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 _iter_parent_trees(self):
378
"""Iterate through parent trees, defaulting to Tree.revision_tree."""
379
for revision_id in self.get_parent_ids():
381
yield self.revision_tree(revision_id)
382
except errors.NoSuchRevisionInTree:
383
yield self.repository.revision_tree(revision_id)
386
def _file_revision(revision_tree, file_id):
387
"""Determine the revision associated with a file in a given tree."""
388
revision_tree.lock_read()
390
return revision_tree.inventory[file_id].revision
392
revision_tree.unlock()
394
def _get_file_revision(self, file_id, vf, tree_revision):
395
"""Ensure that file_id, tree_revision is in vf to plan the merge."""
397
if getattr(self, '_repository', None) is None:
398
last_revision = tree_revision
399
parent_keys = [(file_id, self._file_revision(t, file_id)) for t in
400
self._iter_parent_trees()]
401
vf.add_lines((file_id, last_revision), parent_keys,
402
self.get_file(file_id).readlines())
403
repo = self.branch.repository
406
last_revision = self._file_revision(self, file_id)
407
base_vf = self._repository.texts
408
if base_vf not in vf.fallback_versionedfiles:
409
vf.fallback_versionedfiles.append(base_vf)
412
inventory = property(_get_inventory,
413
doc="Inventory of this Tree")
415
def _check_retrieved(self, ie, f):
418
fp = fingerprint_file(f)
421
if ie.text_size is not None:
422
if ie.text_size != fp['size']:
423
raise BzrError("mismatched size for file %r in %r" % (ie.file_id, self._store),
424
["inventory expects %d bytes" % ie.text_size,
425
"file is actually %d bytes" % fp['size'],
426
"store is probably damaged/corrupt"])
428
if ie.text_sha1 != fp['sha1']:
429
raise BzrError("wrong SHA-1 for file %r in %r" % (ie.file_id, self._store),
430
["inventory expects %s" % ie.text_sha1,
431
"file is actually %s" % fp['sha1'],
432
"store is probably damaged/corrupt"])
435
def path2id(self, path):
436
"""Return the id for path in this tree."""
437
return self._inventory.path2id(path)
439
def paths2ids(self, paths, trees=[], require_versioned=True):
440
"""Return all the ids that can be reached by walking from paths.
442
Each path is looked up in this tree and any extras provided in
443
trees, and this is repeated recursively: the children in an extra tree
444
of a directory that has been renamed under a provided path in this tree
445
are all returned, even if none exist under a provided path in this
446
tree, and vice versa.
448
:param paths: An iterable of paths to start converting to ids from.
449
Alternatively, if paths is None, no ids should be calculated and None
450
will be returned. This is offered to make calling the api unconditional
451
for code that *might* take a list of files.
452
:param trees: Additional trees to consider.
453
:param require_versioned: If False, do not raise NotVersionedError if
454
an element of paths is not versioned in this tree and all of trees.
456
return find_ids_across_trees(paths, [self] + list(trees), require_versioned)
458
def iter_children(self, file_id):
459
entry = self.iter_entries_by_dir([file_id]).next()[1]
460
for child in getattr(entry, 'children', {}).itervalues():
463
@symbol_versioning.deprecated_method(symbol_versioning.one_six)
464
def print_file(self, file_id):
465
"""Print file with id `file_id` to stdout."""
467
sys.stdout.write(self.get_file_text(file_id))
472
def revision_tree(self, revision_id):
473
"""Obtain a revision tree for the revision revision_id.
475
The intention of this method is to allow access to possibly cached
476
tree data. Implementors of this method should raise NoSuchRevision if
477
the tree is not locally available, even if they could obtain the
478
tree via a repository or some other means. Callers are responsible
479
for finding the ultimate source for a revision tree.
481
:param revision_id: The revision_id of the requested tree.
483
:raises: NoSuchRevision if the tree cannot be obtained.
485
raise errors.NoSuchRevisionInTree(self, revision_id)
488
"""What files are present in this tree and unknown.
