1
# Copyright (C) 2005-2010 Canonical Ltd
3
# This program is free software; you can redistribute it and/or modify
4
# it under the terms of the GNU General Public License as published by
5
# the Free Software Foundation; either version 2 of the License, or
6
# (at your option) any later version.
8
# This program is distributed in the hope that it will be useful,
9
# but WITHOUT ANY WARRANTY; without even the implied warranty of
10
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
11
# GNU General Public License for more details.
13
# You should have received a copy of the GNU General Public License
14
# along with this program; if not, write to the Free Software
15
# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
17
"""XML externalization support."""
19
# "XML is like violence: if it doesn't solve your problem, you aren't
20
# using enough of it." -- various
22
# importing this module is fairly slow because it has to load several
27
from bzrlib.serializer import Serializer
28
from bzrlib.trace import mutter
32
# it's in this package in python2.5
33
from xml.etree.cElementTree import (ElementTree, SubElement, Element,
34
XMLTreeBuilder, fromstring, tostring)
35
import xml.etree as elementtree
36
# Also import ElementTree module so monkey-patching below always works
37
import xml.etree.ElementTree
39
from cElementTree import (ElementTree, SubElement, Element,
40
XMLTreeBuilder, fromstring, tostring)
41
import elementtree.ElementTree
42
ParseError = SyntaxError
44
mutter('WARNING: using slower ElementTree; consider installing cElementTree'
45
" and make sure it's on your PYTHONPATH")
46
# this copy is shipped with bzr
47
from util.elementtree.ElementTree import (ElementTree, SubElement,
48
Element, XMLTreeBuilder,
50
import util.elementtree as elementtree
51
from xml.parsers.expat import ExpatError as ParseError
53
from bzrlib import errors
56
class XMLSerializer(Serializer):
57
"""Abstract XML object serialize/deserialize"""
59
squashes_xml_invalid_characters = True
61
def read_inventory_from_string(self, xml_string, revision_id=None,
62
entry_cache=None, return_from_cache=False):
63
"""Read xml_string into an inventory object.
65
:param xml_string: The xml to read.
66
:param revision_id: If not-None, the expected revision id of the
67
inventory. Some serialisers use this to set the results' root
68
revision. This should be supplied for deserialising all
69
from-repository inventories so that xml5 inventories that were
70
serialised without a revision identifier can be given the right
71
revision id (but not for working tree inventories where users can
72
edit the data without triggering checksum errors or anything).
73
:param entry_cache: An optional cache of InventoryEntry objects. If
74
supplied we will look up entries via (file_id, revision_id) which
75
should map to a valid InventoryEntry (File/Directory/etc) object.
76
:param return_from_cache: Return entries directly from the cache,
77
rather than copying them first. This is only safe if the caller
78
promises not to mutate the returned inventory entries, but it can
79
make some operations significantly faster.
82
return self._unpack_inventory(fromstring(xml_string), revision_id,
83
entry_cache=entry_cache,
84
return_from_cache=return_from_cache)
86
raise errors.UnexpectedInventoryFormat(e)
88
def read_inventory(self, f, revision_id=None):
91
return self._unpack_inventory(self._read_element(f),
96
raise errors.UnexpectedInventoryFormat(e)
98
def write_revision(self, rev, f):
99
self._write_element(self._pack_revision(rev), f)
101
def write_revision_to_string(self, rev):
102
return tostring(self._pack_revision(rev)) + '\n'
104
def read_revision(self, f):
105
return self._unpack_revision(self._read_element(f))
107
def read_revision_from_string(self, xml_string):
108
return self._unpack_revision(fromstring(xml_string))
110
def _write_element(self, elt, f):
111
ElementTree(elt).write(f, 'utf-8')
114
def _read_element(self, f):
115
return ElementTree().parse(f)
118
def escape_invalid_chars(message):
119
"""Escape the XML-invalid characters in a commit message.
121
:param message: Commit message to escape
122
:return: tuple with escaped message and number of characters escaped
126
# Python strings can include characters that can't be
127
# represented in well-formed XML; escape characters that
128
# aren't listed in the XML specification
129
# (http://www.w3.org/TR/REC-xml/#NT-Char).
130
return re.subn(u'[^\x09\x0A\x0D\u0020-\uD7FF\uE000-\uFFFD]+',
131
lambda match: match.group(0).encode('unicode_escape'),