mercurial/ignore.py

manifestv2: add (unused) config option

With tree manifests, hashes will change anyway, so now is a good time
to also take up the old plans of a new manifest format. While there
should be little or no reason to use tree manifests with the current
manifest format (v1) once the new format (v2) is supported, we'll try
to keep the two dimensions (flat/tree and v1/v2) separate.

In preparation for adding a the new format, let's add configuration
for it and propagate that configuration to the manifest revlog
subclass. The new configuration ("experimental.manifestv2") says in
what format to write the manifest data. We may later add other
configuration to choose how to hash it, either keeping the v1 hash for
BC or hashing the v2 content.

See http://mercurial.selenic.com/wiki/ManifestV2Plan for more details.

# 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