« back to all changes in this revision
Viewing changes to bzrlib/weave.py
- browse files at revision 885
- compare with another revision
- download diff
- download tarball
- view history from revision 885
- Committer: Martin Pool
- Date: 2005-07-11 03:40:02 UTC
- Revision ID: mbp@sourcefrog.net-20050711034002-575d84b4c7514542
- commit command refuses unless something is changed or --unchanged is given
- files added:
- bzrlib/meta_store.py
- plugins/changeset
- files removed:
- HACKING
- bzrlib/store
- bzrlib/transport
- bzrlib/util
- contrib/emacs
- files renamed:
- contrib/newinventory.py => bzrlib/newinventory.py
- bzrlib/store/__init__.py => bzrlib/store.py
- bzrlib/util/effbot/ => effbot/
- bzrlib/util/elementtree/ => elementtree/
- bzrlib/plugins/ => plugins/
- bzrlib/selftest/test_weave.py => tools/testweave.py
- bzrlib/util/urlgrabber/ => urlgrabber/
- files modified:
- .bzrignore
added
removed
bzrlib/weave.py
21
21
22
22
"""Weave - storage of related text file versions"""
23
23
24
# TODO: Perhaps have copy method for Weave instances?
24
25
25
26
# XXX: If we do weaves this way, will a merge still behave the same
26
27
# way if it's done in a different order? That's a pretty desirable
27
28
# property.
28
29
30
# TODO: How to write these to disk? One option is cPickle, which
31
# would be fast but less friendly to C, and perhaps not portable. Another is
32
29
33
# TODO: Nothing here so far assumes the lines are really \n newlines,
30
34
# rather than being split up in some other way. We could accomodate
31
35
# binaries, perhaps by naively splitting on \n or perhaps using
32
36
# something like a rolling checksum.
33
37
38
# TODO: Perhaps track SHA-1 in the header for protection? This would
39
# be redundant with it being stored in the inventory, but perhaps
40
# usefully so?
41
42
# TODO: Track version names as well as indexes.
43
44
# TODO: Probably do transitive expansion when specifying parents?
45
46
# TODO: Separate out some code to read and write weaves.
47
34
48
# TODO: End marker for each version so we can stop reading?
35
49
36
50
# TODO: Check that no insertion occurs inside a deletion that was
37
51
# active in the version of the insertion.
38
52
39
# TODO: In addition to the SHA-1 check, perhaps have some code that
40
# checks structural constraints of the weave: ie that insertions are
41
# properly nested, that there is no text outside of an insertion, that
42
# insertions or deletions are not repeated, etc.
43
44
# TODO: Parallel-extract that passes back each line along with a
45
# description of which revisions include it. Nice for checking all
46
# shas or calculating stats in parallel.
47
48
# TODO: Using a single _extract routine and then processing the output
49
# is probably inefficient. It's simple enough that we can afford to
50
# have slight specializations for different ways its used: annotate,
51
# basis for add, get, etc.
52
53
# TODO: Perhaps the API should work only in names to hide the integer
54
# indexes from the user?
55
56
# TODO: Is there any potential performance win by having an add()
57
# variant that is passed a pre-cooked version of the single basis
58
# version?
59
60
# TODO: Have a way to go back and insert a revision V1 that is a parent
61
# of an already-stored revision V2. This means some lines previously
62
# counted as new in V2 will be discovered to have actually come from V1.
63
# It is probably necessary to insert V1, then compute a whole new diff
64
# from the mashed ancestors to V2. This must be repeated for every
65
# direct child of V1. The deltas from V2 to its descendents won't change,
66
# although their location within the weave may change. It may be possible
67
# to just adjust the location of those instructions rather than
68
# re-weaving the whole thing. This is expected to be a fairly rare
69
# operation, only used when inserting data that was previously a ghost.
70
71
72
73
74
import sha
75
from difflib import SequenceMatcher
76
77
53
# TODO: Perhaps a special slower check() method that verifies more
54
# nesting constraints and the MD5 of each version?
55
56
57
58
try:
59
set
60
frozenset
61
except NameError:
62
from sets import Set, ImmutableSet
63
set = Set
64
frozenset = ImmutableSet
65
del Set, ImmutableSet
78
66
79
67
80
68
class WeaveError(Exception):
106
94
the version-id is used to reference it in the larger world.
107
95
108
96
The weave is represented as a list mixing edit instructions and
109
literal text. Each entry in _weave can be either a string (or
97
literal text. Each entry in _l can be either a string (or
110
98
unicode), or a tuple. If a string, it means that the given line
111
99
should be output in the currently active revisions.
