1
# Copyright (C) 2008, 2009 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
"""Inventory delta serialisation.
19
See doc/developers/inventory.txt for the description of the format.
21
In this module the interesting classes are:
22
- InventoryDeltaSerializer - object to read/write inventory deltas.
25
__all__ = ['InventoryDeltaSerializer']
27
from bzrlib import errors
28
from bzrlib.osutils import basename
29
from bzrlib import inventory
30
from bzrlib.revision import NULL_REVISION
32
FORMAT_1 = 'bzr inventory delta v1 (bzr 1.14)'
35
class InventoryDeltaError(errors.BzrError):
36
"""An error when serializing or deserializing an inventory delta."""
38
# Most errors when serializing and deserializing are due to bugs, although
39
# damaged input (i.e. a bug in a different process) could cause
40
# deserialization errors too.
44
class IncompatibleInventoryDelta(errors.BzrError):
45
"""The delta could not be deserialised because its contents conflict with
46
the allow_versioned_root or allow_tree_references flags of the
49
internal_error = False
52
def _directory_content(entry):
53
"""Serialize the content component of entry which is a directory.
55
:param entry: An InventoryDirectory.
60
def _file_content(entry):
61
"""Serialize the content component of entry which is a file.
63
:param entry: An InventoryFile.
69
size_exec_sha = (entry.text_size, exec_bytes, entry.text_sha1)
70
if None in size_exec_sha:
71
raise InventoryDeltaError('Missing size or sha for %s' % entry.file_id)
72
return "file\x00%d\x00%s\x00%s" % size_exec_sha
75
def _link_content(entry):
76
"""Serialize the content component of entry which is a symlink.
78
:param entry: An InventoryLink.
80
target = entry.symlink_target
82
raise InventoryDeltaError('Missing target for %s' % entry.file_id)
83
return "link\x00%s" % target.encode('utf8')
86
def _reference_content(entry):
87
"""Serialize the content component of entry which is a tree-reference.
89
:param entry: A TreeReference.
91
tree_revision = entry.reference_revision
92
if tree_revision is None:
93
raise InventoryDeltaError(
94
'Missing reference revision for %s' % entry.file_id)
95
return "tree\x00%s" % tree_revision
98
def _dir_to_entry(content, name, parent_id, file_id, last_modified,
99
_type=inventory.InventoryDirectory):
100
"""Convert a dir content record to an InventoryDirectory."""
101
result = _type(file_id, name, parent_id)
102
result.revision = last_modified
106
def _file_to_entry(content, name, parent_id, file_id, last_modified,
107
_type=inventory.InventoryFile):
108
"""Convert a dir content record to an InventoryFile."""
109
result = _type(file_id, name, parent_id)
110
result.revision = last_modified
111
result.text_size = int(content[1])
112
result.text_sha1 = content[3]
114
result.executable = True
116
result.executable = False
120
def _link_to_entry(content, name, parent_id, file_id, last_modified,
121
_type=inventory.InventoryLink):
122
"""Convert a link content record to an InventoryLink."""
123
result = _type(file_id, name, parent_id)
124
result.revision = last_modified
125
result.symlink_target = content[1].decode('utf8')
129
def _tree_to_entry(content, name, parent_id, file_id, last_modified,
130
_type=inventory.TreeReference):
131
"""Convert a tree content record to a TreeReference."""
132
result = _type(file_id, name, parent_id)
133
result.revision = last_modified
134
result.reference_revision = content[1]
138
class InventoryDeltaSerializer(object):
139
"""Serialize inventory deltas."""
141
def __init__(self, versioned_root, tree_references):
142
"""Create an InventoryDeltaSerializer.
144
:param versioned_root: If True, any root entry that is seen is expected
145
to be versioned, and root entries can have any fileid.
146
:param tree_references: If True support tree-reference entries.
148
self._versioned_root = versioned_root
149
self._tree_references = tree_references
150
self._entry_to_content = {
151
'directory': _directory_content,
152
'file': _file_content,
153
'symlink': _link_content,
156
self._entry_to_content['tree-reference'] = _reference_content
158
def delta_to_lines(self, old_name, new_name, delta_to_new):
159
"""Return a line sequence for delta_to_new.
