1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
|
# Copyright (C) 2005, 2006 Canonical Ltd
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
import errno
import urllib, urllib2
import errno
from StringIO import StringIO
import bzrlib # for the version
from bzrlib.errors import (TransportNotPossible, NoSuchFile, BzrError,
TransportError, ConnectionError)
from bzrlib.trace import mutter
from bzrlib.transport import register_urlparse_netloc_protocol
from bzrlib.transport.http import (HttpTransportBase, HttpServer,
extract_auth, response)
register_urlparse_netloc_protocol('http+urllib')
class Request(urllib2.Request):
"""Request object for urllib2 that allows the method to be overridden."""
method = None
def get_method(self):
if self.method is not None:
return self.method
else:
return urllib2.Request.get_method(self)
class HttpTransport_urllib(HttpTransportBase):
"""Python urllib transport for http and https."""
# TODO: Implement pipelined versions of all of the *_multi() functions.
def __init__(self, base, from_transport=None):
"""Set the base path where files will be stored."""
super(HttpTransport_urllib, self).__init__(base)
# HttpTransport_urllib doesn't maintain any per-transport state yet
# so nothing to do with from_transport
def _get(self, relpath, ranges, tail_amount=0):
path = relpath
try:
path = self._real_abspath(relpath)
resp = self._get_url_impl(path, method='GET', ranges=ranges,
tail_amount=tail_amount)
return resp.code, response.handle_response(path,
resp.code, resp.headers, resp)
except urllib2.HTTPError, e:
mutter('url error code: %s for has url: %r', e.code, path)
if e.code == 404:
raise NoSuchFile(path, extra=e)
raise
except (BzrError, IOError), e:
if getattr(e, 'errno', None) is not None:
mutter('io error: %s %s for has url: %r',
e.errno, errno.errorcode.get(e.errno), path)
if e.errno == errno.ENOENT:
raise NoSuchFile(path, extra=e)
raise ConnectionError(msg = "Error retrieving %s: %s"
% (self.abspath(relpath), str(e)),
orig_error=e)
def _get_url_impl(self, url, method, ranges, tail_amount=0):
"""Actually pass get request into urllib
:returns: urllib Response object
"""
manager = urllib2.HTTPPasswordMgrWithDefaultRealm()
url = extract_auth(url, manager)
auth_handler = urllib2.HTTPBasicAuthHandler(manager)
opener = urllib2.build_opener(auth_handler)
request = Request(url)
request.method = method
request.add_header('Pragma', 'no-cache')
request.add_header('Cache-control', 'max-age=0')
request.add_header('User-Agent',
'bzr/%s (urllib)' % (bzrlib.__version__,))
if ranges or tail_amount:
bytes = 'bytes=' + self.range_header(ranges, tail_amount)
request.add_header('Range', bytes)
response = opener.open(request)
return response
def should_cache(self):
"""Return True if the data pulled across should be cached locally.
"""
return True
def has(self, relpath):
"""Does the target location exist?
"""
abspath = self._real_abspath(relpath)
try:
f = self._get_url_impl(abspath, 'HEAD', [])
# Without the read and then close()
# we tend to have busy sockets.
f.read()
f.close()
return True
except urllib2.HTTPError, e:
mutter('url error code: %s, for has url: %r', e.code, abspath)
if e.code == 404:
return False
raise
except urllib2.URLError, e:
mutter('url error: %s, for has url: %r', e.reason, abspath)
raise
except IOError, e:
mutter('io error: %s %s for has url: %r',
e.errno, errno.errorcode.get(e.errno), abspath)
if e.errno == errno.ENOENT:
return False
raise TransportError(orig_error=e)
def copy_to(self, relpaths, other, mode=None, pb=None):
"""Copy a set of entries from self into another Transport.
:param relpaths: A list/generator of entries to be copied.
TODO: if other is LocalTransport, is it possible to
do better than put(get())?
"""
# At this point HttpTransport_urllib might be able to check and see if
# the remote location is the same, and rather than download, and
# then upload, it could just issue a remote copy_this command.
if isinstance(other, HttpTransport_urllib):
raise TransportNotPossible('http cannot be the target of copy_to()')
else:
return super(HttpTransport_urllib, self).copy_to(relpaths, other, mode=mode, pb=pb)
def move(self, rel_from, rel_to):
"""Move the item at rel_from to the location at rel_to"""
raise TransportNotPossible('http does not support move()')
def delete(self, relpath):
"""Delete the item at relpath"""
raise TransportNotPossible('http does not support delete()')
class HttpServer_urllib(HttpServer):
"""Subclass of HttpServer that gives http+urllib urls.
This is for use in testing: connections to this server will always go
through urllib where possible.
"""
# urls returned by this server should require the urllib client impl
_url_protocol = 'http+urllib'
def get_test_permutations():
"""Return the permutations to be used in testing."""
return [(HttpTransport_urllib, HttpServer_urllib),
]
|