112
100
117
105
The instruction can be '{' or '}' for an insertion block, and '['
118
106
and ']' for a deletion block respectively. The version is the
119
107
integer version index. There is no replace operator, only deletes
120
and inserts. For '}', the end of an insertion, there is no
121
version parameter because it always closes the most recently
122
opened insertion.
108
and inserts.
123
109
124
110
Constraints/notes:
125
111
152
138
should be no way to get an earlier version deleting a later
153
139
version.
154
140
155
_weave
156
Text of the weave; list of control instruction tuples and strings.
157
158
_parents
159
List of parents, indexed by version number.
160
It is only necessary to store the minimal set of parents for
161
each version; the parent's parents are implied.
141
_l
142
Text of the weave.
143
144
_v
145
List of versions, indexed by index number.
146
147
For each version we store the set (included_versions), which
148
lists the previous versions also considered active; the
149
versions included in those versions are included transitively.
150
So new versions created from nothing list []; most versions
151
have a single entry; some have more.
162
152
163
153
_sha1s
164
List of hex SHA-1 of each version.
165
166
_names
167
List of symbolic names for each version. Each should be unique.
168
169
_name_map
170
For each name, the version number.
171
172
_weave_name
173
Descriptive name of this weave; typically the filename if known.
174
Set by read_weave.
154
List of hex SHA-1 of each version, or None if not recorded.
175
155
"""
176
177
__slots__ = ['_weave', '_parents', '_sha1s', '_names', '_name_map',
178
'_weave_name']
179
180
def __init__(self, weave_name=None):
181
self._weave = []
182
self._parents = []
156
def __init__(self):
157
self._l = []
158
self._v = []
183
159
self._sha1s = []
184
self._names = []
185
self._name_map = {}
186
self._weave_name = weave_name
187
188
189
def copy(self):
190
"""Return a deep copy of self.
191
192
The copy can be modified without affecting the original weave."""
193
other = Weave()
194
other._weave = self._weave[:]
195
other._parents = self._parents[:]
196
other._sha1s = self._sha1s[:]
197
other._names = self._names[:]
198
other._name_map = self._name_map.copy()
199
other._weave_name = self._weave_name
200
return other
160
201
161
202
162
def __eq__(self, other):
203
163
if not isinstance(other, Weave):
204
164
return False
205
return self._parents == other._parents \
206
and self._weave == other._weave \
207
and self._sha1s == other._sha1s
165
return self._v == other._v \
166
and self._l == other._l
167
208
168
209
210
169
def __ne__(self, other):
211
170
return not self.__eq__(other)
212
171
213
214
def maybe_lookup(self, name_or_index):
215
"""Convert possible symbolic name to index, or pass through indexes."""
216
if isinstance(name_or_index, (int, long)):
217
return name_or_index
218
else:
219
return self.lookup(name_or_index)
220
221
222
def lookup(self, name):
223
"""Convert symbolic version name to index."""
224
try:
225
return self._name_map[name]
226
except KeyError:
227
raise WeaveError("name %r not present in weave %r" %
228
(name, self._weave_name))
229
230
231
def iter_names(self):
232
"""Yield a list of all names in this weave."""
233
return iter(self._names)
234
235
def idx_to_name(self, version):
236
return self._names[version]
237
238
239
def _check_repeated_add(self, name, parents, text, sha1):
240
"""Check that a duplicated add is OK.
241
242
If it is, return the (old) index; otherwise raise an exception.
243
"""
244
idx = self.lookup(name)
245
if sorted(self._parents[idx]) != sorted(parents):
246
raise WeaveError("name \"%s\" already present in weave "
247
"with different parents" % name)
248
if sha1 != self._sha1s[idx]:
249
raise WeaveError("name \"%s\" already present in weave "
250
"with different text" % name)
251
return idx
252
253
254
255
def add(self, name, parents, text, sha1=None):
172
173
def add(self, parents, text):
256
174
"""Add a single text on top of the weave.
257
175
258
176
Returns the index number of the newly added version.
259
177
260
name
261
Symbolic name for this version.
262
(Typically the revision-id of the revision that added it.)
263
264
178
parents
265
List or set of direct parent version numbers.
266
179
List or set of parent version numbers. This must normally include
180
the parents and the parent's parents, or wierd things might happen.
181
267
182
text
268
Sequence of lines to be added in the new version.
269
270
sha -- SHA-1 of the file, if known. This is trusted to be
271
correct if supplied.
272
"""
273
from bzrlib.osutils import sha_strings
274
275
assert isinstance(name, basestring)
276
if sha1 is None:
277
sha1 = sha_strings(text)
278
if name in self._name_map:
279
return self._check_repeated_add(name, parents, text, sha1)
280
281
parents = map(self.maybe_lookup, parents)
282
self._check_versions(parents)
183
Sequence of lines to be added in the new version."""
