202
191
self.random_revid = False
204
def will_record_deletes(self):
205
"""Tell the commit builder that deletes are being notified.
207
This enables the accumulation of an inventory delta; for the resulting
208
commit to be valid, deletes against the basis MUST be recorded via
209
builder.record_delete().
211
raise NotImplementedError(self.will_record_deletes)
213
def record_iter_changes(self, tree, basis_revision_id, iter_changes):
214
"""Record a new tree via iter_changes.
216
:param tree: The tree to obtain text contents from for changed objects.
217
:param basis_revision_id: The revision id of the tree the iter_changes
218
has been generated against. Currently assumed to be the same
219
as self.parents[0] - if it is not, errors may occur.
220
:param iter_changes: An iter_changes iterator with the changes to apply
221
to basis_revision_id. The iterator must not include any items with
222
a current kind of None - missing items must be either filtered out
223
or errored-on beefore record_iter_changes sees the item.
224
:return: A generator of (file_id, relpath, fs_hash) tuples for use with
227
raise NotImplementedError(self.record_iter_changes)
230
class RepositoryWriteLockResult(LogicalLockResult):
231
"""The result of write locking a repository.
233
:ivar repository_token: The token obtained from the underlying lock, or
235
:ivar unlock: A callable which will unlock the lock.
238
def __init__(self, unlock, repository_token):
239
LogicalLockResult.__init__(self, unlock)
240
self.repository_token = repository_token
243
return "RepositoryWriteLockResult(%s, %s)" % (self.repository_token,
193
def _heads(self, file_id, revision_ids):
194
"""Calculate the graph heads for revision_ids in the graph of file_id.
196
This can use either a per-file graph or a global revision graph as we
197
have an identity relationship between the two graphs.
199
return self.__heads(revision_ids)
201
def _check_root(self, ie, parent_invs, tree):
202
"""Helper for record_entry_contents.
204
:param ie: An entry being added.
205
:param parent_invs: The inventories of the parent revisions of the
207
:param tree: The tree that is being committed.
209
# In this revision format, root entries have no knit or weave When
210
# serializing out to disk and back in root.revision is always
212
ie.revision = self._new_revision_id
214
def _get_delta(self, ie, basis_inv, path):
215
"""Get a delta against the basis inventory for ie."""
216
if ie.file_id not in basis_inv:
218
return (None, path, ie.file_id, ie)
219
elif ie != basis_inv[ie.file_id]:
221
# TODO: avoid tis id2path call.
222
return (basis_inv.id2path(ie.file_id), path, ie.file_id, ie)
227
def record_entry_contents(self, ie, parent_invs, path, tree,
229
"""Record the content of ie from tree into the commit if needed.
231
Side effect: sets ie.revision when unchanged
233
:param ie: An inventory entry present in the commit.
234
:param parent_invs: The inventories of the parent revisions of the
236
:param path: The path the entry is at in the tree.
237
:param tree: The tree which contains this entry and should be used to
239
:param content_summary: Summary data from the tree about the paths
240
content - stat, length, exec, sha/link target. This is only
241
accessed when the entry has a revision of None - that is when it is
242
a candidate to commit.
243
:return: A tuple (change_delta, version_recorded). change_delta is
244
an inventory_delta change for this entry against the basis tree of
245
the commit, or None if no change occured against the basis tree.
246
version_recorded is True if a new version of the entry has been
247
recorded. For instance, committing a merge where a file was only
248
changed on the other side will return (delta, False).
250
if self.new_inventory.root is None:
251
if ie.parent_id is not None:
252
raise errors.RootMissing()
253
self._check_root(ie, parent_invs, tree)
254
if ie.revision is None:
255
kind = content_summary[0]
257
# ie is carried over from a prior commit
259
# XXX: repository specific check for nested tree support goes here - if
260
# the repo doesn't want nested trees we skip it ?
261
if (kind == 'tree-reference' and
262
not self.repository._format.supports_tree_reference):
263
# mismatch between commit builder logic and repository:
264
# this needs the entry creation pushed down into the builder.
265
raise NotImplementedError('Missing repository subtree support.')
266
self.new_inventory.add(ie)
268
# TODO: slow, take it out of the inner loop.
270
basis_inv = parent_invs[0]
272
basis_inv = Inventory(root_id=None)
274
# ie.revision is always None if the InventoryEntry is considered
275
# for committing. We may record the previous parents revision if the
276
# content is actually unchanged against a sole head.
277
if ie.revision is not None:
278
if not self._versioned_root and path == '':
279
# repositories that do not version the root set the root's
280
# revision to the new commit even when no change occurs, and
281
# this masks when a change may have occurred against the basis,
282
# so calculate if one happened.
283
if ie.file_id in basis_inv:
284
delta = (basis_inv.id2path(ie.file_id), path,
288
delta = (None, path, ie.file_id, ie)
291
# we don't need to commit this, because the caller already
292
# determined that an existing revision of this file is
294
return None, (ie.revision == self._new_revision_id)
295
# XXX: Friction: parent_candidates should return a list not a dict
296
# so that we don't have to walk the inventories again.
297
parent_candiate_entries = ie.parent_candidates(parent_invs)
298
head_set = self._heads(ie.file_id, parent_candiate_entries.keys())
300
for inv in parent_invs:
301
if ie.file_id in inv:
302
old_rev = inv[ie.file_id].revision
303
if old_rev in head_set:
304
heads.append(inv[ie.file_id].revision)
305
head_set.remove(inv[ie.file_id].revision)
308
# now we check to see if we need to write a new record to the
310
# We write a new entry unless there is one head to the ancestors, and
311
# the kind-derived content is unchanged.
313
# Cheapest check first: no ancestors, or more the one head in the
314
# ancestors, we write a new node.
318
# There is a single head, look it up for comparison
319
parent_entry = parent_candiate_entries[heads[0]]
320
# if the non-content specific data has changed, we'll be writing a
322
if (parent_entry.parent_id != ie.parent_id or
323
parent_entry.name != ie.name):
325
# now we need to do content specific checks:
327
# if the kind changed the content obviously has
328
if kind != parent_entry.kind:
331
assert content_summary[2] is not None, \
332
"Files must not have executable = None"
334
if (# if the file length changed we have to store:
335
parent_entry.text_size != content_summary[1] or
336
# if the exec bit has changed we have to store:
337
parent_entry.executable != content_summary[2]):
339
elif parent_entry.text_sha1 == content_summary[3]:
340
# all meta and content is unchanged (using a hash cache
341
# hit to check the sha)
342
ie.revision = parent_entry.revision
343
ie.text_size = parent_entry.text_size
344
ie.text_sha1 = parent_entry.text_sha1
345
ie.executable = parent_entry.executable
346
return self._get_delta(ie, basis_inv, path), False
348
# Either there is only a hash change(no hash cache entry,
349
# or same size content change), or there is no change on
351
# Provide the parent's hash to the store layer, so that the
352
# content is unchanged we will not store a new node.
353
nostore_sha = parent_entry.text_sha1
355
# We want to record a new node regardless of the presence or
356
# absence of a content change in the file.
358
ie.executable = content_summary[2]
359
lines = tree.get_file(ie.file_id, path).readlines()
361
ie.text_sha1, ie.text_size = self._add_text_to_weave(
362
ie.file_id, lines, heads, nostore_sha)
363
except errors.ExistingContent:
364
# Turns out that the file content was unchanged, and we were
365
# only going to store a new node if it was changed. Carry over
367
ie.revision = parent_entry.revision
368
ie.text_size = parent_entry.text_size
369
ie.text_sha1 = parent_entry.text_sha1
370
ie.executable = parent_entry.executable
371
return self._get_delta(ie, basis_inv, path), False
372
elif kind == 'directory':
374
# all data is meta here, nothing specific to directory, so
376
ie.revision = parent_entry.revision
377
return self._get_delta(ie, basis_inv, path), False
379
self._add_text_to_weave(ie.file_id, lines, heads, None)
380
elif kind == 'symlink':
381
current_link_target = content_summary[3]
383
# symlink target is not generic metadata, check if it has
385
if current_link_target != parent_entry.symlink_target:
388
# unchanged, carry over.
389
ie.revision = parent_entry.revision
390
ie.symlink_target = parent_entry.symlink_target
391
return self._get_delta(ie, basis_inv, path), False
392
ie.symlink_target = current_link_target
394
self._add_text_to_weave(ie.file_id, lines, heads, None)
395
elif kind == 'tree-reference':
397
if content_summary[3] != parent_entry.reference_revision:
400
# unchanged, carry over.
401
ie.reference_revision = parent_entry.reference_revision
402
ie.revision = parent_entry.revision
403
return self._get_delta(ie, basis_inv, path), False
404
ie.reference_revision = content_summary[3]
406
self._add_text_to_weave(ie.file_id, lines, heads, None)
408
raise NotImplementedError('unknown kind')
409
ie.revision = self._new_revision_id
410
return self._get_delta(ie, basis_inv, path), True
412
def _add_text_to_weave(self, file_id, new_lines, parents, nostore_sha):
413
versionedfile = self.repository.weave_store.get_weave_or_empty(
414
file_id, self.repository.get_transaction())
415
# Don't change this to add_lines - add_lines_with_ghosts is cheaper
416
# than add_lines, and allows committing when a parent is ghosted for
418
# Note: as we read the content directly from the tree, we know its not
419
# been turned into unicode or badly split - but a broken tree
420
# implementation could give us bad output from readlines() so this is
421
# not a guarantee of safety. What would be better is always checking
422
# the content during test suite execution. RBC 20070912
424
return versionedfile.add_lines_with_ghosts(
425
self._new_revision_id, parents, new_lines,
426
nostore_sha=nostore_sha, random_id=self.random_revid,
427
check_content=False)[0:2]
429
versionedfile.clear_cache()
432
class RootCommitBuilder(CommitBuilder):
433
"""This commitbuilder actually records the root id"""
435
# the root entry gets versioned properly by this builder.
436
_versioned_root = True
438
def _check_root(self, ie, parent_invs, tree):
439
"""Helper for record_entry_contents.
