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
26
conflicts as _mod_conflicts,
29
revision as _mod_revision,
33
from bzrlib.decorators import needs_read_lock
34
from bzrlib.errors import BzrError, BzrCheckError
35
from bzrlib import errors
36
from bzrlib.inventory import Inventory, InventoryFile
37
from bzrlib.inter import InterObject
38
from bzrlib.osutils import fingerprint_file
39
import bzrlib.revision
40
from bzrlib.trace import mutter, note
44
"""Abstract file tree.
46
There are several subclasses:
48
* `WorkingTree` exists as files on disk editable by the user.
50
* `RevisionTree` is a tree as recorded at some point in the past.
52
Trees contain an `Inventory` object, and also know how to retrieve
53
file texts mentioned in the inventory, either from a working
54
directory or from a store.
56
It is possible for trees to contain files that are not described
57
in their inventory or vice versa; for this use `filenames()`.
59
Trees can be compared, etc, regardless of whether they are working
60
trees or versioned trees.
63
def changes_from(self, other, want_unchanged=False, specific_files=None,
64
extra_trees=None, require_versioned=False, include_root=False,
65
want_unversioned=False):
66
"""Return a TreeDelta of the changes from other to this tree.
68
:param other: A tree to compare with.
69
:param specific_files: An optional list of file paths to restrict the
70
comparison to. When mapping filenames to ids, all matches in all
71
trees (including optional extra_trees) are used, and all children of
72
matched directories are included.
73
:param want_unchanged: An optional boolean requesting the inclusion of
74
unchanged entries in the result.
75
:param extra_trees: An optional list of additional trees to use when
76
mapping the contents of specific_files (paths) to file_ids.
77
:param require_versioned: An optional boolean (defaults to False). When
78
supplied and True all the 'specific_files' must be versioned, or
79
a PathsNotVersionedError will be thrown.
80
:param want_unversioned: Scan for unversioned paths.
82
The comparison will be performed by an InterTree object looked up on
85
# Martin observes that Tree.changes_from returns a TreeDelta and this
86
# may confuse people, because the class name of the returned object is
87
# a synonym of the object referenced in the method name.
88
return InterTree.get(other, self).compare(
89
want_unchanged=want_unchanged,
90
specific_files=specific_files,
91
extra_trees=extra_trees,
92
require_versioned=require_versioned,
93
include_root=include_root,
94
want_unversioned=want_unversioned,
97
@symbol_versioning.deprecated_method(symbol_versioning.one_three)
98
def _iter_changes(self, *args, **kwargs):
99
return self.iter_changes(*args, **kwargs)
101
def iter_changes(self, from_tree, include_unchanged=False,
102
specific_files=None, pb=None, extra_trees=None,
103
require_versioned=True, want_unversioned=False):
104
intertree = InterTree.get(from_tree, self)
105
return intertree.iter_changes(include_unchanged, specific_files, pb,
106
extra_trees, require_versioned, want_unversioned=want_unversioned)
109
"""Get a list of the conflicts in the tree.
111
Each conflict is an instance of bzrlib.conflicts.Conflict.
113
return _mod_conflicts.ConflictList()
116
"""For trees that can have unversioned files, return all such paths."""
119
def get_parent_ids(self):
120
"""Get the parent ids for this tree.
122
:return: a list of parent ids. [] is returned to indicate
123
a tree with no parents.
124
:raises: BzrError if the parents are not known.
126
raise NotImplementedError(self.get_parent_ids)
128
def has_filename(self, filename):
129
"""True if the tree has given filename."""
130
raise NotImplementedError(self.has_filename)
132
def has_id(self, file_id):
133
return self.inventory.has_id(file_id)
135
__contains__ = has_id
137
def has_or_had_id(self, file_id):
138
if file_id == self.inventory.root.file_id:
140
return self.inventory.has_id(file_id)
142
def is_ignored(self, filename):
143
"""Check whether the filename is ignored by this tree.
145
:param filename: The relative filename within the tree.
146
:return: True if the filename is ignored.
151
return iter(self.inventory)
153
def all_file_ids(self):
154
"""Iterate through all file ids, including ids for missing files."""
155
return set(self.inventory)
157
def id2path(self, file_id):
158
"""Return the path for a file id.
162
return self.inventory.id2path(file_id)
164
def is_control_filename(self, filename):
165
"""True if filename is the name of a control file in this tree.
