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
18
# XXX: Can we do any better about making interrupted commits change
19
# nothing? Perhaps the best approach is to integrate commit of
20
# AtomicFiles with releasing the lock on the Branch.
22
# TODO: Separate 'prepare' phase where we find a list of potentially
23
# committed files. We then can then pause the commit to prompt for a
24
# commit message, knowing the summary will be the same as what's
25
# actually used for the commit. (But perhaps simpler to simply get
26
# the tree status, then use that for a selective commit?)
28
# The newly committed revision is going to have a shape corresponding
29
# to that of the working inventory. Files that are not in the
30
# working tree and that were in the predecessor are reported as
31
# removed --- this can include files that were either removed from the
32
# inventory or deleted in the working tree. If they were only
33
# deleted from disk, they are removed from the working inventory.
35
# We then consider the remaining entries, which will be in the new
36
# version. Directory entries are simply copied across. File entries
37
# must be checked to see if a new version of the file should be
38
# recorded. For each parent revision inventory, we check to see what
39
# version of the file was present. If the file was present in at
40
# least one tree, and if it was the same version in all the trees,
41
# then we can just refer to that version. Otherwise, a new version
42
# representing the merger of the file versions must be added.
44
# TODO: Update hashcache before and after - or does the WorkingTree
47
# This code requires all merge parents to be present in the branch.
48
# We could relax this but for the sake of simplicity the constraint is
49
# here for now. It's not totally clear to me how we'd know which file
50
# need new text versions if some parents are absent. -- mbp 20050915
52
# TODO: Perhaps it'd be enough to just commit an auto-merge of the
53
# ancestries? Wouldn't that always preserve the appropriate ordering?
61
from binascii import hexlify
62
from cStringIO import StringIO
64
from bzrlib.osutils import (local_time_offset, username,
65
rand_bytes, compact_date, user_email,
66
kind_marker, is_inside_any, quotefn,
67
sha_string, sha_strings, sha_file, isdir, isfile,
69
from bzrlib.branch import gen_file_id, INVENTORY_FILEID, ANCESTRY_FILEID
70
from bzrlib.errors import (BzrError, PointlessCommit,
73
from bzrlib.revision import Revision
74
from bzrlib.trace import mutter, note, warning
75
from bzrlib.xml5 import serializer_v5
76
from bzrlib.inventory import Inventory
77
from bzrlib.weave import Weave
78
from bzrlib.weavefile import read_weave, write_weave_v5
79
from bzrlib.atomicfile import AtomicFile
82
def commit(*args, **kwargs):
83
"""Commit a new revision to a branch.
85
Function-style interface for convenience of old callers.
87
New code should use the Commit class instead.
89
## XXX: Remove this in favor of Branch.commit?
90
Commit().commit(*args, **kwargs)
93
class NullCommitReporter(object):
94
"""I report on progress of a commit."""
95
def added(self, path):
98
def removed(self, path):
101
def renamed(self, old_path, new_path):
105
class ReportCommitToLog(NullCommitReporter):
106
def added(self, path):
107
note('added %s', path)
109
def removed(self, path):
110
note('removed %s', path)
112
def renamed(self, old_path, new_path):
113
note('renamed %s => %s', old_path, new_path)
116
class Commit(object):
117
"""Task of committing a new revision.
119
This is a MethodObject: it accumulates state as the commit is
120
prepared, and then it is discarded. It doesn't represent
121
historical revisions, just the act of recording a new one.
124
Modified to hold a list of files that have been deleted from
125
the working directory; these should be removed from the
130
if reporter is not None:
131
self.reporter = reporter
133
self.reporter = NullCommitReporter()
143
allow_pointless=True,
145
"""Commit working copy as a new revision.
147
timestamp -- if not None, seconds-since-epoch for a
148
postdated/predated commit.
150
specific_files -- If true, commit only those files.
152
rev_id -- If set, use this as the new revision id.
153
Useful for test or import commands that need to tightly
154
control what revisions are assigned. If you duplicate
155
a revision id that exists elsewhere it is your own fault.
156
If null (default), a time/random revision id is generated.
158
allow_pointless -- If true (default), commit even if nothing
159
has changed and no merges are recorded.
