« back to all changes in this revision
Viewing changes to bzrlib/knit.py
- browse files at revision 2375.1.5
- compare with another revision
- download diff
- download tarball
- view history from revision 2375.1.5
- Committer: Andrew Bennetts
- Date: 2007-03-26 06:24:01 UTC
- mto: This revision was merged to the branch mainline in revision 2376.
- Revision ID: andrew.bennetts@canonical.com-20070326062401-k3nbefzje5332jaf
Deal with review comments from Robert:
* Add my name to the NEWS file
* Move the test case to a new module in branch_implementations
* Remove revision_history cruft from identitymap and test_identitymap
* Improve some docstrings
Also, this fixes a bug where revision_history was not returning a copy of the
cached data, allowing the cache to be corrupted.
* Add my name to the NEWS file
* Move the test case to a new module in branch_implementations
* Remove revision_history cruft from identitymap and test_identitymap
* Improve some docstrings
Also, this fixes a bug where revision_history was not returning a copy of the
cached data, allowing the cache to be corrupted.
- files added:
- NEWS.developers
- bzrlib/bundle/old
- bzrlib/tests/interversionedfile_implementations
- bzrlib/tests/revisionstore_implementations
- files removed:
- bzrlib/_dirstate_helpers_c.h
- bzrlib/help_topics
- bzrlib/help_topics/en
- bzrlib/smart
- bzrlib/tests/commands
- bzrlib/tests/inventory_implementations
- bzrlib/tests/per_repository_reference
- bzrlib/util/tests
- doc/developers
- doc/en
- doc/en/admin-guide
- doc/en/developer-guide
- doc/en/mini-tutorial
- doc/en/quick-reference
- doc/en/release-notes
- doc/en/tutorials
- doc/en/user-guide
- doc/en/user-guide/images
- doc/en/user-reference
- doc/es
- doc/es/guia-desarrollador
- doc/es/guia-usuario
- doc/es/mini-tutorial
- doc/es/notas-version
- doc/es/referencia
- doc/es/referencia-rapida
- man1
- files renamed:
- doc/developers/HACKING.txt => HACKING
- bzrlib/deprecated_graph.py => bzrlib/graph.py
- bzrlib/help_topics/__init__.py => bzrlib/help_topics.py
- bzrlib/_patiencediff_py.py => bzrlib/patiencediff.py
- bzrlib/plugins/launchpad/lp_directory.py => bzrlib/plugins/launchpad/lp_indirect.py
- bzrlib/plugins/launchpad/test_lp_directory.py => bzrlib/plugins/launchpad/test_lp_indirect.py
- bzrlib/tests/http_utils.py => bzrlib/tests/HTTPTestUtil.py
- bzrlib/tests/http_server.py => bzrlib/tests/HttpServer.py
- bzrlib/tests/blackbox/test_send.py => bzrlib/tests/blackbox/test_bundle.py
- bzrlib/tests/test_deprecated_graph.py => bzrlib/tests/test_graph.py
- bzrlib/tests/test_revisionspec.py => bzrlib/tests/test_revisionnamespaces.py
- bzrlib/transport/remote.py => bzrlib/transport/smart.py
- bzrlib/xml8.py => bzrlib/xml5.py
- doc/en/tutorials/centralized_workflow.txt => doc/centralized_workflow.txt
- bzrlib/help_topics/en/configuration.txt => doc/configuration.txt
- doc/en/user-guide/http_smart_server.txt => doc/http_smart_server.txt
- doc/en/user-guide/index.txt => doc/index.txt
- doc/en/user-guide/plugins.txt => doc/plugins.txt
- doc/en/user-guide/server.txt => doc/server.txt
- doc/en/user-guide/setting_up_email.txt => doc/setting_up_email.txt
- doc/en/user-guide/specifying_revisions.txt => doc/specifying_revisions.txt
- doc/en/tutorials/tutorial.txt => doc/tutorial.txt
- doc/en/user-guide/using_aliases.txt => doc/using_aliases.txt
- doc/en/user-guide/version_info.txt => doc/version_info.txt
- files modified:
- .bzrignore
- setup.py *
added
removed
bzrlib/knit.py
1
# Copyright (C) 2005, 2006, 2007 Canonical Ltd
1
# Copyright (C) 2005, 2006 Canonical Ltd
2
2
#
3
3
# This program is free software; you can redistribute it and/or modify
4
4
# it under the terms of the GNU General Public License as published by
60
60
# record content length ?
61
61
62
62
63
from copy import copy
63
64
from cStringIO import StringIO
65
import difflib
64
66
from itertools import izip, chain
65
67
import operator
66
68
import os
69
import sys
70
import warnings
67
71
68
from bzrlib.lazy_import import lazy_import
69
lazy_import(globals(), """
70
from bzrlib import (
71
annotate,
72
debug,
73
diff,
74
graph as _mod_graph,
75
index as _mod_index,
76
lru_cache,
77
pack,
78
progress,
79
trace,
80
tsort,
81
tuned_gzip,
82
)
83
""")
84
from bzrlib import (
72
import bzrlib
73
from bzrlib import (
74
cache_utf8,
85
75
errors,
86
76
osutils,
87
77
patiencediff,
78
progress,
79
ui,
88
80
)
89
81
from bzrlib.errors import (
90
82
FileExists,
96
88
RevisionNotPresent,
97
89
RevisionAlreadyPresent,
98
90
)
91
from bzrlib.tuned_gzip import GzipFile
92
from bzrlib.trace import mutter
99
93
from bzrlib.osutils import (
100
94
contains_whitespace,
101
95
contains_linebreaks,
102
sha_string,
103
96
sha_strings,
104
split_lines,
105
)
106
from bzrlib.versionedfile import (
107
AbsentContentFactory,
108
adapter_registry,
109
ConstantMapper,
110
ContentFactory,
111
FulltextContentFactory,
112
VersionedFile,
113
VersionedFiles,
114
)
97
)
98
from bzrlib.symbol_versioning import DEPRECATED_PARAMETER, deprecated_passed
99
from bzrlib.tsort import topo_sort
100
import bzrlib.ui
101
import bzrlib.weave
102
from bzrlib.versionedfile import VersionedFile, InterVersionedFile
115
103
116
104
117
105
# TODO: Split out code specific to this format into an associated object.
131
119
INDEX_SUFFIX = '.kndx'
132
120
133
121
134
class KnitAdapter(object):
135
"""Base class for knit record adaption."""
136
137
def __init__(self, basis_vf):
138
"""Create an adapter which accesses full texts from basis_vf.
139
140
:param basis_vf: A versioned file to access basis texts of deltas from.
141
May be None for adapters that do not need to access basis texts.
142
"""
143
self._data = KnitVersionedFiles(None, None)
144
self._annotate_factory = KnitAnnotateFactory()
145
self._plain_factory = KnitPlainFactory()
146
self._basis_vf = basis_vf
147
148
149
class FTAnnotatedToUnannotated(KnitAdapter):
150
"""An adapter from FT annotated knits to unannotated ones."""
151
152
def get_bytes(self, factory, annotated_compressed_bytes):
153
rec, contents = \
154
self._data._parse_record_unchecked(annotated_compressed_bytes)
155
content = self._annotate_factory.parse_fulltext(contents, rec[1])
156
size, bytes = self._data._record_to_data((rec[1],), rec[3], content.text())
157
return bytes
158
159
160
class DeltaAnnotatedToUnannotated(KnitAdapter):
161
"""An adapter for deltas from annotated to unannotated."""
162
163
def get_bytes(self, factory, annotated_compressed_bytes):
164
rec, contents = \
165
self._data._parse_record_unchecked(annotated_compressed_bytes)
166
delta = self._annotate_factory.parse_line_delta(contents, rec[1],
167
plain=True)
168
contents = self._plain_factory.lower_line_delta(delta)
169
size, bytes = self._data._record_to_data((rec[1],), rec[3], contents)
170
return bytes
171
172
173
class FTAnnotatedToFullText(KnitAdapter):
174
"""An adapter from FT annotated knits to unannotated ones."""
175
176
def get_bytes(self, factory, annotated_compressed_bytes):
177
rec, contents = \
178
self._data._parse_record_unchecked(annotated_compressed_bytes)
179
content, delta = self._annotate_factory.parse_record(factory.key[-1],
180
contents, factory._build_details, None)
181
return ''.join(content.text())
182
183
184
class DeltaAnnotatedToFullText(KnitAdapter):
185
"""An adapter for deltas from annotated to unannotated."""
186
187
def get_bytes(self, factory, annotated_compressed_bytes):
188
rec, contents = \
189
self._data._parse_record_unchecked(annotated_compressed_bytes)
190
delta = self._annotate_factory.parse_line_delta(contents, rec[1],
191
plain=True)
192
compression_parent = factory.parents[0]
193
basis_entry = self._basis_vf.get_record_stream(
194
[compression_parent], 'unordered', True).next()
195
if basis_entry.storage_kind == 'absent':
196
raise errors.RevisionNotPresent(compression_parent, self._basis_vf)
197
basis_lines = split_lines(basis_entry.get_bytes_as('fulltext'))
198
# Manually apply the delta because we have one annotated content and
199
# one plain.
200
basis_content = PlainKnitContent(basis_lines, compression_parent)
201
basis_content.apply_delta(delta, rec[1])
202
basis_content._should_strip_eol = factory._build_details[1]
203
return ''.join(basis_content.text())
204
205
206
class FTPlainToFullText(KnitAdapter):
207
"""An adapter from FT plain knits to unannotated ones."""
208
209
def get_bytes(self, factory, compressed_bytes):
210
rec, contents = \
211
self._data._parse_record_unchecked(compressed_bytes)
212
content, delta = self._plain_factory.parse_record(factory.key[-1],
213
contents, factory._build_details, None)
214
return ''.join(content.text())
215
216
217
class DeltaPlainToFullText(KnitAdapter):
218
"""An adapter for deltas from annotated to unannotated."""
219
220
def get_bytes(self, factory, compressed_bytes):
221
rec, contents = \
222
self._data._parse_record_unchecked(compressed_bytes)
223
delta = self._plain_factory.parse_line_delta(contents, rec[1])
224
compression_parent = factory.parents[0]
225
# XXX: string splitting overhead.
226
basis_entry = self._basis_vf.get_record_stream(
227
[compression_parent], 'unordered', True).next()
228
if basis_entry.storage_kind == 'absent':
229
raise errors.RevisionNotPresent(compression_parent, self._basis_vf)
230
basis_lines = split_lines(basis_entry.get_bytes_as('fulltext'))
231
basis_content = PlainKnitContent(basis_lines, compression_parent)
232
# Manually apply the delta because we have one annotated content and
233
# one plain.
234
content, _ = self._plain_factory.parse_record(rec[1], contents,
235
factory._build_details, basis_content)
236
return ''.join(content.text())
237
238
239
class KnitContentFactory(ContentFactory):
240
"""Content factory for streaming from knits.
241
242
:seealso ContentFactory:
243
"""
244
245
def __init__(self, key, parents, build_details, sha1, raw_record,
246
annotated, knit=None):
247
"""Create a KnitContentFactory for key.
248
249
:param key: The key.
250
:param parents: The parents.
251
:param build_details: The build details as returned from
252
get_build_details.
253
:param sha1: The sha1 expected from the full text of this object.
254
:param raw_record: The bytes of the knit data from disk.
255
:param annotated: True if the raw data is annotated.
256
"""
257
ContentFactory.__init__(self)
258
self.sha1 = sha1
259
self.key = key
260
self.parents = parents
261
if build_details[0] == 'line-delta':
262
kind = 'delta'
263
else:
264
kind = 'ft'
265
if annotated:
266
annotated_kind = 'annotated-'
267
else:
268
annotated_kind = ''
269
self.storage_kind = 'knit-%s%s-gz' % (annotated_kind, kind)
270
self._raw_record = raw_record
271
self._build_details = build_details
272
self._knit = knit
273
274
def get_bytes_as(self, storage_kind):
275
if storage_kind == self.storage_kind:
276
return self._raw_record
277
if storage_kind == 'fulltext' and self._knit is not None:
278
return self._knit.get_text(self.key[0])
279
else:
280
raise errors.UnavailableRepresentation(self.key, storage_kind,
281
self.storage_kind)
282
283
284
122
class KnitContent(object):
285
"""Content of a knit version to which deltas can be applied.
286
287
This is always stored in memory as a list of lines with \n at the end,
288
plus a flag saying if the final ending is really there or not, because that
289
corresponds to the on-disk knit representation.
290
"""
291
292
def __init__(self):
293
self._should_strip_eol = False
294
295
def apply_delta(self, delta, new_version_id):
296
"""Apply delta to this object to become new_version_id."""
297
raise NotImplementedError(self.apply_delta)
123
"""Content of a knit version to which deltas can be applied."""
124
125
def __init__(self, lines):
126
self._lines = lines
127
128
def annotate_iter(self):
129
"""Yield tuples of (origin, text) for each content line."""
130
return iter(self._lines)
131
132
def annotate(self):
133
"""Return a list of (origin, text) tuples."""
134
return list(self.annotate_iter())
298
135
299
136
def line_delta_iter(self, new_lines):
300
137
"""Generate line-based delta from this content to new_lines."""
301
138
new_texts = new_lines.text()
302
139
old_texts = self.text()
303
s = patiencediff.PatienceSequenceMatcher(None, old_texts, new_texts)
140
s = KnitSequenceMatcher(None, old_texts, new_texts)
304
141
for tag, i1, i2, j1, j2 in s.get_opcodes():
305
142
if tag == 'equal':
306
143
continue
310
147
def line_delta(self, new_lines):
311
148
return list(self.line_delta_iter(new_lines))
312
149
313
@staticmethod
314
def get_line_delta_blocks(knit_delta, source, target):
315
"""Extract SequenceMatcher.get_matching_blocks() from a knit delta"""
316
target_len = len(target)
317
s_pos = 0
318
t_pos = 0
319
for s_begin, s_end, t_len, new_text in knit_delta:
320
true_n = s_begin - s_pos
321
n = true_n
322
if n > 0:
323
# knit deltas do not provide reliable info about whether the
324
# last line of a file matches, due to eol handling.
325
if source[s_pos + n -1] != target[t_pos + n -1]:
326
n-=1
327
if n > 0:
328
yield s_pos, t_pos, n
329
t_pos += t_len + true_n
330
s_pos = s_end
331
n = target_len - t_pos
332
if n > 0:
333
if source[s_pos + n -1] != target[t_pos + n -1]:
334
n-=1
335
if n > 0:
336
yield s_pos, t_pos, n
337
yield s_pos + (target_len - t_pos), target_len, 0
338
339
340
class AnnotatedKnitContent(KnitContent):
341
"""Annotated content."""
342
343
def __init__(self, lines):
344
KnitContent.__init__(self)
345
self._lines = lines
346
347
def annotate(self):
348
"""Return a list of (origin, text) for each content line."""
349
lines = self._lines[:]
350
if self._should_strip_eol:
351
origin, last_line = lines[-1]
352
lines[-1] = (origin, last_line.rstrip('\n'))
353
return lines
354
355
def apply_delta(self, delta, new_version_id):
356
"""Apply delta to this object to become new_version_id."""
357
offset = 0
358
lines = self._lines
359
for start, end, count, delta_lines in delta:
360
lines[offset+start:offset+end] = delta_lines
361
offset = offset + (start - end) + count
362
363
def text(self):
364
try:
365
lines = [text for origin, text in self._lines]
366
except ValueError, e:
367
# most commonly (only?) caused by the internal form of the knit
368
# missing annotation information because of a bug - see thread
369
# around 20071015
370
raise KnitCorrupt(self,
371
"line in annotated knit missing annotation information: %s"
372
% (e,))
373
if self._should_strip_eol:
374
lines[-1] = lines[-1].rstrip('\n')
375
return lines
376
377
def copy(self):
378
return AnnotatedKnitContent(self._lines[:])
379
380
381
class PlainKnitContent(KnitContent):
382
"""Unannotated content.
383
384
When annotate[_iter] is called on this content, the same version is reported
385
for all lines. Generally, annotate[_iter] is not useful on PlainKnitContent
386
objects.
387
"""
388
389
def __init__(self, lines, version_id):
390
KnitContent.__init__(self)
391
self._lines = lines
392
self._version_id = version_id
393
394
def annotate(self):
395
"""Return a list of (origin, text) for each content line."""
396
return [(self._version_id, line) for line in self._lines]
397
398
def apply_delta(self, delta, new_version_id):
399
"""Apply delta to this object to become new_version_id."""
400
offset = 0
401
lines = self._lines
402
for start, end, count, delta_lines in delta:
403
lines[offset+start:offset+end] = delta_lines
404
offset = offset + (start - end) + count
405
self._version_id = new_version_id
406
407
def copy(self):
408
return PlainKnitContent(self._lines[:], self._version_id)
409
410
def text(self):
411
lines = self._lines
412
if self._should_strip_eol:
413
lines = lines[:]
414
lines[-1] = lines[-1].rstrip('\n')
415
return lines
150
def text(self):
151
return [text for origin, text in self._lines]
152
153
def copy(self):
154
return KnitContent(self._lines[:])
416
155
417
156
418
157
class _KnitFactory(object):
419
"""Base class for common Factory functions."""
420
421
def parse_record(self, version_id, record, record_details,
422
base_content, copy_base_content=True):
423
"""Parse a record into a full content object.
424
425
:param version_id: The official version id for this content
426
:param record: The data returned by read_records_iter()
427
:param record_details: Details about the record returned by
428
get_build_details
429
:param base_content: If get_build_details returns a compression_parent,
430
you must return a base_content here, else use None
431
:param copy_base_content: When building from the base_content, decide
432
you can either copy it and return a new object, or modify it in
433
place.
434
:return: (content, delta) A Content object and possibly a line-delta,
435
delta may be None
436
"""
437
method, noeol = record_details
438
if method == 'line-delta':
439
if copy_base_content:
440
content = base_content.copy()
441
else:
442
content = base_content
443
delta = self.parse_line_delta(record, version_id)
444
content.apply_delta(delta, version_id)
445
else:
446
content = self.parse_fulltext(record, version_id)
447
delta = None
448
content._should_strip_eol = noeol
449
return (content, delta)
158
"""Base factory for creating content objects."""
159
160
def make(self, lines, version_id):
161
num_lines = len(lines)
162
return KnitContent(zip([version_id] * num_lines, lines))
450
163
451
164
452
165
class KnitAnnotateFactory(_KnitFactory):
454
167
455
168
annotated = True
456
169
457
def make(self, lines, version_id):
458
num_lines = len(lines)
459
return AnnotatedKnitContent(zip([version_id] * num_lines, lines))
460
461
170
def parse_fulltext(self, content, version_id):
462
171
"""Convert fulltext to internal representation
463
172
471
180
# Figure out a way to not require the overhead of turning the
472
181
# list back into tuples.
473
182
lines = [tuple(line.split(' ', 1)) for line in content]
474
return AnnotatedKnitContent(lines)
183
return KnitContent(lines)
475
184
476
185
def parse_line_delta_iter(self, lines):
477
186
return iter(self.parse_line_delta(lines))
478
187
479
def parse_line_delta(self, lines, version_id, plain=False):
188
def parse_line_delta(self, lines, version_id):
480
189
"""Convert a line based delta into internal representation.
