Experimental parser: parse character classes

tools/lexer_generator/regex_lexer.py

 # Copyright 2013 the V8 project authors. All rights reserved.
 # Redistribution and use in source and binary forms, with or without
 # modification, are permitted provided that the following conditions are
 # met:
 #
 #     * Redistributions of source code must retain the above copyright
 #       notice, this list of conditions and the following disclaimer.
 #     * Redistributions in binary form must reproduce the above
 #       copyright notice, this list of conditions and the following
 #       disclaimer in the documentation and/or other materials provided
@@ skipping 30 matching lines @@
     'ONE_OR_MORE',
     'ZERO_OR_MORE',
     'ZERO_OR_ONE',
     'ANY',
 
     'LITERAL',
 
     'RANGE',
     'NOT',
     'CLASS_LITERAL',
+    'CHARACTER_CLASS',
   )
 
   states = (
     ('class','exclusive'),
   )
 
   def t_ESCAPED_LITERAL(self, t):
     r'\\\(|\\\)|\\\[|\\\]|\\\||\\\+|\\\*|\\\?|\\\.|\\\\'
     t.type = 'LITERAL'
     t.value = t.value[1:]
@@ skipping 16 matching lines @@
     self.lexer.push_state('class')
     return t
 
   def t_class_CLASS_END(self, t):
     r'\]'
     self.lexer.pop_state()
     return t
 
   t_class_RANGE = '-'
   t_class_NOT = '\^'
+  t_class_CHARACTER_CLASS = ':ws:|:lit:'
 
   def t_class_ESCAPED_CLASS_LITERAL(self, t):
-    r'\\\^|\\-|\\\[|\\\]'
+    r'\\\^|\\-|\\\[|\\\]\\:'
     t.type = 'CLASS_LITERAL'
     t.value = t.value[1:]
     return t
 
   t_class_CLASS_LITERAL = r'[a-zA-Z0-9]' # fix this
 
   t_ANY_ignore  = '\n'
 
   def t_ANY_error(self, t):
     raise Exception("Illegal character '%s'" % t.value[0])
 
   def build(self, **kwargs):
     self.lexer = lex.lex(module=self, **kwargs)