441
:param ie: An entry being added.
442
:param parent_invs: The inventories of the parent revisions of the
444
:param tree: The tree that is being committed.
247
448
######################################################################
251
class Repository(_RelockDebugMixin, controldir.ControlComponent):
451
class Repository(object):
252
452
"""Repository holding history for one or more branches.
254
454
The repository holds and retrieves historical information including
255
455
revisions and file history. It's normally accessed only by the Branch,
256
456
which views a particular line of development through that history.
258
See VersionedFileRepository in bzrlib.vf_repository for the
259
base class for most Bazaar repositories.
458
The Repository builds on top of Stores and a Transport, which respectively
459
describe the disk data format and the way of accessing the (possibly
262
def abort_write_group(self, suppress_errors=False):
463
# What class to use for a CommitBuilder. Often its simpler to change this
464
# in a Repository class subclass rather than to override
465
# get_commit_builder.
466
_commit_builder_class = CommitBuilder
467
# The search regex used by xml based repositories to determine what things
468
# where changed in a single commit.
469
_file_ids_altered_regex = lazy_regex.lazy_compile(
470
r'file_id="(?P<file_id>[^"]+)"'
471
r'.* revision="(?P<revision_id>[^"]+)"'
474
def abort_write_group(self):
263
475
"""Commit the contents accrued within the current write group.
265
:param suppress_errors: if true, abort_write_group will catch and log
266
unexpected errors that happen during the abort, rather than
267
allowing them to propagate. Defaults to False.
269
477
:seealso: start_write_group.
271
479
if self._write_group is not self.get_transaction():
272
480
# has an unlock or relock occured ?
275
'(suppressed) mismatched lock context and write group. %r, %r',
276
self._write_group, self.get_transaction())
278
raise errors.BzrError(
279
'mismatched lock context and write group. %r, %r' %
280
(self._write_group, self.get_transaction()))
282
self._abort_write_group()
283
except Exception, exc:
284
self._write_group = None
285
if not suppress_errors:
287
mutter('abort_write_group failed')
288
log_exception_quietly()
289
note(gettext('bzr: ERROR (ignored): %s'), exc)
481
raise errors.BzrError('mismatched lock context and write group.')
482
self._abort_write_group()
290
483
self._write_group = None
292
485
def _abort_write_group(self):
293
486
"""Template method for per-repository write group cleanup.
295
This is called during abort before the write group is considered to be
488
This is called during abort before the write group is considered to be
296
489
finished and should cleanup any internal state accrued during the write
297
490
group. There is no requirement that data handed to the repository be
298
491
*not* made available - this is not a rollback - but neither should any
817
977
def has_revision(self, revision_id):
818
978
"""True if this repository has a copy of the revision."""
819
return revision_id in self.has_revisions((revision_id,))
822
def has_revisions(self, revision_ids):
823
"""Probe to find out the presence of multiple revisions.
825
:param revision_ids: An iterable of revision_ids.
826
:return: A set of the revision_ids that were present.
828
raise NotImplementedError(self.has_revisions)
979
if 'evil' in debug.debug_flags:
980
mutter_callsite(3, "has_revision is a LBYL symptom.")
981
return self._revision_store.has_revision_id(revision_id,
982
self.get_transaction())
831
985
def get_revision(self, revision_id):
832
986
"""Return the Revision object for a named revision."""
833
987
return self.get_revisions([revision_id])[0]
835
990
def get_revision_reconcile(self, revision_id):
836
991
"""'reconcile' helper routine that allows access to a revision always.
838
993
This variant of get_revision does not cross check the weave graph
839
994
against the revision one as get_revision does: but it should only
840
995
be used by reconcile, or reconcile-alike commands that are correcting
841
996
or testing the revision graph.
843
raise NotImplementedError(self.get_revision_reconcile)
998
return self._get_revisions([revision_id])[0]
845
1001
def get_revisions(self, revision_ids):
846
"""Get many revisions at once.
848
Repositories that need to check data on every revision read should
849
subclass this method.
851
raise NotImplementedError(self.get_revisions)
853
def get_deltas_for_revisions(self, revisions, specific_fileids=None):
1002
"""Get many revisions at once."""
1003
return self._get_revisions(revision_ids)
1006
def _get_revisions(self, revision_ids):
1007
"""Core work logic to get many revisions without sanity checks."""
1008
for rev_id in revision_ids:
1009
if not rev_id or not isinstance(rev_id, basestring):
1010
raise errors.InvalidRevisionId(revision_id=rev_id, branch=self)
1011
revs = self._revision_store.get_revisions(revision_ids,
1012
self.get_transaction())
1014
assert not isinstance(rev.revision_id, unicode)
1015
for parent_id in rev.parent_ids:
1016
assert not isinstance(parent_id, unicode)
1020
def get_revision_xml(self, revision_id):
1021
# TODO: jam 20070210 This shouldn't be necessary since get_revision
1022
# would have already do it.
1023
# TODO: jam 20070210 Just use _serializer.write_revision_to_string()
1024
rev = self.get_revision(revision_id)
1025
rev_tmp = StringIO()
1026
# the current serializer..
1027
self._revision_store._serializer.write_revision(rev, rev_tmp)
1029
return rev_tmp.getvalue()
1032
def get_deltas_for_revisions(self, revisions):
854
1033
"""Produce a generator of revision deltas.
856
1035
Note that the input is a sequence of REVISIONS, not revision_ids.
857
1036
Trees will be held in memory until the generator exits.
858
1037
Each delta is relative to the revision's lefthand predecessor.
860
:param specific_fileids: if not None, the result is filtered
861
so that only those file-ids, their parents and their
862
children are included.
864
# Get the revision-ids of interest
865
1039
required_trees = set()
866
1040
for revision in revisions:
867
1041
required_trees.add(revision.revision_id)
868
1042
required_trees.update(revision.parent_ids[:1])
870
# Get the matching filtered trees. Note that it's more
871
# efficient to pass filtered trees to changes_from() rather
872
# than doing the filtering afterwards. changes_from() could
873
# arguably do the filtering itself but it's path-based, not
874
# file-id based, so filtering before or afterwards is
876
if specific_fileids is None:
877
trees = dict((t.get_revision_id(), t) for
878
t in self.revision_trees(required_trees))
880
trees = dict((t.get_revision_id(), t) for
881
t in self._filtered_revision_trees(required_trees,
884
# Calculate the deltas
1043
trees = dict((t.get_revision_id(), t) for
1044
t in self.revision_trees(required_trees))
885
1045
for revision in revisions:
886
1046
if not revision.parent_ids:
887
old_tree = self.revision_tree(_mod_revision.NULL_REVISION)
1047
old_tree = self.revision_tree(None)
889
1049
old_tree = trees[revision.parent_ids[0]]
890
1050
yield trees[revision.revision_id].changes_from(old_tree)
892
1052
@needs_read_lock
893
def get_revision_delta(self, revision_id, specific_fileids=None):
1053
def get_revision_delta(self, revision_id):
894
1054
"""Return the delta for one revision.
896
1056
The delta is relative to the left-hand predecessor of the
899
:param specific_fileids: if not None, the result is filtered
900
so that only those file-ids, their parents and their
901
children are included.
903
1059
r = self.get_revision(revision_id)
904
return list(self.get_deltas_for_revisions([r],
905
specific_fileids=specific_fileids))[0]
1060
return list(self.get_deltas_for_revisions([r]))[0]
907
1062
@needs_write_lock
908
1063
def store_revision_signature(self, gpg_strategy, plaintext, revision_id):
909
1064
signature = gpg_strategy.sign(plaintext)
910
1065
self.add_signature_text(revision_id, signature)
912
1068
def add_signature_text(self, revision_id, signature):
913
"""Store a signature text for a revision.
915
:param revision_id: Revision id of the revision
916
:param signature: Signature text.
918
raise NotImplementedError(self.add_signature_text)
920
def _find_parent_ids_of_revisions(self, revision_ids):
921
"""Find all parent ids that are mentioned in the revision graph.
923
:return: set of revisions that are parents of revision_ids which are
924
not part of revision_ids themselves
926
parent_map = self.get_parent_map(revision_ids)
928
map(parent_ids.update, parent_map.itervalues())
929
parent_ids.difference_update(revision_ids)
930
parent_ids.discard(_mod_revision.NULL_REVISION)
1069
self._revision_store.add_revision_signature_text(revision_id,
1071
self.get_transaction())
1073
def find_text_key_references(self):
1074
"""Find the text key references within the repository.
1076
:return: a dictionary mapping (file_id, revision_id) tuples to altered file-ids to an iterable of
1077
revision_ids. Each altered file-ids has the exact revision_ids that
1078
altered it listed explicitly.
1079
:return: A dictionary mapping text keys ((fileid, revision_id) tuples)
1080
to whether they were referred to by the inventory of the
1081
revision_id that they contain. The inventory texts from all present
1082
revision ids are assessed to generate this report.
1084
revision_ids = self.all_revision_ids()
1085
w = self.get_inventory_weave()
1086
pb = ui.ui_factory.nested_progress_bar()
1088
return self._find_text_key_references_from_xml_inventory_lines(
1089
w.iter_lines_added_or_present_in_versions(revision_ids, pb=pb))
1093
def _find_text_key_references_from_xml_inventory_lines(self,
1095
"""Core routine for extracting references to texts from inventories.
1097
This performs the translation of xml lines to revision ids.
