Experimental parser: better rule tree visualization

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 153 matching lines @@
 
   def p_fragments(self, p):
     '''fragments : fragment
                  | fragment fragments'''
     if len(p) == 2:
       p[0] = p[1]
     else:
       p[0] = self.__cat(p[1], p[2])
 
   def p_fragment(self, p):
-    '''fragment : literal maybe_modifier
+    '''fragment : literal_array maybe_modifier
                 | class maybe_modifier
                 | group maybe_modifier
                 | any maybe_modifier
     '''
     if p[2] != None:
       if isinstance(p[2], tuple) and p[2][0] == 'REPEAT':
         p[0] = Term(p[2][0], p[2][1], p[2][2], p[1])
       else:
         p[0] = Term(p[2], p[1])
     else:
@@ skipping 10 matching lines @@
       p[0] = self.token_map[p[1]]
 
   def p_repetition(self, p):
     '''repetition : REPEAT_BEGIN NUMBER REPEAT_END
                   | REPEAT_BEGIN NUMBER COMMA NUMBER REPEAT_END'''
     if len(p) == 4:
       p[0] = ("REPEAT", p[2], p[2])
     else:
       p[0] = ("REPEAT", p[2], p[4])
 
-  def p_literal(self, p):
-    '''literal : LITERAL'''
-    p[0] = Term('LITERAL', p[1])
+  def p_literal_array(self, p):
+    '''literal_array : literals'''
+    p[0] = Term('LITERAL', ''.join(reversed(p[1])))
+
+  def p_literals(self, p):
+    '''literals : LITERAL maybe_literals'''
+    if not p[2]:
+      p[0] = [p[1]]
+    else:
+      p[2].append(p[1])
+      p[0] = p[2]
+
+  def p_maybe_literals(self, p):
+    '''maybe_literals : literals
+                      |  empty'''
+    p[0] = p[1]
 
   def p_any(self, p):
     '''any : ANY'''
     p[0] = Term(self.token_map[p[1]])
 
   def p_class(self, p):
     '''class : CLASS_BEGIN class_content CLASS_END
              | CLASS_BEGIN NOT class_content CLASS_END'''
     if len(p) == 4:
       p[0] = Term("CLASS", p[2])
@@ skipping 48 matching lines @@
     parser = RegexParser.__static_instance
     if not parser:
       parser = RegexParser()
       parser.build()
       RegexParser.__static_instance = parser
     try:
       return parser.parser.parse(data, lexer=parser.lexer.lexer)
     except Exception:
       RegexParser.__static_instance = None
       raise