Examples with RuleTransition org.antlr.v4.runtime.atn.RuleTransition used on opensource projects

Example 1 with RuleTransition

use of org.antlr.v4.runtime.atn.RuleTransition in project antlr4 by tunnelvisionlabs.

the class ParserATNFactory method addRuleFollowLinks.

public void addRuleFollowLinks() {
    for (ATNState p : atn.states) {
        if (p != null && p.getStateType() == ATNState.BASIC && p.getNumberOfTransitions() == 1 && p.transition(0) instanceof RuleTransition) {
            RuleTransition rt = (RuleTransition) p.transition(0);
            addFollowLink(rt.ruleIndex, rt.followState);
        }
    }
}

Example 2 with RuleTransition

use of org.antlr.v4.runtime.atn.RuleTransition in project antlr4 by tunnelvisionlabs.

the class ParserATNFactory method _ruleRef.

@NotNull
public Handle _ruleRef(@NotNull GrammarAST node) {
    Rule r = g.getRule(node.getText());
    if (r == null) {
        g.tool.errMgr.grammarError(ErrorType.INTERNAL_ERROR, g.fileName, node.getToken(), "Rule " + node.getText() + " undefined");
        return null;
    }
    RuleStartState start = atn.ruleToStartState[r.index];
    ATNState left = newState(node);
    ATNState right = newState(node);
    int precedence = 0;
    if (((GrammarASTWithOptions) node).getOptionString(LeftRecursiveRuleTransformer.PRECEDENCE_OPTION_NAME) != null) {
        precedence = Integer.parseInt(((GrammarASTWithOptions) node).getOptionString(LeftRecursiveRuleTransformer.PRECEDENCE_OPTION_NAME));
    }
    RuleTransition call = new RuleTransition(start, r.index, precedence, right);
    left.addTransition(call);
    node.atnState = left;
    return new Handle(left, right);
}

Example 3 with RuleTransition

use of org.antlr.v4.runtime.atn.RuleTransition in project antlr4 by tunnelvisionlabs.

the class ParserInterpreter method visitState.

protected void visitState(ATNState p) {
    int predictedAlt = 1;
    if (p.getNumberOfTransitions() > 1) {
        predictedAlt = visitDecisionState((DecisionState) p);
    }
    Transition transition = p.transition(predictedAlt - 1);
    switch(transition.getSerializationType()) {
        case Transition.EPSILON:
            if (pushRecursionContextStates.get(p.stateNumber) && !(transition.target instanceof LoopEndState)) {
                // We are at the start of a left recursive rule's (...)* loop
                // and we're not taking the exit branch of loop.
                InterpreterRuleContext localctx = createInterpreterRuleContext(_parentContextStack.peek().getItem1(), _parentContextStack.peek().getItem2(), _ctx.getRuleIndex());
                pushNewRecursionContext(localctx, atn.ruleToStartState[p.ruleIndex].stateNumber, _ctx.getRuleIndex());
            }
            break;
        case Transition.ATOM:
            match(((AtomTransition) transition).label);
            break;
        case Transition.RANGE:
        case Transition.SET:
        case Transition.NOT_SET:
            if (!transition.matches(_input.LA(1), Token.MIN_USER_TOKEN_TYPE, 65535)) {
                recoverInline();
            }
            matchWildcard();
            break;
        case Transition.WILDCARD:
            matchWildcard();
            break;
        case Transition.RULE:
            RuleStartState ruleStartState = (RuleStartState) transition.target;
            int ruleIndex = ruleStartState.ruleIndex;
            InterpreterRuleContext newctx = createInterpreterRuleContext(_ctx, p.stateNumber, ruleIndex);
            if (ruleStartState.isPrecedenceRule) {
                enterRecursionRule(newctx, ruleStartState.stateNumber, ruleIndex, ((RuleTransition) transition).precedence);
            } else {
                enterRule(newctx, transition.target.stateNumber, ruleIndex);
            }
            break;
        case Transition.PREDICATE:
            PredicateTransition predicateTransition = (PredicateTransition) transition;
            if (!sempred(_ctx, predicateTransition.ruleIndex, predicateTransition.predIndex)) {
                throw new FailedPredicateException(this);
            }
            break;
        case Transition.ACTION:
            ActionTransition actionTransition = (ActionTransition) transition;
            action(_ctx, actionTransition.ruleIndex, actionTransition.actionIndex);
            break;
        case Transition.PRECEDENCE:
            if (!precpred(_ctx, ((PrecedencePredicateTransition) transition).precedence)) {
                throw new FailedPredicateException(this, String.format("precpred(_ctx, %d)", ((PrecedencePredicateTransition) transition).precedence));
            }
            break;
        default:
            throw new UnsupportedOperationException("Unrecognized ATN transition type.");
    }
    setState(transition.target.stateNumber);
}

