56
51
trees or versioned trees.
59
def changes_from(self, other, want_unchanged=False, specific_files=None,
60
extra_trees=None, require_versioned=False, include_root=False):
61
"""Return a TreeDelta of the changes from other to this tree.
63
:param other: A tree to compare with.
64
:param specific_files: An optional list of file paths to restrict the
65
comparison to. When mapping filenames to ids, all matches in all
66
trees (including optional extra_trees) are used, and all children of
67
matched directories are included.
68
:param want_unchanged: An optional boolean requesting the inclusion of
69
unchanged entries in the result.
70
:param extra_trees: An optional list of additional trees to use when
71
mapping the contents of specific_files (paths) to file_ids.
72
:param require_versioned: An optional boolean (defaults to False). When
73
supplied and True all the 'specific_files' must be versioned, or
74
a PathsNotVersionedError will be thrown.
76
The comparison will be performed by an InterTree object looked up on
79
# Martin observes that Tree.changes_from returns a TreeDelta and this
80
# may confuse people, because the class name of the returned object is
81
# a synonym of the object referenced in the method name.
82
return InterTree.get(other, self).compare(
83
want_unchanged=want_unchanged,
84
specific_files=specific_files,
85
extra_trees=extra_trees,
86
require_versioned=require_versioned,
87
include_root=include_root
90
def _iter_changes(self, from_tree, include_unchanged=False,
91
specific_files=None, pb=None, extra_trees=None,
92
require_versioned=True):
93
intertree = InterTree.get(from_tree, self)
94
return intertree._iter_changes(include_unchanged, specific_files, pb,
95
extra_trees, require_versioned)
98
"""Get a list of the conflicts in the tree.
100
Each conflict is an instance of bzrlib.conflicts.Conflict.
104
def get_parent_ids(self):
105
"""Get the parent ids for this tree.
107
:return: a list of parent ids. [] is returned to indicate
108
a tree with no parents.
109
:raises: BzrError if the parents are not known.
111
raise NotImplementedError(self.get_parent_ids)
113
54
def has_filename(self, filename):
114
55
"""True if the tree has given filename."""
115
56
raise NotImplementedError()
117
58
def has_id(self, file_id):
118
file_id = osutils.safe_file_id(file_id)
119
59
return self.inventory.has_id(file_id)
121
__contains__ = has_id
123
61
def has_or_had_id(self, file_id):
124
file_id = osutils.safe_file_id(file_id)
125
62
if file_id == self.inventory.root.file_id:
127
64
return self.inventory.has_id(file_id)
129
68
def __iter__(self):
130
69
return iter(self.inventory)
132
71
def id2path(self, file_id):
133
file_id = osutils.safe_file_id(file_id)
134
72
return self.inventory.id2path(file_id)
136
def is_control_filename(self, filename):
137
"""True if filename is the name of a control file in this tree.
139
:param filename: A filename within the tree. This is a relative path
140
from the root of this tree.
142
This is true IF and ONLY IF the filename is part of the meta data
143
that bzr controls in this tree. I.E. a random .bzr directory placed
144
on disk will not be a control file for this tree.
146
return self.bzrdir.is_control_filename(filename)
149
def iter_entries_by_dir(self, specific_file_ids=None):
150
"""Walk the tree in 'by_dir' order.
152
This will yield each entry in the tree as a (path, entry) tuple. The
153
order that they are yielded is: the contents of a directory are
154
preceeded by the parent of a directory, and all the contents of a
155
directory are grouped together.
157
return self.inventory.iter_entries_by_dir(
158
specific_file_ids=specific_file_ids)
160
def iter_reference_entries(self):
161
for path, entry in self.iter_entries_by_dir():
162
if entry.kind == 'tree-reference':
165
def kind(self, file_id):
166
raise NotImplementedError("subclasses must implement kind")
168
def get_reference_revision(self, entry, path=None):
169
raise NotImplementedError("subclasses must implement "
170
"get_reference_revision")
172
def _comparison_data(self, entry, path):
173
"""Return a tuple of kind, executable, stat_value for a file.
175
entry may be None if there is no inventory entry for the file, but
176
path must always be supplied.
178
kind is None if there is no file present (even if an inventory id is
179
present). executable is False for non-file entries.
