1
# Copyright (C) 2005 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., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
17
"""Tree classes, representing directory at point in time.
21
from collections import deque
22
from cStringIO import StringIO
28
revision as _mod_revision,
29
conflicts as _mod_conflicts,
32
from bzrlib.decorators import needs_read_lock
33
from bzrlib.errors import BzrError, BzrCheckError
34
from bzrlib import errors
35
from bzrlib.inventory import Inventory, InventoryFile
36
from bzrlib.inter import InterObject
37
from bzrlib.osutils import fingerprint_file
38
import bzrlib.revision
39
from bzrlib.trace import mutter, note
43
"""Abstract file tree.
45
There are several subclasses:
47
* `WorkingTree` exists as files on disk editable by the user.
49
* `RevisionTree` is a tree as recorded at some point in the past.
51
Trees contain an `Inventory` object, and also know how to retrieve
52
file texts mentioned in the inventory, either from a working
53
directory or from a store.
55
It is possible for trees to contain files that are not described
56
in their inventory or vice versa; for this use `filenames()`.
58
Trees can be compared, etc, regardless of whether they are working
59
trees or versioned trees.
62
def changes_from(self, other, want_unchanged=False, specific_files=None,
63
extra_trees=None, require_versioned=False, include_root=False,
64
want_unversioned=False):
65
"""Return a TreeDelta of the changes from other to this tree.
67
:param other: A tree to compare with.
68
:param specific_files: An optional list of file paths to restrict the
69
comparison to. When mapping filenames to ids, all matches in all
70
trees (including optional extra_trees) are used, and all children of
71
matched directories are included.
72
:param want_unchanged: An optional boolean requesting the inclusion of
73
unchanged entries in the result.
74
:param extra_trees: An optional list of additional trees to use when
75
mapping the contents of specific_files (paths) to file_ids.
76
:param require_versioned: An optional boolean (defaults to False). When
77
supplied and True all the 'specific_files' must be versioned, or
78
a PathsNotVersionedError will be thrown.
79
:param want_unversioned: Scan for unversioned paths.
81
The comparison will be performed by an InterTree object looked up on
84
# Martin observes that Tree.changes_from returns a TreeDelta and this
85
# may confuse people, because the class name of the returned object is
86
# a synonym of the object referenced in the method name.
87
return InterTree.get(other, self).compare(
88
want_unchanged=want_unchanged,
89
specific_files=specific_files,
90
extra_trees=extra_trees,
91
require_versioned=require_versioned,
92
include_root=include_root,
93
want_unversioned=want_unversioned,
96
@symbol_versioning.deprecated_method(symbol_versioning.one_three)
97
def _iter_changes(self, *args, **kwargs):
98
return self.iter_changes(*args, **kwargs)
100
def iter_changes(self, from_tree, include_unchanged=False,
101
specific_files=None, pb=None, extra_trees=None,
102
require_versioned=True, want_unversioned=False):
103
intertree = InterTree.get(from_tree, self)
104
return intertree.iter_changes(include_unchanged, specific_files, pb,
105
extra_trees, require_versioned, want_unversioned=want_unversioned)
108
"""Get a list of the conflicts in the tree.
110
Each conflict is an instance of bzrlib.conflicts.Conflict.
112
return _mod_conflicts.ConflictList()
115
"""For trees that can have unversioned files, return all such paths."""
118
def get_parent_ids(self):
119
"""Get the parent ids for this tree.
121
:return: a list of parent ids. [] is returned to indicate
122
a tree with no parents.
123
:raises: BzrError if the parents are not known.
125
raise NotImplementedError(self.get_parent_ids)
127
def has_filename(self, filename):
128
"""True if the tree has given filename."""
129
raise NotImplementedError(self.has_filename)
131
def has_id(self, file_id):
132
return self.inventory.has_id(file_id)
134
__contains__ = has_id
136
def has_or_had_id(self, file_id):
137
if file_id == self.inventory.root.file_id:
139
return self.inventory.has_id(file_id)
141
def is_ignored(self, filename):
142
"""Check whether the filename is ignored by this tree.
144
:param filename: The relative filename within the tree.
145
:return: True if the filename is ignored.
