author | Yuya Nishihara <yuya@tcha.org> |
Sat, 13 Feb 2016 20:13:45 +0900 | |
changeset 28272 | 760f9d04842a |
parent 28183 | e07daee83029 |
child 29205 | a0939666b836 |
permissions | -rw-r--r-- |
28129
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
1 |
# automv.py |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
2 |
# |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
3 |
# Copyright 2013-2016 Facebook, Inc. |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
4 |
# |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
5 |
# This software may be used and distributed according to the terms of the |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
6 |
# GNU General Public License version 2 or any later version. |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
7 |
"""Check for unrecorded moves at commit time (EXPERIMENTAL) |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
8 |
|
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
9 |
This extension checks at commit/amend time if any of the committed files |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
10 |
comes from an unrecorded mv. |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
11 |
|
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
12 |
The threshold at which a file is considered a move can be set with the |
28152
5ec1ce8fdf0a
automv: switch to specifying the similarity as an integer (0-100)
Martijn Pieters <mjpieters@fb.com>
parents:
28151
diff
changeset
|
13 |
``automv.similarity`` config option. This option takes a percentage between 0 |
28183
e07daee83029
automv: use 95 as the default similarity threshold
Martijn Pieters <mjpieters@fb.com>
parents:
28152
diff
changeset
|
14 |
(disabled) and 100 (files must be identical), the default is 95. |
28129
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
15 |
|
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
16 |
""" |
28183
e07daee83029
automv: use 95 as the default similarity threshold
Martijn Pieters <mjpieters@fb.com>
parents:
28152
diff
changeset
|
17 |
|
e07daee83029
automv: use 95 as the default similarity threshold
Martijn Pieters <mjpieters@fb.com>
parents:
28152
diff
changeset
|
18 |
# Using 95 as a default similarity is based on an analysis of the mercurial |
e07daee83029
automv: use 95 as the default similarity threshold
Martijn Pieters <mjpieters@fb.com>
parents:
28152
diff
changeset
|
19 |
# repositories of the cpython, mozilla-central & mercurial repositories, as |
e07daee83029
automv: use 95 as the default similarity threshold
Martijn Pieters <mjpieters@fb.com>
parents:
28152
diff
changeset
|
20 |
# well as 2 very large facebook repositories. At 95 50% of all potential |
e07daee83029
automv: use 95 as the default similarity threshold
Martijn Pieters <mjpieters@fb.com>
parents:
28152
diff
changeset
|
21 |
# missed moves would be caught, as well as correspond with 87% of all |
e07daee83029
automv: use 95 as the default similarity threshold
Martijn Pieters <mjpieters@fb.com>
parents:
28152
diff
changeset
|
22 |
# explicitly marked moves. Together, 80% of moved files are 95% similar or |
e07daee83029
automv: use 95 as the default similarity threshold
Martijn Pieters <mjpieters@fb.com>
parents:
28152
diff
changeset
|
23 |
# more. |
e07daee83029
automv: use 95 as the default similarity threshold
Martijn Pieters <mjpieters@fb.com>
parents:
28152
diff
changeset
|
24 |
# |
e07daee83029
automv: use 95 as the default similarity threshold
Martijn Pieters <mjpieters@fb.com>
parents:
28152
diff
changeset
|
25 |
# See http://markmail.org/thread/5pxnljesvufvom57 for context. |
e07daee83029
automv: use 95 as the default similarity threshold
Martijn Pieters <mjpieters@fb.com>
parents:
28152
diff
changeset
|
26 |
|
28129
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
27 |
from __future__ import absolute_import |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
28 |
|
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
29 |
from mercurial import ( |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
30 |
commands, |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
31 |
copies, |
28183
e07daee83029
automv: use 95 as the default similarity threshold
Martijn Pieters <mjpieters@fb.com>
parents:
28152
diff
changeset
|
32 |
error, |
28129
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
33 |
extensions, |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
34 |
scmutil, |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
35 |
similar |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
36 |
) |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
37 |
from mercurial.i18n import _ |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
38 |
|
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
39 |
def extsetup(ui): |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
40 |
entry = extensions.wrapcommand( |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
41 |
commands.table, 'commit', mvcheck) |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
42 |
entry[1].append( |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
43 |
('', 'no-automv', None, |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
44 |
_('disable automatic file move detection'))) |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
45 |
|
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
46 |
def mvcheck(orig, ui, repo, *pats, **opts): |
28149
d356d5250ab2
automv: improve function docstrings
Martijn Pieters <mjpieters@fb.com>
parents:
28148
diff
changeset
|
47 |
"""Hook to check for moves at commit time""" |
28151
74e3d634a30e
automv: do not release lock between marking files and the actual commit
Martijn Pieters <mjpieters@fb.com>
parents:
28150
diff
changeset
|
48 |
renames = None |
28129
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
49 |
disabled = opts.pop('no_automv', False) |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
50 |
if not disabled: |
28183
e07daee83029
automv: use 95 as the default similarity threshold
Martijn Pieters <mjpieters@fb.com>
parents:
28152
diff
changeset
|
51 |
threshold = ui.configint('automv', 'similarity', 95) |
e07daee83029
