Python sre_compile.compile函数代码示例

 def __init__(self, runtimePath) :
     self.availRuleNames = []
     basePath = os.path.join(runtimePath, "rules")
     ruleFiles = os.listdir(basePath)
     rulePattern = sre_compile.compile("^(.*)\.py$")
     for eachRuleFile in ruleFiles :  
         if os.path.isfile(os.path.join(basePath, eachRuleFile)) :
             ruleMatch = rulePattern.match(eachRuleFile)
             if ruleMatch != None and eachRuleFile.find("__init__") == -1 :
                 ruleName = ruleMatch.group(1)
                 self.availRuleNames.append(ruleName)
     self.availRuleCount = len(self.availRuleNames)
     self.availRuleModules = {}
     self.loadedRule = []  
     self.rules = []
     self.preprocessRules = []
     self.functionNameRules = []
     self.functionScopeRules = []       
     self.typeNameRules = []    
     self.typeScopeRules = []
     self.lineRules = []    
     self.fileEndRules = []    
     self.fileStartRules = []
     self.projectRules = [] 
     self.rollBackImporter = None           

def _compile(pattern, flags):
    # internal: compile pattern
    if isinstance(flags, RegexFlag):
        flags = flags.value
    try:
        return _cache[type(pattern), pattern, flags]
    except KeyError:
        pass
    if isinstance(pattern, Pattern):
        if flags:
            raise ValueError(
                "cannot process flags argument with a compiled pattern")
        return pattern
    if not sre_compile.isstring(pattern):
        raise TypeError("first argument must be string or compiled pattern")
    p = sre_compile.compile(pattern, flags)
    if not (flags & DEBUG):
        if len(_cache) >= _MAXCACHE:
            # Drop the oldest item
            try:
                del _cache[next(iter(_cache))]
            except (StopIteration, RuntimeError, KeyError):
                pass
        _cache[type(pattern), pattern, flags] = p
    return p

def compile_regexp_to_noncapturing(pattern, flags=0):
    """
    Convert all grouping parentheses in the given regexp pattern to
    non-capturing groups, and return the result.  E.g.:

        >>> from nltk.internals import compile_regexp_to_noncapturing
        >>> compile_regexp_to_noncapturing('ab(c(x+)(z*))?d')
        'ab(?:c(?:x+)(?:z*))?d'

    :type pattern: str
    :rtype: str
    """
    def convert_regexp_to_noncapturing_parsed(parsed_pattern):
        res_data = []
        for key, value in parsed_pattern.data:
            if key == sre_constants.SUBPATTERN:
                index, subpattern = value
                value = (None, convert_regexp_to_noncapturing(subpattern))
            elif key == sre_constants.GROUPREF:
                raise ValueError('Regular expressions with back-references are not supported: {0}'.format(pattern))
            res_data.append((key, value))
        parsed_pattern.data = res_data
        parsed_pattern.pattern.groups = 1
        parsed_pattern.pattern.groupdict = {}
        return parsed_pattern

    return sre_compile.compile(convert_regexp_to_noncapturing_parsed(sre_parse.parse(pattern)))

def _compile(*key):
    pattern, flags = key
    bypass_cache = flags & DEBUG
    if not bypass_cache:
        cachekey = (type(key[0]),) + key
        p = _cache.get(cachekey)
        if p is not None:
            return p
    if isinstance(pattern, _pattern_type):
        if flags:
            raise ValueError("Cannot process flags argument with a compiled pattern")
        return pattern
    else:
        if not sre_compile.isstring(pattern):
            raise TypeError, "first argument must be string or compiled pattern"
        try:
            p = sre_compile.compile(pattern, flags)
        except error as v:
            raise error, v

        if not bypass_cache:
            if len(_cache) >= _MAXCACHE:
                _cache.clear()
            _cache[cachekey] = p
        return p

    def _compile(*key):
        # internal: compile pattern
        taint = _get_taint(key[0])
        if taint is not None: # can't hash the set
            taint = tuple(taint)
        cachekey = (type(key[0]), key, taint)
        p = re._cache.get(cachekey)
        if p is not None:
            return p
        pattern, flags = key
        if isinstance(pattern, re._pattern_type):
            if flags:
                raise ValueError("Cannot process flags argument with"
                                 " a compiled pattern")
            return pattern
        if not sre_compile.isstring(pattern):
            raise TypeError("first argument must be string or compiled"
                            " pattern")

        p = sre_compile.compile(pattern, flags)

        if len(re._cache) >= re._MAXCACHE:
            re._cache.clear()
        re._cache[cachekey] = p
        return p

 def __init__(self, lexicons, init_state=None, flags=0):
     # All the regexp magic below is copied from re.Scanner from
     # the standard library.
     import sre_compile
     import sre_parse
     from sre_constants import BRANCH, SUBPATTERN
     if init_state is None:
         init_state = State()
     if not hasattr(init_state, 'start'):
         init_state.start = None
     self.init_state = init_state
     self.lexicons = lexicons
     self.scanners = {}
     for start, lexicon in lexicons.iteritems():
         # combine phrases into a compound pattern
         p, a = [], []
         s = sre_parse.Pattern()
         s.flags = flags
         for phrase, action in lexicon:
             p.append(sre_parse.SubPattern(s, [
                         (SUBPATTERN, (len(p)+1,
                                       sre_parse.parse(phrase, flags))),
                         ]))
             a.append(action)
         p = sre_parse.SubPattern(s, [(BRANCH, (None, p))])
         s.groups = len(p)
         self.scanners[start] = sre_compile.compile(p).match, a

