Mercurial > projects > dwt-addons
annotate dwtx/jface/text/rules/WordRule.d @ 162:1a5b8f8129df
...
| author | Frank Benoit <benoit@tionex.de> |
|---|---|
| date | Mon, 08 Sep 2008 00:51:37 +0200 |
| parents | f70d9508c95c |
| children | eb98a5cbfd78 |
| rev | line source |
|---|---|
| 129 | 1 /******************************************************************************* |
| 2 * Copyright (c) 2000, 2006 IBM Corporation and others. | |
| 3 * All rights reserved. This program and the accompanying materials | |
| 4 * are made available under the terms of the Eclipse Public License v1.0 | |
| 5 * which accompanies this distribution, and is available at | |
| 6 * http://www.eclipse.org/legal/epl-v10.html | |
| 7 * | |
| 8 * Contributors: | |
| 9 * IBM Corporation - initial API and implementation | |
| 10 * Port to the D programming language: | |
| 11 * Frank Benoit <benoit@tionex.de> | |
| 12 *******************************************************************************/ | |
| 13 module dwtx.jface.text.rules.WordRule; | |
| 14 | |
| 131 | 15 import dwtx.jface.text.rules.FastPartitioner; // packageimport |
| 16 import dwtx.jface.text.rules.ITokenScanner; // packageimport | |
| 17 import dwtx.jface.text.rules.Token; // packageimport | |
| 18 import dwtx.jface.text.rules.RuleBasedScanner; // packageimport | |
| 19 import dwtx.jface.text.rules.EndOfLineRule; // packageimport | |
| 20 import dwtx.jface.text.rules.WhitespaceRule; // packageimport | |
| 21 import dwtx.jface.text.rules.WordPatternRule; // packageimport | |
| 22 import dwtx.jface.text.rules.IPredicateRule; // packageimport | |
| 23 import dwtx.jface.text.rules.DefaultPartitioner; // packageimport | |
| 24 import dwtx.jface.text.rules.NumberRule; // packageimport | |
| 25 import dwtx.jface.text.rules.SingleLineRule; // packageimport | |
| 26 import dwtx.jface.text.rules.PatternRule; // packageimport | |
| 27 import dwtx.jface.text.rules.IWordDetector; // packageimport | |
| 28 import dwtx.jface.text.rules.RuleBasedDamagerRepairer; // packageimport | |
| 29 import dwtx.jface.text.rules.ICharacterScanner; // packageimport | |
| 30 import dwtx.jface.text.rules.IRule; // packageimport | |
| 31 import dwtx.jface.text.rules.DefaultDamagerRepairer; // packageimport | |
| 32 import dwtx.jface.text.rules.IToken; // packageimport | |
| 33 import dwtx.jface.text.rules.IPartitionTokenScanner; // packageimport | |
| 34 import dwtx.jface.text.rules.MultiLineRule; // packageimport | |
| 35 import dwtx.jface.text.rules.RuleBasedPartitioner; // packageimport | |
| 36 import dwtx.jface.text.rules.RuleBasedPartitionScanner; // packageimport | |
| 37 import dwtx.jface.text.rules.BufferedRuleBasedScanner; // packageimport | |
| 38 import dwtx.jface.text.rules.IWhitespaceDetector; // packageimport | |
| 39 | |
| 40 | |
| 129 | 41 import dwt.dwthelper.utils; |
| 42 | |
| 43 | |
|
153
f70d9508c95c
Fix java Collection imports
Frank Benoit <benoit@tionex.de>
parents:
134
diff
changeset
|
44 import dwtx.dwtxhelper.Collection; |
|
f70d9508c95c
Fix java Collection imports
Frank Benoit <benoit@tionex.de>
parents:
134
diff
changeset
|
45 |
|
f70d9508c95c
Fix java Collection imports
Frank Benoit <benoit@tionex.de>
parents:
134
diff
changeset
|
46 |
| 129 | 47 |
| 48 import dwtx.core.runtime.Assert; | |
| 49 | |
| 50 | |
| 51 | |
| 52 /** | |
| 53 * An implementation of <code>IRule</code> capable of detecting words | |
