1 // [The "BSD licence"] 2 // Copyright (c) 2006-2007 Kay Roepke 2010 Alan Condit 3 // All rights reserved. 4 // 5 // Redistribution and use in source and binary forms, with or without 6 // modification, are permitted provided that the following conditions 7 // are met: 8 // 1. Redistributions of source code must retain the above copyright 9 // notice, this list of conditions and the following disclaimer. 10 // 2. Redistributions in binary form must reproduce the above copyright 11 // notice, this list of conditions and the following disclaimer in the 12 // documentation and/or other materials provided with the distribution. 13 // 3. The name of the author may not be used to endorse or promote products 14 // derived from this software without specific prior written permission. 15 // 16 // THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR 17 // IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES 18 // OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. 19 // IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, 20 // INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT 21 // NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, 22 // DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY 23 // THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT 24 // (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF 25 // THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. 26 27 28 #import <Foundation/Foundation.h> 29 30 #import "IntStream.h" 31 #import "AMutableArray.h" 32 33 // This is an abstract superclass for lexers and parsers. 34 35 #define ANTLR_MEMO_RULE_FAILED -2 36 #define ANTLR_MEMO_RULE_UNKNOWN -1 37 #define ANTLR_INITIAL_FOLLOW_STACK_SIZE 100 38 39 #import "MapElement.h" 40 #import "ANTLRBitSet.h" 41 #import "Token.h" 42 #import "RecognizerSharedState.h" 43 #import "RecognitionException.h" 44 #import "MissingTokenException.h" 45 #import "MismatchedTokenException.h" 46 #import "MismatchedTreeNodeException.h" 47 #import "UnwantedTokenException.h" 48 #import "NoViableAltException.h" 49 #import "EarlyExitException.h" 50 #import "MismatchedSetException.h" 51 #import "MismatchedNotSetException.h" 52 #import "FailedPredicateException.h" 53 54 @interface BaseRecognizer : NSObject { 55 __strong RecognizerSharedState *state; // the state of this recognizer. Might be shared with other recognizers, e.g. in grammar import scenarios. 56 __strong NSString *grammarFileName; // where did the grammar come from. filled in by codegeneration 57 __strong NSString *sourceName; 58 __strong AMutableArray *tokenNames; 59 } 60 61 + (void) initialize; 62 63 + (BaseRecognizer *) newBaseRecognizer; 64 + (BaseRecognizer *) newBaseRecognizerWithRuleLen:(NSInteger)aLen; 65 + (BaseRecognizer *) newBaseRecognizer:(RecognizerSharedState *)aState; 66 67 + (AMutableArray *)getTokenNames; 68 + (void)setTokenNames:(NSArray *)aTokNamArray; 69 + (void)setGrammarFileName:(NSString *)aFileName; 70 71 - (id) init; 72 - (id) initWithLen:(NSInteger)aLen; 73 - (id) initWithState:(RecognizerSharedState *)aState; 74 75 - (void) dealloc; 76 77 // simple accessors 78 - (NSInteger) getBacktrackingLevel; 79 - (void) setBacktrackingLevel:(NSInteger) level; 80 81 - (BOOL) getFailed; 82 - (void) setFailed: (BOOL) flag; 83 84 - (RecognizerSharedState *) getState; 85 - (void) setState:(RecognizerSharedState *) theState; 86 87 // reset this recognizer - might be extended by codegeneration/grammar 88 - (void) reset; 89 90 /** Match needs to return the current input symbol, which gets put 91 * into the label for the associated token ref; e.g., x=ID. Token 92 * and tree parsers need to return different objects. Rather than test 93 * for input stream type or change the IntStream interface, I use 94 * a simple method to ask the recognizer to tell me what the current 95 * input symbol is. 96 * 97 * This is ignored for lexers. 