Mercurial > hg > pyhgsh
view contrib/convert-repo @ 1187:120aa5fc7ced
From mercurial-bounces@selenic.com Thu Sep 1 07:01:32 2005
Return-Path: <mercurial-bounces@selenic.com>
X-Original-To: bos@serpentine.com
Delivered-To: bos@serpentine.com
Received: from waste.org (waste.org [216.27.176.166]) by
demesne.serpentine.com (Postfix) with ESMTP id 3616A20B571 for
<bos@serpentine.com>; Thu, 1 Sep 2005 07:01:32 -0700 (PDT)
Received: from waste.org (localhost [127.0.0.1]) by waste.org
(8.13.4/8.13.4/Debian-3) with ESMTP id j81DxodQ028829; Thu, 1 Sep 2005
08:59:51 -0500
Received: from web32904.mail.mud.yahoo.com (web32904.mail.mud.yahoo.com
[68.142.206.51]) by waste.org (8.13.4/8.13.4/Debian-3) with SMTP id
j81DxnNA028824 for <mercurial@selenic.com>; Thu, 1 Sep 2005 08:59:49 -0500
Received: (qmail 25859 invoked by uid 60001); 1 Sep 2005 13:59:17 -0000
DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com;
h=Message-ID:Received:Date:From:Subject:To:In-Reply-To:MIME-Version:Content-Type:Content-Transfer-Encoding;
b=O6sELrlCknW3M/gKVqijWs82e/CbDEum1sEitcuLKXaP9dHU175PszOqMgcSKykMY+BVXtcH3NeaXLM3FyBmqNkoPAvesezyFbgQsHSM1S028oOexybCKMvtGQJmz66hzd1fDb0QoPj1gCcGU2VDevQaOesSmo1xF9jJwy2LlLE=
;
Message-ID: <20050901135917.25856.qmail@web32904.mail.mud.yahoo.com>
Received: from [60.48.222.94] by web32904.mail.mud.yahoo.com via HTTP; Thu,
01 Sep 2005 06:59:17 PDT
Date: Thu, 1 Sep 2005 06:59:17 -0700 (PDT)
From: TK Soh <teekaysoh@yahoo.com>
To: mercurial@selenic.com
In-Reply-To: <20050828075808.GO27787@waste.org>
MIME-Version: 1.0
Content-Type: text/plain; charset=iso-8859-1
X-Virus-Scanned: by amavisd-new
Subject: Re: add -p to hg tip
X-BeenThere: mercurial@selenic.com
X-Mailman-Version: 2.1.5
Precedence: list
List-Id: mercurial.selenic.com
List-Unsubscribe: <http://selenic.com/mailman/listinfo/mercurial>,
<mailto:mercurial-request@selenic.com?subject=unsubscribe>
List-Archive: <http://www.selenic.com/pipermail/mercurial>
List-Post: <mailto:mercurial@selenic.com>
List-Help: <mailto:mercurial-request@selenic.com?subject=help>
List-Subscribe: <http://selenic.com/mailman/listinfo/mercurial>,
<mailto:mercurial-request@selenic.com?subject=subscribe>
Sender: mercurial-bounces@selenic.com
Errors-To: mercurial-bounces@selenic.com
X-Spam-Checker-Version: SpamAssassin 3.0.4 (2005-06-05) on
demesne.serpentine.com
X-Spam-Level:
X-Spam-Status: No, score=-1.6 required=5.0 tests=AWL,BAYES_00 autolearn=ham
version=3.0.4
X-Evolution-Source: imap://bos@www.serpentine.com/
Content-Transfer-Encoding: 8bit
author | bos@serpentine.internal.keyresearch.com |
---|---|
date | Thu, 01 Sep 2005 07:47:26 -0700 |
parents | 574869103985 |
children | 227cfbe34109 |
line wrap: on
line source
#!/usr/bin/env python # # This is a generalized framework for converting between SCM # repository formats. # # In its current form, it's hardcoded to convert incrementally between # git and Mercurial. # # To use, you must first import the first git version into Mercurial, # and establish a mapping between the git commit hash and the hash in # Mercurial for that version. This mapping is kept in a simple text # file with lines like so: # # <git hash> <mercurial hash> # # To convert the rest of the repo, run: # # convert-repo <git-dir> <hg-dir> <mapfile> # # This updates the mapfile on each commit copied, so it can be # interrupted and can be run repeatedly to copy new commits. import sys, os, zlib, sha, time from mercurial import hg, ui, util class convert_git: def __init__(self, path): self.path = path def getheads(self): h = file(self.path + "/.git/HEAD").read()[:-1] return [h] def catfile(self, rev, type): if rev == "0" * 40: raise IOError() path = os.getcwd() os.chdir(self.path) fh = os.popen("git-cat-file %s %s 2>/dev/null" % (type, rev)) os.chdir(path) return fh.read() def getfile(self, name, rev): return self.catfile(rev, "blob") def getchanges(self, version): path = os.getcwd() os.chdir(self.path) fh = os.popen("git-diff-tree --root -m -r %s" % (version)) os.chdir(path) changes = [] for l in fh: if "\t" not in l: continue m, f = l[:-1].split("\t") m = m.split() h = m[3] p = (m[1] == "100755") changes.append((f, h, p)) return changes def getcommit(self, version): c = self.catfile(version, "commit") # read the commit hash end = c.find("\n\n") message = c[end+2:] l = c[:end].splitlines() manifest = l[0].split()[1] parents = [] for e in l[1:]: n,v = e.split(" ", 1) if n == "author": p = v.split() date = " ".join(p[-2:]) author = " ".join(p[:-2]) if author[0] == "<": author = author[1:-1] if n == "committer": p = v.split() date = " ".join(p[-2:]) committer = " ".join(p[:-2]) if committer[0] == "<": committer = committer[1:-1] message += "\ncommitter: %s %s\n" % (committer, date) if n == "parent": parents.append(v) return (parents, author, date, message) def gettags(self): tags = {} for f in os.listdir(self.path + "/.git/refs/tags"): try: h = file(self.path + "/.git/refs/tags/" + f).read().strip() p, a, d, m = self.getcommit(h) if not p: p = [h] # git is ugly, don't blame me tags[f] = p[0] except: pass return tags class convert_mercurial: def __init__(self, path): self.path = path u = ui.ui() self.repo = hg.repository(u, path) def getheads(self): h = self.repo.changelog.heads() h = [ hg.hex(x) for x in h ] return h def putfile(self, f, e, data): self.repo.wfile(f, "w").write(data) if self.repo.dirstate.state(f) == '?': self.repo.dirstate.update([f], "a") util.set_exec(self.repo.wjoin(f), e) def delfile(self, f): try: os.unlink(self.repo.wjoin(f)) #self.repo.remove([f]) except: pass def putcommit(self, files, parents, author, dest, text): seen = {} pl = [] for p in parents: if p not in seen: pl.append(p) seen[p] = 1 parents = pl if len(parents) < 2: parents.append("0" * 40) if len(parents) < 2: parents.append("0" * 40) p2 = parents.pop(0) while parents: p1 = p2 p2 = parents.pop(0) self.repo.rawcommit(files, text, author, dest, hg.bin(p1), hg.bin(p2)) text = "(octopus merge fixup)\n" return hg.hex(self.repo.changelog.tip()) def puttags(self, tags): try: old = self.repo.wfile(".hgtags").read() oldlines = old.splitlines(1) oldlines.sort() except: oldlines = [] k = tags.keys() k.sort() newlines = [] for tag in k: newlines.append("%s %s\n" % (tags[tag], tag)) newlines.sort() if newlines != oldlines: print "updating tags" f = self.repo.wfile(".hgtags", "w") f.write("".join(newlines)) f.close() if not oldlines: self.repo.add([".hgtags"]) date = "%s 0" % time.mktime(time.gmtime()) self.repo.rawcommit([".hgtags"], "update tags", "convert-repo", date, self.repo.changelog.tip(), hg.nullid) class convert: def __init__(self, source, dest, mapfile): self.source = source self.dest = dest self.mapfile = mapfile self.commitcache = {} self.map = {} for l in file(self.mapfile): sv, dv = l[:-1].split() self.map[sv] = dv def walktree(self, heads): visit = heads known = {} parents = {} while visit: n = visit.pop(0) if n in known or n in self.map: continue known[n] = 1 self.commitcache[n] = self.source.getcommit(n) cp = self.commitcache[n][0] for p in cp: parents.setdefault(n, []).append(p) visit.append(p) return parents def toposort(self, parents): visit = parents.keys() seen = {} children = {} while visit: n = visit.pop(0) if n in seen: continue seen[n] = 1 pc = 0 if n in parents: for p in parents[n]: if p not in self.map: pc += 1 visit.append(p) children.setdefault(p, []).append(n) if not pc: root = n s = [] removed = {} visit = children.keys() while visit: n = visit.pop(0) if n in removed: continue dep = 0 if n in parents: for p in parents[n]: if p in self.map: continue if p not in removed: # we're still dependent visit.append(n) dep = 1 break if not dep: # all n's parents are in the list removed[n] = 1 s.append(n) if n in children: for c in children[n]: visit.insert(0, c) return s def copy(self, rev): p, a, d, t = self.commitcache[rev] files = self.source.getchanges(rev) for f,v,e in files: try: data = self.source.getfile(f, v) except IOError, inst: self.dest.delfile(f) else: self.dest.putfile(f, e, data) r = [self.map[v] for v in p] f = [f for f,v,e in files] self.map[rev] = self.dest.putcommit(f, r, a, d, t) file(self.mapfile, "a").write("%s %s\n" % (rev, self.map[rev])) def convert(self): heads = self.source.getheads() parents = self.walktree(heads) t = self.toposort(parents) num = len(t) for c in t: num -= 1 if c in self.map: continue desc = self.commitcache[c][3].splitlines()[0] print num, desc self.copy(c) tags = self.source.gettags() ctags = {} for k in tags: v = tags[k] if v in self.map: ctags[k] = self.map[v] self.dest.puttags(ctags) gitpath, hgpath, mapfile = sys.argv[1:] c = convert(convert_git(gitpath), convert_mercurial(hgpath), mapfile) c.convert()