Mercurial > hg
view mercurial/similar.py @ 37947:3ea3c96ada54
encoding: introduce tagging type for non-lossy non-ASCII string
This fixes the weird behavior of toutf8b(), which would convert a local
string back to UTF-8 *only if* it was lossy in the system encoding.
Before b7b26e54e37a "encoding: avoid localstr when a string can be encoded
losslessly (issue2763)", all local strings were wrapped by the localstr
class. I think this would justify the round-trip behavior of toutf8b().
ASCII strings are special-cased, so the cost of wrapping with safelocalstr
is negligible.
(with mercurial repo)
$ export HGRCPATH=/dev/null HGPLAIN= HGENCODING=latin-1
$ hg log --time --config experimental.evolution=all > /dev/null
(original)
time: real 11.340 secs (user 11.290+0.000 sys 0.060+0.000)
time: real 11.390 secs (user 11.300+0.000 sys 0.080+0.000)
time: real 11.430 secs (user 11.360+0.000 sys 0.070+0.000)
(this patch)
time: real 11.200 secs (user 11.100+0.000 sys 0.100+0.000)
time: real 11.370 secs (user 11.300+0.000 sys 0.070+0.000)
time: real 11.190 secs (user 11.130+0.000 sys 0.060+0.000)
author | Yuya Nishihara <yuya@tcha.org> |
---|---|
date | Sun, 23 Apr 2017 13:15:30 +0900 |
parents | ded48ad55146 |
children | cd196be26cb7 |
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 ( mdiff, ) 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) # Build table of removed files: {hash(fctx.data()): [fctx, ...]}. # We use hash() to discard fctx.data() from memory. hashes = {} for i, fctx in enumerate(removed): repo.ui.progress(_('searching for exact renames'), i, total=numfiles, unit=_('files')) h = hash(fctx.data()) if h not in hashes: hashes[h] = [fctx] else: hashes[h].append(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')) adata = fctx.data() h = hash(adata) for rfctx in hashes.get(h, []): # compare between actual file contents for exact identity if adata == rfctx.data(): yield (rfctx, fctx) break # Done repo.ui.progress(_('searching for exact renames'), None) def _ctxdata(fctx): # lazily load text orig = fctx.data() return orig, mdiff.splitnewlines(orig) def _score(fctx, otherdata): orig, lines = otherdata text = fctx.data() # mdiff.blocks() returns blocks of matching lines # count the number of bytes in each equal = 0 matches = mdiff.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 def score(fctx1, fctx2): return _score(fctx1, _ctxdata(fctx2)) 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')) data = None for a in added: bestscore = copies.get(a, (None, threshold))[1] if data is None: data = _ctxdata(r) myscore = _score(a, data) if myscore > bestscore: copies[a] = (r, myscore) repo.ui.progress(_('searching'), None) for dest, v in copies.iteritems(): source, bscore = v yield source, dest, bscore def _dropempty(fctxs): return [x for x in fctxs if x.size() > 0] def findrenames(repo, added, removed, threshold): '''find renamed files -- yields (before, after, score) tuples''' wctx = repo[None] pctx = wctx.p1() # 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 = _dropempty(wctx[fp] for fp in sorted(added)) removedfiles = _dropempty(pctx[fp] for fp in sorted(removed) if fp in pctx) # Find exact matches. matchedfiles = set() for (a, b) in _findexactmatches(repo, addedfiles, removedfiles): matchedfiles.add(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: addedfiles = [x for x in addedfiles if x not in matchedfiles] for (a, b, score) in _findsimilarmatches(repo, addedfiles, removedfiles, threshold): yield (a.path(), b.path(), score)