->targetDictSize>>10)); + zcs->targetSectionSize = zcs->sectionSize ? zcs->sectionSize : (size_t)1 << (zcs->params.cParams.windowLog + 2); + zcs->targetSectionSize = MAX(ZSTDMT_SECTION_SIZE_MIN, zcs->targetSectionSize); + zcs->targetSectionSize = MAX(zcs->targetDictSize, zcs->targetSectionSize); + DEBUGLOG(3, "Section Size : %u KB", (U32)(zcs->targetSectionSize>>10)); + zcs->marginSize = zcs->targetSectionSize >> 2; + zcs->inBuffSize = zcs->targetDictSize + zcs->targetSectionSize + zcs->marginSize; + zcs->inBuff.buffer = ZSTDMT_getBuffer(zcs->buffPool, zcs->inBuffSize); + if (zcs->inBuff.buffer.start == NULL) return ERROR(memory_allocation); + zcs->inBuff.filled = 0; + zcs->dictSize = 0; + zcs->doneJobID = 0; + zcs->nextJobID = 0; + zcs->frameEnded = 0; + zcs->allJobsCompleted = 0; + if (params.fParams.checksumFlag) XXH64_reset(&zcs->xxhState, 0); + return 0; +} + +size_t ZSTDMT_initCStream_advanced(ZSTDMT_CCtx* zcs, + const void* dict, size_t dictSize, + ZSTD_parameters params, unsigned long long pledgedSrcSize) +{ + return ZSTDMT_initCStream_internal(zcs, dict, dictSize, 1, params, pledgedSrcSize); +} + +/* ZSTDMT_resetCStream() : + * pledgedSrcSize is optional and can be zero == unknown */ +size_t ZSTDMT_resetCStream(ZSTDMT_CCtx* zcs, unsigned long long pledgedSrcSize) +{ + if (zcs->nbThreads==1) return ZSTD_resetCStream(zcs->cstream, pledgedSrcSize); + return ZSTDMT_initCStream_internal(zcs, NULL, 0, 0, zcs->params, pledgedSrcSize); +} + +size_t ZSTDMT_initCStream(ZSTDMT_CCtx* zcs, int compressionLevel) { + ZSTD_parameters const params = ZSTD_getParams(compressionLevel, 0, 0); + return ZSTDMT_initCStream_internal(zcs, NULL, 0, 1, params, 0); +} + + +static size_t ZSTDMT_createCompressionJob(ZSTDMT_CCtx* zcs, size_t srcSize, unsigned endFrame) +{ + size_t const dstBufferCapacity = ZSTD_compressBound(srcSize); + buffer_t const dstBuffer = ZSTDMT_getBuffer(zcs->buffPool, dstBufferCapacity); + ZSTD_CCtx* const cctx = ZSTDMT_getCCtx(zcs->cctxPool); + unsigned const jobID = zcs->nextJobID & zcs->jobIDMask; + + if ((cctx==NULL) || (dstBuffer.start==NULL)) { + zcs->jobs[jobID].jobCompleted = 1; + zcs->nextJobID++; + ZSTDMT_waitForAllJobsCompleted(zcs); + ZSTDMT_releaseAllJobResources(zcs); + return ERROR(memory_allocation); + } + + DEBUGLOG(4, "preparing job %u to compress %u bytes with %u preload ", zcs->nextJobID, (U32)srcSize, (U32)zcs->dictSize); + zcs->jobs[jobID].src = zcs->inBuff.buffer; + zcs->jobs[jobID].srcStart = zcs->inBuff.buffer.start; + zcs->jobs[jobID].srcSize = srcSize; + zcs->jobs[jobID].dictSize = zcs->dictSize; /* note : zcs->inBuff.filled is presumed >= srcSize + dictSize */ + zcs->jobs[jobID].params = zcs->params; + if (zcs->nextJobID) zcs->jobs[jobID].params.fParams.checksumFlag = 0; /* do not calculate checksum within sections, just keep it in header for first section */ + zcs->jobs[jobID].cdict = zcs->nextJobID==0 ? zcs->cdict : NULL; + zcs->jobs[jobID].fullFrameSize = zcs->frameContentSize; + zcs->jobs[jobID].dstBuff = dstBuffer; + zcs->jobs[jobID].cctx = cctx; + zcs->jobs[jobID].firstChunk = (zcs->nextJobID==0); + zcs->jobs[jobID].lastChunk = endFrame; + zcs->jobs[jobID].jobCompleted = 0; + zcs->jobs[jobID].dstFlushed = 0; + zcs->jobs[jobID].jobCompleted_mutex = &zcs->jobCompleted_mutex; + zcs->jobs[jobID].jobCompleted_cond = &zcs->jobCompleted_cond; + + /* get a new buffer for next input */ + if (!endFrame) { + size_t const newDictSize = MIN(srcSize + zcs->dictSize, zcs->targetDictSize); + zcs->inBuff.buffer = ZSTDMT_getBuffer(zcs->buffPool, zcs->inBuffSize); + if (zcs->inBuff.buffer.start == NULL) { /* not enough memory to allocate next input buffer */ + zcs->jobs[jobID].jobCompleted = 1; + zcs->nextJobID++; + ZSTDMT_waitForAllJobsCompleted(zcs); + ZSTDMT_releaseAllJobResources(zcs); + return ERROR(memory_allocation); + } + DEBUGLOG(5, "inBuff filled to %u", (U32)zcs->inBuff.filled); + zcs->inBuff.filled -= srcSize + zcs->dictSize - newDictSize; + DEBUGLOG(5, "new job : filled to %u, with %u dict and %u src", (U32)zcs->inBuff.filled, (U32)newDictSize, (U32)(zcs->inBuff.filled - newDictSize)); + memmove(zcs->inBuff.buffer.start, (const char*)zcs->jobs[jobID].srcStart + zcs->dictSize + srcSize - newDictSize, zcs->inBuff.filled); + DEBUGLOG(5, "new inBuff pre-filled"); + zcs->dictSize = newDictSize; + } else { + zcs->inBuff.buffer = g_nullBuffer; + zcs->inBuff.filled = 0; + zcs->dictSize = 0; + zcs->frameEnded = 1; + if (zcs->nextJobID == 0) + zcs->params.fParams.checksumFlag = 0; /* single chunk : checksum is calculated directly within worker thread */ + } + + DEBUGLOG(3, "posting job %u : %u bytes (end:%u) (note : doneJob = %u=>%u)", zcs->nextJobID, (U32)zcs->jobs[jobID].srcSize, zcs->jobs[jobID].lastChunk, zcs->doneJobID, zcs->doneJobID & zcs->jobIDMask); + POOL_add(zcs->factory, ZSTDMT_compressChunk, &zcs->jobs[jobID]); /* this call is blocking when thread worker pool is exhausted */ + zcs->nextJobID++; + return 0; +} + + +/* ZSTDMT_flushNextJob() : + * output : will be updated with amount of data flushed . + * blockToFlush : if >0, the function will block and wait if there is no data available to flush . + * @return : amount of data remaining within internal buffer, 1 if unknown but > 0, 0 if no more, or an error code */ +static size_t ZSTDMT_flushNextJob(ZSTDMT_CCtx* zcs, ZSTD_outBuffer* output, unsigned blockToFlush) +{ + unsigned const wJobID = zcs->doneJobID & zcs->jobIDMask; + if (zcs->doneJobID == zcs->nextJobID) return 0; /* all flushed ! */ + PTHREAD_MUTEX_LOCK(&zcs->jobCompleted_mutex); + while (zcs->jobs[wJobID].jobCompleted==0) { + DEBUGLOG(5, "waiting for jobCompleted signal from job %u", zcs->doneJobID); + if (!blockToFlush) { pthread_mutex_unlock(&zcs->jobCompleted_mutex); return 0; } /* nothing ready to be flushed => skip */ + pthread_cond_wait(&zcs->jobCompleted_cond, &zcs->jobCompleted_mutex); /* block when nothing available to flush */ + } + pthread_mutex_unlock(&zcs->jobCompleted_mutex); + /* compression job completed : output can be flushed */ + { ZSTDMT_jobDescription job = zcs->jobs[wJobID]; + if (!job.jobScanned) { + if (ZSTD_isError(job.cSize)) { + DEBUGLOG(5, "compression error detected "); + ZSTDMT_waitForAllJobsCompleted(zcs); + ZSTDMT_releaseAllJobResources(zcs); + return job.cSize; + } + ZSTDMT_releaseCCtx(zcs->cctxPool, job.cctx); + zcs->jobs[wJobID].cctx = NULL; + DEBUGLOG(5, "zcs->params.fParams.checksumFlag : %u ", zcs->params.fParams.checksumFlag); + if (zcs->params.fParams.checksumFlag) { + XXH64_update(&zcs->xxhState, (const char*)job.srcStart + job.dictSize, job.srcSize); + if (zcs->frameEnded && (zcs->doneJobID+1 == zcs->nextJobID)) { /* write checksum at end of last section */ + U32 const checksum = (U32)XXH64_digest(&zcs->xxhState); + DEBUGLOG(4, "writing checksum : %08X \n", checksum); + MEM_writeLE32((char*)job.dstBuff.start + job.cSize, checksum); + job.cSize += 4; + zcs->jobs[wJobID].cSize += 4; + } } + ZSTDMT_releaseBuffer(zcs->buffPool, job.src); + zcs->jobs[wJobID].srcStart = NULL; + zcs->jobs[wJobID].src = g_nullBuffer; + zcs->jobs[wJobID].jobScanned = 1; + } + { size_t const toWrite = MIN(job.cSize - job.dstFlushed, output->size - output->pos); + DEBUGLOG(4, "Flushing %u bytes from job %u ", (U32)toWrite, zcs->doneJobID); + memcpy((char*)output->dst + output->pos, (const char*)job.dstBuff.start + job.dstFlushed, toWrite); + output->pos += toWrite; + job.dstFlushed += toWrite; + } + if (job.dstFlushed == job.cSize) { /* output buffer fully flushed => move to next one */ + ZSTDMT_releaseBuffer(zcs->buffPool, job.dstBuff); + zcs->jobs[wJobID].dstBuff = g_nullBuffer; + zcs->jobs[wJobID].jobCompleted = 0; + zcs->doneJobID++; + } else { + zcs->jobs[wJobID].dstFlushed = job.dstFlushed; + } + /* return value : how many bytes left in buffer ; fake it to 1 if unknown but >0 */ + if (job.cSize > job.dstFlushed) return (job.cSize - job.dstFlushed); + if (zcs->doneJobID < zcs->nextJobID) return 1; /* still some buffer to flush */ + zcs->allJobsCompleted = zcs->frameEnded; /* frame completed and entirely flushed */ + return 0; /* everything flushed */ +} } + + +size_t ZSTDMT_compressStream(ZSTDMT_CCtx* zcs, ZSTD_outBuffer* output, ZSTD_inBuffer* input) +{ + size_t const newJobThreshold = zcs->dictSize + zcs->targetSectionSize + zcs->marginSize; + if (zcs->frameEnded) return ERROR(stage_wrong); /* current frame being ended. Only flush is allowed. Restart with init */ + if (zcs->nbThreads==1) return ZSTD_compressStream(zcs->cstream, output, input); + + /* fill input buffer */ + { size_t const toLoad = MIN(input->size - input->pos, zcs->inBuffSize - zcs->inBuff.filled); + memcpy((char*)zcs->inBuff.buffer.start + zcs->inBuff.filled, input->src, toLoad); + input->pos += toLoad; + zcs->inBuff.filled += toLoad; + } + + if ( (zcs->inBuff.filled >= newJobThreshold) /* filled enough : let's compress */ + && (zcs->nextJobID <= zcs->doneJobID + zcs->jobIDMask) ) { /* avoid overwriting job round buffer */ + CHECK_F( ZSTDMT_createCompressionJob(zcs, zcs->targetSectionSize, 0) ); + } + + /* check for data to flush */ + CHECK_F( ZSTDMT_flushNextJob(zcs, output, (zcs->inBuff.filled == zcs->inBuffSize)) ); /* block if it wasn't possible to create new job due to saturation */ + + /* recommended next input size : fill current input buffer */ + return zcs->inBuffSize - zcs->inBuff.filled; /* note : could be zero when input buffer is fully filled and no more availability to create new job */ +} + + +static size_t ZSTDMT_flushStream_internal(ZSTDMT_CCtx* zcs, ZSTD_outBuffer* output, unsigned endFrame) +{ + size_t const srcSize = zcs->inBuff.filled - zcs->dictSize; + + if (srcSize) DEBUGLOG(4, "flushing : %u bytes left to compress", (U32)srcSize); + if ( ((srcSize > 0) || (endFrame && !zcs->frameEnded)) + && (zcs->nextJobID <= zcs->doneJobID + zcs->jobIDMask) ) { + CHECK_F( ZSTDMT_createCompressionJob(zcs, srcSize, endFrame) ); + } + + /* check if there is any data available to flush */ + DEBUGLOG(5, "zcs->doneJobID : %u ; zcs->nextJobID : %u ", zcs->doneJobID, zcs->nextJobID); + return ZSTDMT_flushNextJob(zcs, output, 1); +} + + +size_t ZSTDMT_flushStream(ZSTDMT_CCtx* zcs, ZSTD_outBuffer* output) +{ + if (zcs->nbThreads==1) return ZSTD_flushStream(zcs->cstream, output); + return ZSTDMT_flushStream_internal(zcs, output, 0); +} + +size_t ZSTDMT_endStream(ZSTDMT_CCtx* zcs, ZSTD_outBuffer* output) +{ + if (zcs->nbThreads==1) return ZSTD_endStream(zcs->cstream, output); + return ZSTDMT_flushStream_internal(zcs, output, 1); +}
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/contrib/python-zstandard/zstd/compress/zstdmt_compress.h Tue Apr 18 12:24:34 2017 -0400 @@ -0,0 +1,78 @@ +/** + * Copyright (c) 2016-present, Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under the BSD-style license found in the + * LICENSE file in the root directory of this source tree. An additional grant + * of patent rights can be found in the PATENTS file in the same directory. + */ + + #ifndef ZSTDMT_COMPRESS_H + #define ZSTDMT_COMPRESS_H + + #if defined (__cplusplus) + extern "C" { + #endif + + +/* Note : All prototypes defined in this file shall be considered experimental. + * There is no guarantee of API continuity (yet) on any of these prototypes */ + +/* === Dependencies === */ +#include <stddef.h> /* size_t */ +#define ZSTD_STATIC_LINKING_ONLY /* ZSTD_parameters */ +#include "zstd.h" /* ZSTD_inBuffer, ZSTD_outBuffer, ZSTDLIB_API */ + + +/* === Simple one-pass functions === */ + +typedef struct ZSTDMT_CCtx_s ZSTDMT_CCtx; +ZSTDLIB_API ZSTDMT_CCtx* ZSTDMT_createCCtx(unsigned nbThreads); +ZSTDLIB_API size_t ZSTDMT_freeCCtx(ZSTDMT_CCtx* cctx); + +ZSTDLIB_API size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* cctx, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + int compressionLevel); + + +/* === Streaming functions === */ + +ZSTDLIB_API size_t ZSTDMT_initCStream(ZSTDMT_CCtx* mtctx, int compressionLevel); +ZSTDLIB_API size_t ZSTDMT_resetCStream(ZSTDMT_CCtx* mtctx, unsigned long long pledgedSrcSize); /**< pledgedSrcSize is optional and can be zero == unknown */ + +ZSTDLIB_API size_t ZSTDMT_compressStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output, ZSTD_inBuffer* input); + +ZSTDLIB_API size_t ZSTDMT_flushStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output); /**< @return : 0 == all flushed; >0 : still some data to be flushed; or an error code (ZSTD_isError()) */ +ZSTDLIB_API size_t ZSTDMT_endStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output); /**< @return : 0 == all flushed; >0 : still some data to be flushed; or an error code (ZSTD_isError()) */ + + +/* === Advanced functions and parameters === */ + +#ifndef ZSTDMT_SECTION_SIZE_MIN +# define ZSTDMT_SECTION_SIZE_MIN (1U << 20) /* 1 MB - Minimum size of each compression job */ +#endif + +ZSTDLIB_API size_t ZSTDMT_initCStream_advanced(ZSTDMT_CCtx* mtctx, const void* dict, size_t dictSize, /**< dict can be released after init, a local copy is preserved within zcs */ + ZSTD_parameters params, unsigned long long pledgedSrcSize); /**< pledgedSrcSize is optional and can be zero == unknown */ + +/* ZSDTMT_parameter : + * List of parameters that can be set using ZSTDMT_setMTCtxParameter() */ +typedef enum { + ZSTDMT_p_sectionSize, /* size of input "section". Each section is compressed in parallel. 0 means default, which is dynamically determined within compression functions */ + ZSTDMT_p_overlapSectionLog /* Log of overlapped section; 0 == no overlap, 6(default) == use 1/8th of window, >=9 == use full window */ +} ZSDTMT_parameter; + +/* ZSTDMT_setMTCtxParameter() : + * allow setting individual parameters, one at a time, among a list of enums defined in ZSTDMT_parameter. + * The function must be called typically after ZSTD_createCCtx(). + * Parameters not explicitly reset by ZSTDMT_init*() remain the same in consecutive compression sessions. + * @return : 0, or an error code (which can be tested using ZSTD_isError()) */ +ZSTDLIB_API size_t ZSTDMT_setMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSDTMT_parameter parameter, unsigned value); + + +#if defined (__cplusplus) +} +#endif + +#endif /* ZSTDMT_COMPRESS_H */
--- a/contrib/python-zstandard/zstd/decompress/zstd_decompress.c Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/python-zstandard/zstd/decompress/zstd_decompress.c Tue Apr 18 12:24:34 2017 -0400 @@ -1444,7 +1444,7 @@ #if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT==1) if (ZSTD_isLegacy(src, srcSize)) return ZSTD_decompressLegacy(dst, dstCapacity, src, srcSize, dict, dictSize); #endif - ZSTD_decompressBegin_usingDict(dctx, dict, dictSize); + CHECK_F(ZSTD_decompressBegin_usingDict(dctx, dict, dictSize)); ZSTD_checkContinuity(dctx, dst); return ZSTD_decompressFrame(dctx, dst, dstCapacity, src, srcSize); } @@ -1671,9 +1671,9 @@ } if (dictPtr+12 > dictEnd) return ERROR(dictionary_corrupted); - dctx->rep[0] = MEM_readLE32(dictPtr+0); if (dctx->rep[0] >= dictSize) return ERROR(dictionary_corrupted); - dctx->rep[1] = MEM_readLE32(dictPtr+4); if (dctx->rep[1] >= dictSize) return ERROR(dictionary_corrupted); - dctx->rep[2] = MEM_readLE32(dictPtr+8); if (dctx->rep[2] >= dictSize) return ERROR(dictionary_corrupted); + dctx->rep[0] = MEM_readLE32(dictPtr+0); if (dctx->rep[0] == 0 || dctx->rep[0] >= dictSize) return ERROR(dictionary_corrupted); + dctx->rep[1] = MEM_readLE32(dictPtr+4); if (dctx->rep[1] == 0 || dctx->rep[1] >= dictSize) return ERROR(dictionary_corrupted); + dctx->rep[2] = MEM_readLE32(dictPtr+8); if (dctx->rep[2] == 0 || dctx->rep[2] >= dictSize) return ERROR(dictionary_corrupted); dictPtr += 12; dctx->litEntropy = dctx->fseEntropy = 1; @@ -1713,39 +1713,44 @@ /* ====== ZSTD_DDict ====== */ struct ZSTD_DDict_s { - void* dict; + void* dictBuffer; + const void* dictContent; size_t dictSize; ZSTD_DCtx* refContext; }; /* typedef'd to ZSTD_DDict within "zstd.h" */ -ZSTD_DDict* ZSTD_createDDict_advanced(const void* dict, size_t dictSize, ZSTD_customMem customMem) +ZSTD_DDict* ZSTD_createDDict_advanced(const void* dict, size_t dictSize, unsigned byReference, ZSTD_customMem customMem) { if (!customMem.customAlloc && !customMem.customFree) customMem = defaultCustomMem; if (!customMem.customAlloc || !customMem.customFree) return NULL; { ZSTD_DDict* const ddict = (ZSTD_DDict*) ZSTD_malloc(sizeof(ZSTD_DDict), customMem); - void* const dictContent = ZSTD_malloc(dictSize, customMem); ZSTD_DCtx* const dctx = ZSTD_createDCtx_advanced(customMem); - if (!dictContent || !ddict || !dctx) { - ZSTD_free(dictContent, customMem); + if (!ddict || !dctx) { ZSTD_free(ddict, customMem); ZSTD_free(dctx, customMem); return NULL; } - if (dictSize) { - memcpy(dictContent, dict, dictSize); + if ((byReference) || (!dict) || (!dictSize)) { + ddict->dictBuffer = NULL; + ddict->dictContent = dict; + } else { + void* const internalBuffer = ZSTD_malloc(dictSize, customMem); + if (!internalBuffer) { ZSTD_free(dctx, customMem); ZSTD_free(ddict, customMem); return NULL; } + memcpy(internalBuffer, dict, dictSize); + ddict->dictBuffer = internalBuffer; + ddict->dictContent = internalBuffer; } - { size_t const errorCode = ZSTD_decompressBegin_usingDict(dctx, dictContent, dictSize); + { size_t const errorCode = ZSTD_decompressBegin_usingDict(dctx, ddict->dictContent, dictSize); if (ZSTD_isError(errorCode)) { - ZSTD_free(dictContent, customMem); + ZSTD_free(ddict->dictBuffer, customMem); ZSTD_free(ddict, customMem); ZSTD_free(dctx, customMem); return NULL; } } - ddict->dict = dictContent; ddict->dictSize = dictSize; ddict->refContext = dctx; return ddict; @@ -1758,15 +1763,27 @@ ZSTD_DDict* ZSTD_createDDict(const void* dict, size_t dictSize) { ZSTD_customMem const allocator = { NULL, NULL, NULL }; - return ZSTD_createDDict_advanced(dict, dictSize, allocator); + return ZSTD_createDDict_advanced(dict, dictSize, 0, allocator); } + +/*! ZSTD_createDDict_byReference() : + * Create a digested dictionary, ready to start decompression operation without startup delay. + * Dictionary content is simply referenced, and therefore stays in dictBuffer. + * It is important that dictBuffer outlives DDict, it must remain read accessible throughout the lifetime of DDict */ +ZSTD_DDict* ZSTD_createDDict_byReference(const void* dictBuffer, size_t dictSize) +{ + ZSTD_customMem const allocator = { NULL, NULL, NULL }; + return ZSTD_createDDict_advanced(dictBuffer, dictSize, 1, allocator); +} + + size_t ZSTD_freeDDict(ZSTD_DDict* ddict) { if (ddict==NULL) return 0; /* support free on NULL */ { ZSTD_customMem const cMem = ddict->refContext->customMem; ZSTD_freeDCtx(ddict->refContext); - ZSTD_free(ddict->dict, cMem); + ZSTD_free(ddict->dictBuffer, cMem); ZSTD_free(ddict, cMem); return 0; } @@ -1775,7 +1792,7 @@ size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict) { if (ddict==NULL) return 0; /* support sizeof on NULL */ - return sizeof(*ddict) + sizeof(ddict->refContext) + ddict->dictSize; + return sizeof(*ddict) + ZSTD_sizeof_DCtx(ddict->refContext) + (ddict->dictBuffer ? ddict->dictSize : 0) ; } /*! ZSTD_getDictID_fromDict() : @@ -1796,7 +1813,7 @@ unsigned ZSTD_getDictID_fromDDict(const ZSTD_DDict* ddict) { if (ddict==NULL) return 0; - return ZSTD_getDictID_fromDict(ddict->dict, ddict->dictSize); + return ZSTD_getDictID_fromDict(ddict->dictContent, ddict->dictSize); } /*! ZSTD_getDictID_fromFrame() : @@ -1827,7 +1844,7 @@ const ZSTD_DDict* ddict) { #if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT==1) - if (ZSTD_isLegacy(src, srcSize)) return ZSTD_decompressLegacy(dst, dstCapacity, src, srcSize, ddict->dict, ddict->dictSize); + if (ZSTD_isLegacy(src, srcSize)) return ZSTD_decompressLegacy(dst, dstCapacity, src, srcSize, ddict->dictContent, ddict->dictSize); #endif ZSTD_refDCtx(dctx, ddict->refContext); ZSTD_checkContinuity(dctx, dst); @@ -1919,7 +1936,7 @@ zds->stage = zdss_loadHeader; zds->lhSize = zds->inPos = zds->outStart = zds->outEnd = 0; ZSTD_freeDDict(zds->ddictLocal); - if (dict) { + if (dict && dictSize >= 8) { zds->ddictLocal = ZSTD_createDDict(dict, dictSize); if (zds->ddictLocal == NULL) return ERROR(memory_allocation); } else zds->ddictLocal = NULL; @@ -1956,7 +1973,7 @@ switch(paramType) { default : return ERROR(parameter_unknown); - case ZSTDdsp_maxWindowSize : zds->maxWindowSize = paramValue ? paramValue : (U32)(-1); break; + case DStream_p_maxWindowSize : zds->maxWindowSize = paramValue ? paramValue : (U32)(-1); break; } return 0; } @@ -2007,7 +2024,7 @@ #if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT>=1) { U32 const legacyVersion = ZSTD_isLegacy(istart, iend-istart); if (legacyVersion) { - const void* const dict = zds->ddict ? zds->ddict->dict : NULL; + const void* const dict = zds->ddict ? zds->ddict->dictContent : NULL; size_t const dictSize = zds->ddict ? zds->ddict->dictSize : 0; CHECK_F(ZSTD_initLegacyStream(&zds->legacyContext, zds->previousLegacyVersion, legacyVersion, dict, dictSize));
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/contrib/python-zstandard/zstd/dictBuilder/cover.c Tue Apr 18 12:24:34 2017 -0400 @@ -0,0 +1,1021 @@ +/** + * Copyright (c) 2016-present, Yann Collet, Facebook, Inc. + * All rights reserved. + * + * This source code is licensed under the BSD-style license found in the + * LICENSE file in the root directory of this source tree. An additional grant + * of patent rights can be found in the PATENTS file in the same directory. + */ + +/*-************************************* +* Dependencies +***************************************/ +#include <stdio.h> /* fprintf */ +#include <stdlib.h> /* malloc, free, qsort */ +#include <string.h> /* memset */ +#include <time.h> /* clock */ + +#include "mem.h" /* read */ +#include "pool.h" +#include "threading.h" +#include "zstd_internal.h" /* includes zstd.h */ +#ifndef ZDICT_STATIC_LINKING_ONLY +#define ZDICT_STATIC_LINKING_ONLY +#endif +#include "zdict.h" + +/*-************************************* +* Constants +***************************************/ +#define COVER_MAX_SAMPLES_SIZE (sizeof(size_t) == 8 ? ((U32)-1) : ((U32)1 GB)) + +/*-************************************* +* Console display +***************************************/ +static int g_displayLevel = 2; +#define DISPLAY(...) \ + { \ + fprintf(stderr, __VA_ARGS__); \ + fflush(stderr); \ + } +#define LOCALDISPLAYLEVEL(displayLevel, l, ...) \ + if (displayLevel >= l) { \ + DISPLAY(__VA_ARGS__); \ + } /* 0 : no display; 1: errors; 2: default; 3: details; 4: debug */ +#define DISPLAYLEVEL(l, ...) LOCALDISPLAYLEVEL(g_displayLevel, l, __VA_ARGS__) + +#define LOCALDISPLAYUPDATE(displayLevel, l, ...) \ + if (displayLevel >= l) { \ + if ((clock() - g_time > refreshRate) || (displayLevel >= 4)) { \ + g_time = clock(); \ + DISPLAY(__VA_ARGS__); \ + if (displayLevel >= 4) \ + fflush(stdout); \ + } \ + } +#define DISPLAYUPDATE(l, ...) LOCALDISPLAYUPDATE(g_displayLevel, l, __VA_ARGS__) +static const clock_t refreshRate = CLOCKS_PER_SEC * 15 / 100; +static clock_t g_time = 0; + +/*-************************************* +* Hash table +*************************************** +* A small specialized hash map for storing activeDmers. +* The map does not resize, so if it becomes full it will loop forever. +* Thus, the map must be large enough to store every value. +* The map implements linear probing and keeps its load less than 0.5. +*/ + +#define MAP_EMPTY_VALUE ((U32)-1) +typedef struct COVER_map_pair_t_s { + U32 key; + U32 value; +} COVER_map_pair_t; + +typedef struct COVER_map_s { + COVER_map_pair_t *data; + U32 sizeLog; + U32 size; + U32 sizeMask; +} COVER_map_t; + +/** + * Clear the map. + */ +static void COVER_map_clear(COVER_map_t *map) { + memset(map->data, MAP_EMPTY_VALUE, map->size * sizeof(COVER_map_pair_t)); +} + +/** + * Initializes a map of the given size. + * Returns 1 on success and 0 on failure. + * The map must be destroyed with COVER_map_destroy(). + * The map is only guaranteed to be large enough to hold size elements. + */ +static int COVER_map_init(COVER_map_t *map, U32 size) { + map->sizeLog = ZSTD_highbit32(size) + 2; + map->size = (U32)1 << map->sizeLog; + map->sizeMask = map->size - 1; + map->data = (COVER_map_pair_t *)malloc(map->size * sizeof(COVER_map_pair_t)); + if (!map->data) { + map->sizeLog = 0; + map->size = 0; + return 0; + } + COVER_map_clear(map); + return 1; +} + +/** + * Internal hash function + */ +static const U32 prime4bytes = 2654435761U; +static U32 COVER_map_hash(COVER_map_t *map, U32 key) { + return (key * prime4bytes) >> (32 - map->sizeLog); +} + +/** + * Helper function that returns the index that a key should be placed into. + */ +static U32 COVER_map_index(COVER_map_t *map, U32 key) { + const U32 hash = COVER_map_hash(map, key); + U32 i; + for (i = hash;; i = (i + 1) & map->sizeMask) { + COVER_map_pair_t *pos = &map->data[i]; + if (pos->value == MAP_EMPTY_VALUE) { + return i; + } + if (pos->key == key) { + return i; + } + } +} + +/** + * Returns the pointer to the value for key. + * If key is not in the map, it is inserted and the value is set to 0. + * The map must not be full. + */ +static U32 *COVER_map_at(COVER_map_t *map, U32 key) { + COVER_map_pair_t *pos = &map->data[COVER_map_index(map, key)]; + if (pos->value == MAP_EMPTY_VALUE) { + pos->key = key; + pos->value = 0; + } + return &pos->value; +} + +/** + * Deletes key from the map if present. + */ +static void COVER_map_remove(COVER_map_t *map, U32 key) { + U32 i = COVER_map_index(map, key); + COVER_map_pair_t *del = &map->data[i]; + U32 shift = 1; + if (del->value == MAP_EMPTY_VALUE) { + return; + } + for (i = (i + 1) & map->sizeMask;; i = (i + 1) & map->sizeMask) { + COVER_map_pair_t *const pos = &map->data[i]; + /* If the position is empty we are done */ + if (pos->value == MAP_EMPTY_VALUE) { + del->value = MAP_EMPTY_VALUE; + return; + } + /* If pos can be moved to del do so */ + if (((i - COVER_map_hash(map, pos->key)) & map->sizeMask) >= shift) { + del->key = pos->key; + del->value = pos->value; + del = pos; + shift = 1; + } else { + ++shift; + } + } +} + +/** + * Destroyes a map that is inited with COVER_map_init(). + */ +static void COVER_map_destroy(COVER_map_t *map) { + if (map->data) { + free(map->data); + } + map->data = NULL; + map->size = 0; +} + +/*-************************************* +* Context +***************************************/ + +typedef struct { + const BYTE *samples; + size_t *offsets; + const size_t *samplesSizes; + size_t nbSamples; + U32 *suffix; + size_t suffixSize; + U32 *freqs; + U32 *dmerAt; + unsigned d; +} COVER_ctx_t; + +/* We need a global context for qsort... */ +static COVER_ctx_t *g_ctx = NULL; + +/*-************************************* +* Helper functions +***************************************/ + +/** + * Returns the sum of the sample sizes. + */ +static size_t COVER_sum(const size_t *samplesSizes, unsigned nbSamples) { + size_t sum = 0; + size_t i; + for (i = 0; i < nbSamples; ++i) { + sum += samplesSizes[i]; + } + return sum; +} + +/** + * Returns -1 if the dmer at lp is less than the dmer at rp. + * Return 0 if the dmers at lp and rp are equal. + * Returns 1 if the dmer at lp is greater than the dmer at rp. + */ +static int COVER_cmp(COVER_ctx_t *ctx, const void *lp, const void *rp) { + const U32 lhs = *(const U32 *)lp; + const U32 rhs = *(const U32 *)rp; + return memcmp(ctx->samples + lhs, ctx->samples + rhs, ctx->d); +} + +/** + * Same as COVER_cmp() except ties are broken by pointer value + * NOTE: g_ctx must be set to call this function. A global is required because + * qsort doesn't take an opaque pointer. + */ +static int COVER_strict_cmp(const void *lp, const void *rp) { + int result = COVER_cmp(g_ctx, lp, rp); + if (result == 0) { + result = lp < rp ? -1 : 1; + } + return result; +} + +/** + * Returns the first pointer in [first, last) whose element does not compare + * less than value. If no such element exists it returns last. + */ +static const size_t *COVER_lower_bound(const size_t *first, const size_t *last, + size_t value) { + size_t count = last - first; + while (count != 0) { + size_t step = count / 2; + const size_t *ptr = first; + ptr += step; + if (*ptr < value) { + first = ++ptr; + count -= step + 1; + } else { + count = step; + } + } + return first; +} + +/** + * Generic groupBy function. + * Groups an array sorted by cmp into groups with equivalent values. + * Calls grp for each group. + */ +static void +COVER_groupBy(const void *data, size_t count, size_t size, COVER_ctx_t *ctx, + int (*cmp)(COVER_ctx_t *, const void *, const void *), + void (*grp)(COVER_ctx_t *, const void *, const void *)) { + const BYTE *ptr = (const BYTE *)data; + size_t num = 0; + while (num < count) { + const BYTE *grpEnd = ptr + size; + ++num; + while (num < count && cmp(ctx, ptr, grpEnd) == 0) { + grpEnd += size; + ++num; + } + grp(ctx, ptr, grpEnd); + ptr = grpEnd; + } +} + +/*-************************************* +* Cover functions +***************************************/ + +/** + * Called on each group of positions with the same dmer. + * Counts the frequency of each dmer and saves it in the suffix array. + * Fills `ctx->dmerAt`. + */ +static void COVER_group(COVER_ctx_t *ctx, const void *group, + const void *groupEnd) { + /* The group consists of all the positions with the same first d bytes. */ + const U32 *grpPtr = (const U32 *)group; + const U32 *grpEnd = (const U32 *)groupEnd; + /* The dmerId is how we will reference this dmer. + * This allows us to map the whole dmer space to a much smaller space, the + * size of the suffix array. + */ + const U32 dmerId = (U32)(grpPtr - ctx->suffix); + /* Count the number of samples this dmer shows up in */ + U32 freq = 0; + /* Details */ + const size_t *curOffsetPtr = ctx->offsets; + const size_t *offsetsEnd = ctx->offsets + ctx->nbSamples; + /* Once *grpPtr >= curSampleEnd this occurrence of the dmer is in a + * different sample than the last. + */ + size_t curSampleEnd = ctx->offsets[0]; + for (; grpPtr != grpEnd; ++grpPtr) { + /* Save the dmerId for this position so we can get back to it. */ + ctx->dmerAt[*grpPtr] = dmerId; + /* Dictionaries only help for the first reference to the dmer. + * After that zstd can reference the match from the previous reference. + * So only count each dmer once for each sample it is in. + */ + if (*grpPtr < curSampleEnd) { + continue; + } + freq += 1; + /* Binary search to find the end of the sample *grpPtr is in. + * In the common case that grpPtr + 1 == grpEnd we can skip the binary + * search because the loop is over. + */ + if (grpPtr + 1 != grpEnd) { + const size_t *sampleEndPtr = + COVER_lower_bound(curOffsetPtr, offsetsEnd, *grpPtr); + curSampleEnd = *sampleEndPtr; + curOffsetPtr = sampleEndPtr + 1; + } + } + /* At this point we are never going to look at this segment of the suffix + * array again. We take advantage of this fact to save memory. + * We store the frequency of the dmer in the first position of the group, + * which is dmerId. + */ + ctx->suffix[dmerId] = freq; +} + +/** + * A segment is a range in the source as well as the score of the segment. + */ +typedef struct { + U32 begin; + U32 end; + double score; +} COVER_segment_t; + +/** + * Selects the best segment in an epoch. + * Segments of are scored according to the function: + * + * Let F(d) be the frequency of dmer d. + * Let S_i be the dmer at position i of segment S which has length k. + * + * Score(S) = F(S_1) + F(S_2) + ... + F(S_{k-d+1}) + * + * Once the dmer d is in the dictionay we set F(d) = 0. + */ +static COVER_segment_t COVER_selectSegment(const COVER_ctx_t *ctx, U32 *freqs, + COVER_map_t *activeDmers, U32 begin, + U32 end, COVER_params_t parameters) { + /* Constants */ + const U32 k = parameters.k; + const U32 d = parameters.d; + const U32 dmersInK = k - d + 1; + /* Try each segment (activeSegment) and save the best (bestSegment) */ + COVER_segment_t bestSegment = {0, 0, 0}; + COVER_segment_t activeSegment; + /* Reset the activeDmers in the segment */ + COVER_map_clear(activeDmers); + /* The activeSegment starts at the beginning of the epoch. */ + activeSegment.begin = begin; + activeSegment.end = begin; + activeSegment.score = 0; + /* Slide the activeSegment through the whole epoch. + * Save the best segment in bestSegment. + */ + while (activeSegment.end < end) { + /* The dmerId for the dmer at the next position */ + U32 newDmer = ctx->dmerAt[activeSegment.end]; + /* The entry in activeDmers for this dmerId */ + U32 *newDmerOcc = COVER_map_at(activeDmers, newDmer); + /* If the dmer isn't already present in the segment add its score. */ + if (*newDmerOcc == 0) { + /* The paper suggest using the L-0.5 norm, but experiments show that it + * doesn't help. + */ + activeSegment.score += freqs[newDmer]; + } + /* Add the dmer to the segment */ + activeSegment.end += 1; + *newDmerOcc += 1; + + /* If the window is now too large, drop the first position */ + if (activeSegment.end - activeSegment.begin == dmersInK + 1) { + U32 delDmer = ctx->dmerAt[activeSegment.begin]; + U32 *delDmerOcc = COVER_map_at(activeDmers, delDmer); + activeSegment.begin += 1; + *delDmerOcc -= 1; + /* If this is the last occurence of the dmer, subtract its score */ + if (*delDmerOcc == 0) { + COVER_map_remove(activeDmers, delDmer); + activeSegment.score -= freqs[delDmer]; + } + } + + /* If this segment is the best so far save it */ + if (activeSegment.score > bestSegment.score) { + bestSegment = activeSegment; + } + } + { + /* Trim off the zero frequency head and tail from the segment. */ + U32 newBegin = bestSegment.end; + U32 newEnd = bestSegment.begin; + U32 pos; + for (pos = bestSegment.begin; pos != bestSegment.end; ++pos) { + U32 freq = freqs[ctx->dmerAt[pos]]; + if (freq != 0) { + newBegin = MIN(newBegin, pos); + newEnd = pos + 1; + } + } + bestSegment.begin = newBegin; + bestSegment.end = newEnd; + } + { + /* Zero out the frequency of each dmer covered by the chosen segment. */ + U32 pos; + for (pos = bestSegment.begin; pos != bestSegment.end; ++pos) { + freqs[ctx->dmerAt[pos]] = 0; + } + } + return bestSegment; +} + +/** + * Check the validity of the parameters. + * Returns non-zero if the parameters are valid and 0 otherwise. + */ +static int COVER_checkParameters(COVER_params_t parameters) { + /* k and d are required parameters */ + if (parameters.d == 0 || parameters.k == 0) { + return 0; + } + /* d <= k */ + if (parameters.d > parameters.k) { + return 0; + } + return 1; +} + +/** + * Clean up a context initialized with `COVER_ctx_init()`. + */ +static void COVER_ctx_destroy(COVER_ctx_t *ctx) { + if (!ctx) { + return; + } + if (ctx->suffix) { + free(ctx->suffix); + ctx->suffix = NULL; + } + if (ctx->freqs) { + free(ctx->freqs); + ctx->freqs = NULL; + } + if (ctx->dmerAt) { + free(ctx->dmerAt); + ctx->dmerAt = NULL; + } + if (ctx->offsets) { + free(ctx->offsets); + ctx->offsets = NULL; + } +} + +/** + * Prepare a context for dictionary building. + * The context is only dependent on the parameter `d` and can used multiple + * times. + * Returns 1 on success or zero on error. + * The context must be destroyed with `COVER_ctx_destroy()`. + */ +static int COVER_ctx_init(COVER_ctx_t *ctx, const void *samplesBuffer, + const size_t *samplesSizes, unsigned nbSamples, + unsigned d) { + const BYTE *const samples = (const BYTE *)samplesBuffer; + const size_t totalSamplesSize = COVER_sum(samplesSizes, nbSamples); + /* Checks */ + if (totalSamplesSize < d || + totalSamplesSize >= (size_t)COVER_MAX_SAMPLES_SIZE) { + DISPLAYLEVEL(1, "Total samples size is too large, maximum size is %u MB\n", + (COVER_MAX_SAMPLES_SIZE >> 20)); + return 0; + } + /* Zero the context */ + memset(ctx, 0, sizeof(*ctx)); + DISPLAYLEVEL(2, "Training on %u samples of total size %u\n", nbSamples, + (U32)totalSamplesSize); + ctx->samples = samples; + ctx->samplesSizes = samplesSizes; + ctx->nbSamples = nbSamples; + /* Partial suffix array */ + ctx->suffixSize = totalSamplesSize - d + 1; + ctx->suffix = (U32 *)malloc(ctx->suffixSize * sizeof(U32)); + /* Maps index to the dmerID */ + ctx->dmerAt = (U32 *)malloc(ctx->suffixSize * sizeof(U32)); + /* The offsets of each file */ + ctx->offsets = (size_t *)malloc((nbSamples + 1) * sizeof(size_t)); + if (!ctx->suffix || !ctx->dmerAt || !ctx->offsets) { + DISPLAYLEVEL(1, "Failed to allocate scratch buffers\n"); + COVER_ctx_destroy(ctx); + return 0; + } + ctx->freqs = NULL; + ctx->d = d; + + /* Fill offsets from the samlesSizes */ + { + U32 i; + ctx->offsets[0] = 0; + for (i = 1; i <= nbSamples; ++i) { + ctx->offsets[i] = ctx->offsets[i - 1] + samplesSizes[i - 1]; + } + } + DISPLAYLEVEL(2, "Constructing partial suffix array\n"); + { + /* suffix is a partial suffix array. + * It only sorts suffixes by their first parameters.d bytes. + * The sort is stable, so each dmer group is sorted by position in input. + */ + U32 i; + for (i = 0; i < ctx->suffixSize; ++i) { + ctx->suffix[i] = i; + } + /* qsort doesn't take an opaque pointer, so pass as a global */ + g_ctx = ctx; + qsort(ctx->suffix, ctx->suffixSize, sizeof(U32), &COVER_strict_cmp); + } + DISPLAYLEVEL(2, "Computing frequencies\n"); + /* For each dmer group (group of positions with the same first d bytes): + * 1. For each position we set dmerAt[position] = dmerID. The dmerID is + * (groupBeginPtr - suffix). This allows us to go from position to + * dmerID so we can look up values in freq. + * 2. We calculate how many samples the dmer occurs in and save it in + * freqs[dmerId]. + */ + COVER_groupBy(ctx->suffix, ctx->suffixSize, sizeof(U32), ctx, &COVER_cmp, + &COVER_group); + ctx->freqs = ctx->suffix; + ctx->suffix = NULL; + return 1; +} + +/** + * Given the prepared context build the dictionary. + */ +static size_t COVER_buildDictionary(const COVER_ctx_t *ctx, U32 *freqs, + COVER_map_t *activeDmers, void *dictBuffer, + size_t dictBufferCapacity, + COVER_params_t parameters) { + BYTE *const dict = (BYTE *)dictBuffer; + size_t tail = dictBufferCapacity; + /* Divide the data up into epochs of equal size. + * We will select at least one segment from each epoch. + */ + const U32 epochs = (U32)(dictBufferCapacity / parameters.k); + const U32 epochSize = (U32)(ctx->suffixSize / epochs); + size_t epoch; + DISPLAYLEVEL(2, "Breaking content into %u epochs of size %u\n", epochs, + epochSize); + /* Loop through the epochs until there are no more segments or the dictionary + * is full. + */ + for (epoch = 0; tail > 0; epoch = (epoch + 1) % epochs) { + const U32 epochBegin = (U32)(epoch * epochSize); + const U32 epochEnd = epochBegin + epochSize; + size_t segmentSize; + /* Select a segment */ + COVER_segment_t segment = COVER_selectSegment( + ctx, freqs, activeDmers, epochBegin, epochEnd, parameters); + /* Trim the segment if necessary and if it is empty then we are done */ + segmentSize = MIN(segment.end - segment.begin + parameters.d - 1, tail); + if (segmentSize == 0) { + break; + } + /* We fill the dictionary from the back to allow the best segments to be + * referenced with the smallest offsets. + */ + tail -= segmentSize; + memcpy(dict + tail, ctx->samples + segment.begin, segmentSize); + DISPLAYUPDATE( + 2, "\r%u%% ", + (U32)(((dictBufferCapacity - tail) * 100) / dictBufferCapacity)); + } + DISPLAYLEVEL(2, "\r%79s\r", ""); + return tail; +} + +/** + * Translate from COVER_params_t to ZDICT_params_t required for finalizing the + * dictionary. + */ +static ZDICT_params_t COVER_translateParams(COVER_params_t parameters) { + ZDICT_params_t zdictParams; + memset(&zdictParams, 0, sizeof(zdictParams)); + zdictParams.notificationLevel = 1; + zdictParams.dictID = parameters.dictID; + zdictParams.compressionLevel = parameters.compressionLevel; + return zdictParams; +} + +/** + * Constructs a dictionary using a heuristic based on the following paper: + * + * Liao, Petri, Moffat, Wirth + * Effective Construction of Relative Lempel-Ziv Dictionaries + * Published in WWW 2016. + */ +ZDICTLIB_API size_t COVER_trainFromBuffer( + void *dictBuffer, size_t dictBufferCapacity, const void *samplesBuffer, + const size_t *samplesSizes, unsigned nbSamples, COVER_params_t parameters) { + BYTE *const dict = (BYTE *)dictBuffer; + COVER_ctx_t ctx; + COVER_map_t activeDmers; + /* Checks */ + if (!COVER_checkParameters(parameters)) { + DISPLAYLEVEL(1, "Cover parameters incorrect\n"); + return ERROR(GENERIC); + } + if (nbSamples == 0) { + DISPLAYLEVEL(1, "Cover must have at least one input file\n"); + return ERROR(GENERIC); + } + if (dictBufferCapacity < ZDICT_DICTSIZE_MIN) { + DISPLAYLEVEL(1, "dictBufferCapacity must be at least %u\n", + ZDICT_DICTSIZE_MIN); + return ERROR(dstSize_tooSmall); + } + /* Initialize global data */ + g_displayLevel = parameters.notificationLevel; + /* Initialize context and activeDmers */ + if (!COVER_ctx_init(&ctx, samplesBuffer, samplesSizes, nbSamples, + parameters.d)) { + return ERROR(GENERIC); + } + if (!COVER_map_init(&activeDmers, parameters.k - parameters.d + 1)) { + DISPLAYLEVEL(1, "Failed to allocate dmer map: out of memory\n"); + COVER_ctx_destroy(&ctx); + return ERROR(GENERIC); + } + + DISPLAYLEVEL(2, "Building dictionary\n"); + { + const size_t tail = + COVER_buildDictionary(&ctx, ctx.freqs, &activeDmers, dictBuffer, + dictBufferCapacity, parameters); + ZDICT_params_t zdictParams = COVER_translateParams(parameters); + const size_t dictionarySize = ZDICT_finalizeDictionary( + dict, dictBufferCapacity, dict + tail, dictBufferCapacity - tail, + samplesBuffer, samplesSizes, nbSamples, zdictParams); + if (!ZSTD_isError(dictionarySize)) { + DISPLAYLEVEL(2, "Constructed dictionary of size %u\n", + (U32)dictionarySize); + } + COVER_ctx_destroy(&ctx); + COVER_map_destroy(&activeDmers); + return dictionarySize; + } +} + +/** + * COVER_best_t is used for two purposes: + * 1. Synchronizing threads. + * 2. Saving the best parameters and dictionary. + * + * All of the methods except COVER_best_init() are thread safe if zstd is + * compiled with multithreaded support. + */ +typedef struct COVER_best_s { + pthread_mutex_t mutex; + pthread_cond_t cond; + size_t liveJobs; + void *dict; + size_t dictSize; + COVER_params_t parameters; + size_t compressedSize; +} COVER_best_t; + +/** + * Initialize the `COVER_best_t`. + */ +static void COVER_best_init(COVER_best_t *best) { + if (!best) { + return; + } + pthread_mutex_init(&best->mutex, NULL); + pthread_cond_init(&best->cond, NULL); + best->liveJobs = 0; + best->dict = NULL; + best->dictSize = 0; + best->compressedSize = (size_t)-1; + memset(&best->parameters, 0, sizeof(best->parameters)); +} + +/** + * Wait until liveJobs == 0. + */ +static void COVER_best_wait(COVER_best_t *best) { + if (!best) { + return; + } + pthread_mutex_lock(&best->mutex); + while (best->liveJobs != 0) { + pthread_cond_wait(&best->cond, &best->mutex); + } + pthread_mutex_unlock(&best->mutex); +} + +/** + * Call COVER_best_wait() and then destroy the COVER_best_t. + */ +static void COVER_best_destroy(COVER_best_t *best) { + if (!best) { + return; + } + COVER_best_wait(best); + if (best->dict) { + free(best->dict); + } + pthread_mutex_destroy(&best->mutex); + pthread_cond_destroy(&best->cond); +} + +/** + * Called when a thread is about to be launched. + * Increments liveJobs. + */ +static void COVER_best_start(COVER_best_t *best) { + if (!best) { + return; + } + pthread_mutex_lock(&best->mutex); + ++best->liveJobs; + pthread_mutex_unlock(&best->mutex); +} + +/** + * Called when a thread finishes executing, both on error or success. + * Decrements liveJobs and signals any waiting threads if liveJobs == 0. + * If this dictionary is the best so far save it and its parameters. + */ +static void COVER_best_finish(COVER_best_t *best, size_t compressedSize, + COVER_params_t parameters, void *dict, + size_t dictSize) { + if (!best) { + return; + } + { + size_t liveJobs; + pthread_mutex_lock(&best->mutex); + --best->liveJobs; + liveJobs = best->liveJobs; + /* If the new dictionary is better */ + if (compressedSize < best->compressedSize) { + /* Allocate space if necessary */ + if (!best->dict || best->dictSize < dictSize) { + if (best->dict) { + free(best->dict); + } + best->dict = malloc(dictSize); + if (!best->dict) { + best->compressedSize = ERROR(GENERIC); + best->dictSize = 0; + return; + } + } + /* Save the dictionary, parameters, and size */ + memcpy(best->dict, dict, dictSize); + best->dictSize = dictSize; + best->parameters = parameters; + best->compressedSize = compressedSize; + } + pthread_mutex_unlock(&best->mutex); + if (liveJobs == 0) { + pthread_cond_broadcast(&best->cond); + } + } +} + +/** + * Parameters for COVER_tryParameters(). + */ +typedef struct COVER_tryParameters_data_s { + const COVER_ctx_t *ctx; + COVER_best_t *best; + size_t dictBufferCapacity; + COVER_params_t parameters; +} COVER_tryParameters_data_t; + +/** + * Tries a set of parameters and upates the COVER_best_t with the results. + * This function is thread safe if zstd is compiled with multithreaded support. + * It takes its parameters as an *OWNING* opaque pointer to support threading. + */ +static void COVER_tryParameters(void *opaque) { + /* Save parameters as local variables */ + COVER_tryParameters_data_t *const data = (COVER_tryParameters_data_t *)opaque; + const COVER_ctx_t *const ctx = data->ctx; + const COVER_params_t parameters = data->parameters; + size_t dictBufferCapacity = data->dictBufferCapacity; + size_t totalCompressedSize = ERROR(GENERIC); + /* Allocate space for hash table, dict, and freqs */ + COVER_map_t activeDmers; + BYTE *const dict = (BYTE * const)malloc(dictBufferCapacity); + U32 *freqs = (U32 *)malloc(ctx->suffixSize * sizeof(U32)); + if (!COVER_map_init(&activeDmers, parameters.k - parameters.d + 1)) { + DISPLAYLEVEL(1, "Failed to allocate dmer map: out of memory\n"); + goto _cleanup; + } + if (!dict || !freqs) { + DISPLAYLEVEL(1, "Failed to allocate buffers: out of memory\n"); + goto _cleanup; + } + /* Copy the frequencies because we need to modify them */ + memcpy(freqs, ctx->freqs, ctx->suffixSize * sizeof(U32)); + /* Build the dictionary */ + { + const size_t tail = COVER_buildDictionary(ctx, freqs, &activeDmers, dict, + dictBufferCapacity, parameters); + const ZDICT_params_t zdictParams = COVER_translateParams(parameters); + dictBufferCapacity = ZDICT_finalizeDictionary( + dict, dictBufferCapacity, dict + tail, dictBufferCapacity - tail, + ctx->samples, ctx->samplesSizes, (unsigned)ctx->nbSamples, zdictParams); + if (ZDICT_isError(dictBufferCapacity)) { + DISPLAYLEVEL(1, "Failed to finalize dictionary\n"); + goto _cleanup; + } + } + /* Check total compressed size */ + { + /* Pointers */ + ZSTD_CCtx *cctx; + ZSTD_CDict *cdict; + void *dst; + /* Local variables */ + size_t dstCapacity; + size_t i; + /* Allocate dst with enough space to compress the maximum sized sample */ + { + size_t maxSampleSize = 0; + for (i = 0; i < ctx->nbSamples; ++i) { + maxSampleSize = MAX(ctx->samplesSizes[i], maxSampleSize); + } + dstCapacity = ZSTD_compressBound(maxSampleSize); + dst = malloc(dstCapacity); + } + /* Create the cctx and cdict */ + cctx = ZSTD_createCCtx(); + cdict = + ZSTD_createCDict(dict, dictBufferCapacity, parameters.compressionLevel); + if (!dst || !cctx || !cdict) { + goto _compressCleanup; + } + /* Compress each sample and sum their sizes (or error) */ + totalCompressedSize = 0; + for (i = 0; i < ctx->nbSamples; ++i) { + const size_t size = ZSTD_compress_usingCDict( + cctx, dst, dstCapacity, ctx->samples + ctx->offsets[i], + ctx->samplesSizes[i], cdict); + if (ZSTD_isError(size)) { + totalCompressedSize = ERROR(GENERIC); + goto _compressCleanup; + } + totalCompressedSize += size; + } + _compressCleanup: + ZSTD_freeCCtx(cctx); + ZSTD_freeCDict(cdict); + if (dst) { + free(dst); + } + } + +_cleanup: + COVER_best_finish(data->best, totalCompressedSize, parameters, dict, + dictBufferCapacity); + free(data); + COVER_map_destroy(&activeDmers); + if (dict) { + free(dict); + } + if (freqs) { + free(freqs); + } +} + +ZDICTLIB_API size_t COVER_optimizeTrainFromBuffer(void *dictBuffer, + size_t dictBufferCapacity, + const void *samplesBuffer, + const size_t *samplesSizes, + unsigned nbSamples, + COVER_params_t *parameters) { + /* constants */ + const unsigned nbThreads = parameters->nbThreads; + const unsigned kMinD = parameters->d == 0 ? 6 : parameters->d; + const unsigned kMaxD = parameters->d == 0 ? 16 : parameters->d; + const unsigned kMinK = parameters->k == 0 ? kMaxD : parameters->k; + const unsigned kMaxK = parameters->k == 0 ? 2048 : parameters->k; + const unsigned kSteps = parameters->steps == 0 ? 32 : parameters->steps; + const unsigned kStepSize = MAX((kMaxK - kMinK) / kSteps, 1); + const unsigned kIterations = + (1 + (kMaxD - kMinD) / 2) * (1 + (kMaxK - kMinK) / kStepSize); + /* Local variables */ + const int displayLevel = parameters->notificationLevel; + unsigned iteration = 1; + unsigned d; + unsigned k; + COVER_best_t best; + POOL_ctx *pool = NULL; + /* Checks */ + if (kMinK < kMaxD || kMaxK < kMinK) { + LOCALDISPLAYLEVEL(displayLevel, 1, "Incorrect parameters\n"); + return ERROR(GENERIC); + } + if (nbSamples == 0) { + DISPLAYLEVEL(1, "Cover must have at least one input file\n"); + return ERROR(GENERIC); + } + if (dictBufferCapacity < ZDICT_DICTSIZE_MIN) { + DISPLAYLEVEL(1, "dictBufferCapacity must be at least %u\n", + ZDICT_DICTSIZE_MIN); + return ERROR(dstSize_tooSmall); + } + if (nbThreads > 1) { + pool = POOL_create(nbThreads, 1); + if (!pool) { + return ERROR(memory_allocation); + } + } + /* Initialization */ + COVER_best_init(&best); + /* Turn down global display level to clean up display at level 2 and below */ + g_displayLevel = parameters->notificationLevel - 1; + /* Loop through d first because each new value needs a new context */ + LOCALDISPLAYLEVEL(displayLevel, 2, "Trying %u different sets of parameters\n", + kIterations); + for (d = kMinD; d <= kMaxD; d += 2) { + /* Initialize the context for this value of d */ + COVER_ctx_t ctx; + LOCALDISPLAYLEVEL(displayLevel, 3, "d=%u\n", d); + if (!COVER_ctx_init(&ctx, samplesBuffer, samplesSizes, nbSamples, d)) { + LOCALDISPLAYLEVEL(displayLevel, 1, "Failed to initialize context\n"); + COVER_best_destroy(&best); + return ERROR(GENERIC); + } + /* Loop through k reusing the same context */ + for (k = kMinK; k <= kMaxK; k += kStepSize) { + /* Prepare the arguments */ + COVER_tryParameters_data_t *data = (COVER_tryParameters_data_t *)malloc( + sizeof(COVER_tryParameters_data_t)); + LOCALDISPLAYLEVEL(displayLevel, 3, "k=%u\n", k); + if (!data) { + LOCALDISPLAYLEVEL(displayLevel, 1, "Failed to allocate parameters\n"); + COVER_best_destroy(&best); + COVER_ctx_destroy(&ctx); + return ERROR(GENERIC); + } + data->ctx = &ctx; + data->best = &best; + data->dictBufferCapacity = dictBufferCapacity; + data->parameters = *parameters; + data->parameters.k = k; + data->parameters.d = d; + data->parameters.steps = kSteps; + /* Check the parameters */ + if (!COVER_checkParameters(data->parameters)) { + DISPLAYLEVEL(1, "Cover parameters incorrect\n"); + continue; + } + /* Call the function and pass ownership of data to it */ + COVER_best_start(&best); + if (pool) { + POOL_add(pool, &COVER_tryParameters, data); + } else { + COVER_tryParameters(data); + } + /* Print status */ + LOCALDISPLAYUPDATE(displayLevel, 2, "\r%u%% ", + (U32)((iteration * 100) / kIterations)); + ++iteration; + } + COVER_best_wait(&best); + COVER_ctx_destroy(&ctx); + } + LOCALDISPLAYLEVEL(displayLevel, 2, "\r%79s\r", ""); + /* Fill the output buffer and parameters with output of the best parameters */ + { + const size_t dictSize = best.dictSize; + if (ZSTD_isError(best.compressedSize)) { + COVER_best_destroy(&best); + return best.compressedSize; + } + *parameters = best.parameters; + memcpy(dictBuffer, best.dict, dictSize); + COVER_best_destroy(&best); + POOL_free(pool); + return dictSize; + } +}
--- a/contrib/python-zstandard/zstd/dictBuilder/zdict.c Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/python-zstandard/zstd/dictBuilder/zdict.c Tue Apr 18 12:24:34 2017 -0400 @@ -36,12 +36,11 @@ #include <time.h> /* clock */ #include "mem.h" /* read */ -#include "error_private.h" #include "fse.h" /* FSE_normalizeCount, FSE_writeNCount */ #define HUF_STATIC_LINKING_ONLY -#include "huf.h" +#include "huf.h" /* HUF_buildCTable, HUF_writeCTable */ #include "zstd_internal.h" /* includes zstd.h */ -#include "xxhash.h" +#include "xxhash.h" /* XXH64 */ #include "divsufsort.h" #ifndef ZDICT_STATIC_LINKING_ONLY # define ZDICT_STATIC_LINKING_ONLY @@ -61,7 +60,7 @@ #define NOISELENGTH 32 #define MINRATIO 4 -static const int g_compressionLevel_default = 5; +static const int g_compressionLevel_default = 6; static const U32 g_selectivity_default = 9; static const size_t g_provision_entropySize = 200; static const size_t g_min_fast_dictContent = 192; @@ -307,13 +306,13 @@ } while (length >=MINMATCHLENGTH); /* look backward */ - length = MINMATCHLENGTH; - while ((length >= MINMATCHLENGTH) & (start > 0)) { - length = ZDICT_count(b + pos, b + suffix[start - 1]); - if (length >= LLIMIT) length = LLIMIT - 1; - lengthList[length]++; - if (length >= MINMATCHLENGTH) start--; - } + length = MINMATCHLENGTH; + while ((length >= MINMATCHLENGTH) & (start > 0)) { + length = ZDICT_count(b + pos, b + suffix[start - 1]); + if (length >= LLIMIT) length = LLIMIT - 1; + lengthList[length]++; + if (length >= MINMATCHLENGTH) start--; + } /* largest useful length */ memset(cumulLength, 0, sizeof(cumulLength)); @@ -570,7 +569,7 @@ if (ZSTD_isError(errorCode)) { DISPLAYLEVEL(1, "warning : ZSTD_copyCCtx failed \n"); return; } } cSize = ZSTD_compressBlock(esr.zc, esr.workPlace, ZSTD_BLOCKSIZE_ABSOLUTEMAX, src, srcSize); - if (ZSTD_isError(cSize)) { DISPLAYLEVEL(1, "warning : could not compress sample size %u \n", (U32)srcSize); return; } + if (ZSTD_isError(cSize)) { DISPLAYLEVEL(3, "warning : could not compress sample size %u \n", (U32)srcSize); return; } if (cSize) { /* if == 0; block is not compressible */ const seqStore_t* seqStorePtr = ZSTD_getSeqStore(esr.zc); @@ -825,6 +824,55 @@ } + +size_t ZDICT_finalizeDictionary(void* dictBuffer, size_t dictBufferCapacity, + const void* customDictContent, size_t dictContentSize, + const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples, + ZDICT_params_t params) +{ + size_t hSize; +#define HBUFFSIZE 256 + BYTE header[HBUFFSIZE]; + int const compressionLevel = (params.compressionLevel <= 0) ? g_compressionLevel_default : params.compressionLevel; + U32 const notificationLevel = params.notificationLevel; + + /* check conditions */ + if (dictBufferCapacity < dictContentSize) return ERROR(dstSize_tooSmall); + if (dictContentSize < ZDICT_CONTENTSIZE_MIN) return ERROR(srcSize_wrong); + if (dictBufferCapacity < ZDICT_DICTSIZE_MIN) return ERROR(dstSize_tooSmall); + + /* dictionary header */ + MEM_writeLE32(header, ZSTD_DICT_MAGIC); + { U64 const randomID = XXH64(customDictContent, dictContentSize, 0); + U32 const compliantID = (randomID % ((1U<<31)-32768)) + 32768; + U32 const dictID = params.dictID ? params.dictID : compliantID; + MEM_writeLE32(header+4, dictID); + } + hSize = 8; + + /* entropy tables */ + DISPLAYLEVEL(2, "\r%70s\r", ""); /* clean display line */ + DISPLAYLEVEL(2, "statistics ... \n"); + { size_t const eSize = ZDICT_analyzeEntropy(header+hSize, HBUFFSIZE-hSize, + compressionLevel, + samplesBuffer, samplesSizes, nbSamples, + customDictContent, dictContentSize, + notificationLevel); + if (ZDICT_isError(eSize)) return eSize; + hSize += eSize; + } + + /* copy elements in final buffer ; note : src and dst buffer can overlap */ + if (hSize + dictContentSize > dictBufferCapacity) dictContentSize = dictBufferCapacity - hSize; + { size_t const dictSize = hSize + dictContentSize; + char* dictEnd = (char*)dictBuffer + dictSize; + memmove(dictEnd - dictContentSize, customDictContent, dictContentSize); + memcpy(dictBuffer, header, hSize); + return dictSize; + } +} + + size_t ZDICT_addEntropyTablesFromBuffer_advanced(void* dictBuffer, size_t dictContentSize, size_t dictBufferCapacity, const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples, ZDICT_params_t params)