1099
:param line_iterator: An iterator of lines, origin_version_id
1100
:return: A dictionary mapping text keys ((fileid, revision_id) tuples)
1101
to whether they were referred to by the inventory of the
1102
revision_id that they contain. Note that if that revision_id was
1103
not part of the line_iterator's output then False will be given -
1104
even though it may actually refer to that key.
1106
if not self._serializer.support_altered_by_hack:
1107
raise AssertionError(
1108
"_find_text_key_references_from_xml_inventory_lines only "
1109
"supported for branches which store inventory as unnested xml"
1110
", not on %r" % self)
1113
# this code needs to read every new line in every inventory for the
1114
# inventories [revision_ids]. Seeing a line twice is ok. Seeing a line
1115
# not present in one of those inventories is unnecessary but not
1116
# harmful because we are filtering by the revision id marker in the
1117
# inventory lines : we only select file ids altered in one of those
1118
# revisions. We don't need to see all lines in the inventory because
1119
# only those added in an inventory in rev X can contain a revision=X
1121
unescape_revid_cache = {}
1122
unescape_fileid_cache = {}
1124
# jam 20061218 In a big fetch, this handles hundreds of thousands
1125
# of lines, so it has had a lot of inlining and optimizing done.
1126
# Sorry that it is a little bit messy.
1127
# Move several functions to be local variables, since this is a long
1129
search = self._file_ids_altered_regex.search
1130
unescape = _unescape_xml
1131
setdefault = result.setdefault
1132
for line, version_id in line_iterator:
1133
match = search(line)
1136
# One call to match.group() returning multiple items is quite a
1137
# bit faster than 2 calls to match.group() each returning 1
1138
file_id, revision_id = match.group('file_id', 'revision_id')
1140
# Inlining the cache lookups helps a lot when you make 170,000
1141
# lines and 350k ids, versus 8.4 unique ids.
1142
# Using a cache helps in 2 ways:
1143
# 1) Avoids unnecessary decoding calls
1144
# 2) Re-uses cached strings, which helps in future set and
1146
# (2) is enough that removing encoding entirely along with
1147
# the cache (so we are using plain strings) results in no
1148
# performance improvement.
1150
revision_id = unescape_revid_cache[revision_id]
1152
unescaped = unescape(revision_id)
1153
unescape_revid_cache[revision_id] = unescaped
1154
revision_id = unescaped
1156
# Note that unconditionally unescaping means that we deserialise
1157
# every fileid, which for general 'pull' is not great, but we don't
1158
# really want to have some many fulltexts that this matters anyway.
1161
file_id = unescape_fileid_cache[file_id]
1163
unescaped = unescape(file_id)
1164
unescape_fileid_cache[file_id] = unescaped
1167
key = (file_id, revision_id)
1168
setdefault(key, False)
1169
if revision_id == version_id:
1173
def _find_file_ids_from_xml_inventory_lines(self, line_iterator,
1175
"""Helper routine for fileids_altered_by_revision_ids.
1177
This performs the translation of xml lines to revision ids.
1179
:param line_iterator: An iterator of lines, origin_version_id
1180
:param revision_ids: The revision ids to filter for. This should be a
1181
set or other type which supports efficient __contains__ lookups, as
1182
the revision id from each parsed line will be looked up in the
1183
revision_ids filter.
1184
:return: a dictionary mapping altered file-ids to an iterable of
1185
revision_ids. Each altered file-ids has the exact revision_ids that
1186
altered it listed explicitly.
1189
setdefault = result.setdefault
1190
for file_id, revision_id in \
1191
self._find_text_key_references_from_xml_inventory_lines(
1192
line_iterator).iterkeys():
1193
# once data is all ensured-consistent; then this is
1194
# if revision_id == version_id
1195
if revision_id in revision_ids:
1196
setdefault(file_id, set()).add(revision_id)
1199
def fileids_altered_by_revision_ids(self, revision_ids):
1200
"""Find the file ids and versions affected by revisions.
1202
:param revisions: an iterable containing revision ids.
1203
:return: a dictionary mapping altered file-ids to an iterable of
1204
revision_ids. Each altered file-ids has the exact revision_ids that
1205
altered it listed explicitly.
1207
selected_revision_ids = set(revision_ids)
1208
w = self.get_inventory_weave()
1209
pb = ui.ui_factory.nested_progress_bar()
1211
return self._find_file_ids_from_xml_inventory_lines(
1212
w.iter_lines_added_or_present_in_versions(
1213
selected_revision_ids, pb=pb),
1214
selected_revision_ids)
933
1218
def iter_files_bytes(self, desired_files):
934
1219
"""Iterate through file versions.
941
1226
uniquely identify the file version in the caller's context. (Examples:
942
1227
an index number or a TreeTransform trans_id.)
1229
bytes_iterator is an iterable of bytestrings for the file. The
1230
kind of iterable and length of the bytestrings are unspecified, but for
1231
this implementation, it is a list of lines produced by
1232
VersionedFile.get_lines().
944
1234
:param desired_files: a list of (file_id, revision_id, identifier)
947
raise NotImplementedError(self.iter_files_bytes)
949
def get_rev_id_for_revno(self, revno, known_pair):
950
"""Return the revision id of a revno, given a later (revno, revid)
951
pair in the same history.
953
:return: if found (True, revid). If the available history ran out
954
before reaching the revno, then this returns
955
(False, (closest_revno, closest_revid)).
957
known_revno, known_revid = known_pair
958
partial_history = [known_revid]
959
distance_from_known = known_revno - revno
960
if distance_from_known < 0:
962
'requested revno (%d) is later than given known revno (%d)'
963
% (revno, known_revno))
966
self, partial_history, stop_index=distance_from_known)
967
except errors.RevisionNotPresent, err:
968
if err.revision_id == known_revid:
969
# The start revision (known_revid) wasn't found.
971
# This is a stacked repository with no fallbacks, or a there's a
972
# left-hand ghost. Either way, even though the revision named in
973
# the error isn't in this repo, we know it's the next step in this
975
partial_history.append(err.revision_id)
976
if len(partial_history) <= distance_from_known:
977
# Didn't find enough history to get a revid for the revno.
978
earliest_revno = known_revno - len(partial_history) + 1
979
return (False, (earliest_revno, partial_history[-1]))
980
if len(partial_history) - 1 > distance_from_known:
981
raise AssertionError('_iter_for_revno returned too much history')
982
return (True, partial_history[-1])
1237
transaction = self.get_transaction()
1238
for file_id, revision_id, callable_data in desired_files:
1240
weave = self.weave_store.get_weave(file_id, transaction)
1241
except errors.NoSuchFile:
1242
raise errors.NoSuchIdInRepository(self, file_id)
1243
yield callable_data, weave.get_lines(revision_id)
1245
def _generate_text_key_index(self, text_key_references=None,
1247
"""Generate a new text key index for the repository.
1249
This is an expensive function that will take considerable time to run.
1251
:return: A dict mapping text keys ((file_id, revision_id) tuples) to a
1252
list of parents, also text keys. When a given key has no parents,
1253
the parents list will be [NULL_REVISION].
1255
# All revisions, to find inventory parents.
1256
if ancestors is None:
1257
revision_graph = self.get_revision_graph_with_ghosts()
1258
ancestors = revision_graph.get_ancestors()
1259
if text_key_references is None:
1260
text_key_references = self.find_text_key_references()
1261
pb = ui.ui_factory.nested_progress_bar()
1263
return self._do_generate_text_key_index(ancestors,
1264
text_key_references, pb)
1268
def _do_generate_text_key_index(self, ancestors, text_key_references, pb):
1269
"""Helper for _generate_text_key_index to avoid deep nesting."""
1270
revision_order = tsort.topo_sort(ancestors)
1271
invalid_keys = set()
1273
for revision_id in revision_order:
1274
revision_keys[revision_id] = set()
1275
text_count = len(text_key_references)
1276
# a cache of the text keys to allow reuse; costs a dict of all the
1277
# keys, but saves a 2-tuple for every child of a given key.
1279
for text_key, valid in text_key_references.iteritems():
1281
invalid_keys.add(text_key)
1283
revision_keys[text_key[1]].add(text_key)
1284
text_key_cache[text_key] = text_key
1285
del text_key_references
1287
text_graph = graph.Graph(graph.DictParentsProvider(text_index))
1288
NULL_REVISION = _mod_revision.NULL_REVISION
1289
# Set a cache with a size of 10 - this suffices for bzr.dev but may be
1290
# too small for large or very branchy trees. However, for 55K path
1291
# trees, it would be easy to use too much memory trivially. Ideally we
1292
# could gauge this by looking at available real memory etc, but this is
1293
# always a tricky proposition.
1294
inventory_cache = lru_cache.LRUCache(10)
1295
batch_size = 10 # should be ~150MB on a 55K path tree
1296
batch_count = len(revision_order) / batch_size + 1
1298
pb.update("Calculating text parents.", processed_texts, text_count)
1299
for offset in xrange(batch_count):
1300
to_query = revision_order[offset * batch_size:(offset + 1) *
1304
for rev_tree in self.revision_trees(to_query):
1305
revision_id = rev_tree.get_revision_id()
1306
parent_ids = ancestors[revision_id]
1307
for text_key in revision_keys[revision_id]:
1308
pb.update("Calculating text parents.", processed_texts)
1309
processed_texts += 1
1310
candidate_parents = []
1311
for parent_id in parent_ids:
1312
parent_text_key = (text_key[0], parent_id)
1314
check_parent = parent_text_key not in \
1315
revision_keys[parent_id]
1317
# the parent parent_id is a ghost:
1318
check_parent = False
1319
# truncate the derived graph against this ghost.
1320
parent_text_key = None
1322
# look at the parent commit details inventories to
1323
# determine possible candidates in the per file graph.
1326
inv = inventory_cache[parent_id]
1328
inv = self.revision_tree(parent_id).inventory
1329
inventory_cache[parent_id] = inv
1330
parent_entry = inv._byid.get(text_key[0], None)
1331
if parent_entry is not None:
1333
text_key[0], parent_entry.revision)
1335
parent_text_key = None
1336
if parent_text_key is not None:
1337
candidate_parents.append(
1338
text_key_cache[parent_text_key])
1339
parent_heads = text_graph.heads(candidate_parents)
1340
new_parents = list(parent_heads)
1341
new_parents.sort(key=lambda x:candidate_parents.index(x))
1342
if new_parents == []:
1343
new_parents = [NULL_REVISION]
1344
text_index[text_key] = new_parents
1346
for text_key in invalid_keys:
1347
text_index[text_key] = [NULL_REVISION]
1350
def item_keys_introduced_by(self, revision_ids, _files_pb=None):
1351
"""Get an iterable listing the keys of all the data introduced by a set
1354
The keys will be ordered so that the corresponding items can be safely
1355
fetched and inserted in that order.
