Skip to main content
aboutsummaryrefslogtreecommitdiffstats
blob: ad683e74238e502c06f5c1ebd78051275d10e2ea (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
/*******************************************************************************
 * Copyright (c) 2000, 2017 IBM Corporation and others.
 * All rights reserved. This program and the accompanying materials
 * are made available under the terms of the Eclipse Public License v1.0
 * which accompanies this distribution, and is available at
 * http://www.eclipse.org/legal/epl-v10.html
 *
 * Contributors:
 *     IBM Corporation - initial API and implementation
 *******************************************************************************/
package org.eclipse.team.internal.core;


import java.util.Vector;

/**
 * A string pattern matcher. Supports '*' and '?' wildcards.
 * Note: code copied from org.eclipse.jdt.internal.core.util.StringMatcher on April 3, 2001
 * (version 0.1 - 010901H18 [rename jbl]). Sync'ed on November 4, 2009 (revision 1.17).
 *
 */
public class StringMatcher {
	protected String fPattern;
	protected int fLength; // pattern length
	protected boolean fIgnoreWildCards;
	protected boolean fIgnoreCase;
	protected boolean fHasLeadingStar;
	protected boolean fHasTrailingStar;
	protected String fSegments[]; //the given pattern is split into * separated segments

	/* boundary value beyond which we don't need to search in the text */
	protected int fBound = 0;
	private boolean fPathPattern;


	protected static final char fSingleWildCard = '\u0000';

	public static class Position {
		int start; //inclusive
		int end; //exclusive
		public Position(int start, int end) {
			this.start = start;
			this.end = end;
		}
		public int getStart() {
			return start;
		}
		public int getEnd() {
			return end;
		}
	}

	/**
	 * StringMatcher constructor takes in a String object that is a simple
	 * pattern. The pattern may contain '*' for 0 and many characters and
	 * '?' for exactly one character.
	 *
	 * Literal '*' and '?' characters must be escaped in the pattern
	 * e.g., "\*" means literal "*", etc.
	 *
	 * Escaping any other character (including the escape character itself),
	 * just results in that character in the pattern.
	 * e.g., "\a" means "a" and "\\" means "\"
	 *
	 * If invoking the StringMatcher with string literals in Java, don't forget
	 * escape characters are represented by "\\".
	 *
	 * @param pattern the pattern to match text against
	 * @param ignoreCase if true, case is ignored
	 * @param ignoreWildCards if true, wild cards and their escape sequences are ignored
	 * 		  (everything is taken literally).
	 */
	public StringMatcher(String pattern, boolean ignoreCase, boolean ignoreWildCards) {
		if (pattern == null)
			throw new IllegalArgumentException();
		fIgnoreCase = ignoreCase;
		fIgnoreWildCards = ignoreWildCards;
		fPattern= pattern;
		fLength = pattern.length();
		fPathPattern = pattern.indexOf('/') != -1;

		if (fIgnoreWildCards) {
			parseNoWildCards();
		} else {
			parseWildCards();
		}
	}

	/**
	 * Find the first occurrence of the pattern between <code>start</code>(inclusive)
	 * and <code>end</code>(exclusive).
	 * @param text the String object to search in
	 * @param start the starting index of the search range, inclusive
	 * @param end the ending index of the search range, exclusive
	 * @return an <code>StringMatcher.Position</code> object that keeps the starting
	 * (inclusive) and ending positions (exclusive) of the first occurrence of the
	 * pattern in the specified range of the text; return null if not found or subtext
	 * is empty (start==end). A pair of zeros is returned if pattern is empty string
	 * Note that for pattern like "*abc*" with leading and trailing stars, position of "abc"
	 * is returned. For a pattern like"*??*" in text "abcdf", (1,3) is returned
	 */

	public StringMatcher.Position find(String text, int start, int end) {
		if (fPattern  == null|| text == null)
			throw new IllegalArgumentException();

		int tlen = text.length();
		if (start < 0)
			start = 0;
		if (end > tlen)
			end = tlen;
		if (end < 0 ||start >= end )
			return null;
		if (fLength == 0)
			return new Position(start, start);
		if (fIgnoreWildCards) {
			int x = posIn(text, start, end);
			if (x < 0)
				return null;
			return new Position(x, x+fLength);
		}

