17 |
ilm |
1 |
/*
|
|
|
2 |
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS HEADER.
|
|
|
3 |
*
|
|
|
4 |
* Copyright 2011 OpenConcerto, by ILM Informatique. All rights reserved.
|
|
|
5 |
*
|
|
|
6 |
* The contents of this file are subject to the terms of the GNU General Public License Version 3
|
|
|
7 |
* only ("GPL"). You may not use this file except in compliance with the License. You can obtain a
|
|
|
8 |
* copy of the License at http://www.gnu.org/licenses/gpl-3.0.html See the License for the specific
|
|
|
9 |
* language governing permissions and limitations under the License.
|
|
|
10 |
*
|
|
|
11 |
* When distributing the software, include this License Header Notice in each file.
|
|
|
12 |
*/
|
|
|
13 |
|
|
|
14 |
/*
|
|
|
15 |
* Créé le 3 mars 2005
|
|
|
16 |
*/
|
|
|
17 |
package org.openconcerto.utils;
|
|
|
18 |
|
83 |
ilm |
19 |
import java.awt.FontMetrics;
|
|
|
20 |
import java.math.BigDecimal;
|
19 |
ilm |
21 |
import java.nio.charset.Charset;
|
177 |
ilm |
22 |
import java.text.Normalizer;
|
|
|
23 |
import java.text.Normalizer.Form;
|
17 |
ilm |
24 |
import java.util.ArrayList;
|
|
|
25 |
import java.util.Collections;
|
|
|
26 |
import java.util.HashMap;
|
|
|
27 |
import java.util.HashSet;
|
83 |
ilm |
28 |
import java.util.Iterator;
|
17 |
ilm |
29 |
import java.util.LinkedHashMap;
|
|
|
30 |
import java.util.List;
|
177 |
ilm |
31 |
import java.util.Locale;
|
17 |
ilm |
32 |
import java.util.Map;
|
|
|
33 |
import java.util.Set;
|
174 |
ilm |
34 |
import java.util.regex.Matcher;
|
28 |
ilm |
35 |
import java.util.regex.Pattern;
|
17 |
ilm |
36 |
|
177 |
ilm |
37 |
import com.ibm.icu.lang.UCharacter;
|
|
|
38 |
|
17 |
ilm |
39 |
/**
|
|
|
40 |
* @author Sylvain CUAZ
|
|
|
41 |
*/
|
|
|
42 |
public class StringUtils {
|
|
|
43 |
|
80 |
ilm |
44 |
// required encoding see Charset
|
|
|
45 |
public static final Charset UTF8 = Charset.forName("UTF-8");
|
|
|
46 |
public static final Charset UTF16 = Charset.forName("UTF-16");
|
|
|
47 |
public static final Charset ASCII = Charset.forName("US-ASCII");
|
|
|
48 |
public static final Charset ISO8859_1 = Charset.forName("ISO-8859-1");
|
|
|
49 |
// included in rt.jar see
|
28 |
ilm |
50 |
// http://docs.oracle.com/javase/7/docs/technotes/guides/intl/encoding.doc.html
|
80 |
ilm |
51 |
public static final Charset ISO8859_15 = Charset.forName("ISO-8859-15");
|
28 |
ilm |
52 |
public static final Charset Cp1252 = Charset.forName("Cp1252");
|
|
|
53 |
public static final Charset Cp850 = Charset.forName("Cp850");
|
19 |
ilm |
54 |
|
144 |
ilm |
55 |
public static final char BOM = '\ufeff';
|
|
|
56 |
|
93 |
ilm |
57 |
final protected static char[] hexArray = "0123456789ABCDEF".toCharArray();
|
|
|
58 |
|
17 |
ilm |
59 |
/**
|
|
|
60 |
* Retourne la chaine avec la première lettre en majuscule et le reste en minuscule.
|
|
|
61 |
*
|
|
|
62 |
* @param s la chaîne à transformer.
|
|
|
63 |
* @return la chaine avec la première lettre en majuscule et le reste en minuscule.
|
|
|
64 |
*/
|
|
|
65 |
public static String firstUpThenLow(String s) {
|
|
|
66 |
if (s.length() == 0) {
|
|
|
67 |
return s;
|
|
|
68 |
}
|
|
|
69 |
if (s.length() == 1) {
|
|
|
70 |
return s.toUpperCase();
|
|
|
71 |
}
|
|
|
72 |
return s.substring(0, 1).toUpperCase() + s.substring(1).toLowerCase();
|
|
|
73 |
}
|
|
|
74 |
|
|
|
75 |
public static String firstUp(String s) {
|
|
|
76 |
if (s.length() == 0) {
|
|
|
77 |
return s;
|
|
|
78 |
}
|
|
|
79 |
if (s.length() == 1) {
|
|
|
80 |
return s.toUpperCase();
|
|
|
81 |
}
|
|
|
82 |
return s.substring(0, 1).toUpperCase() + s.substring(1);
|
|
|
83 |
}
|
|
|
84 |
|
19 |
ilm |
85 |
static public abstract class Shortener {
|
|
|
86 |
|
|
|
87 |
private final int hashSize;
|
|
|
88 |
private final int hashPartSize;
|
|
|
89 |
private final String prefix;
|
|
|
90 |
private final String suffix;
|
|
|
91 |
private final int minStringLength;
|
|
|
92 |
|
|
|
93 |
protected Shortener(int hashSize, String prefix, String suffix, int minCharsBeforeAndAfter) {
|
|
|
94 |
super();
|
|
|
95 |
this.hashSize = hashSize;
|
|
|
96 |
this.prefix = prefix;
|
|
|
97 |
this.suffix = suffix;
|
|
|
98 |
this.hashPartSize = this.hashSize + this.prefix.length() + this.suffix.length();
|
|
|
99 |
if (minCharsBeforeAndAfter < 1)
|
|
|
100 |
throw new IllegalArgumentException("minCharsBeforeAndAfter must be at least 1: " + minCharsBeforeAndAfter);
|
|
|
101 |
this.minStringLength = this.hashPartSize + minCharsBeforeAndAfter * 2;
|
|
|
102 |
}
|
|
|
103 |
|
|
|
104 |
public final int getMinStringLength() {
|
|
|
105 |
return this.minStringLength;
|
|
|
106 |
}
|
|
|
107 |
|
|
|
108 |
public final String getBoundedLengthString(final String s, final int maxLength) {
|
|
|
109 |
// don't test first for s.length, it's more predictable
|
|
|
110 |
// (otherwise boundedString("a", 2) would succeed)
|
|
|
111 |
if (maxLength < this.getMinStringLength())
|
|
|
112 |
throw new IllegalArgumentException("Maximum too low : " + maxLength + "<" + getMinStringLength());
|
|
|
113 |
if (s.length() <= maxLength)
|
|
|
114 |
return s;
|
|
|
115 |
else
|
|
|
116 |
return this.shorten(s, maxLength);
|
|
|
117 |
}
|
|
|
118 |
|
|
|
119 |
final String shorten(final String s, final int maxLength) {
|
|
|
120 |
assert s.length() >= this.getMinStringLength();
|
|
|
121 |
final int toRemoveLength = s.length() - maxLength + this.hashPartSize;
|
|
|
122 |
// remove the middle part of encoded
