« back to all changes in this revision
Viewing changes to bzrlib/weave.py
- browse files at revision 1418
- compare with another revision
- download diff
- download tarball
- view history from revision 1418
- Committer: Robert Collins
- Date: 2005-10-06 12:14:01 UTC
- mfrom: (1393.1.67)
- Revision ID: robertc@robertcollins.net-20051006121401-ce87bcb93909bbdf
merge martins latest
- files added:
- HACKING
- bzrlib/plugins
- bzrlib/selftest
- bzrlib/store
- bzrlib/transport
- bzrlib/util
- bzrlib/util/effbot
- bzrlib/util/effbot/org
- contrib/emacs
- patches
- tools
- files removed:
- bzrlib/remotebranch.py
- files renamed:
- bzrlib/store.py => bzrlib/store/__init__.py
- elementtree/ => bzrlib/util/elementtree/
- urlgrabber/ => bzrlib/util/urlgrabber/
- contrib/bash/bzr => contrib/bash/bzr.simple
- bzrlib/newinventory.py => contrib/newinventory.py
- files modified:
- .bzrignore
added
removed
bzrlib/weave.py
1
#! /usr/bin/python
2
3
# Copyright (C) 2005 Canonical Ltd
4
5
# This program is free software; you can redistribute it and/or modify
6
# it under the terms of the GNU General Public License as published by
7
# the Free Software Foundation; either version 2 of the License, or
8
# (at your option) any later version.
9
10
# This program is distributed in the hope that it will be useful,
11
# but WITHOUT ANY WARRANTY; without even the implied warranty of
12
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
13
# GNU General Public License for more details.
14
15
# You should have received a copy of the GNU General Public License
16
# along with this program; if not, write to the Free Software
17
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
18
19
# Author: Martin Pool <mbp@canonical.com>
20
21
22
"""Weave - storage of related text file versions"""
23
24
25
# XXX: If we do weaves this way, will a merge still behave the same
26
# way if it's done in a different order? That's a pretty desirable
27
# property.
28
29
# TODO: Nothing here so far assumes the lines are really \n newlines,
30
# rather than being split up in some other way. We could accomodate
31
# binaries, perhaps by naively splitting on \n or perhaps using
32
# something like a rolling checksum.
33
34
# TODO: End marker for each version so we can stop reading?
35
36
# TODO: Check that no insertion occurs inside a deletion that was
37
# active in the version of the insertion.
38
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
78
79
80
class WeaveError(Exception):
81
"""Exception in processing weave"""
82
83
84
class WeaveFormatError(WeaveError):
85
"""Weave invariant violated"""
86
87
88
class Weave(object):
89
"""weave - versioned text file storage.
90
91
A Weave manages versions of line-based text files, keeping track
92
of the originating version for each line.
93
94
To clients the "lines" of the file are represented as a list of strings.
95
These strings will typically have terminal newline characters, but
96
this is not required. In particular files commonly do not have a newline
97
at the end of the file.
98
99
Texts can be identified in either of two ways:
100
101
* a nonnegative index number.
102
103
* a version-id string.
104
105
Typically the index number will be valid only inside this weave and
106
the version-id is used to reference it in the larger world.
107
108
The weave is represented as a list mixing edit instructions and
109
literal text. Each entry in _weave can be either a string (or
110
unicode), or a tuple. If a string, it means that the given line
111
should be output in the currently active revisions.
112
113
If a tuple, it gives a processing instruction saying in which
114
revisions the enclosed lines are active. The tuple has the form
115
(instruction, version).
116
117
The instruction can be '{' or '}' for an insertion block, and '['
118
and ']' for a deletion block respectively. The version is the
119
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.
123
124
Constraints/notes:
125
126
* A later version can delete lines that were introduced by any
127
number of ancestor versions; this implies that deletion
128
instructions can span insertion blocks without regard to the
129
insertion block's nesting.
130
131
* Similarly, deletions need not be properly nested with regard to
132
each other, because they might have been generated by
133
independent revisions.
134
135
* Insertions are always made by inserting a new bracketed block
136
into a single point in the previous weave. This implies they
137
can nest but not overlap, and the nesting must always have later
138
insertions on the inside.
139
140
* It doesn't seem very useful to have an active insertion
141
inside an inactive insertion, but it might happen.
142
143
* Therefore, all instructions are always"considered"; that
144
is passed onto and off the stack. An outer inactive block
145
doesn't disable an inner block.
146
147
* Lines are enabled if the most recent enclosing insertion is
148
active and none of the enclosing deletions are active.
149
150
* There is no point having a deletion directly inside its own
151
insertion; you might as well just not write it. And there
152
should be no way to get an earlier version deleting a later
153
version.
154
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.
162
163
_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.
