comparison mercurial/match.py @ 25213:08a8e9da0ae7

match: add source to kindpats list

Future patches will be adding the ability to recursively include pattern files
in a match rule expression. Part of that behavior will require tracking which
file each pattern came from so we can report errors correctly.

Let's add a 'source' arg to the kindpats list to track this. Initially it will
only be populated by listfile rules.

25212:a39c35e8e559

def _expandsets(kindpats, ctx, listsubrepos):
    '''Returns the kindpats list with the 'set' patterns expanded.'''
    fset = set()
    other = []

    for kind, pat in kindpats:
        if kind == 'set':
            if not ctx:
                raise util.Abort("fileset expression with no context")
            s = ctx.getfileset(pat)
            fset.update(s)

                for subpath in ctx.substate:
                    s = ctx.sub(subpath).getfileset(pat)
                    fset.update(subpath + '/' + f for f in s)

            continue
        other.append((kind, pat))
    return fset, other

def _kindpatsalwaysmatch(kindpats):
    """"Checks whether the kindspats match everything, as e.g.
    'relpath:.' does.
    """
    for kind, pat in kindpats:
        if pat != '' or kind not in ['relpath', 'glob']:
            return False
    return True

class match(object):

                    else:
                        files = files.splitlines()
                    files = [f for f in files if f]
                except EnvironmentError:
                    raise util.Abort(_("unable to read file list (%s)") % pat)
                kindpats += self._normalize(files, default, root, cwd, auditor)
                continue
            # else: re or relre - which cannot be normalized
            kindpats.append((kind, pat))
        return kindpats

def exact(root, cwd, files):
    return match(root, cwd, files, exact=True)

    def _normalize(self, patterns, default, root, cwd, auditor):
        self._kp = super(icasefsmatcher, self)._normalize(patterns, default,
                                                          root, cwd, auditor)
        kindpats = []
        for kind, pats in self._kp:
            if kind not in ('re', 'relre'):  # regex can't be normalized
                pats = self._dsnormalize(pats)
            kindpats.append((kind, pats))
        return kindpats

def patkind(pattern, default=None):
    '''If pattern is 'kind:pat' with a known kind, return kind.'''
    return _patsplit(pattern, default)[0]

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) 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

            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 in kindpats:
            try:
                _rematcher('(?:%s)' % _regex(k, p, globsuffix))
            except re.error:
                raise util.Abort(_("invalid pattern (%s): %s") % (k, p))
        raise util.Abort(_("invalid pattern"))

def _roots(kindpats):
    '''return roots and exact explicitly listed files from patterns

    >>> _roots([('glob', 'g/*'), ('glob', 'g'), ('glob', 'g*')])
    ['g', 'g', '.']
    >>> _roots([('relpath', 'r'), ('path', 'p/p'), ('path', '')])
    ['r', 'p/p', '.']
    >>> _roots([('relglob', 'rg*'), ('re', 're/'), ('relre', 'rr')])
    ['.', '.', '.']
    '''
    r = []
    for kind, pat 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

        else: # relglob, re, relre
            r.append('.')
    return r

def _anypats(kindpats):
    for kind, pat in kindpats:
        if kind in ('glob', 're', 'relglob', 'relre', 'set'):
            return True

_commentre = None

25213:08a8e9da0ae7

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 util.Abort("fileset expression with no context")
            s = ctx.getfileset(pat)
            fset.update(s)

                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 _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

class match(object):

                    else:
                        files = files.splitlines()
                    files = [f for f in files if f]
                except EnvironmentError:
                    raise util.Abort(_("unable to read file list (%s)") % pat)
                for k, p, source in self._normalize(files, default, root, cwd,
                                                    auditor):
                    kindpats.append((k, p, pat))
                continue
            # else: re or relre - which cannot be normalized
            kindpats.append((kind, pat, ''))
        return kindpats

def exact(root, cwd, files):
    return match(root, cwd, files, exact=True)

    def _normalize(self, patterns, default, root, cwd, auditor):
        self._kp = super(icasefsmatcher, self)._normalize(patterns, default,
                                                          root, cwd, auditor)
        kindpats = []
        for kind, pats, source in self._kp:
            if kind not in ('re', 'relre'):  # regex can't be normalized
                pats = self._dsnormalize(pats)
            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 _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

            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 util.Abort(_("%s: invalid pattern (%s): %s") %
                                     (s, k, p))
                else:
                    raise util.Abort(_("invalid pattern (%s): %s") % (k, p))
        raise util.Abort(_("invalid pattern"))

def _roots(kindpats):
    '''return roots and exact explicitly listed files from patterns

    >>> _roots([('glob', 'g/*', ''), ('glob', 'g', ''), ('glob', 'g*', '')])
    ['g', 'g', '.']
    >>> _roots([('relpath', 'r', ''), ('path', 'p/p', ''), ('path', '', '')])
    ['r', 'p/p', '.']
    >>> _roots([('relglob', 'rg*', ''), ('re', 're/', ''), ('relre', 'rr', '')])
    ['.', '.', '.']
    '''
    r = []
    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

        else: # relglob, re, relre
            r.append('.')
    return r

def _anypats(kindpats):
    for kind, pat, source in kindpats:
        if kind in ('glob', 're', 'relglob', 'relre', 'set'):
            return True

_commentre = None