001 /*
002 * Licensed to the Apache Software Foundation (ASF) under one or more
003 * contributor license agreements. See the NOTICE file distributed with
004 * this work for additional information regarding copyright ownership.
005 * The ASF licenses this file to You under the Apache License, Version 2.0
006 * (the "License"); you may not use this file except in compliance with
007 * the License. You may obtain a copy of the License at
008 *
009 * http://www.apache.org/licenses/LICENSE-2.0
010 *
011 * Unless required by applicable law or agreed to in writing, software
012 * distributed under the License is distributed on an "AS IS" BASIS,
013 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
014 * See the License for the specific language governing permissions and
015 * limitations under the License.
016 */
017 package org.apache.commons.lang;
018
019 /**
020 * <p>Operations on char primitives and Character objects.</p>
021 *
022 * <p>This class tries to handle <code>null</code> input gracefully.
023 * An exception will not be thrown for a <code>null</code> input.
024 * Each method documents its behaviour in more detail.</p>
025 *
026 * <p>#ThreadSafe#</p>
027 * @author Apache Software Foundation
028 * @since 2.1
029 * @version $Id: CharUtils.java 1056988 2011-01-09 17:58:53Z niallp $
030 */
031 public class CharUtils {
032
033 private static final String CHAR_STRING =
034 "\u0000\u0001\u0002\u0003\u0004\u0005\u0006\u0007" +
035 "\b\t\n\u000b\f\r\u000e\u000f" +
036 "\u0010\u0011\u0012\u0013\u0014\u0015\u0016\u0017" +
037 "\u0018\u0019\u001a\u001b\u001c\u001d\u001e\u001f" +
038 "\u0020\u0021\"\u0023\u0024\u0025\u0026\u0027" +
039 "\u0028\u0029\u002a\u002b\u002c\u002d\u002e\u002f" +
040 "\u0030\u0031\u0032\u0033\u0034\u0035\u0036\u0037" +
041 "\u0038\u0039\u003a\u003b\u003c\u003d\u003e\u003f" +
042 "\u0040\u0041\u0042\u0043\u0044\u0045\u0046\u0047" +
043 "\u0048\u0049\u004a\u004b\u004c\u004d\u004e\u004f" +
044 "\u0050\u0051\u0052\u0053\u0054\u0055\u0056\u0057" +
045 "\u0058\u0059\u005a\u005b\\\u005d\u005e\u005f" +
046 "\u0060\u0061\u0062\u0063\u0064\u0065\u0066\u0067" +
047 "\u0068\u0069\u006a\u006b\u006c\u006d\u006e\u006f" +
048 "\u0070\u0071\u0072\u0073\u0074\u0075\u0076\u0077" +
049 "\u0078\u0079\u007a\u007b\u007c\u007d\u007e\u007f";
050
051 private static final String[] CHAR_STRING_ARRAY = new String[128];
052 private static final Character[] CHAR_ARRAY = new Character[128];
053
054 /**
055 * <code>\u000a</code> linefeed LF ('\n').
056 *
057 * @see <a href="http://java.sun.com/docs/books/jls/third_edition/html/lexical.html#101089">JLF: Escape Sequences
058 * for Character and String Literals</a>
059 * @since 2.2
060 */
061 public static final char LF = '\n';
062
063 /**
064 * <code>\u000d</code> carriage return CR ('\r').
065 *
066 * @see <a href="http://java.sun.com/docs/books/jls/third_edition/html/lexical.html#101089">JLF: Escape Sequences
067 * for Character and String Literals</a>
068 * @since 2.2
069 */
070 public static final char CR = '\r';
071
072
073 static {
074 for (int i = 127; i >= 0; i--) {
075 CHAR_STRING_ARRAY[i] = CHAR_STRING.substring(i, i + 1);
076 CHAR_ARRAY[i] = new Character((char) i);
077 }
078 }
079
080 /**
081 * <p><code>CharUtils</code> instances should NOT be constructed in standard programming.