1357
:returns: An iterable producing tuples of (knit-kind, file-id,
1358
versions). knit-kind is one of 'file', 'inventory', 'signatures',
1359
'revisions'. file-id is None unless knit-kind is 'file'.
1361
# XXX: it's a bit weird to control the inventory weave caching in this
1362
# generator. Ideally the caching would be done in fetch.py I think. Or
1363
# maybe this generator should explicitly have the contract that it
1364
# should not be iterated until the previously yielded item has been
1367
inv_w = self.get_inventory_weave()
1368
inv_w.enable_cache()
1370
# file ids that changed
1371
file_ids = self.fileids_altered_by_revision_ids(revision_ids)
1373
num_file_ids = len(file_ids)
1374
for file_id, altered_versions in file_ids.iteritems():
1375
if _files_pb is not None:
1376
_files_pb.update("fetch texts", count, num_file_ids)
1378
yield ("file", file_id, altered_versions)
1379
# We're done with the files_pb. Note that it finished by the caller,
1380
# just as it was created by the caller.
1384
yield ("inventory", None, revision_ids)
1388
revisions_with_signatures = set()
1389
for rev_id in revision_ids:
1391
self.get_signature_text(rev_id)
1392
except errors.NoSuchRevision:
1396
revisions_with_signatures.add(rev_id)
1398
yield ("signatures", None, revisions_with_signatures)
1401
yield ("revisions", None, revision_ids)
1404
def get_inventory_weave(self):
1405
return self.control_weaves.get_weave('inventory',
1406
self.get_transaction())
1409
def get_inventory(self, revision_id):
1410
"""Get Inventory object by hash."""
1411
return self.deserialise_inventory(
1412
revision_id, self.get_inventory_xml(revision_id))
1414
def deserialise_inventory(self, revision_id, xml):
1415
"""Transform the xml into an inventory object.
1417
:param revision_id: The expected revision id of the inventory.
1418
:param xml: A serialised inventory.
1420
return self._serializer.read_inventory_from_string(xml, revision_id)
1422
def serialise_inventory(self, inv):
1423
return self._serializer.write_inventory_to_string(inv)
1425
def _serialise_inventory_to_lines(self, inv):
1426
return self._serializer.write_inventory_to_lines(inv)
1428
def get_serializer_format(self):
1429
return self._serializer.format_num
1432
def get_inventory_xml(self, revision_id):
1433
"""Get inventory XML as a file object."""
1435
assert isinstance(revision_id, str), type(revision_id)
1436
iw = self.get_inventory_weave()
1437
return iw.get_text(revision_id)
1439
raise errors.HistoryMissing(self, 'inventory', revision_id)
1442
def get_inventory_sha1(self, revision_id):
1443
"""Return the sha1 hash of the inventory entry
1445
return self.get_revision(revision_id).inventory_sha1
1448
def get_revision_graph(self, revision_id=None):
1449
"""Return a dictionary containing the revision graph.
1451
NB: This method should not be used as it accesses the entire graph all
1452
at once, which is much more data than most operations should require.
1454
:param revision_id: The revision_id to get a graph from. If None, then
1455
the entire revision graph is returned. This is a deprecated mode of
1456
operation and will be removed in the future.
1457
:return: a dictionary of revision_id->revision_parents_list.
1459
raise NotImplementedError(self.get_revision_graph)
1462
def get_revision_graph_with_ghosts(self, revision_ids=None):
1463
"""Return a graph of the revisions with ghosts marked as applicable.
1465
:param revision_ids: an iterable of revisions to graph or None for all.
1466
:return: a Graph object with the graph reachable from revision_ids.
1468
if 'evil' in debug.debug_flags:
1470
"get_revision_graph_with_ghosts scales with size of history.")
1471
result = deprecated_graph.Graph()
1472
if not revision_ids:
1473
pending = set(self.all_revision_ids())
1476
pending = set(revision_ids)
1477
# special case NULL_REVISION
1478
if _mod_revision.NULL_REVISION in pending:
1479
pending.remove(_mod_revision.NULL_REVISION)
1480
required = set(pending)
1483
revision_id = pending.pop()
1485
rev = self.get_revision(revision_id)
1486
except errors.NoSuchRevision:
1487
if revision_id in required:
1490
result.add_ghost(revision_id)
1492
for parent_id in rev.parent_ids:
1493
# is this queued or done ?
1494
if (parent_id not in pending and
1495
parent_id not in done):
1497
pending.add(parent_id)
1498
result.add_node(revision_id, rev.parent_ids)
1499
done.add(revision_id)
1502
def _get_history_vf(self):
1503
"""Get a versionedfile whose history graph reflects all revisions.
1505
For weave repositories, this is the inventory weave.
1507
return self.get_inventory_weave()
1509
def iter_reverse_revision_history(self, revision_id):
1510
"""Iterate backwards through revision ids in the lefthand history
1512
:param revision_id: The revision id to start with. All its lefthand
1513
ancestors will be traversed.
1515
if revision_id in (None, _mod_revision.NULL_REVISION):
1517
next_id = revision_id
1518
versionedfile = self._get_history_vf()
1521
parents = versionedfile.get_parents(next_id)
1522
if len(parents) == 0:
1525
next_id = parents[0]
1528
def get_revision_inventory(self, revision_id):
1529
"""Return inventory of a past revision."""
1530
# TODO: Unify this with get_inventory()
1531
# bzr 0.0.6 and later imposes the constraint that the inventory_id
1532
# must be the same as its revision, so this is trivial.
1533
if revision_id is None:
1534
# This does not make sense: if there is no revision,
1535
# then it is the current tree inventory surely ?!
1536
# and thus get_root_id() is something that looks at the last
1537
# commit on the branch, and the get_root_id is an inventory check.
1538
raise NotImplementedError
1539
# return Inventory(self.get_root_id())
1541
return self.get_inventory(revision_id)
984
1544
def is_shared(self):
985
1545
"""Return True if this repository is flagged as a shared repository."""
986
1546
raise NotImplementedError(self.is_shared)
1000
1560
for repositories to maintain loaded indices across multiple locks
1001
1561
by checking inside their implementation of this method to see
1002
1562
whether their indices are still valid. This depends of course on
1003
the disk format being validatable in this manner. This method is
1004
also called by the refresh_data() public interface to cause a refresh
1005
to occur while in a write lock so that data inserted by a smart server
1006
push operation is visible on the client's instance of the physical
1563
the disk format being validatable in this manner.
1010
1566
@needs_read_lock
1011
1567
def revision_tree(self, revision_id):
1012
1568
"""Return Tree for a revision on this branch.
1014
`revision_id` may be NULL_REVISION for the empty tree revision.
1570
`revision_id` may be None for the empty tree revision.
1016
raise NotImplementedError(self.revision_tree)
1572
# TODO: refactor this to use an existing revision object
1573
# so we don't need to read it in twice.
1574
if revision_id is None or revision_id == _mod_revision.NULL_REVISION:
1575
return RevisionTree(self, Inventory(root_id=None),
1576
_mod_revision.NULL_REVISION)
1578
inv = self.get_revision_inventory(revision_id)
1579
return RevisionTree(self, inv, revision_id)
1018
1582
def revision_trees(self, revision_ids):
1019
"""Return Trees for revisions in this repository.
1021
:param revision_ids: a sequence of revision-ids;
1022
a revision-id may not be None or 'null:'
1583
"""Return Tree for a revision on this branch.
1585
`revision_id` may not be None or 'null:'"""
1586
assert None not in revision_ids
1587
assert _mod_revision.NULL_REVISION not in revision_ids
1588
texts = self.get_inventory_weave().get_texts(revision_ids)
1589
for text, revision_id in zip(texts, revision_ids):
1590
inv = self.deserialise_inventory(revision_id, text)
1591
yield RevisionTree(self, inv, revision_id)
1594
def get_ancestry(self, revision_id, topo_sorted=True):
1595
"""Return a list of revision-ids integrated by a revision.
1597
The first element of the list is always None, indicating the origin
1598
revision. This might change when we have history horizons, or
1599
perhaps we should have a new API.
1601
This is topologically sorted.
1024
raise NotImplementedError(self.revision_trees)
1603
if _mod_revision.is_null(revision_id):
1605
if not self.has_revision(revision_id):
1606
raise errors.NoSuchRevision(self, revision_id)
1607
w = self.get_inventory_weave()
1608
candidates = w.get_ancestry(revision_id, topo_sorted)
1609
return [None] + candidates # self._eliminate_revisions_not_present(candidates)
1026
def pack(self, hint=None, clean_obsolete_packs=False):
1027
1612
"""Compress the data within the repository.