161
Both the versioned_root and tree_references flags must be set via
162
require_flags before calling this.
164
:param old_name: A UTF8 revision id for the old inventory. May be
165
NULL_REVISION if there is no older inventory and delta_to_new
166
includes the entire inventory contents.
167
:param new_name: The version name of the inventory we create with this
169
:param delta_to_new: An inventory delta such as Inventory.apply_delta
171
:return: The serialized delta as lines.
173
if type(old_name) is not str:
174
raise TypeError('old_name should be str, got %r' % (old_name,))
175
if type(new_name) is not str:
176
raise TypeError('new_name should be str, got %r' % (new_name,))
177
lines = ['', '', '', '', '']
178
to_line = self._delta_item_to_line
179
for delta_item in delta_to_new:
180
line = to_line(delta_item, new_name)
181
if line.__class__ != str:
182
raise InventoryDeltaError(
183
'to_line generated non-str output %r' % lines[-1])
186
lines[0] = "format: %s\n" % FORMAT_1
187
lines[1] = "parent: %s\n" % old_name
188
lines[2] = "version: %s\n" % new_name
189
lines[3] = "versioned_root: %s\n" % self._serialize_bool(
190
self._versioned_root)
191
lines[4] = "tree_references: %s\n" % self._serialize_bool(
192
self._tree_references)
195
def _serialize_bool(self, value):
201
def _delta_item_to_line(self, delta_item, new_version):
202
"""Convert delta_item to a line."""
203
oldpath, newpath, file_id, entry = delta_item
206
oldpath_utf8 = '/' + oldpath.encode('utf8')
207
newpath_utf8 = 'None'
209
last_modified = NULL_REVISION
210
content = 'deleted\x00\x00'
213
oldpath_utf8 = 'None'
215
oldpath_utf8 = '/' + oldpath.encode('utf8')
217
raise AssertionError(
218
"Bad inventory delta: '/' is not a valid newpath "
219
"(should be '') in delta item %r" % (delta_item,))
220
# TODO: Test real-world utf8 cache hit rate. It may be a win.
221
newpath_utf8 = '/' + newpath.encode('utf8')
222
# Serialize None as ''
223
parent_id = entry.parent_id or ''
224
# Serialize unknown revisions as NULL_REVISION
225
last_modified = entry.revision
226
# special cases for /
227
if newpath_utf8 == '/' and not self._versioned_root:
228
# This is an entry for the root, this inventory does not
229
# support versioned roots. So this must be an unversioned
230
# root, i.e. last_modified == new revision. Otherwise, this
232
# Note: the non-rich-root repositories *can* have roots with
233
# file-ids other than TREE_ROOT, e.g. repo formats that use the
235
if last_modified != new_version:
236
raise InventoryDeltaError(
237
'Version present for / in %s (%s != %s)'
238
% (file_id, last_modified, new_version))
239
if last_modified is None:
240
raise InventoryDeltaError("no version for fileid %s" % file_id)
241
content = self._entry_to_content[entry.kind](entry)
242
return ("%s\x00%s\x00%s\x00%s\x00%s\x00%s\n" %
243
(oldpath_utf8, newpath_utf8, file_id, parent_id, last_modified,
247
class InventoryDeltaDeserializer(object):
248
"""Deserialize inventory deltas."""
250
def __init__(self, allow_versioned_root=True, allow_tree_references=True):
251
"""Create an InventoryDeltaDeserializer.
253
:param versioned_root: If True, any root entry that is seen is expected
254
to be versioned, and root entries can have any fileid.
255
:param tree_references: If True support tree-reference entries.
257
self._allow_versioned_root = allow_versioned_root
258
self._allow_tree_references = allow_tree_references
260
def _deserialize_bool(self, value):
263
elif value == "false":
266
raise InventoryDeltaError("value %r is not a bool" % (value,))
268
def parse_text_bytes(self, bytes):
269
"""Parse the text bytes of a serialized inventory delta.
271
If versioned_root and/or tree_references flags were set via
272
require_flags, then the parsed flags must match or a BzrError will be
275
:param bytes: The bytes to parse. This can be obtained by calling
276
delta_to_lines and then doing ''.join(delta_lines).