481
190
482
191
line delta is in the form of:
485
194
revid(utf8) newline\n
486
195
internal representation is
487
196
(start, end, count, [1..count tuples (revid, newline)])
488
489
:param plain: If True, the lines are returned as a plain
490
list without annotations, not as a list of (origin, content) tuples, i.e.
491
(start, end, count, [1..count newline])
492
197
"""
493
198
result = []
494
199
lines = iter(lines)
500
205
return cache.setdefault(origin, origin), text
501
206
502
207
# walk through the lines parsing.
503
# Note that the plain test is explicitly pulled out of the
504
# loop to minimise any performance impact
505
if plain:
506
for header in lines:
507
start, end, count = [int(n) for n in header.split(',')]
508
contents = [next().split(' ', 1)[1] for i in xrange(count)]
509
result.append((start, end, count, contents))
510
else:
511
for header in lines:
512
start, end, count = [int(n) for n in header.split(',')]
513
contents = [tuple(next().split(' ', 1)) for i in xrange(count)]
514
result.append((start, end, count, contents))
208
for header in lines:
209
start, end, count = [int(n) for n in header.split(',')]
210
contents = [tuple(next().split(' ', 1)) for i in xrange(count)]
211
result.append((start, end, count, contents))
515
212
return result
516
213
517
214
def get_fulltext_content(self, lines):
556
253
for origin, text in lines)
557
254
return out
558
255
559
def annotate(self, knit, key):
560
content = knit._get_content(key)
561
# adjust for the fact that serialised annotations are only key suffixes
562
# for this factory.
563
if type(key) == tuple:
564
prefix = key[:-1]
565
origins = content.annotate()
566
result = []
567
for origin, line in origins:
568
result.append((prefix + (origin,), line))
569
return result
570
else:
571
# XXX: This smells a bit. Why would key ever be a non-tuple here?
572
# Aren't keys defined to be tuples? -- spiv 20080618
573
return content.annotate()
574
575
256
576
257
class KnitPlainFactory(_KnitFactory):
577
258
"""Factory for creating plain Content objects."""
578
259
579
260
annotated = False
580
261
581
def make(self, lines, version_id):
582
return PlainKnitContent(lines, version_id)
583
584
262
def parse_fulltext(self, content, version_id):
585
263
"""This parses an unannotated fulltext.
586
264
596
274
header = lines[cur]
597
275
cur += 1
598
276
start, end, c = [int(n) for n in header.split(',')]
599
yield start, end, c, lines[cur:cur+c]
277
yield start, end, c, zip([version_id] * c, lines[cur:cur+c])
600
278
cur += c
601
279
602
280
def parse_line_delta(self, lines, version_id):
627
305
out = []
628
306
for start, end, c, lines in delta:
629
307
out.append('%d,%d,%d\n' % (start, end, c))
630
out.extend(lines)
308
out.extend([text for origin, text in lines])
631
309
return out
632
310
633
def annotate(self, knit, key):
634
annotator = _KnitAnnotator(knit)
635
return annotator.annotate(key)
636
637
638
639
def make_file_factory(annotated, mapper):
640
"""Create a factory for creating a file based KnitVersionedFiles.
641
642
This is only functional enough to run interface tests, it doesn't try to
643
provide a full pack environment.
644
645
:param annotated: knit annotations are wanted.
646
:param mapper: The mapper from keys to paths.
647
"""
648
def factory(transport):
649
index = _KndxIndex(transport, mapper, lambda:None, lambda:True, lambda:True)
650
access = _KnitKeyAccess(transport, mapper)
651
return KnitVersionedFiles(index, access, annotated=annotated)
652
return factory
653
654
655
def make_pack_factory(graph, delta, keylength):
656
"""Create a factory for creating a pack based VersionedFiles.
657
658
This is only functional enough to run interface tests, it doesn't try to
659
provide a full pack environment.
660
661
:param graph: Store a graph.
662
:param delta: Delta compress contents.
663
:param keylength: How long should keys be.
664
"""
665
def factory(transport):
666
parents = graph or delta
667
ref_length = 0
668
if graph:
669
ref_length += 1
670
if delta:
671
ref_length += 1
672
max_delta_chain = 200
673
else:
674
max_delta_chain = 0
675
graph_index = _mod_index.InMemoryGraphIndex(reference_lists=ref_length,
676
key_elements=keylength)
677
stream = transport.open_write_stream('newpack')
678
writer = pack.ContainerWriter(stream.write)
679
writer.begin()
680
index = _KnitGraphIndex(graph_index, lambda:True, parents=parents,
681
deltas=delta, add_callback=graph_index.add_nodes)
682
access = _DirectPackAccess({})
683
access.set_writer(writer, graph_index, (transport, 'newpack'))
684
result = KnitVersionedFiles(index, access,
685
max_delta_chain=max_delta_chain)
686
result.stream = stream
687
result.writer = writer
688
return result
689
return factory
690
691
692
def cleanup_pack_knit(versioned_files):
693
versioned_files.stream.close()
694
versioned_files.writer.end()
695
696
697
class KnitVersionedFiles(VersionedFiles):
698
"""Storage for many versioned files using knit compression.
699
700
Backend storage is managed by indices and data objects.
701
"""
702
703
def __init__(self, index, data_access, max_delta_chain=200,
704
annotated=False):
705
"""Create a KnitVersionedFiles with index and data_access.
706
707
:param index: The index for the knit data.
708
:param data_access: The access object to store and retrieve knit
709
records.
710
:param max_delta_chain: The maximum number of deltas to permit during
711
insertion. Set to 0 to prohibit the use of deltas.
712
:param annotated: Set to True to cause annotations to be calculated and
713
stored during insertion.
714
"""
715
self._index = index
716
self._access = data_access
717
self._max_delta_chain = max_delta_chain
718
if annotated:
719
self._factory = KnitAnnotateFactory()
720
else:
721
self._factory = KnitPlainFactory()
722
self._fallback_vfs = []
723
724
def add_fallback_versioned_files(self, a_versioned_files):
725
"""Add a source of texts for texts not present in this knit.
726
727
:param a_versioned_files: A VersionedFiles object.
728
"""
729
self._fallback_vfs.append(a_versioned_files)
730
731
def add_lines(self, key, parents, lines, parent_texts=None,
732
left_matching_blocks=None, nostore_sha=None, random_id=False,
733
check_content=True):
734
"""See VersionedFiles.add_lines()."""
735
self._index._check_write_ok()
736
self._check_add(key, lines, random_id, check_content)
737
if parents is None:
738
# The caller might pass None if there is no graph data, but kndx
739
# indexes can't directly store that, so we give them
740
# an empty tuple instead.
741
parents = ()
742
return self._add(key, lines, parents,
743
parent_texts, left_matching_blocks, nostore_sha, random_id)
744
745
def _add(self, key, lines, parents, parent_texts,
746
left_matching_blocks, nostore_sha, random_id):
747
"""Add a set of lines on top of version specified by parents.
748
749
Any versions not present will be converted into ghosts.
750
"""
751
# first thing, if the content is something we don't need to store, find
752
# that out.
753
line_bytes = ''.join(lines)
754
digest = sha_string(line_bytes)
755
if nostore_sha == digest:
756
raise errors.ExistingContent
757
758
present_parents = []
759
if parent_texts is None:
760
parent_texts = {}
761
# Do a single query to ascertain parent presence.
762
present_parent_map = self.get_parent_map(parents)
763
for parent in parents:
764
if parent in present_parent_map:
765
present_parents.append(parent)
766
767
# Currently we can only compress against the left most present parent.
768
if (len(present_parents) == 0 or
769
present_parents[0] != parents[0]):
770
delta = False
771
else:
772
# To speed the extract of texts the delta chain is limited
773
# to a fixed number of deltas. This should minimize both
774
# I/O and the time spend applying deltas.
775
delta = self._check_should_delta(present_parents[0])
776
777
text_length = len(line_bytes)
778
options = []
779
if lines:
780
if lines[-1][-1] != '\n':
781
# copy the contents of lines.
782
lines = lines[:]
783
options.append('no-eol')
784
lines[-1] = lines[-1] + '\n'
785
line_bytes += '\n'
786
787
for element in key:
788
if type(element) != str:
789
raise TypeError("key contains non-strings: %r" % (key,))
790
# Knit hunks are still last-element only
791
version_id = key[-1]
792
content = self._factory.make(lines, version_id)
793
if 'no-eol' in options:
794
# Hint to the content object that its text() call should strip the
795
# EOL.
796
content._should_strip_eol = True
797
if delta or (self._factory.annotated and len(present_parents) > 0):
798
# Merge annotations from parent texts if needed.
799
delta_hunks = self._merge_annotations(content, present_parents,
800
parent_texts, delta, self._factory.annotated,
801
left_matching_blocks)
802
803
if delta:
804
options.append('line-delta')
805
store_lines = self._factory.lower_line_delta(delta_hunks)
806
size, bytes = self._record_to_data(key, digest,
807
store_lines)
808
else:
809
options.append('fulltext')
810
# isinstance is slower and we have no hierarchy.
811
if self._factory.__class__ == KnitPlainFactory:
812
# Use the already joined bytes saving iteration time in
813
# _record_to_data.
814
size, bytes = self._record_to_data(key, digest,
815
lines, [line_bytes])
816
else:
817
# get mixed annotation + content and feed it into the
818
# serialiser.
819
store_lines = self._factory.lower_fulltext(content)
820
size, bytes = self._record_to_data(key, digest,
821
store_lines)
822
823
access_memo = self._access.add_raw_records([(key, size)], bytes)[0]
824
self._index.add_records(
825
((key, options, access_memo, parents),),
826
random_id=random_id)
827
return digest, text_length, content
828
829
def annotate(self, key):
830
"""See VersionedFiles.annotate."""
831
return self._factory.annotate(self, key)
832
833
def check(self, progress_bar=None):
834
"""See VersionedFiles.check()."""
835
# This doesn't actually test extraction of everything, but that will
836
# impact 'bzr check' substantially, and needs to be integrated with
837
# care. However, it does check for the obvious problem of a delta with
838
# no basis.
839
keys = self._index.keys()
840
parent_map = self.get_parent_map(keys)
841
for key in keys:
842
if self._index.get_method(key) != 'fulltext':
843
compression_parent = parent_map[key][0]
844
if compression_parent not in parent_map:
845
raise errors.KnitCorrupt(self,
846
"Missing basis parent %s for %s" % (
847
compression_parent, key))
848
for fallback_vfs in self._fallback_vfs:
849
fallback_vfs.check()
850
851
def _check_add(self, key, lines, random_id, check_content):
852
"""check that version_id and lines are safe to add."""
853
version_id = key[-1]
854
if contains_whitespace(version_id):
855
raise InvalidRevisionId(version_id, self)
856
self.check_not_reserved_id(version_id)
857
# TODO: If random_id==False and the key is already present, we should
858
# probably check that the existing content is identical to what is
859
# being inserted, and otherwise raise an exception. This would make
860
# the bundle code simpler.
861
if check_content:
862
self._check_lines_not_unicode(lines)
863
self._check_lines_are_lines(lines)
864
865
def _check_header(self, key, line):
866
rec = self._split_header(line)
867
self._check_header_version(rec, key[-1])
868
return rec
869
870
def _check_header_version(self, rec, version_id):
871
"""Checks the header version on original format knit records.
311
312
def make_empty_knit(transport, relpath):
313
"""Construct a empty knit at the specified location."""
314
k = KnitVersionedFile(transport, relpath, 'w', KnitPlainFactory)
315
k._data._open_file()
316
317
318
class KnitVersionedFile(VersionedFile):
319
"""Weave-like structure with faster random access.
320
321
A knit stores a number of texts and a summary of the relationships
322
between them. Texts are identified by a string version-id. Texts
323
are normally stored and retrieved as a series of lines, but can
324
also be passed as single strings.
325
326
Lines are stored with the trailing newline (if any) included, to
327
avoid special cases for files with no final newline. Lines are
328
composed of 8-bit characters, not unicode. The combination of
329
these approaches should mean any 'binary' file can be safely
330
stored and retrieved.
331
"""
332
333
def __init__(self, relpath, transport, file_mode=None, access_mode=None,
334
factory=None, basis_knit=DEPRECATED_PARAMETER, delta=True,
335
create=False, create_parent_dir=False, delay_create=False,
336
dir_mode=None):
337
"""Construct a knit at location specified by relpath.
872
338
873
These have the last component of the key embedded in the record.
339
:param create: If not True, only open an existing knit.
340
:param create_parent_dir: If True, create the parent directory if
341
creating the file fails. (This is used for stores with
342
hash-prefixes that may not exist yet)
343
:param delay_create: The calling code is aware that the knit won't
344
actually be created until the first data is stored.
874
345
"""
875
if rec[1] != version_id:
876
raise KnitCorrupt(self,
877
'unexpected version, wanted %r, got %r' % (version_id, rec[1]))
878
879
def _check_should_delta(self, parent):
346
if deprecated_passed(basis_knit):
347
warnings.warn("KnitVersionedFile.__(): The basis_knit parameter is"
348
" deprecated as of bzr 0.9.",
349
DeprecationWarning, stacklevel=2)
350
if access_mode is None:
351
access_mode = 'w'
352
super(KnitVersionedFile, self).__init__(access_mode)
353
assert access_mode in ('r', 'w'), "invalid mode specified %r" % access_mode
354
self.transport = transport
355
self.filename = relpath
356
self.factory = factory or KnitAnnotateFactory()
357
self.writable = (access_mode == 'w')
358
self.delta = delta
359
360
self._max_delta_chain = 200
361
362
self._index = _KnitIndex(transport, relpath + INDEX_SUFFIX,
363
access_mode, create=create, file_mode=file_mode,
364
create_parent_dir=create_parent_dir, delay_create=delay_create,
365
dir_mode=dir_mode)
366
self._data = _KnitData(transport, relpath + DATA_SUFFIX,
367
access_mode, create=create and not len(self), file_mode=file_mode,
368
create_parent_dir=create_parent_dir, delay_create=delay_create,
369
dir_mode=dir_mode)
370
371
def __repr__(self):
372
return '%s(%s)' % (self.__class__.__name__,
373
self.transport.abspath(self.filename))
374
375
def _check_should_delta(self, first_parents):
880
376
"""Iterate back through the parent listing, looking for a fulltext.
881
377
882
378
This is used when we want to decide whether to add a delta or a new
889
385
"""
890
386
delta_size = 0
891
387
fulltext_size = None
388
delta_parents = first_parents
892
389
for count in xrange(self._max_delta_chain):
893
# XXX: Collapse these two queries:
894
try:
895
method = self._index.get_method(parent)
896
except RevisionNotPresent:
897
# Some basis is not locally present: always delta
898
return False
899
index, pos, size = self._index.get_position(parent)
390
parent = delta_parents[0]
391
method = self._index.get_method(parent)
392
pos, size = self._index.get_position(parent)
900
393
if method == 'fulltext':
901
394
fulltext_size = size
902
395
break
903
396
delta_size += size
904
# We don't explicitly check for presence because this is in an
905
# inner loop, and if it's missing it'll fail anyhow.
906
# TODO: This should be asking for compression parent, not graph
907
# parent.
908
parent = self._index.get_parent_map([parent])[parent][0]
397
delta_parents = self._index.get_parents(parent)
909
398
else:
910
399
# We couldn't find a fulltext, so we must create a new one
911
400
return False
912
# Simple heuristic - if the total I/O wold be greater as a delta than
913
# the originally installed fulltext, we create a new fulltext.
401
914
402
return fulltext_size > delta_size
915
403
916
def _build_details_to_components(self, build_details):
917
"""Convert a build_details tuple to a position tuple."""
918
# record_details, access_memo, compression_parent
919
return build_details[3], build_details[0], build_details[1]
920
921
def _get_components_positions(self, keys, allow_missing=False):
922
"""Produce a map of position data for the components of keys.
404
def _add_delta(self, version_id, parents, delta_parent, sha1, noeol, delta):
405
"""See VersionedFile._add_delta()."""
406
self._check_add(version_id, []) # should we check the lines ?
407
self._check_versions_present(parents)
408
present_parents = []
409
ghosts = []
410
parent_texts = {}
411
for parent in parents:
412
if not self.has_version(parent):
413
ghosts.append(parent)
414
else:
415
present_parents.append(parent)
416
417
if delta_parent is None:
418
# reconstitute as full text.
419
assert len(delta) == 1 or len(delta) == 0
420
if len(delta):
421
assert delta[0][0] == 0
422
assert delta[0][1] == 0, delta[0][1]
423
return super(KnitVersionedFile, self)._add_delta(version_id,
424
parents,
425
delta_parent,
426
sha1,
427
noeol,
428
delta)
429
430
digest = sha1
431
432
options = []
433
if noeol:
434
options.append('no-eol')
435
436
if delta_parent is not None:
437
# determine the current delta chain length.
438
# To speed the extract of texts the delta chain is limited
439
# to a fixed number of deltas. This should minimize both
440
# I/O and the time spend applying deltas.
441
# The window was changed to a maximum of 200 deltas, but also added
442
# was a check that the total compressed size of the deltas is
443
# smaller than the compressed size of the fulltext.
444
if not self._check_should_delta([delta_parent]):
445
# We don't want a delta here, just do a normal insertion.
446
return super(KnitVersionedFile, self)._add_delta(version_id,
447
parents,
448
delta_parent,
449
sha1,
450
noeol,
451
delta)
452
453
options.append('line-delta')
454
store_lines = self.factory.lower_line_delta(delta)
455
456
where, size = self._data.add_record(version_id, digest, store_lines)
457
self._index.add_version(version_id, options, where, size, parents)
458
459
def _add_raw_records(self, records, data):
460
"""Add all the records 'records' with data pre-joined in 'data'.
461
462
:param records: A list of tuples(version_id, options, parents, size).
463
:param data: The data for the records. When it is written, the records
464
are adjusted to have pos pointing into data by the sum of
465
the preceding records sizes.
466
"""
467
# write all the data
468
pos = self._data.add_raw_record(data)
469
offset = 0
470
index_entries = []
471
for (version_id, options, parents, size) in records:
472
index_entries.append((version_id, options, pos+offset,
473
size, parents))
474
if self._data._do_cache:
475
self._data._cache[version_id] = data[offset:offset+size]
476
offset += size
477
self._index.add_versions(index_entries)
478
479
def enable_cache(self):
480
"""Start caching data for this knit"""
481
self._data.enable_cache()
482
483
def clear_cache(self):
484
"""Clear the data cache only."""
485
self._data.clear_cache()
486
487
def copy_to(self, name, transport):
488
"""See VersionedFile.copy_to()."""
489
# copy the current index to a temp index to avoid racing with local
490
# writes
491
transport.put_file_non_atomic(name + INDEX_SUFFIX + '.tmp',
492
self.transport.get(self._index._filename))
493
# copy the data file
494
f = self._data._open_file()
495
try:
496
transport.put_file(name + DATA_SUFFIX, f)
497
finally:
498
f.close()
499
# move the copied index into place
500
transport.move(name + INDEX_SUFFIX + '.tmp', name + INDEX_SUFFIX)
501
502
def create_empty(self, name, transport, mode=None):
503
return KnitVersionedFile(name, transport, factory=self.factory,
504
delta=self.delta, create=True)
505
506
def _fix_parents(self, version_id, new_parents):
507
"""Fix the parents list for version.