--- a/contrib/python-zstandard/zstd/dictBuilder/zdict.h Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/python-zstandard/zstd/dictBuilder/zdict.h Tue Apr 18 12:24:34 2017 -0400 @@ -19,15 +19,18 @@ #include <stddef.h> /* size_t */ -/*====== Export for Windows ======*/ -/*! -* ZSTD_DLL_EXPORT : -* Enable exporting of functions when building a Windows DLL -*/ -#if defined(_WIN32) && defined(ZSTD_DLL_EXPORT) && (ZSTD_DLL_EXPORT==1) -# define ZDICTLIB_API __declspec(dllexport) +/* ===== ZDICTLIB_API : control library symbols visibility ===== */ +#if defined(__GNUC__) && (__GNUC__ >= 4) +# define ZDICTLIB_VISIBILITY __attribute__ ((visibility ("default"))) #else -# define ZDICTLIB_API +# define ZDICTLIB_VISIBILITY +#endif +#if defined(ZSTD_DLL_EXPORT) && (ZSTD_DLL_EXPORT==1) +# define ZDICTLIB_API __declspec(dllexport) ZDICTLIB_VISIBILITY +#elif defined(ZSTD_DLL_IMPORT) && (ZSTD_DLL_IMPORT==1) +# define ZDICTLIB_API __declspec(dllimport) ZDICTLIB_VISIBILITY /* It isn't required but allows to generate better code, saving a function pointer load from the IAT and an indirect jump.*/ +#else +# define ZDICTLIB_API ZDICTLIB_VISIBILITY #endif @@ -79,27 +82,114 @@ or an error code, which can be tested by ZDICT_isError(). note : ZDICT_trainFromBuffer_advanced() will send notifications into stderr if instructed to, using notificationLevel>0. */ -size_t ZDICT_trainFromBuffer_advanced(void* dictBuffer, size_t dictBufferCapacity, +ZDICTLIB_API size_t ZDICT_trainFromBuffer_advanced(void* dictBuffer, size_t dictBufferCapacity, + const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples, + ZDICT_params_t parameters); + +/*! COVER_params_t : + For all values 0 means default. + kMin and d are the only required parameters. +*/ +typedef struct { + unsigned k; /* Segment size : constraint: 0 < k : Reasonable range [16, 2048+] */ + unsigned d; /* dmer size : constraint: 0 < d <= k : Reasonable range [6, 16] */ + unsigned steps; /* Number of steps : Only used for optimization : 0 means default (32) : Higher means more parameters checked */ + + unsigned nbThreads; /* Number of threads : constraint: 0 < nbThreads : 1 means single-threaded : Only used for optimization : Ignored if ZSTD_MULTITHREAD is not defined */ + unsigned notificationLevel; /* Write to stderr; 0 = none (default); 1 = errors; 2 = progression; 3 = details; 4 = debug; */ + unsigned dictID; /* 0 means auto mode (32-bits random value); other : force dictID value */ + int compressionLevel; /* 0 means default; target a specific zstd compression level */ +} COVER_params_t; + + +/*! COVER_trainFromBuffer() : + Train a dictionary from an array of samples using the COVER algorithm. + Samples must be stored concatenated in a single flat buffer `samplesBuffer`, + supplied with an array of sizes `samplesSizes`, providing the size of each sample, in order. + The resulting dictionary will be saved into `dictBuffer`. + @return : size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`) + or an error code, which can be tested with ZDICT_isError(). + Note : COVER_trainFromBuffer() requires about 9 bytes of memory for each input byte. + Tips : In general, a reasonable dictionary has a size of ~ 100 KB. + It's obviously possible to target smaller or larger ones, just by specifying different `dictBufferCapacity`. + In general, it's recommended to provide a few thousands samples, but this can vary a lot. + It's recommended that total size of all samples be about ~x100 times the target size of dictionary. +*/ +ZDICTLIB_API size_t COVER_trainFromBuffer(void* dictBuffer, size_t dictBufferCapacity, + const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples, + COVER_params_t parameters); + +/*! COVER_optimizeTrainFromBuffer() : + The same requirements as above hold for all the parameters except `parameters`. + This function tries many parameter combinations and picks the best parameters. + `*parameters` is filled with the best parameters found, and the dictionary + constructed with those parameters is stored in `dictBuffer`. + + All of the parameters d, k, steps are optional. + If d is non-zero then we don't check multiple values of d, otherwise we check d = {6, 8, 10, 12, 14, 16}. + if steps is zero it defaults to its default value. + If k is non-zero then we don't check multiple values of k, otherwise we check steps values in [16, 2048]. + + @return : size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`) + or an error code, which can be tested with ZDICT_isError(). + On success `*parameters` contains the parameters selected. + Note : COVER_optimizeTrainFromBuffer() requires about 8 bytes of memory for each input byte and additionally another 5 bytes of memory for each byte of memory for each thread. +*/ +ZDICTLIB_API size_t COVER_optimizeTrainFromBuffer(void* dictBuffer, size_t dictBufferCapacity, + const void* samplesBuffer, const size_t *samplesSizes, unsigned nbSamples, + COVER_params_t *parameters); + +/*! ZDICT_finalizeDictionary() : + + Given a custom content as a basis for dictionary, and a set of samples, + finalize dictionary by adding headers and statistics. + + Samples must be stored concatenated in a flat buffer `samplesBuffer`, + supplied with an array of sizes `samplesSizes`, providing the size of each sample in order. + + dictContentSize must be > ZDICT_CONTENTSIZE_MIN bytes. + maxDictSize must be >= dictContentSize, and must be > ZDICT_DICTSIZE_MIN bytes. + + @return : size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`), + or an error code, which can be tested by ZDICT_isError(). + note : ZDICT_finalizeDictionary() will push notifications into stderr if instructed to, using notificationLevel>0. + note 2 : dictBuffer and customDictContent can overlap +*/ +#define ZDICT_CONTENTSIZE_MIN 256 +#define ZDICT_DICTSIZE_MIN 512 +ZDICTLIB_API size_t ZDICT_finalizeDictionary(void* dictBuffer, size_t dictBufferCapacity, + const void* customDictContent, size_t dictContentSize, const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples, ZDICT_params_t parameters); -/*! ZDICT_addEntropyTablesFromBuffer() : - - Given a content-only dictionary (built using any 3rd party algorithm), - add entropy tables computed from an array of samples. - Samples must be stored concatenated in a flat buffer `samplesBuffer`, - supplied with an array of sizes `samplesSizes`, providing the size of each sample in order. - The input dictionary content must be stored *at the end* of `dictBuffer`. - Its size is `dictContentSize`. - The resulting dictionary with added entropy tables will be *written back to `dictBuffer`*, - starting from its beginning. - @return : size of dictionary stored into `dictBuffer` (<= `dictBufferCapacity`). -*/ +/* Deprecation warnings */ +/* It is generally possible to disable deprecation warnings from compiler, + for example with -Wno-deprecated-declarations for gcc + or _CRT_SECURE_NO_WARNINGS in Visual. + Otherwise, it's also possible to manually define ZDICT_DISABLE_DEPRECATE_WARNINGS */ +#ifdef ZDICT_DISABLE_DEPRECATE_WARNINGS +# define ZDICT_DEPRECATED(message) ZDICTLIB_API /* disable deprecation warnings */ +#else +# define ZDICT_GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__) +# if defined (__cplusplus) && (__cplusplus >= 201402) /* C++14 or greater */ +# define ZDICT_DEPRECATED(message) ZDICTLIB_API [[deprecated(message)]] +# elif (ZDICT_GCC_VERSION >= 405) || defined(__clang__) +# define ZDICT_DEPRECATED(message) ZDICTLIB_API __attribute__((deprecated(message))) +# elif (ZDICT_GCC_VERSION >= 301) +# define ZDICT_DEPRECATED(message) ZDICTLIB_API __attribute__((deprecated)) +# elif defined(_MSC_VER) +# define ZDICT_DEPRECATED(message) ZDICTLIB_API __declspec(deprecated(message)) +# else +# pragma message("WARNING: You need to implement ZDICT_DEPRECATED for this compiler") +# define ZDICT_DEPRECATED(message) ZDICTLIB_API +# endif +#endif /* ZDICT_DISABLE_DEPRECATE_WARNINGS */ + +ZDICT_DEPRECATED("use ZDICT_finalizeDictionary() instead") size_t ZDICT_addEntropyTablesFromBuffer(void* dictBuffer, size_t dictContentSize, size_t dictBufferCapacity, - const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples); - + const void* samplesBuffer, const size_t* samplesSizes, unsigned nbSamples); #endif /* ZDICT_STATIC_LINKING_ONLY */
--- a/contrib/python-zstandard/zstd/zstd.h Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/python-zstandard/zstd/zstd.h Tue Apr 18 12:24:34 2017 -0400 @@ -20,13 +20,16 @@ /* ===== ZSTDLIB_API : control library symbols visibility ===== */ #if defined(__GNUC__) && (__GNUC__ >= 4) -# define ZSTDLIB_API __attribute__ ((visibility ("default"))) -#elif defined(ZSTD_DLL_EXPORT) && (ZSTD_DLL_EXPORT==1) -# define ZSTDLIB_API __declspec(dllexport) +# define ZSTDLIB_VISIBILITY __attribute__ ((visibility ("default"))) +#else +# define ZSTDLIB_VISIBILITY +#endif +#if defined(ZSTD_DLL_EXPORT) && (ZSTD_DLL_EXPORT==1) +# define ZSTDLIB_API __declspec(dllexport) ZSTDLIB_VISIBILITY #elif defined(ZSTD_DLL_IMPORT) && (ZSTD_DLL_IMPORT==1) -# define ZSTDLIB_API __declspec(dllimport) /* It isn't required but allows to generate better code, saving a function pointer load from the IAT and an indirect jump.*/ +# define ZSTDLIB_API __declspec(dllimport) ZSTDLIB_VISIBILITY /* It isn't required but allows to generate better code, saving a function pointer load from the IAT and an indirect jump.*/ #else -# define ZSTDLIB_API +# define ZSTDLIB_API ZSTDLIB_VISIBILITY #endif @@ -53,7 +56,7 @@ /*------ Version ------*/ #define ZSTD_VERSION_MAJOR 1 #define ZSTD_VERSION_MINOR 1 -#define ZSTD_VERSION_RELEASE 2 +#define ZSTD_VERSION_RELEASE 3 #define ZSTD_LIB_VERSION ZSTD_VERSION_MAJOR.ZSTD_VERSION_MINOR.ZSTD_VERSION_RELEASE #define ZSTD_QUOTE(str) #str @@ -170,8 +173,8 @@ * When compressing multiple messages / blocks with the same dictionary, it's recommended to load it just once. * ZSTD_createCDict() will create a digested dictionary, ready to start future compression operations without startup delay. * ZSTD_CDict can be created once and used by multiple threads concurrently, as its usage is read-only. -* `dict` can be released after ZSTD_CDict creation. */ -ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict(const void* dict, size_t dictSize, int compressionLevel); +* `dictBuffer` can be released after ZSTD_CDict creation, as its content is copied within CDict */ +ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict(const void* dictBuffer, size_t dictSize, int compressionLevel); /*! ZSTD_freeCDict() : * Function frees memory allocated by ZSTD_createCDict(). */ @@ -191,8 +194,8 @@ /*! ZSTD_createDDict() : * Create a digested dictionary, ready to start decompression operation without startup delay. -* `dict` can be released after creation. */ -ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict(const void* dict, size_t dictSize); +* dictBuffer can be released after DDict creation, as its content is copied inside DDict */ +ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict(const void* dictBuffer, size_t dictSize); /*! ZSTD_freeDDict() : * Function frees memory allocated with ZSTD_createDDict() */ @@ -325,7 +328,7 @@ * ***************************************************************************************/ /* --- Constants ---*/ -#define ZSTD_MAGICNUMBER 0xFD2FB528 /* v0.8 */ +#define ZSTD_MAGICNUMBER 0xFD2FB528 /* >= v0.8.0 */ #define ZSTD_MAGIC_SKIPPABLE_START 0x184D2A50U #define ZSTD_WINDOWLOG_MAX_32 25 @@ -345,8 +348,9 @@ #define ZSTD_TARGETLENGTH_MAX 999 #define ZSTD_FRAMEHEADERSIZE_MAX 18 /* for static allocation */ +#define ZSTD_FRAMEHEADERSIZE_MIN 6 static const size_t ZSTD_frameHeaderSize_prefix = 5; -static const size_t ZSTD_frameHeaderSize_min = 6; +static const size_t ZSTD_frameHeaderSize_min = ZSTD_FRAMEHEADERSIZE_MIN; static const size_t ZSTD_frameHeaderSize_max = ZSTD_FRAMEHEADERSIZE_MAX; static const size_t ZSTD_skippableHeaderSize = 8; /* magic number + skippable frame length */ @@ -365,9 +369,9 @@ } ZSTD_compressionParameters; typedef struct { - unsigned contentSizeFlag; /**< 1: content size will be in frame header (if known). */ - unsigned checksumFlag; /**< 1: will generate a 22-bits checksum at end of frame, to be used for error detection by decompressor */ - unsigned noDictIDFlag; /**< 1: no dict ID will be saved into frame header (if dictionary compression) */ + unsigned contentSizeFlag; /**< 1: content size will be in frame header (when known) */ + unsigned checksumFlag; /**< 1: generate a 32-bits checksum at end of frame, for error detection */ + unsigned noDictIDFlag; /**< 1: no dictID will be saved into frame header (if dictionary compression) */ } ZSTD_frameParameters; typedef struct { @@ -397,9 +401,23 @@ * Gives the amount of memory used by a given ZSTD_CCtx */ ZSTDLIB_API size_t ZSTD_sizeof_CCtx(const ZSTD_CCtx* cctx); +typedef enum { + ZSTD_p_forceWindow /* Force back-references to remain < windowSize, even when referencing Dictionary content (default:0)*/ +} ZSTD_CCtxParameter; +/*! ZSTD_setCCtxParameter() : + * Set advanced parameters, selected through enum ZSTD_CCtxParameter + * @result : 0, or an error code (which can be tested with ZSTD_isError()) */ +ZSTDLIB_API size_t ZSTD_setCCtxParameter(ZSTD_CCtx* cctx, ZSTD_CCtxParameter param, unsigned value); + +/*! ZSTD_createCDict_byReference() : + * Create a digested dictionary for compression + * Dictionary content is simply referenced, and therefore stays in dictBuffer. + * It is important that dictBuffer outlives CDict, it must remain read accessible throughout the lifetime of CDict */ +ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict_byReference(const void* dictBuffer, size_t dictSize, int compressionLevel); + /*! ZSTD_createCDict_advanced() : * Create a ZSTD_CDict using external alloc and free, and customized compression parameters */ -ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict_advanced(const void* dict, size_t dictSize, +ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict_advanced(const void* dict, size_t dictSize, unsigned byReference, ZSTD_parameters params, ZSTD_customMem customMem); /*! ZSTD_sizeof_CDict() : @@ -455,6 +473,15 @@ * Gives the amount of memory used by a given ZSTD_DCtx */ ZSTDLIB_API size_t ZSTD_sizeof_DCtx(const ZSTD_DCtx* dctx); +/*! ZSTD_createDDict_byReference() : + * Create a digested dictionary, ready to start decompression operation without startup delay. + * Dictionary content is simply referenced, and therefore stays in dictBuffer. + * It is important that dictBuffer outlives DDict, it must remain read accessible throughout the lifetime of DDict */ +ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict_byReference(const void* dictBuffer, size_t dictSize); + +ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict_advanced(const void* dict, size_t dictSize, + unsigned byReference, ZSTD_customMem customMem); + /*! ZSTD_sizeof_DDict() : * Gives the amount of memory used by a given ZSTD_DDict */ ZSTDLIB_API size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict); @@ -463,13 +490,13 @@ * Provides the dictID stored within dictionary. * if @return == 0, the dictionary is not conformant with Zstandard specification. * It can still be loaded, but as a content-only dictionary. */ -unsigned ZSTD_getDictID_fromDict(const void* dict, size_t dictSize); +ZSTDLIB_API unsigned ZSTD_getDictID_fromDict(const void* dict, size_t dictSize); /*! ZSTD_getDictID_fromDDict() : * Provides the dictID of the dictionary loaded into `ddict`. * If @return == 0, the dictionary is not conformant to Zstandard specification, or empty. * Non-conformant dictionaries can still be loaded, but as content-only dictionaries. */ -unsigned ZSTD_getDictID_fromDDict(const ZSTD_DDict* ddict); +ZSTDLIB_API unsigned ZSTD_getDictID_fromDDict(const ZSTD_DDict* ddict); /*! ZSTD_getDictID_fromFrame() : * Provides the dictID required to decompressed the frame stored within `src`. @@ -481,7 +508,7 @@ * - `srcSize` is too small, and as a result, the frame header could not be decoded (only possible if `srcSize < ZSTD_FRAMEHEADERSIZE_MAX`). * - This is not a Zstandard frame. * When identifying the exact failure cause, it's possible to used ZSTD_getFrameParams(), which will provide a more precise error code. */ -unsigned ZSTD_getDictID_fromFrame(const void* src, size_t srcSize); +ZSTDLIB_API unsigned ZSTD_getDictID_fromFrame(const void* src, size_t srcSize); /******************************************************************** @@ -491,7 +518,7 @@ /*===== Advanced Streaming compression functions =====*/ ZSTDLIB_API ZSTD_CStream* ZSTD_createCStream_advanced(ZSTD_customMem customMem); ZSTDLIB_API size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigned long long pledgedSrcSize); /**< pledgedSrcSize must be correct */ -ZSTDLIB_API size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t dictSize, int compressionLevel); +ZSTDLIB_API size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t dictSize, int compressionLevel); /**< note: a dict will not be used if dict == NULL or dictSize < 8 */ ZSTDLIB_API size_t ZSTD_initCStream_advanced(ZSTD_CStream* zcs, const void* dict, size_t dictSize, ZSTD_parameters params, unsigned long long pledgedSrcSize); /**< pledgedSrcSize is optional and can be zero == unknown */ ZSTDLIB_API size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict); /**< note : cdict will just be referenced, and must outlive compression session */ @@ -500,9 +527,9 @@ /*===== Advanced Streaming decompression functions =====*/ -typedef enum { ZSTDdsp_maxWindowSize } ZSTD_DStreamParameter_e; +typedef enum { DStream_p_maxWindowSize } ZSTD_DStreamParameter_e; ZSTDLIB_API ZSTD_DStream* ZSTD_createDStream_advanced(ZSTD_customMem customMem); -ZSTDLIB_API size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t dictSize); +ZSTDLIB_API size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t dictSize); /**< note: a dict will not be used if dict == NULL or dictSize < 8 */ ZSTDLIB_API size_t ZSTD_setDStreamParameter(ZSTD_DStream* zds, ZSTD_DStreamParameter_e paramType, unsigned paramValue); ZSTDLIB_API size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* zds, const ZSTD_DDict* ddict); /**< note : ddict will just be referenced, and must outlive decompression session */ ZSTDLIB_API size_t ZSTD_resetDStream(ZSTD_DStream* zds); /**< re-use decompression parameters from previous init; saves dictionary loading */ @@ -542,10 +569,10 @@ In which case, it will "discard" the relevant memory section from its history. Finish a frame with ZSTD_compressEnd(), which will write the last block(s) and optional checksum. - It's possible to use a NULL,0 src content, in which case, it will write a final empty block to end the frame, - Without last block mark, frames will be considered unfinished (broken) by decoders. + It's possible to use srcSize==0, in which case, it will write a final empty block to end the frame. + Without last block mark, frames will be considered unfinished (corrupted) by decoders. - You can then reuse `ZSTD_CCtx` (ZSTD_compressBegin()) to compress some new frame. + `ZSTD_CCtx` object can be re-used (ZSTD_compressBegin()) to compress some new frame. */ /*===== Buffer-less streaming compression functions =====*/ @@ -553,6 +580,7 @@ ZSTDLIB_API size_t ZSTD_compressBegin_usingDict(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, int compressionLevel); ZSTDLIB_API size_t ZSTD_compressBegin_advanced(ZSTD_CCtx* cctx, const void* dict, size_t dictSize, ZSTD_parameters params, unsigned long long pledgedSrcSize); ZSTDLIB_API size_t ZSTD_copyCCtx(ZSTD_CCtx* cctx, const ZSTD_CCtx* preparedCCtx, unsigned long long pledgedSrcSize); +ZSTDLIB_API size_t ZSTD_compressBegin_usingCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict, unsigned long long pledgedSrcSize); ZSTDLIB_API size_t ZSTD_compressContinue(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize); ZSTDLIB_API size_t ZSTD_compressEnd(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize);
--- a/contrib/python-zstandard/zstd_cffi.py Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/python-zstandard/zstd_cffi.py Tue Apr 18 12:24:34 2017 -0400 @@ -8,145 +8,1250 @@ from __future__ import absolute_import, unicode_literals -import io +import os +import sys from _zstd_cffi import ( ffi, lib, ) +if sys.version_info[0] == 2: + bytes_type = str + int_type = long +else: + bytes_type = bytes + int_type = int -_CSTREAM_IN_SIZE = lib.ZSTD_CStreamInSize() -_CSTREAM_OUT_SIZE = lib.ZSTD_CStreamOutSize() + +COMPRESSION_RECOMMENDED_INPUT_SIZE = lib.ZSTD_CStreamInSize() +COMPRESSION_RECOMMENDED_OUTPUT_SIZE = lib.ZSTD_CStreamOutSize() +DECOMPRESSION_RECOMMENDED_INPUT_SIZE = lib.ZSTD_DStreamInSize() +DECOMPRESSION_RECOMMENDED_OUTPUT_SIZE = lib.ZSTD_DStreamOutSize() + +new_nonzero = ffi.new_allocator(should_clear_after_alloc=False) + + +MAX_COMPRESSION_LEVEL = lib.ZSTD_maxCLevel() +MAGIC_NUMBER = lib.ZSTD_MAGICNUMBER +FRAME_HEADER = b'\x28\xb5\x2f\xfd' +ZSTD_VERSION = (lib.ZSTD_VERSION_MAJOR, lib.ZSTD_VERSION_MINOR, lib.ZSTD_VERSION_RELEASE) + +WINDOWLOG_MIN = lib.ZSTD_WINDOWLOG_MIN +WINDOWLOG_MAX = lib.ZSTD_WINDOWLOG_MAX +CHAINLOG_MIN = lib.ZSTD_CHAINLOG_MIN +CHAINLOG_MAX = lib.ZSTD_CHAINLOG_MAX +HASHLOG_MIN = lib.ZSTD_HASHLOG_MIN +HASHLOG_MAX = lib.ZSTD_HASHLOG_MAX +HASHLOG3_MAX = lib.ZSTD_HASHLOG3_MAX +SEARCHLOG_MIN = lib.ZSTD_SEARCHLOG_MIN +SEARCHLOG_MAX = lib.ZSTD_SEARCHLOG_MAX +SEARCHLENGTH_MIN = lib.ZSTD_SEARCHLENGTH_MIN +SEARCHLENGTH_MAX = lib.ZSTD_SEARCHLENGTH_MAX +TARGETLENGTH_MIN = lib.ZSTD_TARGETLENGTH_MIN +TARGETLENGTH_MAX = lib.ZSTD_TARGETLENGTH_MAX + +STRATEGY_FAST = lib.ZSTD_fast +STRATEGY_DFAST = lib.ZSTD_dfast +STRATEGY_GREEDY = lib.ZSTD_greedy +STRATEGY_LAZY = lib.ZSTD_lazy +STRATEGY_LAZY2 = lib.ZSTD_lazy2 +STRATEGY_BTLAZY2 = lib.ZSTD_btlazy2 +STRATEGY_BTOPT = lib.ZSTD_btopt + +COMPRESSOBJ_FLUSH_FINISH = 0 +COMPRESSOBJ_FLUSH_BLOCK = 1 + + +def _cpu_count(): + # os.cpu_count() was introducd in Python 3.4. + try: + return os.cpu_count() or 0 + except AttributeError: + pass + + # Linux. + try: + if sys.version_info[0] == 2: + return os.sysconf(b'SC_NPROCESSORS_ONLN') + else: + return os.sysconf(u'SC_NPROCESSORS_ONLN') + except (AttributeError, ValueError): + pass + + # TODO implement on other platforms. + return 0 + + +class ZstdError(Exception): + pass -class _ZstdCompressionWriter(object): - def __init__(self, cstream, writer): - self._cstream = cstream +class CompressionParameters(object): + def __init__(self, window_log, chain_log, hash_log, search_log, + search_length, target_length, strategy): + if window_log < WINDOWLOG_MIN or window_log > WINDOWLOG_MAX: + raise ValueError('invalid window log value') + + if chain_log < CHAINLOG_MIN or chain_log > CHAINLOG_MAX: + raise ValueError('invalid chain log value') + + if hash_log < HASHLOG_MIN or hash_log > HASHLOG_MAX: + raise ValueError('invalid hash log value') + + if search_log < SEARCHLOG_MIN or search_log > SEARCHLOG_MAX: + raise ValueError('invalid search log value') + + if search_length < SEARCHLENGTH_MIN or search_length > SEARCHLENGTH_MAX: + raise ValueError('invalid search length value') + + if target_length < TARGETLENGTH_MIN or target_length > TARGETLENGTH_MAX: + raise ValueError('invalid target length value') + + if strategy < STRATEGY_FAST or strategy > STRATEGY_BTOPT: + raise ValueError('invalid strategy value') + + self.window_log = window_log + self.chain_log = chain_log + self.hash_log = hash_log + self.search_log = search_log + self.search_length = search_length + self.target_length = target_length + self.strategy = strategy + + zresult = lib.ZSTD_checkCParams(self.as_compression_parameters()) + if lib.ZSTD_isError(zresult): + raise ValueError('invalid compression parameters: %s', + ffi.string(lib.ZSTD_getErrorName(zresult))) + + def estimated_compression_context_size(self): + return lib.ZSTD_estimateCCtxSize(self.as_compression_parameters()) + + def as_compression_parameters(self): + p = ffi.new('ZSTD_compressionParameters *')[0] + p.windowLog = self.window_log + p.chainLog = self.chain_log + p.hashLog = self.hash_log + p.searchLog = self.search_log + p.searchLength = self.search_length + p.targetLength = self.target_length + p.strategy = self.strategy + + return p + +def get_compression_parameters(level, source_size=0, dict_size=0): + params = lib.ZSTD_getCParams(level, source_size, dict_size) + return CompressionParameters(window_log=params.windowLog, + chain_log=params.chainLog, + hash_log=params.hashLog, + search_log=params.searchLog, + search_length=params.searchLength, + target_length=params.targetLength, + strategy=params.strategy) + + +def estimate_compression_context_size(params): + if not isinstance(params, CompressionParameters): + raise ValueError('argument must be a CompressionParameters') + + cparams = params.as_compression_parameters() + return lib.ZSTD_estimateCCtxSize(cparams) + + +def estimate_decompression_context_size(): + return lib.ZSTD_estimateDCtxSize() + + +class ZstdCompressionWriter(object): + def __init__(self, compressor, writer, source_size, write_size): + self._compressor = compressor self._writer = writer + self._source_size = source_size + self._write_size = write_size + self._entered = False + self._mtcctx = compressor._cctx if compressor._multithreaded else None def __enter__(self): + if self._entered: + raise ZstdError('cannot __enter__ multiple times') + + if self._mtcctx: + self._compressor._init_mtcstream(self._source_size) + else: + self._compressor._ensure_cstream(self._source_size) + self._entered = True return self def __exit__(self, exc_type, exc_value, exc_tb): + self._entered = False + if not exc_type and not exc_value and not exc_tb: out_buffer = ffi.new('ZSTD_outBuffer *') - out_buffer.dst = ffi.new('char[]', _CSTREAM_OUT_SIZE) - out_buffer.size = _CSTREAM_OUT_SIZE + dst_buffer = ffi.new('char[]', self._write_size) + out_buffer.dst = dst_buffer + out_buffer.size = self._write_size out_buffer.pos = 0 while True: - res = lib.ZSTD_endStream(self._cstream, out_buffer) - if lib.ZSTD_isError(res): - raise Exception('error ending compression stream: %s' % lib.ZSTD_getErrorName) + if self._mtcctx: + zresult = lib.ZSTDMT_endStream(self._mtcctx, out_buffer) + else: + zresult = lib.ZSTD_endStream(self._compressor._cstream, out_buffer) + if lib.ZSTD_isError(zresult): + raise ZstdError('error ending compression stream: %s' % + ffi.string(lib.ZSTD_getErrorName(zresult))) if out_buffer.pos: - self._writer.write(ffi.buffer(out_buffer.dst, out_buffer.pos)) + self._writer.write(ffi.buffer(out_buffer.dst, out_buffer.pos)[:]) out_buffer.pos = 0 - if res == 0: + if zresult == 0: break + self._compressor = None + return False + def memory_size(self): + if not self._entered: + raise ZstdError('cannot determine size of an inactive compressor; ' + 'call when a context manager is active') + + return lib.ZSTD_sizeof_CStream(self._compressor._cstream) + def write(self, data): + if not self._entered: + raise ZstdError('write() must be called from an active context ' + 'manager') + + total_write = 0 + + data_buffer = ffi.from_buffer(data) + + in_buffer = ffi.new('ZSTD_inBuffer *') + in_buffer.src = data_buffer + in_buffer.size = len(data_buffer) + in_buffer.pos = 0 + out_buffer = ffi.new('ZSTD_outBuffer *') - out_buffer.dst = ffi.new('char[]', _CSTREAM_OUT_SIZE) - out_buffer.size = _CSTREAM_OUT_SIZE + dst_buffer = ffi.new('char[]', self._write_size) + out_buffer.dst = dst_buffer + out_buffer.size = self._write_size + out_buffer.pos = 0 + + while in_buffer.pos < in_buffer.size: + if self._mtcctx: + zresult = lib.ZSTDMT_compressStream(self._mtcctx, out_buffer, + in_buffer) + else: + zresult = lib.ZSTD_compressStream(self._compressor._cstream, out_buffer, + in_buffer) + if lib.ZSTD_isError(zresult): + raise ZstdError('zstd compress error: %s' % + ffi.string(lib.ZSTD_getErrorName(zresult))) + + if out_buffer.pos: + self._writer.write(ffi.buffer(out_buffer.dst, out_buffer.pos)[:]) + total_write += out_buffer.pos + out_buffer.pos = 0 + + return total_write + + def flush(self): + if not self._entered: + raise ZstdError('flush must be called from an active context manager') + + total_write = 0 + + out_buffer = ffi.new('ZSTD_outBuffer *') + dst_buffer = ffi.new('char[]', self._write_size) + out_buffer.dst = dst_buffer + out_buffer.size = self._write_size out_buffer.pos = 0 - # TODO can we reuse existing memory? - in_buffer = ffi.new('ZSTD_inBuffer *') - in_buffer.src = ffi.new('char[]', data) - in_buffer.size = len(data) - in_buffer.pos = 0 - while in_buffer.pos < in_buffer.size: - res = lib.ZSTD_compressStream(self._cstream, out_buffer, in_buffer) - if lib.ZSTD_isError(res): - raise Exception('zstd compress error: %s' % lib.ZSTD_getErrorName(res)) + while True: + if self._mtcctx: + zresult = lib.ZSTDMT_flushStream(self._mtcctx, out_buffer) + else: + zresult = lib.ZSTD_flushStream(self._compressor._cstream, out_buffer) + if lib.ZSTD_isError(zresult): + raise ZstdError('zstd compress error: %s' % + ffi.string(lib.ZSTD_getErrorName(zresult))) + + if not out_buffer.pos: + break + + self._writer.write(ffi.buffer(out_buffer.dst, out_buffer.pos)[:]) + total_write += out_buffer.pos + out_buffer.pos = 0 + + return total_write + + +class ZstdCompressionObj(object): + def compress(self, data): + if self._finished: + raise ZstdError('cannot call compress() after compressor finished') + + data_buffer = ffi.from_buffer(data) + source = ffi.new('ZSTD_inBuffer *') + source.src = data_buffer + source.size = len(data_buffer) + source.pos = 0 + + chunks = [] + + while source.pos < len(data): + if self._mtcctx: + zresult = lib.ZSTDMT_compressStream(self._mtcctx, + self._out, source) + else: + zresult = lib.ZSTD_compressStream(self._compressor._cstream, self._out, + source) + if lib.ZSTD_isError(zresult): + raise ZstdError('zstd compress error: %s' % + ffi.string(lib.ZSTD_getErrorName(zresult))) + + if self._out.pos: + chunks.append(ffi.buffer(self._out.dst, self._out.pos)[:]) + self._out.pos = 0 + + return b''.join(chunks) - if out_buffer.pos: - self._writer.write(ffi.buffer(out_buffer.dst, out_buffer.pos)) - out_buffer.pos = 0 + def flush(self, flush_mode=COMPRESSOBJ_FLUSH_FINISH): + if flush_mode not in (COMPRESSOBJ_FLUSH_FINISH, COMPRESSOBJ_FLUSH_BLOCK): + raise ValueError('flush mode not recognized') + + if self._finished: + raise ZstdError('compressor object already finished') + + assert self._out.pos == 0 + + if flush_mode == COMPRESSOBJ_FLUSH_BLOCK: + if self._mtcctx: + zresult = lib.ZSTDMT_flushStream(self._mtcctx, self._out) + else: + zresult = lib.ZSTD_flushStream(self._compressor._cstream, self._out) + if lib.ZSTD_isError(zresult): + raise ZstdError('zstd compress error: %s' % + ffi.string(lib.ZSTD_getErrorName(zresult))) + + # Output buffer is guaranteed to hold full block. + assert zresult == 0 + + if self._out.pos: + result = ffi.buffer(self._out.dst, self._out.pos)[:] + self._out.pos = 0 + return result + else: + return b'' + + assert flush_mode == COMPRESSOBJ_FLUSH_FINISH + self._finished = True + + chunks = [] + + while True: + if self._mtcctx: + zresult = lib.ZSTDMT_endStream(self._mtcctx, self._out) + else: + zresult = lib.ZSTD_endStream(self._compressor._cstream, self._out) + if lib.ZSTD_isError(zresult): + raise ZstdError('error ending compression stream: %s' % + ffi.string(lib.ZSTD_getErroName(zresult))) + + if self._out.pos: + chunks.append(ffi.buffer(self._out.dst, self._out.pos)[:]) + self._out.pos = 0 + + if not zresult: + break + + return b''.join(chunks) class ZstdCompressor(object): - def __init__(self, level=3, dict_data=None, compression_params=None): - if dict_data: - raise Exception('dict_data not yet supported') - if compression_params: - raise Exception('compression_params not yet supported') + def __init__(self, level=3, dict_data=None, compression_params=None, + write_checksum=False, write_content_size=False, + write_dict_id=True, threads=0): + if level < 1: + raise ValueError('level must be greater than 0') + elif level > lib.ZSTD_maxCLevel(): + raise ValueError('level must be less than %d' % lib.ZSTD_maxCLevel()) + + if threads < 0: + threads = _cpu_count() self._compression_level = level + self._dict_data = dict_data + self._cparams = compression_params + self._fparams = ffi.new('ZSTD_frameParameters *')[0] + self._fparams.checksumFlag = write_checksum + self._fparams.contentSizeFlag = write_content_size + self._fparams.noDictIDFlag = not write_dict_id - def compress(self, data): - # Just use the stream API for now. - output = io.BytesIO() - with self.write_to(output) as compressor: - compressor.write(data) - return output.getvalue() + if threads: + cctx = lib.ZSTDMT_createCCtx(threads) + if cctx == ffi.NULL: + raise MemoryError() + + self._cctx = ffi.gc(cctx, lib.ZSTDMT_freeCCtx) + self._multithreaded = True + else: + cctx = lib.ZSTD_createCCtx() + if cctx == ffi.NULL: + raise MemoryError() + + self._cctx = ffi.gc(cctx, lib.ZSTD_freeCCtx) + self._multithreaded = False + + self._cstream = None + + def compress(self, data, allow_empty=False): + if len(data) == 0 and self._fparams.contentSizeFlag and not allow_empty: + raise ValueError('cannot write empty inputs when writing content sizes') + + if self._multithreaded and self._dict_data: + raise ZstdError('compress() cannot be used with both dictionaries and multi-threaded compression') + + if self._multithreaded and self._cparams: + raise ZstdError('compress() cannot be used with both compression parameters and multi-threaded compression') + + # TODO use a CDict for performance. + dict_data = ffi.NULL + dict_size = 0 + + if self._dict_data: + dict_data = self._dict_data.as_bytes() + dict_size = len(self._dict_data) + + params = ffi.new('ZSTD_parameters *')[0] + if self._cparams: + params.cParams = self._cparams.as_compression_parameters() + else: + params.cParams = lib.ZSTD_getCParams(self._compression_level, len(data), + dict_size) + params.fParams = self._fparams + + dest_size = lib.ZSTD_compressBound(len(data)) + out = new_nonzero('char[]', dest_size) - def copy_stream(self, ifh, ofh): - cstream = self._get_cstream() + if self._multithreaded: + zresult = lib.ZSTDMT_compressCCtx(self._cctx, + ffi.addressof(out), dest_size, + data, len(data), + self._compression_level) + else: + zresult = lib.ZSTD_compress_advanced(self._cctx, + ffi.addressof(out), dest_size, + data, len(data), + dict_data, dict_size, + params) + + if lib.ZSTD_isError(zresult): + raise ZstdError('cannot compress: %s' % + ffi.string(lib.ZSTD_getErrorName(zresult))) + + return ffi.buffer(out, zresult)[:] + + def compressobj(self, size=0): + if self._multithreaded: + self._init_mtcstream(size) + else: + self._ensure_cstream(size) + + cobj = ZstdCompressionObj() + cobj._out = ffi.new('ZSTD_outBuffer *') + cobj._dst_buffer = ffi.new('char[]', COMPRESSION_RECOMMENDED_OUTPUT_SIZE) + cobj._out.dst = cobj._dst_buffer + cobj._out.size = COMPRESSION_RECOMMENDED_OUTPUT_SIZE + cobj._out.pos = 0 + cobj._compressor = self + cobj._finished = False + + if self._multithreaded: + cobj._mtcctx = self._cctx + else: + cobj._mtcctx = None + + return cobj + + def copy_stream(self, ifh, ofh, size=0, + read_size=COMPRESSION_RECOMMENDED_INPUT_SIZE, + write_size=COMPRESSION_RECOMMENDED_OUTPUT_SIZE): + + if not hasattr(ifh, 'read'): + raise ValueError('first argument must have a read() method') + if not hasattr(ofh, 'write'): + raise ValueError('second argument must have a write() method') + + mt = self._multithreaded + if mt: + self._init_mtcstream(size) + else: + self._ensure_cstream(size) in_buffer = ffi.new('ZSTD_inBuffer *') out_buffer = ffi.new('ZSTD_outBuffer *') - out_buffer.dst = ffi.new('char[]', _CSTREAM_OUT_SIZE) - out_buffer.size = _CSTREAM_OUT_SIZE + dst_buffer = ffi.new('char[]', write_size) + out_buffer.dst = dst_buffer + out_buffer.size = write_size out_buffer.pos = 0 total_read, total_write = 0, 0 while True: - data = ifh.read(_CSTREAM_IN_SIZE) + data = ifh.read(read_size) if not data: break - total_read += len(data) - - in_buffer.src = ffi.new('char[]', data) - in_buffer.size = len(data) + data_buffer = ffi.from_buffer(data) + total_read += len(data_buffer) + in_buffer.src = data_buffer + in_buffer.size = len(data_buffer) in_buffer.pos = 0 while in_buffer.pos < in_buffer.size: - res = lib.ZSTD_compressStream(cstream, out_buffer, in_buffer) - if lib.ZSTD_isError(res): - raise Exception('zstd compress error: %s' % - lib.ZSTD_getErrorName(res)) + if mt: + zresult = lib.ZSTDMT_compressStream(self._cctx, out_buffer, in_buffer) + else: + zresult = lib.ZSTD_compressStream(self._cstream, + out_buffer, in_buffer) + if lib.ZSTD_isError(zresult): + raise ZstdError('zstd compress error: %s' % + ffi.string(lib.ZSTD_getErrorName(zresult))) if out_buffer.pos: ofh.write(ffi.buffer(out_buffer.dst, out_buffer.pos)) - total_write = out_buffer.pos + total_write += out_buffer.pos out_buffer.pos = 0 # We've finished reading. Flush the compressor. while True: - res = lib.ZSTD_endStream(cstream, out_buffer) - if lib.ZSTD_isError(res): - raise Exception('error ending compression stream: %s' % - lib.ZSTD_getErrorName(res)) + if mt: + zresult = lib.ZSTDMT_endStream(self._cctx, out_buffer) + else: + zresult = lib.ZSTD_endStream(self._cstream, out_buffer) + if lib.ZSTD_isError(zresult): + raise ZstdError('error ending compression stream: %s' % + ffi.string(lib.ZSTD_getErrorName(zresult))) if out_buffer.pos: ofh.write(ffi.buffer(out_buffer.dst, out_buffer.pos)) total_write += out_buffer.pos out_buffer.pos = 0 - if res == 0: + if zresult == 0: break return total_read, total_write - def write_to(self, writer): - return _ZstdCompressionWriter(self._get_cstream(), writer) + def write_to(self, writer, size=0, + write_size=COMPRESSION_RECOMMENDED_OUTPUT_SIZE): + + if not hasattr(writer, 'write'): + raise ValueError('must pass an object with a write() method') + + return ZstdCompressionWriter(self, writer, size, write_size) + + def read_from(self, reader, size=0, + read_size=COMPRESSION_RECOMMENDED_INPUT_SIZE, + write_size=COMPRESSION_RECOMMENDED_OUTPUT_SIZE): + if hasattr(reader, 'read'): + have_read = True + elif hasattr(reader, '__getitem__'): + have_read = False + buffer_offset = 0 + size = len(reader) + else: + raise ValueError('must pass an object with a read() method or ' + 'conforms to buffer protocol') + + if self._multithreaded: + self._init_mtcstream(size) + else: + self._ensure_cstream(size) + + in_buffer = ffi.new('ZSTD_inBuffer *') + out_buffer = ffi.new('ZSTD_outBuffer *') + + in_buffer.src = ffi.NULL + in_buffer.size = 0 + in_buffer.pos = 0 + + dst_buffer = ffi.new('char[]', write_size) + out_buffer.dst = dst_buffer + out_buffer.size = write_size + out_buffer.pos = 0 + + while True: + # We should never have output data sitting around after a previous + # iteration. + assert out_buffer.pos == 0 + + # Collect input data. + if have_read: + read_result = reader.read(read_size) + else: + remaining = len(reader) - buffer_offset + slice_size = min(remaining, read_size) + read_result = reader[buffer_offset:buffer_offset + slice_size] + buffer_offset += slice_size + + # No new input data. Break out of the read loop. + if not read_result: + break - def _get_cstream(self): + # Feed all read data into the compressor and emit output until + # exhausted. + read_buffer = ffi.from_buffer(read_result) + in_buffer.src = read_buffer + in_buffer.size = len(read_buffer) + in_buffer.pos = 0 + + while in_buffer.pos < in_buffer.size: + if self._multithreaded: + zresult = lib.ZSTDMT_compressStream(self._cctx, out_buffer, in_buffer) + else: + zresult = lib.ZSTD_compressStream(self._cstream, out_buffer, in_buffer) + if lib.ZSTD_isError(zresult): + raise ZstdError('zstd compress error: %s' % + ffi.string(lib.ZSTD_getErrorName(zresult))) + + if out_buffer.pos: + data = ffi.buffer(out_buffer.dst, out_buffer.pos)[:] + out_buffer.pos = 0 + yield data + + assert out_buffer.pos == 0 + + # And repeat the loop to collect more data. + continue + + # If we get here, input is exhausted. End the stream and emit what + # remains. + while True: + assert out_buffer.pos == 0 + if self._multithreaded: + zresult = lib.ZSTDMT_endStream(self._cctx, out_buffer) + else: + zresult = lib.ZSTD_endStream(self._cstream, out_buffer) + if lib.ZSTD_isError(zresult): + raise ZstdError('error ending compression stream: %s' % + ffi.string(lib.ZSTD_getErrorName(zresult))) + + if out_buffer.pos: + data = ffi.buffer(out_buffer.dst, out_buffer.pos)[:] + out_buffer.pos = 0 + yield data + + if zresult == 0: + break + + def _ensure_cstream(self, size): + if self._cstream: + zresult = lib.ZSTD_resetCStream(self._cstream, size) + if lib.ZSTD_isError(zresult): + raise ZstdError('could not reset CStream: %s' % + ffi.string(lib.ZSTD_getErrorName(zresult))) + + return + cstream = lib.ZSTD_createCStream() + if cstream == ffi.NULL: + raise MemoryError() + cstream = ffi.gc(cstream, lib.ZSTD_freeCStream) - res = lib.ZSTD_initCStream(cstream, self._compression_level) - if lib.ZSTD_isError(res): + dict_data = ffi.NULL + dict_size = 0 + if self._dict_data: + dict_data = self._dict_data.as_bytes() + dict_size = len(self._dict_data) + + zparams = ffi.new('ZSTD_parameters *')[0] + if self._cparams: + zparams.cParams = self._cparams.as_compression_parameters() + else: + zparams.cParams = lib.ZSTD_getCParams(self._compression_level, + size, dict_size) + zparams.fParams = self._fparams + + zresult = lib.ZSTD_initCStream_advanced(cstream, dict_data, dict_size, + zparams, size) + if lib.ZSTD_isError(zresult): raise Exception('cannot init CStream: %s' % - lib.ZSTD_getErrorName(res)) + ffi.string(lib.ZSTD_getErrorName(zresult))) + + self._cstream = cstream + + def _init_mtcstream(self, size): + assert self._multithreaded + + dict_data = ffi.NULL + dict_size = 0 + if self._dict_data: + dict_data = self._dict_data.as_bytes() + dict_size = len(self._dict_data) + + zparams = ffi.new('ZSTD_parameters *')[0] + if self._cparams: + zparams.cParams = self._cparams.as_compression_parameters() + else: + zparams.cParams = lib.ZSTD_getCParams(self._compression_level, + size, dict_size) + + zparams.fParams = self._fparams + + zresult = lib.ZSTDMT_initCStream_advanced(self._cctx, dict_data, dict_size, + zparams, size) + + if lib.ZSTD_isError(zresult): + raise ZstdError('cannot init CStream: %s' % + ffi.string(lib.ZSTD_getErrorName(zresult))) + + +class FrameParameters(object): + def __init__(self, fparams): + self.content_size = fparams.frameContentSize + self.window_size = fparams.windowSize + self.dict_id = fparams.dictID + self.has_checksum = bool(fparams.checksumFlag) + + +def get_frame_parameters(data): + if not isinstance(data, bytes_type): + raise TypeError('argument must be bytes') + + params = ffi.new('ZSTD_frameParams *') + + zresult = lib.ZSTD_getFrameParams(params, data, len(data)) + if lib.ZSTD_isError(zresult): + raise ZstdError('cannot get frame parameters: %s' % + ffi.string(lib.ZSTD_getErrorName(zresult))) + + if zresult: + raise ZstdError('not enough data for frame parameters; need %d bytes' % + zresult) + + return FrameParameters(params[0]) + + +class ZstdCompressionDict(object): + def __init__(self, data, k=0, d=0): + assert isinstance(data, bytes_type) + self._data = data + self.k = k + self.d = d + + def __len__(self): + return len(self._data) + + def dict_id(self): + return int_type(lib.ZDICT_getDictID(self._data, len(self._data))) + + def as_bytes(self): + return self._data + + +def train_dictionary(dict_size, samples, selectivity=0, level=0, + notifications=0, dict_id=0): + if not isinstance(samples, list): + raise TypeError('samples must be a list') + + total_size = sum(map(len, samples)) + + samples_buffer = new_nonzero('char[]', total_size) + sample_sizes = new_nonzero('size_t[]', len(samples)) + + offset = 0 + for i, sample in enumerate(samples): + if not isinstance(sample, bytes_type): + raise ValueError('samples must be bytes') + + l = len(sample) + ffi.memmove(samples_buffer + offset, sample, l) + offset += l + sample_sizes[i] = l + + dict_data = new_nonzero('char[]', dict_size) + + dparams = ffi.new('ZDICT_params_t *')[0] + dparams.selectivityLevel = selectivity + dparams.compressionLevel = level + dparams.notificationLevel = notifications + dparams.dictID = dict_id + + zresult = lib.ZDICT_trainFromBuffer_advanced( + ffi.addressof(dict_data), dict_size, + ffi.addressof(samples_buffer), + ffi.addressof(sample_sizes, 0), len(samples), + dparams) + + if lib.ZDICT_isError(zresult): + raise ZstdError('Cannot train dict: %s' % + ffi.string(lib.ZDICT_getErrorName(zresult))) + + return ZstdCompressionDict(ffi.buffer(dict_data, zresult)[:]) + + +def train_cover_dictionary(dict_size, samples, k=0, d=0, + notifications=0, dict_id=0, level=0, optimize=False, + steps=0, threads=0): + if not isinstance(samples, list): + raise TypeError('samples must be a list') + + if threads < 0: + threads = _cpu_count() + + total_size = sum(map(len, samples)) + + samples_buffer = new_nonzero('char[]', total_size) + sample_sizes = new_nonzero('size_t[]', len(samples)) + + offset = 0 + for i, sample in enumerate(samples): + if not isinstance(sample, bytes_type): + raise ValueError('samples must be bytes') + + l = len(sample) + ffi.memmove(samples_buffer + offset, sample, l) + offset += l + sample_sizes[i] = l + + dict_data = new_nonzero('char[]', dict_size) + + dparams = ffi.new('COVER_params_t *')[0] + dparams.k = k + dparams.d = d + dparams.steps = steps + dparams.nbThreads = threads + dparams.notificationLevel = notifications + dparams.dictID = dict_id + dparams.compressionLevel = level + + if optimize: + zresult = lib.COVER_optimizeTrainFromBuffer( + ffi.addressof(dict_data), dict_size, + ffi.addressof(samples_buffer), + ffi.addressof(sample_sizes, 0), len(samples), + ffi.addressof(dparams)) + else: + zresult = lib.COVER_trainFromBuffer( + ffi.addressof(dict_data), dict_size, + ffi.addressof(samples_buffer), + ffi.addressof(sample_sizes, 0), len(samples), + dparams) + + if lib.ZDICT_isError(zresult): + raise ZstdError('cannot train dict: %s' % + ffi.string(lib.ZDICT_getErrorName(zresult))) + + return ZstdCompressionDict(ffi.buffer(dict_data, zresult)[:], + k=dparams.k, d=dparams.d) + + +class ZstdDecompressionObj(object): + def __init__(self, decompressor): + self._decompressor = decompressor + self._finished = False + + def decompress(self, data): + if self._finished: + raise ZstdError('cannot use a decompressobj multiple times') + + assert(self._decompressor._dstream) + + in_buffer = ffi.new('ZSTD_inBuffer *') + out_buffer = ffi.new('ZSTD_outBuffer *') + + data_buffer = ffi.from_buffer(data) + in_buffer.src = data_buffer + in_buffer.size = len(data_buffer) + in_buffer.pos = 0 + + dst_buffer = ffi.new('char[]', DECOMPRESSION_RECOMMENDED_OUTPUT_SIZE) + out_buffer.dst = dst_buffer + out_buffer.size = len(dst_buffer) + out_buffer.pos = 0 + + chunks = [] + + while in_buffer.pos < in_buffer.size: + zresult = lib.ZSTD_decompressStream(self._decompressor._dstream, + out_buffer, in_buffer) + if lib.ZSTD_isError(zresult): + raise ZstdError('zstd decompressor error: %s' % + ffi.string(lib.ZSTD_getErrorName(zresult))) + + if zresult == 0: + self._finished = True + self._decompressor = None + + if out_buffer.pos: + chunks.append(ffi.buffer(out_buffer.dst, out_buffer.pos)[:]) + out_buffer.pos = 0 + + return b''.join(chunks) + + +class ZstdDecompressionWriter(object): + def __init__(self, decompressor, writer, write_size): + self._decompressor = decompressor + self._writer = writer + self._write_size = write_size + self._entered = False + + def __enter__(self): + if self._entered: + raise ZstdError('cannot __enter__ multiple times') + + self._decompressor._ensure_dstream() + self._entered = True + + return self + + def __exit__(self, exc_type, exc_value, exc_tb): + self._entered = False + + def memory_size(self): + if not self._decompressor._dstream: + raise ZstdError('cannot determine size of inactive decompressor ' + 'call when context manager is active') + + return lib.ZSTD_sizeof_DStream(self._decompressor._dstream) + + def write(self, data): + if not self._entered: + raise ZstdError('write must be called from an active context manager') + + total_write = 0 + + in_buffer = ffi.new('ZSTD_inBuffer *') + out_buffer = ffi.new('ZSTD_outBuffer *') + + data_buffer = ffi.from_buffer(data) + in_buffer.src = data_buffer + in_buffer.size = len(data_buffer) + in_buffer.pos = 0 + + dst_buffer = ffi.new('char[]', self._write_size) + out_buffer.dst = dst_buffer + out_buffer.size = len(dst_buffer) + out_buffer.pos = 0 + + dstream = self._decompressor._dstream + + while in_buffer.pos < in_buffer.size: + zresult = lib.ZSTD_decompressStream(dstream, out_buffer, in_buffer) + if lib.ZSTD_isError(zresult): + raise ZstdError('zstd decompress error: %s' % + ffi.string(lib.ZSTD_getErrorName(zresult))) + + if out_buffer.pos: + self._writer.write(ffi.buffer(out_buffer.dst, out_buffer.pos)[:]) + total_write += out_buffer.pos + out_buffer.pos = 0 + + return total_write + + +class ZstdDecompressor(object): + def __init__(self, dict_data=None): + self._dict_data = dict_data + + dctx = lib.ZSTD_createDCtx() + if dctx == ffi.NULL: + raise MemoryError() + + self._refdctx = ffi.gc(dctx, lib.ZSTD_freeDCtx) + self._dstream = None - return cstream + @property + def _ddict(self): + if self._dict_data: + dict_data = self._dict_data.as_bytes() + dict_size = len(self._dict_data) + + ddict = lib.ZSTD_createDDict(dict_data, dict_size) + if ddict == ffi.NULL: + raise ZstdError('could not create decompression dict') + else: + ddict = None + + self.__dict__['_ddict'] = ddict + return ddict + + def decompress(self, data, max_output_size=0): + data_buffer = ffi.from_buffer(data) + + orig_dctx = new_nonzero('char[]', lib.ZSTD_sizeof_DCtx(self._refdctx)) + dctx = ffi.cast('ZSTD_DCtx *', orig_dctx) + lib.ZSTD_copyDCtx(dctx, self._refdctx) + + ddict = self._ddict + + output_size = lib.ZSTD_getDecompressedSize(data_buffer, len(data_buffer)) + if output_size: + result_buffer = ffi.new('char[]', output_size) + result_size = output_size + else: + if not max_output_size: + raise ZstdError('input data invalid or missing content size ' + 'in frame header') + + result_buffer = ffi.new('char[]', max_output_size) + result_size = max_output_size + + if ddict: + zresult = lib.ZSTD_decompress_usingDDict(dctx, + result_buffer, result_size, + data_buffer, len(data_buffer), + ddict) + else: + zresult = lib.ZSTD_decompressDCtx(dctx, + result_buffer, result_size, + data_buffer, len(data_buffer)) + if lib.ZSTD_isError(zresult): + raise ZstdError('decompression error: %s' % + ffi.string(lib.ZSTD_getErrorName(zresult))) + elif output_size and zresult != output_size: + raise ZstdError('decompression error: decompressed %d bytes; expected %d' % + (zresult, output_size)) + + return ffi.buffer(result_buffer, zresult)[:] + + def decompressobj(self): + self._ensure_dstream() + return ZstdDecompressionObj(self) + + def read_from(self, reader, read_size=DECOMPRESSION_RECOMMENDED_INPUT_SIZE, + write_size=DECOMPRESSION_RECOMMENDED_OUTPUT_SIZE, + skip_bytes=0): + if skip_bytes >= read_size: + raise ValueError('skip_bytes must be smaller than read_size') + + if hasattr(reader, 'read'): + have_read = True + elif hasattr(reader, '__getitem__'): + have_read = False + buffer_offset = 0 + size = len(reader) + else: + raise ValueError('must pass an object with a read() method or ' + 'conforms to buffer protocol') + + if skip_bytes: + if have_read: + reader.read(skip_bytes) + else: + if skip_bytes > size: + raise ValueError('skip_bytes larger than first input chunk') + + buffer_offset = skip_bytes + + self._ensure_dstream() + + in_buffer = ffi.new('ZSTD_inBuffer *') + out_buffer = ffi.new('ZSTD_outBuffer *') + + dst_buffer = ffi.new('char[]', write_size) + out_buffer.dst = dst_buffer + out_buffer.size = len(dst_buffer) + out_buffer.pos = 0 + + while True: + assert out_buffer.pos == 0 + + if have_read: + read_result = reader.read(read_size) + else: + remaining = size - buffer_offset + slice_size = min(remaining, read_size) + read_result = reader[buffer_offset:buffer_offset + slice_size] + buffer_offset += slice_size + + # No new input. Break out of read loop. + if not read_result: + break + + # Feed all read data into decompressor and emit output until + # exhausted. + read_buffer = ffi.from_buffer(read_result) + in_buffer.src = read_buffer + in_buffer.size = len(read_buffer) + in_buffer.pos = 0 + + while in_buffer.pos < in_buffer.size: + assert out_buffer.pos == 0 + + zresult = lib.ZSTD_decompressStream(self._dstream, out_buffer, in_buffer) + if lib.ZSTD_isError(zresult): + raise ZstdError('zstd decompress error: %s' % + ffi.string(lib.ZSTD_getErrorName(zresult))) + + if out_buffer.pos: + data = ffi.buffer(out_buffer.dst, out_buffer.pos)[:] + out_buffer.pos = 0 + yield data + + if zresult == 0: + return + + # Repeat loop to collect more input data. + continue + + # If we get here, input is exhausted. + + def write_to(self, writer, write_size=DECOMPRESSION_RECOMMENDED_OUTPUT_SIZE): + if not hasattr(writer, 'write'): + raise ValueError('must pass an object with a write() method') + + return ZstdDecompressionWriter(self, writer, write_size) + + def copy_stream(self, ifh, ofh, + read_size=DECOMPRESSION_RECOMMENDED_INPUT_SIZE, + write_size=DECOMPRESSION_RECOMMENDED_OUTPUT_SIZE): + if not hasattr(ifh, 'read'): + raise ValueError('first argument must have a read() method') + if not hasattr(ofh, 'write'): + raise ValueError('second argument must have a write() method') + + self._ensure_dstream() + + in_buffer = ffi.new('ZSTD_inBuffer *') + out_buffer = ffi.new('ZSTD_outBuffer *') + + dst_buffer = ffi.new('char[]', write_size) + out_buffer.dst = dst_buffer + out_buffer.size = write_size + out_buffer.pos = 0 + + total_read, total_write = 0, 0 + + # Read all available input. + while True: + data = ifh.read(read_size) + if not data: + break + + data_buffer = ffi.from_buffer(data) + total_read += len(data_buffer) + in_buffer.src = data_buffer + in_buffer.size = len(data_buffer) + in_buffer.pos = 0 + + # Flush all read data to output. + while in_buffer.pos < in_buffer.size: + zresult = lib.ZSTD_decompressStream(self._dstream, out_buffer, in_buffer) + if lib.ZSTD_isError(zresult): + raise ZstdError('zstd decompressor error: %s' % + ffi.string(lib.ZSTD_getErrorName(zresult))) + + if out_buffer.pos: + ofh.write(ffi.buffer(out_buffer.dst, out_buffer.pos)) + total_write += out_buffer.pos + out_buffer.pos = 0 + + # Continue loop to keep reading. + + return total_read, total_write + + def decompress_content_dict_chain(self, frames): + if not isinstance(frames, list): + raise TypeError('argument must be a list') + + if not frames: + raise ValueError('empty input chain') + + # First chunk should not be using a dictionary. We handle it specially. + chunk = frames[0] + if not isinstance(chunk, bytes_type): + raise ValueError('chunk 0 must be bytes') + + # All chunks should be zstd frames and should have content size set. + chunk_buffer = ffi.from_buffer(chunk) + params = ffi.new('ZSTD_frameParams *') + zresult = lib.ZSTD_getFrameParams(params, chunk_buffer, len(chunk_buffer)) + if lib.ZSTD_isError(zresult): + raise ValueError('chunk 0 is not a valid zstd frame') + elif zresult: + raise ValueError('chunk 0 is too small to contain a zstd frame') + + if not params.frameContentSize: + raise ValueError('chunk 0 missing content size in frame') + + dctx = lib.ZSTD_createDCtx() + if dctx == ffi.NULL: + raise MemoryError() + + dctx = ffi.gc(dctx, lib.ZSTD_freeDCtx) + + last_buffer = ffi.new('char[]', params.frameContentSize) + + zresult = lib.ZSTD_decompressDCtx(dctx, last_buffer, len(last_buffer), + chunk_buffer, len(chunk_buffer)) + if lib.ZSTD_isError(zresult): + raise ZstdError('could not decompress chunk 0: %s' % + ffi.string(lib.ZSTD_getErrorName(zresult))) + + # Special case of chain length of 1 + if len(frames) == 1: + return ffi.buffer(last_buffer, len(last_buffer))[:] + + i = 1 + while i < len(frames): + chunk = frames[i] + if not isinstance(chunk, bytes_type): + raise ValueError('chunk %d must be bytes' % i) + + chunk_buffer = ffi.from_buffer(chunk) + zresult = lib.ZSTD_getFrameParams(params, chunk_buffer, len(chunk_buffer)) + if lib.ZSTD_isError(zresult): + raise ValueError('chunk %d is not a valid zstd frame' % i) + elif zresult: + raise ValueError('chunk %d is too small to contain a zstd frame' % i) + + if not params.frameContentSize: + raise ValueError('chunk %d missing content size in frame' % i) + + dest_buffer = ffi.new('char[]', params.frameContentSize) + + zresult = lib.ZSTD_decompress_usingDict(dctx, dest_buffer, len(dest_buffer), + chunk_buffer, len(chunk_buffer), + last_buffer, len(last_buffer)) + if lib.ZSTD_isError(zresult): + raise ZstdError('could not decompress chunk %d' % i) + + last_buffer = dest_buffer + i += 1 + + return ffi.buffer(last_buffer, len(last_buffer))[:] + + def _ensure_dstream(self): + if self._dstream: + zresult = lib.ZSTD_resetDStream(self._dstream) + if lib.ZSTD_isError(zresult): + raise ZstdError('could not reset DStream: %s' % + ffi.string(lib.ZSTD_getErrorName(zresult))) + + return + + self._dstream = lib.ZSTD_createDStream() + if self._dstream == ffi.NULL: + raise MemoryError() + + self._dstream = ffi.gc(self._dstream, lib.ZSTD_freeDStream) + + if self._dict_data: + zresult = lib.ZSTD_initDStream_usingDict(self._dstream, + self._dict_data.as_bytes(), + len(self._dict_data)) + else: + zresult = lib.ZSTD_initDStream(self._dstream) + + if lib.ZSTD_isError(zresult): + self._dstream = None + raise ZstdError('could not initialize DStream: %s' % + ffi.string(lib.ZSTD_getErrorName(zresult)))
--- a/contrib/undumprevlog Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/undumprevlog Tue Apr 18 12:24:34 2017 -0400 @@ -9,15 +9,15 @@ from mercurial import ( node, revlog, - scmutil, transaction, util, + vfs as vfsmod, ) for fp in (sys.stdin, sys.stdout, sys.stderr): util.setbinary(fp) -opener = scmutil.opener('.', False) +opener = vfsmod.vfs('.', False) tr = transaction.transaction(sys.stderr.write, opener, {'store': opener}, "undump.journal") while True:
--- a/contrib/win32/mercurial.ini Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/win32/mercurial.ini Tue Apr 18 12:24:34 2017 -0400 @@ -19,6 +19,8 @@ editor = notepad ; show changed files and be a bit more verbose if True ; verbose = True +; colorize commands output +; color = auto ; username data to appear in commits ; it usually takes the form: Joe User <joe.user@host.com> @@ -40,7 +42,6 @@ ;bugzilla = ;children = ;churn = -;color = ;convert = ;eol = ;extdiff =
--- a/contrib/wix/help.wxs Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/wix/help.wxs Tue Apr 18 12:24:34 2017 -0400 @@ -15,6 +15,8 @@ <DirectoryRef Id="INSTALLDIR"> <Directory Id="helpdir" Name="help" FileSource="$(var.SourceDir)"> <Component Id="help.root" Guid="$(var.help.root.guid)" Win64='$(var.IsX64)'> + <File Name="bundlespec.txt" /> + <File Name="color.txt" /> <File Name="config.txt" KeyPath="yes" /> <File Name="dates.txt" /> <File Name="diffs.txt" /> @@ -25,6 +27,7 @@ <File Name="hgignore.txt" /> <File Name="hgweb.txt" /> <File Name="merge-tools.txt" /> + <File Name="pager.txt" /> <File Name="patterns.txt" /> <File Name="phases.txt" /> <File Name="revisions.txt" /> @@ -37,6 +40,7 @@ <Directory Id="help.internaldir" Name="internals"> <Component Id="help.internals" Guid="$(var.help.internals.guid)" Win64='$(var.IsX64)'> <File Id="internals.bundles.txt" Name="bundles.txt" KeyPath="yes" /> + <File Id="internals.censor.txt" Name="censor.txt" KeyPath="yes" /> <File Id="internals.changegroups.txt" Name="changegroups.txt" /> <File Id="internals.requirements.txt" Name="requirements.txt" /> <File Id="internals.revlogs.txt" Name="revlogs.txt" />
--- a/contrib/wix/templates.wxs Tue Apr 18 11:22:42 2017 -0400 +++ b/contrib/wix/templates.wxs Tue Apr 18 12:24:34 2017 -0400 @@ -32,6 +32,7 @@ <File Name="map-cmdline.changelog" KeyPath="yes" /> <File Name="map-cmdline.compact" /> <File Name="map-cmdline.default" /> + <File Name="map-cmdline.show" /> <File Name="map-cmdline.bisect" /> <File Name="map-cmdline.xml" /> <File Name="map-cmdline.status" /> @@ -225,6 +226,7 @@ <File Id="static.coal.file.png" Name="coal-file.png" /> <File Id="static.coal.folder.png" Name="coal-folder.png" /> <File Id="static.excanvas.js" Name="excanvas.js" /> + <File Id="static.followlines.js" Name="followlines.js" /> <File Id="static.mercurial.js" Name="mercurial.js" /> <File Id="static.hgicon.png" Name="hgicon.png" /> <File Id="static.hglogo.png" Name="hglogo.png" />
--- a/hgext/automv.py Tue Apr 18 11:22:42 2017 -0400 +++ b/hgext/automv.py Tue Apr 18 12:24:34 2017 -0400 @@ -4,7 +4,7 @@ # # This software may be used and distributed according to the terms of the # GNU General Public License version 2 or any later version. -"""Check for unrecorded moves at commit time (EXPERIMENTAL) +"""check for unrecorded moves at commit time (EXPERIMENTAL) This extension checks at commit/amend time if any of the committed files comes from an unrecorded mv.
