annotate mercurial/keepalive.py @ 4072:e916bc0dfdd6

transplant: remote bundle source was not closed before deleting the fetched bundle. It fails under win32 because "normal" opened files cannot be removed.
author Patrick Mezard <pmezard@gmail.com>
date Sun, 11 Feb 2007 18:37:23 +0100
parents 8520a773a141
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
2435
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
1 # This library is free software; you can redistribute it and/or
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
2 # modify it under the terms of the GNU Lesser General Public
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
3 # License as published by the Free Software Foundation; either
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
4 # version 2.1 of the License, or (at your option) any later version.
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
5 #
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
6 # This library is distributed in the hope that it will be useful,
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
7 # but WITHOUT ANY WARRANTY; without even the implied warranty of
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
8 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
9 # Lesser General Public License for more details.
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
10 #
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
11 # You should have received a copy of the GNU Lesser General Public
2600
c4325f0a9b91 clean up trailing white space.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents: 2444
diff changeset
12 # License along with this library; if not, write to the
c4325f0a9b91 clean up trailing white space.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents: 2444
diff changeset
13 # Free Software Foundation, Inc.,
c4325f0a9b91 clean up trailing white space.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents: 2444
diff changeset
14 # 59 Temple Place, Suite 330,
2435
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
15 # Boston, MA 02111-1307 USA
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
16
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
17 # This file is part of urlgrabber, a high-level cross-protocol url-grabber
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
18 # Copyright 2002-2004 Michael D. Stenner, Ryan Tomayko
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
19
4026
8520a773a141 fix for digest auth when using keepalive.py
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 2600
diff changeset
20 # Modified by Benoit Boissinot:
8520a773a141 fix for digest auth when using keepalive.py
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 2600
diff changeset
21 # - fix for digest auth (inspired from urllib2.py @ Python v2.4)
8520a773a141 fix for digest auth when using keepalive.py
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 2600
diff changeset
22
2435
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
23 """An HTTP handler for urllib2 that supports HTTP 1.1 and keepalive.
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
24
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
25 >>> import urllib2
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
26 >>> from keepalive import HTTPHandler
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
27 >>> keepalive_handler = HTTPHandler()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
28 >>> opener = urllib2.build_opener(keepalive_handler)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
29 >>> urllib2.install_opener(opener)
2600
c4325f0a9b91 clean up trailing white space.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents: 2444
diff changeset
30 >>>
2435
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
31 >>> fo = urllib2.urlopen('http://www.python.org')
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
32
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
33 If a connection to a given host is requested, and all of the existing
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
34 connections are still in use, another connection will be opened. If
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
35 the handler tries to use an existing connection but it fails in some
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
36 way, it will be closed and removed from the pool.
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
37
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
38 To remove the handler, simply re-run build_opener with no arguments, and
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
39 install that opener.
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
40
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
41 You can explicitly close connections by using the close_connection()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
42 method of the returned file-like object (described below) or you can
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
43 use the handler methods:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
44
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
45 close_connection(host)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
46 close_all()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
47 open_connections()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
48
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
49 NOTE: using the close_connection and close_all methods of the handler
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
50 should be done with care when using multiple threads.
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
51 * there is nothing that prevents another thread from creating new
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
52 connections immediately after connections are closed
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
53 * no checks are done to prevent in-use connections from being closed
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
54
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
55 >>> keepalive_handler.close_all()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
56
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
57 EXTRA ATTRIBUTES AND METHODS
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
58
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
59 Upon a status of 200, the object returned has a few additional
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
60 attributes and methods, which should not be used if you want to
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
61 remain consistent with the normal urllib2-returned objects:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
62
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
63 close_connection() - close the connection to the host
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
64 readlines() - you know, readlines()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
65 status - the return status (ie 404)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
66 reason - english translation of status (ie 'File not found')
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
67
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
68 If you want the best of both worlds, use this inside an
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
69 AttributeError-catching try:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
70
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
71 >>> try: status = fo.status
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
72 >>> except AttributeError: status = None
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
73
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
74 Unfortunately, these are ONLY there if status == 200, so it's not
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
75 easy to distinguish between non-200 responses. The reason is that
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
76 urllib2 tries to do clever things with error codes 301, 302, 401,
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
77 and 407, and it wraps the object upon return.