150
return iter(self.inventory)
152
def all_file_ids(self):
153
"""Iterate through all file ids, including ids for missing files."""
154
return set(self.inventory)
156
def id2path(self, file_id):
157
"""Return the path for a file id.
161
return self.inventory.id2path(file_id)
163
def is_control_filename(self, filename):
164
"""True if filename is the name of a control file in this tree.
166
:param filename: A filename within the tree. This is a relative path
167
from the root of this tree.
169
This is true IF and ONLY IF the filename is part of the meta data
170
that bzr controls in this tree. I.E. a random .bzr directory placed
171
on disk will not be a control file for this tree.
173
return self.bzrdir.is_control_filename(filename)
176
def iter_entries_by_dir(self, specific_file_ids=None):
177
"""Walk the tree in 'by_dir' order.
179
This will yield each entry in the tree as a (path, entry) tuple. The
180
order that they are yielded is: the contents of a directory are
181
preceeded by the parent of a directory, and all the contents of a
182
directory are grouped together.
184
return self.inventory.iter_entries_by_dir(
185
specific_file_ids=specific_file_ids)
187
def iter_references(self):
188
for path, entry in self.iter_entries_by_dir():
189
if entry.kind == 'tree-reference':
190
yield path, entry.file_id
192
def kind(self, file_id):
193
raise NotImplementedError("Tree subclass %s must implement kind"
194
% self.__class__.__name__)
196
def stored_kind(self, file_id):
197
"""File kind stored for this file_id.
199
May not match kind on disk for working trees. Always available
200
for versioned files, even when the file itself is missing.
202
return self.kind(file_id)
204
def path_content_summary(self, path):
205
"""Get a summary of the information about path.
207
:param path: A relative path within the tree.
208
:return: A tuple containing kind, size, exec, sha1-or-link.
209
Kind is always present (see tree.kind()).
210
size is present if kind is file, None otherwise.
211
exec is None unless kind is file and the platform supports the 'x'
213
sha1-or-link is the link target if kind is symlink, or the sha1 if
214
it can be obtained without reading the file.
216
raise NotImplementedError(self.path_content_summary)
218
def get_reference_revision(self, file_id, path=None):
219
raise NotImplementedError("Tree subclass %s must implement "
220
"get_reference_revision"
221
% self.__class__.__name__)
223
def _comparison_data(self, entry, path):
224
"""Return a tuple of kind, executable, stat_value for a file.
226
entry may be None if there is no inventory entry for the file, but
227
path must always be supplied.
229
kind is None if there is no file present (even if an inventory id is
230
present). executable is False for non-file entries.
232
raise NotImplementedError(self._comparison_data)
234
def _file_size(self, entry, stat_value):
235
raise NotImplementedError(self._file_size)
237
def _get_inventory(self):
238
return self._inventory
240
def get_file(self, file_id, path=None):
241
"""Return a file object for the file file_id in the tree.
243
If both file_id and path are defined, it is implementation defined as
244
to which one is used.
246
raise NotImplementedError(self.get_file)
248
def get_file_mtime(self, file_id, path=None):
249
"""Return the modification time for a file.
251
:param file_id: The handle for this file.
252
:param path: The path that this file can be found at.
253
These must point to the same object.
255
raise NotImplementedError(self.get_file_mtime)
257
def get_file_size(self, file_id):
258
"""Return the size of a file in bytes.
260
This applies only to regular files. If invoked on directories or
261
symlinks, it will return None.
262
:param file_id: The file-id of the file
264
raise NotImplementedError(self.get_file_size)
266
def get_file_by_path(self, path):
267
return self.get_file(self._inventory.path2id(path), path)
269
def iter_files_bytes(self, desired_files):
270
"""Iterate through file contents.
272
Files will not necessarily be returned in the order they occur in
273
desired_files. No specific order is guaranteed.
275
Yields pairs of identifier, bytes_iterator. identifier is an opaque
276
value supplied by the caller as part of desired_files. It should
277
uniquely identify the file version in the caller's context. (Examples:
278
an index number or a TreeTransform trans_id.)
280
bytes_iterator is an iterable of bytestrings for the file. The
281
kind of iterable and length of the bytestrings are unspecified, but for
282
this implementation, it is a tuple containing a single bytestring with
283
the complete text of the file.