--- a/hgext/bugzilla.py Tue Apr 18 11:22:42 2017 -0400 +++ b/hgext/bugzilla.py Tue Apr 18 12:24:34 2017 -0400 @@ -15,14 +15,16 @@ The bug references can optionally include an update for Bugzilla of the hours spent working on the bug. Bugs can also be marked fixed. -Three basic modes of access to Bugzilla are provided: +Four basic modes of access to Bugzilla are provided: + +1. Access via the Bugzilla REST-API. Requires bugzilla 5.0 or later. -1. Access via the Bugzilla XMLRPC interface. Requires Bugzilla 3.4 or later. +2. Access via the Bugzilla XMLRPC interface. Requires Bugzilla 3.4 or later. -2. Check data via the Bugzilla XMLRPC interface and submit bug change +3. Check data via the Bugzilla XMLRPC interface and submit bug change via email to Bugzilla email interface. Requires Bugzilla 3.4 or later. -3. Writing directly to the Bugzilla database. Only Bugzilla installations +4. Writing directly to the Bugzilla database. Only Bugzilla installations using MySQL are supported. Requires Python MySQLdb. Writing directly to the database is susceptible to schema changes, and @@ -50,11 +52,16 @@ Bugzilla is used instead as the source of the comment. Marking bugs fixed works on all supported Bugzilla versions. +Access via the REST-API needs either a Bugzilla username and password +or an apikey specified in the configuration. Comments are made under +the given username or the user assoicated with the apikey in Bugzilla. + Configuration items common to all access modes: bugzilla.version The access type to use. Values recognized are: + :``restapi``: Bugzilla REST-API, Bugzilla 5.0 and later. :``xmlrpc``: Bugzilla XMLRPC interface. :``xmlrpc+email``: Bugzilla XMLRPC and email interfaces. :``3.0``: MySQL access, Bugzilla 3.0 and later. @@ -135,7 +142,7 @@ committer email to Bugzilla user email. See also ``bugzilla.usermap``. Contains entries of the form ``committer = Bugzilla user``. -XMLRPC access mode configuration: +XMLRPC and REST-API access mode configuration: bugzilla.bzurl The base URL for the Bugzilla installation. @@ -148,6 +155,13 @@ bugzilla.password The password for Bugzilla login. +REST-API access mode uses the options listed above as well as: + +bugzilla.apikey + An apikey generated on the Bugzilla instance for api access. + Using an apikey removes the need to store the user and password + options. + XMLRPC+email access mode uses the XMLRPC access mode configuration items, and also: @@ -279,6 +293,7 @@ from __future__ import absolute_import +import json import re import time @@ -288,10 +303,10 @@ cmdutil, error, mail, + url, util, ) -urlparse = util.urlparse xmlrpclib = util.xmlrpclib # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for @@ -641,7 +656,7 @@ self.bztoken = login.get('token', '') def transport(self, uri): - if urlparse.urlparse(uri, "http")[0] == "https": + if util.urlreq.urlparse(uri, "http")[0] == "https": return cookiesafetransport() else: return cookietransport() @@ -773,6 +788,136 @@ cmds.append(self.makecommandline("resolution", self.fixresolution)) self.send_bug_modify_email(bugid, cmds, text, committer) +class NotFound(LookupError): + pass + +class bzrestapi(bzaccess): + """Read and write bugzilla data using the REST API available since + Bugzilla 5.0. + """ + def __init__(self, ui): + bzaccess.__init__(self, ui) + bz = self.ui.config('bugzilla', 'bzurl', + 'http://localhost/bugzilla/') + self.bzroot = '/'.join([bz, 'rest']) + self.apikey = self.ui.config('bugzilla', 'apikey', '') + self.user = self.ui.config('bugzilla', 'user', 'bugs') + self.passwd = self.ui.config('bugzilla', 'password') + self.fixstatus = self.ui.config('bugzilla', 'fixstatus', 'RESOLVED') + self.fixresolution = self.ui.config('bugzilla', 'fixresolution', + 'FIXED') + + def apiurl(self, targets, include_fields=None): + url = '/'.join([self.bzroot] + [str(t) for t in targets]) + qv = {} + if self.apikey: + qv['api_key'] = self.apikey + elif self.user and self.passwd: + qv['login'] = self.user + qv['password'] = self.passwd + if include_fields: + qv['include_fields'] = include_fields + if qv: + url = '%s?%s' % (url, util.urlreq.urlencode(qv)) + return url + + def _fetch(self, burl): + try: + resp = url.open(self.ui, burl) + return json.loads(resp.read()) + except util.urlerr.httperror as inst: + if inst.code == 401: + raise error.Abort(_('authorization failed')) + if inst.code == 404: + raise NotFound() + else: + raise + + def _submit(self, burl, data, method='POST'): + data = json.dumps(data) + if method == 'PUT': + class putrequest(util.urlreq.request): + def get_method(self): + return 'PUT' + request_type = putrequest + else: + request_type = util.urlreq.request + req = request_type(burl, data, + {'Content-Type': 'application/json'}) + try: + resp = url.opener(self.ui).open(req) + return json.loads(resp.read()) + except util.urlerr.httperror as inst: + if inst.code == 401: + raise error.Abort(_('authorization failed')) + if inst.code == 404: + raise NotFound() + else: + raise + + def filter_real_bug_ids(self, bugs): + '''remove bug IDs that do not exist in Bugzilla from bugs.''' + badbugs = set() + for bugid in bugs: + burl = self.apiurl(('bug', bugid), include_fields='status') + try: + self._fetch(burl) + except NotFound: + badbugs.add(bugid) + for bugid in badbugs: + del bugs[bugid] + + def filter_cset_known_bug_ids(self, node, bugs): + '''remove bug IDs where node occurs in comment text from bugs.''' + sn = short(node) + for bugid in bugs.keys(): + burl = self.apiurl(('bug', bugid, 'comment'), include_fields='text') + result = self._fetch(burl) + comments = result['bugs'][str(bugid)]['comments'] + if any(sn in c['text'] for c in comments): + self.ui.status(_('bug %d already knows about changeset %s\n') % + (bugid, sn)) + del bugs[bugid] + + def updatebug(self, bugid, newstate, text, committer): + '''update the specified bug. Add comment text and set new states. + + If possible add the comment as being from the committer of + the changeset. Otherwise use the default Bugzilla user. + ''' + bugmod = {} + if 'hours' in newstate: + bugmod['work_time'] = newstate['hours'] + if 'fix' in newstate: + bugmod['status'] = self.fixstatus + bugmod['resolution'] = self.fixresolution + if bugmod: + # if we have to change the bugs state do it here + bugmod['comment'] = { + 'comment': text, + 'is_private': False, + 'is_markdown': False, + } + burl = self.apiurl(('bug', bugid)) + self._submit(burl, bugmod, method='PUT') + self.ui.debug('updated bug %s\n' % bugid) + else: + burl = self.apiurl(('bug', bugid, 'comment')) + self._submit(burl, { + 'comment': text, + 'is_private': False, + 'is_markdown': False, + }) + self.ui.debug('added comment to bug %s\n' % bugid) + + def notify(self, bugs, committer): + '''Force sending of Bugzilla notification emails. + + Only required if the access method does not trigger notification + emails automatically. + ''' + pass + class bugzilla(object): # supported versions of bugzilla. different versions have # different schemas. @@ -781,7 +926,8 @@ '2.18': bzmysql_2_18, '3.0': bzmysql_3_0, 'xmlrpc': bzxmlrpc, - 'xmlrpc+email': bzxmlrpcemail + 'xmlrpc+email': bzxmlrpcemail, + 'restapi': bzrestapi, } _default_bug_re = (r'bugs?\s*,?\s*(?:#|nos?\.?|num(?:ber)?s?)?\s*'
--- a/hgext/clonebundles.py Tue Apr 18 11:22:42 2017 -0400 +++ b/hgext/clonebundles.py Tue Apr 18 12:24:34 2017 -0400 @@ -177,7 +177,7 @@ # Only advertise if a manifest exists. This does add some I/O to requests. # But this should be cheaper than a wasted network round trip due to # missing file. - if repo.opener.exists('clonebundles.manifest'): + if repo.vfs.exists('clonebundles.manifest'): caps.append('clonebundles') return caps
--- a/hgext/color.py Tue Apr 18 11:22:42 2017 -0400 +++ b/hgext/color.py Tue Apr 18 12:24:34 2017 -0400 @@ -5,652 +5,27 @@ # This software may be used and distributed according to the terms of the # GNU General Public License version 2 or any later version. -'''colorize output from some commands - -The color extension colorizes output from several Mercurial commands. -For example, the diff command shows additions in green and deletions -in red, while the status command shows modified files in magenta. Many -other commands have analogous colors. It is possible to customize -these colors. - -Effects -------- - -Other effects in addition to color, like bold and underlined text, are -also available. By default, the terminfo database is used to find the -terminal codes used to change color and effect. If terminfo is not -available, then effects are rendered with the ECMA-48 SGR control -function (aka ANSI escape codes). - -The available effects in terminfo mode are 'blink', 'bold', 'dim', -'inverse', 'invisible', 'italic', 'standout', and 'underline'; in -ECMA-48 mode, the options are 'bold', 'inverse', 'italic', and -'underline'. How each is rendered depends on the terminal emulator. -Some may not be available for a given terminal type, and will be -silently ignored. - -If the terminfo entry for your terminal is missing codes for an effect -or has the wrong codes, you can add or override those codes in your -configuration:: - - [color] - terminfo.dim = \E[2m - -where '\E' is substituted with an escape character. +'''enable Mercurial color mode (DEPRECATED) -Labels ------- - -Text receives color effects depending on the labels that it has. Many -default Mercurial commands emit labelled text. You can also define -your own labels in templates using the label function, see :hg:`help -templates`. A single portion of text may have more than one label. In -that case, effects given to the last label will override any other -effects. This includes the special "none" effect, which nullifies -other effects. - -Labels are normally invisible. In order to see these labels and their -position in the text, use the global --color=debug option. The same -anchor text may be associated to multiple labels, e.g. - - [log.changeset changeset.secret|changeset: 22611:6f0a53c8f587] - -The following are the default effects for some default labels. Default -effects may be overridden from your configuration file:: - - [color] - status.modified = blue bold underline red_background - status.added = green bold - status.removed = red bold blue_background - status.deleted = cyan bold underline - status.unknown = magenta bold underline - status.ignored = black bold - - # 'none' turns off all effects - status.clean = none - status.copied = none - - qseries.applied = blue bold underline - qseries.unapplied = black bold - qseries.missing = red bold +This extension enables Mercurial color mode. The feature is now directly +available in Mercurial core. You can access it using:: - diff.diffline = bold - diff.extended = cyan bold - diff.file_a = red bold - diff.file_b = green bold - diff.hunk = magenta - diff.deleted = red - diff.inserted = green - diff.changed = white - diff.tab = - diff.trailingwhitespace = bold red_background - - # Blank so it inherits the style of the surrounding label - changeset.public = - changeset.draft = - changeset.secret = - - resolve.unresolved = red bold - resolve.resolved = green bold - - bookmarks.active = green - - branches.active = none - branches.closed = black bold - branches.current = green - branches.inactive = none - - tags.normal = green - tags.local = black bold - - rebase.rebased = blue - rebase.remaining = red bold - - shelve.age = cyan - shelve.newest = green bold - shelve.name = blue bold - - histedit.remaining = red bold - -Custom colors -------------- + [ui] + color = auto -Because there are only eight standard colors, this module allows you -to define color names for other color slots which might be available -for your terminal type, assuming terminfo mode. For instance:: - - color.brightblue = 12 - color.pink = 207 - color.orange = 202 - -to set 'brightblue' to color slot 12 (useful for 16 color terminals -that have brighter colors defined in the upper eight) and, 'pink' and -'orange' to colors in 256-color xterm's default color cube. These -defined colors may then be used as any of the pre-defined eight, -including appending '_background' to set the background to that color. - -Modes ------ - -By default, the color extension will use ANSI mode (or win32 mode on -Windows) if it detects a terminal. To override auto mode (to enable -terminfo mode, for example), set the following configuration option:: - - [color] - mode = terminfo - -Any value other than 'ansi', 'win32', 'terminfo', or 'auto' will -disable color. - -Note that on some systems, terminfo mode may cause problems when using -color with the pager extension and less -R. less with the -R option -will only display ECMA-48 color codes, and terminfo mode may sometimes -emit codes that less doesn't understand. You can work around this by -either using ansi mode (or auto mode), or by using less -r (which will -pass through all terminal control codes, not just color control -codes). - -On some systems (such as MSYS in Windows), the terminal may support -a different color mode than the pager (activated via the "pager" -extension). It is possible to define separate modes depending on whether -the pager is active:: - - [color] - mode = auto - pagermode = ansi - -If ``pagermode`` is not defined, the ``mode`` will be used. +See :hg:`help color` for details. ''' from __future__ import absolute_import -from mercurial.i18n import _ -from mercurial import ( - cmdutil, - color, - commands, - dispatch, - encoding, - extensions, - pycompat, - subrepo, - ui as uimod, - util, -) +from mercurial import color -cmdtable = {} -command = cmdutil.command(cmdtable) # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should # be specifying the version(s) of Mercurial they are tested with, or # leave the attribute unspecified. testedwith = 'ships-with-hg-core' -# start and stop parameters for effects -_effects = {'none': 0, 'black': 30, 'red': 31, 'green': 32, 'yellow': 33, - 'blue': 34, 'magenta': 35, 'cyan': 36, 'white': 37, 'bold': 1, - 'italic': 3, 'underline': 4, 'inverse': 7, 'dim': 2, - 'black_background': 40, 'red_background': 41, - 'green_background': 42, 'yellow_background': 43, - 'blue_background': 44, 'purple_background': 45, - 'cyan_background': 46, 'white_background': 47} - -def _terminfosetup(ui, mode): - '''Initialize terminfo data and the terminal if we're in terminfo mode.''' - - # If we failed to load curses, we go ahead and return. - if not _terminfo_params: - return - # Otherwise, see what the config file says. - if mode not in ('auto', 'terminfo'): - return - - _terminfo_params.update((key[6:], (False, int(val), '')) - for key, val in ui.configitems('color') - if key.startswith('color.')) - _terminfo_params.update((key[9:], (True, '', val.replace('\\E', '\x1b'))) - for key, val in ui.configitems('color') - if key.startswith('terminfo.')) - - try: - curses.setupterm() - except curses.error as e: - _terminfo_params.clear() - return - - for key, (b, e, c) in _terminfo_params.items(): - if not b: - continue - if not c and not curses.tigetstr(e): - # Most terminals don't support dim, invis, etc, so don't be - # noisy and use ui.debug(). - ui.debug("no terminfo entry for %s\n" % e) - del _terminfo_params[key] - if not curses.tigetstr('setaf') or not curses.tigetstr('setab'): - # Only warn about missing terminfo entries if we explicitly asked for - # terminfo mode. - if mode == "terminfo": - ui.warn(_("no terminfo entry for setab/setaf: reverting to " - "ECMA-48 color\n")) - _terminfo_params.clear() - -def _modesetup(ui, coloropt): - if coloropt == 'debug': - return 'debug' - - auto = (coloropt == 'auto') - always = not auto and util.parsebool(coloropt) - if not always and not auto: - return None - - formatted = (always or (encoding.environ.get('TERM') != 'dumb' - and ui.formatted())) - - mode = ui.config('color', 'mode', 'auto') - - # If pager is active, color.pagermode overrides color.mode. - if getattr(ui, 'pageractive', False): - mode = ui.config('color', 'pagermode', mode) - - realmode = mode - if mode == 'auto': - if pycompat.osname == 'nt': - term = encoding.environ.get('TERM') - # TERM won't be defined in a vanilla cmd.exe environment. - - # UNIX-like environments on Windows such as Cygwin and MSYS will - # set TERM. They appear to make a best effort attempt at setting it - # to something appropriate. However, not all environments with TERM - # defined support ANSI. Since "ansi" could result in terminal - # gibberish, we error on the side of selecting "win32". However, if - # w32effects is not defined, we almost certainly don't support - # "win32", so don't even try. - if (term and 'xterm' in term) or not w32effects: - realmode = 'ansi' - else: - realmode = 'win32' - else: - realmode = 'ansi' - - def modewarn(): - # only warn if color.mode was explicitly set and we're in - # a formatted terminal - if mode == realmode and ui.formatted(): - ui.warn(_('warning: failed to set color mode to %s\n') % mode) - - if realmode == 'win32': - _terminfo_params.clear() - if not w32effects: - modewarn() - return None - _effects.update(w32effects) - elif realmode == 'ansi': - _terminfo_params.clear() - elif realmode == 'terminfo': - _terminfosetup(ui, mode) - if not _terminfo_params: - ## FIXME Shouldn't we return None in this case too? - modewarn() - realmode = 'ansi' - else: - return None - - if always or (auto and formatted): - return realmode - return None - -try: - import curses - # Mapping from effect name to terminfo attribute name (or raw code) or - # color number. This will also force-load the curses module. - _terminfo_params = {'none': (True, 'sgr0', ''), - 'standout': (True, 'smso', ''), - 'underline': (True, 'smul', ''), - 'reverse': (True, 'rev', ''), - 'inverse': (True, 'rev', ''), - 'blink': (True, 'blink', ''), - 'dim': (True, 'dim', ''), - 'bold': (True, 'bold', ''), - 'invisible': (True, 'invis', ''), - 'italic': (True, 'sitm', ''), - 'black': (False, curses.COLOR_BLACK, ''), - 'red': (False, curses.COLOR_RED, ''), - 'green': (False, curses.COLOR_GREEN, ''), - 'yellow': (False, curses.COLOR_YELLOW, ''), - 'blue': (False, curses.COLOR_BLUE, ''), - 'magenta': (False, curses.COLOR_MAGENTA, ''), - 'cyan': (False, curses.COLOR_CYAN, ''), - 'white': (False, curses.COLOR_WHITE, '')} -except ImportError: - _terminfo_params = {} - -def _effect_str(effect): - '''Helper function for render_effects().''' - - bg = False - if effect.endswith('_background'): - bg = True - effect = effect[:-11] - try: - attr, val, termcode = _terminfo_params[effect] - except KeyError: - return '' - if attr: - if termcode: - return termcode - else: - return curses.tigetstr(val) - elif bg: - return curses.tparm(curses.tigetstr('setab'), val) - else: - return curses.tparm(curses.tigetstr('setaf'), val) - -def render_effects(text, effects): - 'Wrap text in commands to turn on each effect.' - if not text: - return text - if not _terminfo_params: - start = [str(_effects[e]) for e in ['none'] + effects.split()] - start = '\033[' + ';'.join(start) + 'm' - stop = '\033[' + str(_effects['none']) + 'm' - else: - start = ''.join(_effect_str(effect) - for effect in ['none'] + effects.split()) - stop = _effect_str('none') - return ''.join([start, text, stop]) - -def valideffect(effect): - 'Determine if the effect is valid or not.' - good = False - if not _terminfo_params and effect in _effects: - good = True - elif effect in _terminfo_params or effect[:-11] in _terminfo_params: - good = True - return good - -def configstyles(ui): - for status, cfgeffects in ui.configitems('color'): - if '.' not in status or status.startswith(('color.', 'terminfo.')): - continue - cfgeffects = ui.configlist('color', status) - if cfgeffects: - good = [] - for e in cfgeffects: - if valideffect(e): - good.append(e) - else: - ui.warn(_("ignoring unknown color/effect %r " - "(configured in color.%s)\n") - % (e, status)) - color._styles[status] = ' '.join(good) - -class colorui(uimod.ui): - _colormode = 'ansi' - def write(self, *args, **opts): - if self._colormode is None: - return super(colorui, self).write(*args, **opts) - - label = opts.get('label', '') - if self._buffers and not opts.get('prompt', False): - if self._bufferapplylabels: - self._buffers[-1].extend(self.label(a, label) for a in args) - else: - self._buffers[-1].extend(args) - elif self._colormode == 'win32': - for a in args: - win32print(a, super(colorui, self).write, **opts) - else: - return super(colorui, self).write( - *[self.label(a, label) for a in args], **opts) - - def write_err(self, *args, **opts): - if self._colormode is None: - return super(colorui, self).write_err(*args, **opts) - - label = opts.get('label', '') - if self._bufferstates and self._bufferstates[-1][0]: - return self.write(*args, **opts) - if self._colormode == 'win32': - for a in args: - win32print(a, super(colorui, self).write_err, **opts) - else: - return super(colorui, self).write_err( - *[self.label(a, label) for a in args], **opts) - - def showlabel(self, msg, label): - if label and msg: - if msg[-1] == '\n': - return "[%s|%s]\n" % (label, msg[:-1]) - else: - return "[%s|%s]" % (label, msg) - else: - return msg - - def label(self, msg, label): - if self._colormode is None: - return super(colorui, self).label(msg, label) - - if self._colormode == 'debug': - return self.showlabel(msg, label) - - effects = [] - for l in label.split(): - s = color._styles.get(l, '') - if s: - effects.append(s) - elif valideffect(l): - effects.append(l) - effects = ' '.join(effects) - if effects: - return '\n'.join([render_effects(line, effects) - for line in msg.split('\n')]) - return msg - -def uisetup(ui): - if ui.plain(): - return - if not isinstance(ui, colorui): - colorui.__bases__ = (ui.__class__,) - ui.__class__ = colorui - def colorcmd(orig, ui_, opts, cmd, cmdfunc): - mode = _modesetup(ui_, opts['color']) - colorui._colormode = mode - if mode and mode != 'debug': - configstyles(ui_) - return orig(ui_, opts, cmd, cmdfunc) - def colorgit(orig, gitsub, commands, env=None, stream=False, cwd=None): - if gitsub.ui._colormode and len(commands) and commands[0] == "diff": - # insert the argument in the front, - # the end of git diff arguments is used for paths - commands.insert(1, '--color') - return orig(gitsub, commands, env, stream, cwd) - extensions.wrapfunction(dispatch, '_runcommand', colorcmd) - extensions.wrapfunction(subrepo.gitsubrepo, '_gitnodir', colorgit) - def extsetup(ui): - commands.globalopts.append( - ('', 'color', 'auto', - # i18n: 'always', 'auto', 'never', and 'debug' are keywords - # and should not be translated - _("when to colorize (boolean, always, auto, never, or debug)"), - _('TYPE'))) - -@command('debugcolor', - [('', 'style', None, _('show all configured styles'))], - 'hg debugcolor') -def debugcolor(ui, repo, **opts): - """show available color, effects or style""" - ui.write(('color mode: %s\n') % ui._colormode) - if opts.get('style'): - return _debugdisplaystyle(ui) - else: - return _debugdisplaycolor(ui) - -def _debugdisplaycolor(ui): - oldstyle = color._styles.copy() - try: - color._styles.clear() - for effect in _effects.keys(): - color._styles[effect] = effect - if _terminfo_params: - for k, v in ui.configitems('color'): - if k.startswith('color.'): - color._styles[k] = k[6:] - elif k.startswith('terminfo.'): - color._styles[k] = k[9:] - ui.write(_('available colors:\n')) - # sort label with a '_' after the other to group '_background' entry. - items = sorted(color._styles.items(), - key=lambda i: ('_' in i[0], i[0], i[1])) - for colorname, label in items: - ui.write(('%s\n') % colorname, label=label) - finally: - color._styles.clear() - color._styles.update(oldstyle) - -def _debugdisplaystyle(ui): - ui.write(_('available style:\n')) - width = max(len(s) for s in color._styles) - for label, effects in sorted(color._styles.items()): - ui.write('%s' % label, label=label) - if effects: - # 50 - ui.write(': ') - ui.write(' ' * (max(0, width - len(label)))) - ui.write(', '.join(ui.label(e, e) for e in effects.split())) - ui.write('\n') - -if pycompat.osname != 'nt': - w32effects = None -else: - import ctypes - import re - - _kernel32 = ctypes.windll.kernel32 - - _WORD = ctypes.c_ushort - - _INVALID_HANDLE_VALUE = -1 - - class _COORD(ctypes.Structure): - _fields_ = [('X', ctypes.c_short), - ('Y', ctypes.c_short)] - - class _SMALL_RECT(ctypes.Structure): - _fields_ = [('Left', ctypes.c_short), - ('Top', ctypes.c_short), - ('Right', ctypes.c_short), - ('Bottom', ctypes.c_short)] - - class _CONSOLE_SCREEN_BUFFER_INFO(ctypes.Structure): - _fields_ = [('dwSize', _COORD), - ('dwCursorPosition', _COORD), - ('wAttributes', _WORD), - ('srWindow', _SMALL_RECT), - ('dwMaximumWindowSize', _COORD)] - - _STD_OUTPUT_HANDLE = 0xfffffff5 # (DWORD)-11 - _STD_ERROR_HANDLE = 0xfffffff4 # (DWORD)-12 - - _FOREGROUND_BLUE = 0x0001 - _FOREGROUND_GREEN = 0x0002 - _FOREGROUND_RED = 0x0004 - _FOREGROUND_INTENSITY = 0x0008 - - _BACKGROUND_BLUE = 0x0010 - _BACKGROUND_GREEN = 0x0020 - _BACKGROUND_RED = 0x0040 - _BACKGROUND_INTENSITY = 0x0080 - - _COMMON_LVB_REVERSE_VIDEO = 0x4000 - _COMMON_LVB_UNDERSCORE = 0x8000 - - # http://msdn.microsoft.com/en-us/library/ms682088%28VS.85%29.aspx - w32effects = { - 'none': -1, - 'black': 0, - 'red': _FOREGROUND_RED, - 'green': _FOREGROUND_GREEN, - 'yellow': _FOREGROUND_RED | _FOREGROUND_GREEN, - 'blue': _FOREGROUND_BLUE, - 'magenta': _FOREGROUND_BLUE | _FOREGROUND_RED, - 'cyan': _FOREGROUND_BLUE | _FOREGROUND_GREEN, - 'white': _FOREGROUND_RED | _FOREGROUND_GREEN | _FOREGROUND_BLUE, - 'bold': _FOREGROUND_INTENSITY, - 'black_background': 0x100, # unused value > 0x0f - 'red_background': _BACKGROUND_RED, - 'green_background': _BACKGROUND_GREEN, - 'yellow_background': _BACKGROUND_RED | _BACKGROUND_GREEN, - 'blue_background': _BACKGROUND_BLUE, - 'purple_background': _BACKGROUND_BLUE | _BACKGROUND_RED, - 'cyan_background': _BACKGROUND_BLUE | _BACKGROUND_GREEN, - 'white_background': (_BACKGROUND_RED | _BACKGROUND_GREEN | - _BACKGROUND_BLUE), - 'bold_background': _BACKGROUND_INTENSITY, - 'underline': _COMMON_LVB_UNDERSCORE, # double-byte charsets only - 'inverse': _COMMON_LVB_REVERSE_VIDEO, # double-byte charsets only - } - - passthrough = set([_FOREGROUND_INTENSITY, - _BACKGROUND_INTENSITY, - _COMMON_LVB_UNDERSCORE, - _COMMON_LVB_REVERSE_VIDEO]) - - stdout = _kernel32.GetStdHandle( - _STD_OUTPUT_HANDLE) # don't close the handle returned - if stdout is None or stdout == _INVALID_HANDLE_VALUE: - w32effects = None - else: - csbi = _CONSOLE_SCREEN_BUFFER_INFO() - if not _kernel32.GetConsoleScreenBufferInfo( - stdout, ctypes.byref(csbi)): - # stdout may not support GetConsoleScreenBufferInfo() - # when called from subprocess or redirected - w32effects = None - else: - origattr = csbi.wAttributes - ansire = re.compile('\033\[([^m]*)m([^\033]*)(.*)', - re.MULTILINE | re.DOTALL) - - def win32print(text, orig, **opts): - label = opts.get('label', '') - attr = origattr - - def mapcolor(val, attr): - if val == -1: - return origattr - elif val in passthrough: - return attr | val - elif val > 0x0f: - return (val & 0x70) | (attr & 0x8f) - else: - return (val & 0x07) | (attr & 0xf8) - - # determine console attributes based on labels - for l in label.split(): - style = color._styles.get(l, '') - for effect in style.split(): - try: - attr = mapcolor(w32effects[effect], attr) - except KeyError: - # w32effects could not have certain attributes so we skip - # them if not found - pass - # hack to ensure regexp finds data - if not text.startswith('\033['): - text = '\033[m' + text - - # Look for ANSI-like codes embedded in text - m = re.match(ansire, text) - - try: - while m: - for sattr in m.group(1).split(';'): - if sattr: - attr = mapcolor(int(sattr), attr) - _kernel32.SetConsoleTextAttribute(stdout, attr) - orig(m.group(2), **opts) - m = re.match(ansire, m.group(3)) - finally: - # Explicitly reset original attributes - _kernel32.SetConsoleTextAttribute(stdout, origattr) + # change default color config + color._enabledbydefault = True
--- a/hgext/convert/cvsps.py Tue Apr 18 11:22:42 2017 -0400 +++ b/hgext/convert/cvsps.py Tue Apr 18 12:24:34 2017 -0400 @@ -622,7 +622,7 @@ # Sort changesets by date odd = set() - def cscmp(l, r, odd=odd): + def cscmp(l, r): d = sum(l.date) - sum(r.date) if d: return d
--- a/hgext/convert/hg.py Tue Apr 18 11:22:42 2017 -0400 +++ b/hgext/convert/hg.py Tue Apr 18 12:24:34 2017 -0400 @@ -90,10 +90,10 @@ self.wlock.release() def revmapfile(self): - return self.repo.join("shamap") + return self.repo.vfs.join("shamap") def authorfile(self): - return self.repo.join("authormap") + return self.repo.vfs.join("authormap") def setbranch(self, branch, pbranches): if not self.clonebranches: @@ -625,7 +625,7 @@ def converted(self, rev, destrev): if self.convertfp is None: - self.convertfp = open(self.repo.join('shamap'), 'a') + self.convertfp = open(self.repo.vfs.join('shamap'), 'a') self.convertfp.write('%s %s\n' % (destrev, rev)) self.convertfp.flush()
--- a/hgext/convert/p4.py Tue Apr 18 11:22:42 2017 -0400 +++ b/hgext/convert/p4.py Tue Apr 18 12:24:34 2017 -0400 @@ -161,7 +161,12 @@ d = self._fetch_revision(change) c = self._construct_commit(d, parents) - shortdesc = c.desc.splitlines(True)[0].rstrip('\r\n') + descarr = c.desc.splitlines(True) + if len(descarr) > 0: + shortdesc = descarr[0].rstrip('\r\n') + else: + shortdesc = '**empty changelist description**' + t = '%s %s' % (c.rev, repr(shortdesc)[1:-1]) ui.status(util.ellipsis(t, 80) + '\n')
--- a/hgext/convert/subversion.py Tue Apr 18 11:22:42 2017 -0400 +++ b/hgext/convert/subversion.py Tue Apr 18 12:24:34 2017 -0400 @@ -13,8 +13,8 @@ encoding, error, pycompat, - scmutil, util, + vfs as vfsmod, ) from . import common @@ -1146,8 +1146,8 @@ self.run0('checkout', path, wcpath) self.wc = wcpath - self.opener = scmutil.opener(self.wc) - self.wopener = scmutil.opener(self.wc) + self.opener = vfsmod.vfs(self.wc) + self.wopener = vfsmod.vfs(self.wc) self.childmap = mapfile(ui, self.join('hg-childmap')) if util.checkexec(self.wc): self.is_exec = util.isexec @@ -1186,7 +1186,7 @@ # best bet is to assume they are in local # encoding. They will be passed to command line calls # later anyway, so they better be. - m.add(encoding.tolocal(name.encode('utf-8'))) + m.add(encoding.unitolocal(name)) break return m @@ -1306,7 +1306,7 @@ self.setexec = [] fd, messagefile = tempfile.mkstemp(prefix='hg-convert-') - fp = os.fdopen(fd, 'w') + fp = os.fdopen(fd, pycompat.sysstr('w')) fp.write(commit.desc) fp.close() try:
--- a/hgext/eol.py Tue Apr 18 11:22:42 2017 -0400 +++ b/hgext/eol.py Tue Apr 18 12:24:34 2017 -0400 @@ -101,6 +101,7 @@ error, extensions, match, + pycompat, util, ) @@ -112,11 +113,6 @@ # Matches a lone LF, i.e., one that is not part of CRLF. singlelf = re.compile('(^|[^\r])\n') -# Matches a single EOL which can either be a CRLF where repeated CR -# are removed or a LF. We do not care about old Macintosh files, so a -# stray CR is an error. -eolre = re.compile('\r*\n') - def inconsistenteol(data): return '\r\n' in data and singlelf.search(data) @@ -130,7 +126,7 @@ if (ui.configbool('eol', 'fix-trailing-newline', False) and s and s[-1] != '\n'): s = s + '\n' - return eolre.sub('\n', s) + return util.tolf(s) def tocrlf(s, params, ui, **kwargs): """Filter to convert to CRLF EOLs.""" @@ -141,7 +137,7 @@ if (ui.configbool('eol', 'fix-trailing-newline', False) and s and s[-1] != '\n'): s = s + '\n' - return eolre.sub('\r\n', s) + return util.tocrlf(s) def isbinary(s, params): """Filter to do nothing with the file.""" @@ -170,7 +166,7 @@ isrepolf = self.cfg.get('repository', 'native') != 'CRLF' self._encode['NATIVE'] = isrepolf and 'to-lf' or 'to-crlf' - iswdlf = ui.config('eol', 'native', os.linesep) in ('LF', '\n') + iswdlf = ui.config('eol', 'native', pycompat.oslinesep) in ('LF', '\n') self._decode['NATIVE'] = iswdlf and 'to-lf' or 'to-crlf' include = [] @@ -223,7 +219,7 @@ if node is None: # Cannot use workingctx.data() since it would load # and cache the filters before we configure them. - data = repo.wfile('.hgeol').read() + data = repo.wvfs('.hgeol').read() else: data = repo[node]['.hgeol'].data() return eolfile(ui, repo.root, data) @@ -314,7 +310,7 @@ oldeol = None try: - cachemtime = os.path.getmtime(self.join("eol.cache")) + cachemtime = os.path.getmtime(self.vfs.join("eol.cache")) except OSError: cachemtime = 0 else:
--- a/hgext/extdiff.py Tue Apr 18 11:22:42 2017 -0400 +++ b/hgext/extdiff.py Tue Apr 18 12:24:34 2017 -0400 @@ -273,7 +273,7 @@ cmdline = re.sub(regex, quote, cmdline) ui.debug('running %r in %s\n' % (cmdline, tmproot)) - ui.system(cmdline, cwd=tmproot) + ui.system(cmdline, cwd=tmproot, blockedtag='extdiff') for copy_fn, working_fn, mtime in fns_and_mtime: if os.lstat(copy_fn).st_mtime != mtime: @@ -342,7 +342,7 @@ def __init__(self, path, cmdline): # We can't pass non-ASCII through docstrings (and path is # in an unknown encoding anyway) - docpath = path.encode("string-escape") + docpath = util.escapestr(path) self.__doc__ = self.__doc__ % {'path': util.uirepr(docpath)} self._cmdline = cmdline
--- a/hgext/fsmonitor/__init__.py Tue Apr 18 11:22:42 2017 -0400 +++ b/hgext/fsmonitor/__init__.py Tue Apr 18 12:24:34 2017 -0400 @@ -91,14 +91,17 @@ from __future__ import absolute_import +import codecs import hashlib import os import stat +import sys from mercurial.i18n import _ from mercurial import ( context, encoding, + error, extensions, localrepo, merge, @@ -110,6 +113,7 @@ from mercurial import match as matchmod from . import ( + pywatchman, state, watchmanclient, ) @@ -159,6 +163,28 @@ sha1.update('\0') return sha1.hexdigest() +_watchmanencoding = pywatchman.encoding.get_local_encoding() +_fsencoding = sys.getfilesystemencoding() or sys.getdefaultencoding() +_fixencoding = codecs.lookup(_watchmanencoding) != codecs.lookup(_fsencoding) + +def _watchmantofsencoding(path): + """Fix path to match watchman and local filesystem encoding + + watchman's paths encoding can differ from filesystem encoding. For example, + on Windows, it's always utf-8. + """ + try: + decoded = path.decode(_watchmanencoding) + except UnicodeDecodeError as e: + raise error.Abort(str(e), hint='watchman encoding error') + + try: + encoded = decoded.encode(_fsencoding, 'strict') + except UnicodeEncodeError as e: + raise error.Abort(str(e)) + + return encoded + def overridewalk(orig, self, match, subrepos, unknown, ignored, full=True): '''Replacement for dirstate.walk, hooking into Watchman. @@ -303,6 +329,8 @@ # for name case changes. for entry in result['files']: fname = entry['name'] + if _fixencoding: + fname = _watchmantofsencoding(fname) if switch_slashes: fname = fname.replace('\\', '/') if normalize:
--- a/hgext/fsmonitor/state.py Tue Apr 18 11:22:42 2017 -0400 +++ b/hgext/fsmonitor/state.py Tue Apr 18 12:24:34 2017 -0400 @@ -20,7 +20,7 @@ class state(object): def __init__(self, repo): - self._opener = repo.opener + self._vfs = repo.vfs self._ui = repo.ui self._rootdir = pathutil.normasprefix(repo.root) self._lastclock = None @@ -33,7 +33,7 @@ def get(self): try: - file = self._opener('fsmonitor.state', 'rb') + file = self._vfs('fsmonitor.state', 'rb') except IOError as inst: if inst.errno != errno.ENOENT: raise @@ -91,7 +91,7 @@ return try: - file = self._opener('fsmonitor.state', 'wb', atomictemp=True) + file = self._vfs('fsmonitor.state', 'wb', atomictemp=True) except (IOError, OSError): self._ui.warn(_("warning: unable to write out fsmonitor state\n")) return
--- a/hgext/gpg.py Tue Apr 18 11:22:42 2017 -0400 +++ b/hgext/gpg.py Tue Apr 18 12:24:34 2017 -0400 @@ -18,6 +18,7 @@ error, match, node as hgnode, + pycompat, util, ) @@ -44,11 +45,11 @@ try: # create temporary files fd, sigfile = tempfile.mkstemp(prefix="hg-gpg-", suffix=".sig") - fp = os.fdopen(fd, 'wb') + fp = os.fdopen(fd, pycompat.sysstr('wb')) fp.write(sig) fp.close() fd, datafile = tempfile.mkstemp(prefix="hg-gpg-", suffix=".txt") - fp = os.fdopen(fd, 'wb') + fp = os.fdopen(fd, pycompat.sysstr('wb')) fp.write(data) fp.close() gpgcmd = ("%s --logger-fd 1 --status-fd 1 --verify " @@ -280,7 +281,7 @@ raise error.Abort(_("working copy of .hgsigs is changed "), hint=_("please commit .hgsigs manually")) - sigsfile = repo.wfile(".hgsigs", "ab") + sigsfile = repo.wvfs(".hgsigs", "ab") sigsfile.write(sigmessage) sigsfile.close()
--- a/hgext/hgk.py Tue Apr 18 11:22:42 2017 -0400 +++ b/hgext/hgk.py Tue Apr 18 12:24:34 2017 -0400 @@ -71,8 +71,10 @@ inferrepo=True) def difftree(ui, repo, node1=None, node2=None, *files, **opts): """diff trees from two commits""" - def __difftree(repo, node1, node2, files=[]): + def __difftree(repo, node1, node2, files=None): assert node2 is not None + if files is None: + files = [] mmap = repo[node1].manifest() mmap2 = repo[node2].manifest() m = scmutil.match(repo[node1], files) @@ -345,4 +347,4 @@ cmd = ui.config("hgk", "path", "hgk") + " %s %s" % (optstr, " ".join(etc)) ui.debug("running %s\n" % cmd) - ui.system(cmd) + ui.system(cmd, blockedtag='hgk_view')
--- a/hgext/histedit.py Tue Apr 18 11:22:42 2017 -0400 +++ b/hgext/histedit.py Tue Apr 18 12:24:34 2017 -0400 @@ -36,7 +36,7 @@ # p, pick = use commit # e, edit = use commit, but stop for amending # f, fold = use commit, but combine it with the one above - # r, roll = like fold, but discard this commit's description + # r, roll = like fold, but discard this commit's description and date # d, drop = remove commit from history # m, mess = edit commit message without changing commit content # @@ -58,7 +58,7 @@ # p, pick = use commit # e, edit = use commit, but stop for amending # f, fold = use commit, but combine it with the one above - # r, roll = like fold, but discard this commit's description + # r, roll = like fold, but discard this commit's description and date # d, drop = remove commit from history # m, mess = edit commit message without changing commit content # @@ -71,11 +71,11 @@ *** Add delta -Edit the commit message to your liking, then close the editor. For -this example, let's assume that the commit message was changed to -``Add beta and delta.`` After histedit has run and had a chance to -remove any old or temporary revisions it needed, the history looks -like this:: +Edit the commit message to your liking, then close the editor. The date used +for the commit will be the later of the two commits' dates. For this example, +let's assume that the commit message was changed to ``Add beta and delta.`` +After histedit has run and had a chance to remove any old or temporary +revisions it needed, the history looks like this:: @ 2[tip] 989b4d060121 2009-04-27 18:04 -0500 durin42 | Add beta and delta. @@ -97,9 +97,10 @@ allowing you to edit files freely, or even use ``hg record`` to commit some changes as a separate commit. When you're done, any remaining uncommitted changes will be committed as well. When done, run ``hg -histedit --continue`` to finish this step. You'll be prompted for a -new commit message, but the default commit message will be the -original message for the ``edit`` ed revision. +histedit --continue`` to finish this step. If there are uncommitted +changes, you'll be prompted for a new commit message, but the default +commit message will be the original message for the ``edit`` ed +revision, and the date of the original commit will be preserved. The ``message`` operation will give you a chance to revise a commit message without changing the contents. It's a shortcut for doing @@ -167,6 +168,15 @@ [histedit] dropmissing = True +By default, histedit will close the transaction after each action. For +performance purposes, you can configure histedit to use a single transaction +across the entire histedit. WARNING: This setting introduces a significant risk +of losing the work you've done in a histedit if the histedit aborts +unexpectedly:: + + [histedit] + singletransaction = True + """ from __future__ import absolute_import @@ -268,6 +278,7 @@ self.lock = lock self.wlock = wlock self.backupfile = None + self.tr = None if replacements is None: self.replacements = [] else: @@ -299,8 +310,15 @@ self.replacements = replacements self.backupfile = backupfile - def write(self): - fp = self.repo.vfs('histedit-state', 'w') + def write(self, tr=None): + if tr: + tr.addfilegenerator('histedit-state', ('histedit-state',), + self._write, location='plain') + else: + with self.repo.vfs("histedit-state", "w") as f: + self._write(f) + + def _write(self, fp): fp.write('v1\n') fp.write('%s\n' % node.hex(self.parentctxnode)) fp.write('%s\n' % node.hex(self.topmost)) @@ -316,7 +334,6 @@ if not backupfile: backupfile = '' fp.write('%s\n' % backupfile) - fp.close() def _load(self): fp = self.repo.vfs('histedit-state', 'r') @@ -501,16 +518,12 @@ """ phasemin = src.phase() def commitfunc(**kwargs): - phasebackup = repo.ui.backupconfig('phases', 'new-commit') - try: - repo.ui.setconfig('phases', 'new-commit', phasemin, - 'histedit') + overrides = {('phases', 'new-commit'): phasemin} + with repo.ui.configoverride(overrides, 'histedit'): extra = kwargs.get('extra', {}).copy() extra['histedit_source'] = src.hex() kwargs['extra'] = extra return repo.commit(**kwargs) - finally: - repo.ui.restoreconfig(phasebackup) return commitfunc def applychanges(ui, repo, ctx, opts): @@ -724,6 +737,15 @@ """ return True + def firstdate(self): + """Returns true if the rule should preserve the date of the first + change. + + This exists mainly so that 'rollup' rules can be a subclass of + 'fold'. + """ + return False + def finishfold(self, ui, repo, ctx, oldctx, newnode, internalchanges): parent = ctx.parents()[0].node() repo.ui.pushbuffer() @@ -742,21 +764,21 @@ [oldctx.description()]) + '\n' commitopts['message'] = newmessage # date - commitopts['date'] = max(ctx.date(), oldctx.date()) + if self.firstdate(): + commitopts['date'] = ctx.date() + else: + commitopts['date'] = max(ctx.date(), oldctx.date()) extra = ctx.extra().copy() # histedit_source # note: ctx is likely a temporary commit but that the best we can do # here. This is sufficient to solve issue3681 anyway. extra['histedit_source'] = '%s,%s' % (ctx.hex(), oldctx.hex()) commitopts['extra'] = extra - phasebackup = repo.ui.backupconfig('phases', 'new-commit') - try: - phasemin = max(ctx.phase(), oldctx.phase()) - repo.ui.setconfig('phases', 'new-commit', phasemin, 'histedit') + phasemin = max(ctx.phase(), oldctx.phase()) + overrides = {('phases', 'new-commit'): phasemin} + with repo.ui.configoverride(overrides, 'histedit'): n = collapse(repo, ctx, repo[newnode], commitopts, skipprompt=self.skipprompt()) - finally: - repo.ui.restoreconfig(phasebackup) if n is None: return ctx, [] repo.ui.pushbuffer() @@ -809,7 +831,7 @@ return True @action(["roll", "r"], - _("like fold, but discard this commit's description")) + _("like fold, but discard this commit's description and date")) class rollup(fold): def mergedescs(self): return False @@ -817,6 +839,9 @@ def skipprompt(self): return True + def firstdate(self): + return True + @action(["drop", "d"], _('remove commit from history')) class drop(histeditaction): @@ -884,11 +909,11 @@ - `mess` to reword the changeset commit message - - `fold` to combine it with the preceding changeset + - `fold` to combine it with the preceding changeset (using the later date) - - `roll` like fold, but discarding this commit's description + - `roll` like fold, but discarding this commit's description and date - - `edit` to edit this changeset + - `edit` to edit this changeset (preserving date) There are a number of ways to select the root changeset: @@ -992,7 +1017,8 @@ def _readfile(ui, path): if path == '-': - return ui.fin.read() + with ui.timeblockedsection('histedit'): + return ui.fin.read() else: with open(path, 'rb') as f: return f.read() @@ -1082,17 +1108,45 @@ total = len(state.actions) pos = 0 - while state.actions: - state.write() - actobj = state.actions.pop(0) - pos += 1 - ui.progress(_("editing"), pos, actobj.torule(), - _('changes'), total) - ui.debug('histedit: processing %s %s\n' % (actobj.verb,\ - actobj.torule())) - parentctx, replacement_ = actobj.run() - state.parentctxnode = parentctx.node() - state.replacements.extend(replacement_) + state.tr = None + + # Force an initial state file write, so the user can run --abort/continue + # even if there's an exception before the first transaction serialize. + state.write() + try: + # Don't use singletransaction by default since it rolls the entire + # transaction back if an unexpected exception happens (like a + # pretxncommit hook throws, or the user aborts the commit msg editor). + if ui.configbool("histedit", "singletransaction", False): + # Don't use a 'with' for the transaction, since actions may close + # and reopen a transaction. For example, if the action executes an + # external process it may choose to commit the transaction first. + state.tr = repo.transaction('histedit') + + while state.actions: + state.write(tr=state.tr) + actobj = state.actions[0] + pos += 1 + ui.progress(_("editing"), pos, actobj.torule(), + _('changes'), total) + ui.debug('histedit: processing %s %s\n' % (actobj.verb,\ + actobj.torule())) + parentctx, replacement_ = actobj.run() + state.parentctxnode = parentctx.node() + state.replacements.extend(replacement_) + state.actions.pop(0) + + if state.tr is not None: + state.tr.close() + except error.InterventionRequired: + if state.tr is not None: + state.tr.close() + raise + except Exception: + if state.tr is not None: + state.tr.abort() + raise + state.write() ui.progress(_("editing"), None) @@ -1115,29 +1169,13 @@ for n in succs[1:]: ui.debug(m % node.short(n)) - supportsmarkers = obsolete.isenabled(repo, obsolete.createmarkersopt) - if supportsmarkers: - # Only create markers if the temp nodes weren't already removed. - obsolete.createmarkers(repo, ((repo[t],()) for t in sorted(tmpnodes) - if t in repo)) - else: - cleanupnode(ui, repo, 'temp', tmpnodes) + safecleanupnode(ui, repo, 'temp', tmpnodes) if not state.keep: if mapping: movebookmarks(ui, repo, mapping, state.topmost, ntm) # TODO update mq state - if supportsmarkers: - markers = [] - # sort by revision number because it sound "right" - for prec in sorted(mapping, key=repo.changelog.rev): - succs = mapping[prec] - markers.append((repo[prec], - tuple(repo[s] for s in succs))) - if markers: - obsolete.createmarkers(repo, markers) - else: - cleanupnode(ui, repo, 'replaced', mapping) + safecleanupnode(ui, repo, 'replaced', mapping) state.clear() if os.path.exists(repo.sjoin('undo')): @@ -1154,7 +1192,7 @@ # Recover our old commits if necessary if not state.topmost in repo and state.backupfile: - backupfile = repo.join(state.backupfile) + backupfile = repo.vfs.join(state.backupfile) f = hg.openpath(ui, backupfile) gen = exchange.readbundle(ui, f, backupfile) with repo.transaction('histedit.abort') as tr: @@ -1340,7 +1378,7 @@ # Save edit rules in .hg/histedit-last-edit.txt in case # the user needs to ask for help after something # surprising happens. - f = open(repo.join('histedit-last-edit.txt'), 'w') + f = open(repo.vfs.join('histedit-last-edit.txt'), 'w') f.write(rules) f.close() @@ -1564,6 +1602,34 @@ # This would reduce bundle overhead repair.strip(ui, repo, c) +def safecleanupnode(ui, repo, name, nodes): + """strip or obsolete nodes + + nodes could be either a set or dict which maps to replacements. + nodes could be unknown (outside the repo). + """ + supportsmarkers = obsolete.isenabled(repo, obsolete.createmarkersopt) + if supportsmarkers: + if util.safehasattr(nodes, 'get'): + # nodes is a dict-like mapping + # use unfiltered repo for successors in case they are hidden + urepo = repo.unfiltered() + def getmarker(prec): + succs = tuple(urepo[n] for n in nodes.get(prec, ())) + return (repo[prec], succs) + else: + # nodes is a set-like + def getmarker(prec): + return (repo[prec], ()) + # sort by revision number because it sound "right" + sortednodes = sorted([n for n in nodes if n in repo], + key=repo.changelog.rev) + markers = [getmarker(t) for t in sortednodes] + if markers: + obsolete.createmarkers(repo, markers) + else: + return cleanupnode(ui, repo, name, nodes) + def stripwrapper(orig, ui, repo, nodelist, *args, **kwargs): if isinstance(nodelist, str): nodelist = [nodelist] @@ -1581,7 +1647,7 @@ extensions.wrapfunction(repair, 'strip', stripwrapper) def summaryhook(ui, repo): - if not os.path.exists(repo.join('histedit-state')): + if not os.path.exists(repo.vfs.join('histedit-state')): return state = histeditstate(repo) state.read()
--- a/hgext/journal.py Tue Apr 18 11:22:42 2017 -0400 +++ b/hgext/journal.py Tue Apr 18 12:24:34 2017 -0400 @@ -4,7 +4,7 @@ # # This software may be used and distributed according to the terms of the # GNU General Public License version 2 or any later version. -"""Track previous positions of bookmarks (EXPERIMENTAL) +"""track previous positions of bookmarks (EXPERIMENTAL) This extension adds a new command: `hg journal`, which shows you where bookmarks were previously located. @@ -163,7 +163,7 @@ # to copy. move shared date over from source to destination but # move the local file first if repo.vfs.exists('namejournal'): - journalpath = repo.join('namejournal') + journalpath = repo.vfs.join('namejournal') util.rename(journalpath, journalpath + '.bak') storage = repo.journal local = storage._open(
--- a/hgext/keyword.py Tue Apr 18 11:22:42 2017 -0400 +++ b/hgext/keyword.py Tue Apr 18 12:24:34 2017 -0400 @@ -438,7 +438,7 @@ # simulate hgrc parsing rcmaps = '[keywordmaps]\n%s\n' % '\n'.join(args) repo.vfs.write('hgrc', rcmaps) - ui.readconfig(repo.join('hgrc')) + ui.readconfig(repo.vfs.join('hgrc')) kwmaps = dict(ui.configitems('keywordmaps')) elif opts.get('default'): if svn:
--- a/hgext/largefiles/basestore.py Tue Apr 18 11:22:42 2017 -0400 +++ b/hgext/largefiles/basestore.py Tue Apr 18 12:24:34 2017 -0400 @@ -130,7 +130,7 @@ key = (filename, fctx.filenode()) if key not in verified: verified.add(key) - expectedhash = fctx.data()[0:40] + expectedhash = lfutil.readasstandin(fctx) filestocheck.append((cset, filename, expectedhash)) failed = self._verifyfiles(contents, filestocheck)
--- a/hgext/largefiles/lfcommands.py Tue Apr 18 11:22:42 2017 -0400 +++ b/hgext/largefiles/lfcommands.py Tue Apr 18 12:24:34 2017 -0400 @@ -220,7 +220,8 @@ normalfiles.add(f) if f in lfiles: - dstfiles.append(lfutil.standin(f)) + fstandin = lfutil.standin(f) + dstfiles.append(fstandin) # largefile in manifest if it has not been removed/renamed if f in ctx.manifest(): fctx = ctx.filectx(f) @@ -236,7 +237,7 @@ if f not in lfiletohash or lfiletohash[f] != hash: rdst.wwrite(f, ctx[f].data(), ctx[f].flags()) executable = 'x' in ctx[f].flags() - lfutil.writestandin(rdst, lfutil.standin(f), hash, + lfutil.writestandin(rdst, fstandin, hash, executable) lfiletohash[f] = hash else: @@ -244,10 +245,10 @@ dstfiles.append(f) def getfilectx(repo, memctx, f): - if lfutil.isstandin(f): + srcfname = lfutil.splitstandin(f) + if srcfname is not None: # if the file isn't in the manifest then it was removed - # or renamed, raise IOError to indicate this - srcfname = lfutil.splitstandin(f) + # or renamed, return None to indicate this try: fctx = ctx.filectx(srcfname) except error.LookupError: @@ -402,9 +403,10 @@ lfiles = set(lfiles) & set(filelist) toget = [] + ctx = repo[node] for lfile in lfiles: try: - expectedhash = repo[node][lfutil.standin(lfile)].data().strip() + expectedhash = lfutil.readasstandin(ctx[lfutil.standin(lfile)]) except IOError as err: if err.errno == errno.ENOENT: continue # node must be None and standin wasn't found in wctx @@ -456,6 +458,7 @@ update = {} updated, removed = 0, 0 wvfs = repo.wvfs + wctx = repo[None] for lfile in lfiles: rellfile = lfile rellfileorig = os.path.relpath( @@ -471,9 +474,9 @@ shutil.copyfile(wvfs.join(rellfile), wvfs.join(rellfileorig)) wvfs.unlinkpath(relstandinorig) - expecthash = lfutil.readstandin(repo, lfile) + expecthash = lfutil.readasstandin(wctx[relstandin]) if expecthash != '': - if lfile not in repo[None]: # not switched to normal file + if lfile not in wctx: # not switched to normal file wvfs.unlinkpath(rellfile, ignoremissing=True) # use normallookup() to allocate an entry in largefiles # dirstate to prevent lfilesrepo.status() from reporting @@ -486,7 +489,7 @@ # largefile is converted back to a normal file: the standin # disappears, but a new (normal) file appears as the lfile. if (wvfs.exists(rellfile) and - repo.dirstate.normalize(lfile) not in repo[None]): + repo.dirstate.normalize(lfile) not in wctx): wvfs.unlinkpath(rellfile) removed += 1
--- a/hgext/largefiles/lfutil.py Tue Apr 18 11:22:42 2017 -0400 +++ b/hgext/largefiles/lfutil.py Tue Apr 18 12:24:34 2017 -0400 @@ -27,6 +27,7 @@ pycompat, scmutil, util, + vfs as vfsmod, ) shortname = '.hglf' @@ -144,7 +145,7 @@ ''' vfs = repo.vfs lfstoredir = longname - opener = scmutil.opener(vfs.join(lfstoredir)) + opener = vfsmod.vfs(vfs.join(lfstoredir)) lfdirstate = largefilesdirstate(opener, ui, repo.root, repo.dirstate._validate) @@ -164,16 +165,16 @@ return lfdirstate def lfdirstatestatus(lfdirstate, repo): - wctx = repo['.'] + pctx = repo['.'] match = matchmod.always(repo.root, repo.getcwd()) unsure, s = lfdirstate.status(match, [], False, False, False) modified, clean = s.modified, s.clean for lfile in unsure: try: - fctx = wctx[standin(lfile)] + fctx = pctx[standin(lfile)] except LookupError: fctx = None - if not fctx or fctx.data().strip() != hashfile(repo.wjoin(lfile)): + if not fctx or readasstandin(fctx) != hashfile(repo.wjoin(lfile)): modified.append(lfile) else: clean.append(lfile) @@ -201,7 +202,7 @@ file with the given hash.''' if not forcelocal and repo.shared(): return repo.vfs.reljoin(repo.sharedpath, longname, hash) - return repo.join(longname, hash) + return repo.vfs.join(longname, hash) def findstorepath(repo, hash): '''Search through the local store path(s) to find the file for the given @@ -244,9 +245,9 @@ return False return True -def copytostore(repo, rev, file, uploaded=False): +def copytostore(repo, ctx, file, fstandin): wvfs = repo.wvfs - hash = readstandin(repo, file, rev) + hash = readasstandin(ctx[fstandin]) if instore(repo, hash): return if wvfs.exists(file): @@ -260,9 +261,9 @@ ctx = repo[node] for filename in ctx.files(): - if isstandin(filename) and filename in ctx.manifest(): - realfile = splitstandin(filename) - copytostore(repo, ctx.node(), realfile) + realfile = splitstandin(filename) + if realfile is not None and filename in ctx.manifest(): + copytostore(repo, ctx, realfile, filename) def copytostoreabsolute(repo, file, hash): if inusercache(repo.ui, hash): @@ -341,19 +342,24 @@ else: return None -def updatestandin(repo, standin): - file = repo.wjoin(splitstandin(standin)) - if repo.wvfs.exists(splitstandin(standin)): +def updatestandin(repo, lfile, standin): + """Re-calculate hash value of lfile and write it into standin + + This assumes that "lfutil.standin(lfile) == standin", for efficiency. + """ + file = repo.wjoin(lfile) + if repo.wvfs.exists(lfile): hash = hashfile(file) executable = getexecutable(file) writestandin(repo, standin, hash, executable) else: - raise error.Abort(_('%s: file not found!') % splitstandin(standin)) + raise error.Abort(_('%s: file not found!') % lfile) -def readstandin(repo, filename, node=None): - '''read hex hash from standin for filename at given node, or working - directory if no node is given''' - return repo[node][standin(filename)].data().strip() +def readasstandin(fctx): + '''read hex hash from given filectx of standin file + + This encapsulates how "standin" data is stored into storage layer.''' + return fctx.data().strip() def writestandin(repo, standin, hash, executable): '''write hash to <repo.root>/<standin>''' @@ -368,17 +374,11 @@ outfile.write(data) return hasher.hexdigest() -def hashrepofile(repo, file): - return hashfile(repo.wjoin(file)) - def hashfile(file): if not os.path.exists(file): return '' - hasher = hashlib.sha1('') with open(file, 'rb') as fd: - for data in util.filechunkiter(fd): - hasher.update(data) - return hasher.hexdigest() + return hexsha1(fd) def getexecutable(filename): mode = os.stat(filename).st_mode @@ -399,11 +399,11 @@ url = join(url, a) return url -def hexsha1(data): +def hexsha1(fileobj): """hexsha1 returns the hex-encoded sha1 sum of the data in the file-like object data""" h = hashlib.sha1() - for chunk in util.filechunkiter(data): + for chunk in util.filechunkiter(fileobj): h.update(chunk) return h.hexdigest() @@ -429,10 +429,11 @@ def getstandinsstate(repo): standins = [] matcher = getstandinmatcher(repo) + wctx = repo[None] for standin in repo.dirstate.walk(matcher, [], False, False): lfile = splitstandin(standin) try: - hash = readstandin(repo, lfile) + hash = readasstandin(wctx[standin]) except IOError: hash = None standins.append((lfile, hash)) @@ -477,12 +478,17 @@ lfdirstate = openlfdirstate(repo.ui, repo) for f in ctx.files(): - if isstandin(f): - lfile = splitstandin(f) + lfile = splitstandin(f) + if lfile is not None: synclfdirstate(repo, lfdirstate, lfile, False) lfdirstate.write() # As part of committing, copy all of the largefiles into the cache. + # + # Using "node" instead of "ctx" implies additional "repo[node]" + # lookup while copyalltostore(), but can omit redundant check for + # files comming from the 2nd parent, which should exist in store + # at merging. copyalltostore(repo, node) def getlfilestoupdate(oldstandins, newstandins): @@ -522,7 +528,7 @@ files.add(f) for fn in files: if isstandin(fn) and fn in ctx: - addfunc(fn, ctx[fn].data().strip()) + addfunc(fn, readasstandin(ctx[fn])) repo.ui.progress(_('finding outgoing largefiles'), None) def updatestandinsbymatch(repo, match): @@ -553,13 +559,13 @@ # removed/renamed) for lfile in lfiles: if lfile in modifiedfiles: - if repo.wvfs.exists(standin(lfile)): + fstandin = standin(lfile) + if repo.wvfs.exists(fstandin): # this handles the case where a rebase is being # performed and the working copy is not updated # yet. if repo.wvfs.exists(lfile): - updatestandin(repo, - standin(lfile)) + updatestandin(repo, lfile, fstandin) return match @@ -585,7 +591,7 @@ for fstandin in standins: lfile = splitstandin(fstandin) if lfdirstate[lfile] != 'r': - updatestandin(repo, fstandin) + updatestandin(repo, lfile, fstandin) # Cook up a new matcher that only matches regular files or # standins corresponding to the big files requested by the
--- a/hgext/largefiles/overrides.py Tue Apr 18 11:22:42 2017 -0400 +++ b/hgext/largefiles/overrides.py Tue Apr 18 12:24:34 2017 -0400 @@ -22,8 +22,8 @@ match as matchmod, pathutil, registrar, - revset, scmutil, + smartset, util, ) @@ -223,7 +223,7 @@ if not opts.get('dry_run'): if not after: - util.unlinkpath(repo.wjoin(f), ignoremissing=True) + repo.wvfs.unlinkpath(f, ignoremissing=True) if opts.get('dry_run'): return result @@ -233,7 +233,7 @@ # function handle this. if not isaddremove: for f in remove: - util.unlinkpath(repo.wjoin(f), ignoremissing=True) + repo.wvfs.unlinkpath(f, ignoremissing=True) repo[None].forget(remove) for f in remove: @@ -351,7 +351,7 @@ pats.update(fixpats(f, tostandin) for f in p) else: def tostandin(f): - if lfutil.splitstandin(f): + if lfutil.isstandin(f): return f return lfutil.standin(f) pats.update(fixpats(f, tostandin) for f in p) @@ -365,10 +365,9 @@ # support naming a directory on the command line with only # largefiles. The original directory is kept to support normal # files. - if standin in repo[ctx.node()]: + if standin in ctx: m._files[i] = standin - elif m._files[i] not in repo[ctx.node()] \ - and repo.wvfs.isdir(standin): + elif m._files[i] not in ctx and repo.wvfs.isdir(standin): m._files.append(standin) m._fileroots = set(m._files) @@ -554,9 +553,9 @@ return origfn(premerge, repo, mynode, orig, fcd, fco, fca, labels=labels) - ahash = fca.data().strip().lower() - dhash = fcd.data().strip().lower() - ohash = fco.data().strip().lower() + ahash = lfutil.readasstandin(fca).lower() + dhash = lfutil.readasstandin(fcd).lower() + ohash = lfutil.readasstandin(fco).lower() if (ohash != ahash and ohash != dhash and (dhash == ahash or @@ -649,10 +648,13 @@ m._files = [lfutil.standin(f) for f in m._files if lfile(f)] m._fileroots = set(m._files) origmatchfn = m.matchfn - m.matchfn = lambda f: (lfutil.isstandin(f) and - (f in manifest) and - origmatchfn(lfutil.splitstandin(f)) or - None) + def matchfn(f): + lfile = lfutil.splitstandin(f) + return (lfile is not None and + (f in manifest) and + origmatchfn(lfile) or + None) + m.matchfn = matchfn return m oldmatch = installmatchfn(overridematch) listpats = [] @@ -694,7 +696,7 @@ # The file is gone, but this deletes any empty parent # directories as a side-effect. - util.unlinkpath(repo.wjoin(srclfile), True) + repo.wvfs.unlinkpath(srclfile, ignoremissing=True) lfdirstate.remove(srclfile) else: util.copyfile(repo.wjoin(srclfile), @@ -734,10 +736,11 @@ s = lfutil.lfdirstatestatus(lfdirstate, repo) lfdirstate.write() for lfile in s.modified: - lfutil.updatestandin(repo, lfutil.standin(lfile)) + lfutil.updatestandin(repo, lfile, lfutil.standin(lfile)) for lfile in s.deleted: - if (repo.wvfs.exists(lfutil.standin(lfile))): - repo.wvfs.unlink(lfutil.standin(lfile)) + fstandin = lfutil.standin(lfile) + if (repo.wvfs.exists(fstandin)): + repo.wvfs.unlink(fstandin) oldstandins = lfutil.getstandinsstate(repo) @@ -755,20 +758,23 @@ lfdirstate = lfutil.openlfdirstate(mctx.repo().ui, mctx.repo(), False) - def tostandin(f): + wctx = repo[None] + matchfiles = [] + for f in m._files: standin = lfutil.standin(f) if standin in ctx or standin in mctx: - return standin - elif standin in repo[None] or lfdirstate[f] == 'r': - return None - return f - m._files = [tostandin(f) for f in m._files] - m._files = [f for f in m._files if f is not None] + matchfiles.append(standin) + elif standin in wctx or lfdirstate[f] == 'r': + continue + else: + matchfiles.append(f) + m._files = matchfiles m._fileroots = set(m._files) origmatchfn = m.matchfn def matchfn(f): - if lfutil.isstandin(f): - return (origmatchfn(lfutil.splitstandin(f)) and + lfile = lfutil.splitstandin(f) + if lfile is not None: + return (origmatchfn(lfile) and (f in ctx or f in mctx)) return origmatchfn(f) m.matchfn = matchfn @@ -855,7 +861,7 @@ firstpulled = repo.firstpulled except AttributeError: raise error.Abort(_("pulled() only available in --lfrev")) - return revset.baseset([r for r in subset if r >= firstpulled]) + return smartset.baseset([r for r in subset if r >= firstpulled]) def overrideclone(orig, ui, source, dest=None, **opts): d = dest @@ -897,6 +903,14 @@ return result +def hgpostshare(orig, sourcerepo, destrepo, bookmarks=True, defaultpath=None): + orig(sourcerepo, destrepo, bookmarks, defaultpath) + + # If largefiles is required for this repo, permanently enable it locally + if 'largefiles' in destrepo.requirements: + with destrepo.vfs('hgrc', 'a+', text=True) as fp: + fp.write('\n[extensions]\nlargefiles=\n') + def overriderebase(orig, ui, repo, **opts): if not util.safehasattr(repo, '_largefilesenabled'): return orig(ui, repo, **opts) @@ -968,18 +982,19 @@ for f in ctx: ff = ctx.flags(f) getdata = ctx[f].data - if lfutil.isstandin(f): + lfile = lfutil.splitstandin(f) + if lfile is not None: if node is not None: path = lfutil.findfile(repo, getdata().strip()) if path is None: raise error.Abort( _('largefile %s not found in repo store or system cache') - % lfutil.splitstandin(f)) + % lfile) else: - path = lfutil.splitstandin(f) + path = lfile - f = lfutil.splitstandin(f) + f = lfile getdata = lambda: util.readfile(path) write(f, 'x' in ff and 0o755 or 0o644, 'l' in ff, getdata) @@ -993,9 +1008,9 @@ archiver.done() -def hgsubrepoarchive(orig, repo, archiver, prefix, match=None): +def hgsubrepoarchive(orig, repo, archiver, prefix, match=None, decode=True): if not repo._repo.lfstatus: - return orig(repo, archiver, prefix, match) + return orig(repo, archiver, prefix, match, decode) repo._get(repo._state + ('hg',)) rev = repo._state[1] @@ -1010,24 +1025,27 @@ if match and not match(f): return data = getdata() + if decode: + data = repo._repo.wwritedata(name, data) archiver.addfile(prefix + repo._path + '/' + name, mode, islink, data) for f in ctx: ff = ctx.flags(f) getdata = ctx[f].data - if lfutil.isstandin(f): + lfile = lfutil.splitstandin(f) + if lfile is not None: if ctx.node() is not None: path = lfutil.findfile(repo._repo, getdata().strip()) if path is None: raise error.Abort( _('largefile %s not found in repo store or system cache') - % lfutil.splitstandin(f)) + % lfile) else: - path = lfutil.splitstandin(f) + path = lfile - f = lfutil.splitstandin(f) + f = lfile getdata = lambda: util.readfile(os.path.join(prefix, path)) @@ -1037,7 +1055,7 @@ sub = ctx.workingsub(subpath) submatch = matchmod.subdirmatcher(subpath, match) sub._repo.lfstatus = True - sub.archive(archiver, prefix + repo._path + '/', submatch) + sub.archive(archiver, prefix + repo._path + '/', submatch, decode) # If a largefile is modified, the change is not reflected in its # standin until a commit. cmdutil.bailifchanged() raises an exception @@ -1068,12 +1086,13 @@ s = repo.status(match=m, clean=True) finally: repo.lfstatus = False + manifest = repo[None].manifest() forget = sorted(s.modified + s.added + s.deleted + s.clean) - forget = [f for f in forget if lfutil.standin(f) in repo[None].manifest()] + forget = [f for f in forget if lfutil.standin(f) in manifest] for f in forget: - if lfutil.standin(f) not in repo.dirstate and not \ - repo.wvfs.isdir(lfutil.standin(f)): + fstandin = lfutil.standin(f) + if fstandin not in repo.dirstate and not repo.wvfs.isdir(fstandin): ui.warn(_('not removing %s: file is already untracked\n') % m.rel(f)) bad.append(f) @@ -1094,7 +1113,7 @@ lfdirstate.write() standins = [lfutil.standin(f) for f in forget] for f in standins: - util.unlinkpath(repo.wjoin(f), ignoremissing=True) + repo.wvfs.unlinkpath(f, ignoremissing=True) rejected = repo[None].forget(standins) bad.extend(f for f in rejected if f in m.files()) @@ -1346,7 +1365,7 @@ data = repo.wwritedata(f, data) fp.write(data) else: - hash = lfutil.readstandin(repo, lf, ctx.rev()) + hash = lfutil.readasstandin(ctx[f]) if not lfutil.inusercache(repo.ui, hash): store = storefactory.openstore(repo) success, missing = store.get([(lf, hash)]) @@ -1388,19 +1407,25 @@ [], False, True, False) oldclean = set(s.clean) pctx = repo['.'] + dctx = repo[node] for lfile in unsure + s.modified: lfileabs = repo.wvfs.join(lfile) if not repo.wvfs.exists(lfileabs): continue - lfhash = lfutil.hashrepofile(repo, lfile) + lfhash = lfutil.hashfile(lfileabs) standin = lfutil.standin(lfile) lfutil.writestandin(repo, standin, lfhash, lfutil.getexecutable(lfileabs)) if (standin in pctx and - lfhash == lfutil.readstandin(repo, lfile, '.')): + lfhash == lfutil.readasstandin(pctx[standin])): oldclean.add(lfile) for lfile in s.added: - lfutil.updatestandin(repo, lfutil.standin(lfile)) + fstandin = lfutil.standin(lfile) + if fstandin not in dctx: + # in this case, content of standin file is meaningless + # (in dctx, lfile is unknown, or normal file) + continue + lfutil.updatestandin(repo, lfile, fstandin) # mark all clean largefiles as dirty, just in case the update gets # interrupted before largefiles and lfdirstate are synchronized for lfile in oldclean: @@ -1431,7 +1456,11 @@ def scmutilmarktouched(orig, repo, files, *args, **kwargs): result = orig(repo, files, *args, **kwargs) - filelist = [lfutil.splitstandin(f) for f in files if lfutil.isstandin(f)] + filelist = [] + for f in files: + lf = lfutil.splitstandin(f) + if lf is not None: + filelist.append(lf) if filelist: lfcommands.updatelfiles(repo.ui, repo, filelist=filelist, printmessage=False, normallookup=True)
--- a/hgext/largefiles/reposetup.py Tue Apr 18 11:22:42 2017 -0400 +++ b/hgext/largefiles/reposetup.py Tue Apr 18 12:24:34 2017 -0400 @@ -172,7 +172,7 @@ if standin not in ctx1: # from second parent modified.append(lfile) - elif ctx1[standin].data().strip() \ + elif lfutil.readasstandin(ctx1[standin]) \ != lfutil.hashfile(self.wjoin(lfile)): modified.append(lfile) else: @@ -188,7 +188,7 @@ standin = lfutil.standin(lfile) if standin in ctx1: abslfile = self.wjoin(lfile) - if ((ctx1[standin].data().strip() != + if ((lfutil.readasstandin(ctx1[standin]) != lfutil.hashfile(abslfile)) or (checkexec and ('x' in ctx1.flags(standin)) != @@ -272,7 +272,9 @@ # contents updated to reflect the hash of their largefile. # Do that here. def commit(self, text="", user=None, date=None, match=None, - force=False, editor=False, extra={}): + force=False, editor=False, extra=None): + if extra is None: + extra = {} orig = super(lfilesrepo, self).commit with self.wlock():
--- a/hgext/largefiles/uisetup.py Tue Apr 18 11:22:42 2017 -0400 +++ b/hgext/largefiles/uisetup.py Tue Apr 18 12:24:34 2017 -0400 @@ -120,6 +120,7 @@ _('download all versions of all largefiles'))] entry[1].extend(cloneopt) entry = extensions.wrapfunction(hg, 'clone', overrides.hgclone) + entry = extensions.wrapfunction(hg, 'postshare', overrides.hgpostshare) entry = extensions.wrapcommand(commands.table, 'cat', overrides.overridecat)
--- a/hgext/logtoprocess.py Tue Apr 18 11:22:42 2017 -0400 +++ b/hgext/logtoprocess.py Tue Apr 18 12:24:34 2017 -0400 @@ -4,7 +4,7 @@ # # This software may be used and distributed according to the terms of the # GNU General Public License version 2 or any later version. -"""Send ui.log() data to a subprocess (EXPERIMENTAL) +"""send ui.log() data to a subprocess (EXPERIMENTAL) This extension lets you specify a shell command per ui.log() event, sending all remaining arguments to as environment variables to that command.
