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
58
from binascii import hexlify
59
from cStringIO import StringIO
61
from bzrlib.osutils import (local_time_offset, username,
62
rand_bytes, compact_date, user_email,
63
kind_marker, is_inside_any, quotefn,
64
sha_string, sha_strings, sha_file, isdir, isfile,
66
from bzrlib.branch import gen_file_id, INVENTORY_FILEID, ANCESTRY_FILEID
67
from bzrlib.errors import (BzrError, PointlessCommit,
70
from bzrlib.revision import Revision
71
from bzrlib.trace import mutter, note, warning
72
from bzrlib.xml5 import serializer_v5
73
from bzrlib.inventory import Inventory
74
from bzrlib.weave import Weave
75
from bzrlib.weavefile import read_weave, write_weave_v5
76
from bzrlib.atomicfile import AtomicFile
79
def commit(*args, **kwargs):
80
"""Commit a new revision to a branch.
82
Function-style interface for convenience of old callers.
84
New code should use the Commit class instead.
86
## XXX: Remove this in favor of Branch.commit?
87
Commit().commit(*args, **kwargs)
90
class NullCommitReporter(object):
91
"""I report on progress of a commit."""
92
def added(self, path):
95
def removed(self, path):
98
def renamed(self, old_path, new_path):
102
class ReportCommitToLog(NullCommitReporter):
103
def added(self, path):
104
note('added %s', path)
106
def removed(self, path):
107
note('removed %s', path)
109
def renamed(self, old_path, new_path):
110
note('renamed %s => %s', old_path, new_path)
113
class Commit(object):
114
"""Task of committing a new revision.
116
This is a MethodObject: it accumulates state as the commit is
117
prepared, and then it is discarded. It doesn't represent
118
historical revisions, just the act of recording a new one.
121
Modified to hold a list of files that have been deleted from
122
the working directory; these should be removed from the
127
if reporter is not None:
128
self.reporter = reporter
130
self.reporter = NullCommitReporter()
140
allow_pointless=True,
142
"""Commit working copy as a new revision.
144
timestamp -- if not None, seconds-since-epoch for a
145
postdated/predated commit.
147
specific_files -- If true, commit only those files.
149
rev_id -- If set, use this as the new revision id.
150
Useful for test or import commands that need to tightly
151
control what revisions are assigned. If you duplicate
152
a revision id that exists elsewhere it is your own fault.
153
If null (default), a time/random revision id is generated.
155
allow_pointless -- If true (default), commit even if nothing
156
has changed and no merges are recorded.
158
mutter('preparing to commit')
161
self.weave_store = branch.weave_store
163
self.specific_files = specific_files
164
self.allow_pointless = allow_pointless
166
if timestamp is None:
167
self.timestamp = time.time()
169
self.timestamp = long(timestamp)
172
self.rev_id = _gen_revision_id(self.branch, self.timestamp)
176
if committer is None:
177
self.committer = username(self.branch)
179
assert isinstance(committer, basestring), type(committer)
180
self.committer = committer
183
self.timezone = local_time_offset()
185
self.timezone = int(timezone)
187
assert isinstance(message, basestring), type(message)
188
self.message = message
190
self.branch.lock_write()
192
self.work_tree = self.branch.working_tree()
193
self.work_inv = self.work_tree.inventory
194
self.basis_tree = self.branch.basis_tree()
195
self.basis_inv = self.basis_tree.inventory
197
self._gather_parents()
198
self._check_parents_present()
200
self._remove_deleted()
201
self.new_inv = Inventory()
202
self._store_entries()
203
self._report_deletes()
204
self._set_name_versions()
206
if not (self.allow_pointless
207
or len(self.parents) > 1
208
or self.new_inv != self.basis_inv):
209
raise PointlessCommit()
211
self._record_inventory()
212
self._record_ancestry()
213
self._make_revision()
214
note('committed r%d {%s}', (self.branch.revno() + 1),
216
self.branch.append_revision(self.rev_id)
217
self.branch.set_pending_merges([])
223
def _record_inventory(self):
224
"""Store the inventory for the new revision."""
