22
22
"""Weave - storage of related text file versions"""
24
# before intset (r923) 2000 versions in 41.5s
25
# with intset (r926) 2000 versions in 93s !!!
26
# better to just use plain sets.
28
# making _extract build and return a list, rather than being a generator
31
# with python -O, r923 does 2000 versions in 36.87s
33
# with optimizations to avoid mutating lists - 35.75! I guess copying
34
# all the elements every time costs more than the small manipulations.
35
# a surprisingly small change.
37
# r931, which avoids using a generator for extract, does 36.98s
39
# with memoized inclusions, takes 41.49s; not very good
41
# with slots, takes 37.35s; without takes 39.16, a bit surprising
43
# with the delta calculation mixed in with the add method, rather than
44
# separated, takes 36.78s
46
# with delta folded in and mutation of the list, 36.13s
48
# with all this and simplification of add code, 33s
54
# TODO: Perhaps have copy method for Weave instances?
25
56
# XXX: If we do weaves this way, will a merge still behave the same
26
57
# way if it's done in a different order? That's a pretty desirable
44
75
# TODO: Parallel-extract that passes back each line along with a
45
76
# description of which revisions include it. Nice for checking all
46
# shas or calculating stats in parallel.
48
79
# TODO: Using a single _extract routine and then processing the output
49
80
# is probably inefficient. It's simple enough that we can afford to
50
81
# have slight specializations for different ways its used: annotate,
51
82
# basis for add, get, etc.
53
# TODO: Probably the API should work only in names to hide the integer
54
# indexes from the user.
56
# TODO: Is there any potential performance win by having an add()
57
# variant that is passed a pre-cooked version of the single basis
60
# TODO: Reweave can possibly be made faster by remembering diffs
61
# where the basis and destination are unchanged.
63
# FIXME: Sometimes we will be given a parents list for a revision
64
# that includes some redundant parents (i.e. already a parent of
65
# something in the list.) We should eliminate them. This can
66
# be done fairly efficiently because the sequence numbers constrain
67
# the possible relationships.
84
# TODO: Perhaps the API should work only in names to hide the integer
85
# indexes from the user?
71
from difflib import SequenceMatcher
73
from bzrlib.trace import mutter
76
93
class WeaveError(Exception):
170
183
For each name, the version number.
173
Descriptive name of this weave; typically the filename if known.
177
__slots__ = ['_weave', '_parents', '_sha1s', '_names', '_name_map',
186
__slots__ = ['_weave', '_parents', '_sha1s', '_names', '_name_map']
180
def __init__(self, weave_name=None):
182
190
self._parents = []
185
193
self._name_map = {}
186
self._weave_name = weave_name
190
"""Return a deep copy of self.
192
The copy can be modified without affecting the original weave."""
194
other._weave = self._weave[:]
195
other._parents = self._parents[:]
196
other._sha1s = self._sha1s[:]
197
other._names = self._names[:]
198
other._name_map = self._name_map.copy()
199
other._weave_name = self._weave_name
202
196
def __eq__(self, other):
203
197
if not isinstance(other, Weave):
211
205
return not self.__eq__(other)
214
def maybe_lookup(self, name_or_index):
215
"""Convert possible symbolic name to index, or pass through indexes."""
216
if isinstance(name_or_index, (int, long)):
219
return self.lookup(name_or_index)
222
208
def lookup(self, name):
223
"""Convert symbolic version name to index."""
225
210
return self._name_map[name]
227
raise WeaveError("name %r not present in weave %r" %
228
(name, self._weave_name))
231
def iter_names(self):
232
"""Yield a list of all names in this weave."""
233
return iter(self._names)
235
def idx_to_name(self, version):
236
return self._names[version]
239
def _check_repeated_add(self, name, parents, text, sha1):
240
"""Check that a duplicated add is OK.
242
If it is, return the (old) index; otherwise raise an exception.
244
idx = self.lookup(name)
245
if sorted(self._parents[idx]) != sorted(parents):
246
raise WeaveError("name \"%s\" already present in weave "
247
"with different parents" % name)
248
if sha1 != self._sha1s[idx]:
249
raise WeaveError("name \"%s\" already present in weave "
250
"with different text" % name)
255
def add(self, name, parents, text, sha1=None):
212
raise WeaveError("name %s not present in weave" % name)
215
def add(self, name, parents, text):
256
216
"""Add a single text on top of the weave.
258
218
Returns the index number of the newly added version.
265
225
List or set of direct parent version numbers.
268
Sequence of lines to be added in the new version.
270
sha -- SHA-1 of the file, if known. This is trusted to be
273
from bzrlib.osutils import sha_strings
228
Sequence of lines to be added in the new version."""
275
230
assert isinstance(name, basestring)
277
sha1 = sha_strings(text)
278
231
if name in self._name_map:
279
return self._check_repeated_add(name, parents, text, sha1)
281
parents = map(self.maybe_lookup, parents)
232
raise WeaveError("name %r already present in weave" % name)
282
234
self._check_versions(parents)
283
235
## self._check_lines(text)
284
236
new_version = len(self._parents)
287
243
# if we abort after here the (in-memory) weave will be corrupt because only
288
244
# some fields are updated
378
335
return new_version
380
def add_identical(self, old_rev_id, new_rev_id, parents):
381
"""Add an identical text to old_rev_id as new_rev_id."""
382
old_lines = self.get(self.lookup(old_rev_id))
383
self.add(new_rev_id, parents, old_lines)
385
338
def inclusions(self, versions):
386
339
"""Return set of all ancestors of given version(s)."""
