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
# TODO: Rather than mashing together the ancestry and storing it back,
48
# perhaps the weave should have single method which does it all in one
49
# go, avoiding a lot of redundant work.
51
# TODO: Perhaps give a warning if one of the revisions marked as
52
# merged is already in the ancestry, and then don't record it as a
55
# TODO: If the file is newly merged but unchanged from the version it
56
# merges from, then it should still be reported as newly added
57
# relative to the basis revision.
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
75
from bzrlib.errors import (BzrError, PointlessCommit,
79
from bzrlib.revision import Revision
80
from bzrlib.trace import mutter, note, warning
81
from bzrlib.xml5 import serializer_v5
82
from bzrlib.inventory import Inventory, ROOT_ID
83
from bzrlib.weave import Weave
84
from bzrlib.weavefile import read_weave, write_weave_v5
85
from bzrlib.atomicfile import AtomicFile
88
def commit(*args, **kwargs):
89
"""Commit a new revision to a branch.
91
Function-style interface for convenience of old callers.
93
New code should use the Commit class instead.
95
## XXX: Remove this in favor of Branch.commit?
96
Commit().commit(*args, **kwargs)
99
class NullCommitReporter(object):
100
"""I report on progress of a commit."""
102
def snapshot_change(self, change, path):
105
def completed(self, revno, rev_id):
108
def deleted(self, file_id):
111
def escaped(self, escape_count, message):
114
def missing(self, path):
117
class ReportCommitToLog(NullCommitReporter):
119
def snapshot_change(self, change, path):
120
note("%s %s", change, path)
122
def completed(self, revno, rev_id):
123
note('committed r%d {%s}', revno, rev_id)
125
def deleted(self, file_id):
126
note('deleted %s', file_id)
128
def escaped(self, escape_count, message):
129
note("replaced %d control characters in message", escape_count)
131
def missing(self, path):
132
note('missing %s', path)
134
class Commit(object):
135
"""Task of committing a new revision.
137
This is a MethodObject: it accumulates state as the commit is
138
prepared, and then it is discarded. It doesn't represent
139
historical revisions, just the act of recording a new one.
142
Modified to hold a list of files that have been deleted from
143
the working directory; these should be removed from the
148
if reporter is not None:
149
self.reporter = reporter
151
self.reporter = NullCommitReporter()
161
allow_pointless=True,
163
"""Commit working copy as a new revision.
165
timestamp -- if not None, seconds-since-epoch for a
166
postdated/predated commit.
168
specific_files -- If true, commit only those files.
170
rev_id -- If set, use this as the new revision id.
171
Useful for test or import commands that need to tightly
172
control what revisions are assigned. If you duplicate
173
a revision id that exists elsewhere it is your own fault.
174
If null (default), a time/random revision id is generated.
176
allow_pointless -- If true (default), commit even if nothing
177
has changed and no merges are recorded.
179
mutter('preparing to commit')
182
self.weave_store = branch.weave_store
184
self.specific_files = specific_files
185
self.allow_pointless = allow_pointless
187
if timestamp is None:
188
self.timestamp = time.time()
190
self.timestamp = long(timestamp)
193
self.rev_id = _gen_revision_id(self.branch, self.timestamp)
197
if committer is None:
198
self.committer = username(self.branch)
200
assert isinstance(committer, basestring), type(committer)
201
self.committer = committer
204
self.timezone = local_time_offset()
206
self.timezone = int(timezone)
208
assert isinstance(message, basestring), type(message)
209
self.message = message
210
self._escape_commit_message()
212
self.branch.lock_write()
214
self.work_tree = self.branch.working_tree()
215
self.work_inv = self.work_tree.inventory
216
self.basis_tree = self.branch.basis_tree()
217
self.basis_inv = self.basis_tree.inventory
219
self._gather_parents()
220
if len(self.parents) > 1 and self.specific_files:
221
raise NotImplementedError('selected-file commit of merges is not supported yet')
222
self._check_parents_present()
224
self._remove_deleted()
225
self._populate_new_inv()
226
self._store_snapshot()
227
self._report_deletes()
229
if not (self.allow_pointless
230
or len(self.parents) > 1
231
or self.new_inv != self.basis_inv):
232
raise PointlessCommit()
234
if len(list(self.work_tree.iter_conflicts()))>0:
235
raise ConflictsInTree
237
self._record_inventory()
238
self._make_revision()
239
self.reporter.completed(self.branch.revno()+1, self.rev_id)
240
self.branch.append_revision(self.rev_id)
241
self.branch.set_pending_merges([])
245
def _record_inventory(self):
246
"""Store the inventory for the new revision."""
247
inv_text = serializer_v5.write_inventory_to_string(self.new_inv)
248
self.inv_sha1 = sha_string(inv_text)
249
s = self.branch.control_weaves
250
s.add_text('inventory', self.rev_id,
251
split_lines(inv_text), self.present_parents)
253
def _escape_commit_message(self):
254
"""Replace xml-incompatible control characters."""
