1 /*
2 * Licensed to the Apache Software Foundation (ASF) under one or more
3 * contributor license agreements. See the NOTICE file distributed with
4 * this work for additional information regarding copyright ownership.
5 * The ASF licenses this file to You under the Apache License, Version 2.0
6 * (the "License"); you may not use this file except in compliance with
7 * the License. You may obtain a copy of the License at
8 *
9 * http://www.apache.org/licenses/LICENSE-2.0
10 *
11 * Unless required by applicable law or agreed to in writing, software
12 * distributed under the License is distributed on an "AS IS" BASIS,
13 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 * See the License for the specific language governing permissions and
15 * limitations under the License.
16 */
17 package org.apache.commons.lang3;
18
19 import java.io.UnsupportedEncodingException;
20 import java.nio.charset.Charset;
21 import java.text.Normalizer;
22 import java.util.ArrayList;
23 import java.util.Arrays;
24 import java.util.HashSet;
25 import java.util.Iterator;
26 import java.util.List;
27 import java.util.Locale;
28 import java.util.Objects;
29 import java.util.Set;
30 import java.util.function.Supplier;
31 import java.util.regex.Pattern;
32
33 import org.apache.commons.lang3.function.Suppliers;
34 import org.apache.commons.lang3.function.ToBooleanBiFunction;
35 import org.apache.commons.lang3.stream.LangCollectors;
36 import org.apache.commons.lang3.stream.Streams;
37
38 /**
39 * Operations on {@link java.lang.String} that are
40 * {@code null} safe.
41 *
42 * <ul>
43 * <li><b>IsEmpty/IsBlank</b>
44 * - checks if a String contains text</li>
45 * <li><b>Trim/Strip</b>
46 * - removes leading and trailing whitespace</li>
47 * <li><b>Equals/Compare</b>
48 * - compares two strings in a null-safe manner</li>
49 * <li><b>startsWith</b>
50 * - check if a String starts with a prefix in a null-safe manner</li>
51 * <li><b>endsWith</b>
52 * - check if a String ends with a suffix in a null-safe manner</li>
53 * <li><b>IndexOf/LastIndexOf/Contains</b>
54 * - null-safe index-of checks
55 * <li><b>IndexOfAny/LastIndexOfAny/IndexOfAnyBut/LastIndexOfAnyBut</b>
56 * - index-of any of a set of Strings</li>
57 * <li><b>ContainsOnly/ContainsNone/ContainsAny</b>
58 * - checks if String contains only/none/any of these characters</li>
59 * <li><b>Substring/Left/Right/Mid</b>
60 * - null-safe substring extractions</li>
61 * <li><b>SubstringBefore/SubstringAfter/SubstringBetween</b>
62 * - substring extraction relative to other strings</li>
63 * <li><b>Split/Join</b>
64 * - splits a String into an array of substrings and vice versa</li>
65 * <li><b>Remove/Delete</b>
66 * - removes part of a String</li>
67 * <li><b>Replace/Overlay</b>
68 * - Searches a String and replaces one String with another</li>
69 * <li><b>Chomp/Chop</b>
70 * - removes the last part of a String</li>
71 * <li><b>AppendIfMissing</b>
72 * - appends a suffix to the end of the String if not present</li>
73 * <li><b>PrependIfMissing</b>
74 * - prepends a prefix to the start of the String if not present</li>
75 * <li><b>LeftPad/RightPad/Center/Repeat</b>
76 * - pads a String</li>
77 * <li><b>UpperCase/LowerCase/SwapCase/Capitalize/Uncapitalize</b>
78 * - changes the case of a String</li>
79 * <li><b>CountMatches</b>
80 * - counts the number of occurrences of one String in another</li>
81 * <li><b>IsAlpha/IsNumeric/IsWhitespace/IsAsciiPrintable</b>
82 * - checks the characters in a String</li>
83 * <li><b>DefaultString</b>
84 * - protects against a null input String</li>
85 * <li><b>Rotate</b>
86 * - rotate (circular shift) a String</li>
87 * <li><b>Reverse/ReverseDelimited</b>
88 * - reverses a String</li>
89 * <li><b>Abbreviate</b>
90 * - abbreviates a string using ellipses or another given String</li>
91 * <li><b>Difference</b>
92 * - compares Strings and reports on their differences</li>
93 * <li><b>LevenshteinDistance</b>
94 * - the number of changes needed to change one String into another</li>
95 * </ul>
96 *
97 * <p>The {@link StringUtils} class defines certain words related to
98 * String handling.</p>
99 *
100 * <ul>
101 * <li>null - {@code null}</li>
102 * <li>empty - a zero-length string ({@code ""})</li>
103 * <li>space - the space character ({@code ' '}, char 32)</li>
104 * <li>whitespace - the characters defined by {@link Character#isWhitespace(char)}</li>
105 * <li>trim - the characters <= 32 as in {@link String#trim()}</li>
106 * </ul>
107 *
108 * <p>{@link StringUtils} handles {@code null} input Strings quietly.