285
:param desired_files: a list of (file_id, identifier) pairs
287
for file_id, identifier in desired_files:
288
# We wrap the string in a tuple so that we can return an iterable
289
# of bytestrings. (Technically, a bytestring is also an iterable
290
# of bytestrings, but iterating through each character is not
292
cur_file = (self.get_file_text(file_id),)
293
yield identifier, cur_file
295
def get_symlink_target(self, file_id):
296
"""Get the target for a given file_id.
298
It is assumed that the caller already knows that file_id is referencing
300
:param file_id: Handle for the symlink entry.
301
:return: The path the symlink points to.
303
raise NotImplementedError(self.get_symlink_target)
305
def get_root_id(self):
306
"""Return the file_id for the root of this tree."""
307
raise NotImplementedError(self.get_root_id)
309
def annotate_iter(self, file_id,
310
default_revision=_mod_revision.CURRENT_REVISION):
311
"""Return an iterator of revision_id, line tuples.
313
For working trees (and mutable trees in general), the special
314
revision_id 'current:' will be used for lines that are new in this
315
tree, e.g. uncommitted changes.
316
:param file_id: The file to produce an annotated version from
317
:param default_revision: For lines that don't match a basis, mark them
318
with this revision id. Not all implementations will make use of
321
raise NotImplementedError(self.annotate_iter)
323
def _get_plan_merge_data(self, file_id, other, base):
324
from bzrlib import merge, versionedfile
325
vf = versionedfile._PlanMergeVersionedFile(file_id)
326
last_revision_a = self._get_file_revision(file_id, vf, 'this:')
327
last_revision_b = other._get_file_revision(file_id, vf, 'other:')
329
last_revision_base = None
331
last_revision_base = base._get_file_revision(file_id, vf, 'base:')
332
return vf, last_revision_a, last_revision_b, last_revision_base
334
def plan_file_merge(self, file_id, other, base=None):
335
"""Generate a merge plan based on annotations.
337
If the file contains uncommitted changes in this tree, they will be
338
attributed to the 'current:' pseudo-revision. If the file contains
339
uncommitted changes in the other tree, they will be assigned to the
340
'other:' pseudo-revision.
342
data = self._get_plan_merge_data(file_id, other, base)
343
vf, last_revision_a, last_revision_b, last_revision_base = data
344
return vf.plan_merge(last_revision_a, last_revision_b,
347
def plan_file_lca_merge(self, file_id, other, base=None):
348
"""Generate a merge plan based lca-newness.
350
If the file contains uncommitted changes in this tree, they will be
351
attributed to the 'current:' pseudo-revision. If the file contains
352
uncommitted changes in the other tree, they will be assigned to the
353
'other:' pseudo-revision.
355
data = self._get_plan_merge_data(file_id, other, base)
356
vf, last_revision_a, last_revision_b, last_revision_base = data
357
return vf.plan_lca_merge(last_revision_a, last_revision_b,
360
def _get_file_revision(self, file_id, vf, tree_revision):
361
def file_revision(revision_tree):
362
revision_tree.lock_read()
364
return revision_tree.inventory[file_id].revision
366
revision_tree.unlock()
368
def iter_parent_trees():
369
for revision_id in self.get_parent_ids():
371
yield self.revision_tree(revision_id)
373
yield self.repository.revision_tree(revision_id)
375
if getattr(self, '_get_weave', None) is None:
376
last_revision = tree_revision
377
parent_revisions = [file_revision(t) for t in iter_parent_trees()]
378
vf.add_lines(last_revision, parent_revisions,
379
self.get_file(file_id).readlines())
380
repo = self.branch.repository
381
transaction = repo.get_transaction()
382
base_vf = repo.weave_store.get_weave(file_id, transaction)
384
last_revision = file_revision(self)
385
base_vf = self._get_weave(file_id)
386
vf.fallback_versionedfiles.append(base_vf)
389
inventory = property(_get_inventory,
390
doc="Inventory of this Tree")
392
def _check_retrieved(self, ie, f):
395
fp = fingerprint_file(f)
398
if ie.text_size is not None:
399
if ie.text_size != fp['size']:
400
raise BzrError("mismatched size for file %r in %r" % (ie.file_id, self._store),
401
["inventory expects %d bytes" % ie.text_size,
402
"file is actually %d bytes" % fp['size'],
403
"store is probably damaged/corrupt"])
405
if ie.text_sha1 != fp['sha1']:
406
raise BzrError("wrong SHA-1 for file %r in %r" % (ie.file_id, self._store),
407
["inventory expects %s" % ie.text_sha1,
408
"file is actually %s" % fp['sha1'],
409
"store is probably damaged/corrupt"])
412
def path2id(self, path):
413
"""Return the id for path in this tree."""
