def getEpsilonTarget(self, input: InputStream, config: LexerATNConfig, t: Transition, configs: ATNConfigSet, speculative: bool, treatEofAsEpsilon: bool): c = None if t.serializationType == Transition.RULE: newContext = SingletonPredictionContext.create( config.context, t.followState.stateNumber) c = LexerATNConfig(state=t.target, config=config, context=newContext) elif t.serializationType == Transition.PRECEDENCE: raise UnsupportedOperationException( "Precedence predicates are not supported in lexers.") elif t.serializationType == Transition.PREDICATE: # Track traversing semantic predicates. If we traverse, # we cannot add a DFA state for this "reach" computation # because the DFA would not test the predicate again in the # future. Rather than creating collections of semantic predicates # like v3 and testing them on prediction, v4 will test them on the # fly all the time using the ATN not the DFA. This is slower but # semantically it's not used that often. One of the key elements to # this predicate mechanism is not adding DFA states that see # predicates immediately afterwards in the ATN. For example, # a : ID {p1}? | ID {p2}? ; # should create the start state for rule 'a' (to save start state # competition), but should not create target of ID state. The # collection of ATN states the following ID references includes # states reached by traversing predicates. Since this is when we # test them, we cannot cash the DFA state target of ID. if self.debug: print("EVAL rule " + str(t.ruleIndex) + ":" + str(t.predIndex)) configs.hasSemanticContext = True if self.evaluatePredicate(input, t.ruleIndex, t.predIndex, speculative): c = LexerATNConfig(state=t.target, config=config) elif t.serializationType == Transition.ACTION: if config.context is None or config.context.hasEmptyPath(): # execute actions anywhere in the start rule for a token. # # TODO: if the entry rule is invoked recursively, some # actions may be executed during the recursive call. The # problem can appear when hasEmptyPath() is true but # isEmpty() is false. In this case, the config needs to be # split into two contexts - one with just the empty path # and another with everything but the empty path. # Unfortunately, the current algorithm does not allow # getEpsilonTarget to return two configurations, so # additional modifications are needed before we can support # the split operation. lexerActionExecutor = LexerActionExecutor.append( config.lexerActionExecutor, self.atn.lexerActions[t.actionIndex]) c = LexerATNConfig(state=t.target, config=config, lexerActionExecutor=lexerActionExecutor) else: # ignore actions in referenced rules c = LexerATNConfig(state=t.target, config=config) elif t.serializationType == Transition.EPSILON: c = LexerATNConfig(state=t.target, config=config) elif t.serializationType in [ Transition.ATOM, Transition.RANGE, Transition.SET ]: if treatEofAsEpsilon: if t.matches(Token.EOF, 0, 0xFFFF): c = LexerATNConfig(state=t.target, config=config) return c
def _LOOK(self, s, stopState , ctx, look, lookBusy, \ calledRuleStack, seeThruPreds, addEOF): c = ATNConfig(s, 0, ctx) if c in lookBusy: return lookBusy.add(c) if s == stopState: if ctx is None: look.addOne(Token.EPSILON) return elif ctx.isEmpty() and addEOF: look.addOne(Token.EOF) return if isinstance(s, RuleStopState ): if ctx is None: look.addOne(Token.EPSILON) return elif ctx.isEmpty() and addEOF: look.addOne(Token.EOF) return if ctx != PredictionContext.EMPTY: # run thru all possible stack tops in ctx for i in range(0, len(ctx)): returnState = self.atn.states[ctx.getReturnState(i)] removed = returnState.ruleIndex in calledRuleStack try: calledRuleStack.discard(returnState.ruleIndex) self._LOOK(returnState, stopState, ctx.getParent(i), look, lookBusy, calledRuleStack, seeThruPreds, addEOF) finally: if removed: calledRuleStack.add(returnState.ruleIndex) return for t in s.transitions: if