1029
1614
This operation only makes sense for some repository types. For other
1030
1615
types it should be a no-op that just returns.
1032
1617
This stub method does not require a lock, but subclasses should use
1033
@needs_write_lock as this is a long running call it's reasonable to
1618
@needs_write_lock as this is a long running call its reasonable to
1034
1619
implicitly lock for the user.
1036
:param hint: If not supplied, the whole repository is packed.
1037
If supplied, the repository may use the hint parameter as a
1038
hint for the parts of the repository to pack. A hint can be
1039
obtained from the result of commit_write_group(). Out of
1040
date hints are simply ignored, because concurrent operations
1041
can obsolete them rapidly.
1043
:param clean_obsolete_packs: Clean obsolete packs immediately after
1623
def print_file(self, file, revision_id):
1624
"""Print `file` to stdout.
1626
FIXME RBC 20060125 as John Meinel points out this is a bad api
1627
- it writes to stdout, it assumes that that is valid etc. Fix
1628
by creating a new more flexible convenience function.
1630
tree = self.revision_tree(revision_id)
1631
# use inventory as it was in that revision
1632
file_id = tree.inventory.path2id(file)
1634
# TODO: jam 20060427 Write a test for this code path
1635
# it had a bug in it, and was raising the wrong
1637
raise errors.BzrError("%r is not present in revision %s" % (file, revision_id))
1638
tree.print_file(file_id)
1047
1640
def get_transaction(self):
1048
1641
return self.control_files.get_transaction()
1050
def get_parent_map(self, revision_ids):
1051
"""See graph.StackedParentsProvider.get_parent_map"""
1052
raise NotImplementedError(self.get_parent_map)
1643
def revision_parents(self, revision_id):
1644
return self.get_inventory_weave().parent_names(revision_id)
1054
def _get_parent_map_no_fallbacks(self, revision_ids):
1055
"""Same as Repository.get_parent_map except doesn't query fallbacks."""
1056
# revisions index works in keys; this just works in revisions
1057
# therefore wrap and unwrap
1646
def get_parents(self, revision_ids):
1647
"""See StackedParentsProvider.get_parents"""
1060
1649
for revision_id in revision_ids:
1061
1650
if revision_id == _mod_revision.NULL_REVISION:
1062
result[revision_id] = ()
1063
elif revision_id is None:
1064
raise ValueError('get_parent_map(None) is not valid')
1066
query_keys.append((revision_id ,))
1067
vf = self.revisions.without_fallbacks()
1068
for ((revision_id,), parent_keys) in \
1069
vf.get_parent_map(query_keys).iteritems():
1071
result[revision_id] = tuple([parent_revid
1072
for (parent_revid,) in parent_keys])
1074
result[revision_id] = (_mod_revision.NULL_REVISION,)
1654
parents = self.get_revision(revision_id).parent_ids
1655
except errors.NoSuchRevision:
1658
if len(parents) == 0:
1659
parents = [_mod_revision.NULL_REVISION]
1660
parents_list.append(parents)
1077
1663
def _make_parents_provider(self):
1078
if not self._format.supports_external_lookups:
1080
return graph.StackedParentsProvider(_LazyListJoin(
1081
[self._make_parents_provider_unstacked()],
1082
self._fallback_repositories))
1084
def _make_parents_provider_unstacked(self):
1085
return graph.CallableToParentsProviderAdapter(
1086
self._get_parent_map_no_fallbacks)
1089
def get_known_graph_ancestry(self, revision_ids):
1090
"""Return the known graph for a set of revision ids and their ancestors.
1092
raise NotImplementedError(self.get_known_graph_ancestry)
1094
def get_file_graph(self):
1095
"""Return the graph walker for files."""
1096
raise NotImplementedError(self.get_file_graph)
1098
1666
def get_graph(self, other_repository=None):
1099
1667
"""Return the graph walker for this repository format"""
1100
1668
parents_provider = self._make_parents_provider()
1101
1669
if (other_repository is not None and
1102
not self.has_same_location(other_repository)):
1103
parents_provider = graph.StackedParentsProvider(
1670
other_repository.bzrdir.transport.base !=
1671
self.bzrdir.transport.base):
1672
parents_provider = graph._StackedParentsProvider(
1104
1673
[parents_provider, other_repository._make_parents_provider()])
1105
1674
return graph.Graph(parents_provider)
1676
def _get_versioned_file_checker(self):
1677
"""Return an object suitable for checking versioned files."""
1678
return _VersionedFileChecker(self)
1107
1680
@needs_write_lock
1108
1681
def set_make_working_trees(self, new_value):
1109
1682
"""Set the policy flag for making working trees when creating branches.
1220
1752
revision_id.decode('ascii')
1221
1753
except UnicodeDecodeError:
1222
1754
raise errors.NonAsciiRevisionId(method, self)
1756
def revision_graph_can_have_wrong_parents(self):
1757
"""Is it possible for this repository to have a revision graph with
1760
If True, then this repository must also implement
1761
_find_inconsistent_revision_parents so that check and reconcile can
1762
check for inconsistencies before proceeding with other checks that may
1763
depend on the revision index being consistent.
1765
raise NotImplementedError(self.revision_graph_can_have_wrong_parents)
1767
# remove these delegates a while after bzr 0.15
1768
def __make_delegated(name, from_module):
1769
def _deprecated_repository_forwarder():
1770
symbol_versioning.warn('%s moved to %s in bzr 0.15'
1771
% (name, from_module),
1774
m = __import__(from_module, globals(), locals(), [name])
1776
return getattr(m, name)
1777
except AttributeError:
1778
raise AttributeError('module %s has no name %s'
1780
globals()[name] = _deprecated_repository_forwarder
1783
'AllInOneRepository',
1784
'WeaveMetaDirRepository',
1785
'PreSplitOutRepositoryFormat',
1786
'RepositoryFormat4',
1787
'RepositoryFormat5',
1788
'RepositoryFormat6',
1789
'RepositoryFormat7',
1791
__make_delegated(_name, 'bzrlib.repofmt.weaverepo')
1795
'RepositoryFormatKnit',
1796
'RepositoryFormatKnit1',
1798
__make_delegated(_name, 'bzrlib.repofmt.knitrepo')
1801
def install_revision(repository, rev, revision_tree):
1802
"""Install all revision data into a repository."""
1803
install_revisions(repository, [(rev, revision_tree, None)])
1806
def install_revisions(repository, iterable):
1807
"""Install all revision data into a repository.
1809
Accepts an iterable of revision, tree, signature tuples. The signature
1812
repository.start_write_group()
1814
for revision, revision_tree, signature in iterable:
1815
_install_revision(repository, revision, revision_tree, signature)
1817
repository.abort_write_group()
1820
repository.commit_write_group()
1823
def _install_revision(repository, rev, revision_tree, signature):
1824
"""Install all revision data into a repository."""
1825
present_parents = []
1827
for p_id in rev.parent_ids:
1828
if repository.has_revision(p_id):
1829
present_parents.append(p_id)
1830
parent_trees[p_id] = repository.revision_tree(p_id)
1832
parent_trees[p_id] = repository.revision_tree(None)
1834
inv = revision_tree.inventory
1835
entries = inv.iter_entries()
1836
# backwards compatibility hack: skip the root id.
1837
if not repository.supports_rich_root():
1838
path, root = entries.next()
1839
if root.revision != rev.revision_id:
1840
raise errors.IncompatibleRevision(repr(repository))
1841
# Add the texts that are not already present
1842
for path, ie in entries:
1843
w = repository.weave_store.get_weave_or_empty(ie.file_id,
1844
repository.get_transaction())
1845
if ie.revision not in w:
1847
# FIXME: TODO: The following loop *may* be overlapping/duplicate
1848
# with InventoryEntry.find_previous_heads(). if it is, then there
1849
# is a latent bug here where the parents may have ancestors of each
1851
for revision, tree in parent_trees.iteritems():
1852
if ie.file_id not in tree:
1854
parent_id = tree.inventory[ie.file_id].revision
1855
if parent_id in text_parents:
1857
text_parents.append(parent_id)
1859
vfile = repository.weave_store.get_weave_or_empty(ie.file_id,
1860
repository.get_transaction())
1861
lines = revision_tree.get_file(ie.file_id).readlines()
1862
vfile.add_lines(rev.revision_id, text_parents, lines)
1864
# install the inventory
1865
repository.add_inventory(rev.revision_id, inv, present_parents)
1866
except errors.RevisionAlreadyPresent:
1868
if signature is not None:
1869
repository.add_signature_text(rev.revision_id, signature)
1870
repository.add_revision(rev.revision_id, rev, inv)
1225
1873
class MetaDirRepository(Repository):
1226
"""Repositories in the new meta-dir layout.
1228
:ivar _transport: Transport for access to repository control files,
1229
typically pointing to .bzr/repository.
1232
def __init__(self, _format, a_bzrdir, control_files):
1233
super(MetaDirRepository, self).__init__(_format, a_bzrdir, control_files)
1234
self._transport = control_files._transport
1874
"""Repositories in the new meta-dir layout."""
1876
def __init__(self, _format, a_bzrdir, control_files, _revision_store, control_store, text_store):
1877
super(MetaDirRepository, self).__init__(_format,
1883
dir_mode = self.control_files._dir_mode
1884
file_mode = self.control_files._file_mode
1236
1887
def is_shared(self):
1237
1888
"""Return True if this repository is flagged as a shared repository."""
1238
return self._transport.has('shared-storage')
1889
return self.control_files._transport.has('shared-storage')
1240
1891
@needs_write_lock
1241
1892
def set_make_working_trees(self, new_value):
1632
2205
_optimisers = []
1633
2206
"""The available optimised InterRepository types."""
