Experimental lexer generator: parse {} in regexps.

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 25 matching lines @@
 
     'CLASS_BEGIN',
     'CLASS_END',
 
     'OR',
     'ONE_OR_MORE',
     'ZERO_OR_MORE',
     'ZERO_OR_ONE',
     'ANY',
 
+    'REPEAT_BEGIN',
+    'REPEAT_END',
+
+    'NUMBER',
+    'COMMA',
     '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:]
     return t
 
   t_GROUP_BEGIN = r'\('
   t_GROUP_END = r'\)'
 
+  t_REPEAT_BEGIN = r'\{'
+  t_REPEAT_END = r'\}'
+
   t_OR = r'\|'
   t_ONE_OR_MORE = r'\+'
   t_ZERO_OR_MORE = r'\*'
   t_ZERO_OR_ONE = r'\?'
 
+  t_NUMBER = r'[0-9]+'
+  t_COMMA = r','
+
   t_ANY = r'\.'
 
   t_LITERAL = r'.'
 
   def t_CLASS_BEGIN(self, t):
     r'\['
     self.lexer.push_state('class')
     return t
 
   def t_class_CLASS_END(self, t):
@@ skipping 13 matching lines @@
 
   t_class_CLASS_LITERAL = r'[\w $_+]' # 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)