type(t) == RuleTransition: if t.target.ruleIndex in calledRuleStack: continue newContext = SingletonPredictionContext.create(ctx, t.followState.stateNumber) try: calledRuleStack.add(t.target.ruleIndex) self._LOOK(t.target, stopState, newContext, look, lookBusy, calledRuleStack, seeThruPreds, addEOF) finally: calledRuleStack.remove(t.target.ruleIndex) elif isinstance(t, AbstractPredicateTransition ): if seeThruPreds: self._LOOK(t.target, stopState, ctx, look, lookBusy, calledRuleStack, seeThruPreds, addEOF) else: look.addOne(self.HIT_PRED) elif t.isEpsilon: self._LOOK(t.target, stopState, ctx, look, lookBusy, calledRuleStack, seeThruPreds, addEOF) elif type(t) == WildcardTransition: look.addRange( Interval(Token.MIN_USER_TOKEN_TYPE, self.atn.maxTokenType + 1) ) else: set = t.label if set is not None: if isinstance(t, NotSetTransition): set = set.complement(Token.MIN_USER_TOKEN_TYPE, self.atn.maxTokenType) look.addSet(set)
def getEpsilonTarget(self, input:InputStream, config:LexerATNConfig, t:Transition, configs:ATNConfigSet, speculative:bool, treatEofAsEpsilon:bool): c = None if t.serializationType==Transition.RULE: newContext = SingletonPredictionContext.create(config.context, t.followState.stateNumber) c = LexerATNConfig(state=t.target, config=config, context=newContext) elif t.serializationType==Transition.PRECEDENCE: raise UnsupportedOperationException("Precedence predicates are not supported in lexers.") elif t.serializationType==Transition.PREDICATE: # Track traversing semantic predicates. If we traverse, # we cannot add a DFA state for this "reach" computation # because the DFA would not test the predicate again in the # future. Rather than creating collections of semantic predicates # like v3 and testing them on prediction, v4 will test them on the # fly all the time using the ATN not the DFA. This is slower but # semantically it's not used that often. One of the key elements to # this predicate mechanism is not adding DFA states that see # predicates immediately afterwards in the ATN. For example, # a : ID {p1}? | ID {p2}? ; # should create the start state for rule 'a' (to save start state # competition), but should not create target of ID state. The # collection of ATN states the following ID references includes # states reached by traversing predicates. Since this is when we # test them, we cannot cash the DFA state target of ID. if LexerATNSimulator.debug: print("EVAL rule "+ str(t.ruleIndex) + ":" + str(t.predIndex)) configs.hasSemanticContext = True if self.evaluatePredicate(input, t.ruleIndex, t.predIndex, speculative): c = LexerATNConfig(state=t.target, config=config) elif t.serializationType==Transition.ACTION: if config.context is None or config.context.hasEmptyPath(): # execute actions anywhere in the start rule for a token. # # TODO: if the entry rule is invoked recursively, some # actions may be executed during the recursive call. The # problem can appear when hasEmptyPath() is true but # isEmpty() is false. In this case, the config needs to be # split into two contexts - one with just the empty path # and another with everything but the empty path. # Unfortunately, the current algorithm does not allow # getEpsilonTarget to return two configurations, so # additional modifications are needed before we can support # the split operation. lexerActionExecutor = LexerActionExecutor.append(config.lexerActionExecutor, self.atn.lexerActions[t.actionIndex]) c = LexerATNConfig(state=t.target, config=config, lexerActionExecutor=lexerActionExecutor) else: # ignore actions in referenced rules c = LexerATNConfig(state=t.target, config=config) elif t.serializationType==Transition.EPSILON: c = LexerATNConfig(state=t.target, config=config) elif t.serializationType in [ Transition.ATOM, Transition.RANGE, Transition.SET ]: if treatEofAsEpsilon: if t.matches(Token.EOF, 0, 0xFFFF): c = LexerATNConfig(state=t.target, config=config) return c