|
|
|
123 |
final int toRemoveStartIndex = s.length() / 2 - toRemoveLength / 2;
|
|
|
124 |
final String toHash = s.substring(toRemoveStartIndex, toRemoveStartIndex + toRemoveLength);
|
|
|
125 |
|
|
|
126 |
final String hash = shorten(toHash);
|
|
|
127 |
assert this.hashSize == hash.length();
|
|
|
128 |
|
|
|
129 |
final String res = s.substring(0, toRemoveStartIndex) + this.prefix + hash + this.suffix + s.substring(toRemoveStartIndex + toRemoveLength);
|
|
|
130 |
assert res.length() == maxLength;
|
|
|
131 |
return res;
|
|
|
132 |
}
|
|
|
133 |
|
|
|
134 |
protected abstract String shorten(String s);
|
|
|
135 |
|
|
|
136 |
static public final Shortener Ellipsis = new Shortener(1, "", "", 1) {
|
|
|
137 |
@Override
|
|
|
138 |
protected String shorten(String s) {
|
|
|
139 |
return "…";
|
|
|
140 |
}
|
|
|
141 |
};
|
|
|
142 |
|
|
|
143 |
// String.hashCode() is an int written in hex
|
|
|
144 |
static public final Shortener JavaHashCode = new Shortener(Integer.SIZE / 8 * 2, "#", "#", 3) {
|
|
|
145 |
@Override
|
|
|
146 |
protected String shorten(String s) {
|
|
|
147 |
return MessageDigestUtils.asHex(MessageDigestUtils.int2bytes(s.hashCode()));
|
|
|
148 |
}
|
|
|
149 |
};
|
|
|
150 |
|
|
|
151 |
// 128 bits written in hex
|
|
|
152 |
static public final Shortener MD5 = new Shortener(128 / 8 * 2, "#", "#", 11) {
|
|
|
153 |
@Override
|
|
|
154 |
protected String shorten(String s) {
|
|
|
155 |
return MessageDigestUtils.getHashString(MessageDigestUtils.getMD5(), s.getBytes(UTF8));
|
|
|
156 |
}
|
|
|
157 |
};
|
|
|
158 |
|
|
|
159 |
// order descendant by getMinStringLength()
|
|
|
160 |
static final Shortener[] ORDERED = new Shortener[] { MD5, JavaHashCode, Ellipsis };
|
|
|
161 |
}
|
|
|
162 |
|
|
|
163 |
/**
|
|
|
164 |
* The minimum value for {@link #getBoundedLengthString(String, int)}.
|
|
|
165 |
*
|
|
|
166 |
* @return the minimum value for <code>maxLength</code>.
|
|
|
167 |
*/
|
|
|
168 |
public static final int getLeastMaximum() {
|
|
|
169 |
return Shortener.ORDERED[Shortener.ORDERED.length - 1].getMinStringLength();
|
|
|
170 |
}
|
|
|
171 |
|
|
|
172 |
private static final Shortener getShortener(final int l) {
|
|
|
173 |
for (final Shortener sh : Shortener.ORDERED) {
|
|
|
174 |
if (l >= sh.getMinStringLength())
|
|
|
175 |
return sh;
|
|
|
176 |
}
|
|
|
177 |
return null;
|
|
|
178 |
}
|
|
|
179 |
|
|
|
180 |
/**
|
|
|
181 |
* Return a string built from <code>s</code> that is at most <code>maxLength</code> long.
|
|
|
182 |
*
|
|
|
183 |
* @param s the string to bound.
|
|
|
184 |
* @param maxLength the maximum length the result must have.
|
|
|
185 |
* @return a string built from <code>s</code>.
|
|
|
186 |
* @throws IllegalArgumentException if <code>maxLength</code> is too small.
|
|
|
187 |
* @see #getLeastMaximum()
|
|
|
188 |
* @see Shortener#getBoundedLengthString(String, int)
|
|
|
189 |
*/
|
|
|
190 |
public static final String getBoundedLengthString(final String s, final int maxLength) throws IllegalArgumentException {
|
|
|
191 |
// don't test first for s.length, it's more predictable
|
|
|
192 |
// (otherwise boundedString("a", 2) would succeed)
|
|
|
193 |
if (maxLength < getLeastMaximum())
|
|
|
194 |
throw new IllegalArgumentException("Maximum too low : " + maxLength + "<" + getLeastMaximum());
|
|
|
195 |
|
|
|
196 |
final String res;
|
|
|
197 |
if (s.length() <= maxLength) {
|
|
|
198 |
res = s;
|
|
|
199 |
} else {
|
|
|
200 |
// use maxLength to choose the shortener since it's generally a constant
|
|
|
201 |
// and thus the strings returned by this method have the same pattern
|
|
|
202 |
res = getShortener(maxLength).shorten(s, maxLength);
|
|
|
203 |
}
|
|
|
204 |
return res;
|
|
|
205 |
}
|
|
|
206 |
|
80 |
ilm |
207 |
static public enum Side {
|
|
|
208 |
LEFT, RIGHT
|
|
|
209 |
}
|
|
|
210 |
|
|
|
211 |
public static String getFixedWidthString(final String s, final int width, final Side align) {
|
|
|
212 |
return getFixedWidthString(s, width, align, false);
|
|
|
213 |
}
|
|
|
214 |
|
132 |
ilm |
215 |
public static String getFixedWidthString(final String s, final int width, final Side align, final boolean allowShorten) {
|
80 |
ilm |
216 |
final int length = s.length();
|
|
|
217 |
final String res;
|
|
|
218 |
if (length == width) {
|
|
|
219 |
res = s;
|
|
|
220 |
} else if (length < width) {
|
132 |
ilm |
221 |
// we already tested length, so no need to allow shorten
|
|
|
222 |
res = appendFixedWidthString(new StringBuilder(width), s, width, align, ' ', false).toString();
|
|
|
223 |
} else {
|
|
|
224 |
res = getTooWideString(s, width, allowShorten);
|
|
|
225 |
}
|
|
|
226 |
assert res.length() == width;
|
|
|
227 |
return res;
|
|
|
228 |
}
|
|
|
229 |
|
|
|
230 |
private static String getTooWideString(final String s, final int width, final boolean allowShorten) {
|
|
|
231 |
assert s.length() > width;
|
|
|
232 |
if (!allowShorten)
|
|
|
233 |
throw new IllegalArgumentException("Too wide : " + s.length() + " > " + width);
|
|
|
234 |
return getBoundedLengthString(s, width);
|
|
|
235 |
}
|
|
|
236 |
|
|
|
237 |
public static StringBuilder appendFixedWidthString(final StringBuilder sb, final String s, final int width, final Side align, final char filler, final boolean allowShorten) {
|
|
|
238 |
final int origBuilderLen = sb.length();
|
|
|
239 |
final int length = s.length();
|
|
|
240 |
if (length <= width) {
|
|
|
241 |
sb.ensureCapacity(origBuilderLen + width);
