Mercurial > hg
view mercurial/similar.py @ 46400:7525e77b5eac
convert: option to set date and time for svn commits
Converting to subversion repository is not preserving original commit dates as
it may break some subversion functionality if commit dates are not monotonically
increasing.
This patch adds `convert.svn.dangerous-set-commit-dates` configuration option
to change this behaviour and enable commit dates convertion for those who want
to take risks.
Subversion always uses commit dates with UTC timezone, so only timestamps
are used.
Test `test-convert-svn-sink.t` uses `svnxml.py` script to dump history of svn
repositories. Atm the script is not printing `date` field from svn log. This
patch changes this to allow checks on correctness of date and time convertion.
Documentation is updated. Additional test case is added to test commit dates
convertion.
Differential Revision: https://phab.mercurial-scm.org/D9721
author | Nikita Slyusarev <nslus@yandex-team.com> |
---|---|
date | Tue, 12 Jan 2021 00:11:16 +0300 |
parents | 89a2afe31e82 |
children | d4ba4d51f85f |
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, pycompat, ) 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. """ # Build table of removed files: {hash(fctx.data()): [fctx, ...]}. # We use hash() to discard fctx.data() from memory. hashes = {} progress = repo.ui.makeprogress( _(b'searching for exact renames'), total=(len(added) + len(removed)), unit=_(b'files'), ) for fctx in removed: progress.increment() 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 fctx in added: progress.increment() 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 progress.complete() 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 = {} progress = repo.ui.makeprogress( _(b'searching for similar files'), unit=_(b'files'), total=len(removed) ) for r in removed: progress.increment() 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) progress.complete() for dest, v in pycompat.iteritems(copies): 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)