Mercurial > hg
annotate mercurial/similar.py @ 24847:b705e5ab3b07 stable
bundle2: capture transaction rollback message output (issue4614)
The output from the transaction rollback was not included into the reply bundle.
It was eventually caught by the usual 'unbundle' output capture and sent to the
client but the result was out of order on the client side. We now capture the
output for the transaction release and transmit it the same way as all other
output.
We should probably rethink the whole output capture things but this would not be
appropriate for stable.
The is still multiple cases were output failed to be properly capture, they will
be fixed in later changesets.
author | Pierre-Yves David <pierre-yves.david@fb.com> |
---|---|
date | Thu, 23 Apr 2015 14:20:36 +0100 |
parents | 525fdb738975 |
children | a56c47ed3885 |
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 |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
8 from i18n import _ |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
9 import util |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
10 import mdiff |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
11 import bdiff |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
12 |
11060
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
13 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
|
14 '''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
|
15 |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
16 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
|
17 (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
|
18 ''' |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
19 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
|
20 |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
21 # 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
|
22 hashes = {} |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
23 for i, fctx in enumerate(removed): |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
24 repo.ui.progress(_('searching for exact renames'), i, total=numfiles) |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
25 h = util.sha1(fctx.data()).digest() |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
26 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
|
27 |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
28 # 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
|
29 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
|
30 repo.ui.progress(_('searching for exact renames'), i + len(removed), |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
31 total=numfiles) |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
32 h = util.sha1(fctx.data()).digest() |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
33 if h in hashes: |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
34 yield (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
|
35 |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
36 # Done |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
37 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
|
38 |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
39 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
|
40 '''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
|
41 |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
42 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
|
43 (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
|
44 ''' |
11059
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
45 copies = {} |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
46 for i, r in enumerate(removed): |
16683 | 47 repo.ui.progress(_('searching for similar files'), i, |
48 total=len(removed)) | |
11059
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
49 |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
50 # lazily load text |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
51 @util.cachefunc |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
52 def data(): |
11060
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
53 orig = r.data() |
11059
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
54 return orig, mdiff.splitnewlines(orig) |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
55 |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
56 def score(text): |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
57 orig, lines = data() |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
58 # bdiff.blocks() returns blocks of matching lines |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
59 # count the number of bytes in each |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
60 equal = 0 |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
61 matches = bdiff.blocks(text, orig) |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
62 for x1, x2, y1, y2 in matches: |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
63 for line in lines[y1:y2]: |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
64 equal += len(line) |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
65 |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
66 lengths = len(text) + len(orig) |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
67 return equal * 2.0 / lengths |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
68 |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
69 for a in added: |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
70 bestscore = copies.get(a, (None, threshold))[1] |
11060
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
71 myscore = score(a.data()) |
11059
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
72 if myscore >= bestscore: |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
73 copies[a] = (r, myscore) |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
74 repo.ui.progress(_('searching'), None) |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
75 |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
76 for dest, v in copies.iteritems(): |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
77 source, score = v |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
78 yield source, dest, score |
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
79 |
11060
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
80 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
|
81 '''find renamed files -- yields (before, after, score) tuples''' |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
82 parentctx = repo['.'] |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
83 workingctx = repo[None] |
11059
ef4aa90b1e58
Move 'findrenames' code into its own file.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
diff
changeset
|
84 |
11060
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
85 # 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
|
86 # 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
|
87 # harm than good. We strip them out here to avoid matching them later on. |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
88 addedfiles = set([workingctx[fp] for fp in added |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
89 if workingctx[fp].size() > 0]) |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
90 removedfiles = set([parentctx[fp] for fp in removed |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
91 if fp in parentctx and parentctx[fp].size() > 0]) |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
92 |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
93 # Find exact matches. |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
94 for (a, b) in _findexactmatches(repo, |
11085
0c8646292ca4
fix coding style
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents:
11060
diff
changeset
|
95 sorted(addedfiles), sorted(removedfiles)): |
11060
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
96 addedfiles.remove(b) |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
97 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
|
98 |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
99 # 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
|
100 if threshold < 1.0: |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
101 for (a, b, score) in _findsimilarmatches(repo, |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
102 sorted(addedfiles), sorted(removedfiles), threshold): |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
103 yield (a.path(), b.path(), score) |
e6df01776e08
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
David Greenaway <hg-dev@davidgreenaway.com>
parents:
11059
diff
changeset
|
104 |