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
78
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
79 For python versions earlier than 2.4, you can avoid this fancy error
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
80 handling by setting the module-level global HANDLE_ERRORS to zero.
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
81 You see, prior to 2.4, it's the HTTP Handler's job to determine what
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
82 to handle specially, and what to just pass up. HANDLE_ERRORS == 0
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
83 means "pass everything up". In python 2.4, however, this job no
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
84 longer belongs to the HTTP Handler and is now done by a NEW handler,
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
85 HTTPErrorProcessor. Here's the bottom line:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
86
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
87 python version < 2.4
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
88 HANDLE_ERRORS == 1 (default) pass up 200, treat the rest as
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
89 errors
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
90 HANDLE_ERRORS == 0 pass everything up, error processing is
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
91 left to the calling code
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
92 python version >= 2.4
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
93 HANDLE_ERRORS == 1 pass up 200, treat the rest as errors
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
94 HANDLE_ERRORS == 0 (default) pass everything up, let the
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
95 other handlers (specifically,
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
96 HTTPErrorProcessor) decide what to do
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
97
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
98 In practice, setting the variable either way makes little difference
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
99 in python 2.4, so for the most consistent behavior across versions,
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
100 you probably just want to use the defaults, which will give you
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
101 exceptions on errors.
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
102
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
103 """
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
104
2444
5eb02f9ed804 Update keepalive.py to current CVS version of urlgrabber.
Alexis S. L. Carvalho <alexis@cecm.usp.br>
parents: 2435
diff changeset
105 # $Id: keepalive.py,v 1.14 2006/04/04 21:00:32 mstenner Exp $
2435
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
106
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
107 import urllib2
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
108 import httplib
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
109 import socket
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
110 import thread
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
111
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
112 DEBUG = None
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
113
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
114 import sys
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
115 if sys.version_info < (2, 4): HANDLE_ERRORS = 1
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
116 else: HANDLE_ERRORS = 0
2600
c4325f0a9b91 clean up trailing white space.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents: 2444
diff changeset
117
2435
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
118 class ConnectionManager:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
119 """
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
120 The connection manager must be able to:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
121 * keep track of all existing
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
122 """
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
123 def __init__(self):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
124 self._lock = thread.allocate_lock()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
125 self._hostmap = {} # map hosts to a list of connections
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
126 self._connmap = {} # map connections to host
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
127 self._readymap = {} # map connection to ready state
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
128
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
129 def add(self, host, connection, ready):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
130 self._lock.acquire()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
131 try:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
132 if not self._hostmap.has_key(host): self._hostmap[host] = []
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
133 self._hostmap[host].append(connection)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
134 self._connmap[connection] = host
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
135 self._readymap[connection] = ready
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
136 finally:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
137 self._lock.release()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
138
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
139 def remove(self, connection):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
140 self._lock.acquire()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
141 try:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
142 try:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
143 host = self._connmap[connection]
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
144 except KeyError:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
145 pass
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
146 else:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
147 del self._connmap[connection]
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
148 del self._readymap[connection]
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
149 self._hostmap[host].remove(connection)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
150 if not self._hostmap[host]: del self._hostmap[host]
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
151 finally:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
152 self._lock.release()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
153
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
154 def set_ready(self, connection, ready):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
155 try: self._readymap[connection] = ready
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
156 except KeyError: pass
2600
c4325f0a9b91 clean up trailing white space.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents: 2444
diff changeset
157
2435
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
158 def get_ready_conn(self, host):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
159 conn = None
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
160 self._lock.acquire()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
161 try:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
162 if self._hostmap.has_key(host):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
163 for c in self._hostmap[host]:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
164 if self._readymap[c]:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
165 self._readymap[c] = 0
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
166 conn = c
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
167 break
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
168 finally:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
169 self._lock.release()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
170 return conn
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
171
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
172 def get_all(self, host=None):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
173 if host:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
174 return list(self._hostmap.get(host, []))
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
175 else:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
176 return dict(self._hostmap)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
177
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
178 class HTTPHandler(urllib2.HTTPHandler):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
179 def __init__(self):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
180 self._cm = ConnectionManager()
2600
c4325f0a9b91 clean up trailing white space.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents: 2444
diff changeset
181
2435
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
182 #### Connection Management
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
183 def open_connections(self):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
184 """return a list of connected hosts and the number of connections
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
185 to each. [('foo.com:80', 2), ('bar.org', 1)]"""
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
186 return [(host, len(li)) for (host, li) in self._cm.get_all().items()]
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
187
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
188 def close_connection(self, host):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
189 """close connection(s) to <host>
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
190 host is the host:port spec, as in 'www.cnn.com:8080' as passed in.