109 * That is to say that a {@code null} input will return {@code null}.
110 * Where a {@code boolean} or {@code int} is being returned
111 * details vary by method.</p>
112 *
113 * <p>A side effect of the {@code null} handling is that a
114 * {@link NullPointerException} should be considered a bug in
115 * {@link StringUtils}.</p>
116 *
117 * <p>Methods in this class include sample code in their Javadoc comments to explain their operation.
118 * The symbol {@code *} is used to indicate any input including {@code null}.</p>
119 *
120 * <p>#ThreadSafe#</p>
121 * @see String
122 * @since 1.0
123 */
124 //@Immutable
125 public class StringUtils {
126
127 // Performance testing notes (JDK 1.4, Jul03, scolebourne)
128 // Whitespace:
129 // Character.isWhitespace() is faster than WHITESPACE.indexOf()
130 // where WHITESPACE is a string of all whitespace characters
131 //
132 // Character access:
133 // String.charAt(n) versus toCharArray(), then array[n]
134 // String.charAt(n) is about 15% worse for a 10K string
135 // They are about equal for a length 50 string
136 // String.charAt(n) is about 4 times better for a length 3 string
137 // String.charAt(n) is best bet overall
138 //
139 // Append:
140 // String.concat about twice as fast as StringBuffer.append
141 // (not sure who tested this)
142
143 /**
144 * A String for a space character.
145 *
146 * @since 3.2
147 */
148 public static final String SPACE = " ";
149
150 /**
151 * The empty String {@code ""}.
152 * @since 2.0
153 */
154 public static final String EMPTY = "";
155
156 /**
157 * A String for linefeed LF ("\n").
158 *
159 * @see <a href="https://docs.oracle.com/javase/specs/jls/se8/html/jls-3.html#jls-3.10.6">JLF: Escape Sequences
160 * for Character and String Literals</a>
161 * @since 3.2
162 */
163 public static final String LF = "\n";
164
165 /**
166 * A String for carriage return CR ("\r").
167 *
168 * @see <a href="https://docs.oracle.com/javase/specs/jls/se8/html/jls-3.html#jls-3.10.6">JLF: Escape Sequences
169 * for Character and String Literals</a>
170 * @since 3.2
171 */
172 public static final String CR = "\r";
173
174 /**
175 * Represents a failed index search.
176 * @since 2.1
177 */
178 public static final int INDEX_NOT_FOUND = -1;
179
180 /**
181 * The maximum size to which the padding constant(s) can expand.
182 */
183 private static final int PAD_LIMIT = 8192;
184
185 /**
186 * Pattern used in {@link #stripAccents(String)}.
187 */
188 private static final Pattern STRIP_ACCENTS_PATTERN = Pattern.compile("\\p{InCombiningDiacriticalMarks}+"); //$NON-NLS-1$
189
190 /**
191 * Abbreviates a String using ellipses. This will turn
192 * "Now is the time for all good men" into "Now is the time for..."