181
raise NotImplementedError(self._comparison_data)
183
def _file_size(self, entry, stat_value):
184
raise NotImplementedError(self._file_size)
186
74
def _get_inventory(self):
187
75
return self._inventory
189
def get_file(self, file_id):
190
"""Return a file object for the file file_id in the tree."""
191
raise NotImplementedError(self.get_file)
193
77
def get_file_by_path(self, path):
194
78
return self.get_file(self._inventory.path2id(path))
196
def get_symlink_target(self, file_id):
197
"""Get the target for a given file_id.
199
It is assumed that the caller already knows that file_id is referencing
201
:param file_id: Handle for the symlink entry.
202
:return: The path the symlink points to.
204
raise NotImplementedError(self.get_symlink_target)
206
def annotate_iter(self, file_id):
207
"""Return an iterator of revision_id, line tuples
209
For working trees (and mutable trees in general), the special
210
revision_id 'current:' will be used for lines that are new in this
211
tree, e.g. uncommitted changes.
212
:param file_id: The file to produce an annotated version from
214
raise NotImplementedError(self.annotate_iter)
216
80
inventory = property(_get_inventory,
217
81
doc="Inventory of this Tree")
235
99
"file is actually %s" % fp['sha1'],
236
100
"store is probably damaged/corrupt"])
238
def path2id(self, path):
239
"""Return the id for path in this tree."""
240
return self._inventory.path2id(path)
242
def paths2ids(self, paths, trees=[], require_versioned=True):
243
"""Return all the ids that can be reached by walking from paths.
245
Each path is looked up in each this tree and any extras provided in
246
trees, and this is repeated recursively: the children in an extra tree
247
of a directory that has been renamed under a provided path in this tree
248
are all returned, even if none exist until a provided path in this
249
tree, and vice versa.
251
:param paths: An iterable of paths to start converting to ids from.
252
Alternatively, if paths is None, no ids should be calculated and None
253
will be returned. This is offered to make calling the api unconditional
254
for code that *might* take a list of files.
255
:param trees: Additional trees to consider.
256
:param require_versioned: If False, do not raise NotVersionedError if
257
an element of paths is not versioned in this tree and all of trees.
259
return find_ids_across_trees(paths, [self] + list(trees), require_versioned)
261
103
def print_file(self, file_id):
262
104
"""Print file with id `file_id` to stdout."""
263
file_id = osutils.safe_file_id(file_id)
265
106
sys.stdout.write(self.get_file_text(file_id))
270
def revision_tree(self, revision_id):
271
"""Obtain a revision tree for the revision revision_id.
273
The intention of this method is to allow access to possibly cached
274
tree data. Implementors of this method should raise NoSuchRevision if
275
the tree is not locally available, even if they could obtain the
276
tree via a repository or some other means. Callers are responsible
277
for finding the ultimate source for a revision tree.
279
:param revision_id: The revision_id of the requested tree.
281
:raises: NoSuchRevision if the tree cannot be obtained.
283
raise errors.NoSuchRevisionInTree(self, revision_id)
286
"""What files are present in this tree and unknown.
288
:return: an iterator over the unknown files.
295
def filter_unversioned_files(self, paths):
296
"""Filter out paths that are not versioned.
298
:return: set of paths.
300
# NB: we specifically *don't* call self.has_filename, because for
301
# WorkingTrees that can indicate files that exist on disk but that
303
pred = self.inventory.has_filename
304
return set((p for p in paths if not pred(p)))
306
def walkdirs(self, prefix=""):
307
"""Walk the contents of this tree from path down.
309
This yields all the data about the contents of a directory at a time.
310
After each directory has been yielded, if the caller has mutated the
311
list to exclude some directories, they are then not descended into.
313
The data yielded is of the form:
314
((directory-relpath, directory-path-from-root, directory-fileid),
315
[(relpath, basename, kind, lstat, path_from_tree_root, file_id,
316
versioned_kind), ...]),
317
- directory-relpath is the containing dirs relpath from prefix
318
- directory-path-from-root is the containing dirs path from /
319
- directory-fileid is the id of the directory if it is versioned.
320
- relpath is the relative path within the subtree being walked.