184
## self._check_versions(parents)
283
185
## self._check_lines(text)
284
new_version = len(self._parents)
285
286
287
# if we abort after here the (in-memory) weave will be corrupt because only
288
# some fields are updated
289
self._parents.append(parents[:])
186
idx = len(self._v)
187
188
import sha
189
s = sha.new()
190
for l in text:
191
s.update(l)
192
sha1 = s.hexdigest()
193
del s
194
195
if parents:
196
delta = self._delta(self.inclusions(parents), text)
197
198
# offset gives the number of lines that have been inserted
199
# into the weave up to the current point; if the original edit instruction
200
# says to change line A then we actually change (A+offset)
201
offset = 0
202
203
for i1, i2, newlines in delta:
204
assert 0 <= i1
205
assert i1 <= i2
206
assert i2 <= len(self._l)
207
208
# the deletion and insertion are handled separately.
209
# first delete the region.
210
if i1 != i2:
211
self._l.insert(i1+offset, ('[', idx))
212
self._l.insert(i2+offset+1, (']', idx))
213
offset += 2
214
# is this OK???
215
216
if newlines:
217
# there may have been a deletion spanning up to
218
# i2; we want to insert after this region to make sure
219
# we don't destroy ourselves
220
i = i2 + offset
221
self._l[i:i] = [('{', idx)] \
222
+ newlines \
223
+ [('}', idx)]
224
offset += 2 + len(newlines)
225
226
self._addversion(parents)
227
else:
228
# special case; adding with no parents revision; can do this
229
# more quickly by just appending unconditionally
230
self._l.append(('{', idx))
231
self._l += text
232
self._l.append(('}', idx))
233
234
self._addversion(None)
235
290
236
self._sha1s.append(sha1)
291
self._names.append(name)
292
self._name_map[name] = new_version
293
294
295
if not parents:
296
# special case; adding with no parents revision; can do
297
# this more quickly by just appending unconditionally.
298
# even more specially, if we're adding an empty text we
299
# need do nothing at all.
300
if text:
301
self._weave.append(('{', new_version))
302
self._weave.extend(text)
303
self._weave.append(('}', None))
304
305
return new_version
306
307
if len(parents) == 1:
308
pv = list(parents)[0]
309
if sha1 == self._sha1s[pv]:
310
# special case: same as the single parent
311
return new_version
312
313
314
ancestors = self.inclusions(parents)
315
316
l = self._weave
317
318
# basis a list of (origin, lineno, line)
319
basis_lineno = []
320
basis_lines = []
321
for origin, lineno, line in self._extract(ancestors):
322
basis_lineno.append(lineno)
323
basis_lines.append(line)
324
325
# another small special case: a merge, producing the same text
326
# as auto-merge
327
if text == basis_lines:
328
return new_version
329
330
# add a sentinal, because we can also match against the final line
331
basis_lineno.append(len(self._weave))
332
333
# XXX: which line of the weave should we really consider
334
# matches the end of the file? the current code says it's the
335
# last line of the weave?
336
337
#print 'basis_lines:', basis_lines
338
#print 'new_lines: ', lines
339
340
s = SequenceMatcher(None, basis_lines, text)
341
342
# offset gives the number of lines that have been inserted
343
# into the weave up to the current point; if the original edit instruction
344
# says to change line A then we actually change (A+offset)
345
offset = 0
346
347
for tag, i1, i2, j1, j2 in s.get_opcodes():
348
# i1,i2 are given in offsets within basis_lines; we need to map them
349
# back to offsets within the entire weave
350
#print 'raw match', tag, i1, i2, j1, j2
351
if tag == 'equal':
352
continue
353
354
i1 = basis_lineno[i1]
355
i2 = basis_lineno[i2]
356
357
assert 0 <= j1 <= j2 <= len(text)
358
359
#print tag, i1, i2, j1, j2
360
361
# the deletion and insertion are handled separately.
362
# first delete the region.
363
if i1 != i2:
364
self._weave.insert(i1+offset, ('[', new_version))
365
self._weave.insert(i2+offset+1, (']', new_version))
366
offset += 2
367
368
if j1 != j2:
369
# there may have been a deletion spanning up to
370
# i2; we want to insert after this region to make sure
371
# we don't destroy ourselves
372
i = i2 + offset
373
self._weave[i:i] = ([('{', new_version)]
374
+ text[j1:j2]
375
+ [('}', None)])
376
offset += 2 + (j2 - j1)
377
378
return new_version
379
380
def add_identical(self, old_rev_id, new_rev_id, parents):
381
"""Add an identical text to old_rev_id as new_rev_id."""
