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.
62
from binascii import hexlify
63
from cStringIO import StringIO
65
from bzrlib.osutils import (local_time_offset, username,
66
rand_bytes, compact_date, user_email,
67
kind_marker, is_inside_any, quotefn,
68
sha_string, sha_strings, sha_file, isdir, isfile,
70
from bzrlib.branch import gen_file_id, INVENTORY_FILEID, ANCESTRY_FILEID
71
from bzrlib.errors import (BzrError, PointlessCommit,
74
from bzrlib.revision import Revision
75
from bzrlib.trace import mutter, note, warning
76
from bzrlib.xml5 import serializer_v5
77
from bzrlib.inventory import Inventory
78
from bzrlib.weave import Weave
79
from bzrlib.weavefile import read_weave, write_weave_v5
80
from bzrlib.atomicfile import AtomicFile
83
def commit(*args, **kwargs):
84
"""Commit a new revision to a branch.
86
Function-style interface for convenience of old callers.
88
New code should use the Commit class instead.
90
## XXX: Remove this in favor of Branch.commit?
91
Commit().commit(*args, **kwargs)
94
class NullCommitReporter(object):
95
"""I report on progress of a commit."""
96
def added(self, path):
99
def removed(self, path):
102
def renamed(self, old_path, new_path):
106
class ReportCommitToLog(NullCommitReporter):
107
def added(self, path):
108
note('added %s', path)
110
def removed(self, path):
111
note('removed %s', path)
113
def renamed(self, old_path, new_path):
114
note('renamed %s => %s', old_path, new_path)
117
class Commit(object):
118
"""Task of committing a new revision.
120
This is a MethodObject: it accumulates state as the commit is
121
prepared, and then it is discarded. It doesn't represent
122
historical revisions, just the act of recording a new one.
125
Modified to hold a list of files that have been deleted from
126
the working directory; these should be removed from the
131
if reporter is not None:
132
self.reporter = reporter
134
self.reporter = NullCommitReporter()
144
allow_pointless=True,
146
"""Commit working copy as a new revision.
148
timestamp -- if not None, seconds-since-epoch for a
149
postdated/predated commit.
151
specific_files -- If true, commit only those files.
153
rev_id -- If set, use this as the new revision id.
154
Useful for test or import commands that need to tightly
155
control what revisions are assigned. If you duplicate
156
a revision id that exists elsewhere it is your own fault.
157
If null (default), a time/random revision id is generated.
159
allow_pointless -- If true (default), commit even if nothing
160
has changed and no merges are recorded.
162
mutter('preparing to commit')
165
self.weave_store = branch.weave_store
167
self.specific_files = specific_files
168
self.allow_pointless = allow_pointless
170
if timestamp is None:
171
self.timestamp = time.time()
173
self.timestamp = long(timestamp)
176
self.rev_id = _gen_revision_id(self.branch, self.timestamp)
180
if committer is None:
181
self.committer = username(self.branch)
183
assert isinstance(committer, basestring), type(committer)
184
self.committer = committer
187
self.timezone = local_time_offset()
189
self.timezone = int(timezone)
191
assert isinstance(message, basestring), type(message)
192
self.message = message
194
self.branch.lock_write()
196
self.work_tree = self.branch.working_tree()
197
self.work_inv = self.work_tree.inventory
198
self.basis_tree = self.branch.basis_tree()
199
self.basis_inv = self.basis_tree.inventory
201
self._gather_parents()
202
self._check_parents_present()
204
self._remove_deleted()
205
self.new_inv = Inventory()
206
self._store_entries()
207
self._report_deletes()
208
self._set_name_versions()
210
if not (self.allow_pointless
211
or len(self.parents) > 1
212
or self.new_inv != self.basis_inv):
213
raise PointlessCommit()
215
self._record_inventory()
216
self._record_ancestry()
217
self._make_revision()
218
note('committed r%d {%s}', (self.branch.revno() + 1),
220
self.branch.append_revision(self.rev_id)
221
self.branch.set_pending_merges([])
227
def _record_inventory(self):
228
"""Store the inventory for the new revision."""