508
509
This is done by appending a new version to the index
510
with identical data except for the parents list.
511
the parents list must be a superset of the current
512
list.
513
"""
514
current_values = self._index._cache[version_id]
515
assert set(current_values[4]).difference(set(new_parents)) == set()
516
self._index.add_version(version_id,
517
current_values[1],
518
current_values[2],
519
current_values[3],
520
new_parents)
521
522
def get_delta(self, version_id):
523
"""Get a delta for constructing version from some other version."""
524
version_id = osutils.safe_revision_id(version_id)
525
self.check_not_reserved_id(version_id)
526
if not self.has_version(version_id):
527
raise RevisionNotPresent(version_id, self.filename)
528
529
parents = self.get_parents(version_id)
530
if len(parents):
531
parent = parents[0]
532
else:
533
parent = None
534
data_pos, data_size = self._index.get_position(version_id)
535
data, sha1 = self._data.read_records(((version_id, data_pos, data_size),))[version_id]
536
noeol = 'no-eol' in self._index.get_options(version_id)
537
if 'fulltext' == self._index.get_method(version_id):
538
new_content = self.factory.parse_fulltext(data, version_id)
539
if parent is not None:
540
reference_content = self._get_content(parent)
541
old_texts = reference_content.text()
542
else:
543
old_texts = []
544
new_texts = new_content.text()
545
delta_seq = KnitSequenceMatcher(None, old_texts, new_texts)
546
return parent, sha1, noeol, self._make_line_delta(delta_seq, new_content)
547
else:
548
delta = self.factory.parse_line_delta(data, version_id)
549
return parent, sha1, noeol, delta
550
551
def get_graph_with_ghosts(self):
552
"""See VersionedFile.get_graph_with_ghosts()."""
553
graph_items = self._index.get_graph()
554
return dict(graph_items)
555
556
def get_sha1(self, version_id):
557
"""See VersionedFile.get_sha1()."""
558
version_id = osutils.safe_revision_id(version_id)
559
record_map = self._get_record_map([version_id])
560
method, content, digest, next = record_map[version_id]
561
return digest
562
563
@staticmethod
564
def get_suffixes():
565
"""See VersionedFile.get_suffixes()."""
566
return [DATA_SUFFIX, INDEX_SUFFIX]
567
568
def has_ghost(self, version_id):
569
"""True if there is a ghost reference in the file to version_id."""
570
version_id = osutils.safe_revision_id(version_id)
571
# maybe we have it
572
if self.has_version(version_id):
573
return False
574
# optimisable if needed by memoising the _ghosts set.
575
items = self._index.get_graph()
576
for node, parents in items:
577
for parent in parents:
578
if parent not in self._index._cache:
579
if parent == version_id:
580
return True
581
return False
582
583
def versions(self):
584
"""See VersionedFile.versions."""
585
return self._index.get_versions()
586
587
def has_version(self, version_id):
588
"""See VersionedFile.has_version."""
589
version_id = osutils.safe_revision_id(version_id)
590
return self._index.has_version(version_id)
591
592
__contains__ = has_version
593
594
def _merge_annotations(self, content, parents, parent_texts={},
595
delta=None, annotated=None):
596
"""Merge annotations for content. This is done by comparing
597
the annotations based on changed to the text.
598
"""
599
if annotated:
600
delta_seq = None
601
for parent_id in parents:
602
merge_content = self._get_content(parent_id, parent_texts)
603
seq = patiencediff.PatienceSequenceMatcher(
604
None, merge_content.text(), content.text())
605
if delta_seq is None:
606
# setup a delta seq to reuse.
607
delta_seq = seq
608
for i, j, n in seq.get_matching_blocks():
609
if n == 0:
610
continue
611
# this appears to copy (origin, text) pairs across to the new
612
# content for any line that matches the last-checked parent.
613
# FIXME: save the sequence control data for delta compression
614
# against the most relevant parent rather than rediffing.
615
content._lines[j:j+n] = merge_content._lines[i:i+n]
616
if delta:
617
if not annotated:
618
reference_content = self._get_content(parents[0], parent_texts)
619
new_texts = content.text()
620
old_texts = reference_content.text()
621
delta_seq = patiencediff.PatienceSequenceMatcher(
622
None, old_texts, new_texts)
623
return self._make_line_delta(delta_seq, content)
624
625
def _make_line_delta(self, delta_seq, new_content):
626
"""Generate a line delta from delta_seq and new_content."""
627
diff_hunks = []
628
for op in delta_seq.get_opcodes():
629
if op[0] == 'equal':
630
continue
631
diff_hunks.append((op[1], op[2], op[4]-op[3], new_content._lines[op[3]:op[4]]))
632
return diff_hunks
633
634
def _get_components_positions(self, version_ids):
635
"""Produce a map of position data for the components of versions.
923
636
924
637
This data is intended to be used for retrieving the knit records.
925
638
926
A dict of key to (record_details, index_memo, next, parents) is
639
A dict of version_id to (method, data_pos, data_size, next) is
927
640
returned.
928
641
method is the way referenced data should be applied.
929
index_memo is the handle to pass to the data access to actually get the
930
data
642
data_pos is the position of the data in the knit.
643
data_size is the size of the data in the knit.
931
644
next is the build-parent of the version, or None for fulltexts.
932
parents is the version_ids of the parents of this version
933
934
:param allow_missing: If True do not raise an error on a missing component,
935
just ignore it.
936
645
"""
937
646
component_data = {}
938
pending_components = keys
939
while pending_components:
940
build_details = self._index.get_build_details(pending_components)
941
current_components = set(pending_components)
942
pending_components = set()
943
for key, details in build_details.iteritems():
944
(index_memo, compression_parent, parents,
945
record_details) = details
946
method = record_details[0]
947
if compression_parent is not None:
948
pending_components.add(compression_parent)
949
component_data[key] = self._build_details_to_components(details)
950
missing = current_components.difference(build_details)
951
if missing and not allow_missing:
952
raise errors.RevisionNotPresent(missing.pop(), self)
647
for version_id in version_ids:
648
cursor = version_id
649
650
while cursor is not None and cursor not in component_data:
651
method = self._index.get_method(cursor)
652
if method == 'fulltext':
653
next = None
654
else:
655
next = self.get_parents(cursor)[0]
656
data_pos, data_size = self._index.get_position(cursor)
657
component_data[cursor] = (method, data_pos, data_size, next)
658
cursor = next
953
659
return component_data
954
660
955
def _get_content(self, key, parent_texts={}):
661
def _get_content(self, version_id, parent_texts={}):
956
662
"""Returns a content object that makes up the specified
957
663
version."""
958
cached_version = parent_texts.get(key, None)
664
if not self.has_version(version_id):
665
raise RevisionNotPresent(version_id, self.filename)
666
667
cached_version = parent_texts.get(version_id, None)
959
668
if cached_version is not None:
960
# Ensure the cache dict is valid.
961
if not self.get_parent_map([key]):
962
raise RevisionNotPresent(key, self)
963
669
return cached_version
964
text_map, contents_map = self._get_content_maps([key])
965
return contents_map[key]
966
967
def _get_content_maps(self, keys, nonlocal_keys=None):
670
671
text_map, contents_map = self._get_content_maps([version_id])
672
return contents_map[version_id]
673
674
def _check_versions_present(self, version_ids):
675
"""Check that all specified versions are present."""
676
self._index.check_versions_present(version_ids)
677
678
def _add_lines_with_ghosts(self, version_id, parents, lines, parent_texts):
679
"""See VersionedFile.add_lines_with_ghosts()."""
680
self._check_add(version_id, lines)
681
return self._add(version_id, lines[:], parents, self.delta, parent_texts)
682
683
def _add_lines(self, version_id, parents, lines, parent_texts):
684
"""See VersionedFile.add_lines."""
685
self._check_add(version_id, lines)
686
self._check_versions_present(parents)
687
return self._add(version_id, lines[:], parents, self.delta, parent_texts)
688
689
def _check_add(self, version_id, lines):
690
"""check that version_id and lines are safe to add."""
691
assert self.writable, "knit is not opened for write"
692
### FIXME escape. RBC 20060228
693
if contains_whitespace(version_id):
694
raise InvalidRevisionId(version_id, self.filename)
695
self.check_not_reserved_id(version_id)
696
if self.has_version(version_id):
697
raise RevisionAlreadyPresent(version_id, self.filename)
698
self._check_lines_not_unicode(lines)
699
self._check_lines_are_lines(lines)
700
701
def _add(self, version_id, lines, parents, delta, parent_texts):
702
"""Add a set of lines on top of version specified by parents.
703
704
If delta is true, compress the text as a line-delta against
705
the first parent.
706
707
Any versions not present will be converted into ghosts.
708
"""
709
# 461 0 6546.0390 43.9100 bzrlib.knit:489(_add)
710
# +400 0 889.4890 418.9790 +bzrlib.knit:192(lower_fulltext)
711
# +461 0 1364.8070 108.8030 +bzrlib.knit:996(add_record)
712
# +461 0 193.3940 41.5720 +bzrlib.knit:898(add_version)
713
# +461 0 134.0590 18.3810 +bzrlib.osutils:361(sha_strings)
714
# +461 0 36.3420 15.4540 +bzrlib.knit:146(make)
715
# +1383 0 8.0370 8.0370 +<len>
716
# +61 0 13.5770 7.9190 +bzrlib.knit:199(lower_line_delta)
717
# +61 0 963.3470 7.8740 +bzrlib.knit:427(_get_content)
718
# +61 0 973.9950 5.2950 +bzrlib.knit:136(line_delta)
719
# +61 0 1918.1800 5.2640 +bzrlib.knit:359(_merge_annotations)
720
721
present_parents = []
722
ghosts = []
723
if parent_texts is None:
724
parent_texts = {}
725
for parent in parents:
726
if not self.has_version(parent):
727
ghosts.append(parent)
728
else:
729
present_parents.append(parent)
730
731
if delta and not len(present_parents):
732
delta = False
733
734
digest = sha_strings(lines)
735
options = []
736
if lines:
737
if lines[-1][-1] != '\n':
738
options.append('no-eol')
739
lines[-1] = lines[-1] + '\n'
740
741
if len(present_parents) and delta:
742
# To speed the extract of texts the delta chain is limited
743
# to a fixed number of deltas. This should minimize both
744
# I/O and the time spend applying deltas.
745
delta = self._check_should_delta(present_parents)
746
747
assert isinstance(version_id, str)
748
lines = self.factory.make(lines, version_id)
749
if delta or (self.factory.annotated and len(present_parents) > 0):
750
# Merge annotations from parent texts if so is needed.
751
delta_hunks = self._merge_annotations(lines, present_parents, parent_texts,
752
delta, self.factory.annotated)
753
754
if delta:
755
options.append('line-delta')
756
store_lines = self.factory.lower_line_delta(delta_hunks)
757
else:
758
options.append('fulltext')
759
store_lines = self.factory.lower_fulltext(lines)
760
761
where, size = self._data.add_record(version_id, digest, store_lines)
762
self._index.add_version(version_id, options, where, size, parents)
763
return lines
764
765
def check(self, progress_bar=None):
766
"""See VersionedFile.check()."""
767
768
def _clone_text(self, new_version_id, old_version_id, parents):
769
"""See VersionedFile.clone_text()."""
770
# FIXME RBC 20060228 make fast by only inserting an index with null
771
# delta.
772
self.add_lines(new_version_id, parents, self.get_lines(old_version_id))
773
774
def get_lines(self, version_id):
775
"""See VersionedFile.get_lines()."""
776
return self.get_line_list([version_id])[0]
777
778
def _get_record_map(self, version_ids):
779
"""Produce a dictionary of knit records.
780
781
The keys are version_ids, the values are tuples of (method, content,
782
digest, next).
783
method is the way the content should be applied.
784
content is a KnitContent object.
785
digest is the SHA1 digest of this version id after all steps are done
786
next is the build-parent of the version, i.e. the leftmost ancestor.
787
If the method is fulltext, next will be None.
788
"""
789
position_map = self._get_components_positions(version_ids)
790
# c = component_id, m = method, p = position, s = size, n = next
791
records = [(c, p, s) for c, (m, p, s, n) in position_map.iteritems()]
792
record_map = {}
793
for component_id, content, digest in \
794
self._data.read_records_iter(records):
795
method, position, size, next = position_map[component_id]
796
record_map[component_id] = method, content, digest, next
797
798
return record_map
799
800
def get_text(self, version_id):
801
"""See VersionedFile.get_text"""
802
return self.get_texts([version_id])[0]
803
804
def get_texts(self, version_ids):
805
return [''.join(l) for l in self.get_line_list(version_ids)]
806
807
def get_line_list(self, version_ids):
808
"""Return the texts of listed versions as a list of strings."""
809
version_ids = [osutils.safe_revision_id(v) for v in version_ids]
810
for version_id in version_ids:
811
self.check_not_reserved_id(version_id)
812
text_map, content_map = self._get_content_maps(version_ids)
813
return [text_map[v] for v in version_ids]
814
815
def _get_content_maps(self, version_ids):
968
816
"""Produce maps of text and KnitContents
969
817
970
:param keys: The keys to produce content maps for.
971
:param nonlocal_keys: An iterable of keys(possibly intersecting keys)
972
which are known to not be in this knit, but rather in one of the
973
fallback knits.
974
818
:return: (text_map, content_map) where text_map contains the texts for
975
the requested versions and content_map contains the KnitContents.
819
the requested versions and content_map contains the KnitContents.
820
Both dicts take version_ids as their keys.
976
821
"""
977
# FUTURE: This function could be improved for the 'extract many' case
978
# by tracking each component and only doing the copy when the number of
979
# children than need to apply delta's to it is > 1 or it is part of the
980
# final output.
981
keys = list(keys)
982
multiple_versions = len(keys) != 1
983
record_map = self._get_record_map(keys, allow_missing=True)
822
for version_id in version_ids:
823
if not self.has_version(version_id):
824
raise RevisionNotPresent(version_id, self.filename)
825
record_map = self._get_record_map(version_ids)
984
826
985
827
text_map = {}
986
828
content_map = {}
987
829
final_content = {}
988
if nonlocal_keys is None:
989
nonlocal_keys = set()
990
else:
991
nonlocal_keys = frozenset(nonlocal_keys)
992
missing_keys = set(nonlocal_keys)
993
for source in self._fallback_vfs:
994
if not missing_keys:
995
break
996
for record in source.get_record_stream(missing_keys,
997
'unordered', True):
998
if record.storage_kind == 'absent':
999
continue
1000
missing_keys.remove(record.key)
1001
lines = split_lines(record.get_bytes_as('fulltext'))
1002
text_map[record.key] = lines
1003
content_map[record.key] = PlainKnitContent(lines, record.key)
1004
if record.key in keys:
1005
final_content[record.key] = content_map[record.key]
1006
for key in keys:
1007
if key in nonlocal_keys:
1008
# already handled
1009
continue
830
for version_id in version_ids:
1010
831
components = []
1011
cursor = key
832
cursor = version_id
1012
833
while cursor is not None:
1013
try:
1014
record, record_details, digest, next = record_map[cursor]
1015
except KeyError:
1016
raise RevisionNotPresent(cursor, self)
1017
components.append((cursor, record, record_details, digest))
1018
cursor = next
834
method, data, digest, next = record_map[cursor]
835
components.append((cursor, method, data, digest))
1019
836
if cursor in content_map:
1020
# no need to plan further back
1021
components.append((cursor, None, None, None))
1022
837
break
838
cursor = next
1023
839
1024
840
content = None
1025
for (component_id, record, record_details,
1026
digest) in reversed(components):
841
for component_id, method, data, digest in reversed(components):
1027
842
if component_id in content_map:
1028
843
content = content_map[component_id]
1029
844
else:
1030
content, delta = self._factory.parse_record(key[-1],
1031
record, record_details, content,
1032
copy_base_content=multiple_versions)
1033
if multiple_versions:
1034
content_map[component_id] = content
845
if method == 'fulltext':
846
assert content is None
847
content = self.factory.parse_fulltext(data, version_id)
848
elif method == 'line-delta':
849
delta = self.factory.parse_line_delta(data, version_id)
850
content = content.copy()
851
content._lines = self._apply_delta(content._lines,
852
delta)
853
content_map[component_id] = content
1035
854
1036
final_content[key] = content
855
if 'no-eol' in self._index.get_options(version_id):
856
content = content.copy()
857
line = content._lines[-1][1].rstrip('\n')
858
content._lines[-1] = (content._lines[-1][0], line)
859
final_content[version_id] = content
1037
860
1038
861
# digest here is the digest from the last applied component.
1039
862
text = content.text()
1040
actual_sha = sha_strings(text)
1041
if actual_sha != digest:
1042
raise KnitCorrupt(self,
1043
'\n sha-1 %s'
1044
'\n of reconstructed text does not match'
1045
'\n expected %s'
1046
'\n for version %s' %
1047
(actual_sha, digest, key))
1048
text_map[key] = text
1049
return text_map, final_content
1050
1051
def get_parent_map(self, keys):
1052
"""Get a map of the graph parents of keys.
1053
1054
:param keys: The keys to look up parents for.
1055
:return: A mapping from keys to parents. Absent keys are absent from
1056
the mapping.
1057
"""
1058
return self._get_parent_map_with_sources(keys)[0]
1059
1060
def _get_parent_map_with_sources(self, keys):
1061
"""Get a map of the parents of keys.
1062
1063
:param keys: The keys to look up parents for.
1064
:return: A tuple. The first element is a mapping from keys to parents.
1065
Absent keys are absent from the mapping. The second element is a
1066
list with the locations each key was found in. The first element
1067
is the in-this-knit parents, the second the first fallback source,
1068
and so on.
1069
"""
1070
result = {}
1071
sources = [self._index] + self._fallback_vfs
1072
source_results = []
1073
missing = set(keys)
1074
for source in sources:
1075
if not missing:
1076
break
1077
new_result = source.get_parent_map(missing)
1078
source_results.append(new_result)
1079
result.update(new_result)
1080
missing.difference_update(set(new_result))
1081
return result, source_results
1082
1083
def _get_record_map(self, keys, allow_missing=False):
1084
"""Produce a dictionary of knit records.
1085
1086
:return: {key:(record, record_details, digest, next)}
1087
record
1088
data returned from read_records
1089
record_details
1090
opaque information to pass to parse_record
1091
digest
1092
SHA1 digest of the full text after all steps are done
1093
next
1094
build-parent of the version, i.e. the leftmost ancestor.
1095
Will be None if the record is not a delta.
1096
:param keys: The keys to build a map for
1097
:param allow_missing: If some records are missing, rather than
1098
error, just return the data that could be generated.
1099
"""
1100
position_map = self._get_components_positions(keys,
1101
allow_missing=allow_missing)
1102
# key = component_id, r = record_details, i_m = index_memo, n = next
1103
records = [(key, i_m) for key, (r, i_m, n)
1104
in position_map.iteritems()]
1105
record_map = {}
1106
for key, record, digest in \
1107
self._read_records_iter(records):
1108
(record_details, index_memo, next) = position_map[key]
1109
record_map[key] = record, record_details, digest, next
1110
return record_map
1111
1112
def get_record_stream(self, keys, ordering, include_delta_closure):
1113
"""Get a stream of records for keys.
