view mercurial/ignore.py @ 9820:0b999aec64e8

bundle: don't send too many changesets (Issue1704)

The fast path in changegroupsubset can send too many csets. This happens
because it uses the parents of all bases as common nodes and then goes
forward from this again. If a base has a parent that has another child,
which is -not- a base, then this other child will nevertheless end up in
the changegroup.

The fix is to not use findmissing(), but use nodesbetween() instead, as
do the slow path and incoming/outgoing.

The change to test-notify.out is correct, because it actually hits this
bug, as can be seen by glog'ing the two repos:

@    22c88
|\
| o  0a184
| |
o |  0647d
|/
o  cb9a9

and

o  0647d
|
@  cb9a9

It used to pull 0647d again, which is unnecessary.

# 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, incorporated herein by reference.

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