Mass Deface ...) The substring matched by the group is accessible by name. (?P=name) Matches the text matched earlier by the group named name. (?#...) A comment; ignored. (?=...) Matches if ... matches next, but doesn't consume the string. (?!...) Matches if ... doesn't match next. (?<=...) Matches if preceded by ... (must be fixed length). (?= 0x02020000: __all__.append("finditer") def finditer(pattern, string, flags=0): """Return an iterator over all non-overlapping matches in the string. For each match, the iterator returns a match object. Empty matches are included in the result.""" return _compile(pattern, flags).finditer(string) def compile(pattern, flags=0): "Compile a regular expression pattern, returning a pattern object." return _compile(pattern, flags) def purge(): "Clear the regular expression cache" _cache.clear() _cache_repl.clear() def template(pattern, flags=0): "Compile a template pattern, returning a pattern object" return _compile(pattern, flags|T) _alphanum = frozenset( "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789") def escape(pattern): "Escape all non-alphanumeric characters in pattern." s = list(pattern) alphanum = _alphanum for i, c in enumerate(pattern): if c not in alphanum: if c == "\000": s[i] = "\\000" else: s[i] = "\\" + c return pattern[:0].join(s) # -------------------------------------------------------------------- # internals _cache = {} _cache_repl = {} _pattern_type = type(sre_compile.compile("", 0)) _MAXCACHE = 100 def _compile(*key): # internal: compile pattern cachekey = (type(key[0]),) + key p = _cache.get(cachekey) if p is not None: return p pattern, flags = key 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" try: p = sre_compile.compile(pattern, flags) except error, v: raise error, v # invalid expression if len(_cache) >= _MAXCACHE: _cache.clear() _cache[cachekey] = p return p def _compile_repl(*key): # internal: compile replacement pattern p = _cache_repl.get(key) if p is not None: return p repl, pattern = key try: p = sre_parse.parse_template(repl, pattern) except error, v: raise error, v # invalid expression if len(_cache_repl) >= _MAXCACHE: _cache_repl.clear() _cache_repl[key] = p return p def _expand(pattern, match, template): # internal: match.expand implementation hook template = sre_parse.parse_template(template, pattern) return sre_parse.expand_template(template, match) def _subx(pattern, template): # internal: pattern.sub/subn implementation helper template = _compile_repl(template, pattern) if not template[0] and len(template[1]) == 1: # literal replacement return template[1][0] def filter(match, template=template): return sre_parse.expand_template(template, match) return filter # register myself for pickling import copy_reg def _pickle(p): return _compile, (p.pattern, p.flags) copy_reg.pickle(_pattern_type, _pickle, _compile) # -------------------------------------------------------------------- # experimental stuff (see python-dev discussions for details) class Scanner: def __init__(self, lexicon, flags=0): from sre_constants import BRANCH, SUBPATTERN self.lexicon = lexicon # combine phrases into a compound pattern 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 scan(self, string): result = [] append = result.append match = self.scanner.scanner(string).match i = 0 while 1: m = match() if not m: break j = m.end() if i == j: break action = self.lexicon[m.lastindex-1][1] if hasattr(action, '__call__'): self.match = m action = action(self, m.group()) if action is not None: append(action) i = j return result, string[i:]