255
# Python strings can include characters that can't be
256
# represented in well-formed XML; escape characters that
257
# aren't listed in the XML specification
258
# (http://www.w3.org/TR/REC-xml/#NT-Char).
259
if isinstance(self.message, unicode):
260
char_pattern = u'[^\x09\x0A\x0D\u0020-\uD7FF\uE000-\uFFFD]'
262
# Use a regular 'str' as pattern to avoid having re.subn
263
# return 'unicode' results.
264
char_pattern = '[^x09\x0A\x0D\x20-\xFF]'
265
self.message, escape_count = re.subn(
267
lambda match: match.group(0).encode('unicode_escape'),
270
self.reporter.escaped(escape_count, self.message)
272
def _gather_parents(self):
273
"""Record the parents of a merge for merge detection."""
274
pending_merges = self.branch.pending_merges()
276
self.parent_invs = []
277
self.present_parents = []
278
precursor_id = self.branch.last_revision()
280
self.parents.append(precursor_id)
281
self.parents += pending_merges
282
for revision in self.parents:
283
if self.branch.has_revision(revision):
284
self.parent_invs.append(self.branch.get_inventory(revision))
285
self.present_parents.append(revision)
287
def _check_parents_present(self):
288
for parent_id in self.parents:
289
mutter('commit parent revision {%s}', parent_id)
290
if not self.branch.has_revision(parent_id):
291
if parent_id == self.branch.last_revision():
292
warning("parent is missing %r", parent_id)
293
raise HistoryMissing(self.branch, 'revision', parent_id)
295
mutter("commit will ghost revision %r", parent_id)
297
def _make_revision(self):
298
"""Record a new revision object for this commit."""
299
self.rev = Revision(timestamp=self.timestamp,
300
timezone=self.timezone,
301
committer=self.committer,
302
message=self.message,
303
inventory_sha1=self.inv_sha1,
304
revision_id=self.rev_id)
305
self.rev.parent_ids = self.parents
307
serializer_v5.write_revision(self.rev, rev_tmp)
309
self.branch.revision_store.add(rev_tmp, self.rev_id)
310
mutter('new revision_id is {%s}', self.rev_id)
312
def _remove_deleted(self):
313
"""Remove deleted files from the working inventories.
315
This is done prior to taking the working inventory as the
316
basis for the new committed inventory.
318
This returns true if any files
319
*that existed in the basis inventory* were deleted.
320
Files that were added and deleted
321
in the working copy don't matter.
323
specific = self.specific_files
325
for path, ie in self.work_inv.iter_entries():
326
if specific and not is_inside_any(specific, path):
328
if not self.work_tree.has_filename(path):
329
self.reporter.missing(path)
330
deleted_ids.append((path, ie.file_id))
332
deleted_ids.sort(reverse=True)
333
for path, file_id in deleted_ids:
334
del self.work_inv[file_id]
335
self.branch._write_inventory(self.work_inv)
337
def _store_snapshot(self):
338
"""Pass over inventory and record a snapshot.
340
Entries get a new revision when they are modified in
341
any way, which includes a merge with a new set of
342
parents that have the same entry.
344
# XXX: Need to think more here about when the user has
345
# made a specific decision on a particular value -- c.f.
347
for path, ie in self.new_inv.iter_entries():
348
previous_entries = ie.find_previous_heads(
350
self.weave_store.get_weave_or_empty(ie.file_id))
351
if ie.revision is None:
352
change = ie.snapshot(self.rev_id, path, previous_entries,
353
self.work_tree, self.weave_store)
356
self.reporter.snapshot_change(change, path)
358
def _populate_new_inv(self):
359
"""Build revision inventory.
361
This creates a new empty inventory. Depending on
362
which files are selected for commit, and what is present in the
363
current tree, the new inventory is populated. inventory entries
364
which are candidates for modification have their revision set to
365
None; inventory entries that are carried over untouched have their
366
revision set to their prior value.
368
mutter("Selecting files for commit with filter %s", self.specific_files)
369
self.new_inv = Inventory()
370
for path, new_ie in self.work_inv.iter_entries():
371
file_id = new_ie.file_id
372
mutter('check %s {%s}', path, new_ie.file_id)
373
if self.specific_files:
374
if not is_inside_any(self.specific_files, path):
375
mutter('%s not selected for commit', path)
376
self._carry_entry(file_id)
379
# this is selected, ensure its parents are too.
380
parent_id = new_ie.parent_id
381
while parent_id != ROOT_ID:
382
if not self.new_inv.has_id(parent_id):
383
ie = self._select_entry(self.work_inv[parent_id])
384
mutter('%s selected for commit because of %s',
385
self.new_inv.id2path(parent_id), path)
387
ie = self.new_inv[parent_id]
388
if ie.revision is not None:
390
mutter('%s selected for commit because of %s',
391
self.new_inv.id2path(parent_id), path)
392
parent_id = ie.parent_id
393
mutter('%s selected for commit', path)
394
self._select_entry(new_ie)
396
def _select_entry(self, new_ie):
397
"""Make new_ie be considered for committing."""
403
def _carry_entry(self, file_id):
404
"""Carry the file unchanged from the basis revision."""
405
if self.basis_inv.has_id(file_id):
406
self.new_inv.add(self.basis_inv[file_id].copy())
408
def _report_deletes(self):
409
for file_id in self.basis_inv:
410
if file_id not in self.new_inv:
411
self.reporter.deleted(self.basis_inv.id2path(file_id))
413
def _gen_revision_id(branch, when):
414
"""Return new revision-id."""
415
s = '%s-%s-' % (user_email(branch), compact_date(when))
416
s += hexlify(rand_bytes(8))
added
removed
bzrlib/commit.py
