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

Example 31 with ATNState

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

the class LL1Analyzer method getDecisionLookahead.

/**
 * Calculates the SLL(1) expected lookahead set for each outgoing transition
 * of an {@link ATNState}. The returned array has one element for each
 * outgoing transition in {@code s}. If the closure from transition
 * <em>i</em> leads to a semantic predicate before matching a symbol, the
 * element at index <em>i</em> of the result will be {@code null}.
 *
 * @param s the ATN state
 * @return the expected symbols for each outgoing transition of {@code s}.
 */
@Nullable
public IntervalSet[] getDecisionLookahead(@Nullable ATNState s) {
    // System.out.println("LOOK("+s.stateNumber+")");
    if (s == null) {
        return null;
    }
    IntervalSet[] look = new IntervalSet[s.getNumberOfTransitions()];
    for (int alt = 0; alt < s.getNumberOfTransitions(); alt++) {
        look[alt] = new IntervalSet();
        Set<ATNConfig> lookBusy = new HashSet<ATNConfig>();
        // fail to get lookahead upon pred
        boolean seeThruPreds = false;
        _LOOK(s.transition(alt).target, null, PredictionContext.EMPTY_LOCAL, look[alt], lookBusy, new BitSet(), seeThruPreds, false);
        // or we had a predicate when we !seeThruPreds
        if (look[alt].size() == 0 || look[alt].contains(HIT_PRED)) {
            look[alt] = null;
        }
    }
    return look;
}

Example 32 with ATNState

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

the class DFASerializer method getContextLabel.

protected String getContextLabel(int i) {
    if (i == PredictionContext.EMPTY_FULL_STATE_KEY) {
        return "ctx:EMPTY_FULL";
    } else if (i == PredictionContext.EMPTY_LOCAL_STATE_KEY) {
        return "ctx:EMPTY_LOCAL";
    }
    if (atn != null && i > 0 && i <= atn.states.size()) {
        ATNState state = atn.states.get(i);
        int ruleIndex = state.ruleIndex;
        if (ruleNames != null && ruleIndex >= 0 && ruleIndex < ruleNames.length) {
            return "ctx:" + String.valueOf(i) + "(" + ruleNames[ruleIndex] + ")";
        }
    }
    return "ctx:" + String.valueOf(i);
}

Example 33 with ATNState

use of org.antlr.v4.runtime.atn.ATNState 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;
}

Example 34 with ATNState

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

the class LexerATNSimulator method matchATN.

protected int matchATN(CharStream input) {
    ATNState startState = atn.modeToStartState.get(mode);
    if (debug) {
        System.out.format(Locale.getDefault(), "matchATN mode %d start: %s\n", mode, startState);
    }
    int old_mode = mode;
    ATNConfigSet s0_closure = computeStartState(input, startState);
    boolean suppressEdge = s0_closure.hasSemanticContext;
    s0_closure.hasSemanticContext = false;
    DFAState next = addDFAState(s0_closure);
    if (!suppressEdge) {
        decisionToDFA[mode].s0 = next;
    }
    int predict = execATN(input, next);
    if (debug) {
        System.out.format(Locale.getDefault(), "DFA after matchATN: %s\n", decisionToDFA[old_mode].toLexerString());
    }
    return predict;
}

Example 35 with ATNState

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

the class ATN method getExpectedTokens.

/**
 * Computes the set of input symbols which could follow ATN state number
 * {@code stateNumber} in the specified full {@code context}. This method
 * considers the complete parser context, but does not evaluate semantic
 * predicates (i.e. all predicates encountered during the calculation are
 * assumed true). If a path in the ATN exists from the starting state to the
 * {@link RuleStopState} of the outermost context without matching any
 * symbols, {@link Token#EOF} is added to the returned set.
 *
 * <p>If {@code context} is {@code null}, it is treated as {@link ParserRuleContext#EMPTY}.</p>
 *
 * Note that this does NOT give you the set of all tokens that could
 * appear at a given token position in the input phrase.  In other words,
 * it does not answer:
 *
 *   "Given a specific partial input phrase, return the set of all tokens
 *    that can follow the last token in the input phrase."
 *
 * The big difference is that with just the input, the parser could
 * land right in the middle of a lookahead decision. Getting
 * all *possible* tokens given a partial input stream is a separate
 * computation. See https://github.com/antlr/antlr4/issues/1428
 *
 * For this function, we are specifying an ATN state and call stack to compute
 * what token(s) can come next and specifically: outside of a lookahead decision.
 * That is what you want for error reporting and recovery upon parse error.
 *
 * @param stateNumber the ATN state number
 * @param context the full parse context
 * @return The set of potentially valid input symbols which could follow the
 * specified state in the specified context.
 * @throws IllegalArgumentException if the ATN does not contain a state with
 * number {@code stateNumber}
 */
public IntervalSet getExpectedTokens(int stateNumber, RuleContext context) {
    if (stateNumber < 0 || stateNumber >= states.size()) {
        throw new IllegalArgumentException("Invalid state number.");
    }
    RuleContext ctx = context;
    ATNState s = states.get(stateNumber);
    IntervalSet following = nextTokens(s);
    if (!following.contains(Token.EPSILON)) {
        return following;
    }
    IntervalSet expected = new IntervalSet();
    expected.addAll(following);
    expected.remove(Token.EPSILON);
    while (ctx != null && ctx.invokingState >= 0 && following.contains(Token.EPSILON)) {
        ATNState invokingState = states.get(ctx.invokingState);
        RuleTransition rt = (RuleTransition) invokingState.transition(0);
        following = nextTokens(rt.followState);
        expected.addAll(following);
        expected.remove(Token.EPSILON);
        ctx = ctx.parent;
    }
    if (following.contains(Token.EPSILON)) {
        expected.add(Token.EOF);
    }
    return expected;
}