match: simplify the regexps created for glob patterns

For legibility of the resulting regexes, although it may help with
performance as well.

Differential Revision: https://phab.mercurial-scm.org/D6764

mercurial/match.py

@@ -1,1526 +1,1531
 # match.py - filename matching
 #
 #  Copyright 2008, 2009 Matt Mackall <[e-mail]> and others
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import, print_function
 
 import copy
 import itertools
 import os
 import re
 
 from .i18n import _
 from . import (
     encoding,
     error,
     pathutil,
     policy,
     pycompat,
     util,
 )
 from .utils import (
     stringutil,
 )
 
 rustmod = policy.importrust(r'filepatterns')
 
 allpatternkinds = ('re', 'glob', 'path', 'relglob', 'relpath', 'relre',
                    'rootglob',
                    'listfile', 'listfile0', 'set', 'include', 'subinclude',
                    'rootfilesin')
 cwdrelativepatternkinds = ('relpath', 'glob')
 
 propertycache = util.propertycache
 
 def _rematcher(regex):
     '''compile the regexp with the best available regexp engine and return a
     matcher function'''
     m = util.re.compile(regex)
     try:
         # slightly faster, provided by facebook's re2 bindings
         return m.test_match
     except AttributeError:
         return m.match
 
 def _expandsets(kindpats, ctx=None, listsubrepos=False, badfn=None):
     '''Returns the kindpats list with the 'set' patterns expanded to matchers'''
     matchers = []
     other = []
 
     for kind, pat, source in kindpats:
         if kind == 'set':
             if ctx is None:
                 raise error.ProgrammingError("fileset expression with no "
                                              "context")
             matchers.append(ctx.matchfileset(pat, badfn=badfn))
 
             if listsubrepos:
                 for subpath in ctx.substate:
                     sm = ctx.sub(subpath).matchfileset(pat, badfn=badfn)
                     pm = prefixdirmatcher(subpath, sm, badfn=badfn)
                     matchers.append(pm)
 
             continue
         other.append((kind, pat, source))
     return matchers, other
 
 def _expandsubinclude(kindpats, root):
     '''Returns the list of subinclude matcher args and the kindpats without the
     subincludes in it.'''
     relmatchers = []
     other = []
 
     for kind, pat, source in kindpats:
         if kind == 'subinclude':
             sourceroot = pathutil.dirname(util.normpath(source))
             pat = util.pconvert(pat)
             path = pathutil.join(sourceroot, pat)
 
             newroot = pathutil.dirname(path)
             matcherargs = (newroot, '', [], ['include:%s' % path])
 
             prefix = pathutil.canonpath(root, root, newroot)
             if prefix:
                 prefix += '/'
             relmatchers.append((prefix, matcherargs))
         else:
             other.append((kind, pat, source))
 
     return relmatchers, other
 
 def _kindpatsalwaysmatch(kindpats):
     """"Checks whether the kindspats match everything, as e.g.
     'relpath:.' does.
     """
     for kind, pat, source in kindpats:
         if pat != '' or kind not in ['relpath', 'glob']:
             return False
     return True
 
 def _buildkindpatsmatcher(matchercls, root, kindpats, ctx=None,
                           listsubrepos=False, badfn=None):
     matchers = []
     fms, kindpats = _expandsets(kindpats, ctx=ctx,
                                 listsubrepos=listsubrepos, badfn=badfn)
     if kindpats:
         m = matchercls(root, kindpats, badfn=badfn)
         matchers.append(m)
     if fms:
         matchers.extend(fms)
     if not matchers:
         return nevermatcher(badfn=badfn)
     if len(matchers) == 1:
         return matchers[0]
     return unionmatcher(matchers)
 
 def match(root, cwd, patterns=None, include=None, exclude=None, default='glob',
           auditor=None, ctx=None, listsubrepos=False, warn=None,
           badfn=None, icasefs=False):
     r"""build an object to match a set of file patterns
 
     arguments:
     root - the canonical root of the tree you're matching against
     cwd - the current working directory, if relevant
     patterns - patterns to find
     include - patterns to include (unless they are excluded)
     exclude - patterns to exclude (even if they are included)
     default - if a pattern in patterns has no explicit type, assume this one
     auditor - optional path auditor
     ctx - optional changecontext
     listsubrepos - if True, recurse into subrepositories
     warn - optional function used for printing warnings
     badfn - optional bad() callback for this matcher instead of the default
     icasefs - make a matcher for wdir on case insensitive filesystems, which
         normalizes the given patterns to the case in the filesystem
 
     a pattern is one of:
     'glob:<glob>' - a glob relative to cwd
     're:<regexp>' - a regular expression
     'path:<path>' - a path relative to repository root, which is matched
                     recursively
     'rootfilesin:<path>' - a path relative to repository root, which is
                     matched non-recursively (will not match subdirectories)
     'relglob:<glob>' - an unrooted glob (*.c matches C files in all dirs)
     'relpath:<path>' - a path relative to cwd
     'relre:<regexp>' - a regexp that needn't match the start of a name
     'set:<fileset>' - a fileset expression
     'include:<path>' - a file of patterns to read and include
     'subinclude:<path>' - a file of patterns to match against files under
                           the same directory
     '<something>' - a pattern of the specified default type
 
     Usually a patternmatcher is returned:
     >>> match(b'foo', b'.', [b're:.*\.c$', b'path:foo/a', b'*.py'])
     <patternmatcher patterns='.*\\.c$|foo/a(?:/|$)|[^/]*\\.py$'>
 
     Combining 'patterns' with 'include' (resp. 'exclude') gives an
     intersectionmatcher (resp. a differencematcher):
     >>> type(match(b'foo', b'.', [b're:.*\.c$'], include=[b'path:lib']))
     <class 'mercurial.match.intersectionmatcher'>
     >>> type(match(b'foo', b'.', [b're:.*\.c$'], exclude=[b'path:build']))
     <class 'mercurial.match.differencematcher'>
 
     Notice that, if 'patterns' is empty, an alwaysmatcher is returned:
     >>> match(b'foo', b'.', [])
     <alwaysmatcher>
 
     The 'default' argument determines which kind of pattern is assumed if a
     pattern has no prefix:
     >>> match(b'foo', b'.', [b'.*\.c$'], default=b're')
     <patternmatcher patterns='.*\\.c$'>
     >>> match(b'foo', b'.', [b'main.py'], default=b'relpath')
     <patternmatcher patterns='main\\.py(?:/|$)'>
     >>> match(b'foo', b'.', [b'main.py'], default=b're')
     <patternmatcher patterns='main.py'>
 
     The primary use of matchers is to check whether a value (usually a file
     name) matches againset one of the patterns given at initialization. There
     are two ways of doing this check.
 
     >>> m = match(b'foo', b'', [b're:.*\.c$', b'relpath:a'])
 
     1. Calling the matcher with a file name returns True if any pattern
     matches that file name:
     >>> m(b'a')
     True
     >>> m(b'main.c')
     True
     >>> m(b'test.py')
     False
 
     2. Using the exact() method only returns True if the file name matches one
     of the exact patterns (i.e. not re: or glob: patterns):
     >>> m.exact(b'a')
     True
     >>> m.exact(b'main.c')
     False
     """
     normalize = _donormalize
     if icasefs:
         dirstate = ctx.repo().dirstate
         dsnormalize = dirstate.normalize
 
         def normalize(patterns, default, root, cwd, auditor, warn):
             kp = _donormalize(patterns, default, root, cwd, auditor, warn)
             kindpats = []
             for kind, pats, source in kp:
                 if kind not in ('re', 'relre'):  # regex can't be normalized
                     p = pats
                     pats = dsnormalize(pats)
 
                     # Preserve the original to handle a case only rename.
                     if p != pats and p in dirstate:
                         kindpats.append((kind, p, source))
 
                 kindpats.append((kind, pats, source))
             return kindpats
 
     if patterns:
         kindpats = normalize(patterns, default, root, cwd, auditor, warn)
         if _kindpatsalwaysmatch(kindpats):
             m = alwaysmatcher(badfn)
         else:
             m = _buildkindpatsmatcher(patternmatcher, root, kindpats, ctx=ctx,
                                       listsubrepos=listsubrepos, badfn=badfn)
     else:
         # It's a little strange that no patterns means to match everything.
         # Consider changing this to match nothing (probably using nevermatcher).
         m = alwaysmatcher(badfn)
 
     if include:
         kindpats = normalize(include, 'glob', root, cwd, auditor, warn)
         im = _buildkindpatsmatcher(includematcher, root, kindpats, ctx=ctx,
                                    listsubrepos=listsubrepos, badfn=None)
         m = intersectmatchers(m, im)
     if exclude:
         kindpats = normalize(exclude, 'glob', root, cwd, auditor, warn)
         em = _buildkindpatsmatcher(includematcher, root, kindpats, ctx=ctx,
                                    listsubrepos=listsubrepos, badfn=None)
         m = differencematcher(m, em)
     return m
 
 def exact(files, badfn=None):
     return exactmatcher(files, badfn=badfn)
 
 def always(badfn=None):
     return alwaysmatcher(badfn)
 
 def never(badfn=None):
     return nevermatcher(badfn)
 
 def badmatch(match, badfn):
     """Make a copy of the given matcher, replacing its bad method with the given
     one.
     """
     m = copy.copy(match)
     m.bad = badfn
     return m
 
 def _donormalize(patterns, default, root, cwd, auditor=None, warn=None):
     '''Convert 'kind:pat' from the patterns list to tuples with kind and
     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=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':
                     files = files.split('\0')
                 else:
                     files = files.splitlines()
                 files = [f for f in files if f]
             except EnvironmentError:
                 raise error.Abort(_("unable to read file list (%s)") % pat)
             for k, p, source in _donormalize(files, default, root, cwd,
                                              auditor, warn):
                 kindpats.append((k, p, pat))
             continue
         elif kind == 'include':
             try:
                 fullpath = os.path.join(root, util.localpath(pat))
                 includepats = readpatternfile(fullpath, warn)
                 for k, p, source in _donormalize(includepats, default,
                                                  root, cwd, auditor, warn):
                     kindpats.append((k, p, source or pat))
             except error.Abort as inst:
                 raise error.Abort('%s: %s' % (pat, inst[0]))
             except IOError as inst:
                 if warn:
                     warn(_("skipping unreadable pattern file '%s': %s\n") %
                          (pat, stringutil.forcebytestr(inst.strerror)))
             continue
         # else: re or relre - which cannot be normalized
         kindpats.append((kind, pat, ''))
     return kindpats
 
 class basematcher(object):
 
     def __init__(self, badfn=None):
         if badfn is not None:
             self.bad = badfn
 
     def __call__(self, fn):
         return self.matchfn(fn)
     # Callbacks related to how the matcher is used by dirstate.walk.
     # Subscribers to these events must monkeypatch the matcher object.
     def bad(self, f, msg):
         '''Callback from dirstate.walk for each explicit file that can't be
         found/accessed, with an error message.'''
 
     # If an explicitdir is set, it will be called when an explicitly listed
     # directory is visited.
     explicitdir = None
 
     # If an traversedir is set, it will be called when a directory discovered
     # by recursive traversal is visited.
     traversedir = None
 
     @propertycache
     def _files(self):
         return []
 
     def files(self):
         '''Explicitly listed files or patterns or roots:
         if no patterns or .always(): empty list,
         if exact: list exact files,
         if not .anypats(): list all files and dirs,
         else: optimal roots'''
         return self._files
 
     @propertycache
     def _fileset(self):
         return set(self._files)
 
     def exact(self, f):
         '''Returns True if f is in .files().'''
         return f in self._fileset
 
     def matchfn(self, f):
         return False
 
     def visitdir(self, dir):
         '''Decides whether a directory should be visited based on whether it
         has potential matches in it or one of its subdirectories. This is
         based on the match's primary, included, and excluded patterns.
 
         Returns the string 'all' if the given directory and all subdirectories
         should be visited. Otherwise returns True or False indicating whether
         the given directory should be visited.
         '''
         return True
 
     def visitchildrenset(self, dir):
         '''Decides whether a directory should be visited based on whether it
         has potential matches in it or one of its subdirectories, and
         potentially lists which subdirectories of that directory should be
         visited. This is based on the match's primary, included, and excluded
         patterns.
 
         This function is very similar to 'visitdir', and the following mapping
         can be applied:
 
              visitdir | visitchildrenlist
             ----------+-------------------
              False    | set()
              'all'    | 'all'
              True     | 'this' OR non-empty set of subdirs -or files- to visit
 
         Example:
           Assume matchers ['path:foo/bar', 'rootfilesin:qux'], we would return
           the following values (assuming the implementation of visitchildrenset
           is capable of recognizing this; some implementations are not).
 