167
:param filename: A filename within the tree. This is a relative path
168
from the root of this tree.
170
This is true IF and ONLY IF the filename is part of the meta data
171
that bzr controls in this tree. I.E. a random .bzr directory placed
172
on disk will not be a control file for this tree.
174
return self.bzrdir.is_control_filename(filename)
177
def iter_entries_by_dir(self, specific_file_ids=None):
178
"""Walk the tree in 'by_dir' order.
180
This will yield each entry in the tree as a (path, entry) tuple.
181
The order that they are yielded is:
183
Directories are walked in a depth-first lexicographical order,
184
however, whenever a directory is reached, all of its direct child
185
nodes are yielded in lexicographical order before yielding the
188
For example, in the tree::
198
The yield order (ignoring root) would be::
199
a, f, a/b, a/d, a/b/c, a/d/e, f/g
201
return self.inventory.iter_entries_by_dir(
202
specific_file_ids=specific_file_ids)
204
def iter_references(self):
205
for path, entry in self.iter_entries_by_dir():
206
if entry.kind == 'tree-reference':
207
yield path, entry.file_id
209
def kind(self, file_id):
210
raise NotImplementedError("Tree subclass %s must implement kind"
211
% self.__class__.__name__)
213
def stored_kind(self, file_id):
214
"""File kind stored for this file_id.
216
May not match kind on disk for working trees. Always available
217
for versioned files, even when the file itself is missing.
219
return self.kind(file_id)
221
def path_content_summary(self, path):
222
"""Get a summary of the information about path.
224
:param path: A relative path within the tree.
225
:return: A tuple containing kind, size, exec, sha1-or-link.
226
Kind is always present (see tree.kind()).
227
size is present if kind is file, None otherwise.
228
exec is None unless kind is file and the platform supports the 'x'
230
sha1-or-link is the link target if kind is symlink, or the sha1 if
231
it can be obtained without reading the file.
233
raise NotImplementedError(self.path_content_summary)
235
def get_reference_revision(self, file_id, path=None):
236
raise NotImplementedError("Tree subclass %s must implement "
237
"get_reference_revision"
238
% self.__class__.__name__)
240
def _comparison_data(self, entry, path):
241
"""Return a tuple of kind, executable, stat_value for a file.
243
entry may be None if there is no inventory entry for the file, but
244
path must always be supplied.
246
kind is None if there is no file present (even if an inventory id is
247
present). executable is False for non-file entries.
249
raise NotImplementedError(self._comparison_data)
251
def _file_size(self, entry, stat_value):
252
raise NotImplementedError(self._file_size)
254
def _get_inventory(self):
255
return self._inventory
257
def get_file(self, file_id, path=None):
258
"""Return a file object for the file file_id in the tree.
260
If both file_id and path are defined, it is implementation defined as
261
to which one is used.
263
raise NotImplementedError(self.get_file)
265
def get_file_mtime(self, file_id, path=None):
266
"""Return the modification time for a file.
268
:param file_id: The handle for this file.
269
:param path: The path that this file can be found at.
270
These must point to the same object.
272
raise NotImplementedError(self.get_file_mtime)
274
def get_file_size(self, file_id):
275
"""Return the size of a file in bytes.
277
This applies only to regular files. If invoked on directories or
278
symlinks, it will return None.
279
:param file_id: The file-id of the file
281
raise NotImplementedError(self.get_file_size)
283
def get_file_by_path(self, path):
284
return self.get_file(self._inventory.path2id(path), path)
286
def iter_files_bytes(self, desired_files):
287
"""Iterate through file contents.
289
Files will not necessarily be returned in the order they occur in
290
desired_files. No specific order is guaranteed.
292
Yields pairs of identifier, bytes_iterator. identifier is an opaque
293
value supplied by the caller as part of desired_files. It should
294
uniquely identify the file version in the caller's context. (Examples:
295
an index number or a TreeTransform trans_id.)
297
bytes_iterator is an iterable of bytestrings for the file. The
298
kind of iterable and length of the bytestrings are unspecified, but for
299
this implementation, it is a tuple containing a single bytestring with
300
the complete text of the file.
302
:param desired_files: a list of (file_id, identifier) pairs
304
for file_id, identifier in desired_files:
305
# We wrap the string in a tuple so that we can return an iterable
306
# of bytestrings. (Technically, a bytestring is also an iterable
307
# of bytestrings, but iterating through each character is not
309
cur_file = (self.get_file_text(file_id),)
310
yield identifier, cur_file
312
def get_symlink_target(self, file_id):
313
"""Get the target for a given file_id.