193 *
194 * <p>Specifically:</p>
195 * <ul>
196 * <li>If the number of characters in {@code str} is less than or equal to
197 * {@code maxWidth}, return {@code str}.</li>
198 * <li>Else abbreviate it to {@code (substring(str, 0, max-3) + "...")}.</li>
199 * <li>If {@code maxWidth} is less than {@code 4}, throw an
200 * {@link IllegalArgumentException}.</li>
201 * <li>In no case will it return a String of length greater than
202 * {@code maxWidth}.</li>
203 * </ul>
204 *
205 * <pre>
206 * StringUtils.abbreviate(null, *) = null
207 * StringUtils.abbreviate("", 4) = ""
208 * StringUtils.abbreviate("abcdefg", 6) = "abc..."
209 * StringUtils.abbreviate("abcdefg", 7) = "abcdefg"
210 * StringUtils.abbreviate("abcdefg", 8) = "abcdefg"
211 * StringUtils.abbreviate("abcdefg", 4) = "a..."
212 * StringUtils.abbreviate("abcdefg", 3) = IllegalArgumentException
213 * </pre>
214 *
215 * @param str the String to check, may be null
216 * @param maxWidth maximum length of result String, must be at least 4
217 * @return abbreviated String, {@code null} if null String input
218 * @throws IllegalArgumentException if the width is too small
219 * @since 2.0
220 */
221 public static String abbreviate(final String str, final int maxWidth) {
222 return abbreviate(str, "...", 0, maxWidth);
223 }
224
225 /**
226 * Abbreviates a String using ellipses. This will turn
227 * "Now is the time for all good men" into "...is the time for..."
228 *
229 * <p>Works like {@code abbreviate(String, int)}, but allows you to specify
230 * a "left edge" offset. Note that this left edge is not necessarily going to
231 * be the leftmost character in the result, or the first character following the
232 * ellipses, but it will appear somewhere in the result.
233 *
234 * <p>In no case will it return a String of length greater than
235 * {@code maxWidth}.</p>
236 *
237 * <pre>
238 * StringUtils.abbreviate(null, *, *) = null
239 * StringUtils.abbreviate("", 0, 4) = ""
240 * StringUtils.abbreviate("abcdefghijklmno", -1, 10) = "abcdefg..."
241 * StringUtils.abbreviate("abcdefghijklmno", 0, 10) = "abcdefg..."
242 * StringUtils.abbreviate("abcdefghijklmno", 1, 10) = "abcdefg..."
243 * StringUtils.abbreviate("abcdefghijklmno", 4, 10) = "abcdefg..."
244 * StringUtils.abbreviate("abcdefghijklmno", 5, 10) = "...fghi..."
245 * StringUtils.abbreviate("abcdefghijklmno", 6, 10) = "...ghij..."
246 * StringUtils.abbreviate("abcdefghijklmno", 8, 10) = "...ijklmno"
247 * StringUtils.abbreviate("abcdefghijklmno", 10, 10) = "...ijklmno"
248 * StringUtils.abbreviate("abcdefghijklmno", 12, 10) = "...ijklmno"
249 * StringUtils.abbreviate("abcdefghij", 0, 3) = IllegalArgumentException
250 * StringUtils.abbreviate("abcdefghij", 5, 6) = IllegalArgumentException
251 * </pre>
252 *
253 * @param str the String to check, may be null
254 * @param offset left edge of source String
255 * @param maxWidth maximum length of result String, must be at least 4
256 * @return abbreviated String, {@code null} if null String input
257 * @throws IllegalArgumentException if the width is too small
258 * @since 2.0
259 */
260 public static String abbreviate(final String str, final int offset, final int maxWidth) {
261 return abbreviate(str, "...", offset, maxWidth);
262 }
263
264 /**
265 * Abbreviates a String using another given String as replacement marker. This will turn
266 * "Now is the time for all good men" into "Now is the time for..." if "..." was defined
267 * as the replacement marker.
268 *
269 * <p>Specifically:</p>
270 * <ul>
271 * <li>If the number of characters in {@code str} is less than or equal to
272 * {@code maxWidth}, return {@code str}.</li>
273 * <li>Else abbreviate it to {@code (substring(str, 0, max-abbrevMarker.length) + abbrevMarker)}.</li>
274 * <li>If {@code maxWidth} is less than {@code abbrevMarker.length + 1}, throw an
275 * {@link IllegalArgumentException}.</li>
276 * <li>In no case will it return a String of length greater than
277 * {@code maxWidth}.</li>
278 * </ul>
279 *
280 * <pre>
281 * StringUtils.abbreviate(null, "...", *) = null
282 * StringUtils.abbreviate("abcdefg", null, *) = "abcdefg"
283 * StringUtils.abbreviate("", "...", 4) = ""
284 * StringUtils.abbreviate("abcdefg", ".", 5) = "abcd."
