Experimental parser: dfa optimization to remove transitions from keyword lexing

tools/lexer_generator/rule_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 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.yacc as yacc
 from automaton import Action
 from rule_lexer import RuleLexer
 from regex_parser import RegexParser
 from nfa_builder import NfaBuilder
 from dfa import Dfa
+from dfa_optimizer import DfaOptimizer
 from transition_keys import TransitionKey, KeyEncoding
 
 class RuleParserState:
 
   def __init__(self, encoding):
     self.aliases = {}
     self.character_classes = {}
     self.current_state = None
     self.rules = {}
     self.transitions = set()
@@ skipping 242 matching lines @@
       if not self.__nfa:
         self.__nfa = self.__builder.nfa(self.__graph)
       return self.__nfa
 
     def dfa(self):
       if not self.__dfa:
         (start, dfa_nodes) = self.nfa().compute_dfa()
         self.__dfa = Dfa(self.nfa().encoding(), start, dfa_nodes)
       return self.__dfa
 
+    def optimize_dfa(self, log = False):
+      assert not self.__dfa
+      self.__dfa = DfaOptimizer.optimize(self.dfa(), log)
+
     def minimal_dfa(self):
       if not self.__minimial_dfa:
         self.__minimial_dfa = self.dfa().minimize()
       return self.__minimial_dfa
 
   def __process_parser_state(self, parser_state):
     rule_map = {}
     builder = NfaBuilder(parser_state.encoding, parser_state.character_classes)
     assert 'default' in parser_state.rules
     def process(subgraph, v):
@@ skipping 27 matching lines @@
     for k, v in parser_state.rules.items():
       if k == 'default': continue
       process(k, v)
     process('default', parser_state.rules['default'])
     # build the automata
     for rule_name, graph in rule_map.items():
       self.__automata[rule_name] = RuleProcessor.Automata(builder, graph)
     # process default_action
     default_action = parser_state.rules['default']['default_action']
     self.default_action = Action(None, default_action[1]) if default_action else None