1636
2208
def copy_content(self, revision_id=None):
1637
"""Make a complete copy of the content in self into destination.
1639
This is a destructive operation! Do not use it on existing
1642
:param revision_id: Only copy the content needed to construct
1643
revision_id and its parents.
1646
self.target.set_make_working_trees(self.source.make_working_trees())
1647
except NotImplementedError:
1649
self.target.fetch(self.source, revision_id=revision_id)
1652
def fetch(self, revision_id=None, find_ghosts=False):
2209
raise NotImplementedError(self.copy_content)
2211
def fetch(self, revision_id=None, pb=None, find_ghosts=False):
1653
2212
"""Fetch the content required to construct revision_id.
1655
2214
The content is copied from self.source to self.target.
1657
2216
:param revision_id: if None all content is copied, if NULL_REVISION no
1658
2217
content is copied.
2218
:param pb: optional progress bar to use for progress reports. If not
2219
provided a default one will be created.
2221
Returns the copied revision count and the failed revisions in a tuple:
1661
2224
raise NotImplementedError(self.fetch)
1663
2226
@needs_read_lock
1664
def search_missing_revision_ids(self,
1665
revision_id=symbol_versioning.DEPRECATED_PARAMETER,
1666
find_ghosts=True, revision_ids=None, if_present_ids=None,
2227
def missing_revision_ids(self, revision_id=None, find_ghosts=True):
1668
2228
"""Return the revision ids that source has that target does not.
2230
These are returned in topological order.
1670
2232
:param revision_id: only return revision ids included by this
1672
:param revision_ids: return revision ids included by these
1673
revision_ids. NoSuchRevision will be raised if any of these
1674
revisions are not present.
1675
:param if_present_ids: like revision_ids, but will not cause
1676
NoSuchRevision if any of these are absent, instead they will simply
1677
not be in the result. This is useful for e.g. finding revisions
1678
to fetch for tags, which may reference absent revisions.
1679
:param find_ghosts: If True find missing revisions in deep history
1680
rather than just finding the surface difference.
1681
:param limit: Maximum number of revisions to return, topologically
1683
:return: A bzrlib.graph.SearchResult.
1685
raise NotImplementedError(self.search_missing_revision_ids)
2235
# generic, possibly worst case, slow code path.
2236
target_ids = set(self.target.all_revision_ids())
2237
if revision_id is not None:
2238
source_ids = self.source.get_ancestry(revision_id)
2239
assert source_ids[0] is None
2242
source_ids = self.source.all_revision_ids()
2243
result_set = set(source_ids).difference(target_ids)
2244
# this may look like a no-op: its not. It preserves the ordering
2245
# other_ids had while only returning the members from other_ids
2246
# that we've decided we need.
2247
return [rev_id for rev_id in source_ids if rev_id in result_set]
1688
2250
def _same_model(source, target):
1689
"""True if source and target have the same data representation.
1691
Note: this is always called on the base class; overriding it in a
1692
subclass will have no effect.
1695
InterRepository._assert_same_model(source, target)
1697
except errors.IncompatibleRepositories, e:
2251
"""True if source and target have the same data representation."""
2252
if source.supports_rich_root() != target.supports_rich_root():
1701
def _assert_same_model(source, target):
1702
"""Raise an exception if two repositories do not use the same model.
1704
if source.supports_rich_root() != target.supports_rich_root():
1705
raise errors.IncompatibleRepositories(source, target,
1706
"different rich-root support")
1707
2254
if source._serializer != target._serializer:
1708
raise errors.IncompatibleRepositories(source, target,
1709
"different serializers")
2259
class InterSameDataRepository(InterRepository):
2260
"""Code for converting between repositories that represent the same data.
2262
Data format and model must match for this to work.
2266
def _get_repo_format_to_test(self):
2267
"""Repository format for testing with.
2269
InterSameData can pull from subtree to subtree and from non-subtree to
2270
non-subtree, so we test this with the richest repository format.
2272
from bzrlib.repofmt import knitrepo
2273
return knitrepo.RepositoryFormatKnit3()
2276
def is_compatible(source, target):
2277
return InterRepository._same_model(source, target)
2280
def copy_content(self, revision_id=None):
2281
"""Make a complete copy of the content in self into destination.
2283
This copies both the repository's revision data, and configuration information
2284
such as the make_working_trees setting.
2286
This is a destructive operation! Do not use it on existing
2289
:param revision_id: Only copy the content needed to construct
2290
revision_id and its parents.
2293
self.target.set_make_working_trees(self.source.make_working_trees())
2294
except NotImplementedError:
2296
# but don't bother fetching if we have the needed data now.
2297
if (revision_id not in (None, _mod_revision.NULL_REVISION) and
2298
self.target.has_revision(revision_id)):
2300
self.target.fetch(self.source, revision_id=revision_id)
2303
def fetch(self, revision_id=None, pb=None, find_ghosts=False):
2304
"""See InterRepository.fetch()."""
2305
from bzrlib.fetch import GenericRepoFetcher
2306
mutter("Using fetch logic to copy between %s(%s) and %s(%s)",
2307
self.source, self.source._format, self.target,
2308
self.target._format)
2309
f = GenericRepoFetcher(to_repository=self.target,
2310
from_repository=self.source,
2311
last_revision=revision_id,
2313
return f.count_copied, f.failed_revisions
2316
class InterWeaveRepo(InterSameDataRepository):
2317
"""Optimised code paths between Weave based repositories.
2319
This should be in bzrlib/repofmt/weaverepo.py but we have not yet
2320
implemented lazy inter-object optimisation.
2324
def _get_repo_format_to_test(self):
2325
from bzrlib.repofmt import weaverepo
2326
return weaverepo.RepositoryFormat7()
2329
def is_compatible(source, target):
2330
"""Be compatible with known Weave formats.
2332
We don't test for the stores being of specific types because that
2333
could lead to confusing results, and there is no need to be
2336
from bzrlib.repofmt.weaverepo import (
2342
return (isinstance(source._format, (RepositoryFormat5,
2344
RepositoryFormat7)) and
2345
isinstance(target._format, (RepositoryFormat5,
2347
RepositoryFormat7)))
2348
except AttributeError:
2352
def copy_content(self, revision_id=None):
2353
"""See InterRepository.copy_content()."""
2354
# weave specific optimised path:
2356
self.target.set_make_working_trees(self.source.make_working_trees())
2357
except NotImplementedError:
2359
# FIXME do not peek!
2360
if self.source.control_files._transport.listable():
2361
pb = ui.ui_factory.nested_progress_bar()
2363
self.target.weave_store.copy_all_ids(
2364
self.source.weave_store,
2366
from_transaction=self.source.get_transaction(),
2367
to_transaction=self.target.get_transaction())
2368
pb.update('copying inventory', 0, 1)
2369
self.target.control_weaves.copy_multi(
2370
self.source.control_weaves, ['inventory'],
2371
from_transaction=self.source.get_transaction(),
2372
to_transaction=self.target.get_transaction())
2373
self.target._revision_store.text_store.copy_all_ids(
2374
self.source._revision_store.text_store,
2379
self.target.fetch(self.source, revision_id=revision_id)
2382
def fetch(self, revision_id=None, pb=None, find_ghosts=False):
2383
"""See InterRepository.fetch()."""
2384
from bzrlib.fetch import GenericRepoFetcher
2385
mutter("Using fetch logic to copy between %s(%s) and %s(%s)",
2386
self.source, self.source._format, self.target, self.target._format)
2387
f = GenericRepoFetcher(to_repository=self.target,
2388
from_repository=self.source,
2389
last_revision=revision_id,
2391
return f.count_copied, f.failed_revisions
2394
def missing_revision_ids(self, revision_id=None, find_ghosts=True):
2395
"""See InterRepository.missing_revision_ids()."""
2396
# we want all revisions to satisfy revision_id in source.
2397
# but we don't want to stat every file here and there.
2398
# we want then, all revisions other needs to satisfy revision_id
2399
# checked, but not those that we have locally.
2400
# so the first thing is to get a subset of the revisions to
2401
# satisfy revision_id in source, and then eliminate those that
2402
# we do already have.
2403
# this is slow on high latency connection to self, but as as this
2404
# disk format scales terribly for push anyway due to rewriting
2405
# inventory.weave, this is considered acceptable.
2407
if revision_id is not None:
2408
source_ids = self.source.get_ancestry(revision_id)
2409
assert source_ids[0] is None
2412
source_ids = self.source._all_possible_ids()
2413
source_ids_set = set(source_ids)
2414
# source_ids is the worst possible case we may need to pull.
2415
# now we want to filter source_ids against what we actually
2416
# have in target, but don't try to check for existence where we know
2417
# we do not have a revision as that would be pointless.
2418
target_ids = set(self.target._all_possible_ids())
2419
possibly_present_revisions = target_ids.intersection(source_ids_set)
2420
actually_present_revisions = set(self.target._eliminate_revisions_not_present(possibly_present_revisions))
2421
required_revisions = source_ids_set.difference(actually_present_revisions)
2422
required_topo_revisions = [rev_id for rev_id in source_ids if rev_id in required_revisions]
2423
if revision_id is not None:
2424
# we used get_ancestry to determine source_ids then we are assured all
2425
# revisions referenced are present as they are installed in topological order.
2426
# and the tip revision was validated by get_ancestry.
2427
return required_topo_revisions
2429
# if we just grabbed the possibly available ids, then
2430
# we only have an estimate of whats available and need to validate
2431
# that against the revision records.
2432
return self.source._eliminate_revisions_not_present(required_topo_revisions)
2435
class InterKnitRepo(InterSameDataRepository):
2436
"""Optimised code paths between Knit based repositories."""
