Examples with Grammar org.antlr.v4.tool.Grammar used on opensource projects

Example 1 with Grammar

use of org.antlr.v4.tool.Grammar 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.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 2 with Grammar

use of org.antlr.v4.tool.Grammar in project antlr4 by antlr.

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.
	 */
protected IntervalSet getErrorRecoverySet(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 3 with Grammar

use of org.antlr.v4.tool.Grammar in project antlr4 by antlr.

the class Grammar method importTokensFromTokensFile.

public void importTokensFromTokensFile() {
    String vocab = getOptionString("tokenVocab");
    if (vocab != null) {
        TokenVocabParser vparser = new TokenVocabParser(this);
        Map<String, Integer> tokens = vparser.load();
        tool.log("grammar", "tokens=" + tokens);
        for (String t : tokens.keySet()) {
            if (t.charAt(0) == '\'')
                defineStringLiteral(t, tokens.get(t));
            else
                defineTokenName(t, tokens.get(t));
        }
    }
}

Example 4 with Grammar

use of org.antlr.v4.tool.Grammar in project antlr4 by antlr.

the class Grammar method loadImportedGrammars.

public void loadImportedGrammars() {
    if (ast == null)
        return;
    GrammarAST i = (GrammarAST) ast.getFirstChildWithType(ANTLRParser.IMPORT);
    if (i == null)
        return;
    Set<String> visited = new HashSet<>();
    visited.add(this.name);
    importedGrammars = new ArrayList<Grammar>();
    for (Object c : i.getChildren()) {
        GrammarAST t = (GrammarAST) c;
        String importedGrammarName = null;
        if (t.getType() == ANTLRParser.ASSIGN) {
            t = (GrammarAST) t.getChild(1);
            importedGrammarName = t.getText();
        } else if (t.getType() == ANTLRParser.ID) {
            importedGrammarName = t.getText();
        }
        if (visited.contains(importedGrammarName)) {
            // ignore circular refs
            continue;
        }
        Grammar g;
        try {
            g = tool.loadImportedGrammar(this, t);
        } catch (IOException ioe) {
            tool.errMgr.grammarError(ErrorType.ERROR_READING_IMPORTED_GRAMMAR, importedGrammarName, t.getToken(), importedGrammarName, name);
            continue;
        }
        // did it come back as error node or missing?
        if (g == null)
            continue;
        g.parent = this;
        importedGrammars.add(g);
        // recursively pursue any imports in this import
        g.loadImportedGrammars();
    }
}

Example 5 with Grammar

use of org.antlr.v4.tool.Grammar in project antlr4 by antlr.

the class GrammarParserInterpreter method getAllPossibleParseTrees.

/** Given an ambiguous parse information, return the list of ambiguous parse trees.
	 *  An ambiguity occurs when a specific token sequence can be recognized
	 *  in more than one way by the grammar. These ambiguities are detected only
	 *  at decision points.
	 *
	 *  The list of trees includes the actual interpretation (that for
	 *  the minimum alternative number) and all ambiguous alternatives.
	 *  The actual interpretation is always first.
	 *
	 *  This method reuses the same physical input token stream used to
	 *  detect the ambiguity by the original parser in the first place.
	 *  This method resets/seeks within but does not alter originalParser.
	 *
	 *  The trees are rooted at the node whose start..stop token indices
	 *  include the start and stop indices of this ambiguity event. That is,
	 *  the trees returned will always include the complete ambiguous subphrase
	 *  identified by the ambiguity event.  The subtrees returned will
	 *  also always contain the node associated with the overridden decision.
	 *
	 *  Be aware that this method does NOT notify error or parse listeners as
	 *  it would trigger duplicate or otherwise unwanted events.
	 *
	 *  This uses a temporary ParserATNSimulator and a ParserInterpreter
	 *  so we don't mess up any statistics, event lists, etc...
	 *  The parse tree constructed while identifying/making ambiguityInfo is
	 *  not affected by this method as it creates a new parser interp to
	 *  get the ambiguous interpretations.
	 *
	 *  Nodes in the returned ambig trees are independent of the original parse
	 *  tree (constructed while identifying/creating ambiguityInfo).
	 *
	 *  @since 4.5.1
	 *
	 *  @param g              From which grammar should we drive alternative
	 *                        numbers and alternative labels.
	 *
	 *  @param originalParser The parser used to create ambiguityInfo; it
	 *                        is not modified by this routine and can be either
	 *                        a generated or interpreted parser. It's token
	 *                        stream *is* reset/seek()'d.
	 *  @param tokens		  A stream of tokens to use with the temporary parser.
	 *                        This will often be just the token stream within the
	 *                        original parser but here it is for flexibility.
	 *
	 *  @param decision       Which decision to try different alternatives for.
	 *
	 *  @param alts           The set of alternatives to try while re-parsing.
	 *
	 *  @param startIndex	  The index of the first token of the ambiguous
	 *                        input or other input of interest.
	 *
	 *  @param stopIndex      The index of the last token of the ambiguous input.
	 *                        The start and stop indexes are used primarily to
	 *                        identify how much of the resulting parse tree
	 *                        to return.
	 *
	 *  @param startRuleIndex The start rule for the entire grammar, not
	 *                        the ambiguous decision. We re-parse the entire input
	 *                        and so we need the original start rule.
	 *
	 *  @return               The list of all possible interpretations of
	 *                        the input for the decision in ambiguityInfo.
	 *                        The actual interpretation chosen by the parser
	 *                        is always given first because this method
	 *                        retests the input in alternative order and
	 *                        ANTLR always resolves ambiguities by choosing
	 *                        the first alternative that matches the input.
	 *                        The subtree returned
	 *
	 *  @throws RecognitionException Throws upon syntax error while matching
	 *                               ambig input.
	 */
public static List<ParserRuleContext> getAllPossibleParseTrees(Grammar g, Parser originalParser, TokenStream tokens, int decision, BitSet alts, int startIndex, int stopIndex, int startRuleIndex) throws RecognitionException {
    List<ParserRuleContext> trees = new ArrayList<ParserRuleContext>();
    // Create a new parser interpreter to parse the ambiguous subphrase
    ParserInterpreter parser = deriveTempParserInterpreter(g, originalParser, tokens);
    if (stopIndex >= (tokens.size() - 1)) {
        // if we are pointing at EOF token
        // EOF is not in tree, so must be 1 less than last non-EOF token
        stopIndex = tokens.size() - 2;
    }
    // get ambig trees
    int alt = alts.nextSetBit(0);
    while (alt >= 0) {
        // re-parse entire input for all ambiguous alternatives
        // (don't have to do first as it's been parsed, but do again for simplicity
        //  using this temp parser.)
        parser.reset();
        parser.addDecisionOverride(decision, startIndex, alt);
        ParserRuleContext t = parser.parse(startRuleIndex);
        GrammarInterpreterRuleContext ambigSubTree = (GrammarInterpreterRuleContext) Trees.getRootOfSubtreeEnclosingRegion(t, startIndex, stopIndex);
        // Use higher of overridden decision tree or tree enclosing all tokens
        if (Trees.isAncestorOf(parser.getOverrideDecisionRoot(), ambigSubTree)) {
            ambigSubTree = (GrammarInterpreterRuleContext) parser.getOverrideDecisionRoot();
        }
        trees.add(ambigSubTree);
        alt = alts.nextSetBit(alt + 1);
    }
    return trees;
}