285 * StringUtils.abbreviate("abcdefg", ".", 7) = "abcdefg"
286 * StringUtils.abbreviate("abcdefg", ".", 8) = "abcdefg"
287 * StringUtils.abbreviate("abcdefg", "..", 4) = "ab.."
288 * StringUtils.abbreviate("abcdefg", "..", 3) = "a.."
289 * StringUtils.abbreviate("abcdefg", "..", 2) = IllegalArgumentException
290 * StringUtils.abbreviate("abcdefg", "...", 3) = IllegalArgumentException
291 * </pre>
292 *
293 * @param str the String to check, may be null
294 * @param abbrevMarker the String used as replacement marker
295 * @param maxWidth maximum length of result String, must be at least {@code abbrevMarker.length + 1}
296 * @return abbreviated String, {@code null} if null String input
297 * @throws IllegalArgumentException if the width is too small
298 * @since 3.6
299 */
300 public static String abbreviate(final String str, final String abbrevMarker, final int maxWidth) {
301 return abbreviate(str, abbrevMarker, 0, maxWidth);
302 }
303 /**
304 * Abbreviates a String using a given replacement marker. This will turn
305 * "Now is the time for all good men" into "...is the time for..." if "..." was defined
306 * as the replacement marker.
307 *
308 * <p>Works like {@code abbreviate(String, String, int)}, but allows you to specify
309 * a "left edge" offset. Note that this left edge is not necessarily going to
310 * be the leftmost character in the result, or the first character following the
311 * replacement marker, but it will appear somewhere in the result.
312 *
313 * <p>In no case will it return a String of length greater than {@code maxWidth}.</p>
314 *
315 * <pre>
316 * StringUtils.abbreviate(null, null, *, *) = null
317 * StringUtils.abbreviate("abcdefghijklmno", null, *, *) = "abcdefghijklmno"
318 * StringUtils.abbreviate("", "...", 0, 4) = ""
319 * StringUtils.abbreviate("abcdefghijklmno", "---", -1, 10) = "abcdefg---"
320 * StringUtils.abbreviate("abcdefghijklmno", ",", 0, 10) = "abcdefghi,"
321 * StringUtils.abbreviate("abcdefghijklmno", ",", 1, 10) = "abcdefghi,"
322 * StringUtils.abbreviate("abcdefghijklmno", ",", 2, 10) = "abcdefghi,"
323 * StringUtils.abbreviate("abcdefghijklmno", "::", 4, 10) = "::efghij::"
324 * StringUtils.abbreviate("abcdefghijklmno", "...", 6, 10) = "...ghij..."