082 * Instead, the class should be used as <code>CharUtils.toString('c');</code>.</p>
083 *
084 * <p>This constructor is public to permit tools that require a JavaBean instance
085 * to operate.</p>
086 */
087 public CharUtils() {
088 super();
089 }
090
091 //-----------------------------------------------------------------------
092 /**
093 * <p>Converts the character to a Character.</p>
094 *
095 * <p>For ASCII 7 bit characters, this uses a cache that will return the
096 * same Character object each time.</p>
097 *
098 * <pre>
099 * CharUtils.toCharacterObject(' ') = ' '
100 * CharUtils.toCharacterObject('A') = 'A'
101 * </pre>
102 *
103 * @param ch the character to convert
104 * @return a Character of the specified character
105 */
106 public static Character toCharacterObject(char ch) {
107 if (ch < CHAR_ARRAY.length) {
108 return CHAR_ARRAY[ch];
109 }
110 return new Character(ch);
111 }
112
113 /**
114 * <p>Converts the String to a Character using the first character, returning
115 * null for empty Strings.</p>
116 *
117 * <p>For ASCII 7 bit characters, this uses a cache that will return the
118 * same Character object each time.</p>
119 *
120 * <pre>
121 * CharUtils.toCharacterObject(null) = null
122 * CharUtils.toCharacterObject("") = null
123 * CharUtils.toCharacterObject("A") = 'A'
124 * CharUtils.toCharacterObject("BA") = 'B'
125 * </pre>
126 *
127 * @param str the character to convert
128 * @return the Character value of the first letter of the String
129 */
130 public static Character toCharacterObject(String str) {
131 if (StringUtils.isEmpty(str)) {
132 return null;
133 }
134 return toCharacterObject(str.charAt(0));
135 }
136
137 //-----------------------------------------------------------------------
138 /**
139 * <p>Converts the Character to a char throwing an exception for <code>null</code>.</p>
140 *
141 * <pre>
142 * CharUtils.toChar(null) = IllegalArgumentException
143 * CharUtils.toChar(' ') = ' '
144 * CharUtils.toChar('A') = 'A'
145 * </pre>
146 *
147 * @param ch the character to convert
148 * @return the char value of the Character
149 * @throws IllegalArgumentException if the Character is null
150 */
151 public static char toChar(Character ch) {
152 if (ch == null) {
153 throw new IllegalArgumentException("The Character must not be null");
154 }
155 return ch.charValue();
156 }
157
158 /**
159 * <p>Converts the Character to a char handling <code>null</code>.</p>
160 *
161 * <pre>
162 * CharUtils.toChar(null, 'X') = 'X'
163 * CharUtils.toChar(' ', 'X') = ' '
164 * CharUtils.toChar('A', 'X') = 'A'
165 * </pre>
166 *
167 * @param ch the character to convert
168 * @param defaultValue the value to use if the Character is null
169 * @return the char value of the Character or the default if null
170 */
171 public static char toChar(Character ch, char defaultValue) {
172 if (ch == null) {
173 return defaultValue;
174 }
175 return ch.charValue();
176 }
177
178 //-----------------------------------------------------------------------
179 /**
180 * <p>Converts the String to a char using the first character, throwing
181 * an exception on empty Strings.</p>
182 *
183 * <pre>
184 * CharUtils.toChar(null) = IllegalArgumentException
185 * CharUtils.toChar("") = IllegalArgumentException
186 * CharUtils.toChar("A") = 'A'
187 * CharUtils.toChar("BA") = 'B'
188 * </pre>
189 *
190 * @param str the character to convert
191 * @return the char value of the first letter of the String
192 * @throws IllegalArgumentException if the String is empty
193 */
194 public static char toChar(String str) {
195 if (StringUtils.isEmpty(str)) {
196 throw new IllegalArgumentException("The String must not be empty");
197 }
198 return str.charAt(0);
199 }
200
201 /**
202 * <p>Converts the String to a char using the first character, defaulting
203 * the value on empty Strings.</p>
204 *
205 * <pre>
206 * CharUtils.toChar(null, 'X') = 'X'