|
80 |
ilm |
242 |
if (align == Side.LEFT)
|
|
|
243 |
sb.append(s);
|
132 |
ilm |
244 |
for (int i = length; i < width; i++) {
|
|
|
245 |
sb.append(filler);
|
80 |
ilm |
246 |
}
|
|
|
247 |
if (align == Side.RIGHT)
|
|
|
248 |
sb.append(s);
|
|
|
249 |
} else {
|
132 |
ilm |
250 |
sb.append(getTooWideString(s, width, allowShorten));
|
80 |
ilm |
251 |
}
|
132 |
ilm |
252 |
assert sb.length() == origBuilderLen + width;
|
|
|
253 |
return sb;
|
80 |
ilm |
254 |
}
|
|
|
255 |
|
17 |
ilm |
256 |
public static final List<String> fastSplit(final String string, final char sep) {
|
|
|
257 |
final List<String> l = new ArrayList<String>();
|
|
|
258 |
final int length = string.length();
|
|
|
259 |
final char[] cars = string.toCharArray();
|
|
|
260 |
int rfirst = 0;
|
|
|
261 |
|
|
|
262 |
for (int i = 0; i < length; i++) {
|
|
|
263 |
if (cars[i] == sep) {
|
|
|
264 |
l.add(new String(cars, rfirst, i - rfirst));
|
|
|
265 |
rfirst = i + 1;
|
|
|
266 |
}
|
|
|
267 |
}
|
|
|
268 |
|
|
|
269 |
if (rfirst < length) {
|
|
|
270 |
l.add(new String(cars, rfirst, length - rfirst));
|
|
|
271 |
}
|
|
|
272 |
return l;
|
|
|
273 |
}
|
|
|
274 |
|
83 |
ilm |
275 |
public static final List<String> fastSplitTrimmed(final String string, final char sep) {
|
|
|
276 |
final List<String> l = new ArrayList<String>();
|
|
|
277 |
final int length = string.length();
|
|
|
278 |
final char[] cars = string.toCharArray();
|
|
|
279 |
int rfirst = 0;
|
|
|
280 |
|
|
|
281 |
for (int i = 0; i < length; i++) {
|
|
|
282 |
if (cars[i] == sep) {
|
|
|
283 |
l.add(new String(cars, rfirst, i - rfirst).trim());
|
|
|
284 |
rfirst = i + 1;
|
|
|
285 |
}
|
|
|
286 |
}
|
|
|
287 |
|
|
|
288 |
if (rfirst < length) {
|
|
|
289 |
l.add(new String(cars, rfirst, length - rfirst).trim());
|
|
|
290 |
}
|
|
|
291 |
return l;
|
|
|
292 |
}
|
|
|
293 |
|
19 |
ilm |
294 |
/**
|
|
|
295 |
* Split une string s tous les nbCharMaxLine
|
|
|
296 |
*
|
|
|
297 |
* @param s
|
|
|
298 |
* @param nbCharMaxLine
|
|
|
299 |
* @return
|
|
|
300 |
*/
|
|
|
301 |
public static String splitString(String s, int nbCharMaxLine) {
|
|
|
302 |
|
|
|
303 |
if (s == null) {
|
|
|
304 |
return s;
|
|
|
305 |
}
|
|
|
306 |
|
|
|
307 |
if (s.trim().length() < nbCharMaxLine) {
|
|
|
308 |
return s;
|
|
|
309 |
}
|
|
|
310 |
StringBuffer lastString = new StringBuffer();
|
|
|
311 |
StringBuffer result = new StringBuffer();
|
|
|
312 |
for (int i = 0; i < s.length(); i++) {
|
|
|
313 |
|
|
|
314 |
if (lastString.length() == nbCharMaxLine) {
|
|
|
315 |
int esp = lastString.lastIndexOf(" ");
|
25 |
ilm |
316 |
if (result.length() > 0 && result.charAt(result.length() - 1) != '\n') {
|
19 |
ilm |
317 |
result.append("\n");
|
|
|
318 |
}
|
|
|
319 |
if (esp > 0) {
|
|
|
320 |
result.append(lastString.substring(0, esp).toString().trim());
|
|
|
321 |
lastString = new StringBuffer(lastString.substring(esp, lastString.length()));
|
|
|
322 |
} else {
|
|
|
323 |
result.append(lastString.toString().trim());
|
|
|
324 |
lastString = new StringBuffer();
|
|
|
325 |
}
|
25 |
ilm |
326 |
result.append("\n");
|
19 |
ilm |
327 |
}
|
|
|
328 |
|
|
|
329 |
char charAt = s.charAt(i);
|
|
|
330 |
if (charAt == '\n') {
|
|
|
331 |
lastString.append(charAt);
|
21 |
ilm |
332 |
result.append(lastString);
|
19 |
ilm |
333 |
lastString = new StringBuffer();
|
|
|
334 |
} else {
|
|
|
335 |
lastString.append(charAt);
|
|
|
336 |
}
|
|
|
337 |
}
|
|
|
338 |
|
25 |
ilm |
339 |
if (result.length() > 0 && result.charAt(result.length() - 1) != '\n') {
|
19 |
ilm |
340 |
result.append("\n");
|
|
|
341 |
}
|
|
|
342 |
|
|
|
343 |
result.append(lastString.toString().trim());
|
|
|
344 |
|
|
|
345 |
return result.toString();
|
|
|
346 |
}
|
|
|
347 |
|
83 |
ilm |
348 |
static public int firstIndexOf(final String s, final char[] chars) {
|
|
|
349 |
return firstIndexOf(s, 0, chars);
|
|
|
350 |
}
|
|
|
351 |
|
|
|
352 |
static public int firstIndexOf(final String s, final int offset, final char[] chars) {
|
|
|
353 |
int res = -1;
|
|
|
354 |
for (final char c : chars) {
|
|
|
355 |
final int index = s.indexOf(c, offset);
|
|
|
356 |
if (index >= 0 && (res == -1 || index < res))
|
|
|
357 |
res = index;
|
|
|
358 |
}
|
|
|
359 |
return res;
|
|
|
360 |
}
|
|
|
361 |
|
61 |
ilm |
362 |
static private final Pattern quotePatrn = Pattern.compile("\"", Pattern.LITERAL);
|
|
|
363 |
static private final Pattern slashPatrn = Pattern.compile("(\\\\+)");
|
28 |
ilm |
364 |
|
|
|
365 |
static public String doubleQuote(String s) {
|
142 |
ilm |
366 |
return doubleQuote(s, true);
|
|
|
367 |
}
|
|
|
368 |
|
|
|
369 |
static public String doubleQuote(String s, final boolean escapeEscapeChar) {
|
61 |
ilm |
370 |
// http://developer.apple.com/library/mac/#documentation/applescript/conceptual/applescriptlangguide/reference/ASLR_classes.html#//apple_ref/doc/uid/TP40000983-CH1g-SW6
|
|
|
371 |
// http://docs.oracle.com/javase/specs/jls/se7/html/jls-3.html#jls-3.10.5
|
|
|
372 |
// https://developer.mozilla.org/en/JavaScript/Guide/Values%2C_Variables%2C_and_Literals#Escaping_characters
|
28 |
ilm |
373 |
if (s.length() > 0) {
|
142 |
ilm |
374 |
if (escapeEscapeChar)
|
|
|
375 |
s = slashPatrn.matcher(s).replaceAll("$1$1");
|
61 |
ilm |
376 |
s = quotePatrn.matcher(s).replaceAll("\\\\\"");
|
28 |
ilm |
377 |
}
|
|
|
378 |
return '"' + s + '"';
|
|
|
379 |
}
|
|
|
380 |
|
83 |
ilm |
381 |
/**
|
|
|
382 |
* Unquote a double quoted string.