           '' -> {'foo', 'qux'}
           'baz' -> set()
           'foo' -> {'bar'}
           # Ideally this would be 'all', but since the prefix nature of matchers
           # is applied to the entire matcher, we have to downgrade this to
           # 'this' due to the non-prefix 'rootfilesin'-kind matcher being mixed
           # in.
           'foo/bar' -> 'this'
           'qux' -> 'this'
 
         Important:
           Most matchers do not know if they're representing files or
           directories. They see ['path:dir/f'] and don't know whether 'f' is a
           file or a directory, so visitchildrenset('dir') for most matchers will
           return {'f'}, but if the matcher knows it's a file (like exactmatcher
           does), it may return 'this'. Do not rely on the return being a set
           indicating that there are no files in this dir to investigate (or
           equivalently that if there are files to investigate in 'dir' that it
           will always return 'this').
         '''
         return 'this'
 
     def always(self):
         '''Matcher will match everything and .files() will be empty --
         optimization might be possible.'''
         return False
 
     def isexact(self):
         '''Matcher will match exactly the list of files in .files() --
         optimization might be possible.'''
         return False
 
     def prefix(self):
         '''Matcher will match the paths in .files() recursively --
         optimization might be possible.'''
         return False
 
     def anypats(self):
         '''None of .always(), .isexact(), and .prefix() is true --
         optimizations will be difficult.'''
         return not self.always() and not self.isexact() and not self.prefix()
 
 class alwaysmatcher(basematcher):
     '''Matches everything.'''
 
     def __init__(self, badfn=None):
         super(alwaysmatcher, self).__init__(badfn)
 
     def always(self):
         return True
 
     def matchfn(self, f):
         return True
 
     def visitdir(self, dir):
         return 'all'
 
     def visitchildrenset(self, dir):
         return 'all'
 
     def __repr__(self):
         return r'<alwaysmatcher>'
 
 class nevermatcher(basematcher):
     '''Matches nothing.'''
 
     def __init__(self, badfn=None):
         super(nevermatcher, self).__init__(badfn)
 
     # It's a little weird to say that the nevermatcher is an exact matcher
     # or a prefix matcher, but it seems to make sense to let callers take
     # fast paths based on either. There will be no exact matches, nor any
     # prefixes (files() returns []), so fast paths iterating over them should
     # be efficient (and correct).
     def isexact(self):
         return True
 
     def prefix(self):
         return True
 
     def visitdir(self, dir):
         return False
 
     def visitchildrenset(self, dir):
         return set()
 
     def __repr__(self):
         return r'<nevermatcher>'
 
 class predicatematcher(basematcher):
     """A matcher adapter for a simple boolean function"""
 
     def __init__(self, predfn, predrepr=None, badfn=None):
         super(predicatematcher, self).__init__(badfn)
         self.matchfn = predfn
         self._predrepr = predrepr
 
     @encoding.strmethod
     def __repr__(self):
         s = (stringutil.buildrepr(self._predrepr)
              or pycompat.byterepr(self.matchfn))
         return '<predicatenmatcher pred=%s>' % s
 
 def normalizerootdir(dir, funcname):
     if dir == '.':
         util.nouideprecwarn("match.%s() no longer accepts "
                             "'.', use '' instead." % funcname, '5.1')
         return ''
     return dir
 
 
 class patternmatcher(basematcher):
     """Matches a set of (kind, pat, source) against a 'root' directory.
 
     >>> kindpats = [
     ...     (b're', br'.*\.c$', b''),
     ...     (b'path', b'foo/a', b''),
     ...     (b'relpath', b'b', b''),
     ...     (b'glob', b'*.h', b''),
     ... ]
     >>> m = patternmatcher(b'foo', kindpats)
     >>> m(b'main.c')  # matches re:.*\.c$
     True
     >>> m(b'b.txt')
     False
     >>> m(b'foo/a')  # matches path:foo/a
     True
     >>> m(b'a')  # does not match path:b, since 'root' is 'foo'
     False
     >>> m(b'b')  # matches relpath:b, since 'root' is 'foo'
     True
     >>> m(b'lib.h')  # matches glob:*.h
     True
 
     >>> m.files()
     ['', 'foo/a', 'b', '']
     >>> m.exact(b'foo/a')
     True
     >>> m.exact(b'b')
     True
     >>> m.exact(b'lib.h')  # exact matches are for (rel)path kinds
     False
     """
 
     def __init__(self, root, kindpats, badfn=None):
         super(patternmatcher, self).__init__(badfn)
 
         self._files = _explicitfiles(kindpats)
         self._prefix = _prefix(kindpats)
         self._pats, self.matchfn = _buildmatch(kindpats, '$', root)
 
     @propertycache
     def _dirs(self):
         return set(util.dirs(self._fileset))
 
     def visitdir(self, dir):
         dir = normalizerootdir(dir, 'visitdir')
         if self._prefix and dir in self._fileset:
             return 'all'
         return (dir in self._fileset or
                 dir in self._dirs or
                 any(parentdir in self._fileset
                     for parentdir in util.finddirs(dir)))
 
     def visitchildrenset(self, dir):
         ret = self.visitdir(dir)
         if ret is True:
             return 'this'
         elif not ret:
             return set()
         assert ret == 'all'
         return 'all'
 
     def prefix(self):
         return self._prefix
 
     @encoding.strmethod
     def __repr__(self):
         return ('<patternmatcher patterns=%r>' % pycompat.bytestr(self._pats))
 
 # This is basically a reimplementation of util.dirs that stores the children
 # instead of just a count of them, plus a small optional optimization to avoid
 # some directories we don't need.
 class _dirchildren(object):
     def __init__(self, paths, onlyinclude=None):
         self._dirs = {}
         self._onlyinclude = onlyinclude or []
         addpath = self.addpath
         for f in paths:
             addpath(f)
 
     def addpath(self, path):
         if path == '':
             return
         dirs = self._dirs
         findsplitdirs = _dirchildren._findsplitdirs
         for d, b in findsplitdirs(path):
             if d not in self._onlyinclude:
                 continue
             dirs.setdefault(d, set()).add(b)
 
     @staticmethod
     def _findsplitdirs(path):
         # yields (dirname, basename) tuples, walking back to the root.  This is
         # very similar to util.finddirs, except:
         #  - produces a (dirname, basename) tuple, not just 'dirname'
         # Unlike manifest._splittopdir, this does not suffix `dirname` with a
         # slash.
         oldpos = len(path)
         pos = path.rfind('/')
         while pos != -1:
             yield path[:pos], path[pos + 1:oldpos]
             oldpos = pos
             pos = path.rfind('/', 0, pos)
         yield '', path[:oldpos]
 
     def get(self, path):
         return self._dirs.get(path, set())
 
 class includematcher(basematcher):
 
     def __init__(self, root, kindpats, badfn=None):
         super(includematcher, self).__init__(badfn)
 
         self._pats, self.matchfn = _buildmatch(kindpats, '(?:/|$)', root)
         self._prefix = _prefix(kindpats)
         roots, dirs, parents = _rootsdirsandparents(kindpats)
         # roots are directories which are recursively included.
         self._roots = set(roots)
         # dirs are directories which are non-recursively included.
         self._dirs = set(dirs)
         # parents are directories which are non-recursively included because
         # they are needed to get to items in _dirs or _roots.
         self._parents = parents
 
     def visitdir(self, dir):
         dir = normalizerootdir(dir, 'visitdir')
         if self._prefix and dir in self._roots:
             return 'all'
         return (dir in self._roots or
                 dir in self._dirs or
                 dir in self._parents or
                 any(parentdir in self._roots
                     for parentdir in util.finddirs(dir)))
 
     @propertycache
     def _allparentschildren(self):
         # It may seem odd that we add dirs, roots, and parents, and then
         # restrict to only parents. This is to catch the case of:
         #   dirs = ['foo/bar']
         #   parents = ['foo']
         # if we asked for the children of 'foo', but had only added
         # self._parents, we wouldn't be able to respond ['bar'].
         return _dirchildren(
                 itertools.chain(self._dirs, self._roots, self._parents),
                 onlyinclude=self._parents)
 
     def visitchildrenset(self, dir):
         if self._prefix and dir in self._roots:
             return 'all'
         # Note: this does *not* include the 'dir in self._parents' case from
         # visitdir, that's handled below.
         if ('' in self._roots or
             dir in self._roots or
             dir in self._dirs or
             any(parentdir in self._roots
                 for parentdir in util.finddirs(dir))):
             return 'this'
 
         if dir in self._parents:
             return self._allparentschildren.get(dir) or set()
         return set()
 
     @encoding.strmethod
     def __repr__(self):
         return ('<includematcher includes=%r>' % pycompat.bytestr(self._pats))
 
 class exactmatcher(basematcher):
     r'''Matches the input files exactly. They are interpreted as paths, not
     patterns (so no kind-prefixes).
 
     >>> m = exactmatcher([b'a.txt', br're:.*\.c$'])
     >>> m(b'a.txt')
     True
     >>> m(b'b.txt')
     False
 
     Input files that would be matched are exactly those returned by .files()
     >>> m.files()
     ['a.txt', 're:.*\\.c$']
 
     So pattern 're:.*\.c$' is not considered as a regex, but as a file name
     >>> m(b'main.c')
     False
     >>> m(br're:.*\.c$')
     True
     '''
 
     def __init__(self, files, badfn=None):
         super(exactmatcher, self).__init__(badfn)
 
         if isinstance(files, list):
             self._files = files
         else:
             self._files = list(files)
 
     matchfn = basematcher.exact
 
     @propertycache
     def _dirs(self):
         return set(util.dirs(self._fileset))
 
     def visitdir(self, dir):
         dir = normalizerootdir(dir, 'visitdir')
         return dir in self._dirs
 
     def visitchildrenset(self, dir):
         dir = normalizerootdir(dir, 'visitchildrenset')
 
         if not self._fileset or dir not in self._dirs:
             return set()
 
         candidates = self._fileset | self._dirs - {''}
         if dir != '':
             d = dir + '/'
             candidates = set(c[len(d):] for c in candidates if
                              c.startswith(d))
         # self._dirs includes all of the directories, recursively, so if
         # we're attempting to match foo/bar/baz.txt, it'll have '', 'foo',
         # 'foo/bar' in it. Thus we can safely ignore a candidate that has a
         # '/' in it, indicating a it's for a subdir-of-a-subdir; the
         # immediate subdir will be in there without a slash.
         ret = {c for c in candidates if '/' not in c}
         # We really do not expect ret to be empty, since that would imply that
         # there's something in _dirs that didn't have a file in _fileset.
         assert ret
         return ret
 
     def isexact(self):
         return True
 
     @encoding.strmethod
     def __repr__(self):
         return ('<exactmatcher files=%r>' % self._files)
 
 class differencematcher(basematcher):
     '''Composes two matchers by matching if the first matches and the second
     does not.
 
     The second matcher's non-matching-attributes (bad, explicitdir,
     traversedir) are ignored.
     '''
     def __init__(self, m1, m2):
         super(differencematcher, self).__init__()
         self._m1 = m1
         self._m2 = m2
         self.bad = m1.bad
         self.explicitdir = m1.explicitdir
         self.traversedir = m1.traversedir
 
     def matchfn(self, f):
         return self._m1(f) and not self._m2(f)
 
     @propertycache
     def _files(self):
         if self.isexact():
             return [f for f in self._m1.files() if self(f)]
         # If m1 is not an exact matcher, we can't easily figure out the set of
         # files, because its files() are not always files. For example, if
         # m1 is "path:dir" and m2 is "rootfileins:.", we don't
         # want to remove "dir" from the set even though it would match m2,
         # because the "dir" in m1 may not be a file.
         return self._m1.files()
 
     def visitdir(self, dir):
         if self._m2.visitdir(dir) == 'all':
             return False
         elif not self._m2.visitdir(dir):
             # m2 does not match dir, we can return 'all' here if possible
             return self._m1.visitdir(dir)
         return bool(self._m1.visitdir(dir))
 
     def visitchildrenset(self, dir):
         m2_set = self._m2.visitchildrenset(dir)
         if m2_set == 'all':
             return set()
         m1_set = self._m1.visitchildrenset(dir)
         # Possible values for m1: 'all', 'this', set(...), set()
         # Possible values for m2:        'this', set(...), set()
         # If m2 has nothing under here that we care about, return m1, even if
         # it's 'all'. This is a change in behavior from visitdir, which would
         # return True, not 'all', for some reason.
         if not m2_set:
             return m1_set
         if m1_set in ['all', 'this']:
             # Never return 'all' here if m2_set is any kind of non-empty (either
             # 'this' or set(foo)), since m2 might return set() for a
             # subdirectory.
             return 'this'
         # Possible values for m1:         set(...), set()
         # Possible values for m2: 'this', set(...)
         # We ignore m2's set results. They're possibly incorrect:
         #  m1 = path:dir/subdir, m2=rootfilesin:dir, visitchildrenset(''):
         #    m1 returns {'dir'}, m2 returns {'dir'}, if we subtracted we'd
         #    return set(), which is *not* correct, we still need to visit 'dir'!
         return m1_set
 
     def isexact(self):
         return self._m1.isexact()
 
     @encoding.strmethod
     def __repr__(self):
         return ('<differencematcher m1=%r, m2=%r>' % (self._m1, self._m2))
 
 def intersectmatchers(m1, m2):
     '''Composes two matchers by matching if both of them match.
 