		int segCount = fSegments.length;
		if (segCount == 0)//pattern contains only '*'(s)
			return new Position (start, end);

		int curPos = start;
		int matchStart = -1;
		int i;
		for (i = 0; i < segCount && curPos < end; ++i) {
			String current = fSegments[i];
			int nextMatch = regExpPosIn(text, curPos, end, current);
			if (nextMatch < 0 )
				return null;
			if(i == 0)
				matchStart = nextMatch;
			curPos = nextMatch + current.length();
		}
		if (i < segCount)
			return null;
		return new Position(matchStart, curPos);
	}

	/**
	 * match the given <code>text</code> with the pattern
	 * @return <code>true</code> if matched otherwise <code>false</code>
	 * @param text a String object
	 */
	public boolean match(String text) {
		return match(text, 0, text.length());
	}
	/**
	 * Given the starting (inclusive) and the ending (exclusive) positions in the
	 * <code>text</code>, determine if the given substring matches with aPattern
	 * @return true if the specified portion of the text matches the pattern
	 * @param text a String object that contains the substring to match
	 * @param start marks the starting position (inclusive) of the substring
	 * @param end marks the ending index (exclusive) of the substring
	 */
	public boolean match(String text, int start, int end) {
		if (null == text)
			throw new IllegalArgumentException();

		if (start > end)
			return false;

		if (fIgnoreWildCards)
			return (end - start == fLength) && fPattern.regionMatches(fIgnoreCase, 0, text, start, fLength);
		int segCount= fSegments.length;
		if (segCount == 0 && (fHasLeadingStar || fHasTrailingStar))  // pattern contains only '*'(s)
			return true;
		if (start == end)
			return fLength == 0;
		if (fLength == 0)
			return start == end;

		int tlen= text.length();
		if (start < 0)
			start= 0;
		if (end > tlen)
			end= tlen;

		int tCurPos= start;
		int bound= end - fBound;
		if ( bound < 0)
			return false;
		int i=0;
		String current= fSegments[i];
		int segLength= current.length();

		/* process first segment */
		if (!fHasLeadingStar){
			if(!regExpRegionMatches(text, start, current, 0, segLength)) {
				return false;
			} else {
				++i;
				tCurPos= tCurPos + segLength;
			}
		}
		if ((fSegments.length == 1) && (!fHasLeadingStar) && (!fHasTrailingStar)) {
			// only one segment to match, no wildcards specified
			return tCurPos == end;
		}
		/* process middle segments */
		while (i < segCount) {
			current= fSegments[i];
			int currentMatch;
			int k= current.indexOf(fSingleWildCard);
			if (k < 0) {
				currentMatch= textPosIn(text, tCurPos, end, current);
				if (currentMatch < 0)
					return false;
			} else {
				currentMatch= regExpPosIn(text, tCurPos, end, current);
				if (currentMatch < 0)
					return false;
			}
			tCurPos= currentMatch + current.length();
			i++;
		}

		/* process final segment */
		if (!fHasTrailingStar && tCurPos != end) {
			int clen= current.length();
			return regExpRegionMatches(text, end - clen, current, 0, clen);
		}
		return i == segCount ;
	}

	/**
	 * check existence of '/' in the pattern.
	 * @return <b>true</b> if pattern contains '/'
	 */
	public boolean isPathPattern() {
		return fPathPattern;
	}

	/**
	 * This method parses the given pattern into segments seperated by wildcard '*' characters.
	 * Since wildcards are not being used in this case, the pattern consists of a single segment.
	 */
	private void parseNoWildCards() {
		fSegments = new String[1];
		fSegments[0] = fPattern;
		fBound = fLength;
	}
	/**
	 * Parses the given pattern into segments seperated by wildcard '*' characters.
	 */
	private void parseWildCards() {
		if(fPattern.startsWith("*"))//$NON-NLS-1$
			fHasLeadingStar = true;
		if(fPattern.endsWith("*")) {//$NON-NLS-1$
			/* make sure it's not an escaped wildcard */
			if (fLength > 1 && fPattern.charAt(fLength - 2) != '\\') {
				fHasTrailingStar = true;
			}
		}