387
340
i = set(versions)
388
for v in xrange(max(versions), 0, -1):
390
# include all its parents
391
i.update(self._parents[v])
393
## except IndexError:
394
## raise ValueError("version %d not present in weave" % v)
397
def parents(self, version):
398
return self._parents[version]
401
def parent_names(self, version):
402
"""Return version names for parents of a version."""
403
return map(self.idx_to_name, self._parents[self.lookup(version)])
345
# include all its parents
346
i.update(self._parents[v])
350
raise ValueError("version %d not present in weave" % v)
406
353
def minimal_parents(self, version):
562
def get_iter(self, name_or_index):
504
def get_iter(self, version):
563
505
"""Yield lines for the specified version."""
564
incls = [self.maybe_lookup(name_or_index)]
565
for origin, lineno, line in self._extract(incls):
506
for origin, lineno, line in self._extract([version]):
569
def get_text(self, name_or_index):
570
return ''.join(self.get_iter(name_or_index))
571
assert isinstance(version, int)
574
def get_lines(self, name_or_index):
575
return list(self.get_iter(name_or_index))
510
def get(self, index):
511
return list(self.get_iter(index))
581
514
def mash_iter(self, included):
582
515
"""Return composed version of multiple included versions."""
583
included = map(self.maybe_lookup, included)
584
516
for origin, lineno, text in self._extract(included):
774
def join(self, other):
775
"""Integrate versions from other into this weave.
777
The resulting weave contains all the history of both weaves;
778
any version you could retrieve from either self or other can be
779
retrieved from self after this call.
781
It is illegal for the two weaves to contain different values
782
or different parents for any version. See also reweave().
784
if other.numversions() == 0:
785
return # nothing to update, easy
786
# two loops so that we do not change ourselves before verifying it
788
# work through in index order to make sure we get all dependencies
789
for other_idx, name in enumerate(other._names):
790
if self._check_version_consistent(other, other_idx, name):
792
for other_idx, name in enumerate(other._names):
793
# TODO: If all the parents of the other version are already
794
# present then we can avoid some work by just taking the delta
795
# and adjusting the offsets.
796
new_parents = self._imported_parents(other, other_idx)
797
lines = other.get_lines(other_idx)
798
sha1 = other._sha1s[other_idx]
799
self.add(name, new_parents, lines, sha1)
802
def _imported_parents(self, other, other_idx):
803
"""Return list of parents in self corresponding to indexes in other."""
805
for parent_idx in other._parents[other_idx]:
806
parent_name = other._names[parent_idx]
807
if parent_name not in self._names:
808
# should not be possible
809
raise WeaveError("missing parent {%s} of {%s} in %r"
810
% (parent_name, other._name_map[other_idx], self))
811
new_parents.append(self._name_map[parent_name])
814
def _check_version_consistent(self, other, other_idx, name):
815
"""Check if a version in consistent in this and other.
817
To be consistent it must have:
820
* the same direct parents (by name, not index, and disregarding
823
If present & correct return True;
824
if not present in self return False;
825
if inconsistent raise error."""
826
this_idx = self._name_map.get(name, -1)
828
if self._sha1s[this_idx] != other._sha1s[other_idx]:
829
raise WeaveError("inconsistent texts for version {%s} "
830
"when joining weaves"
832
self_parents = self._parents[this_idx]
833
other_parents = other._parents[other_idx]
834
n1 = [self._names[i] for i in self_parents]
835
n2 = [other._names[i] for i in other_parents]
839
raise WeaveParentMismatch("inconsistent parents "
840
"for version {%s}: %s vs %s" % (name, n1, n2))
846
def reweave(self, other):
847
"""Reweave self with other."""
848
new_weave = reweave(self, other)
849
for attr in self.__slots__:
850
setattr(self, attr, getattr(new_weave, attr))
854
"""Combine two weaves and return the result.
856
This works even if a revision R has different parents in
857
wa and wb. In the resulting weave all the parents are given.
859
This is done by just building up a new weave, maintaining ordering
860
of the versions in the two inputs. More efficient approaches
861
might be possible but it should only be necessary to do
862
this operation rarely, when a new previously ghost version is
867
queue_a = range(wa.numversions())
868
queue_b = range(wb.numversions())
869
# first determine combined parents of all versions
870
# map from version name -> all parent names
871
combined_parents = _reweave_parent_graphs(wa, wb)
872
mutter("combined parents: %r", combined_parents)
873
order = _make_reweave_order(wa._names, wb._names, combined_parents)
874
mutter("order to reweave: %r", order)
876
if name in wa._name_map:
877
lines = wa.get_lines(name)
878
if name in wb._name_map:
879
assert lines == wb.get_lines(name)
881
lines = wb.get_lines(name)
882
wr.add(name, combined_parents[name], lines)
886
def _reweave_parent_graphs(wa, wb):
887
"""Return combined parent ancestry for two weaves.
889
Returned as a list of (version_name, set(parent_names))"""
891
for weave in [wa, wb]:
892
for idx, name in enumerate(weave._names):
893
p = combined.setdefault(name, set())
894
p.update(map(weave.idx_to_name, weave._parents[idx]))
898
def _make_reweave_order(wa_order, wb_order, combined_parents):
899
"""Return an order to reweave versions respecting parents."""
903
next_a = next_b = None
904
len_a = len(wa_order)
905
len_b = len(wb_order)
906
while ia < len(wa_order) or ib < len(wb_order):
908
next_a = wa_order[ia]
912
if combined_parents[next_a].issubset(done):
914
result.append(next_a)
918
next_b = wb_order[ib]
922
elif combined_parents[next_b].issubset(done):
924
result.append(next_b)
927
raise WeaveError("don't know how to reweave at {%s} and {%s}"
932
712
def weave_toc(w):
added
removed
bzrlib/weave.py