|
|
|
383 |
*
|
|
|
384 |
* @param s the string to unquote, e.g. "foo\\bar".
|
|
|
385 |
* @return the unquoted form, e.g. foo\bar.
|
|
|
386 |
* @throws IllegalArgumentException if the string is not quoted, or if there's some extra
|
|
|
387 |
* content at the end.
|
|
|
388 |
*/
|
|
|
389 |
static public String unDoubleQuote(String s) {
|
|
|
390 |
final Tuple2<String, Integer> res = unDoubleQuote(s, 0);
|
|
|
391 |
if (res.get1().intValue() != s.length())
|
|
|
392 |
throw new IllegalArgumentException("Extra content at the end : " + s.substring(res.get1()));
|
|
|
393 |
return res.get0();
|
|
|
394 |
}
|
|
|
395 |
|
|
|
396 |
/**
|
|
|
397 |
* Unquote part of a double quoted string.
|
|
|
398 |
*
|
|
|
399 |
* @param s the string to unquote, e.g. pre"foo\\bar"post.
|
|
|
400 |
* @param offset the start index of the quotes, e.g. 3.
|
|
|
401 |
* @return the unquoted form and the index after the end quote, e.g. foo\bar and 13.
|
|
|
402 |
* @throws IllegalArgumentException if the string is not quoted.
|
|
|
403 |
*/
|
|
|
404 |
static public Tuple2<String, Integer> unDoubleQuote(String s, int offset) {
|
|
|
405 |
if (s.charAt(offset) != '"')
|
|
|
406 |
throw new IllegalArgumentException("Expected quote but got : " + s.charAt(offset));
|
|
|
407 |
final int l = s.length();
|
|
|
408 |
if (offset + 1 < l && s.charAt(offset + 1) == '"')
|
|
|
409 |
return Tuple2.create("", offset + 2);
|
|
|
410 |
|
|
|
411 |
offset++;
|
|
|
412 |
final char[] chars = new char[] { '"', '\\' };
|
|
|
413 |
final StringBuilder sb = new StringBuilder(512);
|
|
|
414 |
boolean foundEnd = false;
|
|
|
415 |
while (offset < l && !foundEnd) {
|
|
|
416 |
final int index = firstIndexOf(s, offset, chars);
|
|
|
417 |
if (index < 0)
|
|
|
418 |
throw new IllegalArgumentException("End quote not found after " + offset);
|
|
|
419 |
sb.append(s.substring(offset, index));
|
|
|
420 |
if (s.charAt(index) == '"') {
|
|
|
421 |
offset = index + 1;
|
|
|
422 |
foundEnd = true;
|
|
|
423 |
} else {
|
|
|
424 |
assert s.charAt(index) == '\\';
|
|
|
425 |
sb.append(s.charAt(index + 1));
|
|
|
426 |
offset = index + 2;
|
|
|
427 |
}
|
|
|
428 |
}
|
|
|
429 |
if (!foundEnd)
|
|
|
430 |
throw new IllegalArgumentException("End quote not found after " + offset);
|
|
|
431 |
return Tuple2.create(sb.toString(), offset);
|
|
|
432 |
}
|
|
|
433 |
|
17 |
ilm |
434 |
public static final class Escaper {
|
|
|
435 |
|
|
|
436 |
// eg '
|
|
|
437 |
private final char esc;
|
|
|
438 |
|
|
|
439 |
// eg { '=> S, " => D}
|
|
|
440 |
private final Map<Character, Character> substitution;
|
|
|
441 |
private final Map<Character, Character> inv;
|
|
|
442 |
|
|
|
443 |
/**
|
|
|
444 |
* A new escaper that will have <code>esc</code> as escape character.
|
|
|
445 |
*
|
|
|
446 |
* @param esc the escape character, eg '
|
|
|
447 |
* @param name the character that will be appended to <code>esc</code>, eg with S all
|
|
|
448 |
* occurrences of ' will be replaced by 'S
|
|
|
449 |
*/
|
|
|
450 |
public Escaper(char esc, char name) {
|
|
|
451 |
super();
|
|
|
452 |
this.esc = esc;
|
|
|
453 |
this.substitution = new LinkedHashMap<Character, Character>();
|
|
|
454 |
this.inv = new HashMap<Character, Character>();
|
|
|
455 |
this.add(esc, name);
|
|
|
456 |
}
|
|
|
457 |
|
|
|
458 |
public Escaper add(char toRemove, char escapedName) {
|
|
|
459 |
if (this.inv.containsKey(escapedName))
|
|
|
460 |
throw new IllegalArgumentException(escapedName + " already replaces " + this.inv.get(escapedName));
|
|
|
461 |
this.substitution.put(toRemove, escapedName);
|
|
|
462 |
this.inv.put(escapedName, toRemove);
|
|
|
463 |
return this;
|
|
|
464 |
}
|
|
|
465 |
|
|
|
466 |
public final Set<Character> getEscapedChars() {
|
|
|
467 |
final Set<Character> res = new HashSet<Character>(this.substitution.keySet());
|
|
|
468 |
res.remove(this.esc);
|
|
|
469 |
return res;
|
|
|
470 |
}
|
|
|
471 |
|
|
|
472 |
/**
|
|
|
473 |
* Escape <code>s</code>, so that the resulting string has none of
|
|
|
474 |
* {@link #getEscapedChars()}.