1114
1115
:param keys: The keys to include.
1116
:param ordering: Either 'unordered' or 'topological'. A topologically
1117
sorted stream has compression parents strictly before their
1118
children.
1119
:param include_delta_closure: If True then the closure across any
1120
compression parents will be included (in the opaque data).
1121
:return: An iterator of ContentFactory objects, each of which is only
1122
valid until the iterator is advanced.
1123
"""
1124
# keys might be a generator
1125
keys = set(keys)
1126
if not keys:
1127
return
1128
if not self._index.has_graph:
1129
# Cannot topological order when no graph has been stored.
1130
ordering = 'unordered'
1131
if include_delta_closure:
1132
positions = self._get_components_positions(keys, allow_missing=True)
1133
else:
1134
build_details = self._index.get_build_details(keys)
1135
# map from key to
1136
# (record_details, access_memo, compression_parent_key)
1137
positions = dict((key, self._build_details_to_components(details))
1138
for key, details in build_details.iteritems())
1139
absent_keys = keys.difference(set(positions))
1140
# There may be more absent keys : if we're missing the basis component
1141
# and are trying to include the delta closure.
1142
if include_delta_closure:
1143
needed_from_fallback = set()
1144
# Build up reconstructable_keys dict. key:True in this dict means
1145
# the key can be reconstructed.
1146
reconstructable_keys = {}
1147
for key in keys:
1148
# the delta chain
1149
try:
1150
chain = [key, positions[key][2]]
1151
except KeyError:
1152
needed_from_fallback.add(key)
1153
continue
1154
result = True
1155
while chain[-1] is not None:
1156
if chain[-1] in reconstructable_keys:
1157
result = reconstructable_keys[chain[-1]]
1158
break
1159
else:
1160
try:
1161
chain.append(positions[chain[-1]][2])
1162
except KeyError:
1163
# missing basis component
1164
needed_from_fallback.add(chain[-1])
1165
result = True
1166
break
1167
for chain_key in chain[:-1]:
1168
reconstructable_keys[chain_key] = result
1169
if not result:
1170
needed_from_fallback.add(key)
1171
# Double index lookups here : need a unified api ?
1172
global_map, parent_maps = self._get_parent_map_with_sources(keys)
1173
if ordering == 'topological':
1174
# Global topological sort
1175
present_keys = tsort.topo_sort(global_map)
1176
# Now group by source:
1177
source_keys = []
1178
current_source = None
1179
for key in present_keys:
1180
for parent_map in parent_maps:
1181
if key in parent_map:
1182
key_source = parent_map
1183
break
1184
if current_source is not key_source:
1185
source_keys.append((key_source, []))
1186
current_source = key_source
1187
source_keys[-1][1].append(key)
1188
else:
1189
# Just group by source; remote sources first.
1190
present_keys = []
1191
source_keys = []
1192
for parent_map in reversed(parent_maps):
1193
source_keys.append((parent_map, []))
1194
for key in parent_map:
1195
present_keys.append(key)
1196
source_keys[-1][1].append(key)
1197
absent_keys = keys - set(global_map)
1198
for key in absent_keys:
1199
yield AbsentContentFactory(key)
1200
# restrict our view to the keys we can answer.
1201
# XXX: Memory: TODO: batch data here to cap buffered data at (say) 1MB.
1202
# XXX: At that point we need to consider the impact of double reads by
1203
# utilising components multiple times.
1204
if include_delta_closure:
1205
# XXX: get_content_maps performs its own index queries; allow state
1206
# to be passed in.
1207
text_map, _ = self._get_content_maps(present_keys,
1208
needed_from_fallback - absent_keys)
1209
for key in present_keys:
1210
yield FulltextContentFactory(key, global_map[key], None,
1211
''.join(text_map[key]))
1212
else:
1213
for source, keys in source_keys:
1214
if source is parent_maps[0]:
1215
# this KnitVersionedFiles
1216
records = [(key, positions[key][1]) for key in keys]
1217
for key, raw_data, sha1 in self._read_records_iter_raw(records):
1218
(record_details, index_memo, _) = positions[key]
1219
yield KnitContentFactory(key, global_map[key],
1220
record_details, sha1, raw_data, self._factory.annotated, None)
1221
else:
1222
vf = self._fallback_vfs[parent_maps.index(source) - 1]
1223
for record in vf.get_record_stream(keys, ordering,
1224
include_delta_closure):
1225
yield record
1226
1227
def get_sha1s(self, keys):
1228
"""See VersionedFiles.get_sha1s()."""
1229
missing = set(keys)
1230
record_map = self._get_record_map(missing, allow_missing=True)
1231
result = {}
1232
for key, details in record_map.iteritems():
1233
if key not in missing:
1234
continue
1235
# record entry 2 is the 'digest'.
1236
result[key] = details[2]
1237
missing.difference_update(set(result))
1238
for source in self._fallback_vfs:
1239
if not missing:
1240
break
1241
new_result = source.get_sha1s(missing)
1242
result.update(new_result)
1243
missing.difference_update(set(new_result))
1244
return result
1245
1246
def insert_record_stream(self, stream):
1247
"""Insert a record stream into this container.
1248
1249
:param stream: A stream of records to insert.
1250
:return: None
1251
:seealso VersionedFiles.get_record_stream:
1252
"""
1253
def get_adapter(adapter_key):
1254
try:
1255
return adapters[adapter_key]
1256
except KeyError:
1257
adapter_factory = adapter_registry.get(adapter_key)
1258
adapter = adapter_factory(self)
1259
adapters[adapter_key] = adapter
1260
return adapter
1261
if self._factory.annotated:
1262
# self is annotated, we need annotated knits to use directly.
1263
annotated = "annotated-"
1264
convertibles = []
1265
else:
1266
# self is not annotated, but we can strip annotations cheaply.
1267
annotated = ""
1268
convertibles = set(["knit-annotated-ft-gz"])
1269
if self._max_delta_chain:
1270
convertibles.add("knit-annotated-delta-gz")
1271
# The set of types we can cheaply adapt without needing basis texts.
1272
native_types = set()
1273
if self._max_delta_chain:
1274
native_types.add("knit-%sdelta-gz" % annotated)
1275
native_types.add("knit-%sft-gz" % annotated)
1276
knit_types = native_types.union(convertibles)
1277
adapters = {}
1278
# Buffer all index entries that we can't add immediately because their
1279
# basis parent is missing. We don't buffer all because generating
1280
# annotations may require access to some of the new records. However we
1281
# can't generate annotations from new deltas until their basis parent
1282
# is present anyway, so we get away with not needing an index that
1283
# includes the new keys.
1284
# key = basis_parent, value = index entry to add
1285
buffered_index_entries = {}
1286
for record in stream:
1287
parents = record.parents
1288
# Raise an error when a record is missing.
1289
if record.storage_kind == 'absent':
1290
raise RevisionNotPresent([record.key], self)
1291
if record.storage_kind in knit_types:
1292
if record.storage_kind not in native_types:
1293
try:
1294
adapter_key = (record.storage_kind, "knit-delta-gz")
1295
adapter = get_adapter(adapter_key)
1296
except KeyError:
1297
adapter_key = (record.storage_kind, "knit-ft-gz")
1298
adapter = get_adapter(adapter_key)
1299
bytes = adapter.get_bytes(
1300
record, record.get_bytes_as(record.storage_kind))
1301
else:
1302
bytes = record.get_bytes_as(record.storage_kind)
1303
options = [record._build_details[0]]
1304
if record._build_details[1]:
1305
options.append('no-eol')
1306
# Just blat it across.
1307
# Note: This does end up adding data on duplicate keys. As
1308
# modern repositories use atomic insertions this should not
1309
# lead to excessive growth in the event of interrupted fetches.
1310
# 'knit' repositories may suffer excessive growth, but as a
1311
# deprecated format this is tolerable. It can be fixed if
1312
# needed by in the kndx index support raising on a duplicate
1313
# add with identical parents and options.
1314
access_memo = self._access.add_raw_records(
1315
[(record.key, len(bytes))], bytes)[0]
1316
index_entry = (record.key, options, access_memo, parents)
1317
buffered = False
1318
if 'fulltext' not in options:
1319
basis_parent = parents[0]
1320
# Note that pack backed knits don't need to buffer here
1321
# because they buffer all writes to the transaction level,
1322
# but we don't expose that difference at the index level. If
1323
# the query here has sufficient cost to show up in
1324
# profiling we should do that.
1325
if basis_parent not in self.get_parent_map([basis_parent]):
1326
pending = buffered_index_entries.setdefault(
1327
basis_parent, [])
1328
pending.append(index_entry)
1329
buffered = True
1330
if not buffered:
1331
self._index.add_records([index_entry])
1332
elif record.storage_kind == 'fulltext':
1333
self.add_lines(record.key, parents,
1334
split_lines(record.get_bytes_as('fulltext')))
1335
else:
1336
adapter_key = record.storage_kind, 'fulltext'
1337
adapter = get_adapter(adapter_key)
1338
lines = split_lines(adapter.get_bytes(
1339
record, record.get_bytes_as(record.storage_kind)))
1340
try:
1341
self.add_lines(record.key, parents, lines)
1342
except errors.RevisionAlreadyPresent:
1343
pass
1344
# Add any records whose basis parent is now available.
1345
added_keys = [record.key]
1346
while added_keys:
1347
key = added_keys.pop(0)
1348
if key in buffered_index_entries:
1349
index_entries = buffered_index_entries[key]
1350
self._index.add_records(index_entries)
1351
added_keys.extend(
1352
[index_entry[0] for index_entry in index_entries])
1353
del buffered_index_entries[key]
1354
# If there were any deltas which had a missing basis parent, error.
1355
if buffered_index_entries:
1356
raise errors.RevisionNotPresent(buffered_index_entries.keys()[0],
1357
self)
1358
1359
def iter_lines_added_or_present_in_keys(self, keys, pb=None):
1360
"""Iterate over the lines in the versioned files from keys.
1361
1362
This may return lines from other keys. Each item the returned
1363
iterator yields is a tuple of a line and a text version that that line
1364
is present in (not introduced in).
1365
1366
Ordering of results is in whatever order is most suitable for the
1367
underlying storage format.
1368
1369
If a progress bar is supplied, it may be used to indicate progress.
1370
The caller is responsible for cleaning up progress bars (because this
1371
is an iterator).
1372
1373
NOTES:
1374
* Lines are normalised by the underlying store: they will all have \n
1375
terminators.
1376
* Lines are returned in arbitrary order.
1377
1378
:return: An iterator over (line, key).
1379
"""
863
if sha_strings(text) != digest:
864
raise KnitCorrupt(self.filename,
865
'sha-1 does not match %s' % version_id)
866
867
text_map[version_id] = text
868
return text_map, final_content
869
870
def iter_lines_added_or_present_in_versions(self, version_ids=None,
871
pb=None):
872
"""See VersionedFile.iter_lines_added_or_present_in_versions()."""
873
if version_ids is None:
874
version_ids = self.versions()
875
else:
876
version_ids = [osutils.safe_revision_id(v) for v in version_ids]
1380
877
if pb is None:
1381
878
pb = progress.DummyProgress()
1382
keys = set(keys)
1383
total = len(keys)
1384
879
# we don't care about inclusions, the caller cares.
1385
880
# but we need to setup a list of records to visit.
1386
# we need key, position, length
1387
key_records = []
1388
build_details = self._index.get_build_details(keys)
1389
for key, details in build_details.iteritems():
1390
if key in keys:
1391
key_records.append((key, details[0]))
1392
keys.remove(key)
1393
records_iter = enumerate(self._read_records_iter(key_records))
1394
for (key_idx, (key, data, sha_value)) in records_iter:
1395
pb.update('Walking content.', key_idx, total)
1396
compression_parent = build_details[key][1]
1397
if compression_parent is None:
1398
# fulltext
1399
line_iterator = self._factory.get_fulltext_content(data)
881
# we need version_id, position, length
882
version_id_records = []
883
requested_versions = set(version_ids)
884
# filter for available versions
885
for version_id in requested_versions:
886
if not self.has_version(version_id):
887
raise RevisionNotPresent(version_id, self.filename)
888
# get a in-component-order queue:
889
for version_id in self.versions():
890
if version_id in requested_versions:
891
data_pos, length = self._index.get_position(version_id)
892
version_id_records.append((version_id, data_pos, length))
893
894
total = len(version_id_records)
895
for version_idx, (version_id, data, sha_value) in \
896
enumerate(self._data.read_records_iter(version_id_records)):
897
pb.update('Walking content.', version_idx, total)
898
method = self._index.get_method(version_id)
899
900
assert method in ('fulltext', 'line-delta')
901
if method == 'fulltext':
902
line_iterator = self.factory.get_fulltext_content(data)
1400
903
else:
1401
# Delta
1402
line_iterator = self._factory.get_linedelta_content(data)
1403
# XXX: It might be more efficient to yield (key,
1404
# line_iterator) in the future. However for now, this is a simpler
1405
# change to integrate into the rest of the codebase. RBC 20071110
904
line_iterator = self.factory.get_linedelta_content(data)
1406
905
for line in line_iterator:
1407
yield line, key
1408
for source in self._fallback_vfs:
1409
if not keys:
1410
break
1411
source_keys = set()
1412
for line, key in source.iter_lines_added_or_present_in_keys(keys):
1413
source_keys.add(key)
1414
yield line, key
1415
keys.difference_update(source_keys)
1416
if keys:
1417
raise RevisionNotPresent(keys, self.filename)
906
yield line
907
1418
908
pb.update('Walking content.', total, total)
1419
1420
def _make_line_delta(self, delta_seq, new_content):
1421
"""Generate a line delta from delta_seq and new_content."""
1422
diff_hunks = []
1423
for op in delta_seq.get_opcodes():
1424
if op[0] == 'equal':
1425
continue
1426
diff_hunks.append((op[1], op[2], op[4]-op[3], new_content._lines[op[3]:op[4]]))
1427
return diff_hunks
1428
1429
def _merge_annotations(self, content, parents, parent_texts={},
1430
delta=None, annotated=None,
1431
left_matching_blocks=None):
1432
"""Merge annotations for content and generate deltas.
1433
1434
This is done by comparing the annotations based on changes to the text
1435
and generating a delta on the resulting full texts. If annotations are
1436
not being created then a simple delta is created.
1437
"""
1438
if left_matching_blocks is not None:
1439
delta_seq = diff._PrematchedMatcher(left_matching_blocks)
1440
else:
1441
delta_seq = None
1442
if annotated:
1443
for parent_key in parents:
1444
merge_content = self._get_content(parent_key, parent_texts)
1445
if (parent_key == parents[0] and delta_seq is not None):
1446
seq = delta_seq
1447
else:
1448
seq = patiencediff.PatienceSequenceMatcher(
1449
None, merge_content.text(), content.text())
1450
for i, j, n in seq.get_matching_blocks():
1451
if n == 0:
1452
continue
1453
# this copies (origin, text) pairs across to the new
1454
# content for any line that matches the last-checked
1455
# parent.
1456
content._lines[j:j+n] = merge_content._lines[i:i+n]
1457
# XXX: Robert says the following block is a workaround for a
1458
# now-fixed bug and it can probably be deleted. -- mbp 20080618
1459
if content._lines and content._lines[-1][1][-1] != '\n':
1460
# The copied annotation was from a line without a trailing EOL,
1461
# reinstate one for the content object, to ensure correct
1462
# serialization.
1463
line = content._lines[-1][1] + '\n'
1464
content._lines[-1] = (content._lines[-1][0], line)
1465
if delta:
1466
if delta_seq is None:
1467
reference_content = self._get_content(parents[0], parent_texts)
1468
new_texts = content.text()
1469
old_texts = reference_content.text()
1470
delta_seq = patiencediff.PatienceSequenceMatcher(
1471
None, old_texts, new_texts)
1472
return self._make_line_delta(delta_seq, content)
1473
1474
def _parse_record(self, version_id, data):
1475
"""Parse an original format knit record.
1476
1477
These have the last element of the key only present in the stored data.
1478
"""
1479
rec, record_contents = self._parse_record_unchecked(data)
1480
self._check_header_version(rec, version_id)
1481
return record_contents, rec[3]
1482
1483
def _parse_record_header(self, key, raw_data):
1484
"""Parse a record header for consistency.
1485
1486
:return: the header and the decompressor stream.
1487
as (stream, header_record)
1488
"""
1489
df = tuned_gzip.GzipFile(mode='rb', fileobj=StringIO(raw_data))
1490
try:
1491
# Current serialise
1492
rec = self._check_header(key, df.readline())
1493
except Exception, e:
1494
raise KnitCorrupt(self,
1495
"While reading {%s} got %s(%s)"
1496
% (key, e.__class__.__name__, str(e)))
1497
return df, rec
1498
1499
def _parse_record_unchecked(self, data):
1500
# profiling notes:
1501
# 4168 calls in 2880 217 internal
1502
# 4168 calls to _parse_record_header in 2121
1503
# 4168 calls to readlines in 330
1504
df = tuned_gzip.GzipFile(mode='rb', fileobj=StringIO(data))
1505
try:
1506
record_contents = df.readlines()
1507
except Exception, e:
1508
raise KnitCorrupt(self, "Corrupt compressed record %r, got %s(%s)" %
1509
(data, e.__class__.__name__, str(e)))
1510
header = record_contents.pop(0)
1511
rec = self._split_header(header)
1512
last_line = record_contents.pop()
1513
if len(record_contents) != int(rec[2]):
1514
raise KnitCorrupt(self,
1515
'incorrect number of lines %s != %s'
1516
' for version {%s} %s'
1517
% (len(record_contents), int(rec[2]),
1518
rec[1], record_contents))
1519
if last_line != 'end %s\n' % rec[1]:
1520
raise KnitCorrupt(self,
1521
'unexpected version end line %r, wanted %r'
1522
% (last_line, rec[1]))
1523
df.close()
1524
return rec, record_contents
1525
1526
def _read_records_iter(self, records):
1527
"""Read text records from data file and yield result.
1528
1529
The result will be returned in whatever is the fastest to read.
1530
Not by the order requested. Also, multiple requests for the same
1531
record will only yield 1 response.
1532
:param records: A list of (key, access_memo) entries
1533
:return: Yields (key, contents, digest) in the order
1534
read, not the order requested
1535
"""
1536
if not records:
1537
return
1538
1539
# XXX: This smells wrong, IO may not be getting ordered right.
1540
needed_records = sorted(set(records), key=operator.itemgetter(1))
1541
if not needed_records:
1542
return
1543
1544
# The transport optimizes the fetching as well
1545
# (ie, reads continuous ranges.)
1546
raw_data = self._access.get_raw_records(
1547
[index_memo for key, index_memo in needed_records])
1548
1549
for (key, index_memo), data in \
1550
izip(iter(needed_records), raw_data):
1551
content, digest = self._parse_record(key[-1], data)
1552
yield key, content, digest
1553
1554
def _read_records_iter_raw(self, records):
1555
"""Read text records from data file and yield raw data.
1556
1557
This unpacks enough of the text record to validate the id is
1558
as expected but thats all.
1559
1560
Each item the iterator yields is (key, bytes, sha1_of_full_text).