--- a/hgext/mq.py Tue Apr 18 11:22:42 2017 -0400 +++ b/hgext/mq.py Tue Apr 18 12:24:34 2017 -0400 @@ -14,7 +14,7 @@ Known patches are represented as patch files in the .hg/patches directory. Applied patches are both patch files and changesets. -Common tasks (use :hg:`help command` for more details):: +Common tasks (use :hg:`help COMMAND` for more details):: create new patch qnew import existing patch qimport @@ -89,10 +89,12 @@ phases, pycompat, registrar, - revset, + revsetlang, scmutil, + smartset, subrepo, util, + vfs as vfsmod, ) release = lockmod.release @@ -403,18 +405,12 @@ if phase is None: if repo.ui.configbool('mq', 'secret', False): phase = phases.secret + overrides = {('ui', 'allowemptycommit'): True} if phase is not None: - phasebackup = repo.ui.backupconfig('phases', 'new-commit') - allowemptybackup = repo.ui.backupconfig('ui', 'allowemptycommit') - try: - if phase is not None: - repo.ui.setconfig('phases', 'new-commit', phase, 'mq') + overrides[('phases', 'new-commit')] = phase + with repo.ui.configoverride(overrides, 'mq'): repo.ui.setconfig('ui', 'allowemptycommit', True) return repo.commit(*args, **kwargs) - finally: - repo.ui.restoreconfig(allowemptybackup) - if phase is not None: - repo.ui.restoreconfig(phasebackup) class AbortNoCleanup(error.Abort): pass @@ -433,7 +429,7 @@ except IOError: curpath = os.path.join(path, 'patches') self.path = patchdir or curpath - self.opener = scmutil.opener(self.path) + self.opener = vfsmod.vfs(self.path) self.ui = ui self.baseui = baseui self.applieddirty = False @@ -719,7 +715,9 @@ util.rename(absf, absorig) def printdiff(self, repo, diffopts, node1, node2=None, files=None, - fp=None, changes=None, opts={}): + fp=None, changes=None, opts=None): + if opts is None: + opts = {} stat = opts.get('stat') m = scmutil.match(repo[node1], files, opts) cmdutil.diffordiffstat(self.ui, repo, diffopts, node1, node2, m, @@ -1118,6 +1116,10 @@ if name in self._reserved: raise error.Abort(_('"%s" cannot be used as the name of a patch') % name) + if name != name.strip(): + # whitespace is stripped by parseseries() + raise error.Abort(_('patch name cannot begin or end with ' + 'whitespace')) for prefix in ('.hg', '.mq'): if name.startswith(prefix): raise error.Abort(_('patch name cannot begin with "%s"') @@ -1477,7 +1479,7 @@ # created while patching for f in all_files: if f not in repo.dirstate: - util.unlinkpath(repo.wjoin(f), ignoremissing=True) + repo.wvfs.unlinkpath(f, ignoremissing=True) self.ui.warn(_('done\n')) raise @@ -1580,7 +1582,7 @@ self.backup(repo, tobackup) repo.dirstate.beginparentchange() for f in a: - util.unlinkpath(repo.wjoin(f), ignoremissing=True) + repo.wvfs.unlinkpath(f, ignoremissing=True) repo.dirstate.drop(f) for f in m + r: fctx = ctx[f] @@ -2675,6 +2677,7 @@ Returns 0 on success. """ + ui.pager('qdiff') repo.mq.diff(repo, pats, opts) return 0 @@ -2917,7 +2920,7 @@ opts = fixkeepchangesopts(ui, opts) if opts.get('merge'): if opts.get('name'): - newpath = repo.join(opts.get('name')) + newpath = repo.vfs.join(opts.get('name')) else: newpath, i = lastsavename(q.path) if not newpath: @@ -2957,7 +2960,7 @@ opts = fixkeepchangesopts(ui, opts) localupdate = True if opts.get('name'): - q = queue(ui, repo.baseui, repo.path, repo.join(opts.get('name'))) + q = queue(ui, repo.baseui, repo.path, repo.vfs.join(opts.get('name'))) ui.warn(_('using patch queue: %s\n') % q.path) localupdate = False else: @@ -3311,9 +3314,9 @@ def _queuedir(name): if name == 'patches': - return repo.join('patches') + return repo.vfs.join('patches') else: - return repo.join('patches-' + name) + return repo.vfs.join('patches-' + name) def _validname(name): for n in name: @@ -3336,7 +3339,7 @@ continue fh.write('%s\n' % (queue,)) fh.close() - util.rename(repo.join('patches.queues.new'), repo.join(_allqueues)) + repo.vfs.rename('patches.queues.new', _allqueues) if not name or opts.get('list') or opts.get('active'): current = _getcurrent() @@ -3389,7 +3392,7 @@ else: fh.write('%s\n' % (queue,)) fh.close() - util.rename(repo.join('patches.queues.new'), repo.join(_allqueues)) + repo.vfs.rename('patches.queues.new', _allqueues) _setactivenocheck(name) elif opts.get('delete'): _delete(name) @@ -3435,7 +3438,9 @@ raise error.Abort(errmsg) def commit(self, text="", user=None, date=None, match=None, - force=False, editor=False, extra={}): + force=False, editor=False, extra=None): + if extra is None: + extra = {} self.abortifwdirpatched( _('cannot commit over an applied mq patch'), force) @@ -3567,9 +3572,9 @@ def revsetmq(repo, subset, x): """Changesets managed by MQ. """ - revset.getargs(x, 0, 0, _("mq takes no arguments")) + revsetlang.getargs(x, 0, 0, _("mq takes no arguments")) applied = set([repo[r.node].rev() for r in repo.mq.applied]) - return revset.baseset([r for r in subset if r in applied]) + return smartset.baseset([r for r in subset if r in applied]) # tell hggettext to extract docstrings from these functions: i18nfunctions = [revsetmq]
--- a/hgext/pager.py Tue Apr 18 11:22:42 2017 -0400 +++ b/hgext/pager.py Tue Apr 18 12:24:34 2017 -0400 @@ -12,68 +12,22 @@ # # Run 'hg help pager' to get info on configuration. -'''browse command output with an external pager - -To set the pager that should be used, set the application variable:: - - [pager] - pager = less -FRX - -If no pager is set, the pager extensions uses the environment variable -$PAGER. If neither pager.pager, nor $PAGER is set, no pager is used. - -You can disable the pager for certain commands by adding them to the -pager.ignore list:: +'''browse command output with an external pager (DEPRECATED) - [pager] - ignore = version, help, update - -You can also enable the pager only for certain commands using -pager.attend. Below is the default list of commands to be paged:: - - [pager] - attend = annotate, cat, diff, export, glog, log, qdiff - -Setting pager.attend to an empty value will cause all commands to be -paged. - -If pager.attend is present, pager.ignore will be ignored. - -Lastly, you can enable and disable paging for individual commands with -the attend-<command> option. This setting takes precedence over -existing attend and ignore options and defaults:: +Forcibly enable paging for individual commands that don't typically +request pagination with the attend-<command> option. This setting +takes precedence over ignore options and defaults:: [pager] attend-cat = false - -To ignore global commands like :hg:`version` or :hg:`help`, you have -to specify them in your user configuration file. - -To control whether the pager is used at all for an individual command, -you can use --pager=<value>:: - - - use as needed: `auto`. - - require the pager: `yes` or `on`. - - suppress the pager: `no` or `off` (any unrecognized value - will also work). - ''' from __future__ import absolute_import -import atexit -import os -import signal -import subprocess -import sys - -from mercurial.i18n import _ from mercurial import ( cmdutil, commands, dispatch, - encoding, extensions, - util, ) # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for @@ -82,58 +36,12 @@ # leave the attribute unspecified. testedwith = 'ships-with-hg-core' -def _runpager(ui, p): - pager = subprocess.Popen(p, shell=True, bufsize=-1, - close_fds=util.closefds, stdin=subprocess.PIPE, - stdout=util.stdout, stderr=util.stderr) - - # back up original file objects and descriptors - olduifout = ui.fout - oldstdout = util.stdout - stdoutfd = os.dup(util.stdout.fileno()) - stderrfd = os.dup(util.stderr.fileno()) - - # create new line-buffered stdout so that output can show up immediately - ui.fout = util.stdout = newstdout = os.fdopen(util.stdout.fileno(), 'wb', 1) - os.dup2(pager.stdin.fileno(), util.stdout.fileno()) - if ui._isatty(util.stderr): - os.dup2(pager.stdin.fileno(), util.stderr.fileno()) - - @atexit.register - def killpager(): - if util.safehasattr(signal, "SIGINT"): - signal.signal(signal.SIGINT, signal.SIG_IGN) - pager.stdin.close() - ui.fout = olduifout - util.stdout = oldstdout - # close new stdout while it's associated with pager; otherwise stdout - # fd would be closed when newstdout is deleted - newstdout.close() - # restore original fds: stdout is open again - os.dup2(stdoutfd, util.stdout.fileno()) - os.dup2(stderrfd, util.stderr.fileno()) - pager.wait() - def uisetup(ui): - class pagerui(ui.__class__): - def _runpager(self, pagercmd): - _runpager(self, pagercmd) - - ui.__class__ = pagerui def pagecmd(orig, ui, options, cmd, cmdfunc): - p = ui.config("pager", "pager", encoding.environ.get("PAGER")) - usepager = False - always = util.parsebool(options['pager']) auto = options['pager'] == 'auto' - - if not p or '--debugger' in sys.argv or not ui.formatted(): - pass - elif always: - usepager = True - elif not auto: + if auto and not ui.pageractive: usepager = False - else: attend = ui.configlist('pager', 'attend', attended) ignore = ui.configlist('pager', 'ignore') cmds, _ = cmdutil.findcmd(cmd, commands.table) @@ -148,27 +56,18 @@ usepager = True break - setattr(ui, 'pageractive', usepager) - - if usepager: - ui.setconfig('ui', 'formatted', ui.formatted(), 'pager') - ui.setconfig('ui', 'interactive', False, 'pager') - if util.safehasattr(signal, "SIGPIPE"): - signal.signal(signal.SIGPIPE, signal.SIG_DFL) - ui._runpager(p) + if usepager: + # Slight hack: the attend list is supposed to override + # the ignore list for the pager extension, but the + # core code doesn't know about attend, so we have to + # lobotomize the ignore list so that the extension's + # behavior is preserved. + ui.setconfig('pager', 'ignore', '', 'pager') + ui.pager('extension-via-attend-' + cmd) + else: + ui.disablepager() return orig(ui, options, cmd, cmdfunc) - # Wrap dispatch._runcommand after color is loaded so color can see - # ui.pageractive. Otherwise, if we loaded first, color's wrapped - # dispatch._runcommand would run without having access to ui.pageractive. - def afterloaded(loaded): - extensions.wrapfunction(dispatch, '_runcommand', pagecmd) - extensions.afterloaded('color', afterloaded) - -def extsetup(ui): - commands.globalopts.append( - ('', 'pager', 'auto', - _("when to paginate (boolean, always, auto, or never)"), - _('TYPE'))) + extensions.wrapfunction(dispatch, '_runcommand', pagecmd) attended = ['annotate', 'cat', 'diff', 'export', 'glog', 'log', 'qdiff']
--- a/hgext/patchbomb.py Tue Apr 18 11:22:42 2017 -0400 +++ b/hgext/patchbomb.py Tue Apr 18 12:24:34 2017 -0400 @@ -60,6 +60,14 @@ intro=never # never include an introduction message intro=always # always include an introduction message +You can specify a template for flags to be added in subject prefixes. Flags +specified by --flag option are exported as ``{flags}`` keyword:: + + [patchbomb] + flagtemplate = "{separate(' ', + ifeq(branch, 'default', '', branch|upper), + flags)}" + You can set patchbomb to always ask for confirmation by setting ``patchbomb.confirm`` to true. ''' @@ -75,13 +83,14 @@ from mercurial import ( cmdutil, commands, - encoding, error, + formatter, hg, mail, node as nodemod, patch, scmutil, + templater, util, ) stringio = util.stringio @@ -135,7 +144,32 @@ intro = 1 < number return intro -def makepatch(ui, repo, patchlines, opts, _charsets, idx, total, numbered, +def _formatflags(ui, repo, rev, flags): + """build flag string optionally by template""" + tmpl = ui.config('patchbomb', 'flagtemplate') + if not tmpl: + return ' '.join(flags) + out = util.stringio() + opts = {'template': templater.unquotestring(tmpl)} + with formatter.templateformatter(ui, out, 'patchbombflag', opts) as fm: + fm.startitem() + fm.context(ctx=repo[rev]) + fm.write('flags', '%s', fm.formatlist(flags, name='flag')) + return out.getvalue() + +def _formatprefix(ui, repo, rev, flags, idx, total, numbered): + """build prefix to patch subject""" + flag = _formatflags(ui, repo, rev, flags) + if flag: + flag = ' ' + flag + + if not numbered: + return '[PATCH%s]' % flag + else: + tlen = len(str(total)) + return '[PATCH %0*d of %d%s]' % (tlen, idx, total, flag) + +def makepatch(ui, repo, rev, patchlines, opts, _charsets, idx, total, numbered, patchname=None): desc = [] @@ -202,16 +236,13 @@ else: msg = mail.mimetextpatch(body, display=opts.get('test')) - flag = ' '.join(opts.get('flag')) - if flag: - flag = ' ' + flag - + prefix = _formatprefix(ui, repo, rev, opts.get('flag'), idx, total, + numbered) subj = desc[0].strip().rstrip('. ') if not numbered: - subj = '[PATCH%s] %s' % (flag, opts.get('subject') or subj) + subj = ' '.join([prefix, opts.get('subject') or subj]) else: - tlen = len(str(total)) - subj = '[PATCH %0*d of %d%s] %s' % (tlen, idx, total, flag, subj) + subj = ' '.join([prefix, subj]) msg['Subject'] = mail.headencode(ui, subj, _charsets, opts.get('test')) msg['X-Mercurial-Node'] = node msg['X-Mercurial-Series-Index'] = '%i' % idx @@ -303,19 +334,16 @@ msg['Subject'] = mail.headencode(ui, subj, _charsets, opts.get('test')) return [(msg, subj, None)] -def _makeintro(repo, sender, patches, **opts): +def _makeintro(repo, sender, revs, patches, **opts): """make an introduction email, asking the user for content if needed email is returned as (subject, body, cumulative-diffstat)""" ui = repo.ui _charsets = mail._charsets(ui) - tlen = len(str(len(patches))) - flag = opts.get('flag') or '' - if flag: - flag = ' ' + ' '.join(flag) - prefix = '[PATCH %0*d of %d%s]' % (tlen, 0, len(patches), flag) - + # use the last revision which is likely to be a bookmarked head + prefix = _formatprefix(ui, repo, revs.last(), opts.get('flag'), + 0, len(patches), numbered=True) subj = (opts.get('subject') or prompt(ui, '(optional) Subject: ', rest=prefix, default='')) if not subj: @@ -337,7 +365,7 @@ opts.get('test')) return (msg, subj, diffstat) -def _getpatchmsgs(repo, sender, patches, patchnames=None, **opts): +def _getpatchmsgs(repo, sender, revs, patchnames=None, **opts): """return a list of emails from a list of patches This involves introduction message creation if necessary. @@ -346,6 +374,7 @@ """ ui = repo.ui _charsets = mail._charsets(ui) + patches = list(_getpatches(repo, revs, **opts)) msgs = [] ui.write(_('this patch series consists of %d patches.\n\n') @@ -353,7 +382,7 @@ # build the intro message, or skip it if the user declines if introwanted(ui, opts, len(patches)): - msg = _makeintro(repo, sender, patches, **opts) + msg = _makeintro(repo, sender, revs, patches, **opts) if msg: msgs.append(msg) @@ -362,10 +391,11 @@ # now generate the actual patch messages name = None - for i, p in enumerate(patches): + assert len(revs) == len(patches) + for i, (r, p) in enumerate(zip(revs, patches)): if patchnames: name = patchnames[i] - msg = makepatch(ui, repo, p, opts, _charsets, i + 1, + msg = makepatch(ui, repo, r, p, opts, _charsets, i + 1, len(patches), numbered, name) msgs.append(msg) @@ -467,9 +497,7 @@ With -n/--test, all steps will run, but mail will not be sent. You will be prompted for an email recipient address, a subject and an introductory message describing the patches of your patchbomb. - Then when all is done, patchbomb messages are displayed. If the - PAGER environment variable is set, your pager will be fired up once - for each patchbomb message, so you can verify everything is alright. + Then when all is done, patchbomb messages are displayed. In case email sending fails, you will find a backup of your series introductory message in ``.hg/last-email.txt``. @@ -511,14 +539,12 @@ mbox = opts.get('mbox') outgoing = opts.get('outgoing') rev = opts.get('rev') - # internal option used by pbranches - patches = opts.get('patches') if not (opts.get('test') or mbox): # really sending mail.validateconfig(ui) - if not (revs or rev or outgoing or bundle or patches): + if not (revs or rev or outgoing or bundle): raise error.Abort(_('specify at least one changeset with -r or -o')) if outgoing and bundle: @@ -590,17 +616,13 @@ ui.config('patchbomb', 'from') or prompt(ui, 'From', ui.username())) - if patches: - msgs = _getpatchmsgs(repo, sender, patches, opts.get('patchnames'), - **opts) - elif bundle: + if bundle: bundledata = _getbundle(repo, dest, **opts) bundleopts = opts.copy() bundleopts.pop('bundle', None) # already processed msgs = _getbundlemsgs(repo, sender, bundledata, **bundleopts) else: - _patches = list(_getpatches(repo, revs, **opts)) - msgs = _getpatchmsgs(repo, sender, _patches, **opts) + msgs = _getpatchmsgs(repo, sender, revs, **opts) showaddrs = [] @@ -693,20 +715,14 @@ m['Reply-To'] = ', '.join(replyto) if opts.get('test'): ui.status(_('displaying '), subj, ' ...\n') - ui.flush() - if 'PAGER' in encoding.environ and not ui.plain(): - fp = util.popen(encoding.environ['PAGER'], 'w') - else: - fp = ui - generator = emailmod.Generator.Generator(fp, mangle_from_=False) + ui.pager('email') + generator = emailmod.Generator.Generator(ui, mangle_from_=False) try: generator.flatten(m, 0) - fp.write('\n') + ui.write('\n') except IOError as inst: if inst.errno != errno.EPIPE: raise - if fp is not ui: - fp.close() else: if not sendmail: sendmail = mail.connect(ui, mbox=mbox)
--- a/hgext/rebase.py Tue Apr 18 11:22:42 2017 -0400 +++ b/hgext/rebase.py Tue Apr 18 12:24:34 2017 -0400 @@ -47,6 +47,7 @@ repoview, revset, scmutil, + smartset, util, ) @@ -118,8 +119,8 @@ # i18n: "_rebasedefaultdest" is a keyword sourceset = None if x is not None: - sourceset = revset.getset(repo, revset.fullreposet(repo), x) - return subset & revset.baseset([_destrebase(repo, sourceset)]) + sourceset = revset.getset(repo, smartset.fullreposet(repo), x) + return subset & smartset.baseset([_destrebase(repo, sourceset)]) class rebaseruntime(object): """This class is a container for rebase runtime state""" @@ -158,6 +159,37 @@ self.keepopen = opts.get('keepopen', False) self.obsoletenotrebased = {} + def storestatus(self, tr=None): + """Store the current status to allow recovery""" + if tr: + tr.addfilegenerator('rebasestate', ('rebasestate',), + self._writestatus, location='plain') + else: + with self.repo.vfs("rebasestate", "w") as f: + self._writestatus(f) + + def _writestatus(self, f): + repo = self.repo.unfiltered() + f.write(repo[self.originalwd].hex() + '\n') + f.write(repo[self.target].hex() + '\n') + f.write(repo[self.external].hex() + '\n') + f.write('%d\n' % int(self.collapsef)) + f.write('%d\n' % int(self.keepf)) + f.write('%d\n' % int(self.keepbranchesf)) + f.write('%s\n' % (self.activebookmark or '')) + for d, v in self.state.iteritems(): + oldrev = repo[d].hex() + if v >= 0: + newrev = repo[v].hex() + elif v == revtodo: + # To maintain format compatibility, we have to use nullid. + # Please do remove this special case when upgrading the format. + newrev = hex(nullid) + else: + newrev = v + f.write("%s:%s\n" % (oldrev, newrev)) + repo.ui.debug('rebase status stored\n') + def restorestatus(self): """Restore a previously stored status""" repo = self.repo @@ -218,7 +250,7 @@ repo.ui.debug('computed skipped revs: %s\n' % (' '.join(str(r) for r in sorted(skipped)) or None)) repo.ui.debug('rebase status resumed\n') - _setrebasesetvisibility(repo, state.keys()) + _setrebasesetvisibility(repo, set(state.keys()) | set([originalwd])) self.originalwd = originalwd self.target = target @@ -251,7 +283,7 @@ def _prepareabortorcontinue(self, isabort): try: self.restorestatus() - self.collapsemsg = restorecollapsemsg(self.repo) + self.collapsemsg = restorecollapsemsg(self.repo, isabort) except error.RepoLookupError: if isabort: clearstatus(self.repo) @@ -294,11 +326,11 @@ self.ui.status(_('nothing to rebase\n')) return _nothingtorebase() - root = min(rebaseset) - if not self.keepf and not self.repo[root].mutable(): - raise error.Abort(_("can't rebase public changeset %s") - % self.repo[root], - hint=_("see 'hg help phases' for details")) + for root in self.repo.set('roots(%ld)', rebaseset): + if not self.keepf and not root.mutable(): + raise error.Abort(_("can't rebase public changeset %s") + % root, + hint=_("see 'hg help phases' for details")) (self.originalwd, self.target, self.state) = result if self.collapsef: @@ -311,7 +343,7 @@ if dest.closesbranch() and not self.keepbranchesf: self.ui.status(_('reopening closed branch head %s\n') % dest) - def _performrebase(self): + def _performrebase(self, tr): repo, ui, opts = self.repo, self.ui, self.opts if self.keepbranchesf: # insert _savebranch at the start of extrafns so if @@ -337,6 +369,10 @@ if self.activebookmark: bookmarks.deactivate(repo) + # Store the state before we begin so users can run 'hg rebase --abort' + # if we fail before the transaction closes. + self.storestatus() + sortedrevs = repo.revs('sort(%ld, -topo)', self.state) cands = [k for k, v in self.state.iteritems() if v == revtodo] total = len(cands) @@ -357,10 +393,7 @@ self.state, self.targetancestors, self.obsoletenotrebased) - storestatus(repo, self.originalwd, self.target, - self.state, self.collapsef, self.keepf, - self.keepbranchesf, self.external, - self.activebookmark) + self.storestatus(tr=tr) storecollapsemsg(repo, self.collapsemsg) if len(repo[None].parents()) == 2: repo.ui.debug('resuming interrupted rebase\n') @@ -442,12 +475,24 @@ editopt = True editor = cmdutil.getcommiteditor(edit=editopt, editform=editform) revtoreuse = max(self.state) - newnode = concludenode(repo, revtoreuse, p1, self.external, - commitmsg=commitmsg, - extrafn=_makeextrafn(self.extrafns), - editor=editor, - keepbranches=self.keepbranchesf, - date=self.date) + dsguard = dirstateguard.dirstateguard(repo, 'rebase') + try: + newnode = concludenode(repo, revtoreuse, p1, self.external, + commitmsg=commitmsg, + extrafn=_makeextrafn(self.extrafns), + editor=editor, + keepbranches=self.keepbranchesf, + date=self.date) + dsguard.close() + release(dsguard) + except error.InterventionRequired: + dsguard.close() + release(dsguard) + raise + except Exception: + release(dsguard) + raise + if newnode is None: newrev = self.target else: @@ -617,6 +662,16 @@ hg rebase -r "branch(featureX)" -d 1.3 --keepbranches + Configuration Options: + + You can make rebase require a destination if you set the following config + option: + + [commands] + rebase.requiredest = False + + Return Values: + Returns 0 on success, 1 if nothing to rebase or there are unresolved conflicts. @@ -678,15 +733,31 @@ if retcode is not None: return retcode - rbsrt._performrebase() + with repo.transaction('rebase') as tr: + dsguard = dirstateguard.dirstateguard(repo, 'rebase') + try: + rbsrt._performrebase(tr) + dsguard.close() + release(dsguard) + except error.InterventionRequired: + dsguard.close() + release(dsguard) + tr.close() + raise + except Exception: + release(dsguard) + raise rbsrt._finishrebase() finally: release(lock, wlock) -def _definesets(ui, repo, destf=None, srcf=None, basef=None, revf=[], +def _definesets(ui, repo, destf=None, srcf=None, basef=None, revf=None, destspace=None): """use revisions argument to define destination and rebase set """ + if revf is None: + revf = [] + # destspace is here to work around issues with `hg pull --rebase` see # issue5214 for details if srcf and basef: @@ -699,6 +770,10 @@ cmdutil.checkunfinished(repo) cmdutil.bailifchanged(repo) + if ui.configbool('commands', 'rebase.requiredest') and not destf: + raise error.Abort(_('you must specify a destination'), + hint=_('use: hg rebase -d REV')) + if destf: dest = scmutil.revsingle(repo, destf) @@ -799,36 +874,28 @@ '''Commit the wd changes with parents p1 and p2. Reuse commit info from rev but also store useful information in extra. Return node of committed revision.''' - dsguard = dirstateguard.dirstateguard(repo, 'rebase') - try: - repo.setparents(repo[p1].node(), repo[p2].node()) - ctx = repo[rev] - if commitmsg is None: - commitmsg = ctx.description() - keepbranch = keepbranches and repo[p1].branch() != ctx.branch() - extra = {'rebase_source': ctx.hex()} - if extrafn: - extrafn(ctx, extra) + repo.setparents(repo[p1].node(), repo[p2].node()) + ctx = repo[rev] + if commitmsg is None: + commitmsg = ctx.description() + keepbranch = keepbranches and repo[p1].branch() != ctx.branch() + extra = {'rebase_source': ctx.hex()} + if extrafn: + extrafn(ctx, extra) - backup = repo.ui.backupconfig('phases', 'new-commit') - try: - targetphase = max(ctx.phase(), phases.draft) - repo.ui.setconfig('phases', 'new-commit', targetphase, 'rebase') - if keepbranch: - repo.ui.setconfig('ui', 'allowemptycommit', True) - # Commit might fail if unresolved files exist - if date is None: - date = ctx.date() - newnode = repo.commit(text=commitmsg, user=ctx.user(), - date=date, extra=extra, editor=editor) - finally: - repo.ui.restoreconfig(backup) + targetphase = max(ctx.phase(), phases.draft) + overrides = {('phases', 'new-commit'): targetphase} + with repo.ui.configoverride(overrides, 'rebase'): + if keepbranch: + repo.ui.setconfig('ui', 'allowemptycommit', True) + # Commit might fail if unresolved files exist + if date is None: + date = ctx.date() + newnode = repo.commit(text=commitmsg, user=ctx.user(), + date=date, extra=extra, editor=editor) - repo.dirstate.setbranch(repo[newnode].branch()) - dsguard.close() - return newnode - finally: - release(dsguard) + repo.dirstate.setbranch(repo[newnode].branch()) + return newnode def rebasenode(repo, rev, p1, base, state, collapse, target): 'Rebase a single revision rev on top of p1 using base as merge ancestor' @@ -1061,9 +1128,9 @@ def clearcollapsemsg(repo): 'Remove collapse message file' - util.unlinkpath(repo.join("last-message.txt"), ignoremissing=True) + repo.vfs.unlinkpath("last-message.txt", ignoremissing=True) -def restorecollapsemsg(repo): +def restorecollapsemsg(repo, isabort): 'Restore previously stored collapse message' try: f = repo.vfs("last-message.txt") @@ -1072,38 +1139,17 @@ except IOError as err: if err.errno != errno.ENOENT: raise - raise error.Abort(_('no rebase in progress')) + if isabort: + # Oh well, just abort like normal + collapsemsg = '' + else: + raise error.Abort(_('missing .hg/last-message.txt for rebase')) return collapsemsg -def storestatus(repo, originalwd, target, state, collapse, keep, keepbranches, - external, activebookmark): - 'Store the current status to allow recovery' - f = repo.vfs("rebasestate", "w") - f.write(repo[originalwd].hex() + '\n') - f.write(repo[target].hex() + '\n') - f.write(repo[external].hex() + '\n') - f.write('%d\n' % int(collapse)) - f.write('%d\n' % int(keep)) - f.write('%d\n' % int(keepbranches)) - f.write('%s\n' % (activebookmark or '')) - for d, v in state.iteritems(): - oldrev = repo[d].hex() - if v >= 0: - newrev = repo[v].hex() - elif v == revtodo: - # To maintain format compatibility, we have to use nullid. - # Please do remove this special case when upgrading the format. - newrev = hex(nullid) - else: - newrev = v - f.write("%s:%s\n" % (oldrev, newrev)) - f.close() - repo.ui.debug('rebase status stored\n') - def clearstatus(repo): 'Remove the status files' _clearrebasesetvisibiliy(repo) - util.unlinkpath(repo.join("rebasestate"), ignoremissing=True) + repo.vfs.unlinkpath("rebasestate", ignoremissing=True) def needupdate(repo, state): '''check whether we should `update --clean` away from a merge, or if @@ -1155,8 +1201,11 @@ if rebased: strippoints = [ c.node() for c in repo.set('roots(%ld)', rebased)] - shouldupdate = len([ - c.node() for c in repo.set('. & (%ld)', rebased)]) > 0 + + updateifonnodes = set(rebased) + updateifonnodes.add(target) + updateifonnodes.add(originalwd) + shouldupdate = repo['.'].rev() in updateifonnodes # Update away from the rebase if necessary if shouldupdate or needupdate(repo, state): @@ -1183,7 +1232,8 @@ dest: context rebaseset: set of rev ''' - _setrebasesetvisibility(repo, rebaseset) + originalwd = repo['.'].rev() + _setrebasesetvisibility(repo, set(rebaseset) | set([originalwd])) # This check isn't strictly necessary, since mq detects commits over an # applied patch. But it prevents messing up the working directory when @@ -1203,7 +1253,12 @@ if commonbase == root: raise error.Abort(_('source is ancestor of destination')) if commonbase == dest: - samebranch = root.branch() == dest.branch() + wctx = repo[None] + if dest == wctx.p1(): + # when rebasing to '.', it will use the current wd branch name + samebranch = root.branch() == wctx.branch() + else: + samebranch = root.branch() == dest.branch() if not collapse and samebranch and root in dest.children(): repo.ui.debug('source is a child of destination\n') return None @@ -1268,7 +1323,7 @@ state[r] = revpruned else: state[r] = revprecursor - return repo['.'].rev(), dest.rev(), state + return originalwd, dest.rev(), state def clearrebased(ui, repo, state, skipped, collapsedas=None): """dispose of rebased revision at the end of the rebase @@ -1307,6 +1362,11 @@ 'Call rebase after pull if the latter has been invoked with --rebase' ret = None if opts.get('rebase'): + if ui.configbool('commands', 'rebase.requiredest'): + msg = _('rebase destination required by configuration') + hint = _('use hg pull followed by hg rebase -d DEST') + raise error.Abort(msg, hint=hint) + wlock = lock = None try: wlock = repo.wlock() @@ -1367,9 +1427,8 @@ """store the currently rebased set on the repo object This is used by another function to prevent rebased revision to because - hidden (see issue4505)""" + hidden (see issue4504)""" repo = repo.unfiltered() - revs = set(revs) repo._rebaseset = revs # invalidate cache if visibility changes hiddens = repo.filteredrevcache.get('visible', set()) @@ -1383,7 +1442,7 @@ del repo._rebaseset def _rebasedvisible(orig, repo): - """ensure rebased revs stay visible (see issue4505)""" + """ensure rebased revs stay visible (see issue4504)""" blockers = orig(repo) blockers.update(getattr(repo, '_rebaseset', ())) return blockers
--- a/hgext/record.py Tue Apr 18 11:22:42 2017 -0400 +++ b/hgext/record.py Tue Apr 18 12:24:34 2017 -0400 @@ -68,12 +68,9 @@ 'commit') opts["interactive"] = True - backup = ui.backupconfig('experimental', 'crecord') - try: - ui.setconfig('experimental', 'crecord', False, 'record') + overrides = {('experimental', 'crecord'): False} + with ui.configoverride(overrides, 'record'): return commands.commit(ui, repo, *pats, **opts) - finally: - ui.restoreconfig(backup) def qrefresh(origfn, ui, repo, *pats, **opts): if not opts['interactive']: @@ -117,13 +114,10 @@ opts['checkname'] = False mq.new(ui, repo, patch, *pats, **opts) - backup = ui.backupconfig('experimental', 'crecord') - try: - ui.setconfig('experimental', 'crecord', False, 'record') + overrides = {('experimental', 'crecord'): False} + with ui.configoverride(overrides, 'record'): cmdutil.dorecord(ui, repo, committomq, cmdsuggest, False, cmdutil.recordfilter, *pats, **opts) - finally: - ui.restoreconfig(backup) def qnew(origfn, ui, repo, patch, *args, **opts): if opts['interactive']:
--- a/hgext/schemes.py Tue Apr 18 11:22:42 2017 -0400 +++ b/hgext/schemes.py Tue Apr 18 12:24:34 2017 -0400 @@ -63,6 +63,7 @@ # leave the attribute unspecified. testedwith = 'ships-with-hg-core' +_partre = re.compile(br'\{(\d+)\}') class ShortRepository(object): def __init__(self, url, scheme, templater): @@ -70,7 +71,7 @@ self.templater = templater self.url = url try: - self.parts = max(map(int, re.findall(r'\{(\d+)\}', self.url))) + self.parts = max(map(int, _partre.findall(self.url))) except ValueError: self.parts = 0
--- a/hgext/share.py Tue Apr 18 11:22:42 2017 -0400 +++ b/hgext/share.py Tue Apr 18 12:24:34 2017 -0400 @@ -48,6 +48,7 @@ error, extensions, hg, + txnutil, util, ) @@ -64,10 +65,14 @@ @command('share', [('U', 'noupdate', None, _('do not create a working directory')), - ('B', 'bookmarks', None, _('also share bookmarks'))], + ('B', 'bookmarks', None, _('also share bookmarks')), + ('', 'relative', None, _('point to source using a relative path ' + '(EXPERIMENTAL)')), + ], _('[-U] [-B] SOURCE [DEST]'), norepo=True) -def share(ui, source, dest=None, noupdate=False, bookmarks=False): +def share(ui, source, dest=None, noupdate=False, bookmarks=False, + relative=False): """create a new shared repository Initialize a new repository and working directory that shares its @@ -86,7 +91,7 @@ """ return hg.share(ui, source, dest=dest, update=not noupdate, - bookmarks=bookmarks) + bookmarks=bookmarks, relative=relative) @command('unshare', [], '') def unshare(ui, repo): @@ -108,10 +113,11 @@ destlock = hg.copystore(ui, repo, repo.path) - sharefile = repo.join('sharedpath') + sharefile = repo.vfs.join('sharedpath') util.rename(sharefile, sharefile + '.old') - repo.requirements.discard('sharedpath') + repo.requirements.discard('shared') + repo.requirements.discard('relshared') repo._writerequirements() finally: destlock and destlock.release() @@ -171,7 +177,28 @@ if _hassharedbookmarks(repo): srcrepo = _getsrcrepo(repo) if srcrepo is not None: + # just orig(srcrepo) doesn't work as expected, because + # HG_PENDING refers repo.root. + try: + fp, pending = txnutil.trypending(repo.root, repo.vfs, + 'bookmarks') + if pending: + # only in this case, bookmark information in repo + # is up-to-date. + return fp + fp.close() + except IOError as inst: + if inst.errno != errno.ENOENT: + raise + + # otherwise, we should read bookmarks from srcrepo, + # because .hg/bookmarks in srcrepo might be already + # changed via another sharing repo repo = srcrepo + + # TODO: Pending changes in repo are still invisible in + # srcrepo, because bookmarks.pending is written only into repo. + # See also https://www.mercurial-scm.org/wiki/SharedRepository return orig(repo) def recordchange(orig, self, tr):
--- a/hgext/shelve.py Tue Apr 18 11:22:42 2017 -0400 +++ b/hgext/shelve.py Tue Apr 18 12:24:34 2017 -0400 @@ -28,6 +28,7 @@ from mercurial.i18n import _ from mercurial import ( + bookmarks, bundle2, bundlerepo, changegroup, @@ -46,6 +47,7 @@ scmutil, templatefilters, util, + vfs as vfsmod, ) from . import ( @@ -62,7 +64,7 @@ backupdir = 'shelve-backup' shelvedir = 'shelved' -shelvefileextensions = ['hg', 'patch'] +shelvefileextensions = ['hg', 'patch', 'oshelve'] # universal extension is present in all types of shelves patchextension = 'patch' @@ -78,8 +80,8 @@ def __init__(self, repo, name, filetype=None): self.repo = repo self.name = name - self.vfs = scmutil.vfs(repo.join(shelvedir)) - self.backupvfs = scmutil.vfs(repo.join(backupdir)) + self.vfs = vfsmod.vfs(repo.vfs.join(shelvedir)) + self.backupvfs = vfsmod.vfs(repo.vfs.join(backupdir)) self.ui = self.repo.ui if filetype: self.fname = name + '.' + filetype @@ -153,6 +155,12 @@ bundle2.writebundle(self.ui, cg, self.fname, btype, self.vfs, compression=compression) + def writeobsshelveinfo(self, info): + scmutil.simplekeyvaluefile(self.vfs, self.fname).write(info) + + def readobsshelveinfo(self): + return scmutil.simplekeyvaluefile(self.vfs, self.fname).read() + class shelvedstate(object): """Handle persistence during unshelving operations. @@ -163,6 +171,8 @@ _filename = 'shelvedstate' _keep = 'keep' _nokeep = 'nokeep' + # colon is essential to differentiate from a real bookmark name + _noactivebook = ':no-active-bookmark' @classmethod def load(cls, repo): @@ -177,9 +187,10 @@ wctx = nodemod.bin(fp.readline().strip()) pendingctx = nodemod.bin(fp.readline().strip()) parents = [nodemod.bin(h) for h in fp.readline().split()] - stripnodes = [nodemod.bin(h) for h in fp.readline().split()] + nodestoremove = [nodemod.bin(h) for h in fp.readline().split()] branchtorestore = fp.readline().strip() keep = fp.readline().strip() == cls._keep + activebook = fp.readline().strip() except (ValueError, TypeError) as err: raise error.CorruptedState(str(err)) finally: @@ -191,17 +202,20 @@ obj.wctx = repo[wctx] obj.pendingctx = repo[pendingctx] obj.parents = parents - obj.stripnodes = stripnodes + obj.nodestoremove = nodestoremove obj.branchtorestore = branchtorestore obj.keep = keep + obj.activebookmark = '' + if activebook != cls._noactivebook: + obj.activebookmark = activebook except error.RepoLookupError as err: raise error.CorruptedState(str(err)) return obj @classmethod - def save(cls, repo, name, originalwctx, pendingctx, stripnodes, - branchtorestore, keep=False): + def save(cls, repo, name, originalwctx, pendingctx, nodestoremove, + branchtorestore, keep=False, activebook=''): fp = repo.vfs(cls._filename, 'wb') fp.write('%i\n' % cls._version) fp.write('%s\n' % name) @@ -210,17 +224,18 @@ fp.write('%s\n' % ' '.join([nodemod.hex(p) for p in repo.dirstate.parents()])) fp.write('%s\n' % - ' '.join([nodemod.hex(n) for n in stripnodes])) + ' '.join([nodemod.hex(n) for n in nodestoremove])) fp.write('%s\n' % branchtorestore) fp.write('%s\n' % (cls._keep if keep else cls._nokeep)) + fp.write('%s\n' % (activebook or cls._noactivebook)) fp.close() @classmethod def clear(cls, repo): - util.unlinkpath(repo.join(cls._filename), ignoremissing=True) + repo.vfs.unlinkpath(cls._filename, ignoremissing=True) def cleanupoldbackups(repo): - vfs = scmutil.vfs(repo.join(backupdir)) + vfs = vfsmod.vfs(repo.vfs.join(backupdir)) maxbackups = repo.ui.configint('shelve', 'maxbackups', 10) hgfiles = [f for f in vfs.listdir() if f.endswith('.' + patchextension)] @@ -235,11 +250,17 @@ continue base = f[:-(1 + len(patchextension))] for ext in shelvefileextensions: - try: - vfs.unlink(base + '.' + ext) - except OSError as err: - if err.errno != errno.ENOENT: - raise + vfs.tryunlink(base + '.' + ext) + +def _backupactivebookmark(repo): + activebookmark = repo._activebookmark + if activebookmark: + bookmarks.deactivate(repo) + return activebookmark + +def _restoreactivebookmark(repo, mark): + if mark: + bookmarks.activate(repo, mark) def _aborttransaction(repo): '''Abort current transaction for shelve/unshelve, but keep dirstate @@ -313,17 +334,16 @@ hasmq = util.safehasattr(repo, 'mq') if hasmq: saved, repo.mq.checkapplied = repo.mq.checkapplied, False - backup = repo.ui.backupconfig('phases', 'new-commit') + overrides = {('phases', 'new-commit'): phases.secret} try: - repo.ui.setconfig('phases', 'new-commit', phases.secret) editor_ = False if editor: editor_ = cmdutil.getcommiteditor(editform='shelve.shelve', **opts) - return repo.commit(message, shelveuser, opts.get('date'), match, - editor=editor_, extra=extra) + with repo.ui.configoverride(overrides): + return repo.commit(message, shelveuser, opts.get('date'), + match, editor=editor_, extra=extra) finally: - repo.ui.restoreconfig(backup) if hasmq: repo.mq.checkapplied = saved @@ -375,7 +395,7 @@ if not opts.get('message'): opts['message'] = desc - lock = tr = None + lock = tr = activebookmark = None try: lock = repo.lock() @@ -388,6 +408,7 @@ not opts.get('addremove', False)) name = getshelvename(repo, parent, opts) + activebookmark = _backupactivebookmark(repo) extra = {} if includeunknown: _includeunknownfiles(repo, pats, opts, extra) @@ -402,7 +423,8 @@ node = cmdutil.commit(ui, repo, commitfunc, pats, opts) else: node = cmdutil.dorecord(ui, repo, commitfunc, None, - False, cmdutil.recordfilter, *pats, **opts) + False, cmdutil.recordfilter, *pats, + **opts) if not node: _nothingtoshelvemessaging(ui, repo, pats, opts) return 1 @@ -418,6 +440,7 @@ _finishshelve(repo) finally: + _restoreactivebookmark(repo, activebookmark) lockmod.release(tr, lock) def _isbareshelve(pats, opts): @@ -485,6 +508,7 @@ if not ui.plain(): width = ui.termwidth() namelabel = 'shelve.newest' + ui.pager('shelve') for mtime, name in listshelves(repo): sname = util.split(name)[1] if pats and sname not in pats: @@ -549,19 +573,17 @@ try: checkparents(repo, state) - util.rename(repo.join('unshelverebasestate'), - repo.join('rebasestate')) + repo.vfs.rename('unshelverebasestate', 'rebasestate') try: rebase.rebase(ui, repo, **{ 'abort' : True }) except Exception: - util.rename(repo.join('rebasestate'), - repo.join('unshelverebasestate')) + repo.vfs.rename('rebasestate', 'unshelverebasestate') raise mergefiles(ui, repo, state.wctx, state.pendingctx) - repair.strip(ui, repo, state.stripnodes, backup=False, + repair.strip(ui, repo, state.nodestoremove, backup=False, topic='shelve') finally: shelvedstate.clear(repo) @@ -570,9 +592,7 @@ def mergefiles(ui, repo, wctx, shelvectx): """updates to wctx and merges the changes from shelvectx into the dirstate.""" - oldquiet = ui.quiet - try: - ui.quiet = True + with ui.configoverride({('ui', 'quiet'): True}): hg.update(repo, wctx.node()) files = [] files.extend(shelvectx.files()) @@ -587,8 +607,6 @@ *pathtofiles(repo, files), **{'no_backup': True}) ui.popbuffer() - finally: - ui.quiet = oldquiet def restorebranch(ui, repo, branchtorestore): if branchtorestore and branchtorestore != repo.dirstate.branch(): @@ -617,15 +635,13 @@ _("unresolved conflicts, can't continue"), hint=_("see 'hg resolve', then 'hg unshelve --continue'")) - util.rename(repo.join('unshelverebasestate'), - repo.join('rebasestate')) + repo.vfs.rename('unshelverebasestate', 'rebasestate') try: rebase.rebase(ui, repo, **{ 'continue' : True }) except Exception: - util.rename(repo.join('rebasestate'), - repo.join('unshelverebasestate')) + repo.vfs.rename('rebasestate', 'unshelverebasestate') raise shelvectx = repo['tip'] @@ -634,12 +650,14 @@ shelvectx = state.pendingctx else: # only strip the shelvectx if the rebase produced it - state.stripnodes.append(shelvectx.node()) + state.nodestoremove.append(shelvectx.node()) mergefiles(ui, repo, state.wctx, shelvectx) restorebranch(ui, repo, state.branchtorestore) - repair.strip(ui, repo, state.stripnodes, backup=False, topic='shelve') + repair.strip(ui, repo, state.nodestoremove, backup=False, + topic='shelve') + _restoreactivebookmark(repo, state.activebookmark) shelvedstate.clear(repo) unshelvecleanup(ui, repo, state.name, opts) ui.status(_("unshelve of '%s' complete\n") % state.name) @@ -659,21 +677,21 @@ tempopts = {} tempopts['message'] = "pending changes temporary commit" tempopts['date'] = opts.get('date') - ui.quiet = True - node = cmdutil.commit(ui, repo, commitfunc, [], tempopts) + with ui.configoverride({('ui', 'quiet'): True}): + node = cmdutil.commit(ui, repo, commitfunc, [], tempopts) tmpwctx = repo[node] return tmpwctx, addedbefore -def _unshelverestorecommit(ui, repo, basename, oldquiet): +def _unshelverestorecommit(ui, repo, basename): """Recreate commit in the repository during the unshelve""" - ui.quiet = True - shelvedfile(repo, basename, 'hg').applybundle() - shelvectx = repo['tip'] - ui.quiet = oldquiet + with ui.configoverride({('ui', 'quiet'): True}): + shelvedfile(repo, basename, 'hg').applybundle() + shelvectx = repo['tip'] return repo, shelvectx def _rebaserestoredcommit(ui, repo, opts, tr, oldtiprev, basename, pctx, - tmpwctx, shelvectx, branchtorestore): + tmpwctx, shelvectx, branchtorestore, + activebookmark): """Rebase restored commit from its original location to a destination""" # If the shelve is not immediately on top of the commit # we'll be merging with, rebase it to be on top. @@ -691,13 +709,12 @@ except error.InterventionRequired: tr.close() - stripnodes = [repo.changelog.node(rev) - for rev in xrange(oldtiprev, len(repo))] - shelvedstate.save(repo, basename, pctx, tmpwctx, stripnodes, - branchtorestore, opts.get('keep')) + nodestoremove = [repo.changelog.node(rev) + for rev in xrange(oldtiprev, len(repo))] + shelvedstate.save(repo, basename, pctx, tmpwctx, nodestoremove, + branchtorestore, opts.get('keep'), activebookmark) - util.rename(repo.join('rebasestate'), - repo.join('unshelverebasestate')) + repo.vfs.rename('rebasestate', 'unshelverebasestate') raise error.InterventionRequired( _("unresolved conflicts (see 'hg resolve', then " "'hg unshelve --continue')")) @@ -721,7 +738,8 @@ toforget = (addedafter & shelveunknown) - addedbefore repo[None].forget(toforget) -def _finishunshelve(repo, oldtiprev, tr): +def _finishunshelve(repo, oldtiprev, tr, activebookmark): + _restoreactivebookmark(repo, activebookmark) # The transaction aborting will strip all the commits for us, # but it doesn't update the inmemory structures, so addchangegroup # hooks still fire and try to operate on the missing commits. @@ -747,10 +765,12 @@ _('continue an incomplete unshelve operation')), ('k', 'keep', None, _('keep shelve after unshelving')), + ('n', 'name', '', + _('restore shelved change with given name'), _('NAME')), ('t', 'tool', '', _('specify merge tool')), ('', 'date', '', _('set date for temporary commits (DEPRECATED)'), _('DATE'))], - _('hg unshelve [SHELVED]')) + _('hg unshelve [[-n] SHELVED]')) def unshelve(ui, repo, *shelved, **opts): """restore a shelved change to the working directory @@ -795,6 +815,9 @@ continuef = opts.get('continue') if not abortf and not continuef: cmdutil.checkunfinished(repo) + shelved = list(shelved) + if opts.get("name"): + shelved.append(opts["name"]) if abortf or continuef: if abortf and continuef: @@ -846,13 +869,9 @@ if not shelvedfile(repo, basename, patchextension).exists(): raise error.Abort(_("shelved change '%s' not found") % basename) - oldquiet = ui.quiet lock = tr = None - forcemerge = ui.backupconfig('ui', 'forcemerge') try: - ui.setconfig('ui', 'forcemerge', opts.get('tool', ''), 'unshelve') lock = repo.lock() - tr = repo.transaction('unshelve', report=lambda x: None) oldtiprev = len(repo) @@ -864,31 +883,32 @@ # and shelvectx is the unshelved changes. Then we merge it all down # to the original pctx. - tmpwctx, addedbefore = _commitworkingcopychanges(ui, repo, opts, - tmpwctx) - - repo, shelvectx = _unshelverestorecommit(ui, repo, basename, oldquiet) - _checkunshelveuntrackedproblems(ui, repo, shelvectx) - branchtorestore = '' - if shelvectx.branch() != shelvectx.p1().branch(): - branchtorestore = shelvectx.branch() + activebookmark = _backupactivebookmark(repo) + overrides = {('ui', 'forcemerge'): opts.get('tool', '')} + with ui.configoverride(overrides, 'unshelve'): + tmpwctx, addedbefore = _commitworkingcopychanges(ui, repo, opts, + tmpwctx) + repo, shelvectx = _unshelverestorecommit(ui, repo, basename) + _checkunshelveuntrackedproblems(ui, repo, shelvectx) + branchtorestore = '' + if shelvectx.branch() != shelvectx.p1().branch(): + branchtorestore = shelvectx.branch() - shelvectx = _rebaserestoredcommit(ui, repo, opts, tr, oldtiprev, - basename, pctx, tmpwctx, shelvectx, - branchtorestore) - mergefiles(ui, repo, pctx, shelvectx) - restorebranch(ui, repo, branchtorestore) - _forgetunknownfiles(repo, shelvectx, addedbefore) + shelvectx = _rebaserestoredcommit(ui, repo, opts, tr, oldtiprev, + basename, pctx, tmpwctx, + shelvectx, branchtorestore, + activebookmark) + mergefiles(ui, repo, pctx, shelvectx) + restorebranch(ui, repo, branchtorestore) + _forgetunknownfiles(repo, shelvectx, addedbefore) - shelvedstate.clear(repo) - _finishunshelve(repo, oldtiprev, tr) - unshelvecleanup(ui, repo, basename, opts) + shelvedstate.clear(repo) + _finishunshelve(repo, oldtiprev, tr, activebookmark) + unshelvecleanup(ui, repo, basename, opts) finally: - ui.quiet = oldquiet if tr: tr.release() lockmod.release(lock) - ui.restoreconfig(forcemerge) @command('shelve', [('A', 'addremove', None,
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/hgext/show.py Tue Apr 18 12:24:34 2017 -0400 @@ -0,0 +1,222 @@ +# show.py - Extension implementing `hg show` +# +# Copyright 2017 Gregory Szorc <gregory.szorc@gmail.com> +# +# This software may be used and distributed according to the terms of the +# GNU General Public License version 2 or any later version. + +"""unified command to show various repository information (EXPERIMENTAL) + +This extension provides the :hg:`show` command, which provides a central +command for displaying commonly-accessed repository data and views of that +data. +""" + +from __future__ import absolute_import + +from mercurial.i18n import _ +from mercurial.node import nullrev +from mercurial import ( + cmdutil, + error, + formatter, + graphmod, + pycompat, + registrar, + revset, + revsetlang, +) + +# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for +# extensions which SHIP WITH MERCURIAL. Non-mainline extensions should +# be specifying the version(s) of Mercurial they are tested with, or +# leave the attribute unspecified. +testedwith = 'ships-with-hg-core' + +cmdtable = {} +command = cmdutil.command(cmdtable) +revsetpredicate = registrar.revsetpredicate() + +class showcmdfunc(registrar._funcregistrarbase): + """Register a function to be invoked for an `hg show <thing>`.""" + + # Used by _formatdoc(). + _docformat = '%s -- %s' + + def _extrasetup(self, name, func, fmtopic=None): + """Called with decorator arguments to register a show view. + + ``name`` is the sub-command name. + + ``func`` is the function being decorated. + + ``fmtopic`` is the topic in the style that will be rendered for + this view. + """ + func._fmtopic = fmtopic + +showview = showcmdfunc() + +@command('show', [ + # TODO: Switch this template flag to use commands.formatteropts if + # 'hg show' becomes stable before --template/-T is stable. For now, + # we are putting it here without the '(EXPERIMENTAL)' flag because it + # is an important part of the 'hg show' user experience and the entire + # 'hg show' experience is experimental. + ('T', 'template', '', ('display with template'), _('TEMPLATE')), + ], _('VIEW')) +def show(ui, repo, view=None, template=None): + """show various repository information + + A requested view of repository data is displayed. + + If no view is requested, the list of available views is shown and the + command aborts. + + .. note:: + + There are no backwards compatibility guarantees for the output of this + command. Output may change in any future Mercurial release. + + Consumers wanting stable command output should specify a template via + ``-T/--template``. + + List of available views: + """ + if ui.plain() and not template: + hint = _('invoke with -T/--template to control output format') + raise error.Abort(_('must specify a template in plain mode'), hint=hint) + + views = showview._table + + if not view: + ui.pager('show') + # TODO consider using formatter here so available views can be + # rendered to custom format. + ui.write(_('available views:\n')) + ui.write('\n') + + for name, func in sorted(views.items()): + ui.write(('%s\n') % func.__doc__) + + ui.write('\n') + raise error.Abort(_('no view requested'), + hint=_('use "hg show VIEW" to choose a view')) + + # TODO use same logic as dispatch to perform prefix matching. + if view not in views: + raise error.Abort(_('unknown view: %s') % view, + hint=_('run "hg show" to see available views')) + + template = template or 'show' + fmtopic = 'show%s' % views[view]._fmtopic + + ui.pager('show') + with ui.formatter(fmtopic, {'template': template}) as fm: + return views[view](ui, repo, fm) + +@showview('bookmarks', fmtopic='bookmarks') +def showbookmarks(ui, repo, fm): + """bookmarks and their associated changeset""" + marks = repo._bookmarks + if not len(marks): + # This is a bit hacky. Ideally, templates would have a way to + # specify an empty output, but we shouldn't corrupt JSON while + # waiting for this functionality. + if not isinstance(fm, formatter.jsonformatter): + ui.write(_('(no bookmarks set)\n')) + return + + active = repo._activebookmark + longestname = max(len(b) for b in marks) + # TODO consider exposing longest shortest(node). + + for bm, node in sorted(marks.items()): + fm.startitem() + fm.context(ctx=repo[node]) + fm.write('bookmark', '%s', bm) + fm.write('node', fm.hexfunc(node), fm.hexfunc(node)) + fm.data(active=bm == active, + longestbookmarklen=longestname) + +@revsetpredicate('_underway([commitage[, headage]])') +def underwayrevset(repo, subset, x): + args = revset.getargsdict(x, 'underway', 'commitage headage') + if 'commitage' not in args: + args['commitage'] = None + if 'headage' not in args: + args['headage'] = None + + # We assume callers of this revset add a topographical sort on the + # result. This means there is no benefit to making the revset lazy + # since the topographical sort needs to consume all revs. + # + # With this in mind, we build up the set manually instead of constructing + # a complex revset. This enables faster execution. + + # Mutable changesets (non-public) are the most important changesets + # to return. ``not public()`` will also pull in obsolete changesets if + # there is a non-obsolete changeset with obsolete ancestors. This is + # why we exclude obsolete changesets from this query. + rs = 'not public() and not obsolete()' + rsargs = [] + if args['commitage']: + rs += ' and date(%s)' + rsargs.append(revsetlang.getstring(args['commitage'], + _('commitage requires a string'))) + + mutable = repo.revs(rs, *rsargs) + relevant = revset.baseset(mutable) + + # Add parents of mutable changesets to provide context. + relevant += repo.revs('parents(%ld)', mutable) + + # We also pull in (public) heads if they a) aren't closing a branch + # b) are recent. + rs = 'head() and not closed()' + rsargs = [] + if args['headage']: + rs += ' and date(%s)' + rsargs.append(revsetlang.getstring(args['headage'], + _('headage requires a string'))) + + relevant += repo.revs(rs, *rsargs) + + # Add working directory parent. + wdirrev = repo['.'].rev() + if wdirrev != nullrev: + relevant += revset.baseset(set([wdirrev])) + + return subset & relevant + +@showview('underway', fmtopic='underway') +def showunderway(ui, repo, fm): + """changesets that aren't finished""" + # TODO support date-based limiting when calling revset. + revs = repo.revs('sort(_underway(), topo)') + + revdag = graphmod.dagwalker(repo, revs) + displayer = cmdutil.changeset_templater(ui, repo, None, None, + tmpl=fm._t.load(fm._topic), + mapfile=None, buffered=True) + + ui.setconfig('experimental', 'graphshorten', True) + cmdutil.displaygraph(ui, repo, revdag, displayer, graphmod.asciiedges) + +# Adjust the docstring of the show command so it shows all registered views. +# This is a bit hacky because it runs at the end of module load. When moved +# into core or when another extension wants to provide a view, we'll need +# to do this more robustly. +# TODO make this more robust. +def _updatedocstring(): + longest = max(map(len, showview._table.keys())) + entries = [] + for key in sorted(showview._table.keys()): + entries.append(pycompat.sysstr(' %s %s' % ( + key.ljust(longest), showview._table[key]._origdoc))) + + cmdtable['show'][0].__doc__ = pycompat.sysstr('%s\n\n%s\n ') % ( + cmdtable['show'][0].__doc__.rstrip(), + pycompat.sysstr('\n\n').join(entries)) + +_updatedocstring()
--- a/hgext/transplant.py Tue Apr 18 11:22:42 2017 -0400 +++ b/hgext/transplant.py Tue Apr 18 12:24:34 2017 -0400 @@ -28,11 +28,14 @@ merge, node as nodemod, patch, + pycompat, registrar, revlog, revset, scmutil, + smartset, util, + vfs as vfsmod, ) class TransplantError(error.Abort): @@ -58,7 +61,7 @@ self.opener = opener if not opener: - self.opener = scmutil.opener(self.path) + self.opener = vfsmod.vfs(self.path) self.transplants = {} self.dirty = False self.read() @@ -100,8 +103,8 @@ class transplanter(object): def __init__(self, ui, repo, opts): self.ui = ui - self.path = repo.join('transplant') - self.opener = scmutil.opener(self.path) + self.path = repo.vfs.join('transplant') + self.opener = vfsmod.vfs(self.path) self.transplants = transplants(self.path, 'transplants', opener=self.opener) def getcommiteditor(): @@ -197,7 +200,7 @@ patchfile = None else: fd, patchfile = tempfile.mkstemp(prefix='hg-transplant-') - fp = os.fdopen(fd, 'w') + fp = os.fdopen(fd, pycompat.sysstr('w')) gen = patch.diff(source, parent, node, opts=diffopts) for chunk in gen: fp.write(chunk) @@ -245,7 +248,7 @@ self.ui.status(_('filtering %s\n') % patchfile) user, date, msg = (changelog[1], changelog[2], changelog[4]) fd, headerfile = tempfile.mkstemp(prefix='hg-transplant-') - fp = os.fdopen(fd, 'w') + fp = os.fdopen(fd, pycompat.sysstr('w')) fp.write("# HG changeset patch\n") fp.write("# User %s\n" % user) fp.write("# Date %d %d\n" % date) @@ -258,7 +261,8 @@ environ={'HGUSER': changelog[1], 'HGREVISION': nodemod.hex(node), }, - onerr=error.Abort, errprefix=_('filter failed')) + onerr=error.Abort, errprefix=_('filter failed'), + blockedtag='transplant_filter') user, date, msg = self.parselog(file(headerfile))[1:4] finally: os.unlink(headerfile) @@ -722,7 +726,7 @@ s = revset.getset(repo, subset, x) else: s = subset - return revset.baseset([r for r in s if + return smartset.baseset([r for r in s if repo[r].extra().get('transplant_source')]) templatekeyword = registrar.templatekeyword()
--- a/hgext/win32text.py Tue Apr 18 11:22:42 2017 -0400 +++ b/hgext/win32text.py Tue Apr 18 12:24:34 2017 -0400 @@ -74,7 +74,7 @@ 'and does not need EOL conversion by the win32text plugin.\n' 'Before your next commit, please reconsider your ' 'encode/decode settings in \nMercurial.ini or %s.\n') % - (filename, newlinestr[newline], repo.join('hgrc'))) + (filename, newlinestr[newline], repo.vfs.join('hgrc'))) def dumbdecode(s, cmd, **kwargs): checknewline(s, '\r\n', **kwargs)
--- a/hgext/zeroconf/__init__.py Tue Apr 18 11:22:42 2017 -0400 +++ b/hgext/zeroconf/__init__.py Tue Apr 18 12:24:34 2017 -0400 @@ -64,7 +64,9 @@ # Generic method, sometimes gives useless results try: dumbip = socket.gethostbyaddr(socket.gethostname())[2][0] - if not dumbip.startswith('127.') and ':' not in dumbip: + if ':' in dumbip: + dumbip = '127.0.0.1' + if not dumbip.startswith('127.'): return dumbip except (socket.gaierror, socket.herror): dumbip = '127.0.0.1'
--- a/mercurial/__init__.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/__init__.py Tue Apr 18 12:24:34 2017 -0400 @@ -68,7 +68,7 @@ # indicates the type of module. So just assume what we found # is OK (even though it could be a pure Python module). except ImportError: - if modulepolicy == 'c': + if modulepolicy == b'c': raise zl = ziploader('mercurial', 'pure') mod = zl.load_module(name) @@ -106,7 +106,7 @@ 'version should exist' % name) except ImportError: - if modulepolicy == 'c': + if modulepolicy == b'c': raise # Could not load the C extension and pure Python is allowed. So @@ -137,6 +137,9 @@ # Only handle Mercurial-related modules. if not fullname.startswith(('mercurial.', 'hgext.', 'hgext3rd.')): return None + # zstd is already dual-version clean, don't try and mangle it + if fullname.startswith('mercurial.zstd'): + return None # This assumes Python 3 doesn't support loading C modules. if fullname in _dualmodules: @@ -280,7 +283,8 @@ continue r, c = t.start l = (b'; from mercurial.pycompat import ' - b'delattr, getattr, hasattr, setattr, xrange\n') + b'delattr, getattr, hasattr, setattr, xrange, ' + b'open, unicode\n') for u in tokenize.tokenize(io.BytesIO(l).readline): if u.type in (tokenize.ENCODING, token.ENDMARKER): continue @@ -307,17 +311,10 @@ if argidx is not None: _ensureunicode(argidx) - # Bare open call (not an attribute on something else), the - # second argument (mode) must be a string, not bytes - elif fn == 'open' and not _isop(i - 1, '.'): - arg1idx = _findargnofcall(1) - if arg1idx is not None: - _ensureunicode(arg1idx) - - # It changes iteritems to items as iteritems is not + # It changes iteritems/values to items/values as they are not # present in Python 3 world. - elif fn == 'iteritems': - yield t._replace(string='items') + elif fn in ('iteritems', 'itervalues'): + yield t._replace(string=fn[4:]) continue # Emit unmodified token. @@ -327,7 +324,7 @@ # ``replacetoken`` or any mechanism that changes semantics of module # loading is changed. Otherwise cached bytecode may get loaded without # the new transformation mechanisms applied. - BYTECODEHEADER = b'HG\x00\x06' + BYTECODEHEADER = b'HG\x00\x0a' class hgloader(importlib.machinery.SourceFileLoader): """Custom module loader that transforms source code.
--- a/mercurial/ancestor.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/ancestor.py Tue Apr 18 12:24:34 2017 -0400 @@ -296,6 +296,8 @@ except StopIteration: return False + __bool__ = __nonzero__ + def __iter__(self): """Generate the ancestors of _initrevs in reverse topological order.
--- a/mercurial/archival.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/archival.py Tue Apr 18 12:24:34 2017 -0400 @@ -22,8 +22,8 @@ encoding, error, match as matchmod, - scmutil, util, + vfs as vfsmod, ) stringio = util.stringio @@ -249,7 +249,7 @@ def __init__(self, name, mtime): self.basedir = name - self.opener = scmutil.opener(self.basedir) + self.opener = vfsmod.vfs(self.basedir) def addfile(self, name, mode, islink, data): if islink: @@ -331,7 +331,7 @@ for subpath in sorted(ctx.substate): sub = ctx.workingsub(subpath) submatch = matchmod.subdirmatcher(subpath, matchfn) - total += sub.archive(archiver, prefix, submatch) + total += sub.archive(archiver, prefix, submatch, decode) if total == 0: raise error.Abort(_('no files match the archive pattern'))
--- a/mercurial/bdiff_module.c Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/bdiff_module.c Tue Apr 18 12:24:34 2017 -0400 @@ -158,7 +158,7 @@ r = PyBytes_AsString(s); rlen = PyBytes_Size(s); - w = (char *)malloc(rlen ? rlen : 1); + w = (char *)PyMem_Malloc(rlen ? rlen : 1); if (!w) goto nomem; @@ -178,7 +178,7 @@ result = PyBytes_FromStringAndSize(w, wlen); nomem: - free(w); + PyMem_Free(w); return result ? result : PyErr_NoMemory(); }
--- a/mercurial/bookmarks.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/bookmarks.py Tue Apr 18 12:24:34 2017 -0400 @@ -19,6 +19,7 @@ error, lock as lockmod, obsolete, + txnutil, util, ) @@ -29,17 +30,8 @@ bookmarks or the committed ones. Other extensions (like share) may need to tweak this behavior further. """ - bkfile = None - if 'HG_PENDING' in encoding.environ: - try: - bkfile = repo.vfs('bookmarks.pending') - except IOError as inst: - if inst.errno != errno.ENOENT: - raise - if bkfile is None: - bkfile = repo.vfs('bookmarks') - return bkfile - + fp, pending = txnutil.trypending(repo.root, repo.vfs, 'bookmarks') + return fp class bmstore(dict): """Storage for bookmarks. @@ -139,11 +131,7 @@ finally: f.close() else: - try: - self._repo.vfs.unlink('bookmarks.current') - except OSError as inst: - if inst.errno != errno.ENOENT: - raise + self._repo.vfs.tryunlink('bookmarks.current') self._aclean = True def _write(self, fp):
--- a/mercurial/branchmap.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/branchmap.py Tue Apr 18 12:24:34 2017 -0400 @@ -7,9 +7,7 @@ from __future__ import absolute_import -import array import struct -import time from .node import ( bin, @@ -21,12 +19,12 @@ encoding, error, scmutil, + util, ) -array = array.array calcsize = struct.calcsize -pack = struct.pack -unpack = struct.unpack +pack_into = struct.pack_into +unpack_from = struct.unpack_from def _filename(repo): """name of a branchcache file for a given repo or repoview""" @@ -233,7 +231,7 @@ def write(self, repo): try: f = repo.vfs(_filename(repo), "w", atomictemp=True) - cachekey = [hex(self.tipnode), str(self.tiprev)] + cachekey = [hex(self.tipnode), '%d' % self.tiprev] if self.filteredhash is not None: cachekey.append(hex(self.filteredhash)) f.write(" ".join(cachekey) + '\n') @@ -261,7 +259,7 @@ missing heads, and a generator of nodes that are strictly a superset of heads missing, this function updates self to be correct. """ - starttime = time.time() + starttime = util.timer() cl = repo.changelog # collect new branch entries newbranches = {} @@ -314,7 +312,7 @@ self.tiprev = tiprev self.filteredhash = scmutil.filteredhash(repo, self.tiprev) - duration = time.time() - starttime + duration = util.timer() - starttime repo.ui.log('branchcache', 'updated %s branch cache in %.4f seconds\n', repo.filtername, duration) @@ -357,12 +355,14 @@ assert repo.filtername is None self._repo = repo self._names = [] # branch names in local encoding with static index - self._rbcrevs = array('c') # structs of type _rbcrecfmt + self._rbcrevs = bytearray() self._rbcsnameslen = 0 # length of names read at _rbcsnameslen try: bndata = repo.vfs.read(_rbcnames) self._rbcsnameslen = len(bndata) # for verification before writing - self._names = [encoding.tolocal(bn) for bn in bndata.split('\0')] + if bndata: + self._names = [encoding.tolocal(bn) + for bn in bndata.split('\0')] except (IOError, OSError): if readonly: # don't try to use cache - fall back to the slow path @@ -371,7 +371,7 @@ if self._names: try: data = repo.vfs.read(_rbcrevs) - self._rbcrevs.fromstring(data) + self._rbcrevs[:] = data except (IOError, OSError) as inst: repo.ui.debug("couldn't read revision branch cache: %s\n" % inst) @@ -390,8 +390,7 @@ self._rbcnamescount = 0 self._namesreverse.clear() self._rbcrevslen = len(self._repo.changelog) - self._rbcrevs = array('c') - self._rbcrevs.fromstring('\0' * (self._rbcrevslen * _rbcrecsize)) + self._rbcrevs = bytearray(self._rbcrevslen * _rbcrecsize) def branchinfo(self, rev): """Return branch name and close flag for rev, using and updating @@ -409,8 +408,8 @@ # fast path: extract data from cache, use it if node is matching reponode = changelog.node(rev)[:_rbcnodelen] - cachenode, branchidx = unpack( - _rbcrecfmt, buffer(self._rbcrevs, rbcrevidx, _rbcrecsize)) + cachenode, branchidx = unpack_from( + _rbcrecfmt, util.buffer(self._rbcrevs), rbcrevidx) close = bool(branchidx & _rbccloseflag) if close: branchidx &= _rbcbranchidxmask @@ -427,7 +426,7 @@ else: # rev/node map has changed, invalidate the cache from here up self._repo.ui.debug("history modification detected - truncating " - "revision branch cache to revision %s\n" % rev) + "revision branch cache to revision %d\n" % rev) truncate = rbcrevidx + _rbcrecsize del self._rbcrevs[truncate:] self._rbcrevslen = min(self._rbcrevslen, truncate) @@ -453,14 +452,14 @@ def _setcachedata(self, rev, node, branchidx): """Writes the node's branch data to the in-memory cache data.""" + if rev == nullrev: + return rbcrevidx = rev * _rbcrecsize - rec = array('c') - rec.fromstring(pack(_rbcrecfmt, node, branchidx)) if len(self._rbcrevs) < rbcrevidx + _rbcrecsize: self._rbcrevs.extend('\0' * (len(self._repo.changelog) * _rbcrecsize - len(self._rbcrevs))) - self._rbcrevs[rbcrevidx:rbcrevidx + _rbcrecsize] = rec + pack_into(_rbcrecfmt, self._rbcrevs, rbcrevidx, node, branchidx) self._rbcrevslen = min(self._rbcrevslen, rev) tr = self._repo.currenttransaction() @@ -504,7 +503,7 @@ len(self._rbcrevs) // _rbcrecsize) f = repo.vfs.open(_rbcrevs, 'ab') if f.tell() != start: - repo.ui.debug("truncating %s to %s\n" % (_rbcrevs, start)) + repo.ui.debug("truncating %s to %d\n" % (_rbcrevs, start)) f.seek(start) if f.tell() != start: start = 0
--- a/mercurial/bundle2.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/bundle2.py Tue Apr 18 12:24:34 2017 -0400 @@ -271,6 +271,8 @@ def __nonzero__(self): return bool(self._sequences) + __bool__ = __nonzero__ + class bundleoperation(object): """an object that represents a single bundling process @@ -320,9 +322,6 @@ It iterates over each part then searches for and uses the proper handling code to process the part. Parts are processed in order. - This is very early version of this function that will be strongly reworked - before final usage. - Unknown Mandatory part will abort the process. It is temporarily possible to provide a prebuilt bundleoperation to the @@ -355,9 +354,19 @@ for nbpart, part in iterparts: _processpart(op, part) except Exception as exc: - for nbpart, part in iterparts: - # consume the bundle content - part.seek(0, 2) + # Any exceptions seeking to the end of the bundle at this point are + # almost certainly related to the underlying stream being bad. + # And, chances are that the exception we're handling is related to + # getting in that bad state. So, we swallow the seeking error and + # re-raise the original error. + seekerror = False + try: + for nbpart, part in iterparts: + # consume the bundle content + part.seek(0, 2) + except Exception: + seekerror = True + # Small hack to let caller code distinguish exceptions from bundle2 # processing from processing the old format. This is mostly # needed to handle different return codes to unbundle according to the @@ -371,7 +380,13 @@ replycaps = op.reply.capabilities exc._replycaps = replycaps exc._bundle2salvagedoutput = salvaged - raise + + # Re-raising from a variable loses the original stack. So only use + # that form if we need to. + if seekerror: + raise exc + else: + raise finally: repo.ui.debug('bundle2-input-bundle: %i parts total\n' % nbpart) @@ -618,41 +633,27 @@ def __init__(self, fp): self._fp = fp - self._seekable = (util.safehasattr(fp, 'seek') and - util.safehasattr(fp, 'tell')) def _unpack(self, format): - """unpack this struct format from the stream""" + """unpack this struct format from the stream + + This method is meant for internal usage by the bundle2 protocol only. + They directly manipulate the low level stream including bundle2 level + instruction. + + Do not use it to implement higher-level logic or methods.""" data = self._readexact(struct.calcsize(format)) return _unpack(format, data) def _readexact(self, size): - """read exactly <size> bytes from the stream""" - return changegroup.readexactly(self._fp, size) - - def seek(self, offset, whence=0): - """move the underlying file pointer""" - if self._seekable: - return self._fp.seek(offset, whence) - else: - raise NotImplementedError(_('File pointer is not seekable')) + """read exactly <size> bytes from the stream - def tell(self): - """return the file offset, or None if file is not seekable""" - if self._seekable: - try: - return self._fp.tell() - except IOError as e: - if e.errno == errno.ESPIPE: - self._seekable = False - else: - raise - return None + This method is meant for internal usage by the bundle2 protocol only. + They directly manipulate the low level stream including bundle2 level + instruction. - def close(self): - """close underlying file""" - if util.safehasattr(self._fp, 'close'): - return self._fp.close() + Do not use it to implement higher-level logic or methods.""" + return changegroup.readexactly(self._fp, size) def getunbundler(ui, fp, magicstring=None): """return a valid unbundler object for a given magicstring""" @@ -806,6 +807,11 @@ self.params # load params return self._compressed + def close(self): + """close underlying file""" + if util.safehasattr(self._fp, 'close'): + return self._fp.close() + formatmap = {'20': unbundle20} b2streamparamsmap = {} @@ -856,7 +862,7 @@ self._seenparams = set() for pname, __ in self._mandatoryparams + self._advisoryparams: if pname in self._seenparams: - raise RuntimeError('duplicated params: %s' % pname) + raise error.ProgrammingError('duplicated params: %s' % pname) self._seenparams.add(pname) # status of the part's generation: # - None: not started, @@ -865,6 +871,11 @@ self._generated = None self.mandatory = mandatory + def __repr__(self): + cls = "%s.%s" % (self.__class__.__module__, self.__class__.__name__) + return ('<%s object at %x; id: %s; type: %s; mandatory: %s>' + % (cls, id(self), self.id, self.type, self.mandatory)) + def copy(self): """return a copy of the part @@ -896,6 +907,13 @@ return tuple(self._advisoryparams) def addparam(self, name, value='', mandatory=True): + """add a parameter to the part + + If 'mandatory' is set to True, the remote handler must claim support + for this parameter or the unbundling will be aborted. + + The 'name' and 'value' cannot exceed 255 bytes each. + """ if self._generated is not None: raise error.ReadOnlyPartError('part is being generated') if name in self._seenparams: @@ -909,7 +927,7 @@ # methods used to generates the bundle2 stream def getchunks(self, ui): if self._generated is not None: - raise RuntimeError('part can only be consumed once') + raise error.ProgrammingError('part can only be consumed once') self._generated = False if ui.debugflag: @@ -1078,7 +1096,7 @@ @property def repo(self): - raise RuntimeError('no repo access from stream interruption') + raise error.ProgrammingError('no repo access from stream interruption') def gettransaction(self): raise TransactionUnavailable('no repo access from stream interruption') @@ -1088,6 +1106,8 @@ def __init__(self, ui, header, fp): super(unbundlepart, self).__init__(fp) + self._seekable = (util.safehasattr(fp, 'seek') and + util.safehasattr(fp, 'tell')) self.ui = ui # unbundle state attr self._headerdata = header @@ -1135,11 +1155,11 @@ '''seek to specified chunk and start yielding data''' if len(self._chunkindex) == 0: assert chunknum == 0, 'Must start with chunk 0' - self._chunkindex.append((0, super(unbundlepart, self).tell())) + self._chunkindex.append((0, self._tellfp())) else: assert chunknum < len(self._chunkindex), \ 'Unknown chunk %d' % chunknum - super(unbundlepart, self).seek(self._chunkindex[chunknum][1]) + self._seekfp(self._chunkindex[chunknum][1]) pos = self._chunkindex[chunknum][0] payloadsize = self._unpack(_fpayloadsize)[0] @@ -1157,8 +1177,7 @@ chunknum += 1 pos += payloadsize if chunknum == len(self._chunkindex): - self._chunkindex.append((pos, - super(unbundlepart, self).tell())) + self._chunkindex.append((pos, self._tellfp())) yield result payloadsize = self._unpack(_fpayloadsize)[0] indebug(self.ui, 'payload chunk size: %i' % payloadsize) @@ -1251,6 +1270,37 @@ raise error.Abort(_('Seek failed\n')) self._pos = newpos + def _seekfp(self, offset, whence=0): + """move the underlying file pointer + + This method is meant for internal usage by the bundle2 protocol only. + They directly manipulate the low level stream including bundle2 level + instruction. + + Do not use it to implement higher-level logic or methods.""" + if self._seekable: + return self._fp.seek(offset, whence) + else: + raise NotImplementedError(_('File pointer is not seekable')) + + def _tellfp(self): + """return the file offset, or None if file is not seekable + + This method is meant for internal usage by the bundle2 protocol only. + They directly manipulate the low level stream including bundle2 level + instruction. + + Do not use it to implement higher-level logic or methods.""" + if self._seekable: + try: + return self._fp.tell() + except IOError as e: + if e.errno == errno.ESPIPE: + self._seekable = False + else: + raise + return None + # These are only the static capabilities. # Check the 'getrepocaps' function for the rest. capabilities = {'HG20': (),
--- a/mercurial/bundlerepo.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/bundlerepo.py Tue Apr 18 12:24:34 2017 -0400 @@ -37,8 +37,8 @@ phases, pycompat, revlog, - scmutil, util, + vfs as vfsmod, ) class bundlerevlog(revlog.revlog): @@ -50,7 +50,7 @@ # # To differentiate a rev in the bundle from a rev in the revlog, we # check revision against repotiprev. - opener = scmutil.readonlyvfs(opener) + opener = vfsmod.readonlyvfs(opener) revlog.revlog.__init__(self, opener, indexfile) self.bundle = bundle n = len(self) @@ -65,6 +65,7 @@ cs = chunkdata['cs'] deltabase = chunkdata['deltabase'] delta = chunkdata['delta'] + flags = chunkdata['flags'] size = len(delta) start = bundle.tell() - size @@ -87,7 +88,7 @@ baserev = self.rev(deltabase) # start, size, full unc. size, base (unused), link, p1, p2, node - e = (revlog.offset_type(start, 0), size, -1, baserev, link, + e = (revlog.offset_type(start, flags), size, -1, baserev, link, self.rev(p1), self.rev(p2), node) self.index.insert(-1, e) self.nodemap[node] = n @@ -114,8 +115,8 @@ elif rev1 <= self.repotiprev and rev2 <= self.repotiprev: return revlog.revlog.revdiff(self, rev1, rev2) - return mdiff.textdiff(self.revision(self.node(rev1)), - self.revision(self.node(rev2))) + return mdiff.textdiff(self.revision(rev1, raw=True), + self.revision(rev2, raw=True)) def revision(self, nodeorrev, raw=False): """return an uncompressed revision of a given node or revision @@ -131,35 +132,35 @@ if node == nullid: return "" - text = None + rawtext = None chain = [] iterrev = rev # reconstruct the revision if it is from a changegroup while iterrev > self.repotiprev: if self._cache and self._cache[1] == iterrev: - text = self._cache[2] + rawtext = self._cache[2] break chain.append(iterrev) iterrev = self.index[iterrev][3] - if text is None: - text = self.baserevision(iterrev) + if rawtext is None: + rawtext = self.baserevision(iterrev) while chain: delta = self._chunk(chain.pop()) - text = mdiff.patches(text, [delta]) + rawtext = mdiff.patches(rawtext, [delta]) - text, validatehash = self._processflags(text, self.flags(rev), + text, validatehash = self._processflags(rawtext, self.flags(rev), 'read', raw=raw) if validatehash: self.checkhash(text, node, rev=rev) - self._cache = (node, rev, text) + self._cache = (node, rev, rawtext) return text def baserevision(self, nodeorrev): # Revlog subclasses may override 'revision' method to modify format of # content retrieved from revlog. To use bundlerevlog with such class one # needs to override 'baserevision' and make more specific call here. - return revlog.revlog.revision(self, nodeorrev) + return revlog.revlog.revision(self, nodeorrev, raw=True) def addrevision(self, text, transaction, link, p1=None, p2=None, d=None): raise NotImplementedError @@ -187,7 +188,7 @@ oldfilter = self.filteredrevs try: self.filteredrevs = () - return changelog.changelog.revision(self, nodeorrev) + return changelog.changelog.revision(self, nodeorrev, raw=True) finally: self.filteredrevs = oldfilter @@ -209,9 +210,9 @@ node = self.node(node) if node in self.fulltextcache: - result = self.fulltextcache[node].tostring() + result = '%s' % self.fulltextcache[node] else: - result = manifest.manifestrevlog.revision(self, nodeorrev) + result = manifest.manifestrevlog.revision(self, nodeorrev, raw=True) return result def dirlog(self, d): @@ -229,7 +230,7 @@ linkmapper) def baserevision(self, nodeorrev): - return filelog.filelog.revision(self, nodeorrev) + return filelog.filelog.revision(self, nodeorrev, raw=True) class bundlepeer(localrepo.localpeer): def canpush(self): @@ -239,7 +240,7 @@ def __init__(self, *args, **kwargs): super(bundlephasecache, self).__init__(*args, **kwargs) if util.safehasattr(self, 'opener'): - self.opener = scmutil.readonlyvfs(self.opener) + self.opener = vfsmod.readonlyvfs(self.opener) def write(self): raise NotImplementedError @@ -272,7 +273,7 @@ suffix=".hg10un") self.tempfile = temp - with os.fdopen(fdtemp, 'wb') as fptemp: + with os.fdopen(fdtemp, pycompat.sysstr('wb')) as fptemp: fptemp.write(header) while True: chunk = read(2**18)