|
|
|
475 |
*
|
|
|
476 |
* @param s a string to escape.
|
|
|
477 |
* @return the escaped form.
|
|
|
478 |
*/
|
|
|
479 |
public final String escape(String s) {
|
|
|
480 |
String res = s;
|
|
|
481 |
// this.esc en premier
|
|
|
482 |
for (final Character toEsc : this.substitution.keySet()) {
|
|
|
483 |
// use Pattern.LITERAL to avoid interpretion
|
|
|
484 |
res = res.replace(toEsc + "", getEscaped(toEsc));
|
|
|
485 |
}
|
|
|
486 |
return res;
|
|
|
487 |
}
|
|
|
488 |
|
|
|
489 |
private String getEscaped(final Character toEsc) {
|
|
|
490 |
return this.esc + "" + this.substitution.get(toEsc);
|
|
|
491 |
}
|
|
|
492 |
|
|
|
493 |
public final String unescape(String escaped) {
|
|
|
494 |
String res = escaped;
|
|
|
495 |
final List<Character> toEscs = new ArrayList<Character>(this.substitution.keySet());
|
|
|
496 |
Collections.reverse(toEscs);
|
|
|
497 |
for (final Character toEsc : toEscs) {
|
|
|
498 |
res = res.replaceAll(getEscaped(toEsc), toEsc + "");
|
|
|
499 |
}
|
|
|
500 |
return res;
|
|
|
501 |
}
|
|
|
502 |
|
|
|
503 |
@Override
|
|
|
504 |
public boolean equals(Object obj) {
|
|
|
505 |
if (obj instanceof Escaper) {
|
|
|
506 |
final Escaper o = (Escaper) obj;
|
|
|
507 |
return this.esc == o.esc && this.substitution.equals(o.substitution);
|
|
|
508 |
} else
|
|
|
509 |
return false;
|
|
|
510 |
}
|
|
|
511 |
|
|
|
512 |
@Override
|
|
|
513 |
public int hashCode() {
|
|
|
514 |
return this.esc + this.substitution.hashCode();
|
|
|
515 |
}
|
|
|
516 |
}
|
|
|
517 |
|
25 |
ilm |
518 |
public static String rightAlign(String s, int width) {
|
|
|
519 |
String r = s;
|
|
|
520 |
int n = width - s.length();
|
|
|
521 |
for (int i = 0; i < n; i++) {
|
|
|
522 |
r = ' ' + r;
|
|
|
523 |
}
|
|
|
524 |
return r;
|
|
|
525 |
}
|
|
|
526 |
|
|
|
527 |
public static String leftAlign(String s, int width) {
|
|
|
528 |
String r = s;
|
|
|
529 |
int n = width - s.length();
|
|
|
530 |
for (int i = 0; i < n; i++) {
|
|
|
531 |
r += ' ';
|
|
|
532 |
}
|
|
|
533 |
return r;
|
|
|
534 |
}
|
73 |
ilm |
535 |
|
|
|
536 |
public static String trim(final String s, final boolean leading) {
|
|
|
537 |
// from String.trim()
|
|
|
538 |
int end = s.length();
|
|
|
539 |
int st = 0;
|
|
|
540 |
|
|
|
541 |
if (leading) {
|
|
|
542 |
while ((st < end) && (s.charAt(st) <= ' ')) {
|
|
|
543 |
st++;
|
|
|
544 |
}
|
|
|
545 |
} else {
|
|
|
546 |
while ((st < end) && (s.charAt(end - 1) <= ' ')) {
|
|
|
547 |
end--;
|
|
|
548 |
}
|
|
|
549 |
}
|
|
|
550 |
return ((st > 0) || (end < s.length())) ? s.substring(st, end) : s;
|
|
|
551 |
}
|
80 |
ilm |
552 |
|
|
|
553 |
public static String limitLength(String s, int maxLength) {
|
|
|
554 |
if (s.length() <= maxLength) {
|
|
|
555 |
return s;
|
|
|
556 |
}
|
|
|
557 |
return s.substring(0, maxLength);
|
|
|
558 |
}
|
|
|
559 |
|
|
|
560 |
public static String removeAllSpaces(String text) {
|
|
|
561 |
final int length = text.length();
|
|
|
562 |
final StringBuilder builder = new StringBuilder(length);
|
|
|
563 |
for (int i = 0; i < length; i++) {
|
|
|
564 |
char c = text.charAt(i);
|
|
|
565 |
if (c <= ' ' && c != 160) {
|
|
|
566 |
// remove non printable chars
|
|
|
567 |
// spaces
|
|
|
568 |
// non breakable space (160)
|
|
|
569 |
builder.append(c);
|
|
|
570 |
}
|
|
|
571 |
}
|
|
|
572 |
return builder.toString();
|
|
|
573 |
}
|
|
|
574 |
|
|
|
575 |
public static String removeNonDecimalChars(String text) {
|
|
|
576 |
final int length = text.length();
|
|
|
577 |
final StringBuilder builder = new StringBuilder(length);
|
|
|
578 |
for (int i = 0; i < length; i++) {
|
|
|
579 |
char c = text.charAt(i);
|
|
|
580 |
if (Character.isDigit(c) || c == '.' || c == '+' || c == '-') {
|
|
|
581 |
builder.append(c);
|
|
|
582 |
}
|
|
|
583 |
}
|
|
|
584 |
return builder.toString();
|
|
|
585 |
}
|
83 |
ilm |
586 |
|
|
|
587 |
public static BigDecimal getBigDecimalFromUserText(String text) {
|
|
|
588 |
text = text.trim();
|
|
|
589 |
if (text.isEmpty() || text.equals("-")) {
|
|
|
590 |
return BigDecimal.ZERO;
|
|
|
591 |
}
|
|
|
592 |
text = removeNonDecimalChars(text);
|
|
|
593 |
BigDecimal result = null;
|
|
|
594 |
try {
|
|
|
595 |
result = new BigDecimal(text);
|
|
|
596 |
} catch (Exception e) {
|
|
|
597 |
Log.get().info(text + " is not a valid decimal");
|
|
|
598 |
}
|
|
|
599 |
return result;
|
|
|
600 |
}
|
|
|
601 |
|
|
|
602 |
/**
|
|
|
603 |
* Returns an array of strings, one for each line in the string after it has been wrapped to fit
|
|
|
604 |
* lines of <var>maxWidth</var>. Lines end with any of cr, lf, or cr lf. A line ending at the
|
|
|
605 |
* end of the string will not output a further, empty string.