315
It is assumed that the caller already knows that file_id is referencing
317
:param file_id: Handle for the symlink entry.
318
:return: The path the symlink points to.
320
raise NotImplementedError(self.get_symlink_target)
322
def get_root_id(self):
323
"""Return the file_id for the root of this tree."""
324
raise NotImplementedError(self.get_root_id)
326
def annotate_iter(self, file_id,
327
default_revision=_mod_revision.CURRENT_REVISION):
328
"""Return an iterator of revision_id, line tuples.
330
For working trees (and mutable trees in general), the special
331
revision_id 'current:' will be used for lines that are new in this
332
tree, e.g. uncommitted changes.
333
:param file_id: The file to produce an annotated version from
334
:param default_revision: For lines that don't match a basis, mark them
335
with this revision id. Not all implementations will make use of
338
raise NotImplementedError(self.annotate_iter)
340
def _get_plan_merge_data(self, file_id, other, base):
341
from bzrlib import merge, versionedfile
342
vf = versionedfile._PlanMergeVersionedFile(file_id)
343
last_revision_a = self._get_file_revision(file_id, vf, 'this:')
344
last_revision_b = other._get_file_revision(file_id, vf, 'other:')
346
last_revision_base = None
348
last_revision_base = base._get_file_revision(file_id, vf, 'base:')
349
return vf, last_revision_a, last_revision_b, last_revision_base
351
def plan_file_merge(self, file_id, other, base=None):
352
"""Generate a merge plan based on annotations.
354
If the file contains uncommitted changes in this tree, they will be
355
attributed to the 'current:' pseudo-revision. If the file contains
356
uncommitted changes in the other tree, they will be assigned to the
357
'other:' pseudo-revision.
359
data = self._get_plan_merge_data(file_id, other, base)
360
vf, last_revision_a, last_revision_b, last_revision_base = data
361
return vf.plan_merge(last_revision_a, last_revision_b,
364
def plan_file_lca_merge(self, file_id, other, base=None):
365
"""Generate a merge plan based lca-newness.
367
If the file contains uncommitted changes in this tree, they will be
368
attributed to the 'current:' pseudo-revision. If the file contains
369
uncommitted changes in the other tree, they will be assigned to the
370
'other:' pseudo-revision.
372
data = self._get_plan_merge_data(file_id, other, base)
373
vf, last_revision_a, last_revision_b, last_revision_base = data
374
return vf.plan_lca_merge(last_revision_a, last_revision_b,
377
def _get_file_revision(self, file_id, vf, tree_revision):
378
"""Ensure that file_id, tree_revision is in vf to plan the merge."""
379
def file_revision(revision_tree):
380
revision_tree.lock_read()
382
return revision_tree.inventory[file_id].revision
384
revision_tree.unlock()
386
def iter_parent_trees():
387
for revision_id in self.get_parent_ids():
389
yield self.revision_tree(revision_id)
391
yield self.repository.revision_tree(revision_id)
393
if getattr(self, '_repository', None) is None:
394
last_revision = tree_revision
395
parent_keys = [(file_id, file_revision(t)) for t in
397
vf.add_lines((file_id, last_revision), parent_keys,
398
self.get_file(file_id).readlines())
399
repo = self.branch.repository
402
last_revision = file_revision(self)
403
base_vf = self._repository.texts
404
if base_vf not in vf.fallback_versionedfiles:
405
vf.fallback_versionedfiles.append(base_vf)
408
inventory = property(_get_inventory,
409
doc="Inventory of this Tree")
411
def _check_retrieved(self, ie, f):
414
fp = fingerprint_file(f)
417
if ie.text_size is not None:
418
if ie.text_size != fp['size']:
419
raise BzrError("mismatched size for file %r in %r" % (ie.file_id, self._store),
420
["inventory expects %d bytes" % ie.text_size,
421
"file is actually %d bytes" % fp['size'],
422
"store is probably damaged/corrupt"])
424
if ie.text_sha1 != fp['sha1']:
425
raise BzrError("wrong SHA-1 for file %r in %r" % (ie.file_id, self._store),
426
["inventory expects %s" % ie.text_sha1,
427
"file is actually %s" % fp['sha1'],
428
"store is probably damaged/corrupt"])
431
def path2id(self, path):
432
"""Return the id for path in this tree."""
