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: Rather than mashing together the ancestry and storing it back,
53
# perhaps the weave should have single method which does it all in one
54
# go, avoiding a lot of redundant work.
56
# TODO: Perhaps give a warning if one of the revisions marked as
57
# merged is already in the ancestry, and then don't record it as a
66
from binascii import hexlify
67
from cStringIO import StringIO
69
from bzrlib.osutils import (local_time_offset, username,
70
rand_bytes, compact_date, user_email,
71
kind_marker, is_inside_any, quotefn,
72
sha_string, sha_strings, sha_file, isdir, isfile,
74
from bzrlib.branch import gen_file_id, INVENTORY_FILEID, ANCESTRY_FILEID
75
from bzrlib.errors import (BzrError, PointlessCommit,
78
from bzrlib.revision import Revision
79
from bzrlib.trace import mutter, note, warning
80
from bzrlib.xml5 import serializer_v5
81
from bzrlib.inventory import Inventory
82
from bzrlib.weave import Weave
83
from bzrlib.weavefile import read_weave, write_weave_v5
84
from bzrlib.atomicfile import AtomicFile
87
def commit(*args, **kwargs):
88
"""Commit a new revision to a branch.
90
Function-style interface for convenience of old callers.
92
New code should use the Commit class instead.
94
## XXX: Remove this in favor of Branch.commit?
95
Commit().commit(*args, **kwargs)
98
class NullCommitReporter(object):
99
"""I report on progress of a commit."""
100
def added(self, path):
103
def removed(self, path):
106
def renamed(self, old_path, new_path):
110
class ReportCommitToLog(NullCommitReporter):
111
def added(self, path):
112
note('added %s', path)
114
def removed(self, path):
115
note('removed %s', path)
117
def renamed(self, old_path, new_path):
118
note('renamed %s => %s', old_path, new_path)
121
class Commit(object):
122
"""Task of committing a new revision.
124
This is a MethodObject: it accumulates state as the commit is
125
prepared, and then it is discarded. It doesn't represent
126
historical revisions, just the act of recording a new one.
129
Modified to hold a list of files that have been deleted from
130
the working directory; these should be removed from the
135
if reporter is not None:
136
self.reporter = reporter
138
self.reporter = NullCommitReporter()
148
allow_pointless=True,
150
"""Commit working copy as a new revision.
152
timestamp -- if not None, seconds-since-epoch for a
153
postdated/predated commit.
155
specific_files -- If true, commit only those files.
157
rev_id -- If set, use this as the new revision id.
158
Useful for test or import commands that need to tightly
159
control what revisions are assigned. If you duplicate
160
a revision id that exists elsewhere it is your own fault.
161
If null (default), a time/random revision id is generated.
163
allow_pointless -- If true (default), commit even if nothing
164
has changed and no merges are recorded.
166
mutter('preparing to commit')
169
self.weave_store = branch.weave_store
171
self.specific_files = specific_files
172
self.allow_pointless = allow_pointless
174
if timestamp is None:
175
self.timestamp = time.time()
177
self.timestamp = long(timestamp)
180
self.rev_id = _gen_revision_id(self.branch, self.timestamp)
184
if committer is None:
185
self.committer = username(self.branch)
187
assert isinstance(committer, basestring), type(committer)
188
self.committer = committer
191
self.timezone = local_time_offset()
193
self.timezone = int(timezone)
195
assert isinstance(message, basestring), type(message)
196
self.message = message
198
self.branch.lock_write()
200
self.work_tree = self.branch.working_tree()
201
self.work_inv = self.work_tree.inventory
202
self.basis_tree = self.branch.basis_tree()
203
self.basis_inv = self.basis_tree.inventory
205
self._gather_parents()
206
self._check_parents_present()
208
self._remove_deleted()
209
self.new_inv = Inventory()
210
self._store_entries()
211
self._report_deletes()
212
self._set_name_versions()
214
if not (self.allow_pointless
215
or len(self.parents) > 1
216
or self.new_inv != self.basis_inv):
217
raise PointlessCommit()
219
self._record_inventory()
220
self._record_ancestry()
221
self._make_revision()
222
note('committed r%d {%s}', (self.branch.revno() + 1),
224
self.branch.append_revision(self.rev_id)
225
self.branch.set_pending_merges([])
231
def _record_inventory(self):
232
"""Store the inventory for the new revision."""