1561
"""
1562
# setup an iterator of the external records:
1563
# uses readv so nice and fast we hope.
1564
if len(records):
1565
# grab the disk data needed.
1566
needed_offsets = [index_memo for key, index_memo
1567
in records]
1568
raw_records = self._access.get_raw_records(needed_offsets)
1569
1570
for key, index_memo in records:
1571
data = raw_records.next()
1572
# validate the header (note that we can only use the suffix in
1573
# current knit records).
1574
df, rec = self._parse_record_header(key, data)
1575
df.close()
1576
yield key, data, rec[3]
1577
1578
def _record_to_data(self, key, digest, lines, dense_lines=None):
1579
"""Convert key, digest, lines into a raw data block.
1580
1581
:param key: The key of the record. Currently keys are always serialised
1582
using just the trailing component.
1583
:param dense_lines: The bytes of lines but in a denser form. For
1584
instance, if lines is a list of 1000 bytestrings each ending in \n,
1585
dense_lines may be a list with one line in it, containing all the
1586
1000's lines and their \n's. Using dense_lines if it is already
1587
known is a win because the string join to create bytes in this
1588
function spends less time resizing the final string.
1589
:return: (len, a StringIO instance with the raw data ready to read.)
1590
"""
1591
# Note: using a string copy here increases memory pressure with e.g.
1592
# ISO's, but it is about 3 seconds faster on a 1.2Ghz intel machine
1593
# when doing the initial commit of a mozilla tree. RBC 20070921
1594
bytes = ''.join(chain(
1595
["version %s %d %s\n" % (key[-1],
1596
len(lines),
1597
digest)],
1598
dense_lines or lines,
1599
["end %s\n" % key[-1]]))
1600
if type(bytes) != str:
1601
raise AssertionError(
1602
'data must be plain bytes was %s' % type(bytes))
1603
if lines and lines[-1][-1] != '\n':
1604
raise ValueError('corrupt lines value %r' % lines)
1605
compressed_bytes = tuned_gzip.bytes_to_gzip(bytes)
1606
return len(compressed_bytes), compressed_bytes
1607
1608
def _split_header(self, line):
1609
rec = line.split()
1610
if len(rec) != 4:
1611
raise KnitCorrupt(self,
1612
'unexpected number of elements in record header')
1613
return rec
1614
1615
def keys(self):
1616
"""See VersionedFiles.keys."""
1617
if 'evil' in debug.debug_flags:
1618
trace.mutter_callsite(2, "keys scales with size of history")
1619
sources = [self._index] + self._fallback_vfs
1620
result = set()
1621
for source in sources:
1622
result.update(source.keys())
1623
return result
1624
1625
1626
1627
class _KndxIndex(object):
1628
"""Manages knit index files
1629
1630
The index is kept in memory and read on startup, to enable
909
910
def num_versions(self):
911
"""See VersionedFile.num_versions()."""
912
return self._index.num_versions()
913
914
__len__ = num_versions
915
916
def annotate_iter(self, version_id):
917
"""See VersionedFile.annotate_iter."""
918
version_id = osutils.safe_revision_id(version_id)
919
content = self._get_content(version_id)
920
for origin, text in content.annotate_iter():
921
yield origin, text
922
923
def get_parents(self, version_id):
924
"""See VersionedFile.get_parents."""
925
# perf notes:
926
# optimism counts!
927
# 52554 calls in 1264 872 internal down from 3674
928
version_id = osutils.safe_revision_id(version_id)
929
try:
930
return self._index.get_parents(version_id)
931
except KeyError:
932
raise RevisionNotPresent(version_id, self.filename)
933
934
def get_parents_with_ghosts(self, version_id):
935
"""See VersionedFile.get_parents."""
936
version_id = osutils.safe_revision_id(version_id)
937
try:
938
return self._index.get_parents_with_ghosts(version_id)
939
except KeyError:
940
raise RevisionNotPresent(version_id, self.filename)
941
942
def get_ancestry(self, versions):
943
"""See VersionedFile.get_ancestry."""
944
if isinstance(versions, basestring):
945
versions = [versions]
946
if not versions:
947
return []
948
versions = [osutils.safe_revision_id(v) for v in versions]
949
return self._index.get_ancestry(versions)
950
951
def get_ancestry_with_ghosts(self, versions):
952
"""See VersionedFile.get_ancestry_with_ghosts."""
953
if isinstance(versions, basestring):
954
versions = [versions]
955
if not versions:
956
return []
957
versions = [osutils.safe_revision_id(v) for v in versions]
958
return self._index.get_ancestry_with_ghosts(versions)
959
960
#@deprecated_method(zero_eight)
961
def walk(self, version_ids):
962
"""See VersionedFile.walk."""
963
# We take the short path here, and extract all relevant texts
964
# and put them in a weave and let that do all the work. Far
965
# from optimal, but is much simpler.
966
# FIXME RB 20060228 this really is inefficient!
967
from bzrlib.weave import Weave
968
969
w = Weave(self.filename)
970
ancestry = self.get_ancestry(version_ids)
971
sorted_graph = topo_sort(self._index.get_graph())
972
version_list = [vid for vid in sorted_graph if vid in ancestry]
973
974
for version_id in version_list:
975
lines = self.get_lines(version_id)
976
w.add_lines(version_id, self.get_parents(version_id), lines)
977
978
for lineno, insert_id, dset, line in w.walk(version_ids):
979
yield lineno, insert_id, dset, line
980
981
def plan_merge(self, ver_a, ver_b):
982
"""See VersionedFile.plan_merge."""
983
ver_a = osutils.safe_revision_id(ver_a)
984
ver_b = osutils.safe_revision_id(ver_b)
985
ancestors_b = set(self.get_ancestry(ver_b))
986
def status_a(revision, text):
987
if revision in ancestors_b:
988
return 'killed-b', text
989
else:
990
return 'new-a', text
991
992
ancestors_a = set(self.get_ancestry(ver_a))
993
def status_b(revision, text):
994
if revision in ancestors_a:
995
return 'killed-a', text
996
else:
997
return 'new-b', text
998
999
annotated_a = self.annotate(ver_a)
1000
annotated_b = self.annotate(ver_b)
1001
plain_a = [t for (a, t) in annotated_a]
1002
plain_b = [t for (a, t) in annotated_b]
1003
blocks = KnitSequenceMatcher(None, plain_a, plain_b).get_matching_blocks()
1004
a_cur = 0
1005
b_cur = 0
1006
for ai, bi, l in blocks:
1007
# process all mismatched sections
1008
# (last mismatched section is handled because blocks always
1009
# includes a 0-length last block)
1010
for revision, text in annotated_a[a_cur:ai]:
1011
yield status_a(revision, text)
1012
for revision, text in annotated_b[b_cur:bi]:
1013
yield status_b(revision, text)
1014
1015
# and now the matched section
1016
a_cur = ai + l
1017
b_cur = bi + l
1018
for text_a, text_b in zip(plain_a[ai:a_cur], plain_b[bi:b_cur]):
1019
assert text_a == text_b
1020
yield "unchanged", text_a
1021
1022
1023
class _KnitComponentFile(object):
1024
"""One of the files used to implement a knit database"""
1025
1026
def __init__(self, transport, filename, mode, file_mode=None,
1027
create_parent_dir=False, dir_mode=None):
1028
self._transport = transport
1029
self._filename = filename
1030
self._mode = mode
1031
self._file_mode = file_mode
1032
self._dir_mode = dir_mode
1033
self._create_parent_dir = create_parent_dir
1034
self._need_to_create = False
1035
1036
def _full_path(self):
1037
"""Return the full path to this file."""
1038
return self._transport.base + self._filename
1039
1040
def check_header(self, fp):
1041
line = fp.readline()
1042
if line == '':
1043
# An empty file can actually be treated as though the file doesn't
1044
# exist yet.
1045
raise errors.NoSuchFile(self._full_path())
1046
if line != self.HEADER:
1047
raise KnitHeaderError(badline=line,
1048
filename=self._transport.abspath(self._filename))
1049
1050
def commit(self):
1051
"""Commit is a nop."""
1052
1053
def __repr__(self):
1054
return '%s(%s)' % (self.__class__.__name__, self._filename)
1055
1056
1057
class _KnitIndex(_KnitComponentFile):
1058
"""Manages knit index file.
1059
1060
The index is already kept in memory and read on startup, to enable
1631
1061
fast lookups of revision information. The cursor of the index
1632
1062
file is always pointing to the end, making it easy to append
1633
1063
entries.
1675
1105
to ensure that records always start on new lines even if the last write was
1676
1106
interrupted. As a result its normal for the last line in the index to be
1677
1107
missing a trailing newline. One can be added with no harmful effects.
1678
1679
:ivar _kndx_cache: dict from prefix to the old state of KnitIndex objects,
1680
where prefix is e.g. the (fileid,) for .texts instances or () for
1681
constant-mapped things like .revisions, and the old state is
1682
tuple(history_vector, cache_dict). This is used to prevent having an
1683
ABI change with the C extension that reads .kndx files.
1684
1108
"""
1685
1109
1686
1110
HEADER = "# bzr knit index 8\n"
1687
1111
1688
def __init__(self, transport, mapper, get_scope, allow_writes, is_locked):
1689
"""Create a _KndxIndex on transport using mapper."""
1690
self._transport = transport
1691
self._mapper = mapper
1692
self._get_scope = get_scope
1693
self._allow_writes = allow_writes
1694
self._is_locked = is_locked
1695
self._reset_cache()
1696
self.has_graph = True
1697
1698
def add_records(self, records, random_id=False):
1699
"""Add multiple records to the index.
1700
1701
:param records: a list of tuples:
1702
(key, options, access_memo, parents).
1703
:param random_id: If True the ids being added were randomly generated
1704
and no check for existence will be performed.
1705
"""
1706
paths = {}
1707
for record in records:
1708
key = record[0]
1709
prefix = key[:-1]
1710
path = self._mapper.map(key) + '.kndx'
1711
path_keys = paths.setdefault(path, (prefix, []))
1712
path_keys[1].append(record)
1713
for path in sorted(paths):
1714
prefix, path_keys = paths[path]
1715
self._load_prefixes([prefix])
1716
lines = []
1717
orig_history = self._kndx_cache[prefix][1][:]
1718
orig_cache = self._kndx_cache[prefix][0].copy()
1719
1720
try:
1721
for key, options, (_, pos, size), parents in path_keys:
1722
if parents is None:
1723
# kndx indices cannot be parentless.
1724
parents = ()
1725
line = "\n%s %s %s %s %s :" % (
1726
key[-1], ','.join(options), pos, size,
1727
self._dictionary_compress(parents))
1728
if type(line) != str:
1729
raise AssertionError(
1730
'data must be utf8 was %s' % type(line))
1731
lines.append(line)
1732
self._cache_key(key, options, pos, size, parents)
1733
if len(orig_history):
1734
self._transport.append_bytes(path, ''.join(lines))
1735
else:
1736
self._init_index(path, lines)
1737
except:
1738
# If any problems happen, restore the original values and re-raise
1739
self._kndx_cache[prefix] = (orig_cache, orig_history)
1740
raise
1741
1742
def _cache_key(self, key, options, pos, size, parent_keys):
1112
# speed of knit parsing went from 280 ms to 280 ms with slots addition.
1113
# __slots__ = ['_cache', '_history', '_transport', '_filename']
1114
1115
def _cache_version(self, version_id, options, pos, size, parents):
1743
1116
"""Cache a version record in the history array and index cache.
1744
1117
1745
1118
This is inlined into _load_data for performance. KEEP IN SYNC.
1746
1119
(It saves 60ms, 25% of the __init__ overhead on local 4000 record
1747
1120
indexes).
1748
1121
"""
1749
prefix = key[:-1]
1750
version_id = key[-1]
1751
# last-element only for compatibilty with the C load_data.
1752
parents = tuple(parent[-1] for parent in parent_keys)
1753
for parent in parent_keys:
1754
if parent[:-1] != prefix:
1755
raise ValueError("mismatched prefixes for %r, %r" % (
1756
key, parent_keys))
1757
cache, history = self._kndx_cache[prefix]
1758
1122
# only want the _history index to reference the 1st index entry
1759
1123
# for version_id
1760
if version_id not in cache:
1761
index = len(history)
1762
history.append(version_id)
1124
if version_id not in self._cache:
1125
index = len(self._history)
1126
self._history.append(version_id)
1763
1127
else:
1764
index = cache[version_id][5]
1765
cache[version_id] = (version_id,
1128
index = self._cache[version_id][5]
1129
self._cache[version_id] = (version_id,
1766
1130
options,
1767
1131
pos,
1768
1132
size,
1769
1133
parents,
1770
1134
index)
1771
1135
1772
def check_header(self, fp):
1773
line = fp.readline()
1774
if line == '':
1775
# An empty file can actually be treated as though the file doesn't
1776
# exist yet.
1777
raise errors.NoSuchFile(self)
1778
if line != self.HEADER:
1779
raise KnitHeaderError(badline=line, filename=self)
1780
1781
def _check_read(self):
1782
if not self._is_locked():
1783
raise errors.ObjectNotLocked(self)
1784
if self._get_scope() != self._scope:
1785
self._reset_cache()
1786
1787
def _check_write_ok(self):
1788
"""Assert if not writes are permitted."""
1789
if not self._is_locked():
1790
raise errors.ObjectNotLocked(self)
1791
if self._get_scope() != self._scope:
1792
self._reset_cache()
1793
if self._mode != 'w':
1794
raise errors.ReadOnlyObjectDirtiedError(self)
1795
1796
def get_build_details(self, keys):
1797
"""Get the method, index_memo and compression parent for keys.
1798
1799
Ghosts are omitted from the result.
1800
1801
:param keys: An iterable of keys.
1802
:return: A dict of key:(index_memo, compression_parent, parents,
1803
record_details).
1804
index_memo
1805
opaque structure to pass to read_records to extract the raw
1806
data
1807
compression_parent
1808
Content that this record is built upon, may be None
1809
parents
1810
Logical parents of this node
1811
record_details
1812
extra information about the content which needs to be passed to
1813
Factory.parse_record
1814
"""
1815
prefixes = self._partition_keys(keys)
1816
parent_map = self.get_parent_map(keys)
1817
result = {}
1818
for key in keys:
1819
if key not in parent_map:
1820
continue # Ghost
1821
method = self.get_method(key)
1822
parents = parent_map[key]
1823
if method == 'fulltext':
1824
compression_parent = None
1825
else:
1826
compression_parent = parents[0]
1827
noeol = 'no-eol' in self.get_options(key)
1828
index_memo = self.get_position(key)
1829
result[key] = (index_memo, compression_parent,
1830
parents, (method, noeol))
1831
return result
1832
1833
def get_method(self, key):
1834
"""Return compression method of specified key."""
1835
options = self.get_options(key)
1836
if 'fulltext' in options:
1837
return 'fulltext'
1838
elif 'line-delta' in options:
1839
return 'line-delta'
1840
else:
1841
raise errors.KnitIndexUnknownMethod(self, options)
1842
1843
def get_options(self, key):
1844
"""Return a list representing options.
1845
1846
e.g. ['foo', 'bar']
1847
"""
1848
prefix, suffix = self._split_key(key)
1849
self._load_prefixes([prefix])
1136
def __init__(self, transport, filename, mode, create=False, file_mode=None,
1137
create_parent_dir=False, delay_create=False, dir_mode=None):
1138
_KnitComponentFile.__init__(self, transport, filename, mode,
1139
file_mode=file_mode,
1140
create_parent_dir=create_parent_dir,
1141
dir_mode=dir_mode)
1142
self._cache = {}
1143
# position in _history is the 'official' index for a revision
1144
# but the values may have come from a newer entry.
1145
# so - wc -l of a knit index is != the number of unique names
1146
# in the knit.
1147
self._history = []
1850
1148
try:
1851
return self._kndx_cache[prefix][0][suffix][1]
1852
except KeyError:
1853
raise RevisionNotPresent(key, self)
1854
1855
def get_parent_map(self, keys):
1856
"""Get a map of the parents of keys.
1857
1858
:param keys: The keys to look up parents for.
1859
:return: A mapping from keys to parents. Absent keys are absent from
1860
the mapping.
1861
"""
1862
# Parse what we need to up front, this potentially trades off I/O
1863
# locality (.kndx and .knit in the same block group for the same file
1864
# id) for less checking in inner loops.
1865
prefixes = set(key[:-1] for key in keys)
1866
self._load_prefixes(prefixes)
1867
result = {}
1868
for key in keys:
1869
prefix = key[:-1]
1870
try:
1871
suffix_parents = self._kndx_cache[prefix][0][key[-1]][4]
1872
except KeyError:
1873
pass
1874
else:
1875
result[key] = tuple(prefix + (suffix,) for
1876
suffix in suffix_parents)
1877
return result
1878
1879
def get_position(self, key):
1880
"""Return details needed to access the version.
1881
1882
:return: a tuple (key, data position, size) to hand to the access
1883
logic to get the record.
1884
"""
1885
prefix, suffix = self._split_key(key)
1886
self._load_prefixes([prefix])
1887
entry = self._kndx_cache[prefix][0][suffix]
1888
return key, entry[2], entry[3]
1889
1890
def _init_index(self, path, extra_lines=[]):
1891
"""Initialize an index."""
1892
sio = StringIO()
1893
sio.write(self.HEADER)
1894
sio.writelines(extra_lines)
1895
sio.seek(0)
1896
self._transport.put_file_non_atomic(path, sio,
1897
create_parent_dir=True)
1898
# self._create_parent_dir)
1899
# mode=self._file_mode,
1900
# dir_mode=self._dir_mode)
1901
1902
def keys(self):
1903
"""Get all the keys in the collection.
1904
1905
The keys are not ordered.
1906
"""
1907
result = set()
1908
# Identify all key prefixes.
1909
# XXX: A bit hacky, needs polish.
1910
if type(self._mapper) == ConstantMapper:
1911
prefixes = [()]
1912
else:
1913
relpaths = set()
1914
for quoted_relpath in self._transport.iter_files_recursive():
1915
path, ext = os.path.splitext(quoted_relpath)
1916
relpaths.add(path)
1917
prefixes = [self._mapper.unmap(path) for path in relpaths]
1918
self._load_prefixes(prefixes)
1919
for prefix in prefixes:
1920
for suffix in self._kndx_cache[prefix][1]:
1921
result.add(prefix + (suffix,))
1922
return result
1923
1924
def _load_prefixes(self, prefixes):
1925
"""Load the indices for prefixes."""
1926
self._check_read()
1927
for prefix in prefixes:
1928
if prefix not in self._kndx_cache:
1929
# the load_data interface writes to these variables.
1930
self._cache = {}
1931
self._history = []
1932
self._filename = prefix
1933
try:
1934
path = self._mapper.map(prefix) + '.kndx'
1935
fp = self._transport.get(path)
1936
try:
1937
# _load_data may raise NoSuchFile if the target knit is
1938
# completely empty.
1939
_load_data(self, fp)
1940
finally:
1941
fp.close()
1942
self._kndx_cache[prefix] = (self._cache, self._history)
1943
del self._cache
1944
del self._filename
1945
del self._history
1946
except NoSuchFile:
1947
self._kndx_cache[prefix] = ({}, [])
1948
if type(self._mapper) == ConstantMapper:
1949
# preserve behaviour for revisions.kndx etc.
1950
self._init_index(path)
1951
del self._cache
1952
del self._filename
1953
del self._history
1954
1955
def _partition_keys(self, keys):
1956
"""Turn keys into a dict of prefix:suffix_list."""