2439
def _get_repo_format_to_test(self):
2440
from bzrlib.repofmt import knitrepo
2441
return knitrepo.RepositoryFormatKnit1()
2444
def is_compatible(source, target):
2445
"""Be compatible with known Knit formats.
2447
We don't test for the stores being of specific types because that
2448
could lead to confusing results, and there is no need to be
2451
from bzrlib.repofmt.knitrepo import RepositoryFormatKnit
2453
are_knits = (isinstance(source._format, RepositoryFormatKnit) and
2454
isinstance(target._format, RepositoryFormatKnit))
2455
except AttributeError:
2457
return are_knits and InterRepository._same_model(source, target)
2460
def fetch(self, revision_id=None, pb=None, find_ghosts=False):
2461
"""See InterRepository.fetch()."""
2462
from bzrlib.fetch import KnitRepoFetcher
2463
mutter("Using fetch logic to copy between %s(%s) and %s(%s)",
2464
self.source, self.source._format, self.target, self.target._format)
2465
f = KnitRepoFetcher(to_repository=self.target,
2466
from_repository=self.source,
2467
last_revision=revision_id,
2469
return f.count_copied, f.failed_revisions
2472
def missing_revision_ids(self, revision_id=None, find_ghosts=True):
2473
"""See InterRepository.missing_revision_ids()."""
2474
if revision_id is not None:
2475
source_ids = self.source.get_ancestry(revision_id)
2476
assert source_ids[0] is None
2479
source_ids = self.source.all_revision_ids()
2480
source_ids_set = set(source_ids)
2481
# source_ids is the worst possible case we may need to pull.
2482
# now we want to filter source_ids against what we actually
2483
# have in target, but don't try to check for existence where we know
2484
# we do not have a revision as that would be pointless.
2485
target_ids = set(self.target.all_revision_ids())
2486
possibly_present_revisions = target_ids.intersection(source_ids_set)
2487
actually_present_revisions = set(self.target._eliminate_revisions_not_present(possibly_present_revisions))
2488
required_revisions = source_ids_set.difference(actually_present_revisions)
2489
required_topo_revisions = [rev_id for rev_id in source_ids if rev_id in required_revisions]
2490
if revision_id is not None:
2491
# we used get_ancestry to determine source_ids then we are assured all
2492
# revisions referenced are present as they are installed in topological order.
2493
# and the tip revision was validated by get_ancestry.
2494
return required_topo_revisions
2496
# if we just grabbed the possibly available ids, then
2497
# we only have an estimate of whats available and need to validate
2498
# that against the revision records.
2499
return self.source._eliminate_revisions_not_present(required_topo_revisions)
2502
class InterPackRepo(InterSameDataRepository):
2503
"""Optimised code paths between Pack based repositories."""
2506
def _get_repo_format_to_test(self):
2507
from bzrlib.repofmt import pack_repo
2508
return pack_repo.RepositoryFormatKnitPack1()
2511
def is_compatible(source, target):
2512
"""Be compatible with known Pack formats.
2514
We don't test for the stores being of specific types because that
2515
could lead to confusing results, and there is no need to be
2518
from bzrlib.repofmt.pack_repo import RepositoryFormatPack
2520
are_packs = (isinstance(source._format, RepositoryFormatPack) and
2521
isinstance(target._format, RepositoryFormatPack))
2522
except AttributeError:
2524
return are_packs and InterRepository._same_model(source, target)
2527
def fetch(self, revision_id=None, pb=None, find_ghosts=False):
2528
"""See InterRepository.fetch()."""
2529
from bzrlib.repofmt.pack_repo import Packer
2530
mutter("Using fetch logic to copy between %s(%s) and %s(%s)",
2531
self.source, self.source._format, self.target, self.target._format)
2532
self.count_copied = 0
2533
if revision_id is None:
2535
# everything to do - use pack logic
2536
# to fetch from all packs to one without
2537
# inventory parsing etc, IFF nothing to be copied is in the target.
2539
revision_ids = self.source.all_revision_ids()
2540
# implementing the TODO will involve:
2541
# - detecting when all of a pack is selected
2542
# - avoiding as much as possible pre-selection, so the
2543
# more-core routines such as create_pack_from_packs can filter in
2544
# a just-in-time fashion. (though having a HEADS list on a
2545
# repository might make this a lot easier, because we could
2546
# sensibly detect 'new revisions' without doing a full index scan.
2547
elif _mod_revision.is_null(revision_id):
2552
revision_ids = self.missing_revision_ids(revision_id,
2553
find_ghosts=find_ghosts)
2554
except errors.NoSuchRevision:
2555
raise errors.InstallFailed([revision_id])
2556
packs = self.source._pack_collection.all_packs()
2557
pack = Packer(self.target._pack_collection, packs, '.fetch',
2558
revision_ids).pack()
2559
if pack is not None:
2560
self.target._pack_collection._save_pack_names()
2561
# Trigger an autopack. This may duplicate effort as we've just done
2562
# a pack creation, but for now it is simpler to think about as
2563
# 'upload data, then repack if needed'.
2564
self.target._pack_collection.autopack()
2565
return (pack.get_revision_count(), [])
2570
def missing_revision_ids(self, revision_id=None, find_ghosts=True):
2571
"""See InterRepository.missing_revision_ids().
2573
:param find_ghosts: Find ghosts throughough the ancestry of
2576
if not find_ghosts and revision_id is not None:
2577
graph = self.source.get_graph()
2578
missing_revs = set()
2579
searcher = graph._make_breadth_first_searcher([revision_id])
2581
self.target._pack_collection.revision_index.combined_index
2582
null_set = frozenset([_mod_revision.NULL_REVISION])
2585
next_revs = set(searcher.next())
2586
except StopIteration:
2588
next_revs.difference_update(null_set)
2589
target_keys = [(key,) for key in next_revs]
2590
have_revs = frozenset(node[1][0] for node in
2591
target_index.iter_entries(target_keys))
2592
missing_revs.update(next_revs - have_revs)
2593
searcher.stop_searching_any(have_revs)
2594
if next_revs - have_revs == set([revision_id]):
2595
# we saw the start rev itself, but no parents from it (or
2596
# next_revs would have been updated to e.g. set(). We remove
2597
# have_revs because if we found revision_id locally we
2598
# stop_searching at the first time around.
2599
raise errors.NoSuchRevision(self.source, revision_id)
2601
elif revision_id is not None:
2602
source_ids = self.source.get_ancestry(revision_id)
2603
assert source_ids[0] is None
2606
source_ids = self.source.all_revision_ids()
2607
# source_ids is the worst possible case we may need to pull.
2608
# now we want to filter source_ids against what we actually
2609
# have in target, but don't try to check for existence where we know
2610
# we do not have a revision as that would be pointless.
2611
target_ids = set(self.target.all_revision_ids())
2612
return [r for r in source_ids if (r not in target_ids)]
2615
class InterModel1and2(InterRepository):
2618
def _get_repo_format_to_test(self):
2622
def is_compatible(source, target):
2623
if not source.supports_rich_root() and target.supports_rich_root():
2629
def fetch(self, revision_id=None, pb=None, find_ghosts=False):
2630
"""See InterRepository.fetch()."""
2631
from bzrlib.fetch import Model1toKnit2Fetcher
2632
f = Model1toKnit2Fetcher(to_repository=self.target,
2633
from_repository=self.source,
2634
last_revision=revision_id,
2636
return f.count_copied, f.failed_revisions
2639
def copy_content(self, revision_id=None):
2640
"""Make a complete copy of the content in self into destination.
2642
This is a destructive operation! Do not use it on existing
2645
:param revision_id: Only copy the content needed to construct
2646
revision_id and its parents.
2649
self.target.set_make_working_trees(self.source.make_working_trees())
2650
except NotImplementedError:
2652
# but don't bother fetching if we have the needed data now.
2653
if (revision_id not in (None, _mod_revision.NULL_REVISION) and
2654
self.target.has_revision(revision_id)):
2656
self.target.fetch(self.source, revision_id=revision_id)
2659
class InterKnit1and2(InterKnitRepo):
2662
def _get_repo_format_to_test(self):
2666
def is_compatible(source, target):
2667
"""Be compatible with Knit1 source and Knit3 target"""
2668
from bzrlib.repofmt.knitrepo import RepositoryFormatKnit3
2670
from bzrlib.repofmt.knitrepo import (RepositoryFormatKnit1,
2671
RepositoryFormatKnit3)
2672
from bzrlib.repofmt.pack_repo import (RepositoryFormatKnitPack1,
2673
RepositoryFormatKnitPack3)
2674
return (isinstance(source._format,
2675
(RepositoryFormatKnit1, RepositoryFormatKnitPack1)) and
2676
isinstance(target._format,
2677
(RepositoryFormatKnit3, RepositoryFormatKnitPack3))
2679
except AttributeError:
2683
def fetch(self, revision_id=None, pb=None, find_ghosts=False):
2684
"""See InterRepository.fetch()."""
2685
from bzrlib.fetch import Knit1to2Fetcher
2686
mutter("Using fetch logic to copy between %s(%s) and %s(%s)",
2687
self.source, self.source._format, self.target,
2688
self.target._format)
2689
f = Knit1to2Fetcher(to_repository=self.target,
2690
from_repository=self.source,
2691
last_revision=revision_id,
2693
return f.count_copied, f.failed_revisions
2696
class InterDifferingSerializer(InterKnitRepo):
2699
def _get_repo_format_to_test(self):
2703
def is_compatible(source, target):
2704
"""Be compatible with Knit2 source and Knit3 target"""
2705
if source.supports_rich_root() != target.supports_rich_root():
2707
# Ideally, we'd support fetching if the source had no tree references
2708
# even if it supported them...
2709
if (getattr(source, '_format.supports_tree_reference', False) and
2710
not getattr(target, '_format.supports_tree_reference', False)):
2715
def fetch(self, revision_id=None, pb=None, find_ghosts=False):
2716
"""See InterRepository.fetch()."""