225
inv_text = serializer_v5.write_inventory_to_string(self.new_inv)
226
self.inv_sha1 = sha_string(inv_text)
227
self.weave_store.add_text(INVENTORY_FILEID, self.rev_id,
228
split_lines(inv_text), self.parents)
231
def _record_ancestry(self):
232
"""Append merged revision ancestry to the ancestry file.
234
This should be the merged ancestry of all parents, plus the
236
w = self.weave_store.get_weave_or_empty(ANCESTRY_FILEID)
237
lines = self._make_ancestry(w)
238
w.add(self.rev_id, self.parents, lines)
239
self.weave_store.put_weave(ANCESTRY_FILEID, w)
242
def _make_ancestry(self, ancestry_weave):
243
"""Return merged ancestry lines.
245
The lines are revision-ids followed by newlines."""
246
parent_ancestries = [ancestry_weave.get(p) for p in self.parents]
247
new_lines = merge_ancestry_lines(self.rev_id, parent_ancestries)
248
mutter('merged ancestry of {%s}:\n%s', self.rev_id, ''.join(new_lines))
252
def _gather_parents(self):
253
pending_merges = self.branch.pending_merges()
255
self.parent_trees = []
256
precursor_id = self.branch.last_revision()
258
self.parents.append(precursor_id)
259
self.parent_trees.append(self.basis_tree)
260
self.parents += pending_merges
261
self.parent_trees.extend(map(self.branch.revision_tree, pending_merges))
264
def _check_parents_present(self):
265
for parent_id in self.parents:
266
mutter('commit parent revision {%s}', parent_id)
267
if not self.branch.has_revision(parent_id):
268
warning("can't commit a merge from an absent parent")
269
raise HistoryMissing(self.branch, 'revision', parent_id)
272
def _make_revision(self):
273
"""Record a new revision object for this commit."""
274
self.rev = Revision(timestamp=self.timestamp,
275
timezone=self.timezone,
276
committer=self.committer,
277
message=self.message,
278
inventory_sha1=self.inv_sha1,
279
revision_id=self.rev_id)
280
self.rev.parent_ids = self.parents
282
serializer_v5.write_revision(self.rev, rev_tmp)
284
self.branch.revision_store.add(rev_tmp, self.rev_id)
285
mutter('new revision_id is {%s}', self.rev_id)
288
def _remove_deleted(self):
289
"""Remove deleted files from the working inventories.
291
This is done prior to taking the working inventory as the
292
basis for the new committed inventory.
294
This returns true if any files
295
*that existed in the basis inventory* were deleted.
296
Files that were added and deleted
297
in the working copy don't matter.
299
specific = self.specific_files
301
for path, ie in self.work_inv.iter_entries():
302
if specific and not is_inside_any(specific, path):
304
if not self.work_tree.has_filename(path):
305
note('missing %s', path)
306
deleted_ids.append(ie.file_id)
308
for file_id in deleted_ids:
309
del self.work_inv[file_id]
310
self.branch._write_inventory(self.work_inv)
313
def _find_file_parents(self, file_id):
314
"""Return the text versions and hashes for all file parents.
316
Returned as a map from text version to inventory entry.
318
This is a set containing the file versions in all parents
319
revisions containing the file. If the file is new, the set
322
for tree in self.parent_trees:
323
if file_id in tree.inventory:
324
ie = tree.inventory[file_id]
325
assert ie.kind == 'file'
326
assert ie.file_id == file_id
327
if ie.text_version in r:
328
assert r[ie.text_version] == ie
330
r[ie.text_version] = ie
334
def _set_name_versions(self):
335
"""Pass over inventory and mark new entry version as needed.
337
Files get a new name version when they are new, have a
338
different parent, or a different name from in the
339
basis inventory, or if the file is in a different place
340
to any of the parents."""
341
# XXX: Need to think more here about when the user has
342
# made a specific decision on a particular value -- c.f.
344
for path, ie in self.new_inv.iter_entries():
347
for parent_tree in self.parent_trees:
348
parent_inv = parent_tree.inventory
349
if file_id not in parent_inv:
351
parent_ie = parent_inv[file_id]
352
if parent_ie.parent_id != ie.parent_id:
355
elif parent_ie.name != ie.name:
358
elif old_version is None:
359
old_version = parent_ie.name_version
360
elif old_version != parent_ie.name_version:
364
pass # so far so good
365
if old_version is None:
366
mutter('new name_version for {%s}', file_id)
367
ie.name_version = self.rev_id
369
mutter('name_version for {%s} inherited as {%s}',
370
file_id, old_version)
371
ie.name_version = old_version
374
def _store_entries(self):
375
"""Build revision inventory and store modified files.