|
|
|
606 |
* <p>
|
|
|
607 |
* This code assumes <var>str</var> is not <code>null</code>.
|
|
|
608 |
*
|
|
|
609 |
* @param str the string to split
|
|
|
610 |
* @param fm needed for string width calculations
|
|
|
611 |
* @param maxWidth the max line width, in points
|
|
|
612 |
* @return a non-empty list of strings
|
|
|
613 |
*/
|
|
|
614 |
public static List<String> wrap(String str, FontMetrics fm, int maxWidth) {
|
|
|
615 |
List<String> lines = splitIntoLines(str);
|
|
|
616 |
if (lines.size() == 0)
|
|
|
617 |
return lines;
|
|
|
618 |
|
|
|
619 |
List<String> strings = new ArrayList<String>();
|
|
|
620 |
for (Iterator<String> iter = lines.iterator(); iter.hasNext();) {
|
|
|
621 |
wrapLineInto(iter.next(), strings, fm, maxWidth);
|
|
|
622 |
}
|
|
|
623 |
return strings;
|
|
|
624 |
}
|
|
|
625 |
|
|
|
626 |
/**
|
|
|
627 |
* Given a line of text and font metrics information, wrap the line and add the new line(s) to
|
|
|
628 |
* <var>list</var>.
|
|
|
629 |
*
|
|
|
630 |
* @param line a line of text
|
|
|
631 |
* @param list an output list of strings
|
|
|
632 |
* @param fm font metrics
|
|
|
633 |
* @param maxWidth maximum width of the line(s)
|
|
|
634 |
*/
|
|
|
635 |
public static void wrapLineInto(String line, List<String> list, FontMetrics fm, int maxWidth) {
|
|
|
636 |
int len = line.length();
|
|
|
637 |
int width;
|
|
|
638 |
while (len > 0 && (width = fm.stringWidth(line)) > maxWidth) {
|
|
|
639 |
// Guess where to split the line. Look for the next space before
|
|
|
640 |
// or after the guess.
|
|
|
641 |
int guess = len * maxWidth / width;
|
|
|
642 |
String before = line.substring(0, guess).trim();
|
|
|
643 |
|
|
|
644 |
width = fm.stringWidth(before);
|
|
|
645 |
int pos;
|
|
|
646 |
if (width > maxWidth) // Too long
|
|
|
647 |
pos = findBreakBefore(line, guess);
|
|
|
648 |
else { // Too short or possibly just right
|
|
|
649 |
pos = findBreakAfter(line, guess);
|
|
|
650 |
if (pos != -1) { // Make sure this doesn't make us too long
|
|
|
651 |
before = line.substring(0, pos).trim();
|
|
|
652 |
if (fm.stringWidth(before) > maxWidth)
|
|
|
653 |
pos = findBreakBefore(line, guess);
|
|
|
654 |
}
|
|
|
655 |
}
|
|
|
656 |
if (pos == -1)
|
|
|
657 |
pos = guess; // Split in the middle of the word
|
|
|
658 |
|
|
|
659 |
list.add(line.substring(0, pos).trim());
|
|
|
660 |
line = line.substring(pos).trim();
|
|
|
661 |
len = line.length();
|
|
|
662 |
}
|
|
|
663 |
if (len > 0) {
|
|
|
664 |
list.add(line);
|
|
|
665 |
}
|
|
|
666 |
}
|
|
|
667 |
|
|
|
668 |
/**
|
|
|
669 |
* Returns the index of the first whitespace character or '-' in <var>line</var> that is at or
|
|
|
670 |
* before <var>start</var>. Returns -1 if no such character is found.
|
|
|
671 |
*
|
|
|
672 |
* @param line a string
|
|
|
673 |
* @param start where to star looking
|
|
|
674 |
*/
|
|
|
675 |
public static int findBreakBefore(String line, int start) {
|
|
|
676 |
for (int i = start; i >= 0; --i) {
|
|
|
677 |
char c = line.charAt(i);
|
|
|
678 |
if (Character.isWhitespace(c) || c == '-')
|
|
|
679 |
return i;
|
|
|
680 |
}
|
|
|
681 |
return -1;
|
|
|
682 |
}
|
|
|
683 |
|
|
|
684 |
/**
|
|
|
685 |
* Returns the index of the first whitespace character or '-' in <var>line</var> that is at or
|
|
|
686 |
* after <var>start</var>. Returns -1 if no such character is found.
|
|
|
687 |
*
|
|
|
688 |
* @param line a string
|
|
|
689 |
* @param start where to star looking
|
|
|
690 |
*/
|
|
|
691 |
public static int findBreakAfter(String line, int start) {
|
|
|
692 |
int len = line.length();
|
|
|
693 |
for (int i = start; i < len; ++i) {
|
|
|
694 |
char c = line.charAt(i);
|
|
|
695 |
if (Character.isWhitespace(c) || c == '-')
|
|
|
696 |
return i;
|
|
|
697 |
}
|
|
|
698 |
return -1;
|
|
|
699 |
}
|
|
|
700 |
|
|
|
701 |
/**
|
|
|
702 |
* Returns an array of strings, one for each line in the string. Lines end with any of cr, lf,
|
|
|
703 |
* or cr lf. A line ending at the end of the string will not output a further, empty string.
|
|
|
704 |
* <p>
|
|
|
705 |
* This code assumes <var>str</var> is not <code>null</code>.