233
inv_text = serializer_v5.write_inventory_to_string(self.new_inv)
234
self.inv_sha1 = sha_string(inv_text)
235
self.weave_store.add_text(INVENTORY_FILEID, self.rev_id,
236
split_lines(inv_text), self.parents)
239
def _record_ancestry(self):
240
"""Append merged revision ancestry to the ancestry file.
242
This should be the merged ancestry of all parents, plus the
244
w = self.weave_store.get_weave_or_empty(ANCESTRY_FILEID)
245
lines = self._make_ancestry(w)
246
w.add(self.rev_id, self.parents, lines)
247
self.weave_store.put_weave(ANCESTRY_FILEID, w)
250
def _make_ancestry(self, ancestry_weave):
251
"""Return merged ancestry lines.
253
The lines are revision-ids followed by newlines."""
254
parent_ancestries = [ancestry_weave.get(p) for p in self.parents]
255
new_lines = merge_ancestry_lines(self.rev_id, parent_ancestries)
256
mutter('merged ancestry of {%s}:\n%s', self.rev_id, ''.join(new_lines))
260
def _gather_parents(self):
261
pending_merges = self.branch.pending_merges()
263
self.parent_trees = []
264
precursor_id = self.branch.last_revision()
266
self.parents.append(precursor_id)
267
self.parent_trees.append(self.basis_tree)
268
self.parents += pending_merges
269
self.parent_trees.extend(map(self.branch.revision_tree, pending_merges))
272
def _check_parents_present(self):
273
for parent_id in self.parents:
274
mutter('commit parent revision {%s}', parent_id)
275
if not self.branch.has_revision(parent_id):
276
warning("can't commit a merge from an absent parent")
277
raise HistoryMissing(self.branch, 'revision', parent_id)
280
def _make_revision(self):
281
"""Record a new revision object for this commit."""
282
self.rev = Revision(timestamp=self.timestamp,
283
timezone=self.timezone,
284
committer=self.committer,
285
message=self.message,
286
inventory_sha1=self.inv_sha1,
287
revision_id=self.rev_id)
288
self.rev.parent_ids = self.parents
290
serializer_v5.write_revision(self.rev, rev_tmp)
292
self.branch.revision_store.add(rev_tmp, self.rev_id)
293
mutter('new revision_id is {%s}', self.rev_id)
296
def _remove_deleted(self):
297
"""Remove deleted files from the working inventories.
299
This is done prior to taking the working inventory as the
300
basis for the new committed inventory.
302
This returns true if any files
303
*that existed in the basis inventory* were deleted.
304
Files that were added and deleted
305
in the working copy don't matter.
307
specific = self.specific_files
309
for path, ie in self.work_inv.iter_entries():
310
if specific and not is_inside_any(specific, path):
312
if not self.work_tree.has_filename(path):
313
note('missing %s', path)
314
deleted_ids.append(ie.file_id)
316
for file_id in deleted_ids:
317
del self.work_inv[file_id]
318
self.branch._write_inventory(self.work_inv)
321
def _find_file_parents(self, file_id):
322
"""Return the text versions and hashes for all file parents.
324
Returned as a map from text version to inventory entry.
326
This is a set containing the file versions in all parents
327
revisions containing the file. If the file is new, the set
330
for tree in self.parent_trees:
331
if file_id in tree.inventory:
332
ie = tree.inventory[file_id]
333
assert ie.kind == 'file'
334
assert ie.file_id == file_id
335
if ie.text_version in r:
336
assert r[ie.text_version] == ie
338
r[ie.text_version] = ie
342
def _set_name_versions(self):
343
"""Pass over inventory and mark new entry version as needed.
345
Files get a new name version when they are new, have a
346
different parent, or a different name from in the
347
basis inventory, or if the file is in a different place
348
to any of the parents."""
349
# XXX: Need to think more here about when the user has
350
# made a specific decision on a particular value -- c.f.
352
for path, ie in self.new_inv.iter_entries():
355
for parent_tree in self.parent_trees:
356
parent_inv = parent_tree.inventory
357
if file_id not in parent_inv:
359
parent_ie = parent_inv[file_id]
360
if parent_ie.parent_id != ie.parent_id:
363
elif parent_ie.name != ie.name:
366
elif old_version is None:
367
old_version = parent_ie.name_version
368
elif old_version != parent_ie.name_version:
372
pass # so far so good
373
if old_version is None:
374
mutter('new name_version for {%s}', file_id)
375
ie.name_version = self.rev_id
377
mutter('name_version for {%s} inherited as {%s}',
378
file_id, old_version)
379
ie.name_version = old_version
382
def _store_entries(self):
383
"""Build revision inventory and store modified files.
