Mercurial > hg
view mercurial/similar.py @ 37485:0b7475ea38cf
wireproto: port heads command to wire protocol v2
After much thought and consideration, wire protocol version 2's
commands will be defined in different functions from the existing
commands. This will make it easier to implement these commands
because it won't require shoehorning things like response formatting
and argument declaration into the same APIs.
For example, wire protocol version 1 requires that commands declare
a fixed and ordered list of argument names. It isn't really possible
to insert new arguments or have optional arguments without
breaking backwards compatibility. Wire protocol version 2, however,
uses CBOR maps for passing arguments. So arguments a) can be
optional b) can be added without BC c) can be strongly typed.
This commit starts our trek towards reimplementing the wire protocol
for version 2 with the heads command. It is pretty similar to the
existing heads command. One added feature is it can be told to
operate on only public phase changesets. This is useful for
making discovery faster when a repo has tens of thousands of
draft phase heads (such as Mozilla's "try" repository).
The HTTPv2 server-side protocol has had its `getargs()` implementation
updated to reflect that arguments are a map and not a list.
Differential Revision: https://phab.mercurial-scm.org/D3179
author | Gregory Szorc <gregory.szorc@gmail.com> |
---|---|
date | Wed, 28 Mar 2018 14:55:13 -0700 |
parents | ded48ad55146 |
children | cd196be26cb7 |
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. ''' numfiles = len(added) + len(removed) # Build table of removed files: {hash(fctx.data()): [fctx, ...]}. # We use hash() to discard fctx.data() from memory. hashes = {} for i, fctx in enumerate(removed): repo.ui.progress(_('searching for exact renames'), i, total=numfiles, unit=_('files')) 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 i, fctx in enumerate(added): repo.ui.progress(_('searching for exact renames'), i + len(removed), total=numfiles, unit=_('files')) 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 repo.ui.progress(_('searching for exact renames'), None) 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 = {} for i, r in enumerate(removed): repo.ui.progress(_('searching for similar files'), i, total=len(removed), unit=_('files')) 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) repo.ui.progress(_('searching'), None) 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)