Mercurial > public > mercurial-scm > hg-stable
annotate mercurial/similar.py @ 31588:2e254165a37c
similar: do not look up and create filectx more than once
Benchmark with 50k added/removed files, on tmpfs:
$ hg addremove --dry-run --time -q
previous: real 16.070 secs (user 14.470+0.000 sys 1.580+0.000)
this patch: real 12.420 secs (user 11.120+0.000 sys 1.280+0.000)
author | Yuya Nishihara <yuya@tcha.org> |
---|---|
date | Thu, 23 Mar 2017 21:17:08 +0900 |
parents | b1528d195a13 |
children | 2efd9771323e |
rev | line source |
---|---|
11059
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
1 # similar.py - mechanisms for finding similar files |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
2 # |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
3 # Copyright 2005-2007 Matt Mackall <mpm@selenic.com> |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
4 # |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
5 # This software may be used and distributed according to the terms of the |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
6 # GNU General Public License version 2 or any later version. |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
7 |
27359
a56c47ed3885
similar: use absolute_import
Gregory Szorc <gregory.szorc@gmail.com>
parents:
16683
diff
changeset
|
8 from __future__ import absolute_import |
a56c47ed3885
similar: use absolute_import
Gregory Szorc <gregory.szorc@gmail.com>
parents:
16683
diff
changeset
|
9 |
29341
0d83ad967bf8
cleanup: replace uses of util.(md5|sha1|sha256|sha512) with hashlib.\1
Augie Fackler <raf@durin42.com>
parents:
29337
diff
changeset
|
10 import hashlib |
0d83ad967bf8
cleanup: replace uses of util.(md5|sha1|sha256|sha512) with hashlib.\1
Augie Fackler <raf@durin42.com>
parents:
29337
diff
changeset
|
11 |
27359
a56c47ed3885
similar: use absolute_import
Gregory Szorc <gregory.szorc@gmail.com>
parents:
16683
diff
changeset
|
12 from .i18n import _ |
a56c47ed3885
similar: use absolute_import
Gregory Szorc <gregory.szorc@gmail.com>
parents:
16683
diff
changeset
|
13 from . import ( |
a56c47ed3885
similar: use absolute_import
Gregory Szorc <gregory.szorc@gmail.com>
parents:
16683
diff
changeset
|
14 bdiff, |
a56c47ed3885
similar: use absolute_import
Gregory Szorc <gregory.szorc@gmail.com>
parents:
16683
diff
changeset
|
15 mdiff, |
a56c47ed3885
similar: use absolute_import
Gregory Szorc <gregory.szorc@gmail.com>
parents:
16683
diff
changeset
|
16 ) |
11059
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
17 |
11060
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
18 def _findexactmatches(repo, added, removed): |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
19 '''find renamed files that have no changes |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
20 |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
21 Takes a list of new filectxs and a list of removed filectxs, and yields |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
22 (before, after) tuples of exact matches. |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
23 ''' |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
24 numfiles = len(added) + len(removed) |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
25 |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
26 # Get hashes of removed files. |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
27 hashes = {} |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
28 for i, fctx in enumerate(removed): |
28468
0d6b3630b9a3
similar: specify unit for ui.progress when operating on files
Anton Shestakov <av6@dwimlabs.net>
parents:
27359
diff
changeset
|
29 repo.ui.progress(_('searching for exact renames'), i, total=numfiles, |
0d6b3630b9a3
similar: specify unit for ui.progress when operating on files
Anton Shestakov <av6@dwimlabs.net>
parents:
27359
diff
changeset
|
30 unit=_('files')) |
29341
0d83ad967bf8
cleanup: replace uses of util.(md5|sha1|sha256|sha512) with hashlib.\1
Augie Fackler <raf@durin42.com>
parents:
29337
diff
changeset
|
31 h = hashlib.sha1(fctx.data()).digest() |
11060
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
32 hashes[h] = fctx |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
33 |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
34 # For each added file, see if it corresponds to a removed file. |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
35 for i, fctx in enumerate(added): |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
36 repo.ui.progress(_('searching for exact renames'), i + len(removed), |
28468
0d6b3630b9a3
similar: specify unit for ui.progress when operating on files
Anton Shestakov <av6@dwimlabs.net>
parents:
27359
diff
changeset
|
37 total=numfiles, unit=_('files')) |
31220
e1d035905b2e
similar: compare between actual file contents for exact identity
FUJIWARA Katsunori <foozy@lares.dti.ne.jp>
parents:
30809
diff
changeset
|
38 adata = fctx.data() |
e1d035905b2e
similar: compare between actual file contents for exact identity
FUJIWARA Katsunori <foozy@lares.dti.ne.jp>
parents:
30809
diff
changeset
|
39 h = hashlib.sha1(adata).digest() |
11060
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
40 if h in hashes: |
31220
e1d035905b2e
similar: compare between actual file contents for exact identity
FUJIWARA Katsunori <foozy@lares.dti.ne.jp>
parents:
30809
diff
changeset
