bzr branch
http://gegoxaren.bato24.eu/bzr/brz/remove-bazaar
| 1
by mbp at sourcefrog import from baz patch-364 | 1 | # -*- coding: UTF-8 -*-
 | 
| 1887.1.1
by Adeodato Simó Do not separate paragraphs in the copyright statement with blank lines, | 2 | #
 | 
| 1
by mbp at sourcefrog import from baz patch-364 | 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.
 | |
| 1887.1.1
by Adeodato Simó Do not separate paragraphs in the copyright statement with blank lines, | 7 | #
 | 
| 1
by mbp at sourcefrog import from baz patch-364 | 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.
 | |
| 1887.1.1
by Adeodato Simó Do not separate paragraphs in the copyright statement with blank lines, | 12 | #
 | 
| 1
by mbp at sourcefrog import from baz patch-364 | 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., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 | |
| 16 | ||
| 17 | """XML externalization support."""
 | |
| 18 | ||
| 48
by Martin Pool witty comment | 19 | # "XML is like violence: if it doesn't solve your problem, you aren't
 | 
| 20 | # using enough of it." -- various
 | |
| 21 | ||
| 1180
by Martin Pool - start splitting code for xml (de)serialization away from objects | 22 | # importing this module is fairly slow because it has to load several
 | 
| 23 | # ElementTree bits
 | |
| 24 | ||
| 1248
by Martin Pool - new weave based cleanup [broken] | 25 | from bzrlib.trace import mutter, warning | 
| 26 | ||
| 802
by Martin Pool - Remove XMLMixin class in favour of simple pack_xml, unpack_xml functions | 27 | try: | 
| 1283
by Martin Pool - cElementTree is typically not installed in util | 28 | from cElementTree import (ElementTree, SubElement, Element, | 
| 29 | XMLTreeBuilder, fromstring, tostring) | |
| 1772.1.1
by mbp at sourcefrog Fix up loading of fallback ElementTree | 30 | import elementtree | 
| 2029.2.1
by Marien Zwart Handle the different exception (non-c)ElementTree raises. | 31 | ParseError = SyntaxError | 
| 802
by Martin Pool - Remove XMLMixin class in favour of simple pack_xml, unpack_xml functions | 32 | except ImportError: | 
| 1185.33.68
by Martin Pool Emit warning to trace file only if using cElementTree. | 33 | mutter('WARNING: using slower ElementTree; consider installing cElementTree' | 
| 34 | " and make sure it's on your PYTHONPATH") | |
| 1227
by Martin Pool - methods to deserialize objects from strings | 35 | from util.elementtree.ElementTree import (ElementTree, SubElement, | 
| 1248
by Martin Pool - new weave based cleanup [broken] | 36 | Element, XMLTreeBuilder, | 
| 37 | fromstring, tostring) | |
| 1772.1.1
by mbp at sourcefrog Fix up loading of fallback ElementTree | 38 | import util.elementtree as elementtree | 
| 2029.2.1
by Marien Zwart Handle the different exception (non-c)ElementTree raises. | 39 | from xml.parsers.expat import ExpatError as ParseError | 
| 802
by Martin Pool - Remove XMLMixin class in favour of simple pack_xml, unpack_xml functions | 40 | |
| 1910.2.31
by Aaron Bentley Fix bugs in basis inventory handling, change filename | 41 | from bzrlib import errors | 
| 1180
by Martin Pool - start splitting code for xml (de)serialization away from objects | 42 | |
| 43 | ||
| 44 | class Serializer(object): | |
| 45 | """Abstract object serialize/deserialize""" | |
| 46 | def write_inventory(self, inv, f): | |
| 47 | """Write inventory to a file""" | |
| 48 | elt = self._pack_inventory(inv) | |
| 49 | self._write_element(elt, f) | |
| 50 | ||
| 1248
by Martin Pool - new weave based cleanup [broken] | 51 | def write_inventory_to_string(self, inv): | 
| 1185.16.123
by Martin Pool Fix syntax of serializer_v5.pack_revision_to_string | 52 | return tostring(self._pack_inventory(inv)) + '\n' | 
| 1248
by Martin Pool - new weave based cleanup [broken] | 53 | |
| 1227
by Martin Pool - methods to deserialize objects from strings | 54 | def read_inventory_from_string(self, xml_string): | 
| 1910.2.31
by Aaron Bentley Fix bugs in basis inventory handling, change filename | 55 | try: | 
| 56 | return self._unpack_inventory(fromstring(xml_string)) | |
| 2029.2.1
by Marien Zwart Handle the different exception (non-c)ElementTree raises. | 57 | except ParseError, e: | 
| 1910.2.31
by Aaron Bentley Fix bugs in basis inventory handling, change filename | 58 | raise errors.UnexpectedInventoryFormat(e) | 
| 1227
by Martin Pool - methods to deserialize objects from strings | 59 | |
| 1180
by Martin Pool - start splitting code for xml (de)serialization away from objects | 60 | def read_inventory(self, f): | 
| 1910.2.31
by Aaron Bentley Fix bugs in basis inventory handling, change filename | 61 | try: | 
| 62 | return self._unpack_inventory(self._read_element(f)) | |
| 2029.2.1
by Marien Zwart Handle the different exception (non-c)ElementTree raises. | 63 | except ParseError, e: | 