321
- basename is the basename
322
- kind is the kind of the file now. If unknonwn then the file is not
323
present within the tree - but it may be recorded as versioned. See
325
- lstat is the stat data *if* the file was statted.
326
- path_from_tree_root is the path from the root of the tree.
327
- file_id is the file_id is the entry is versioned.
328
- versioned_kind is the kind of the file as last recorded in the
329
versioning system. If 'unknown' the file is not versioned.
330
One of 'kind' and 'versioned_kind' must not be 'unknown'.
332
:param prefix: Start walking from prefix within the tree rather than
333
at the root. This allows one to walk a subtree but get paths that are
334
relative to a tree rooted higher up.
335
:return: an iterator over the directory data.
337
raise NotImplementedError(self.walkdirs)
109
def export(self, dest, format='dir', root=None):
110
"""Export this tree."""
112
exporter = exporters[format]
114
from bzrlib.errors import BzrCommandError
115
raise BzrCommandError("export format %r not supported" % format)
116
exporter(self, dest, root)
120
class RevisionTree(Tree):
121
"""Tree viewing a previous revision.
123
File text can be retrieved from the text store.
125
TODO: Some kind of `__repr__` method, but a good one
126
probably means knowing the branch and revision number,
127
or at least passing a description to the constructor.
130
def __init__(self, weave_store, inv, revision_id):
131
self._weave_store = weave_store
132
self._inventory = inv
133
self._revision_id = revision_id
135
def get_weave(self, file_id):
136
# FIXME: RevisionTree should be given a branch
137
# not a store, or the store should know the branch.
138
import bzrlib.transactions as transactions
139
return self._weave_store.get_weave(file_id,
140
transactions.PassThroughTransaction())
143
def get_file_lines(self, file_id):
144
ie = self._inventory[file_id]
145
weave = self.get_weave(file_id)
146
return weave.get(ie.revision)
149
def get_file_text(self, file_id):
150
return ''.join(self.get_file_lines(file_id))
153
def get_file(self, file_id):
154
return StringIO(self.get_file_text(file_id))
156
def get_file_size(self, file_id):
157
return self._inventory[file_id].text_size
159
def get_file_sha1(self, file_id):
160
ie = self._inventory[file_id]
161
if ie.kind == "file":
164
def is_executable(self, file_id):
165
ie = self._inventory[file_id]
166
if ie.kind != "file":
168
return self._inventory[file_id].executable
170
def has_filename(self, filename):
171
return bool(self.inventory.path2id(filename))
173
def list_files(self):
174
# The only files returned by this are those from the version
175
for path, entry in self.inventory.iter_entries():
176
yield path, 'V', entry.kind, entry.file_id, entry
178
def get_symlink_target(self, file_id):
179
ie = self._inventory[file_id]
180
return ie.symlink_target;
182
def kind(self, file_id):
183
return self._inventory[file_id].kind
340
185
class EmptyTree(Tree):
342
186
def __init__(self):
343
self._inventory = Inventory(root_id=None)
344
symbol_versioning.warn('EmptyTree is deprecated as of bzr 0.9 please'
345
' use repository.revision_tree instead.',
346
DeprecationWarning, stacklevel=2)
348
def get_parent_ids(self):
187
self._inventory = Inventory()
351
189
def get_symlink_target(self, file_id):
435
268
yield (old_name, new_name)
438
def find_ids_across_trees(filenames, trees, require_versioned=True):
439
"""Find the ids corresponding to specified filenames.
441
All matches in all trees will be used, and all children of matched
442
directories will be used.
444
:param filenames: The filenames to find file_ids for (if None, returns
446
:param trees: The trees to find file_ids within
447
:param require_versioned: if true, all specified filenames must occur in
449
:return: a set of file ids for the specified filenames and their children.
453
specified_path_ids = _find_ids_across_trees(filenames, trees,
455
return _find_children_across_trees(specified_path_ids, trees)
456
# specified_ids = [id for path, id in _find_path_ids_across_trees(filenames, trees, require_versioned)]
457
# return _find_children_across_trees(specified_ids, trees)
459
def find_path_ids_across_trees(filenames, trees, require_versioned=True):
460
"""Find the paths and ids corresponding to specified filenames.