382
old_lines = self.get(self.lookup(old_rev_id))
383
self.add(new_rev_id, parents, old_lines)
237
238
return idx
239
384
240
385
241
def inclusions(self, versions):
386
"""Return set of all ancestors of given version(s)."""
242
"""Expand out everything included by versions."""
387
243
i = set(versions)
388
for v in xrange(max(versions), 0, -1):
389
if v in i:
390
# include all its parents
391
i.update(self._parents[v])
244
for v in versions:
245
try:
246
i.update(self._v[v])
247
except IndexError:
248
raise ValueError("version %d not present in weave" % v)
392
249
return i
393
## except IndexError:
394
## raise ValueError("version %d not present in weave" % v)
395
396
397
def parents(self, version):
398
return self._parents[version]
399
400
401
def minimal_parents(self, version):
402
"""Find the minimal set of parents for the version."""
403
included = self._parents[version]
404
if not included:
405
return []
406
407
li = list(included)
408
li.sort(reverse=True)
409
410
mininc = []
411
gotit = set()
412
413
for pv in li:
414
if pv not in gotit:
415
mininc.append(pv)
416
gotit.update(self.inclusions(pv))
417
418
assert mininc[0] >= 0
419
assert mininc[-1] < version
420
return mininc
421
250
251
252
def _addversion(self, parents):
253
if parents:
254
self._v.append(frozenset(parents))
255
else:
256
self._v.append(frozenset())
422
257
423
258
424
259
def _check_lines(self, text):
436
271
"""Check everything in the sequence of indexes is valid"""
437
272
for i in indexes:
438
273
try:
439
self._parents[i]
274
self._v[i]
440
275
except IndexError:
441
276
raise IndexError("invalid version number %r" % i)
442
277
443
278
444
def annotate(self, name_or_index):
445
return list(self.annotate_iter(name_or_index))
446
447
448
def annotate_iter(self, name_or_index):
279
def annotate(self, index):
280
return list(self.annotate_iter(index))
281
282
283
def annotate_iter(self, version):
449
284
"""Yield list of (index-id, line) pairs for the specified version.
450
285
451
286
The index indicates when the line originated in the weave."""
452
incls = [self.maybe_lookup(name_or_index)]
453
for origin, lineno, text in self._extract(incls):
287
included = self.inclusions([version])
288
for origin, lineno, text in self._extract(included):
454
289
yield origin, text
455
290
456
291
457
def _walk(self):
458
"""Walk the weave.
459
460
Yields sequence of
461
(lineno, insert, deletes, text)
462
for each literal line.
463
"""
464
465
istack = []
466
dset = set()
467
468
lineno = 0 # line of weave, 0-based
469
470
for l in self._weave:
471
if isinstance(l, tuple):
472
c, v = l
473
isactive = None
474
if c == '{':
475
istack.append(v)
476
elif c == '}':
477
istack.pop()
478
elif c == '[':
479
assert v not in dset
480
dset.add(v)
481
elif c == ']':
482
dset.remove(v)
483
else:
484
raise WeaveFormatError('unexpected instruction %r'
485
% v)
486
else:
487
assert isinstance(l, basestring)
488
assert istack
489
yield lineno, istack[-1], dset, l
490
lineno += 1
491
492
493
494
def _extract(self, versions):
292
def _extract(self, included):
495
293
"""Yield annotation of lines in included set.
496
294
497
295
Yields a sequence of tuples (origin, lineno, text), where
500
298
501
299
The set typically but not necessarily corresponds to a version.
502
300
"""
503
for i in versions:
504
if not isinstance(i, int):
505
raise ValueError(i)
506
507
included = self.inclusions(versions)
508
301
509
302
istack = []
510
303
dset = set()
511
304
512
305
lineno = 0 # line of weave, 0-based
513
514
isactive = None
515
516
result = []
306
isactive = False
517
307
518
308
WFE = WeaveFormatError
519
309
520
for l in self._weave:
310
for l in self._l:
521
311
if isinstance(l, tuple):
522
312
c, v = l
523
isactive = None
524
if c == '{':
525
assert v not in istack
526
istack.append(v)
527
elif c == '}':
528
istack.pop()
529
elif c == '[':
530
if v in included:
313
if v in included: # only active blocks are interesting
314
if c == '{':
315
assert v not in istack
316
istack.append(v)
317
isactive = not dset
318
elif c == '}':
319
oldv = istack.pop()
320
assert oldv == v
321
isactive = istack and not dset
322
elif c == '[':
531
323
assert v not in dset
532
324
dset.add(v)
533
else:
534
assert c == ']'
535
if v in included:
325
isactive = False
326
else:
327
assert c == ']'
536
328
assert v in dset
537
329
dset.remove(v)
330
isactive = istack and not dset
538
331
else:
539
332
assert isinstance(l, basestring)
540
if isactive is None:
541
isactive = (not dset) and istack and (istack[-1] in included)
542
333
if isactive:
543
result.append((istack[-1], lineno, l))
334
yield origin, lineno, l
544
335
lineno += 1
545
336
546
337
if istack:
550
341
raise WFE("unclosed deletion blocks at end of weave",
551
342
dset)
552
343
553
return result
554
555
556
557
def get_iter(self, name_or_index):
344
345
def get_iter(self, version):
558
346
"""Yield lines for the specified version."""