490
:return: an iterator over the unknown files.
497
def filter_unversioned_files(self, paths):
498
"""Filter out paths that are versioned.
500
:return: set of paths.
502
# NB: we specifically *don't* call self.has_filename, because for
503
# WorkingTrees that can indicate files that exist on disk but that
505
pred = self.inventory.has_filename
506
return set((p for p in paths if not pred(p)))
508
def walkdirs(self, prefix=""):
509
"""Walk the contents of this tree from path down.
511
This yields all the data about the contents of a directory at a time.
512
After each directory has been yielded, if the caller has mutated the
513
list to exclude some directories, they are then not descended into.
515
The data yielded is of the form:
516
((directory-relpath, directory-path-from-root, directory-fileid),
517
[(relpath, basename, kind, lstat, path_from_tree_root, file_id,
518
versioned_kind), ...]),
519
- directory-relpath is the containing dirs relpath from prefix
520
- directory-path-from-root is the containing dirs path from /
521
- directory-fileid is the id of the directory if it is versioned.
522
- relpath is the relative path within the subtree being walked.
523
- basename is the basename
524
- kind is the kind of the file now. If unknonwn then the file is not
525
present within the tree - but it may be recorded as versioned. See
527
- lstat is the stat data *if* the file was statted.
528
- path_from_tree_root is the path from the root of the tree.
529
- file_id is the file_id if the entry is versioned.
530
- versioned_kind is the kind of the file as last recorded in the
531
versioning system. If 'unknown' the file is not versioned.
532
One of 'kind' and 'versioned_kind' must not be 'unknown'.
534
:param prefix: Start walking from prefix within the tree rather than
535
at the root. This allows one to walk a subtree but get paths that are
536
relative to a tree rooted higher up.
537
:return: an iterator over the directory data.
539
raise NotImplementedError(self.walkdirs)
541
def iter_search_rules(self, path_names, pref_names=None,
542
_default_searcher=rules._per_user_searcher):
543
"""Find the preferences for filenames in a tree.
545
:param path_names: an iterable of paths to find attributes for.
546
Paths are given relative to the root of the tree.
547
:param pref_names: the list of preferences to lookup - None for all
548
:param _default_searcher: private parameter to assist testing - don't use
549
:return: an iterator of tuple sequences, one per path-name.
550
See _RulesSearcher.get_items for details on the tuple sequence.
552
searcher = self._get_rules_searcher(_default_searcher)
553
if searcher is not None:
554
if pref_names is not None:
555
for path in path_names:
556
yield searcher.get_selected_items(path, pref_names)
558
for path in path_names:
559
yield searcher.get_items(path)
562
def _get_rules_searcher(self, default_searcher):
563
"""Get the RulesSearcher for this tree given the default one."""
564
searcher = default_searcher
565
file_id = self.path2id(rules.RULES_TREE_FILENAME)
566
if file_id is not None:
567
ini_file = self.get_file(file_id)
568
searcher = rules._StackedRulesSearcher(
569
[rules._IniBasedRulesSearcher(ini_file), default_searcher])
573
class EmptyTree(Tree):
576
self._inventory = Inventory(root_id=None)
577
symbol_versioning.warn('EmptyTree is deprecated as of bzr 0.9 please'
578
' use repository.revision_tree instead.',
579
DeprecationWarning, stacklevel=2)
581
def get_parent_ids(self):
584
def get_symlink_target(self, file_id):
587
def has_filename(self, filename):
590
def kind(self, file_id):
593
def list_files(self, include_root=False):
596
def __contains__(self, file_id):
597
return (file_id in self._inventory)
599
def get_file_sha1(self, file_id, path=None, stat_value=None):
603
######################################################################
606
# TODO: Merge these two functions into a single one that can operate
607
# on either a whole tree or a set of files.
609
# TODO: Return the diff in order by filename, not by category or in
610
# random order. Can probably be done by lock-stepping through the
611
# filenames from both trees.
614
def file_status(filename, old_tree, new_tree):
615
"""Return single-letter status, old and new names for a file.