462
All matches in all trees will be used, and all children of matched
463
directories will be included
465
:param filenames: The filenames to find file_ids for
466
:param trees: The trees to find file_ids within
467
:param require_versioned: if true, all specified filenames must occur in
469
:return: a set of (path, file ids) for the specified filenames and their
470
children. The returned path is the path of the id in the first tree
471
that contains it. This matters when files have been moved
475
# This function needs to know the ids for filenames in all trees, then
476
# search for those same files and children in all the other trees.
477
# it is complicated by the same path in two trees being able to have
478
# different ids, which might both be present in both trees.
479
# consider two trees, which have had 'mv foo bar' and 'mv baz foo' done
480
# in this case, a diff of 'foo' should should changes to both the current
481
# 'bar' and the current 'foo' which was baz. Its arguable that if
482
# the situation is 'mv parent/foo bar' and 'mv baz parent/foo', that
483
# we should return the current bar and the current parent/foo' - at the
484
# moment we do, but we loop around all ids and all trees: I*T checks.
486
# Updating this algorithm to be fast in the common case:
487
# nothing has moved, all files have the same id in parent, child and there
488
# are only two trees (or one is working tree and the others are parents).
489
# walk the dirstate. as we find each path, gather the paths of that
490
# id in all trees. add a mapping from the id to the path in those trees.
491
# now lookup children by id, again in all trees; for these trees that
492
# nothing has moved in, the id->path mapping will allow us to find the
493
# parent trivially. To answer 'has anything been moved' in one of the
494
# dirstate parent trees though, we will need to stare harder at it.
496
# Now, given a path index, that is trivial for any one tree, and given
497
# that we can ask for additional data from a dirstate tree, its a single
498
# pass, though it will require scanning the entire tree to find paths
499
# that were at the current location.
500
# ideal results?: There are three things: tree, path, id. Pathologically
501
# we can have completely disjoint ids for each tree; but we cannot have
502
# disjoin paths for each tree, except if we scan each tree for the
503
# different ids from other trees.
505
specified_path_ids = _find_ids_across_trees(filenames, trees,
507
return _find_path_id_children_across_trees(specified_path_ids, trees)
510
def _find_ids_across_trees(filenames, trees, require_versioned):
511
"""Find the ids corresponding to specified filenames.
513
All matches in all trees will be used, but subdirectories are not scanned.
515
:param filenames: The filenames to find file_ids for
516
:param trees: The trees to find file_ids within
517
:param require_versioned: if true, all specified filenames must occur in
519
:return: a set of (path, file ids) for the specified filenames
522
interesting_ids = set()
523
for tree_path in filenames:
526
file_id = tree.path2id(tree_path)
527
if file_id is not None:
528
interesting_ids.add(file_id)
531
not_versioned.append(tree_path)
532
if len(not_versioned) > 0 and require_versioned:
533
raise errors.PathsNotVersionedError(not_versioned)
534
return interesting_ids
537
def _find_children_across_trees(specified_ids, trees):
538
"""Return a set including specified ids and their children
540
All matches in all trees will be used.
542
:param trees: The trees to find file_ids within
543
:return: a set containing all specified ids and their children
545
interesting_ids = set(specified_ids)
546
pending = interesting_ids
547
# now handle children of interesting ids
548
# we loop so that we handle all children of each id in both trees
549
while len(pending) > 0:
551
for file_id in pending:
553
if not tree.has_id(file_id):
555
entry = tree.inventory[file_id]
556
for child in getattr(entry, 'children', {}).itervalues():
557
if child.file_id not in interesting_ids:
558
new_pending.add(child.file_id)
559
interesting_ids.update(new_pending)
560
pending = new_pending
561
return interesting_ids
564
class InterTree(InterObject):
565
"""This class represents operations taking place between two Trees.
567
Its instances have methods like 'compare' and contain references to the
568
source and target trees these operations are to be carried out on.
570
clients of bzrlib should not need to use InterTree directly, rather they
571
should use the convenience methods on Tree such as 'Tree.compare()' which
572
will pass through to InterTree as appropriate.
578
def compare(self, want_unchanged=False, specific_files=None,
579
extra_trees=None, require_versioned=False, include_root=False):
580
"""Return the changes from source to target.
582
:return: A TreeDelta.
583
:param specific_files: An optional list of file paths to restrict the
584
comparison to. When mapping filenames to ids, all matches in all
585
trees (including optional extra_trees) are used, and all children of
586
matched directories are included.