     The second matcher's non-matching-attributes (bad, explicitdir,
     traversedir) are ignored.
     '''
     if m1 is None or m2 is None:
         return m1 or m2
     if m1.always():
         m = copy.copy(m2)
         # TODO: Consider encapsulating these things in a class so there's only
         # one thing to copy from m1.
         m.bad = m1.bad
         m.explicitdir = m1.explicitdir
         m.traversedir = m1.traversedir
         return m
     if m2.always():
         m = copy.copy(m1)
         return m
     return intersectionmatcher(m1, m2)
 
 class intersectionmatcher(basematcher):
     def __init__(self, m1, m2):
         super(intersectionmatcher, self).__init__()
         self._m1 = m1
         self._m2 = m2
         self.bad = m1.bad
         self.explicitdir = m1.explicitdir
         self.traversedir = m1.traversedir
 
     @propertycache
     def _files(self):
         if self.isexact():
             m1, m2 = self._m1, self._m2
             if not m1.isexact():
                 m1, m2 = m2, m1
             return [f for f in m1.files() if m2(f)]
         # It neither m1 nor m2 is an exact matcher, we can't easily intersect
         # the set of files, because their files() are not always files. For
         # example, if intersecting a matcher "-I glob:foo.txt" with matcher of
         # "path:dir2", we don't want to remove "dir2" from the set.
         return self._m1.files() + self._m2.files()
 
     def matchfn(self, f):
         return self._m1(f) and self._m2(f)
 
     def visitdir(self, dir):
         visit1 = self._m1.visitdir(dir)
         if visit1 == 'all':
             return self._m2.visitdir(dir)
         # bool() because visit1=True + visit2='all' should not be 'all'
         return bool(visit1 and self._m2.visitdir(dir))
 
     def visitchildrenset(self, dir):
         m1_set = self._m1.visitchildrenset(dir)
         if not m1_set:
             return set()
         m2_set = self._m2.visitchildrenset(dir)
         if not m2_set:
             return set()
 
         if m1_set == 'all':
             return m2_set
         elif m2_set == 'all':
             return m1_set
 
         if m1_set == 'this' or m2_set == 'this':
             return 'this'
 
         assert isinstance(m1_set, set) and isinstance(m2_set, set)
         return m1_set.intersection(m2_set)
 
     def always(self):
         return self._m1.always() and self._m2.always()
 
     def isexact(self):
         return self._m1.isexact() or self._m2.isexact()
 
     @encoding.strmethod
     def __repr__(self):
         return ('<intersectionmatcher m1=%r, m2=%r>' % (self._m1, self._m2))
 
 class subdirmatcher(basematcher):
     """Adapt a matcher to work on a subdirectory only.
 
     The paths are remapped to remove/insert the path as needed:
 
     >>> from . import pycompat
     >>> m1 = match(b'root', b'', [b'a.txt', b'sub/b.txt'])
     >>> m2 = subdirmatcher(b'sub', m1)
     >>> m2(b'a.txt')
     False
     >>> m2(b'b.txt')
     True
     >>> m2.matchfn(b'a.txt')
     False
     >>> m2.matchfn(b'b.txt')
     True
     >>> m2.files()
     ['b.txt']
     >>> m2.exact(b'b.txt')
     True
     >>> def bad(f, msg):
     ...     print(pycompat.sysstr(b"%s: %s" % (f, msg)))
     >>> m1.bad = bad
     >>> m2.bad(b'x.txt', b'No such file')
     sub/x.txt: No such file
     """
 
     def __init__(self, path, matcher):
         super(subdirmatcher, self).__init__()
         self._path = path
         self._matcher = matcher
         self._always = matcher.always()
 
         self._files = [f[len(path) + 1:] for f in matcher._files
                        if f.startswith(path + "/")]
 
         # If the parent repo had a path to this subrepo and the matcher is
         # a prefix matcher, this submatcher always matches.
         if matcher.prefix():
             self._always = any(f == path for f in matcher._files)
 
     def bad(self, f, msg):
         self._matcher.bad(self._path + "/" + f, msg)
 
     def matchfn(self, f):
         # Some information is lost in the superclass's constructor, so we
         # can not accurately create the matching function for the subdirectory
         # from the inputs. Instead, we override matchfn() and visitdir() to
         # call the original matcher with the subdirectory path prepended.
         return self._matcher.matchfn(self._path + "/" + f)
 
     def visitdir(self, dir):
         dir = normalizerootdir(dir, 'visitdir')
         if dir == '':
             dir = self._path
         else:
             dir = self._path + "/" + dir
         return self._matcher.visitdir(dir)
 
     def visitchildrenset(self, dir):
         dir = normalizerootdir(dir, 'visitchildrenset')
         if dir == '':
             dir = self._path
         else:
             dir = self._path + "/" + dir
         return self._matcher.visitchildrenset(dir)
 
     def always(self):
         return self._always
 
     def prefix(self):
         return self._matcher.prefix() and not self._always
 
     @encoding.strmethod
     def __repr__(self):
         return ('<subdirmatcher path=%r, matcher=%r>' %
                 (self._path, self._matcher))
 
 class prefixdirmatcher(basematcher):
     """Adapt a matcher to work on a parent directory.
 
     The matcher's non-matching-attributes (bad, explicitdir, traversedir) are
     ignored.
 
     The prefix path should usually be the relative path from the root of
     this matcher to the root of the wrapped matcher.
 
     >>> m1 = match(util.localpath(b'root/d/e'), b'f', [b'../a.txt', b'b.txt'])
     >>> m2 = prefixdirmatcher(b'd/e', m1)
     >>> m2(b'a.txt')
     False
     >>> m2(b'd/e/a.txt')
     True
     >>> m2(b'd/e/b.txt')
     False
     >>> m2.files()
     ['d/e/a.txt', 'd/e/f/b.txt']
     >>> m2.exact(b'd/e/a.txt')
     True
     >>> m2.visitdir(b'd')
     True
     >>> m2.visitdir(b'd/e')
     True
     >>> m2.visitdir(b'd/e/f')
     True
     >>> m2.visitdir(b'd/e/g')
     False
     >>> m2.visitdir(b'd/ef')
     False
     """
 
     def __init__(self, path, matcher, badfn=None):
         super(prefixdirmatcher, self).__init__(badfn)
         if not path:
             raise error.ProgrammingError('prefix path must not be empty')
         self._path = path
         self._pathprefix = path + '/'
         self._matcher = matcher
 
     @propertycache
     def _files(self):
         return [self._pathprefix + f for f in self._matcher._files]
 
     def matchfn(self, f):
         if not f.startswith(self._pathprefix):
             return False
         return self._matcher.matchfn(f[len(self._pathprefix):])
 
     @propertycache
     def _pathdirs(self):
         return set(util.finddirs(self._path))
 
     def visitdir(self, dir):
         if dir == self._path:
             return self._matcher.visitdir('')
         if dir.startswith(self._pathprefix):
             return self._matcher.visitdir(dir[len(self._pathprefix):])
         return dir in self._pathdirs
 
     def visitchildrenset(self, dir):
         if dir == self._path:
             return self._matcher.visitchildrenset('')
         if dir.startswith(self._pathprefix):
             return self._matcher.visitchildrenset(dir[len(self._pathprefix):])
         if dir in self._pathdirs:
             return 'this'
         return set()
 
     def isexact(self):
         return self._matcher.isexact()
 
     def prefix(self):
         return self._matcher.prefix()
 
     @encoding.strmethod
     def __repr__(self):
         return ('<prefixdirmatcher path=%r, matcher=%r>'
                 % (pycompat.bytestr(self._path), self._matcher))
 
 class unionmatcher(basematcher):
     """A matcher that is the union of several matchers.
 
     The non-matching-attributes (bad, explicitdir, traversedir) are taken from
     the first matcher.
     """
 
     def __init__(self, matchers):
         m1 = matchers[0]
         super(unionmatcher, self).__init__()
         self.explicitdir = m1.explicitdir
         self.traversedir = m1.traversedir
         self._matchers = matchers
 
     def matchfn(self, f):
         for match in self._matchers:
             if match(f):
                 return True
         return False
 
     def visitdir(self, dir):
         r = False
         for m in self._matchers:
             v = m.visitdir(dir)
             if v == 'all':
                 return v
             r |= v
         return r
 
     def visitchildrenset(self, dir):
         r = set()
         this = False
         for m in self._matchers:
             v = m.visitchildrenset(dir)
             if not v:
                 continue
             if v == 'all':
                 return v
             if this or v == 'this':
                 this = True
                 # don't break, we might have an 'all' in here.
                 continue
             assert isinstance(v, set)
             r = r.union(v)
         if this:
             return 'this'
         return r
 
     @encoding.strmethod
     def __repr__(self):
         return ('<unionmatcher matchers=%r>' % self._matchers)
 
 def patkind(pattern, default=None):
     '''If pattern is 'kind:pat' with a known kind, return kind.
 
     >>> patkind(br're:.*\.c$')
     're'
     >>> patkind(b'glob:*.c')
     'glob'
     >>> patkind(b'relpath:test.py')
     'relpath'
     >>> patkind(b'main.py')
     >>> patkind(b'main.py', default=b're')
     're'
     '''
     return _patsplit(pattern, default)[0]
 
 def _patsplit(pattern, default):
     """Split a string into the optional pattern kind prefix and the actual
     pattern."""
     if ':' in pattern:
         kind, pat = pattern.split(':', 1)
         if kind in allpatternkinds:
             return kind, pat
     return default, pattern
 
 def _globre(pat):
     r'''Convert an extended glob string to a regexp string.
 
     >>> from . import pycompat
     >>> def bprint(s):
     ...     print(pycompat.sysstr(s))
     >>> bprint(_globre(br'?'))
     .
     >>> bprint(_globre(br'*'))
     [^/]*
     >>> bprint(_globre(br'**'))
     .*
     >>> bprint(_globre(br'**/a'))
     (?:.*/)?a
     >>> bprint(_globre(br'a/**/b'))
     a/(?:.*/)?b
     >>> bprint(_globre(br'[a*?!^][^b][!c]'))
     [a*?!^][\^b][^c]
     >>> bprint(_globre(br'{a,b}'))
     (?:a|b)
     >>> bprint(_globre(br'.\*\?'))
     \.\*\?
     '''
     i, n = 0, len(pat)
     res = ''
     group = 0
     escape = util.stringutil.regexbytesescapemap.get
     def peek():
         return i < n and pat[i:i + 1]
     while i < n:
         c = pat[i:i + 1]
         i += 1
         if c not in '*?[{},\\':
             res += escape(c, c)
         elif c == '*':
             if peek() == '*':
                 i += 1
                 if peek() == '/':
                     i += 1
                     res += '(?:.*/)?'
                 else:
                     res += '.*'
             else:
                 res += '[^/]*'
         elif c == '?':
             res += '.'
         elif c == '[':
             j = i
             if j < n and pat[j:j + 1] in '!]':
                 j += 1
             while j < n and pat[j:j + 1] != ']':
                 j += 1
             if j >= n:
                 res += '\\['
             else:
                 stuff = pat[i:j].replace('\\','\\\\')
                 i = j + 1
                 if stuff[0:1] == '!':
                     stuff = '^' + stuff[1:]
                 elif stuff[0:1] == '^':
                     stuff = '\\' + stuff
                 res = '%s[%s]' % (res, stuff)
         elif c == '{':
             group += 1
             res += '(?:'
         elif c == '}' and group:
             res += ')'
             group -= 1
         elif c == ',' and group:
             res += '|'
         elif c == '\\':
             p = peek()
             if p:
                 i += 1
                 res += escape(p, p)
             else:
                 res += escape(c, c)
         else:
             res += escape(c, c)
     return res
 
 def _regex(kind, pat, globsuffix):
     '''Convert a (normalized) pattern of any kind into a
     regular expression.
     globsuffix is appended to the regexp of globs.'''
 
