1
# Copyright (C) 2005, 2006 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
25
from bzrlib.serializer import Serializer
26
from bzrlib.trace import mutter, warning
30
# it's in this package in python2.5
31
from xml.etree.cElementTree import (ElementTree, SubElement, Element,
32
XMLTreeBuilder, fromstring, tostring)
33
import xml.etree as elementtree
35
from cElementTree import (ElementTree, SubElement, Element,
36
XMLTreeBuilder, fromstring, tostring)
37
import elementtree.ElementTree
38
ParseError = SyntaxError
40
mutter('WARNING: using slower ElementTree; consider installing cElementTree'
41
" and make sure it's on your PYTHONPATH")
42
# this copy is shipped with bzr
43
from util.elementtree.ElementTree import (ElementTree, SubElement,
44
Element, XMLTreeBuilder,
46
import util.elementtree as elementtree
47
from xml.parsers.expat import ExpatError as ParseError
49
from bzrlib import errors
52
class XMLSerializer(Serializer):
53
"""Abstract XML object serialize/deserialize"""
55
def read_inventory_from_string(self, xml_string, revision_id=None,
57
"""Read xml_string into an inventory object.
59
:param xml_string: The xml to read.
60
:param revision_id: If not-None, the expected revision id of the
61
inventory. Some serialisers use this to set the results' root
62
revision. This should be supplied for deserialising all
63
from-repository inventories so that xml5 inventories that were
64
serialised without a revision identifier can be given the right
65
revision id (but not for working tree inventories where users can
66
edit the data without triggering checksum errors or anything).
67
:param entry_cache: An optional cache of InventoryEntry objects. If
68
supplied we will look up entries via (file_id, revision_id) which
69
should map to a valid InventoryEntry (File/Directory/etc) object.
72
return self._unpack_inventory(fromstring(xml_string), revision_id,
73
entry_cache=entry_cache)
75
raise errors.UnexpectedInventoryFormat(e)
77
def read_inventory(self, f, revision_id=None):
79
return self._unpack_inventory(self._read_element(f),
82
raise errors.UnexpectedInventoryFormat(e)
84
def write_revision(self, rev, f):
85
self._write_element(self._pack_revision(rev), f)
87
def write_revision_to_string(self, rev):
88
return tostring(self._pack_revision(rev)) + '\n'
90
def read_revision(self, f):
91
return self._unpack_revision(self._read_element(f))
93
def read_revision_from_string(self, xml_string):
94
return self._unpack_revision(fromstring(xml_string))
96
def _write_element(self, elt, f):
97
ElementTree(elt).write(f, 'utf-8')
100
def _read_element(self, f):
101
return ElementTree().parse(f)
104
# performance tuning for elementree's serialiser. This should be
105
# sent upstream - RBC 20060523.
106
# the functions here are patched into elementtree at runtime.
108
escape_re = re.compile("[&'\"<>]")
111
"'":"'", # FIXME: overkill
116
def _escape_replace(match, map=escape_map):
117
return map[match.group()]
119
def _escape_attrib(text, encoding=None, replace=None):
120
# escape attribute value
124
text = elementtree.ElementTree._encode(text, encoding)
126
return elementtree.ElementTree._encode_entity(text)
128
return escape_re.sub(_escape_replace, text)
130
text = replace(text, "&", "&")
131
text = replace(text, "'", "'") # FIXME: overkill
132
text = replace(text, "\"", """)
133
text = replace(text, "<", "<")
134
text = replace(text, ">", ">")
136
except (TypeError, AttributeError):
137
elementtree.ElementTree._raise_serialization_error(text)
139
elementtree.ElementTree._escape_attrib = _escape_attrib
141
escape_cdata_re = re.compile("[&<>]")
147
def _escape_cdata_replace(match, map=escape_cdata_map):
148
return map[match.group()]
150
def _escape_cdata(text, encoding=None, replace=None):
151
# escape character data
155
text = elementtree.ElementTree._encode(text, encoding)
157
return elementtree.ElementTree._encode_entity(text)
159
return escape_cdata_re.sub(_escape_cdata_replace, text)
161
text = replace(text, "&", "&")
162
text = replace(text, "<", "<")
163
text = replace(text, ">", ">")
165
except (TypeError, AttributeError):
166
elementtree.ElementTree._raise_serialization_error(text)
168
elementtree.ElementTree._escape_cdata = _escape_cdata
171
def escape_invalid_chars(message):
172
"""Escape the XML-invalid characters in a commit message.
174
:param message: Commit message to escape
175
:return: tuple with escaped message and number of characters escaped
177
# Python strings can include characters that can't be
178
# represented in well-formed XML; escape characters that
179
# aren't listed in the XML specification
180
# (http://www.w3.org/TR/REC-xml/#NT-Char).
181
return re.subn(u'[^\x09\x0A\x0D\u0020-\uD7FF\uE000-\uFFFD]+',
182
lambda match: match.group(0).encode('unicode_escape'),
added
removed
bzrlib/xml_serializer.py