| 54 * Word rules also allow for the association of tokens with specific words. | |
| 55 * That is, not only can the rule be used to provide tokens for exact matches, | |
| 56 * but also for the generalized notion of a word in the context in which it is used. | |
| 57 * A word rules uses a word detector to determine what a word is. | |
| 58 * | |
| 59 * @see IWordDetector | |
| 60 */ | |
| 61 public class WordRule : IRule { | |
| 62 | |
| 63 /** Internal setting for the un-initialized column constraint. */ | |
| 162 | 64 protected static const int UNDEFINED= -1; |
| 129 | 65 |
| 66 /** The word detector used by this rule. */ | |
| 67 protected IWordDetector fDetector; | |
| 68 /** The default token to be returned on success and if nothing else has been specified. */ | |
| 69 protected IToken fDefaultToken; | |
| 70 /** The column constraint. */ | |
| 71 protected int fColumn= UNDEFINED; | |
| 72 /** The table of predefined words and token for this rule. */ | |
| 162 | 73 protected Map fWords; |
| 129 | 74 /** Buffer used for pattern detection. */ |
| 162 | 75 private StringBuffer fBuffer; |
| 129 | 76 /** |
| 77 * Tells whether this rule is case sensitive. | |
| 78 * @since 3.3 | |
| 79 */ | |
| 80 private bool fIgnoreCase= false; | |
| 81 | |
| 82 /** | |
| 83 * Creates a rule which, with the help of an word detector, will return the token | |
| 84 * associated with the detected word. If no token has been associated, the scanner | |
| 85 * will be rolled back and an undefined token will be returned in order to allow | |
| 86 * any subsequent rules to analyze the characters. | |
| 87 * | |
| 88 * @param detector the word detector to be used by this rule, may not be <code>null</code> | |
| 89 * @see #addWord(String, IToken) | |
| 90 */ | |
|
133
7d818bd32d63
Fix ctors to this with gvim regexp
Frank Benoit <benoit@tionex.de>
parents:
131
diff
changeset
|
91 public this(IWordDetector detector) { |
| 129 | 92 this(detector, Token.UNDEFINED, false); |
| 93 } | |
| 94 | |
| 95 /** | |
| 96 * Creates a rule which, with the help of a word detector, will return the token | |
| 97 * associated with the detected word. If no token has been associated, the | |
| 98 * specified default token will be returned. | |
| 99 * | |
| 100 * @param detector the word detector to be used by this rule, may not be <code>null</code> | |
| 101 * @param defaultToken the default token to be returned on success | |
| 102 * if nothing else is specified, may not be <code>null</code> | |
| 103 * @see #addWord(String, IToken) | |
| 104 */ | |
|
133
7d818bd32d63
Fix ctors to this with gvim regexp
Frank Benoit <benoit@tionex.de>
parents:
131
diff
changeset
|
105 public this(IWordDetector detector, IToken defaultToken) { |
| 129 | 106 this(detector, defaultToken, false); |
| 107 } | |
| 108 | |
| 109 /** | |
| 110 * Creates a rule which, with the help of a word detector, will return the token | |
| 111 * associated with the detected word. If no token has been associated, the | |
| 112 * specified default token will be returned. | |
| 113 * | |
| 114 * @param detector the word detector to be used by this rule, may not be <code>null</code> | |
| 115 * @param defaultToken the default token to be returned on success | |
| 116 * if nothing else is specified, may not be <code>null</code> | |
| 117 * @param ignoreCase the case sensitivity associated with this rule | |
| 118 * @see #addWord(String, IToken) | |