     if rustmod is not None:
         try:
             return rustmod.build_single_regex(
                 kind,
                 pat,
                 globsuffix
             )
         except rustmod.PatternError:
             raise error.ProgrammingError(
                 'not a regex pattern: %s:%s' % (kind, pat)
             )
 
     if not pat and kind in ('glob', 'relpath'):
         return ''
     if kind == 're':
         return pat
     if kind in ('path', 'relpath'):
         if pat == '.':
             return ''
         return util.stringutil.reescape(pat) + '(?:/|$)'
     if kind == 'rootfilesin':
         if pat == '.':
             escaped = ''
         else:
             # Pattern is a directory name.
             escaped = util.stringutil.reescape(pat) + '/'
         # Anything after the pattern must be a non-directory.
         return escaped + '[^/]+$'
     if kind == 'relglob':
-        return '(?:|.*/)' + _globre(pat) + globsuffix
+        globre = _globre(pat)
+        if globre.startswith('[^/]*'):
+            # When pat has the form *XYZ (common), make the returned regex more
+            # legible by returning the regex for **XYZ instead of **/*XYZ.
+            return '.*' + globre[len('[^/]*'):] + globsuffix
+        return '(?:|.*/)' + globre + 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, root):
     '''Return regexp string and a matcher function for kindpats.
     globsuffix is appended to the regexp of globs.'''
     matchfuncs = []
 
     subincludes, kindpats = _expandsubinclude(kindpats, root)
     if subincludes:
         submatchers = {}
         def matchsubinclude(f):
             for prefix, matcherargs in subincludes:
                 if f.startswith(prefix):
                     mf = submatchers.get(prefix)
                     if mf is None:
                         mf = match(*matcherargs)
                         submatchers[prefix] = mf
 
                     if mf(f[len(prefix):]):
                         return True
             return False
         matchfuncs.append(matchsubinclude)
 
     regex = ''
     if kindpats:
         if all(k == 'rootfilesin' for k, p, s in kindpats):
             dirs = {p for k, p, s in kindpats}
             def mf(f):
                 i = f.rfind('/')
                 if i >= 0:
                     dir = f[:i]
                 else:
                     dir = '.'
                 return dir in dirs
             regex = b'rootfilesin: %s' % stringutil.pprint(list(sorted(dirs)))
             matchfuncs.append(mf)
         else:
             regex, mf = _buildregexmatch(kindpats, globsuffix)
             matchfuncs.append(mf)
 
     if len(matchfuncs) == 1:
         return regex, matchfuncs[0]
     else:
         return regex, lambda f: any(mf(f) for mf in matchfuncs)
 
 MAX_RE_SIZE = 20000
 
 def _joinregexes(regexps):
     """gather multiple regular expressions into a single one"""
     return '|'.join(regexps)
 
 def _buildregexmatch(kindpats, globsuffix):
     """Build a match function from a list of kinds and kindpats,
     return regexp string and a matcher function.
 
     Test too large input
     >>> _buildregexmatch([
     ...     (b'relglob', b'?' * MAX_RE_SIZE, b'')
     ... ], b'$')
     Traceback (most recent call last):
     ...
     Abort: matcher pattern is too long (20009 bytes)
     """
     try:
         allgroups = []
         regexps = [_regex(k, p, globsuffix) for (k, p, s) in kindpats]
         fullregexp = _joinregexes(regexps)
 
         startidx = 0
         groupsize = 0
         for idx, r in enumerate(regexps):
             piecesize = len(r)
             if piecesize > MAX_RE_SIZE:
                 msg = _("matcher pattern is too long (%d bytes)") % piecesize
                 raise error.Abort(msg)
             elif (groupsize + piecesize) > MAX_RE_SIZE:
                 group = regexps[startidx:idx]
                 allgroups.append(_joinregexes(group))
                 startidx = idx
                 groupsize = 0
             groupsize += piecesize + 1
 
         if startidx == 0:
             matcher = _rematcher(fullregexp)
             func = lambda s: bool(matcher(s))
         else:
             group = regexps[startidx:]
             allgroups.append(_joinregexes(group))
             allmatchers = [_rematcher(g) for g in allgroups]
             func = lambda s: any(m(s) for m in allmatchers)
         return fullregexp, func
     except re.error:
         for k, p, s in kindpats:
             try:
                 _rematcher(_regex(k, p, globsuffix))
             except re.error:
                 if s:
                     raise error.Abort(_("%s: invalid pattern (%s): %s") %
                                       (s, k, p))
                 else:
                     raise error.Abort(_("invalid pattern (%s): %s") % (k, p))
         raise error.Abort(_("invalid pattern"))
 
 def _patternrootsanddirs(kindpats):
     '''Returns roots and directories corresponding to each pattern.
 
     This calculates the roots and directories exactly matching the patterns and
     returns a tuple of (roots, dirs) for each. It does not return other
     directories which may also need to be considered, like the parent
     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)
             r.append('/'.join(root))
         elif kind in ('relpath', 'path'):
             if pat == '.':
                 pat = ''
             r.append(pat)
         elif kind in ('rootfilesin',):
             if pat == '.':
                 pat = ''
             d.append(pat)
         else: # relglob, re, relre
             r.append('')
     return r, d
 
 def _roots(kindpats):
     '''Returns root directories to match recursively from the given patterns.'''
     roots, dirs = _patternrootsanddirs(kindpats)
     return roots
 
 def _rootsdirsandparents(kindpats):
     '''Returns roots and exact directories from patterns.
 
     `roots` are directories to match recursively, `dirs` should
     be matched non-recursively, and `parents` are the implicitly required
     directories to walk to items in either roots or dirs.
 
     Returns a tuple of (roots, dirs, parents).
 
     >>> r = _rootsdirsandparents(
     ...     [(b'glob', b'g/h/*', b''), (b'glob', b'g/h', b''),
     ...      (b'glob', b'g*', b'')])
     >>> print(r[0:2], sorted(r[2])) # the set has an unstable output
     (['g/h', 'g/h', ''], []) ['', 'g']
     >>> r = _rootsdirsandparents(
     ...     [(b'rootfilesin', b'g/h', b''), (b'rootfilesin', b'', b'')])
     >>> print(r[0:2], sorted(r[2])) # the set has an unstable output
     ([], ['g/h', '']) ['', 'g']
     >>> r = _rootsdirsandparents(
     ...     [(b'relpath', b'r', b''), (b'path', b'p/p', b''),
     ...      (b'path', b'', b'')])
     >>> print(r[0:2], sorted(r[2])) # the set has an unstable output
     (['r', 'p/p', ''], []) ['', 'p']
     >>> r = _rootsdirsandparents(
     ...     [(b'relglob', b'rg*', b''), (b're', b're/', b''),
     ...      (b'relre', b'rr', b'')])
     >>> print(r[0:2], sorted(r[2])) # the set has an unstable output
     (['', '', ''], []) ['']
     '''
     r, d = _patternrootsanddirs(kindpats)
 
     p = set()
     # Add the parents as non-recursive/exact directories, since they must be
     # scanned to get to either the roots or the other exact directories.
     p.update(util.dirs(d))
     p.update(util.dirs(r))
 
     # FIXME: all uses of this function convert these to sets, do so before
     # returning.
     # FIXME: all uses of this function do not need anything in 'roots' and
     # 'dirs' to also be in 'parents', consider removing them before returning.
     return r, d, p
 
 def _explicitfiles(kindpats):
     '''Returns the potential explicit filenames from the patterns.
 
     >>> _explicitfiles([(b'path', b'foo/bar', b'')])
     ['foo/bar']
     >>> _explicitfiles([(b'rootfilesin', b'foo/bar', b'')])
     []
     '''
     # Keep only the pattern kinds where one can specify filenames (vs only
     # directory names).
     filable = [kp for kp in kindpats if kp[0] not in ('rootfilesin',)]
     return _roots(filable)
 
 def _prefix(kindpats):
     '''Whether all the patterns match a prefix (i.e. recursively)'''
     for kind, pat, source in kindpats:
         if kind not in ('path', 'relpath'):
             return False
     return True
 
 _commentre = None
 
 def readpatternfile(filepath, warn, sourceinfo=False):
     '''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.
 
     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
     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.
     '''
 
     if rustmod is not None:
         result, warnings = rustmod.read_pattern_file(
             filepath,
             bool(warn),
             sourceinfo,
         )
 
         for warning_params in warnings:
             # Can't be easily emitted from Rust, because it would require
             # a mechanism for both gettext and calling the `warn` function.
             warn(_("%s: ignoring invalid syntax '%s'\n") % warning_params)
 
         return result
 
     syntaxes = {
         're': 'relre:',
         'regexp': 'relre:',
         'glob': 'relglob:',
         'rootglob': 'rootglob:',
         'include': 'include',
         'subinclude': 'subinclude',
     }
     syntax = 'relre:'
     patterns = []
 
     fp = open(filepath, 'rb')
     for lineno, line in enumerate(util.iterfile(fp), start=1):
         if "#" in line:
             global _commentre
             if not _commentre:
                 _commentre = util.re.compile(br'((?:^|[^\\])(?:\\\\)*)#.*')
             # remove comments prefixed by an even number of escapes
             m = _commentre.search(line)
             if m:
                 line = line[:m.end(1)]
             # 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:
                 if warn:
                     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
         if sourceinfo:
             patterns.append((linesyntax + line, lineno, line))
         else:
             patterns.append(linesyntax + line)
     fp.close()
     return patterns

rust/hg-core/src/filepatterns.rs

@@ -1,384 +1,392
 // filepatterns.rs
 //
 // Copyright 2019 Raphaël Gomès <[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.
 
 //! Handling of Mercurial-specific patterns.
 
 use crate::{
     utils::{files::get_path_from_bytes, SliceExt},
     LineNumber, PatternError, PatternFileError,
 };
 use lazy_static::lazy_static;
 use regex::bytes::{NoExpand, Regex};
 use std::collections::HashMap;
 use std::fs::File;
 use std::io::Read;
 use std::vec::Vec;
 
 lazy_static! {
     static ref RE_ESCAPE: Vec<Vec<u8>> = {
         let mut v: Vec<Vec<u8>> = (0..=255).map(|byte| vec![byte]).collect();
         let to_escape = b"()[]{}?*+-|^$\\.&~# \t\n\r\x0b\x0c";
         for byte in to_escape {
             v[*byte as usize].insert(0, b'\\');
         }
         v
     };
 }
 
 /// These are matched in order
 const GLOB_REPLACEMENTS: &[(&[u8], &[u8])] =
     &[(b"*/", b"(?:.*/)?"), (b"*", b".*"), (b"", b"[^/]*")];
 
 #[derive(Debug, Copy, Clone, PartialEq, Eq)]
 pub enum PatternSyntax {
     Regexp,
     /// Glob that matches at the front of the path
     RootGlob,
     /// Glob that matches at any suffix of the path (still anchored at
     /// slashes)
     Glob,
     Path,
     RelPath,
     RelGlob,
     RelRegexp,
     RootFiles,
 }
 
 /// Transforms a glob pattern into a regex
 fn glob_to_re(pat: &[u8]) -> Vec<u8> {
     let mut input = pat;
     let mut res: Vec<u8> = vec![];
     let mut group_depth = 0;
 
     while let Some((c, rest)) = input.split_first() {
         input = rest;
 
         match c {
             b'*' => {
                 for (source, repl) in GLOB_REPLACEMENTS {
                     if let Some(rest) = input.drop_prefix(source) {
                         input = rest;
                         res.extend(*repl);
                         break;
                     }
                 }
             }
             b'?' => res.extend(b"."),
             b'[' => {
                 match input.iter().skip(1).position(|b| *b == b']') {
                     None => res.extend(b"\\["),
                     Some(end) => {
                         // Account for the one we skipped
                         let end = end + 1;
 
                         res.extend(b"[");
 
                         for (i, b) in input[..end].iter().enumerate() {
                             if *b == b'!' && i == 0 {
                                 res.extend(b"^")
                             } else if *b == b'^' && i == 0 {
                                 res.extend(b"\\^")
                             } else if *b == b'\\' {
                                 res.extend(b"\\\\")
                             } else {
                                 res.push(*b)
                             }
                         }
                         res.extend(b"]");
                         input = &input[end + 1..];
                     }
                 }
             }
             b'{' => {
                 group_depth += 1;
                 res.extend(b"(?:")
             }
             b'}' if group_depth > 0 => {
                 group_depth -= 1;
                 res.extend(b")");
             }
             b',' if group_depth > 0 => res.extend(b"|"),
             b'\\' => {
                 let c = {
                     if let Some((c, rest)) = input.split_first() {
                         input = rest;
                         c
                     } else {
                         c
                     }
                 };
                 res.extend(&RE_ESCAPE[*c as usize])
             }
             _ => res.extend(&RE_ESCAPE[*c as usize]),
         }
     }
     res
 }
 
 fn escape_pattern(pattern: &[u8]) -> Vec<u8> {
     pattern
         .iter()
         .flat_map(|c| RE_ESCAPE[*c as usize].clone())
         .collect()
 }
 
 fn parse_pattern_syntax(kind: &[u8]) -> Result<PatternSyntax, PatternError> {
     match kind {
         b"re" => Ok(PatternSyntax::Regexp),
         b"path" => Ok(PatternSyntax::Path),
         b"relpath" => Ok(PatternSyntax::RelPath),
         b"rootfilesin" => Ok(PatternSyntax::RootFiles),
         b"relglob" => Ok(PatternSyntax::RelGlob),
         b"relre" => Ok(PatternSyntax::RelRegexp),
         b"glob" => Ok(PatternSyntax::Glob),
         b"rootglob" => Ok(PatternSyntax::RootGlob),
         _ => Err(PatternError::UnsupportedSyntax(
             String::from_utf8_lossy(kind).to_string(),
         )),
     }
 }
 
 /// Builds the regex that corresponds to the given pattern.
 /// If within a `syntax: regexp` context, returns the pattern,
 /// otherwise, returns the corresponding regex.
 fn _build_single_regex(
     syntax: PatternSyntax,
     pattern: &[u8],
     globsuffix: &[u8],
 ) -> Vec<u8> {
     if pattern.is_empty() {
         return vec![];
     }
     match syntax {
         PatternSyntax::Regexp => pattern.to_owned(),
         PatternSyntax::RelRegexp => {
             if pattern[0] == b'^' {
                 return pattern.to_owned();
             }
             let mut res = b".*".to_vec();
             res.extend(pattern);
             res
         }
         PatternSyntax::Path | PatternSyntax::RelPath => {
             if pattern == b"." {
                 return vec![];
             }
             let mut pattern = escape_pattern(pattern);
             pattern.extend(b"(?:/|$)");
             pattern
         }
         PatternSyntax::RootFiles => {
             let mut res = if pattern == b"." {
                 vec![]
             } else {
                 // Pattern is a directory name.
                 let mut as_vec: Vec<u8> = escape_pattern(pattern);
                 as_vec.push(b'/');
                 as_vec
             };
 
             // Anything after the pattern must be a non-directory.
             res.extend(b"[^/]+$");
             res
         }
+        PatternSyntax::RelGlob => {
+            let mut res: Vec<u8> = vec![];
+            let glob_re = glob_to_re(pattern);
+            if let Some(rest) = glob_re.drop_prefix(b"[^/]*") {
+                res.extend(b".*");
+                res.extend(rest);
+            } else {
+                res.extend(b"(?:|.*/)");
+                res.extend(glob_re);
+            }
+            res.extend(globsuffix.iter());
+            res
+        }
         PatternSyntax::Glob
-        | PatternSyntax::RelGlob
         | PatternSyntax::RootGlob => {
             let mut res: Vec<u8> = vec![];
-            if syntax == PatternSyntax::RelGlob {
-                res.extend(b"(?:|.*/)");
-            }
-
             res.extend(glob_to_re(pattern));
             res.extend(globsuffix.iter());
             res
         }
     }
 }
 
 const GLOB_SPECIAL_CHARACTERS: [u8; 7] =
     [b'*', b'?', b'[', b']', b'{', b'}', b'\\'];
 
 /// Wrapper function to `_build_single_regex` that short-circuits 'exact' globs
 /// that don't need to be transformed into a regex.
 pub fn build_single_regex(
     kind: &[u8],
     pat: &[u8],
     globsuffix: &[u8],
 ) -> Result<Vec<u8>, PatternError> {
     let enum_kind = parse_pattern_syntax(kind)?;
     if enum_kind == PatternSyntax::RootGlob
         && !pat.iter().any(|b| GLOB_SPECIAL_CHARACTERS.contains(b))
     {
         let mut escaped = escape_pattern(pat);
         escaped.extend(b"(?:/|$)");
         Ok(escaped)
     } else {
         Ok(_build_single_regex(enum_kind, pat, globsuffix))
     }
 }
 
 lazy_static! {
     static ref SYNTAXES: HashMap<&'static [u8], &'static [u8]> = {
         let mut m = HashMap::new();
 
         m.insert(b"re".as_ref(), b"relre:".as_ref());
         m.insert(b"regexp".as_ref(), b"relre:".as_ref());
         m.insert(b"glob".as_ref(), b"relglob:".as_ref());
         m.insert(b"rootglob".as_ref(), b"rootglob:".as_ref());
         m.insert(b"include".as_ref(), b"include".as_ref());
         m.insert(b"subinclude".as_ref(), b"subinclude".as_ref());
         m
     };
 }
 
 pub type PatternTuple = (Vec<u8>, LineNumber, Vec<u8>);
 type WarningTuple = (Vec<u8>, Vec<u8>);
 
 pub fn parse_pattern_file_contents(
     lines: &[u8],
     file_path: &[u8],
     warn: bool,
 ) -> (Vec<PatternTuple>, Vec<WarningTuple>) {
     let comment_regex = Regex::new(r"((?:^|[^\\])(?:\\\\)*)#.*").unwrap();
     let comment_escape_regex = Regex::new(r"\\#").unwrap();
     let mut inputs: Vec<PatternTuple> = vec![];
     let mut warnings: Vec<WarningTuple> = vec![];
 
     let mut current_syntax = b"relre:".as_ref();
 
     for (line_number, mut line) in lines.split(|c| *c == b'\n').enumerate() {
         let line_number = line_number + 1;
 
         let line_buf;
         if line.contains(&b'#') {
             if let Some(cap) = comment_regex.captures(line) {
                 line = &line[..cap.get(1).unwrap().end()]
             }
             line_buf = comment_escape_regex.replace_all(line, NoExpand(b"#"));
             line = &line_buf;
         }
 
         let mut line = line.trim_end();
 
         if line.is_empty() {
             continue;
         }
 
         if let Some(syntax) = line.drop_prefix(b"syntax:") {
             let syntax = syntax.trim();
 
             if let Some(rel_syntax) = SYNTAXES.get(syntax) {
                 current_syntax = rel_syntax;
             } else if warn {
                 warnings.push((file_path.to_owned(), syntax.to_owned()));
             }
             continue;
         }
 
         let mut line_syntax: &[u8] = &current_syntax;
 
         for (s, rels) in SYNTAXES.iter() {
             if let Some(rest) = line.drop_prefix(rels) {
                 line_syntax = rels;
                 line = rest;
                 break;
             }
             if let Some(rest) = line.drop_prefix(&[s, &b":"[..]].concat()) {
                 line_syntax = rels;
                 line = rest;
                 break;
             }
         }
 
         inputs.push((
             [line_syntax, line].concat(),
             line_number,
             line.to_owned(),
         ));
     }
     (inputs, warnings)
 }
 
 pub fn read_pattern_file(
     file_path: &[u8],
     warn: bool,
 ) -> Result<(Vec<PatternTuple>, Vec<WarningTuple>), PatternFileError> {
     let mut f = File::open(get_path_from_bytes(file_path))?;
     let mut contents = Vec::new();
 
     f.read_to_end(&mut contents)?;
 
     Ok(parse_pattern_file_contents(&contents, file_path, warn))
 }
 
 #[cfg(test)]
 mod tests {
     use super::*;
 
     #[test]
     fn escape_pattern_test() {
         let untouched = br#"!"%',/0123456789:;<=>@ABCDEFGHIJKLMNOPQRSTUVWXYZ_`abcdefghijklmnopqrstuvwxyz"#;
         assert_eq!(escape_pattern(untouched), untouched.to_vec());
         // All escape codes
         assert_eq!(
             escape_pattern(br#"()[]{}?*+-|^$\\.&~# \t\n\r\v\f"#),
             br#"\(\)\[\]\{\}\?\*\+\-\|\^\$\\\\\.\&\~\#\ \\t\\n\\r\\v\\f"#
                 .to_vec()
         );
     }
 
     #[test]
     fn glob_test() {
         assert_eq!(glob_to_re(br#"?"#), br#"."#);
         assert_eq!(glob_to_re(br#"*"#), br#"[^/]*"#);
         assert_eq!(glob_to_re(br#"**"#), br#".*"#);
         assert_eq!(glob_to_re(br#"**/a"#), br#"(?:.*/)?a"#);
         assert_eq!(glob_to_re(br#"a/**/b"#), br#"a/(?:.*/)?b"#);
         assert_eq!(glob_to_re(br#"[a*?!^][^b][!c]"#), br#"[a*?!^][\^b][^c]"#);
         assert_eq!(glob_to_re(br#"{a,b}"#), br#"(?:a|b)"#);
         assert_eq!(glob_to_re(br#".\*\?"#), br#"\.\*\?"#);
     }
 
     #[test]
     fn test_parse_pattern_file_contents() {
         let lines = b"syntax: glob\n*.elc";
 
         assert_eq!(
             vec![(b"relglob:*.elc".to_vec(), 2, b"*.elc".to_vec())],
             parse_pattern_file_contents(lines, b"file_path", false).0,
         );
 
         let lines = b"syntax: include\nsyntax: glob";
 
         assert_eq!(
             parse_pattern_file_contents(lines, b"file_path", false).0,
             vec![]
         );
         let lines = b"glob:**.o";
         assert_eq!(
             parse_pattern_file_contents(lines, b"file_path", false).0,
             vec![(b"relglob:**.o".to_vec(), 1, b"**.o".to_vec())]
         );
     }
 
     #[test]
     fn test_build_single_regex_shortcut() {
         assert_eq!(
             br"(?:/|$)".to_vec(),
             build_single_regex(b"rootglob", b"", b"").unwrap()
         );
         assert_eq!(
             br"whatever(?:/|$)".to_vec(),
             build_single_regex(b"rootglob", b"whatever", b"").unwrap()
         );
         assert_eq!(
             br"[^/]*\.o".to_vec(),
             build_single_regex(b"rootglob", b"*.o", b"").unwrap()
         );
     }
 }

tests/test-hgignore.t

@@ -1,390 +1,390
   $ hg init ignorerepo
   $ cd ignorerepo
 
 debugignore with no hgignore should be deterministic:
   $ hg debugignore
   <nevermatcher>
 
 Issue562: .hgignore requires newline at end:
 
   $ touch foo
   $ touch bar
   $ touch baz
   $ cat > makeignore.py <<EOF
   > f = open(".hgignore", "w")
   > f.write("ignore\n")
   > f.write("foo\n")
   > # No EOL here
   > f.write("bar")
   > f.close()
   > EOF
 
   $ "$PYTHON" makeignore.py
 
 Should display baz only:
 
   $ hg status
   ? baz
 
   $ rm foo bar baz .hgignore makeignore.py
 
   $ touch a.o
   $ touch a.c
   $ touch syntax
   $ mkdir dir
   $ touch dir/a.o
   $ touch dir/b.o
   $ touch dir/c.o
 
   $ hg add dir/a.o
   $ hg commit -m 0
   $ hg add dir/b.o
 
   $ hg status
   A dir/b.o
   ? a.c
   ? a.o
   ? dir/c.o
   ? syntax
 
   $ echo "*.o" > .hgignore
   $ hg status
   abort: $TESTTMP/ignorerepo/.hgignore: invalid pattern (relre): *.o (glob)
   [255]
 
 Ensure given files are relative to cwd
 
   $ echo "dir/.*\.o" > .hgignore
   $ hg status -i
   I dir/c.o
 
   $ hg debugignore dir/c.o dir/missing.o
   dir/c.o is ignored
   (ignore rule in $TESTTMP/ignorerepo/.hgignore, line 1: 'dir/.*\.o') (glob)
   dir/missing.o is ignored
   (ignore rule in $TESTTMP/ignorerepo/.hgignore, line 1: 'dir/.*\.o') (glob)
   $ cd dir
   $ hg debugignore c.o missing.o
   c.o is ignored
   (ignore rule in $TESTTMP/ignorerepo/.hgignore, line 1: 'dir/.*\.o') (glob)
   missing.o is ignored
   (ignore rule in $TESTTMP/ignorerepo/.hgignore, line 1: 'dir/.*\.o') (glob)
 
 For icasefs, inexact matches also work, except for missing files
 
 #if icasefs
   $ hg debugignore c.O missing.O
   c.o is ignored
   (ignore rule in $TESTTMP/ignorerepo/.hgignore, line 1: 'dir/.*\.o') (glob)
   missing.O is not ignored
 #endif
 
   $ cd ..
 
   $ echo ".*\.o" > .hgignore
   $ hg status
   A dir/b.o
   ? .hgignore
   ? a.c
   ? syntax
 
 Ensure that comments work:
 
   $ touch 'foo#bar' 'quux#' 'quu0#'
 #if no-windows
   $ touch 'baz\' 'baz\wat' 'ba0\#wat' 'ba1\\' 'ba1\\wat' 'quu0\'
 #endif
 
   $ cat <<'EOF' >> .hgignore
   > # full-line comment
   >   # whitespace-only comment line
   > syntax# pattern, no whitespace, then comment
   > a.c  # pattern, then whitespace, then comment
   > baz\\# # (escaped) backslash, then comment
   > ba0\\\#w # (escaped) backslash, escaped comment character, then comment
   > ba1\\\\# # (escaped) backslashes, then comment
   > foo\#b # escaped comment character
   > quux\## escaped comment character at end of name
   > EOF
   $ hg status
   A dir/b.o
   ? .hgignore
   ? quu0#
   ? quu0\ (no-windows !)
 
   $ cat <<'EOF' > .hgignore
   > .*\.o
   > syntax: glob
   > syntax# pattern, no whitespace, then comment
   > a.c  # pattern, then whitespace, then comment
   > baz\\#* # (escaped) backslash, then comment
   > ba0\\\#w* # (escaped) backslash, escaped comment character, then comment
   > ba1\\\\#* # (escaped) backslashes, then comment
   > foo\#b* # escaped comment character
   > quux\## escaped comment character at end of name
   > quu0[\#]# escaped comment character inside [...]
   > EOF
   $ hg status
   A dir/b.o
   ? .hgignore
   ? ba1\\wat (no-windows !)
   ? baz\wat (no-windows !)
   ? quu0\ (no-windows !)
 
   $ rm 'foo#bar' 'quux#' 'quu0#'
 #if no-windows
   $ rm 'baz\' 'baz\wat' 'ba0\#wat' 'ba1\\' 'ba1\\wat' 'quu0\'
 #endif
 
 Check that '^\.' does not ignore the root directory:
 
   $ echo "^\." > .hgignore
   $ hg status
   A dir/b.o
   ? a.c
   ? a.o
   ? dir/c.o
   ? syntax
 
 Test that patterns from ui.ignore options are read:
 
   $ echo > .hgignore
   $ cat >> $HGRCPATH << EOF
   > [ui]
   > ignore.other = $TESTTMP/ignorerepo/.hg/testhgignore
   > EOF
   $ echo "glob:**.o" > .hg/testhgignore
   $ hg status
   A dir/b.o
   ? .hgignore
   ? a.c
   ? syntax
 
 empty out testhgignore
   $ echo > .hg/testhgignore
 
 Test relative ignore path (issue4473):
 
   $ cat >> $HGRCPATH << EOF
   > [ui]
   > ignore.relative = .hg/testhgignorerel
   > EOF
   $ echo "glob:*.o" > .hg/testhgignorerel
   $ cd dir
   $ hg status
   A dir/b.o
   ? .hgignore
   ? a.c
   ? syntax
   $ hg debugignore
-  <includematcher includes='(?:|.*/)[^/]*\\.o(?:/|$)'>
+  <includematcher includes='.*\\.o(?:/|$)'>
 
   $ cd ..
   $ echo > .hg/testhgignorerel
   $ echo "syntax: glob" > .hgignore
   $ echo "re:.*\.o" >> .hgignore
   $ hg status
   A dir/b.o
   ? .hgignore
   ? a.c
   ? syntax
 
   $ echo "syntax: invalid" > .hgignore
   $ hg status
   $TESTTMP/ignorerepo/.hgignore: ignoring invalid syntax 'invalid'
   A dir/b.o
   ? .hgignore
   ? a.c
   ? a.o
   ? dir/c.o
   ? syntax
 
   $ echo "syntax: glob" > .hgignore
   $ echo "*.o" >> .hgignore
   $ hg status
   A dir/b.o
   ? .hgignore
   ? a.c
   ? syntax
 
   $ echo "relglob:syntax*" > .hgignore
   $ hg status
   A dir/b.o
   ? .hgignore
   ? a.c
   ? a.o
   ? dir/c.o
 
   $ echo "relglob:*" > .hgignore
   $ hg status
   A dir/b.o
 
   $ cd dir
   $ hg status .
   A b.o
 
   $ hg debugignore
-  <includematcher includes='(?:|.*/)[^/]*(?:/|$)'>
+  <includematcher includes='.*(?:/|$)'>
 
   $ hg debugignore b.o
   b.o is ignored
   (ignore rule in $TESTTMP/ignorerepo/.hgignore, line 1: '*') (glob)
 
   $ cd ..
 
 Check patterns that match only the directory
 
 "(fsmonitor !)" below assumes that fsmonitor is enabled with
 "walk_on_invalidate = false" (default), which doesn't involve
 re-walking whole repository at detection of .hgignore change.
 
   $ echo "^dir\$" > .hgignore
   $ hg status
   A dir/b.o
   ? .hgignore
   ? a.c
   ? a.o
   ? dir/c.o (fsmonitor !)
   ? syntax
 
 Check recursive glob pattern matches no directories (dir/**/c.o matches dir/c.o)
 
   $ echo "syntax: glob" > .hgignore
   $ echo "dir/**/c.o" >> .hgignore
   $ touch dir/c.o
   $ mkdir dir/subdir
   $ touch dir/subdir/c.o
   $ hg status
   A dir/b.o
   ? .hgignore
   ? a.c
   ? a.o
   ? syntax
   $ hg debugignore a.c
   a.c is not ignored
   $ hg debugignore dir/c.o
   dir/c.o is ignored
   (ignore rule in $TESTTMP/ignorerepo/.hgignore, line 2: 'dir/**/c.o') (glob)
 
 Check rooted globs
 
   $ hg purge --all --config extensions.purge=
   $ echo "syntax: rootglob" > .hgignore
   $ echo "a/*.ext" >> .hgignore
   $ for p in a b/a aa; do mkdir -p $p; touch $p/b.ext; done
   $ hg status -A 'set:**.ext'
   ? aa/b.ext
   ? b/a/b.ext
   I a/b.ext
 
 Check using 'include:' in ignore file
 
   $ hg purge --all --config extensions.purge=
   $ touch foo.included
 
   $ echo ".*.included" > otherignore
   $ hg status -I "include:otherignore"
   ? foo.included
 
   $ echo "include:otherignore" >> .hgignore
   $ hg status
   A dir/b.o
   ? .hgignore
   ? otherignore
 
 Check recursive uses of 'include:'
 
   $ echo "include:nested/ignore" >> otherignore
   $ mkdir nested nested/more
   $ echo "glob:*ignore" > nested/ignore
   $ echo "rootglob:a" >> nested/ignore
   $ touch a nested/a nested/more/a
   $ hg status
   A dir/b.o
   ? nested/a
   ? nested/more/a
   $ rm a nested/a nested/more/a
 
   $ cp otherignore goodignore
   $ echo "include:badignore" >> otherignore
   $ hg status
   skipping unreadable pattern file 'badignore': $ENOENT$
   A dir/b.o
 
   $ mv goodignore otherignore
 
 Check using 'include:' while in a non-root directory
 
   $ cd ..
   $ hg -R ignorerepo status
   A dir/b.o
   $ cd ignorerepo
 
 Check including subincludes
 
   $ hg revert -q --all
   $ hg purge --all --config extensions.purge=
   $ echo ".hgignore" > .hgignore
   $ mkdir dir1 dir2
   $ touch dir1/file1 dir1/file2 dir2/file1 dir2/file2
   $ echo "subinclude:dir2/.hgignore" >> .hgignore
   $ echo "glob:file*2" > dir2/.hgignore
   $ hg status
   ? dir1/file1
   ? dir1/file2
   ? dir2/file1
 
 Check including subincludes with other patterns
 
   $ echo "subinclude:dir1/.hgignore" >> .hgignore
 
   $ mkdir dir1/subdir
   $ touch dir1/subdir/file1
   $ echo "rootglob:f?le1" > dir1/.hgignore
   $ hg status
   ? dir1/file2
   ? dir1/subdir/file1
   ? dir2/file1
   $ rm dir1/subdir/file1
 
   $ echo "regexp:f.le1" > dir1/.hgignore
   $ hg status
   ? dir1/file2
   ? dir2/file1
 
 Check multiple levels of sub-ignores
 
   $ touch dir1/subdir/subfile1 dir1/subdir/subfile3 dir1/subdir/subfile4
   $ echo "subinclude:subdir/.hgignore" >> dir1/.hgignore
   $ echo "glob:subfil*3" >> dir1/subdir/.hgignore
 
   $ hg status
   ? dir1/file2
   ? dir1/subdir/subfile4
   ? dir2/file1
 
 Check include subignore at the same level
 
   $ mv dir1/subdir/.hgignore dir1/.hgignoretwo
   $ echo "regexp:f.le1" > dir1/.hgignore
   $ echo "subinclude:.hgignoretwo" >> dir1/.hgignore
   $ echo "glob:file*2" > dir1/.hgignoretwo
 
   $ hg status | grep file2
   [1]
   $ hg debugignore dir1/file2
   dir1/file2 is ignored
   (ignore rule in dir2/.hgignore, line 1: 'file*2')
 
 #if windows
 
 Windows paths are accepted on input
 
   $ rm dir1/.hgignore
   $ echo "dir1/file*" >> .hgignore
   $ hg debugignore "dir1\file2"
   dir1/file2 is ignored
   (ignore rule in $TESTTMP\ignorerepo\.hgignore, line 4: 'dir1/file*')
   $ hg up -qC .
 
 #endif

tests/test-walk.t

@@ -1,652 +1,652
   $ hg init t
   $ cd t
   $ mkdir -p beans
   $ for b in kidney navy turtle borlotti black pinto; do
   >     echo $b > beans/$b
   > done
   $ mkdir -p mammals/Procyonidae
   $ for m in cacomistle coatimundi raccoon; do
   >     echo $m > mammals/Procyonidae/$m
   > done
   $ echo skunk > mammals/skunk
   $ echo fennel > fennel
   $ echo fenugreek > fenugreek
   $ echo fiddlehead > fiddlehead
   $ hg addremove
   adding beans/black
   adding beans/borlotti
   adding beans/kidney
   adding beans/navy
   adding beans/pinto
   adding beans/turtle
   adding fennel
   adding fenugreek
   adding fiddlehead
   adding mammals/Procyonidae/cacomistle
   adding mammals/Procyonidae/coatimundi
   adding mammals/Procyonidae/raccoon
   adding mammals/skunk
   $ hg commit -m "commit #0"
 
   $ hg debugwalk -v
   * matcher:
   <alwaysmatcher>
   f  beans/black                     beans/black
   f  beans/borlotti                  beans/borlotti
   f  beans/kidney                    beans/kidney
   f  beans/navy                      beans/navy
   f  beans/pinto                     beans/pinto
   f  beans/turtle                    beans/turtle
   f  fennel                          fennel
   f  fenugreek                       fenugreek
   f  fiddlehead                      fiddlehead
   f  mammals/Procyonidae/cacomistle  mammals/Procyonidae/cacomistle
   f  mammals/Procyonidae/coatimundi  mammals/Procyonidae/coatimundi
   f  mammals/Procyonidae/raccoon     mammals/Procyonidae/raccoon
   f  mammals/skunk                   mammals/skunk
   $ hg debugwalk -v -I.
   * matcher:
   <includematcher includes=''>
   f  beans/black                     beans/black
   f  beans/borlotti                  beans/borlotti
   f  beans/kidney                    beans/kidney
   f  beans/navy                      beans/navy
   f  beans/pinto                     beans/pinto
   f  beans/turtle                    beans/turtle
   f  fennel                          fennel
   f  fenugreek                       fenugreek
   f  fiddlehead                      fiddlehead
   f  mammals/Procyonidae/cacomistle  mammals/Procyonidae/cacomistle
   f  mammals/Procyonidae/coatimundi  mammals/Procyonidae/coatimundi
   f  mammals/Procyonidae/raccoon     mammals/Procyonidae/raccoon
   f  mammals/skunk                   mammals/skunk
 
   $ cd mammals
   $ hg debugwalk -v
   * matcher:
   <alwaysmatcher>
   f  beans/black                     ../beans/black
   f  beans/borlotti                  ../beans/borlotti
   f  beans/kidney                    ../beans/kidney
   f  beans/navy                      ../beans/navy
   f  beans/pinto                     ../beans/pinto
   f  beans/turtle                    ../beans/turtle
   f  fennel                          ../fennel
   f  fenugreek                       ../fenugreek
   f  fiddlehead                      ../fiddlehead
   f  mammals/Procyonidae/cacomistle  Procyonidae/cacomistle
   f  mammals/Procyonidae/coatimundi  Procyonidae/coatimundi
   f  mammals/Procyonidae/raccoon     Procyonidae/raccoon
   f  mammals/skunk                   skunk
   $ hg debugwalk -v -X ../beans
   * matcher:
   <differencematcher
     m1=<alwaysmatcher>,
     m2=<includematcher includes='beans(?:/|$)'>>
   f  fennel                          ../fennel
   f  fenugreek                       ../fenugreek
   f  fiddlehead                      ../fiddlehead
   f  mammals/Procyonidae/cacomistle  Procyonidae/cacomistle
   f  mammals/Procyonidae/coatimundi  Procyonidae/coatimundi
   f  mammals/Procyonidae/raccoon     Procyonidae/raccoon
   f  mammals/skunk                   skunk
   $ hg debugwalk -v -I '*k'
   * matcher:
   <includematcher includes='mammals/[^/]*k(?:/|$)'>
   f  mammals/skunk  skunk
   $ hg debugwalk -v -I 'glob:*k'
   * matcher:
   <includematcher includes='mammals/[^/]*k(?:/|$)'>
   f  mammals/skunk  skunk
   $ hg debugwalk -v -I 'relglob:*k'
   * matcher:
-  <includematcher includes='(?:|.*/)[^/]*k(?:/|$)'>
+  <includematcher includes='.*k(?:/|$)'>
   f  beans/black    ../beans/black
   f  fenugreek      ../fenugreek
   f  mammals/skunk  skunk
   $ hg debugwalk -v -I 'relglob:*k' .
   * matcher:
   <intersectionmatcher
     m1=<patternmatcher patterns='mammals(?:/|$)'>,
-    m2=<includematcher includes='(?:|.*/)[^/]*k(?:/|$)'>>
+    m2=<includematcher includes='.*k(?:/|$)'>>
   f  mammals/skunk  skunk
   $ hg debugwalk -v -I 're:.*k$'
   * matcher:
   <includematcher includes='.*k$'>
   f  beans/black    ../beans/black
   f  fenugreek      ../fenugreek
   f  mammals/skunk  skunk
   $ hg debugwalk -v -I 'relre:.*k$'
   * matcher:
   <includematcher includes='.*.*k$'>
   f  beans/black    ../beans/black
   f  fenugreek      ../fenugreek
   f  mammals/skunk  skunk
   $ hg debugwalk -v -I 'path:beans'
   * matcher:
   <includematcher includes='beans(?:/|$)'>
   f  beans/black     ../beans/black
   f  beans/borlotti  ../beans/borlotti
   f  beans/kidney    ../beans/kidney
   f  beans/navy      ../beans/navy
   f  beans/pinto     ../beans/pinto
   f  beans/turtle    ../beans/turtle
   $ hg debugwalk -v -I 'relpath:detour/../../beans'
   * matcher:
   <includematcher includes='beans(?:/|$)'>
   f  beans/black     ../beans/black
   f  beans/borlotti  ../beans/borlotti
   f  beans/kidney    ../beans/kidney
   f  beans/navy      ../beans/navy
   f  beans/pinto     ../beans/pinto
   f  beans/turtle    ../beans/turtle
 
   $ hg debugwalk -v 'rootfilesin:'
   * matcher:
   <patternmatcher patterns="rootfilesin: ['.']">
   f  fennel      ../fennel
   f  fenugreek   ../fenugreek
   f  fiddlehead  ../fiddlehead
   $ hg debugwalk -v -I 'rootfilesin:'
   * matcher:
   <includematcher includes="rootfilesin: ['.']">
   f  fennel      ../fennel
   f  fenugreek   ../fenugreek
   f  fiddlehead  ../fiddlehead
   $ hg debugwalk -v 'rootfilesin:.'
   * matcher:
   <patternmatcher patterns="rootfilesin: ['.']">
   f  fennel      ../fennel
   f  fenugreek   ../fenugreek
   f  fiddlehead  ../fiddlehead
   $ hg debugwalk -v -I 'rootfilesin:.'
   * matcher:
   <includematcher includes="rootfilesin: ['.']">
   f  fennel      ../fennel
   f  fenugreek   ../fenugreek
   f  fiddlehead  ../fiddlehead
   $ hg debugwalk -v -X 'rootfilesin:'
   * matcher:
   <differencematcher
     m1=<alwaysmatcher>,
     m2=<includematcher includes="rootfilesin: ['.']">>
   f  beans/black                     ../beans/black
   f  beans/borlotti                  ../beans/borlotti
   f  beans/kidney                    ../beans/kidney
   f  beans/navy                      ../beans/navy
   f  beans/pinto                     ../beans/pinto
   f  beans/turtle                    ../beans/turtle
   f  mammals/Procyonidae/cacomistle  Procyonidae/cacomistle
   f  mammals/Procyonidae/coatimundi  Procyonidae/coatimundi
   f  mammals/Procyonidae/raccoon     Procyonidae/raccoon
   f  mammals/skunk                   skunk
   $ hg debugwalk -v 'rootfilesin:fennel'
   * matcher:
   <patternmatcher patterns="rootfilesin: ['fennel']">
   $ hg debugwalk -v -I 'rootfilesin:fennel'
   * matcher:
   <includematcher includes="rootfilesin: ['fennel']">
   $ hg debugwalk -v 'rootfilesin:skunk'
   * matcher:
   <patternmatcher patterns="rootfilesin: ['skunk']">
   $ hg debugwalk -v -I 'rootfilesin:skunk'
   * matcher:
   <includematcher includes="rootfilesin: ['skunk']">
   $ hg debugwalk -v 'rootfilesin:beans'
   * matcher:
   <patternmatcher patterns="rootfilesin: ['beans']">
   f  beans/black     ../beans/black
   f  beans/borlotti  ../beans/borlotti
   f  beans/kidney    ../beans/kidney
   f  beans/navy      ../beans/navy
   f  beans/pinto     ../beans/pinto
   f  beans/turtle    ../beans/turtle
   $ hg debugwalk -v -I 'rootfilesin:beans'
   * matcher:
   <includematcher includes="rootfilesin: ['beans']">
   f  beans/black     ../beans/black
   f  beans/borlotti  ../beans/borlotti
   f  beans/kidney    ../beans/kidney
   f  beans/navy      ../beans/navy
   f  beans/pinto     ../beans/pinto
   f  beans/turtle    ../beans/turtle
   $ hg debugwalk -v 'rootfilesin:mammals'
   * matcher:
   <patternmatcher patterns="rootfilesin: ['mammals']">
   f  mammals/skunk  skunk
   $ hg debugwalk -v -I 'rootfilesin:mammals'
   * matcher:
   <includematcher includes="rootfilesin: ['mammals']">
   f  mammals/skunk  skunk
   $ hg debugwalk -v 'rootfilesin:mammals/'
   * matcher:
   <patternmatcher patterns="rootfilesin: ['mammals']">
   f  mammals/skunk  skunk
   $ hg debugwalk -v -I 'rootfilesin:mammals/'
   * matcher:
   <includematcher includes="rootfilesin: ['mammals']">
   f  mammals/skunk  skunk
   $ hg debugwalk -v -X 'rootfilesin:mammals'
   * matcher:
   <differencematcher
     m1=<alwaysmatcher>,
     m2=<includematcher includes="rootfilesin: ['mammals']">>
   f  beans/black                     ../beans/black
   f  beans/borlotti                  ../beans/borlotti
   f  beans/kidney                    ../beans/kidney
   f  beans/navy                      ../beans/navy
   f  beans/pinto                     ../beans/pinto
   f  beans/turtle                    ../beans/turtle
   f  fennel                          ../fennel
   f  fenugreek                       ../fenugreek
   f  fiddlehead                      ../fiddlehead
   f  mammals/Procyonidae/cacomistle  Procyonidae/cacomistle
   f  mammals/Procyonidae/coatimundi  Procyonidae/coatimundi
   f  mammals/Procyonidae/raccoon     Procyonidae/raccoon
 
   $ hg debugwalk -v .
   * matcher:
   <patternmatcher patterns='mammals(?:/|$)'>
   f  mammals/Procyonidae/cacomistle  Procyonidae/cacomistle
   f  mammals/Procyonidae/coatimundi  Procyonidae/coatimundi
   f  mammals/Procyonidae/raccoon     Procyonidae/raccoon
   f  mammals/skunk                   skunk
   $ hg debugwalk -v -I.
   * matcher:
   <includematcher includes='mammals(?:/|$)'>
   f  mammals/Procyonidae/cacomistle  Procyonidae/cacomistle
   f  mammals/Procyonidae/coatimundi  Procyonidae/coatimundi
   f  mammals/Procyonidae/raccoon     Procyonidae/raccoon
   f  mammals/skunk                   skunk
   $ hg debugwalk -v Procyonidae
   * matcher:
   <patternmatcher patterns='mammals/Procyonidae(?:/|$)'>
   f  mammals/Procyonidae/cacomistle  Procyonidae/cacomistle
   f  mammals/Procyonidae/coatimundi  Procyonidae/coatimundi
   f  mammals/Procyonidae/raccoon     Procyonidae/raccoon
 
   $ cd Procyonidae
   $ hg debugwalk -v .
   * matcher:
   <patternmatcher patterns='mammals/Procyonidae(?:/|$)'>
   f  mammals/Procyonidae/cacomistle  cacomistle
   f  mammals/Procyonidae/coatimundi  coatimundi
   f  mammals/Procyonidae/raccoon     raccoon
   $ hg debugwalk -v ..
   * matcher:
   <patternmatcher patterns='mammals(?:/|$)'>
   f  mammals/Procyonidae/cacomistle  cacomistle
   f  mammals/Procyonidae/coatimundi  coatimundi
   f  mammals/Procyonidae/raccoon     raccoon
   f  mammals/skunk                   ../skunk
   $ cd ..
 
   $ hg debugwalk -v ../beans
   * matcher:
   <patternmatcher patterns='beans(?:/|$)'>
   f  beans/black     ../beans/black
   f  beans/borlotti  ../beans/borlotti
   f  beans/kidney    ../beans/kidney
   f  beans/navy      ../beans/navy
   f  beans/pinto     ../beans/pinto
   f  beans/turtle    ../beans/turtle
   $ hg debugwalk -v .
   * matcher:
   <patternmatcher patterns='mammals(?:/|$)'>
   f  mammals/Procyonidae/cacomistle  Procyonidae/cacomistle
   f  mammals/Procyonidae/coatimundi  Procyonidae/coatimundi
   f  mammals/Procyonidae/raccoon     Procyonidae/raccoon
   f  mammals/skunk                   skunk
   $ hg debugwalk -v .hg
   abort: path 'mammals/.hg' is inside nested repo 'mammals'
   [255]
   $ hg debugwalk -v ../.hg
   abort: path contains illegal component: .hg
   [255]
   $ cd ..
 