559
incls = [self.maybe_lookup(name_or_index)]
560
for origin, lineno, line in self._extract(incls):
347
for origin, lineno, line in self._extract(self.inclusions([version])):
561
348
yield line
562
349
563
350
564
def get_text(self, name_or_index):
565
return ''.join(self.get_iter(name_or_index))
566
assert isinstance(version, int)
567
568
569
def get_lines(self, name_or_index):
570
return list(self.get_iter(name_or_index))
571
572
573
get = get_lines
351
def get(self, index):
352
return list(self.get_iter(index))
574
353
575
354
576
355
def mash_iter(self, included):
577
356
"""Return composed version of multiple included versions."""
578
included = map(self.maybe_lookup, included)
357
included = frozenset(included)
579
358
for origin, lineno, text in self._extract(included):
580
359
yield text
581
360
582
361
583
362
def dump(self, to_file):
584
363
from pprint import pprint
585
print >>to_file, "Weave._weave = ",
586
pprint(self._weave, to_file)
587
print >>to_file, "Weave._parents = ",
588
pprint(self._parents, to_file)
364
print >>to_file, "Weave._l = ",
365
pprint(self._l, to_file)
366
print >>to_file, "Weave._v = ",
367
pprint(self._v, to_file)
589
368
590
369
591
370
592
371
def numversions(self):
593
l = len(self._parents)
372
l = len(self._v)
594
373
assert l == len(self._sha1s)
595
374
return l
596
375
597
376
598
def __len__(self):
599
return self.numversions()
600
601
602
def check(self, progress_bar=None):
377
def check(self):
603
378
# check no circular inclusions
604
379
for version in range(self.numversions()):
605
inclusions = list(self._parents[version])
380
inclusions = list(self._v[version])
606
381
if inclusions:
607
382
inclusions.sort()
608
383
if inclusions[-1] >= version:
611
386
612
387
# try extracting all versions; this is a bit slow and parallel
613
388
# extraction could be used
614
nv = self.numversions()
615
for version in range(nv):
616
if progress_bar:
617
progress_bar.update('checking text', version, nv)
389
import sha
390
for version in range(self.numversions()):
618
391
s = sha.new()
619
392
for l in self.get_iter(version):
620
393
s.update(l)
641
414
If there is a chunk of the file where there's no diagreement,
642
415
only one alternative is given.
643
416
"""
417
644
418
# approach: find the included versions common to all the
645
419
# merged versions
646
420
raise NotImplementedError()
666
440
If line1=line2, this is a pure insert; if newlines=[] this is a
667
441
pure delete. (Similar to difflib.)
668
442
"""
669
raise NotImplementedError()
670
671
672
def plan_merge(self, ver_a, ver_b):
673
"""Return pseudo-annotation indicating how the two versions merge.
674
675
This is computed between versions a and b and their common
676
base.
677
678
Weave lines present in none of them are skipped entirely.