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
191 no error occurs if there is no connection to that host."""
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
192 for h in self._cm.get_all(host):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
193 self._cm.remove(h)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
194 h.close()
2600
c4325f0a9b91 clean up trailing white space.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents: 2444
diff changeset
195
2435
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
196 def close_all(self):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
197 """close all open connections"""
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
198 for host, conns in self._cm.get_all().items():
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
199 for h in conns:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
200 self._cm.remove(h)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
201 h.close()
2600
c4325f0a9b91 clean up trailing white space.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents: 2444
diff changeset
202
2435
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
203 def _request_closed(self, request, host, connection):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
204 """tells us that this request is now closed and the the
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
205 connection is ready for another request"""
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
206 self._cm.set_ready(connection, 1)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
207
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
208 def _remove_connection(self, host, connection, close=0):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
209 if close: connection.close()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
210 self._cm.remove(connection)
2600
c4325f0a9b91 clean up trailing white space.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents: 2444
diff changeset
211
2435
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
212 #### Transaction Execution
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
213 def http_open(self, req):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
214 return self.do_open(HTTPConnection, req)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
215
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
216 def do_open(self, http_class, req):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
217 host = req.get_host()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
218 if not host:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
219 raise urllib2.URLError('no host given')
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
220
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
221 try:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
222 h = self._cm.get_ready_conn(host)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
223 while h:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
224 r = self._reuse_connection(h, req, host)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
225
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
226 # if this response is non-None, then it worked and we're
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
227 # done. Break out, skipping the else block.
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
228 if r: break
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
229
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
230 # connection is bad - possibly closed by server
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
231 # discard it and ask for the next free connection
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
232 h.close()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
233 self._cm.remove(h)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
234 h = self._cm.get_ready_conn(host)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
235 else:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
236 # no (working) free connections were found. Create a new one.
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
237 h = http_class(host)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
238 if DEBUG: DEBUG.info("creating new connection to %s (%d)",
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
239 host, id(h))
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
240 self._cm.add(host, h, 0)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
241 self._start_transaction(h, req)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
242 r = h.getresponse()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
243 except (socket.error, httplib.HTTPException), err:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
244 raise urllib2.URLError(err)
2600
c4325f0a9b91 clean up trailing white space.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents: 2444
diff changeset
245
2435
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
246 # if not a persistent connection, don't try to reuse it
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
247 if r.will_close: self._cm.remove(h)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
248
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
249 if DEBUG: DEBUG.info("STATUS: %s, %s", r.status, r.reason)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
250 r._handler = self
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
251 r._host = host
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
252 r._url = req.get_full_url()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
253 r._connection = h
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
254 r.code = r.status
2444
5eb02f9ed804 Update keepalive.py to current CVS version of urlgrabber.
Alexis S. L. Carvalho <alexis@cecm.usp.br>
parents: 2435
diff changeset
255 r.headers = r.msg
5eb02f9ed804 Update keepalive.py to current CVS version of urlgrabber.
Alexis S. L. Carvalho <alexis@cecm.usp.br>
parents: 2435
diff changeset
256 r.msg = r.reason
2600
c4325f0a9b91 clean up trailing white space.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents: 2444
diff changeset
257
2435
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
258 if r.status == 200 or not HANDLE_ERRORS:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
259 return r
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
260 else:
2444
5eb02f9ed804 Update keepalive.py to current CVS version of urlgrabber.
Alexis S. L. Carvalho <alexis@cecm.usp.br>
parents: 2435
diff changeset
261 return self.parent.error('http', req, r,
5eb02f9ed804 Update keepalive.py to current CVS version of urlgrabber.
Alexis S. L. Carvalho <alexis@cecm.usp.br>
parents: 2435
diff changeset
262 r.status, r.msg, r.headers)
2435
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
263
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
264 def _reuse_connection(self, h, req, host):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
265 """start the transaction with a re-used connection
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
266 return a response object (r) upon success or None on failure.
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
267 This DOES not close or remove bad connections in cases where
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
268 it returns. However, if an unexpected exception occurs, it
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
269 will close and remove the connection before re-raising.
