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 cStringIO import StringIO
22
from warnings import warn
25
from bzrlib.errors import BzrError, BzrCheckError
26
from bzrlib import errors
27
from bzrlib.inventory import Inventory
28
from bzrlib.osutils import fingerprint_file
29
import bzrlib.revision
30
from bzrlib.trace import mutter, note
34
"""Abstract file tree.
36
There are several subclasses:
38
* `WorkingTree` exists as files on disk editable by the user.
40
* `RevisionTree` is a tree as recorded at some point in the past.
42
Trees contain an `Inventory` object, and also know how to retrieve
43
file texts mentioned in the inventory, either from a working
44
directory or from a store.
46
It is possible for trees to contain files that are not described
47
in their inventory or vice versa; for this use `filenames()`.
49
Trees can be compared, etc, regardless of whether they are working
50
trees or versioned trees.
54
"""Get a list of the conflicts in the tree.
56
Each conflict is an instance of bzrlib.conflicts.Conflict.
60
def get_parent_ids(self):
61
"""Get the parent ids for this tree.
63
:return: a list of parent ids. [] is returned to indicate
64
a tree with no parents.
65
:raises: BzrError if the parents are not known.
67
raise NotImplementedError(self.get_parent_ids)
69
def has_filename(self, filename):
70
"""True if the tree has given filename."""
71
raise NotImplementedError()
73
def has_id(self, file_id):
74
return self.inventory.has_id(file_id)
78
def has_or_had_id(self, file_id):
79
if file_id == self.inventory.root.file_id:
81
return self.inventory.has_id(file_id)
84
return iter(self.inventory)
86
def id2path(self, file_id):
87
return self.inventory.id2path(file_id)
89
def iter_entries_by_dir(self):
90
"""Walk the tree in 'by_dir' order.
92
This will yield each entry in the tree as a (path, entry) tuple. The
93
order that they are yielded is: the contents of a directory are
94
preceeded by the parent of a directory, and all the contents of a
95
directory are grouped together.
97
return self.inventory.iter_entries_by_dir()
99
def kind(self, file_id):
100
raise NotImplementedError("subclasses must implement kind")
102
def _get_inventory(self):
103
return self._inventory
105
def get_file_by_path(self, path):
106
return self.get_file(self._inventory.path2id(path))
108
inventory = property(_get_inventory,
109
doc="Inventory of this Tree")
111
def _check_retrieved(self, ie, f):
114
fp = fingerprint_file(f)
117
if ie.text_size != None:
118
if ie.text_size != fp['size']:
119
raise BzrError("mismatched size for file %r in %r" % (ie.file_id, self._store),
120
["inventory expects %d bytes" % ie.text_size,
121
"file is actually %d bytes" % fp['size'],
122
"store is probably damaged/corrupt"])
124
if ie.text_sha1 != fp['sha1']:
125
raise BzrError("wrong SHA-1 for file %r in %r" % (ie.file_id, self._store),
126
["inventory expects %s" % ie.text_sha1,
127
"file is actually %s" % fp['sha1'],
128
"store is probably damaged/corrupt"])
131
def print_file(self, file_id):
132
"""Print file with id `file_id` to stdout."""
134
sys.stdout.write(self.get_file_text(file_id))
140
"""What files are present in this tree and unknown.
142
:return: an iterator over the unknown files.
149
def filter_unversioned_files(self, paths):
150
"""Filter out paths that are not versioned.
152
:return: set of paths.
154
# NB: we specifically *don't* call self.has_filename, because for
155
# WorkingTrees that can indicate files that exist on disk but that
157
pred = self.inventory.has_filename
158
return set((p for p in paths if not pred(p)))
161
class RevisionTree(Tree):
162
"""Tree viewing a previous revision.
164
File text can be retrieved from the text store.
166
TODO: Some kind of `__repr__` method, but a good one
167
probably means knowing the branch and revision number,
168
or at least passing a description to the constructor.
171
def __init__(self, branch, inv, revision_id):
172
# for compatability the 'branch' parameter has not been renamed to
173
# repository at this point. However, we should change RevisionTree's
174
# construction to always be via Repository and not via direct
175
# construction - this will mean that we can change the constructor
176
# with much less chance of breaking client code.
177
self._repository = branch
178
self._weave_store = branch.weave_store
179
self._inventory = inv
180
self._revision_id = revision_id
182
def get_parent_ids(self):
183
"""See Tree.get_parent_ids.
185
A RevisionTree's parents match the revision graph.
187
parent_ids = self._repository.get_revision(self._revision_id).parent_ids
190
def get_revision_id(self):
191
"""Return the revision id associated with this tree."""