|
|
|
706 |
*
|
|
|
707 |
* @param str the string to split
|
|
|
708 |
* @return a non-empty list of strings
|
|
|
709 |
*/
|
|
|
710 |
public static List<String> splitIntoLines(String str) {
|
|
|
711 |
List<String> strings = new ArrayList<String>();
|
|
|
712 |
|
|
|
713 |
int len = str.length();
|
|
|
714 |
if (len == 0) {
|
|
|
715 |
strings.add("");
|
|
|
716 |
return strings;
|
|
|
717 |
}
|
|
|
718 |
|
|
|
719 |
int lineStart = 0;
|
|
|
720 |
|
|
|
721 |
for (int i = 0; i < len; ++i) {
|
|
|
722 |
char c = str.charAt(i);
|
|
|
723 |
if (c == '\r') {
|
|
|
724 |
int newlineLength = 1;
|
|
|
725 |
if ((i + 1) < len && str.charAt(i + 1) == '\n')
|
|
|
726 |
newlineLength = 2;
|
|
|
727 |
strings.add(str.substring(lineStart, i));
|
|
|
728 |
lineStart = i + newlineLength;
|
|
|
729 |
if (newlineLength == 2) // skip \n next time through loop
|
|
|
730 |
++i;
|
|
|
731 |
} else if (c == '\n') {
|
|
|
732 |
strings.add(str.substring(lineStart, i));
|
|
|
733 |
lineStart = i + 1;
|
|
|
734 |
}
|
|
|
735 |
}
|
|
|
736 |
if (lineStart < len)
|
|
|
737 |
strings.add(str.substring(lineStart));
|
|
|
738 |
|
|
|
739 |
return strings;
|
|
|
740 |
}
|
|
|
741 |
|
93 |
ilm |
742 |
/**
|
|
|
743 |
* convert a byte array to its hexa representation
|
132 |
ilm |
744 |
*/
|
93 |
ilm |
745 |
public static String bytesToHexString(byte[] bytes) {
|
|
|
746 |
final int length = bytes.length;
|
|
|
747 |
char[] hexChars = new char[length * 2];
|
|
|
748 |
for (int j = 0; j < length; j++) {
|
|
|
749 |
int v = bytes[j] & 0xFF;
|
|
|
750 |
hexChars[j * 2] = hexArray[v >>> 4];
|
|
|
751 |
hexChars[j * 2 + 1] = hexArray[v & 0x0F];
|
|
|
752 |
}
|
|
|
753 |
return new String(hexChars);
|
|
|
754 |
}
|
142 |
ilm |
755 |
|
|
|
756 |
/**
|
|
|
757 |
* Whether the parameter is empty.
|
|
|
758 |
*
|
|
|
759 |
* @param s the string to test.
|
|
|
760 |
* @return <code>true</code> if <code>null</code> or {@link String#isEmpty() empty}.
|
|
|
761 |
*/
|
|
|
762 |
public static boolean isEmpty(final String s) {
|
|
|
763 |
return isEmpty(s, false);
|
|
|
764 |
}
|
|
|
765 |
|
|
|
766 |
public static boolean isEmpty(final String s, final boolean trim) {
|
|
|
767 |
return s == null || (trim ? s.trim() : s).isEmpty();
|
|
|
768 |
}
|
|
|
769 |
|
|
|
770 |
/**
|
|
|
771 |
* Return the first parameter that is non-empty.
|
|
|
772 |
*
|
|
|
773 |
* @param s1 the string to test.
|
|
|
774 |
* @param s2 the alternate value.
|
|
|
775 |
* @return <code>s1</code> if not <code>null</code> and not {@link String#isEmpty() empty},
|
|
|
776 |
* <code>s2</code> otherwise.
|
|
|
777 |
*/
|
|
|
778 |
public static String coalesce(String s1, String s2) {
|
|
|
779 |
return isEmpty(s1) ? s2 : s1;
|
|
|
780 |
}
|
|
|
781 |
|
|
|
782 |
/**
|
|
|
783 |
* Return the first value that is non-empty.
|
|
|
784 |
*
|
|
|
785 |
* @param values values to test for emptiness.
|
|
|
786 |
* @return the first value that is neither <code>null</code> nor {@link String#isEmpty() empty}.
|
|
|
787 |
*/
|
|
|
788 |
public static String coalesce(String... values) {
|
|
|
789 |
return coalesce(false, values);
|
|
|
790 |
}
|
|
|
791 |
|
|
|
792 |
public static String coalesce(final boolean trim, String... values) {
|
|
|
793 |
for (final String s : values)
|
|
|
794 |
if (!isEmpty(s, trim))
|
|
|
795 |
return s;
|
|
|
796 |
return null;
|
|
|
797 |
}
|
149 |
ilm |
798 |
|
|
|
799 |
public static String toAsciiString(String str) {
|
|
|
800 |
if (str == null) {
|
|
|
801 |
return null;
|
|
|
802 |
}
|
|
|
803 |
final int length = str.length();
|
|
|
804 |
final StringBuilder b = new StringBuilder(length);
|
|
|
805 |
for (int i = 0; i < length; i++) {
|
|
|
806 |
final char c = str.charAt(i);
|
|
|
807 |
final char newChar;
|
|
|
808 |
if (c < 128) {
|
|
|
809 |
newChar = c;
|
|
|
810 |
} else if (c == 'é' || c == 'è' || c == 'ê') {
|
|
|
811 |
newChar = 'e';
|
|
|
812 |
} else if (c == 'â' || c == 'à') {
|
|
|
813 |
newChar = 'a';
|
|
|
814 |
} else if (c == 'î') {
|
|
|
815 |
newChar = 'i';
|
|
|
816 |
} else if (c == 'ù' || c == 'û') {
|
|
|
817 |
newChar = 'u';
|
|
|
818 |
} else if (c == 'ô') {
|
|
|
819 |
newChar = 'o';
|
|
|
820 |
} else if (c == 'ç') {
|
|
|
821 |
newChar = 'c';
|
|
|
822 |
} else {
|
|
|
823 |
newChar = ' ';
|
|
|
824 |
}
|
|
|
825 |
b.append(newChar);
|
|
|
826 |
}
|
|
|
827 |
return b.toString();
|
|
|
828 |
}
|
174 |
ilm |
829 |
|
|
|
830 |
public static final Matcher findFirstContaining(final String s, final Pattern... patterns) {
|
|
|
831 |
for (final Pattern p : patterns) {
|
|
|
832 |
final Matcher matcher = p.matcher(s);
|
|
|
833 |
if (matcher.find())
|
|
|
834 |
return matcher;
|
|
|
835 |
}
|
|
|
836 |
return null;
|
|
|
837 |
}
|
177 |
ilm |
838 |
|
|
|
839 |
static public interface Search {
|
|
|
840 |
public boolean equals(String str, String anotherString);
|
|
|
841 |
|
|
|
842 |
public boolean startsWith(String str, String prefix);
|
|
|
843 |
|
|
|
844 |
public boolean endsWith(String str, String suffix);
|
|
|
845 |
|
|
|
846 |
public boolean contains(String str, String anotherString);
|
|
|
847 |
}
|
|
|
848 |
|
|
|
849 |
static public final Search EXACT_SEARCH = new Search() {