| 119 * @since 3.3 | |
| 120 */ | |
|
133
7d818bd32d63
Fix ctors to this with gvim regexp
Frank Benoit <benoit@tionex.de>
parents:
131
diff
changeset
|
121 public this(IWordDetector detector, IToken defaultToken, bool ignoreCase) { |
| 162 | 122 fWords= new HashMap(); |
| 123 fBuffer= new StringBuffer(); | |
| 124 | |
| 125 Assert.isNotNull(cast(Object)detector); | |
| 126 Assert.isNotNull(cast(Object)defaultToken); | |
| 129 | 127 |
| 128 fDetector= detector; | |
| 129 fDefaultToken= defaultToken; | |
| 130 fIgnoreCase= ignoreCase; | |
| 131 } | |
| 132 | |
| 133 /** | |
| 134 * Adds a word and the token to be returned if it is detected. | |
| 135 * | |
| 136 * @param word the word this rule will search for, may not be <code>null</code> | |
| 137 * @param token the token to be returned if the word has been found, may not be <code>null</code> | |
| 138 */ | |
| 139 public void addWord(String word, IToken token) { | |
| 162 | 140 //Assert.isNotNull(word); |
| 141 Assert.isNotNull(cast(Object)token); | |
| 129 | 142 |
| 162 | 143 fWords.put(word, cast(Object)token); |
| 129 | 144 } |
| 145 | |
| 146 /** | |
| 147 * Sets a column constraint for this rule. If set, the rule's token | |
| 148 * will only be returned if the pattern is detected starting at the | |
| 149 * specified column. If the column is smaller then 0, the column | |
| 150 * constraint is considered removed. | |
| 151 * | |
| 152 * @param column the column in which the pattern starts | |
| 153 */ | |
| 154 public void setColumnConstraint(int column) { | |
| 155 if (column < 0) | |
| 156 column= UNDEFINED; | |
| 157 fColumn= column; | |
| 158 } | |
| 159 | |
| 160 /* | |
| 161 * @see IRule#evaluate(ICharacterScanner) | |
| 162 */ | |
| 163 public IToken evaluate(ICharacterScanner scanner) { | |
| 164 int c= scanner.read(); | |
| 162 | 165 if (c !is ICharacterScanner.EOF && fDetector.isWordStart(cast(char) c)) { |
| 129 | 166 if (fColumn is UNDEFINED || (fColumn is scanner.getColumn() - 1)) { |
| 167 | |
| 162 | 168 fBuffer.truncate(0); |
| 129 | 169 do { |
| 162 | 170 fBuffer.append(cast(char) c); |
| 129 | 171 c= scanner.read(); |
| 162 | 172 } while (c !is ICharacterScanner.EOF && fDetector.isWordPart(cast(char) c)); |
| 129 | 173 scanner.unread(); |
| 174 | |
| 175 String buffer= fBuffer.toString(); | |
| 134 | 176 IToken token= cast(IToken)fWords.get(buffer); |
| 162 | 177 |
| 129 | 178 if(fIgnoreCase) { |
| 179 Iterator iter= fWords.keySet().iterator(); | |
| 180 while (iter.hasNext()) { | |
| 162 | 181 String key= stringcast(iter.next()); |
| 129 | 182 if(buffer.equalsIgnoreCase(key)) { |
| 134 | 183 token= cast(IToken)fWords.get(key); |
| 129 | 184 break; |
| 185 } | |
| 186 } | |
| 187 } else | |
| 134 | 188 token= cast(IToken)fWords.get(buffer); |
| 162 | 189 |
| 129 | 190 if (token !is null) |
| 191 return token; | |
| 192 | |
| 193 if (fDefaultToken.isUndefined()) | |
| 194 unreadBuffer(scanner); | |
| 195 | |
| 196 return fDefaultToken; | |
| 197 } | |
| 198 } | |
| 199 | |
| 200 scanner.unread(); | |
| 201 return Token.UNDEFINED; | |
| 202 } | |
| 203 | |
| 204 /** | |
| 205 * Returns the characters in the buffer to the scanner. | |
| 206 * | |
| 207 * @param scanner the scanner to be used | |
| 208 */ | |
| 209 protected void unreadBuffer(ICharacterScanner scanner) { | |
| 210 for (int i= fBuffer.length() - 1; i >= 0; i--) | |
| 211 scanner.unread(); | |
| 212 } | |
| 213 | |
| 214 } |