161
mutter('preparing to commit')
164
self.weave_store = branch.weave_store
166
self.specific_files = specific_files
167
self.allow_pointless = allow_pointless
169
if timestamp is None:
170
self.timestamp = time.time()
172
self.timestamp = long(timestamp)
175
self.rev_id = _gen_revision_id(self.branch, self.timestamp)
179
if committer is None:
180
self.committer = username(self.branch)
182
assert isinstance(committer, basestring), type(committer)
183
self.committer = committer
186
self.timezone = local_time_offset()
188
self.timezone = int(timezone)
190
assert isinstance(message, basestring), type(message)
191
self.message = message
193
self.branch.lock_write()
195
self.work_tree = self.branch.working_tree()
196
self.work_inv = self.work_tree.inventory
197
self.basis_tree = self.branch.basis_tree()
198
self.basis_inv = self.basis_tree.inventory
200
self._gather_parents()
201
self._check_parents_present()
203
self._remove_deleted()
204
self.new_inv = Inventory()
205
self._store_entries()
206
self._report_deletes()
207
self._set_name_versions()
209
if not (self.allow_pointless
210
or len(self.parents) > 1
211
or self.new_inv != self.basis_inv):
212
raise PointlessCommit()
214
self._record_inventory()
215
self._record_ancestry()
216
self._make_revision()
217
note('committed r%d {%s}', (self.branch.revno() + 1),
219
self.branch.append_revision(self.rev_id)
220
self.branch.set_pending_merges([])
226
def _record_inventory(self):
227
"""Store the inventory for the new revision."""
228
inv_text = serializer_v5.write_inventory_to_string(self.new_inv)
229
self.inv_sha1 = sha_string(inv_text)
230
self.weave_store.add_text(INVENTORY_FILEID, self.rev_id,
231
split_lines(inv_text), self.parents)
234
def _record_ancestry(self):
235
"""Append merged revision ancestry to the ancestry file.
237
This should be the merged ancestry of all parents, plus the
239
w = self.weave_store.get_weave_or_empty(ANCESTRY_FILEID)
240
lines = self._make_ancestry(w)
241
w.add(self.rev_id, self.parents, lines)
242
self.weave_store.put_weave(ANCESTRY_FILEID, w)
245
def _make_ancestry(self, ancestry_weave):
246
"""Return merged ancestry lines.
248
The lines are revision-ids followed by newlines."""
249
parent_ancestries = [ancestry_weave.get(p) for p in self.parents]
250
new_lines = merge_ancestry_lines(self.rev_id, parent_ancestries)
251
mutter('merged ancestry of {%s}:\n%s', self.rev_id, ''.join(new_lines))
255
def _gather_parents(self):
256
pending_merges = self.branch.pending_merges()
258
self.parent_trees = []
259
precursor_id = self.branch.last_revision()
261
self.parents.append(precursor_id)
262
self.parent_trees.append(self.basis_tree)
263
self.parents += pending_merges
264
self.parent_trees.extend(map(self.branch.revision_tree, pending_merges))
267
def _check_parents_present(self):
268
for parent_id in self.parents:
269
mutter('commit parent revision {%s}', parent_id)
270
if not self.branch.has_revision(parent_id):
271
warning("can't commit a merge from an absent parent")
272
raise HistoryMissing(self.branch, 'revision', parent_id)
275
def _make_revision(self):
276
"""Record a new revision object for this commit."""
277
self.rev = Revision(timestamp=self.timestamp,
278
timezone=self.timezone,
279
committer=self.committer,
280
message=self.message,
281
inventory_sha1=self.inv_sha1,
282
revision_id=self.rev_id)
283
self.rev.parent_ids = self.parents
285
serializer_v5.write_revision(self.rev, rev_tmp)
287
self.branch.revision_store.add(rev_tmp, self.rev_id)
288
mutter('new revision_id is {%s}', self.rev_id)
291
def _remove_deleted(self):
292
"""Remove deleted files from the working inventories.
294
This is done prior to taking the working inventory as the
295
basis for the new committed inventory.
297
This returns true if any files
298
*that existed in the basis inventory* were deleted.
299
Files that were added and deleted
300
in the working copy don't matter.
302
specific = self.specific_files
304
for path, ie in self.work_inv.iter_entries():
305
if specific and not is_inside_any(specific, path):
307
if not self.work_tree.has_filename(path):
308
note('missing %s', path)
309
deleted_ids.append(ie.file_id)
311
for file_id in deleted_ids:
312
del self.work_inv[file_id]
313
self.branch._write_inventory(self.work_inv)
316
def _find_file_parents(self, file_id):
317
"""Return the text versions and hashes for all file parents.
319
Returned as a map from text version to inventory entry.
321
This is a set containing the file versions in all parents
322
revisions containing the file. If the file is new, the set
325
for tree in self.parent_trees:
326
if file_id in tree.inventory:
327
ie = tree.inventory[file_id]
328
assert ie.kind == 'file'
329
assert ie.file_id == file_id
330
if ie.text_version in r:
331
assert r[ie.text_version] == ie
333
r[ie.text_version] = ie
337
def _set_name_versions(self):
338
"""Pass over inventory and mark new entry version as needed.
340
Files get a new name version when they are new, have a
341
different parent, or a different name from in the
342
basis inventory, or if the file is in a different place
343
to any of the parents."""