| 1910.2.31
by Aaron Bentley Fix bugs in basis inventory handling, change filename | 64 | raise errors.UnexpectedInventoryFormat(e) | 
| 1180
by Martin Pool - start splitting code for xml (de)serialization away from objects | 65 | |
| 1182
by Martin Pool - more disentangling of xml storage format from objects | 66 | def write_revision(self, rev, f): | 
| 67 | self._write_element(self._pack_revision(rev), f) | |
| 68 | ||
| 1248
by Martin Pool - new weave based cleanup [broken] | 69 | def write_revision_to_string(self, rev): | 
| 1185.16.123
by Martin Pool Fix syntax of serializer_v5.pack_revision_to_string | 70 | return tostring(self._pack_revision(rev)) + '\n' | 
| 1248
by Martin Pool - new weave based cleanup [broken] | 71 | |
| 1182
by Martin Pool - more disentangling of xml storage format from objects | 72 | def read_revision(self, f): | 
| 73 | return self._unpack_revision(self._read_element(f)) | |
| 74 | ||
| 1227
by Martin Pool - methods to deserialize objects from strings | 75 | def read_revision_from_string(self, xml_string): | 
| 1248
by Martin Pool - new weave based cleanup [broken] | 76 | return self._unpack_revision(fromstring(xml_string)) | 
| 1227
by Martin Pool - methods to deserialize objects from strings | 77 | |
| 1180
by Martin Pool - start splitting code for xml (de)serialization away from objects | 78 | def _write_element(self, elt, f): | 
| 79 | ElementTree(elt).write(f, 'utf-8') | |
| 80 | f.write('\n') | |
| 81 | ||
| 82 | def _read_element(self, f): | |
| 83 | return ElementTree().parse(f) | |
| 1713.1.12
by Robert Collins Improve serialisation of xml performance by overriding elementree's escape routines. | 84 | |
| 85 | ||
| 1772.1.1
by mbp at sourcefrog Fix up loading of fallback ElementTree | 86 | # performance tuning for elementree's serialiser. This should be
 | 
| 1713.1.14
by Robert Collins Review feedback. | 87 | # sent upstream - RBC 20060523.
 | 
| 1759.2.1
by Jelmer Vernooij Fix some types (found using aspell). | 88 | # the functions here are patched into elementtree at runtime.
 | 
| 1713.1.12
by Robert Collins Improve serialisation of xml performance by overriding elementree's escape routines. | 89 | import re | 
| 1713.1.14
by Robert Collins Review feedback. | 90 | escape_re = re.compile("[&'\"<>]") | 
| 1713.1.12
by Robert Collins Improve serialisation of xml performance by overriding elementree's escape routines. | 91 | escape_map = { | 
| 92 | "&":'&', | |
| 93 | "'":"'", # FIXME: overkill | |
| 94 | "\"":""", | |
| 95 | "<":"<", | |
| 96 | ">":">", | |
| 97 |     }
 | |
| 98 | def _escape_replace(match, map=escape_map): | |
| 99 | return map[match.group()] | |
| 100 | ||
| 101 | def _escape_attrib(text, encoding=None, replace=None): | |
| 102 |     # escape attribute value
 | |
| 103 | try: | |
| 104 | if encoding: | |
| 105 | try: | |
| 106 | text = elementtree.ElementTree._encode(text, encoding) | |
| 107 | except UnicodeError: | |
| 108 | return elementtree.ElementTree._encode_entity(text) | |
| 109 | if replace is None: | |
| 110 | return escape_re.sub(_escape_replace, text) | |
| 111 | else: | |
| 112 | text = replace(text, "&", "&") | |
| 113 | text = replace(text, "'", "'") # FIXME: overkill | |
| 114 | text = replace(text, "\"", """) | |
| 115 | text = replace(text, "<", "<") | |
| 116 | text = replace(text, ">", ">") | |
| 117 | return text | |
| 118 | except (TypeError, AttributeError): | |
| 119 | elementtree.ElementTree._raise_serialization_error(text) | |
| 120 | ||
| 121 | elementtree.ElementTree._escape_attrib = _escape_attrib | |
| 122 | ||
| 1713.1.14
by Robert Collins Review feedback. | 123 | escape_cdata_re = re.compile("[&<>]") | 
| 1713.1.12
by Robert Collins Improve serialisation of xml performance by overriding elementree's escape routines. | 124 | escape_cdata_map = { | 
| 125 | "&":'&', | |
| 126 | "<":"<", | |
| 127 | ">":">", | |
| 128 |     }
 | |
| 129 | def _escape_cdata_replace(match, map=escape_cdata_map): | |
| 130 | return map[match.group()] | |
| 131 | ||
| 132 | def _escape_cdata(text, encoding=None, replace=None): | |
| 133 |     # escape character data
 | |
| 134 | try: | |
| 135 | if encoding: | |
| 136 | try: | |
| 137 | text = elementtree.ElementTree._encode(text, encoding) | |
| 138 | except UnicodeError: | |
| 139 | return elementtree.ElementTree._encode_entity(text) | |
| 140 | if replace is None: | |
| 141 | return escape_cdata_re.sub(_escape_cdata_replace, text) | |
| 142 | else: | |
| 143 | text = replace(text, "&", "&") | |
| 144 | text = replace(text, "<", "<") | |
| 145 | text = replace(text, ">", ">") | |
| 146 | return text | |
| 147 | except (TypeError, AttributeError): | |
| 148 | elementtree.ElementTree._raise_serialization_error(text) | |
| 149 | ||
| 150 | elementtree.ElementTree._escape_cdata = _escape_cdata |