Mercurial > hg
view mercurial/similar.py @ 39662:50f46b771921
py3: partially fix pager spawning on Windows
Previously, spinning up the pager crashed because the command and environment
was in bytes. (See also 543a788eea2d.) Now it aborts with an invalid handle:
$ HGMODULEPOLICY=py py -3 ../hg --traceback --config extensions.evolve=!
Traceback (most recent call last):
File "c:\Users\Matt\projects\hg\mercurial\ui.py", line 967, in _write
self.fout.write(''.join(msgs))
File "c:\Users\Matt\projects\hg\mercurial\windows.py", line 173, in write
self.fp.write(s[start:end])
OSError: [WinError 6] The handle is invalid
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "c:\Users\Matt\projects\hg\mercurial\scmutil.py", line 164, in callcatch
return func()
File "c:\Users\Matt\projects\hg\mercurial\dispatch.py", line 350, in _runcatchfunc
return _dispatch(req)
File "c:\Users\Matt\projects\hg\mercurial\dispatch.py", line 930, in _dispatch
return commands.help_(ui, 'shortlist')
File "c:\Users\Matt\projects\hg\mercurial\commands.py", line 2930, in help_
ui.write(formatted)
File "c:\Users\Matt\projects\hg\mercurial\ui.py", line 948, in write
self._writenobuf(*args, **opts)
File "c:\Users\Matt\projects\hg\mercurial\ui.py", line 960, in _writenobuf
self._write(*msgs, **opts)
File "c:\Users\Matt\projects\hg\mercurial\ui.py", line 969, in _write
raise error.StdioError(err)
mercurial.error.StdioError: [Errno 9] The handle is invalid
abort: The handle is invalid
The interesting bit here is that the abort message is marked with ANSI color,
but the OSError is not.
author | Matt Harbison <matt_harbison@yahoo.com> |
---|---|
date | Sat, 15 Sep 2018 13:31:41 -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)