207 * CharUtils.toChar("", 'X') = 'X'
208 * CharUtils.toChar("A", 'X') = 'A'
209 * CharUtils.toChar("BA", 'X') = 'B'
210 * </pre>
211 *
212 * @param str the character to convert
213 * @param defaultValue the value to use if the Character is null
214 * @return the char value of the first letter of the String or the default if null
215 */
216 public static char toChar(String str, char defaultValue) {
217 if (StringUtils.isEmpty(str)) {
218 return defaultValue;
219 }
220 return str.charAt(0);
221 }
222
223 //-----------------------------------------------------------------------
224 /**
225 * <p>Converts the character to the Integer it represents, throwing an
226 * exception if the character is not numeric.</p>
227 *
228 * <p>This method coverts the char '1' to the int 1 and so on.</p>
229 *
230 * <pre>
231 * CharUtils.toIntValue('3') = 3
232 * CharUtils.toIntValue('A') = IllegalArgumentException
233 * </pre>
234 *
235 * @param ch the character to convert
236 * @return the int value of the character
237 * @throws IllegalArgumentException if the character is not ASCII numeric
238 */
239 public static int toIntValue(char ch) {
240 if (isAsciiNumeric(ch) == false) {
241 throw new IllegalArgumentException("The character " + ch + " is not in the range '0' - '9'");
242 }
243 return ch - 48;
244 }
245
246 /**
247 * <p>Converts the character to the Integer it represents, throwing an
248 * exception if the character is not numeric.</p>
249 *
250 * <p>This method coverts the char '1' to the int 1 and so on.</p>
251 *
252 * <pre>
253 * CharUtils.toIntValue('3', -1) = 3
254 * CharUtils.toIntValue('A', -1) = -1
255 * </pre>
256 *
257 * @param ch the character to convert
258 * @param defaultValue the default value to use if the character is not numeric
259 * @return the int value of the character
260 */
261 public static int toIntValue(char ch, int defaultValue) {
262 if (isAsciiNumeric(ch) == false) {
263 return defaultValue;
264 }
265 return ch - 48;
266 }
267
268 /**
269 * <p>Converts the character to the Integer it represents, throwing an
270 * exception if the character is not numeric.</p>
271 *
272 * <p>This method coverts the char '1' to the int 1 and so on.</p>
273 *
274 * <pre>
275 * CharUtils.toIntValue(null) = IllegalArgumentException
276 * CharUtils.toIntValue('3') = 3
277 * CharUtils.toIntValue('A') = IllegalArgumentException
278 * </pre>
279 *
280 * @param ch the character to convert, not null
281 * @return the int value of the character
282 * @throws IllegalArgumentException if the Character is not ASCII numeric or is null
283 */
284 public static int toIntValue(Character ch) {
285 if (ch == null) {
286 throw new IllegalArgumentException("The character must not be null");
287 }
288 return toIntValue(ch.charValue());
289 }
290
291 /**
292 * <p>Converts the character to the Integer it represents, throwing an
293 * exception if the character is not numeric.</p>
294 *
295 * <p>This method coverts the char '1' to the int 1 and so on.</p>
296 *
297 * <pre>
298 * CharUtils.toIntValue(null, -1) = -1
299 * CharUtils.toIntValue('3', -1) = 3
300 * CharUtils.toIntValue('A', -1) = -1
301 * </pre>
302 *
303 * @param ch the character to convert
304 * @param defaultValue the default value to use if the character is not numeric
305 * @return the int value of the character
306 */
307 public static int toIntValue(Character ch, int defaultValue) {
308 if (ch == null) {
309 return defaultValue;
310 }
311 return toIntValue(ch.charValue(), defaultValue);
312 }
313
314 //-----------------------------------------------------------------------
315 /**
316 * <p>Converts the character to a String that contains the one character.</p>
317 *
318 * <p>For ASCII 7 bit characters, this uses a cache that will return the
319 * same String object each time.</p>
320 *
321 * <pre>
322 * CharUtils.toString(' ') = " "