		Vector<String> temp = new Vector<>();

		int pos = 0;
		StringBuffer buf = new StringBuffer();
		while (pos < fLength) {
			char c = fPattern.charAt(pos++);
			switch (c) {
				case '\\':
					if (pos >= fLength) {
						buf.append(c);
					} else {
						char next = fPattern.charAt(pos++);
						/* if it's an escape sequence */
						if (next == '*' || next == '?' || next == '\\') {
							buf.append(next);
						} else {
							/* not an escape sequence, just insert literally */
							buf.append(c);
							buf.append(next);
						}
					}
				break;
				case '*':
					if (buf.length() > 0) {
						/* new segment */
						temp.addElement(buf.toString());
						fBound += buf.length();
						buf.setLength(0);
					}
				break;
				case '?':
					/* append special character representing single match wildcard */
					buf.append(fSingleWildCard);
				break;
				default:
					buf.append(c);
			}
		}

		/* add last buffer to segment list */
		if (buf.length() > 0) {
			temp.addElement(buf.toString());
			fBound += buf.length();
		}

		fSegments = new String[temp.size()];
		temp.copyInto(fSegments);
	}
	/**
	 * @param text a string which contains no wildcard
	 * @param start the starting index in the text for search, inclusive
	 * @param end the stopping point of search, exclusive
	 * @return the starting index in the text of the pattern , or -1 if not found
	 */
	protected int posIn(String text, int start, int end) {//no wild card in pattern
		int max = end - fLength;

		if (!fIgnoreCase) {
			int i = text.indexOf(fPattern, start);
			if (i == -1 || i > max)
				return -1;
			return i;
		}

		for (int i = start; i <= max; ++i) {
			if (text.regionMatches(true, i, fPattern, 0, fLength))
				return i;
		}

		return -1;
	}
	/**
	 * @param text a simple regular expression that may only contain '?'(s)
	 * @param start the starting index in the text for search, inclusive
	 * @param end the stopping point of search, exclusive
	 * @param p a simple regular expression that may contains '?'
	 * @return the starting index in the text of the pattern , or -1 if not found
	 */
	protected int regExpPosIn(String text, int start, int end, String p) {
		int plen = p.length();

		int max = end - plen;
		for (int i = start; i <= max; ++i) {
			if (regExpRegionMatches(text, i, p, 0, plen))
				return i;
		}
		return -1;
	}

	/**
	 *
	 * @param text the text
	 * @param tStart the start
	 * @param p the pattern
	 * @param pStart the pattern start
	 * @param plen the pattern length
	 * @return whether the region matches
	 */
	protected boolean regExpRegionMatches(String text, int tStart, String p, int pStart, int plen) {
		while (plen-- > 0) {
			char tchar = text.charAt(tStart++);
			char pchar = p.charAt(pStart++);

			/* process wild cards */
			if (!fIgnoreWildCards) {
				/* skip single wild cards */
				if (pchar == fSingleWildCard) {
					continue;
				}
			}
			if (pchar == tchar)
				continue;
			if (fIgnoreCase) {
				if (Character.toUpperCase(tchar) == Character.toUpperCase(pchar))
					continue;
				// comparing after converting to upper case doesn't handle all cases;
				// also compare after converting to lower case
				if (Character.toLowerCase(tchar) == Character.toLowerCase(pchar))
					continue;
			}
			return false;
		}
		return true;
	}
	/**
	 * @param text the string to match
	 * @param start the starting index in the text for search, inclusive
	 * @param end the stopping point of search, exclusive
	 * @param p a string that has no wildcard
	 * @return the starting index in the text of the pattern , or -1 if not found
	 */
	protected int textPosIn(String text, int start, int end, String p) {

		int plen = p.length();
		int max = end - plen;

		if (!fIgnoreCase) {
			int i = text.indexOf(p, start);
			if (i == -1 || i > max)
				return -1;
			return i;
		}

		for (int i = start; i <= max; ++i) {
			if (text.regionMatches(true, i, p, 0, plen))
				return i;
		}

		return -1;
	}
}

Back to the top