Example 4 with RuleTransition

use of org.antlr.v4.runtime.atn.RuleTransition in project antlr4 by tunnelvisionlabs.

the class DefaultErrorStrategy method getErrorRecoverySet.

/*  Compute the error recovery set for the current rule.  During
	 *  rule invocation, the parser pushes the set of tokens that can
	 *  follow that rule reference on the stack; this amounts to
	 *  computing FIRST of what follows the rule reference in the
	 *  enclosing rule. See LinearApproximator.FIRST().
	 *  This local follow set only includes tokens
	 *  from within the rule; i.e., the FIRST computation done by
	 *  ANTLR stops at the end of a rule.
	 *
	 *  EXAMPLE
	 *
	 *  When you find a "no viable alt exception", the input is not
	 *  consistent with any of the alternatives for rule r.  The best
	 *  thing to do is to consume tokens until you see something that
	 *  can legally follow a call to r *or* any rule that called r.
	 *  You don't want the exact set of viable next tokens because the
	 *  input might just be missing a token--you might consume the
	 *  rest of the input looking for one of the missing tokens.
	 *
	 *  Consider grammar:
	 *
	 *  a : '[' b ']'
	 *    | '(' b ')'
	 *    ;
	 *  b : c '^' INT ;
	 *  c : ID
	 *    | INT
	 *    ;
	 *
	 *  At each rule invocation, the set of tokens that could follow
	 *  that rule is pushed on a stack.  Here are the various
	 *  context-sensitive follow sets:
	 *
	 *  FOLLOW(b1_in_a) = FIRST(']') = ']'
	 *  FOLLOW(b2_in_a) = FIRST(')') = ')'
	 *  FOLLOW(c_in_b) = FIRST('^') = '^'
	 *
	 *  Upon erroneous input "[]", the call chain is
	 *
	 *  a -> b -> c
	 *
	 *  and, hence, the follow context stack is:
	 *
	 *  depth     follow set       start of rule execution
	 *    0         <EOF>                    a (from main())
	 *    1          ']'                     b
	 *    2          '^'                     c
	 *
	 *  Notice that ')' is not included, because b would have to have
	 *  been called from a different context in rule a for ')' to be
	 *  included.
	 *
	 *  For error recovery, we cannot consider FOLLOW(c)
	 *  (context-sensitive or otherwise).  We need the combined set of
	 *  all context-sensitive FOLLOW sets--the set of all tokens that
	 *  could follow any reference in the call chain.  We need to
	 *  resync to one of those tokens.  Note that FOLLOW(c)='^' and if
	 *  we resync'd to that token, we'd consume until EOF.  We need to
	 *  sync to context-sensitive FOLLOWs for a, b, and c: {']','^'}.
	 *  In this case, for input "[]", LA(1) is ']' and in the set, so we would
	 *  not consume anything. After printing an error, rule c would
	 *  return normally.  Rule b would not find the required '^' though.
	 *  At this point, it gets a mismatched token error and throws an
	 *  exception (since LA(1) is not in the viable following token
	 *  set).  The rule exception handler tries to recover, but finds
	 *  the same recovery set and doesn't consume anything.  Rule b
	 *  exits normally returning to rule a.  Now it finds the ']' (and
	 *  with the successful match exits errorRecovery mode).
	 *
	 *  So, you can see that the parser walks up the call chain looking
	 *  for the token that was a member of the recovery set.
	 *
	 *  Errors are not generated in errorRecovery mode.
	 *
	 *  ANTLR's error recovery mechanism is based upon original ideas:
	 *
	 *  "Algorithms + Data Structures = Programs" by Niklaus Wirth
	 *
	 *  and
	 *
	 *  "A note on error recovery in recursive descent parsers":
	 *  http://portal.acm.org/citation.cfm?id=947902.947905
	 *
	 *  Later, Josef Grosch had some good ideas:
	 *
	 *  "Efficient and Comfortable Error Recovery in Recursive Descent
	 *  Parsers":
	 *  ftp://www.cocolab.com/products/cocktail/doca4.ps/ell.ps.zip
	 *
	 *  Like Grosch I implement context-sensitive FOLLOW sets that are combined
	 *  at run-time upon error to avoid overhead during parsing.
	 */
@NotNull
protected IntervalSet getErrorRecoverySet(@NotNull Parser recognizer) {
    ATN atn = recognizer.getInterpreter().atn;
    RuleContext ctx = recognizer._ctx;
    IntervalSet recoverSet = new IntervalSet();
    while (ctx != null && ctx.invokingState >= 0) {
        // compute what follows who invoked us
        ATNState invokingState = atn.states.get(ctx.invokingState);
        RuleTransition rt = (RuleTransition) invokingState.transition(0);
        IntervalSet follow = atn.nextTokens(rt.followState);
        recoverSet.addAll(follow);
        ctx = ctx.parent;
    }
    recoverSet.remove(Token.EPSILON);
    // System.out.println("recover set "+recoverSet.toString(recognizer.getTokenNames()));
    return recoverSet;
}

