1 /* 2 [The "BSD license"] 3 Copyright (c) 2005-2009 Terence Parr 4 All rights reserved. 5 6 Redistribution and use in source and binary forms, with or without 7 modification, are permitted provided that the following conditions 8 are met: 9 1. Redistributions of source code must retain the above copyright 10 notice, this list of conditions and the following disclaimer. 11 2. Redistributions in binary form must reproduce the above copyright 12 notice, this list of conditions and the following disclaimer in the 13 documentation and/or other materials provided with the distribution. 14 3. The name of the author may not be used to endorse or promote products 15 derived from this software without specific prior written permission. 16 17 THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR 18 IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES 19 OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. 20 IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, 21 INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT 22 NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, 23 DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY 24 THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT 25 (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF 26 THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. 27 */package org.antlr.runtime; 28 29 import java.util.Map; 30 31 /** The set of fields needed by an abstract recognizer to recognize input 32 * and recover from errors etc... As a separate state object, it can be 33 * shared among multiple grammars; e.g., when one grammar imports another. 34 * 35 * These fields are publically visible but the actual state pointer per 36 * parser is protected. 37 */ 38 public class RecognizerSharedState { 39 /** Track the set of token types that can follow any rule invocation. 40 * Stack grows upwards. When it hits the max, it grows 2x in size 41 * and keeps going. 42 */ 43 public BitSet[] following = new BitSet[BaseRecognizer.INITIAL_FOLLOW_STACK_SIZE]; 44 public int _fsp = -1; 45 46 /** This is true when we see an error and before having successfully 47 * matched a token. Prevents generation of more than one error message 48 * per error. 49 */ 50 public boolean errorRecovery = false; 51 52 /** The index into the input stream where the last error occurred. 53 * This is used to prevent infinite loops where an error is found 54 * but no token is consumed during recovery...another error is found, 55 * ad naseum. This is a failsafe mechanism to guarantee that at least 56 * one token/tree node is consumed for two errors. 57 */ 58 public int lastErrorIndex = -1; 59 60 /** In lieu of a return value, this indicates that a rule or token 61 * has failed to match. Reset to false upon valid token match. 62 */ 63 public boolean failed = false; 64 65 /** Did the recognizer encounter a syntax error? Track how many. */ 66 public int syntaxErrors = 0; 67 68 /** If 0, no backtracking is going on. Safe to exec actions etc... 69 * If >0 then it's the level of backtracking. 70 */ 71 public int backtracking = 0; 72 73 /** An array[size num rules] of Map<Integer,Integer> that tracks 74 * the stop token index for each rule. ruleMemo[ruleIndex] is 75 * the memoization table for ruleIndex. For key ruleStartIndex, you 76 * get back the stop token for associated rule or MEMO_RULE_FAILED. 77 * 78 * This is only used if rule memoization is on (which it is by default). 79 */ 80 public Map[] ruleMemo; 81 82 83 // LEXER FIELDS (must be in same state object to avoid casting 84 // constantly in generated code and Lexer object) :( 85 86 87 /** The goal of all lexer rules/methods is to create a token object. 88 * This is an instance variable as multiple rules may collaborate to 89 * create a single token. nextToken will return this object after 90 * matching lexer rule(s). If you subclass to allow multiple token 91 * emissions, then set this to the last token to be matched or 92 * something nonnull so that the auto token emit mechanism will not 93 * emit another token. 94 */ 95 public Token token; 96 97 /** What character index in the stream did the current token start at? 98 * Needed, for example, to get the text for current token. Set at 99 * the start of nextToken. 100 */ 101 public int tokenStartCharIndex = -1; 102 103 /** The line on which the first character of the token resides */ 104 public int tokenStartLine; 105 106 /** The character position of first character within the line */ 107 public int tokenStartCharPositionInLine; 108 109 /** The channel number for the current token */ 110 public int channel; 111 112 /** The token type for the current token */ 113 public int type; 114 115 /** You can set the text for the current token to override what is in 116 * the input char buffer. Use setText() or can set this instance var. 117 */ 118 public String text; 119 120 public RecognizerSharedState() {;} 121 122 public RecognizerSharedState(RecognizerSharedState state) { 123 if ( this.following.length < state.following.length ) { 124 this.following = new BitSet[state.following.length]; 125 } 126 System.arraycopy(state.following, 0, this.following, 0, state.following.length); 127 this._fsp = state._fsp; 128 this.errorRecovery = state.errorRecovery; 129 this.lastErrorIndex = state.lastErrorIndex; 130 this.failed = state.failed; 131 this.syntaxErrors = state.syntaxErrors; 132 this.backtracking = state.backtracking; 133 if ( state.ruleMemo!=null ) { 134 this.ruleMemo = new Map[state.ruleMemo.length]; 135 System.arraycopy(state.ruleMemo, 0, this.ruleMemo, 0, state.ruleMemo.length); 136 } 137 this.token = state.token; 138 this.tokenStartCharIndex = state.tokenStartCharIndex; 139 this.tokenStartCharPositionInLine = state.tokenStartCharPositionInLine; 140 this.channel = state.channel; 141 this.type = state.type; 142 this.text = state.text; 143 } 144 } 145