1957
result = {}
1958
for key in keys:
1959
prefix_keys = result.setdefault(key[:-1], [])
1960
prefix_keys.append(key[-1])
1961
return result
1962
1963
def _dictionary_compress(self, keys):
1964
"""Dictionary compress keys.
1965
1966
:param keys: The keys to generate references to.
1967
:return: A string representation of keys. keys which are present are
1968
dictionary compressed, and others are emitted as fulltext with a
1969
'.' prefix.
1970
"""
1971
if not keys:
1972
return ''
1149
fp = self._transport.get(self._filename)
1150
try:
1151
# _load_data may raise NoSuchFile if the target knit is
1152
# completely empty.
1153
self._load_data(fp)
1154
finally:
1155
fp.close()
1156
except NoSuchFile:
1157
if mode != 'w' or not create:
1158
raise
1159
elif delay_create:
1160
self._need_to_create = True
1161
else:
1162
self._transport.put_bytes_non_atomic(
1163
self._filename, self.HEADER, mode=self._file_mode)
1164
1165
def _load_data(self, fp):
1166
cache = self._cache
1167
history = self._history
1168
1169
self.check_header(fp)
1170
# readlines reads the whole file at once:
1171
# bad for transports like http, good for local disk
1172
# we save 60 ms doing this one change (
1173
# from calling readline each time to calling
1174
# readlines once.
1175
# probably what we want for nice behaviour on
1176
# http is a incremental readlines that yields, or
1177
# a check for local vs non local indexes,
1178
history_top = len(history) - 1
1179
for line in fp.readlines():
1180
rec = line.split()
1181
if len(rec) < 5 or rec[-1] != ':':
1182
# corrupt line.
1183
# FIXME: in the future we should determine if its a
1184
# short write - and ignore it
1185
# or a different failure, and raise. RBC 20060407
1186
continue
1187
1188
parents = []
1189
for value in rec[4:-1]:
1190
if value[0] == '.':
1191
# uncompressed reference
1192
parent_id = value[1:]
1193
else:
1194
parent_id = history[int(value)]
1195
parents.append(parent_id)
1196
1197
version_id, options, pos, size = rec[:4]
1198
version_id = version_id
1199
1200
# See self._cache_version
1201
# only want the _history index to reference the 1st
1202
# index entry for version_id
1203
if version_id not in cache:
1204
history_top += 1
1205
index = history_top
1206
history.append(version_id)
1207
else:
1208
index = cache[version_id][5]
1209
cache[version_id] = (version_id,
1210
options.split(','),
1211
int(pos),
1212
int(size),
1213
parents,
1214
index)
1215
# end self._cache_version
1216
1217
def get_graph(self):
1218
return [(vid, idx[4]) for vid, idx in self._cache.iteritems()]
1219
1220
def get_ancestry(self, versions):
1221
"""See VersionedFile.get_ancestry."""
1222
# get a graph of all the mentioned versions:
1223
graph = {}
1224
pending = set(versions)
1225
cache = self._cache
1226
while pending:
1227
version = pending.pop()
1228
# trim ghosts
1229
try:
1230
parents = [p for p in cache[version][4] if p in cache]
1231
except KeyError:
1232
raise RevisionNotPresent(version, self._filename)
1233
# if not completed and not a ghost
1234
pending.update([p for p in parents if p not in graph])
1235
graph[version] = parents
1236
return topo_sort(graph.items())
1237
1238
def get_ancestry_with_ghosts(self, versions):
1239
"""See VersionedFile.get_ancestry_with_ghosts."""
1240
# get a graph of all the mentioned versions:
1241
self.check_versions_present(versions)
1242
cache = self._cache
1243
graph = {}
1244
pending = set(versions)
1245
while pending:
1246
version = pending.pop()
1247
try:
1248
parents = cache[version][4]
1249
except KeyError:
1250
# ghost, fake it
1251
graph[version] = []
1252
else:
1253
# if not completed
1254
pending.update([p for p in parents if p not in graph])
1255
graph[version] = parents
1256
return topo_sort(graph.items())
1257
1258
def num_versions(self):
1259
return len(self._history)
1260
1261
__len__ = num_versions
1262
1263
def get_versions(self):
1264
return self._history
1265
1266
def idx_to_name(self, idx):
1267
return self._history[idx]
1268
1269
def lookup(self, version_id):
1270
assert version_id in self._cache
1271
return self._cache[version_id][5]
1272
1273
def _version_list_to_index(self, versions):
1973
1274
result_list = []
1974
prefix = keys[0][:-1]
1975
cache = self._kndx_cache[prefix][0]
1976
for key in keys:
1977
if key[:-1] != prefix:
1978
# kndx indices cannot refer across partitioned storage.
1979
raise ValueError("mismatched prefixes for %r" % keys)
1980
if key[-1] in cache:
1275
cache = self._cache
1276
for version in versions:
1277
if version in cache:
1981
1278
# -- inlined lookup() --
1982
result_list.append(str(cache[key[-1]][5]))
1279
result_list.append(str(cache[version][5]))
1983
1280
# -- end lookup () --
1984
1281
else:
1985
result_list.append('.' + key[-1])
1282
result_list.append('.' + version)
1986
1283
return ' '.join(result_list)
1987
1284
1988
def _reset_cache(self):
1989
# Possibly this should be a LRU cache. A dictionary from key_prefix to
1990
# (cache_dict, history_vector) for parsed kndx files.
1991
self._kndx_cache = {}
1992
self._scope = self._get_scope()
1993
allow_writes = self._allow_writes()
1994
if allow_writes:
1995
self._mode = 'w'
1996
else:
1997
self._mode = 'r'
1998
1999
def _split_key(self, key):
2000
"""Split key into a prefix and suffix."""
2001
return key[:-1], key[-1]
2002
2003
2004
class _KnitGraphIndex(object):
2005
"""A KnitVersionedFiles index layered on GraphIndex."""
2006
2007
def __init__(self, graph_index, is_locked, deltas=False, parents=True,
2008
add_callback=None):
2009
"""Construct a KnitGraphIndex on a graph_index.
2010
2011
:param graph_index: An implementation of bzrlib.index.GraphIndex.
2012
:param is_locked: A callback to check whether the object should answer
2013
queries.
2014
:param deltas: Allow delta-compressed records.
2015
:param parents: If True, record knits parents, if not do not record
2016
parents.
2017
:param add_callback: If not None, allow additions to the index and call
2018
this callback with a list of added GraphIndex nodes:
2019
[(node, value, node_refs), ...]
2020
:param is_locked: A callback, returns True if the index is locked and
2021
thus usable.
2022
"""
2023
self._add_callback = add_callback
2024
self._graph_index = graph_index
2025
self._deltas = deltas
2026
self._parents = parents
2027
if deltas and not parents:
2028
# XXX: TODO: Delta tree and parent graph should be conceptually
2029
# separate.
2030
raise KnitCorrupt(self, "Cannot do delta compression without "
2031
"parent tracking.")
2032
self.has_graph = parents
2033
self._is_locked = is_locked
2034
2035
def __repr__(self):
2036
return "%s(%r)" % (self.__class__.__name__, self._graph_index)
2037
2038
def add_records(self, records, random_id=False):
2039
"""Add multiple records to the index.
2040
2041
This function does not insert data into the Immutable GraphIndex
2042
backing the KnitGraphIndex, instead it prepares data for insertion by
2043
the caller and checks that it is safe to insert then calls
2044
self._add_callback with the prepared GraphIndex nodes.
2045
2046
:param records: a list of tuples:
2047
(key, options, access_memo, parents).
2048
:param random_id: If True the ids being added were randomly generated
2049
and no check for existence will be performed.
2050
"""
2051
if not self._add_callback:
2052
raise errors.ReadOnlyError(self)
2053
# we hope there are no repositories with inconsistent parentage
2054
# anymore.
2055
2056
keys = {}
2057
for (key, options, access_memo, parents) in records:
2058
if self._parents:
2059
parents = tuple(parents)
2060
index, pos, size = access_memo
2061
if 'no-eol' in options:
2062
value = 'N'
2063
else:
2064
value = ' '
2065
value += "%d %d" % (pos, size)
2066
if not self._deltas:
2067
if 'line-delta' in options:
2068
raise KnitCorrupt(self, "attempt to add line-delta in non-delta knit")
2069
if self._parents:
2070
if self._deltas:
2071
if 'line-delta' in options:
2072
node_refs = (parents, (parents[0],))
2073
else:
2074
node_refs = (parents, ())
2075
else:
2076
node_refs = (parents, )
2077
else:
2078
if parents:
2079
raise KnitCorrupt(self, "attempt to add node with parents "
2080
"in parentless index.")
2081
node_refs = ()
2082
keys[key] = (value, node_refs)
2083
# check for dups
2084
if not random_id:
2085
present_nodes = self._get_entries(keys)
2086
for (index, key, value, node_refs) in present_nodes:
2087
if (value[0] != keys[key][0][0] or
2088
node_refs != keys[key][1]):
2089
raise KnitCorrupt(self, "inconsistent details in add_records"
2090
": %s %s" % ((value, node_refs), keys[key]))
2091
del keys[key]
2092
result = []
2093
if self._parents:
2094
for key, (value, node_refs) in keys.iteritems():
2095
result.append((key, value, node_refs))
2096
else:
2097
for key, (value, node_refs) in keys.iteritems():
2098
result.append((key, value))
2099
self._add_callback(result)
2100
2101
def _check_read(self):
2102
"""raise if reads are not permitted."""
2103
if not self._is_locked():
2104
raise errors.ObjectNotLocked(self)
2105
2106
def _check_write_ok(self):
2107
"""Assert if writes are not permitted."""
2108
if not self._is_locked():
2109
raise errors.ObjectNotLocked(self)
2110
2111
def _compression_parent(self, an_entry):
2112
# return the key that an_entry is compressed against, or None
2113
# Grab the second parent list (as deltas implies parents currently)
2114
compression_parents = an_entry[3][1]
2115
if not compression_parents:
2116
return None
2117
if len(compression_parents) != 1:
2118
raise AssertionError(
2119
"Too many compression parents: %r" % compression_parents)
2120
return compression_parents[0]
2121
2122
def get_build_details(self, keys):
2123
"""Get the method, index_memo and compression parent for version_ids.
2124
2125
Ghosts are omitted from the result.
2126
2127
:param keys: An iterable of keys.
2128
:return: A dict of key:
2129
(index_memo, compression_parent, parents, record_details).
2130
index_memo
2131
opaque structure to pass to read_records to extract the raw
2132
data
2133
compression_parent
2134
Content that this record is built upon, may be None
2135
parents
2136
Logical parents of this node
2137
record_details
2138
extra information about the content which needs to be passed to
2139
Factory.parse_record
2140
"""
2141
self._check_read()
2142
result = {}
2143
entries = self._get_entries(keys, False)
2144
for entry in entries:
2145
key = entry[1]
2146
if not self._parents:
2147
parents = ()
2148
else:
2149
parents = entry[3][0]
2150
if not self._deltas:
2151
compression_parent_key = None
2152
else:
2153
compression_parent_key = self._compression_parent(entry)
2154
noeol = (entry[2][0] == 'N')
2155
if compression_parent_key:
2156
method = 'line-delta'
2157
else:
2158
method = 'fulltext'
2159
result[key] = (self._node_to_position(entry),
2160
compression_parent_key, parents,
2161
(method, noeol))
2162
return result
2163
2164
def _get_entries(self, keys, check_present=False):
2165
"""Get the entries for keys.
2166
2167
:param keys: An iterable of index key tuples.
2168
"""
2169
keys = set(keys)
2170
found_keys = set()
2171
if self._parents:
2172
for node in self._graph_index.iter_entries(keys):
2173
yield node
2174
found_keys.add(node[1])
2175
else:
2176
# adapt parentless index to the rest of the code.
2177
for node in self._graph_index.iter_entries(keys):
2178
yield node[0], node[1], node[2], ()
2179
found_keys.add(node[1])
2180
if check_present:
2181
missing_keys = keys.difference(found_keys)
2182
if missing_keys:
2183
raise RevisionNotPresent(missing_keys.pop(), self)
2184
2185
def get_method(self, key):
2186
"""Return compression method of specified key."""
2187
return self._get_method(self._get_node(key))
2188
2189
def _get_method(self, node):
2190
if not self._deltas:
1285
def add_version(self, version_id, options, pos, size, parents):
1286
"""Add a version record to the index."""
1287
self.add_versions(((version_id, options, pos, size, parents),))
1288
1289
def add_versions(self, versions):
1290
"""Add multiple versions to the index.
1291
1292
:param versions: a list of tuples:
1293
(version_id, options, pos, size, parents).
1294
"""
1295
lines = []
1296
orig_history = self._history[:]
1297
orig_cache = self._cache.copy()
1298
1299
try:
1300
for version_id, options, pos, size, parents in versions:
1301
line = "\n%s %s %s %s %s :" % (version_id,
1302
','.join(options),
1303
pos,
1304
size,
1305
self._version_list_to_index(parents))
1306
assert isinstance(line, str), \
1307
'content must be utf-8 encoded: %r' % (line,)
1308
lines.append(line)
1309
self._cache_version(version_id, options, pos, size, parents)
1310
if not self._need_to_create:
1311
self._transport.append_bytes(self._filename, ''.join(lines))
1312
else:
1313
sio = StringIO()
1314
sio.write(self.HEADER)
1315
sio.writelines(lines)
1316
sio.seek(0)
1317
self._transport.put_file_non_atomic(self._filename, sio,
1318
create_parent_dir=self._create_parent_dir,
1319
mode=self._file_mode,
1320
dir_mode=self._dir_mode)
1321
self._need_to_create = False
1322
except:
1323
# If any problems happen, restore the original values and re-raise
1324
self._history = orig_history
1325
self._cache = orig_cache
1326
raise
1327
1328
def has_version(self, version_id):
1329
"""True if the version is in the index."""
1330
return version_id in self._cache
1331
1332
def get_position(self, version_id):
1333
"""Return data position and size of specified version."""
1334
entry = self._cache[version_id]
1335
return entry[2], entry[3]
1336
1337
def get_method(self, version_id):
1338
"""Return compression method of specified version."""
1339
options = self._cache[version_id][1]
1340
if 'fulltext' in options:
2191
1341
return 'fulltext'
2192
if self._compression_parent(node):
1342
else:
1343
if 'line-delta' not in options:
1344
raise errors.KnitIndexUnknownMethod(self._full_path(), options)
2193
1345
return 'line-delta'
2194
else:
2195
return 'fulltext'
2196
2197
def _get_node(self, key):
2198
try:
2199
return list(self._get_entries([key]))[0]
2200
except IndexError:
2201
raise RevisionNotPresent(key, self)
2202
2203
def get_options(self, key):
2204
"""Return a list representing options.
2205
2206
e.g. ['foo', 'bar']
2207
"""
2208
node = self._get_node(key)
2209
options = [self._get_method(node)]
2210
if node[2][0] == 'N':
2211
options.append('no-eol')
2212
return options
2213
2214
def get_parent_map(self, keys):
2215
"""Get a map of the parents of keys.
2216
2217
:param keys: The keys to look up parents for.
2218
:return: A mapping from keys to parents. Absent keys are absent from
2219
the mapping.
2220
"""
2221
self._check_read()
2222
nodes = self._get_entries(keys)
2223
result = {}
2224
if self._parents:
2225
for node in nodes:
2226
result[node[1]] = node[3][0]
2227
else:
2228
for node in nodes:
2229
result[node[1]] = None
2230
return result
2231
2232
def get_position(self, key):
2233
"""Return details needed to access the version.
2234
2235
:return: a tuple (index, data position, size) to hand to the access
2236
logic to get the record.
2237
"""
2238
node = self._get_node(key)
2239
return self._node_to_position(node)
2240
2241
def keys(self):
2242
"""Get all the keys in the collection.
2243
2244
The keys are not ordered.
2245
"""
2246
self._check_read()
2247
return [node[1] for node in self._graph_index.iter_all_entries()]
2248
2249
def _node_to_position(self, node):
2250
"""Convert an index value to position details."""
2251
bits = node[2][1:].split(' ')
2252
return node[0], int(bits[0]), int(bits[1])
2253
2254
2255
class _KnitKeyAccess(object):
2256
"""Access to records in .knit files."""
2257
2258
def __init__(self, transport, mapper):
2259
"""Create a _KnitKeyAccess with transport and mapper.
2260
2261
:param transport: The transport the access object is rooted at.
2262
:param mapper: The mapper used to map keys to .knit files.
2263
"""
2264
self._transport = transport
2265
self._mapper = mapper
2266
2267
def add_raw_records(self, key_sizes, raw_data):
2268
"""Add raw knit bytes to a storage area.
2269
2270
The data is spooled to the container writer in one bytes-record per
2271
raw data item.
2272
2273
:param sizes: An iterable of tuples containing the key and size of each
2274
raw data segment.
2275
:param raw_data: A bytestring containing the data.
2276
:return: A list of memos to retrieve the record later. Each memo is an
2277
opaque index memo. For _KnitKeyAccess the memo is (key, pos,
2278
length), where the key is the record key.
2279
"""
2280
if type(raw_data) != str:
2281
raise AssertionError(
2282
'data must be plain bytes was %s' % type(raw_data))
2283
result = []
2284
offset = 0
2285
# TODO: This can be tuned for writing to sftp and other servers where
2286
# append() is relatively expensive by grouping the writes to each key
2287
# prefix.
2288
for key, size in key_sizes:
2289
path = self._mapper.map(key)
2290
try:
2291
base = self._transport.append_bytes(path + '.knit',
2292
raw_data[offset:offset+size])
2293
except errors.NoSuchFile:
2294
self._transport.mkdir(osutils.dirname(path))
2295
base = self._transport.append_bytes(path + '.knit',
2296
raw_data[offset:offset+size])
2297
# if base == 0:
2298
# chmod.
2299
offset += size
2300
result.append((key, base, size))
2301
return result
2302
2303
def get_raw_records(self, memos_for_retrieval):
2304
"""Get the raw bytes for a records.
2305
2306
:param memos_for_retrieval: An iterable containing the access memo for
2307
retrieving the bytes.
2308
:return: An iterator over the bytes of the records.
2309
"""
2310
# first pass, group into same-index request to minimise readv's issued.
2311
request_lists = []
2312
current_prefix = None
2313
for (key, offset, length) in memos_for_retrieval:
2314
if current_prefix == key[:-1]:
2315
current_list.append((offset, length))
2316
else:
2317
if current_prefix is not None:
2318
request_lists.append((current_prefix, current_list))
2319
current_prefix = key[:-1]
2320
current_list = [(offset, length)]
2321
# handle the last entry
2322
if current_prefix is not None:
2323
request_lists.append((current_prefix, current_list))
2324
for prefix, read_vector in request_lists:
2325
path = self._mapper.map(prefix) + '.knit'
2326
for pos, data in self._transport.readv(path, read_vector):
2327
yield data
2328
2329
2330
class _DirectPackAccess(object):
2331
"""Access to data in one or more packs with less translation."""