277
:return: (parent_id, new_id, versioned_root, tree_references,
280
if bytes[-1:] != '\n':
281
last_line = bytes.rsplit('\n', 1)[-1]
282
raise InventoryDeltaError('last line not empty: %r' % (last_line,))
283
lines = bytes.split('\n')[:-1] # discard the last empty line
284
if not lines or lines[0] != 'format: %s' % FORMAT_1:
285
raise InventoryDeltaError('unknown format %r' % lines[0:1])
286
if len(lines) < 2 or not lines[1].startswith('parent: '):
287
raise InventoryDeltaError('missing parent: marker')
288
delta_parent_id = lines[1][8:]
289
if len(lines) < 3 or not lines[2].startswith('version: '):
290
raise InventoryDeltaError('missing version: marker')
291
delta_version_id = lines[2][9:]
292
if len(lines) < 4 or not lines[3].startswith('versioned_root: '):
293
raise InventoryDeltaError('missing versioned_root: marker')
294
delta_versioned_root = self._deserialize_bool(lines[3][16:])
295
if len(lines) < 5 or not lines[4].startswith('tree_references: '):
296
raise InventoryDeltaError('missing tree_references: marker')
297
delta_tree_references = self._deserialize_bool(lines[4][17:])
298
if (not self._allow_versioned_root and delta_versioned_root):
299
raise IncompatibleInventoryDelta("versioned_root not allowed")
302
line_iter = iter(lines)
305
for line in line_iter:
306
(oldpath_utf8, newpath_utf8, file_id, parent_id, last_modified,
307
content) = line.split('\x00', 5)
308
parent_id = parent_id or None
309
if file_id in seen_ids:
310
raise InventoryDeltaError(
311
"duplicate file id in inventory delta %r" % lines)
312
seen_ids.add(file_id)
313
if (newpath_utf8 == '/' and not delta_versioned_root and
314
last_modified != delta_version_id):
315
# Delta claims to be not have a versioned root, yet here's
316
# a root entry with a non-default version.
317
raise InventoryDeltaError("Versioned root found: %r" % line)
318
elif newpath_utf8 != 'None' and last_modified[-1] == ':':
319
# Deletes have a last_modified of null:, but otherwise special
320
# revision ids should not occur.
321
raise InventoryDeltaError('special revisionid found: %r' % line)
322
if content.startswith('tree\x00'):
323
if delta_tree_references is False:
324
raise InventoryDeltaError(
325
"Tree reference found (but header said "
326
"tree_references: false): %r" % line)
327
elif not self._allow_tree_references:
328
raise IncompatibleInventoryDelta(
329
"Tree reference not allowed")
330
if oldpath_utf8 == 'None':
332
elif oldpath_utf8[:1] != '/':
333
raise InventoryDeltaError(
334
"oldpath invalid (does not start with /): %r"
337
oldpath_utf8 = oldpath_utf8[1:]
338
oldpath = oldpath_utf8.decode('utf8')
339
if newpath_utf8 == 'None':
341
elif newpath_utf8[:1] != '/':
342
raise InventoryDeltaError(
343
"newpath invalid (does not start with /): %r"
347
newpath_utf8 = newpath_utf8[1:]
348
newpath = newpath_utf8.decode('utf8')
349
content_tuple = tuple(content.split('\x00'))
350
if content_tuple[0] == 'deleted':
353
entry = _parse_entry(
354
newpath, file_id, parent_id, last_modified, content_tuple)
355
delta_item = (oldpath, newpath, file_id, entry)
356
result.append(delta_item)
357
return (delta_parent_id, delta_version_id, delta_versioned_root,
358
delta_tree_references, result)
361
def _parse_entry(path, file_id, parent_id, last_modified, content):
363
'dir': _dir_to_entry,
364
'file': _file_to_entry,
365
'link': _link_to_entry,
366
'tree': _tree_to_entry,
369
if path.startswith('/'):
371
name = basename(path)
372
return entry_factory[content[0]](
373
content, name, parent_id, file_id, last_modified)
added
removed
bzrlib/inventory_delta.py