229
inv_text = serializer_v5.write_inventory_to_string(self.new_inv)
230
self.inv_sha1 = sha_string(inv_text)
231
self.weave_store.add_text(INVENTORY_FILEID, self.rev_id,
232
split_lines(inv_text), self.parents)
235
def _record_ancestry(self):
236
"""Append merged revision ancestry to the ancestry file.
238
This should be the merged ancestry of all parents, plus the
240
w = self.weave_store.get_weave_or_empty(ANCESTRY_FILEID)
241
lines = self._make_ancestry(w)
242
w.add(self.rev_id, self.parents, lines)
243
self.weave_store.put_weave(ANCESTRY_FILEID, w)
246
def _make_ancestry(self, ancestry_weave):
247
"""Return merged ancestry lines.
249
The lines are revision-ids followed by newlines."""
250
parent_ancestries = [ancestry_weave.get(p) for p in self.parents]
251
new_lines = merge_ancestry_lines(self.rev_id, parent_ancestries)
252
mutter('merged ancestry of {%s}:\n%s', self.rev_id, ''.join(new_lines))
256
def _gather_parents(self):
257
pending_merges = self.branch.pending_merges()
259
self.parent_trees = []
260
precursor_id = self.branch.last_revision()
262
self.parents.append(precursor_id)
263
self.parent_trees.append(self.basis_tree)
264
self.parents += pending_merges
265
self.parent_trees.extend(map(self.branch.revision_tree, pending_merges))
268
def _check_parents_present(self):
269
for parent_id in self.parents:
270
mutter('commit parent revision {%s}', parent_id)
271
if not self.branch.has_revision(parent_id):
272
warning("can't commit a merge from an absent parent")
273
raise HistoryMissing(self.branch, 'revision', parent_id)
276
def _make_revision(self):
277
"""Record a new revision object for this commit."""
278
self.rev = Revision(timestamp=self.timestamp,
279
timezone=self.timezone,
280
committer=self.committer,
281
message=self.message,
282
inventory_sha1=self.inv_sha1,
283
revision_id=self.rev_id)
284
self.rev.parent_ids = self.parents
286
serializer_v5.write_revision(self.rev, rev_tmp)
288
self.branch.revision_store.add(rev_tmp, self.rev_id)
289
mutter('new revision_id is {%s}', self.rev_id)
292
def _remove_deleted(self):
293
"""Remove deleted files from the working inventories.
295
This is done prior to taking the working inventory as the
296
basis for the new committed inventory.
298
This returns true if any files
299
*that existed in the basis inventory* were deleted.
300
Files that were added and deleted
301
in the working copy don't matter.
303
specific = self.specific_files
305
for path, ie in self.work_inv.iter_entries():
306
if specific and not is_inside_any(specific, path):
308
if not self.work_tree.has_filename(path):
309
note('missing %s', path)
310
deleted_ids.append(ie.file_id)
312
for file_id in deleted_ids:
313
del self.work_inv[file_id]
314
self.branch._write_inventory(self.work_inv)
317
def _find_file_parents(self, file_id):
318
"""Return the text versions and hashes for all file parents.
320
Returned as a map from text version to inventory entry.
322
This is a set containing the file versions in all parents
323
revisions containing the file. If the file is new, the set
326
for tree in self.parent_trees:
327
if file_id in tree.inventory:
328
ie = tree.inventory[file_id]
329
assert ie.kind == 'file'
330
assert ie.file_id == file_id
331
if ie.text_version in r:
332
assert r[ie.text_version] == ie
334
r[ie.text_version] = ie
338
def _set_name_versions(self):
339
"""Pass over inventory and mark new entry version as needed.
341
Files get a new name version when they are new, have a
342
different parent, or a different name from in the
343
basis inventory, or if the file is in a different place
344
to any of the parents."""
345
# XXX: Need to think more here about when the user has
346
# made a specific decision on a particular value -- c.f.
348
for path, ie in self.new_inv.iter_entries():
351
for parent_tree in self.parent_trees:
352
parent_inv = parent_tree.inventory
353
if file_id not in parent_inv:
355
parent_ie = parent_inv[file_id]
356
if parent_ie.parent_id != ie.parent_id:
359
elif parent_ie.name != ie.name:
362
elif old_version is None:
363
old_version = parent_ie.name_version
364
elif old_version != parent_ie.name_version:
368
pass # so far so good
369
if old_version is None:
370
mutter('new name_version for {%s}', file_id)
371
ie.name_version = self.rev_id
373
mutter('name_version for {%s} inherited as {%s}',
374
file_id, old_version)
375
ie.name_version = old_version
378
def _store_entries(self):
379
"""Build revision inventory and store modified files.
