view mercurial/ignore.py @ 25166:7f53f305d4a6

ignore: rename readignorefile to readpatternfile A future commit will move the readignorefile logic into match.py so it can be used from general match rules. Let's rename the function to represent this new behavior.
author Durham Goode <durham@fb.com>
date Sat, 16 May 2015 15:45:46 -0700
parents 581e2066d802
children 6f7048cc2419
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 readpatternfile(filepath, warn):
    '''parse a pattern file, returning a list of
    patterns. 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 = []

    fp = open(filepath)
    for line in fp:
        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:
                warn(_("%s: ignoring invalid syntax '%s'\n") % (filepath, s))
            continue

        linesyntax = syntax
        for s, rels in syntaxes.iteritems():
            if line.startswith(rels):
                linesyntax = rels
                line = line[len(rels):]
                break
            elif line.startswith(s+':'):
                linesyntax = rels
                line = line[len(s) + 1:]
                break
        patterns.append(linesyntax + line)

    fp.close()
    return patterns

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] = readpatternfile(f, warn)
        except IOError, inst:
            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