433
return self._inventory.path2id(path)
435
def paths2ids(self, paths, trees=[], require_versioned=True):
436
"""Return all the ids that can be reached by walking from paths.
438
Each path is looked up in this tree and any extras provided in
439
trees, and this is repeated recursively: the children in an extra tree
440
of a directory that has been renamed under a provided path in this tree
441
are all returned, even if none exist under a provided path in this
442
tree, and vice versa.
444
:param paths: An iterable of paths to start converting to ids from.
445
Alternatively, if paths is None, no ids should be calculated and None
446
will be returned. This is offered to make calling the api unconditional
447
for code that *might* take a list of files.
448
:param trees: Additional trees to consider.
449
:param require_versioned: If False, do not raise NotVersionedError if
450
an element of paths is not versioned in this tree and all of trees.
452
return find_ids_across_trees(paths, [self] + list(trees), require_versioned)
454
@symbol_versioning.deprecated_method(symbol_versioning.one_six)
455
def print_file(self, file_id):
456
"""Print file with id `file_id` to stdout."""
458
sys.stdout.write(self.get_file_text(file_id))
463
def revision_tree(self, revision_id):
464
"""Obtain a revision tree for the revision revision_id.
466
The intention of this method is to allow access to possibly cached
467
tree data. Implementors of this method should raise NoSuchRevision if
468
the tree is not locally available, even if they could obtain the
469
tree via a repository or some other means. Callers are responsible
470
for finding the ultimate source for a revision tree.
472
:param revision_id: The revision_id of the requested tree.
474
:raises: NoSuchRevision if the tree cannot be obtained.
476
raise errors.NoSuchRevisionInTree(self, revision_id)
479
"""What files are present in this tree and unknown.
481
:return: an iterator over the unknown files.
488
def filter_unversioned_files(self, paths):
489
"""Filter out paths that are versioned.
491
:return: set of paths.
493
# NB: we specifically *don't* call self.has_filename, because for
494
# WorkingTrees that can indicate files that exist on disk but that
496
pred = self.inventory.has_filename
497
return set((p for p in paths if not pred(p)))
499
def walkdirs(self, prefix=""):
500
"""Walk the contents of this tree from path down.
502
This yields all the data about the contents of a directory at a time.
503
After each directory has been yielded, if the caller has mutated the
504
list to exclude some directories, they are then not descended into.
506
The data yielded is of the form:
507
((directory-relpath, directory-path-from-root, directory-fileid),
508
[(relpath, basename, kind, lstat, path_from_tree_root, file_id,
509
versioned_kind), ...]),
510
- directory-relpath is the containing dirs relpath from prefix
511
- directory-path-from-root is the containing dirs path from /
512
- directory-fileid is the id of the directory if it is versioned.
513
- relpath is the relative path within the subtree being walked.
514
- basename is the basename
515
- kind is the kind of the file now. If unknonwn then the file is not
516
present within the tree - but it may be recorded as versioned. See
518
- lstat is the stat data *if* the file was statted.
519
- path_from_tree_root is the path from the root of the tree.
520
- file_id is the file_id if the entry is versioned.
521
- versioned_kind is the kind of the file as last recorded in the
522
versioning system. If 'unknown' the file is not versioned.
523
One of 'kind' and 'versioned_kind' must not be 'unknown'.
525
:param prefix: Start walking from prefix within the tree rather than
526
at the root. This allows one to walk a subtree but get paths that are
527
relative to a tree rooted higher up.
528
:return: an iterator over the directory data.
530
raise NotImplementedError(self.walkdirs)
532
def iter_search_rules(self, path_names, pref_names=None,
533
_default_searcher=rules._per_user_searcher):
534
"""Find the preferences for filenames in a tree.
536
:param path_names: an iterable of paths to find attributes for.
537
Paths are given relative to the root of the tree.
538
:param pref_names: the list of preferences to lookup - None for all
539
:param _default_searcher: private parameter to assist testing - don't use
540
:return: an iterator of tuple sequences, one per path-name.
541
See _RulesSearcher.get_items for details on the tuple sequence.
543
searcher = self._get_rules_searcher(_default_searcher)
544
if searcher is not None:
545
if pref_names is not None:
546
for path in path_names:
547
yield searcher.get_selected_items(path, pref_names)
549
for path in path_names:
550
yield searcher.get_items(path)
553
def _get_rules_searcher(self, default_searcher):
554
"""Get the RulesSearcher for this tree given the default one."""