385
This is called with new_inv a new empty inventory. Depending on
386
which files are selected for commit, and which ones have
387
been modified or merged, new inventory entries are built
388
based on the working and parent inventories.
390
As a side-effect this stores new text versions for committed
391
files with text changes or merges.
393
Each entry can have one of several things happen:
395
carry_file -- carried from the previous version (if not
398
commit_nonfile -- no text to worry about
400
commit_old_text -- same text, may have moved
402
commit_file -- new text version
404
for path, new_ie in self.work_inv.iter_entries():
405
file_id = new_ie.file_id
406
mutter('check %s {%s}', path, new_ie.file_id)
407
if self.specific_files:
408
if not is_inside_any(self.specific_files, path):
409
mutter('%s not selected for commit', path)
410
self._carry_file(file_id)
412
if new_ie.kind != 'file':
413
self._commit_nonfile(file_id)
416
file_parents = self._find_file_parents(file_id)
417
if len(file_parents) == 1:
418
parent_ie = file_parents.values()[0]
419
wc_sha1 = self.work_tree.get_file_sha1(file_id)
420
if parent_ie.text_sha1 == wc_sha1:
421
# text not changed or merged
422
self._commit_old_text(file_id, parent_ie)
425
mutter('parents of %s are %r', path, file_parents)
427
# file is either new, or a file merge; need to record
429
if len(file_parents) > 1:
430
note('merged %s', path)
431
elif len(file_parents) == 0:
432
note('added %s', path)
434
note('modified %s', path)
435
self._commit_file(new_ie, file_id, file_parents)
438
def _commit_nonfile(self, file_id):
439
self.new_inv.add(self.work_inv[file_id].copy())
442
def _carry_file(self, file_id):
443
"""Carry the file unchanged from the basis revision."""
444
if self.basis_inv.has_id(file_id):
445
self.new_inv.add(self.basis_inv[file_id].copy())
448
def _commit_old_text(self, file_id, parent_ie):
449
"""Keep the same text as last time, but possibly a different name."""
450
ie = self.work_inv[file_id].copy()
451
ie.text_version = parent_ie.text_version
452
ie.text_size = parent_ie.text_size
453
ie.text_sha1 = parent_ie.text_sha1
457
def _report_deletes(self):
458
for file_id in self.basis_inv:
459
if file_id not in self.new_inv:
460
note('deleted %s', self.basis_inv.id2path(file_id))
463
def _commit_file(self, new_ie, file_id, file_parents):
464
mutter('store new text for {%s} in revision {%s}',
465
file_id, self.rev_id)
466
new_lines = self.work_tree.get_file(file_id).readlines()
467
self._add_text_to_weave(file_id, new_lines, file_parents)
468
new_ie.text_version = self.rev_id
469
new_ie.text_sha1 = sha_strings(new_lines)
470
new_ie.text_size = sum(map(len, new_lines))
471
self.new_inv.add(new_ie)
474
def _add_text_to_weave(self, file_id, new_lines, parents):
475
if file_id.startswith('__'):
476
raise ValueError('illegal file-id %r for text file' % file_id)
477
self.weave_store.add_text(file_id, self.rev_id, new_lines, parents)
480
def _gen_revision_id(branch, when):
481
"""Return new revision-id."""
482
s = '%s-%s-' % (user_email(branch), compact_date(when))
483
s += hexlify(rand_bytes(8))
489
def merge_ancestry_lines(rev_id, ancestries):
490
"""Return merged ancestry lines.
492
rev_id -- id of the new revision
494
ancestries -- a sequence of ancestries for parent revisions,
495
as newline-terminated line lists.
497
if len(ancestries) == 0:
498
return [rev_id + '\n']
499
seen = set(ancestries[0])
500
ancs = ancestries[0][:]
501
for parent_ancestry in ancestries[1:]:
502
for line in parent_ancestry:
503
assert line[-1] == '\n'
added
removed
bzrlib/commit.py