192
return self._revision_id
194
def get_weave(self, file_id):
195
return self._weave_store.get_weave(file_id,
196
self._repository.get_transaction())
198
def get_file_lines(self, file_id):
199
ie = self._inventory[file_id]
200
weave = self.get_weave(file_id)
201
return weave.get_lines(ie.revision)
203
def get_file_text(self, file_id):
204
return ''.join(self.get_file_lines(file_id))
206
def get_file(self, file_id):
207
return StringIO(self.get_file_text(file_id))
209
def get_file_size(self, file_id):
210
return self._inventory[file_id].text_size
212
def get_file_sha1(self, file_id, path=None):
213
ie = self._inventory[file_id]
214
if ie.kind == "file":
218
def get_file_mtime(self, file_id, path=None):
219
ie = self._inventory[file_id]
220
revision = self._repository.get_revision(ie.revision)
221
return revision.timestamp
223
def is_executable(self, file_id, path=None):
224
ie = self._inventory[file_id]
225
if ie.kind != "file":
227
return self._inventory[file_id].executable
229
def has_filename(self, filename):
230
return bool(self.inventory.path2id(filename))
232
def list_files(self):
233
# The only files returned by this are those from the version
234
entries = self.inventory.iter_entries()
235
# skip the root for compatability with the current apis.
237
for path, entry in entries:
238
yield path, 'V', entry.kind, entry.file_id, entry
240
def get_symlink_target(self, file_id):
241
ie = self._inventory[file_id]
242
return ie.symlink_target;
244
def kind(self, file_id):
245
return self._inventory[file_id].kind
248
self._repository.lock_read()
251
self._repository.unlock()
254
class EmptyTree(Tree):
257
self._inventory = Inventory()
258
warn('EmptyTree is deprecated as of bzr 0.9 please use '
259
'repository.revision_tree instead.',
260
DeprecationWarning, stacklevel=2)
262
def get_parent_ids(self):
265
def get_symlink_target(self, file_id):
268
def has_filename(self, filename):
271
def kind(self, file_id):
272
assert self._inventory[file_id].kind == "root_directory"
273
return "root_directory"
275
def list_files(self):
278
def __contains__(self, file_id):
279
return file_id in self._inventory
281
def get_file_sha1(self, file_id, path=None):
282
assert self._inventory[file_id].kind == "root_directory"
286
######################################################################
289
# TODO: Merge these two functions into a single one that can operate
290
# on either a whole tree or a set of files.
292
# TODO: Return the diff in order by filename, not by category or in
293
# random order. Can probably be done by lock-stepping through the
294
# filenames from both trees.
297
def file_status(filename, old_tree, new_tree):
298
"""Return single-letter status, old and new names for a file.
300
The complexity here is in deciding how to represent renames;
301
many complex cases are possible.
303
old_inv = old_tree.inventory
304
new_inv = new_tree.inventory
305
new_id = new_inv.path2id(filename)
306
old_id = old_inv.path2id(filename)
308
if not new_id and not old_id:
309
# easy: doesn't exist in either; not versioned at all
310
if new_tree.is_ignored(filename):
311
return 'I', None, None
313
return '?', None, None
315
# There is now a file of this name, great.
318
# There is no longer a file of this name, but we can describe
319
# what happened to the file that used to have
320
# this name. There are two possibilities: either it was
321
# deleted entirely, or renamed.
323
if new_inv.has_id(old_id):
324
return 'X', old_inv.id2path(old_id), new_inv.id2path(old_id)
326
return 'D', old_inv.id2path(old_id), None
328
# if the file_id is new in this revision, it is added
329
if new_id and not old_inv.has_id(new_id):
332
# if there used to be a file of this name, but that ID has now
333
# disappeared, it is deleted
334
if old_id and not new_inv.has_id(old_id):
341
def find_renames(old_inv, new_inv):
342
for file_id in old_inv:
343
if file_id not in new_inv:
345
old_name = old_inv.id2path(file_id)
346
new_name = new_inv.id2path(file_id)
347
if old_name != new_name:
348
yield (old_name, new_name)
351
def find_ids_across_trees(filenames, trees, require_versioned=True):
352
"""Find the ids corresponding to specified filenames.
354
All matches in all trees will be used, and all children of matched
355
directories will be used.
357
:param filenames: The filenames to find file_ids for
358
:param trees: The trees to find file_ids within
359
:param require_versioned: if true, all specified filenames must occur in
361
:return: a set of file ids for the specified filenames and their children.
365
specified_ids = _find_filename_ids_across_trees(filenames, trees,
367
return _find_children_across_trees(specified_ids, trees)
370
def _find_filename_ids_across_trees(filenames, trees, require_versioned):
371
"""Find the ids corresponding to specified filenames.
373
All matches in all trees will be used.
375
:param filenames: The filenames to find file_ids for
376
:param trees: The trees to find file_ids within
377
:param require_versioned: if true, all specified filenames must occur in
379
:return: a set of file ids for the specified filenames
382
interesting_ids = set()
383
for tree_path in filenames:
386
file_id = tree.inventory.path2id(tree_path)
387
if file_id is not None:
388
interesting_ids.add(file_id)
391
not_versioned.append(tree_path)
392
if len(not_versioned) > 0 and require_versioned:
393
raise errors.PathsNotVersionedError(not_versioned)
394
return interesting_ids
397
def _find_children_across_trees(specified_ids, trees):
398
"""Return a set including specified ids and their children
400
All matches in all trees will be used.
402
:param trees: The trees to find file_ids within
403
:return: a set containing all specified ids and their children
405
interesting_ids = set(specified_ids)
406
pending = interesting_ids
407
# now handle children of interesting ids
408
# we loop so that we handle all children of each id in both trees
409
while len(pending) > 0:
411
for file_id in pending:
413
if file_id not in tree:
415
entry = tree.inventory[file_id]
416
for child in getattr(entry, 'children', {}).itervalues():
417
if child.file_id not in interesting_ids:
418
new_pending.add(child.file_id)
419
interesting_ids.update(new_pending)
420
pending = new_pending
421
return interesting_ids
added
removed
bzrlib/tree.py