--- a/mercurial/changegroup.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/changegroup.py Tue Apr 18 12:24:34 2017 -0400 @@ -26,6 +26,7 @@ error, mdiff, phases, + pycompat, util, ) @@ -98,7 +99,7 @@ fh = open(filename, "wb", 131072) else: fd, filename = tempfile.mkstemp(prefix="hg-bundle-", suffix=".hg") - fh = os.fdopen(fd, "wb") + fh = os.fdopen(fd, pycompat.sysstr("wb")) cleanup = filename for c in chunks: fh.write(c)
--- a/mercurial/changelog.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/changelog.py Tue Apr 18 12:24:34 2017 -0400 @@ -32,7 +32,7 @@ >>> s 'ab\\ncd\\\\\\\\n\\x00ab\\rcd\\\\\\n' >>> res = _string_escape(s) - >>> s == res.decode('string_escape') + >>> s == util.unescapestr(res) True """ # subset of the string_escape codec @@ -57,7 +57,7 @@ l = l.replace('\\\\', '\\\\\n') l = l.replace('\\0', '\0') l = l.replace('\n', '') - k, v = l.decode('string_escape').split(':', 1) + k, v = util.unescapestr(l).split(':', 1) extra[k] = v return extra @@ -120,7 +120,7 @@ return ret def write(self, s): - self.data.append(str(s)) + self.data.append(bytes(s)) self.offset += len(s) self._end += len(s)
--- a/mercurial/chgserver.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/chgserver.py Tue Apr 18 12:24:34 2017 -0400 @@ -31,13 +31,15 @@ :: [chgserver] - idletimeout = 3600 # seconds, after which an idle server will exit - skiphash = False # whether to skip config or env change checks + # how long (in seconds) should an idle chg server exit + idletimeout = 3600 + + # whether to skip config or env change checks + skiphash = False """ from __future__ import absolute_import -import errno import hashlib import inspect import os @@ -176,30 +178,22 @@ else: self._csystem = csystem - def system(self, cmd, environ=None, cwd=None, onerr=None, - errprefix=None): + def _runsystem(self, cmd, environ, cwd, out): # fallback to the original system method if the output needs to be # captured (to self._buffers), or the output stream is not stdout # (e.g. stderr, cStringIO), because the chg client is not aware of # these situations and will behave differently (write to stdout). - if (any(s[1] for s in self._bufferstates) + if (out is not self.fout or not util.safehasattr(self.fout, 'fileno') or self.fout.fileno() != util.stdout.fileno()): - return super(chgui, self).system(cmd, environ, cwd, onerr, - errprefix) + return util.system(cmd, environ=environ, cwd=cwd, out=out) self.flush() - rc = self._csystem(cmd, util.shellenviron(environ), cwd) - if rc and onerr: - errmsg = '%s %s' % (os.path.basename(cmd.split(None, 1)[0]), - util.explainexit(rc)[0]) - if errprefix: - errmsg = '%s: %s' % (errprefix, errmsg) - raise onerr(errmsg) - return rc + return self._csystem(cmd, util.shellenviron(environ), cwd) - def _runpager(self, cmd): - self._csystem(cmd, util.shellenviron(), type='pager', + def _runpager(self, cmd, env=None): + self._csystem(cmd, util.shellenviron(env), type='pager', cmdtable={'attachio': attachio}) + return True return chgui(srcui) @@ -219,8 +213,8 @@ # stolen from tortoisehg.util.copydynamicconfig() for section, name, value in srcui.walkconfig(): source = srcui.configsource(section, name) - if ':' in source or source == '--config': - # path:line or command line + if ':' in source or source == '--config' or source.startswith('$'): + # path:line or command line, or environ continue newui.setconfig(section, name, value, source) @@ -287,9 +281,9 @@ _iochannels = [ # server.ch, ui.fp, mode - ('cin', 'fin', 'rb'), - ('cout', 'fout', 'wb'), - ('cerr', 'ferr', 'wb'), + ('cin', 'fin', pycompat.sysstr('rb')), + ('cout', 'fout', pycompat.sysstr('wb')), + ('cerr', 'ferr', pycompat.sysstr('wb')), ] class chgcmdserver(commandserver.server): @@ -549,11 +543,7 @@ # remove another server's socket file. but that's okay # since that server will detect and exit automatically and # the client will start a new server on demand. - try: - os.unlink(self._realaddress) - except OSError as exc: - if exc.errno != errno.ENOENT: - raise + util.tryunlink(self._realaddress) def printbanner(self, address): # no "listening at" message should be printed to simulate hg behavior
--- a/mercurial/cmdutil.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/cmdutil.py Tue Apr 18 12:24:34 2017 -0400 @@ -8,6 +8,7 @@ from __future__ import absolute_import import errno +import itertools import os import re import tempfile @@ -26,14 +27,12 @@ changelog, copies, crecord as crecordmod, - dirstateguard as dirstateguardmod, encoding, error, formatter, graphmod, lock as lockmod, match as matchmod, - mergeutil, obsolete, patch, pathutil, @@ -43,9 +42,11 @@ revlog, revset, scmutil, + smartset, templatekw, templater, util, + vfs as vfsmod, ) stringio = util.stringio @@ -201,7 +202,7 @@ newlyaddedandmodifiedfiles] backups = {} if tobackup: - backupdir = repo.join('record-backups') + backupdir = repo.vfs.join('record-backups') try: os.mkdir(backupdir) except OSError as err: @@ -584,7 +585,7 @@ raise error.CommandError(cmd, _('invalid arguments')) if not os.path.isfile(file_): raise error.Abort(_("revlog '%s' not found") % file_) - r = revlog.revlog(scmutil.opener(pycompat.getcwd(), audit=False), + r = revlog.revlog(vfsmod.vfs(pycompat.getcwd(), audit=False), file_[:-2] + ".i") return r @@ -728,7 +729,7 @@ dryrun=dryrun, cwd=cwd) if rename and not dryrun: if not after and srcexists and not samefile: - util.unlinkpath(repo.wjoin(abssrc)) + repo.wvfs.unlinkpath(abssrc) wctx.forget([abssrc]) # pat: ossep @@ -971,20 +972,18 @@ editor = None else: editor = getcommiteditor(editform=editform, **opts) - allowemptyback = repo.ui.backupconfig('ui', 'allowemptycommit') extra = {} for idfunc in extrapreimport: extrapreimportmap[idfunc](repo, extractdata, extra, opts) - try: - if partial: - repo.ui.setconfig('ui', 'allowemptycommit', True) + overrides = {} + if partial: + overrides[('ui', 'allowemptycommit')] = True + with repo.ui.configoverride(overrides, 'import'): n = repo.commit(message, user, date, match=m, editor=editor, extra=extra) for idfunc in extrapostimport: extrapostimportmap[idfunc](repo[n]) - finally: - repo.ui.restoreconfig(allowemptyback) else: if opts.get('exact') or importbranch: branch = branch or 'default' @@ -1157,6 +1156,8 @@ def _changesetlabels(ctx): labels = ['log.changeset', 'changeset.%s' % ctx.phasestr()] + if ctx.obsolete(): + labels.append('changeset.obsolete') if ctx.troubled(): labels.append('changeset.troubled') for trouble in ctx.troubles(): @@ -1300,7 +1301,7 @@ for key, value in sorted(extra.items()): # i18n: column positioning for "hg log" self.ui.write(_("extra: %s=%s\n") - % (key, value.encode('string_escape')), + % (key, util.escapestr(value)), label='ui.debug log.extra') description = ctx.description().strip() @@ -1443,26 +1444,16 @@ def __init__(self, ui, repo, matchfn, diffopts, tmpl, mapfile, buffered): changeset_printer.__init__(self, ui, repo, matchfn, diffopts, buffered) - formatnode = ui.debugflag and (lambda x: x) or (lambda x: x[:12]) - filters = {'formatnode': formatnode} - defaulttempl = { - 'parent': '{rev}:{node|formatnode} ', - 'manifest': '{rev}:{node|formatnode}', - 'file_copy': '{name} ({source})', - 'envvar': '{key}={value}', - 'extra': '{key}={value|stringescape}' - } - # filecopy is preserved for compatibility reasons - defaulttempl['filecopy'] = defaulttempl['file_copy'] assert not (tmpl and mapfile) + defaulttempl = templatekw.defaulttempl if mapfile: - self.t = templater.templater.frommapfile(mapfile, filters=filters, + self.t = templater.templater.frommapfile(mapfile, cache=defaulttempl) else: self.t = formatter.maketemplater(ui, 'changeset', tmpl, - filters=filters, cache=defaulttempl) + self._counter = itertools.count() self.cache = {} # find correct templates for current mode @@ -1501,6 +1492,7 @@ props['ctx'] = ctx props['repo'] = self.repo props['ui'] = self.repo.ui + props['index'] = next(self._counter) props['revcache'] = {'copies': copies} props['cache'] = self.cache @@ -2092,11 +2084,11 @@ if opts.get('rev'): revs = scmutil.revrange(repo, opts['rev']) elif follow and repo.dirstate.p1() == nullid: - revs = revset.baseset() + revs = smartset.baseset() elif follow: revs = repo.revs('reverse(:.)') else: - revs = revset.spanset(repo) + revs = smartset.spanset(repo) revs.reverse() return revs @@ -2111,7 +2103,7 @@ limit = loglimit(opts) revs = _logrevs(repo, opts) if not revs: - return revset.baseset(), None, None + return smartset.baseset(), None, None expr, filematcher = _makelogrevset(repo, pats, opts, revs) if opts.get('rev'): # User-specified revs might be unsorted, but don't sort before @@ -2127,7 +2119,7 @@ if idx >= limit: break limitedrevs.append(rev) - revs = revset.baseset(limitedrevs) + revs = smartset.baseset(limitedrevs) return revs, expr, filematcher @@ -2142,7 +2134,7 @@ limit = loglimit(opts) revs = _logrevs(repo, opts) if not revs: - return revset.baseset([]), None, None + return smartset.baseset([]), None, None expr, filematcher = _makelogrevset(repo, pats, opts, revs) if expr: matcher = revset.match(repo.ui, expr, order=revset.followorder) @@ -2153,7 +2145,7 @@ if limit <= idx: break limitedrevs.append(r) - revs = revset.baseset(limitedrevs) + revs = smartset.baseset(limitedrevs) return revs, expr, filematcher @@ -2162,6 +2154,7 @@ if not spec: return templatekw.showgraphnode # fast path for "{graphnode}" + spec = templater.unquotestring(spec) templ = formatter.gettemplater(ui, 'graphnode', spec) cache = {} if isinstance(displayer, changeset_templater): @@ -2225,7 +2218,7 @@ graphmod.ascii(ui, state, type, char, lines, coldata) displayer.close() -def graphlog(ui, repo, *pats, **opts): +def graphlog(ui, repo, pats, opts): # Parameters are identical to log command ones revs, expr, filematcher = getgraphlogrevs(repo, pats, opts) revdag = graphmod.dagwalker(repo, revs) @@ -2236,6 +2229,8 @@ if opts.get('rev'): endrev = scmutil.revrange(repo, opts.get('rev')).max() + 1 getrenamed = templatekw.getrenamedfn(repo, endrev=endrev) + + ui.pager('log') displayer = show_changeset(ui, repo, opts, buffered=True) displaygraph(ui, repo, revdag, displayer, graphmod.asciiedges, getrenamed, filematcher) @@ -2296,6 +2291,15 @@ bad.extend(f for f in rejected if f in match.files()) return bad +def addwebdirpath(repo, serverpath, webconf): + webconf[serverpath] = repo.root + repo.ui.debug('adding %s = %s\n' % (serverpath, repo.root)) + + for r in repo.revs('filelog("path:.hgsub")'): + ctx = repo[r] + for subpath in ctx.substate: + ctx.sub(subpath).addwebdirpath(serverpath, webconf) + def forget(ui, repo, match, prefix, explicitonly): join = lambda f: os.path.join(prefix, f) bad = [] @@ -2483,7 +2487,7 @@ for f in list: if f in added: continue # we never unlink added files on remove - util.unlinkpath(repo.wjoin(f), ignoremissing=True) + repo.wvfs.unlinkpath(f, ignoremissing=True) repo[None].forget(list) if warn: @@ -2764,6 +2768,7 @@ while forms: tmpl = repo.ui.config('committemplate', '.'.join(forms)) if tmpl: + tmpl = templater.unquotestring(tmpl) templatetext = committext = buildcommittemplate( repo, ctx, subs, extramsg, tmpl) break @@ -2975,13 +2980,6 @@ clean = set(changes.clean) modadded = set() - # split between files known in target manifest and the others - smf = set(mf) - - # determine the exact nature of the deleted changesets - deladded = _deleted - smf - deleted = _deleted - deladded - # We need to account for the state of the file in the dirstate, # even when we revert against something else than parent. This will # slightly alter the behavior of revert (doing back up or not, delete @@ -3023,7 +3021,10 @@ # in case of merge, files that are actually added can be reported as # modified, we need to post process the result if p2 != nullid: - mergeadd = dsmodified - smf + mergeadd = set(dsmodified) + for path in dsmodified: + if path in mf: + mergeadd.remove(path) dsadded |= mergeadd dsmodified -= mergeadd @@ -3036,6 +3037,13 @@ dsremoved.add(src) names[src] = (repo.pathto(src, cwd), True) + # determine the exact nature of the deleted changesets + deladded = set(_deleted) + for path in _deleted: + if path in mf: + deladded.remove(path) + deleted = _deleted - deladded + # distinguish between file to forget and the other added = set() for abs in dsadded: @@ -3205,7 +3213,7 @@ def doremove(f): try: - util.unlinkpath(repo.wjoin(f)) + repo.wvfs.unlinkpath(f) except OSError: pass repo.dirstate.remove(f) @@ -3254,15 +3262,18 @@ diffopts = patch.difffeatureopts(repo.ui, whitespace=True) diffopts.nodates = True diffopts.git = True - reversehunks = repo.ui.configbool('experimental', - 'revertalternateinteractivemode', - True) + operation = 'discard' + reversehunks = True + if node != parent: + operation = 'revert' + reversehunks = repo.ui.configbool('experimental', + 'revertalternateinteractivemode', + True) if reversehunks: diff = patch.diff(repo, ctx.node(), None, m, opts=diffopts) else: diff = patch.diff(repo, None, ctx.node(), m, opts=diffopts) originalchunks = patch.parsepatch(diff) - operation = 'discard' if node == parent else 'revert' try: @@ -3366,11 +3377,6 @@ return cmd -def checkunresolved(ms): - ms._repo.ui.deprecwarn('checkunresolved moved from cmdutil to mergeutil', - '4.1') - return mergeutil.checkunresolved(ms) - # a list of (ui, repo, otherpeer, opts, missing) functions called by # commands.outgoing. "missing" is "missing" of the result of # "findcommonoutgoing()" @@ -3420,7 +3426,7 @@ raise error.Abort(msg, hint=hint) for f, clearable, allowcommit, msg, hint in unfinishedstates: if clearable and repo.vfs.exists(f): - util.unlink(repo.join(f)) + util.unlink(repo.vfs.join(f)) afterresolvedstates = [ ('graftstate', @@ -3477,10 +3483,3 @@ if after[1]: hint = after[0] raise error.Abort(_('no %s in progress') % task, hint=hint) - -class dirstateguard(dirstateguardmod.dirstateguard): - def __init__(self, repo, name): - dirstateguardmod.dirstateguard.__init__(self, repo, name) - repo.ui.deprecwarn( - 'dirstateguard has moved from cmdutil to dirstateguard', - '4.1')
--- a/mercurial/color.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/color.py Tue Apr 18 12:24:34 2017 -0400 @@ -7,59 +7,499 @@ from __future__ import absolute_import -_styles = {'grep.match': 'red bold', - 'grep.linenumber': 'green', - 'grep.rev': 'green', - 'grep.change': 'green', - 'grep.sep': 'cyan', - 'grep.filename': 'magenta', - 'grep.user': 'magenta', - 'grep.date': 'magenta', - 'bookmarks.active': 'green', - 'branches.active': 'none', - 'branches.closed': 'black bold', - 'branches.current': 'green', - 'branches.inactive': 'none', - 'diff.changed': 'white', - 'diff.deleted': 'red', - 'diff.diffline': 'bold', - 'diff.extended': 'cyan bold', - 'diff.file_a': 'red bold', - 'diff.file_b': 'green bold', - 'diff.hunk': 'magenta', - 'diff.inserted': 'green', - 'diff.tab': '', - 'diff.trailingwhitespace': 'bold red_background', - 'changeset.public' : '', - 'changeset.draft' : '', - 'changeset.secret' : '', - 'diffstat.deleted': 'red', - 'diffstat.inserted': 'green', - 'histedit.remaining': 'red bold', - 'ui.prompt': 'yellow', - 'log.changeset': 'yellow', - 'patchbomb.finalsummary': '', - 'patchbomb.from': 'magenta', - 'patchbomb.to': 'cyan', - 'patchbomb.subject': 'green', - 'patchbomb.diffstats': '', - 'rebase.rebased': 'blue', - 'rebase.remaining': 'red bold', - 'resolve.resolved': 'green bold', - 'resolve.unresolved': 'red bold', - 'shelve.age': 'cyan', - 'shelve.newest': 'green bold', - 'shelve.name': 'blue bold', - 'status.added': 'green bold', - 'status.clean': 'none', - 'status.copied': 'none', - 'status.deleted': 'cyan bold underline', - 'status.ignored': 'black bold', - 'status.modified': 'blue bold', - 'status.removed': 'red bold', - 'status.unknown': 'magenta bold underline', - 'tags.normal': 'green', - 'tags.local': 'black bold'} +import re + +from .i18n import _ + +from . import ( + encoding, + pycompat, + util +) + +try: + import curses + # Mapping from effect name to terminfo attribute name (or raw code) or + # color number. This will also force-load the curses module. + _baseterminfoparams = { + 'none': (True, 'sgr0', ''), + 'standout': (True, 'smso', ''), + 'underline': (True, 'smul', ''), + 'reverse': (True, 'rev', ''), + 'inverse': (True, 'rev', ''), + 'blink': (True, 'blink', ''), + 'dim': (True, 'dim', ''), + 'bold': (True, 'bold', ''), + 'invisible': (True, 'invis', ''), + 'italic': (True, 'sitm', ''), + 'black': (False, curses.COLOR_BLACK, ''), + 'red': (False, curses.COLOR_RED, ''), + 'green': (False, curses.COLOR_GREEN, ''), + 'yellow': (False, curses.COLOR_YELLOW, ''), + 'blue': (False, curses.COLOR_BLUE, ''), + 'magenta': (False, curses.COLOR_MAGENTA, ''), + 'cyan': (False, curses.COLOR_CYAN, ''), + 'white': (False, curses.COLOR_WHITE, ''), + } +except ImportError: + curses = None + _baseterminfoparams = {} + +_enabledbydefault = True + +# start and stop parameters for effects +_effects = { + 'none': 0, + 'black': 30, + 'red': 31, + 'green': 32, + 'yellow': 33, + 'blue': 34, + 'magenta': 35, + 'cyan': 36, + 'white': 37, + 'bold': 1, + 'italic': 3, + 'underline': 4, + 'inverse': 7, + 'dim': 2, + 'black_background': 40, + 'red_background': 41, + 'green_background': 42, + 'yellow_background': 43, + 'blue_background': 44, + 'purple_background': 45, + 'cyan_background': 46, + 'white_background': 47, + } + +_defaultstyles = { + 'grep.match': 'red bold', + 'grep.linenumber': 'green', + 'grep.rev': 'green', + 'grep.change': 'green', + 'grep.sep': 'cyan', + 'grep.filename': 'magenta', + 'grep.user': 'magenta', + 'grep.date': 'magenta', + 'bookmarks.active': 'green', + 'branches.active': 'none', + 'branches.closed': 'black bold', + 'branches.current': 'green', + 'branches.inactive': 'none', + 'diff.changed': 'white', + 'diff.deleted': 'red', + 'diff.diffline': 'bold', + 'diff.extended': 'cyan bold', + 'diff.file_a': 'red bold', + 'diff.file_b': 'green bold', + 'diff.hunk': 'magenta', + 'diff.inserted': 'green', + 'diff.tab': '', + 'diff.trailingwhitespace': 'bold red_background', + 'changeset.public' : '', + 'changeset.draft' : '', + 'changeset.secret' : '', + 'diffstat.deleted': 'red', + 'diffstat.inserted': 'green', + 'histedit.remaining': 'red bold', + 'ui.prompt': 'yellow', + 'log.changeset': 'yellow', + 'patchbomb.finalsummary': '', + 'patchbomb.from': 'magenta', + 'patchbomb.to': 'cyan', + 'patchbomb.subject': 'green', + 'patchbomb.diffstats': '', + 'rebase.rebased': 'blue', + 'rebase.remaining': 'red bold', + 'resolve.resolved': 'green bold', + 'resolve.unresolved': 'red bold', + 'shelve.age': 'cyan', + 'shelve.newest': 'green bold', + 'shelve.name': 'blue bold', + 'status.added': 'green bold', + 'status.clean': 'none', + 'status.copied': 'none', + 'status.deleted': 'cyan bold underline', + 'status.ignored': 'black bold', + 'status.modified': 'blue bold', + 'status.removed': 'red bold', + 'status.unknown': 'magenta bold underline', + 'tags.normal': 'green', + 'tags.local': 'black bold', +} def loadcolortable(ui, extname, colortable): - _styles.update(colortable) + _defaultstyles.update(colortable) + +def _terminfosetup(ui, mode): + '''Initialize terminfo data and the terminal if we're in terminfo mode.''' + + # If we failed to load curses, we go ahead and return. + if curses is None: + return + # Otherwise, see what the config file says. + if mode not in ('auto', 'terminfo'): + return + ui._terminfoparams.update(_baseterminfoparams) + + for key, val in ui.configitems('color'): + if key.startswith('color.'): + newval = (False, int(val), '') + ui._terminfoparams[key[6:]] = newval + elif key.startswith('terminfo.'): + newval = (True, '', val.replace('\\E', '\x1b')) + ui._terminfoparams[key[9:]] = newval + try: + curses.setupterm() + except curses.error as e: + ui._terminfoparams.clear() + return + + for key, (b, e, c) in ui._terminfoparams.items(): + if not b: + continue + if not c and not curses.tigetstr(e): + # Most terminals don't support dim, invis, etc, so don't be + # noisy and use ui.debug(). + ui.debug("no terminfo entry for %s\n" % e) + del ui._terminfoparams[key] + if not curses.tigetstr('setaf') or not curses.tigetstr('setab'): + # Only warn about missing terminfo entries if we explicitly asked for + # terminfo mode. + if mode == "terminfo": + ui.warn(_("no terminfo entry for setab/setaf: reverting to " + "ECMA-48 color\n")) + ui._terminfoparams.clear() + +def setup(ui): + """configure color on a ui + + That function both set the colormode for the ui object and read + the configuration looking for custom colors and effect definitions.""" + mode = _modesetup(ui) + ui._colormode = mode + if mode and mode != 'debug': + configstyles(ui) + +def _modesetup(ui): + if ui.plain(): + return None + default = 'never' + if _enabledbydefault: + default = 'auto' + config = ui.config('ui', 'color', default) + if config == 'debug': + return 'debug' + + auto = (config == 'auto') + always = not auto and util.parsebool(config) + if not always and not auto: + return None + + formatted = (always or (encoding.environ.get('TERM') != 'dumb' + and ui.formatted())) + + mode = ui.config('color', 'mode', 'auto') + + # If pager is active, color.pagermode overrides color.mode. + if getattr(ui, 'pageractive', False): + mode = ui.config('color', 'pagermode', mode) + + realmode = mode + if mode == 'auto': + if pycompat.osname == 'nt': + term = encoding.environ.get('TERM') + # TERM won't be defined in a vanilla cmd.exe environment. + + # UNIX-like environments on Windows such as Cygwin and MSYS will + # set TERM. They appear to make a best effort attempt at setting it + # to something appropriate. However, not all environments with TERM + # defined support ANSI. Since "ansi" could result in terminal + # gibberish, we error on the side of selecting "win32". However, if + # w32effects is not defined, we almost certainly don't support + # "win32", so don't even try. + if (term and 'xterm' in term) or not w32effects: + realmode = 'ansi' + else: + realmode = 'win32' + else: + realmode = 'ansi' + + def modewarn(): + # only warn if color.mode was explicitly set and we're in + # a formatted terminal + if mode == realmode and ui.formatted(): + ui.warn(_('warning: failed to set color mode to %s\n') % mode) + + if realmode == 'win32': + ui._terminfoparams.clear() + if not w32effects: + modewarn() + return None + elif realmode == 'ansi': + ui._terminfoparams.clear() + elif realmode == 'terminfo': + _terminfosetup(ui, mode) + if not ui._terminfoparams: + ## FIXME Shouldn't we return None in this case too? + modewarn() + realmode = 'ansi' + else: + return None + + if always or (auto and formatted): + return realmode + return None + +def configstyles(ui): + ui._styles.update(_defaultstyles) + for status, cfgeffects in ui.configitems('color'): + if '.' not in status or status.startswith(('color.', 'terminfo.')): + continue + cfgeffects = ui.configlist('color', status) + if cfgeffects: + good = [] + for e in cfgeffects: + if valideffect(ui, e): + good.append(e) + else: + ui.warn(_("ignoring unknown color/effect %r " + "(configured in color.%s)\n") + % (e, status)) + ui._styles[status] = ' '.join(good) + +def _activeeffects(ui): + '''Return the effects map for the color mode set on the ui.''' + if ui._colormode == 'win32': + return w32effects + elif ui._colormode is not None: + return _effects + return {} + +def valideffect(ui, effect): + 'Determine if the effect is valid or not.' + return ((not ui._terminfoparams and effect in _activeeffects(ui)) + or (effect in ui._terminfoparams + or effect[:-11] in ui._terminfoparams)) + +def _effect_str(ui, effect): + '''Helper function for render_effects().''' + + bg = False + if effect.endswith('_background'): + bg = True + effect = effect[:-11] + try: + attr, val, termcode = ui._terminfoparams[effect] + except KeyError: + return '' + if attr: + if termcode: + return termcode + else: + return curses.tigetstr(val) + elif bg: + return curses.tparm(curses.tigetstr('setab'), val) + else: + return curses.tparm(curses.tigetstr('setaf'), val) + +def _mergeeffects(text, start, stop): + """Insert start sequence at every occurrence of stop sequence + + >>> s = _mergeeffects('cyan', '[C]', '|') + >>> s = _mergeeffects(s + 'yellow', '[Y]', '|') + >>> s = _mergeeffects('ma' + s + 'genta', '[M]', '|') + >>> s = _mergeeffects('red' + s, '[R]', '|') + >>> s + '[R]red[M]ma[Y][C]cyan|[R][M][Y]yellow|[R][M]genta|' + """ + parts = [] + for t in text.split(stop): + if not t: + continue + parts.extend([start, t, stop]) + return ''.join(parts) + +def _render_effects(ui, text, effects): + 'Wrap text in commands to turn on each effect.' + if not text: + return text + if ui._terminfoparams: + start = ''.join(_effect_str(ui, effect) + for effect in ['none'] + effects.split()) + stop = _effect_str(ui, 'none') + else: + activeeffects = _activeeffects(ui) + start = [pycompat.bytestr(activeeffects[e]) + for e in ['none'] + effects.split()] + start = '\033[' + ';'.join(start) + 'm' + stop = '\033[' + pycompat.bytestr(activeeffects['none']) + 'm' + return _mergeeffects(text, start, stop) + +_ansieffectre = re.compile(br'\x1b\[[0-9;]*m') + +def stripeffects(text): + """Strip ANSI control codes which could be inserted by colorlabel()""" + return _ansieffectre.sub('', text) + +def colorlabel(ui, msg, label): + """add color control code according to the mode""" + if ui._colormode == 'debug': + if label and msg: + if msg[-1] == '\n': + msg = "[%s|%s]\n" % (label, msg[:-1]) + else: + msg = "[%s|%s]" % (label, msg) + elif ui._colormode is not None: + effects = [] + for l in label.split(): + s = ui._styles.get(l, '') + if s: + effects.append(s) + elif valideffect(ui, l): + effects.append(l) + effects = ' '.join(effects) + if effects: + msg = '\n'.join([_render_effects(ui, line, effects) + for line in msg.split('\n')]) + return msg + +w32effects = None +if pycompat.osname == 'nt': + import ctypes + + _kernel32 = ctypes.windll.kernel32 + + _WORD = ctypes.c_ushort + + _INVALID_HANDLE_VALUE = -1 + + class _COORD(ctypes.Structure): + _fields_ = [('X', ctypes.c_short), + ('Y', ctypes.c_short)] + + class _SMALL_RECT(ctypes.Structure): + _fields_ = [('Left', ctypes.c_short), + ('Top', ctypes.c_short), + ('Right', ctypes.c_short), + ('Bottom', ctypes.c_short)] + + class _CONSOLE_SCREEN_BUFFER_INFO(ctypes.Structure): + _fields_ = [('dwSize', _COORD), + ('dwCursorPosition', _COORD), + ('wAttributes', _WORD), + ('srWindow', _SMALL_RECT), + ('dwMaximumWindowSize', _COORD)] + + _STD_OUTPUT_HANDLE = 0xfffffff5 # (DWORD)-11 + _STD_ERROR_HANDLE = 0xfffffff4 # (DWORD)-12 + + _FOREGROUND_BLUE = 0x0001 + _FOREGROUND_GREEN = 0x0002 + _FOREGROUND_RED = 0x0004 + _FOREGROUND_INTENSITY = 0x0008 + + _BACKGROUND_BLUE = 0x0010 + _BACKGROUND_GREEN = 0x0020 + _BACKGROUND_RED = 0x0040 + _BACKGROUND_INTENSITY = 0x0080 + + _COMMON_LVB_REVERSE_VIDEO = 0x4000 + _COMMON_LVB_UNDERSCORE = 0x8000 + + # http://msdn.microsoft.com/en-us/library/ms682088%28VS.85%29.aspx + w32effects = { + 'none': -1, + 'black': 0, + 'red': _FOREGROUND_RED, + 'green': _FOREGROUND_GREEN, + 'yellow': _FOREGROUND_RED | _FOREGROUND_GREEN, + 'blue': _FOREGROUND_BLUE, + 'magenta': _FOREGROUND_BLUE | _FOREGROUND_RED, + 'cyan': _FOREGROUND_BLUE | _FOREGROUND_GREEN, + 'white': _FOREGROUND_RED | _FOREGROUND_GREEN | _FOREGROUND_BLUE, + 'bold': _FOREGROUND_INTENSITY, + 'black_background': 0x100, # unused value > 0x0f + 'red_background': _BACKGROUND_RED, + 'green_background': _BACKGROUND_GREEN, + 'yellow_background': _BACKGROUND_RED | _BACKGROUND_GREEN, + 'blue_background': _BACKGROUND_BLUE, + 'purple_background': _BACKGROUND_BLUE | _BACKGROUND_RED, + 'cyan_background': _BACKGROUND_BLUE | _BACKGROUND_GREEN, + 'white_background': (_BACKGROUND_RED | _BACKGROUND_GREEN | + _BACKGROUND_BLUE), + 'bold_background': _BACKGROUND_INTENSITY, + 'underline': _COMMON_LVB_UNDERSCORE, # double-byte charsets only + 'inverse': _COMMON_LVB_REVERSE_VIDEO, # double-byte charsets only + } + + passthrough = set([_FOREGROUND_INTENSITY, + _BACKGROUND_INTENSITY, + _COMMON_LVB_UNDERSCORE, + _COMMON_LVB_REVERSE_VIDEO]) + + stdout = _kernel32.GetStdHandle( + _STD_OUTPUT_HANDLE) # don't close the handle returned + if stdout is None or stdout == _INVALID_HANDLE_VALUE: + w32effects = None + else: + csbi = _CONSOLE_SCREEN_BUFFER_INFO() + if not _kernel32.GetConsoleScreenBufferInfo( + stdout, ctypes.byref(csbi)): + # stdout may not support GetConsoleScreenBufferInfo() + # when called from subprocess or redirected + w32effects = None + else: + origattr = csbi.wAttributes + ansire = re.compile('\033\[([^m]*)m([^\033]*)(.*)', + re.MULTILINE | re.DOTALL) + + def win32print(ui, writefunc, *msgs, **opts): + for text in msgs: + _win32print(ui, text, writefunc, **opts) + + def _win32print(ui, text, writefunc, **opts): + label = opts.get('label', '') + attr = origattr + + def mapcolor(val, attr): + if val == -1: + return origattr + elif val in passthrough: + return attr | val + elif val > 0x0f: + return (val & 0x70) | (attr & 0x8f) + else: + return (val & 0x07) | (attr & 0xf8) + + # determine console attributes based on labels + for l in label.split(): + style = ui._styles.get(l, '') + for effect in style.split(): + try: + attr = mapcolor(w32effects[effect], attr) + except KeyError: + # w32effects could not have certain attributes so we skip + # them if not found + pass + # hack to ensure regexp finds data + if not text.startswith('\033['): + text = '\033[m' + text + + # Look for ANSI-like codes embedded in text + m = re.match(ansire, text) + + try: + while m: + for sattr in m.group(1).split(';'): + if sattr: + attr = mapcolor(int(sattr), attr) + ui.flush() + _kernel32.SetConsoleTextAttribute(stdout, attr) + writefunc(m.group(2), **opts) + m = re.match(ansire, m.group(3)) + finally: + # Explicitly reset original attributes + ui.flush() + _kernel32.SetConsoleTextAttribute(stdout, origattr)
--- a/mercurial/commands.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/commands.py Tue Apr 18 12:24:34 2017 -0400 @@ -11,17 +11,10 @@ import errno import os import re -import socket -import string -import sys -import tempfile -import time from .i18n import _ from .node import ( - bin, hex, - nullhex, nullid, nullrev, short, @@ -40,30 +33,24 @@ error, exchange, extensions, - formatter, graphmod, hbisect, help, hg, lock as lockmod, merge as mergemod, - minirst, obsolete, patch, phases, - policy, - pvec, pycompat, - repair, - revlog, - revset, + rcutil, + revsetlang, scmutil, server, sshserver, - sslutil, streamclone, + tags as tagsmod, templatekw, - templater, ui as uimod, util, ) @@ -92,6 +79,11 @@ _('do not prompt, automatically pick the first choice for all prompts')), ('q', 'quiet', None, _('suppress output')), ('v', 'verbose', None, _('enable additional output')), + ('', 'color', '', + # i18n: 'always', 'auto', 'never', and 'debug' are keywords + # and should not be translated + _("when to colorize (boolean, always, auto, never, or debug)"), + _('TYPE')), ('', 'config', [], _('set/override config option (use \'section.name=value\')'), _('CONFIG')), @@ -107,6 +99,8 @@ ('', 'version', None, _('output version information and exit')), ('h', 'help', None, _('display help and exit')), ('', 'hidden', False, _('consider hidden changesets')), + ('', 'pager', 'auto', + _("when to paginate (boolean, always, auto, or never)"), _('TYPE')), ] dryrunopts = [('n', 'dry-run', None, @@ -168,6 +162,7 @@ diffopts = [ ('a', 'text', None, _('treat all files as text')), ('g', 'git', None, _('use git extended diff format')), + ('', 'binary', None, _('generate binary diffs in git mode (default)')), ('', 'nodates', None, _('omit dates from diff headers')) ] @@ -433,6 +428,8 @@ if linenumber and (not opts.get('changeset')) and (not opts.get('number')): raise error.Abort(_('at least one of -n/-c is required for -l')) + ui.pager('annotate') + if fm.isplain(): def makefunc(get, fmt): return lambda x: fmt(get(x)) @@ -892,7 +889,8 @@ # update state state['current'] = [node] hbisect.save_state(repo, state) - status = ui.system(command, environ={'HG_NODE': hex(node)}) + status = ui.system(command, environ={'HG_NODE': hex(node)}, + blockedtag='bisect_check') if status == 125: transition = "skip" elif status == 0: @@ -1228,6 +1226,7 @@ Returns 0. """ + ui.pager('branches') fm = ui.formatter('branches', opts) hexfunc = fm.hexfunc @@ -1264,6 +1263,7 @@ fmt = ' ' * padsize + ' %d:%s' fm.condwrite(not ui.quiet, 'rev node', fmt, rev, hexfunc(ctx.node()), label='log.changeset changeset.%s' % ctx.phasestr()) + fm.context(ctx=ctx) fm.data(active=isactive, closed=not isopen, current=current) if not ui.quiet: fm.plain(notice) @@ -1282,12 +1282,11 @@ ('a', 'all', None, _('bundle all changesets in the repository')), ('t', 'type', 'bzip2', _('bundle compression type to use'), _('TYPE')), ] + remoteopts, - _('[-f] [-t TYPE] [-a] [-r REV]... [--base REV]... FILE [DEST]')) + _('[-f] [-t BUNDLESPEC] [-a] [-r REV]... [--base REV]... FILE [DEST]')) def bundle(ui, repo, fname, dest=None, **opts): - """create a changegroup file - - Generate a changegroup file collecting changesets to be added - to a repository. + """create a bundle file + + Generate a bundle file containing data to be added to a repository. To create a bundle containing all changesets, use -a/--all (or --base null). Otherwise, hg assumes the destination will have @@ -1295,11 +1294,10 @@ will assume the repository has all the nodes in destination, or default-push/default if no destination is specified. - You can change bundle format with the -t/--type option. You can - specify a compression, a bundle version or both using a dash - (comp-version). The available compression methods are: none, bzip2, - and gzip (by default, bundles are compressed using bzip2). The - available formats are: v1, v2 (default to most suitable). + You can change bundle format with the -t/--type option. See + :hg:`help bundlespec` for documentation on this format. By default, + the most appropriate format is used and compression defaults to + bzip2. The bundle file can then be transferred using conventional means and applied to another repository with the unbundle or pull @@ -1324,7 +1322,7 @@ repo, bundletype, strict=False) except error.UnsupportedBundleSpecification as e: raise error.Abort(str(e), - hint=_("see 'hg help bundle' for supported " + hint=_("see 'hg help bundlespec' for supported " "values for --type")) # Packed bundles are a pseudo bundle format for now. @@ -1379,9 +1377,11 @@ bcompression = 'UN' bversion = 'HG10' + bcompression bcompression = None + elif cgversion in ('02', '03'): + bversion = 'HG20' else: - assert cgversion == '02' - bversion = 'HG20' + raise error.ProgrammingError( + 'bundle: unexpected changegroup version %s' % cgversion) # TODO compression options should be derived from bundlespec parsing. # This is a temporary hack to allow adjusting bundle compression @@ -1427,6 +1427,7 @@ ctx = scmutil.revsingle(repo, opts.get('rev')) m = scmutil.match(ctx, (file1,) + pats, opts) + ui.pager('cat') return cmdutil.cat(ui, repo, ctx, m, '', **opts) @command('^clone', @@ -1638,10 +1639,12 @@ release(lock, wlock) def _docommit(ui, repo, *pats, **opts): + opts = pycompat.byteskwargs(opts) if opts.get('interactive'): opts.pop('interactive') ret = cmdutil.dorecord(ui, repo, commit, None, False, - cmdutil.recordfilter, *pats, **opts) + cmdutil.recordfilter, *pats, + **pycompat.strkwargs(opts)) # ret can be 0 (no changes to record) or the value returned by # commit(), 1 if nothing changed or None on success. return 1 if ret == 0 else ret @@ -1704,25 +1707,23 @@ return 1 else: def commitfunc(ui, repo, message, match, opts): - backup = ui.backupconfig('phases', 'new-commit') + overrides = {} + if opts.get('secret'): + overrides[('phases', 'new-commit')] = 'secret' + baseui = repo.baseui - basebackup = baseui.backupconfig('phases', 'new-commit') - try: - if opts.get('secret'): - ui.setconfig('phases', 'new-commit', 'secret', 'commit') - # Propagate to subrepos - baseui.setconfig('phases', 'new-commit', 'secret', 'commit') - - editform = cmdutil.mergeeditform(repo[None], 'commit.normal') - editor = cmdutil.getcommiteditor(editform=editform, **opts) - return repo.commit(message, opts.get('user'), opts.get('date'), - match, - editor=editor, - extra=extra) - finally: - ui.restoreconfig(backup) - repo.baseui.restoreconfig(basebackup) - + with baseui.configoverride(overrides, 'commit'): + with ui.configoverride(overrides, 'commit'): + editform = cmdutil.mergeeditform(repo[None], + 'commit.normal') + editor = cmdutil.getcommiteditor( + editform=editform, **pycompat.strkwargs(opts)) + return repo.commit(message, + opts.get('user'), + opts.get('date'), + match, + editor=editor, + extra=extra) node = cmdutil.commit(ui, repo, commitfunc, pats, opts) @@ -1775,11 +1776,11 @@ if opts.get('local'): if not repo: raise error.Abort(_("can't use --local outside a repository")) - paths = [repo.join('hgrc')] + paths = [repo.vfs.join('hgrc')] elif opts.get('global'): - paths = scmutil.systemrcpath() + paths = rcutil.systemrcpath() else: - paths = scmutil.userrcpath() + paths = rcutil.userrcpath() for f in paths: if os.path.exists(f): @@ -1799,12 +1800,19 @@ editor = ui.geteditor() ui.system("%s \"%s\"" % (editor, f), - onerr=error.Abort, errprefix=_("edit failed")) + onerr=error.Abort, errprefix=_("edit failed"), + blockedtag='config_edit') return - + ui.pager('config') fm = ui.formatter('config', opts) - for f in scmutil.rcpath(): - ui.debug('read config from: %s\n' % f) + for t, f in rcutil.rccomponents(): + if t == 'path': + ui.debug('read config from: %s\n' % f) + elif t == 'items': + for section, name, value, source in f: + ui.debug('set config by: %s\n' % source) + else: + raise error.ProgrammingError('unknown rctype: %s' % t) untrusted = bool(opts.get('untrusted')) if values: sections = [v for v in values if '.' not in v] @@ -1814,7 +1822,7 @@ matched = False for section, name, value in ui.walkconfig(untrusted=untrusted): source = ui.configsource(section, name, untrusted) - value = str(value) + value = pycompat.bytestr(value) if fm.isplain(): source = source or 'none' value = value.replace('\n', '\\n') @@ -1866,1176 +1874,6 @@ with repo.wlock(False): return cmdutil.copy(ui, repo, pats, opts) -@command('debuginstall', [] + formatteropts, '', norepo=True) -def debuginstall(ui, **opts): - '''test Mercurial installation - - Returns 0 on success. - ''' - - def writetemp(contents): - (fd, name) = tempfile.mkstemp(prefix="hg-debuginstall-") - f = os.fdopen(fd, "wb") - f.write(contents) - f.close() - return name - - problems = 0 - - fm = ui.formatter('debuginstall', opts) - fm.startitem() - - # encoding - fm.write('encoding', _("checking encoding (%s)...\n"), encoding.encoding) - err = None - try: - encoding.fromlocal("test") - except error.Abort as inst: - err = inst - problems += 1 - fm.condwrite(err, 'encodingerror', _(" %s\n" - " (check that your locale is properly set)\n"), err) - - # Python - fm.write('pythonexe', _("checking Python executable (%s)\n"), - pycompat.sysexecutable) - fm.write('pythonver', _("checking Python version (%s)\n"), - ("%d.%d.%d" % sys.version_info[:3])) - fm.write('pythonlib', _("checking Python lib (%s)...\n"), - os.path.dirname(os.__file__)) - - security = set(sslutil.supportedprotocols) - if sslutil.hassni: - security.add('sni') - - fm.write('pythonsecurity', _("checking Python security support (%s)\n"), - fm.formatlist(sorted(security), name='protocol', - fmt='%s', sep=',')) - - # These are warnings, not errors. So don't increment problem count. This - # may change in the future. - if 'tls1.2' not in security: - fm.plain(_(' TLS 1.2 not supported by Python install; ' - 'network connections lack modern security\n')) - if 'sni' not in security: - fm.plain(_(' SNI not supported by Python install; may have ' - 'connectivity issues with some servers\n')) - - # TODO print CA cert info - - # hg version - hgver = util.version() - fm.write('hgver', _("checking Mercurial version (%s)\n"), - hgver.split('+')[0]) - fm.write('hgverextra', _("checking Mercurial custom build (%s)\n"), - '+'.join(hgver.split('+')[1:])) - - # compiled modules - fm.write('hgmodulepolicy', _("checking module policy (%s)\n"), - policy.policy) - fm.write('hgmodules', _("checking installed modules (%s)...\n"), - os.path.dirname(__file__)) - - err = None - try: - from . import ( - base85, - bdiff, - mpatch, - osutil, - ) - dir(bdiff), dir(mpatch), dir(base85), dir(osutil) # quiet pyflakes - except Exception as inst: - err = inst - problems += 1 - fm.condwrite(err, 'extensionserror', " %s\n", err) - - compengines = util.compengines._engines.values() - fm.write('compengines', _('checking registered compression engines (%s)\n'), - fm.formatlist(sorted(e.name() for e in compengines), - name='compengine', fmt='%s', sep=', ')) - fm.write('compenginesavail', _('checking available compression engines ' - '(%s)\n'), - fm.formatlist(sorted(e.name() for e in compengines - if e.available()), - name='compengine', fmt='%s', sep=', ')) - wirecompengines = util.compengines.supportedwireengines(util.SERVERROLE) - fm.write('compenginesserver', _('checking available compression engines ' - 'for wire protocol (%s)\n'), - fm.formatlist([e.name() for e in wirecompengines - if e.wireprotosupport()], - name='compengine', fmt='%s', sep=', ')) - - # templates - p = templater.templatepaths() - fm.write('templatedirs', 'checking templates (%s)...\n', ' '.join(p)) - fm.condwrite(not p, '', _(" no template directories found\n")) - if p: - m = templater.templatepath("map-cmdline.default") - if m: - # template found, check if it is working - err = None - try: - templater.templater.frommapfile(m) - except Exception as inst: - err = inst - p = None - fm.condwrite(err, 'defaulttemplateerror', " %s\n", err) - else: - p = None - fm.condwrite(p, 'defaulttemplate', - _("checking default template (%s)\n"), m) - fm.condwrite(not m, 'defaulttemplatenotfound', - _(" template '%s' not found\n"), "default") - if not p: - problems += 1 - fm.condwrite(not p, '', - _(" (templates seem to have been installed incorrectly)\n")) - - # editor - editor = ui.geteditor() - editor = util.expandpath(editor) - fm.write('editor', _("checking commit editor... (%s)\n"), editor) - cmdpath = util.findexe(pycompat.shlexsplit(editor)[0]) - fm.condwrite(not cmdpath and editor == 'vi', 'vinotfound', - _(" No commit editor set and can't find %s in PATH\n" - " (specify a commit editor in your configuration" - " file)\n"), not cmdpath and editor == 'vi' and editor) - fm.condwrite(not cmdpath and editor != 'vi', 'editornotfound', - _(" Can't find editor '%s' in PATH\n" - " (specify a commit editor in your configuration" - " file)\n"), not cmdpath and editor) - if not cmdpath and editor != 'vi': - problems += 1 - - # check username - username = None - err = None - try: - username = ui.username() - except error.Abort as e: - err = e - problems += 1 - - fm.condwrite(username, 'username', _("checking username (%s)\n"), username) - fm.condwrite(err, 'usernameerror', _("checking username...\n %s\n" - " (specify a username in your configuration file)\n"), err) - - fm.condwrite(not problems, '', - _("no problems detected\n")) - if not problems: - fm.data(problems=problems) - fm.condwrite(problems, 'problems', - _("%d problems detected," - " please check your install!\n"), problems) - fm.end() - - return problems - -@command('debugknown', [], _('REPO ID...'), norepo=True) -def debugknown(ui, repopath, *ids, **opts): - """test whether node ids are known to a repo - - Every ID must be a full-length hex node id string. Returns a list of 0s - and 1s indicating unknown/known. - """ - repo = hg.peer(ui, opts, repopath) - if not repo.capable('known'): - raise error.Abort("known() not supported by target repository") - flags = repo.known([bin(s) for s in ids]) - ui.write("%s\n" % ("".join([f and "1" or "0" for f in flags]))) - -@command('debuglabelcomplete', [], _('LABEL...')) -def debuglabelcomplete(ui, repo, *args): - '''backwards compatibility with old bash completion scripts (DEPRECATED)''' - debugnamecomplete(ui, repo, *args) - -@command('debugmergestate', [], '') -def debugmergestate(ui, repo, *args): - """print merge state - - Use --verbose to print out information about whether v1 or v2 merge state - was chosen.""" - def _hashornull(h): - if h == nullhex: - return 'null' - else: - return h - - def printrecords(version): - ui.write(('* version %s records\n') % version) - if version == 1: - records = v1records - else: - records = v2records - - for rtype, record in records: - # pretty print some record types - if rtype == 'L': - ui.write(('local: %s\n') % record) - elif rtype == 'O': - ui.write(('other: %s\n') % record) - elif rtype == 'm': - driver, mdstate = record.split('\0', 1) - ui.write(('merge driver: %s (state "%s")\n') - % (driver, mdstate)) - elif rtype in 'FDC': - r = record.split('\0') - f, state, hash, lfile, afile, anode, ofile = r[0:7] - if version == 1: - onode = 'not stored in v1 format' - flags = r[7] - else: - onode, flags = r[7:9] - ui.write(('file: %s (record type "%s", state "%s", hash %s)\n') - % (f, rtype, state, _hashornull(hash))) - ui.write((' local path: %s (flags "%s")\n') % (lfile, flags)) - ui.write((' ancestor path: %s (node %s)\n') - % (afile, _hashornull(anode))) - ui.write((' other path: %s (node %s)\n') - % (ofile, _hashornull(onode))) - elif rtype == 'f': - filename, rawextras = record.split('\0', 1) - extras = rawextras.split('\0') - i = 0 - extrastrings = [] - while i < len(extras): - extrastrings.append('%s = %s' % (extras[i], extras[i + 1])) - i += 2 - - ui.write(('file extras: %s (%s)\n') - % (filename, ', '.join(extrastrings))) - elif rtype == 'l': - labels = record.split('\0', 2) - labels = [l for l in labels if len(l) > 0] - ui.write(('labels:\n')) - ui.write((' local: %s\n' % labels[0])) - ui.write((' other: %s\n' % labels[1])) - if len(labels) > 2: - ui.write((' base: %s\n' % labels[2])) - else: - ui.write(('unrecognized entry: %s\t%s\n') - % (rtype, record.replace('\0', '\t'))) - - # Avoid mergestate.read() since it may raise an exception for unsupported - # merge state records. We shouldn't be doing this, but this is OK since this - # command is pretty low-level. - ms = mergemod.mergestate(repo) - - # sort so that reasonable information is on top - v1records = ms._readrecordsv1() - v2records = ms._readrecordsv2() - order = 'LOml' - def key(r): - idx = order.find(r[0]) - if idx == -1: - return (1, r[1]) - else: - return (0, idx) - v1records.sort(key=key) - v2records.sort(key=key) - - if not v1records and not v2records: - ui.write(('no merge state found\n')) - elif not v2records: - ui.note(('no version 2 merge state\n')) - printrecords(1) - elif ms._v1v2match(v1records, v2records): - ui.note(('v1 and v2 states match: using v2\n')) - printrecords(2) - else: - ui.note(('v1 and v2 states mismatch: using v1\n')) - printrecords(1) - if ui.verbose: - printrecords(2) - -@command('debugnamecomplete', [], _('NAME...')) -def debugnamecomplete(ui, repo, *args): - '''complete "names" - tags, open branch names, bookmark names''' - - names = set() - # since we previously only listed open branches, we will handle that - # specially (after this for loop) - for name, ns in repo.names.iteritems(): - if name != 'branches': - names.update(ns.listnames(repo)) - names.update(tag for (tag, heads, tip, closed) - in repo.branchmap().iterbranches() if not closed) - completions = set() - if not args: - args = [''] - for a in args: - completions.update(n for n in names if n.startswith(a)) - ui.write('\n'.join(sorted(completions))) - ui.write('\n') - -@command('debuglocks', - [('L', 'force-lock', None, _('free the store lock (DANGEROUS)')), - ('W', 'force-wlock', None, - _('free the working state lock (DANGEROUS)'))], - _('[OPTION]...')) -def debuglocks(ui, repo, **opts): - """show or modify state of locks - - By default, this command will show which locks are held. This - includes the user and process holding the lock, the amount of time - the lock has been held, and the machine name where the process is - running if it's not local. - - Locks protect the integrity of Mercurial's data, so should be - treated with care. System crashes or other interruptions may cause - locks to not be properly released, though Mercurial will usually - detect and remove such stale locks automatically. - - However, detecting stale locks may not always be possible (for - instance, on a shared filesystem). Removing locks may also be - blocked by filesystem permissions. - - Returns 0 if no locks are held. - - """ - - if opts.get('force_lock'): - repo.svfs.unlink('lock') - if opts.get('force_wlock'): - repo.vfs.unlink('wlock') - if opts.get('force_lock') or opts.get('force_lock'): - return 0 - - now = time.time() - held = 0 - - def report(vfs, name, method): - # this causes stale locks to get reaped for more accurate reporting - try: - l = method(False) - except error.LockHeld: - l = None - - if l: - l.release() - else: - try: - stat = vfs.lstat(name) - age = now - stat.st_mtime - user = util.username(stat.st_uid) - locker = vfs.readlock(name) - if ":" in locker: - host, pid = locker.split(':') - if host == socket.gethostname(): - locker = 'user %s, process %s' % (user, pid) - else: - locker = 'user %s, process %s, host %s' \ - % (user, pid, host) - ui.write(("%-6s %s (%ds)\n") % (name + ":", locker, age)) - return 1 - except OSError as e: - if e.errno != errno.ENOENT: - raise - - ui.write(("%-6s free\n") % (name + ":")) - return 0 - - held += report(repo.svfs, "lock", repo.lock) - held += report(repo.vfs, "wlock", repo.wlock) - - return held - -@command('debugobsolete', - [('', 'flags', 0, _('markers flag')), - ('', 'record-parents', False, - _('record parent information for the precursor')), - ('r', 'rev', [], _('display markers relevant to REV')), - ('', 'index', False, _('display index of the marker')), - ('', 'delete', [], _('delete markers specified by indices')), - ] + commitopts2 + formatteropts, - _('[OBSOLETED [REPLACEMENT ...]]')) -def debugobsolete(ui, repo, precursor=None, *successors, **opts): - """create arbitrary obsolete marker - - With no arguments, displays the list of obsolescence markers.""" - - def parsenodeid(s): - try: - # We do not use revsingle/revrange functions here to accept - # arbitrary node identifiers, possibly not present in the - # local repository. - n = bin(s) - if len(n) != len(nullid): - raise TypeError() - return n - except TypeError: - raise error.Abort('changeset references must be full hexadecimal ' - 'node identifiers') - - if opts.get('delete'): - indices = [] - for v in opts.get('delete'): - try: - indices.append(int(v)) - except ValueError: - raise error.Abort(_('invalid index value: %r') % v, - hint=_('use integers for indices')) - - if repo.currenttransaction(): - raise error.Abort(_('cannot delete obsmarkers in the middle ' - 'of transaction.')) - - with repo.lock(): - n = repair.deleteobsmarkers(repo.obsstore, indices) - ui.write(_('deleted %i obsolescence markers\n') % n) - - return - - if precursor is not None: - if opts['rev']: - raise error.Abort('cannot select revision when creating marker') - metadata = {} - metadata['user'] = opts['user'] or ui.username() - succs = tuple(parsenodeid(succ) for succ in successors) - l = repo.lock() - try: - tr = repo.transaction('debugobsolete') - try: - date = opts.get('date') - if date: - date = util.parsedate(date) - else: - date = None - prec = parsenodeid(precursor) - parents = None - if opts['record_parents']: - if prec not in repo.unfiltered(): - raise error.Abort('cannot used --record-parents on ' - 'unknown changesets') - parents = repo.unfiltered()[prec].parents() - parents = tuple(p.node() for p in parents) - repo.obsstore.create(tr, prec, succs, opts['flags'], - parents=parents, date=date, - metadata=metadata) - tr.close() - except ValueError as exc: - raise error.Abort(_('bad obsmarker input: %s') % exc) - finally: - tr.release() - finally: - l.release() - else: - if opts['rev']: - revs = scmutil.revrange(repo, opts['rev']) - nodes = [repo[r].node() for r in revs] - markers = list(obsolete.getmarkers(repo, nodes=nodes)) - markers.sort(key=lambda x: x._data) - else: - markers = obsolete.getmarkers(repo) - - markerstoiter = markers - isrelevant = lambda m: True - if opts.get('rev') and opts.get('index'): - markerstoiter = obsolete.getmarkers(repo) - markerset = set(markers) - isrelevant = lambda m: m in markerset - - fm = ui.formatter('debugobsolete', opts) - for i, m in enumerate(markerstoiter): - if not isrelevant(m): - # marker can be irrelevant when we're iterating over a set - # of markers (markerstoiter) which is bigger than the set - # of markers we want to display (markers) - # this can happen if both --index and --rev options are - # provided and thus we need to iterate over all of the markers - # to get the correct indices, but only display the ones that - # are relevant to --rev value - continue - fm.startitem() - ind = i if opts.get('index') else None - cmdutil.showmarker(fm, m, index=ind) - fm.end() - -@command('debugpathcomplete', - [('f', 'full', None, _('complete an entire path')), - ('n', 'normal', None, _('show only normal files')), - ('a', 'added', None, _('show only added files')), - ('r', 'removed', None, _('show only removed files'))], - _('FILESPEC...')) -def debugpathcomplete(ui, repo, *specs, **opts): - '''complete part or all of a tracked path - - This command supports shells that offer path name completion. It - currently completes only files already known to the dirstate. - - Completion extends only to the next path segment unless - --full is specified, in which case entire paths are used.''' - - def complete(path, acceptable): - dirstate = repo.dirstate - spec = os.path.normpath(os.path.join(pycompat.getcwd(), path)) - rootdir = repo.root + pycompat.ossep - if spec != repo.root and not spec.startswith(rootdir): - return [], [] - if os.path.isdir(spec): - spec += '/' - spec = spec[len(rootdir):] - fixpaths = pycompat.ossep != '/' - if fixpaths: - spec = spec.replace(pycompat.ossep, '/') - speclen = len(spec) - fullpaths = opts['full'] - files, dirs = set(), set() - adddir, addfile = dirs.add, files.add - for f, st in dirstate.iteritems(): - if f.startswith(spec) and st[0] in acceptable: - if fixpaths: - f = f.replace('/', pycompat.ossep) - if fullpaths: - addfile(f) - continue - s = f.find(pycompat.ossep, speclen) - if s >= 0: - adddir(f[:s]) - else: - addfile(f) - return files, dirs - - acceptable = '' - if opts['normal']: - acceptable += 'nm' - if opts['added']: - acceptable += 'a' - if opts['removed']: - acceptable += 'r' - cwd = repo.getcwd() - if not specs: - specs = ['.'] - - files, dirs = set(), set() - for spec in specs: - f, d = complete(spec, acceptable or 'nmar') - files.update(f) - dirs.update(d) - files.update(dirs) - ui.write('\n'.join(repo.pathto(p, cwd) for p in sorted(files))) - ui.write('\n') - -@command('debugpushkey', [], _('REPO NAMESPACE [KEY OLD NEW]'), norepo=True) -def debugpushkey(ui, repopath, namespace, *keyinfo, **opts): - '''access the pushkey key/value protocol - - With two args, list the keys in the given namespace. - - With five args, set a key to new if it currently is set to old. - Reports success or failure. - ''' - - target = hg.peer(ui, {}, repopath) - if keyinfo: - key, old, new = keyinfo - r = target.pushkey(namespace, key, old, new) - ui.status(str(r) + '\n') - return not r - else: - for k, v in sorted(target.listkeys(namespace).iteritems()): - ui.write("%s\t%s\n" % (k.encode('string-escape'), - v.encode('string-escape'))) - -@command('debugpvec', [], _('A B')) -def debugpvec(ui, repo, a, b=None): - ca = scmutil.revsingle(repo, a) - cb = scmutil.revsingle(repo, b) - pa = pvec.ctxpvec(ca) - pb = pvec.ctxpvec(cb) - if pa == pb: - rel = "=" - elif pa > pb: - rel = ">" - elif pa < pb: - rel = "<" - elif pa | pb: - rel = "|" - ui.write(_("a: %s\n") % pa) - ui.write(_("b: %s\n") % pb) - ui.write(_("depth(a): %d depth(b): %d\n") % (pa._depth, pb._depth)) - ui.write(_("delta: %d hdist: %d distance: %d relation: %s\n") % - (abs(pa._depth - pb._depth), pvec._hamming(pa._vec, pb._vec), - pa.distance(pb), rel)) - -@command('debugrebuilddirstate|debugrebuildstate', - [('r', 'rev', '', _('revision to rebuild to'), _('REV')), - ('', 'minimal', None, _('only rebuild files that are inconsistent with ' - 'the working copy parent')), - ], - _('[-r REV]')) -def debugrebuilddirstate(ui, repo, rev, **opts): - """rebuild the dirstate as it would look like for the given revision - - If no revision is specified the first current parent will be used. - - The dirstate will be set to the files of the given revision. - The actual working directory content or existing dirstate - information such as adds or removes is not considered. - - ``minimal`` will only rebuild the dirstate status for files that claim to be - tracked but are not in the parent manifest, or that exist in the parent - manifest but are not in the dirstate. It will not change adds, removes, or - modified files that are in the working copy parent. - - One use of this command is to make the next :hg:`status` invocation - check the actual file content. - """ - ctx = scmutil.revsingle(repo, rev) - with repo.wlock(): - dirstate = repo.dirstate - changedfiles = None - # See command doc for what minimal does. - if opts.get('minimal'): - manifestfiles = set(ctx.manifest().keys()) - dirstatefiles = set(dirstate) - manifestonly = manifestfiles - dirstatefiles - dsonly = dirstatefiles - manifestfiles - dsnotadded = set(f for f in dsonly if dirstate[f] != 'a') - changedfiles = manifestonly | dsnotadded - - dirstate.rebuild(ctx.node(), ctx.manifest(), changedfiles) - -@command('debugrebuildfncache', [], '') -def debugrebuildfncache(ui, repo): - """rebuild the fncache file""" - repair.rebuildfncache(ui, repo) - -@command('debugrename', - [('r', 'rev', '', _('revision to debug'), _('REV'))], - _('[-r REV] FILE')) -def debugrename(ui, repo, file1, *pats, **opts): - """dump rename information""" - - ctx = scmutil.revsingle(repo, opts.get('rev')) - m = scmutil.match(ctx, (file1,) + pats, opts) - for abs in ctx.walk(m): - fctx = ctx[abs] - o = fctx.filelog().renamed(fctx.filenode()) - rel = m.rel(abs) - if o: - ui.write(_("%s renamed from %s:%s\n") % (rel, o[0], hex(o[1]))) - else: - ui.write(_("%s not renamed\n") % rel) - -@command('debugrevlog', debugrevlogopts + - [('d', 'dump', False, _('dump index data'))], - _('-c|-m|FILE'), - optionalrepo=True) -def debugrevlog(ui, repo, file_=None, **opts): - """show data and statistics about a revlog""" - r = cmdutil.openrevlog(repo, 'debugrevlog', file_, opts) - - if opts.get("dump"): - numrevs = len(r) - ui.write(("# rev p1rev p2rev start end deltastart base p1 p2" - " rawsize totalsize compression heads chainlen\n")) - ts = 0 - heads = set() - - for rev in xrange(numrevs): - dbase = r.deltaparent(rev) - if dbase == -1: - dbase = rev - cbase = r.chainbase(rev) - clen = r.chainlen(rev) - p1, p2 = r.parentrevs(rev) - rs = r.rawsize(rev) - ts = ts + rs - heads -= set(r.parentrevs(rev)) - heads.add(rev) - try: - compression = ts / r.end(rev) - except ZeroDivisionError: - compression = 0 - ui.write("%5d %5d %5d %5d %5d %10d %4d %4d %4d %7d %9d " - "%11d %5d %8d\n" % - (rev, p1, p2, r.start(rev), r.end(rev), - r.start(dbase), r.start(cbase), - r.start(p1), r.start(p2), - rs, ts, compression, len(heads), clen)) - return 0 - - v = r.version - format = v & 0xFFFF - flags = [] - gdelta = False - if v & revlog.REVLOGNGINLINEDATA: - flags.append('inline') - if v & revlog.REVLOGGENERALDELTA: - gdelta = True - flags.append('generaldelta') - if not flags: - flags = ['(none)'] - - nummerges = 0 - numfull = 0 - numprev = 0 - nump1 = 0 - nump2 = 0 - numother = 0 - nump1prev = 0 - nump2prev = 0 - chainlengths = [] - - datasize = [None, 0, 0] - fullsize = [None, 0, 0] - deltasize = [None, 0, 0] - chunktypecounts = {} - chunktypesizes = {} - - def addsize(size, l): - if l[0] is None or size < l[0]: - l[0] = size - if size > l[1]: - l[1] = size - l[2] += size - - numrevs = len(r) - for rev in xrange(numrevs): - p1, p2 = r.parentrevs(rev) - delta = r.deltaparent(rev) - if format > 0: - addsize(r.rawsize(rev), datasize) - if p2 != nullrev: - nummerges += 1 - size = r.length(rev) - if delta == nullrev: - chainlengths.append(0) - numfull += 1 - addsize(size, fullsize) - else: - chainlengths.append(chainlengths[delta] + 1) - addsize(size, deltasize) - if delta == rev - 1: - numprev += 1 - if delta == p1: - nump1prev += 1 - elif delta == p2: - nump2prev += 1 - elif delta == p1: - nump1 += 1 - elif delta == p2: - nump2 += 1 - elif delta != nullrev: - numother += 1 - - # Obtain data on the raw chunks in the revlog. - chunk = r._chunkraw(rev, rev)[1] - if chunk: - chunktype = chunk[0] - else: - chunktype = 'empty' - - if chunktype not in chunktypecounts: - chunktypecounts[chunktype] = 0 - chunktypesizes[chunktype] = 0 - - chunktypecounts[chunktype] += 1 - chunktypesizes[chunktype] += size - - # Adjust size min value for empty cases - for size in (datasize, fullsize, deltasize): - if size[0] is None: - size[0] = 0 - - numdeltas = numrevs - numfull - numoprev = numprev - nump1prev - nump2prev - totalrawsize = datasize[2] - datasize[2] /= numrevs - fulltotal = fullsize[2] - fullsize[2] /= numfull - deltatotal = deltasize[2] - if numrevs - numfull > 0: - deltasize[2] /= numrevs - numfull - totalsize = fulltotal + deltatotal - avgchainlen = sum(chainlengths) / numrevs - maxchainlen = max(chainlengths) - compratio = 1 - if totalsize: - compratio = totalrawsize / totalsize - - basedfmtstr = '%%%dd\n' - basepcfmtstr = '%%%dd %s(%%5.2f%%%%)\n' - - def dfmtstr(max): - return basedfmtstr % len(str(max)) - def pcfmtstr(max, padding=0): - return basepcfmtstr % (len(str(max)), ' ' * padding) - - def pcfmt(value, total): - if total: - return (value, 100 * float(value) / total) - else: - return value, 100.0 - - ui.write(('format : %d\n') % format) - ui.write(('flags : %s\n') % ', '.join(flags)) - - ui.write('\n') - fmt = pcfmtstr(totalsize) - fmt2 = dfmtstr(totalsize) - ui.write(('revisions : ') + fmt2 % numrevs) - ui.write((' merges : ') + fmt % pcfmt(nummerges, numrevs)) - ui.write((' normal : ') + fmt % pcfmt(numrevs - nummerges, numrevs)) - ui.write(('revisions : ') + fmt2 % numrevs) - ui.write((' full : ') + fmt % pcfmt(numfull, numrevs)) - ui.write((' deltas : ') + fmt % pcfmt(numdeltas, numrevs)) - ui.write(('revision size : ') + fmt2 % totalsize) - ui.write((' full : ') + fmt % pcfmt(fulltotal, totalsize)) - ui.write((' deltas : ') + fmt % pcfmt(deltatotal, totalsize)) - - def fmtchunktype(chunktype): - if chunktype == 'empty': - return ' %s : ' % chunktype - elif chunktype in string.ascii_letters: - return ' 0x%s (%s) : ' % (hex(chunktype), chunktype) - else: - return ' 0x%s : ' % hex(chunktype) - - ui.write('\n') - ui.write(('chunks : ') + fmt2 % numrevs) - for chunktype in sorted(chunktypecounts): - ui.write(fmtchunktype(chunktype)) - ui.write(fmt % pcfmt(chunktypecounts[chunktype], numrevs)) - ui.write(('chunks size : ') + fmt2 % totalsize) - for chunktype in sorted(chunktypecounts): - ui.write(fmtchunktype(chunktype)) - ui.write(fmt % pcfmt(chunktypesizes[chunktype], totalsize)) - - ui.write('\n') - fmt = dfmtstr(max(avgchainlen, compratio)) - ui.write(('avg chain length : ') + fmt % avgchainlen) - ui.write(('max chain length : ') + fmt % maxchainlen) - ui.write(('compression ratio : ') + fmt % compratio) - - if format > 0: - ui.write('\n') - ui.write(('uncompressed data size (min/max/avg) : %d / %d / %d\n') - % tuple(datasize)) - ui.write(('full revision size (min/max/avg) : %d / %d / %d\n') - % tuple(fullsize)) - ui.write(('delta size (min/max/avg) : %d / %d / %d\n') - % tuple(deltasize)) - - if numdeltas > 0: - ui.write('\n') - fmt = pcfmtstr(numdeltas) - fmt2 = pcfmtstr(numdeltas, 4) - ui.write(('deltas against prev : ') + fmt % pcfmt(numprev, numdeltas)) - if numprev > 0: - ui.write((' where prev = p1 : ') + fmt2 % pcfmt(nump1prev, - numprev)) - ui.write((' where prev = p2 : ') + fmt2 % pcfmt(nump2prev, - numprev)) - ui.write((' other : ') + fmt2 % pcfmt(numoprev, - numprev)) - if gdelta: - ui.write(('deltas against p1 : ') - + fmt % pcfmt(nump1, numdeltas)) - ui.write(('deltas against p2 : ') - + fmt % pcfmt(nump2, numdeltas)) - ui.write(('deltas against other : ') + fmt % pcfmt(numother, - numdeltas)) - -@command('debugrevspec', - [('', 'optimize', None, - _('print parsed tree after optimizing (DEPRECATED)')), - ('p', 'show-stage', [], - _('print parsed tree at the given stage'), _('NAME')), - ('', 'no-optimized', False, _('evaluate tree without optimization')), - ('', 'verify-optimized', False, _('verify optimized result')), - ], - ('REVSPEC')) -def debugrevspec(ui, repo, expr, **opts): - """parse and apply a revision specification - - Use -p/--show-stage option to print the parsed tree at the given stages. - Use -p all to print tree at every stage. - - Use --verify-optimized to compare the optimized result with the unoptimized - one. Returns 1 if the optimized result differs. - """ - stages = [ - ('parsed', lambda tree: tree), - ('expanded', lambda tree: revset.expandaliases(ui, tree)), - ('concatenated', revset.foldconcat), - ('analyzed', revset.analyze), - ('optimized', revset.optimize), - ] - if opts['no_optimized']: - stages = stages[:-1] - if opts['verify_optimized'] and opts['no_optimized']: - raise error.Abort(_('cannot use --verify-optimized with ' - '--no-optimized')) - stagenames = set(n for n, f in stages) - - showalways = set() - showchanged = set() - if ui.verbose and not opts['show_stage']: - # show parsed tree by --verbose (deprecated) - showalways.add('parsed') - showchanged.update(['expanded', 'concatenated']) - if opts['optimize']: - showalways.add('optimized') - if opts['show_stage'] and opts['optimize']: - raise error.Abort(_('cannot use --optimize with --show-stage')) - if opts['show_stage'] == ['all']: - showalways.update(stagenames) - else: - for n in opts['show_stage']: - if n not in stagenames: - raise error.Abort(_('invalid stage name: %s') % n) - showalways.update(opts['show_stage']) - - treebystage = {} - printedtree = None - tree = revset.parse(expr, lookup=repo.__contains__) - for n, f in stages: - treebystage[n] = tree = f(tree) - if n in showalways or (n in showchanged and tree != printedtree): - if opts['show_stage'] or n != 'parsed': - ui.write(("* %s:\n") % n) - ui.write(revset.prettyformat(tree), "\n") - printedtree = tree - - if opts['verify_optimized']: - arevs = revset.makematcher(treebystage['analyzed'])(repo) - brevs = revset.makematcher(treebystage['optimized'])(repo) - if ui.verbose: - ui.note(("* analyzed set:\n"), revset.prettyformatset(arevs), "\n") - ui.note(("* optimized set:\n"), revset.prettyformatset(brevs), "\n") - arevs = list(arevs) - brevs = list(brevs) - if arevs == brevs: - return 0 - ui.write(('--- analyzed\n'), label='diff.file_a') - ui.write(('+++ optimized\n'), label='diff.file_b') - sm = difflib.SequenceMatcher(None, arevs, brevs) - for tag, alo, ahi, blo, bhi in sm.get_opcodes(): - if tag in ('delete', 'replace'): - for c in arevs[alo:ahi]: - ui.write('-%s\n' % c, label='diff.deleted') - if tag in ('insert', 'replace'): - for c in brevs[blo:bhi]: - ui.write('+%s\n' % c, label='diff.inserted') - if tag == 'equal': - for c in arevs[alo:ahi]: - ui.write(' %s\n' % c) - return 1 - - func = revset.makematcher(tree) - revs = func(repo) - if ui.verbose: - ui.note(("* set:\n"), revset.prettyformatset(revs), "\n") - for c in revs: - ui.write("%s\n" % c) - -@command('debugsetparents', [], _('REV1 [REV2]')) -def debugsetparents(ui, repo, rev1, rev2=None): - """manually set the parents of the current working directory - - This is useful for writing repository conversion tools, but should - be used with care. For example, neither the working directory nor the - dirstate is updated, so file status may be incorrect after running this - command. - - Returns 0 on success. - """ - - r1 = scmutil.revsingle(repo, rev1).node() - r2 = scmutil.revsingle(repo, rev2, 'null').node() - - with repo.wlock(): - repo.setparents(r1, r2) - -@command('debugdirstate|debugstate', - [('', 'nodates', None, _('do not display the saved mtime')), - ('', 'datesort', None, _('sort by saved mtime'))], - _('[OPTION]...')) -def debugstate(ui, repo, **opts): - """show the contents of the current dirstate""" - - nodates = opts.get('nodates') - datesort = opts.get('datesort') - - timestr = "" - if datesort: - keyfunc = lambda x: (x[1][3], x[0]) # sort by mtime, then by filename - else: - keyfunc = None # sort by filename - for file_, ent in sorted(repo.dirstate._map.iteritems(), key=keyfunc): - if ent[3] == -1: - timestr = 'unset ' - elif nodates: - timestr = 'set ' - else: - timestr = time.strftime("%Y-%m-%d %H:%M:%S ", - time.localtime(ent[3])) - if ent[1] & 0o20000: - mode = 'lnk' - else: - mode = '%3o' % (ent[1] & 0o777 & ~util.umask) - ui.write("%c %s %10d %s%s\n" % (ent[0], mode, ent[2], timestr, file_)) - for f in repo.dirstate.copies(): - ui.write(_("copy: %s -> %s\n") % (repo.dirstate.copied(f), f)) - -@command('debugsub', - [('r', 'rev', '', - _('revision to check'), _('REV'))], - _('[-r REV] [REV]')) -def debugsub(ui, repo, rev=None): - ctx = scmutil.revsingle(repo, rev, None) - for k, v in sorted(ctx.substate.items()): - ui.write(('path %s\n') % k) - ui.write((' source %s\n') % v[0]) - ui.write((' revision %s\n') % v[1]) - -@command('debugsuccessorssets', - [], - _('[REV]')) -def debugsuccessorssets(ui, repo, *revs): - """show set of successors for revision - - A successors set of changeset A is a consistent group of revisions that - succeed A. It contains non-obsolete changesets only. - - In most cases a changeset A has a single successors set containing a single - successor (changeset A replaced by A'). - - A changeset that is made obsolete with no successors are called "pruned". - Such changesets have no successors sets at all. - - A changeset that has been "split" will have a successors set containing - more than one successor. - - A changeset that has been rewritten in multiple different ways is called - "divergent". Such changesets have multiple successor sets (each of which - may also be split, i.e. have multiple successors). - - Results are displayed as follows:: - - <rev1> - <successors-1A> - <rev2> - <successors-2A> - <successors-2B1> <successors-2B2> <successors-2B3> - - Here rev2 has two possible (i.e. divergent) successors sets. The first - holds one element, whereas the second holds three (i.e. the changeset has - been split). - """ - # passed to successorssets caching computation from one call to another - cache = {} - ctx2str = str - node2str = short - if ui.debug(): - def ctx2str(ctx): - return ctx.hex() - node2str = hex - for rev in scmutil.revrange(repo, revs): - ctx = repo[rev] - ui.write('%s\n'% ctx2str(ctx)) - for succsset in obsolete.successorssets(repo, ctx.node(), cache): - if succsset: - ui.write(' ') - ui.write(node2str(succsset[0])) - for node in succsset[1:]: - ui.write(' ') - ui.write(node2str(node)) - ui.write('\n') - -@command('debugtemplate', - [('r', 'rev', [], _('apply template on changesets'), _('REV')), - ('D', 'define', [], _('define template keyword'), _('KEY=VALUE'))], - _('[-r REV]... [-D KEY=VALUE]... TEMPLATE'), - optionalrepo=True) -def debugtemplate(ui, repo, tmpl, **opts): - """parse and apply a template - - If -r/--rev is given, the template is processed as a log template and - applied to the given changesets. Otherwise, it is processed as a generic - template. - - Use --verbose to print the parsed tree. - """ - revs = None - if opts['rev']: - if repo is None: - raise error.RepoError(_('there is no Mercurial repository here ' - '(.hg not found)')) - revs = scmutil.revrange(repo, opts['rev']) - - props = {} - for d in opts['define']: - try: - k, v = (e.strip() for e in d.split('=', 1)) - if not k: - raise ValueError - props[k] = v - except ValueError: - raise error.Abort(_('malformed keyword definition: %s') % d) - - if ui.verbose: - aliases = ui.configitems('templatealias') - tree = templater.parse(tmpl) - ui.note(templater.prettyformat(tree), '\n') - newtree = templater.expandaliases(tree, aliases) - if newtree != tree: - ui.note(("* expanded:\n"), templater.prettyformat(newtree), '\n') - - mapfile = None - if revs is None: - k = 'debugtemplate' - t = formatter.maketemplater(ui, k, tmpl) - ui.write(templater.stringify(t(k, **props))) - else: - displayer = cmdutil.changeset_templater(ui, repo, None, opts, tmpl, - mapfile, buffered=False) - for r in revs: - displayer.show(repo[r], **props) - displayer.close() - -@command('debugwalk', walkopts, _('[OPTION]... [FILE]...'), inferrepo=True) -def debugwalk(ui, repo, *pats, **opts): - """show how files match on given patterns""" - m = scmutil.match(repo[None], pats, opts) - items = list(repo.walk(m)) - if not items: - return - f = lambda fn: fn - if ui.configbool('ui', 'slash') and pycompat.ossep != '/': - f = lambda fn: util.normpath(fn) - fmt = 'f %%-%ds %%-%ds %%s' % ( - max([len(abs) for abs in items]), - max([len(m.rel(abs)) for abs in items])) - for abs in items: - line = fmt % (abs, f(m.rel(abs)), m.exact(abs) and 'exact' or '') - ui.write("%s\n" % line.rstrip()) - -@command('debugwireargs', - [('', 'three', '', 'three'), - ('', 'four', '', 'four'), - ('', 'five', '', 'five'), - ] + remoteopts, - _('REPO [OPTIONS]... [ONE [TWO]]'), - norepo=True) -def debugwireargs(ui, repopath, *vals, **opts): - repo = hg.peer(ui, opts, repopath) - for opt in remoteopts: - del opts[opt[1]] - args = {} - for k, v in opts.iteritems(): - if v: - args[k] = v - # run twice to check that we don't mess up the stream for the next command - res1 = repo.debugwireargs(*vals, **args) - res2 = repo.debugwireargs(*vals, **args) - ui.write("%s\n" % res1) - if res1 != res2: - ui.warn("%s\n" % res2) - @command('^diff', [('r', 'rev', [], _('revision'), _('REV')), ('c', 'change', '', _('change made by revision'), _('REV')) @@ -3119,6 +1957,7 @@ diffopts = patch.diffallopts(ui, opts) m = scmutil.match(repo[node2], pats, opts) + ui.pager('diff') cmdutil.diffordiffstat(ui, repo, diffopts, node1, node2, m, stat=stat, listsubrepos=opts.get('subrepos'), root=opts.get('root')) @@ -3190,6 +2029,7 @@ Returns 0 on success. """ + opts = pycompat.byteskwargs(opts) changesets += tuple(opts.get('rev', [])) if not changesets: changesets = ['.'] @@ -3200,6 +2040,7 @@ ui.note(_('exporting patches:\n')) else: ui.note(_('exporting patch:\n')) + ui.pager('export') cmdutil.export(repo, revs, template=opts.get('output'), switch_parent=opts.get('switch_parent'), opts=patch.diffallopts(ui, opts)) @@ -3253,7 +2094,7 @@ Returns 0 if a match is found, 1 otherwise. """ - ctx = scmutil.revsingle(repo, opts.get('rev'), None) + ctx = scmutil.revsingle(repo, opts.get(r'rev'), None) end = '\n' if opts.get('print0'): @@ -3261,6 +2102,7 @@ fmt = '%s' + end m = scmutil.match(ctx, pats, opts) + ui.pager('files') with ui.formatter('files', opts) as fm: return cmdutil.files(ui, ctx, m, fm, fmt, opts.get('subrepos')) @@ -3552,7 +2394,7 @@ # remove state when we complete successfully if not opts.get('dry_run'): - util.unlinkpath(repo.join('graftstate'), ignoremissing=True) + repo.vfs.unlinkpath('graftstate', ignoremissing=True) return 0 @@ -3782,6 +2624,7 @@ except error.LookupError: pass + ui.pager('grep') fm = ui.formatter('grep', opts) for ctx in cmdutil.walkchangerevs(repo, matchfn, opts, prep): rev = ctx.rev() @@ -3872,6 +2715,7 @@ if not heads: return 1 + ui.pager('heads') heads = sorted(heads, key=lambda x: -x.rev()) displayer = cmdutil.show_changeset(ui, repo, opts) for ctx in heads: @@ -3897,11 +2741,6 @@ Returns 0 if successful. """ - textwidth = ui.configint('ui', 'textwidth', 78) - termwidth = ui.termwidth() - 2 - if textwidth <= 0 or termwidth < textwidth: - textwidth = termwidth - keep = opts.get('system') or [] if len(keep) == 0: if pycompat.sysplatform.startswith('win'): @@ -3916,36 +2755,8 @@ if ui.verbose: keep.append('verbose') - section = None - subtopic = None - if name and '.' in name: - name, remaining = name.split('.', 1) - remaining = encoding.lower(remaining) - if '.' in remaining: - subtopic, section = remaining.split('.', 1) - else: - if name in help.subtopics: - subtopic = remaining - else: - section = remaining - - text = help.help_(ui, name, subtopic=subtopic, **opts) - - formatted, pruned = minirst.format(text, textwidth, keep=keep, - section=section) - - # We could have been given a weird ".foo" section without a name - # to look for, or we could have simply failed to found "foo.bar" - # because bar isn't a section of foo - if section and not (formatted and name): - raise error.Abort(_("help section not found")) - - if 'verbose' in pruned: - keep.append('omitted') - else: - keep.append('notomitted') - formatted, pruned = minirst.format(text, textwidth, keep=keep, - section=section) + formatted = help.formattedhelp(ui, name, keep=keep, **opts) + ui.pager('help') ui.write(formatted) @@ -4127,8 +2938,9 @@ Import a list of patches and commit them individually (unless --no-commit is specified). - To read a patch from standard input, use "-" as the patch name. If - a URL is specified, the patch will be downloaded from there. + To read a patch from standard input (stdin), use "-" as the patch + name. If a URL is specified, the patch will be downloaded from + there. Import first applies changes to the working directory (unless --bypass is specified), import will abort if there are outstanding @@ -4198,6 +3010,10 @@ hg import incoming-patches.mbox + - import patches from stdin:: + + hg import - + - attempt to exactly restore an exported changeset (not always possible):: @@ -4372,6 +3188,7 @@ Returns 0 if there are incoming changes, 1 otherwise. """ + opts = pycompat.byteskwargs(opts) if opts.get('graph'): cmdutil.checkunsupportedgraphflags([], opts) def display(other, chlist, displayer): @@ -4392,6 +3209,7 @@ if 'bookmarks' not in other.listkeys('namespaces'): ui.warn(_("remote doesn't support bookmarks\n")) return 0 + ui.pager('incoming') ui.status(_('comparing with %s\n') % util.hidepassword(source)) return bookmarks.incoming(ui, repo, other) @@ -4458,6 +3276,7 @@ m = scmutil.match(ctx, pats, opts, default='relglob', badfn=lambda x, y: False) + ui.pager('locate') for abs in ctx.matches(m): if opts.get('fullpath'): ui.write(repo.wjoin(abs), end) @@ -4588,12 +3407,13 @@ Returns 0 on success. """ + opts = pycompat.byteskwargs(opts) if opts.get('follow') and opts.get('rev'): - opts['rev'] = [revset.formatspec('reverse(::%lr)', opts.get('rev'))] + opts['rev'] = [revsetlang.formatspec('reverse(::%lr)', opts.get('rev'))] del opts['follow'] if opts.get('graph'): - return cmdutil.graphlog(ui, repo, *pats, **opts) + return cmdutil.graphlog(ui, repo, pats, opts) revs, expr, filematcher = cmdutil.getlogrevs(repo, pats, opts) limit = cmdutil.loglimit(opts) @@ -4606,6 +3426,7 @@ endrev = scmutil.revrange(repo, opts.get('rev')).max() + 1 getrenamed = templatekw.getrenamedfn(repo, endrev=endrev) + ui.pager('log') displayer = cmdutil.show_changeset(ui, repo, opts, buffered=True) for rev in revs: if count == limit: @@ -4648,7 +3469,6 @@ Returns 0 on success. """ - fm = ui.formatter('manifest', opts) if opts.get('all'): @@ -4664,6 +3484,7 @@ for fn, b, size in repo.store.datafiles(): if size != 0 and fn[-slen:] == suffix and fn[:plen] == prefix: res.append(fn[plen:-slen]) + ui.pager('manifest') for f in res: fm.startitem() fm.write("path", '%s\n', f) @@ -4680,6 +3501,7 @@ mode = {'l': '644', 'x': '755', '': '644'} ctx = scmutil.revsingle(repo, node) mf = ctx.manifest() + ui.pager('manifest') for f in ctx: fm.startitem() fl = ctx[f].flags() @@ -4812,6 +3634,7 @@ return revdag = cmdutil.graphrevs(repo, o, opts) + ui.pager('outgoing') displayer = cmdutil.show_changeset(ui, repo, opts, buffered=True) cmdutil.displaygraph(ui, repo, revdag, displayer, graphmod.asciiedges) cmdutil.outgoinghooks(ui, repo, other, opts, o) @@ -4825,6 +3648,7 @@ ui.warn(_("remote doesn't support bookmarks\n")) return 0 ui.status(_('comparing with %s\n') % util.hidepassword(dest)) + ui.pager('outgoing') return bookmarks.outgoing(ui, repo, other) repo._subtoppath = ui.expandpath(dest or 'default-push', dest or 'default') @@ -4921,6 +3745,7 @@ Returns 0 on success. """ + ui.pager('paths') if search: pathitems = [(name, path) for name, path in ui.paths.iteritems() if name == search] @@ -5113,6 +3938,12 @@ Returns 0 on success, 1 if an update had unresolved files. """ + + if ui.configbool('commands', 'update.requiredest') and opts.get('update'): + msg = _('update destination required by configuration') + hint = _('use hg pull followed by hg update DEST') + raise error.Abort(msg, hint=hint) + source, branches = hg.parseurl(ui.expandpath(source), opts.get('branch')) ui.status(_('pulling from %s\n') % util.hidepassword(source)) other = hg.peer(repo, opts, source) @@ -5268,7 +4099,7 @@ elif path.pushrev: # It doesn't make any sense to specify ancestor revisions. So limit # to DAG heads to make discovery simpler. - expr = revset.formatspec('heads(%r)', path.pushrev) + expr = revsetlang.formatspec('heads(%r)', path.pushrev) revs = scmutil.revrange(repo, [expr]) revs = [repo[rev].node() for rev in revs] if not revs: @@ -5434,6 +4265,8 @@ - :hg:`resolve -l`: list files which had or still have conflicts. In the printed list, ``U`` = unresolved and ``R`` = resolved. + You can use ``set:unresolved()`` or ``set:resolved()`` to filter + the list. See :hg:`help filesets` for details. .. note:: @@ -5457,6 +4290,7 @@ hint=('use --all to re-merge all unresolved files')) if show: + ui.pager('resolve') fm = ui.formatter('resolve', opts) ms = mergemod.mergestate.read(repo) m = scmutil.match(repo[None], pats, opts) @@ -5780,12 +4614,13 @@ ('', 'webdir-conf', '', _('name of the hgweb config file (DEPRECATED)'), _('FILE')), ('', 'pid-file', '', _('name of file to write process ID to'), _('FILE')), - ('', 'stdio', None, _('for remote clients')), - ('', 'cmdserver', '', _('for remote clients'), _('MODE')), + ('', 'stdio', None, _('for remote clients (ADVANCED)')), + ('', 'cmdserver', '', _('for remote clients (ADVANCED)'), _('MODE')), ('t', 'templates', '', _('web templates to use'), _('TEMPLATE')), ('', 'style', '', _('template style to use'), _('STYLE')), ('6', 'ipv6', None, _('use IPv6 in addition to IPv4')), - ('', 'certificate', '', _('SSL certificate file'), _('FILE'))], + ('', 'certificate', '', _('SSL certificate file'), _('FILE'))] + + subrepoopts, _('[OPTION]...'), optionalrepo=True) def serve(ui, repo, **opts): @@ -5904,6 +4739,7 @@ Returns 0 on success. """ + opts = pycompat.byteskwargs(opts) revs = opts.get('rev') change = opts.get('change') @@ -5916,7 +4752,7 @@ else: node1, node2 = scmutil.revpair(repo, revs) - if pats: + if pats or ui.configbool('commands', 'status.relative'): cwd = repo.getcwd() else: cwd = '' @@ -5940,12 +4776,13 @@ stat = repo.status(node1, node2, m, 'ignored' in show, 'clean' in show, 'unknown' in show, opts.get('subrepos')) - changestates = zip(states, 'MAR!?IC', stat) + changestates = zip(states, pycompat.iterbytestr('MAR!?IC'), stat) if (opts.get('all') or opts.get('copies') or ui.configbool('ui', 'statuscopies')) and not opts.get('no_status'): copy = copies.pathcopies(repo[node1], repo[node2], m) + ui.pager('status') fm = ui.formatter('status', opts) fmt = '%s' + end showchar = not opts.get('no_status') @@ -5976,6 +4813,7 @@ Returns 0 on success. """ + ui.pager('summary') ctx = repo[None] parents = ctx.parents() pnode = parents[0].node() @@ -5996,7 +4834,7 @@ # label with log.changeset (instead of log.parent) since this # shows a working directory parent *changeset*: # i18n: column positioning for "hg summary" - ui.write(_('parent: %d:%s ') % (p.rev(), str(p)), + ui.write(_('parent: %d:%s ') % (p.rev(), p), label=cmdutil._changesetlabels(p)) ui.write(' '.join(p.tags()), label='log.tag') if p.bookmarks(): @@ -6006,6 +4844,8 @@ ui.write(_(' (empty repository)')) else: ui.write(_(' (no revision checked out)')) + if p.obsolete(): + ui.write(_(' (obsolete)')) if p.troubled(): ui.write(' (' + ', '.join(ui.label(trouble, 'trouble.