Example 5 with RuleTransition

use of org.antlr.v4.runtime.atn.RuleTransition in project antlr4 by antlr.

the class ATNSerializer method serialize.

/**
 * Serialize state descriptors, edge descriptors, and decision→state map
 *  into list of ints:
 *
 * 		grammar-type, (ANTLRParser.LEXER, ...)
 *  	max token type,
 *  	num states,
 *  	state-0-type ruleIndex, state-1-type ruleIndex, ... state-i-type ruleIndex optional-arg ...
 *  	num rules,
 *  	rule-1-start-state rule-1-args, rule-2-start-state  rule-2-args, ...
 *  	(args are token type,actionIndex in lexer else 0,0)
 *      num modes,
 *      mode-0-start-state, mode-1-start-state, ... (parser has 0 modes)
 *      num unicode-bmp-sets
 *      bmp-set-0-interval-count intervals, bmp-set-1-interval-count intervals, ...
 *      num unicode-smp-sets
 *      smp-set-0-interval-count intervals, smp-set-1-interval-count intervals, ...
 *	num total edges,
 *      src, trg, edge-type, edge arg1, optional edge arg2 (present always), ...
 *      num decisions,
 *      decision-0-start-state, decision-1-start-state, ...
 *
 *  Convenient to pack into unsigned shorts to make as Java string.
 */
public IntegerList serialize() {
    IntegerList data = new IntegerList();
    data.add(ATNDeserializer.SERIALIZED_VERSION);
    serializeUUID(data, ATNDeserializer.SERIALIZED_UUID);
    // convert grammar type to ATN const to avoid dependence on ANTLRParser
    data.add(atn.grammarType.ordinal());
    data.add(atn.maxTokenType);
    int nedges = 0;
    // Note that we use a LinkedHashMap as a set to
    // maintain insertion order while deduplicating
    // entries with the same key.
    Map<IntervalSet, Boolean> sets = new LinkedHashMap<>();
    // dump states, count edges and collect sets while doing so
    IntegerList nonGreedyStates = new IntegerList();
    IntegerList precedenceStates = new IntegerList();
    data.add(atn.states.size());
    for (ATNState s : atn.states) {
        if (s == null) {
            // might be optimized away
            data.add(ATNState.INVALID_TYPE);
            continue;
        }
        int stateType = s.getStateType();
        if (s instanceof DecisionState && ((DecisionState) s).nonGreedy) {
            nonGreedyStates.add(s.stateNumber);
        }
        if (s instanceof RuleStartState && ((RuleStartState) s).isLeftRecursiveRule) {
            precedenceStates.add(s.stateNumber);
        }
        data.add(stateType);
        if (s.ruleIndex == -1) {
            data.add(Character.MAX_VALUE);
        } else {
            data.add(s.ruleIndex);
        }
        if (s.getStateType() == ATNState.LOOP_END) {
            data.add(((LoopEndState) s).loopBackState.stateNumber);
        } else if (s instanceof BlockStartState) {
            data.add(((BlockStartState) s).endState.stateNumber);
        }
        if (s.getStateType() != ATNState.RULE_STOP) {
            // the deserializer can trivially derive these edges, so there's no need to serialize them
            nedges += s.getNumberOfTransitions();
        }
        for (int i = 0; i < s.getNumberOfTransitions(); i++) {
            Transition t = s.transition(i);
            int edgeType = Transition.serializationTypes.get(t.getClass());
            if (edgeType == Transition.SET || edgeType == Transition.NOT_SET) {
                SetTransition st = (SetTransition) t;
                sets.put(st.set, true);
            }
        }
    }
    // non-greedy states
    data.add(nonGreedyStates.size());
    for (int i = 0; i < nonGreedyStates.size(); i++) {
        data.add(nonGreedyStates.get(i));
    }
    // precedence states
    data.add(precedenceStates.size());
    for (int i = 0; i < precedenceStates.size(); i++) {
        data.add(precedenceStates.get(i));
    }
    int nrules = atn.ruleToStartState.length;
    data.add(nrules);
    for (int r = 0; r < nrules; r++) {
        ATNState ruleStartState = atn.ruleToStartState[r];
        data.add(ruleStartState.stateNumber);
        if (atn.grammarType == ATNType.LEXER) {
            if (atn.ruleToTokenType[r] == Token.EOF) {
                data.add(Character.MAX_VALUE);
            } else {
                data.add(atn.ruleToTokenType[r]);
            }
        }
    }
    int nmodes = atn.modeToStartState.size();
    data.add(nmodes);
    if (nmodes > 0) {
        for (ATNState modeStartState : atn.modeToStartState) {
            data.add(modeStartState.stateNumber);
        }
    }
    List<IntervalSet> bmpSets = new ArrayList<>();
    List<IntervalSet> smpSets = new ArrayList<>();
    for (IntervalSet set : sets.keySet()) {
        if (!set.isNil() && set.getMaxElement() <= Character.MAX_VALUE) {
            bmpSets.add(set);
        } else {
            smpSets.add(set);
        }
    }
    serializeSets(data, bmpSets, new CodePointSerializer() {

        @Override
        public void serializeCodePoint(IntegerList data, int cp) {
            data.add(cp);
        }
    });
    serializeSets(data, smpSets, new CodePointSerializer() {

