view mercurial/ignore.py @ 22451:186fd06283b4

revset: lower weight for _intlist function

The histedit command uses a revset like:

(_intlist('1234\x001235')) and merge()

Previously the optimizer gave a weight of 1.5 to the _intlist side (1 for the
function, 0.5 for the string) which caused it to process the merge() side first.
This caused it to evaluate merge against every commit in the repo, which took
2.5 seconds on a large repo.

I changed the weight of _intlist to 0, since it's a trivial calculation, which
makes it process intlist first, which makes merge apply only to the revs in the
list. Which makes the revset take 0.15 seconds now. Cutting off 2.4 seconds off
our histedit performance.

>From the revset benchmark:
revset #25: (_intlist('20000\x0020001')) and merge()
0) obsolete feature not enabled but 54243 markers found!
! wall 0.036767 comb 0.040000 user 0.040000 sys 0.000000 (best of 100)
1) obsolete feature not enabled but 54243 markers found!
! wall 0.000198 comb 0.000000 user 0.000000 sys 0.000000 (best of 9084)

# ignore.py - ignored file handling for mercurial
#
# Copyright 2007 Matt Mackall <[e-mail]>
#
# 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