view mercurial/ignore.py @ 20182:04036798ebed

branches: avoid unnecessary changectx.branch() calls This requires reading from the changelog, which can be costly over NFS. Note that this does not totally remove reading from the changelog; we still do that when calling changectx.closesbranch(). That call will be removed in a later patch. Running hg branches on the PyPy repo (with 996) over a busy NFS server, before this change: $ time hg --profile branches > /dev/null CallCount Recursive Total(s) Inline(s) module:lineno(function) 2042 0 2.2827 2.2827 <open> 2036 0 0.9840 0.9840 <method 'close' of 'file' objects> 2036 0 0.0464 0.0464 <method 'read' of 'file' objects> 5233 0 0.1985 0.0453 mercurial.repoview:161(changelog) 10462 0 0.0791 0.0314 mercurial.changelog:133(tip) 5233 0 0.0388 0.0176 mercurial.localrepo:26(__get__) 10462 0 0.0250 0.0126 <len> 5233 0 0.0059 0.0039 mercurial.repoview:112(filterrevs) 10462 0 0.0029 0.0029 <hash> 2034 0 0.0444 0.0444 <method 'seek' of 'file' objects> 5340 0 0.0390 0.0390 mercurial.revlog:296(rev) 2582 0 0.0371 0.0371 <zlib.decompress> 3155 0 0.1963 0.0366 mercurial.context:202(__init__) 3155 0 0.1238 0.0306 mercurial.repoview:161(changelog) 3155 0 0.0261 0.0080 mercurial.changelog:183(rev) 9465 0 0.0061 0.0061 <isinstance> 1096 0 0.0023 0.0023 <binascii.unhexlify> 4251 0 0.0014 0.0014 <len> 2059 0 3.7341 0.0332 mercurial.changelog:270(read) 2059 0 3.6304 0.0307 mercurial.revlog:907(revision) 2057 0 0.0262 0.0137 mercurial.changelog:28(decodeextra) 4118 0 0.0094 0.0094 <method 'split' of 'str' objects> 4118 0 0.0270 0.0048 mercurial.encoding:61(tolocal) 2059 0 0.0040 0.0040 <method 'index' of 'str' objects> 10462 0 0.0791 0.0314 mercurial.changelog:133(tip) 10462 0 0.0289 0.0207 mercurial.changelog:190(node) 10462 0 0.0188 0.0091 <len> 52433 20932 0.0478 0.0310 <len> 20932 0 0.0221 0.0168 mercurial.revlog:262(__len__) 2059 0 3.6304 0.0307 mercurial.revlog:907(revision) real 0m4.361s user 0m0.986s sys 0m0.237s After this change: $ time hg --profile branches > /dev/null CallCount Recursive Total(s) Inline(s) module:lineno(function) 1069 0 1.1098 1.1098 <open> 1063 0 0.4865 0.4865 <method 'close' of 'file' objects> 4122 0 0.1811 0.0404 mercurial.repoview:161(changelog) 8240 0 0.0712 0.0272 mercurial.changelog:133(tip) 4122 0 0.0378 0.0177 mercurial.localrepo:26(__get__) 8240 0 0.0221 0.0115 <len> 4122 0 0.0057 0.0033 mercurial.repoview:112(filterrevs) 8240 0 0.0025 0.0025 <hash> 3029 0 0.1979 0.0371 mercurial.context:202(__init__) 3029 0 0.1278 0.0310 mercurial.repoview:161(changelog) 3029 0 0.0230 0.0081 mercurial.changelog:183(rev) 9087 0 0.0061 0.0061 <isinstance> 1096 0 0.0026 0.0026 <binascii.unhexlify> 4125 0 0.0014 0.0014 <len> 4229 0 0.0337 0.0337 mercurial.revlog:296(rev) 1061 0 0.0296 0.0296 <method 'seek' of 'file' objects> 1063 0 0.0292 0.0292 <method 'read' of 'file' objects> 8240 0 0.0712 0.0272 mercurial.changelog:133(tip) 8240 0 0.0271 0.0196 mercurial.changelog:190(node) 8240 0 0.0169 0.0083 <len> 40476 16488 0.0422 0.0271 <len> 16488 0 0.0193 0.0152 mercurial.revlog:262(__len__) 1342 0 0.0241 0.0241 <zlib.decompress> 9445 0 0.0336 0.0224 mercurial.changelog:190(node) 9445 0 0.0112 0.0112 mercurial.revlog:317(node) 1074 0 1.9102 0.0224 mercurial.changelog:270(read) 1074 0 1.8397 0.0202 mercurial.revlog:907(revision) 1073 0 0.0187 0.0099 mercurial.changelog:28(decodeextra) 2148 0 0.0061 0.0061 <method 'split' of 'str' objects> 2148 0 0.0184 0.0034 mercurial.encoding:61(tolocal) real 0m2.402s user 0m0.735s sys 0m0.177s
author Brodie Rao <brodie@sf.io>
date Fri, 15 Nov 2013 23:18:08 -0500
parents 0127366df8fe
children 8cf7f0c4cb14
line wrap: on
line source

# 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 readpats(root, files, warn):
    '''return a dict mapping ignore-file-name to list-of-patterns'''

    pats = {}
    for f in files:
        if f in pats:
            continue
        try:
            pats[f] = []
            fp = open(f)
            pats[f], warnings = ignorepats(fp)
            fp.close()
            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))
    return [(f, pats[f]) for f in files if f in pats]

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 = readpats(root, files, warn)

    allpats = []
    for f, patlist in pats:
        allpats.extend(patlist)
    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:
            try:
                match.match(root, '', [], patlist)
            except util.Abort, inst:
                raise util.Abort('%s: %s' % (f, inst[0]))

    return ignorefunc