679
"""
680
inc_a = self.inclusions([ver_a])
681
inc_b = self.inclusions([ver_b])
682
inc_c = inc_a & inc_b
683
684
for lineno, insert, deleteset, line in self._walk():
685
if deleteset & inc_c:
686
# killed in parent; can't be in either a or b
687
# not relevant to our work
688
yield 'killed-base', line
689
elif insert in inc_c:
690
# was inserted in base
691
killed_a = bool(deleteset & inc_a)
692
killed_b = bool(deleteset & inc_b)
693
if killed_a and killed_b:
694
yield 'killed-both', line
695
elif killed_a:
696
yield 'killed-a', line
697
elif killed_b:
698
yield 'killed-b', line
699
else:
700
yield 'unchanged', line
701
elif insert in inc_a:
702
if deleteset & inc_a:
703
yield 'ghost-a', line
704
else:
705
# new in A; not in B
706
yield 'new-a', line
707
elif insert in inc_b:
708
if deleteset & inc_b:
709
yield 'ghost-b', line
710
else:
711
yield 'new-b', line
712
else:
713
# not in either revision
714
yield 'irrelevant', line
715
716
yield 'unchanged', '' # terminator
717
718
719
720
def weave_merge(self, plan):
721
lines_a = []
722
lines_b = []
723
ch_a = ch_b = False
724
725
for state, line in plan:
726
if state == 'unchanged' or state == 'killed-both':
727
# resync and flush queued conflicts changes if any
728
if not lines_a and not lines_b:
729
pass
730
elif ch_a and not ch_b:
731
# one-sided change:
732
for l in lines_a: yield l
733
elif ch_b and not ch_a:
734
for l in lines_b: yield l
735
elif lines_a == lines_b:
736
for l in lines_a: yield l
737
else:
738
yield '<<<<\n'
739
for l in lines_a: yield l
740
yield '====\n'
741
for l in lines_b: yield l
742
yield '>>>>\n'
743
744
del lines_a[:]
745
del lines_b[:]
746
ch_a = ch_b = False
747
748
if state == 'unchanged':
749
if line:
750
yield line
751
elif state == 'killed-a':
752
ch_a = True
753
lines_b.append(line)
754
elif state == 'killed-b':
755
ch_b = True
756
lines_a.append(line)
757
elif state == 'new-a':
758
ch_a = True
759
lines_a.append(line)
760
elif state == 'new-b':
761
ch_b = True
762
lines_b.append(line)
763
else:
764
assert state in ('irrelevant', 'ghost-a', 'ghost-b', 'killed-base',
765
'killed-both'), \
766
state
767
768
769
def join(self, other):
770
"""Integrate versions from other into this weave.
771
772
The resulting weave contains all the history of both weaves;
773
any version you could retrieve from either self or other can be
774
retrieved from self after this call.
775
776
It is illegal for the two weaves to contain different values
777
for any version.
778
"""
779
if other.numversions() == 0:
780
return # nothing to update, easy
781
# work through in index order to make sure we get all dependencies
782
for other_idx, name in enumerate(other._names):
783
# TODO: If all the parents of the other version are already
784
# present then we can avoid some work by just taking the delta
785
# and adjusting the offsets.
786
if self._check_version_consistent(other, other_idx, name):
443
# basis a list of (origin, lineno, line)
444
basis_lineno = []
445
basis_lines = []
446
for origin, lineno, line in self._extract(included):
447
basis_lineno.append(lineno)
448
basis_lines.append(line)
449
450
# add a sentinal, because we can also match against the final line
451
basis_lineno.append(len(self._l))
452
453
# XXX: which line of the weave should we really consider
454
# matches the end of the file? the current code says it's the
455
# last line of the weave?
456
457
from difflib import SequenceMatcher
458
s = SequenceMatcher(None, basis_lines, lines)
459
460
# TODO: Perhaps return line numbers from composed weave as well?
461
462
for tag, i1, i2, j1, j2 in s.get_opcodes():
463
##print tag, i1, i2, j1, j2
464
465
if tag == 'equal':
787
466
continue
788
new_parents = self._imported_parents(other, other_idx)
789
lines = other.get_lines(other_idx)
790
sha1 = other._sha1s[other_idx]
791
self.add(name, new_parents, lines, sha1)
792
793
794
def _imported_parents(self, other, other_idx):
795
"""Return list of parents in self corresponding to indexes in other."""
796
new_parents = []
797
for parent_idx in other._parents[other_idx]:
798
parent_name = other._names[parent_idx]
799
if parent_name not in self._names:
800
# should not be possible
801
raise WeaveError("missing parent {%s} of {%s} in %r"
802
% (parent_name, other._name_map[other_idx], self))
803
new_parents.append(self._name_map[parent_name])
804
return new_parents
805
806
def _check_version_consistent(self, other, other_idx, name):
807
"""Check if a version in consistent in this and other.
808
809
To be consistent it must have:
810
811
* the same text
812
* the same direct parents (by name, not index, and disregarding
813
order)
814
815
If present & correct return True;
816
if not present in self return False;
817
if inconsistent raise error."""
818
this_idx = self._name_map.get(name, -1)
819
if this_idx != -1:
820
if self._sha1s[this_idx] != other._sha1s[other_idx]:
821
raise WeaveError("inconsistent texts for version {%s} "
822
"when joining weaves"
823
% (name))
824
self_parents = self._parents[this_idx]
825
other_parents = other._parents[other_idx]
826
n1 = [self._names[i] for i in self_parents]
827
n2 = [other._names[i] for i in other_parents]
828
n1.sort()
829
n2.sort()
830
if n1 != n2:
831
raise WeaveError("inconsistent parents for version {%s}: "
832
"%s vs %s"
833
% (name, n1, n2))
834
else:
835
return True # ok!