%s' % trouble) @@ -6352,8 +5192,8 @@ scmutil.revsingle(repo, rev_).rev() == nullrev): raise error.Abort(_("cannot tag null revision")) - repo.tag(names, r, message, opts.get('local'), opts.get('user'), date, - editor=editor) + tagsmod.tag(repo, names, r, message, opts.get('local'), + opts.get('user'), date, editor=editor) finally: release(lock, wlock) @@ -6368,6 +5208,7 @@ Returns 0 on success. """ + ui.pager('tags') fm = ui.formatter('tags', opts) hexfunc = fm.hexfunc tagtype = "" @@ -6420,10 +5261,9 @@ _('update to new branch head if changesets were unbundled'))], _('[-u] FILE...')) def unbundle(ui, repo, fname1, *fnames, **opts): - """apply one or more changegroup files - - Apply one or more compressed changegroup files generated by the - bundle command. + """apply one or more bundle files + + Apply one or more bundle files generated by :hg:`bundle`. Returns 0 on success, 1 if an update has unresolved files. """ @@ -6464,12 +5304,13 @@ @command('^update|up|checkout|co', [('C', 'clean', None, _('discard uncommitted changes (no backup)')), ('c', 'check', None, _('require clean working directory')), + ('m', 'merge', None, _('merge uncommitted changes')), ('d', 'date', '', _('tipmost revision matching date'), _('DATE')), ('r', 'rev', '', _('revision'), _('REV')) ] + mergetoolopts, - _('[-c] [-C] [-d DATE] [[-r] REV]')) + _('[-C|-c|-m] [-d DATE] [[-r] REV]')) def update(ui, repo, node=None, rev=None, clean=False, date=None, check=False, - tool=None): + merge=None, tool=None): """update working directory (or switch revisions) Update the repository's working directory to the specified @@ -6488,10 +5329,11 @@ .. container:: verbose - The following rules apply when the working directory contains - uncommitted changes: - - 1. If neither -c/--check nor -C/--clean is specified, and if + The -C/--clean, -c/--check, and -m/--merge options control what + happens if the working directory contains uncommitted changes. + At most of one of them can be specified. + + 1. If no option is specified, and if the requested changeset is an ancestor or descendant of the working directory's parent, the uncommitted changes are merged into the requested changeset and the merged @@ -6500,10 +5342,14 @@ branch), the update is aborted and the uncommitted changes are preserved. - 2. With the -c/--check option, the update is aborted and the + 2. With the -m/--merge option, the update is allowed even if the + requested changeset is not an ancestor or descendant of + the working directory's parent. + + 3. With the -c/--check option, the update is aborted and the uncommitted changes are preserved. - 3. With the -C/--clean option, uncommitted changes are discarded and + 4. With the -C/--clean option, uncommitted changes are discarded and the working directory is updated to the requested changeset. To cancel an uncommitted merge (and lose your changes), use @@ -6522,14 +5368,26 @@ if rev and node: raise error.Abort(_("please specify just one revision")) + if ui.configbool('commands', 'update.requiredest'): + if not node and not rev and not date: + raise error.Abort(_('you must specify a destination'), + hint=_('for example: hg update ".::"')) + if rev is None or rev == '': rev = node if date and rev is not None: raise error.Abort(_("you can't specify a revision and a date")) - if check and clean: - raise error.Abort(_("cannot specify both -c/--check and -C/--clean")) + if len([x for x in (clean, check, merge) if x]) > 1: + raise error.Abort(_("can only specify one of -C/--clean, -c/--check, " + "or -m/merge")) + + updatecheck = None + if check: + updatecheck = 'abort' + elif merge: + updatecheck = 'none' with repo.wlock(): cmdutil.clearunfinished(repo) @@ -6541,12 +5399,10 @@ brev = rev rev = scmutil.revsingle(repo, rev, rev).rev() - if check: - cmdutil.bailifchanged(repo, merge=False) - repo.ui.setconfig('ui', 'forcemerge', tool, 'update') - return hg.updatetotally(ui, repo, rev, brev, clean=clean, check=check) + return hg.updatetotally(ui, repo, rev, brev, clean=clean, + updatecheck=updatecheck) @command('verify', []) def verify(ui, repo): @@ -6570,6 +5426,8 @@ @command('version', [] + formatteropts, norepo=True) def version_(ui, **opts): """output version and copyright information""" + if ui.verbose: + ui.pager('version') fm = ui.formatter("version", opts) fm.startitem() fm.write("ver", _("Mercurial Distributed SCM (version %s)\n"),
--- a/mercurial/commandserver.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/commandserver.py Tue Apr 18 12:24:34 2017 -0400 @@ -304,8 +304,8 @@ ui.flush() newfiles = [] nullfd = os.open(os.devnull, os.O_RDWR) - for f, sysf, mode in [(ui.fin, util.stdin, 'rb'), - (ui.fout, util.stdout, 'wb')]: + for f, sysf, mode in [(ui.fin, util.stdin, pycompat.sysstr('rb')), + (ui.fout, util.stdout, pycompat.sysstr('wb'))]: if f is sysf: newfd = os.dup(f.fileno()) os.dup2(nullfd, f.fileno()) @@ -447,6 +447,7 @@ self._sock = None self._oldsigchldhandler = None self._workerpids = set() # updated by signal handler; do not iterate + self._socketunlinked = None def init(self): self._sock = socket.socket(socket.AF_UNIX) @@ -455,11 +456,17 @@ o = signal.signal(signal.SIGCHLD, self._sigchldhandler) self._oldsigchldhandler = o self._servicehandler.printbanner(self.address) + self._socketunlinked = False + + def _unlinksocket(self): + if not self._socketunlinked: + self._servicehandler.unlinksocket(self.address) + self._socketunlinked = True def _cleanup(self): signal.signal(signal.SIGCHLD, self._oldsigchldhandler) self._sock.close() - self._servicehandler.unlinksocket(self.address) + self._unlinksocket() # don't kill child processes as they have active clients, just wait self._reapworkers(0) @@ -470,11 +477,23 @@ self._cleanup() def _mainloop(self): + exiting = False h = self._servicehandler - while not h.shouldexit(): + while True: + if not exiting and h.shouldexit(): + # clients can no longer connect() to the domain socket, so + # we stop queuing new requests. + # for requests that are queued (connect()-ed, but haven't been + # accept()-ed), handle them before exit. otherwise, clients + # waiting for recv() will receive ECONNRESET. + self._unlinksocket() + exiting = True try: ready = select.select([self._sock], [], [], h.pollinterval)[0] if not ready: + # only exit if we completed all queued requests + if exiting: + break continue conn, _addr = self._sock.accept() except (select.error, socket.error) as inst:
--- a/mercurial/config.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/config.py Tue Apr 18 12:24:34 2017 -0400 @@ -13,15 +13,16 @@ from .i18n import _ from . import ( error, + pycompat, util, ) class config(object): - def __init__(self, data=None, includepaths=[]): + def __init__(self, data=None, includepaths=None): self._data = {} self._source = {} self._unset = [] - self._includepaths = includepaths + self._includepaths = includepaths or [] if data: for k in data._data: self._data[k] = data[k].copy() @@ -69,6 +70,9 @@ def items(self, section): return self._data.get(section, {}).items() def set(self, section, item, value, source=""): + if pycompat.ispy3: + assert not isinstance(value, str), ( + 'config values may not be unicode strings on Python 3') if section not in self: self._data[section] = util.sortdict() self._data[section][item] = value @@ -169,5 +173,92 @@ def read(self, path, fp=None, sections=None, remap=None): if not fp: - fp = util.posixfile(path) - self.parse(path, fp.read(), sections, remap, self.read) + fp = util.posixfile(path, 'rb') + assert getattr(fp, 'mode', r'rb') == r'rb', ( + 'config files must be opened in binary mode, got fp=%r mode=%r' % ( + fp, fp.mode)) + self.parse(path, fp.read(), + sections=sections, remap=remap, include=self.read) + +def parselist(value): + """parse a configuration value as a list of comma/space separated strings + + >>> parselist('this,is "a small" ,test') + ['this', 'is', 'a small', 'test'] + """ + + def _parse_plain(parts, s, offset): + whitespace = False + while offset < len(s) and (s[offset:offset + 1].isspace() + or s[offset:offset + 1] == ','): + whitespace = True + offset += 1 + if offset >= len(s): + return None, parts, offset + if whitespace: + parts.append('') + if s[offset:offset + 1] == '"' and not parts[-1]: + return _parse_quote, parts, offset + 1 + elif s[offset:offset + 1] == '"' and parts[-1][-1] == '\\': + parts[-1] = parts[-1][:-1] + s[offset:offset + 1] + return _parse_plain, parts, offset + 1 + parts[-1] += s[offset:offset + 1] + return _parse_plain, parts, offset + 1 + + def _parse_quote(parts, s, offset): + if offset < len(s) and s[offset:offset + 1] == '"': # "" + parts.append('') + offset += 1 + while offset < len(s) and (s[offset:offset + 1].isspace() or + s[offset:offset + 1] == ','): + offset += 1 + return _parse_plain, parts, offset + + while offset < len(s) and s[offset:offset + 1] != '"': + if (s[offset:offset + 1] == '\\' and offset + 1 < len(s) + and s[offset + 1:offset + 2] == '"'): + offset += 1 + parts[-1] += '"' + else: + parts[-1] += s[offset:offset + 1] + offset += 1 + + if offset >= len(s): + real_parts = _configlist(parts[-1]) + if not real_parts: + parts[-1] = '"' + else: + real_parts[0] = '"' + real_parts[0] + parts = parts[:-1] + parts.extend(real_parts) + return None, parts, offset + + offset += 1 + while offset < len(s) and s[offset:offset + 1] in [' ', ',']: + offset += 1 + + if offset < len(s): + if offset + 1 == len(s) and s[offset:offset + 1] == '"': + parts[-1] += '"' + offset += 1 + else: + parts.append('') + else: + return None, parts, offset + + return _parse_plain, parts, offset + + def _configlist(s): + s = s.rstrip(' ,') + if not s: + return [] + parser, parts, offset = _parse_plain, [''], 0 + while parser: + parser, parts, offset = parser(parts, s, offset) + return parts + + if value is not None and isinstance(value, bytes): + result = _configlist(value.lstrip(' ,\n')) + else: + result = value + return result or []
--- a/mercurial/context.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/context.py Tue Apr 18 12:24:34 2017 -0400 @@ -18,11 +18,11 @@ bin, hex, modifiednodeid, - newnodeid, nullid, nullrev, short, wdirid, + wdirnodes, ) from . import ( encoding, @@ -33,6 +33,7 @@ obsolete as obsmod, patch, phases, + pycompat, repoview, revlog, scmutil, @@ -64,6 +65,12 @@ return o def __str__(self): + r = short(self.node()) + if pycompat.ispy3: + return r.decode('ascii') + return r + + def __bytes__(self): return short(self.node()) def __int__(self): @@ -90,14 +97,11 @@ def __iter__(self): return iter(self._manifest) - def _manifestmatches(self, match, s): - """generate a new manifest filtered by the match argument - - This method is for internal use only and mainly exists to provide an - object oriented way for other contexts to customize the manifest - generation. - """ - return self.manifest().matches(match) + def _buildstatusmanifest(self, status): + """Builds a manifest that includes the given status results, if this is + a working copy context. For non-working copy contexts, it just returns + the normal manifest.""" + return self.manifest() def _matchstatus(self, other, match): """return match.always if match is none @@ -116,17 +120,19 @@ # 1000 and cache it so that when you read 1001, we just need to apply a # delta to what's in the cache. So that's one full reconstruction + one # delta application. + mf2 = None if self.rev() is not None and self.rev() < other.rev(): - self.manifest() - mf1 = other._manifestmatches(match, s) - mf2 = self._manifestmatches(match, s) + mf2 = self._buildstatusmanifest(s) + mf1 = other._buildstatusmanifest(s) + if mf2 is None: + mf2 = self._buildstatusmanifest(s) modified, added = [], [] removed = [] clean = [] deleted, unknown, ignored = s.deleted, s.unknown, s.ignored deletedset = set(deleted) - d = mf1.diff(mf2, clean=listclean) + d = mf1.diff(mf2, match=match, clean=listclean) for fn, value in d.iteritems(): if fn in deletedset: continue @@ -140,7 +146,7 @@ removed.append(fn) elif flag1 != flag2: modified.append(fn) - elif node2 != newnodeid: + elif node2 not in wdirnodes: # When comparing files between two commits, we save time by # not comparing the file contents when the nodeids differ. # Note that this means we incorrectly report a reverted change @@ -153,8 +159,10 @@ if removed: # need to filter files if they are already reported as removed - unknown = [fn for fn in unknown if fn not in mf1] - ignored = [fn for fn in ignored if fn not in mf1] + unknown = [fn for fn in unknown if fn not in mf1 and + (not match or match(fn))] + ignored = [fn for fn in ignored if fn not in mf1 and + (not match or match(fn))] # if they're deleted, don't report them as removed removed = [fn for fn in removed if fn not in deletedset] @@ -290,8 +298,10 @@ ''' return subrepo.subrepo(self, path, allowwdir=True) - def match(self, pats=[], include=None, exclude=None, default='glob', + def match(self, pats=None, include=None, exclude=None, default='glob', listsubrepos=False, badfn=None): + if pats is None: + pats = [] r = self._repo return matchmod.match(r.root, r.getcwd(), pats, include, exclude, default, @@ -397,6 +407,19 @@ date, extra, editor) return ctx +def _filterederror(repo, changeid): + """build an exception to be raised about a filtered changeid + + This is extracted in a function to help extensions (eg: evolve) to + experiment with various message variants.""" + if repo.filtername.startswith('visible'): + msg = _("hidden revision '%s'") % changeid + hint = _('use --hidden to access hidden revisions') + return error.FilteredRepoLookupError(msg, hint=hint) + msg = _("filtered revision '%s' (not in '%s' subset)") + msg %= (changeid, repo.filtername) + return error.FilteredRepoLookupError(msg) + class changectx(basectx): """A changecontext object makes access to data related to a particular changeset convenient. It represents a read-only context already present in @@ -418,7 +441,7 @@ self._node = repo.changelog.node(changeid) self._rev = changeid return - if isinstance(changeid, long): + if not pycompat.ispy3 and isinstance(changeid, long): changeid = str(changeid) if changeid == 'null': self._node = nullid @@ -446,7 +469,7 @@ try: r = int(changeid) - if str(r) != changeid: + if '%d' % r != changeid: raise ValueError l = len(repo.changelog) if r < 0: @@ -503,13 +526,7 @@ pass except (error.FilteredIndexError, error.FilteredLookupError, error.FilteredRepoLookupError): - if repo.filtername.startswith('visible'): - msg = _("hidden revision '%s'") % changeid - hint = _('use --hidden to access hidden revisions') - raise error.FilteredRepoLookupError(msg, hint=hint) - msg = _("filtered revision '%s' (not in '%s' subset)") - msg %= (changeid, repo.filtername) - raise error.FilteredRepoLookupError(msg) + raise _filterederror(repo, changeid) except IndexError: pass raise error.RepoLookupError( @@ -524,6 +541,8 @@ def __nonzero__(self): return self._rev != nullrev + __bool__ = __nonzero__ + @propertycache def _changeset(self): return self._repo.changelog.changelogrevision(self.rev()) @@ -712,6 +731,8 @@ # file is missing return False + __bool__ = __nonzero__ + def __str__(self): try: return "%s@%s" % (self.path(), self._changectx) @@ -1166,7 +1187,7 @@ diffinrange = any(stype == '!' for _, stype in filteredblocks) return diffinrange, linerange1 -def blockancestors(fctx, fromline, toline): +def blockancestors(fctx, fromline, toline, followfirst=False): """Yield ancestors of `fctx` with respect to the block of lines within `fromline`-`toline` range. """ @@ -1175,9 +1196,11 @@ while visit: c, linerange2 = visit.pop(max(visit)) pl = c.parents() + if followfirst: + pl = pl[:1] if not pl: # The block originates from the initial revision. - yield c + yield c, linerange2 continue inrange = False for p in pl: @@ -1190,7 +1213,45 @@ continue visit[p.linkrev(), p.filenode()] = p, linerange1 if inrange: - yield c + yield c, linerange2 + +def blockdescendants(fctx, fromline, toline): + """Yield descendants of `fctx` with respect to the block of lines within + `fromline`-`toline` range. + """ + # First possibly yield 'fctx' if it has changes in range with respect to + # its parents. + try: + c, linerange1 = next(blockancestors(fctx, fromline, toline)) + except StopIteration: + pass + else: + if c == fctx: + yield c, linerange1 + + diffopts = patch.diffopts(fctx._repo.ui) + fl = fctx.filelog() + seen = {fctx.filerev(): (fctx, (fromline, toline))} + for i in fl.descendants([fctx.filerev()]): + c = fctx.filectx(i) + inrange = False + for x in fl.parentrevs(i): + try: + p, linerange2 = seen[x] + except KeyError: + # nullrev or other branch + continue + inrangep, linerange1 = _changesrange(c, p, linerange2, diffopts) + inrange = inrange or inrangep + # If revision 'i' has been seen (it's a merge), we assume that its + # line range is the same independently of which parents was used + # to compute it. + assert i not in seen or seen[i][1] == linerange1, ( + 'computed line range for %s is not consistent between ' + 'ancestor branches' % c) + seen[i] = c, linerange1 + if inrange: + yield c, linerange1 class committablectx(basectx): """A committablectx object provides common functionality for a context that @@ -1226,6 +1287,8 @@ def __nonzero__(self): return True + __bool__ = __nonzero__ + def _buildflagfunc(self): # Create a fallback function for getting file flags when the # filesystem doesn't support them @@ -1263,35 +1326,6 @@ return self._repo.dirstate.flagfunc(self._buildflagfunc) @propertycache - def _manifest(self): - """generate a manifest corresponding to the values in self._status - - This reuse the file nodeid from parent, but we append an extra letter - when modified. Modified files get an extra 'm' while added files get - an extra 'a'. This is used by manifests merge to see that files - are different and by update logic to avoid deleting newly added files. - """ - parents = self.parents() - - man = parents[0].manifest().copy() - - ff = self._flagfunc - for i, l in ((addednodeid, self._status.added), - (modifiednodeid, self._status.modified)): - for f in l: - man[f] = i - try: - man.setflag(f, ff(f)) - except OSError: - pass - - for f in self._status.deleted + self._status.removed: - if f in man: - del man[f] - - return man - - @propertycache def _status(self): return self._repo.status() @@ -1534,21 +1568,21 @@ self._repo.dirstate.normallookup(dest) self._repo.dirstate.copy(source, dest) - def match(self, pats=[], include=None, exclude=None, default='glob', + def match(self, pats=None, include=None, exclude=None, default='glob', listsubrepos=False, badfn=None): + if pats is None: + pats = [] r = self._repo # Only a case insensitive filesystem needs magic to translate user input # to actual case in the filesystem. + matcherfunc = matchmod.match if not util.fscasesensitive(r.root): - return matchmod.icasefsmatcher(r.root, r.getcwd(), pats, include, - exclude, default, r.auditor, self, - listsubrepos=listsubrepos, - badfn=badfn) - return matchmod.match(r.root, r.getcwd(), pats, - include, exclude, default, - auditor=r.auditor, ctx=self, - listsubrepos=listsubrepos, badfn=badfn) + matcherfunc = matchmod.icasefsmatcher + return matcherfunc(r.root, r.getcwd(), pats, + include, exclude, default, + auditor=r.auditor, ctx=self, + listsubrepos=listsubrepos, badfn=badfn) def _filtersuspectsymlink(self, files): if not files or self._repo.dirstate._checklink: @@ -1605,22 +1639,6 @@ pass return modified, fixup - def _manifestmatches(self, match, s): - """Slow path for workingctx - - The fast path is when we compare the working directory to its parent - which means this function is comparing with a non-parent; therefore we - need to build a manifest and return what matches. - """ - mf = self._repo['.']._manifestmatches(match, s) - for f in s.modified + s.added: - mf[f] = newnodeid - mf.setflag(f, self.flags(f)) - for f in s.removed: - if f in mf: - del mf[f] - return mf - def _dirstatestatus(self, match=None, ignored=False, clean=False, unknown=False): '''Gets the status from the dirstate -- internal use only.''' @@ -1652,6 +1670,39 @@ return s + @propertycache + def _manifest(self): + """generate a manifest corresponding to the values in self._status + + This reuse the file nodeid from parent, but we use special node + identifiers for added and modified files. This is used by manifests + merge to see that files are different and by update logic to avoid + deleting newly added files. + """ + return self._buildstatusmanifest(self._status) + + def _buildstatusmanifest(self, status): + """Builds a manifest that includes the given status results.""" + parents = self.parents() + + man = parents[0].manifest().copy() + + ff = self._flagfunc + for i, l in ((addednodeid, status.added), + (modifiednodeid, status.modified)): + for f in l: + man[f] = i + try: + man.setflag(f, ff(f)) + except OSError: + pass + + for f in status.deleted + status.removed: + if f in man: + del man[f] + + return man + def _buildstatus(self, other, s, match, listignored, listclean, listunknown): """build a status with respect to another context @@ -1711,6 +1762,8 @@ def __nonzero__(self): return True + __bool__ = __nonzero__ + def linkrev(self): # linked to self._changectx no matter if file is modified or not return self.rev() @@ -1779,7 +1832,7 @@ def remove(self, ignoremissing=False): """wraps unlink for a repo's working directory""" - util.unlinkpath(self._repo.wjoin(self._path), ignoremissing) + self._repo.wvfs.unlinkpath(self._path, ignoremissing=ignoremissing) def write(self, data, flags): """wraps repo.wwrite""" @@ -1856,8 +1909,8 @@ commit function for every file in 'files', but calls order is undefined. If the file is available in the revision being committed (updated or added), filectxfn returns a memfilectx - object. If the file was removed, filectxfn raises an - IOError. Moved files are represented by marking the source file + object. If the file was removed, filectxfn return None for recent + Mercurial. Moved files are represented by marking the source file removed and the new file added with copy information (see memfilectx). @@ -2046,10 +2099,10 @@ # sanity check to ensure that the reused manifest parents are # manifests of our commit parents mp1, mp2 = self.manifestctx().parents - if p1 != nullid and p1.manifestctx().node() != mp1: + if p1 != nullid and p1.manifestnode() != mp1: raise RuntimeError('can\'t reuse the manifest: ' 'its p1 doesn\'t match the new ctx p1') - if p2 != nullid and p2.manifestctx().node() != mp2: + if p2 != nullid and p2.manifestnode() != mp2: raise RuntimeError('can\'t reuse the manifest: ' 'its p2 doesn\'t match the new ctx p2')
--- a/mercurial/copies.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/copies.py Tue Apr 18 12:24:34 2017 -0400 @@ -149,10 +149,7 @@ """ ma = a.manifest() mb = b.manifest() - if match: - ma = ma.matches(match) - mb = mb.matches(match) - return mb.filesnotin(ma) + return mb.filesnotin(ma, match=match) def _forwardcopies(a, b, match=None): '''find {dst@b: src@a} copy mapping where a is an ancestor of b'''
--- a/mercurial/crecord.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/crecord.py Tue Apr 18 12:24:34 2017 -0400 @@ -473,12 +473,17 @@ """ ui.write(_('starting interactive selection\n')) chunkselector = curseschunkselector(headerlist, ui, operation) - f = signal.getsignal(signal.SIGTSTP) - curses.wrapper(chunkselector.main) - if chunkselector.initerr is not None: - raise error.Abort(chunkselector.initerr) - # ncurses does not restore signal handler for SIGTSTP - signal.signal(signal.SIGTSTP, f) + origsigtstp = sentinel = object() + if util.safehasattr(signal, 'SIGTSTP'): + origsigtstp = signal.getsignal(signal.SIGTSTP) + try: + curses.wrapper(chunkselector.main) + if chunkselector.initerr is not None: + raise error.Abort(chunkselector.initerr) + # ncurses does not restore signal handler for SIGTSTP + finally: + if origsigtstp is not sentinel: + signal.signal(signal.SIGTSTP, origsigtstp) return chunkselector.opts def testdecorator(testfn, f): @@ -564,7 +569,7 @@ # affects some ui text if operation not in _headermessages: - raise RuntimeError('unexpected operation: %s' % operation) + raise error.ProgrammingError('unexpected operation: %s' % operation) self.operation = operation def uparrowevent(self): @@ -1375,7 +1380,8 @@ pass helpwin.refresh() try: - helpwin.getkey() + with self.ui.timeblockedsection('crecord'): + helpwin.getkey() except curses.error: pass @@ -1392,7 +1398,8 @@ self.stdscr.refresh() confirmwin.refresh() try: - response = chr(self.stdscr.getch()) + with self.ui.timeblockedsection('crecord'): + response = chr(self.stdscr.getch()) except ValueError: response = None @@ -1412,7 +1419,8 @@ are you sure you want to review/edit and confirm the selected changes [yn]? """) - response = self.confirmationwindow(confirmtext) + with self.ui.timeblockedsection('crecord'): + response = self.confirmationwindow(confirmtext) if response is None: response = "n" if response.lower().startswith("y"): @@ -1611,8 +1619,17 @@ method to be wrapped by curses.wrapper() for selecting chunks. """ - origsigwinchhandler = signal.signal(signal.SIGWINCH, - self.sigwinchhandler) + origsigwinch = sentinel = object() + if util.safehasattr(signal, 'SIGWINCH'): + origsigwinch = signal.signal(signal.SIGWINCH, + self.sigwinchhandler) + try: + return self._main(stdscr) + finally: + if origsigwinch is not sentinel: + signal.signal(signal.SIGWINCH, origsigwinch) + + def _main(self, stdscr): self.stdscr = stdscr # error during initialization, cannot be printed in the curses # interface, it should be printed by the calling code @@ -1655,7 +1672,8 @@ while True: self.updatescreen() try: - keypressed = self.statuswin.getkey() + with self.ui.timeblockedsection('crecord'): + keypressed = self.statuswin.getkey() if self.errorstr is not None: self.errorstr = None continue @@ -1663,4 +1681,3 @@ keypressed = "foobar" if self.handlekeypressed(keypressed): break - signal.signal(signal.SIGWINCH, origsigwinchhandler)
--- a/mercurial/debugcommands.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/debugcommands.py Tue Apr 18 12:24:34 2017 -0400 @@ -7,41 +7,64 @@ from __future__ import absolute_import +import difflib +import errno import operator import os import random +import socket +import string +import sys +import tempfile +import time from .i18n import _ from .node import ( bin, hex, + nullhex, nullid, + nullrev, short, ) from . import ( bundle2, changegroup, cmdutil, + color, commands, context, dagparser, dagutil, + encoding, error, exchange, extensions, fileset, + formatter, hg, localrepo, lock as lockmod, + merge as mergemod, + obsolete, + policy, + pvec, pycompat, repair, revlog, + revset, + revsetlang, scmutil, setdiscovery, simplemerge, + smartset, + sslutil, streamclone, + templater, treediscovery, + upgrade, util, + vfs as vfsmod, ) release = lockmod.release @@ -55,7 +78,7 @@ """find the ancestor revision of two revisions in a given index""" if len(args) == 3: index, rev1, rev2 = args - r = revlog.revlog(scmutil.opener(pycompat.getcwd(), audit=False), index) + r = revlog.revlog(vfsmod.vfs(pycompat.getcwd(), audit=False), index) lookup = r.lookup elif len(args) == 2: if not repo: @@ -324,6 +347,47 @@ error = _(".hg/dirstate inconsistent with current parent's manifest") raise error.Abort(error) +@command('debugcolor', + [('', 'style', None, _('show all configured styles'))], + 'hg debugcolor') +def debugcolor(ui, repo, **opts): + """show available color, effects or style""" + ui.write(('color mode: %s\n') % ui._colormode) + if opts.get('style'): + return _debugdisplaystyle(ui) + else: + return _debugdisplaycolor(ui) + +def _debugdisplaycolor(ui): + ui = ui.copy() + ui._styles.clear() + for effect in color._activeeffects(ui).keys(): + ui._styles[effect] = effect + if ui._terminfoparams: + for k, v in ui.configitems('color'): + if k.startswith('color.'): + ui._styles[k] = k[6:] + elif k.startswith('terminfo.'): + ui._styles[k] = k[9:] + ui.write(_('available colors:\n')) + # sort label with a '_' after the other to group '_background' entry. + items = sorted(ui._styles.items(), + key=lambda i: ('_' in i[0], i[0], i[1])) + for colorname, label in items: + ui.write(('%s\n') % colorname, label=label) + +def _debugdisplaystyle(ui): + ui.write(_('available style:\n')) + width = max(len(s) for s in ui._styles) + for label, effects in sorted(ui._styles.items()): + ui.write('%s' % label, label=label) + if effects: + # 50 + ui.write(': ') + ui.write(' ' * (max(0, width - len(label)))) + ui.write(', '.join(ui.label(e, e) for e in effects.split())) + ui.write('\n') + @command('debugcommands', [], _('[COMMAND]'), norepo=True) def debugcommands(ui, cmd='', *args): """list all available commands and options""" @@ -390,7 +454,7 @@ spaces = opts.get('spaces') dots = opts.get('dots') if file_: - rlog = revlog.revlog(scmutil.opener(pycompat.getcwd(), audit=False), + rlog = revlog.revlog(vfsmod.vfs(pycompat.getcwd(), audit=False), file_) revs = set((int(r) for r in revs)) def events(): @@ -567,6 +631,37 @@ fm.end() +@command('debugdirstate|debugstate', + [('', 'nodates', None, _('do not display the saved mtime')), + ('', 'datesort', None, _('sort by saved mtime'))], + _('[OPTION]...')) +def debugstate(ui, repo, **opts): + """show the contents of the current dirstate""" + + nodates = opts.get('nodates') + datesort = opts.get('datesort') + + timestr = "" + if datesort: + keyfunc = lambda x: (x[1][3], x[0]) # sort by mtime, then by filename + else: + keyfunc = None # sort by filename + for file_, ent in sorted(repo.dirstate._map.iteritems(), key=keyfunc): + if ent[3] == -1: + timestr = 'unset ' + elif nodates: + timestr = 'set ' + else: + timestr = time.strftime("%Y-%m-%d %H:%M:%S ", + time.localtime(ent[3])) + if ent[1] & 0o20000: + mode = 'lnk' + else: + mode = '%3o' % (ent[1] & 0o777 & ~util.umask) + ui.write("%c %s %10d %s%s\n" % (ent[0], mode, ent[2], timestr, file_)) + for f in repo.dirstate.copies(): + ui.write(_("copy: %s -> %s\n") % (repo.dirstate.copied(f), f)) + @command('debugdiscovery', [('', 'old', None, _('use old-style discovery')), ('', 'nonheads', None, @@ -641,7 +736,7 @@ fm = ui.formatter('debugextensions', opts) for extname, extmod in sorted(exts, key=operator.itemgetter(0)): isinternal = extensions.ismoduleinternal(extmod) - extsource = extmod.__file__ + extsource = pycompat.fsencode(extmod.__file__) if isinternal: exttestedwith = [] # never expose magic string to users else: @@ -694,13 +789,17 @@ @command('debugfsinfo', [], _('[PATH]'), norepo=True) def debugfsinfo(ui, path="."): """show information detected about current filesystem""" - util.writefile('.debugfsinfo', '') ui.write(('exec: %s\n') % (util.checkexec(path) and 'yes' or 'no')) + ui.write(('fstype: %s\n') % (util.getfstype(path) or '(unknown)')) ui.write(('symlink: %s\n') % (util.checklink(path) and 'yes' or 'no')) ui.write(('hardlink: %s\n') % (util.checknlink(path) and 'yes' or 'no')) - ui.write(('case-sensitive: %s\n') % (util.fscasesensitive('.debugfsinfo') - and 'yes' or 'no')) - os.unlink('.debugfsinfo') + casesensitive = '(unknown)' + try: + with tempfile.NamedTemporaryFile(prefix='.debugfsinfo', dir=path) as f: + casesensitive = util.fscasesensitive(f.name) and 'yes' or 'no' + except OSError: + pass + ui.write(('case-sensitive: %s\n') % casesensitive) @command('debuggetbundle', [('H', 'head', [], _('id of head node'), _('ID')), @@ -851,6 +950,1106 @@ ui.write("\t%d -> %d\n" % (r.rev(pp[1]), i)) ui.write("}\n") +@command('debuginstall', [] + commands.formatteropts, '', norepo=True) +def debuginstall(ui, **opts): + '''test Mercurial installation + + Returns 0 on success. + ''' + + def writetemp(contents): + (fd, name) = tempfile.mkstemp(prefix="hg-debuginstall-") + f = os.fdopen(fd, pycompat.sysstr("wb")) + f.write(contents) + f.close() + return name + + problems = 0 + + fm = ui.formatter('debuginstall', opts) + fm.startitem() + + # encoding + fm.write('encoding', _("checking encoding (%s)...\n"), encoding.encoding) + err = None + try: + encoding.fromlocal("test") + except error.Abort as inst: + err = inst + problems += 1 + fm.condwrite(err, 'encodingerror', _(" %s\n" + " (check that your locale is properly set)\n"), err) + + # Python + fm.write('pythonexe', _("checking Python executable (%s)\n"), + pycompat.sysexecutable) + fm.write('pythonver', _("checking Python version (%s)\n"), + ("%d.%d.%d" % sys.version_info[:3])) + fm.write('pythonlib', _("checking Python lib (%s)...\n"), + os.path.dirname(pycompat.fsencode(os.__file__))) + + security = set(sslutil.supportedprotocols) + if sslutil.hassni: + security.add('sni') + + fm.write('pythonsecurity', _("checking Python security support (%s)\n"), + fm.formatlist(sorted(security), name='protocol', + fmt='%s', sep=',')) + + # These are warnings, not errors. So don't increment problem count. This + # may change in the future. + if 'tls1.2' not in security: + fm.plain(_(' TLS 1.2 not supported by Python install; ' + 'network connections lack modern security\n')) + if 'sni' not in security: + fm.plain(_(' SNI not supported by Python install; may have ' + 'connectivity issues with some servers\n')) + + # TODO print CA cert info + + # hg version + hgver = util.version() + fm.write('hgver', _("checking Mercurial version (%s)\n"), + hgver.split('+')[0]) + fm.write('hgverextra', _("checking Mercurial custom build (%s)\n"), + '+'.join(hgver.split('+')[1:])) + + # compiled modules + fm.write('hgmodulepolicy', _("checking module policy (%s)\n"), + policy.policy) + fm.write('hgmodules', _("checking installed modules (%s)...\n"), + os.path.dirname(pycompat.fsencode(__file__))) + + err = None + try: + from . import ( + base85, + bdiff, + mpatch, + osutil, + ) + dir(bdiff), dir(mpatch), dir(base85), dir(osutil) # quiet pyflakes + except Exception as inst: + err = inst + problems += 1 + fm.condwrite(err, 'extensionserror', " %s\n", err) + + compengines = util.compengines._engines.values() + fm.write('compengines', _('checking registered compression engines (%s)\n'), + fm.formatlist(sorted(e.name() for e in compengines), + name='compengine', fmt='%s', sep=', ')) + fm.write('compenginesavail', _('checking available compression engines ' + '(%s)\n'), + fm.formatlist(sorted(e.name() for e in compengines + if e.available()), + name='compengine', fmt='%s', sep=', ')) + wirecompengines = util.compengines.supportedwireengines(util.SERVERROLE) + fm.write('compenginesserver', _('checking available compression engines ' + 'for wire protocol (%s)\n'), + fm.formatlist([e.name() for e in wirecompengines + if e.wireprotosupport()], + name='compengine', fmt='%s', sep=', ')) + + # templates + p = templater.templatepaths() + fm.write('templatedirs', 'checking templates (%s)...\n', ' '.join(p)) + fm.condwrite(not p, '', _(" no template directories found\n")) + if p: + m = templater.templatepath("map-cmdline.default") + if m: + # template found, check if it is working + err = None + try: + templater.templater.frommapfile(m) + except Exception as inst: + err = inst + p = None + fm.condwrite(err, 'defaulttemplateerror', " %s\n", err) + else: + p = None + fm.condwrite(p, 'defaulttemplate', + _("checking default template (%s)\n"), m) + fm.condwrite(not m, 'defaulttemplatenotfound', + _(" template '%s' not found\n"), "default") + if not p: + problems += 1 + fm.condwrite(not p, '', + _(" (templates seem to have been installed incorrectly)\n")) + + # editor + editor = ui.geteditor() + editor = util.expandpath(editor) + fm.write('editor', _("checking commit editor... (%s)\n"), editor) + cmdpath = util.findexe(pycompat.shlexsplit(editor)[0]) + fm.condwrite(not cmdpath and editor == 'vi', 'vinotfound', + _(" No commit editor set and can't find %s in PATH\n" + " (specify a commit editor in your configuration" + " file)\n"), not cmdpath and editor == 'vi' and editor) + fm.condwrite(not cmdpath and editor != 'vi', 'editornotfound', + _(" Can't find editor '%s' in PATH\n" + " (specify a commit editor in your configuration" + " file)\n"), not cmdpath and editor) + if not cmdpath and editor != 'vi': + problems += 1 + + # check username + username = None + err = None + try: + username = ui.username() + except error.Abort as e: + err = e + problems += 1 + + fm.condwrite(username, 'username', _("checking username (%s)\n"), username) + fm.condwrite(err, 'usernameerror', _("checking username...\n %s\n" + " (specify a username in your configuration file)\n"), err) + + fm.condwrite(not problems, '', + _("no problems detected\n")) + if not problems: + fm.data(problems=problems) + fm.condwrite(problems, 'problems', + _("%d problems detected," + " please check your install!\n"), problems) + fm.end() + + return problems + +@command('debugknown', [], _('REPO ID...'), norepo=True) +def debugknown(ui, repopath, *ids, **opts): + """test whether node ids are known to a repo + + Every ID must be a full-length hex node id string. Returns a list of 0s + and 1s indicating unknown/known. + """ + repo = hg.peer(ui, opts, repopath) + if not repo.capable('known'): + raise error.Abort("known() not supported by target repository") + flags = repo.known([bin(s) for s in ids]) + ui.write("%s\n" % ("".join([f and "1" or "0" for f in flags]))) + +@command('debuglabelcomplete', [], _('LABEL...')) +def debuglabelcomplete(ui, repo, *args): + '''backwards compatibility with old bash completion scripts (DEPRECATED)''' + debugnamecomplete(ui, repo, *args) + +@command('debuglocks', + [('L', 'force-lock', None, _('free the store lock (DANGEROUS)')), + ('W', 'force-wlock', None, + _('free the working state lock (DANGEROUS)'))], + _('[OPTION]...')) +def debuglocks(ui, repo, **opts): + """show or modify state of locks + + By default, this command will show which locks are held. This + includes the user and process holding the lock, the amount of time + the lock has been held, and the machine name where the process is + running if it's not local. + + Locks protect the integrity of Mercurial's data, so should be + treated with care. System crashes or other interruptions may cause + locks to not be properly released, though Mercurial will usually + detect and remove such stale locks automatically. + + However, detecting stale locks may not always be possible (for + instance, on a shared filesystem). Removing locks may also be + blocked by filesystem permissions. + + Returns 0 if no locks are held. + + """ + + if opts.get('force_lock'): + repo.svfs.unlink('lock') + if opts.get('force_wlock'): + repo.vfs.unlink('wlock') + if opts.get('force_lock') or opts.get('force_lock'): + return 0 + + now = time.time() + held = 0 + + def report(vfs, name, method): + # this causes stale locks to get reaped for more accurate reporting + try: + l = method(False) + except error.LockHeld: + l = None + + if l: + l.release() + else: + try: + stat = vfs.lstat(name) + age = now - stat.st_mtime + user = util.username(stat.st_uid) + locker = vfs.readlock(name) + if ":" in locker: + host, pid = locker.split(':') + if host == socket.gethostname(): + locker = 'user %s, process %s' % (user, pid) + else: + locker = 'user %s, process %s, host %s' \ + % (user, pid, host) + ui.write(("%-6s %s (%ds)\n") % (name + ":", locker, age)) + return 1 + except OSError as e: + if e.errno != errno.ENOENT: + raise + + ui.write(("%-6s free\n") % (name + ":")) + return 0 + + held += report(repo.svfs, "lock", repo.lock) + held += report(repo.vfs, "wlock", repo.wlock) + + return held + +@command('debugmergestate', [], '') +def debugmergestate(ui, repo, *args): + """print merge state + + Use --verbose to print out information about whether v1 or v2 merge state + was chosen.""" + def _hashornull(h): + if h == nullhex: + return 'null' + else: + return h + + def printrecords(version): + ui.write(('* version %s records\n') % version) + if version == 1: + records = v1records + else: + records = v2records + + for rtype, record in records: + # pretty print some record types + if rtype == 'L': + ui.write(('local: %s\n') % record) + elif rtype == 'O': + ui.write(('other: %s\n') % record) + elif rtype == 'm': + driver, mdstate = record.split('\0', 1) + ui.write(('merge driver: %s (state "%s")\n') + % (driver, mdstate)) + elif rtype in 'FDC': + r = record.split('\0') + f, state, hash, lfile, afile, anode, ofile = r[0:7] + if version == 1: + onode = 'not stored in v1 format' + flags = r[7] + else: + onode, flags = r[7:9] + ui.write(('file: %s (record type "%s", state "%s", hash %s)\n') + % (f, rtype, state, _hashornull(hash))) + ui.write((' local path: %s (flags "%s")\n') % (lfile, flags)) + ui.write((' ancestor path: %s (node %s)\n') + % (afile, _hashornull(anode))) + ui.write((' other path: %s (node %s)\n') + % (ofile, _hashornull(onode))) + elif rtype == 'f': + filename, rawextras = record.split('\0', 1) + extras = rawextras.split('\0') + i = 0 + extrastrings = [] + while i < len(extras): + extrastrings.append('%s = %s' % (extras[i], extras[i + 1])) + i += 2 + + ui.write(('file extras: %s (%s)\n') + % (filename, ', '.join(extrastrings))) + elif rtype == 'l': + labels = record.split('\0', 2) + labels = [l for l in labels if len(l) > 0] + ui.write(('labels:\n')) + ui.write((' local: %s\n' % labels[0])) + ui.write((' other: %s\n' % labels[1])) + if len(labels) > 2: + ui.write((' base: %s\n' % labels[2])) + else: + ui.write(('unrecognized entry: %s\t%s\n') + % (rtype, record.replace('\0', '\t'))) + + # Avoid mergestate.read() since it may raise an exception for unsupported + # merge state records. We shouldn't be doing this, but this is OK since this + # command is pretty low-level. + ms = mergemod.mergestate(repo) + + # sort so that reasonable information is on top + v1records = ms._readrecordsv1() + v2records = ms._readrecordsv2() + order = 'LOml' + def key(r): + idx = order.find(r[0]) + if idx == -1: + return (1, r[1]) + else: + return (0, idx) + v1records.sort(key=key) + v2records.sort(key=key) + + if not v1records and not v2records: + ui.write(('no merge state found\n')) + elif not v2records: + ui.note(('no version 2 merge state\n')) + printrecords(1) + elif ms._v1v2match(v1records, v2records): + ui.note(('v1 and v2 states match: using v2\n')) + printrecords(2) + else: + ui.note(('v1 and v2 states mismatch: using v1\n')) + printrecords(1) + if ui.verbose: + printrecords(2) + +@command('debugnamecomplete', [], _('NAME...')) +def debugnamecomplete(ui, repo, *args): + '''complete "names" - tags, open branch names, bookmark names''' + + names = set() + # since we previously only listed open branches, we will handle that + # specially (after this for loop) + for name, ns in repo.names.iteritems(): + if name != 'branches': + names.update(ns.listnames(repo)) + names.update(tag for (tag, heads, tip, closed) + in repo.branchmap().iterbranches() if not closed) + completions = set() + if not args: + args = [''] + for a in args: + completions.update(n for n in names if n.startswith(a)) + ui.write('\n'.join(sorted(completions))) + ui.write('\n') + +@command('debugobsolete', + [('', 'flags', 0, _('markers flag')), + ('', 'record-parents', False, + _('record parent information for the precursor')), + ('r', 'rev', [], _('display markers relevant to REV')), + ('', 'index', False, _('display index of the marker')), + ('', 'delete', [], _('delete markers specified by indices')), + ] + commands.commitopts2 + commands.formatteropts, + _('[OBSOLETED [REPLACEMENT ...]]')) +def debugobsolete(ui, repo, precursor=None, *successors, **opts): + """create arbitrary obsolete marker + + With no arguments, displays the list of obsolescence markers.""" + + def parsenodeid(s): + try: + # We do not use revsingle/revrange functions here to accept + # arbitrary node identifiers, possibly not present in the + # local repository. + n = bin(s) + if len(n) != len(nullid): + raise TypeError() + return n + except TypeError: + raise error.Abort('changeset references must be full hexadecimal ' + 'node identifiers') + + if opts.get('delete'): + indices = [] + for v in opts.get('delete'): + try: + indices.append(int(v)) + except ValueError: + raise error.Abort(_('invalid index value: %r') % v, + hint=_('use integers for indices')) + + if repo.currenttransaction(): + raise error.Abort(_('cannot delete obsmarkers in the middle ' + 'of transaction.')) + + with repo.lock(): + n = repair.deleteobsmarkers(repo.obsstore, indices) + ui.write(_('deleted %i obsolescence markers\n') % n) + + return + + if precursor is not None: + if opts['rev']: + raise error.Abort('cannot select revision when creating marker') + metadata = {} + metadata['user'] = opts['user'] or ui.username() + succs = tuple(parsenodeid(succ) for succ in successors) + l = repo.lock() + try: + tr = repo.transaction('debugobsolete') + try: + date = opts.get('date') + if date: + date = util.parsedate(date) + else: + date = None + prec = parsenodeid(precursor) + parents = None + if opts['record_parents']: + if prec not in repo.unfiltered(): + raise error.Abort('cannot used --record-parents on ' + 'unknown changesets') + parents = repo.unfiltered()[prec].parents() + parents = tuple(p.node() for p in parents) + repo.obsstore.create(tr, prec, succs, opts['flags'], + parents=parents, date=date, + metadata=metadata) + tr.close() + except ValueError as exc: + raise error.Abort(_('bad obsmarker input: %s') % exc) + finally: + tr.release() + finally: + l.release() + else: + if opts['rev']: + revs = scmutil.revrange(repo, opts['rev']) + nodes = [repo[r].node() for r in revs] + markers = list(obsolete.getmarkers(repo, nodes=nodes)) + markers.sort(key=lambda x: x._data) + else: + markers = obsolete.getmarkers(repo) + + markerstoiter = markers + isrelevant = lambda m: True + if opts.get('rev') and opts.get('index'): + markerstoiter = obsolete.getmarkers(repo) + markerset = set(markers) + isrelevant = lambda m: m in markerset + + fm = ui.formatter('debugobsolete', opts) + for i, m in enumerate(markerstoiter): + if not isrelevant(m): + # marker can be irrelevant when we're iterating over a set + # of markers (markerstoiter) which is bigger than the set + # of markers we want to display (markers) + # this can happen if both --index and --rev options are + # provided and thus we need to iterate over all of the markers + # to get the correct indices, but only display the ones that + # are relevant to --rev value + continue + fm.startitem() + ind = i if opts.get('index') else None + cmdutil.showmarker(fm, m, index=ind) + fm.end() + +@command('debugpathcomplete', + [('f', 'full', None, _('complete an entire path')), + ('n', 'normal', None, _('show only normal files')), + ('a', 'added', None, _('show only added files')), + ('r', 'removed', None, _('show only removed files'))], + _('FILESPEC...')) +def debugpathcomplete(ui, repo, *specs, **opts): + '''complete part or all of a tracked path + + This command supports shells that offer path name completion. It + currently completes only files already known to the dirstate. + + Completion extends only to the next path segment unless + --full is specified, in which case entire paths are used.''' + + def complete(path, acceptable): + dirstate = repo.dirstate + spec = os.path.normpath(os.path.join(pycompat.getcwd(), path)) + rootdir = repo.root + pycompat.ossep + if spec != repo.root and not spec.startswith(rootdir): + return [], [] + if os.path.isdir(spec): + spec += '/' + spec = spec[len(rootdir):] + fixpaths = pycompat.ossep != '/' + if fixpaths: + spec = spec.replace(pycompat.ossep, '/') + speclen = len(spec) + fullpaths = opts['full'] + files, dirs = set(), set() + adddir, addfile = dirs.add, files.add + for f, st in dirstate.iteritems(): + if f.startswith(spec) and st[0] in acceptable: + if fixpaths: + f = f.replace('/', pycompat.ossep) + if fullpaths: + addfile(f) + continue + s = f.find(pycompat.ossep, speclen) + if s >= 0: + adddir(f[:s]) + else: + addfile(f) + return files, dirs + + acceptable = '' + if opts['normal']: + acceptable += 'nm' + if opts['added']: + acceptable += 'a' + if opts['removed']: + acceptable += 'r' + cwd = repo.getcwd() + if not specs: + specs = ['.'] + + files, dirs = set(), set() + for spec in specs: + f, d = complete(spec, acceptable or 'nmar') + files.update(f) + dirs.update(d) + files.update(dirs) + ui.write('\n'.join(repo.pathto(p, cwd) for p in sorted(files))) + ui.write('\n') + +@command('debugpushkey', [], _('REPO NAMESPACE [KEY OLD NEW]'), norepo=True) +def debugpushkey(ui, repopath, namespace, *keyinfo, **opts): + '''access the pushkey key/value protocol + + With two args, list the keys in the given namespace. + + With five args, set a key to new if it currently is set to old. + Reports success or failure. + ''' + + target = hg.peer(ui, {}, repopath) + if keyinfo: + key, old, new = keyinfo + r = target.pushkey(namespace, key, old, new) + ui.status(str(r) + '\n') + return not r + else: + for k, v in sorted(target.listkeys(namespace).iteritems()): + ui.write("%s\t%s\n" % (util.escapestr(k), + util.escapestr(v))) + +@command('debugpvec', [], _('A B')) +def debugpvec(ui, repo, a, b=None): + ca = scmutil.revsingle(repo, a) + cb = scmutil.revsingle(repo, b) + pa = pvec.ctxpvec(ca) + pb = pvec.ctxpvec(cb) + if pa == pb: + rel = "=" + elif pa > pb: + rel = ">" + elif pa < pb: + rel = "<" + elif pa | pb: + rel = "|" + ui.write(_("a: %s\n") % pa) + ui.write(_("b: %s\n") % pb) + ui.write(_("depth(a): %d depth(b): %d\n") % (pa._depth, pb._depth)) + ui.write(_("delta: %d hdist: %d distance: %d relation: %s\n") % + (abs(pa._depth - pb._depth), pvec._hamming(pa._vec, pb._vec), + pa.distance(pb), rel)) + +@command('debugrebuilddirstate|debugrebuildstate', + [('r', 'rev', '', _('revision to rebuild to'), _('REV')), + ('', 'minimal', None, _('only rebuild files that are inconsistent with ' + 'the working copy parent')), + ], + _('[-r REV]')) +def debugrebuilddirstate(ui, repo, rev, **opts): + """rebuild the dirstate as it would look like for the given revision + + If no revision is specified the first current parent will be used. + + The dirstate will be set to the files of the given revision. + The actual working directory content or existing dirstate + information such as adds or removes is not considered. + + ``minimal`` will only rebuild the dirstate status for files that claim to be + tracked but are not in the parent manifest, or that exist in the parent + manifest but are not in the dirstate. It will not change adds, removes, or + modified files that are in the working copy parent. + + One use of this command is to make the next :hg:`status` invocation + check the actual file content. + """ + ctx = scmutil.revsingle(repo, rev) + with repo.wlock(): + dirstate = repo.dirstate + changedfiles = None + # See command doc for what minimal does. + if opts.get('minimal'): + manifestfiles = set(ctx.manifest().keys()) + dirstatefiles = set(dirstate) + manifestonly = manifestfiles - dirstatefiles + dsonly = dirstatefiles - manifestfiles + dsnotadded = set(f for f in dsonly if dirstate[f] != 'a') + changedfiles = manifestonly | dsnotadded + + dirstate.rebuild(ctx.node(), ctx.manifest(), changedfiles) + +@command('debugrebuildfncache', [], '') +def debugrebuildfncache(ui, repo): + """rebuild the fncache file""" + repair.rebuildfncache(ui, repo) + +@command('debugrename', + [('r', 'rev', '', _('revision to debug'), _('REV'))], + _('[-r REV] FILE')) +def debugrename(ui, repo, file1, *pats, **opts): + """dump rename information""" + + ctx = scmutil.revsingle(repo, opts.get('rev')) + m = scmutil.match(ctx, (file1,) + pats, opts) + for abs in ctx.walk(m): + fctx = ctx[abs] + o = fctx.filelog().renamed(fctx.filenode()) + rel = m.rel(abs) + if o: + ui.write(_("%s renamed from %s:%s\n") % (rel, o[0], hex(o[1]))) + else: + ui.write(_("%s not renamed\n") % rel) + +@command('debugrevlog', commands.debugrevlogopts + + [('d', 'dump', False, _('dump index data'))], + _('-c|-m|FILE'), + optionalrepo=True) +def debugrevlog(ui, repo, file_=None, **opts): + """show data and statistics about a revlog""" + r = cmdutil.openrevlog(repo, 'debugrevlog', file_, opts) + + if opts.get("dump"): + numrevs = len(r) + ui.write(("# rev p1rev p2rev start end deltastart base p1 p2" + " rawsize totalsize compression heads chainlen\n")) + ts = 0 + heads = set() + + for rev in xrange(numrevs): + dbase = r.deltaparent(rev) + if dbase == -1: + dbase = rev + cbase = r.chainbase(rev) + clen = r.chainlen(rev) + p1, p2 = r.parentrevs(rev) + rs = r.rawsize(rev) + ts = ts + rs + heads -= set(r.parentrevs(rev)) + heads.add(rev) + try: + compression = ts / r.end(rev) + except ZeroDivisionError: + compression = 0 + ui.write("%5d %5d %5d %5d %5d %10d %4d %4d %4d %7d %9d " + "%11d %5d %8d\n" % + (rev, p1, p2, r.start(rev), r.end(rev), + r.start(dbase), r.start(cbase), + r.start(p1), r.start(p2), + rs, ts, compression, len(heads), clen)) + return 0 + + v = r.version + format = v & 0xFFFF + flags = [] + gdelta = False + if v & revlog.REVLOGNGINLINEDATA: + flags.append('inline') + if v & revlog.REVLOGGENERALDELTA: + gdelta = True + flags.append('generaldelta') + if not flags: + flags = ['(none)'] + + nummerges = 0 + numfull = 0 + numprev = 0 + nump1 = 0 + nump2 = 0 + numother = 0 + nump1prev = 0 + nump2prev = 0 + chainlengths = [] + + datasize = [None, 0, 0] + fullsize = [None, 0, 0] + deltasize = [None, 0, 0] + chunktypecounts = {} + chunktypesizes = {} + + def addsize(size, l): + if l[0] is None or size < l[0]: + l[0] = size + if size > l[1]: + l[1] = size + l[2] += size + + numrevs = len(r) + for rev in xrange(numrevs): + p1, p2 = r.parentrevs(rev) + delta = r.deltaparent(rev) + if format > 0: + addsize(r.rawsize(rev), datasize) + if p2 != nullrev: + nummerges += 1 + size = r.length(rev) + if delta == nullrev: + chainlengths.append(0) + numfull += 1 + addsize(size, fullsize) + else: + chainlengths.append(chainlengths[delta] + 1) + addsize(size, deltasize) + if delta == rev - 1: + numprev += 1 + if delta == p1: + nump1prev += 1 + elif delta == p2: + nump2prev += 1 + elif delta == p1: + nump1 += 1 + elif delta == p2: + nump2 += 1 + elif delta != nullrev: + numother += 1 + + # Obtain data on the raw chunks in the revlog. + chunk = r._chunkraw(rev, rev)[1] + if chunk: + chunktype = chunk[0] + else: + chunktype = 'empty' + + if chunktype not in chunktypecounts: + chunktypecounts[chunktype] = 0 + chunktypesizes[chunktype] = 0 + + chunktypecounts[chunktype] += 1 + chunktypesizes[chunktype] += size + + # Adjust size min value for empty cases + for size in (datasize, fullsize, deltasize): + if size[0] is None: + size[0] = 0 + + numdeltas = numrevs - numfull + numoprev = numprev - nump1prev - nump2prev + totalrawsize = datasize[2] + datasize[2] /= numrevs + fulltotal = fullsize[2] + fullsize[2] /= numfull + deltatotal = deltasize[2] + if numrevs - numfull > 0: + deltasize[2] /= numrevs - numfull + totalsize = fulltotal + deltatotal + avgchainlen = sum(chainlengths) / numrevs + maxchainlen = max(chainlengths) + compratio = 1 + if totalsize: + compratio = totalrawsize / totalsize + + basedfmtstr = '%%%dd\n' + basepcfmtstr = '%%%dd %s(%%5.2f%%%%)\n' + + def dfmtstr(max): + return basedfmtstr % len(str(max)) + def pcfmtstr(max, padding=0): + return basepcfmtstr % (len(str(max)), ' ' * padding) + + def pcfmt(value, total): + if total: + return (value, 100 * float(value) / total) + else: + return value, 100.0 + + ui.write(('format : %d\n') % format) + ui.write(('flags : %s\n') % ', '.join(flags)) + + ui.write('\n') + fmt = pcfmtstr(totalsize) + fmt2 = dfmtstr(totalsize) + ui.write(('revisions : ') + fmt2 % numrevs) + ui.write((' merges : ') + fmt % pcfmt(nummerges, numrevs)) + ui.write((' normal : ') + fmt % pcfmt(numrevs - nummerges, numrevs)) + ui.write(('revisions : ') + fmt2 % numrevs) + ui.write((' full : ') + fmt % pcfmt(numfull, numrevs)) + ui.write((' deltas : ') + fmt % pcfmt(numdeltas, numrevs)) + ui.write(('revision size : ') + fmt2 % totalsize) + ui.write((' full : ') + fmt % pcfmt(fulltotal, totalsize)) + ui.write((' deltas : ') + fmt % pcfmt(deltatotal, totalsize)) + + def fmtchunktype(chunktype): + if chunktype == 'empty': + return ' %s : ' % chunktype + elif chunktype in string.ascii_letters: + return ' 0x%s (%s) : ' % (hex(chunktype), chunktype) + else: + return ' 0x%s : ' % hex(chunktype) + + ui.write('\n') + ui.write(('chunks : ') + fmt2 % numrevs) + for chunktype in sorted(chunktypecounts): + ui.write(fmtchunktype(chunktype)) + ui.write(fmt % pcfmt(chunktypecounts[chunktype], numrevs)) + ui.write(('chunks size : ') + fmt2 % totalsize) + for chunktype in sorted(chunktypecounts): + ui.write(fmtchunktype(chunktype)) + ui.write(fmt % pcfmt(chunktypesizes[chunktype], totalsize)) + + ui.write('\n') + fmt = dfmtstr(max(avgchainlen, compratio)) + ui.write(('avg chain length : ') + fmt % avgchainlen) + ui.write(('max chain length : ') + fmt % maxchainlen) + ui.write(('compression ratio : ') + fmt % compratio) + + if format > 0: + ui.write('\n') + ui.write(('uncompressed data size (min/max/avg) : %d / %d / %d\n') + % tuple(datasize)) + ui.write(('full revision size (min/max/avg) : %d / %d / %d\n') + % tuple(fullsize)) + ui.write(('delta size (min/max/avg) : %d / %d / %d\n') + % tuple(deltasize)) + + if numdeltas > 0: + ui.write('\n') + fmt = pcfmtstr(numdeltas) + fmt2 = pcfmtstr(numdeltas, 4) + ui.write(('deltas against prev : ') + fmt % pcfmt(numprev, numdeltas)) + if numprev > 0: + ui.write((' where prev = p1 : ') + fmt2 % pcfmt(nump1prev, + numprev)) + ui.write((' where prev = p2 : ') + fmt2 % pcfmt(nump2prev, + numprev)) + ui.write((' other : ') + fmt2 % pcfmt(numoprev, + numprev)) + if gdelta: + ui.write(('deltas against p1 : ') + + fmt % pcfmt(nump1, numdeltas)) + ui.write(('deltas against p2 : ') + + fmt % pcfmt(nump2, numdeltas)) + ui.write(('deltas against other : ') + fmt % pcfmt(numother, + numdeltas)) + +@command('debugrevspec', + [('', 'optimize', None, + _('print parsed tree after optimizing (DEPRECATED)')), + ('p', 'show-stage', [], + _('print parsed tree at the given stage'), _('NAME')), + ('', 'no-optimized', False, _('evaluate tree without optimization')), + ('', 'verify-optimized', False, _('verify optimized result')), + ], + ('REVSPEC')) +def debugrevspec(ui, repo, expr, **opts): + """parse and apply a revision specification + + Use -p/--show-stage option to print the parsed tree at the given stages. + Use -p all to print tree at every stage. + + Use --verify-optimized to compare the optimized result with the unoptimized + one. Returns 1 if the optimized result differs. + """ + stages = [ + ('parsed', lambda tree: tree), + ('expanded', lambda tree: revsetlang.expandaliases(ui, tree)), + ('concatenated', revsetlang.foldconcat), + ('analyzed', revsetlang.analyze), + ('optimized', revsetlang.optimize), + ] + if opts['no_optimized']: + stages = stages[:-1] + if opts['verify_optimized'] and opts['no_optimized']: + raise error.Abort(_('cannot use --verify-optimized with ' + '--no-optimized')) + stagenames = set(n for n, f in stages) + + showalways = set() + showchanged = set() + if ui.verbose and not opts['show_stage']: + # show parsed tree by --verbose (deprecated) + showalways.add('parsed') + showchanged.update(['expanded', 'concatenated']) + if opts['optimize']: + showalways.add('optimized') + if opts['show_stage'] and opts['optimize']: + raise error.Abort(_('cannot use --optimize with --show-stage')) + if opts['show_stage'] == ['all']: + showalways.update(stagenames) + else: + for n in opts['show_stage']: + if n not in stagenames: + raise error.Abort(_('invalid stage name: %s') % n) + showalways.update(opts['show_stage']) + + treebystage = {} + printedtree = None + tree = revsetlang.parse(expr, lookup=repo.__contains__) + for n, f in stages: + treebystage[n] = tree = f(tree) + if n in showalways or (n in showchanged and tree != printedtree): + if opts['show_stage'] or n != 'parsed': + ui.write(("* %s:\n") % n) + ui.write(revsetlang.prettyformat(tree), "\n") + printedtree = tree + + if opts['verify_optimized']: + arevs = revset.makematcher(treebystage['analyzed'])(repo) + brevs = revset.makematcher(treebystage['optimized'])(repo) + if ui.verbose: + ui.note(("* analyzed set:\n"), smartset.prettyformat(arevs), "\n") + ui.note(("* optimized set:\n"), smartset.prettyformat(brevs), "\n") + arevs = list(arevs) + brevs = list(brevs) + if arevs == brevs: + return 0 + ui.write(('--- analyzed\n'), label='diff.file_a') + ui.write(('+++ optimized\n'), label='diff.file_b') + sm = difflib.SequenceMatcher(None, arevs, brevs) + for tag, alo, ahi, blo, bhi in sm.get_opcodes(): + if tag in ('delete', 'replace'): + for c in arevs[alo:ahi]: + ui.write('-%s\n' % c, label='diff.deleted') + if tag in ('insert', 'replace'): + for c in brevs[blo:bhi]: + ui.write('+%s\n' % c, label='diff.inserted') + if tag == 'equal': + for c in arevs[alo:ahi]: + ui.write(' %s\n' % c) + return 1 + + func = revset.makematcher(tree) + revs = func(repo) + if ui.verbose: + ui.note(("* set:\n"), smartset.prettyformat(revs), "\n") + for c in revs: + ui.write("%s\n" % c) + +@command('debugsetparents', [], _('REV1 [REV2]')) +def debugsetparents(ui, repo, rev1, rev2=None): + """manually set the parents of the current working directory + + This is useful for writing repository conversion tools, but should + be used with care. For example, neither the working directory nor the + dirstate is updated, so file status may be incorrect after running this + command. + + Returns 0 on success. + """ + + r1 = scmutil.revsingle(repo, rev1).node() + r2 = scmutil.revsingle(repo, rev2, 'null').node() + + with repo.wlock(): + repo.setparents(r1, r2) + +@command('debugsub', + [('r', 'rev', '', + _('revision to check'), _('REV'))], + _('[-r REV] [REV]')) +def debugsub(ui, repo, rev=None): + ctx = scmutil.revsingle(repo, rev, None) + for k, v in sorted(ctx.substate.items()): + ui.write(('path %s\n') % k) + ui.write((' source %s\n') % v[0]) + ui.write((' revision %s\n') % v[1]) + +@command('debugsuccessorssets', + [], + _('[REV]')) +def debugsuccessorssets(ui, repo, *revs): + """show set of successors for revision + + A successors set of changeset A is a consistent group of revisions that + succeed A. It contains non-obsolete changesets only. + + In most cases a changeset A has a single successors set containing a single + successor (changeset A replaced by A'). + + A changeset that is made obsolete with no successors are called "pruned". + Such changesets have no successors sets at all. + + A changeset that has been "split" will have a successors set containing + more than one successor. + + A changeset that has been rewritten in multiple different ways is called + "divergent". Such changesets have multiple successor sets (each of which + may also be split, i.e. have multiple successors). + + Results are displayed as follows:: + + <rev1> + <successors-1A> + <rev2> + <successors-2A> + <successors-2B1> <successors-2B2> <successors-2B3> + + Here rev2 has two possible (i.e. divergent) successors sets. The first + holds one element, whereas the second holds three (i.e. the changeset has + been split). + """ + # passed to successorssets caching computation from one call to another + cache = {} + ctx2str = str + node2str = short + if ui.debug(): + def ctx2str(ctx): + return ctx.hex() + node2str = hex + for rev in scmutil.revrange(repo, revs): + ctx = repo[rev] + ui.write('%s\n'% ctx2str(ctx)) + for succsset in obsolete.successorssets(repo, ctx.node(), cache): + if succsset: + ui.write(' ') + ui.write(node2str(succsset[0])) + for node in succsset[1:]: + ui.write(' ') + ui.write(node2str(node)) + ui.write('\n') + +@command('debugtemplate', + [('r', 'rev', [], _('apply template on changesets'), _('REV')), + ('D', 'define', [], _('define template keyword'), _('KEY=VALUE'))], + _('[-r REV]... [-D KEY=VALUE]... TEMPLATE'), + optionalrepo=True) +def debugtemplate(ui, repo, tmpl, **opts): + """parse and apply a template + + If -r/--rev is given, the template is processed as a log template and + applied to the given changesets. Otherwise, it is processed as a generic + template. + + Use --verbose to print the parsed tree. + """ + revs = None + if opts['rev']: + if repo is None: + raise error.RepoError(_('there is no Mercurial repository here ' + '(.hg not found)')) + revs = scmutil.revrange(repo, opts['rev']) + + props = {} + for d in opts['define']: + try: + k, v = (e.strip() for e in d.split('=', 1)) + if not k or k == 'ui': + raise ValueError + props[k] = v + except ValueError: + raise error.Abort(_('malformed keyword definition: %s') % d) + + if ui.verbose: + aliases = ui.configitems('templatealias') + tree = templater.parse(tmpl) + ui.note(templater.prettyformat(tree), '\n') + newtree = templater.expandaliases(tree, aliases) + if newtree != tree: + ui.note(("* expanded:\n"), templater.prettyformat(newtree), '\n') + + mapfile = None + if revs is None: + k = 'debugtemplate' + t = formatter.maketemplater(ui, k, tmpl) + ui.write(templater.stringify(t(k, ui=ui, **props))) + else: + displayer = cmdutil.changeset_templater(ui, repo, None, opts, tmpl, + mapfile, buffered=False) + for r in revs: + displayer.show(repo[r], **props) + displayer.close() + @command('debugupgraderepo', [ ('o', 'optimize', [], _('extra optimization to perform'), _('NAME')), ('', 'run', False, _('performs an upgrade')), @@ -874,4 +2073,44 @@ should complete almost instantaneously and the chances of a consumer being unable to access the repository should be low. """ - return repair.upgraderepo(ui, repo, run=run, optimize=optimize) + return upgrade.upgraderepo(ui, repo, run=run, optimize=optimize) + +@command('debugwalk', commands.walkopts, _('[OPTION]... [FILE]...'), + inferrepo=True) +def debugwalk(ui, repo, *pats, **opts): + """show how files match on given patterns""" + m = scmutil.match(repo[None], pats, opts) + items = list(repo.walk(m)) + if not items: + return + f = lambda fn: fn + if ui.configbool('ui', 'slash') and pycompat.ossep != '/': + f = lambda fn: util.normpath(fn) + fmt = 'f %%-%ds %%-%ds %%s' % ( + max([len(abs) for abs in items]), + max([len(m.rel(abs)) for abs in items])) + for abs in items: + line = fmt % (abs, f(m.rel(abs)), m.exact(abs) and 'exact' or '') + ui.write("%s\n" % line.rstrip()) + +@command('debugwireargs', + [('', 'three', '', 'three'), + ('', 'four', '', 'four'), + ('', 'five', '', 'five'), + ] + commands.remoteopts, + _('REPO [OPTIONS]... [ONE [TWO]]'), + norepo=True) +def debugwireargs(ui, repopath, *vals, **opts): + repo = hg.peer(ui, opts, repopath) + for opt in commands.remoteopts: + del opts[opt[1]] + args = {} + for k, v in opts.iteritems(): + if v: + args[k] = v + # run twice to check that we don't mess up the stream for the next command + res1 = repo.debugwireargs(*vals, **args) + res2 = repo.debugwireargs(*vals, **args) + ui.write("%s\n" % res1) + if res1 != res2: + ui.warn("%s\n" % res2)
--- a/mercurial/demandimport.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/demandimport.py Tue Apr 18 12:24:34 2017 -0400 @@ -76,9 +76,9 @@ else: head = name after = [] - object.__setattr__(self, "_data", + object.__setattr__(self, r"_data", (head, globals, locals, after, level, set())) - object.__setattr__(self, "_module", None) + object.__setattr__(self, r"_module", None) def _extend(self, name): """add to the list of submodules to load""" self._data[3].append(name) @@ -138,7 +138,7 @@ if modref and getattr(modref, head, None) == self: setattr(modref, head, mod) - object.__setattr__(self, "_module", mod) + object.__setattr__(self, r"_module", mod) def __repr__(self): if self._module: @@ -274,6 +274,7 @@ 'fcntl', 'nt', # pathlib2 tests the existence of built-in 'nt' module 'win32com.gen_py', + 'win32com.shell', # 'appdirs' tries to import win32com.shell '_winreg', # 2.7 mimetypes needs immediate ImportError 'pythoncom', # imported by tarfile, not available under Windows
--- a/mercurial/destutil.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/destutil.py Tue Apr 18 12:24:34 2017 -0400 @@ -12,37 +12,10 @@ bookmarks, error, obsolete, + scmutil, ) -def _destupdatevalidate(repo, rev, clean, check): - """validate that the destination comply to various rules - - This exists as its own function to help wrapping from extensions.""" - wc = repo[None] - p1 = wc.p1() - if not clean: - # Check that the update is linear. - # - # Mercurial do not allow update-merge for non linear pattern - # (that would be technically possible but was considered too confusing - # for user a long time ago) - # - # See mercurial.merge.update for details - if p1.rev() not in repo.changelog.ancestors([rev], inclusive=True): - dirty = wc.dirty(missing=True) - foreground = obsolete.foreground(repo, [p1.node()]) - if not repo[rev].node() in foreground: - if dirty: - msg = _("uncommitted changes") - hint = _("commit and merge, or update --clean to" - " discard changes") - raise error.UpdateAbort(msg, hint=hint) - elif not check: # destination is not a descendant. - msg = _("not a linear update") - hint = _("merge or update --check to force update") - raise error.UpdateAbort(msg, hint=hint) - -def _destupdateobs(repo, clean, check): +def _destupdateobs(repo, clean): """decide of an update destination from obsolescence markers""" node = None wc = repo[None] @@ -78,7 +51,7 @@ movemark = repo['.'].node() return node, movemark, None -def _destupdatebook(repo, clean, check): +def _destupdatebook(repo, clean): """decide on an update destination from active bookmark""" # we also move the active bookmark, if any activemark = None @@ -87,7 +60,7 @@ activemark = node return node, movemark, activemark -def _destupdatebranch(repo, clean, check): +def _destupdatebranch(repo, clean): """decide on an update destination from current branch This ignores closed branch heads. @@ -113,7 +86,7 @@ node = repo['.'].node() return node, movemark, None -def _destupdatebranchfallback(repo, clean, check): +def _destupdatebranchfallback(repo, clean): """decide on an update destination from closed heads in current branch""" wc = repo[None] currentbranch = wc.branch() @@ -143,7 +116,7 @@ 'branchfallback': _destupdatebranchfallback, } -def destupdate(repo, clean=False, check=False): +def destupdate(repo, clean=False): """destination for bare update operation return (rev, movemark, activemark) @@ -156,13 +129,11 @@ node = movemark = activemark = None for step in destupdatesteps: - node, movemark, activemark = destupdatestepmap[step](repo, clean, check) + node, movemark, activemark = destupdatestepmap[step](repo, clean) if node is not None: break rev = repo[node].rev() - _destupdatevalidate(repo, rev, clean, check) - return rev, movemark, activemark msgdestmerge = { @@ -372,9 +343,6 @@ def desthistedit(ui, repo): """Default base revision to edit for `hg histedit`.""" - # Avoid cycle: scmutil -> revset -> destutil - from . import scmutil - default = ui.config('histedit', 'defaultrev', histeditdefaultrevset) if default: revs = scmutil.revrange(repo, [default])