        @Override
        public void serializeCodePoint(IntegerList data, int cp) {
            serializeInt(data, cp);
        }
    });
    Map<IntervalSet, Integer> setIndices = new HashMap<>();
    int setIndex = 0;
    for (IntervalSet bmpSet : bmpSets) {
        setIndices.put(bmpSet, setIndex++);
    }
    for (IntervalSet smpSet : smpSets) {
        setIndices.put(smpSet, setIndex++);
    }
    data.add(nedges);
    for (ATNState s : atn.states) {
        if (s == null) {
            // might be optimized away
            continue;
        }
        if (s.getStateType() == ATNState.RULE_STOP) {
            continue;
        }
        for (int i = 0; i < s.getNumberOfTransitions(); i++) {
            Transition t = s.transition(i);
            if (atn.states.get(t.target.stateNumber) == null) {
                throw new IllegalStateException("Cannot serialize a transition to a removed state.");
            }
            int src = s.stateNumber;
            int trg = t.target.stateNumber;
            int edgeType = Transition.serializationTypes.get(t.getClass());
            int arg1 = 0;
            int arg2 = 0;
            int arg3 = 0;
            switch(edgeType) {
                case Transition.RULE:
                    trg = ((RuleTransition) t).followState.stateNumber;
                    arg1 = ((RuleTransition) t).target.stateNumber;
                    arg2 = ((RuleTransition) t).ruleIndex;
                    arg3 = ((RuleTransition) t).precedence;
                    break;
                case Transition.PRECEDENCE:
                    PrecedencePredicateTransition ppt = (PrecedencePredicateTransition) t;
                    arg1 = ppt.precedence;
                    break;
                case Transition.PREDICATE:
                    PredicateTransition pt = (PredicateTransition) t;
                    arg1 = pt.ruleIndex;
                    arg2 = pt.predIndex;
                    arg3 = pt.isCtxDependent ? 1 : 0;
                    break;
                case Transition.RANGE:
                    arg1 = ((RangeTransition) t).from;
                    arg2 = ((RangeTransition) t).to;
                    if (arg1 == Token.EOF) {
                        arg1 = 0;
                        arg3 = 1;
                    }
                    break;
                case Transition.ATOM:
                    arg1 = ((AtomTransition) t).label;
                    if (arg1 == Token.EOF) {
                        arg1 = 0;
                        arg3 = 1;
                    }
                    break;
                case Transition.ACTION:
                    ActionTransition at = (ActionTransition) t;
                    arg1 = at.ruleIndex;
                    arg2 = at.actionIndex;
                    if (arg2 == -1) {
                        arg2 = 0xFFFF;
                    }
                    arg3 = at.isCtxDependent ? 1 : 0;
                    break;
                case Transition.SET:
                    arg1 = setIndices.get(((SetTransition) t).set);
                    break;
                case Transition.NOT_SET:
                    arg1 = setIndices.get(((SetTransition) t).set);
