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
# "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
21
__copyright__ = "Copyright (C) 2005 Canonical Ltd."
22
__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
34
# Also import ElementTree module so monkey-patching below always works
35
import xml.etree.ElementTree
37
from cElementTree import (ElementTree, SubElement, Element,
38
XMLTreeBuilder, fromstring, tostring)
39
import elementtree.ElementTree
40
ParseError = SyntaxError
25
from cElementTree import Element, ElementTree, SubElement
41
26
except ImportError:
42
mutter('WARNING: using slower ElementTree; consider installing cElementTree'
43
" and make sure it's on your PYTHONPATH")
44
# this copy is shipped with bzr
45
from util.elementtree.ElementTree import (ElementTree, SubElement,
46
Element, XMLTreeBuilder,
48
import util.elementtree as elementtree
49
from xml.parsers.expat import ExpatError as ParseError
51
from bzrlib import errors
54
class XMLSerializer(Serializer):
55
"""Abstract XML object serialize/deserialize"""
57
squashes_xml_invalid_characters = True
59
def read_inventory_from_string(self, xml_string, revision_id=None,
60
entry_cache=None, return_from_cache=False):
61
"""Read xml_string into an inventory object.
63
:param xml_string: The xml to read.
64
:param revision_id: If not-None, the expected revision id of the
65
inventory. Some serialisers use this to set the results' root
66
revision. This should be supplied for deserialising all
67
from-repository inventories so that xml5 inventories that were
68
serialised without a revision identifier can be given the right
69
revision id (but not for working tree inventories where users can
70
edit the data without triggering checksum errors or anything).
71
:param entry_cache: An optional cache of InventoryEntry objects. If
72
supplied we will look up entries via (file_id, revision_id) which
73
should map to a valid InventoryEntry (File/Directory/etc) object.
74
:param return_from_cache: Return entries directly from the cache,
75
rather than copying them first. This is only safe if the caller
76
promises not to mutate the returned inventory entries, but it can
77
make some operations significantly faster.
80
return self._unpack_inventory(fromstring(xml_string), revision_id,
81
entry_cache=entry_cache,
82
return_from_cache=return_from_cache)
84
raise errors.UnexpectedInventoryFormat(e)
86
def read_inventory(self, f, revision_id=None):
89
return self._unpack_inventory(self._read_element(f),
94
raise errors.UnexpectedInventoryFormat(e)
96
def write_revision(self, rev, f):
97
self._write_element(self._pack_revision(rev), f)
99
def write_revision_to_string(self, rev):
100
return tostring(self._pack_revision(rev)) + '\n'
102
def read_revision(self, f):
103
return self._unpack_revision(self._read_element(f))
105
def read_revision_from_string(self, xml_string):
106
return self._unpack_revision(fromstring(xml_string))
108
def _write_element(self, elt, f):
109
ElementTree(elt).write(f, 'utf-8')
27
from elementtree import Element, ElementTree, SubElement
30
from trace import mutter
34
raise Exception("XMLMixin.to_element must be overridden in concrete classes")
36
def write_xml(self, f):
37
ElementTree(self.to_element()).write(f, 'utf-8')
112
def _read_element(self, f):
113
return ElementTree().parse(f)
116
# performance tuning for elementree's serialiser. This should be
117
# sent upstream - RBC 20060523.
118
# the functions here are patched into elementtree at runtime.
120
escape_re = re.compile("[&'\"<>]")
123
"'":"'", # FIXME: overkill
128
def _escape_replace(match, map=escape_map):
129
return map[match.group()]
131
def _escape_attrib(text, encoding=None, replace=None):
132
# escape attribute value
136
text = elementtree.ElementTree._encode(text, encoding)
138
return elementtree.ElementTree._encode_entity(text)
140
return escape_re.sub(_escape_replace, text)
142
text = replace(text, "&", "&")
143
text = replace(text, "'", "'") # FIXME: overkill
144
text = replace(text, "\"", """)
145
text = replace(text, "<", "<")
146
text = replace(text, ">", ">")
148
except (TypeError, AttributeError):
149
elementtree.ElementTree._raise_serialization_error(text)
151
elementtree.ElementTree._escape_attrib = _escape_attrib
153
escape_cdata_re = re.compile("[&<>]")
159
def _escape_cdata_replace(match, map=escape_cdata_map):
160
return map[match.group()]
162
def _escape_cdata(text, encoding=None, replace=None):
163
# escape character data
167
text = elementtree.ElementTree._encode(text, encoding)
169
return elementtree.ElementTree._encode_entity(text)
171
return escape_cdata_re.sub(_escape_cdata_replace, text)
173
text = replace(text, "&", "&")
174
text = replace(text, "<", "<")
175
text = replace(text, ">", ">")
177
except (TypeError, AttributeError):
178
elementtree.ElementTree._raise_serialization_error(text)
180
elementtree.ElementTree._escape_cdata = _escape_cdata
183
def escape_invalid_chars(message):
184
"""Escape the XML-invalid characters in a commit message.
186
:param message: Commit message to escape
187
:return: tuple with escaped message and number of characters escaped
191
# Python strings can include characters that can't be
192
# represented in well-formed XML; escape characters that
193
# aren't listed in the XML specification
194
# (http://www.w3.org/TR/REC-xml/#NT-Char).
195
return re.subn(u'[^\x09\x0A\x0D\u0020-\uD7FF\uE000-\uFFFD]+',
196
lambda match: match.group(0).encode('unicode_escape'),
41
return cls.from_element(ElementTree().parse(f))
43
read_xml = classmethod(read_xml)