175
"""
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 = []
183
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
201
202
def __eq__(self, other):
203
if not isinstance(other, Weave):
204
return False
205
return self._parents == other._parents \
206
and self._weave == other._weave \
207
and self._sha1s == other._sha1s
208
209
210
def __ne__(self, other):
211
return not self.__eq__(other)
212
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):
256
"""Add a single text on top of the weave.
257
258
Returns the index number of the newly added version.
259
260
name
261
Symbolic name for this version.
262
(Typically the revision-id of the revision that added it.)
263
264
parents
265
List or set of direct parent version numbers.
266
267
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)
283
## 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[:])
290
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)
384
385
def inclusions(self, versions):
386
"""Return set of all ancestors of given version(s)."""
387
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])
392
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
422
423
424
def _check_lines(self, text):
425
if not isinstance(text, list):
426
raise ValueError("text should be a list, not %s" % type(text))
427
428
for l in text:
429
if not isinstance(l, basestring):
430
raise ValueError("text line should be a string or unicode, not %s"
431
% type(l))
432
433
434
435
def _check_versions(self, indexes):
436
"""Check everything in the sequence of indexes is valid"""
437
for i in indexes:
438
try:
439
self._parents[i]
440
except IndexError:
441
raise IndexError("invalid version number %r" % i)
442
443
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):
449
"""Yield list of (index-id, line) pairs for the specified version.
450
451
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):
454
yield origin, text
455
456
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):
495
"""Yield annotation of lines in included set.
496
497
Yields a sequence of tuples (origin, lineno, text), where
498
origin is the origin version, lineno the index in the weave,
499
and text the text of the line.
500
501
The set typically but not necessarily corresponds to a version.
502
"""
503
for i in versions:
504
if not isinstance(i, int):
505
raise ValueError(i)
506
507
included = self.inclusions(versions)
508
509
istack = []
510
dset = set()
511
512
lineno = 0 # line of weave, 0-based
513
514
isactive = None
515
516
result = []
517
518
WFE = WeaveFormatError
519
520
for l in self._weave:
521
if isinstance(l, tuple):
522
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:
531
assert v not in dset
532
dset.add(v)
533
else:
534
assert c == ']'
535
if v in included:
536
assert v in dset
537
dset.remove(v)
538
else:
539
assert isinstance(l, basestring)
540
if isactive is None:
541
isactive = (not dset) and istack and (istack[-1] in included)
542
if isactive:
543
result.append((istack[-1], lineno, l))
544
lineno += 1
545
546
if istack:
547
raise WFE("unclosed insertion blocks at end of weave",
548
istack)
549
if dset:
550
raise WFE("unclosed deletion blocks at end of weave",
551
dset)
552
553
return result
554
555
556
557
def get_iter(self, name_or_index):
558
"""Yield lines for the specified version."""
559
incls = [self.maybe_lookup(name_or_index)]
560
for origin, lineno, line in self._extract(incls):
561
yield line
562
563
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
574
575
576
def mash_iter(self, included):
577
"""Return composed version of multiple included versions."""
578
included = map(self.maybe_lookup, included)
579
for origin, lineno, text in self._extract(included):
580
yield text
581
582
583
def dump(self, to_file):
584
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)
589
590
591
592
def numversions(self):
593
l = len(self._parents)
594
assert l == len(self._sha1s)
595
return l
596
597
598
def __len__(self):
599
return self.numversions()
600
601
602
def check(self, progress_bar=None):
603
# check no circular inclusions
604
for version in range(self.numversions()):
605
inclusions = list(self._parents[version])
606
if inclusions:
607
inclusions.sort()
608
if inclusions[-1] >= version:
609
raise WeaveFormatError("invalid included version %d for index %d"
610
% (inclusions[-1], version))
611
612
# try extracting all versions; this is a bit slow and parallel
613
# 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)
618
s = sha.new()
619
for l in self.get_iter(version):
620
s.update(l)
621
hd = s.hexdigest()
622
expected = self._sha1s[version]
623
if hd != expected:
624
raise WeaveError("mismatched sha1 for version %d; "
625
"got %s, expected %s"
626
% (version, hd, expected))
627
628
# TODO: check insertions are properly nested, that there are
629
# no lines outside of insertion blocks, that deletions are
630
# properly paired, etc.
631
632
633
634
def merge(self, merge_versions):
635
"""Automerge and mark conflicts between versions.
636
637
This returns a sequence, each entry describing alternatives
638
for a chunk of the file. Each of the alternatives is given as
639
a list of lines.
640
641
If there is a chunk of the file where there's no diagreement,
642
only one alternative is given.
643
"""
644
# approach: find the included versions common to all the
645
# merged versions
646
raise NotImplementedError()
647
648
649
650
def _delta(self, included, lines):
651
"""Return changes from basis to new revision.
652
653
The old text for comparison is the union of included revisions.
654
655
This is used in inserting a new text.
656
657
Delta is returned as a sequence of
658
(weave1, weave2, newlines).
