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,
78
from bzrlib.revision import Revision
79
from bzrlib.trace import mutter, note, warning
80
from bzrlib.xml5 import serializer_v5
81
from bzrlib.inventory import Inventory
82
from bzrlib.weave import Weave
83
from bzrlib.weavefile import read_weave, write_weave_v5
84
from bzrlib.atomicfile import AtomicFile
87
def commit(*args, **kwargs):
88
"""Commit a new revision to a branch.
90
Function-style interface for convenience of old callers.
92
New code should use the Commit class instead.
94
## XXX: Remove this in favor of Branch.commit?
95
Commit().commit(*args, **kwargs)
98
class NullCommitReporter(object):
99
"""I report on progress of a commit."""
100
def added(self, path):
103
def removed(self, path):
106
def renamed(self, old_path, new_path):
110
class ReportCommitToLog(NullCommitReporter):
111
def added(self, path):
112
note('added %s', path)
114
def removed(self, path):
115
note('removed %s', path)
117
def renamed(self, old_path, new_path):
118
note('renamed %s => %s', old_path, new_path)
121
class Commit(object):
122
"""Task of committing a new revision.
124
This is a MethodObject: it accumulates state as the commit is
125
prepared, and then it is discarded. It doesn't represent
126
historical revisions, just the act of recording a new one.
129
Modified to hold a list of files that have been deleted from
130
the working directory; these should be removed from the
135
if reporter is not None:
136
self.reporter = reporter
138
self.reporter = NullCommitReporter()
148
allow_pointless=True,
150
"""Commit working copy as a new revision.
152
timestamp -- if not None, seconds-since-epoch for a
153
postdated/predated commit.
155
specific_files -- If true, commit only those files.
157
rev_id -- If set, use this as the new revision id.
158
Useful for test or import commands that need to tightly
159
control what revisions are assigned. If you duplicate
160
a revision id that exists elsewhere it is your own fault.
161
If null (default), a time/random revision id is generated.
163
allow_pointless -- If true (default), commit even if nothing
164
has changed and no merges are recorded.
166
mutter('preparing to commit')
169
self.weave_store = branch.weave_store
171
self.specific_files = specific_files
172
self.allow_pointless = allow_pointless
174
if timestamp is None:
175
self.timestamp = time.time()
177
self.timestamp = long(timestamp)
180
self.rev_id = _gen_revision_id(self.branch, self.timestamp)
184
if committer is None:
185
self.committer = username(self.branch)
187
assert isinstance(committer, basestring), type(committer)
188
self.committer = committer
191
self.timezone = local_time_offset()
193
self.timezone = int(timezone)
195
assert isinstance(message, basestring), type(message)
196
self.message = message
197
self._escape_commit_message()
199
self.branch.lock_write()
201
self.work_tree = self.branch.working_tree()
202
self.work_inv = self.work_tree.inventory
203
self.basis_tree = self.branch.basis_tree()
204
self.basis_inv = self.basis_tree.inventory
206
self._gather_parents()
207
if len(self.parents) > 1 and self.specific_files:
208
raise NotImplementedError('selected-file commit of merges is not supported yet')
209
self._check_parents_present()
211
self._remove_deleted()
212
self._populate_new_inv()
213
self._store_snapshot()
214
self._report_deletes()
216
if not (self.allow_pointless
217
or len(self.parents) > 1
218
or self.new_inv != self.basis_inv):
219
raise PointlessCommit()
221
self._record_inventory()
222
self._record_ancestry()
223
self._make_revision()
224
note('committed r%d {%s}', (self.branch.revno() + 1),
226
self.branch.append_revision(self.rev_id)
227
self.branch.set_pending_merges([])
231
def _record_inventory(self):
232
"""Store the inventory for the new revision."""
233
inv_text = serializer_v5.write_inventory_to_string(self.new_inv)
234
self.inv_sha1 = sha_string(inv_text)
235
s = self.branch.control_weaves
236
s.add_text('inventory', self.rev_id,
237
split_lines(inv_text), self.present_parents)
239
def _escape_commit_message(self):
240
"""Replace xml-incompatible control characters."""
241
# Python strings can include characters that can't be
242
# represented in well-formed XML; escape characters that
243
# aren't listed in the XML specification
244
# (http://www.w3.org/TR/REC-xml/#NT-Char).
245
if isinstance(self.message, unicode):
246
char_pattern = u'[^\x09\x0A\x0D\u0020-\uD7FF\uE000-\uFFFD]'
248
# Use a regular 'str' as pattern to avoid having re.subn
249
# return 'unicode' results.
250
char_pattern = '[^x09\x0A\x0D\x20-\xFF]'
251
self.message, escape_count = re.subn(
253
lambda match: match.group(0).encode('unicode_escape'),
256
note("replaced %d control characters in message", escape_count)
258
def _record_ancestry(self):
259
"""Append merged revision ancestry to the ancestry file.
261
This should be the merged ancestry of all parents, plus the
263
s = self.branch.control_weaves
264
w = s.get_weave_or_empty('ancestry')
265
lines = self._make_ancestry(w)
266
w.add(self.rev_id, self.present_parents, lines)
267
s.put_weave('ancestry', w)
269
def _make_ancestry(self, ancestry_weave):
270
"""Return merged ancestry lines.
272
The lines are revision-ids followed by newlines."""
273
parent_ancestries = [ancestry_weave.get(p) for p in self.present_parents]
274
new_lines = merge_ancestry_lines(self.rev_id, parent_ancestries)
275
mutter('merged ancestry of {%s}:\n%s', self.rev_id, ''.join(new_lines))
278
def _gather_parents(self):
279
"""Record the parents of a merge for merge detection."""