323 * CharUtils.toString('A') = "A"
324 * </pre>
325 *
326 * @param ch the character to convert
327 * @return a String containing the one specified character
328 */
329 public static String toString(char ch) {
330 if (ch < 128) {
331 return CHAR_STRING_ARRAY[ch];
332 }
333 return new String(new char[] {ch});
334 }
335
336 /**
337 * <p>Converts the character to a String that contains the one character.</p>
338 *
339 * <p>For ASCII 7 bit characters, this uses a cache that will return the
340 * same String object each time.</p>
341 *
342 * <p>If <code>null</code> is passed in, <code>null</code> will be returned.</p>
343 *
344 * <pre>
345 * CharUtils.toString(null) = null
346 * CharUtils.toString(' ') = " "
347 * CharUtils.toString('A') = "A"
348 * </pre>
349 *
350 * @param ch the character to convert
351 * @return a String containing the one specified character
352 */
353 public static String toString(Character ch) {
354 if (ch == null) {
355 return null;
356 }
357 return toString(ch.charValue());
358 }
359
360 //--------------------------------------------------------------------------
361 /**
362 * <p>Converts the string to the unicode format '\u0020'.</p>
363 *
364 * <p>This format is the Java source code format.</p>
365 *
366 * <pre>
367 * CharUtils.unicodeEscaped(' ') = "\u0020"
368 * CharUtils.unicodeEscaped('A') = "\u0041"
369 * </pre>
370 *
371 * @param ch the character to convert
372 * @return the escaped unicode string
373 */
374 public static String unicodeEscaped(char ch) {
375 if (ch < 0x10) {
376 return "\\u000" + Integer.toHexString(ch);
377 } else if (ch < 0x100) {
378 return "\\u00" + Integer.toHexString(ch);
379 } else if (ch < 0x1000) {
380 return "\\u0" + Integer.toHexString(ch);
381 }
382 return "\\u" + Integer.toHexString(ch);
383 }
384
385 /**
386 * <p>Converts the string to the unicode format '\u0020'.</p>
387 *
388 * <p>This format is the Java source code format.</p>
389 *
390 * <p>If <code>null</code> is passed in, <code>null</code> will be returned.</p>
391 *
392 * <pre>
393 * CharUtils.unicodeEscaped(null) = null
394 * CharUtils.unicodeEscaped(' ') = "\u0020"
395 * CharUtils.unicodeEscaped('A') = "\u0041"
396 * </pre>
397 *
398 * @param ch the character to convert, may be null
399 * @return the escaped unicode string, null if null input
400 */
401 public static String unicodeEscaped(Character ch) {
402 if (ch == null) {
403 return null;
404 }
405 return unicodeEscaped(ch.charValue());
406 }
407
408 //--------------------------------------------------------------------------
409 /**
410 * <p>Checks whether the character is ASCII 7 bit.</p>
411 *
412 * <pre>
413 * CharUtils.isAscii('a') = true
414 * CharUtils.isAscii('A') = true
415 * CharUtils.isAscii('3') = true
416 * CharUtils.isAscii('-') = true
417 * CharUtils.isAscii('\n') = true
418 * CharUtils.isAscii('©') = false
419 * </pre>
420 *
421 * @param ch the character to check
422 * @return true if less than 128
423 */
424 public static boolean isAscii(char ch) {
425 return ch < 128;
426 }
427
428 /**
429 * <p>Checks whether the character is ASCII 7 bit printable.</p>
430 *
431 * <pre>
432 * CharUtils.isAsciiPrintable('a') = true
433 * CharUtils.isAsciiPrintable('A') = true
434 * CharUtils.isAsciiPrintable('3') = true
435 * CharUtils.isAsciiPrintable('-') = true
436 * CharUtils.isAsciiPrintable('\n') = false
437 * CharUtils.isAsciiPrintable('©') = false
438 * </pre>
439 *
440 * @param ch the character to check
441 * @return true if between 32 and 126 inclusive
442 */
443 public static boolean isAsciiPrintable(char ch) {
444 return ch >= 32 && ch < 127;
445 }
446
447 /**
448 * <p>Checks whether the character is ASCII 7 bit control.</p>
449 *
450 * <pre>
451 * CharUtils.isAsciiControl('a') = false
452 * CharUtils.isAsciiControl('A') = false
453 * CharUtils.isAsciiControl('3') = false
454 * CharUtils.isAsciiControl('-') = false