325 * StringUtils.abbreviate("abcdefghijklmno", "*", 9, 10) = "*ghijklmno"
326 * StringUtils.abbreviate("abcdefghijklmno", "'", 10, 10) = "'ghijklmno"
327 * StringUtils.abbreviate("abcdefghijklmno", "!", 12, 10) = "!ghijklmno"
328 * StringUtils.abbreviate("abcdefghij", "abra", 0, 4) = IllegalArgumentException
329 * StringUtils.abbreviate("abcdefghij", "...", 5, 6) = IllegalArgumentException
330 * </pre>
331 *
332 * @param str the String to check, may be null
333 * @param abbrevMarker the String used as replacement marker
334 * @param offset left edge of source String
335 * @param maxWidth maximum length of result String, must be at least 4
336 * @return abbreviated String, {@code null} if null String input
337 * @throws IllegalArgumentException if the width is too small
338 * @since 3.6
339 */
340 public static String abbreviate(final String str, final String abbrevMarker, int offset, final int maxWidth) {
341 if (isNotEmpty(str) && EMPTY.equals(abbrevMarker) && maxWidth > 0) {
342 return substring(str, 0, maxWidth);
343 }
344 if (isAnyEmpty(str, abbrevMarker)) {
345 return str;
346 }
347 final int abbrevMarkerLength = abbrevMarker.length();
348 final int minAbbrevWidth = abbrevMarkerLength + 1;
349 final int minAbbrevWidthOffset = abbrevMarkerLength + abbrevMarkerLength + 1;
350
351 if (maxWidth < minAbbrevWidth) {
352 throw new IllegalArgumentException(String.format("Minimum abbreviation width is %d", minAbbrevWidth));
353 }
354 final int strLen = str.length();
355 if (strLen <= maxWidth) {
356 return str;
357 }
358 if (offset > strLen) {
359 offset = strLen;
360 }
361 if (strLen - offset < maxWidth - abbrevMarkerLength) {
362 offset = strLen - (maxWidth - abbrevMarkerLength);
363 }
364 if (offset <= abbrevMarkerLength+1) {
365 return str.substring(0, maxWidth - abbrevMarkerLength) + abbrevMarker;
366 }
367 if (maxWidth < minAbbrevWidthOffset) {
368 throw new IllegalArgumentException(String.format("Minimum abbreviation width with offset is %d", minAbbrevWidthOffset));
369 }
370 if (offset + maxWidth - abbrevMarkerLength < strLen) {
371 return abbrevMarker + abbreviate(str.substring(offset), abbrevMarker, maxWidth - abbrevMarkerLength);
372 }
373 return abbrevMarker + str.substring(strLen - (maxWidth - abbrevMarkerLength));
374 }
375
376 /**
377 * Abbreviates a String to the length passed, replacing the middle characters with the supplied
378 * replacement String.
379 *
380 * <p>This abbreviation only occurs if the following criteria is met:</p>
381 * <ul>
382 * <li>Neither the String for abbreviation nor the replacement String are null or empty </li>
383 * <li>The length to truncate to is less than the length of the supplied String</li>
384 * <li>The length to truncate to is greater than 0</li>
385 * <li>The abbreviated String will have enough room for the length supplied replacement String
386 * and the first and last characters of the supplied String for abbreviation</li>
387 * </ul>
388 * <p>Otherwise, the returned String will be the same as the supplied String for abbreviation.
389 * </p>
390 *
391 * <pre>
392 * StringUtils.abbreviateMiddle(null, null, 0) = null
393 * StringUtils.abbreviateMiddle("abc", null, 0) = "abc"
394 * StringUtils.abbreviateMiddle("abc", ".", 0) = "abc"
395 * StringUtils.abbreviateMiddle("abc", ".", 3) = "abc"
396 * StringUtils.abbreviateMiddle("abcdef", ".", 4) = "ab.f"
397 * </pre>
398 *
399 * @param str the String to abbreviate, may be null
400 * @param middle the String to replace the middle characters with, may be null
401 * @param length the length to abbreviate {@code str} to.
402 * @return the abbreviated String if the above criteria is met, or the original String supplied for abbreviation.
403 * @since 2.5
404 */
405 public static String abbreviateMiddle(final String str, final String middle, final int length) {
406 if (isAnyEmpty(str, middle) || length >= str.length() || length < middle.length()+2) {
407 return str;
408 }
409
410 final int targetSting = length-middle.length();
411 final int startOffset = targetSting/2+targetSting%2;
412 final int endOffset = str.length()-targetSting/2;
413
414 return str.substring(0, startOffset) +
415 middle +
416 str.substring(endOffset);
417 }
418
419 /**
420 * Appends the suffix to the end of the string if the string does not
421 * already end with the suffix.
422 *
423 * @param str The string.
424 * @param suffix The suffix to append to the end of the string.
425 * @param ignoreCase Indicates whether the compare should ignore case.
426 * @param suffixes Additional suffixes that are valid terminators (optional).
427 *
428 * @return A new String if suffix was appended, the same string otherwise.