836
else:
837
return False
838
839
840
def weave_toc(w):
841
"""Show the weave's table-of-contents"""
842
print '%6s %50s %10s %10s' % ('ver', 'name', 'sha1', 'parents')
843
for i in (6, 50, 10, 10):
844
print '-' * i,
845
print
846
for i in range(w.numversions()):
847
sha1 = w._sha1s[i]
848
name = w._names[i]
849
parent_str = ' '.join(map(str, w._parents[i]))
850
print '%6d %-50.50s %10.10s %s' % (i, name, sha1, parent_str)
851
852
853
854
def weave_stats(weave_file, pb):
855
from bzrlib.weavefile import read_weave
856
857
wf = file(weave_file, 'rb')
467
468
# i1,i2 are given in offsets within basis_lines; we need to map them
469
# back to offsets within the entire weave
470
real_i1 = basis_lineno[i1]
471
real_i2 = basis_lineno[i2]
472
473
assert 0 <= j1
474
assert j1 <= j2
475
assert j2 <= len(lines)
476
477
yield real_i1, real_i2, lines[j1:j2]
478
479
480
481
def weave_info(filename, out):
482
"""Show some text information about the weave."""
483
from weavefile import read_weave
484
wf = file(filename, 'rb')
858
485
w = read_weave(wf)
859
486
# FIXME: doesn't work on pipes
860
487
weave_size = wf.tell()
488
print >>out, "weave file size %d bytes" % weave_size
489
print >>out, "weave contains %d versions" % len(w._v)
861
490
862
491
total = 0
863
vers = len(w)
864
for i in range(vers):
865
pb.update('checking sizes', i, vers)
866
for origin, lineno, line in w._extract([i]):
867
total += len(line)
868
869
pb.clear()
870
871
print 'versions %9d' % vers
872
print 'weave file %9d bytes' % weave_size
873
print 'total contents %9d bytes' % total
874
print 'compression ratio %9.2fx' % (float(total) / float(weave_size))
875
if vers:
876
avg = total/vers
877
print 'average size %9d bytes' % avg
878
print 'relative size %9.2fx' % (float(weave_size) / float(avg))
492
print '%6s %6s %8s %40s %20s' % ('ver', 'lines', 'bytes', 'sha1', 'parents')
493
for i in (6, 6, 8, 40, 20):
494
print '-' * i,
495
print
496
for i in range(len(w._v)):
497
text = w.get(i)
498
lines = len(text)
499
bytes = sum((len(a) for a in text))
500
sha1 = w._sha1s[i]
501
print '%6d %6d %8d %40s' % (i, lines, bytes, sha1),
502
print ', '.join(map(str, w._v[i]))
503
total += bytes
504
505
print >>out, "versions total %d bytes" % total
506
print >>out, "compression ratio %.3f" % (float(total)/float(weave_size))
879
507
880
508
881
509
def usage():
890
518
Write out specified version.
891
519
weave check WEAVEFILE
892
520
Check consistency of all versions.
893
weave toc WEAVEFILE
521
weave info WEAVEFILE
894
522
Display table of contents.
895
weave add WEAVEFILE NAME [BASE...] < NEWTEXT
523
weave add WEAVEFILE [BASE...] < NEWTEXT
896
524
Add NEWTEXT, with specified parent versions.
897
525
weave annotate WEAVEFILE VERSION
898
526
Display origin of each line.
900
528
Display composite of all selected versions.
901
529
weave merge WEAVEFILE VERSION1 VERSION2 > OUT
902
530
Auto-merge two versions and display conflicts.
903
weave diff WEAVEFILE VERSION1 VERSION2
904
Show differences between two versions.
905
531
906
532
example:
907
533
908
534
% weave init foo.weave
909
535
% vi foo.txt
910
% weave add foo.weave ver0 < foo.txt
536
% weave add foo.weave < foo.txt
911
537
added version 0
912
538
913
539
(create updated version)
914
540
% vi foo.txt
915
541
% weave get foo.weave 0 | diff -u - foo.txt
916
% weave add foo.weave ver1 0 < foo.txt
542
% weave add foo.weave 0 < foo.txt
917
543
added version 1
918
544
919
545
% weave get foo.weave 0 > foo.txt (create forked version)
920
546
% vi foo.txt
921
% weave add foo.weave ver2 0 < foo.txt
547
% weave add foo.weave 0 < foo.txt
922
548
added version 2
923
549
924
550
% weave merge foo.weave 1 2 > foo.txt (merge them)
925
551
% vi foo.txt (resolve conflicts)
926
% weave add foo.weave merged 1 2 < foo.txt (commit merged version)
552
% weave add foo.weave 1 2 < foo.txt (commit merged version)
927
553
928
554
"""
929
555
932
558
def main(argv):
933
559
import sys
934
560
import os
935
try:
936
import bzrlib
937
except ImportError:
938
# in case we're run directly from the subdirectory
939
sys.path.append('..')