414
return self._inventory.path2id(path)
416
def paths2ids(self, paths, trees=[], require_versioned=True):
417
"""Return all the ids that can be reached by walking from paths.
419
Each path is looked up in this tree and any extras provided in
420
trees, and this is repeated recursively: the children in an extra tree
421
of a directory that has been renamed under a provided path in this tree
422
are all returned, even if none exist under a provided path in this
423
tree, and vice versa.
425
:param paths: An iterable of paths to start converting to ids from.
426
Alternatively, if paths is None, no ids should be calculated and None
427
will be returned. This is offered to make calling the api unconditional
428
for code that *might* take a list of files.
429
:param trees: Additional trees to consider.
430
:param require_versioned: If False, do not raise NotVersionedError if
431
an element of paths is not versioned in this tree and all of trees.
433
return find_ids_across_trees(paths, [self] + list(trees), require_versioned)
435
def print_file(self, file_id):
436
"""Print file with id `file_id` to stdout."""
438
sys.stdout.write(self.get_file_text(file_id))
443
def revision_tree(self, revision_id):
444
"""Obtain a revision tree for the revision revision_id.
446
The intention of this method is to allow access to possibly cached
447
tree data. Implementors of this method should raise NoSuchRevision if
448
the tree is not locally available, even if they could obtain the
449
tree via a repository or some other means. Callers are responsible
450
for finding the ultimate source for a revision tree.
452
:param revision_id: The revision_id of the requested tree.
454
:raises: NoSuchRevision if the tree cannot be obtained.
456
raise errors.NoSuchRevisionInTree(self, revision_id)
459
"""What files are present in this tree and unknown.
461
:return: an iterator over the unknown files.
468
def filter_unversioned_files(self, paths):
469
"""Filter out paths that are versioned.
471
:return: set of paths.
473
# NB: we specifically *don't* call self.has_filename, because for
474
# WorkingTrees that can indicate files that exist on disk but that
476
pred = self.inventory.has_filename
477
return set((p for p in paths if not pred(p)))
479
def walkdirs(self, prefix=""):
480
"""Walk the contents of this tree from path down.
482
This yields all the data about the contents of a directory at a time.
483
After each directory has been yielded, if the caller has mutated the
484
list to exclude some directories, they are then not descended into.
486
The data yielded is of the form:
487
((directory-relpath, directory-path-from-root, directory-fileid),
488
[(relpath, basename, kind, lstat, path_from_tree_root, file_id,
489
versioned_kind), ...]),
490
- directory-relpath is the containing dirs relpath from prefix
491
- directory-path-from-root is the containing dirs path from /
492
- directory-fileid is the id of the directory if it is versioned.
493
- relpath is the relative path within the subtree being walked.
494
- basename is the basename
495
- kind is the kind of the file now. If unknonwn then the file is not
496
present within the tree - but it may be recorded as versioned. See
498
- lstat is the stat data *if* the file was statted.
499
- path_from_tree_root is the path from the root of the tree.
500
- file_id is the file_id if the entry is versioned.
501
- versioned_kind is the kind of the file as last recorded in the
502
versioning system. If 'unknown' the file is not versioned.
503
One of 'kind' and 'versioned_kind' must not be 'unknown'.
505
:param prefix: Start walking from prefix within the tree rather than
506
at the root. This allows one to walk a subtree but get paths that are
507
relative to a tree rooted higher up.
508
:return: an iterator over the directory data.