587
:param want_unchanged: An optional boolean requesting the inclusion of
588
unchanged entries in the result.
589
:param extra_trees: An optional list of additional trees to use when
590
mapping the contents of specific_files (paths) to file_ids.
591
:param require_versioned: An optional boolean (defaults to False). When
592
supplied and True all the 'specific_files' must be versioned, or
593
a PathsNotVersionedError will be thrown.
595
# NB: show_status depends on being able to pass in non-versioned files
596
# and report them as unknown
597
trees = (self.source,)
598
if extra_trees is not None:
599
trees = trees + tuple(extra_trees)
600
# target is usually the newer tree:
601
specific_file_ids = self.target.paths2ids(specific_files, trees,
602
require_versioned=require_versioned)
603
if specific_files and not specific_file_ids:
604
# All files are unversioned, so just return an empty delta
605
# _compare_trees would think we want a complete delta
606
return delta.TreeDelta()
607
return delta._compare_trees(self.source, self.target, want_unchanged,
608
specific_files, include_root, extra_trees=extra_trees)
610
def _iter_changes(self, include_unchanged=False,
611
specific_files=None, pb=None, extra_trees=[],
612
require_versioned=True):
613
"""Generate an iterator of changes between trees.
616
(file_id, path, changed_content, versioned, parent, name, kind,
619
Path is relative to the target tree. changed_content is True if the
620
file's content has changed. This includes changes to its kind, and to
623
versioned, parent, name, kind, executable are tuples of (from, to).
624
If a file is missing in a tree, its kind is None.
626
Iteration is done in parent-to-child order, relative to the target
629
There is no guarantee that all paths are in sorted order: the
630
requirement to expand the search due to renames may result in children
631
that should be found early being found late in the search, after
632
lexically later results have been returned.
633
:param require_versioned: Raise errors.PathsNotVersionedError if a
634
path in the specific_files list is not versioned in one of
635
source, target or extra_trees.
637
lookup_trees = [self.source]
639
lookup_trees.extend(extra_trees)
640
specific_file_ids = self.target.paths2ids(specific_files,
641
lookup_trees, require_versioned=require_versioned)
643
from_entries_by_dir = list(self.source.inventory.iter_entries_by_dir(
644
specific_file_ids=specific_file_ids))
645
from_data = dict((e.file_id, (p, e)) for p, e in from_entries_by_dir)
646
to_entries_by_dir = list(self.target.inventory.iter_entries_by_dir(
647
specific_file_ids=specific_file_ids))
648
num_entries = len(from_entries_by_dir) + len(to_entries_by_dir)
650
for to_path, to_entry in to_entries_by_dir:
651
file_id = to_entry.file_id
652
to_paths[file_id] = to_path
654
changed_content = False
655
from_path, from_entry = from_data.get(file_id, (None, None))
656
from_versioned = (from_entry is not None)
657
if from_entry is not None:
658
from_versioned = True
659
from_name = from_entry.name
660
from_parent = from_entry.parent_id
661
from_kind, from_executable, from_stat = \
662
self.source._comparison_data(from_entry, from_path)
665
from_versioned = False
669
from_executable = None
670
versioned = (from_versioned, True)
671
to_kind, to_executable, to_stat = \
672
self.target._comparison_data(to_entry, to_path)
673
kind = (from_kind, to_kind)
674
if kind[0] != kind[1]:
675
changed_content = True
676
elif from_kind == 'file':
677
from_size = self.source._file_size(from_entry, from_stat)
678
to_size = self.target._file_size(to_entry, to_stat)
679
if from_size != to_size:
680
changed_content = True
681
elif (self.source.get_file_sha1(file_id, from_path, from_stat) !=
682
self.target.get_file_sha1(file_id, to_path, to_stat)):
683
changed_content = True
684
elif from_kind == 'symlink':
685
if (self.source.get_symlink_target(file_id) !=
686
self.target.get_symlink_target(file_id)):
687
changed_content = True
688
elif from_kind == 'tree-reference':