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
270 """
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
271 try:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
272 self._start_transaction(h, req)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
273 r = h.getresponse()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
274 # note: just because we got something back doesn't mean it
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
275 # worked. We'll check the version below, too.
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
276 except (socket.error, httplib.HTTPException):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
277 r = None
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
278 except:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
279 # adding this block just in case we've missed
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
280 # something we will still raise the exception, but
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
281 # lets try and close the connection and remove it
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
282 # first. We previously got into a nasty loop
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
283 # where an exception was uncaught, and so the
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
284 # connection stayed open. On the next try, the
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
285 # same exception was raised, etc. The tradeoff is
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
286 # that it's now possible this call will raise
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
287 # a DIFFERENT exception
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
288 if DEBUG: DEBUG.error("unexpected exception - closing " + \
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
289 "connection to %s (%d)", host, id(h))
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
290 self._cm.remove(h)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
291 h.close()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
292 raise
2600
c4325f0a9b91 clean up trailing white space.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents: 2444
diff changeset
293
2435
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
294 if r is None or r.version == 9:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
295 # httplib falls back to assuming HTTP 0.9 if it gets a
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
296 # bad header back. This is most likely to happen if
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
297 # the socket has been closed by the server since we
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
298 # last used the connection.
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
299 if DEBUG: DEBUG.info("failed to re-use connection to %s (%d)",
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
300 host, id(h))
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
301 r = None
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
302 else:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
303 if DEBUG: DEBUG.info("re-using connection to %s (%d)", host, id(h))
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
304
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
305 return r
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
306
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
307 def _start_transaction(self, h, req):
4026
8520a773a141 fix for digest auth when using keepalive.py
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 2600
diff changeset
308 headers = req.headers.copy()
8520a773a141 fix for digest auth when using keepalive.py
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 2600
diff changeset
309 body = req.data
8520a773a141 fix for digest auth when using keepalive.py
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 2600
diff changeset
310 if sys.version_info >= (2, 4):
8520a773a141 fix for digest auth when using keepalive.py
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 2600
diff changeset
311 headers.update(req.unredirected_hdrs)
2435
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
312 try:
4026
8520a773a141 fix for digest auth when using keepalive.py
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 2600
diff changeset
313 h.request(req.get_method(), req.get_selector(), body, headers)
8520a773a141 fix for digest auth when using keepalive.py
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 2600
diff changeset
314 except socket.error, err: # XXX what error?
2435
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
315 raise urllib2.URLError(err)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
316
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
317 class HTTPResponse(httplib.HTTPResponse):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
318 # we need to subclass HTTPResponse in order to
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
319 # 1) add readline() and readlines() methods
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
320 # 2) add close_connection() methods
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
321 # 3) add info() and geturl() methods
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
322
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
323 # in order to add readline(), read must be modified to deal with a
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
324 # buffer. example: readline must read a buffer and then spit back
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
325 # one line at a time. The only real alternative is to read one
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
326 # BYTE at a time (ick). Once something has been read, it can't be
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
327 # put back (ok, maybe it can, but that's even uglier than this),
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
328 # so if you THEN do a normal read, you must first take stuff from
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
329 # the buffer.
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
330
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
331 # the read method wraps the original to accomodate buffering,
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
332 # although read() never adds to the buffer.
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
333 # Both readline and readlines have been stolen with almost no
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
334 # modification from socket.py
2600
c4325f0a9b91 clean up trailing white space.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents: 2444
diff changeset
335
2435
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
336
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
337 def __init__(self, sock, debuglevel=0, strict=0, method=None):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
338 if method: # the httplib in python 2.3 uses the method arg
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
339 httplib.HTTPResponse.__init__(self, sock, debuglevel, method)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
340 else: # 2.2 doesn't
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
341 httplib.HTTPResponse.__init__(self, sock, debuglevel)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
342 self.fileno = sock.fileno
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
343 self.code = None
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
344 self._rbuf = ''
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
345 self._rbufsize = 8096
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
346 self._handler = None # inserted by the handler later
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
347 self._host = None # (same)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
348 self._url = None # (same)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
349 self._connection = None # (same)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
350
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
351 _raw_read = httplib.HTTPResponse.read
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
352
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
353 def close(self):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
354 if self.fp:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
355 self.fp.close()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
356 self.fp = None
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
357 if self._handler:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
358 self._handler._request_closed(self, self._host,
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
359 self._connection)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
360
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
361 def close_connection(self):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
362 self._handler._remove_connection(self._host, self._connection, close=1)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
363 self.close()
2600
c4325f0a9b91 clean up trailing white space.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents: 2444
diff changeset
364
2435
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
365 def info(self):
2444
5eb02f9ed804 Update keepalive.py to current CVS version of urlgrabber.