510
raise NotImplementedError(self.walkdirs)
513
class EmptyTree(Tree):
516
self._inventory = Inventory(root_id=None)
517
symbol_versioning.warn('EmptyTree is deprecated as of bzr 0.9 please'
518
' use repository.revision_tree instead.',
519
DeprecationWarning, stacklevel=2)
521
def get_parent_ids(self):
524
def get_symlink_target(self, file_id):
527
def has_filename(self, filename):
530
def kind(self, file_id):
533
def list_files(self, include_root=False):
536
def __contains__(self, file_id):
537
return (file_id in self._inventory)
539
def get_file_sha1(self, file_id, path=None, stat_value=None):
543
######################################################################
546
# TODO: Merge these two functions into a single one that can operate
547
# on either a whole tree or a set of files.
549
# TODO: Return the diff in order by filename, not by category or in
550
# random order. Can probably be done by lock-stepping through the
551
# filenames from both trees.
554
def file_status(filename, old_tree, new_tree):
555
"""Return single-letter status, old and new names for a file.
557
The complexity here is in deciding how to represent renames;
558
many complex cases are possible.
560
old_inv = old_tree.inventory
561
new_inv = new_tree.inventory
562
new_id = new_inv.path2id(filename)
563
old_id = old_inv.path2id(filename)
565
if not new_id and not old_id:
566
# easy: doesn't exist in either; not versioned at all
567
if new_tree.is_ignored(filename):
568
return 'I', None, None
570
return '?', None, None
572
# There is now a file of this name, great.
575
# There is no longer a file of this name, but we can describe
576
# what happened to the file that used to have
577
# this name. There are two possibilities: either it was
578
# deleted entirely, or renamed.
579
if new_inv.has_id(old_id):
580
return 'X', old_inv.id2path(old_id), new_inv.id2path(old_id)
582
return 'D', old_inv.id2path(old_id), None
584
# if the file_id is new in this revision, it is added
585
if new_id and not old_inv.has_id(new_id):
588
# if there used to be a file of this name, but that ID has now
589
# disappeared, it is deleted
590
if old_id and not new_inv.has_id(old_id):
597
def find_renames(old_inv, new_inv):
598
for file_id in old_inv:
599
if file_id not in new_inv:
601
old_name = old_inv.id2path(file_id)
602
new_name = new_inv.id2path(file_id)
603
if old_name != new_name:
604
yield (old_name, new_name)
607
def find_ids_across_trees(filenames, trees, require_versioned=True):
608
"""Find the ids corresponding to specified filenames.
610
All matches in all trees will be used, and all children of matched
611
directories will be used.
613
:param filenames: The filenames to find file_ids for (if None, returns
615
:param trees: The trees to find file_ids within
616
:param require_versioned: if true, all specified filenames must occur in
618
:return: a set of file ids for the specified filenames and their children.
622
specified_path_ids = _find_ids_across_trees(filenames, trees,
624
return _find_children_across_trees(specified_path_ids, trees)
627
def _find_ids_across_trees(filenames, trees, require_versioned):
628
"""Find the ids corresponding to specified filenames.
630
All matches in all trees will be used, but subdirectories are not scanned.
632
:param filenames: The filenames to find file_ids for
633
:param trees: The trees to find file_ids within
634
:param require_versioned: if true, all specified filenames must occur in
636
:return: a set of file ids for the specified filenames
639
interesting_ids = set()
640
for tree_path in filenames:
643
file_id = tree.path2id(tree_path)
644
if file_id is not None:
645
interesting_ids.add(file_id)
648
not_versioned.append(tree_path)
649
if len(not_versioned) > 0 and require_versioned:
650
raise errors.PathsNotVersionedError(not_versioned)
651
return interesting_ids
654
def _find_children_across_trees(specified_ids, trees):
655
"""Return a set including specified ids and their children.
657
All matches in all trees will be used.
659
:param trees: The trees to find file_ids within
660
:return: a set containing all specified ids and their children
662
interesting_ids = set(specified_ids)
663
pending = interesting_ids
664
# now handle children of interesting ids
665
# we loop so that we handle all children of each id in both trees
666
while len(pending) > 0:
668
for file_id in pending:
670
if not tree.has_id(file_id):
672
entry = tree.inventory[file_id]
673
for child in getattr(entry, 'children', {}).itervalues():
674
if child.file_id not in interesting_ids:
675
new_pending.add(child.file_id)
676
interesting_ids.update(new_pending)
677
pending = new_pending
678
return interesting_ids
681
class InterTree(InterObject):
682
"""This class represents operations taking place between two Trees.
