comparison mercurial/match.py @ 41282:4fab8a7d2d72

match: support rooted globs in hgignore

In a .hgignore, "glob:foo" always means "**/foo". This cannot be
avoided because there is no syntax like "^" in regexes to say you
don't want the implied "**/" (of course one can use regexes, but glob
syntax is nice).

When you have a long list of fairly specific globs like
path/to/some/thing, this has two consequences:
1. unintended files may be ignored (not too common though)
2. matching performance can suffer significantly
  Here is vanilla hg status timing on a private repository:

  Using syntax:glob everywhere
  real	0m2.199s
  user	0m1.545s
  sys	0m0.619s

  When rooting the appropriate globs
  real	0m1.434s
  user	0m0.847s
  sys	0m0.565s

  (tangentially, none of this shows up in --profile's output. It
   seems that C code doesn't play well with profiling)

The code already supports this but there is no syntax to make use of
it, so it seems reasonable to create such syntax. I create a new
hgignore syntax "rootglob".

Differential Revision: https://phab.mercurial-scm.org/D5493

41281:183df3df6031

from .utils import (
    stringutil,
)

allpatternkinds = ('re', 'glob', 'path', 'relglob', 'relpath', 'relre',
                   'listfile', 'listfile0', 'set', 'include', 'subinclude',
                   'rootfilesin')
cwdrelativepatternkinds = ('relpath', 'glob')

propertycache = util.propertycache

    normalized and rooted patterns and with listfiles expanded.'''
    kindpats = []
    for kind, pat in [_patsplit(p, default) for p in patterns]:
        if kind in cwdrelativepatternkinds:
            pat = pathutil.canonpath(root, cwd, pat, auditor)
        elif kind in ('relglob', 'path', 'rootfilesin'):
            pat = util.normpath(pat)
        elif kind in ('listfile', 'listfile0'):
            try:
                files = util.readfile(pat)
                if kind == 'listfile0':

        return '(?:|.*/)' + _globre(pat) + globsuffix
    if kind == 'relre':
        if pat.startswith('^'):
            return pat
        return '.*' + pat
    if kind == 'glob':
        return _globre(pat) + globsuffix
    raise error.ProgrammingError('not a regex pattern: %s:%s' % (kind, pat))

def _buildmatch(kindpats, globsuffix, listsubrepos, root):
    '''Return regexp string and a matcher function for kindpats.

    directories.
    '''
    r = []
    d = []
    for kind, pat, source in kindpats:
        if kind == 'glob': # find the non-glob prefix
            root = []
            for p in pat.split('/'):
                if '[' in p or '{' in p or '*' in p or '?' in p:
                    break
                root.append(p)

    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

    if sourceinfo is set, returns a list of tuples:
    (pattern, lineno, originalline). This is useful to debug ignore patterns.
    '''

    syntaxes = {
        're': 'relre:',
        'regexp': 'relre:',
        'glob': 'relglob:',
        'include': 'include',
        'subinclude': 'subinclude',
    }
    syntax = 'relre:'
    patterns = []

41282:4fab8a7d2d72

from .utils import (
    stringutil,
)

allpatternkinds = ('re', 'glob', 'path', 'relglob', 'relpath', 'relre',
                   'rootglob',
                   'listfile', 'listfile0', 'set', 'include', 'subinclude',
                   'rootfilesin')
cwdrelativepatternkinds = ('relpath', 'glob')

propertycache = util.propertycache

    normalized and rooted patterns and with listfiles expanded.'''
    kindpats = []
    for kind, pat in [_patsplit(p, default) for p in patterns]:
        if kind in cwdrelativepatternkinds:
            pat = pathutil.canonpath(root, cwd, pat, auditor)
        elif kind in ('relglob', 'path', 'rootfilesin', 'rootglob'):
            pat = util.normpath(pat)
        elif kind in ('listfile', 'listfile0'):
            try:
                files = util.readfile(pat)
                if kind == 'listfile0':

        return '(?:|.*/)' + _globre(pat) + globsuffix
    if kind == 'relre':
        if pat.startswith('^'):
            return pat
        return '.*' + pat
    if kind in ('glob', 'rootglob'):
        return _globre(pat) + globsuffix
    raise error.ProgrammingError('not a regex pattern: %s:%s' % (kind, pat))

def _buildmatch(kindpats, globsuffix, listsubrepos, root):
    '''Return regexp string and a matcher function for kindpats.

    directories.
    '''
    r = []
    d = []
    for kind, pat, source in kindpats:
        if kind in ('glob', 'rootglob'): # find the non-glob prefix
            root = []
            for p in pat.split('/'):
                if '[' in p or '{' in p or '*' in p or '?' in p:
                    break
                root.append(p)

    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
    rootglob:pat   # rooted glob (same root as ^ in regexps)
    pattern        # pattern of the current default type

    if sourceinfo is set, returns a list of tuples:
    (pattern, lineno, originalline). This is useful to debug ignore patterns.
    '''

    syntaxes = {
        're': 'relre:',
        'regexp': 'relre:',
        'glob': 'relglob:',
        'rootglob': 'rootglob:',
        'include': 'include',
        'subinclude': 'subinclude',
    }
    syntax = 'relre:'
    patterns = []