617
The complexity here is in deciding how to represent renames;
618
many complex cases are possible.
620
old_inv = old_tree.inventory
621
new_inv = new_tree.inventory
622
new_id = new_inv.path2id(filename)
623
old_id = old_inv.path2id(filename)
625
if not new_id and not old_id:
626
# easy: doesn't exist in either; not versioned at all
627
if new_tree.is_ignored(filename):
628
return 'I', None, None
630
return '?', None, None
632
# There is now a file of this name, great.
635
# There is no longer a file of this name, but we can describe
636
# what happened to the file that used to have
637
# this name. There are two possibilities: either it was
638
# deleted entirely, or renamed.
639
if new_inv.has_id(old_id):
640
return 'X', old_inv.id2path(old_id), new_inv.id2path(old_id)
642
return 'D', old_inv.id2path(old_id), None
644
# if the file_id is new in this revision, it is added
645
if new_id and not old_inv.has_id(new_id):
648
# if there used to be a file of this name, but that ID has now
649
# disappeared, it is deleted
650
if old_id and not new_inv.has_id(old_id):
657
def find_renames(old_inv, new_inv):
658
for file_id in old_inv:
659
if file_id not in new_inv:
661
old_name = old_inv.id2path(file_id)
662
new_name = new_inv.id2path(file_id)
663
if old_name != new_name:
664
yield (old_name, new_name)
667
def find_ids_across_trees(filenames, trees, require_versioned=True):
668
"""Find the ids corresponding to specified filenames.
670
All matches in all trees will be used, and all children of matched
671
directories will be used.
673
:param filenames: The filenames to find file_ids for (if None, returns
675
:param trees: The trees to find file_ids within
676
:param require_versioned: if true, all specified filenames must occur in
678
:return: a set of file ids for the specified filenames and their children.
680
if filenames is None:
682
specified_path_ids = _find_ids_across_trees(filenames, trees,
684
return _find_children_across_trees(specified_path_ids, trees)
687
def _find_ids_across_trees(filenames, trees, require_versioned):
688
"""Find the ids corresponding to specified filenames.
690
All matches in all trees will be used, but subdirectories are not scanned.
692
:param filenames: The filenames to find file_ids for
693
:param trees: The trees to find file_ids within
694
:param require_versioned: if true, all specified filenames must occur in
696
:return: a set of file ids for the specified filenames
699
interesting_ids = set()
700
for tree_path in filenames:
703
file_id = tree.path2id(tree_path)
704
if file_id is not None:
705
interesting_ids.add(file_id)
708
not_versioned.append(tree_path)
709
if len(not_versioned) > 0 and require_versioned:
710
raise errors.PathsNotVersionedError(not_versioned)
711
return interesting_ids
714
def _find_children_across_trees(specified_ids, trees):
715
"""Return a set including specified ids and their children.
717
All matches in all trees will be used.
719
:param trees: The trees to find file_ids within
720
:return: a set containing all specified ids and their children
722
interesting_ids = set(specified_ids)
723
pending = interesting_ids
724
# now handle children of interesting ids
725
# we loop so that we handle all children of each id in both trees
726
while len(pending) > 0:
728
for file_id in pending:
730
if not tree.has_id(file_id):
732
for child_id in tree.iter_children(file_id):
733
if child_id not in interesting_ids:
734
new_pending.add(child_id)
735
interesting_ids.update(new_pending)
736
pending = new_pending
737
return interesting_ids
740
class InterTree(InterObject):
741
"""This class represents operations taking place between two Trees.
743
Its instances have methods like 'compare' and contain references to the
744
source and target trees these operations are to be carried out on.
746
Clients of bzrlib should not need to use InterTree directly, rather they
747
should use the convenience methods on Tree such as 'Tree.compare()' which
748
will pass through to InterTree as appropriate.
754
def compare(self, want_unchanged=False, specific_files=None,
755
extra_trees=None, require_versioned=False, include_root=False,
756
want_unversioned=False):
757
"""Return the changes from source to target.
