Mercurial > hg
view mercurial/similar.py @ 32383:f928d53b687c stable
dispatch: setup color before pager for correct console information on windows
Before this patch, "hg CMD --pager on" on Windows shows output
unintentionally decorated with ANSI color escape sequences, if color
mode is "auto". This issue occurs in steps below.
1. dispatch() invokes ui.pager() at detection of "--pager on"
2. stdout of hg process is redirected into stdin of pager process
3. "ui.formatted" = True, because isatty(stdout) is so before (2)
4. color module is loaded for colorization
5. color.w32effects = None, because GetConsoleScreenBufferInfo()
fails on stdout redirected at (2)
6. "ansi" color mode is chosen, because of "not w32effects"
7. output is colorized in "ansi" mode because of "ui.formatted" = True
Even if "ansi" color mode is chosen, ordinarily redirected stdout
makes ui.formatted() return False, and colorization is avoided. But in
this issue case, "ui.formatted" = True at (3) forces output to be
colorized.
For correct console information on win32, it is needed to ensure that
color module is loaded before redirection of stdout for pagination.
BTW, if any of enabled extensions has "colortable" attribute, this
issue is avoided even before this patch, because color module is
imported as a part of loading such extension, and extension loading
occurs before setting up pager. For example, mq and keyword have
"colortable".
author | FUJIWARA Katsunori <foozy@lares.dti.ne.jp> |
---|---|
date | Tue, 23 May 2017 03:29:23 +0900 |
parents | 985a98c6bad0 |
children | ded48ad55146 |
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 ( bdiff, 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() # 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 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)