/brz/remove-bazaar

To get this branch, use:
bzr branch http://gegoxaren.bato24.eu/bzr/brz/remove-bazaar

« back to all changes in this revision

Viewing changes to bzrlib/xml_serializer.py

  • Committer: Robert Collins
  • Date: 2009-05-12 03:50:39 UTC
  • mto: This revision was merged to the branch mainline in revision 4593.
  • Revision ID: robertc@robertcollins.net-20090512035039-6x0pahpjpkdnm9zb
Note another possible error.

Show diffs side-by-side

added added

removed removed

Lines of Context:
bzrlib/xml_serializer.py
1
 
# -*- coding: UTF-8 -*-
 
1
# Copyright (C) 2005, 2006 Canonical Ltd
2
2
#
3
3
# This program is free software; you can redistribute it and/or modify
4
4
# it under the terms of the GNU General Public License as published by
12
12
#
13
13
# You should have received a copy of the GNU General Public License
14
14
# along with this program; if not, write to the Free Software
15
 
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 
15
# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
16
16
 
17
17
"""XML externalization support."""
18
18
 
22
22
# importing this module is fairly slow because it has to load several
23
23
# ElementTree bits
24
24
 
 
25
from bzrlib.serializer import Serializer
25
26
from bzrlib.trace import mutter, warning
26
27
 
27
28
try:
28
 
    from cElementTree import (ElementTree, SubElement, Element,
29
 
                              XMLTreeBuilder, fromstring, tostring)
30
 
    import elementtree
 
29
    try:
 
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
    except ImportError:
 
35
        from cElementTree import (ElementTree, SubElement, Element,
 
36
                                  XMLTreeBuilder, fromstring, tostring)
 
37
        import elementtree.ElementTree
 
38
    ParseError = SyntaxError
31
39
except ImportError:
32
40
    mutter('WARNING: using slower ElementTree; consider installing cElementTree'
33
41
           " and make sure it's on your PYTHONPATH")
 
42
    # this copy is shipped with bzr
34
43
    from util.elementtree.ElementTree import (ElementTree, SubElement,
35
44
                                              Element, XMLTreeBuilder,
36
45
                                              fromstring, tostring)
37
46
    import util.elementtree as elementtree
 
47
    from xml.parsers.expat import ExpatError as ParseError
38
48
 
39
49
from bzrlib import errors
40
50
 
41
51
 
42
 
class Serializer(object):
43
 
    """Abstract object serialize/deserialize"""
44
 
    def write_inventory(self, inv, f):
45
 
        """Write inventory to a file"""
46
 
        elt = self._pack_inventory(inv)
47
 
        self._write_element(elt, f)
48
 
 
49
 
    def write_inventory_to_string(self, inv):
50
 
        return tostring(self._pack_inventory(inv)) + '\n'
51
 
 
52
 
    def read_inventory_from_string(self, xml_string):
 
52
class XMLSerializer(Serializer):
 
53
    """Abstract XML object serialize/deserialize"""
 
54
 
 
55
    def read_inventory_from_string(self, xml_string, revision_id=None,
 
56
                                   entry_cache=None):
 
57
        """Read xml_string into an inventory object.
 
58
 
 
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.
 
70
        """
53
71
        try:
54
 
            return self._unpack_inventory(fromstring(xml_string))
55
 
        except SyntaxError, e:
 
72
            return self._unpack_inventory(fromstring(xml_string), revision_id,
 
73
                                          entry_cache=entry_cache)
 
74
        except ParseError, e:
56
75
            raise errors.UnexpectedInventoryFormat(e)
57
76
 
58
 
    def read_inventory(self, f):
 
77
    def read_inventory(self, f, revision_id=None):
59
78
        try:
60
 
            return self._unpack_inventory(self._read_element(f))
61
 
        except SyntaxError, e:
 
79
            return self._unpack_inventory(self._read_element(f),
 
80
                revision_id=None)
 
81
        except ParseError, e:
62
82
            raise errors.UnexpectedInventoryFormat(e)
63
83
 
64
84
    def write_revision(self, rev, f):
95
115
    }
96
116
def _escape_replace(match, map=escape_map):
97
117
    return map[match.group()]
98
 
 
 
118
 
99
119
def _escape_attrib(text, encoding=None, replace=None):
100
120
    # escape attribute value
101
121
    try:
126
146
    }
127
147
def _escape_cdata_replace(match, map=escape_cdata_map):
128
148
    return map[match.group()]
129
 
 
 
149
 
130
150
def _escape_cdata(text, encoding=None, replace=None):
131
151
    # escape character data
132
152
    try:
146
166
        elementtree.ElementTree._raise_serialization_error(text)
147
167
 
148
168
elementtree.ElementTree._escape_cdata = _escape_cdata
 
169
 
 
170
 
 
171
def escape_invalid_chars(message):
 
172
    """Escape the XML-invalid characters in a commit message.
 
173
 
 
174
    :param message: Commit message to escape
 
175
    :param count: Number of characters that were escaped
 
176
    """
 
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'),
 
183
            message)