Experimental parser: parsing regex subexpressions

tools/lexer_generator/rule_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 13 matching lines @@
 # THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 # (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 # OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
 import ply.lex as lex
 
 class RuleLexer:
 
   tokens = (
     'IDENTIFIER',
-    'STRING_REGEX',
+    'STRING',
+    'REGEX',
     'CHARACTER_CLASS_REGEX',
     'TRANSITION',
     'TRANSITION_WITH_CODE',
 
     'PLUS',
     'QUESTION_MARK',
     'EQUALS',
     'OR',
     'STAR',
     'LEFT_PARENTHESIS',
@@ skipping 13 matching lines @@
   )
 
   t_ignore = " \t\n\r"
   t_code_ignore = ""
 
   def t_COMMENT(self, t):
     r'\#.*[\n\r]+'
     pass
 
   t_IDENTIFIER = r'[a-zA-Z0-9_]+'
-  t_STRING_REGEX = r'"((\\("|\w|\\))|[^\\"])+"'
+  t_STRING = r'"((\\("|\w|\\))|[^\\"])+"'
+  t_REGEX = r'/[^\/]+/'
   t_CHARACTER_CLASS_REGEX = r'\[([^\]]|\\\])+\]'
   t_TRANSITION = r':=>'
   t_TRANSITION_WITH_CODE = r'=>'
 
   t_PLUS = r'\+'
   t_QUESTION_MARK = r'\?'
   t_STAR = r'\*'
   t_OR = r'\|'
   t_EQUALS = r'='
   t_LEFT_PARENTHESIS = r'\('
@@ skipping 23 matching lines @@
       t.type = 'CODE_FRAGMENT'
     else:
       self.lexer.pop_state()
     return t
 
   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)