Mercurial > hg
view mercurial/similar.py @ 28627:d7af9b4ae7dd
graphmod: set default edge styles for ascii graphs (BC)
Leaving regular parent edges set to |, grandparent edges set to : and missing
parent edges set to end early. A sample graph:
o changeset: 32:d06dffa21a31
|\ parent: 27:886ed638191b
| : parent: 31:621d83e11f67
| :
o : changeset: 31:621d83e11f67
|\: parent: 21:d42a756af44d
| : parent: 30:6e11cd4b648f
| :
o : changeset: 30:6e11cd4b648f
|\ \ parent: 28:44ecd0b9ae99
| ~ : parent: 29:cd9bb2be7593
| /
o : changeset: 28:44ecd0b9ae99
|\ \ parent: 1:6db2ef61d156
| ~ : parent: 26:7f25b6c2f0b9
| /
o : changeset: 26:7f25b6c2f0b9
|\ \ parent: 18:1aa84d96232a
| | : parent: 25:91da8ed57247
| | :
| o : changeset: 25:91da8ed57247
| |\: parent: 21:d42a756af44d
| | : parent: 24:a9c19a3d96b7
| | :
| o : changeset: 24:a9c19a3d96b7
| |\ \ parent: 0:e6eb3150255d
| | ~ : parent: 23:a01cddf0766d
| | /
| o : changeset: 23:a01cddf0766d
| |\ \ parent: 1:6db2ef61d156
| | ~ : parent: 22:e0d9cccacb5d
| | /
| o : changeset: 22:e0d9cccacb5d
|/:/ parent: 18:1aa84d96232a
| : parent: 21:d42a756af44d
| :
| o changeset: 21:d42a756af44d
| |\ parent: 19:31ddc2c1573b
| | | parent: 20:d30ed6450e32
| | |
+---o changeset: 20:d30ed6450e32
| | | parent: 0:e6eb3150255d
| | ~ parent: 18:1aa84d96232a
| |
| o changeset: 19:31ddc2c1573b
| |\ parent: 15:1dda3f72782d
| ~ ~ parent: 17:44765d7c06e0
|
o changeset: 18:1aa84d96232a
parent: 1:6db2ef61d156
parent: 15:1dda3f72782d
author | Martijn Pieters <mjpieters@fb.com> |
---|---|
date | Wed, 23 Mar 2016 13:34:47 -0700 |
parents | 0d6b3630b9a3 |
children | f72d0c2148da |
line wrap: on
line source
# similar.py - mechanisms for finding similar files # # Copyright 2005-2007 Matt Mackall <mpm@selenic.com> # # This software may be used and distributed according to the terms of the # GNU General Public License version 2 or any later version. from __future__ import absolute_import from .i18n import _ from . import ( bdiff, mdiff, util, ) def _findexactmatches(repo, added, removed): '''find renamed files that have no changes Takes a list of new filectxs and a list of removed filectxs, and yields (before, after) tuples of exact matches. ''' numfiles = len(added) + len(removed) # Get hashes of removed files. hashes = {} for i, fctx in enumerate(removed): repo.ui.progress(_('searching for exact renames'), i, total=numfiles, unit=_('files')) h = util.sha1(fctx.data()).digest() hashes[h] = fctx # For each added file, see if it corresponds to a removed file. for i, fctx in enumerate(added): repo.ui.progress(_('searching for exact renames'), i + len(removed), total=numfiles, unit=_('files')) h = util.sha1(fctx.data()).digest() if h in hashes: yield (hashes[h], fctx) # Done repo.ui.progress(_('searching for exact renames'), None) def _findsimilarmatches(repo, added, removed, threshold): '''find potentially renamed files based on similar file content Takes a list of new filectxs and a list of removed filectxs, and yields (before, after, score) tuples of partial matches. ''' copies = {} for i, r in enumerate(removed): repo.ui.progress(_('searching for similar files'), i, total=len(removed), unit=_('files')) # lazily load text @util.cachefunc def data(): orig = r.data() return orig, mdiff.splitnewlines(orig) def score(text): orig, lines = data() # bdiff.blocks() returns blocks of matching lines # count the number of bytes in each equal = 0 matches = bdiff.blocks(text, orig) for x1, x2, y1, y2 in matches: for line in lines[y1:y2]: equal += len(line) lengths = len(text) + len(orig) return equal * 2.0 / lengths for a in added: bestscore = copies.get(a, (None, threshold))[1] myscore = score(a.data()) if myscore >= bestscore: copies[a] = (r, myscore) repo.ui.progress(_('searching'), None) for dest, v in copies.iteritems(): source, score = v yield source, dest, score def findrenames(repo, added, removed, threshold): '''find renamed files -- yields (before, after, score) tuples''' parentctx = repo['.'] workingctx = repo[None] # Zero length files will be frequently unrelated to each other, and # tracking the deletion/addition of such a file will probably cause more # harm than good. We strip them out here to avoid matching them later on. addedfiles = set([workingctx[fp] for fp in added if workingctx[fp].size() > 0]) removedfiles = set([parentctx[fp] for fp in removed if fp in parentctx and parentctx[fp].size() > 0]) # Find exact matches. for (a, b) in _findexactmatches(repo, sorted(addedfiles), sorted(removedfiles)): addedfiles.remove(b) yield (a.path(), b.path(), 1.0) # If the user requested similar files to be matched, search for them also. if threshold < 1.0: for (a, b, score) in _findsimilarmatches(repo, sorted(addedfiles), sorted(removedfiles), threshold): yield (a.path(), b.path(), score)