Mercurial > hg
view mercurial/similar.py @ 39270:37e56607cbb9
lfs: add a progress bar when searching for blobs to upload
The search itself can take an extreme amount of time if there are a lot of
revisions involved. I've got a local repo that took 6 minutes to push 1850
commits, and 60% of that time was spent here (there are ~70K files):
\ 58.1% wrapper.py: extractpointers line 297: pointers = extractpointers(...
| 57.7% wrapper.py: pointersfromctx line 352: for p in pointersfromctx(ct...
| 57.4% wrapper.py: pointerfromctx line 397: p = pointerfromctx(ctx, f, ...
\ 38.7% context.py: __contains__ line 368: if f not in ctx:
| 38.7% util.py: __get__ line 82: return key in self._manifest
| 38.7% context.py: _manifest line 1416: result = self.func(obj)
| 38.7% manifest.py: read line 472: return self._manifestctx.re...
\ 25.6% revlog.py: revision line 1562: text = rl.revision(self._node)
\ 12.8% revlog.py: _chunks line 2217: bins = self._chunks(chain, ...
| 12.0% revlog.py: decompressline 2112: ladd(decomp(buffer(data, ch...
\ 7.8% revlog.py: checkhash line 2232: self.checkhash(text, node, ...
| 7.8% revlog.py: hash line 2315: if node != self.hash(text, ...
| 7.8% revlog.py: hash line 2242: return hash(text, p1, p2)
\ 12.0% manifest.py: __init__ line 1565: self._data = manifestdict(t...
\ 16.8% context.py: filenode line 378: if not _islfs(fctx.filelog(...
| 15.7% util.py: __get__ line 706: return self._filelog
| 14.8% context.py: _filelog line 1416: result = self.func(obj)
| 14.8% localrepo.py: file line 629: return self._repo.file(self...
| 14.8% filelog.py: __init__ line 1134: return filelog.filelog(self...
| 14.5% revlog.py: __init__ line 24: censorable=True)
author | Matt Harbison <matt_harbison@yahoo.com> |
---|---|
date | Fri, 24 Aug 2018 17:45:46 -0400 |
parents | 59c9d3cc810f |
children | 2372284d9457 |
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. ''' # Build table of removed files: {hash(fctx.data()): [fctx, ...]}. # We use hash() to discard fctx.data() from memory. hashes = {} progress = repo.ui.makeprogress(_('searching for exact renames'), total=(len(added) + len(removed)), unit=_('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(_('searching for similar files'), unit=_('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 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)