2332
2333
def __init__(self, index_to_packs):
2334
"""Create a _DirectPackAccess object.
2335
2336
:param index_to_packs: A dict mapping index objects to the transport
2337
and file names for obtaining data.
2338
"""
2339
self._container_writer = None
2340
self._write_index = None
2341
self._indices = index_to_packs
2342
2343
def add_raw_records(self, key_sizes, raw_data):
2344
"""Add raw knit bytes to a storage area.
2345
2346
The data is spooled to the container writer in one bytes-record per
2347
raw data item.
2348
2349
:param sizes: An iterable of tuples containing the key and size of each
2350
raw data segment.
2351
:param raw_data: A bytestring containing the data.
2352
:return: A list of memos to retrieve the record later. Each memo is an
2353
opaque index memo. For _DirectPackAccess the memo is (index, pos,
2354
length), where the index field is the write_index object supplied
2355
to the PackAccess object.
2356
"""
2357
if type(raw_data) != str:
2358
raise AssertionError(
2359
'data must be plain bytes was %s' % type(raw_data))
2360
result = []
2361
offset = 0
2362
for key, size in key_sizes:
2363
p_offset, p_length = self._container_writer.add_bytes_record(
2364
raw_data[offset:offset+size], [])
2365
offset += size
2366
result.append((self._write_index, p_offset, p_length))
2367
return result
2368
2369
def get_raw_records(self, memos_for_retrieval):
2370
"""Get the raw bytes for a records.
2371
2372
:param memos_for_retrieval: An iterable containing the (index, pos,
2373
length) memo for retrieving the bytes. The Pack access method
2374
looks up the pack to use for a given record in its index_to_pack
2375
map.
2376
:return: An iterator over the bytes of the records.
2377
"""
2378
# first pass, group into same-index requests
2379
request_lists = []
2380
current_index = None
2381
for (index, offset, length) in memos_for_retrieval:
2382
if current_index == index:
2383
current_list.append((offset, length))
2384
else:
2385
if current_index is not None:
2386
request_lists.append((current_index, current_list))
2387
current_index = index
2388
current_list = [(offset, length)]
2389
# handle the last entry
2390
if current_index is not None:
2391
request_lists.append((current_index, current_list))
2392
for index, offsets in request_lists:
2393
transport, path = self._indices[index]
2394
reader = pack.make_readv_reader(transport, path, offsets)
2395
for names, read_func in reader.iter_records():
2396
yield read_func(None)
2397
2398
def set_writer(self, writer, index, transport_packname):
2399
"""Set a writer to use for adding data."""
2400
if index is not None:
2401
self._indices[index] = transport_packname
2402
self._container_writer = writer
2403
self._write_index = index
2404
2405
2406
# Deprecated, use PatienceSequenceMatcher instead
2407
KnitSequenceMatcher = patiencediff.PatienceSequenceMatcher
2408
2409
2410
def annotate_knit(knit, revision_id):
2411
"""Annotate a knit with no cached annotations.
2412
2413
This implementation is for knits with no cached annotations.
2414
It will work for knits with cached annotations, but this is not
2415
recommended.
1346
1347
def get_options(self, version_id):
1348
return self._cache[version_id][1]
1349
1350
def get_parents(self, version_id):
1351
"""Return parents of specified version ignoring ghosts."""
1352
return [parent for parent in self._cache[version_id][4]
1353
if parent in self._cache]
1354
1355
def get_parents_with_ghosts(self, version_id):
1356
"""Return parents of specified version with ghosts."""
1357
return self._cache[version_id][4]
1358
1359
def check_versions_present(self, version_ids):
1360
"""Check that all specified versions are present."""
1361
cache = self._cache
1362
for version_id in version_ids:
1363
if version_id not in cache:
1364
raise RevisionNotPresent(version_id, self._filename)
1365
1366
1367
class _KnitData(_KnitComponentFile):
1368
"""Contents of the knit data file"""
1369
1370
def __init__(self, transport, filename, mode, create=False, file_mode=None,
1371
create_parent_dir=False, delay_create=False,
1372
dir_mode=None):
1373
_KnitComponentFile.__init__(self, transport, filename, mode,
1374
file_mode=file_mode,
1375
create_parent_dir=create_parent_dir,
1376
dir_mode=dir_mode)
1377
self._checked = False
1378
# TODO: jam 20060713 conceptually, this could spill to disk
1379
# if the cached size gets larger than a certain amount
1380
# but it complicates the model a bit, so for now just use
1381
# a simple dictionary
1382
self._cache = {}
1383
self._do_cache = False
1384
if create:
1385
if delay_create:
1386
self._need_to_create = create
1387
else:
1388
self._transport.put_bytes_non_atomic(self._filename, '',
1389
mode=self._file_mode)
1390
1391
def enable_cache(self):
1392
"""Enable caching of reads."""
1393
self._do_cache = True
1394
1395
def clear_cache(self):
1396
"""Clear the record cache."""
1397
self._do_cache = False
1398
self._cache = {}
1399
1400
def _open_file(self):
1401
try:
1402
return self._transport.get(self._filename)
1403
except NoSuchFile:
1404
pass
1405
return None
1406
1407
def _record_to_data(self, version_id, digest, lines):
1408
"""Convert version_id, digest, lines into a raw data block.
1409
1410
:return: (len, a StringIO instance with the raw data ready to read.)
1411
"""
1412
sio = StringIO()
1413
data_file = GzipFile(None, mode='wb', fileobj=sio)
1414
1415
assert isinstance(version_id, str)
1416
data_file.writelines(chain(
1417
["version %s %d %s\n" % (version_id,
1418
len(lines),
1419
digest)],
1420
lines,
1421
["end %s\n" % version_id]))
1422
data_file.close()
1423
length= sio.tell()
1424
1425
sio.seek(0)
1426
return length, sio
1427
1428
def add_raw_record(self, raw_data):
1429
"""Append a prepared record to the data file.
1430
1431
:return: the offset in the data file raw_data was written.
1432
"""
1433
assert isinstance(raw_data, str), 'data must be plain bytes'
1434
if not self._need_to_create:
1435
return self._transport.append_bytes(self._filename, raw_data)
1436
else:
1437
self._transport.put_bytes_non_atomic(self._filename, raw_data,
1438
create_parent_dir=self._create_parent_dir,
1439
mode=self._file_mode,
1440
dir_mode=self._dir_mode)
1441
self._need_to_create = False
1442
return 0
1443
1444
def add_record(self, version_id, digest, lines):
1445
"""Write new text record to disk. Returns the position in the
1446
file where it was written."""
1447
size, sio = self._record_to_data(version_id, digest, lines)
1448
# write to disk
1449
if not self._need_to_create:
1450
start_pos = self._transport.append_file(self._filename, sio)
1451
else:
1452
self._transport.put_file_non_atomic(self._filename, sio,
1453
create_parent_dir=self._create_parent_dir,
1454
mode=self._file_mode,
1455
dir_mode=self._dir_mode)
1456
self._need_to_create = False
1457
start_pos = 0
1458
if self._do_cache:
1459
self._cache[version_id] = sio.getvalue()
1460
return start_pos, size
1461
1462
def _parse_record_header(self, version_id, raw_data):
1463
"""Parse a record header for consistency.
1464
1465
:return: the header and the decompressor stream.
1466
as (stream, header_record)
1467
"""
1468
df = GzipFile(mode='rb', fileobj=StringIO(raw_data))
1469
try:
1470
rec = self._check_header(version_id, df.readline())
1471
except Exception, e:
1472
raise KnitCorrupt(self._filename,
1473
"While reading {%s} got %s(%s)"
1474
% (version_id, e.__class__.__name__, str(e)))
1475
return df, rec
1476
1477
def _check_header(self, version_id, line):
1478
rec = line.split()
1479
if len(rec) != 4:
1480
raise KnitCorrupt(self._filename,
1481
'unexpected number of elements in record header')
1482
if rec[1] != version_id:
1483
raise KnitCorrupt(self._filename,
1484
'unexpected version, wanted %r, got %r'
1485
% (version_id, rec[1]))
1486
return rec
1487
1488
def _parse_record(self, version_id, data):
1489
# profiling notes:
1490
# 4168 calls in 2880 217 internal
1491
# 4168 calls to _parse_record_header in 2121
1492
# 4168 calls to readlines in 330
1493
df = GzipFile(mode='rb', fileobj=StringIO(data))
1494
1495
try:
1496
record_contents = df.readlines()
1497
except Exception, e:
1498
raise KnitCorrupt(self._filename,
1499
"While reading {%s} got %s(%s)"
1500
% (version_id, e.__class__.__name__, str(e)))
1501
header = record_contents.pop(0)
1502
rec = self._check_header(version_id, header)
1503
1504
last_line = record_contents.pop()
1505
if len(record_contents) != int(rec[2]):
1506
raise KnitCorrupt(self._filename,
1507
'incorrect number of lines %s != %s'
1508
' for version {%s}'
1509
% (len(record_contents), int(rec[2]),
1510
version_id))
1511
if last_line != 'end %s\n' % rec[1]:
1512
raise KnitCorrupt(self._filename,
1513
'unexpected version end line %r, wanted %r'
1514
% (last_line, version_id))
1515
df.close()
1516
return record_contents, rec[3]
1517
1518
def read_records_iter_raw(self, records):
1519
"""Read text records from data file and yield raw data.
1520
1521
This unpacks enough of the text record to validate the id is
1522
as expected but thats all.
1523
"""
1524
# setup an iterator of the external records:
1525
# uses readv so nice and fast we hope.
1526
if len(records):
1527
# grab the disk data needed.
1528
if self._cache:
1529
# Don't check _cache if it is empty
1530
needed_offsets = [(pos, size) for version_id, pos, size
1531
in records
1532
if version_id not in self._cache]
1533
else:
1534
needed_offsets = [(pos, size) for version_id, pos, size
1535
in records]
1536
1537
raw_records = self._transport.readv(self._filename, needed_offsets)
1538
1539
for version_id, pos, size in records:
1540
if version_id in self._cache:
1541
# This data has already been validated
1542
data = self._cache[version_id]
1543
else:
1544
pos, data = raw_records.next()
1545
if self._do_cache:
1546
self._cache[version_id] = data
1547
1548
# validate the header
1549
df, rec = self._parse_record_header(version_id, data)
1550
df.close()
1551
yield version_id, data
1552
1553
def read_records_iter(self, records):
1554
"""Read text records from data file and yield result.
1555
1556
The result will be returned in whatever is the fastest to read.
1557
Not by the order requested. Also, multiple requests for the same
1558
record will only yield 1 response.
1559
:param records: A list of (version_id, pos, len) entries
1560
:return: Yields (version_id, contents, digest) in the order
1561
read, not the order requested
1562
"""
1563
if not records:
1564
return
1565
1566
if self._cache:
1567
# Skip records we have alread seen
1568
yielded_records = set()
1569
needed_records = set()
1570
for record in records:
1571
if record[0] in self._cache:
1572
if record[0] in yielded_records:
1573
continue
1574
yielded_records.add(record[0])
1575
data = self._cache[record[0]]
1576
content, digest = self._parse_record(record[0], data)
1577
yield (record[0], content, digest)
1578
else:
1579
needed_records.add(record)
1580
needed_records = sorted(needed_records, key=operator.itemgetter(1))
1581
else:
1582
needed_records = sorted(set(records), key=operator.itemgetter(1))
1583
1584
if not needed_records:
1585
return
1586
1587
# The transport optimizes the fetching as well
1588
# (ie, reads continuous ranges.)
1589
readv_response = self._transport.readv(self._filename,
1590
[(pos, size) for version_id, pos, size in needed_records])
1591
1592
for (version_id, pos, size), (pos, data) in \
1593
izip(iter(needed_records), readv_response):
1594
content, digest = self._parse_record(version_id, data)
1595
if self._do_cache:
1596
self._cache[version_id] = data
1597
yield version_id, content, digest
1598
1599
def read_records(self, records):
1600
"""Read records into a dictionary."""
1601
components = {}
1602
for record_id, content, digest in \
1603
self.read_records_iter(records):
1604
components[record_id] = (content, digest)
1605
return components
1606
1607
1608
class InterKnit(InterVersionedFile):
1609
"""Optimised code paths for knit to knit operations."""
1610
1611
_matching_file_from_factory = KnitVersionedFile
1612
_matching_file_to_factory = KnitVersionedFile
1613
1614
@staticmethod
1615
def is_compatible(source, target):
1616
"""Be compatible with knits. """
1617
try:
1618
return (isinstance(source, KnitVersionedFile) and
1619
isinstance(target, KnitVersionedFile))
1620
except AttributeError:
1621
return False
1622
1623
def join(self, pb=None, msg=None, version_ids=None, ignore_missing=False):
1624
"""See InterVersionedFile.join."""
1625
assert isinstance(self.source, KnitVersionedFile)
1626
assert isinstance(self.target, KnitVersionedFile)
1627
1628
version_ids = self._get_source_version_ids(version_ids, ignore_missing)
1629
1630
if not version_ids:
1631
return 0
1632
1633
pb = ui.ui_factory.nested_progress_bar()
1634
try:
1635
version_ids = list(version_ids)
1636
if None in version_ids:
1637
version_ids.remove(None)
1638
1639
self.source_ancestry = set(self.source.get_ancestry(version_ids))
1640
this_versions = set(self.target._index.get_versions())
1641
needed_versions = self.source_ancestry - this_versions
1642
cross_check_versions = self.source_ancestry.intersection(this_versions)
1643
mismatched_versions = set()
1644
for version in cross_check_versions:
1645
# scan to include needed parents.
1646
n1 = set(self.target.get_parents_with_ghosts(version))
1647
n2 = set(self.source.get_parents_with_ghosts(version))
1648
if n1 != n2:
1649
# FIXME TEST this check for cycles being introduced works
1650
# the logic is we have a cycle if in our graph we are an
1651
# ancestor of any of the n2 revisions.
1652
for parent in n2:
1653
if parent in n1:
1654
# safe
1655
continue
1656
else:
1657
parent_ancestors = self.source.get_ancestry(parent)
1658
if version in parent_ancestors:
1659
raise errors.GraphCycleError([parent, version])
1660
# ensure this parent will be available later.
1661
new_parents = n2.difference(n1)
1662
needed_versions.update(new_parents.difference(this_versions))
1663
mismatched_versions.add(version)
1664
1665
if not needed_versions and not mismatched_versions:
1666
return 0
1667
full_list = topo_sort(self.source.get_graph())
1668
1669
version_list = [i for i in full_list if (not self.target.has_version(i)
1670
and i in needed_versions)]
1671
1672
# plan the join:
1673
copy_queue = []
1674
copy_queue_records = []
1675
copy_set = set()
1676
for version_id in version_list:
1677
options = self.source._index.get_options(version_id)
1678
parents = self.source._index.get_parents_with_ghosts(version_id)
1679
# check that its will be a consistent copy:
1680
for parent in parents:
1681
# if source has the parent, we must :
1682
# * already have it or
1683
# * have it scheduled already
1684
# otherwise we don't care
1685
assert (self.target.has_version(parent) or
1686
parent in copy_set or
1687
not self.source.has_version(parent))
1688
data_pos, data_size = self.source._index.get_position(version_id)
1689
copy_queue_records.append((version_id, data_pos, data_size))
1690
copy_queue.append((version_id, options, parents))
1691
copy_set.add(version_id)
1692
1693
# data suck the join:
1694
count = 0
1695
total = len(version_list)
1696
raw_datum = []
1697
raw_records = []
1698
for (version_id, raw_data), \
1699
(version_id2, options, parents) in \
1700
izip(self.source._data.read_records_iter_raw(copy_queue_records),
1701
copy_queue):
1702
assert version_id == version_id2, 'logic error, inconsistent results'
1703
count = count + 1
1704
pb.update("Joining knit", count, total)
1705
raw_records.append((version_id, options, parents, len(raw_data)))
1706
raw_datum.append(raw_data)
1707
self.target._add_raw_records(raw_records, ''.join(raw_datum))
1708
1709
for version in mismatched_versions:
1710
# FIXME RBC 20060309 is this needed?
1711
n1 = set(self.target.get_parents_with_ghosts(version))
1712
n2 = set(self.source.get_parents_with_ghosts(version))
1713
# write a combined record to our history preserving the current
1714
# parents as first in the list
1715
new_parents = self.target.get_parents_with_ghosts(version) + list(n2.difference(n1))
1716
self.target.fix_parents(version, new_parents)
1717
return count
1718
finally:
1719
pb.finished()
1720
1721
1722
InterVersionedFile.register_optimiser(InterKnit)
1723
1724
1725
class WeaveToKnit(InterVersionedFile):
1726
"""Optimised code paths for weave to knit operations."""
1727
1728
_matching_file_from_factory = bzrlib.weave.WeaveFile
1729
_matching_file_to_factory = KnitVersionedFile
1730
1731
@staticmethod
1732
def is_compatible(source, target):
1733
"""Be compatible with weaves to knits."""
1734
try:
1735
return (isinstance(source, bzrlib.weave.Weave) and
1736
isinstance(target, KnitVersionedFile))
1737
except AttributeError:
1738
return False
1739
1740
def join(self, pb=None, msg=None, version_ids=None, ignore_missing=False):
1741
"""See InterVersionedFile.join."""
1742
assert isinstance(self.source, bzrlib.weave.Weave)
1743
assert isinstance(self.target, KnitVersionedFile)
1744
1745
version_ids = self._get_source_version_ids(version_ids, ignore_missing)
1746
1747
if not version_ids:
1748
return 0
1749
1750
pb = ui.ui_factory.nested_progress_bar()
1751
try:
1752
version_ids = list(version_ids)
1753
1754
self.source_ancestry = set(self.source.get_ancestry(version_ids))
1755
this_versions = set(self.target._index.get_versions())
1756
needed_versions = self.source_ancestry - this_versions
1757
cross_check_versions = self.source_ancestry.intersection(this_versions)
1758
mismatched_versions = set()
1759
for version in cross_check_versions:
1760
# scan to include needed parents.
1761
n1 = set(self.target.get_parents_with_ghosts(version))
1762
n2 = set(self.source.get_parents(version))
1763
# if all of n2's parents are in n1, then its fine.
1764
if n2.difference(n1):
1765
# FIXME TEST this check for cycles being introduced works
1766
# the logic is we have a cycle if in our graph we are an
1767
# ancestor of any of the n2 revisions.
1768
for parent in n2:
1769
if parent in n1:
1770
# safe
1771
continue
1772
else:
1773
parent_ancestors = self.source.get_ancestry(parent)
1774
if version in parent_ancestors:
1775
raise errors.GraphCycleError([parent, version])
1776
# ensure this parent will be available later.
1777
new_parents = n2.difference(n1)
1778
needed_versions.update(new_parents.difference(this_versions))
1779
mismatched_versions.add(version)
1780
1781
if not needed_versions and not mismatched_versions:
1782
return 0
1783
full_list = topo_sort(self.source.get_graph())
1784
1785
version_list = [i for i in full_list if (not self.target.has_version(i)
1786
and i in needed_versions)]
1787
1788
# do the join:
1789
count = 0
1790
total = len(version_list)
1791
for version_id in version_list:
1792
pb.update("Converting to knit", count, total)
1793
parents = self.source.get_parents(version_id)
1794
# check that its will be a consistent copy:
1795
for parent in parents:
1796
# if source has the parent, we must already have it
1797
assert (self.target.has_version(parent))
1798
self.target.add_lines(
1799
version_id, parents, self.source.get_lines(version_id))
1800
count = count + 1
1801
1802
for version in mismatched_versions:
1803
# FIXME RBC 20060309 is this needed?
1804
n1 = set(self.target.get_parents_with_ghosts(version))
1805
n2 = set(self.source.get_parents(version))
1806
# write a combined record to our history preserving the current
1807
# parents as first in the list
1808
new_parents = self.target.get_parents_with_ghosts(version) + list(n2.difference(n1))
1809
self.target.fix_parents(version, new_parents)
1810
return count
1811
finally:
1812
pb.finished()
1813
1814
1815
InterVersionedFile.register_optimiser(WeaveToKnit)
1816
1817
1818
class KnitSequenceMatcher(difflib.SequenceMatcher):
1819
"""Knit tuned sequence matcher.