280
pending_merges = self.branch.pending_merges()
282
self.parent_invs = []
283
self.present_parents = []
284
precursor_id = self.branch.last_revision()
286
self.parents.append(precursor_id)
287
self.parents += pending_merges
288
for revision in self.parents:
289
if self.branch.has_revision(revision):
290
self.parent_invs.append(self.branch.get_inventory(revision))
291
self.present_parents.append(revision)
293
def _check_parents_present(self):
294
for parent_id in self.parents:
295
mutter('commit parent revision {%s}', parent_id)
296
if not self.branch.has_revision(parent_id):
297
if parent_id == self.branch.last_revision():
298
warning("parent is pissing %r", parent_id)
299
raise HistoryMissing(self.branch, 'revision', parent_id)
301
mutter("commit will ghost revision %r", parent_id)
303
def _make_revision(self):
304
"""Record a new revision object for this commit."""
305
self.rev = Revision(timestamp=self.timestamp,
306
timezone=self.timezone,
307
committer=self.committer,
308
message=self.message,
309
inventory_sha1=self.inv_sha1,
310
revision_id=self.rev_id)
311
self.rev.parent_ids = self.parents
313
serializer_v5.write_revision(self.rev, rev_tmp)
315
self.branch.revision_store.add(rev_tmp, self.rev_id)
316
mutter('new revision_id is {%s}', self.rev_id)
319
def _remove_deleted(self):
320
"""Remove deleted files from the working inventories.
322
This is done prior to taking the working inventory as the
323
basis for the new committed inventory.
325
This returns true if any files
326
*that existed in the basis inventory* were deleted.
327
Files that were added and deleted
328
in the working copy don't matter.
330
specific = self.specific_files
332
for path, ie in self.work_inv.iter_entries():
333
if specific and not is_inside_any(specific, path):
335
if not self.work_tree.has_filename(path):
336
note('missing %s', path)
337
deleted_ids.append(ie.file_id)
339
for file_id in deleted_ids:
340
if file_id in self.work_inv:
341
del self.work_inv[file_id]
342
self.branch._write_inventory(self.work_inv)
345
def _find_entry_parents(self, file_id):
346
"""Return the text versions and hashes for all file parents.
348
Returned as a map from text version to inventory entry.
350
This is a map containing the file versions in all parents
351
revisions containing the file. If the file is new, the set
354
for inv in self.parent_invs:
357
assert ie.file_id == file_id
359
assert r[ie.revision] == ie
364
def _store_snapshot(self):
365
"""Pass over inventory and record a snapshot.
367
Entries get a new revision when they are modified in
368
any way, which includes a merge with a new set of
369
parents that have the same entry. Currently we do not
370
check for that set being ancestors of each other - and
371
we should - only parallel children should count for this
372
test see find_entry_parents to correct this. FIXME <---
373
I.e. if we are merging in revision FOO, and our
374
copy of file id BAR is identical to FOO.BAR, we should
375
generate a new revision of BAR IF and only IF FOO is
376
neither a child of our current tip, nor an ancestor of
377
our tip. The presence of FOO in our store should not
378
affect this logic UNLESS we are doing a merge of FOO,
381
# XXX: Need to think more here about when the user has
382
# made a specific decision on a particular value -- c.f.
384
for path, ie in self.new_inv.iter_entries():
385
previous_entries = self._find_entry_parents(ie. file_id)
386
if ie.revision is None:
387
change = ie.snapshot(self.rev_id, path, previous_entries,
388
self.work_tree, self.weave_store)
391
note("%s %s", change, path)
393
def _populate_new_inv(self):
394
"""Build revision inventory.
396
This creates a new empty inventory. Depending on
397
which files are selected for commit, and what is present in the
398
current tree, the new inventory is populated. inventory entries
399
which are candidates for modification have their revision set to
400
None; inventory entries that are carried over untouched have their
401
revision set to their prior value.
403
mutter("Selecting files for commit with filter %s", self.specific_files)
404
self.new_inv = Inventory()
405
for path, new_ie in self.work_inv.iter_entries():
406
file_id = new_ie.file_id
407
mutter('check %s {%s}', path, new_ie.file_id)
408
if self.specific_files:
409
if not is_inside_any(self.specific_files, path):
410
mutter('%s not selected for commit', path)
411
self._carry_file(file_id)
413
mutter('%s selected for commit', path)
418
def _carry_file(self, file_id):
419
"""Carry the file unchanged from the basis revision."""
420
if self.basis_inv.has_id(file_id):
421
self.new_inv.add(self.basis_inv[file_id].copy())
423
def _report_deletes(self):
424
for file_id in self.basis_inv:
425
if file_id not in self.new_inv:
426
note('deleted %s', self.basis_inv.id2path(file_id))
430
def _gen_revision_id(branch, when):
431
"""Return new revision-id."""
432
s = '%s-%s-' % (user_email(branch), compact_date(when))
433
s += hexlify(rand_bytes(8))
439
def merge_ancestry_lines(rev_id, ancestries):
440
"""Return merged ancestry lines.
442
rev_id -- id of the new revision
444
ancestries -- a sequence of ancestries for parent revisions,
445
as newline-terminated line lists.
447
if len(ancestries) == 0:
448
return [rev_id + '\n']
449
seen = set(ancestries[0])
450
ancs = ancestries[0][:]
451
for parent_ancestry in ancestries[1:]:
452
for line in parent_ancestry:
453
assert line[-1] == '\n'
added
removed
bzrlib/commit.py