Alexis S. L. Carvalho <alexis@cecm.usp.br>
parents: 2435
diff changeset
366 return self.headers
2435
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
367
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
368 def geturl(self):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
369 return self._url
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
370
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
371 def read(self, amt=None):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
372 # the _rbuf test is only in this first if for speed. It's not
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
373 # logically necessary
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
374 if self._rbuf and not amt is None:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
375 L = len(self._rbuf)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
376 if amt > L:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
377 amt -= L
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
378 else:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
379 s = self._rbuf[:amt]
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
380 self._rbuf = self._rbuf[amt:]
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
381 return s
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
382
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
383 s = self._rbuf + self._raw_read(amt)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
384 self._rbuf = ''
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
385 return s
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
386
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
387 def readline(self, limit=-1):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
388 data = ""
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
389 i = self._rbuf.find('\n')
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
390 while i < 0 and not (0 < limit <= len(self._rbuf)):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
391 new = self._raw_read(self._rbufsize)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
392 if not new: break
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
393 i = new.find('\n')
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
394 if i >= 0: i = i + len(self._rbuf)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
395 self._rbuf = self._rbuf + new
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
396 if i < 0: i = len(self._rbuf)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
397 else: i = i+1
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
398 if 0 <= limit < len(self._rbuf): i = limit
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
399 data, self._rbuf = self._rbuf[:i], self._rbuf[i:]
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
400 return data
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
401
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
402 def readlines(self, sizehint = 0):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
403 total = 0
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
404 list = []
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
405 while 1:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
406 line = self.readline()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
407 if not line: break
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
408 list.append(line)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
409 total += len(line)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
410 if sizehint and total >= sizehint:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
411 break
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
412 return list
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
413
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
414
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
415 class HTTPConnection(httplib.HTTPConnection):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
416 # use the modified response class
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
417 response_class = HTTPResponse
2600
c4325f0a9b91 clean up trailing white space.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents: 2444
diff changeset
418
2435
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
419 #########################################################################
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
420 ##### TEST FUNCTIONS
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
421 #########################################################################
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
422
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
423 def error_handler(url):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
424 global HANDLE_ERRORS
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
425 orig = HANDLE_ERRORS
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
426 keepalive_handler = HTTPHandler()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
427 opener = urllib2.build_opener(keepalive_handler)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
428 urllib2.install_opener(opener)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
429 pos = {0: 'off', 1: 'on'}
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
430 for i in (0, 1):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
431 print " fancy error handling %s (HANDLE_ERRORS = %i)" % (pos[i], i)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
432 HANDLE_ERRORS = i
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
433 try:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
434 fo = urllib2.urlopen(url)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
435 foo = fo.read()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
436 fo.close()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
437 try: status, reason = fo.status, fo.reason
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
438 except AttributeError: status, reason = None, None
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
439 except IOError, e:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
440 print " EXCEPTION: %s" % e
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
441 raise
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
442 else:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
443 print " status = %s, reason = %s" % (status, reason)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
444 HANDLE_ERRORS = orig
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
445 hosts = keepalive_handler.open_connections()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
446 print "open connections:", hosts
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
447 keepalive_handler.close_all()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
448
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
449 def continuity(url):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
450 import md5
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
451 format = '%25s: %s'
2600
c4325f0a9b91 clean up trailing white space.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents: 2444
diff changeset
452
2435
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
453 # first fetch the file with the normal http handler
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
454 opener = urllib2.build_opener()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
455 urllib2.install_opener(opener)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
456 fo = urllib2.urlopen(url)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
457 foo = fo.read()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
458 fo.close()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
459 m = md5.new(foo)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
460 print format % ('normal urllib', m.hexdigest())
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
461
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
462 # now install the keepalive handler and try again
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
463 opener = urllib2.build_opener(HTTPHandler())
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
464 urllib2.install_opener(opener)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
465
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
466 fo = urllib2.urlopen(url)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
467 foo = fo.read()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
468 fo.close()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
469 m = md5.new(foo)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
470 print format % ('keepalive read', m.hexdigest())
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
471
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