1820
1821
This is based on profiling of difflib which indicated some improvements
1822
for our usage pattern.
2416
1823
"""
2417
annotator = _KnitAnnotator(knit)
2418
return iter(annotator.annotate(revision_id))
2419
2420
2421
class _KnitAnnotator(object):
2422
"""Build up the annotations for a text."""
2423
2424
def __init__(self, knit):
2425
self._knit = knit
2426
2427
# Content objects, differs from fulltexts because of how final newlines
2428
# are treated by knits. the content objects here will always have a
2429
# final newline
2430
self._fulltext_contents = {}
2431
2432
# Annotated lines of specific revisions
2433
self._annotated_lines = {}
2434
2435
# Track the raw data for nodes that we could not process yet.
2436
# This maps the revision_id of the base to a list of children that will
2437
# annotated from it.
2438
self._pending_children = {}
2439
2440
# Nodes which cannot be extracted
2441
self._ghosts = set()
2442
2443
# Track how many children this node has, so we know if we need to keep
2444
# it
2445
self._annotate_children = {}
2446
self._compression_children = {}
2447
2448
self._all_build_details = {}
2449
# The children => parent revision_id graph
2450
self._revision_id_graph = {}
2451
2452
self._heads_provider = None
2453
2454
self._nodes_to_keep_annotations = set()
2455
self._generations_until_keep = 100
2456
2457
def set_generations_until_keep(self, value):
2458
"""Set the number of generations before caching a node.
2459
2460
Setting this to -1 will cache every merge node, setting this higher
2461
will cache fewer nodes.
2462
"""
2463
self._generations_until_keep = value
2464
2465
def _add_fulltext_content(self, revision_id, content_obj):
2466
self._fulltext_contents[revision_id] = content_obj
2467
# TODO: jam 20080305 It might be good to check the sha1digest here
2468
return content_obj.text()
2469
2470
def _check_parents(self, child, nodes_to_annotate):
2471
"""Check if all parents have been processed.
2472
2473
:param child: A tuple of (rev_id, parents, raw_content)
2474
:param nodes_to_annotate: If child is ready, add it to
2475
nodes_to_annotate, otherwise put it back in self._pending_children
2476
"""
2477
for parent_id in child[1]:
2478
if (parent_id not in self._annotated_lines):
2479
# This parent is present, but another parent is missing
2480
self._pending_children.setdefault(parent_id,
2481
[]).append(child)
2482
break
2483
else:
2484
# This one is ready to be processed
2485
nodes_to_annotate.append(child)
2486
2487
def _add_annotation(self, revision_id, fulltext, parent_ids,
2488
left_matching_blocks=None):
2489
"""Add an annotation entry.
2490
2491
All parents should already have been annotated.
2492
:return: A list of children that now have their parents satisfied.
2493
"""
2494
a = self._annotated_lines
2495
annotated_parent_lines = [a[p] for p in parent_ids]
2496
annotated_lines = list(annotate.reannotate(annotated_parent_lines,
2497
fulltext, revision_id, left_matching_blocks,
2498
heads_provider=self._get_heads_provider()))
2499
self._annotated_lines[revision_id] = annotated_lines
2500
for p in parent_ids:
2501
ann_children = self._annotate_children[p]
2502
ann_children.remove(revision_id)
2503
if (not ann_children
2504
and p not in self._nodes_to_keep_annotations):
2505
del self._annotated_lines[p]
2506
del self._all_build_details[p]
2507
if p in self._fulltext_contents:
2508
del self._fulltext_contents[p]
2509
# Now that we've added this one, see if there are any pending
2510
# deltas to be done, certainly this parent is finished
2511
nodes_to_annotate = []
2512
for child in self._pending_children.pop(revision_id, []):
2513
self._check_parents(child, nodes_to_annotate)
2514
return nodes_to_annotate
2515
2516
def _get_build_graph(self, key):
2517
"""Get the graphs for building texts and annotations.
2518
2519
The data you need for creating a full text may be different than the
2520
data you need to annotate that text. (At a minimum, you need both
2521
parents to create an annotation, but only need 1 parent to generate the
2522
fulltext.)
2523
2524
:return: A list of (key, index_memo) records, suitable for
2525
passing to read_records_iter to start reading in the raw data fro/
2526
the pack file.
2527
"""
2528
if key in self._annotated_lines:
2529
# Nothing to do
2530
return []
2531
pending = set([key])
2532
records = []
2533
generation = 0
2534
kept_generation = 0
2535
while pending:
2536
# get all pending nodes
2537
generation += 1
2538
this_iteration = pending
2539
build_details = self._knit._index.get_build_details(this_iteration)
2540
self._all_build_details.update(build_details)
2541
# new_nodes = self._knit._index._get_entries(this_iteration)
2542
pending = set()
2543
for key, details in build_details.iteritems():
2544
(index_memo, compression_parent, parents,
2545
record_details) = details
2546
self._revision_id_graph[key] = parents
2547
records.append((key, index_memo))
2548
# Do we actually need to check _annotated_lines?
2549
pending.update(p for p in parents
2550
if p not in self._all_build_details)
2551
if compression_parent:
2552
self._compression_children.setdefault(compression_parent,
2553
[]).append(key)
2554
if parents:
2555
for parent in parents:
2556
self._annotate_children.setdefault(parent,
2557
[]).append(key)
2558
num_gens = generation - kept_generation
2559
if ((num_gens >= self._generations_until_keep)
2560
and len(parents) > 1):
2561
kept_generation = generation
2562
self._nodes_to_keep_annotations.add(key)
2563
2564
missing_versions = this_iteration.difference(build_details.keys())
2565
self._ghosts.update(missing_versions)
2566
for missing_version in missing_versions:
2567
# add a key, no parents
2568
self._revision_id_graph[missing_version] = ()
2569
pending.discard(missing_version) # don't look for it
2570
if self._ghosts.intersection(self._compression_children):
2571
raise KnitCorrupt(
2572
"We cannot have nodes which have a ghost compression parent:\n"
2573
"ghosts: %r\n"
2574
"compression children: %r"
2575
% (self._ghosts, self._compression_children))
2576
# Cleanout anything that depends on a ghost so that we don't wait for
2577
# the ghost to show up
2578
for node in self._ghosts:
2579
if node in self._annotate_children:
2580
# We won't be building this node
2581
del self._annotate_children[node]
2582
# Generally we will want to read the records in reverse order, because
2583
# we find the parent nodes after the children
2584
records.reverse()
2585
return records
2586
2587
def _annotate_records(self, records):
2588
"""Build the annotations for the listed records."""
2589
# We iterate in the order read, rather than a strict order requested
2590
# However, process what we can, and put off to the side things that
2591
# still need parents, cleaning them up when those parents are
2592
# processed.
2593
for (rev_id, record,
2594
digest) in self._knit._read_records_iter(records):
2595
if rev_id in self._annotated_lines:
2596
continue
2597
parent_ids = self._revision_id_graph[rev_id]
2598
parent_ids = [p for p in parent_ids if p not in self._ghosts]
2599
details = self._all_build_details[rev_id]
2600
(index_memo, compression_parent, parents,
2601
record_details) = details
2602
nodes_to_annotate = []
2603
# TODO: Remove the punning between compression parents, and
2604
# parent_ids, we should be able to do this without assuming
2605
# the build order
2606
if len(parent_ids) == 0:
2607
# There are no parents for this node, so just add it
2608
# TODO: This probably needs to be decoupled
2609
fulltext_content, delta = self._knit._factory.parse_record(
2610
rev_id, record, record_details, None)
2611
fulltext = self._add_fulltext_content(rev_id, fulltext_content)
2612
nodes_to_annotate.extend(self._add_annotation(rev_id, fulltext,
2613
parent_ids, left_matching_blocks=None))
2614
else:
2615
child = (rev_id, parent_ids, record)
2616
# Check if all the parents are present
2617
self._check_parents(child, nodes_to_annotate)
2618
while nodes_to_annotate:
2619
# Should we use a queue here instead of a stack?
2620
(rev_id, parent_ids, record) = nodes_to_annotate.pop()
2621
(index_memo, compression_parent, parents,
2622
record_details) = self._all_build_details[rev_id]
2623
if compression_parent is not None:
2624
comp_children = self._compression_children[compression_parent]
2625
if rev_id not in comp_children:
2626
raise AssertionError("%r not in compression children %r"
2627
% (rev_id, comp_children))
2628
# If there is only 1 child, it is safe to reuse this
2629
# content
2630
reuse_content = (len(comp_children) == 1
2631
and compression_parent not in
2632
self._nodes_to_keep_annotations)
2633
if reuse_content:
2634
# Remove it from the cache since it will be changing
2635
parent_fulltext_content = self._fulltext_contents.pop(compression_parent)
2636
# Make sure to copy the fulltext since it might be
2637
# modified
2638
parent_fulltext = list(parent_fulltext_content.text())
2639
else:
2640
parent_fulltext_content = self._fulltext_contents[compression_parent]
2641
parent_fulltext = parent_fulltext_content.text()
2642
comp_children.remove(rev_id)
2643
fulltext_content, delta = self._knit._factory.parse_record(
2644
rev_id, record, record_details,
2645
parent_fulltext_content,
2646
copy_base_content=(not reuse_content))
2647
fulltext = self._add_fulltext_content(rev_id,
2648
fulltext_content)
2649
blocks = KnitContent.get_line_delta_blocks(delta,
2650
parent_fulltext, fulltext)
2651
else:
2652
fulltext_content = self._knit._factory.parse_fulltext(
2653
record, rev_id)
2654
fulltext = self._add_fulltext_content(rev_id,
2655
fulltext_content)
2656
blocks = None
2657
nodes_to_annotate.extend(
2658
self._add_annotation(rev_id, fulltext, parent_ids,
2659
left_matching_blocks=blocks))
2660
2661
def _get_heads_provider(self):
2662
"""Create a heads provider for resolving ancestry issues."""
2663
if self._heads_provider is not None:
2664
return self._heads_provider
2665
parent_provider = _mod_graph.DictParentsProvider(
2666
self._revision_id_graph)
2667
graph_obj = _mod_graph.Graph(parent_provider)
2668
head_cache = _mod_graph.FrozenHeadsCache(graph_obj)
2669
self._heads_provider = head_cache
2670
return head_cache
2671
2672
def annotate(self, key):
2673
"""Return the annotated fulltext at the given key.
2674
2675
:param key: The key to annotate.
2676
"""
2677
if True or len(self._knit._fallback_vfs) > 0:
2678
# stacked knits can't use the fast path at present.
2679
return self._simple_annotate(key)
2680
records = self._get_build_graph(key)
2681
if key in self._ghosts:
2682
raise errors.RevisionNotPresent(key, self._knit)
2683
self._annotate_records(records)
2684
return self._annotated_lines[key]
2685
2686
def _simple_annotate(self, key):
2687
"""Return annotated fulltext, rediffing from the full texts.
2688
2689
This is slow but makes no assumptions about the repository
2690
being able to produce line deltas.
2691
"""
2692
# TODO: this code generates a parent maps of present ancestors; it
2693
# could be split out into a separate method, and probably should use
2694
# iter_ancestry instead. -- mbp and robertc 20080704
2695
graph = _mod_graph.Graph(self._knit)
2696
head_cache = _mod_graph.FrozenHeadsCache(graph)
2697
search = graph._make_breadth_first_searcher([key])
2698
keys = set()
2699
while True:
1824
1825
def find_longest_match(self, alo, ahi, blo, bhi):
1826
"""Find longest matching block in a[alo:ahi] and b[blo:bhi].
1827
1828
If isjunk is not defined:
1829
1830
Return (i,j,k) such that a[i:i+k] is equal to b[j:j+k], where
1831
alo <= i <= i+k <= ahi
1832
blo <= j <= j+k <= bhi
1833
and for all (i',j',k') meeting those conditions,
1834
k >= k'
1835
i <= i'
1836
and if i == i', j <= j'
1837
1838
In other words, of all maximal matching blocks, return one that
1839
starts earliest in a, and of all those maximal matching blocks that
1840
start earliest in a, return the one that starts earliest in b.
1841
1842
>>> s = SequenceMatcher(None, " abcd", "abcd abcd")
1843
>>> s.find_longest_match(0, 5, 0, 9)
1844
(0, 4, 5)
1845
1846
If isjunk is defined, first the longest matching block is
1847
determined as above, but with the additional restriction that no
1848
junk element appears in the block. Then that block is extended as
1849
far as possible by matching (only) junk elements on both sides. So
1850
the resulting block never matches on junk except as identical junk
1851
happens to be adjacent to an "interesting" match.
1852
1853
Here's the same example as before, but considering blanks to be
1854
junk. That prevents " abcd" from matching the " abcd" at the tail
1855
end of the second sequence directly. Instead only the "abcd" can
1856
match, and matches the leftmost "abcd" in the second sequence:
1857
1858
>>> s = SequenceMatcher(lambda x: x==" ", " abcd", "abcd abcd")
1859
>>> s.find_longest_match(0, 5, 0, 9)
1860
(1, 0, 4)
1861
1862
If no blocks match, return (alo, blo, 0).
1863
1864
>>> s = SequenceMatcher(None, "ab", "c")
1865
>>> s.find_longest_match(0, 2, 0, 1)
1866
(0, 0, 0)
1867
"""
1868
1869
# CAUTION: stripping common prefix or suffix would be incorrect.
1870
# E.g.,
1871
# ab
1872
# acab
1873
# Longest matching block is "ab", but if common prefix is
1874
# stripped, it's "a" (tied with "b"). UNIX(tm) diff does so
1875
# strip, so ends up claiming that ab is changed to acab by
1876
# inserting "ca" in the middle. That's minimal but unintuitive:
1877
# "it's obvious" that someone inserted "ac" at the front.
1878
# Windiff ends up at the same place as diff, but by pairing up
1879
# the unique 'b's and then matching the first two 'a's.
1880
1881
a, b, b2j, isbjunk = self.a, self.b, self.b2j, self.isbjunk
1882
besti, bestj, bestsize = alo, blo, 0
1883
# find longest junk-free match
1884
# during an iteration of the loop, j2len[j] = length of longest
1885
# junk-free match ending with a[i-1] and b[j]
1886
j2len = {}
1887
# nothing = []
1888
b2jget = b2j.get
1889
for i in xrange(alo, ahi):
1890
# look at all instances of a[i] in b; note that because
1891
# b2j has no junk keys, the loop is skipped if a[i] is junk
1892
j2lenget = j2len.get
1893
newj2len = {}
1894
1895
# changing b2j.get(a[i], nothing) to a try:KeyError pair produced the
1896
# following improvement
1897
# 704 0 4650.5320 2620.7410 bzrlib.knit:1336(find_longest_match)
1898
# +326674 0 1655.1210 1655.1210 +<method 'get' of 'dict' objects>
1899
# +76519 0 374.6700 374.6700 +<method 'has_key' of 'dict' objects>
1900
# to
1901
# 704 0 3733.2820 2209.6520 bzrlib.knit:1336(find_longest_match)
1902
# +211400 0 1147.3520 1147.3520 +<method 'get' of 'dict' objects>
1903
# +76519 0 376.2780 376.2780 +<method 'has_key' of 'dict' objects>
1904
2700
1905
try:
2701
present, ghosts = search.next_with_ghosts()
2702
except StopIteration:
2703
break
2704
keys.update(present)
2705
parent_map = self._knit.get_parent_map(keys)
2706
parent_cache = {}
2707
reannotate = annotate.reannotate
2708
for record in self._knit.get_record_stream(keys, 'topological', True):
2709
key = record.key
2710
fulltext = split_lines(record.get_bytes_as('fulltext'))
2711
parents = parent_map[key]
2712
if parents is not None:
2713
parent_lines = [parent_cache[parent] for parent in parent_map[key]]
1906
js = b2j[a[i]]
1907
except KeyError:
1908
pass
2714
1909
else:
2715
parent_lines = []
2716
parent_cache[key] = list(
2717
reannotate(parent_lines, fulltext, key, None, head_cache))
2718
try:
2719
return parent_cache[key]
2720
except KeyError, e:
2721
raise errors.RevisionNotPresent(key, self._knit)
2722
2723
2724
try:
2725
from bzrlib._knit_load_data_c import _load_data_c as _load_data
2726
except ImportError:
2727
from bzrlib._knit_load_data_py import _load_data_py as _load_data
1910
for j in js:
1911
# a[i] matches b[j]
1912
if j >= blo:
1913
if j >= bhi:
1914
break
1915
k = newj2len[j] = 1 + j2lenget(-1 + j, 0)
1916
if k > bestsize:
1917
besti, bestj, bestsize = 1 + i-k, 1 + j-k, k
1918
j2len = newj2len
1919
1920
# Extend the best by non-junk elements on each end. In particular,
1921
# "popular" non-junk elements aren't in b2j, which greatly speeds
1922
# the inner loop above, but also means "the best" match so far
1923
# doesn't contain any junk *or* popular non-junk elements.
1924
while besti > alo and bestj > blo and \
1925
not isbjunk(b[bestj-1]) and \
1926
a[besti-1] == b[bestj-1]:
1927
besti, bestj, bestsize = besti-1, bestj-1, bestsize+1
1928
while besti+bestsize < ahi and bestj+bestsize < bhi and \
1929
not isbjunk(b[bestj+bestsize]) and \
1930
a[besti+bestsize] == b[bestj+bestsize]:
1931
bestsize += 1
1932
1933
# Now that we have a wholly interesting match (albeit possibly
1934
# empty!), we may as well suck up the matching junk on each
1935
# side of it too. Can't think of a good reason not to, and it
1936
# saves post-processing the (possibly considerable) expense of
1937
# figuring out what to do with it. In the case of an empty
1938
# interesting match, this is clearly the right thing to do,
1939
# because no other kind of match is possible in the regions.
1940
while besti > alo and bestj > blo and \
1941
isbjunk(b[bestj-1]) and \
1942
a[besti-1] == b[bestj-1]:
1943
besti, bestj, bestsize = besti-1, bestj-1, bestsize+1
1944
while besti+bestsize < ahi and bestj+bestsize < bhi and \
1945
isbjunk(b[bestj+bestsize]) and \
1946
a[besti+bestsize] == b[bestj+bestsize]:
1947
bestsize = bestsize + 1
1948
1949
return besti, bestj, bestsize
Loggerhead is a web-based interface for Breezy
Version: 2.0.1