555
searcher = default_searcher
556
file_id = self.path2id(rules.RULES_TREE_FILENAME)
557
if file_id is not None:
558
ini_file = self.get_file(file_id)
559
searcher = rules._StackedRulesSearcher(
560
[rules._IniBasedRulesSearcher(ini_file), default_searcher])
564
class EmptyTree(Tree):
567
self._inventory = Inventory(root_id=None)
568
symbol_versioning.warn('EmptyTree is deprecated as of bzr 0.9 please'
569
' use repository.revision_tree instead.',
570
DeprecationWarning, stacklevel=2)
572
def get_parent_ids(self):
575
def get_symlink_target(self, file_id):
578
def has_filename(self, filename):
581
def kind(self, file_id):
584
def list_files(self, include_root=False):
587
def __contains__(self, file_id):
588
return (file_id in self._inventory)
590
def get_file_sha1(self, file_id, path=None, stat_value=None):
594
######################################################################
597
# TODO: Merge these two functions into a single one that can operate
598
# on either a whole tree or a set of files.
600
# TODO: Return the diff in order by filename, not by category or in
601
# random order. Can probably be done by lock-stepping through the
602
# filenames from both trees.
605
def file_status(filename, old_tree, new_tree):
606
"""Return single-letter status, old and new names for a file.
608
The complexity here is in deciding how to represent renames;
609
many complex cases are possible.
611
old_inv = old_tree.inventory
612
new_inv = new_tree.inventory
613
new_id = new_inv.path2id(filename)
614
old_id = old_inv.path2id(filename)
616
if not new_id and not old_id:
617
# easy: doesn't exist in either; not versioned at all
618
if new_tree.is_ignored(filename):
619
return 'I', None, None
621
return '?', None, None
623
# There is now a file of this name, great.
626
# There is no longer a file of this name, but we can describe
627
# what happened to the file that used to have
628
# this name. There are two possibilities: either it was
629
# deleted entirely, or renamed.
630
if new_inv.has_id(old_id):
631
return 'X', old_inv.id2path(old_id), new_inv.id2path(old_id)
633
return 'D', old_inv.id2path(old_id), None
635
# if the file_id is new in this revision, it is added
636
if new_id and not old_inv.has_id(new_id):
639
# if there used to be a file of this name, but that ID has now
640
# disappeared, it is deleted
641
if old_id and not new_inv.has_id(old_id):
648
def find_renames(old_inv, new_inv):
649
for file_id in old_inv:
650
if file_id not in new_inv:
652
old_name = old_inv.id2path(file_id)
653
new_name = new_inv.id2path(file_id)
654
if old_name != new_name:
655
yield (old_name, new_name)
658
def find_ids_across_trees(filenames, trees, require_versioned=True):
659
"""Find the ids corresponding to specified filenames.
661
All matches in all trees will be used, and all children of matched
662
directories will be used.
664
:param filenames: The filenames to find file_ids for (if None, returns
666
:param trees: The trees to find file_ids within
667
:param require_versioned: if true, all specified filenames must occur in
669
:return: a set of file ids for the specified filenames and their children.
673
specified_path_ids = _find_ids_across_trees(filenames, trees,
675
return _find_children_across_trees(specified_path_ids, trees)
678
def _find_ids_across_trees(filenames, trees, require_versioned):
679
"""Find the ids corresponding to specified filenames.
681
All matches in all trees will be used, but subdirectories are not scanned.
683
:param filenames: The filenames to find file_ids for
684
:param trees: The trees to find file_ids within
685
:param require_versioned: if true, all specified filenames must occur in
687
:return: a set of file ids for the specified filenames
690
interesting_ids = set()
691
for tree_path in filenames:
694
file_id = tree.path2id(tree_path)
695
if file_id is not None:
696
interesting_ids.add(file_id)
699
not_versioned.append(tree_path)
700
if len(not_versioned) > 0 and require_versioned:
701
raise errors.PathsNotVersionedError(not_versioned)
702
return interesting_ids
705
def _find_children_across_trees(specified_ids, trees):
706
"""Return a set including specified ids and their children.
708
All matches in all trees will be used.
