Mercurial > hg
view mercurial/similar.py @ 30775:513d68a90398
repair: implement requirements checking for upgrades
This commit introduces functionality for upgrading a repository in
place. The first part that's implemented is testing for upgrade
"compatibility." This is done by examining repository requirements.
There are 5 functions returning sets of requirements that control
upgrading. Why so many functions? Mainly to support extensions.
Functions are easier to monkeypatch than module variables.
Astute readers will see that we don't support "manifestv2" and
"treemanifest" requirements in the upgrade mechanism. I don't have
a great answer for why other than this is a complex set of patches
and I don't want to deal with the complexity of these experimental
features just yet. We can teach the upgrade mechanism about them
later, once the basic upgrade mechanism is in place.
This commit also introduces the "upgraderepo" function. This will be
our main routine for performing an in-place upgrade. Currently, it
just implements requirements checking. The structure of some code in
this function may look a bit weird (e.g. the inline function that is
only called once). But this will make sense after future commits.
author | Gregory Szorc <gregory.szorc@gmail.com> |
---|---|
date | Sun, 18 Dec 2016 16:16:54 -0800 |
parents | 0d83ad967bf8 |
children | ada160a8cfd8 |
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 import hashlib 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 = hashlib.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 = hashlib.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)