Mercurial > hg
view mercurial/similar.py @ 48598:a6f16ec07ed7
stream-clone: add a explicit test for format change during stream clone
They are different kind of requirements, the one which impact the data storage
and are relevant to the files being streamed and the one which does not. For
example some requirements are only relevant to the working copy, like sparse, or
dirstate-v2.
Since they are irrelevant to the content being streamed, they do not prevent the
receiving side to use streaming clone and mercurial skip adverting them over
the wire and, ideally, within the bundle.
In addition, this let the client decide to use whichever format it desire for
the part that does not affect the store itself. So the configuration related to
these format are used as normal when doing a streaming clone.
In practice, the feature was not really tested and is badly broken with bundle-2,
since the requirements are not filtered out from the stream bundle.
So we start with adding simple tests as a good base before the fix and adjust
the feature.
Differential Revision: https://phab.mercurial-scm.org/D12029
author | Pierre-Yves David <pierre-yves.david@octobus.net> |
---|---|
date | Mon, 17 Jan 2022 18:51:47 +0100 |
parents | d4ba4d51f85f |
children | 6000f5b25c9b |
line wrap: on
line source
# similar.py - mechanisms for finding similar files # # Copyright 2005-2007 Olivia Mackall <olivia@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)