|
|
|
850 |
@Override
|
|
|
851 |
public boolean startsWith(String str, String prefix) {
|
|
|
852 |
return str.startsWith(prefix);
|
|
|
853 |
}
|
|
|
854 |
|
|
|
855 |
@Override
|
|
|
856 |
public boolean equals(String str, String anotherString) {
|
|
|
857 |
return str.equals(anotherString);
|
|
|
858 |
}
|
|
|
859 |
|
|
|
860 |
@Override
|
|
|
861 |
public boolean endsWith(String str, String suffix) {
|
|
|
862 |
return str.endsWith(suffix);
|
|
|
863 |
}
|
|
|
864 |
|
|
|
865 |
@Override
|
|
|
866 |
public boolean contains(String str, String searchStr) {
|
|
|
867 |
return str.contains(searchStr);
|
|
|
868 |
}
|
|
|
869 |
};
|
|
|
870 |
|
|
|
871 |
// Simple (Single-Character) Case Mapping
|
|
|
872 |
static public final Search SIMPLE_CASE_MAPPING_SEARCH = new Search() {
|
|
|
873 |
@Override
|
|
|
874 |
public boolean startsWith(String str, String prefix) {
|
|
|
875 |
return str.regionMatches(true, 0, prefix, 0, prefix.length());
|
|
|
876 |
}
|
|
|
877 |
|
|
|
878 |
@Override
|
|
|
879 |
public boolean equals(String str, String anotherString) {
|
|
|
880 |
return str.equalsIgnoreCase(anotherString);
|
|
|
881 |
}
|
|
|
882 |
|
|
|
883 |
@Override
|
|
|
884 |
public boolean endsWith(String str, String suffix) {
|
|
|
885 |
final int suffixLength = suffix.length();
|
|
|
886 |
return str.regionMatches(true, str.length() - suffixLength, suffix, 0, suffixLength);
|
|
|
887 |
}
|
|
|
888 |
|
|
|
889 |
@Override
|
|
|
890 |
public boolean contains(String str, String searchStr) {
|
|
|
891 |
final int length = searchStr.length();
|
|
|
892 |
if (length == 0)
|
|
|
893 |
return true;
|
|
|
894 |
|
|
|
895 |
for (int i = str.length() - length; i >= 0; i--) {
|
|
|
896 |
if (str.regionMatches(true, i, searchStr, 0, length))
|
|
|
897 |
return true;
|
|
|
898 |
}
|
|
|
899 |
return false;
|
|
|
900 |
}
|
|
|
901 |
};
|
|
|
902 |
|
|
|
903 |
static public abstract class NormalizeSearch implements Search {
|
|
|
904 |
|
|
|
905 |
protected abstract String normalize(String s);
|
|
|
906 |
|
|
|
907 |
@Override
|
|
|
908 |
public boolean startsWith(String str, String prefix) {
|
|
|
909 |
return normalize(str).startsWith(normalize(prefix));
|
|
|
910 |
}
|
|
|
911 |
|
|
|
912 |
@Override
|
|
|
913 |
public boolean equals(String str, String anotherString) {
|
|
|
914 |
return normalize(str).equals(normalize(anotherString));
|
|
|
915 |
}
|
|
|
916 |
|
|
|
917 |
@Override
|
|
|
918 |
public boolean endsWith(String str, String suffix) {
|
|
|
919 |
return normalize(str).endsWith(normalize(suffix));
|
|
|
920 |
}
|
|
|
921 |
|
|
|
922 |
@Override
|
|
|
923 |
public boolean contains(String str, String searchStr) {
|
|
|
924 |
return normalize(str).contains(normalize(searchStr));
|
|
|
925 |
}
|
|
|
926 |
};
|
|
|
927 |
|
|
|
928 |
// Fixed Locale
|
|
|
929 |
static public final class LowerCaseMappingSearch extends NormalizeSearch {
|
|
|
930 |
|
|
|
931 |
private final Locale locale;
|
|
|
932 |
|
|
|
933 |
public LowerCaseMappingSearch(Locale locale) {
|
|
|
934 |
super();
|
|
|
935 |
this.locale = locale;
|
|
|
936 |
}
|
|
|
937 |
|
|
|
938 |
public final Locale getLocale() {
|
|
|
939 |
return this.locale;
|
|
|
940 |
}
|
|
|
941 |
|
|
|
942 |
@Override
|
|
|
943 |
protected String normalize(String s) {
|
|
|
944 |
return s.toLowerCase(this.getLocale());
|
|
|
945 |
}
|
|
|
946 |
};
|
|
|
947 |
|
|
|
948 |
// Locale.getDefault() at the time of the call
|
|
|
949 |
static public final Search DEFAULT_LOWERCASE_MAPPING_SEARCH = new NormalizeSearch() {
|
|
|
950 |
@Override
|
|
|
951 |
protected String normalize(String s) {
|
|
|
952 |
return s.toLowerCase();
|
|
|
953 |
}
|
|
|
954 |
};
|
|
|
955 |
|
|
|
956 |
static public final Search CASE_FOLDING_SEARCH = new NormalizeSearch() {
|
|
|
957 |
@Override
|
|
|
958 |
protected String normalize(String s) {
|
|
|
959 |
return normalizeCase(s);
|
|
|
960 |
}
|
|
|
961 |
};
|
|
|
962 |
|
|
|
963 |
static private final Pattern BLANK_PATTERN = Pattern.compile("\\p{Blank}+");
|
|
|
964 |
|
|
|
965 |
// replace tabs and multiple spaces by one space
|
|
|
966 |
static public final String normalizeBlanks(String s) {
|
|
|
967 |
return BLANK_PATTERN.matcher(s.trim()).replaceAll(" ");
|
|
|
968 |
}
|
|
|
969 |
|
|
|
970 |
static private final Pattern DIACRITICAL_PATTERN = Pattern.compile("\\p{InCombiningDiacriticalMarks}+");
|
|
|
971 |
|
|
|
972 |
static public String removeDiacritical(final String s) {
|
|
|
973 |
return DIACRITICAL_PATTERN.matcher(Normalizer.normalize(s, Form.NFD)).replaceAll("");
|
|
|
974 |
}
|
|
|
975 |
|
|
|
976 |
static public final String normalizeCase(final String s) {
|
|
|
977 |
// the JRE only does Single-Character Case Mapping so it can't handle Tschüß/TSCHÜSS
|
|
|
978 |
// http://userguide.icu-project.org/transforms/casemappings
|
|
|
979 |
// https://unicode.org/faq/casemap_charprop.html#casemap
|
|
|
980 |
return UCharacter.foldCase(s, true);
|
|
|
981 |
}
|
|
|
982 |
|
|
|
983 |
static public final String normalizeForSearch(final String s) {
|
|
|
984 |
return normalizeCase(removeDiacritical(normalizeBlanks(s)));
|
|
|
985 |
}
|
17 |
ilm |
986 |
}
|