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
|
# Copyright (C) 2005-2010 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., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
"""XML externalization support."""
# "XML is like violence: if it doesn't solve your problem, you aren't
# using enough of it." -- various
# importing this module is fairly slow because it has to load several
# ElementTree bits
import re
from bzrlib.serializer import Serializer
from bzrlib.trace import mutter
try:
try:
# it's in this package in python2.5
from xml.etree.cElementTree import (ElementTree, SubElement, Element,
XMLTreeBuilder, fromstring, tostring)
import xml.etree as elementtree
# Also import ElementTree module so monkey-patching below always works
import xml.etree.ElementTree
except ImportError:
from cElementTree import (ElementTree, SubElement, Element,
XMLTreeBuilder, fromstring, tostring)
import elementtree.ElementTree
ParseError = SyntaxError
except ImportError:
mutter('WARNING: using slower ElementTree; consider installing cElementTree'
" and make sure it's on your PYTHONPATH")
# this copy is shipped with bzr
from util.elementtree.ElementTree import (ElementTree, SubElement,
Element, XMLTreeBuilder,
fromstring, tostring)
import util.elementtree as elementtree
from xml.parsers.expat import ExpatError as ParseError
from bzrlib import errors
class XMLSerializer(Serializer):
"""Abstract XML object serialize/deserialize"""
squashes_xml_invalid_characters = True
def read_inventory_from_string(self, xml_string, revision_id=None,
entry_cache=None, return_from_cache=False):
"""Read xml_string into an inventory object.
:param xml_string: The xml to read.
:param revision_id: If not-None, the expected revision id of the
inventory. Some serialisers use this to set the results' root
revision. This should be supplied for deserialising all
from-repository inventories so that xml5 inventories that were
serialised without a revision identifier can be given the right
revision id (but not for working tree inventories where users can
edit the data without triggering checksum errors or anything).
:param entry_cache: An optional cache of InventoryEntry objects. If
supplied we will look up entries via (file_id, revision_id) which
should map to a valid InventoryEntry (File/Directory/etc) object.
:param return_from_cache: Return entries directly from the cache,
rather than copying them first. This is only safe if the caller
promises not to mutate the returned inventory entries, but it can
make some operations significantly faster.
"""
try:
return self._unpack_inventory(fromstring(xml_string), revision_id,
entry_cache=entry_cache,
return_from_cache=return_from_cache)
except ParseError, e:
raise errors.UnexpectedInventoryFormat(e)
def read_inventory(self, f, revision_id=None):
try:
try:
return self._unpack_inventory(self._read_element(f),
revision_id=None)
finally:
f.close()
except ParseError, e:
raise errors.UnexpectedInventoryFormat(e)
def write_revision(self, rev, f):
self._write_element(self._pack_revision(rev), f)
def write_revision_to_string(self, rev):
return tostring(self._pack_revision(rev)) + '\n'
def read_revision(self, f):
return self._unpack_revision(self._read_element(f))
def read_revision_from_string(self, xml_string):
return self._unpack_revision(fromstring(xml_string))
def _write_element(self, elt, f):
ElementTree(elt).write(f, 'utf-8')
f.write('\n')
def _read_element(self, f):
return ElementTree().parse(f)
def escape_invalid_chars(message):
"""Escape the XML-invalid characters in a commit message.
:param message: Commit message to escape
:return: tuple with escaped message and number of characters escaped
"""
if message is None:
return None, 0
# Python strings can include characters that can't be
# represented in well-formed XML; escape characters that
# aren't listed in the XML specification
# (http://www.w3.org/TR/REC-xml/#NT-Char).
return re.subn(u'[^\x09\x0A\x0D\u0020-\uD7FF\uE000-\uFFFD]+',
lambda match: match.group(0).encode('unicode_escape'),
message)
|