684
Its instances have methods like 'compare' and contain references to the
685
source and target trees these operations are to be carried out on.
687
Clients of bzrlib should not need to use InterTree directly, rather they
688
should use the convenience methods on Tree such as 'Tree.compare()' which
689
will pass through to InterTree as appropriate.
695
def compare(self, want_unchanged=False, specific_files=None,
696
extra_trees=None, require_versioned=False, include_root=False,
697
want_unversioned=False):
698
"""Return the changes from source to target.
700
:return: A TreeDelta.
701
:param specific_files: An optional list of file paths to restrict the
702
comparison to. When mapping filenames to ids, all matches in all
703
trees (including optional extra_trees) are used, and all children of
704
matched directories are included.
705
:param want_unchanged: An optional boolean requesting the inclusion of
706
unchanged entries in the result.
707
:param extra_trees: An optional list of additional trees to use when
708
mapping the contents of specific_files (paths) to file_ids.
709
:param require_versioned: An optional boolean (defaults to False). When
710
supplied and True all the 'specific_files' must be versioned, or
711
a PathsNotVersionedError will be thrown.
712
:param want_unversioned: Scan for unversioned paths.
714
# NB: show_status depends on being able to pass in non-versioned files
715
# and report them as unknown
716
trees = (self.source,)
717
if extra_trees is not None:
718
trees = trees + tuple(extra_trees)
719
# target is usually the newer tree:
720
specific_file_ids = self.target.paths2ids(specific_files, trees,
721
require_versioned=require_versioned)
722
if specific_files and not specific_file_ids:
723
# All files are unversioned, so just return an empty delta
724
# _compare_trees would think we want a complete delta
725
result = delta.TreeDelta()
726
fake_entry = InventoryFile('unused', 'unused', 'unused')
727
result.unversioned = [(path, None,
728
self.target._comparison_data(fake_entry, path)[0]) for path in
731
return delta._compare_trees(self.source, self.target, want_unchanged,
732
specific_files, include_root, extra_trees=extra_trees,
733
require_versioned=require_versioned,
734
want_unversioned=want_unversioned)
736
def iter_changes(self, include_unchanged=False,
737
specific_files=None, pb=None, extra_trees=[],
738
require_versioned=True, want_unversioned=False):
739
"""Generate an iterator of changes between trees.
742
(file_id, (path_in_source, path_in_target),
743
changed_content, versioned, parent, name, kind,
746
Changed_content is True if the file's content has changed. This
747
includes changes to its kind, and to a symlink's target.
749
versioned, parent, name, kind, executable are tuples of (from, to).
750
If a file is missing in a tree, its kind is None.
752
Iteration is done in parent-to-child order, relative to the target
755
There is no guarantee that all paths are in sorted order: the
756
requirement to expand the search due to renames may result in children
757
that should be found early being found late in the search, after
758
lexically later results have been returned.
759
:param require_versioned: Raise errors.PathsNotVersionedError if a
760
path in the specific_files list is not versioned in one of
761
source, target or extra_trees.
762
:param want_unversioned: Should unversioned files be returned in the
763
output. An unversioned file is defined as one with (False, False)
764
for the versioned pair.
767
lookup_trees = [self.source]
769
lookup_trees.extend(extra_trees)
770
if specific_files == []:
771
specific_file_ids = []
773
specific_file_ids = self.target.paths2ids(specific_files,
774
lookup_trees, require_versioned=require_versioned)
776
all_unversioned = sorted([(p.split('/'), p) for p in
778
if specific_files is None or
779
osutils.is_inside_any(specific_files, p)])
780
all_unversioned = deque(all_unversioned)
782
all_unversioned = deque()
784
from_entries_by_dir = list(self.source.inventory.iter_entries_by_dir(
785
specific_file_ids=specific_file_ids))
786
from_data = dict((e.file_id, (p, e)) for p, e in from_entries_by_dir)
787
to_entries_by_dir = list(self.target.inventory.iter_entries_by_dir(
788
specific_file_ids=specific_file_ids))
789
num_entries = len(from_entries_by_dir) + len(to_entries_by_dir)
