Experimental parser: parse character classes

tools/lexer_generator/regex_parser.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 82 matching lines @@
     else:
       p[0] = ("NOT_CLASS", p[3])
 
   def p_group(self, p):
     '''group : GROUP_BEGIN start GROUP_END'''
     p[0] = p[2]
 
   def p_class_content(self, p):
     '''class_content : CLASS_LITERAL RANGE CLASS_LITERAL maybe_class_content
                      | CLASS_LITERAL maybe_class_content
+                     | CHARACTER_CLASS maybe_class_content
     '''
     if len(p) == 5:
       left = ("RANGE", p[1], p[3])
     else:
-      left = ('LITERAL', p[1])
+      if len(p[1]) == 1:
+        left = ('LITERAL', p[1])
+      else:
+        left = ('CHARACTER_CLASS', p[1:-1])
     p[0] = self.__cat(left, p[len(p)-1])
 
   def p_maybe_class_content(self, p):
     '''maybe_class_content : class_content
                            | empty'''
     p[0] = p[1]
 
   def p_empty(self, p):
     'empty :'
 
   def p_error(self, p):
     raise Exception("Syntax error in input '%s'" % p)
 
   @staticmethod
   def __cat(left, right):
     if right == None:
       return left
     return ('CAT', left, right)
 
   def build(self, **kwargs):
     self.parser = yacc.yacc(module=self, debug=0, write_tables=0, **kwargs)
     self.lexer = RegexLexer()
     self.lexer.build(**kwargs)
 
   @staticmethod
   def parse(data):
     parser = RegexParser()
     parser.build()
     return parser.parser.parse(data, lexer=parser.lexer.lexer)