##// END OF EJS Templates
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes....
findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes. We speed up 'findrenames' for the usecase when a user specifies they want a similarity of 100% by matching files by their exact SHA1 hash value. This reduces the number of comparisons required to find exact matches from O(n^2) to O(n). While it would be nice if we could just use mercurial's pre-calculated SHA1 hash for existing files, this hash includes the file's ancestor information making it unsuitable for our purposes. Instead, we calculate the hash of old content from scratch. The following benchmarks were taken on the current head of crew: addremove 100% similarity: rm -rf *; hg up -C; mv tests tests.new hg --time addremove -s100 --dry-run before: real 176.350 secs (user 128.890+0.000 sys 47.430+0.000) after: real 2.130 secs (user 1.890+0.000 sys 0.240+0.000) addremove 75% similarity: rm -rf *; hg up -C; mv tests tests.new; \ for i in tests.new/*; do echo x >> $i; done hg --time addremove -s75 --dry-run before: real 264.560 secs (user 215.130+0.000 sys 49.410+0.000) after: real 218.710 secs (user 172.790+0.000 sys 45.870+0.000)

File last commit:

r10263:25e57239 stable
r11060:e6df0177 default
Show More
ignore.py
103 lines | 3.2 KiB | text/x-python | PythonLexer
# ignore.py - ignored file handling for mercurial
#
# Copyright 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 i18n import _
import util, match
import re
_commentre = None
def ignorepats(lines):
'''parse lines (iterable) of .hgignore text, returning a tuple of
(patterns, parse errors). These patterns should be given to compile()
to be validated and converted into a match function.'''
syntaxes = {'re': 'relre:', 'regexp': 'relre:', 'glob': 'relglob:'}
syntax = 'relre:'
patterns = []
warnings = []
for line in lines:
if "#" in line:
global _commentre
if not _commentre:
_commentre = re.compile(r'((^|[^\\])(\\\\)*)#.*')
# remove comments prefixed by an even number of escapes
line = _commentre.sub(r'\1', line)
# fixup properly escaped comments that survived the above
line = line.replace("\\#", "#")
line = line.rstrip()
if not line:
continue
if line.startswith('syntax:'):
s = line[7:].strip()
try:
syntax = syntaxes[s]
except KeyError:
warnings.append(_("ignoring invalid syntax '%s'") % s)
continue
pat = syntax + line
for s, rels in syntaxes.iteritems():
if line.startswith(rels):
pat = line
break
elif line.startswith(s+':'):
pat = rels + line[len(s)+1:]
break
patterns.append(pat)
return patterns, warnings
def ignore(root, files, warn):
'''return matcher covering patterns in 'files'.
the files parsed for patterns include:
.hgignore in the repository root
any additional files specified in the [ui] section of ~/.hgrc
trailing white space is dropped.
the escape character is backslash.
comments start with #.
empty lines are skipped.
lines can be of the following formats:
syntax: regexp # defaults following lines to non-rooted regexps
syntax: glob # defaults following lines to non-rooted globs
re:pattern # non-rooted regular expression
glob:pattern # non-rooted glob
pattern # pattern of the current default type'''
pats = {}
for f in files:
try:
pats[f] = []
fp = open(f)
pats[f], warnings = ignorepats(fp)
for warning in warnings:
warn("%s: %s\n" % (f, warning))
except IOError, inst:
if f != files[0]:
warn(_("skipping unreadable ignore file '%s': %s\n") %
(f, inst.strerror))
allpats = []
[allpats.extend(patlist) for patlist in pats.values()]
if not allpats:
return util.never
try:
ignorefunc = match.match(root, '', [], allpats)
except util.Abort:
# Re-raise an exception where the src is the right file
for f, patlist in pats.iteritems():
try:
match.match(root, '', [], patlist)
except util.Abort, inst:
raise util.Abort('%s: %s' % (f, inst[0]))
return ignorefunc