use of org.antlr.v4.runtime.Parser in project antlr4 by antlr.
the class DefaultErrorStrategy method reportMissingToken.
/**
* This method is called to report a syntax error which requires the
* insertion of a missing token into the input stream. At the time this
* method is called, the missing token has not yet been inserted. When this
* method returns, {@code recognizer} is in error recovery mode.
*
* <p>This method is called when {@link #singleTokenInsertion} identifies
* single-token insertion as a viable recovery strategy for a mismatched
* input error.</p>
*
* <p>The default implementation simply returns if the handler is already in
* error recovery mode. Otherwise, it calls {@link #beginErrorCondition} to
* enter error recovery mode, followed by calling
* {@link Parser#notifyErrorListeners}.</p>
*
* @param recognizer the parser instance
*/
protected void reportMissingToken(Parser recognizer) {
if (inErrorRecoveryMode(recognizer)) {
return;
}
beginErrorCondition(recognizer);
Token t = recognizer.getCurrentToken();
IntervalSet expecting = getExpectedTokens(recognizer);
String msg = "missing " + expecting.toString(recognizer.getVocabulary()) + " at " + getTokenErrorDisplay(t);
recognizer.notifyErrorListeners(t, msg, null);
}
use of org.antlr.v4.runtime.Parser in project antlr4 by antlr.
the class DefaultErrorStrategy method getMissingSymbol.
/** Conjure up a missing token during error recovery.
*
* The recognizer attempts to recover from single missing
* symbols. But, actions might refer to that missing symbol.
* For example, x=ID {f($x);}. The action clearly assumes
* that there has been an identifier matched previously and that
* $x points at that token. If that token is missing, but
* the next token in the stream is what we want we assume that
* this token is missing and we keep going. Because we
* have to return some token to replace the missing token,
* we have to conjure one up. This method gives the user control
* over the tokens returned for missing tokens. Mostly,
* you will want to create something special for identifier
* tokens. For literals such as '{' and ',', the default
* action in the parser or tree parser works. It simply creates
* a CommonToken of the appropriate type. The text will be the token.
* If you change what tokens must be created by the lexer,
* override this method to create the appropriate tokens.
*/
protected Token getMissingSymbol(Parser recognizer) {
Token currentSymbol = recognizer.getCurrentToken();
IntervalSet expecting = getExpectedTokens(recognizer);
int expectedTokenType = Token.INVALID_TYPE;
if (!expecting.isNil()) {
// get any element
expectedTokenType = expecting.getMinElement();
}
String tokenText;
if (expectedTokenType == Token.EOF)
tokenText = "<missing EOF>";
else
tokenText = "<missing " + recognizer.getVocabulary().getDisplayName(expectedTokenType) + ">";
Token current = currentSymbol;
Token lookback = recognizer.getInputStream().LT(-1);
if (current.getType() == Token.EOF && lookback != null) {
current = lookback;
}
return recognizer.getTokenFactory().create(new Pair<TokenSource, CharStream>(current.getTokenSource(), current.getTokenSource().getInputStream()), expectedTokenType, tokenText, Token.DEFAULT_CHANNEL, -1, -1, current.getLine(), current.getCharPositionInLine());
}
use of org.antlr.v4.runtime.Parser in project antlr4 by antlr.
the class DefaultErrorStrategy method sync.
/**
* The default implementation of {@link ANTLRErrorStrategy#sync} makes sure
* that the current lookahead symbol is consistent with what were expecting
* at this point in the ATN. You can call this anytime but ANTLR only
* generates code to check before subrules/loops and each iteration.
*
* <p>Implements Jim Idle's magic sync mechanism in closures and optional
* subrules. E.g.,</p>
*
* <pre>
* a : sync ( stuff sync )* ;
* sync : {consume to what can follow sync} ;
* </pre>
*
* At the start of a sub rule upon error, {@link #sync} performs single
* token deletion, if possible. If it can't do that, it bails on the current
* rule and uses the default error recovery, which consumes until the
* resynchronization set of the current rule.