--- a/mercurial/dirstate.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/dirstate.py Tue Apr 18 12:24:34 2017 -0400 @@ -23,6 +23,7 @@ pathutil, pycompat, scmutil, + txnutil, util, ) @@ -54,26 +55,16 @@ def nonnormalentries(dmap): '''Compute the nonnormal dirstate entries from the dmap''' try: - return parsers.nonnormalentries(dmap) + return parsers.nonnormalotherparententries(dmap) except AttributeError: - return set(fname for fname, e in dmap.iteritems() - if e[0] != 'n' or e[3] == -1) - -def _trypending(root, vfs, filename): - '''Open file to be read according to HG_PENDING environment variable - - This opens '.pending' of specified 'filename' only when HG_PENDING - is equal to 'root'. - - This returns '(fp, is_pending_opened)' tuple. - ''' - if root == encoding.environ.get('HG_PENDING'): - try: - return (vfs('%s.pending' % filename), True) - except IOError as inst: - if inst.errno != errno.ENOENT: - raise - return (vfs(filename), False) + nonnorm = set() + otherparent = set() + for fname, e in dmap.iteritems(): + if e[0] != 'n' or e[3] == -1: + nonnorm.add(fname) + if e[0] == 'n' and e[2] == -2: + otherparent.add(fname) + return nonnorm, otherparent class dirstate(object): @@ -104,6 +95,7 @@ self._pendingfilename = '%s.pending' % self._filename self._plchangecallbacks = {} self._origpl = None + self._updatedfiles = set() # for consistent view between _pl() and _read() invocations self._pendingmode = None @@ -145,7 +137,15 @@ @propertycache def _nonnormalset(self): - return nonnormalentries(self._map) + nonnorm, otherparents = nonnormalentries(self._map) + self._otherparentset = otherparents + return nonnorm + + @propertycache + def _otherparentset(self): + nonnorm, otherparents = nonnormalentries(self._map) + self._nonnormalset = nonnorm + return otherparents @propertycache def _filefoldmap(self): @@ -355,7 +355,12 @@ self._pl = p1, p2 copies = {} if oldp2 != nullid and p2 == nullid: - for f, s in self._map.iteritems(): + candidatefiles = self._nonnormalset.union(self._otherparentset) + for f in candidatefiles: + s = self._map.get(f) + if s is None: + continue + # Discard 'm' markers when moving away from a merge state if s[0] == 'm': if f in self._copymap: @@ -385,7 +390,7 @@ raise def _opendirstatefile(self): - fp, mode = _trypending(self._root, self._opener, self._filename) + fp, mode = txnutil.trypending(self._root, self._opener, self._filename) if self._pendingmode is not None and self._pendingmode != mode: fp.close() raise error.Abort(_('working directory state may be ' @@ -441,11 +446,13 @@ def invalidate(self): for a in ("_map", "_copymap", "_filefoldmap", "_dirfoldmap", "_branch", - "_pl", "_dirs", "_ignore", "_nonnormalset"): + "_pl", "_dirs", "_ignore", "_nonnormalset", + "_otherparentset"): if a in self.__dict__: delattr(self, a) self._lastnormaltime = 0 self._dirty = False + self._updatedfiles.clear() self._parentwriters = 0 self._origpl = None @@ -456,8 +463,11 @@ self._dirty = True if source is not None: self._copymap[dest] = source + self._updatedfiles.add(source) + self._updatedfiles.add(dest) elif dest in self._copymap: del self._copymap[dest] + self._updatedfiles.add(dest) def copied(self, file): return self._copymap.get(file, None) @@ -474,6 +484,8 @@ if normed in self._filefoldmap: del self._filefoldmap[normed] + self._updatedfiles.add(f) + def _addpath(self, f, state, mode, size, mtime): oldstate = self[f] if state == 'a' or oldstate == 'r': @@ -490,9 +502,12 @@ if oldstate in "?r" and "_dirs" in self.__dict__: self._dirs.addpath(f) self._dirty = True + self._updatedfiles.add(f) self._map[f] = dirstatetuple(state, mode, size, mtime) if state != 'n' or mtime == -1: self._nonnormalset.add(f) + if size == -2: + self._otherparentset.add(f) def normal(self, f): '''Mark a file normal and clean.''' @@ -567,6 +582,7 @@ size = -1 elif entry[0] == 'n' and entry[2] == -2: # other parent size = -2 + self._otherparentset.add(f) self._map[f] = dirstatetuple('r', 0, size, 0) self._nonnormalset.add(f) if size == 0 and f in self._copymap: @@ -666,11 +682,13 @@ def clear(self): self._map = {} self._nonnormalset = set() + self._otherparentset = set() if "_dirs" in self.__dict__: delattr(self, "_dirs") self._copymap = {} self._pl = [nullid, nullid] self._lastnormaltime = 0 + self._updatedfiles.clear() self._dirty = True def rebuild(self, parent, allfiles, changedfiles=None): @@ -707,13 +725,15 @@ # emulate dropping timestamp in 'parsers.pack_dirstate' now = _getfsnow(self._opener) dmap = self._map - for f, e in dmap.iteritems(): - if e[0] == 'n' and e[3] == now: + for f in self._updatedfiles: + e = dmap.get(f) + if e is not None and e[0] == 'n' and e[3] == now: dmap[f] = dirstatetuple(e[0], e[1], e[2], -1) self._nonnormalset.add(f) # emulate that all 'dirstate.normal' results are written out self._lastnormaltime = 0 + self._updatedfiles.clear() # delay writing in-memory changes out tr.addfilegenerator('dirstate', (self._filename,), @@ -762,7 +782,7 @@ break st.write(parsers.pack_dirstate(self._map, self._copymap, self._pl, now)) - self._nonnormalset = nonnormalentries(self._map) + self._nonnormalset, self._otherparentset = nonnormalentries(self._map) st.close() self._lastnormaltime = 0 self._dirty = self._dirtypl = False @@ -1059,7 +1079,7 @@ # a) not matching matchfn b) ignored, c) missing, or d) under a # symlink directory. if not results and matchalways: - visit = dmap.keys() + visit = [f for f in dmap] else: visit = [f for f in dmap if f not in results and matchfn(f)] visit.sort() @@ -1095,9 +1115,9 @@ else: # We may not have walked the full directory tree above, # so stat and check everything we missed. - nf = iter(visit).next + iv = iter(visit) for st in util.statfiles([join(i) for i in visit]): - results[nf()] = st + results[next(iv)] = st return results def status(self, match, subrepos, ignored, clean, unknown): @@ -1224,8 +1244,9 @@ # use '_writedirstate' instead of 'write' to write changes certainly, # because the latter omits writing out if transaction is running. # output file will be used to create backup of dirstate at this point. - self._writedirstate(self._opener(filename, "w", atomictemp=True, - checkambig=True)) + if self._dirty or not self._opener.exists(filename): + self._writedirstate(self._opener(filename, "w", atomictemp=True, + checkambig=True)) if tr: # ensure that subsequent tr.writepending returns True for @@ -1239,8 +1260,13 @@ # end of this transaction tr.registertmp(filename, location='plain') - self._opener.write(prefix + self._filename + suffix, - self._opener.tryread(filename)) + backupname = prefix + self._filename + suffix + assert backupname != filename + self._opener.tryunlink(backupname) + # hardlink backup is okay because _writedirstate is always called + # with an "atomictemp=True" file. + util.copyfile(self._opener.join(filename), + self._opener.join(backupname), hardlink=True) def restorebackup(self, tr, suffix='', prefix=''): '''Restore dirstate by backup file with suffix'''
--- a/mercurial/discovery.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/discovery.py Tue Apr 18 12:24:34 2017 -0400 @@ -7,8 +7,11 @@ from __future__ import absolute_import +import functools + from .i18n import _ from .node import ( + hex, nullid, short, ) @@ -17,7 +20,6 @@ bookmarks, branchmap, error, - obsolete, phases, setdiscovery, treediscovery, @@ -343,38 +345,13 @@ oldhs.update(unsyncedheads) candidate_newhs.update(unsyncedheads) dhs = None # delta heads, the new heads on branch - discardedheads = set() if not repo.obsstore: + discardedheads = set() newhs = candidate_newhs else: - # remove future heads which are actually obsoleted by another - # pushed element: - # - # XXX as above, There are several cases this code does not handle - # XXX properly - # - # (1) if <nh> is public, it won't be affected by obsolete marker - # and a new is created - # - # (2) if the new heads have ancestors which are not obsolete and - # not ancestors of any other heads we will have a new head too. - # - # These two cases will be easy to handle for known changeset but - # much more tricky for unsynced changes. - # - # In addition, this code is confused by prune as it only looks for - # successors of the heads (none if pruned) leading to issue4354 - newhs = set() - for nh in candidate_newhs: - if nh in repo and repo[nh].phase() <= phases.public: - newhs.add(nh) - else: - for suc in obsolete.allsuccessors(repo.obsstore, [nh]): - if suc != nh and suc in allfuturecommon: - discardedheads.add(nh) - break - else: - newhs.add(nh) + newhs, discardedheads = _postprocessobsolete(pushop, + allfuturecommon, + candidate_newhs) unsynced = sorted(h for h in unsyncedheads if h not in discardedheads) if unsynced: if None in unsynced: @@ -434,3 +411,109 @@ repo.ui.note((" %s\n") % short(h)) if errormsg: raise error.Abort(errormsg, hint=hint) + +def _postprocessobsolete(pushop, futurecommon, candidate_newhs): + """post process the list of new heads with obsolescence information + + Exists as a sub-function to contain the complexity and allow extensions to + experiment with smarter logic. + + Returns (newheads, discarded_heads) tuple + """ + # known issue + # + # * We "silently" skip processing on all changeset unknown locally + # + # * if <nh> is public on the remote, it won't be affected by obsolete + # marker and a new is created + + # define various utilities and containers + repo = pushop.repo + unfi = repo.unfiltered() + tonode = unfi.changelog.node + public = phases.public + getphase = unfi._phasecache.phase + ispublic = (lambda r: getphase(unfi, r) == public) + hasoutmarker = functools.partial(pushingmarkerfor, unfi.obsstore, + futurecommon) + successorsmarkers = unfi.obsstore.successors + newhs = set() # final set of new heads + discarded = set() # new head of fully replaced branch + + localcandidate = set() # candidate heads known locally + unknownheads = set() # candidate heads unknown locally + for h in candidate_newhs: + if h in unfi: + localcandidate.add(h) + else: + if successorsmarkers.get(h) is not None: + msg = ('checkheads: remote head unknown locally has' + ' local marker: %s\n') + repo.ui.debug(msg % hex(h)) + unknownheads.add(h) + + # fast path the simple case + if len(localcandidate) == 1: + return unknownheads | set(candidate_newhs), set() + + # actually process branch replacement + while localcandidate: + nh = localcandidate.pop() + # run this check early to skip the evaluation of the whole branch + if (nh in futurecommon + or unfi[nh].phase() <= public): + newhs.add(nh) + continue + + # Get all revs/nodes on the branch exclusive to this head + # (already filtered heads are "ignored")) + branchrevs = unfi.revs('only(%n, (%ln+%ln))', + nh, localcandidate, newhs) + branchnodes = [tonode(r) for r in branchrevs] + + # The branch won't be hidden on the remote if + # * any part of it is public, + # * any part of it is considered part of the result by previous logic, + # * if we have no markers to push to obsolete it. + if (any(ispublic(r) for r in branchrevs) + or any(n in futurecommon for n in branchnodes) + or any(not hasoutmarker(n) for n in branchnodes)): + newhs.add(nh) + else: + # note: there is a corner case if there is a merge in the branch. + # we might end up with -more- heads. However, these heads are not + # "added" by the push, but more by the "removal" on the remote so I + # think is a okay to ignore them, + discarded.add(nh) + newhs |= unknownheads + return newhs, discarded + +def pushingmarkerfor(obsstore, pushset, node): + """true if some markers are to be pushed for node + + We cannot just look in to the pushed obsmarkers from the pushop because + discovery might have filtered relevant markers. In addition listing all + markers relevant to all changesets in the pushed set would be too expensive + (O(len(repo))) + + (note: There are cache opportunity in this function. but it would requires + a two dimensional stack.) + """ + successorsmarkers = obsstore.successors + stack = [node] + seen = set(stack) + while stack: + current = stack.pop() + if current in pushset: + return True + markers = successorsmarkers.get(current, ()) + # markers fields = ('prec', 'succs', 'flag', 'meta', 'date', 'parents') + for m in markers: + nexts = m[1] # successors + if not nexts: # this is a prune marker + nexts = m[5] # parents + for n in nexts: + if n not in seen: + seen.add(n) + stack.append(n) + return False
--- a/mercurial/dispatch.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/dispatch.py Tue Apr 18 12:24:34 2017 -0400 @@ -7,7 +7,6 @@ from __future__ import absolute_import, print_function -import atexit import difflib import errno import getopt @@ -33,6 +32,7 @@ extensions, fancyopts, fileset, + help, hg, hook, profiling, @@ -58,9 +58,41 @@ self.fout = fout self.ferr = ferr + def _runexithandlers(self): + exc = None + handlers = self.ui._exithandlers + try: + while handlers: + func, args, kwargs = handlers.pop() + try: + func(*args, **kwargs) + except: # re-raises below + if exc is None: + exc = sys.exc_info()[1] + self.ui.warn(('error in exit handlers:\n')) + self.ui.traceback(force=True) + finally: + if exc is not None: + raise exc + def run(): "run the command in sys.argv" - sys.exit((dispatch(request(pycompat.sysargv[1:])) or 0) & 255) + req = request(pycompat.sysargv[1:]) + err = None + try: + status = (dispatch(req) or 0) & 255 + except error.StdioError as err: + status = -1 + if util.safehasattr(req.ui, 'fout'): + try: + req.ui.fout.close() + except IOError as err: + status = -1 + if util.safehasattr(req.ui, 'ferr'): + if err is not None and err.errno != errno.EPIPE: + req.ui.ferr.write('abort: %s\n' % err.strerror) + req.ui.ferr.close() + sys.exit(status & 255) def _getsimilar(symbols, value): sim = lambda x: difflib.SequenceMatcher(None, value, x).ratio() @@ -91,6 +123,9 @@ if inst.hint: write(_("(%s)\n") % inst.hint) +def _formatargs(args): + return ' '.join(util.shellquote(a) for a in args) + def dispatch(req): "run the command specified in req.args" if req.ferr: @@ -122,23 +157,34 @@ _formatparse(ferr.write, inst) return -1 - msg = ' '.join(' ' in a and repr(a) or a for a in req.args) - starttime = time.time() + msg = _formatargs(req.args) + starttime = util.timer() ret = None try: ret = _runcatch(req) except KeyboardInterrupt: try: req.ui.warn(_("interrupted!\n")) + except error.SignalInterrupt: + # maybe pager would quit without consuming all the output, and + # SIGPIPE was raised. we cannot print anything in this case. + pass except IOError as inst: if inst.errno != errno.EPIPE: raise ret = -1 finally: - duration = time.time() - starttime + duration = util.timer() - starttime req.ui.flush() + if req.ui.logblockedtimes: + req.ui._blockedtimes['command_duration'] = duration * 1000 + req.ui.log('uiblocked', 'ui blocked ms', **req.ui._blockedtimes) req.ui.log("commandfinish", "%s exited %s after %0.2f seconds\n", msg, ret or 0, duration) + try: + req._runexithandlers() + except: # exiting, so no re-raises + ret = ret or -1 return ret def _runcatch(req): @@ -244,12 +290,11 @@ if '--debugger' in req.args: traceback.print_exc() debugmortem[debugger](sys.exc_info()[2]) - ui.traceback() raise - return callcatch(ui, _runcatchfunc) + return _callcatch(ui, _runcatchfunc) -def callcatch(ui, func): +def _callcatch(ui, func): """like scmutil.callcatch but handles more high-level exceptions about config parsing and commands. besides, use handlecommandexception to handle uncaught exceptions. @@ -261,28 +306,35 @@ (inst.args[0], " ".join(inst.args[1]))) except error.CommandError as inst: if inst.args[0]: + ui.pager('help') ui.warn(_("hg %s: %s\n") % (inst.args[0], inst.args[1])) commands.help_(ui, inst.args[0], full=False, command=True) else: + ui.pager('help') ui.warn(_("hg: %s\n") % inst.args[1]) commands.help_(ui, 'shortlist') except error.ParseError as inst: _formatparse(ui.warn, inst) return -1 except error.UnknownCommand as inst: - ui.warn(_("hg: unknown command '%s'\n") % inst.args[0]) + nocmdmsg = _("hg: unknown command '%s'\n") % inst.args[0] try: # check if the command is in a disabled extension # (but don't check for extensions themselves) - commands.help_(ui, inst.args[0], unknowncmd=True) + formatted = help.formattedhelp(ui, inst.args[0], unknowncmd=True) + ui.warn(nocmdmsg) + ui.write(formatted) except (error.UnknownCommand, error.Abort): suggested = False if len(inst.args) == 2: sim = _getsimilar(inst.args[1], inst.args[0]) if sim: + ui.warn(nocmdmsg) _reportsimilar(ui.warn, sim) suggested = True if not suggested: + ui.pager('help') + ui.warn(nocmdmsg) commands.help_(ui, 'shortlist') except IOError: raise @@ -306,7 +358,7 @@ if num < len(givenargs): return givenargs[num] raise error.Abort(_('too few arguments for command alias')) - cmd = re.sub(r'\$(\d+|\$)', replacer, cmd) + cmd = re.sub(br'\$(\d+|\$)', replacer, cmd) givenargs = [x for i, x in enumerate(givenargs) if i not in nums] args = pycompat.shlexsplit(cmd) @@ -376,7 +428,8 @@ return '' cmd = re.sub(r'\$(\d+|\$)', _checkvar, self.definition[1:]) cmd = aliasinterpolate(self.name, args, cmd) - return ui.system(cmd, environ=env) + return ui.system(cmd, environ=env, + blockedtag='alias_%s' % self.name) self.fn = fn return @@ -418,7 +471,7 @@ @property def args(self): - args = map(util.expandpath, self.givenargs) + args = pycompat.maplist(util.expandpath, self.givenargs) return aliasargs(self.fn, args) def __getattr__(self, name): @@ -491,7 +544,8 @@ args = aliasargs(entry[0], args) defaults = ui.config("defaults", cmd) if defaults: - args = map(util.expandpath, pycompat.shlexsplit(defaults)) + args + args = pycompat.maplist( + util.expandpath, pycompat.shlexsplit(defaults)) + args c = list(entry[1]) else: cmd = None @@ -686,107 +740,122 @@ rpath = _earlygetopt(["-R", "--repository", "--repo"], args) path, lui = _getlocal(ui, rpath) - # Configure extensions in phases: uisetup, extsetup, cmdtable, and - # reposetup. Programs like TortoiseHg will call _dispatch several - # times so we keep track of configured extensions in _loaded. - extensions.loadall(lui) - exts = [ext for ext in extensions.extensions() if ext[0] not in _loaded] - # Propagate any changes to lui.__class__ by extensions - ui.__class__ = lui.__class__ - - # (uisetup and extsetup are handled in extensions.loadall) - - for name, module in exts: - for objname, loadermod, loadername in extraloaders: - extraobj = getattr(module, objname, None) - if extraobj is not None: - getattr(loadermod, loadername)(ui, name, extraobj) - _loaded.add(name) - - # (reposetup is handled in hg.repository) - # Side-effect of accessing is debugcommands module is guaranteed to be # imported and commands.table is populated. debugcommands.command - addaliases(lui, commands.table) - - # All aliases and commands are completely defined, now. - # Check abbreviation/ambiguity of shell alias. - shellaliasfn = _checkshellalias(lui, ui, args) - if shellaliasfn: - with profiling.maybeprofile(lui): - return shellaliasfn() - - # check for fallback encoding - fallback = lui.config('ui', 'fallbackencoding') - if fallback: - encoding.fallbackencoding = fallback - - fullargs = args - cmd, func, args, options, cmdoptions = _parse(lui, args) - - if options["config"]: - raise error.Abort(_("option --config may not be abbreviated!")) - if options["cwd"]: - raise error.Abort(_("option --cwd may not be abbreviated!")) - if options["repository"]: - raise error.Abort(_( - "option -R has to be separated from other options (e.g. not -qR) " - "and --repository may only be abbreviated as --repo!")) - - if options["encoding"]: - encoding.encoding = options["encoding"] - if options["encodingmode"]: - encoding.encodingmode = options["encodingmode"] - if options["time"]: - def get_times(): - t = os.times() - if t[4] == 0.0: # Windows leaves this as zero, so use time.clock() - t = (t[0], t[1], t[2], t[3], time.clock()) - return t - s = get_times() - def print_time(): - t = get_times() - ui.warn(_("time: real %.3f secs (user %.3f+%.3f sys %.3f+%.3f)\n") % - (t[4]-s[4], t[0]-s[0], t[2]-s[2], t[1]-s[1], t[3]-s[3])) - atexit.register(print_time) - uis = set([ui, lui]) if req.repo: uis.add(req.repo.ui) - if options['verbose'] or options['debug'] or options['quiet']: - for opt in ('verbose', 'debug', 'quiet'): - val = str(bool(options[opt])) - for ui_ in uis: - ui_.setconfig('ui', opt, val, '--' + opt) - - if options['profile']: + if '--profile' in args: for ui_ in uis: ui_.setconfig('profiling', 'enabled', 'true', '--profile') - if options['traceback']: - for ui_ in uis: - ui_.setconfig('ui', 'traceback', 'on', '--traceback') + with profiling.maybeprofile(lui): + # Configure extensions in phases: uisetup, extsetup, cmdtable, and + # reposetup. Programs like TortoiseHg will call _dispatch several + # times so we keep track of configured extensions in _loaded. + extensions.loadall(lui) + exts = [ext for ext in extensions.extensions() if ext[0] not in _loaded] + # Propagate any changes to lui.__class__ by extensions + ui.__class__ = lui.__class__ + + # (uisetup and extsetup are handled in extensions.loadall) + + for name, module in exts: + for objname, loadermod, loadername in extraloaders: + extraobj = getattr(module, objname, None) + if extraobj is not None: + getattr(loadermod, loadername)(ui, name, extraobj) + _loaded.add(name) + + # (reposetup is handled in hg.repository) + + addaliases(lui, commands.table) + + # All aliases and commands are completely defined, now. + # Check abbreviation/ambiguity of shell alias. + shellaliasfn = _checkshellalias(lui, ui, args) + if shellaliasfn: + return shellaliasfn() + + # check for fallback encoding + fallback = lui.config('ui', 'fallbackencoding') + if fallback: + encoding.fallbackencoding = fallback + + fullargs = args + cmd, func, args, options, cmdoptions = _parse(lui, args) + + if options["config"]: + raise error.Abort(_("option --config may not be abbreviated!")) + if options["cwd"]: + raise error.Abort(_("option --cwd may not be abbreviated!")) + if options["repository"]: + raise error.Abort(_( + "option -R has to be separated from other options (e.g. not " + "-qR) and --repository may only be abbreviated as --repo!")) - if options['noninteractive']: - for ui_ in uis: - ui_.setconfig('ui', 'interactive', 'off', '-y') + if options["encoding"]: + encoding.encoding = options["encoding"] + if options["encodingmode"]: + encoding.encodingmode = options["encodingmode"] + if options["time"]: + def get_times(): + t = os.times() + if t[4] == 0.0: + # Windows leaves this as zero, so use time.clock() + t = (t[0], t[1], t[2], t[3], time.clock()) + return t + s = get_times() + def print_time(): + t = get_times() + ui.warn( + _("time: real %.3f secs (user %.3f+%.3f sys %.3f+%.3f)\n") % + (t[4]-s[4], t[0]-s[0], t[2]-s[2], t[1]-s[1], t[3]-s[3])) + ui.atexit(print_time) - if cmdoptions.get('insecure', False): + if options['verbose'] or options['debug'] or options['quiet']: + for opt in ('verbose', 'debug', 'quiet'): + val = str(bool(options[opt])) + if pycompat.ispy3: + val = val.encode('ascii') + for ui_ in uis: + ui_.setconfig('ui', opt, val, '--' + opt) + + if options['traceback']: + for ui_ in uis: + ui_.setconfig('ui', 'traceback', 'on', '--traceback') + + if options['noninteractive']: + for ui_ in uis: + ui_.setconfig('ui', 'interactive', 'off', '-y') + + if util.parsebool(options['pager']): + ui.pager('internal-always-' + cmd) + elif options['pager'] != 'auto': + ui.disablepager() + + if cmdoptions.get('insecure', False): + for ui_ in uis: + ui_.insecureconnections = True + + # setup color handling + coloropt = options['color'] for ui_ in uis: - ui_.insecureconnections = True + if coloropt: + ui_.setconfig('ui', 'color', coloropt, '--color') + color.setup(ui_) - if options['version']: - return commands.version_(ui) - if options['help']: - return commands.help_(ui, cmd, command=cmd is not None) - elif not cmd: - return commands.help_(ui, 'shortlist') + if options['version']: + return commands.version_(ui) + if options['help']: + return commands.help_(ui, cmd, command=cmd is not None) + elif not cmd: + return commands.help_(ui, 'shortlist') - with profiling.maybeprofile(lui): repo = None cmdpats = args[:] if not func.norepo: @@ -833,7 +902,7 @@ elif rpath: ui.warn(_("warning: --repository ignored\n")) - msg = ' '.join(' ' in a and repr(a) or a for a in fullargs) + msg = _formatargs(fullargs) ui.log("command", '%s\n', msg) strcmdopt = pycompat.strkwargs(cmdoptions) d = lambda: util.checksignature(func)(ui, *args, **strcmdopt) @@ -866,6 +935,8 @@ if ui.config('ui', 'supportcontact', None) is None: for name, mod in extensions.extensions(): testedwith = getattr(mod, 'testedwith', '') + if pycompat.ispy3 and isinstance(testedwith, str): + testedwith = testedwith.encode(u'utf-8') report = getattr(mod, 'buglink', _('the extension author.')) if not testedwith.strip(): # We found an untested extension. It's likely the culprit. @@ -886,7 +957,7 @@ worst = name, nearest, report if worst[0] is not None: name, testedwith, report = worst - if not isinstance(testedwith, str): + if not isinstance(testedwith, (bytes, str)): testedwith = '.'.join([str(c) for c in testedwith]) warning = (_('** Unknown exception encountered with ' 'possibly-broken third-party extension %s\n' @@ -900,7 +971,12 @@ bugtracker = _("https://mercurial-scm.org/wiki/BugTracker") warning = (_("** unknown exception encountered, " "please report by visiting\n** ") + bugtracker + '\n') - warning += ((_("** Python %s\n") % sys.version.replace('\n', '')) + + if pycompat.ispy3: + sysversion = sys.version.encode(u'utf-8') + else: + sysversion = sys.version + sysversion = sysversion.replace('\n', '') + warning += ((_("** Python %s\n") % sysversion) + (_("** Mercurial Distributed SCM (version %s)\n") % util.version()) + (_("** Extensions loaded: %s\n") %
--- a/mercurial/encoding.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/encoding.py Tue Apr 18 12:24:34 2017 -0400 @@ -196,6 +196,24 @@ except LookupError as k: raise error.Abort(k, hint="please check your locale settings") +def unitolocal(u): + """Convert a unicode string to a byte string of local encoding""" + return tolocal(u.encode('utf-8')) + +def unifromlocal(s): + """Convert a byte string of local encoding to a unicode string""" + return fromlocal(s).decode('utf-8') + +# converter functions between native str and byte string. use these if the +# character encoding is not aware (e.g. exception message) or is known to +# be locale dependent (e.g. date formatting.) +if pycompat.ispy3: + strtolocal = unitolocal + strfromlocal = unifromlocal +else: + strtolocal = pycompat.identity + strfromlocal = pycompat.identity + if not _nativeenviron: # now encoding and helper functions are available, recreate the environ # dict to be exported to other modules
--- a/mercurial/error.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/error.py Tue Apr 18 12:24:34 2017 -0400 @@ -22,7 +22,7 @@ pass remaining arguments to the exception class. """ def __init__(self, *args, **kw): - self.hint = kw.pop('hint', None) + self.hint = kw.pop(r'hint', None) super(Hint, self).__init__(*args, **kw) class RevlogError(Hint, Exception): @@ -122,6 +122,12 @@ class RequirementError(RepoError): """Exception raised if .hg/requires has an unknown entry.""" +class StdioError(IOError): + """Raised if I/O to stdout or stderr fails""" + + def __init__(self, err): + IOError.__init__(self, err.errno, err.strerror) + class UnsupportedMergeRecords(Abort): def __init__(self, recordtypes): from .i18n import _ @@ -246,3 +252,6 @@ class CorruptedState(Exception): """error raised when a command is not able to read its state from file""" + +class PeerTransportError(Abort): + """Transport-level I/O error when communicating with a peer repo."""
--- a/mercurial/exchange.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/exchange.py Tue Apr 18 12:24:34 2017 -0400 @@ -1737,9 +1737,15 @@ if url.startswith('remote:http:') or url.startswith('remote:https:'): captureoutput = True try: + # note: outside bundle1, 'heads' is expected to be empty and this + # 'check_heads' call wil be a no-op check_heads(repo, heads, 'uploading changes') # push can proceed - if util.safehasattr(cg, 'params'): + if not util.safehasattr(cg, 'params'): + # legacy case: bundle1 (changegroup 01) + lockandtr[1] = repo.lock() + r = cg.apply(repo, source, url) + else: r = None try: def gettransaction(): @@ -1778,9 +1784,6 @@ mandatory=False) parts.append(part) raise - else: - lockandtr[1] = repo.lock() - r = cg.apply(repo, source, url) finally: lockmod.release(lockandtr[2], lockandtr[1], lockandtr[0]) if recordout is not None:
--- a/mercurial/exewrapper.c Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/exewrapper.c Tue Apr 18 12:24:34 2017 -0400 @@ -67,51 +67,35 @@ } pydll = NULL; - /* - We first check, that environment variable PYTHONHOME is *not* set. - This just mimicks the behavior of the regular python.exe, which uses - PYTHONHOME to find its installation directory (if it has been set). - Note: Users of HackableMercurial are expected to *not* set PYTHONHOME! - */ - if (GetEnvironmentVariable("PYTHONHOME", envpyhome, - sizeof(envpyhome)) == 0) - { - /* - Environment var PYTHONHOME is *not* set. Let's see if we are - running inside a HackableMercurial. - */ + + p = strrchr(pyhome, '\\'); + if (p == NULL) { + err = "can't find backslash in module filename"; + goto bail; + } + *p = 0; /* cut at directory */ + + /* check for private Python of HackableMercurial */ + strcat_s(pyhome, sizeof(pyhome), "\\hg-python"); - p = strrchr(pyhome, '\\'); - if (p == NULL) { - err = "can't find backslash in module filename"; + hfind = FindFirstFile(pyhome, &fdata); + if (hfind != INVALID_HANDLE_VALUE) { + /* Path .\hg-python exists. We are probably in HackableMercurial + scenario, so let's load python dll from this dir. */ + FindClose(hfind); + strcpy_s(pydllfile, sizeof(pydllfile), pyhome); + strcat_s(pydllfile, sizeof(pydllfile), "\\" HGPYTHONLIB ".dll"); + pydll = LoadLibrary(pydllfile); + if (pydll == NULL) { + err = "failed to load private Python DLL " HGPYTHONLIB ".dll"; goto bail; } - *p = 0; /* cut at directory */ - - /* check for private Python of HackableMercurial */ - strcat_s(pyhome, sizeof(pyhome), "\\hg-python"); - - hfind = FindFirstFile(pyhome, &fdata); - if (hfind != INVALID_HANDLE_VALUE) { - /* path pyhome exists, let's use it */ - FindClose(hfind); - strcpy_s(pydllfile, sizeof(pydllfile), pyhome); - strcat_s(pydllfile, sizeof(pydllfile), - "\\" HGPYTHONLIB ".dll"); - pydll = LoadLibrary(pydllfile); - if (pydll == NULL) { - err = "failed to load private Python DLL " - HGPYTHONLIB ".dll"; - goto bail; - } - Py_SetPythonHome = (void*)GetProcAddress(pydll, - "Py_SetPythonHome"); - if (Py_SetPythonHome == NULL) { - err = "failed to get Py_SetPythonHome"; - goto bail; - } - Py_SetPythonHome(pyhome); + Py_SetPythonHome = (void*)GetProcAddress(pydll, "Py_SetPythonHome"); + if (Py_SetPythonHome == NULL) { + err = "failed to get Py_SetPythonHome"; + goto bail; } + Py_SetPythonHome(pyhome); } if (pydll == NULL) {
--- a/mercurial/extensions.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/extensions.py Tue Apr 18 12:24:34 2017 -0400 @@ -8,6 +8,7 @@ from __future__ import absolute_import import imp +import inspect import os from .i18n import ( @@ -17,6 +18,7 @@ from . import ( cmdutil, + encoding, error, pycompat, util, @@ -103,11 +105,16 @@ mod = _importh(name) return mod +def _forbytes(inst): + """Portably format an import error into a form suitable for + %-formatting into bytestrings.""" + return encoding.strtolocal(str(inst)) + def _reportimporterror(ui, err, failed, next): # note: this ui.debug happens before --debug is processed, # Use --config ui.debug=1 to see them. ui.debug('could not import %s (%s): trying %s\n' - % (failed, err, next)) + % (failed, _forbytes(err), next)) if ui.debugflag: ui.traceback() @@ -150,7 +157,7 @@ try: extsetup(ui) except TypeError: - if extsetup.func_code.co_argcount != 0: + if inspect.getargspec(extsetup).args: raise extsetup() # old extsetup with no ui argument @@ -159,7 +166,7 @@ newindex = len(_order) for (name, path) in result: if path: - if path[0] == '!': + if path[0:1] == '!': _disabledextensions[name] = path[1:] continue try: @@ -167,6 +174,7 @@ except KeyboardInterrupt: raise except Exception as inst: + inst = _forbytes(inst) if path: ui.warn(_("*** failed to import extension %s from %s: %s\n") % (name, path, inst)) @@ -362,7 +370,8 @@ '''find paths of disabled extensions. returns a dict of {name: path} removes /__init__.py from packages if strip_init is True''' import hgext - extpath = os.path.dirname(os.path.abspath(hgext.__file__)) + extpath = os.path.dirname( + os.path.abspath(pycompat.fsencode(hgext.__file__))) try: # might not be a filesystem path files = os.listdir(extpath) except OSError:
--- a/mercurial/filemerge.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/filemerge.py Tue Apr 18 12:24:34 2017 -0400 @@ -35,7 +35,9 @@ def _toolbool(ui, tool, part, default=False): return ui.configbool("merge-tools", tool + "." + part, default) -def _toollist(ui, tool, part, default=[]): +def _toollist(ui, tool, part, default=None): + if default is None: + default = [] return ui.configlist("merge-tools", tool + "." + part, default) internals = {} @@ -489,8 +491,11 @@ args = util.interpolate(r'\$', replace, args, lambda s: util.shellquote(util.localpath(s))) cmd = toolpath + ' ' + args + if _toolbool(ui, tool, "gui"): + repo.ui.status(_('running merge tool %s for file %s\n') % + (tool, fcd.path())) repo.ui.debug('launching merge tool: %s\n' % cmd) - r = ui.system(cmd, cwd=repo.root, environ=env) + r = ui.system(cmd, cwd=repo.root, environ=env, blockedtag='mergetool') repo.ui.debug('merge tool returned: %s\n' % r) return True, r, False @@ -538,6 +543,7 @@ ui = repo.ui template = ui.config('ui', 'mergemarkertemplate', _defaultconflictmarker) + template = templater.unquotestring(template) tmpl = formatter.maketemplater(ui, 'conflictmarker', template) pad = max(len(l) for l in labels) @@ -582,7 +588,7 @@ pre = "%s~%s." % (os.path.basename(fullbase), prefix) (fd, name) = tempfile.mkstemp(prefix=pre, suffix=ext) data = repo.wwritedata(ctx.path(), ctx.data()) - f = os.fdopen(fd, "wb") + f = os.fdopen(fd, pycompat.sysstr("wb")) f.write(data) f.close() return name
--- a/mercurial/fileset.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/fileset.py Tue Apr 18 12:24:34 2017 -0400 @@ -15,6 +15,7 @@ merge, parser, registrar, + scmutil, util, ) @@ -153,7 +154,7 @@ """ # i18n: "modified" is a keyword getargs(x, 0, 0, _("modified takes no arguments")) - s = mctx.status().modified + s = set(mctx.status().modified) return [f for f in mctx.subset if f in s] @predicate('added()', callstatus=True) @@ -162,7 +163,7 @@ """ # i18n: "added" is a keyword getargs(x, 0, 0, _("added takes no arguments")) - s = mctx.status().added + s = set(mctx.status().added) return [f for f in mctx.subset if f in s] @predicate('removed()', callstatus=True) @@ -171,7 +172,7 @@ """ # i18n: "removed" is a keyword getargs(x, 0, 0, _("removed takes no arguments")) - s = mctx.status().removed + s = set(mctx.status().removed) return [f for f in mctx.subset if f in s] @predicate('deleted()', callstatus=True) @@ -180,7 +181,7 @@ """ # i18n: "deleted" is a keyword getargs(x, 0, 0, _("deleted takes no arguments")) - s = mctx.status().deleted + s = set(mctx.status().deleted) return [f for f in mctx.subset if f in s] @predicate('missing()', callstatus=True) @@ -189,7 +190,7 @@ """ # i18n: "missing" is a keyword getargs(x, 0, 0, _("missing takes no arguments")) - s = mctx.status().deleted + s = set(mctx.status().deleted) return [f for f in mctx.subset if f in s] @predicate('unknown()', callstatus=True) @@ -199,7 +200,7 @@ """ # i18n: "unknown" is a keyword getargs(x, 0, 0, _("unknown takes no arguments")) - s = mctx.status().unknown + s = set(mctx.status().unknown) return [f for f in mctx.subset if f in s] @predicate('ignored()', callstatus=True) @@ -209,7 +210,7 @@ """ # i18n: "ignored" is a keyword getargs(x, 0, 0, _("ignored takes no arguments")) - s = mctx.status().ignored + s = set(mctx.status().ignored) return [f for f in mctx.subset if f in s] @predicate('clean()', callstatus=True) @@ -218,7 +219,7 @@ """ # i18n: "clean" is a keyword getargs(x, 0, 0, _("clean takes no arguments")) - s = mctx.status().clean + s = set(mctx.status().clean) return [f for f in mctx.subset if f in s] def func(mctx, a, b): @@ -438,6 +439,52 @@ s.append(f) return s +@predicate('revs(revs, pattern)') +def revs(mctx, x): + """Evaluate set in the specified revisions. If the revset match multiple + revs, this will return file matching pattern in any of the revision. + """ + # i18n: "revs" is a keyword + r, x = getargs(x, 2, 2, _("revs takes two arguments")) + # i18n: "revs" is a keyword + revspec = getstring(r, _("first argument to revs must be a revision")) + repo = mctx.ctx.repo() + revs = scmutil.revrange(repo, [revspec]) + + found = set() + result = [] + for r in revs: + ctx = repo[r] + for f in getset(mctx.switch(ctx, _buildstatus(ctx, x)), x): + if f not in found: + found.add(f) + result.append(f) + return result + +@predicate('status(base, rev, pattern)') +def status(mctx, x): + """Evaluate predicate using status change between ``base`` and + ``rev``. Examples: + + - ``status(3, 7, added())`` - matches files added from "3" to "7" + """ + repo = mctx.ctx.repo() + # i18n: "status" is a keyword + b, r, x = getargs(x, 3, 3, _("status takes three arguments")) + # i18n: "status" is a keyword + baseerr = _("first argument to status must be a revision") + baserevspec = getstring(b, baseerr) + if not baserevspec: + raise error.ParseError(baseerr) + reverr = _("second argument to status must be a revision") + revspec = getstring(r, reverr) + if not revspec: + raise error.ParseError(reverr) + basenode, node = scmutil.revpair(repo, [baserevspec, revspec]) + basectx = repo[basenode] + ctx = repo[node] + return getset(mctx.switch(ctx, _buildstatus(ctx, x, basectx=basectx)), x) + @predicate('subrepo([pattern])') def subrepo(mctx, x): """Subrepositories whose paths match the given pattern. @@ -474,7 +521,7 @@ } class matchctx(object): - def __init__(self, ctx, subset=None, status=None): + def __init__(self, ctx, subset, status=None): self.ctx = ctx self.subset = subset self._status = status @@ -497,39 +544,71 @@ if (f in self.ctx and f not in removed) or f in unknown) def narrow(self, files): return matchctx(self.ctx, self.filter(files), self._status) + def switch(self, ctx, status=None): + subset = self.filter(_buildsubset(ctx, status)) + return matchctx(ctx, subset, status) + +class fullmatchctx(matchctx): + """A match context where any files in any revisions should be valid""" + + def __init__(self, ctx, status=None): + subset = _buildsubset(ctx, status) + super(fullmatchctx, self).__init__(ctx, subset, status) + def switch(self, ctx, status=None): + return fullmatchctx(ctx, status) + +# filesets using matchctx.switch() +_switchcallers = [ + 'revs', + 'status', +] def _intree(funcs, tree): if isinstance(tree, tuple): if tree[0] == 'func' and tree[1][0] == 'symbol': if tree[1][1] in funcs: return True + if tree[1][1] in _switchcallers: + # arguments won't be evaluated in the current context + return False for s in tree[1:]: if _intree(funcs, s): return True return False +def _buildsubset(ctx, status): + if status: + subset = [] + for c in status: + subset.extend(c) + return subset + else: + return list(ctx.walk(ctx.match([]))) + def getfileset(ctx, expr): tree = parse(expr) + return getset(fullmatchctx(ctx, _buildstatus(ctx, tree)), tree) +def _buildstatus(ctx, tree, basectx=None): # do we need status info? + + # temporaty boolean to simplify the next conditional + purewdir = ctx.rev() is None and basectx is None + if (_intree(_statuscallers, tree) or # Using matchctx.existing() on a workingctx requires us to check # for deleted files. - (ctx.rev() is None and _intree(_existingcallers, tree))): + (purewdir and _intree(_existingcallers, tree))): unknown = _intree(['unknown'], tree) ignored = _intree(['ignored'], tree) r = ctx.repo() - status = r.status(ctx.p1(), ctx, - unknown=unknown, ignored=ignored, clean=True) - subset = [] - for c in status: - subset.extend(c) + if basectx is None: + basectx = ctx.p1() + return r.status(basectx, ctx, + unknown=unknown, ignored=ignored, clean=True) else: - status = None - subset = list(ctx.walk(ctx.match([]))) - - return getset(matchctx(ctx, subset, status), tree) + return None def prettyformat(tree): return parser.prettyformat(tree, ('string', 'symbol'))
--- a/mercurial/formatter.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/formatter.py Tue Apr 18 12:24:34 2017 -0400 @@ -12,6 +12,7 @@ - fm.write() for unconditional output - fm.condwrite() to show some extra data conditionally in plain output +- fm.context() to provide changectx to template output - fm.data() to provide extra data to JSON or template output - fm.plain() to show raw text that isn't provided to JSON or template output @@ -102,6 +103,7 @@ from __future__ import absolute_import +import itertools import os from .i18n import _ @@ -111,8 +113,8 @@ ) from . import ( - encoding, error, + templatefilters, templatekw, templater, util, @@ -171,6 +173,9 @@ # name is mandatory argument for now, but it could be optional if # we have default template keyword, e.g. {item} return self._converter.formatlist(data, name, fmt, sep) + def context(self, **ctxs): + '''insert context objects to be used to render template keywords''' + pass def data(self, **data): '''insert data into item that's not shown in default output''' self._item.update(data) @@ -257,66 +262,52 @@ pass class debugformatter(baseformatter): - def __init__(self, ui, topic, opts): + def __init__(self, ui, out, topic, opts): baseformatter.__init__(self, ui, topic, opts, _nullconverter) - self._ui.write("%s = [\n" % self._topic) + self._out = out + self._out.write("%s = [\n" % self._topic) def _showitem(self): - self._ui.write(" " + repr(self._item) + ",\n") + self._out.write(" " + repr(self._item) + ",\n") def end(self): baseformatter.end(self) - self._ui.write("]\n") + self._out.write("]\n") class pickleformatter(baseformatter): - def __init__(self, ui, topic, opts): + def __init__(self, ui, out, topic, opts): baseformatter.__init__(self, ui, topic, opts, _nullconverter) + self._out = out self._data = [] def _showitem(self): self._data.append(self._item) def end(self): baseformatter.end(self) - self._ui.write(pickle.dumps(self._data)) - -def _jsonifyobj(v): - if isinstance(v, dict): - xs = ['"%s": %s' % (encoding.jsonescape(k), _jsonifyobj(u)) - for k, u in sorted(v.iteritems())] - return '{' + ', '.join(xs) + '}' - elif isinstance(v, (list, tuple)): - return '[' + ', '.join(_jsonifyobj(e) for e in v) + ']' - elif v is None: - return 'null' - elif v is True: - return 'true' - elif v is False: - return 'false' - elif isinstance(v, (int, float)): - return str(v) - else: - return '"%s"' % encoding.jsonescape(v) + self._out.write(pickle.dumps(self._data)) class jsonformatter(baseformatter): - def __init__(self, ui, topic, opts): + def __init__(self, ui, out, topic, opts): baseformatter.__init__(self, ui, topic, opts, _nullconverter) - self._ui.write("[") - self._ui._first = True + self._out = out + self._out.write("[") + self._first = True def _showitem(self): - if self._ui._first: - self._ui._first = False + if self._first: + self._first = False else: - self._ui.write(",") + self._out.write(",") - self._ui.write("\n {\n") + self._out.write("\n {\n") first = True for k, v in sorted(self._item.items()): if first: first = False else: - self._ui.write(",\n") - self._ui.write(' "%s": %s' % (k, _jsonifyobj(v))) - self._ui.write("\n }") + self._out.write(",\n") + u = templatefilters.json(v, paranoid=False) + self._out.write(' "%s": %s' % (k, u)) + self._out.write("\n }") def end(self): baseformatter.end(self) - self._ui.write("\n]\n") + self._out.write("\n]\n") class _templateconverter(object): '''convert non-primitive data types to be processed by templater''' @@ -330,25 +321,46 @@ data = util.sortdict(_iteritems(data)) def f(): yield _plainconverter.formatdict(data, key, value, fmt, sep) - return templatekw._hybrid(f(), data, lambda k: {key: k, value: data[k]}, - lambda d: fmt % (d[key], d[value])) + return templatekw.hybriddict(data, key=key, value=value, fmt=fmt, + gen=f()) @staticmethod def formatlist(data, name, fmt, sep): '''build object that can be evaluated as either plain string or list''' data = list(data) def f(): yield _plainconverter.formatlist(data, name, fmt, sep) - return templatekw._hybrid(f(), data, lambda x: {name: x}, - lambda d: fmt % d[name]) + return templatekw.hybridlist(data, name=name, fmt=fmt, gen=f()) class templateformatter(baseformatter): - def __init__(self, ui, topic, opts): + def __init__(self, ui, out, topic, opts): baseformatter.__init__(self, ui, topic, opts, _templateconverter) + self._out = out self._topic = topic - self._t = gettemplater(ui, topic, opts.get('template', '')) + self._t = gettemplater(ui, topic, opts.get('template', ''), + cache=templatekw.defaulttempl) + self._counter = itertools.count() + self._cache = {} # for templatekw/funcs to store reusable data + def context(self, **ctxs): + '''insert context objects to be used to render template keywords''' + assert all(k == 'ctx' for k in ctxs) + self._item.update(ctxs) def _showitem(self): - g = self._t(self._topic, ui=self._ui, **self._item) - self._ui.write(templater.stringify(g)) + # TODO: add support for filectx. probably each template keyword or + # function will have to declare dependent resources. e.g. + # @templatekeyword(..., requires=('ctx',)) + props = {} + if 'ctx' in self._item: + props.update(templatekw.keywords) + props['index'] = next(self._counter) + # explicitly-defined fields precede templatekw + props.update(self._item) + if 'ctx' in self._item: + # but template resources must be always available + props['templ'] = self._t + props['repo'] = props['ctx'].repo() + props['revcache'] = {} + g = self._t(self._topic, ui=self._ui, cache=self._cache, **props) + self._out.write(templater.stringify(g)) def lookuptemplate(ui, topic, tmpl): # looks like a literal template? @@ -382,17 +394,17 @@ # constant string? return tmpl, None -def gettemplater(ui, topic, spec): +def gettemplater(ui, topic, spec, cache=None): tmpl, mapfile = lookuptemplate(ui, topic, spec) assert not (tmpl and mapfile) if mapfile: - return templater.templater.frommapfile(mapfile) - return maketemplater(ui, topic, tmpl) + return templater.templater.frommapfile(mapfile, cache=cache) + return maketemplater(ui, topic, tmpl, cache=cache) -def maketemplater(ui, topic, tmpl, filters=None, cache=None): +def maketemplater(ui, topic, tmpl, cache=None): """Create a templater from a string template 'tmpl'""" aliases = ui.configitems('templatealias') - t = templater.templater(filters=filters, cache=cache, aliases=aliases) + t = templater.templater(cache=cache, aliases=aliases) if tmpl: t.cache[topic] = tmpl return t @@ -400,17 +412,17 @@ def formatter(ui, topic, opts): template = opts.get("template", "") if template == "json": - return jsonformatter(ui, topic, opts) + return jsonformatter(ui, ui, topic, opts) elif template == "pickle": - return pickleformatter(ui, topic, opts) + return pickleformatter(ui, ui, topic, opts) elif template == "debug": - return debugformatter(ui, topic, opts) + return debugformatter(ui, ui, topic, opts) elif template != "": - return templateformatter(ui, topic, opts) + return templateformatter(ui, ui, topic, opts) # developer config: ui.formatdebug elif ui.configbool('ui', 'formatdebug'): - return debugformatter(ui, topic, opts) + return debugformatter(ui, ui, topic, opts) # deprecated config: ui.formatjson elif ui.configbool('ui', 'formatjson'): - return jsonformatter(ui, topic, opts) + return jsonformatter(ui, ui, topic, opts) return plainformatter(ui, topic, opts)
--- a/mercurial/graphmod.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/graphmod.py Tue Apr 18 12:24:34 2017 -0400 @@ -22,6 +22,7 @@ from .node import nullrev from . import ( revset, + smartset, util, ) @@ -67,8 +68,8 @@ if gp is None: # precompute slow query as we know reachableroots() goes # through all revs (issue4782) - if not isinstance(revs, revset.baseset): - revs = revset.baseset(revs) + if not isinstance(revs, smartset.baseset): + revs = smartset.baseset(revs) gp = gpcache[mpar] = sorted(set(revset.reachableroots( repo, revs, [mpar]))) if not gp: @@ -181,6 +182,9 @@ knownparents = [] newparents = [] for ptype, parent in parents: + if parent == rev: + # self reference (should only be seen in null rev) + continue if parent in seen: knownparents.append(parent) else: @@ -190,8 +194,7 @@ ncols = len(seen) nextseen = seen[:] nextseen[nodeidx:nodeidx + 1] = newparents - edges = [(nodeidx, nextseen.index(p)) - for p in knownparents if p != nullrev] + edges = [(nodeidx, nextseen.index(p)) for p in knownparents] seen[:] = nextseen while len(newparents) > 2:
--- a/mercurial/help.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/help.py Tue Apr 18 12:24:34 2017 -0400 @@ -33,14 +33,17 @@ webcommands, ) -_exclkeywords = [ +_exclkeywords = set([ + "(ADVANCED)", "(DEPRECATED)", "(EXPERIMENTAL)", + # i18n: "(ADVANCED)" is a keyword, must be translated consistently + _("(ADVANCED)"), # i18n: "(DEPRECATED)" is a keyword, must be translated consistently _("(DEPRECATED)"), # i18n: "(EXPERIMENTAL)" is a keyword, must be translated consistently _("(EXPERIMENTAL)"), - ] + ]) def listexts(header, exts, indent=1, showdeprecated=False): '''return a text listing of the given extensions''' @@ -186,6 +189,8 @@ internalstable = sorted([ (['bundles'], _('Bundles'), loaddoc('bundles', subdir='internals')), + (['censor'], _('Censor'), + loaddoc('censor', subdir='internals')), (['changegroups'], _('Changegroups'), loaddoc('changegroups', subdir='internals')), (['requirements'], _('Repository Requirements'), @@ -205,6 +210,8 @@ return ''.join(lines) helptable = sorted([ + (['bundlespec'], _("Bundle File Formats"), loaddoc('bundlespec')), + (['color'], _("Colorizing Outputs"), loaddoc('color')), (["config", "hgrc"], _("Configuration Files"), loaddoc('config')), (["dates"], _("Date Formats"), loaddoc('dates')), (["patterns"], _("File Name Patterns"), loaddoc('patterns')), @@ -230,6 +237,7 @@ loaddoc('scripting')), (['internals'], _("Technical implementation topics"), internalshelp), + (['pager'], _("Pager Support"), loaddoc('pager')), ]) # Maps topics with sub-topics to a list of their sub-topics. @@ -276,6 +284,8 @@ return makeitemsdoc(ui, topic, doc, marker, symbols, dedent=dedent) addtopichook(topic, add) +addtopicsymbols('bundlespec', '.. bundlecompressionmarker', + util.bundlecompressiontopics()) addtopicsymbols('filesets', '.. predicatesmarker', fileset.symbols) addtopicsymbols('merge-tools', '.. internaltoolsmarker', filemerge.internalsdoc) @@ -605,3 +615,49 @@ rst.extend(helplist(None, **opts)) return ''.join(rst) + +def formattedhelp(ui, name, keep=None, unknowncmd=False, full=True, **opts): + """get help for a given topic (as a dotted name) as rendered rst + + Either returns the rendered help text or raises an exception. + """ + if keep is None: + keep = [] + else: + keep = list(keep) # make a copy so we can mutate this later + fullname = name + section = None + subtopic = None + if name and '.' in name: + name, remaining = name.split('.', 1) + remaining = encoding.lower(remaining) + if '.' in remaining: + subtopic, section = remaining.split('.', 1) + else: + if name in subtopics: + subtopic = remaining + else: + section = remaining + textwidth = ui.configint('ui', 'textwidth', 78) + termwidth = ui.termwidth() - 2 + if textwidth <= 0 or termwidth < textwidth: + textwidth = termwidth + text = help_(ui, name, + subtopic=subtopic, unknowncmd=unknowncmd, full=full, **opts) + + formatted, pruned = minirst.format(text, textwidth, keep=keep, + section=section) + + # We could have been given a weird ".foo" section without a name + # to look for, or we could have simply failed to found "foo.bar" + # because bar isn't a section of foo + if section and not (formatted and name): + raise error.Abort(_("help section not found: %s") % fullname) + + if 'verbose' in pruned: + keep.append('omitted') + else: + keep.append('notomitted') + formatted, pruned = minirst.format(text, textwidth, keep=keep, + section=section) + return formatted
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/mercurial/help/bundlespec.txt Tue Apr 18 12:24:34 2017 -0400 @@ -0,0 +1,84 @@ +Mercurial supports generating standalone "bundle" files that hold repository +data. These "bundles" are typically saved locally and used later or exchanged +between different repositories, possibly on different machines. Example +commands using bundles are :hg:`bundle` and :hg:`unbundle`. + +Generation of bundle files is controlled by a "bundle specification" +("bundlespec") string. This string tells the bundle generation process how +to create the bundle. + +A "bundlespec" string is composed of the following elements: + +type + A string denoting the bundle format to use. + +compression + Denotes the compression engine to use compressing the raw bundle data. + +parameters + Arbitrary key-value parameters to further control bundle generation. + +A "bundlespec" string has the following formats: + +<type> + The literal bundle format string is used. + +<compression>-<type> + The compression engine and format are delimited by a hypthen (``-``). + +Optional parameters follow the ``<type>``. Parameters are URI escaped +``key=value`` pairs. Each pair is delimited by a semicolon (``;``). The +first parameter begins after a ``;`` immediately following the ``<type>`` +value. + +Available Types +=============== + +The following bundle <type> strings are available: + +v1 + Produces a legacy "changegroup" version 1 bundle. + + This format is compatible with nearly all Mercurial clients because it is + the oldest. However, it has some limitations, which is why it is no longer + the default for new repositories. + + ``v1`` bundles can be used with modern repositories using the "generaldelta" + storage format. However, it may take longer to produce the bundle and the + resulting bundle may be significantly larger than a ``v2`` bundle. + + ``v1`` bundles can only use the ``gzip``, ``bzip2``, and ``none`` compression + formats. + +v2 + Produces a version 2 bundle. + + Version 2 bundles are an extensible format that can store additional + repository data (such as bookmarks and phases information) and they can + store data more efficiently, resulting in smaller bundles. + + Version 2 bundles can also use modern compression engines, such as + ``zstd``, making them faster to compress and often smaller. + +Available Compression Engines +============================= + +The following bundle <compression> engines can be used: + +.. bundlecompressionmarker + +Examples +======== + +``v2`` + Produce a ``v2`` bundle using default options, including compression. + +``none-v1`` + Produce a ``v2`` bundle with no compression. + +``zstd-v2`` + Produce a ``v2`` bundle with zstandard compression using default + settings. + +``zstd-v1`` + This errors because ``zstd`` is not supported for ``v1`` types.
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/mercurial/help/color.txt Tue Apr 18 12:24:34 2017 -0400 @@ -0,0 +1,134 @@ +Mercurial can colorizes output from several commands. + +For example, the diff command shows additions in green and deletions +in red, while the status command shows modified files in magenta. Many +other commands have analogous colors. It is possible to customize +these colors. + +To enable color use:: + + [ui] + color = auto + +Mode +==== + +Mercurial can use various system to display color. The supported modes are +``ansi``, ``win32``, and ``terminfo``. See :hg:`help config.color` for details +about how to control the mode + +Effects +======= + +Other effects in addition to color, like bold and underlined text, are +also available. By default, the terminfo database is used to find the +terminal codes used to change color and effect. If terminfo is not +available, then effects are rendered with the ECMA-48 SGR control +function (aka ANSI escape codes). + +The available effects in terminfo mode are 'blink', 'bold', 'dim', +'inverse', 'invisible', 'italic', 'standout', and 'underline'; in +ECMA-48 mode, the options are 'bold', 'inverse', 'italic', and +'underline'. How each is rendered depends on the terminal emulator. +Some may not be available for a given terminal type, and will be +silently ignored. + +If the terminfo entry for your terminal is missing codes for an effect +or has the wrong codes, you can add or override those codes in your +configuration:: + + [color] + terminfo.dim = \E[2m + +where '\E' is substituted with an escape character. + +Labels +====== + +Text receives color effects depending on the labels that it has. Many +default Mercurial commands emit labelled text. You can also define +your own labels in templates using the label function, see :hg:`help +templates`. A single portion of text may have more than one label. In +that case, effects given to the last label will override any other +effects. This includes the special "none" effect, which nullifies +other effects. + +Labels are normally invisible. In order to see these labels and their +position in the text, use the global --color=debug option. The same +anchor text may be associated to multiple labels, e.g. + + [log.changeset changeset.secret|changeset: 22611:6f0a53c8f587] + +The following are the default effects for some default labels. Default +effects may be overridden from your configuration file:: + + [color] + status.modified = blue bold underline red_background + status.added = green bold + status.removed = red bold blue_background + status.deleted = cyan bold underline + status.unknown = magenta bold underline + status.ignored = black bold + + # 'none' turns off all effects + status.clean = none + status.copied = none + + qseries.applied = blue bold underline + qseries.unapplied = black bold + qseries.missing = red bold + + diff.diffline = bold + diff.extended = cyan bold + diff.file_a = red bold + diff.file_b = green bold + diff.hunk = magenta + diff.deleted = red + diff.inserted = green + diff.changed = white + diff.tab = + diff.trailingwhitespace = bold red_background + + # Blank so it inherits the style of the surrounding label + changeset.public = + changeset.draft = + changeset.secret = + + resolve.unresolved = red bold + resolve.resolved = green bold + + bookmarks.active = green + + branches.active = none + branches.closed = black bold + branches.current = green + branches.inactive = none + + tags.normal = green + tags.local = black bold + + rebase.rebased = blue + rebase.remaining = red bold + + shelve.age = cyan + shelve.newest = green bold + shelve.name = blue bold + + histedit.remaining = red bold + +Custom colors +============= + +Because there are only eight standard colors, this module allows you +to define color names for other color slots which might be available +for your terminal type, assuming terminfo mode. For instance:: + + color.brightblue = 12 + color.pink = 207 + color.orange = 202 + +to set 'brightblue' to color slot 12 (useful for 16 color terminals +that have brighter colors defined in the upper eight) and, 'pink' and +'orange' to colors in 256-color xterm's default color cube. These +defined colors may then be used as any of the pre-defined eight, +including appending '_background' to set the background to that color.
--- a/mercurial/help/config.txt Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/help/config.txt Tue Apr 18 12:24:34 2017 -0400 @@ -56,6 +56,7 @@ - ``<repo>/.hg/hgrc`` (per-repository) - ``$HOME/.hgrc`` (per-user) + - ``${XDG_CONFIG_HOME:-$HOME/.config}/hg/hgrc`` (per-user) - ``<install-root>/etc/mercurial/hgrc`` (per-installation) - ``<install-root>/etc/mercurial/hgrc.d/*.rc`` (per-installation) - ``/etc/mercurial/hgrc`` (per-system) @@ -276,7 +277,7 @@ will let you do ``hg echo foo`` to have ``foo`` printed in your terminal. A better example might be:: - purge = !$HG status --no-status --unknown -0 re: | xargs -0 rm + purge = !$HG status --no-status --unknown -0 re: | xargs -0 rm -f which will make ``hg purge`` delete all unknown files in the repository in the same manner as the purge extension. @@ -322,12 +323,32 @@ ``auth`` -------- -Authentication credentials for HTTP authentication. This section -allows you to store usernames and passwords for use when logging -*into* HTTP servers. See :hg:`help config.web` if -you want to configure *who* can login to your HTTP server. - -Each line has the following format:: +Authentication credentials and other authentication-like configuration +for HTTP connections. This section allows you to store usernames and +passwords for use when logging *into* HTTP servers. See +:hg:`help config.web` if you want to configure *who* can login to +your HTTP server. + +The following options apply to all hosts. + +``cookiefile`` + Path to a file containing HTTP cookie lines. Cookies matching a + host will be sent automatically. + + The file format uses the Mozilla cookies.txt format, which defines cookies + on their own lines. Each line contains 7 fields delimited by the tab + character (domain, is_domain_cookie, path, is_secure, expires, name, + value). For more info, do an Internet search for "Netscape cookies.txt + format." + + Note: the cookies parser does not handle port numbers on domains. You + will need to remove ports from the domain for the cookie to be recognized. + This could result in a cookie being disclosed to an unwanted server. + + The cookies file is read-only. + +Other options in this section are grouped by name and have the following +format:: <name>.<argument> = <value> @@ -385,6 +406,46 @@ If no suitable authentication entry is found, the user is prompted for credentials as usual if required by the remote. +``color`` +--------- + +Configure the Mercurial color mode. For details about how to define your custom +effect and style see :hg:`help color`. + +``mode`` + String: control the method used to output color. One of ``auto``, ``ansi``, + ``win32``, ``terminfo`` or ``debug``. In auto mode the color extension will + use ANSI mode by default (or win32 mode on Windows) if it detects a + terminal. Any invalid value will disable color. + +``pagermode`` + String: optinal override of ``color.mode`` used with pager (from the pager + extensions). + + On some systems, terminfo mode may cause problems when using + color with the pager extension and less -R. less with the -R option + will only display ECMA-48 color codes, and terminfo mode may sometimes + emit codes that less doesn't understand. You can work around this by + either using ansi mode (or auto mode), or by using less -r (which will + pass through all terminal control codes, not just color control + codes). + + On some systems (such as MSYS in Windows), the terminal may support + a different color mode than the pager (activated via the "pager" + extension). + +``commands`` +------------ + +``status.relative`` + Make paths in ``hg status`` output relative to the current directory. + (default: False) + +``update.requiredest`` + Require that the user pass a destination when running ``hg update``. + For example, ``hg update .::`` will be allowed, but a plain ``hg update`` + will be disallowed. + (default: False) ``committemplate`` ------------------ @@ -700,8 +761,8 @@ Example for ``~/.hgrc``:: [extensions] - # (the color extension will get loaded from Mercurial's path) - color = + # (the churn extension will get loaded from Mercurial's path) + churn = # (this extension will get loaded from the file specified) myfeature = ~/.hgext/myfeature.py @@ -801,8 +862,12 @@ priority.incoming.autobuild = 1 Most hooks are run with environment variables set that give useful -additional information. For each hook below, the environment -variables it is passed are listed with names of the form ``$HG_foo``. +additional information. For each hook below, the environment variables +it is passed are listed with names of the form ``$HG_foo``. The +``$HG_HOOKTYPE`` and ``$HG_HOOKNAME`` variables are set for all hooks. +their respectively contains the type of hook which triggered the run and +the full name of the hooks in the config. In the example about this will +be ``$HG_HOOKTYPE=incoming`` and ``$HG_HOOKNAME=incoming.email``. ``changegroup`` Run after a changegroup has been added via push, pull or unbundle. ID of the @@ -1796,6 +1861,13 @@ By default, the first bundle advertised by the server is used. +``color`` + String: when to use to colorize output. possible value are auto, always, + never, or debug (default: auto). 'auto' will use color whenever it seems + possible. See :hg:`help color` for details. + + (in addition a boolean can be used in place always/never) + ``commitsubrepos`` Whether to commit modified subrepositories when committing the parent repository. If False and one subrepository has uncommitted
--- a/mercurial/help/filesets.txt Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/help/filesets.txt Tue Apr 18 12:24:34 2017 -0400 @@ -69,6 +69,10 @@ hg revert "set:copied() and binary() and size('>1M')" +- Revert files that were added to the working directory:: + + hg revert "set:revs('wdir()', added())" + - Remove files listed in foo.lst that contain the letter a or b:: hg remove "set: 'listfile:foo.lst' and (**a* or **b*)"
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/mercurial/help/internals/censor.txt Tue Apr 18 12:24:34 2017 -0400 @@ -0,0 +1,22 @@ +The censor system allows retroactively removing content from +files. Actually censoring a node requires using the censor extension, +but the functionality for handling censored nodes is partially in core. + +Censored nodes in a filelog have the flag ``REVIDX_ISCENSORED`` set, +and the contents of the censored node are replaced with a censor +tombstone. For historical reasons, the tombstone is packed in the +filelog metadata field ``censored``. This allows censored nodes to be +(mostly) safely transmitted through old formats like changegroup +versions 1 and 2. When using changegroup formats older than 3, the +receiver is required to re-add the ``REVIDX_ISCENSORED`` flag when +storing the revision. This depends on the ``censored`` metadata key +never being used for anything other than censoring revisions, which is +true as of January 2017. Note that the revlog flag is the +authoritative marker of a censored node: the tombstone should only be +consulted when looking for a reason a node was censored or when revlog +flags are unavailable as mentioned above. + +The tombstone data is a free-form string. It's expected that users of +censor will want to record the reason for censoring a node in the +tombstone. Censored nodes must be able to fit in the size of the +content being censored.
--- a/mercurial/help/internals/changegroups.txt Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/help/internals/changegroups.txt Tue Apr 18 12:24:34 2017 -0400 @@ -1,35 +1,49 @@ Changegroups are representations of repository revlog data, specifically -the changelog, manifest, and filelogs. +the changelog data, root/flat manifest data, treemanifest data, and +filelogs. There are 3 versions of changegroups: ``1``, ``2``, and ``3``. From a -high-level, versions ``1`` and ``2`` are almost exactly the same, with -the only difference being a header on entries in the changeset -segment. Version ``3`` adds support for exchanging treemanifests and -includes revlog flags in the delta header. +high-level, versions ``1`` and ``2`` are almost exactly the same, with the +only difference being an additional item in the *delta header*. Version +``3`` adds support for revlog flags in the *delta header* and optionally +exchanging treemanifests (enabled by setting an option on the +``changegroup`` part in the bundle2). -Changegroups consists of 3 logical segments:: +Changegroups when not exchanging treemanifests consist of 3 logical +segments:: +---------------------------------+ | | | | | changeset | manifest | filelogs | | | | | + | | | | +---------------------------------+ +When exchanging treemanifests, there are 4 logical segments:: + + +-------------------------------------------------+ + | | | | | + | changeset | root | treemanifests | filelogs | + | | manifest | | | + | | | | | + +-------------------------------------------------+ + The principle building block of each segment is a *chunk*. A *chunk* is a framed piece of data:: +---------------------------------------+ | | | | length | data | - | (32 bits) | <length> bytes | + | (4 bytes) | (<length - 4> bytes) | | | | +---------------------------------------+ -Each chunk starts with a 32-bit big-endian signed integer indicating -the length of the raw data that follows. +All integers are big-endian signed integers. Each chunk starts with a 32-bit +integer indicating the length of the entire chunk (including the length field +itself). -There is a special case chunk that has 0 length (``0x00000000``). We -call this an *empty chunk*. +There is a special case chunk that has a value of 0 for the length +(``0x00000000``). We call this an *empty chunk*. Delta Groups ============ @@ -43,26 +57,27 @@ +------------------------------------------------------------------------+ | | | | | | | chunk0 length | chunk0 data | chunk1 length | chunk1 data | 0x0 | - | (32 bits) | (various) | (32 bits) | (various) | (32 bits) | + | (4 bytes) | (various) | (4 bytes) | (various) | (4 bytes) | | | | | | | - +------------------------------------------------------------+-----------+ + +------------------------------------------------------------------------+ Each *chunk*'s data consists of the following:: - +-----------------------------------------+ - | | | | - | delta header | mdiff header | delta | - | (various) | (12 bytes) | (various) | - | | | | - +-----------------------------------------+ + +---------------------------------------+ + | | | + | delta header | delta data | + | (various by version) | (various) | + | | | + +---------------------------------------+ -The *length* field is the byte length of the remaining 3 logical pieces -of data. The *delta* is a diff from an existing entry in the changelog. +The *delta data* is a series of *delta*s that describe a diff from an existing +entry (either that the recipient already has, or previously specified in the +bundlei/changegroup). The *delta header* is different between versions ``1``, ``2``, and ``3`` of the changegroup format. -Version 1:: +Version 1 (headerlen=80):: +------------------------------------------------------+ | | | | | @@ -71,7 +86,7 @@ | | | | | +------------------------------------------------------+ -Version 2:: +Version 2 (headerlen=100):: +------------------------------------------------------------------+ | | | | | | @@ -80,30 +95,35 @@ | | | | | | +------------------------------------------------------------------+ -Version 3:: +Version 3 (headerlen=102):: +------------------------------------------------------------------------------+ | | | | | | | - | node | p1 node | p2 node | base node | link node | flags | + | node | p1 node | p2 node | base node | link node | flags | | (20 bytes) | (20 bytes) | (20 bytes) | (20 bytes) | (20 bytes) | (2 bytes) | | | | | | | | +------------------------------------------------------------------------------+ -The *mdiff header* consists of 3 32-bit big-endian signed integers -describing offsets at which to apply the following delta content:: +The *delta data* consists of ``chunklen - 4 - headerlen`` bytes, which contain a +series of *delta*s, densely packed (no separators). These deltas describe a diff +from an existing entry (either that the recipient already has, or previously +specified in the bundle/changegroup). The format is described more fully in +``hg help internals.bdiff``, but briefly:: - +-------------------------------------+ - | | | | - | offset | old length | new length | - | (32 bits) | (32 bits) | (32 bits) | - | | | | - +-------------------------------------+ + +---------------------------------------------------------------+ + | | | | | + | start offset | end offset | new length | content | + | (4 bytes) | (4 bytes) | (4 bytes) | (<new length> bytes) | + | | | | | + +---------------------------------------------------------------+ + +Please note that the length field in the delta data does *not* include itself. In version 1, the delta is always applied against the previous node from the changegroup or the first parent if this is the first entry in the changegroup. -In version 2, the delta base node is encoded in the entry in the +In version 2 and up, the delta base node is encoded in the entry in the changegroup. This allows the delta to be expressed against any parent, which can result in smaller deltas and more efficient encoding of data. @@ -111,43 +131,58 @@ ================= The *changeset segment* consists of a single *delta group* holding -changelog data. It is followed by an *empty chunk* to denote the -boundary to the *manifests segment*. +changelog data. The *empty chunk* at the end of the *delta group* denotes +the boundary to the *manifest segment*. Manifest Segment ================ -The *manifest segment* consists of a single *delta group* holding -manifest data. It is followed by an *empty chunk* to denote the boundary -to the *filelogs segment*. +The *manifest segment* consists of a single *delta group* holding manifest +data. If treemanifests are in use, it contains only the manifest for the +root directory of the repository. Otherwise, it contains the entire +manifest data. The *empty chunk* at the end of the *delta group* denotes +the boundary to the next segment (either the *treemanifests segment* or the +*filelogs segment*, depending on version and the request options). + +Treemanifests Segment +--------------------- + +The *treemanifests segment* only exists in changegroup version ``3``, and +only if the 'treemanifest' param is part of the bundle2 changegroup part +(it is not possible to use changegroup version 3 outside of bundle2). +Aside from the filenames in the *treemanifests segment* containing a +trailing ``/`` character, it behaves identically to the *filelogs segment* +(see below). The final sub-segment is followed by an *empty chunk* (logically, +a sub-segment with filename size 0). This denotes the boundary to the +*filelogs segment*. Filelogs Segment ================ -The *filelogs* segment consists of multiple sub-segments, each +The *filelogs segment* consists of multiple sub-segments, each corresponding to an individual file whose data is being described:: - +--------------------------------------+ - | | | | | - | filelog0 | filelog1 | filelog2 | ... | - | | | | | - +--------------------------------------+ + +--------------------------------------------------+ + | | | | | | + | filelog0 | filelog1 | filelog2 | ... | 0x0 | + | | | | | (4 bytes) | + | | | | | | + +--------------------------------------------------+ -In version ``3`` of the changegroup format, filelogs may include -directory logs when treemanifests are in use. directory logs are -identified by having a trailing '/' on their filename (see below). - -The final filelog sub-segment is followed by an *empty chunk* to denote -the end of the segment and the overall changegroup. +The final filelog sub-segment is followed by an *empty chunk* (logically, +a sub-segment with filename size 0). This denotes the end of the segment +and of the overall changegroup. Each filelog sub-segment consists of the following:: - +------------------------------------------+ - | | | | - | filename size | filename | delta group | - | (32 bits) | (various) | (various) | - | | | | - +------------------------------------------+ + +------------------------------------------------------+ + | | | | + | filename length | filename | delta group | + | (4 bytes) | (<length - 4> bytes) | (various) | + | | | | + +------------------------------------------------------+ That is, a *chunk* consisting of the filename (not terminated or padded) -followed by N chunks constituting the *delta group* for this file. +followed by N chunks constituting the *delta group* for this file. The +*empty chunk* at the end of each *delta group* denotes the boundary to the +next filelog sub-segment.