940
import bzrlib
941
from bzrlib.weavefile import write_weave, read_weave
942
from bzrlib.progress import ProgressBar
943
944
try:
945
import psyco
946
psyco.full()
947
except ImportError:
948
pass
949
950
if len(argv) < 2:
951
usage()
952
return 0
953
561
from weavefile import write_weave, read_weave
954
562
cmd = argv[1]
955
563
956
564
def readit():
961
569
elif cmd == 'add':
962
570
w = readit()
963
571
# at the moment, based on everything in the file
964
name = argv[3]
965
parents = map(int, argv[4:])
572
parents = map(int, argv[3:])
966
573
lines = sys.stdin.readlines()
967
ver = w.add(name, parents, lines)
574
ver = w.add(parents, lines)
968
575
write_weave(w, file(argv[2], 'wb'))
969
print 'added version %r %d' % (name, ver)
576
print 'added version %d' % ver
970
577
elif cmd == 'init':
971
578
fn = argv[2]
972
579
if os.path.exists(fn):
981
588
w = readit()
982
589
sys.stdout.writelines(w.mash_iter(map(int, argv[3:])))
983
590
984
elif cmd == 'diff':
985
from difflib import unified_diff
986
w = readit()
987
fn = argv[2]
988
v1, v2 = map(int, argv[3:5])
989
lines1 = w.get(v1)
990
lines2 = w.get(v2)
991
diff_gen = unified_diff(lines1, lines2,
992
'%s version %d' % (fn, v1),
993
'%s version %d' % (fn, v2))
994
sys.stdout.writelines(diff_gen)
995
996
591
elif cmd == 'annotate':
997
592
w = readit()
998
593
# newline is added to all lines regardless; too hard to get
1006
601
print '%5d | %s' % (origin, text)
1007
602
lasto = origin
1008
603
1009
elif cmd == 'toc':
1010
weave_toc(readit())
1011
1012
elif cmd == 'stats':
1013
weave_stats(argv[2], ProgressBar())
604
elif cmd == 'info':
605
weave_info(argv[2], sys.stdout)
1014
606
1015
607
elif cmd == 'check':
1016
608
w = readit()
1017
pb = ProgressBar()
1018
w.check(pb)
1019
pb.clear()
1020
print '%d versions ok' % w.numversions()
1021
1022
elif cmd == 'inclusions':
1023
w = readit()
1024
print ' '.join(map(str, w.inclusions([int(argv[3])])))
1025
1026
elif cmd == 'parents':
1027
w = readit()
1028
print ' '.join(map(str, w._parents[int(argv[3])]))
1029
1030
elif cmd == 'plan-merge':
1031
w = readit()
1032
for state, line in w.plan_merge(int(argv[3]), int(argv[4])):
1033
if line:
1034
print '%14s | %s' % (state, line),
609
w.check()
1035
610
1036
611
elif cmd == 'merge':
1037
w = readit()
1038
p = w.plan_merge(int(argv[3]), int(argv[4]))
1039
sys.stdout.writelines(w.weave_merge(p))
1040
1041
elif cmd == 'mash-merge':
1042
612
if len(argv) != 5:
1043
613
usage()
1044
614
return 1
1062
632
raise ValueError('unknown command %r' % cmd)
1063
633
1064
634
1065
1066
def profile_main(argv):
1067
import tempfile, hotshot, hotshot.stats
1068
1069
prof_f = tempfile.NamedTemporaryFile()
1070
1071
prof = hotshot.Profile(prof_f.name)
1072
1073
ret = prof.runcall(main, argv)
1074
prof.close()
1075
1076
stats = hotshot.stats.load(prof_f.name)
1077
#stats.strip_dirs()
1078
stats.sort_stats('cumulative')
1079
## XXX: Might like to write to stderr or the trace file instead but
1080
## print_stats seems hardcoded to stdout
1081
stats.print_stats(20)
1082
1083
return ret
1084
1085
1086
635
if __name__ == '__main__':
1087
636
import sys
1088
if '--profile' in sys.argv:
1089
args = sys.argv[:]
1090
args.remove('--profile')
1091
sys.exit(profile_main(args))
1092
else:
1093
sys.exit(main(sys.argv))
1094
637
sys.exit(main(sys.argv))
Loggerhead is a web-based interface for Breezy
Version: 2.0.1