|
41 rfctx = hashes[h] |
e1d035905b2e
similar: compare between actual file contents for exact identity
FUJIWARA Katsunori <foozy@lares.dti.ne.jp>
parents:
30809
diff
changeset
|
42 # compare between actual file contents for exact identity |
e1d035905b2e
similar: compare between actual file contents for exact identity
FUJIWARA Katsunori <foozy@lares.dti.ne.jp>
parents:
30809
diff
changeset
|
43 if adata == rfctx.data(): |
e1d035905b2e
similar: compare between actual file contents for exact identity
FUJIWARA Katsunori <foozy@lares.dti.ne.jp>
parents:
30809
diff
changeset
|
44 yield (rfctx, fctx) |
11060
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
45 |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
46 # Done |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
47 repo.ui.progress(_('searching for exact renames'), None) |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
48 |
30805
0ae287eb6a4f
similar: move score function to module level
Sean Farley <sean@farley.io>
parents:
30791
diff
changeset
|
49 def _ctxdata(fctx): |
0ae287eb6a4f
similar: move score function to module level
Sean Farley <sean@farley.io>
parents:
30791
diff
changeset
|
50 # lazily load text |
0ae287eb6a4f
similar: move score function to module level
Sean Farley <sean@farley.io>
parents:
30791
diff
changeset
|
51 orig = fctx.data() |
0ae287eb6a4f
similar: move score function to module level
Sean Farley <sean@farley.io>
parents:
30791
diff
changeset
|
52 return orig, mdiff.splitnewlines(orig) |
0ae287eb6a4f
similar: move score function to module level
Sean Farley <sean@farley.io>
parents:
30791
diff
changeset
|
53 |
30809
8614546154cb
similar: remove caching from the module level
Pierre-Yves David <pierre-yves.david@ens-lyon.org>
parents:
30805
diff
changeset
|
54 def _score(fctx, otherdata): |
8614546154cb
similar: remove caching from the module level
Pierre-Yves David <pierre-yves.david@ens-lyon.org>
parents:
30805
diff
changeset
|
55 orig, lines = otherdata |
8614546154cb
similar: remove caching from the module level
Pierre-Yves David <pierre-yves.david@ens-lyon.org>
parents:
30805
diff
changeset
|
56 text = fctx.data() |
30805
0ae287eb6a4f
similar: move score function to module level
Sean Farley <sean@farley.io>
parents:
30791
diff
changeset
|
57 # bdiff.blocks() returns blocks of matching lines |
0ae287eb6a4f
similar: move score function to module level
Sean Farley <sean@farley.io>
parents:
30791
diff
changeset
|
58 # count the number of bytes in each |
0ae287eb6a4f
similar: move score function to module level
Sean Farley <sean@farley.io>
parents:
30791
diff
changeset
|
59 equal = 0 |
0ae287eb6a4f
similar: move score function to module level
Sean Farley <sean@farley.io>
parents:
30791
diff
changeset
|
60 matches = bdiff.blocks(text, orig) |
0ae287eb6a4f
similar: move score function to module level
Sean Farley <sean@farley.io>
parents:
30791
diff
changeset
|
61 for x1, x2, y1, y2 in matches: |
0ae287eb6a4f
similar: move score function to module level
Sean Farley <sean@farley.io>
parents:
30791
diff
changeset
|
62 for line in lines[y1:y2]: |
0ae287eb6a4f
similar: move score function to module level
Sean Farley <sean@farley.io>
parents:
30791
diff
changeset
|
63 equal += len(line) |
0ae287eb6a4f
similar: move score function to module level
Sean Farley <sean@farley.io>
parents:
30791
diff
changeset
|
64 |
0ae287eb6a4f
similar: move score function to module level
Sean Farley <sean@farley.io>
parents:
30791
diff
changeset
|
65 lengths = len(text) + len(orig) |
0ae287eb6a4f
similar: move score function to module level
Sean Farley <sean@farley.io>
parents:
30791
diff
changeset
|
66 return equal * 2.0 / lengths |
0ae287eb6a4f
similar: move score function to module level
Sean Farley <sean@farley.io>
parents:
30791
diff
changeset
|
67 |
30809
8614546154cb
similar: remove caching from the module level
Pierre-Yves David <pierre-yves.david@ens-lyon.org>
parents:
30805
diff
changeset
|
68 def score(fctx1, fctx2): |
8614546154cb
similar: remove caching from the module level
Pierre-Yves David <pierre-yves.david@ens-lyon.org>
parents:
30805
diff
changeset
|
69 return _score(fctx1, _ctxdata(fctx2)) |
8614546154cb
similar: remove caching from the module level
Pierre-Yves David <pierre-yves.david@ens-lyon.org>
parents:
30805
diff
changeset
|
70 |
11060
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
71 def _findsimilarmatches(repo, added, removed, threshold): |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
72 '''find potentially renamed files based on similar file content |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
73 |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
74 Takes a list of new filectxs and a list of removed filectxs, and yields |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
75 (before, after, score) tuples of partial matches. |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
76 ''' |
11059
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
77 copies = {} |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
78 for i, r in enumerate(removed): |
16683 | 79 repo.ui.progress(_('searching for similar files'), i, |
28468
0d6b3630b9a3
similar: specify unit for ui.progress when operating on files
Anton Shestakov <av6@dwimlabs.net>
parents:
27359
diff
changeset
|
80 total=len(removed), unit=_('files')) |
11059