2717
revision_ids = self.target.missing_revision_ids(self.source,
2719
def revisions_iterator():
2720
for current_revision_id in revision_ids:
2721
revision = self.source.get_revision(current_revision_id)
2722
tree = self.source.revision_tree(current_revision_id)
2724
signature = self.source.get_signature_text(
2725
current_revision_id)
2726
except errors.NoSuchRevision:
2728
yield revision, tree, signature
2729
install_revisions(self.target, revisions_iterator())
2730
return len(revision_ids), 0
2733
class InterRemoteToOther(InterRepository):
2735
def __init__(self, source, target):
2736
InterRepository.__init__(self, source, target)
2737
self._real_inter = None
2740
def is_compatible(source, target):
2741
if not isinstance(source, remote.RemoteRepository):
2743
source._ensure_real()
2744
real_source = source._real_repository
2745
# Is source's model compatible with target's model, and are they the
2746
# same format? Currently we can only optimise fetching from an
2747
# identical model & format repo.
2748
assert not isinstance(real_source, remote.RemoteRepository), (
2749
"We don't support remote repos backed by remote repos yet.")
2750
return real_source._format == target._format
2753
def fetch(self, revision_id=None, pb=None, find_ghosts=False):
2754
"""See InterRepository.fetch()."""
2755
from bzrlib.fetch import RemoteToOtherFetcher
2756
mutter("Using fetch logic to copy between %s(remote) and %s(%s)",
2757
self.source, self.target, self.target._format)
2758
# TODO: jam 20070210 This should be an assert, not a translate
2759
revision_id = osutils.safe_revision_id(revision_id)
2760
f = RemoteToOtherFetcher(to_repository=self.target,
2761
from_repository=self.source,
2762
last_revision=revision_id,
2764
return f.count_copied, f.failed_revisions
2767
def _get_repo_format_to_test(self):
2771
class InterOtherToRemote(InterRepository):
2773
def __init__(self, source, target):
2774
InterRepository.__init__(self, source, target)
2775
self._real_inter = None
2778
def is_compatible(source, target):
2779
if isinstance(target, remote.RemoteRepository):
2783
def _ensure_real_inter(self):
2784
if self._real_inter is None:
2785
self.target._ensure_real()
2786
real_target = self.target._real_repository
2787
self._real_inter = InterRepository.get(self.source, real_target)
2789
def copy_content(self, revision_id=None):
2790
self._ensure_real_inter()
2791
self._real_inter.copy_content(revision_id=revision_id)
2793
def fetch(self, revision_id=None, pb=None, find_ghosts=False):
2794
self._ensure_real_inter()
2795
self._real_inter.fetch(revision_id=revision_id, pb=pb)
2798
def _get_repo_format_to_test(self):
2802
InterRepository.register_optimiser(InterDifferingSerializer)
2803
InterRepository.register_optimiser(InterSameDataRepository)
2804
InterRepository.register_optimiser(InterWeaveRepo)
2805
InterRepository.register_optimiser(InterKnitRepo)
2806
InterRepository.register_optimiser(InterModel1and2)
2807
InterRepository.register_optimiser(InterKnit1and2)
2808
InterRepository.register_optimiser(InterPackRepo)
2809
InterRepository.register_optimiser(InterRemoteToOther)
2810
InterRepository.register_optimiser(InterOtherToRemote)
1712
2813
class CopyConverter(object):
1713
2814
"""A repository conversion tool which just performs a copy of the content.
1715
2816
This is slow but quite reliable.
1721
2822
:param target_format: The format the resulting repository should be.
1723
2824
self.target_format = target_format
1725
2826
def convert(self, repo, pb):
1726
2827
"""Perform the conversion of to_convert, giving feedback via pb.
1728
2829
:param to_convert: The disk object to convert.
1729
2830
:param pb: a progress bar to use for progress information.
1731
pb = ui.ui_factory.nested_progress_bar()
1734
2835
# this is only useful with metadir layouts - separated repo content.
1735
2836
# trigger an assertion if not such
1736
2837
repo._format.get_format_string()
1737
2838
self.repo_dir = repo.bzrdir
1738
pb.update(gettext('Moving repository to repository.backup'))
2839
self.step('Moving repository to repository.backup')
1739
2840
self.repo_dir.transport.move('repository', 'repository.backup')
1740
2841
backup_transport = self.repo_dir.transport.clone('repository.backup')
1741
2842
repo._format.check_conversion_target(self.target_format)
1742
2843
self.source_repo = repo._format.open(self.repo_dir,
1744
2845
_override_transport=backup_transport)
1745
pb.update(gettext('Creating new repository'))
2846
self.step('Creating new repository')
1746
2847
converted = self.target_format.initialize(self.repo_dir,
1747
2848
self.source_repo.is_shared())
1748
2849
converted.lock_write()
1750
pb.update(gettext('Copying content'))
2851
self.step('Copying content into repository.')
1751
2852
self.source_repo.copy_content_into(converted)
1753
2854
converted.unlock()
1754
pb.update(gettext('Deleting old repository content'))
2855
self.step('Deleting old repository content.')
1755
2856
self.repo_dir.transport.delete_tree('repository.backup')
1756
ui.ui_factory.note(gettext('repository converted'))
1760
def _strip_NULL_ghosts(revision_graph):
1761
"""Also don't use this. more compatibility code for unmigrated clients."""
1762
# Filter ghosts, and null:
1763
if _mod_revision.NULL_REVISION in revision_graph:
1764
del revision_graph[_mod_revision.NULL_REVISION]
1765
for key, parents in revision_graph.items():
1766
revision_graph[key] = tuple(parent for parent in parents if parent
1768
return revision_graph
1771
def _iter_for_revno(repo, partial_history_cache, stop_index=None,
1772
stop_revision=None):
1773
"""Extend the partial history to include a given index
1775
If a stop_index is supplied, stop when that index has been reached.
1776
If a stop_revision is supplied, stop when that revision is
1777
encountered. Otherwise, stop when the beginning of history is
1780
:param stop_index: The index which should be present. When it is
1781
present, history extension will stop.
1782
:param stop_revision: The revision id which should be present. When
1783
it is encountered, history extension will stop.
1785
start_revision = partial_history_cache[-1]
1786
graph = repo.get_graph()
1787
iterator = graph.iter_lefthand_ancestry(start_revision,
1788
(_mod_revision.NULL_REVISION,))
2857
self.pb.note('repository converted')
2859
def step(self, message):
2860
"""Update the pb by a step."""
2862
self.pb.update(message, self.count, self.total)
2874
def _unescaper(match, _map=_unescape_map):
2875
code = match.group(1)
1790
# skip the last revision in the list
1793
if (stop_index is not None and
1794
len(partial_history_cache) > stop_index):
1796
if partial_history_cache[-1] == stop_revision:
1798
revision_id = iterator.next()
1799
partial_history_cache.append(revision_id)
1800
except StopIteration:
1805
class _LazyListJoin(object):
1806
"""An iterable yielding the contents of many lists as one list.
1808
Each iterator made from this will reflect the current contents of the lists
1809
at the time the iterator is made.
2879
if not code.startswith('#'):
2881
return unichr(int(code[1:])).encode('utf8')
2887
def _unescape_xml(data):
2888
"""Unescape predefined XML entities in a string of data."""
2890
if _unescape_re is None:
2891
_unescape_re = re.compile('\&([^;]*);')
2892
return _unescape_re.sub(_unescaper, data)
2895
class _VersionedFileChecker(object):
2897
def __init__(self, repository):
2898
self.repository = repository
2899
self.text_index = self.repository._generate_text_key_index()
1811
This is used by Repository's _make_parents_provider implementation so that
1814
pp = repo._make_parents_provider() # uses a list of fallback repos
1815
pp.add_fallback_repository(other_repo) # appends to that list
1816
result = pp.get_parent_map(...)
1817
# The result will include revs from other_repo
1820
def __init__(self, *list_parts):
1821
self.list_parts = list_parts
1825
for list_part in self.list_parts:
1826
full_list.extend(list_part)
1827
return iter(full_list)
1830
return "%s.%s(%s)" % (self.__module__, self.__class__.__name__,
2901
def calculate_file_version_parents(self, revision_id, file_id):
2902
"""Calculate the correct parents for a file version according to
2905
parent_keys = self.text_index[(file_id, revision_id)]
2906
if parent_keys == [_mod_revision.NULL_REVISION]:
2908
# strip the file_id, for the weave api
2909
return tuple([revision_id for file_id, revision_id in parent_keys])
2911
def check_file_version_parents(self, weave, file_id):
2912
"""Check the parents stored in a versioned file are correct.
2914
It also detects file versions that are not referenced by their
2915
corresponding revision's inventory.
2917
:returns: A tuple of (wrong_parents, dangling_file_versions).
2918
wrong_parents is a dict mapping {revision_id: (stored_parents,
2919
correct_parents)} for each revision_id where the stored parents
2920
are not correct. dangling_file_versions is a set of (file_id,
2921
revision_id) tuples for versions that are present in this versioned
2922
file, but not used by the corresponding inventory.
2925
unused_versions = set()
2926
for num, revision_id in enumerate(weave.versions()):
2928
correct_parents = self.calculate_file_version_parents(
2929
revision_id, file_id)
2931
# The version is not part of the used keys.
2932
unused_versions.add(revision_id)
2935
knit_parents = tuple(weave.get_parents(revision_id))
2936
except errors.RevisionNotPresent:
2938
if correct_parents != knit_parents:
2939
wrong_parents[revision_id] = (knit_parents, correct_parents)
2940
return wrong_parents, unused_versions