344
# XXX: Need to think more here about when the user has
345
# made a specific decision on a particular value -- c.f.
347
for path, ie in self.new_inv.iter_entries():
350
for parent_tree in self.parent_trees:
351
parent_inv = parent_tree.inventory
352
if file_id not in parent_inv:
354
parent_ie = parent_inv[file_id]
355
if parent_ie.parent_id != ie.parent_id:
358
elif parent_ie.name != ie.name:
361
elif old_version is None:
362
old_version = parent_ie.name_version
363
elif old_version != parent_ie.name_version:
367
pass # so far so good
368
if old_version is None:
369
mutter('new name_version for {%s}', file_id)
370
ie.name_version = self.rev_id
372
mutter('name_version for {%s} inherited as {%s}',
373
file_id, old_version)
374
ie.name_version = old_version
377
def _store_entries(self):
378
"""Build revision inventory and store modified files.
380
This is called with new_inv a new empty inventory. Depending on
381
which files are selected for commit, and which ones have
382
been modified or merged, new inventory entries are built
383
based on the working and parent inventories.
385
As a side-effect this stores new text versions for committed
386
files with text changes or merges.
388
Each entry can have one of several things happen:
390
carry_file -- carried from the previous version (if not
393
commit_nonfile -- no text to worry about
395
commit_old_text -- same text, may have moved
397
commit_file -- new text version
399
for path, new_ie in self.work_inv.iter_entries():
400
file_id = new_ie.file_id
401
mutter('check %s {%s}', path, new_ie.file_id)
402
if self.specific_files:
403
if not is_inside_any(self.specific_files, path):
404
mutter('%s not selected for commit', path)
405
self._carry_file(file_id)
407
if new_ie.kind != 'file':
408
self._commit_nonfile(file_id)
411
file_parents = self._find_file_parents(file_id)
412
if len(file_parents) == 1:
413
parent_ie = file_parents.values()[0]
414
wc_sha1 = self.work_tree.get_file_sha1(file_id)
415
if parent_ie.text_sha1 == wc_sha1:
416
# text not changed or merged
417
self._commit_old_text(file_id, parent_ie)
420
mutter('parents of %s are %r', path, file_parents)
422
# file is either new, or a file merge; need to record
424
if len(file_parents) > 1:
425
note('merged %s', path)
426
elif len(file_parents) == 0:
427
note('added %s', path)
429
note('modified %s', path)
430
self._commit_file(new_ie, file_id, file_parents)
433
def _commit_nonfile(self, file_id):
434
self.new_inv.add(self.work_inv[file_id].copy())
437
def _carry_file(self, file_id):
438
"""Carry the file unchanged from the basis revision."""
439
if self.basis_inv.has_id(file_id):
440
self.new_inv.add(self.basis_inv[file_id].copy())
443
def _commit_old_text(self, file_id, parent_ie):
444
"""Keep the same text as last time, but possibly a different name."""
445
ie = self.work_inv[file_id].copy()
446
ie.text_version = parent_ie.text_version
447
ie.text_size = parent_ie.text_size
448
ie.text_sha1 = parent_ie.text_sha1
452
def _report_deletes(self):
453
for file_id in self.basis_inv:
454
if file_id not in self.new_inv:
455
note('deleted %s', self.basis_inv.id2path(file_id))
458
def _commit_file(self, new_ie, file_id, file_parents):
459
mutter('store new text for {%s} in revision {%s}',
460
file_id, self.rev_id)
461
new_lines = self.work_tree.get_file(file_id).readlines()
462
self._add_text_to_weave(file_id, new_lines, file_parents)
463
new_ie.text_version = self.rev_id
464
new_ie.text_sha1 = sha_strings(new_lines)
465
new_ie.text_size = sum(map(len, new_lines))
466
self.new_inv.add(new_ie)
469
def _add_text_to_weave(self, file_id, new_lines, parents):
470
if file_id.startswith('__'):
471
raise ValueError('illegal file-id %r for text file' % file_id)
472
self.weave_store.add_text(file_id, self.rev_id, new_lines, parents)
475
def _gen_revision_id(branch, when):
476
"""Return new revision-id."""
477
s = '%s-%s-' % (user_email(branch), compact_date(when))
478
s += hexlify(rand_bytes(8))
484
def merge_ancestry_lines(rev_id, ancestries):
485
"""Return merged ancestry lines.
487
rev_id -- id of the new revision
489
ancestries -- a sequence of ancestries for parent revisions,
490
as newline-terminated line lists.
492
if len(ancestries) == 0:
493
return [rev_id + '\n']
494
seen = set(ancestries[0])
495
ancs = ancestries[0][:]
496
for parent_ancestry in ancestries[1:]:
497
for line in parent_ancestry:
498
assert line[-1] == '\n'
added
removed
bzrlib/commit.py