472 fo = urllib2.urlopen(url)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
473 foo = ''
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
474 while 1:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
475 f = fo.readline()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
476 if f: foo = foo + f
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
477 else: break
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
478 fo.close()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
479 m = md5.new(foo)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
480 print format % ('keepalive readline', m.hexdigest())
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
481
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
482 def comp(N, url):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
483 print ' making %i connections to:\n %s' % (N, url)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
484
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
485 sys.stdout.write(' first using the normal urllib handlers')
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
486 # first use normal opener
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
487 opener = urllib2.build_opener()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
488 urllib2.install_opener(opener)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
489 t1 = fetch(N, url)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
490 print ' TIME: %.3f s' % t1
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
491
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
492 sys.stdout.write(' now using the keepalive handler ')
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
493 # now install the keepalive handler and try again
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
494 opener = urllib2.build_opener(HTTPHandler())
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
495 urllib2.install_opener(opener)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
496 t2 = fetch(N, url)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
497 print ' TIME: %.3f s' % t2
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
498 print ' improvement factor: %.2f' % (t1/t2, )
2600
c4325f0a9b91 clean up trailing white space.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents: 2444
diff changeset
499
2435
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
500 def fetch(N, url, delay=0):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
501 import time
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
502 lens = []
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
503 starttime = time.time()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
504 for i in range(N):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
505 if delay and i > 0: time.sleep(delay)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
506 fo = urllib2.urlopen(url)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
507 foo = fo.read()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
508 fo.close()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
509 lens.append(len(foo))
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
510 diff = time.time() - starttime
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
511
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
512 j = 0
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
513 for i in lens[1:]:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
514 j = j + 1
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
515 if not i == lens[0]:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
516 print "WARNING: inconsistent length on read %i: %i" % (j, i)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
517
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
518 return diff
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
519
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
520 def test_timeout(url):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
521 global DEBUG
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
522 dbbackup = DEBUG
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
523 class FakeLogger:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
524 def debug(self, msg, *args): print msg % args
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
525 info = warning = error = debug
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
526 DEBUG = FakeLogger()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
527 print " fetching the file to establish a connection"
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
528 fo = urllib2.urlopen(url)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
529 data1 = fo.read()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
530 fo.close()
2600
c4325f0a9b91 clean up trailing white space.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents: 2444
diff changeset
531
2435
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
532 i = 20
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
533 print " waiting %i seconds for the server to close the connection" % i
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
534 while i > 0:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
535 sys.stdout.write('\r %2i' % i)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
536 sys.stdout.flush()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
537 time.sleep(1)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
538 i -= 1
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
539 sys.stderr.write('\r')
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
540
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
541 print " fetching the file a second time"
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
542 fo = urllib2.urlopen(url)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
543 data2 = fo.read()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
544 fo.close()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
545
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
546 if data1 == data2:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
547 print ' data are identical'
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
548 else:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
549 print ' ERROR: DATA DIFFER'
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
550
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
551 DEBUG = dbbackup
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
552
2600
c4325f0a9b91 clean up trailing white space.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents: 2444
diff changeset
553
2435
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
554 def test(url, N=10):
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
555 print "checking error hander (do this on a non-200)"
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
556 try: error_handler(url)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
557 except IOError, e:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
558 print "exiting - exception will prevent further tests"
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
559 sys.exit()
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
560 print
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
561 print "performing continuity test (making sure stuff isn't corrupted)"
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
562 continuity(url)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
563 print
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
564 print "performing speed comparison"
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
565 comp(N, url)
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
566 print
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
567 print "performing dropped-connection check"
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
568 test_timeout(url)
2600
c4325f0a9b91 clean up trailing white space.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents: 2444
diff changeset
569
2435
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
570 if __name__ == '__main__':
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
571 import time
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
572 import sys
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
573 try:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
574 N = int(sys.argv[1])
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
575 url = sys.argv[2]
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
576 except:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
577 print "%s <integer> <url>" % sys.argv[0]
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
578 else:
ff2bac730b99 http client: support persistent connections.
Vadim Gelfer <vadim.gelfer@gmail.com>
parents:
diff changeset
579 test(url, N)