def _compile(pattern, flags):
    # internal: compile pattern
    try:
        p, loc = _cache[type(pattern), pattern, flags]
        if loc is None or loc == _locale.setlocale(_locale.LC_CTYPE):
            return p
    except KeyError:
        pass
    if isinstance(pattern, _pattern_type):
        if flags:
            raise ValueError(
                "cannot process flags argument with a compiled pattern")
        return pattern
    if not sre_compile.isstring(pattern):
        raise TypeError("first argument must be string or compiled pattern")
    p = sre_compile.compile(pattern, flags)
    if not (flags & DEBUG):
        if len(_cache) >= _MAXCACHE:
            _cache.clear()
        if p.flags & LOCALE:
            if not _locale:
                return p
            loc = _locale.setlocale(_locale.LC_CTYPE)
        else:
            loc = None
        _cache[type(pattern), pattern, flags] = p, loc
    return p

    def __init__(self, lexicon, flags=FLAGS):
        self.actions = [None]
        # combine phrases into a compound pattern
        s = sre_parse.Pattern()
        s.flags = flags
        p = []
        # NOTE(kgibbs): These lines must be added to make this file work under
        # Python 2.2, which is commonly used at Google.
        def enumerate(obj):
            i = -1
            for item in obj:
                i += 1
                yield i, item
        # NOTE(kgibbs): End changes.
        for idx, token in enumerate(lexicon):
            phrase = token.pattern
            try:
                subpattern = sre_parse.SubPattern(s,
                    [(SUBPATTERN, (idx + 1, sre_parse.parse(phrase, flags)))])
            except sre_constants.error:
                raise
            p.append(subpattern)
            self.actions.append(token)

        s.groups = len(p)+1  # NOTE(guido): Added to make SRE validation work
        p = sre_parse.SubPattern(s, [(BRANCH, (None, p))])
        self.scanner = sre_compile.compile(p)

 def Sub(self, pattern, repl, s):
   """Replace the string for the pattern by the paramter repl, caching the compiled regexp."""
   # for example: s='a1234a' ,repl='OOOO' pattern = r'd+'
   # result is 'aOOOOa'
   #
   if not pattern in self._regexp_compile_cache:
     self._regexp_compile_cache[pattern] = sre_compile.compile(pattern)
   return self._regexp_compile_cache[pattern].sub(repl,s)

 def Match(self, pattern, s):
   """Matches the string with the pattern, caching the compiled regexp."""
   # The regexp compilation caching is inlined in both Match and Search for
   # performance reasons; factoring it out into a separate function turns out
   # to be noticeably expensive.
   if not pattern in self._regexp_compile_cache:
     self._regexp_compile_cache[pattern] = sre_compile.compile(pattern)
   return self._regexp_compile_cache[pattern].match(s)

def _compile_typed(text_bytes_type, pattern, flags):
    # internal: compile pattern
    if isinstance(pattern, _pattern_type):
        if flags:
            raise ValueError(
                "Cannot process flags argument with a compiled pattern")
        return pattern
    if not sre_compile.isstring(pattern):
        raise TypeError("first argument must be string or compiled pattern")
    return sre_compile.compile(pattern, flags)

 def __init__(self, lexicon, flags=0):
     from sre_constants import BRANCH, SUBPATTERN
     self.lexicon = lexicon
     p = []
     s = sre_parse.Pattern()
     s.flags = flags
     for (phrase, action) in lexicon:
         p.append(sre_parse.SubPattern(s, [(SUBPATTERN, (len(p) + 1, sre_parse.parse(phrase, flags)))]))
     s.groups = len(p) + 1
     p = sre_parse.SubPattern(s, [(BRANCH, (None, p))])
     self.scanner = sre_compile.compile(p)

    def __init__(self, lexicon):
        from sre_constants import BRANCH, SUBPATTERN

        self.lexicon = lexicon
        # combine phrases into a compound pattern
        p = []
        s = sre_parse.Pattern()
        for phrase, action in lexicon:
            p.append(sre_parse.SubPattern(s, [(SUBPATTERN, (len(p), sre_parse.parse(phrase)))]))
        p = sre_parse.SubPattern(s, [(BRANCH, (None, p))])
        s.groups = len(p)
        self.scanner = sre_compile.compile(p)

def _compile(*key):
    # internal: compile pattern
    p = _cache.get(key)
    if p is not None:
        return p
    pattern, flags = key
    if type(pattern) not in sre_compile.STRING_TYPES:
        return pattern
    try:
        p = sre_compile.compile(pattern, flags)
    except error, v:
        raise error, v  # invalid expression

    def _get_group_pattern(self,flags):
        # combine phrases into a compound pattern
	patterns = []
        sub_pattern = sre_parse.Pattern()
        sub_pattern.flags = flags
        for phrase, action in self.lexicon:
            patterns.append(sre_parse.SubPattern(sub_pattern, [
                (SUBPATTERN, (len(patterns) + 1, sre_parse.parse(phrase, flags))),
                ]))
        sub_pattern.groups = len(patterns) + 1
        group_pattern = sre_parse.SubPattern(sub_pattern, [(BRANCH, (None, patterns))])
        return sre_compile.compile(group_pattern)