377
This is called with new_inv a new empty inventory. Depending on
378
which files are selected for commit, and which ones have
379
been modified or merged, new inventory entries are built
380
based on the working and parent inventories.
382
As a side-effect this stores new text versions for committed
383
files with text changes or merges.
385
Each entry can have one of several things happen:
387
carry_file -- carried from the previous version (if not
390
commit_nonfile -- no text to worry about
392
commit_old_text -- same text, may have moved
394
commit_file -- new text version
396
for path, new_ie in self.work_inv.iter_entries():
397
file_id = new_ie.file_id
398
mutter('check %s {%s}', path, new_ie.file_id)
399
if self.specific_files:
400
if not is_inside_any(self.specific_files, path):
401
mutter('%s not selected for commit', path)
402
self._carry_file(file_id)
404
if new_ie.kind != 'file':
405
self._commit_nonfile(file_id)
408
file_parents = self._find_file_parents(file_id)
409
if len(file_parents) == 1:
410
parent_ie = file_parents.values()[0]
411
wc_sha1 = self.work_tree.get_file_sha1(file_id)
412
if parent_ie.text_sha1 == wc_sha1:
413
# text not changed or merged
414
self._commit_old_text(file_id, parent_ie)
417
mutter('parents of %s are %r', path, file_parents)
419
# file is either new, or a file merge; need to record
421
if len(file_parents) > 1:
422
note('merged %s', path)
423
elif len(file_parents) == 0:
424
note('added %s', path)
426
note('modified %s', path)
427
self._commit_file(new_ie, file_id, file_parents)
430
def _commit_nonfile(self, file_id):
431
self.new_inv.add(self.work_inv[file_id].copy())
434
def _carry_file(self, file_id):
435
"""Carry the file unchanged from the basis revision."""
436
if self.basis_inv.has_id(file_id):
437
self.new_inv.add(self.basis_inv[file_id].copy())
440
def _commit_old_text(self, file_id, parent_ie):
441
"""Keep the same text as last time, but possibly a different name."""
442
ie = self.work_inv[file_id].copy()
443
ie.text_version = parent_ie.text_version
444
ie.text_size = parent_ie.text_size
445
ie.text_sha1 = parent_ie.text_sha1
449
def _report_deletes(self):
450
for file_id in self.basis_inv:
451
if file_id not in self.new_inv:
452
note('deleted %s', self.basis_inv.id2path(file_id))
455
def _commit_file(self, new_ie, file_id, file_parents):
456
mutter('store new text for {%s} in revision {%s}',
457
file_id, self.rev_id)
458
new_lines = self.work_tree.get_file(file_id).readlines()
459
self._add_text_to_weave(file_id, new_lines, file_parents)
460
new_ie.text_version = self.rev_id
461
new_ie.text_sha1 = sha_strings(new_lines)
462
new_ie.text_size = sum(map(len, new_lines))
463
self.new_inv.add(new_ie)
466
def _add_text_to_weave(self, file_id, new_lines, parents):
467
if file_id.startswith('__'):
468
raise ValueError('illegal file-id %r for text file' % file_id)
469
self.weave_store.add_text(file_id, self.rev_id, new_lines, parents)
472
def _gen_revision_id(branch, when):
473
"""Return new revision-id."""
474
s = '%s-%s-' % (user_email(branch), compact_date(when))
475
s += hexlify(rand_bytes(8))
481
def merge_ancestry_lines(rev_id, ancestries):
482
"""Return merged ancestry lines.
484
rev_id -- id of the new revision
486
ancestries -- a sequence of ancestries for parent revisions,
487
as newline-terminated line lists.
489
if len(ancestries) == 0:
490
return [rev_id + '\n']
491
seen = set(ancestries[0])
492
ancs = ancestries[0][:]
493
for parent_ancestry in ancestries[1:]:
494
for line in parent_ancestry:
495
assert line[-1] == '\n'
added
removed
bzrlib/commit.py