759
:return: A TreeDelta.
760
:param specific_files: An optional list of file paths to restrict the
761
comparison to. When mapping filenames to ids, all matches in all
762
trees (including optional extra_trees) are used, and all children of
763
matched directories are included.
764
:param want_unchanged: An optional boolean requesting the inclusion of
765
unchanged entries in the result.
766
:param extra_trees: An optional list of additional trees to use when
767
mapping the contents of specific_files (paths) to file_ids.
768
:param require_versioned: An optional boolean (defaults to False). When
769
supplied and True all the 'specific_files' must be versioned, or
770
a PathsNotVersionedError will be thrown.
771
:param want_unversioned: Scan for unversioned paths.
773
# NB: show_status depends on being able to pass in non-versioned files
774
# and report them as unknown
775
trees = (self.source,)
776
if extra_trees is not None:
777
trees = trees + tuple(extra_trees)
778
# target is usually the newer tree:
779
specific_file_ids = self.target.paths2ids(specific_files, trees,
780
require_versioned=require_versioned)
781
if specific_files and not specific_file_ids:
782
# All files are unversioned, so just return an empty delta
783
# _compare_trees would think we want a complete delta
784
result = delta.TreeDelta()
785
fake_entry = InventoryFile('unused', 'unused', 'unused')
786
result.unversioned = [(path, None,
787
self.target._comparison_data(fake_entry, path)[0]) for path in
790
return delta._compare_trees(self.source, self.target, want_unchanged,
791
specific_files, include_root, extra_trees=extra_trees,
792
require_versioned=require_versioned,
793
want_unversioned=want_unversioned)
795
def iter_changes(self, include_unchanged=False,
796
specific_files=None, pb=None, extra_trees=[],
797
require_versioned=True, want_unversioned=False):
798
"""Generate an iterator of changes between trees.
801
(file_id, (path_in_source, path_in_target),
802
changed_content, versioned, parent, name, kind,
805
Changed_content is True if the file's content has changed. This
806
includes changes to its kind, and to a symlink's target.
808
versioned, parent, name, kind, executable are tuples of (from, to).
809
If a file is missing in a tree, its kind is None.
811
Iteration is done in parent-to-child order, relative to the target
814
There is no guarantee that all paths are in sorted order: the
815
requirement to expand the search due to renames may result in children
816
that should be found early being found late in the search, after
817
lexically later results have been returned.
818
:param require_versioned: Raise errors.PathsNotVersionedError if a
819
path in the specific_files list is not versioned in one of
820
source, target or extra_trees.
821
:param want_unversioned: Should unversioned files be returned in the
822
output. An unversioned file is defined as one with (False, False)
823
for the versioned pair.
826
lookup_trees = [self.source]
828
lookup_trees.extend(extra_trees)
829
if specific_files == []:
830
specific_file_ids = []
832
specific_file_ids = self.target.paths2ids(specific_files,
833
lookup_trees, require_versioned=require_versioned)
835
all_unversioned = sorted([(p.split('/'), p) for p in
837
if specific_files is None or
838
osutils.is_inside_any(specific_files, p)])
839
all_unversioned = deque(all_unversioned)
841
all_unversioned = deque()
843
from_entries_by_dir = list(self.source.inventory.iter_entries_by_dir(
844
specific_file_ids=specific_file_ids))
845
from_data = dict((e.file_id, (p, e)) for p, e in from_entries_by_dir)
846
to_entries_by_dir = list(self.target.inventory.iter_entries_by_dir(
847
specific_file_ids=specific_file_ids))
848
num_entries = len(from_entries_by_dir) + len(to_entries_by_dir)
