1
# Copyright (C) 2005-2010 Canonical Ltd
2
# -*- coding: UTF-8 -*-
3
4
# This program is free software; you can redistribute it and/or modify
4
5
# it under the terms of the GNU General Public License as published by
5
6
# the Free Software Foundation; either version 2 of the License, or
6
7
# (at your option) any later version.
8
9
# This program is distributed in the hope that it will be useful,
9
10
# but WITHOUT ANY WARRANTY; without even the implied warranty of
10
11
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
11
12
# GNU General Public License for more details.
13
14
# You should have received a copy of the GNU General Public License
14
15
# along with this program; if not, write to the Free Software
15
# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
16
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
17
18
"""XML externalization support."""
19
20
# "XML is like violence: if it doesn't solve your problem, you aren't
20
21
# 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
24
__copyright__ = "Copyright (C) 2005 Canonical Ltd."
25
__author__ = "Martin Pool <mbp@canonical.com>"
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
28
from cElementTree import Element, ElementTree, SubElement
39
29
except ImportError:
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
squashes_xml_invalid_characters = True
57
def read_inventory_from_string(self, xml_string, revision_id=None,
58
entry_cache=None, return_from_cache=False):
59
"""Read xml_string into an inventory object.
61
:param xml_string: The xml to read.
62
:param revision_id: If not-None, the expected revision id of the
63
inventory. Some serialisers use this to set the results' root
64
revision. This should be supplied for deserialising all
65
from-repository inventories so that xml5 inventories that were
66
serialised without a revision identifier can be given the right
67
revision id (but not for working tree inventories where users can
68
edit the data without triggering checksum errors or anything).
69
:param entry_cache: An optional cache of InventoryEntry objects. If
70
supplied we will look up entries via (file_id, revision_id) which
71
should map to a valid InventoryEntry (File/Directory/etc) object.
72
:param return_from_cache: Return entries directly from the cache,
73
rather than copying them first. This is only safe if the caller
74
promises not to mutate the returned inventory entries, but it can
75
make some operations significantly faster.
78
return self._unpack_inventory(fromstring(xml_string), revision_id,
79
entry_cache=entry_cache,
80
return_from_cache=return_from_cache)
82
raise errors.UnexpectedInventoryFormat(e)
84
def read_inventory(self, f, revision_id=None):
87
return self._unpack_inventory(self._read_element(f),
92
raise errors.UnexpectedInventoryFormat(e)
94
def write_revision(self, rev, f):
95
self._write_element(self._pack_revision(rev), f)
97
def write_revision_to_string(self, rev):
98
return tostring(self._pack_revision(rev)) + '\n'
100
def read_revision(self, f):
101
return self._unpack_revision(self._read_element(f))
103
def read_revision_from_string(self, xml_string):
104
return self._unpack_revision(fromstring(xml_string))
106
def _write_element(self, elt, f):
107
ElementTree(elt).write(f, 'utf-8')
30
from elementtree.ElementTree import Element, ElementTree, SubElement
33
from trace import mutter
37
raise Exception("XMLMixin.to_element must be overridden in concrete classes")
39
def write_xml(self, f):
40
ElementTree(self.to_element()).write(f, 'utf-8')
110
def _read_element(self, f):
111
return ElementTree().parse(f)
114
# performance tuning for elementree's serialiser. This should be
115
# sent upstream - RBC 20060523.
116
# the functions here are patched into elementtree at runtime.
118
escape_re = re.compile("[&'\"<>]")
121
"'":"'", # FIXME: overkill
126
def _escape_replace(match, map=escape_map):
127
return map[match.group()]
129
def _escape_attrib(text, encoding=None, replace=None):
130
# escape attribute value
134
text = elementtree.ElementTree._encode(text, encoding)
136
return elementtree.ElementTree._encode_entity(text)
138
return escape_re.sub(_escape_replace, text)
140
text = replace(text, "&", "&")
141
text = replace(text, "'", "'") # FIXME: overkill
142
text = replace(text, "\"", """)
143
text = replace(text, "<", "<")
144
text = replace(text, ">", ">")
146
except (TypeError, AttributeError):
147
elementtree.ElementTree._raise_serialization_error(text)
149
elementtree.ElementTree._escape_attrib = _escape_attrib
151
escape_cdata_re = re.compile("[&<>]")
157
def _escape_cdata_replace(match, map=escape_cdata_map):
158
return map[match.group()]
160
def _escape_cdata(text, encoding=None, replace=None):
161
# escape character data
165
text = elementtree.ElementTree._encode(text, encoding)
167
return elementtree.ElementTree._encode_entity(text)
169
return escape_cdata_re.sub(_escape_cdata_replace, text)
171
text = replace(text, "&", "&")
172
text = replace(text, "<", "<")
173
text = replace(text, ">", ">")
175
except (TypeError, AttributeError):
176
elementtree.ElementTree._raise_serialization_error(text)
178
elementtree.ElementTree._escape_cdata = _escape_cdata
181
def escape_invalid_chars(message):
182
"""Escape the XML-invalid characters in a commit message.
184
:param message: Commit message to escape
185
:return: tuple with escaped message and number of characters escaped
189
# Python strings can include characters that can't be
190
# represented in well-formed XML; escape characters that
191
# aren't listed in the XML specification
192
# (http://www.w3.org/TR/REC-xml/#NT-Char).
193
return re.subn(u'[^\x09\x0A\x0D\u0020-\uD7FF\uE000-\uFFFD]+',
194
lambda match: match.group(0).encode('unicode_escape'),
44
return cls.from_element(ElementTree().parse(f))
46
read_xml = classmethod(read_xml)
added
removed
bzrlib/xml.py