--- a/mercurial/help/internals/requirements.txt Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/help/internals/requirements.txt Tue Apr 18 12:24:34 2017 -0400 @@ -55,6 +55,17 @@ The requirement was added in Mercurial 1.3 (released July 2009). +relshared +========= + +Derivative of ``shared``; the location of the store is relative to the +store of this repository. + +This requirement is set when a repository is created via :hg:`share` +using the ``--relative`` option. + +The requirement was added in Mercurial 4.2 (released May 2017). + dotencode =========
--- a/mercurial/help/internals/revlogs.txt Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/help/internals/revlogs.txt Tue Apr 18 12:24:34 2017 -0400 @@ -108,9 +108,9 @@ 16-19 (4 bytes) Base or previous revision this revision's delta was produced against. - -1 means this revision holds full text (as opposed to a delta). - For generaldelta repos, this is the previous revision in the delta - chain. For non-generaldelta repos, this is the base or first + This revision holds full text (as opposed to a delta) if it points to + itself. For generaldelta repos, this is the previous revision in the + delta chain. For non-generaldelta repos, this is the base or first revision in the delta chain. 20-23 (4 bytes)
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/mercurial/help/pager.txt Tue Apr 18 12:24:34 2017 -0400 @@ -0,0 +1,35 @@ +Some Mercurial commands produce a lot of output, and Mercurial will +attempt to use a pager to make those commands more pleasant. + +To set the pager that should be used, set the application variable:: + + [pager] + pager = less -FRX + +If no pager is set, the pager extensions uses the environment variable +$PAGER. If neither pager.pager, nor $PAGER is set, a default pager +will be used, typically `more`. + +You can disable the pager for certain commands by adding them to the +pager.ignore list:: + + [pager] + ignore = version, help, update + +To ignore global commands like :hg:`version` or :hg:`help`, you have +to specify them in your user configuration file. + +To control whether the pager is used at all for an individual command, +you can use --pager=<value>:: + + - use as needed: `auto`. + - require the pager: `yes` or `on`. + - suppress the pager: `no` or `off` (any unrecognized value + will also work). + +To globally turn off all attempts to use a pager, set:: + + [pager] + enable = false + +which will prevent the pager from running.
--- a/mercurial/help/patterns.txt Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/help/patterns.txt Tue Apr 18 12:24:34 2017 -0400 @@ -13,7 +13,10 @@ To use a plain path name without any pattern matching, start it with ``path:``. These path names must completely match starting at the -current repository root. +current repository root, and when the path points to a directory, it is matched +recursively. To match all files in a directory non-recursively (not including +any files in subdirectories), ``rootfilesin:`` can be used, specifying an +absolute path (relative to the repository root). To use an extended glob, start a name with ``glob:``. Globs are rooted at the current directory; a glob such as ``*.c`` will only match files @@ -39,12 +42,15 @@ All patterns, except for ``glob:`` specified in command line (not for ``-I`` or ``-X`` options), can match also against directories: files under matched directories are treated as matched. +For ``-I`` and ``-X`` options, ``glob:`` will match directories recursively. Plain examples:: - path:foo/bar a name bar in a directory named foo in the root - of the repository - path:path:name a file or directory named "path:name" + path:foo/bar a name bar in a directory named foo in the root + of the repository + path:path:name a file or directory named "path:name" + rootfilesin:foo/bar the files in a directory called foo/bar, but not any files + in its subdirectories and not a file bar in directory foo Glob examples:: @@ -52,6 +58,8 @@ *.c any name ending in ".c" in the current directory **.c any name ending in ".c" in any subdirectory of the current directory including itself. + foo/* any file in directory foo plus all its subdirectories, + recursively foo/*.c any name ending in ".c" in the directory foo foo/**.c any name ending in ".c" in any subdirectory of foo including itself.
--- a/mercurial/help/subrepos.txt Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/help/subrepos.txt Tue Apr 18 12:24:34 2017 -0400 @@ -136,6 +136,10 @@ subrepository changes are available when referenced by top-level repositories. Push is a no-op for Subversion subrepositories. +:serve: serve does not recurse into subrepositories unless + -S/--subrepos is specified. Git and Subversion subrepositories + are currently silently ignored. + :status: status does not recurse into subrepositories unless -S/--subrepos is specified. Subrepository changes are displayed as regular Mercurial changes on the subrepository
--- a/mercurial/hg.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/hg.py Tue Apr 18 12:24:34 2017 -0400 @@ -40,6 +40,7 @@ url, util, verify as verifymod, + vfs as vfsmod, ) release = lock.release @@ -102,7 +103,7 @@ if u.fragment: branch = u.fragment u.fragment = None - return str(u), (branch, branches or []) + return bytes(u), (branch, branches or []) schemes = { 'bundle': bundlerepo, @@ -195,7 +196,8 @@ return '' return os.path.basename(os.path.normpath(path)) -def share(ui, source, dest=None, update=True, bookmarks=True, defaultpath=None): +def share(ui, source, dest=None, update=True, bookmarks=True, defaultpath=None, + relative=False): '''create a shared repository''' if not islocal(source): @@ -218,8 +220,8 @@ sharedpath = srcrepo.sharedpath # if our source is already sharing - destwvfs = scmutil.vfs(dest, realpath=True) - destvfs = scmutil.vfs(os.path.join(destwvfs.base, '.hg'), realpath=True) + destwvfs = vfsmod.vfs(dest, realpath=True) + destvfs = vfsmod.vfs(os.path.join(destwvfs.base, '.hg'), realpath=True) if destvfs.lexists(): raise error.Abort(_('destination already exists')) @@ -235,7 +237,16 @@ if inst.errno != errno.ENOENT: raise - requirements += 'shared\n' + if relative: + try: + sharedpath = os.path.relpath(sharedpath, destvfs.base) + requirements += 'relshared\n' + except IOError as e: + raise error.Abort(_('cannot calculate relative path'), + hint=str(e)) + else: + requirements += 'shared\n' + destvfs.write('requires', requirements) destvfs.write('sharedpath', sharedpath) @@ -302,8 +313,8 @@ else: ui.progress(topic, pos + num) srcpublishing = srcrepo.publishing() - srcvfs = scmutil.vfs(srcrepo.sharedpath) - dstvfs = scmutil.vfs(destpath) + srcvfs = vfsmod.vfs(srcrepo.sharedpath) + dstvfs = vfsmod.vfs(destpath) for f in srcrepo.store.copylist(): if srcpublishing and f.endswith('phaseroots'): continue @@ -359,7 +370,7 @@ if e.errno != errno.EEXIST: raise - poolvfs = scmutil.vfs(pooldir) + poolvfs = vfsmod.vfs(pooldir) basename = os.path.basename(sharepath) with lock.lock(poolvfs, '%s.lock' % basename): @@ -464,7 +475,7 @@ if not dest: raise error.Abort(_("empty destination path is not valid")) - destvfs = scmutil.vfs(dest, expandpath=True) + destvfs = vfsmod.vfs(dest, expandpath=True) if destvfs.lexists(): if not destvfs.isdir(): raise error.Abort(_("destination '%s' already exists") % dest) @@ -548,7 +559,7 @@ destlock = copystore(ui, srcrepo, destpath) # copy bookmarks over - srcbookmarks = srcrepo.join('bookmarks') + srcbookmarks = srcrepo.vfs.join('bookmarks') dstbookmarks = os.path.join(destpath, 'bookmarks') if os.path.exists(srcbookmarks): util.copyfile(srcbookmarks, dstbookmarks) @@ -556,7 +567,7 @@ # Recomputing branch cache might be slow on big repos, # so just copy it def copybranchcache(fname): - srcbranchcache = srcrepo.join('cache/%s' % fname) + srcbranchcache = srcrepo.vfs.join('cache/%s' % fname) dstbranchcache = os.path.join(dstcachedir, fname) if os.path.exists(srcbranchcache): if not os.path.exists(dstcachedir): @@ -602,14 +613,10 @@ else: stream = None # internal config: ui.quietbookmarkmove - quiet = local.ui.backupconfig('ui', 'quietbookmarkmove') - try: - local.ui.setconfig( - 'ui', 'quietbookmarkmove', True, 'clone') + overrides = {('ui', 'quietbookmarkmove'): True} + with local.ui.configoverride(overrides, 'clone'): exchange.pull(local, srcpeer, revs, streamclonerequested=stream) - finally: - local.ui.restoreconfig(quiet) elif srcrepo: exchange.push(srcrepo, destpeer, revs=revs, bookmarks=srcrepo._bookmarks.keys()) @@ -681,18 +688,19 @@ repo.ui.status(_("%d files updated, %d files merged, " "%d files removed, %d files unresolved\n") % stats) -def updaterepo(repo, node, overwrite): +def updaterepo(repo, node, overwrite, updatecheck=None): """Update the working directory to node. When overwrite is set, changes are clobbered, merged else returns stats (see pydoc mercurial.merge.applyupdates)""" return mergemod.update(repo, node, False, overwrite, - labels=['working copy', 'destination']) + labels=['working copy', 'destination'], + updatecheck=updatecheck) -def update(repo, node, quietempty=False): - """update the working directory to node, merging linear changes""" - stats = updaterepo(repo, node, False) +def update(repo, node, quietempty=False, updatecheck=None): + """update the working directory to node""" + stats = updaterepo(repo, node, False, updatecheck=updatecheck) _showstats(repo, stats, quietempty) if stats[3]: repo.ui.status(_("use 'hg resolve' to retry unresolved file merges\n")) @@ -704,7 +712,7 @@ def clean(repo, node, show_stats=True, quietempty=False): """forcibly switch the working directory to node, clobbering changes""" stats = updaterepo(repo, node, True) - util.unlinkpath(repo.join('graftstate'), ignoremissing=True) + repo.vfs.unlinkpath('graftstate', ignoremissing=True) if show_stats: _showstats(repo, stats, quietempty) return stats[3] > 0 @@ -712,7 +720,7 @@ # naming conflict in updatetotally() _clean = clean -def updatetotally(ui, repo, checkout, brev, clean=False, check=False): +def updatetotally(ui, repo, checkout, brev, clean=False, updatecheck=None): """Update the working directory with extra care for non-file components This takes care of non-file components below: @@ -724,22 +732,38 @@ :checkout: to which revision the working directory is updated :brev: a name, which might be a bookmark to be activated after updating :clean: whether changes in the working directory can be discarded - :check: whether changes in the working directory should be checked + :updatecheck: how to deal with a dirty working directory + + Valid values for updatecheck are (None => linear): + + * abort: abort if the working directory is dirty + * none: don't check (merge working directory changes into destination) + * linear: check that update is linear before merging working directory + changes into destination + * noconflict: check that the update does not result in file merges This returns whether conflict is detected at updating or not. """ + if updatecheck is None: + updatecheck = ui.config('experimental', 'updatecheck') + if updatecheck not in ('abort', 'none', 'linear', 'noconflict'): + # If not configured, or invalid value configured + updatecheck = 'linear' with repo.wlock(): movemarkfrom = None warndest = False if checkout is None: - updata = destutil.destupdate(repo, clean=clean, check=check) + updata = destutil.destupdate(repo, clean=clean) checkout, movemarkfrom, brev = updata warndest = True if clean: ret = _clean(repo, checkout) else: - ret = _update(repo, checkout) + if updatecheck == 'abort': + cmdutil.bailifchanged(repo, merge=False) + updatecheck = 'none' + ret = _update(repo, checkout, updatecheck=updatecheck) if not ret and movemarkfrom: if movemarkfrom == repo['.'].node(): @@ -802,7 +826,7 @@ if not chlist: ui.status(_("no changes found\n")) return subreporecurse() - + ui.pager('incoming') displayer = cmdutil.show_changeset(ui, other, opts, buffered) displaychlist(other, chlist, displayer) displayer.close() @@ -870,6 +894,7 @@ if opts.get('newest_first'): o.reverse() + ui.pager('outgoing') displayer = cmdutil.show_changeset(ui, repo, opts) count = 0 for n in o:
--- a/mercurial/hgweb/common.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/hgweb/common.py Tue Apr 18 12:24:34 2017 -0400 @@ -91,11 +91,13 @@ class ErrorResponse(Exception): - def __init__(self, code, message=None, headers=[]): + def __init__(self, code, message=None, headers=None): if message is None: message = _statusmessage(code) Exception.__init__(self, message) self.code = code + if headers is None: + headers = [] self.headers = headers class continuereader(object): @@ -133,6 +135,17 @@ def get_mtime(spath): return get_stat(spath, "00changelog.i").st_mtime +def ispathsafe(path): + """Determine if a path is safe to use for filesystem access.""" + parts = path.split('/') + for part in parts: + if (part in ('', os.curdir, os.pardir) or + pycompat.ossep in part or + pycompat.osaltsep is not None and pycompat.osaltsep in part): + return False + + return True + def staticfile(directory, fname, req): """return a file inside directory with guessed Content-Type header @@ -142,13 +155,10 @@ Return an empty string if fname is illegal or file not found. """ - parts = fname.split('/') - for part in parts: - if (part in ('', os.curdir, os.pardir) or - pycompat.ossep in part or - pycompat.osaltsep is not None and pycompat.osaltsep in part): - return - fpath = os.path.join(*parts) + if not ispathsafe(fname): + return + + fpath = os.path.join(*fname.split('/')) if isinstance(directory, str): directory = [directory] for d in directory: @@ -158,9 +168,9 @@ try: os.stat(path) ct = mimetypes.guess_type(path)[0] or "text/plain" - fp = open(path, 'rb') - data = fp.read() - fp.close() + with open(path, 'rb') as fh: + data = fh.read() + req.respond(HTTP_OK, ct, body=data) except TypeError: raise ErrorResponse(HTTP_SERVER_ERROR, 'illegal filename')
--- a/mercurial/hgweb/hgweb_mod.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/hgweb/hgweb_mod.py Tue Apr 18 12:24:34 2017 -0400 @@ -335,7 +335,7 @@ req.url = req.env['SCRIPT_NAME'] if not req.url.endswith('/'): req.url += '/' - if 'REPO_NAME' in req.env: + if req.env.get('REPO_NAME'): req.url += req.env['REPO_NAME'] + '/' if 'PATH_INFO' in req.env:
--- a/mercurial/hgweb/hgwebdir_mod.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/hgweb/hgwebdir_mod.py Tue Apr 18 12:24:34 2017 -0400 @@ -254,15 +254,32 @@ return [] # top-level index - elif not virtual: + + repos = dict(self.repos) + + if (not virtual or virtual == 'index') and virtual not in repos: req.respond(HTTP_OK, ctype) return self.makeindex(req, tmpl) # nested indexes and hgwebs - repos = dict(self.repos) - virtualrepo = virtual - while virtualrepo: + if virtual.endswith('/index') and virtual not in repos: + subdir = virtual[:-len('index')] + if any(r.startswith(subdir) for r in repos): + req.respond(HTTP_OK, ctype) + return self.makeindex(req, tmpl, subdir) + + def _virtualdirs(): + # Check the full virtual path, each parent, and the root ('') + if virtual != '': + yield virtual + + for p in util.finddirs(virtual): + yield p + + yield '' + + for virtualrepo in _virtualdirs(): real = repos.get(virtualrepo) if real: req.env['REPO_NAME'] = virtualrepo @@ -276,11 +293,6 @@ except error.RepoError as inst: raise ErrorResponse(HTTP_SERVER_ERROR, str(inst)) - up = virtualrepo.rfind('/') - if up < 0: - break - virtualrepo = virtualrepo[:up] - # browse subdirectories subdir = virtual + '/' if [r for r in repos if r.startswith(subdir)]: @@ -352,8 +364,7 @@ pass parts = [name] - if 'PATH_INFO' in req.env: - parts.insert(0, req.env['PATH_INFO'].rstrip('/')) + parts.insert(0, '/' + subdir.rstrip('/')) if req.env['SCRIPT_NAME']: parts.insert(0, req.env['SCRIPT_NAME']) url = re.sub(r'/+', '/', '/'.join(parts) + '/')
--- a/mercurial/hgweb/webcommands.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/hgweb/webcommands.py Tue Apr 18 12:24:34 2017 -0400 @@ -28,11 +28,14 @@ from .. import ( archival, + context, encoding, error, graphmod, revset, + revsetlang, scmutil, + smartset, templatefilters, templater, util, @@ -238,20 +241,20 @@ revdef = 'reverse(%s)' % query try: - tree = revset.parse(revdef) + tree = revsetlang.parse(revdef) except error.ParseError: # can't parse to a revset tree return MODE_KEYWORD, query - if revset.depth(tree) <= 2: + if revsetlang.depth(tree) <= 2: # no revset syntax used return MODE_KEYWORD, query if any((token, (value or '')[:3]) == ('string', 're:') - for token, value, pos in revset.tokenize(revdef)): + for token, value, pos in revsetlang.tokenize(revdef)): return MODE_KEYWORD, query - funcsused = revset.funcsused(tree) + funcsused = revsetlang.funcsused(tree) if not funcsused.issubset(revset.safesymbols): return MODE_KEYWORD, query @@ -752,13 +755,13 @@ if fctx is not None: path = fctx.path() ctx = fctx.changectx() + basectx = ctx.p1() - parity = paritygen(web.stripecount) style = web.config('web', 'style', 'paper') if 'style' in req.form: style = req.form['style'][0] - diffs = webutil.diffs(web.repo, tmpl, ctx, None, [path], parity, style) + diffs = webutil.diffs(web, tmpl, ctx, basectx, [path], style) if fctx is not None: rename = webutil.renamelink(fctx) ctx = fctx @@ -966,11 +969,20 @@ except ValueError: pass + lrange = webutil.linerange(req) + lessvars = copy.copy(tmpl.defaults['sessionvars']) lessvars['revcount'] = max(revcount / 2, 1) morevars = copy.copy(tmpl.defaults['sessionvars']) morevars['revcount'] = revcount * 2 + patch = 'patch' in req.form + if patch: + lessvars['patch'] = morevars['patch'] = req.form['patch'][0] + descend = 'descend' in req.form + if descend: + lessvars['descend'] = morevars['descend'] = req.form['descend'][0] + count = fctx.filerev() + 1 start = max(0, count - revcount) # first rev on this page end = min(count, start + revcount) # last rev on this page @@ -979,26 +991,74 @@ repo = web.repo revs = fctx.filelog().revs(start, end - 1) entries = [] - for i in revs: - iterfctx = fctx.filectx(i) - entries.append(dict( - parity=next(parity), - filerev=i, - file=f, - rename=webutil.renamelink(iterfctx), - **webutil.commonentry(repo, iterfctx))) - entries.reverse() + + diffstyle = web.config('web', 'style', 'paper') + if 'style' in req.form: + diffstyle = req.form['style'][0] + + def diff(fctx, linerange=None): + ctx = fctx.changectx() + basectx = ctx.p1() + path = fctx.path() + return webutil.diffs(web, tmpl, ctx, basectx, [path], diffstyle, + linerange=linerange, + lineidprefix='%s-' % ctx.hex()[:12]) + + linerange = None + if lrange is not None: + linerange = webutil.formatlinerange(*lrange) + # deactivate numeric nav links when linerange is specified as this + # would required a dedicated "revnav" class + nav = None + if descend: + it = context.blockdescendants(fctx, *lrange) + else: + it = context.blockancestors(fctx, *lrange) + for i, (c, lr) in enumerate(it, 1): + diffs = None + if patch: + diffs = diff(c, linerange=lr) + # follow renames accross filtered (not in range) revisions + path = c.path() + entries.append(dict( + parity=next(parity), + filerev=c.rev(), + file=path, + diff=diffs, + linerange=webutil.formatlinerange(*lr), + **webutil.commonentry(repo, c))) + if i == revcount: + break + lessvars['linerange'] = webutil.formatlinerange(*lrange) + morevars['linerange'] = lessvars['linerange'] + else: + for i in revs: + iterfctx = fctx.filectx(i) + diffs = None + if patch: + diffs = diff(iterfctx) + entries.append(dict( + parity=next(parity), + filerev=i, + file=f, + diff=diffs, + rename=webutil.renamelink(iterfctx), + **webutil.commonentry(repo, iterfctx))) + entries.reverse() + revnav = webutil.filerevnav(web.repo, fctx.path()) + nav = revnav.gen(end - 1, revcount, count) latestentry = entries[:1] - revnav = webutil.filerevnav(web.repo, fctx.path()) - nav = revnav.gen(end - 1, revcount, count) return tmpl("filelog", file=f, nav=nav, symrev=webutil.symrevorshortnode(req, fctx), entries=entries, + descend=descend, + patch=patch, latestentry=latestentry, + linerange=linerange, revcount=revcount, morevars=morevars, lessvars=lessvars, @@ -1148,7 +1208,7 @@ # We have to feed a baseset to dagwalker as it is expecting smartset # object. This does not have a big impact on hgweb performance itself # since hgweb graphing code is not itself lazy yet. - dag = graphmod.dagwalker(web.repo, revset.baseset(revs)) + dag = graphmod.dagwalker(web.repo, smartset.baseset(revs)) # As we said one line above... not lazy. tree = list(graphmod.colored(dag, web.repo))
--- a/mercurial/hgweb/webutil.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/hgweb/webutil.py Tue Apr 18 12:24:34 2017 -0400 @@ -18,6 +18,7 @@ from .common import ( ErrorResponse, + HTTP_BAD_REQUEST, HTTP_NOT_FOUND, paritygen, ) @@ -26,6 +27,7 @@ context, error, match, + mdiff, patch, pathutil, templatefilters, @@ -72,6 +74,8 @@ """return True if any revision to navigate over""" return self._first() is not None + __bool__ = __nonzero__ + def _first(self): """return the minimum non-filtered changeset or None""" try: @@ -142,7 +146,9 @@ return hex(self._changelog.node(self._revlog.linkrev(rev))) class _siblings(object): - def __init__(self, siblings=[], hiderev=None): + def __init__(self, siblings=None, hiderev=None): + if siblings is None: + siblings = [] self.siblings = [s for s in siblings if s.node() != nullid] if len(self.siblings) == 1 and self.siblings[0].rev() == hiderev: self.siblings = [] @@ -313,6 +319,26 @@ return fctx +def linerange(req): + linerange = req.form.get('linerange') + if linerange is None: + return None + if len(linerange) > 1: + raise ErrorResponse(HTTP_BAD_REQUEST, + 'redundant linerange parameter') + try: + fromline, toline = map(int, linerange[0].split(':', 1)) + except ValueError: + raise ErrorResponse(HTTP_BAD_REQUEST, + 'invalid linerange parameter') + try: + return util.processlinerange(fromline, toline) + except error.ParseError as exc: + raise ErrorResponse(HTTP_BAD_REQUEST, str(exc)) + +def formatlinerange(fromline, toline): + return '%d:%d' % (fromline + 1, toline) + def commonentry(repo, ctx): node = ctx.node() return { @@ -384,8 +410,7 @@ if 'style' in req.form: style = req.form['style'][0] - parity = paritygen(web.stripecount) - diff = diffs(web.repo, tmpl, ctx, basectx, None, parity, style) + diff = diffs(web, tmpl, ctx, basectx, None, style) parity = paritygen(web.stripecount) diffstatsgen = diffstatgen(ctx, basectx) @@ -410,18 +435,12 @@ if len(files) > max: yield tmpl('fileellipses') -def diffs(repo, tmpl, ctx, basectx, files, parity, style): +def diffs(web, tmpl, ctx, basectx, files, style, linerange=None, + lineidprefix=''): - def countgen(): - start = 1 - while True: - yield start - start += 1 - - blockcount = countgen() - def prettyprintlines(diff, blockno): - for lineno, l in enumerate(diff.splitlines(True)): - difflineno = "%d.%d" % (blockno, lineno + 1) + def prettyprintlines(lines, blockno): + for lineno, l in enumerate(lines, 1): + difflineno = "%d.%d" % (blockno, lineno) if l.startswith('+'): ltype = "difflineplus" elif l.startswith('-'): @@ -432,39 +451,35 @@ ltype = "diffline" yield tmpl(ltype, line=l, - lineno=lineno + 1, - lineid="l%s" % difflineno, + lineno=lineno, + lineid=lineidprefix + "l%s" % difflineno, linenumber="% 8s" % difflineno) + repo = web.repo if files: m = match.exact(repo.root, repo.getcwd(), files) else: m = match.always(repo.root, repo.getcwd()) diffopts = patch.diffopts(repo.ui, untrusted=True) - if basectx is None: - parents = ctx.parents() - if parents: - node1 = parents[0].node() - else: - node1 = nullid - else: - node1 = basectx.node() + node1 = basectx.node() node2 = ctx.node() + parity = paritygen(web.stripecount) - block = [] - for chunk in patch.diff(repo, node1, node2, m, opts=diffopts): - if chunk.startswith('diff') and block: - blockno = next(blockcount) + diffhunks = patch.diffhunks(repo, node1, node2, m, opts=diffopts) + for blockno, (header, hunks) in enumerate(diffhunks, 1): + if style != 'raw': + header = header[1:] + lines = [h + '\n' for h in header] + for hunkrange, hunklines in hunks: + if linerange is not None and hunkrange is not None: + s1, l1, s2, l2 = hunkrange + if not mdiff.hunkinrange((s2, l2), linerange): + continue + lines.extend(hunklines) + if lines: yield tmpl('diffblock', parity=next(parity), blockno=blockno, - lines=prettyprintlines(''.join(block), blockno)) - block = [] - if chunk.startswith('diff') and style != 'raw': - chunk = ''.join(chunk.splitlines(True)[1:]) - block.append(chunk) - blockno = next(blockcount) - yield tmpl('diffblock', parity=next(parity), blockno=blockno, - lines=prettyprintlines(''.join(block), blockno)) + lines=prettyprintlines(lines, blockno)) def compare(tmpl, context, leftlines, rightlines): '''Generator function that provides side-by-side comparison data.'''
--- a/mercurial/hook.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/hook.py Tue Apr 18 12:24:34 2017 -0400 @@ -9,7 +9,6 @@ import os import sys -import time from .i18n import _ from . import ( @@ -20,7 +19,7 @@ util, ) -def _pythonhook(ui, repo, name, hname, funcname, args, throw): +def _pythonhook(ui, repo, htype, hname, funcname, args, throw): '''call python hook. hook is callable object, looked up as name in python module. if callable returns "true", hook fails, else passes. if hook raises exception, treated as @@ -88,10 +87,10 @@ % (hname, funcname)) ui.note(_("calling hook %s: %s\n") % (hname, funcname)) - starttime = time.time() + starttime = util.timer() try: - r = obj(ui=ui, repo=repo, hooktype=name, **args) + r = obj(ui=ui, repo=repo, hooktype=htype, **args) except Exception as exc: if isinstance(exc, error.Abort): ui.warn(_('error: %s hook failed: %s\n') % @@ -106,19 +105,19 @@ ui.traceback() return True, True finally: - duration = time.time() - starttime + duration = util.timer() - starttime ui.log('pythonhook', 'pythonhook-%s: %s finished in %0.2f seconds\n', - name, funcname, duration) + htype, funcname, duration) if r: if throw: raise error.HookAbort(_('%s hook failed') % hname) ui.warn(_('warning: %s hook failed\n') % hname) return r, False -def _exthook(ui, repo, name, cmd, args, throw): +def _exthook(ui, repo, htype, name, cmd, args, throw): ui.note(_("running hook %s: %s\n") % (name, cmd)) - starttime = time.time() + starttime = util.timer() env = {} # make in-memory changes visible to external process @@ -127,6 +126,8 @@ repo.dirstate.write(tr) if tr and tr.writepending(): env['HG_PENDING'] = repo.root + env['HG_HOOKTYPE'] = htype + env['HG_HOOKNAME'] = name for k, v in args.iteritems(): if callable(v): @@ -143,9 +144,9 @@ cwd = repo.root else: cwd = pycompat.getcwd() - r = ui.system(cmd, environ=env, cwd=cwd) + r = ui.system(cmd, environ=env, cwd=cwd, blockedtag='exthook-%s' % (name,)) - duration = time.time() - starttime + duration = util.timer() - starttime ui.log('exthook', 'exthook-%s: %s finished in %0.2f seconds\n', name, cmd, duration) if r: @@ -187,22 +188,22 @@ global _redirect _redirect = state -def hook(ui, repo, name, throw=False, **args): +def hook(ui, repo, htype, throw=False, **args): if not ui.callhooks: return False hooks = [] for hname, cmd in _allhooks(ui): - if hname.split('.')[0] == name and cmd: + if hname.split('.')[0] == htype and cmd: hooks.append((hname, cmd)) - res = runhooks(ui, repo, name, hooks, throw=throw, **args) + res = runhooks(ui, repo, htype, hooks, throw=throw, **args) r = False for hname, cmd in hooks: r = res[hname][0] or r return r -def runhooks(ui, repo, name, hooks, throw=False, **args): +def runhooks(ui, repo, htype, hooks, throw=False, **args): res = {} oldstdout = -1 @@ -224,13 +225,14 @@ if cmd is _fromuntrusted: if throw: raise error.HookAbort( - _('untrusted hook %s not executed') % name, + _('untrusted hook %s not executed') % hname, hint = _("see 'hg help config.trusted'")) - ui.warn(_('warning: untrusted hook %s not executed\n') % name) + ui.warn(_('warning: untrusted hook %s not executed\n') % hname) r = 1 raised = False elif callable(cmd): - r, raised = _pythonhook(ui, repo, name, hname, cmd, args, throw) + r, raised = _pythonhook(ui, repo, htype, hname, cmd, args, + throw) elif cmd.startswith('python:'): if cmd.count(':') >= 2: path, cmd = cmd[7:].rsplit(':', 1) @@ -245,10 +247,10 @@ hookfn = getattr(mod, cmd) else: hookfn = cmd[7:].strip() - r, raised = _pythonhook(ui, repo, name, hname, hookfn, args, + r, raised = _pythonhook(ui, repo, htype, hname, hookfn, args, throw) else: - r = _exthook(ui, repo, hname, cmd, args, throw) + r = _exthook(ui, repo, htype, hname, cmd, args, throw) raised = False res[hname] = r, raised
--- a/mercurial/httpclient/__init__.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/httpclient/__init__.py Tue Apr 18 12:24:34 2017 -0400 @@ -631,7 +631,7 @@ self.close() self._connect(pheaders) - def request(self, method, path, body=None, headers={}, + def request(self, method, path, body=None, headers=None, expect_continue=False): """Send a request to the server. @@ -642,6 +642,8 @@ available. Use the `getresponse()` method to retrieve the response. """ + if headers is None: + headers = {} method = _ensurebytes(method) path = _ensurebytes(path) if self.busy():
--- a/mercurial/httpconnection.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/httpconnection.py Tue Apr 18 12:24:34 2017 -0400 @@ -44,10 +44,10 @@ self._total = self.length // 1024 * 2 def read(self, *args, **kwargs): - try: - ret = self._data.read(*args, **kwargs) - except EOFError: + ret = self._data.read(*args, **kwargs) + if not ret: self.ui.progress(_('sending'), None) + return ret self._pos += len(ret) # We pass double the max for total because we currently have # to send the bundle twice in the case of a server that @@ -67,13 +67,16 @@ # moved here from url.py to avoid a cycle def readauthforuri(ui, uri, user): # Read configuration - config = dict() + groups = {} for key, val in ui.configitems('auth'): + if key in ('cookiefile',): + continue + if '.' not in key: ui.warn(_("ignoring invalid [auth] key '%s'\n") % key) continue group, setting = key.rsplit('.', 1) - gdict = config.setdefault(group, dict()) + gdict = groups.setdefault(group, {}) if setting in ('username', 'cert', 'key'): val = util.expandpath(val) gdict[setting] = val @@ -83,7 +86,7 @@ bestuser = None bestlen = 0 bestauth = None - for group, auth in config.iteritems(): + for group, auth in groups.iteritems(): if user and user != auth.get('username', user): # If a username was set in the URI, the entry username # must either match it or be unset
--- a/mercurial/httppeer.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/httppeer.py Tue Apr 18 12:24:34 2017 -0400 @@ -20,6 +20,7 @@ bundle2, error, httpconnection, + pycompat, statichttprepo, url, util, @@ -30,30 +31,6 @@ urlerr = util.urlerr urlreq = util.urlreq -# FUTURE: consider refactoring this API to use generators. This will -# require a compression engine API to emit generators. -def decompressresponse(response, engine): - try: - reader = engine.decompressorreader(response) - except httplib.HTTPException: - raise IOError(None, _('connection ended unexpectedly')) - - # We need to wrap reader.read() so HTTPException on subsequent - # reads is also converted. - # Ideally we'd use super() here. However, if ``reader`` isn't a new-style - # class, this can raise: - # TypeError: super() argument 1 must be type, not classobj - origread = reader.read - class readerproxy(reader.__class__): - def read(self, *args, **kwargs): - try: - return origread(*args, **kwargs) - except httplib.HTTPException: - raise IOError(None, _('connection ended unexpectedly')) - - reader.__class__ = readerproxy - return reader - def encodevalueinheaders(value, header, limit): """Encode a string value into multiple HTTP headers. @@ -74,6 +51,41 @@ return result +def _wraphttpresponse(resp): + """Wrap an HTTPResponse with common error handlers. + + This ensures that any I/O from any consumer raises the appropriate + error and messaging. + """ + origread = resp.read + + class readerproxy(resp.__class__): + def read(self, size=None): + try: + return origread(size) + except httplib.IncompleteRead as e: + # e.expected is an integer if length known or None otherwise. + if e.expected: + msg = _('HTTP request error (incomplete response; ' + 'expected %d bytes got %d)') % (e.expected, + len(e.partial)) + else: + msg = _('HTTP request error (incomplete response)') + + raise error.PeerTransportError( + msg, + hint=_('this may be an intermittent network failure; ' + 'if the error persists, consider contacting the ' + 'network or server operator')) + except httplib.HTTPException as e: + raise error.PeerTransportError( + _('HTTP request error (%s)') % e, + hint=_('this may be an intermittent failure; ' + 'if the error persists, consider contacting the ' + 'network or server operator')) + + resp.__class__ = readerproxy + class httppeer(wireproto.wirepeer): def __init__(self, ui, path): self.path = path @@ -206,7 +218,9 @@ headers[header] = value varyheaders.append(header) - headers['Vary'] = ','.join(varyheaders) + if varyheaders: + headers['Vary'] = ','.join(varyheaders) + req = self.requestbuilder(cu, data, headers) if data is not None: @@ -222,6 +236,10 @@ self.ui.debug('http error while sending %s command\n' % cmd) self.ui.traceback() raise IOError(None, inst) + + # Insert error handlers for common I/O failures. + _wraphttpresponse(resp) + # record the url we got redirected to resp_url = resp.geturl() if resp_url.endswith(qs): @@ -257,9 +275,11 @@ raise error.RepoError(_("'%s' sent a broken Content-Type " "header (%s)") % (safeurl, proto)) + # TODO consider switching to a decompression reader that uses + # generators. if version_info == (0, 1): if _compressible: - return decompressresponse(resp, util.compengines['zlib']) + return util.compengines['zlib'].decompressorreader(resp) return resp elif version_info == (0, 2): # application/mercurial-0.2 always identifies the compression @@ -267,13 +287,13 @@ elen = struct.unpack('B', resp.read(1))[0] ename = resp.read(elen) engine = util.compengines.forwiretype(ename) - return decompressresponse(resp, engine) + return engine.decompressorreader(resp) else: raise error.RepoError(_("'%s' uses newer protocol %s") % (safeurl, version)) if _compressible: - return decompressresponse(resp, util.compengines['zlib']) + return util.compengines['zlib'].decompressorreader(resp) return resp @@ -327,7 +347,7 @@ try: # dump bundle to disk fd, filename = tempfile.mkstemp(prefix="hg-bundle-", suffix=".hg") - fh = os.fdopen(fd, "wb") + fh = os.fdopen(fd, pycompat.sysstr("wb")) d = fp.read(4096) while d: fh.write(d)
--- a/mercurial/i18n.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/i18n.py Tue Apr 18 12:24:34 2017 -0400 @@ -21,7 +21,7 @@ if getattr(sys, 'frozen', None) is not None: module = pycompat.sysexecutable else: - module = __file__ + module = pycompat.fsencode(__file__) try: unicode
--- a/mercurial/keepalive.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/keepalive.py Tue Apr 18 12:24:34 2017 -0400 @@ -298,11 +298,12 @@ def _start_transaction(self, h, req): # What follows mostly reimplements HTTPConnection.request() - # except it adds self.parent.addheaders in the mix. - headers = dict(self.parent.addheaders) - headers.update(req.headers) - headers.update(req.unredirected_hdrs) - headers = dict((n.lower(), v) for n, v in headers.items()) + # except it adds self.parent.addheaders in the mix and sends headers + # in a deterministic order (to make testing easier). + headers = util.sortdict(self.parent.addheaders) + headers.update(sorted(req.headers.items())) + headers.update(sorted(req.unredirected_hdrs.items())) + headers = util.sortdict((n.lower(), v) for n, v in headers.items()) skipheaders = {} for n in ('host', 'accept-encoding'): if n in headers: @@ -310,14 +311,16 @@ try: if req.has_data(): data = req.get_data() - h.putrequest('POST', req.get_selector(), **skipheaders) + h.putrequest( + req.get_method(), req.get_selector(), **skipheaders) if 'content-type' not in headers: h.putheader('Content-type', 'application/x-www-form-urlencoded') if 'content-length' not in headers: h.putheader('Content-length', '%d' % len(data)) else: - h.putrequest('GET', req.get_selector(), **skipheaders) + h.putrequest( + req.get_method(), req.get_selector(), **skipheaders) except socket.error as err: raise urlerr.urlerror(err) for k, v in headers.items():
--- a/mercurial/localrepo.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/localrepo.py Tue Apr 18 12:24:34 2017 -0400 @@ -28,6 +28,7 @@ bundle2, changegroup, changelog, + color, context, dirstate, dirstateguard, @@ -48,14 +49,18 @@ peer, phases, pushkey, + pycompat, repoview, revset, + revsetlang, scmutil, store, subrepo, tags as tagsmod, transaction, + txnutil, util, + vfs as vfsmod, ) release = lockmod.release @@ -66,6 +71,8 @@ """All filecache usage on repo are done for logic that should be unfiltered """ + def join(self, obj, fname): + return obj.vfs.join(fname) def __get__(self, repo, type=None): if repo is None: return self @@ -113,7 +120,9 @@ class localpeer(peer.peerrepository): '''peer for a local repo; reflects only the most recent API''' - def __init__(self, repo, caps=moderncaps): + def __init__(self, repo, caps=None): + if caps is None: + caps = moderncaps.copy() peer.peerrepository.__init__(self) self._repo = repo.filtered('served') self.ui = repo.ui @@ -241,7 +250,7 @@ supportedformats = set(('revlogv1', 'generaldelta', 'treemanifest', 'manifestv2')) _basesupported = supportedformats | set(('store', 'fncache', 'shared', - 'dotencode')) + 'relshared', 'dotencode')) openerreqs = set(('revlogv1', 'generaldelta', 'treemanifest', 'manifestv2')) filtername = None @@ -251,16 +260,21 @@ def __init__(self, baseui, path, create=False): self.requirements = set() - self.wvfs = scmutil.vfs(path, expandpath=True, realpath=True) - self.wopener = self.wvfs + # wvfs: rooted at the repository root, used to access the working copy + self.wvfs = vfsmod.vfs(path, expandpath=True, realpath=True) + # vfs: rooted at .hg, used to access repo files outside of .hg/store + self.vfs = None + # svfs: usually rooted at .hg/store, used to access repository history + # If this is a shared repository, this vfs may point to another + # repository's .hg/store directory. + self.svfs = None self.root = self.wvfs.base self.path = self.wvfs.join(".hg") self.origroot = path self.auditor = pathutil.pathauditor(self.root, self._checknested) self.nofsauditor = pathutil.pathauditor(self.root, self._checknested, realfs=False) - self.vfs = scmutil.vfs(self.path) - self.opener = self.vfs + self.vfs = vfsmod.vfs(self.path) self.baseui = baseui self.ui = baseui.copy() self.ui.copy = baseui.copy # prevent copying repo configuration @@ -269,8 +283,8 @@ # This list it to be filled by extension during repo setup self._phasedefaults = [] try: - self.ui.readconfig(self.join("hgrc"), self.root) - extensions.loadall(self.ui) + self.ui.readconfig(self.vfs.join("hgrc"), self.root) + self._loadextensions() except IOError: pass @@ -283,6 +297,7 @@ setupfunc(self.ui, self.supported) else: self.supported = self._basesupported + color.setup(self.ui) # Add compression engines. for name in util.compengines: @@ -321,8 +336,10 @@ self.sharedpath = self.path try: - vfs = scmutil.vfs(self.vfs.read("sharedpath").rstrip('\n'), - realpath=True) + sharedpath = self.vfs.read("sharedpath").rstrip('\n') + if 'relshared' in self.requirements: + sharedpath = self.vfs.join(sharedpath) + vfs = vfsmod.vfs(sharedpath, realpath=True) s = vfs.base if not vfs.exists(): raise error.RepoError( @@ -333,7 +350,7 @@ raise self.store = store.store( - self.requirements, self.sharedpath, scmutil.vfs) + self.requirements, self.sharedpath, vfsmod.vfs) self.spath = self.store.path self.svfs = self.store.vfs self.sjoin = self.store.join @@ -368,9 +385,22 @@ # generic mapping between names and nodes self.names = namespaces.namespaces() + @property + def wopener(self): + self.ui.deprecwarn("use 'repo.wvfs' instead of 'repo.wopener'", '4.2') + return self.wvfs + + @property + def opener(self): + self.ui.deprecwarn("use 'repo.vfs' instead of 'repo.opener'", '4.2') + return self.vfs + def close(self): self._writecaches() + def _loadextensions(self): + extensions.loadall(self.ui) + def _writecaches(self): if self._revbranchcache: self._revbranchcache.write() @@ -461,9 +491,9 @@ """Return a filtered version of a repository""" # build a new class with the mixin and the current class # (possibly subclass of the repo) - class proxycls(repoview.repoview, self.unfiltered().__class__): + class filteredrepo(repoview.repoview, self.unfiltered().__class__): pass - return proxycls(self, name) + return filteredrepo(self, name) @repofilecache('bookmarks', 'bookmarks.current') def _bookmarks(self): @@ -509,10 +539,8 @@ @storecache('00changelog.i') def changelog(self): c = changelog.changelog(self.svfs) - if 'HG_PENDING' in encoding.environ: - p = encoding.environ['HG_PENDING'] - if p.startswith(self.root): - c.readpending('00changelog.i.a') + if txnutil.mayhavepending(self.root): + c.readpending('00changelog.i.a') return c def _constructmanifest(self): @@ -560,6 +588,8 @@ def __nonzero__(self): return True + __bool__ = __nonzero__ + def __len__(self): return len(self.changelog) @@ -570,15 +600,16 @@ '''Find revisions matching a revset. The revset is specified as a string ``expr`` that may contain - %-formatting to escape certain types. See ``revset.formatspec``. + %-formatting to escape certain types. See ``revsetlang.formatspec``. Revset aliases from the configuration are not expanded. To expand - user aliases, consider calling ``scmutil.revrange()``. + user aliases, consider calling ``scmutil.revrange()`` or + ``repo.anyrevs([expr], user=True)``. Returns a revset.abstractsmartset, which is a list-like interface that contains integer revisions. ''' - expr = revset.formatspec(expr, *args) + expr = revsetlang.formatspec(expr, *args) m = revset.match(None, expr) return m(self) @@ -594,6 +625,18 @@ for r in self.revs(expr, *args): yield self[r] + def anyrevs(self, specs, user=False): + '''Find revisions matching one of the given revsets. + + Revset aliases from the configuration are not expanded by default. To + expand user aliases, specify ``user=True``. + ''' + if user: + m = revset.matchany(self.ui, specs, repo=self) + else: + m = revset.matchany(None, specs) + return m(self) + def url(self): return 'file:' + self.root @@ -606,109 +649,10 @@ """ return hook.hook(self.ui, self, name, throw, **args) - @unfilteredmethod - def _tag(self, names, node, message, local, user, date, extra=None, - editor=False): - if isinstance(names, str): - names = (names,) - - branches = self.branchmap() - for name in names: - self.hook('pretag', throw=True, node=hex(node), tag=name, - local=local) - if name in branches: - self.ui.warn(_("warning: tag %s conflicts with existing" - " branch name\n") % name) - - def writetags(fp, names, munge, prevtags): - fp.seek(0, 2) - if prevtags and prevtags[-1] != '\n': - fp.write('\n') - for name in names: - if munge: - m = munge(name) - else: - m = name - - if (self._tagscache.tagtypes and - name in self._tagscache.tagtypes): - old = self.tags().get(name, nullid) - fp.write('%s %s\n' % (hex(old), m)) - fp.write('%s %s\n' % (hex(node), m)) - fp.close() - - prevtags = '' - if local: - try: - fp = self.vfs('localtags', 'r+') - except IOError: - fp = self.vfs('localtags', 'a') - else: - prevtags = fp.read() - - # local tags are stored in the current charset - writetags(fp, names, None, prevtags) - for name in names: - self.hook('tag', node=hex(node), tag=name, local=local) - return - - try: - fp = self.wfile('.hgtags', 'rb+') - except IOError as e: - if e.errno != errno.ENOENT: - raise - fp = self.wfile('.hgtags', 'ab') - else: - prevtags = fp.read() - - # committed tags are stored in UTF-8 - writetags(fp, names, encoding.fromlocal, prevtags) - - fp.close() - - self.invalidatecaches() - - if '.hgtags' not in self.dirstate: - self[None].add(['.hgtags']) - - m = matchmod.exact(self.root, '', ['.hgtags']) - tagnode = self.commit(message, user, date, extra=extra, match=m, - editor=editor) - - for name in names: - self.hook('tag', node=hex(node), tag=name, local=local) - - return tagnode - def tag(self, names, node, message, local, user, date, editor=False): - '''tag a revision with one or more symbolic names. - - names is a list of strings or, when adding a single tag, names may be a - string. - - if local is True, the tags are stored in a per-repository file. - otherwise, they are stored in the .hgtags file, and a new - changeset is committed with the change. - - keyword arguments: - - local: whether to store tags in non-version-controlled file - (default False) - - message: commit message to use if committing - - user: name of user to use if committing - - date: date tuple to use if committing''' - - if not local: - m = matchmod.exact(self.root, '', ['.hgtags']) - if any(self.status(match=m, unknown=True, ignored=True)): - raise error.Abort(_('working copy of .hgtags is changed'), - hint=_('please commit .hgtags manually')) - - self.tags() # instantiate the cache - self._tag(names, node, message, local, user, date, editor=editor) + self.ui.deprecwarn("use 'tagsmod.tag' instead of 'repo.tag'", '4.2') + tagsmod.tag(self, names, node, message, local, user, date, + editor=editor) @filteredpropertycache def _tagscache(self): @@ -763,10 +707,12 @@ # be one tagtype for all such "virtual" tags? Or is the status # quo fine? - alltags = {} # map tag name to (node, hist) - tagtypes = {} - tagsmod.findglobaltags(self.ui, self, alltags, tagtypes) + # map tag name to (node, hist) + alltags = tagsmod.findglobaltags(self.ui, self) + # map tag name to tag type + tagtypes = dict((tag, 'global') for tag in alltags) + tagsmod.readlocaltags(self.ui, self, alltags, tagtypes) # Build the return dicts. Have to re-encode tag names because @@ -896,6 +842,7 @@ return None def join(self, f, *insidef): + self.ui.deprecwarn("use 'repo.vfs.join' instead of 'repo.join'", '4.2') return self.vfs.join(os.path.join(f, *insidef)) def wjoin(self, f, *insidef): @@ -938,9 +885,12 @@ return self.dirstate.pathto(f, cwd) def wfile(self, f, mode='r'): + self.ui.deprecwarn("use 'repo.wvfs' instead of 'repo.wfile'", '4.2') return self.wvfs(f, mode) def _link(self, f): + self.ui.deprecwarn("use 'repo.wvfs.islink' instead of 'repo._link'", + '4.2') return self.wvfs.islink(f) def _loadfilter(self, filter): @@ -988,7 +938,7 @@ self._datafilters[name] = filter def wread(self, filename): - if self._link(filename): + if self.wvfs.islink(filename): data = self.wvfs.readlink(filename) else: data = self.wvfs.read(filename) @@ -1038,7 +988,8 @@ hint=_("run 'hg recover' to clean up transaction")) idbase = "%.40f#%f" % (random.random(), time.time()) - txnid = 'TXN:' + hashlib.sha1(idbase).hexdigest() + ha = hex(hashlib.sha1(idbase).digest()) + txnid = 'TXN:' + ha self.hook('pretxnopen', throw=True, txnname=desc, txnid=txnid) self._writejournal(desc) @@ -1050,10 +1001,82 @@ vfsmap = {'plain': self.vfs} # root of .hg/ # we must avoid cyclic reference between repo and transaction. reporef = weakref.ref(self) - def validate(tr): + # Code to track tag movement + # + # Since tags are all handled as file content, it is actually quite hard + # to track these movement from a code perspective. So we fallback to a + # tracking at the repository level. One could envision to track changes + # to the '.hgtags' file through changegroup apply but that fails to + # cope with case where transaction expose new heads without changegroup + # being involved (eg: phase movement). + # + # For now, We gate the feature behind a flag since this likely comes + # with performance impacts. The current code run more often than needed + # and do not use caches as much as it could. The current focus is on + # the behavior of the feature so we disable it by default. The flag + # will be removed when we are happy with the performance impact. + # + # Once this feature is no longer experimental move the following + # documentation to the appropriate help section: + # + # The ``HG_TAG_MOVED`` variable will be set if the transaction touched + # tags (new or changed or deleted tags). In addition the details of + # these changes are made available in a file at: + # ``REPOROOT/.hg/changes/tags.changes``. + # Make sure you check for HG_TAG_MOVED before reading that file as it + # might exist from a previous transaction even if no tag were touched + # in this one. Changes are recorded in a line base format:: + # + # <action> <hex-node> <tag-name>\n + # + # Actions are defined as follow: + # "-R": tag is removed, + # "+A": tag is added, + # "-M": tag is moved (old value), + # "+M": tag is moved (new value), + tracktags = lambda x: None + # experimental config: experimental.hook-track-tags + shouldtracktags = self.ui.configbool('experimental', 'hook-track-tags', + False) + if desc != 'strip' and shouldtracktags: + oldheads = self.changelog.headrevs() + def tracktags(tr2): + repo = reporef() + oldfnodes = tagsmod.fnoderevs(repo.ui, repo, oldheads) + newheads = repo.changelog.headrevs() + newfnodes = tagsmod.fnoderevs(repo.ui, repo, newheads) + # notes: we compare lists here. + # As we do it only once buiding set would not be cheaper + changes = tagsmod.difftags(repo.ui, repo, oldfnodes, newfnodes) + if changes: + tr2.hookargs['tag_moved'] = '1' + with repo.vfs('changes/tags.changes', 'w', + atomictemp=True) as changesfile: + # note: we do not register the file to the transaction + # because we needs it to still exist on the transaction + # is close (for txnclose hooks) + tagsmod.writediff(changesfile, changes) + def validate(tr2): """will run pre-closing hooks""" + # XXX the transaction API is a bit lacking here so we take a hacky + # path for now + # + # We cannot add this as a "pending" hooks since the 'tr.hookargs' + # dict is copied before these run. In addition we needs the data + # available to in memory hooks too. + # + # Moreover, we also need to make sure this runs before txnclose + # hooks and there is no "pending" mechanism that would execute + # logic only if hooks are about to run. + # + # Fixing this limitation of the transaction is also needed to track + # other families of changes (bookmarks, phases, obsolescence). + # + # This will have to be fixed before we remove the experimental + # gating. + tracktags(tr2) reporef().hook('pretxnclose', throw=True, - txnname=desc, **tr.hookargs) + txnname=desc, **pycompat.strkwargs(tr.hookargs)) def releasefn(tr, success): repo = reporef() if success: @@ -1094,7 +1117,7 @@ def hook(): reporef().hook('txnclose', throw=False, txnname=desc, - **hookargs) + **pycompat.strkwargs(hookargs)) reporef()._afterlock(hook) tr.addfinalize('txnclose-hook', txnclosehook) def txnaborthook(tr2): @@ -1270,7 +1293,7 @@ redundant one doesn't). ''' unfiltered = self.unfiltered() # all file caches are stored unfiltered - for k in self._filecache.keys(): + for k in list(self._filecache.keys()): # dirstate is invalidated separately in invalidatedirstate() if k == 'dirstate': continue @@ -1852,6 +1875,11 @@ listsubrepos) def heads(self, start=None): + if start is None: + cl = self.changelog + headrevs = reversed(cl.headrevs()) + return [cl.node(rev) for rev in headrevs] + heads = self.changelog.heads(start) # sort the output in rev descending order return sorted(heads, key=self.changelog.rev, reverse=True) @@ -1972,6 +2000,10 @@ renamefiles = [tuple(t) for t in files] def a(): for vfs, src, dest in renamefiles: + # if src and dest refer to a same file, vfs.rename is a no-op, + # leaving both src and dest on disk. delete dest to make sure + # the rename couldn't be such a no-op. + vfs.tryunlink(dest) try: vfs.rename(src, dest) except OSError: # journal file does not yet exist
--- a/mercurial/lock.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/lock.py Tue Apr 18 12:24:34 2017 -0400 @@ -9,15 +9,36 @@ import contextlib import errno +import os import socket import time import warnings from . import ( + encoding, error, + pycompat, util, ) +def _getlockprefix(): + """Return a string which is used to differentiate pid namespaces + + It's useful to detect "dead" processes and remove stale locks with + confidence. Typically it's just hostname. On modern linux, we include an + extra Linux-specific pid namespace identifier. + """ + result = socket.gethostname() + if pycompat.ispy3: + result = result.encode(pycompat.sysstr(encoding.encoding), 'replace') + if pycompat.sysplatform.startswith('linux'): + try: + result += '/%x' % os.stat('/proc/self/ns/pid').st_ino + except OSError as ex: + if ex.errno not in (errno.ENOENT, errno.EACCES, errno.ENOTDIR): + raise + return result + class lock(object): '''An advisory lock held by one process to control access to a set of files. Non-cooperating processes or incorrectly written scripts @@ -99,8 +120,8 @@ self.held += 1 return if lock._host is None: - lock._host = socket.gethostname() - lockname = '%s:%s' % (lock._host, self.pid) + lock._host = _getlockprefix() + lockname = '%s:%d' % (lock._host, self.pid) retry = 5 while not self.held and retry: retry -= 1
--- a/mercurial/mail.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/mail.py Tue Apr 18 12:24:34 2017 -0400 @@ -353,4 +353,4 @@ except UnicodeDecodeError: pass uparts.append(part.decode('ISO-8859-1')) - return encoding.tolocal(u' '.join(uparts).encode('UTF-8')) + return encoding.unitolocal(u' '.join(uparts))
--- a/mercurial/manifest.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/manifest.py Tue Apr 18 12:24:34 2017 -0400 @@ -7,12 +7,15 @@ from __future__ import absolute_import -import array import heapq import os import struct from .i18n import _ +from .node import ( + bin, + hex, +) from . import ( error, mdiff, @@ -38,9 +41,9 @@ prev = l f, n = l.split('\0') if len(n) > 40: - yield f, revlog.bin(n[:40]), n[40:] + yield f, bin(n[:40]), n[40:] else: - yield f, revlog.bin(n), '' + yield f, bin(n), '' def _parsev2(data): metadataend = data.find('\n') @@ -124,6 +127,8 @@ zeropos = data.find('\x00', pos) return data[pos:zeropos] + __next__ = next + class lazymanifestiterentries(object): def __init__(self, lm): self.lm = lm @@ -147,8 +152,10 @@ self.pos += 1 return (data[pos:zeropos], hashval, flags) + __next__ = next + def unhexlify(data, extra, pos, length): - s = data[pos:pos + length].decode('hex') + s = bin(data[pos:pos + length]) if extra: s += chr(extra & 0xff) return s @@ -173,7 +180,7 @@ if not data: return [] pos = data.find("\n") - if pos == -1 or data[-1] != '\n': + if pos == -1 or data[-1:] != '\n': raise ValueError("Manifest did not end in a newline.") positions = [0] prev = data[:data.find('\x00')] @@ -251,8 +258,8 @@ return self.data[start:end] def __getitem__(self, key): - if not isinstance(key, str): - raise TypeError("getitem: manifest keys must be a string.") + if not isinstance(key, bytes): + raise TypeError("getitem: manifest keys must be a bytes.") needle = self.bsearch(key) if needle == -1: raise KeyError @@ -277,17 +284,17 @@ self.data = self.data[:cur] + '\x00' + self.data[cur + 1:] def __setitem__(self, key, value): - if not isinstance(key, str): - raise TypeError("setitem: manifest keys must be a string.") + if not isinstance(key, bytes): + raise TypeError("setitem: manifest keys must be a byte string.") if not isinstance(value, tuple) or len(value) != 2: raise TypeError("Manifest values must be a tuple of (node, flags).") hashval = value[0] - if not isinstance(hashval, str) or not 20 <= len(hashval) <= 22: - raise TypeError("node must be a 20-byte string") + if not isinstance(hashval, bytes) or not 20 <= len(hashval) <= 22: + raise TypeError("node must be a 20-byte byte string") flags = value[1] if len(hashval) == 22: hashval = hashval[:-1] - if not isinstance(flags, str) or len(flags) > 1: + if not isinstance(flags, bytes) or len(flags) > 1: raise TypeError("flags must a 0 or 1 byte string, got %r", flags) needle, found = self.bsearch2(key) if found: @@ -351,7 +358,7 @@ self.extradata = [] def _pack(self, d): - return d[0] + '\x00' + d[1][:20].encode('hex') + d[2] + '\n' + return d[0] + '\x00' + hex(d[1][:20]) + d[2] + '\n' def text(self): self._compact() @@ -427,6 +434,8 @@ # makes it easier for extensions to override. return len(self._lm) != 0 + __bool__ = __nonzero__ + def __setitem__(self, key, node): self._lm[key] = node, self.flags(key, '') @@ -445,8 +454,12 @@ def keys(self): return list(self.iterkeys()) - def filesnotin(self, m2): + def filesnotin(self, m2, match=None): '''Set of files in this manifest that are not in the other''' + if match: + m1 = self.matches(match) + m2 = m2.matches(match) + return m1.filesnotin(m2) diff = self.diff(m2) files = set(filepath for filepath, hashflags in diff.iteritems() @@ -523,7 +536,7 @@ m._lm = self._lm.filtercopy(match) return m - def diff(self, m2, clean=False): + def diff(self, m2, match=None, clean=False): '''Finds changes between the current manifest and m2. Args: @@ -538,6 +551,10 @@ the nodeid will be None and the flags will be the empty string. ''' + if match: + m1 = self.matches(match) + m2 = m2.matches(match) + return m1.diff(m2, clean=clean) return self._lm.diff(m2._lm, clean) def setflag(self, key, flag): @@ -574,7 +591,7 @@ return self._lm.text() def fastdelta(self, base, changes): - """Given a base manifest text as an array.array and a list of changes + """Given a base manifest text as a bytearray and a list of changes relative to that text, compute a delta that can be used by revlog. """ delta = [] @@ -620,8 +637,9 @@ else: # For large changes, it's much cheaper to just build the text and # diff it. - arraytext = array.array('c', self.text()) - deltatext = mdiff.textdiff(base, arraytext) + arraytext = bytearray(self.text()) + deltatext = mdiff.textdiff( + util.buffer(base), util.buffer(arraytext)) return arraytext, deltatext @@ -632,10 +650,10 @@ that string. If start == end the string was not found and they indicate the proper sorted insertion point. - m should be a buffer or a string - s is a string''' + m should be a buffer, a memoryview or a byte string. + s is a byte string''' def advance(i, c): - while i < lenm and m[i] != c: + while i < lenm and m[i:i + 1] != c: i += 1 return i if not s: @@ -646,10 +664,10 @@ while lo < hi: mid = (lo + hi) // 2 start = mid - while start > 0 and m[start - 1] != '\n': + while start > 0 and m[start - 1:start] != '\n': start -= 1 end = advance(start, '\0') - if m[start:end] < s: + if bytes(m[start:end]) < s: # we know that after the null there are 40 bytes of sha1 # this translates to the bisect lo = mid + 1 lo = advance(end + 40, '\n') + 1 @@ -679,12 +697,12 @@ # for large addlist arrays, building a new array is cheaper # than repeatedly modifying the existing one currentposition = 0 - newaddlist = array.array('c') + newaddlist = bytearray() for start, end, content in x: newaddlist += addlist[currentposition:start] if content: - newaddlist += array.array('c', content) + newaddlist += bytearray(content) currentposition = end @@ -906,8 +924,13 @@ copy._copyfunc = self._copyfunc return copy - def filesnotin(self, m2): + def filesnotin(self, m2, match=None): '''Set of files in this manifest that are not in the other''' + if match: + m1 = self.matches(match) + m2 = m2.matches(match) + return m1.filesnotin(m2) + files = set() def _filesnotin(t1, t2): if t1._node == t2._node and not t1._dirty and not t2._dirty: @@ -1025,7 +1048,7 @@ ret._dirty = True return ret - def diff(self, m2, clean=False): + def diff(self, m2, match=None, clean=False): '''Finds changes between the current manifest and m2. Args: @@ -1040,6 +1063,10 @@ the nodeid will be None and the flags will be the empty string. ''' + if match: + m1 = self.matches(match) + m2 = m2.matches(match) + return m1.diff(m2, clean=clean) result = {} emptytree = treemanifest() def _diff(t1, t2): @@ -1128,11 +1155,32 @@ subp1, subp2 = subp2, subp1 writesubtree(subm, subp1, subp2) + def walksubtrees(self, matcher=None): + """Returns an iterator of the subtrees of this manifest, including this + manifest itself. + + If `matcher` is provided, it only returns subtrees that match. + """ + if matcher and not matcher.visitdir(self._dir[:-1] or '.'): + return + if not matcher or matcher(self._dir[:-1]): + yield self + + self._load() + for d, subm in self._dirs.iteritems(): + for subtree in subm.walksubtrees(matcher=matcher): + yield subtree + class manifestrevlog(revlog.revlog): '''A revlog that stores manifest texts. This is responsible for caching the full-text manifest contents. ''' - def __init__(self, opener, dir='', dirlogcache=None): + def __init__(self, opener, dir='', dirlogcache=None, indexfile=None): + """Constructs a new manifest revlog + + `indexfile` - used by extensions to have two manifests at once, like + when transitioning between flatmanifeset and treemanifests. + """ # During normal operations, we expect to deal with not more than four # revs at a time (such as during commit --amend). When rebasing large # stacks of commits, the number can go up, hence the config knob below. @@ -1150,12 +1198,16 @@ self._fulltextcache = util.lrucachedict(cachesize) - indexfile = "00manifest.i" if dir: assert self._treeondisk, 'opts is %r' % opts if not dir.endswith('/'): dir = dir + '/' - indexfile = "meta/" + dir + "00manifest.i" + + if indexfile is None: + indexfile = '00manifest.i' + if dir: + indexfile = "meta/" + dir + indexfile + self._dir = dir # The dirlogcache is kept on the root manifest log if dir: @@ -1214,7 +1266,7 @@ else: text = m.text(self._usemanifestv2) n = self.addrevision(text, transaction, link, p1, p2) - arraytext = array.array('c', text) + arraytext = bytearray(text) if arraytext is not None: self.fulltextcache[n] = arraytext @@ -1224,7 +1276,7 @@ def _addtree(self, m, transaction, link, m1, m2, readtree): # If the manifest is unchanged compared to one parent, # don't write a new revision - if m.unmodifiedsince(m1) or m.unmodifiedsince(m2): + if self._dir != '' and (m.unmodifiedsince(m1) or m.unmodifiedsince(m2)): return m.node() def writesubtree(subm, subp1, subp2): sublog = self.dirlog(subm.dir()) @@ -1232,13 +1284,17 @@ readtree=readtree) m.writesubtrees(m1, m2, writesubtree) text = m.dirtext(self._usemanifestv2) - # Double-check whether contents are unchanged to one parent - if text == m1.dirtext(self._usemanifestv2): - n = m1.node() - elif text == m2.dirtext(self._usemanifestv2): - n = m2.node() - else: + n = None + if self._dir != '': + # Double-check whether contents are unchanged to one parent + if text == m1.dirtext(self._usemanifestv2): + n = m1.node() + elif text == m2.dirtext(self._usemanifestv2): + n = m2.node() + + if not n: n = self.addrevision(text, transaction, link, m1.node(), m2.node()) + # Save nodeid so parent manifest can calculate its nodeid m.setnode(n) return n @@ -1252,8 +1308,6 @@ class do not care about the implementation details of the actual manifests they receive (i.e. tree or flat or lazily loaded, etc).""" def __init__(self, opener, repo): - self._repo = repo - usetreemanifest = False cachesize = 4 @@ -1300,7 +1354,7 @@ if node not in dirlog.nodemap: raise LookupError(node, dirlog.indexfile, _('no node')) - m = treemanifestctx(self._repo, dir, node) + m = treemanifestctx(self, dir, node) else: raise error.Abort( _("cannot ask for manifest directory '%s' in a flat " @@ -1311,9 +1365,9 @@ raise LookupError(node, self._revlog.indexfile, _('no node')) if self._treeinmem: - m = treemanifestctx(self._repo, '', node) + m = treemanifestctx(self, '', node) else: - m = manifestctx(self._repo, node) + m = manifestctx(self, node) if node != revlog.nullid: mancache = self._dirmancache.get(dir) @@ -1328,18 +1382,18 @@ self._revlog.clearcaches() class memmanifestctx(object): - def __init__(self, repo): - self._repo = repo + def __init__(self, manifestlog): + self._manifestlog = manifestlog self._manifestdict = manifestdict() def _revlog(self): - return self._repo.manifestlog._revlog + return self._manifestlog._revlog def new(self): - return memmanifestctx(self._repo) + return memmanifestctx(self._manifestlog) def copy(self): - memmf = memmanifestctx(self._repo) + memmf = memmanifestctx(self._manifestlog) memmf._manifestdict = self.read().copy() return memmf @@ -1354,8 +1408,8 @@ """A class representing a single revision of a manifest, including its contents, its parent revs, and its linkrev. """ - def __init__(self, repo, node): - self._repo = repo + def __init__(self, manifestlog, node): + self._manifestlog = manifestlog self._data = None self._node = node @@ -1368,16 +1422,16 @@ #self.linkrev = revlog.linkrev(rev) def _revlog(self): - return self._repo.manifestlog._revlog + return self._manifestlog._revlog def node(self): return self._node def new(self): - return memmanifestctx(self._repo) + return memmanifestctx(self._manifestlog) def copy(self): - memmf = memmanifestctx(self._repo) + memmf = memmanifestctx(self._manifestlog) memmf._manifestdict = self.read().copy() return memmf @@ -1386,13 +1440,13 @@ return self._revlog().parents(self._node) def read(self): - if not self._data: + if self._data is None: if self._node == revlog.nullid: self._data = manifestdict() else: rl = self._revlog() text = rl.revision(self._node) - arraytext = array.array('c', text) + arraytext = bytearray(text) rl._fulltextcache[self._node] = arraytext self._data = manifestdict(text) return self._data @@ -1422,7 +1476,7 @@ if revlog._usemanifestv2: # Need to perform a slow delta r0 = revlog.deltaparent(revlog.rev(self._node)) - m0 = self._repo.manifestlog[revlog.node(r0)].read() + m0 = self._manifestlog[revlog.node(r0)].read() m1 = self.read() md = manifestdict() for f, ((n0, fl0), (n1, fl1)) in m0.diff(m1).iteritems(): @@ -1440,19 +1494,19 @@ return self.read().find(key) class memtreemanifestctx(object): - def __init__(self, repo, dir=''): - self._repo = repo + def __init__(self, manifestlog, dir=''): + self._manifestlog = manifestlog self._dir = dir self._treemanifest = treemanifest() def _revlog(self): - return self._repo.manifestlog._revlog + return self._manifestlog._revlog def new(self, dir=''): - return memtreemanifestctx(self._repo, dir=dir) + return memtreemanifestctx(self._manifestlog, dir=dir) def copy(self): - memmf = memtreemanifestctx(self._repo, dir=self._dir) + memmf = memtreemanifestctx(self._manifestlog, dir=self._dir) memmf._treemanifest = self._treemanifest.copy() return memmf @@ -1461,13 +1515,13 @@ def write(self, transaction, link, p1, p2, added, removed): def readtree(dir, node): - return self._repo.manifestlog.get(dir, node).read() + return self._manifestlog.get(dir, node).read() return self._revlog().add(self._treemanifest, transaction, link, p1, p2, added, removed, readtree=readtree) class treemanifestctx(object): - def __init__(self, repo, dir, node): - self._repo = repo + def __init__(self, manifestlog, dir, node): + self._manifestlog = manifestlog self._dir = dir self._data = None @@ -1481,10 +1535,10 @@ #self.linkrev = revlog.linkrev(rev) def _revlog(self): - return self._repo.manifestlog._revlog.dirlog(self._dir) + return self._manifestlog._revlog.dirlog(self._dir) def read(self): - if not self._data: + if self._data is None: rl = self._revlog() if self._node == revlog.nullid: self._data = treemanifest() @@ -1495,14 +1549,13 @@ def readsubtree(dir, subm): # Set verify to False since we need to be able to create # subtrees for trees that don't exist on disk. - return self._repo.manifestlog.get(dir, subm, - verify=False).read() + return self._manifestlog.get(dir, subm, verify=False).read() m.read(gettext, readsubtree) m.setnode(self._node) self._data = m else: text = rl.revision(self._node) - arraytext = array.array('c', text) + arraytext = bytearray(text) rl.fulltextcache[self._node] = arraytext self._data = treemanifest(dir=self._dir, text=text) @@ -1512,10 +1565,10 @@ return self._node def new(self, dir=''): - return memtreemanifestctx(self._repo, dir=dir) + return memtreemanifestctx(self._manifestlog, dir=dir) def copy(self): - memmf = memtreemanifestctx(self._repo, dir=self._dir) + memmf = memtreemanifestctx(self._manifestlog, dir=self._dir) memmf._treemanifest = self.read().copy() return memmf @@ -1542,7 +1595,7 @@ else: # Need to perform a slow delta r0 = revlog.deltaparent(revlog.rev(self._node)) - m0 = self._repo.manifestlog.get(self._dir, revlog.node(r0)).read() + m0 = self._manifestlog.get(self._dir, revlog.node(r0)).read() m1 = self.read() md = treemanifest(dir=self._dir) for f, ((n0, fl0), (n1, fl1)) in m0.diff(m1).iteritems():
--- a/mercurial/match.py Tue Apr 18 11:22:42 2017 -0400 +++ b/mercurial/match.py Tue Apr 18 12:24:34 2017 -0400 @@ -85,7 +85,7 @@ return True class match(object): - def __init__(self, root, cwd, patterns, include=[], exclude=[], + def __init__(self, root, cwd, patterns, include=None, exclude=None, default='glob', exact=False, auditor=None, ctx=None, listsubrepos=False, warn=None, badfn=None): """build an object to match a set of file patterns @@ -104,7 +104,10 @@ a pattern is one of: 'glob:<glob>' - a glob relative to cwd 're:<regexp>' - a regular expression - 'path:<path>' - a path relative to repository root + 'path:<path>' - a path relative to repository root, which is matched + recursively + 'rootfilesin:<path>' - a path relative to repository root, which is + matched non-recursively (will not match subdirectories) 'relglob:<glob>' - an unrooted glob (*.c matches C files in all dirs) 'relpath:<path>' - a path relative to cwd 'relre:<regexp>' - a regexp that needn't match the start of a name @@ -114,6 +117,10 @@ the same directory '<something>' - a pattern of the specified default type """ + if include is None: + include = [] + if exclude is None: + exclude = [] self._root = root self._cwd = cwd @@ -122,9 +129,12 @@ self._always = False self._pathrestricted = bool(include or exclude or patterns) self._warn = warn + + # roots are directories which are recursively included/excluded. self._includeroots = set() + self._excluderoots = set() + # dirs are directories which are non-recursively included. self._includedirs = set(['.']) - self._excluderoots = set() if badfn is not None: self.bad = badfn @@ -134,14 +144,20 @@ kindpats = self._normalize(include, 'glob', root, cwd, auditor) self.includepat, im = _buildmatch(ctx, kindpats, '(?:/|$)', listsubrepos, root) - self._includeroots.update(_roots(kindpats)) - self._includedirs.update(util.dirs(self._includeroots)) + roots, dirs = _rootsanddirs(kindpats) + self._includeroots.update(roots) + self._includedirs.update(dirs) matchfns.append(im) if exclude: kindpats = self._normalize(exclude, 'glob', root, cwd, auditor) self.excludepat, em = _buildmatch(ctx, kindpats, '(?:/|$)', listsubrepos, root) if not _anypats(kindpats): + # Only consider recursive excludes as such - if a non-recursive + # exclude is used, we must still recurse into the excluded + # directory, at least to find subdirectories. In such a case, + # the regex still won't match the non-recursively-excluded + # files. self._excluderoots.update(_roots(kindpats)) matchfns.append(lambda f: not em(f)) if exact: @@ -153,7 +169,7 @@ elif patterns: kindpats = self._normalize(patterns, default, root, cwd, auditor) if not _kindpatsalwaysmatch(kindpats): - self._files = _roots(kindpats) + self._files = _explicitfiles(kindpats) self._anypats = self._anypats or _anypats(kindpats) self.patternspat, pm = _buildmatch(ctx, kindpats, '$', listsubrepos, root) @@ -238,7 +254,7 @@ return 'all' if dir in self._excluderoots: