match: don't print explicitly listed files with wrong case (BC)

On case-insensitive file systems, if file A exists and you try to
remove it (or add, etc.) by specifying a different case, you will see
something like this:

  $ hg rm a
  removing file A

I honestly found this surprising because it seems to me like it was
explicitly listed by the user. Still, there is a comment in the code
describing it, so it is very clearly intentional. The code was added
in baa11dde8c0e (match: add a subclass for dirstate normalizing of the
matched patterns, 2015-04-12).

I'm going to do a lot of refactoring to matchers and the feature
mentioned above is going to get in my way. I'm therefore removing it
for the time being and we can hopefully add it back when I'm done.

mercurial/match.py

@@ -1,816 +1,808 b''
 # 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
 
 import copy
 import os
 import re
 
 from .i18n import _
 from . import (
     error,
     pathutil,
     util,
 )
 
 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, listsubrepos):
     '''Returns the kindpats list with the 'set' patterns expanded.'''
     fset = set()
     other = []
 
     for kind, pat, source in kindpats:
         if kind == 'set':
             if not ctx:
                 raise error.Abort(_("fileset expression with no context"))
             s = ctx.getfileset(pat)
             fset.update(s)
 
             if listsubrepos:
                 for subpath in ctx.substate:
                     s = ctx.sub(subpath).getfileset(pat)
                     fset.update(subpath + '/' + f for f in s)
 
             continue
         other.append((kind, pat, source))
     return fset, 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 match(root, cwd, patterns, include=None, exclude=None, default='glob',
           exact=False, auditor=None, ctx=None, listsubrepos=False, warn=None,
           badfn=None):
     """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
     exact - patterns are actually filenames (include/exclude still apply)
     warn - optional function used for printing warnings
     badfn - optional bad() callback for this matcher instead of the default
 
     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
     """
     return matcher(root, cwd, patterns, include=include, exclude=exclude,
                    default=default, exact=exact, auditor=auditor, ctx=ctx,
                    listsubrepos=listsubrepos, warn=warn, badfn=badfn)
 
 def icasefsmatch(root, cwd, patterns, include=None, exclude=None,
                  default='glob', auditor=None, ctx=None,
                  listsubrepos=False, badfn=None):
     """A matcher for wdir on case insensitive filesystems, which normalizes the
     given patterns to the case in the filesystem.
     """
     return icasefsmatcher(root, cwd, patterns, include=include, exclude=exclude,
                           default=default, auditor=auditor, ctx=ctx,
                           listsubrepos=listsubrepos, badfn=badfn)
 
 def exact(root, cwd, files, badfn=None):
     return match(root, cwd, files, exact=True, badfn=badfn)
 
 def always(root, cwd):
     return match(root, cwd, [])
 
 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, warn):
     '''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 ('glob', 'relpath'):
             pat = pathutil.canonpath(root, cwd, pat, auditor)
         elif kind in ('relglob', 'path', 'rootfilesin'):
             pat = util.normpath(pat)
         elif kind in ('listfile', 'listfile0'):
             try:
                 files = util.readfile(pat)
                 if kind == 'listfile0':
                     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, inst.strerror))
             continue
         # else: re or relre - which cannot be normalized
         kindpats.append((kind, pat, ''))
     return kindpats
 
 class matcher(object):
 
     def __init__(self, root, cwd, patterns, include=None, exclude=None,
                  default='glob', exact=False, auditor=None, ctx=None,
                  listsubrepos=False, warn=None, badfn=None):
         if include is None:
             include = []
         if exclude is None:
             exclude = []
 
         self._root = root
         self._cwd = cwd
         self._files = [] # exact files and roots of patterns
         self._anypats = bool(include or exclude)
         self._always = False
         self._pathrestricted = bool(include or exclude or patterns)
 
         # roots are directories which are recursively included/excluded.
         self._includeroots = set()
         self._excluderoots = set()
         # dirs are directories which are non-recursively included.
         self._includedirs = set()
 
         if badfn is not None:
             self.bad = badfn
 
         matchfns = []
         if include:
             kindpats = self._normalize(include, 'glob', root, cwd, auditor,
                                        warn)
             self.includepat, im = _buildmatch(ctx, kindpats, '(?:/|$)',
                                               listsubrepos, root)
             roots, dirs = _rootsanddirs(kindpats)
             self._includeroots.update(roots)
             self._includedirs.update(dirs)
             matchfns.append(im)
         if exclude:
             kindpats = self._normalize(exclude, 'glob', root, cwd, auditor,
                                        warn)
             self.excludepat, em = _buildmatch(ctx, kindpats, '(?:/|$)',
                                               listsubrepos, root)
             if not _anypats(kindpats):
                 # Only consider recursive excludes as such - if a non-recursive
                 # exclude is used, we must still recurse into the excluded
                 # directory, at least to find subdirectories. In such a case,
                 # the regex still won't match the non-recursively-excluded
                 # files.
                 self._excluderoots.update(_roots(kindpats))
             matchfns.append(lambda f: not em(f))
         if exact:
             if isinstance(patterns, list):
                 self._files = patterns
             else:
                 self._files = list(patterns)
             matchfns.append(self.exact)
         elif patterns:
             kindpats = self._normalize(patterns, default, root, cwd, auditor,
                                        warn)
             if not _kindpatsalwaysmatch(kindpats):
                 self._files = _explicitfiles(kindpats)
                 self._anypats = self._anypats or _anypats(kindpats)
                 self.patternspat, pm = _buildmatch(ctx, kindpats, '$',
                                                    listsubrepos, root)
                 matchfns.append(pm)
 
         if not matchfns:
             m = util.always
             self._always = True
         elif len(matchfns) == 1:
             m = matchfns[0]
         else:
             def m(f):
                 for matchfn in matchfns:
                     if not matchfn(f):
                         return False
                 return True
 
         self.matchfn = m
 
     def __call__(self, fn):
         return self.matchfn(fn)
     def __iter__(self):
         for f in self._files:
             yield f
 
     # 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.'''
         pass
 
     # 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
 
     def abs(self, f):
         '''Convert a repo path back to path that is relative to the root of the
         matcher.'''
         return f
 
     def rel(self, f):
         '''Convert repo path back to path that is relative to cwd of matcher.'''
         return util.pathto(self._root, self._cwd, f)
 
     def uipath(self, f):
         '''Convert repo path to a display path.  If patterns or -I/-X were used
         to create this matcher, the display path will be relative to cwd.
         Otherwise it is relative to the root of the repo.'''
         return (self._pathrestricted and self.rel(f)) or self.abs(f)
 
     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)
 
     @propertycache
     def _dirs(self):
         return set(util.dirs(self._fileset)) | {'.'}
 
     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.
 
         This function's behavior is undefined if it has returned False for
         one of the dir's parent directories.
         '''
         if self.prefix() and dir in self._fileset:
             return 'all'
         if dir in self._excluderoots:
             return False
         if ((self._includeroots or self._includedirs) and
             '.' not in self._includeroots and
             dir not in self._includeroots and
             dir not in self._includedirs and
             not any(parent in self._includeroots
                     for parent in util.finddirs(dir))):
             return False
         return (not self._fileset or
                 '.' in self._fileset or
                 dir in self._fileset or
                 dir in self._dirs or
                 any(parentdir in self._fileset
                     for parentdir in util.finddirs(dir)))
 
     def exact(self, f):
         '''Returns True if f is in .files().'''
         return f in self._fileset
 
     def anypats(self):
         '''Matcher uses patterns or include/exclude.'''
         return self._anypats
 
     def always(self):
         '''Matcher will match everything and .files() will be empty
         - optimization might be possible and necessary.'''
         return self._always
 
     def isexact(self):
         return self.matchfn == self.exact
 
     def prefix(self):
         return not self.always() and not self.isexact() and not self.anypats()
 
     def _normalize(self, patterns, default, root, cwd, auditor, warn):
         return _donormalize(patterns, default, root, cwd, auditor, warn)
 
 class subdirmatcher(matcher):
     """Adapt a matcher to work on a subdirectory only.
 
     The paths are remapped to remove/insert the path as needed:
 
     >>> m1 = match('root', '', ['a.txt', 'sub/b.txt'])
     >>> m2 = subdirmatcher('sub', m1)
     >>> bool(m2('a.txt'))
     False
     >>> bool(m2('b.txt'))
     True
     >>> bool(m2.matchfn('a.txt'))
     False
     >>> bool(m2.matchfn('b.txt'))
     True
     >>> m2.files()
     ['b.txt']
     >>> m2.exact('b.txt')
     True
     >>> util.pconvert(m2.rel('b.txt'))
     'sub/b.txt'
     >>> def bad(f, msg):
     ...     print "%s: %s" % (f, msg)
     >>> m1.bad = bad
     >>> m2.bad('x.txt', 'No such file')
     sub/x.txt: No such file
     >>> m2.abs('c.txt')
     'sub/c.txt'
     """
 
     def __init__(self, path, matcher):
         self._root = matcher._root
         self._cwd = matcher._cwd
         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)
 
         self._anypats = matcher._anypats
         # 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.
         self.matchfn = lambda fn: matcher.matchfn(self._path + "/" + fn)
 
     def bad(self, f, msg):
         self._matcher.bad(self._path + "/" + f, msg)
 
     def abs(self, f):
         return self._matcher.abs(self._path + "/" + f)
 
     def rel(self, f):
         return self._matcher.rel(self._path + "/" + f)
 
     def uipath(self, f):
         return self._matcher.uipath(self._path + "/" + f)
 
     def visitdir(self, dir):
         if dir == '.':
             dir = self._path
         else:
             dir = self._path + "/" + dir
         return self._matcher.visitdir(dir)
 
 class icasefsmatcher(matcher):
 
     def __init__(self, root, cwd, patterns, include, exclude, default, auditor,
                  ctx, listsubrepos=False, badfn=None):
         init = super(icasefsmatcher, self).__init__
         self._dirstate = ctx.repo().dirstate
         self._dsnormalize = self._dirstate.normalize
 
         init(root, cwd, patterns, include, exclude, default, auditor=auditor,
              ctx=ctx, listsubrepos=listsubrepos, badfn=badfn)
 
-        # m.exact(file) must be based off of the actual user input, otherwise
-        # inexact case matches are treated as exact, and not noted without -v.
-        if self._files:
-            roots, dirs = _rootsanddirs(self._kp)
-            self._fileset = set(roots)
-            self._fileset.update(dirs)
-
     def _normalize(self, patterns, default, root, cwd, auditor, warn):
-        self._kp = super(icasefsmatcher, self)._normalize(patterns, default,
-                                                          root, cwd, auditor,
-                                                          warn)
+        kp = super(icasefsmatcher, self)._normalize(patterns, default, root,
+                                                    cwd, auditor, warn)
         kindpats = []
-        for kind, pats, source in self._kp:
+        for kind, pats, source in kp:
             if kind not in ('re', 'relre'):  # regex can't be normalized
                 p = pats
                 pats = self._dsnormalize(pats)
 
                 # Preserve the original to handle a case only rename.
                 if p != pats and p in self._dirstate:
                     kindpats.append((kind, p, source))
 
             kindpats.append((kind, pats, source))
         return kindpats
 
 def patkind(pattern, default=None):
     '''If pattern is 'kind:pat' with a known kind, return kind.'''
     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 ('re', 'glob', 'path', 'relglob', 'relpath', 'relre',
                     'listfile', 'listfile0', 'set', 'include', 'subinclude',
                     'rootfilesin'):
             return kind, pat
     return default, pattern
 
 def _globre(pat):
     r'''Convert an extended glob string to a regexp string.
 
     >>> print _globre(r'?')
     .
     >>> print _globre(r'*')
     [^/]*
     >>> print _globre(r'**')
     .*
     >>> print _globre(r'**/a')
     (?:.*/)?a
     >>> print _globre(r'a/**/b')
     a\/(?:.*/)?b
     >>> print _globre(r'[a*?!^][^b][!c]')
     [a*?!^][\^b][^c]
     >>> print _globre(r'{a,b}')
     (?:a|b)
     >>> print _globre(r'.\*\?')
     \.\*\?
     '''
     i, n = 0, len(pat)
     res = ''
     group = 0
     escape = util.re.escape
     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)
         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)
             else:
                 res += escape(c)
         else:
             res += escape(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 not pat:
         return ''
     if kind == 're':
         return pat
     if kind == 'path':
         if pat == '.':
             return ''
         return '^' + util.re.escape(pat) + '(?:/|$)'
     if kind == 'rootfilesin':
         if pat == '.':
             escaped = ''
         else:
             # Pattern is a directory name.
             escaped = util.re.escape(pat) + '/'
         # Anything after the pattern must be a non-directory.
         return '^' + escaped + '[^/]+$'
     if kind == 'relglob':
         return '(?:|.*/)' + _globre(pat) + globsuffix
     if kind == 'relpath':
         return util.re.escape(pat) + '(?:/|$)'
     if kind == 'relre':
         if pat.startswith('^'):
             return pat
         return '.*' + pat
     return _globre(pat) + globsuffix
 
 def _buildmatch(ctx, kindpats, globsuffix, listsubrepos, 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)
 
     fset, kindpats = _expandsets(kindpats, ctx, listsubrepos)
     if fset:
         matchfuncs.append(fset.__contains__)
 
     regex = ''
     if kindpats:
         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)
 
 def _buildregexmatch(kindpats, globsuffix):
     """Build a match function from a list of kinds and kindpats,
     return regexp string and a matcher function."""
     try:
         regex = '(?:%s)' % '|'.join([_regex(k, p, globsuffix)
                                      for (k, p, s) in kindpats])
         if len(regex) > 20000:
             raise OverflowError
         return regex, _rematcher(regex)
     except OverflowError:
         # We're using a Python with a tiny regex engine and we
         # made it explode, so we'll divide the pattern list in two
         # until it works
         l = len(kindpats)
         if l < 2:
             raise
         regexa, a = _buildregexmatch(kindpats[:l//2], globsuffix)
         regexb, b = _buildregexmatch(kindpats[l//2:], globsuffix)
         return regex, lambda s: a(s) or b(s)
     except re.error:
         for k, p, s in kindpats:
             try:
                 _rematcher('(?:%s)' % _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 == 'glob': # find the non-glob prefix
             root = []
             for p in pat.split('/'):
                 if '[' in p or '{' in p or '*' in p or '?' in p:
                     break
                 root.append(p)
             r.append('/'.join(root) or '.')
         elif kind in ('relpath', 'path'):
             r.append(pat or '.')
         elif kind in ('rootfilesin',):
             d.append(pat or '.')
         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 _rootsanddirs(kindpats):
     '''Returns roots and exact directories from patterns.
 
     roots are directories to match recursively, whereas exact directories should
     be matched non-recursively. The returned (roots, dirs) tuple will also
     include directories that need to be implicitly considered as either, such as
     parent directories.
 
     >>> _rootsanddirs(\
         [('glob', 'g/h/*', ''), ('glob', 'g/h', ''), ('glob', 'g*', '')])
     (['g/h', 'g/h', '.'], ['g', '.'])
     >>> _rootsanddirs(\
         [('rootfilesin', 'g/h', ''), ('rootfilesin', '', '')])
     ([], ['g/h', '.', 'g', '.'])
     >>> _rootsanddirs(\
         [('relpath', 'r', ''), ('path', 'p/p', ''), ('path', '', '')])
     (['r', 'p/p', '.'], ['p', '.'])
     >>> _rootsanddirs(\
         [('relglob', 'rg*', ''), ('re', 're/', ''), ('relre', 'rr', '')])
     (['.', '.', '.'], ['.'])
     '''
     r, d = _patternrootsanddirs(kindpats)
 
     # Append the parents as non-recursive/exact directories, since they must be
     # scanned to get to either the roots or the other exact directories.
     d.extend(util.dirs(d))
     d.extend(util.dirs(r))
     # util.dirs() does not include the root directory, so add it manually
     d.append('.')
 
     return r, d
 
 def _explicitfiles(kindpats):
     '''Returns the potential explicit filenames from the patterns.
 
     >>> _explicitfiles([('path', 'foo/bar', '')])
     ['foo/bar']
     >>> _explicitfiles([('rootfilesin', 'foo/bar', '')])
     []
     '''
     # 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 _anypats(kindpats):
     for kind, pat, source in kindpats:
         if kind in ('glob', 're', 'relglob', 'relre', 'set', 'rootfilesin'):
             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
     pattern        # pattern of the current default type
 
     if sourceinfo is set, returns a list of tuples:
     (pattern, lineno, originalline). This is useful to debug ignore patterns.
     '''
 
     syntaxes = {'re': 'relre:', 'regexp': 'relre:', 'glob': 'relglob:',
                 'include': 'include', 'subinclude': 'subinclude'}
     syntax = 'relre:'
     patterns = []
 
     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

tests/test-add.t

@@ -1,248 +1,246 b''
   $ hg init a
   $ cd a
   $ echo a > a
   $ hg add -n
   adding a
   $ hg st
   ? a
   $ hg add
   adding a
   $ hg st
   A a
   $ hg forget a
   $ hg add
   adding a
   $ hg st
   A a
 
   $ echo b > b
   $ hg add -n b
   $ hg st
   A a
   ? b
   $ hg add b
   $ hg st
   A a
   A b
 
 should fail
 
   $ hg add b
   b already tracked!
   $ hg st
   A a
   A b
 
 #if no-windows
   $ echo foo > con.xml
   $ hg --config ui.portablefilenames=jump add con.xml
   abort: ui.portablefilenames value is invalid ('jump')
   [255]
   $ hg --config ui.portablefilenames=abort add con.xml
   abort: filename contains 'con', which is reserved on Windows: 'con.xml'
   [255]
   $ hg st
   A a
   A b
   ? con.xml
   $ hg add con.xml
   warning: filename contains 'con', which is reserved on Windows: 'con.xml'
   $ hg st
   A a
   A b
   A con.xml
   $ hg forget con.xml
   $ rm con.xml
 #endif
 
 #if eol-in-paths
   $ echo bla > 'hello:world'
   $ hg --config ui.portablefilenames=abort add
   adding hello:world
   abort: filename contains ':', which is reserved on Windows: 'hello:world'
   [255]
   $ hg st
   A a
   A b
   ? hello:world
   $ hg --config ui.portablefilenames=ignore add
   adding hello:world
   $ hg st
   A a
   A b
   A hello:world
 #endif
 
   $ hg ci -m 0 --traceback
 
   $ hg log -r "heads(. or wdir() & file('**'))"
   changeset:   0:* (glob)
   tag:         tip
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     0
   
 should fail
 
   $ hg add a
   a already tracked!
 
   $ echo aa > a
   $ hg ci -m 1
   $ hg up 0
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ echo aaa > a
   $ hg ci -m 2
   created new head
 
   $ hg merge
   merging a
   warning: conflicts while merging a! (edit, then use 'hg resolve --mark')
   0 files updated, 0 files merged, 0 files removed, 1 files unresolved
   use 'hg resolve' to retry unresolved file merges or 'hg update -C .' to abandon
   [1]
   $ hg st
   M a
   ? a.orig
 
 wdir doesn't cause a crash, and can be dynamically selected if dirty
 
   $ hg log -r "heads(. or wdir() & file('**'))"
   changeset:   2147483647:ffffffffffff
   parent:      2:* (glob)
   parent:      1:* (glob)
   user:        test
   date:        * (glob)
   
 should fail
 
   $ hg add a
   a already tracked!
   $ hg st
   M a
   ? a.orig
   $ hg resolve -m a
   (no more unresolved files)
   $ hg ci -m merge
 
 Issue683: peculiarity with hg revert of an removed then added file
 
   $ hg forget a
   $ hg add a
   $ hg st
   ? a.orig
   $ hg rm a
   $ hg st
   R a
   ? a.orig
   $ echo a > a
   $ hg add a
   $ hg st
   M a
   ? a.orig
 
 Forgotten file can be added back (as either clean or modified)
 
   $ hg forget b
   $ hg add b
   $ hg st -A b
   C b
   $ hg forget b
   $ echo modified > b
   $ hg add b
   $ hg st -A b
   M b
   $ hg revert -qC b
 
   $ hg add c && echo "unexpected addition of missing file"
   c: * (glob)
   [1]
   $ echo c > c
   $ hg add d c && echo "unexpected addition of missing file"
   d: * (glob)
   [1]
   $ hg st
   M a
   A c
   ? a.orig
   $ hg up -C
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
 forget and get should have the right order: added but missing dir should be
 forgotten before file with same name is added
 
   $ echo file d > d
   $ hg add d
   $ hg ci -md
   $ hg rm d
   $ mkdir d
   $ echo a > d/a
   $ hg add d/a
   $ rm -r d
   $ hg up -C
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ cat d
   file d
 
 Test that adding a directory doesn't require case matching (issue4578)
 #if icasefs
   $ mkdir -p CapsDir1/CapsDir
   $ echo abc > CapsDir1/CapsDir/AbC.txt
   $ mkdir CapsDir1/CapsDir/SubDir
   $ echo def > CapsDir1/CapsDir/SubDir/Def.txt
 
   $ hg add capsdir1/capsdir
   adding CapsDir1/CapsDir/AbC.txt (glob)
   adding CapsDir1/CapsDir/SubDir/Def.txt (glob)
 
   $ hg forget capsdir1/capsdir/abc.txt
-  removing CapsDir1/CapsDir/AbC.txt (glob)
 
   $ hg forget capsdir1/capsdir
   removing CapsDir1/CapsDir/SubDir/Def.txt (glob)
 
   $ hg add capsdir1
   adding CapsDir1/CapsDir/AbC.txt (glob)
   adding CapsDir1/CapsDir/SubDir/Def.txt (glob)
 
   $ hg ci -m "AbCDef" capsdir1/capsdir
 
   $ hg status -A capsdir1/capsdir
   C CapsDir1/CapsDir/AbC.txt
   C CapsDir1/CapsDir/SubDir/Def.txt
 
   $ hg files capsdir1/capsdir
   CapsDir1/CapsDir/AbC.txt (glob)
   CapsDir1/CapsDir/SubDir/Def.txt (glob)
 
   $ echo xyz > CapsDir1/CapsDir/SubDir/Def.txt
   $ hg ci -m xyz capsdir1/capsdir/subdir/def.txt
 
   $ hg revert -r '.^' capsdir1/capsdir
   reverting CapsDir1/CapsDir/SubDir/Def.txt (glob)
 
 The conditional tests above mean the hash on the diff line differs on Windows
 and OS X
   $ hg diff capsdir1/capsdir
   diff -r * CapsDir1/CapsDir/SubDir/Def.txt (glob)
   --- a/CapsDir1/CapsDir/SubDir/Def.txt	Thu Jan 01 00:00:00 1970 +0000
   +++ b/CapsDir1/CapsDir/SubDir/Def.txt	* (glob)
   @@ -1,1 +1,1 @@
   -xyz
   +def
 
   $ hg mv CapsDir1/CapsDir/abc.txt CapsDir1/CapsDir/ABC.txt
-  moving CapsDir1/CapsDir/AbC.txt to CapsDir1/CapsDir/ABC.txt (glob)
   $ hg ci -m "case changing rename" CapsDir1/CapsDir/AbC.txt CapsDir1/CapsDir/ABC.txt
 
   $ hg status -A capsdir1/capsdir
   M CapsDir1/CapsDir/SubDir/Def.txt
   C CapsDir1/CapsDir/ABC.txt
 
   $ hg remove -f 'glob:**.txt' -X capsdir1/capsdir
   $ hg remove -f 'glob:**.txt' -I capsdir1/capsdir
   removing CapsDir1/CapsDir/ABC.txt (glob)
   removing CapsDir1/CapsDir/SubDir/Def.txt (glob)
 #endif
 
   $ cd ..

tests/test-casefolding.t

@@ -1,259 +1,256 b''
 #require icasefs
 
   $ hg debugfs | grep 'case-sensitive:'
   case-sensitive: no
 
 test file addition with bad case
 
   $ hg init repo1
   $ cd repo1
   $ echo a > a
   $ hg add A
-  adding a
   $ hg st
   A a
   $ hg ci -m adda
   $ hg manifest
   a
   $ cd ..
 
 test case collision on rename (issue750)
 
   $ hg init repo2
   $ cd repo2
   $ echo a > a
   $ hg --debug ci -Am adda
   adding a
   committing files:
   a
   committing manifest
   committing changelog
   updating the branch cache
   committed changeset 0:07f4944404050f47db2e5c5071e0e84e7a27bba9
 
 Case-changing renames should work:
 
   $ hg mv a A
   $ hg mv A a
   $ hg st
 
 addremove after case-changing rename has no effect (issue4590)
 
   $ hg mv a A
   $ hg addremove
   recording removal of a as rename to A (100% similar)
   $ hg revert --all
   forgetting A
   undeleting a
 
 test changing case of path components
 
   $ mkdir D
   $ echo b > D/b
   $ hg ci -Am addb D/b
   $ hg mv D/b d/b
   D/b: not overwriting - file already committed
   (hg rename --force to replace the file by recording a rename)
   $ hg mv D/b d/c
   $ hg st
   A D/c
   R D/b
   $ mv D temp
   $ mv temp d
   $ hg st
   A D/c
   R D/b
   $ hg revert -aq
   $ rm d/c
   $ echo c > D/c
   $ hg add D/c
   $ hg st
   A D/c
   $ hg ci -m addc D/c
   $ hg mv d/b d/e
-  moving D/b to D/e (glob)
   $ hg st
   A D/e
   R D/b
   $ hg revert -aq
   $ rm d/e
   $ hg mv d/b D/B
-  moving D/b to D/B (glob)
   $ hg st
   A D/B
   R D/b
   $ cd ..
 
 test case collision between revisions (issue912)
 
   $ hg init repo3
   $ cd repo3
   $ echo a > a
   $ hg ci -Am adda
   adding a
   $ hg rm a
   $ hg ci -Am removea
   $ echo A > A
 
 on linux hfs keeps the old case stored, force it
 
   $ mv a aa
   $ mv aa A
   $ hg ci -Am addA
   adding A
 
 used to fail under case insensitive fs
 
   $ hg up -C 0
   1 files updated, 0 files merged, 1 files removed, 0 files unresolved
   $ hg up -C
   1 files updated, 0 files merged, 1 files removed, 0 files unresolved
 
 no clobbering of untracked files with wrong casing
 
   $ hg up -r null
   0 files updated, 0 files merged, 1 files removed, 0 files unresolved
   $ echo gold > a
   $ hg up
   A: untracked file differs
   abort: untracked files in working directory differ from files in requested revision
   [255]
   $ cat a
   gold
   $ rm a
 
 test that normal file in different case on target context is not
 unlinked by largefiles extension.
 
   $ cat >> .hg/hgrc <<EOF
   > [extensions]
   > largefiles=
   > EOF
   $ hg update -q -C 1
   $ hg status -A
   $ echo 'A as largefiles' > A
   $ hg add --large A
   $ hg commit -m '#3'
   created new head
   $ hg manifest -r 3
   .hglf/A
   $ hg manifest -r 0
   a
   $ hg update -q -C 0
   $ hg status -A
   C a
   $ hg update -q -C 3
   $ hg update -q 0
 
   $ hg up -C -r 2
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ hg mv A a
   $ hg diff -g > rename.diff
   $ hg ci -m 'A -> a'
   $ hg up -q '.^'
   $ hg import rename.diff -m "import rename A -> a"
   applying rename.diff
   $ hg st
   ? rename.diff
   $ hg files
   a
   $ find * | sort
   a
   rename.diff
 
   $ rm rename.diff
 
   $ cd ..
 
 issue 3342: file in nested directory causes unexpected abort
 
   $ hg init issue3342
   $ cd issue3342
 
   $ mkdir -p a/B/c/D
   $ echo e > a/B/c/D/e
   $ hg add a/B/c/D/e
   $ hg ci -m 'add e'
 
 issue 4481: revert across case only renames
   $ hg mv a/B/c/D/e a/B/c/d/E
   $ hg ci -m "uppercase E"
   $ echo 'foo' > a/B/c/D/E
   $ hg ci -m 'e content change'
   $ hg revert --all -r 0
   removing a/B/c/D/E (glob)
   adding a/B/c/D/e (glob)
   $ find * | sort
   a
   a/B
   a/B/c
   a/B/c/D
   a/B/c/D/e
   a/B/c/D/e.orig
 
   $ cd ..
 
 issue 3340: mq does not handle case changes correctly
 
 in addition to reported case, 'hg qrefresh' is also tested against
 case changes.
 
   $ echo "[extensions]" >> $HGRCPATH
   $ echo "mq=" >> $HGRCPATH
 
   $ hg init issue3340
   $ cd issue3340
 
   $ echo a > mIxEdCaSe
   $ hg add mIxEdCaSe
   $ hg commit -m '#0'
   $ hg rename mIxEdCaSe tmp
   $ hg rename tmp MiXeDcAsE
   $ hg status -A
   A MiXeDcAsE
     mIxEdCaSe
   R mIxEdCaSe
   $ hg qnew changecase
   $ hg status -A
   C MiXeDcAsE
 
   $ hg qpop -a
   popping changecase
   patch queue now empty
   $ hg qnew refresh-casechange
   $ hg status -A
   C mIxEdCaSe
   $ hg rename mIxEdCaSe tmp
   $ hg rename tmp MiXeDcAsE
   $ hg status -A
   A MiXeDcAsE
     mIxEdCaSe
   R mIxEdCaSe
   $ hg qrefresh
   $ hg status -A
   C MiXeDcAsE
 
   $ hg qpop -a
   popping refresh-casechange
   patch queue now empty
   $ hg qnew refresh-pattern
   $ hg status
   $ echo A > A
   $ hg add
   adding A
   $ hg qrefresh a # issue 3271, qrefresh with file handled case wrong
   $ hg status # empty status means the qrefresh worked
 
 #if osx
 
 We assume anyone running the tests on a case-insensitive volume on OS
 X will be using HFS+. If that's not true, this test will fail.
 
   $ rm A
   >>> open(u'a\u200c'.encode('utf-8'), 'w').write('unicode is fun')
   $ hg status
   M A
 
 #endif
 
   $ cd ..