710
:param trees: The trees to find file_ids within
711
:return: a set containing all specified ids and their children
713
interesting_ids = set(specified_ids)
714
pending = interesting_ids
715
# now handle children of interesting ids
716
# we loop so that we handle all children of each id in both trees
717
while len(pending) > 0:
719
for file_id in pending:
721
if not tree.has_id(file_id):
723
entry = tree.inventory[file_id]
724
for child in getattr(entry, 'children', {}).itervalues():
725
if child.file_id not in interesting_ids:
726
new_pending.add(child.file_id)
727
interesting_ids.update(new_pending)
728
pending = new_pending
729
return interesting_ids
732
class InterTree(InterObject):
733
"""This class represents operations taking place between two Trees.
735
Its instances have methods like 'compare' and contain references to the
736
source and target trees these operations are to be carried out on.
738
Clients of bzrlib should not need to use InterTree directly, rather they
739
should use the convenience methods on Tree such as 'Tree.compare()' which
740
will pass through to InterTree as appropriate.
746
def compare(self, want_unchanged=False, specific_files=None,
747
extra_trees=None, require_versioned=False, include_root=False,
748
want_unversioned=False):
749
"""Return the changes from source to target.
751
:return: A TreeDelta.
752
:param specific_files: An optional list of file paths to restrict the
753
comparison to. When mapping filenames to ids, all matches in all
754
trees (including optional extra_trees) are used, and all children of
755
matched directories are included.
756
:param want_unchanged: An optional boolean requesting the inclusion of
757
unchanged entries in the result.
758
:param extra_trees: An optional list of additional trees to use when
759
mapping the contents of specific_files (paths) to file_ids.
760
:param require_versioned: An optional boolean (defaults to False). When
761
supplied and True all the 'specific_files' must be versioned, or
762
a PathsNotVersionedError will be thrown.
763
:param want_unversioned: Scan for unversioned paths.
765
# NB: show_status depends on being able to pass in non-versioned files
766
# and report them as unknown
767
trees = (self.source,)
768
if extra_trees is not None:
769
trees = trees + tuple(extra_trees)
770
# target is usually the newer tree:
771
specific_file_ids = self.target.paths2ids(specific_files, trees,
772
require_versioned=require_versioned)
773
if specific_files and not specific_file_ids:
774
# All files are unversioned, so just return an empty delta
775
# _compare_trees would think we want a complete delta
776
result = delta.TreeDelta()
777
fake_entry = InventoryFile('unused', 'unused', 'unused')
778
result.unversioned = [(path, None,
779
self.target._comparison_data(fake_entry, path)[0]) for path in
782
return delta._compare_trees(self.source, self.target, want_unchanged,
783
specific_files, include_root, extra_trees=extra_trees,
784
require_versioned=require_versioned,
785
want_unversioned=want_unversioned)
787
def iter_changes(self, include_unchanged=False,
788
specific_files=None, pb=None, extra_trees=[],
789
require_versioned=True, want_unversioned=False):
790
"""Generate an iterator of changes between trees.
793
(file_id, (path_in_source, path_in_target),
794
changed_content, versioned, parent, name, kind,
797
Changed_content is True if the file's content has changed. This
798
includes changes to its kind, and to a symlink's target.
800
versioned, parent, name, kind, executable are tuples of (from, to).
801
If a file is missing in a tree, its kind is None.
803
Iteration is done in parent-to-child order, relative to the target
806
There is no guarantee that all paths are in sorted order: the
807
requirement to expand the search due to renames may result in children
808
that should be found early being found late in the search, after
809
lexically later results have been returned.
810
:param require_versioned: Raise errors.PathsNotVersionedError if a
811
path in the specific_files list is not versioned in one of
812
source, target or extra_trees.
813
:param want_unversioned: Should unversioned files be returned in the
814
output. An unversioned file is defined as one with (False, False)
815
for the versioned pair.
818
lookup_trees = [self.source]
820
lookup_trees.extend(extra_trees)
821
if specific_files == []:
822
specific_file_ids = []
824
specific_file_ids = self.target.paths2ids(specific_files,
825
lookup_trees, require_versioned=require_versioned)
827
all_unversioned = sorted([(p.split('/'), p) for p in
829
if specific_files is None or
830
osutils.is_inside_any(specific_files, p)])
831
all_unversioned = deque(all_unversioned)
833
all_unversioned = deque()
835
from_entries_by_dir = list(self.source.inventory.iter_entries_by_dir(
836
specific_file_ids=specific_file_ids))
837
from_data = dict((e.file_id, (p, e)) for p, e in from_entries_by_dir)
838
to_entries_by_dir = list(self.target.inventory.iter_entries_by_dir(
839
specific_file_ids=specific_file_ids))
840
num_entries = len(from_entries_by_dir) + len(to_entries_by_dir)