automv: use 95 as the default similarity threshold
Martijn Pieters <mjpieters@fb.com>
parents:
28152
diff
changeset
|
52 |
if not 0 <= threshold <= 100: |
e07daee83029
automv: use 95 as the default similarity threshold
Martijn Pieters <mjpieters@fb.com>
parents:
28152
diff
changeset
|
53 |
raise error.Abort(_('automv.similarity must be between 0 and 100')) |
28129
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
54 |
if threshold > 0: |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
55 |
match = scmutil.match(repo[None], pats, opts) |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
56 |
added, removed = _interestingfiles(repo, match) |
28152
5ec1ce8fdf0a
automv: switch to specifying the similarity as an integer (0-100)
Martijn Pieters <mjpieters@fb.com>
parents:
28151
diff
changeset
|
57 |
renames = _findrenames(repo, match, added, removed, |
5ec1ce8fdf0a
automv: switch to specifying the similarity as an integer (0-100)
Martijn Pieters <mjpieters@fb.com>
parents:
28151
diff
changeset
|
58 |
threshold / 100.0) |
28151
74e3d634a30e
automv: do not release lock between marking files and the actual commit
Martijn Pieters <mjpieters@fb.com>
parents:
28150
diff
changeset
|
59 |
|
74e3d634a30e
automv: do not release lock between marking files and the actual commit
Martijn Pieters <mjpieters@fb.com>
parents:
28150
diff
changeset
|
60 |
with repo.wlock(): |
74e3d634a30e
automv: do not release lock between marking files and the actual commit
Martijn Pieters <mjpieters@fb.com>
parents:
28150
diff
changeset
|
61 |
if renames is not None: |
28150
7a984cece04a
automv: reuse existing scutil._markchanges() function
Martijn Pieters <mjpieters@fb.com>
parents:
28149
diff
changeset
|
62 |
scmutil._markchanges(repo, (), (), renames) |
28151
74e3d634a30e
automv: do not release lock between marking files and the actual commit
Martijn Pieters <mjpieters@fb.com>
parents:
28150
diff
changeset
|
63 |
return orig(ui, repo, *pats, **opts) |
28129
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
64 |
|
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
65 |
def _interestingfiles(repo, matcher): |
28149
d356d5250ab2
automv: improve function docstrings
Martijn Pieters <mjpieters@fb.com>
parents:
28148
diff
changeset
|
66 |
"""Find what files were added or removed in this commit. |
d356d5250ab2
automv: improve function docstrings
Martijn Pieters <mjpieters@fb.com>
parents:
28148
diff
changeset
|
67 |
|
d356d5250ab2
automv: improve function docstrings
Martijn Pieters <mjpieters@fb.com>
parents:
28148
diff
changeset
|
68 |
Returns a tuple of two lists: (added, removed). Only files not *already* |
d356d5250ab2
automv: improve function docstrings
Martijn Pieters <mjpieters@fb.com>
parents:
28148
diff
changeset
|
69 |
marked as moved are included in the added list. |
d356d5250ab2
automv: improve function docstrings
Martijn Pieters <mjpieters@fb.com>
parents:
28148
diff
changeset
|
70 |
|
d356d5250ab2
automv: improve function docstrings
Martijn Pieters <mjpieters@fb.com>
parents:
28148
diff
changeset
|
71 |
""" |
28146
28024d0d42dc
automv: simplify retrieving the status
Martijn Pieters <mjpieters@fb.com>
parents:
28129
diff
changeset
|
72 |
stat = repo.status(match=matcher) |
28129
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
73 |
added = stat[1] |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
74 |
removed = stat[2] |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
75 |
|
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
76 |
copy = copies._forwardcopies(repo['.'], repo[None], matcher) |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
77 |
# remove the copy files for which we already have copy info |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
78 |
added = [f for f in added if f not in copy] |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
79 |
|
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
80 |
return added, removed |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
81 |
|
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
82 |
def _findrenames(repo, matcher, added, removed, similarity): |
28149
d356d5250ab2
automv: improve function docstrings
Martijn Pieters <mjpieters@fb.com>
parents:
28148
diff
changeset
|
83 |
"""Find what files in added are really moved files. |
d356d5250ab2
automv: improve function docstrings
Martijn Pieters <mjpieters@fb.com>
parents:
28148
diff
changeset
|
84 |
|
d356d5250ab2
automv: improve function docstrings
Martijn Pieters <mjpieters@fb.com>
parents:
28148
diff
changeset
|
85 |
Any file named in removed that is at least similarity% similar to a file |
d356d5250ab2
automv: improve function docstrings
Martijn Pieters <mjpieters@fb.com>
parents:
28148
diff
changeset
|
86 |
in added is seen as a rename. |
d356d5250ab2
automv: improve function docstrings
Martijn Pieters <mjpieters@fb.com>
parents:
28148
diff
changeset
|
87 |
|
d356d5250ab2
automv: improve function docstrings
Martijn Pieters <mjpieters@fb.com>
parents:
28148
diff
changeset
|
88 |
""" |
28129
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
89 |
renames = {} |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
90 |
if similarity > 0: |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
91 |
for src, dst, score in similar.findrenames( |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
92 |
repo, added, removed, similarity): |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
93 |
if repo.ui.verbose: |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
94 |
repo.ui.status( |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
95 |
_('detected move of %s as %s (%d%% similar)\n') % ( |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
96 |
matcher.rel(src), matcher.rel(dst), score * 100)) |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
97 |
renames[dst] = src |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
98 |
if renames: |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
99 |
repo.ui.status(_('detected move of %d files\n') % len(renames)) |
7c40b4b7f8f1
automv: new experimental extension
Martijn Pieters <mjpieters@fb.com>
parents:
diff
changeset
|
100 |
return renames |