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, RevisionReference
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
Commit().commit(*args, **kwargs)
89
class NullCommitReporter(object):
90
"""I report on progress of a commit."""
91
def added(self, path):
94
def removed(self, path):
97
def renamed(self, old_path, new_path):
101
class ReportCommitToLog(NullCommitReporter):
102
def added(self, path):
103
note('added %s', path)
105
def removed(self, path):
106
note('removed %s', path)
108
def renamed(self, old_path, new_path):
109
note('renamed %s => %s', old_path, new_path)
112
class Commit(object):
113
"""Task of committing a new revision.
115
This is a MethodObject: it accumulates state as the commit is
116
prepared, and then it is discarded. It doesn't represent
117
historical revisions, just the act of recording a new one.
120
Modified to hold a list of files that have been deleted from
121
the working directory; these should be removed from the
126
if reporter is not None:
127
self.reporter = reporter
129
self.reporter = NullCommitReporter()
139
allow_pointless=True):
140
"""Commit working copy as a new revision.
142
timestamp -- if not None, seconds-since-epoch for a
143
postdated/predated commit.
145
specific_files -- If true, commit only those files.
147
rev_id -- If set, use this as the new revision id.
148
Useful for test or import commands that need to tightly
149
control what revisions are assigned. If you duplicate
150
a revision id that exists elsewhere it is your own fault.
151
If null (default), a time/random revision id is generated.
153
allow_pointless -- If true (default), commit even if nothing
154
has changed and no merges are recorded.
156
self.any_changes = False
159
self.weave_store = branch.weave_store
161
self.specific_files = specific_files
162
self.allow_pointless = allow_pointless
164
if timestamp is None:
165
self.timestamp = time.time()
167
self.timestamp = long(timestamp)
170
self.rev_id = _gen_revision_id(self.branch, self.timestamp)
174
if committer is None:
175
self.committer = username(self.branch)
177
assert isinstance(committer, basestring), type(committer)
178
self.committer = committer
181
self.timezone = local_time_offset()
183
self.timezone = int(timezone)
185
assert isinstance(message, basestring), type(message)
186
self.message = message
188
self.branch.lock_write()
190
self.work_tree = self.branch.working_tree()
191
self.work_inv = self.work_tree.inventory
192
self.basis_tree = self.branch.basis_tree()
193
self.basis_inv = self.basis_tree.inventory
195
self._gather_parents()
197
self._remove_deleted()
198
self.new_inv = Inventory()
200
self._report_deletes()
202
if not (self.allow_pointless
203
or len(self.parents) != 1
204
or self.new_inv != self.basis_inv):
205
raise PointlessCommit()
207
self._record_inventory()
208
self._record_ancestry()
209
self._make_revision()
210
note('committed r%d {%s}', (self.branch.revno() + 1),
212
self.branch.append_revision(self.rev_id)
213
self.branch.set_pending_merges([])
219
def _record_inventory(self):
220
"""Store the inventory for the new revision."""
221
inv_text = serializer_v5.write_inventory_to_string(self.new_inv)
222
self.inv_sha1 = sha_string(inv_text)
223
self.weave_store.add_text(INVENTORY_FILEID, self.rev_id,
224
split_lines(inv_text), self.parents)
227
def _record_ancestry(self):
228
"""Append merged revision ancestry to the ancestry file.
230
This should be the merged ancestry of all parents, plus the
232
w = self.weave_store.get_weave_or_empty(ANCESTRY_FILEID)
233
lines = self._merge_ancestry_lines(w)
234
w.add(self.rev_id, self.parents, lines)
235
self.weave_store.put_weave(ANCESTRY_FILEID, w)
238
def _merge_ancestry_lines(self, ancestry_weave):
239
"""Return merged ancestry lines.
241
The lines are revision-ids followed by newlines."""
244
for parent_id in self.parents:
245
for line in ancestry_weave.get(parent_id):
246
assert line[-1] == '\n'
250
r = self.rev_id + '\n'
253
mutter('merged ancestry of {%s}:\n%s', self.rev_id, ''.join(ancs))
257
def _gather_parents(self):
258
pending_merges = self.branch.pending_merges()
260
precursor_id = self.branch.last_revision()
262
self.parents.append(precursor_id)
263
self.parents += pending_merges
264
for parent_id in self.parents:
265
mutter('commit parent revision {%s}', parent_id)
266
if not self.branch.has_revision(parent_id):
267
warning("can't commit a merge from an absent parent")
268
raise HistoryMissing(self.branch, 'revision', parent_id)
269
self.parent_trees = map(self.branch.revision_tree, self.parents)
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.parents = map(RevisionReference, 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 text sha1.
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.text_sha1
330
r[ie.text_version] = ie.text_sha1
334
def _store_files(self):
335
"""Store new texts of modified/added files.
337
This is called with new_inv set to a copy of the working
338
inventory, with deleted/removed files already cut out. So
339
this code only needs to deal with setting text versions, and
340
possibly recording new file texts."""
341
for path, new_ie in self.work_inv.iter_entries():
342
file_id = new_ie.file_id
343
mutter('check %s {%s}', path, new_ie.file_id)
344
if self.specific_files:
345
if not is_inside_any(self.specific_files, path):
346
mutter('%s not selected for commit', path)
347
self._carry_file(file_id)
349
if new_ie.kind != 'file':
350
self._commit_nonfile(file_id)
352
file_parents = self._find_file_parents(file_id)
353
wc_sha1 = self.work_tree.get_file_sha1(file_id)
354
if (len(file_parents) == 1
355
and file_parents.values()[0] == wc_sha1):
356
# not changed or merged
357
self._carry_file(file_id)
360
mutter('parents of %s are %r', path, file_parents)
362
# file is either new, or a file merge; need to record
364
if len(file_parents) > 1:
365
note('merged %s', path)
366
elif len(file_parents) == 0:
367
note('added %s', path)
369
note('modified %s', path)
370
self._commit_file(new_ie, file_id, file_parents)
373
def _commit_nonfile(self, file_id):
374
self.new_inv.add(self.work_inv[file_id].copy())
377
def _carry_file(self, file_id):
378
"""Keep a file in the same state as in the basis."""
379
if self.basis_inv.has_id(file_id):
380
self.new_inv.add(self.basis_inv[file_id].copy())
383
def _report_deletes(self):
384
for file_id in self.basis_inv:
385
if file_id not in self.new_inv:
386
note('deleted %s', self.basis_inv.id2path(file_id))
389
def _commit_file(self, new_ie, file_id, file_parents):
390
mutter('store new text for {%s} in revision {%s}',
391
file_id, self.rev_id)
392
new_lines = self.work_tree.get_file(file_id).readlines()
393
self._add_text_to_weave(file_id, new_lines, file_parents)
394
new_ie.text_version = self.rev_id
395
new_ie.text_sha1 = sha_strings(new_lines)
396
new_ie.text_size = sum(map(len, new_lines))
397
self.new_inv.add(new_ie)
400
def _add_text_to_weave(self, file_id, new_lines, parents):
401
if file_id.startswith('__'):
402
raise ValueError('illegal file-id %r for text file' % file_id)
403
self.weave_store.add_text(file_id, self.rev_id, new_lines, parents)
406
def _gen_revision_id(branch, when):
407
"""Return new revision-id."""
408
s = '%s-%s-' % (user_email(branch), compact_date(when))
409
s += hexlify(rand_bytes(8))
added
removed
bzrlib/commit.py