659
660
This indicates that weave1:weave2 of the old weave should be
661
replaced by the sequence of lines in newlines. Note that
662
these line numbers are positions in the total weave and don't
663
correspond to the lines in any extracted version, or even the
664
extracted union of included versions.
665
666
If line1=line2, this is a pure insert; if newlines=[] this is a
667
pure delete. (Similar to difflib.)
668
"""
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):
787
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')
858
w = read_weave(wf)
859
# FIXME: doesn't work on pipes
860
weave_size = wf.tell()
861
862
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))
879
880
881
def usage():
882
print """bzr weave tool
883
884
Experimental tool for weave algorithm.
885
886
usage:
887
weave init WEAVEFILE
888
Create an empty weave file
889
weave get WEAVEFILE VERSION
890
Write out specified version.
891
weave check WEAVEFILE
892
Check consistency of all versions.
893
weave toc WEAVEFILE
894
Display table of contents.
895
weave add WEAVEFILE NAME [BASE...] < NEWTEXT
896
Add NEWTEXT, with specified parent versions.
897
weave annotate WEAVEFILE VERSION
898
Display origin of each line.
899
weave mash WEAVEFILE VERSION...
900
Display composite of all selected versions.
901
weave merge WEAVEFILE VERSION1 VERSION2 > OUT
902
Auto-merge two versions and display conflicts.
903
weave diff WEAVEFILE VERSION1 VERSION2
904
Show differences between two versions.
905
906
example:
907
908
% weave init foo.weave
909
% vi foo.txt
910
% weave add foo.weave ver0 < foo.txt
911
added version 0
912
913
(create updated version)
914
% vi foo.txt
915
% weave get foo.weave 0 | diff -u - foo.txt
916
% weave add foo.weave ver1 0 < foo.txt
917
added version 1
918
919
% weave get foo.weave 0 > foo.txt (create forked version)
920
% vi foo.txt
921
% weave add foo.weave ver2 0 < foo.txt
922
added version 2
923
924
% weave merge foo.weave 1 2 > foo.txt (merge them)
925
% vi foo.txt (resolve conflicts)
926
% weave add foo.weave merged 1 2 < foo.txt (commit merged version)
927
928
"""
929
930
931
932
def main(argv):
933
import sys
934
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
954
cmd = argv[1]
955
956
def readit():
957
return read_weave(file(argv[2], 'rb'))
958
959
if cmd == 'help':
960
usage()
961
elif cmd == 'add':
962
w = readit()
963
# at the moment, based on everything in the file
964
name = argv[3]
965
parents = map(int, argv[4:])
966
lines = sys.stdin.readlines()
967
ver = w.add(name, parents, lines)
968
write_weave(w, file(argv[2], 'wb'))
969
print 'added version %r %d' % (name, ver)
970
elif cmd == 'init':
971
fn = argv[2]
972
if os.path.exists(fn):
973
raise IOError("file exists")
974
w = Weave()
975
write_weave(w, file(fn, 'wb'))
976
elif cmd == 'get': # get one version
977
w = readit()
978
sys.stdout.writelines(w.get_iter(int(argv[3])))
979
980
elif cmd == 'mash': # get composite
981
w = readit()
982
sys.stdout.writelines(w.mash_iter(map(int, argv[3:])))
983
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
elif cmd == 'annotate':
997
w = readit()
998
# newline is added to all lines regardless; too hard to get
999
# reasonable formatting otherwise
1000
lasto = None
1001
for origin, text in w.annotate(int(argv[3])):
1002
text = text.rstrip('\r\n')
1003
if origin == lasto:
1004
print ' | %s' % (text)
1005
else:
1006
print '%5d | %s' % (origin, text)
1007
lasto = origin
1008
1009
elif cmd == 'toc':
1010
weave_toc(readit())
1011
1012
elif cmd == 'stats':
1013
weave_stats(argv[2], ProgressBar())
1014
1015
elif cmd == 'check':
1016
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),
1035
1036
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
if len(argv) != 5:
1043
usage()
1044
return 1
1045
1046
w = readit()
1047
v1, v2 = map(int, argv[3:5])
1048
1049
basis = w.inclusions([v1]).intersection(w.inclusions([v2]))
1050
1051
base_lines = list(w.mash_iter(basis))
1052
a_lines = list(w.get(v1))
1053
b_lines = list(w.get(v2))
1054
1055
from bzrlib.merge3 import Merge3
1056
m3 = Merge3(base_lines, a_lines, b_lines)
1057
1058
name_a = 'version %d' % v1
1059
name_b = 'version %d' % v2
1060
sys.stdout.writelines(m3.merge_lines(name_a=name_a, name_b=name_b))
1061
else:
1062
raise ValueError('unknown command %r' % cmd)
1063
1064
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
if __name__ == '__main__':
1087
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
Loggerhead is a web-based interface for Breezy
Version: 2.0.1