455 * CharUtils.isAsciiControl('\n') = true
456 * CharUtils.isAsciiControl('©') = false
457 * </pre>
458 *
459 * @param ch the character to check
460 * @return true if less than 32 or equals 127
461 */
462 public static boolean isAsciiControl(char ch) {
463 return ch < 32 || ch == 127;
464 }
465
466 /**
467 * <p>Checks whether the character is ASCII 7 bit alphabetic.</p>
468 *
469 * <pre>
470 * CharUtils.isAsciiAlpha('a') = true
471 * CharUtils.isAsciiAlpha('A') = true
472 * CharUtils.isAsciiAlpha('3') = false
473 * CharUtils.isAsciiAlpha('-') = false
474 * CharUtils.isAsciiAlpha('\n') = false
475 * CharUtils.isAsciiAlpha('©') = false
476 * </pre>
477 *
478 * @param ch the character to check
479 * @return true if between 65 and 90 or 97 and 122 inclusive
480 */
481 public static boolean isAsciiAlpha(char ch) {
482 return (ch >= 'A' && ch <= 'Z') || (ch >= 'a' && ch <= 'z');
483 }
484
485 /**
486 * <p>Checks whether the character is ASCII 7 bit alphabetic upper case.</p>
487 *
488 * <pre>
489 * CharUtils.isAsciiAlphaUpper('a') = false
490 * CharUtils.isAsciiAlphaUpper('A') = true
491 * CharUtils.isAsciiAlphaUpper('3') = false
492 * CharUtils.isAsciiAlphaUpper('-') = false
493 * CharUtils.isAsciiAlphaUpper('\n') = false
494 * CharUtils.isAsciiAlphaUpper('©') = false
495 * </pre>
496 *
497 * @param ch the character to check
498 * @return true if between 65 and 90 inclusive
499 */
500 public static boolean isAsciiAlphaUpper(char ch) {
501 return ch >= 'A' && ch <= 'Z';
502 }
503
504 /**
505 * <p>Checks whether the character is ASCII 7 bit alphabetic lower case.</p>
506 *
507 * <pre>
508 * CharUtils.isAsciiAlphaLower('a') = true
509 * CharUtils.isAsciiAlphaLower('A') = false
510 * CharUtils.isAsciiAlphaLower('3') = false
511 * CharUtils.isAsciiAlphaLower('-') = false
512 * CharUtils.isAsciiAlphaLower('\n') = false
513 * CharUtils.isAsciiAlphaLower('©') = false
514 * </pre>
515 *
516 * @param ch the character to check
517 * @return true if between 97 and 122 inclusive
518 */
519 public static boolean isAsciiAlphaLower(char ch) {
520 return ch >= 'a' && ch <= 'z';
521 }
522
523 /**
524 * <p>Checks whether the character is ASCII 7 bit numeric.</p>
525 *
526 * <pre>
527 * CharUtils.isAsciiNumeric('a') = false
528 * CharUtils.isAsciiNumeric('A') = false
529 * CharUtils.isAsciiNumeric('3') = true
530 * CharUtils.isAsciiNumeric('-') = false
531 * CharUtils.isAsciiNumeric('\n') = false
532 * CharUtils.isAsciiNumeric('©') = false
533 * </pre>
534 *
535 * @param ch the character to check
536 * @return true if between 48 and 57 inclusive
537 */
538 public static boolean isAsciiNumeric(char ch) {
539 return ch >= '0' && ch <= '9';
540 }
541
542 /**
543 * <p>Checks whether the character is ASCII 7 bit numeric.</p>
544 *
545 * <pre>
546 * CharUtils.isAsciiAlphanumeric('a') = true
547 * CharUtils.isAsciiAlphanumeric('A') = true
548 * CharUtils.isAsciiAlphanumeric('3') = true
549 * CharUtils.isAsciiAlphanumeric('-') = false
550 * CharUtils.isAsciiAlphanumeric('\n') = false
551 * CharUtils.isAsciiAlphanumeric('©') = false
552 * </pre>
553 *
554 * @param ch the character to check
555 * @return true if between 48 and 57 or 65 and 90 or 97 and 122 inclusive
556 */
557 public static boolean isAsciiAlphanumeric(char ch) {
558 return (ch >= 'A' && ch <= 'Z') || (ch >= 'a' && ch <= 'z') || (ch >= '0' && ch <= '9');
559 }
560
561 // ----------------- Following code copied from Apache Harmony (Character class)
562 /**
563 * Indicates whether {@code ch} is a high- (or leading-) surrogate code unit
564 * that is used for representing supplementary characters in UTF-16
565 * encoding.
566 *
567 * @param ch
568 * the character to test.
569 * @return {@code true} if {@code ch} is a high-surrogate code unit;
570 * {@code false} otherwise.
571 */
572 static boolean isHighSurrogate(char ch) {
573 return ('\uD800' <= ch && '\uDBFF' >= ch);
574 }
575
576 }