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
## 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()
205
if not (self.allow_pointless
206
or len(self.parents) > 1
207
or self.new_inv != self.basis_inv):
208
raise PointlessCommit()
210
self._record_inventory()
211
self._record_ancestry()
212
self._make_revision()
213
note('committed r%d {%s}', (self.branch.revno() + 1),
215
self.branch.append_revision(self.rev_id)
216
self.branch.set_pending_merges([])
222
def _record_inventory(self):
223
"""Store the inventory for the new revision."""
224
inv_text = serializer_v5.write_inventory_to_string(self.new_inv)
225
self.inv_sha1 = sha_string(inv_text)
226
self.weave_store.add_text(INVENTORY_FILEID, self.rev_id,
227
split_lines(inv_text), self.parents)
230
def _record_ancestry(self):
231
"""Append merged revision ancestry to the ancestry file.
233
This should be the merged ancestry of all parents, plus the
235
w = self.weave_store.get_weave_or_empty(ANCESTRY_FILEID)
236
lines = self._merge_ancestry_lines(w)
237
w.add(self.rev_id, self.parents, lines)
238
self.weave_store.put_weave(ANCESTRY_FILEID, w)
241
def _merge_ancestry_lines(self, ancestry_weave):
242
"""Return merged ancestry lines.
244
The lines are revision-ids followed by newlines."""
247
for parent_id in self.parents:
248
for line in ancestry_weave.get(parent_id):
249
assert line[-1] == '\n'
253
r = self.rev_id + '\n'
256
mutter('merged ancestry of {%s}:\n%s', self.rev_id, ''.join(ancs))
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.parents = map(RevisionReference, 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 _store_entries(self):
343
"""Build revision inventory and store modified files.
345
This is called with new_inv a new empty inventory. Depending on
346
which files are selected for commit, and which ones have
347
been modified or merged, new inventory entries are built
348
based on the working and parent inventories.
350
As a side-effect this stores new text versions for committed
351
files with text changes or merges.
353
Each entry can have one of several things happen:
355
carry_file -- carried from the previous version (if not
358
commit_nonfile -- no text to worry about
360
commit_old_text -- same text, may have moved
362
commit_file -- new text version
364
for path, new_ie in self.work_inv.iter_entries():
365
file_id = new_ie.file_id
366
mutter('check %s {%s}', path, new_ie.file_id)
367
if self.specific_files:
368
if not is_inside_any(self.specific_files, path):
369
mutter('%s not selected for commit', path)
370
self._carry_file(file_id)
372
if new_ie.kind != 'file':
373
self._commit_nonfile(file_id)
376
file_parents = self._find_file_parents(file_id)
377
if len(file_parents) == 1:
378
parent_ie = file_parents.values()[0]
379
wc_sha1 = self.work_tree.get_file_sha1(file_id)
380
if parent_ie.text_sha1 == wc_sha1:
381
# text not changed or merged
382
self._commit_old_text(file_id, parent_ie)
385
mutter('parents of %s are %r', path, file_parents)
387
# file is either new, or a file merge; need to record
389
if len(file_parents) > 1:
390
note('merged %s', path)
391
elif len(file_parents) == 0:
392
note('added %s', path)
394
note('modified %s', path)
395
self._commit_file(new_ie, file_id, file_parents)
398
def _commit_nonfile(self, file_id):
399
self.new_inv.add(self.work_inv[file_id].copy())
402
def _carry_file(self, file_id):
403
"""Carry the file unchanged from the basis revision."""
404
if self.basis_inv.has_id(file_id):
405
self.new_inv.add(self.basis_inv[file_id].copy())
408
def _commit_old_text(self, file_id, parent_ie):
409
"""Keep the same text as last time, but possibly a different name."""
410
ie = self.work_inv[file_id].copy()
411
ie.text_version = parent_ie.text_version
412
ie.text_size = parent_ie.text_size
413
ie.text_sha1 = parent_ie.text_sha1
417
def _report_deletes(self):
418
for file_id in self.basis_inv:
419
if file_id not in self.new_inv:
420
note('deleted %s', self.basis_inv.id2path(file_id))
423
def _commit_file(self, new_ie, file_id, file_parents):
424
mutter('store new text for {%s} in revision {%s}',
425
file_id, self.rev_id)
426
new_lines = self.work_tree.get_file(file_id).readlines()
427
self._add_text_to_weave(file_id, new_lines, file_parents)
428
new_ie.text_version = self.rev_id
429
new_ie.text_sha1 = sha_strings(new_lines)
430
new_ie.text_size = sum(map(len, new_lines))
431
self.new_inv.add(new_ie)
434
def _add_text_to_weave(self, file_id, new_lines, parents):
435
if file_id.startswith('__'):
436
raise ValueError('illegal file-id %r for text file' % file_id)
437
self.weave_store.add_text(file_id, self.rev_id, new_lines, parents)
440
def _gen_revision_id(branch, when):
441
"""Return new revision-id."""
442
s = '%s-%s-' % (user_email(branch), compact_date(when))
443
s += hexlify(rand_bytes(8))
added
removed
bzrlib/commit.py