850
# the unversioned path lookup only occurs on real trees - where there
851
# can be extras. So the fake_entry is solely used to look up
852
# executable it values when execute is not supported.
853
fake_entry = InventoryFile('unused', 'unused', 'unused')
854
for to_path, to_entry in to_entries_by_dir:
855
while all_unversioned and all_unversioned[0][0] < to_path.split('/'):
856
unversioned_path = all_unversioned.popleft()
857
to_kind, to_executable, to_stat = \
858
self.target._comparison_data(fake_entry, unversioned_path[1])
859
yield (None, (None, unversioned_path[1]), True, (False, False),
861
(None, unversioned_path[0][-1]),
863
(None, to_executable))
864
file_id = to_entry.file_id
865
to_paths[file_id] = to_path
867
changed_content = False
868
from_path, from_entry = from_data.get(file_id, (None, None))
869
from_versioned = (from_entry is not None)
870
if from_entry is not None:
871
from_versioned = True
872
from_name = from_entry.name
873
from_parent = from_entry.parent_id
874
from_kind, from_executable, from_stat = \
875
self.source._comparison_data(from_entry, from_path)
878
from_versioned = False
882
from_executable = None
883
versioned = (from_versioned, True)
884
to_kind, to_executable, to_stat = \
885
self.target._comparison_data(to_entry, to_path)
886
kind = (from_kind, to_kind)
887
if kind[0] != kind[1]:
888
changed_content = True
889
elif from_kind == 'file':
890
from_size = self.source._file_size(from_entry, from_stat)
891
to_size = self.target._file_size(to_entry, to_stat)
892
if from_size != to_size:
893
changed_content = True
894
elif (self.source.get_file_sha1(file_id, from_path, from_stat) !=
895
self.target.get_file_sha1(file_id, to_path, to_stat)):
896
changed_content = True
897
elif from_kind == 'symlink':
898
if (self.source.get_symlink_target(file_id) !=
899
self.target.get_symlink_target(file_id)):
900
changed_content = True
901
elif from_kind == 'tree-reference':
902
if (self.source.get_reference_revision(file_id, from_path)
903
!= self.target.get_reference_revision(file_id, to_path)):
904
changed_content = True
905
parent = (from_parent, to_entry.parent_id)
906
name = (from_name, to_entry.name)
907
executable = (from_executable, to_executable)
909
pb.update('comparing files', entry_count, num_entries)
910
if (changed_content is not False or versioned[0] != versioned[1]
911
or parent[0] != parent[1] or name[0] != name[1] or
912
executable[0] != executable[1] or include_unchanged):
913
yield (file_id, (from_path, to_path), changed_content,
914
versioned, parent, name, kind, executable)
916
while all_unversioned:
917
# yield any trailing unversioned paths
918
unversioned_path = all_unversioned.popleft()
919
to_kind, to_executable, to_stat = \
920
self.target._comparison_data(fake_entry, unversioned_path[1])
921
yield (None, (None, unversioned_path[1]), True, (False, False),
923
(None, unversioned_path[0][-1]),
925
(None, to_executable))
927
def get_to_path(to_entry):
928
if to_entry.parent_id is None:
929
to_path = '' # the root
931
if to_entry.parent_id not in to_paths:
933
return get_to_path(self.target.inventory[to_entry.parent_id])
934
to_path = osutils.pathjoin(to_paths[to_entry.parent_id],
936
to_paths[to_entry.file_id] = to_path
939
for path, from_entry in from_entries_by_dir:
940
file_id = from_entry.file_id
941
if file_id in to_paths:
944
if not file_id in self.target.inventory:
945
# common case - paths we have not emitted are not present in
949
to_path = get_to_path(self.target.inventory[file_id])
952
pb.update('comparing files', entry_count, num_entries)
953
versioned = (True, False)
954
parent = (from_entry.parent_id, None)
955
name = (from_entry.name, None)
956
from_kind, from_executable, stat_value = \
957
self.source._comparison_data(from_entry, path)
958
kind = (from_kind, None)
959
executable = (from_executable, None)
960
changed_content = True
961
# the parent's path is necessarily known at this point.
962
yield(file_id, (path, to_path), changed_content, versioned, parent,
963
name, kind, executable)
added
removed
bzrlib/tree.py
