Mercurial > hg
view mercurial/similar.py @ 28240:1ac8ce137377
changegroup: fix treemanifests on merges
The current code for generating treemanifest revisions takes the list
of files in the changeset and finds the directories from them. This
does not work for merges, since a merge may pick file A from one side
and file B from another and neither of them would appear in the
changeset's "files" list, but the manifest would still change.
Fix this by instead walking the root manifest log for all needed
revisions, storing all needed file and subdirectory revisions, then
recursively visiting the subdirectories. This also turns out to be
faster: cloning a version of hg core converted to treemanifests went
from ~28s to ~19s (timing somewhat unfair: before this patch, timed
until crash; after this patch, timed until manifests complete).
The new algorithm is used only on treemanifest repos. Although it
works equally well on flat manifests, we leave the iteration over
files in the changeset for flat manifests for now.
author | Martin von Zweigbergk <martinvonz@google.com> |
---|---|
date | Fri, 12 Feb 2016 23:09:09 -0800 |
parents | a56c47ed3885 |
children | 0d6b3630b9a3 |
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) 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) 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)) # 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)