*
* <p>If the sub rule is optional ({@code (...)?}, {@code (...)*}, or block
* with an empty alternative), then the expected set includes what follows
* the subrule.</p>
*
* <p>During loop iteration, it consumes until it sees a token that can start a
* sub rule or what follows loop. Yes, that is pretty aggressive. We opt to
* stay in the loop as long as possible.</p>
*
* <p><strong>ORIGINS</strong></p>
*
* <p>Previous versions of ANTLR did a poor job of their recovery within loops.
* A single mismatch token or missing token would force the parser to bail
* out of the entire rules surrounding the loop. So, for rule</p>
*
* <pre>
* classDef : 'class' ID '{' member* '}'
* </pre>
*
* input with an extra token between members would force the parser to
* consume until it found the next class definition rather than the next
* member definition of the current class.
*
* <p>This functionality cost a little bit of effort because the parser has to
* compare token set at the start of the loop and at each iteration. If for
* some reason speed is suffering for you, you can turn off this
* functionality by simply overriding this method as a blank { }.</p>
*/
@Override
public void sync(Parser recognizer) throws RecognitionException {
ATNState s = recognizer.getInterpreter().atn.states.get(recognizer.getState());
// If already recovering, don't try to sync
if (inErrorRecoveryMode(recognizer)) {
return;
}
TokenStream tokens = recognizer.getInputStream();
int la = tokens.LA(1);
// try cheaper subset first; might get lucky. seems to shave a wee bit off
IntervalSet nextTokens = recognizer.getATN().nextTokens(s);
if (nextTokens.contains(Token.EPSILON) || nextTokens.contains(la)) {
return;
}
switch(s.getStateType()) {
case ATNState.BLOCK_START:
case ATNState.STAR_BLOCK_START:
case ATNState.PLUS_BLOCK_START:
case ATNState.STAR_LOOP_ENTRY:
// report error and recover if possible
if (singleTokenDeletion(recognizer) != null) {
return;
}
throw new InputMismatchException(recognizer);
case ATNState.PLUS_LOOP_BACK:
case ATNState.STAR_LOOP_BACK:
// System.err.println("at loop back: "+s.getClass().getSimpleName());
reportUnwantedToken(recognizer);
IntervalSet expecting = recognizer.getExpectedTokens();
IntervalSet whatFollowsLoopIterationOrRule = expecting.or(getErrorRecoverySet(recognizer));
consumeUntil(recognizer, whatFollowsLoopIterationOrRule);
break;
default:
// do nothing if we can't identify the exact kind of ATN state
break;
}
}
use of org.antlr.v4.runtime.Parser in project antlr4 by antlr.
the class Parser method getATNWithBypassAlts.
/**
* The ATN with bypass alternatives is expensive to create so we create it
* lazily.
*
* @throws UnsupportedOperationException if the current parser does not
* implement the {@link #getSerializedATN()} method.
*/
public ATN getATNWithBypassAlts() {
String serializedAtn = getSerializedATN();
if (serializedAtn == null) {
throw new UnsupportedOperationException("The current parser does not support an ATN with bypass alternatives.");
}
synchronized (bypassAltsAtnCache) {
ATN result = bypassAltsAtnCache.get(serializedAtn);
if (result == null) {
ATNDeserializationOptions deserializationOptions = new ATNDeserializationOptions();
deserializationOptions.setGenerateRuleBypassTransitions(true);
result = new ATNDeserializer(deserializationOptions).deserialize(serializedAtn.toCharArray());
bypassAltsAtnCache.put(serializedAtn, result);
}
return result;
}
}
use of org.antlr.v4.runtime.Parser in project antlr4 by antlr.
the class ParserRuleContext method addChild.
/** Add a child to this node based upon matchedToken. It
* creates a TerminalNodeImpl rather than using
* {@link Parser#createTerminalNode(ParserRuleContext, Token)}. I'm leaving this
* in for compatibility but the parser doesn't use this anymore.
*/
@Deprecated
public TerminalNode addChild(Token matchedToken) {
TerminalNodeImpl t = new TerminalNodeImpl(matchedToken);
addAnyChild(t);
t.setParent(this);
return t;
}
Aggregations