   $ hg debugwalk -v -Ibeans
   * matcher:
   <includematcher includes='beans(?:/|$)'>
   f  beans/black     beans/black
   f  beans/borlotti  beans/borlotti
   f  beans/kidney    beans/kidney
   f  beans/navy      beans/navy
   f  beans/pinto     beans/pinto
   f  beans/turtle    beans/turtle
   $ hg debugwalk -v -I '{*,{b,m}*/*}k'
   * matcher:
   <includematcher includes='(?:[^/]*|(?:b|m)[^/]*/[^/]*)k(?:/|$)'>
   f  beans/black    beans/black
   f  fenugreek      fenugreek
   f  mammals/skunk  mammals/skunk
   $ hg debugwalk -v -Ibeans mammals
   * matcher:
   <intersectionmatcher
     m1=<patternmatcher patterns='mammals(?:/|$)'>,
     m2=<includematcher includes='beans(?:/|$)'>>
   $ hg debugwalk -v -Inon-existent
   * matcher:
   <includematcher includes='non\\-existent(?:/|$)'>
   $ hg debugwalk -v -Inon-existent -Ibeans/black
   * matcher:
   <includematcher includes='non\\-existent(?:/|$)|beans/black(?:/|$)'>
   f  beans/black  beans/black
   $ hg debugwalk -v -Ibeans beans/black
   * matcher:
   <intersectionmatcher
     m1=<patternmatcher patterns='beans/black(?:/|$)'>,
     m2=<includematcher includes='beans(?:/|$)'>>
   f  beans/black  beans/black  exact
   $ hg debugwalk -v -Ibeans/black beans
   * matcher:
   <intersectionmatcher
     m1=<patternmatcher patterns='beans(?:/|$)'>,
     m2=<includematcher includes='beans/black(?:/|$)'>>
   f  beans/black  beans/black
   $ hg debugwalk -v -Xbeans/black beans
   * matcher:
   <differencematcher
     m1=<patternmatcher patterns='beans(?:/|$)'>,
     m2=<includematcher includes='beans/black(?:/|$)'>>
   f  beans/borlotti  beans/borlotti
   f  beans/kidney    beans/kidney
   f  beans/navy      beans/navy
   f  beans/pinto     beans/pinto
   f  beans/turtle    beans/turtle
   $ hg debugwalk -v -Xbeans/black -Ibeans
   * matcher:
   <differencematcher
     m1=<includematcher includes='beans(?:/|$)'>,
     m2=<includematcher includes='beans/black(?:/|$)'>>
   f  beans/borlotti  beans/borlotti
   f  beans/kidney    beans/kidney
   f  beans/navy      beans/navy
   f  beans/pinto     beans/pinto
   f  beans/turtle    beans/turtle
   $ hg debugwalk -v -Xbeans/black beans/black
   * matcher:
   <differencematcher
     m1=<patternmatcher patterns='beans/black(?:/|$)'>,
     m2=<includematcher includes='beans/black(?:/|$)'>>
   $ hg debugwalk -v -Xbeans/black -Ibeans/black
   * matcher:
   <differencematcher
     m1=<includematcher includes='beans/black(?:/|$)'>,
     m2=<includematcher includes='beans/black(?:/|$)'>>
   $ hg debugwalk -v -Xbeans beans/black
   * matcher:
   <differencematcher
     m1=<patternmatcher patterns='beans/black(?:/|$)'>,
     m2=<includematcher includes='beans(?:/|$)'>>
   $ hg debugwalk -v -Xbeans -Ibeans/black
   * matcher:
   <differencematcher
     m1=<includematcher includes='beans/black(?:/|$)'>,
     m2=<includematcher includes='beans(?:/|$)'>>
   $ hg debugwalk -v 'glob:mammals/../beans/b*'
   * matcher:
   <patternmatcher patterns='beans/b[^/]*$'>
   f  beans/black     beans/black
   f  beans/borlotti  beans/borlotti
   $ hg debugwalk -v '-X*/Procyonidae' mammals
   * matcher:
   <differencematcher
     m1=<patternmatcher patterns='mammals(?:/|$)'>,
     m2=<includematcher includes='[^/]*/Procyonidae(?:/|$)'>>
   f  mammals/skunk  mammals/skunk
   $ hg debugwalk -v path:mammals
   * matcher:
   <patternmatcher patterns='mammals(?:/|$)'>
   f  mammals/Procyonidae/cacomistle  mammals/Procyonidae/cacomistle
   f  mammals/Procyonidae/coatimundi  mammals/Procyonidae/coatimundi
   f  mammals/Procyonidae/raccoon     mammals/Procyonidae/raccoon
   f  mammals/skunk                   mammals/skunk
   $ hg debugwalk -v ..
   abort: .. not under root '$TESTTMP/t'
   [255]
   $ hg debugwalk -v beans/../..
   abort: beans/../.. not under root '$TESTTMP/t'
   [255]
   $ hg debugwalk -v .hg
   abort: path contains illegal component: .hg
   [255]
   $ hg debugwalk -v beans/../.hg
   abort: path contains illegal component: .hg
   [255]
   $ hg debugwalk -v beans/../.hg/data
   abort: path contains illegal component: .hg/data
   [255]
   $ hg debugwalk -v beans/.hg
   abort: path 'beans/.hg' is inside nested repo 'beans'
   [255]
 
 Test explicit paths and excludes:
 
   $ hg debugwalk -v fennel -X fennel
   * matcher:
   <differencematcher
     m1=<patternmatcher patterns='fennel(?:/|$)'>,
     m2=<includematcher includes='fennel(?:/|$)'>>
   $ hg debugwalk -v fennel -X 'f*'
   * matcher:
   <differencematcher
     m1=<patternmatcher patterns='fennel(?:/|$)'>,
     m2=<includematcher includes='f[^/]*(?:/|$)'>>
   $ hg debugwalk -v beans/black -X 'path:beans'
   * matcher:
   <differencematcher
     m1=<patternmatcher patterns='beans/black(?:/|$)'>,
     m2=<includematcher includes='beans(?:/|$)'>>
   $ hg debugwalk -v -I 'path:beans/black' -X 'path:beans'
   * matcher:
   <differencematcher
     m1=<includematcher includes='beans/black(?:/|$)'>,
     m2=<includematcher includes='beans(?:/|$)'>>
 
 Test absolute paths:
 
   $ hg debugwalk -v `pwd`/beans
   * matcher:
   <patternmatcher patterns='beans(?:/|$)'>
   f  beans/black     beans/black
   f  beans/borlotti  beans/borlotti
   f  beans/kidney    beans/kidney
   f  beans/navy      beans/navy
   f  beans/pinto     beans/pinto
   f  beans/turtle    beans/turtle
   $ hg debugwalk -v `pwd`/..
   abort: $TESTTMP/t/.. not under root '$TESTTMP/t'
   [255]
 
 Test patterns:
 
   $ hg debugwalk -v glob:\*
   * matcher:
   <patternmatcher patterns='[^/]*$'>
   f  fennel      fennel
   f  fenugreek   fenugreek
   f  fiddlehead  fiddlehead
 #if eol-in-paths
   $ echo glob:glob > glob:glob
   $ hg addremove
   adding glob:glob
   warning: filename contains ':', which is reserved on Windows: 'glob:glob'
   $ hg debugwalk -v glob:\*
   * matcher:
   <patternmatcher patterns='[^/]*$'>
   f  fennel      fennel
   f  fenugreek   fenugreek
   f  fiddlehead  fiddlehead
   f  glob:glob   glob:glob
   $ hg debugwalk -v glob:glob
   * matcher:
   <patternmatcher patterns='glob$'>
   glob: $ENOENT$
   $ hg debugwalk -v glob:glob:glob
   * matcher:
   <patternmatcher patterns='glob:glob$'>
   f  glob:glob  glob:glob  exact
   $ hg debugwalk -v path:glob:glob
   * matcher:
   <patternmatcher patterns='glob:glob(?:/|$)'>
   f  glob:glob  glob:glob  exact
   $ rm glob:glob
   $ hg addremove
   removing glob:glob
 #endif
 
   $ hg debugwalk -v 'glob:**e'
   * matcher:
   <patternmatcher patterns='.*e$'>
   f  beans/turtle                    beans/turtle
   f  mammals/Procyonidae/cacomistle  mammals/Procyonidae/cacomistle
 
   $ hg debugwalk -v 're:.*[kb]$'
   * matcher:
   <patternmatcher patterns='.*[kb]$'>
   f  beans/black    beans/black
   f  fenugreek      fenugreek
   f  mammals/skunk  mammals/skunk
 
   $ hg debugwalk -v path:beans/black
   * matcher:
   <patternmatcher patterns='beans/black(?:/|$)'>
   f  beans/black  beans/black  exact
   $ hg debugwalk -v path:beans//black
   * matcher:
   <patternmatcher patterns='beans/black(?:/|$)'>
   f  beans/black  beans/black  exact
 
   $ hg debugwalk -v relglob:Procyonidae
   * matcher:
   <patternmatcher patterns='(?:|.*/)Procyonidae$'>
   $ hg debugwalk -v 'relglob:Procyonidae/**'
   * matcher:
   <patternmatcher patterns='(?:|.*/)Procyonidae/.*$'>
   f  mammals/Procyonidae/cacomistle  mammals/Procyonidae/cacomistle
   f  mammals/Procyonidae/coatimundi  mammals/Procyonidae/coatimundi
   f  mammals/Procyonidae/raccoon     mammals/Procyonidae/raccoon
   $ hg debugwalk -v 'relglob:Procyonidae/**' fennel
   * matcher:
   <patternmatcher patterns='(?:|.*/)Procyonidae/.*$|fennel(?:/|$)'>
   f  fennel                          fennel                          exact
   f  mammals/Procyonidae/cacomistle  mammals/Procyonidae/cacomistle
   f  mammals/Procyonidae/coatimundi  mammals/Procyonidae/coatimundi
   f  mammals/Procyonidae/raccoon     mammals/Procyonidae/raccoon
   $ hg debugwalk -v beans 'glob:beans/*'
   * matcher:
   <patternmatcher patterns='beans(?:/|$)|beans/[^/]*$'>
   f  beans/black     beans/black
   f  beans/borlotti  beans/borlotti
   f  beans/kidney    beans/kidney
   f  beans/navy      beans/navy
   f  beans/pinto     beans/pinto
   f  beans/turtle    beans/turtle
   $ hg debugwalk -v 'glob:mamm**'
   * matcher:
   <patternmatcher patterns='mamm.*$'>
   f  mammals/Procyonidae/cacomistle  mammals/Procyonidae/cacomistle
   f  mammals/Procyonidae/coatimundi  mammals/Procyonidae/coatimundi
   f  mammals/Procyonidae/raccoon     mammals/Procyonidae/raccoon
   f  mammals/skunk                   mammals/skunk
   $ hg debugwalk -v 'glob:mamm**' fennel
   * matcher:
   <patternmatcher patterns='mamm.*$|fennel(?:/|$)'>
   f  fennel                          fennel                          exact
   f  mammals/Procyonidae/cacomistle  mammals/Procyonidae/cacomistle
   f  mammals/Procyonidae/coatimundi  mammals/Procyonidae/coatimundi
   f  mammals/Procyonidae/raccoon     mammals/Procyonidae/raccoon
   f  mammals/skunk                   mammals/skunk
   $ hg debugwalk -v 'glob:j*'
   * matcher:
   <patternmatcher patterns='j[^/]*$'>
   $ hg debugwalk -v NOEXIST
   * matcher:
   <patternmatcher patterns='NOEXIST(?:/|$)'>
   NOEXIST: * (glob)
 
 #if fifo
   $ mkfifo fifo
   $ hg debugwalk -v fifo
   * matcher:
   <patternmatcher patterns='fifo(?:/|$)'>
   fifo: unsupported file type (type is fifo)
 #endif
 
   $ rm fenugreek
   $ hg debugwalk -v fenugreek
   * matcher:
   <patternmatcher patterns='fenugreek(?:/|$)'>
   f  fenugreek  fenugreek  exact
   $ hg rm fenugreek
   $ hg debugwalk -v fenugreek
   * matcher:
   <patternmatcher patterns='fenugreek(?:/|$)'>
   f  fenugreek  fenugreek  exact
   $ touch new
   $ hg debugwalk -v new
   * matcher:
   <patternmatcher patterns='new(?:/|$)'>
   f  new  new  exact
 
   $ mkdir ignored
   $ touch ignored/file
   $ echo '^ignored$' > .hgignore
   $ hg debugwalk -v ignored
   * matcher:
   <patternmatcher patterns='ignored(?:/|$)'>
   $ hg debugwalk -v ignored/file
   * matcher:
   <patternmatcher patterns='ignored/file(?:/|$)'>
   f  ignored/file  ignored/file  exact
 
 Test listfile and listfile0
 
   $ "$PYTHON" -c "open('listfile0', 'wb').write(b'fenugreek\0new\0')"
   $ hg debugwalk -v -I 'listfile0:listfile0'
   * matcher:
   <includematcher includes='fenugreek(?:/|$)|new(?:/|$)'>
   f  fenugreek  fenugreek
   f  new        new
   $ "$PYTHON" -c "open('listfile', 'wb').write(b'fenugreek\nnew\r\nmammals/skunk\n')"
   $ hg debugwalk -v -I 'listfile:listfile'
   * matcher:
   <includematcher includes='fenugreek(?:/|$)|new(?:/|$)|mammals/skunk(?:/|$)'>
   f  fenugreek      fenugreek
   f  mammals/skunk  mammals/skunk
   f  new            new
 
   $ cd ..
   $ hg debugwalk -v -R t t/mammals/skunk
   * matcher:
   <patternmatcher patterns='mammals/skunk(?:/|$)'>
   f  mammals/skunk  t/mammals/skunk  exact
   $ mkdir t2
   $ cd t2
   $ hg debugwalk -v -R ../t ../t/mammals/skunk
   * matcher:
   <patternmatcher patterns='mammals/skunk(?:/|$)'>
   f  mammals/skunk  ../t/mammals/skunk  exact
   $ hg debugwalk -v --cwd ../t mammals/skunk
   * matcher:
   <patternmatcher patterns='mammals/skunk(?:/|$)'>
   f  mammals/skunk  mammals/skunk  exact
 
   $ cd ..
 
 Test split patterns on overflow
 
   $ cd t
   $ echo fennel > overflow.list
   $ cat >> printnum.py <<EOF
   > from __future__ import print_function
   > for i in range(20000 // 100):
   >   print('x' * 100)
   > EOF
   $ "$PYTHON" printnum.py >> overflow.list
   $ echo fenugreek >> overflow.list
   $ hg debugwalk 'listfile:overflow.list' 2>&1 | egrep -v '^xxx'
   f  fennel     fennel     exact
   f  fenugreek  fenugreek  exact
   $ cd ..