98 */ 99 - (id) input; 100 101 - (void)skip; 102 103 // do actual matching of tokens/characters 104 - (id) match:(id<IntStream>)anInput TokenType:(NSInteger)ttype Follow:(ANTLRBitSet *)follow; 105 - (void) matchAny:(id<IntStream>)anInput; 106 - (BOOL) mismatchIsUnwantedToken:(id<IntStream>)anInput TokenType:(NSInteger) ttype; 107 - (BOOL) mismatchIsMissingToken:(id<IntStream>)anInput Follow:(ANTLRBitSet *)follow; 108 109 // error reporting and recovery 110 - (void) reportError:(RecognitionException *)e; 111 - (void) displayRecognitionError:(AMutableArray *)theTokNams Exception:(RecognitionException *)e; 112 - (NSString *)getErrorMessage:(RecognitionException *)e TokenNames:(AMutableArray *)theTokNams; 113 - (NSInteger) getNumberOfSyntaxErrors; 114 - (NSString *)getErrorHeader:(RecognitionException *)e; 115 - (NSString *)getTokenErrorDisplay:(id<Token>)t; 116 - (void) emitErrorMessage:(NSString *)msg; 117 - (void) recover:(id<IntStream>)anInput Exception:(RecognitionException *)e; 118 119 // begin hooks for debugger 120 - (void) beginResync; 121 - (void) endResync; 122 // end hooks for debugger 123 124 // compute the bitsets necessary to do matching and recovery 125 - (ANTLRBitSet *)computeErrorRecoverySet; 126 - (ANTLRBitSet *)computeContextSensitiveRuleFOLLOW; 127 - (ANTLRBitSet *)combineFollows:(BOOL) exact; 128 129 - (id<Token>) recoverFromMismatchedToken:(id<IntStream>)anInput 130 TokenType:(NSInteger)ttype 131 Follow:(ANTLRBitSet *)follow; 132 133 - (id<Token>)recoverFromMismatchedSet:(id<IntStream>)anInput 134 Exception:(RecognitionException *)e 135 Follow:(ANTLRBitSet *)follow; 136 137 - (id) getCurrentInputSymbol:(id<IntStream>)anInput; 138 - (id) getMissingSymbol:(id<IntStream>)anInput 139 Exception:(RecognitionException *)e 140 TokenType:(NSInteger) expectedTokenType 141 Follow:(ANTLRBitSet *)follow; 142 143 // helper methods for recovery. try to resync somewhere 144 - (void) consumeUntilTType:(id<IntStream>)anInput TokenType:(NSInteger)ttype; 145 - (void) consumeUntilFollow:(id<IntStream>)anInput Follow:(ANTLRBitSet *)bitSet; 146 - (void) pushFollow:(ANTLRBitSet *)fset; 147 - (ANTLRBitSet *)popFollow; 148 149 // to be used by the debugger to do reporting. maybe hook in incremental stuff here, too. 150 - (AMutableArray *) getRuleInvocationStack; 151 - (AMutableArray *) getRuleInvocationStack:(RecognitionException *)exception 152 Recognizer:(NSString *)recognizerClassName; 153 154 - (AMutableArray *) getTokenNames; 155 - (NSString *)getGrammarFileName; 156 - (NSString *)getSourceName; 157 - (AMutableArray *) toStrings:(NSArray *)tokens; 158 // support for memoization 159 - (NSInteger) getRuleMemoization:(NSInteger)ruleIndex StartIndex:(NSInteger)ruleStartIndex; 160 - (BOOL) alreadyParsedRule:(id<IntStream>)anInput RuleIndex:(NSInteger)ruleIndex; 161 - (void) memoize:(id<IntStream>)anInput 162 RuleIndex:(NSInteger)ruleIndex 163 StartIndex:(NSInteger)ruleStartIndex; 164 - (NSInteger) getRuleMemoizationCacheSize; 165 - (void)traceIn:(NSString *)ruleName Index:(NSInteger)ruleIndex Object:(id)inputSymbol; 166 - (void)traceOut:(NSString *)ruleName Index:(NSInteger)ruleIndex Object:(id)inputSymbol; 167 168 169 // support for syntactic predicates. these are called indirectly to support funky stuff in grammars, 170 // like supplying selectors instead of writing code directly into the actions of the grammar. 171 - (BOOL) evaluateSyntacticPredicate:(SEL)synpredFragment; 172 // stream:(id<IntStream>)anInput; 173 174 @property (retain) RecognizerSharedState *state; 175 @property (retain) NSString *grammarFileName; 176 @property (retain) NSString *sourceName; 177 @property (retain) AMutableArray *tokenNames; 178 179 @end 180