842
# the unversioned path lookup only occurs on real trees - where there
843
# can be extras. So the fake_entry is solely used to look up
844
# executable it values when execute is not supported.
845
fake_entry = InventoryFile('unused', 'unused', 'unused')
846
for to_path, to_entry in to_entries_by_dir:
847
while all_unversioned and all_unversioned[0][0] < to_path.split('/'):
848
unversioned_path = all_unversioned.popleft()
849
to_kind, to_executable, to_stat = \
850
self.target._comparison_data(fake_entry, unversioned_path[1])
851
yield (None, (None, unversioned_path[1]), True, (False, False),
853
(None, unversioned_path[0][-1]),
855
(None, to_executable))
856
file_id = to_entry.file_id
857
to_paths[file_id] = to_path
859
changed_content = False
860
from_path, from_entry = from_data.get(file_id, (None, None))
861
from_versioned = (from_entry is not None)
862
if from_entry is not None:
863
from_versioned = True
864
from_name = from_entry.name
865
from_parent = from_entry.parent_id
866
from_kind, from_executable, from_stat = \
867
self.source._comparison_data(from_entry, from_path)
870
from_versioned = False
874
from_executable = None
875
versioned = (from_versioned, True)
876
to_kind, to_executable, to_stat = \
877
self.target._comparison_data(to_entry, to_path)
878
kind = (from_kind, to_kind)
879
if kind[0] != kind[1]:
880
changed_content = True
881
elif from_kind == 'file':
882
from_size = self.source._file_size(from_entry, from_stat)
883
to_size = self.target._file_size(to_entry, to_stat)
884
if from_size != to_size:
885
changed_content = True
886
elif (self.source.get_file_sha1(file_id, from_path, from_stat) !=
887
self.target.get_file_sha1(file_id, to_path, to_stat)):
888
changed_content = True
889
elif from_kind == 'symlink':
890
if (self.source.get_symlink_target(file_id) !=
891
self.target.get_symlink_target(file_id)):
892
changed_content = True
893
elif from_kind == 'tree-reference':
894
if (self.source.get_reference_revision(file_id, from_path)
895
!= self.target.get_reference_revision(file_id, to_path)):
896
changed_content = True
897
parent = (from_parent, to_entry.parent_id)
898
name = (from_name, to_entry.name)
899
executable = (from_executable, to_executable)
901
pb.update('comparing files', entry_count, num_entries)
902
if (changed_content is not False or versioned[0] != versioned[1]
903
or parent[0] != parent[1] or name[0] != name[1] or
904
executable[0] != executable[1] or include_unchanged):
905
yield (file_id, (from_path, to_path), changed_content,
906
versioned, parent, name, kind, executable)
908
while all_unversioned:
909
# yield any trailing unversioned paths
910
unversioned_path = all_unversioned.popleft()
911
to_kind, to_executable, to_stat = \
912
self.target._comparison_data(fake_entry, unversioned_path[1])
913
yield (None, (None, unversioned_path[1]), True, (False, False),
915
(None, unversioned_path[0][-1]),
917
(None, to_executable))
919
def get_to_path(to_entry):
920
if to_entry.parent_id is None:
921
to_path = '' # the root
923
if to_entry.parent_id not in to_paths:
925
return get_to_path(self.target.inventory[to_entry.parent_id])
926
to_path = osutils.pathjoin(to_paths[to_entry.parent_id],
928
to_paths[to_entry.file_id] = to_path
931
for path, from_entry in from_entries_by_dir:
932
file_id = from_entry.file_id
933
if file_id in to_paths:
936
if not file_id in self.target.inventory:
937
# common case - paths we have not emitted are not present in
941
to_path = get_to_path(self.target.inventory[file_id])
944
pb.update('comparing files', entry_count, num_entries)
945
versioned = (True, False)
946
parent = (from_entry.parent_id, None)
947
name = (from_entry.name, None)
948
from_kind, from_executable, stat_value = \
949
self.source._comparison_data(from_entry, path)
950
kind = (from_kind, None)
951
executable = (from_executable, None)
952
changed_content = True
953
# the parent's path is necessarily known at this point.
954
yield(file_id, (path, to_path), changed_content, versioned, parent,
955
name, kind, executable)
added
removed
bzrlib/tree.py