689
if (self.source.get_reference_revision(from_entry, from_path)
690
!= self.target.get_reference_revision(to_entry, to_path)):
691
changed_content = True
692
parent = (from_parent, to_entry.parent_id)
693
name = (from_name, to_entry.name)
694
executable = (from_executable, to_executable)
696
pb.update('comparing files', entry_count, num_entries)
697
if (changed_content is not False or versioned[0] != versioned[1]
698
or parent[0] != parent[1] or name[0] != name[1] or
699
executable[0] != executable[1] or include_unchanged):
700
yield (file_id, to_path, changed_content, versioned, parent,
701
name, kind, executable)
703
def get_to_path(from_entry):
704
if from_entry.parent_id is None:
707
if from_entry.parent_id not in to_paths:
708
get_to_path(self.source.inventory[from_entry.parent_id])
709
to_path = osutils.pathjoin(to_paths[from_entry.parent_id],
711
to_paths[from_entry.file_id] = to_path
714
for path, from_entry in from_entries_by_dir:
715
file_id = from_entry.file_id
716
if file_id in to_paths:
718
to_path = get_to_path(from_entry)
721
pb.update('comparing files', entry_count, num_entries)
722
versioned = (True, False)
723
parent = (from_entry.parent_id, None)
724
name = (from_entry.name, None)
725
from_kind, from_executable, stat_value = \
726
self.source._comparison_data(from_entry, path)
727
kind = (from_kind, None)
728
executable = (from_executable, None)
729
changed_content = True
730
# the parent's path is necessarily known at this point.
731
yield(file_id, to_path, changed_content, versioned, parent,
732
name, kind, executable)
735
# This was deprecated before 0.12, but did not have an official warning
736
@symbol_versioning.deprecated_function(symbol_versioning.zero_twelve)
737
def RevisionTree(*args, **kwargs):
738
"""RevisionTree has moved to bzrlib.revisiontree.RevisionTree()
740
Accessing it as bzrlib.tree.RevisionTree has been deprecated as of
743
from bzrlib.revisiontree import RevisionTree as _RevisionTree
744
return _RevisionTree(*args, **kwargs)
272
######################################################################
275
def dir_exporter(tree, dest, root):
276
"""Export this tree to a new directory.
278
`dest` should not exist, and will be created holding the
279
contents of this tree.
281
TODO: To handle subdirectories we need to create the
284
:note: If the export fails, the destination directory will be
285
left in a half-assed state.
289
mutter('export version %r' % tree)
291
for dp, ie in inv.iter_entries():
292
ie.put_on_disk(dest, dp, tree)
294
exporters['dir'] = dir_exporter
301
def get_root_name(dest):
302
"""Get just the root name for a tarball.
304
>>> get_root_name('mytar.tar')
306
>>> get_root_name('mytar.tar.bz2')
308
>>> get_root_name('tar.tar.tar.tgz')
310
>>> get_root_name('bzr-0.0.5.tar.gz')
312
>>> get_root_name('a/long/path/mytar.tgz')
314
>>> get_root_name('../parent/../dir/other.tbz2')
317
endings = ['.tar', '.tar.gz', '.tgz', '.tar.bz2', '.tbz2']
318
dest = os.path.basename(dest)
320
if dest.endswith(end):
321
return dest[:-len(end)]
323
def tar_exporter(tree, dest, root, compression=None):
324
"""Export this tree to a new tar file.
326
`dest` will be created holding the contents of this tree; if it
327
already exists, it will be clobbered, like with "tar -c".
329
from time import time
331
compression = str(compression or '')
333
root = get_root_name(dest)
335
ball = tarfile.open(dest, 'w:' + compression)
336
except tarfile.CompressionError, e:
337
raise BzrError(str(e))
338
mutter('export version %r' % tree)
340
for dp, ie in inv.iter_entries():
341
mutter(" export {%s} kind %s to %s" % (ie.file_id, ie.kind, dest))
342
item, fileobj = ie.get_tar_item(root, dp, now, tree)
343
ball.addfile(item, fileobj)
346
exporters['tar'] = tar_exporter
348
def tgz_exporter(tree, dest, root):
349
tar_exporter(tree, dest, root, compression='gz')
350
exporters['tgz'] = tgz_exporter
352
def tbz_exporter(tree, dest, root):
353
tar_exporter(tree, dest, root, compression='bz2')
354
exporters['tbz2'] = tbz_exporter