381
This is called with new_inv a new empty inventory. Depending on
382
which files are selected for commit, and which ones have
383
been modified or merged, new inventory entries are built
384
based on the working and parent inventories.
386
As a side-effect this stores new text versions for committed
387
files with text changes or merges.
389
Each entry can have one of several things happen:
391
carry_file -- carried from the previous version (if not
394
commit_nonfile -- no text to worry about
396
commit_old_text -- same text, may have moved
398
commit_file -- new text version
400
for path, new_ie in self.work_inv.iter_entries():
401
file_id = new_ie.file_id
402
mutter('check %s {%s}', path, new_ie.file_id)
403
if self.specific_files:
404
if not is_inside_any(self.specific_files, path):
405
mutter('%s not selected for commit', path)
406
self._carry_file(file_id)
408
if new_ie.kind != 'file':
409
self._commit_nonfile(file_id)
412
file_parents = self._find_file_parents(file_id)
413
if len(file_parents) == 1:
414
parent_ie = file_parents.values()[0]
415
wc_sha1 = self.work_tree.get_file_sha1(file_id)
416
if parent_ie.text_sha1 == wc_sha1:
417
# text not changed or merged
418
self._commit_old_text(file_id, parent_ie)
421
mutter('parents of %s are %r', path, file_parents)
423
# file is either new, or a file merge; need to record
425
if len(file_parents) > 1:
426
note('merged %s', path)
427
elif len(file_parents) == 0:
428
note('added %s', path)
430
note('modified %s', path)
431
self._commit_file(new_ie, file_id, file_parents)
434
def _commit_nonfile(self, file_id):
435
self.new_inv.add(self.work_inv[file_id].copy())
438
def _carry_file(self, file_id):
439
"""Carry the file unchanged from the basis revision."""
440
if self.basis_inv.has_id(file_id):
441
self.new_inv.add(self.basis_inv[file_id].copy())
444
def _commit_old_text(self, file_id, parent_ie):
445
"""Keep the same text as last time, but possibly a different name."""
446
ie = self.work_inv[file_id].copy()
447
ie.text_version = parent_ie.text_version
448
ie.text_size = parent_ie.text_size
449
ie.text_sha1 = parent_ie.text_sha1
453
def _report_deletes(self):
454
for file_id in self.basis_inv:
455
if file_id not in self.new_inv:
456
note('deleted %s', self.basis_inv.id2path(file_id))
459
def _commit_file(self, new_ie, file_id, file_parents):
460
mutter('store new text for {%s} in revision {%s}',
461
file_id, self.rev_id)
462
new_lines = self.work_tree.get_file(file_id).readlines()
463
self._add_text_to_weave(file_id, new_lines, file_parents)
464
new_ie.text_version = self.rev_id
465
new_ie.text_sha1 = sha_strings(new_lines)
466
new_ie.text_size = sum(map(len, new_lines))
467
self.new_inv.add(new_ie)
470
def _add_text_to_weave(self, file_id, new_lines, parents):
471
if file_id.startswith('__'):
472
raise ValueError('illegal file-id %r for text file' % file_id)
473
self.weave_store.add_text(file_id, self.rev_id, new_lines, parents)
476
def _gen_revision_id(branch, when):
477
"""Return new revision-id."""
478
s = '%s-%s-' % (user_email(branch), compact_date(when))
479
s += hexlify(rand_bytes(8))
485
def merge_ancestry_lines(rev_id, ancestries):
486
"""Return merged ancestry lines.
488
rev_id -- id of the new revision
490
ancestries -- a sequence of ancestries for parent revisions,
491
as newline-terminated line lists.
493
if len(ancestries) == 0:
494
return [rev_id + '\n']
495
seen = set(ancestries[0])
496
ancs = ancestries[0][:]
497
for parent_ancestry in ancestries[1:]:
498
for line in parent_ancestry:
499
assert line[-1] == '\n'
added
removed
bzrlib/commit.py