791
# the unversioned path lookup only occurs on real trees - where there
792
# can be extras. So the fake_entry is solely used to look up
793
# executable it values when execute is not supported.
794
fake_entry = InventoryFile('unused', 'unused', 'unused')
795
for to_path, to_entry in to_entries_by_dir:
796
while all_unversioned and all_unversioned[0][0] < to_path.split('/'):
797
unversioned_path = all_unversioned.popleft()
798
to_kind, to_executable, to_stat = \
799
self.target._comparison_data(fake_entry, unversioned_path[1])
800
yield (None, (None, unversioned_path[1]), True, (False, False),
802
(None, unversioned_path[0][-1]),
804
(None, to_executable))
805
file_id = to_entry.file_id
806
to_paths[file_id] = to_path
808
changed_content = False
809
from_path, from_entry = from_data.get(file_id, (None, None))
810
from_versioned = (from_entry is not None)
811
if from_entry is not None:
812
from_versioned = True
813
from_name = from_entry.name
814
from_parent = from_entry.parent_id
815
from_kind, from_executable, from_stat = \
816
self.source._comparison_data(from_entry, from_path)
819
from_versioned = False
823
from_executable = None
824
versioned = (from_versioned, True)
825
to_kind, to_executable, to_stat = \
826
self.target._comparison_data(to_entry, to_path)
827
kind = (from_kind, to_kind)
828
if kind[0] != kind[1]:
829
changed_content = True
830
elif from_kind == 'file':
831
from_size = self.source._file_size(from_entry, from_stat)
832
to_size = self.target._file_size(to_entry, to_stat)
833
if from_size != to_size:
834
changed_content = True
835
elif (self.source.get_file_sha1(file_id, from_path, from_stat) !=
836
self.target.get_file_sha1(file_id, to_path, to_stat)):
837
changed_content = True
838
elif from_kind == 'symlink':
839
if (self.source.get_symlink_target(file_id) !=
840
self.target.get_symlink_target(file_id)):
841
changed_content = True
842
elif from_kind == 'tree-reference':
843
if (self.source.get_reference_revision(file_id, from_path)
844
!= self.target.get_reference_revision(file_id, to_path)):
845
changed_content = True
846
parent = (from_parent, to_entry.parent_id)
847
name = (from_name, to_entry.name)
848
executable = (from_executable, to_executable)
850
pb.update('comparing files', entry_count, num_entries)
851
if (changed_content is not False or versioned[0] != versioned[1]
852
or parent[0] != parent[1] or name[0] != name[1] or
853
executable[0] != executable[1] or include_unchanged):
854
yield (file_id, (from_path, to_path), changed_content,
855
versioned, parent, name, kind, executable)
857
while all_unversioned:
858
# yield any trailing unversioned paths
859
unversioned_path = all_unversioned.popleft()
860
to_kind, to_executable, to_stat = \
861
self.target._comparison_data(fake_entry, unversioned_path[1])
862
yield (None, (None, unversioned_path[1]), True, (False, False),
864
(None, unversioned_path[0][-1]),
866
(None, to_executable))
868
def get_to_path(to_entry):
869
if to_entry.parent_id is None:
870
to_path = '' # the root
872
if to_entry.parent_id not in to_paths:
874
return get_to_path(self.target.inventory[to_entry.parent_id])
875
to_path = osutils.pathjoin(to_paths[to_entry.parent_id],
877
to_paths[to_entry.file_id] = to_path
880
for path, from_entry in from_entries_by_dir:
881
file_id = from_entry.file_id
882
if file_id in to_paths:
885
if not file_id in self.target.inventory:
886
# common case - paths we have not emitted are not present in
890
to_path = get_to_path(self.target.inventory[file_id])
893
pb.update('comparing files', entry_count, num_entries)
894
versioned = (True, False)
895
parent = (from_entry.parent_id, None)
896
name = (from_entry.name, None)
897
from_kind, from_executable, stat_value = \
898
self.source._comparison_data(from_entry, path)
899
kind = (from_kind, None)
900
executable = (from_executable, None)
901
changed_content = True
902
# the parent's path is necessarily known at this point.
903
yield(file_id, (path, to_path), changed_content, versioned, parent,
904
name, kind, executable)
added
removed
bzrlib/tree.py