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
81 |
30809
8614546154cb
similar: remove caching from the module level
Pierre-Yves David <pierre-yves.david@ens-lyon.org>
parents:
30805
diff
changeset
|
82 data = None |
11059
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
83 for a in added: |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
84 bestscore = copies.get(a, (None, threshold))[1] |
30809
8614546154cb
similar: remove caching from the module level
Pierre-Yves David <pierre-yves.david@ens-lyon.org>
parents:
30805
diff
changeset
|
85 if data is None: |
8614546154cb
similar: remove caching from the module level
Pierre-Yves David <pierre-yves.david@ens-lyon.org>
parents:
30805
diff
changeset
|
86 data = _ctxdata(r) |
8614546154cb
similar: remove caching from the module level
Pierre-Yves David <pierre-yves.david@ens-lyon.org>
parents:
30805
diff
changeset
|
87 myscore = _score(a, data) |
11059
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
88 if myscore >= bestscore: |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
89 copies[a] = (r, myscore) |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
90 repo.ui.progress(_('searching'), None) |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
91 |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
92 for dest, v in copies.iteritems(): |
30791
ada160a8cfd8
similar: rename local variable to not collide with previous
Sean Farley <sean@farley.io>
parents:
29341
diff
changeset
|
93 source, bscore = v |
ada160a8cfd8
similar: rename local variable to not collide with previous
Sean Farley <sean@farley.io>
parents:
29341
diff
changeset
|
94 yield source, dest, bscore |
11059
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
95 |
31588
2e254165a37c
similar: do not look up and create filectx more than once
Yuya Nishihara <yuya@tcha.org>
parents:
31587
diff
changeset
|
96 def _dropempty(fctxs): |
2e254165a37c
similar: do not look up and create filectx more than once
Yuya Nishihara <yuya@tcha.org>
parents:
31587
diff
changeset
|
97 return [x for x in fctxs if x.size() > 0] |
2e254165a37c
similar: do not look up and create filectx more than once
Yuya Nishihara <yuya@tcha.org>
parents:
31587
diff
changeset
|
98 |
11060
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
99 def findrenames(repo, added, removed, threshold): |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
100 '''find renamed files -- yields (before, after, score) tuples''' |
31587
b1528d195a13
similar: use common names for changectx variables
Yuya Nishihara <yuya@tcha.org>
parents:
31586
diff
changeset
|
101 wctx = repo[None] |
b1528d195a13
similar: use common names for changectx variables
Yuya Nishihara <yuya@tcha.org>
parents:
31586
diff
changeset
|
102 pctx = wctx.p1() |
11059
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
103 |
11060
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
104 # Zero length files will be frequently unrelated to each other, and |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
105 # tracking the deletion/addition of such a file will probably cause more |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
106 # harm than good. We strip them out here to avoid matching them later on. |
31588
2e254165a37c
similar: do not look up and create filectx more than once
Yuya Nishihara <yuya@tcha.org>
parents:
31587
diff
changeset
|
107 addedfiles = _dropempty(wctx[fp] for fp in sorted(added)) |
2e254165a37c
similar: do not look up and create filectx more than once
Yuya Nishihara <yuya@tcha.org>
parents:
31587
diff
changeset
|
108 removedfiles = _dropempty(pctx[fp] for fp in sorted(removed) if fp in pctx) |
11060
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
109 |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
110 # Find exact matches. |
31586
d3e2af4e0128
similar: get rid of quadratic addedfiles.remove()
Yuya Nishihara <yuya@tcha.org>
parents:
31585
diff
changeset
|
111 matchedfiles = set() |
d3e2af4e0128
similar: get rid of quadratic addedfiles.remove()
Yuya Nishihara <yuya@tcha.org>
parents:
31585
diff
changeset
|
112 for (a, b) in _findexactmatches(repo, addedfiles, removedfiles): |
d3e2af4e0128
similar: get rid of quadratic addedfiles.remove()
Yuya Nishihara <yuya@tcha.org>
parents:
31585
diff
changeset
|
113 matchedfiles.add(b) |
11060
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
114 yield (a.path(), b.path(), 1.0) |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
115 |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
116 # If the user requested similar files to be matched, search for them also. |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
117 if threshold < 1.0: |
31586
d3e2af4e0128
similar: get rid of quadratic addedfiles.remove()
Yuya Nishihara <yuya@tcha.org>
parents:
31585
diff
changeset
|
118 addedfiles = [x for x in addedfiles if x not in matchedfiles] |
31585
3a383caa97f4
similar: sort files not by object id but by path for stable result
Yuya Nishihara <yuya@tcha.org>
parents:
31220
diff
changeset
|
119 for (a, b, score) in _findsimilarmatches(repo, addedfiles, |
3a383caa97f4
similar: sort files not by object id but by path for stable result
Yuya Nishihara <yuya@tcha.org>
parents:
31220
diff
changeset
|
120 removedfiles, threshold): |
11060
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
121 yield (a.path(), b.path(), score) |