                    break;
                case Transition.WILDCARD:
                    break;
            }
            data.add(src);
            data.add(trg);
            data.add(edgeType);
            data.add(arg1);
            data.add(arg2);
            data.add(arg3);
        }
    }
    int ndecisions = atn.decisionToState.size();
    data.add(ndecisions);
    for (DecisionState decStartState : atn.decisionToState) {
        data.add(decStartState.stateNumber);
    }
    // 
    if (atn.grammarType == ATNType.LEXER) {
        data.add(atn.lexerActions.length);
        for (LexerAction action : atn.lexerActions) {
            data.add(action.getActionType().ordinal());
            switch(action.getActionType()) {
                case CHANNEL:
                    int channel = ((LexerChannelAction) action).getChannel();
                    data.add(channel != -1 ? channel : 0xFFFF);
                    data.add(0);
                    break;
                case CUSTOM:
                    int ruleIndex = ((LexerCustomAction) action).getRuleIndex();
                    int actionIndex = ((LexerCustomAction) action).getActionIndex();
                    data.add(ruleIndex != -1 ? ruleIndex : 0xFFFF);
                    data.add(actionIndex != -1 ? actionIndex : 0xFFFF);
                    break;
                case MODE:
                    int mode = ((LexerModeAction) action).getMode();
                    data.add(mode != -1 ? mode : 0xFFFF);
                    data.add(0);
                    break;
                case MORE:
                    data.add(0);
                    data.add(0);
                    break;
                case POP_MODE:
                    data.add(0);
                    data.add(0);
                    break;
                case PUSH_MODE:
                    mode = ((LexerPushModeAction) action).getMode();
                    data.add(mode != -1 ? mode : 0xFFFF);
                    data.add(0);
                    break;
                case SKIP:
                    data.add(0);
                    data.add(0);
                    break;
                case TYPE:
                    int type = ((LexerTypeAction) action).getType();
                    data.add(type != -1 ? type : 0xFFFF);
                    data.add(0);
                    break;
                default:
                    String message = String.format(Locale.getDefault(), "The specified lexer action type %s is not valid.", action.getActionType());
                    throw new IllegalArgumentException(message);
            }
        }
    }
    // don't adjust the first value since that's the version number
    for (int i = 1; i < data.size(); i++) {
        if (data.get(i) < Character.MIN_VALUE || data.get(i) > Character.MAX_VALUE) {
            throw new UnsupportedOperationException("Serialized ATN data element " + data.get(i) + " element " + i + " out of range " + (int) Character.MIN_VALUE + ".." + (int) Character.MAX_VALUE);
        }
        int value = (data.get(i) + 2) & 0xFFFF;
        data.set(i, value);
    }
    return data;
}