429 */
430 private static String appendIfMissing(final String str, final CharSequence suffix, final boolean ignoreCase, final CharSequence... suffixes) {
431 if (str == null || isEmpty(suffix) || endsWith(str, suffix, ignoreCase)) {
432 return str;
433 }
434 if (ArrayUtils.isNotEmpty(suffixes)) {
435 for (final CharSequence s : suffixes) {
436 if (endsWith(str, s, ignoreCase)) {
437 return str;
438 }
439 }
440 }
441 return str + suffix.toString();
442 }
443
444 /**
445 * Appends the suffix to the end of the string if the string does not
446 * already end with any of the suffixes.
447 *
448 * <pre>
449 * StringUtils.appendIfMissing(null, null) = null
450 * StringUtils.appendIfMissing("abc", null) = "abc"
451 * StringUtils.appendIfMissing("", "xyz") = "xyz"
452 * StringUtils.appendIfMissing("abc", "xyz") = "abcxyz"
453 * StringUtils.appendIfMissing("abcxyz", "xyz") = "abcxyz"
454 * StringUtils.appendIfMissing("abcXYZ", "xyz") = "abcXYZxyz"
455 * </pre>
456 * <p>With additional suffixes,</p>
457 * <pre>
458 * StringUtils.appendIfMissing(null, null, null) = null
459 * StringUtils.appendIfMissing("abc", null, null) = "abc"
460 * StringUtils.appendIfMissing("", "xyz", null) = "xyz"
461 * StringUtils.appendIfMissing("abc", "xyz", new CharSequence[]{null}) = "abcxyz"
462 * StringUtils.appendIfMissing("abc", "xyz", "") = "abc"
463 * StringUtils.appendIfMissing("abc", "xyz", "mno") = "abcxyz"
464 * StringUtils.appendIfMissing("abcxyz", "xyz", "mno") = "abcxyz"
465 * StringUtils.appendIfMissing("abcmno", "xyz", "mno") = "abcmno"
466 * StringUtils.appendIfMissing("abcXYZ", "xyz", "mno") = "abcXYZxyz"
467 * StringUtils.appendIfMissing("abcMNO", "xyz", "mno") = "abcMNOxyz"
468 * </pre>
469 *
470 * @param str The string.
471 * @param suffix The suffix to append to the end of the string.
472 * @param suffixes Additional suffixes that are valid terminators.
473 *
474 * @return A new String if suffix was appended, the same string otherwise.
475 *
476 * @since 3.2
477 */
478 public static String appendIfMissing(final String str, final CharSequence suffix, final CharSequence... suffixes) {
479 return appendIfMissing(str, suffix, false, suffixes);
480 }
481
482 /**
483 * Appends the suffix to the end of the string if the string does not
484 * already end, case-insensitive, with any of the suffixes.
485 *
486 * <pre>
487 * StringUtils.appendIfMissingIgnoreCase(null, null) = null
488 * StringUtils.appendIfMissingIgnoreCase("abc", null) = "abc"
489 * StringUtils.appendIfMissingIgnoreCase("", "xyz") = "xyz"
490 * StringUtils.appendIfMissingIgnoreCase("abc", "xyz") = "abcxyz"
491 * StringUtils.appendIfMissingIgnoreCase("abcxyz", "xyz") = "abcxyz"
492 * StringUtils.appendIfMissingIgnoreCase("abcXYZ", "xyz") = "abcXYZ"
493 * </pre>
494 * <p>With additional suffixes,</p>
495 * <pre>
496 * StringUtils.appendIfMissingIgnoreCase(null, null, null) = null
497 * StringUtils.appendIfMissingIgnoreCase("abc", null, null) = "abc"
498 * StringUtils.appendIfMissingIgnoreCase("", "xyz", null) = "xyz"
499 * StringUtils.appendIfMissingIgnoreCase("abc", "xyz", new CharSequence[]{null}) = "abcxyz"
500 * StringUtils.appendIfMissingIgnoreCase("abc", "xyz", "") = "abc"
501 * StringUtils.appendIfMissingIgnoreCase("abc", "xyz", "mno") = "abcxyz"
502 * StringUtils.appendIfMissingIgnoreCase("abcxyz", "xyz", "mno") = "abcxyz"
503 * StringUtils.appendIfMissingIgnoreCase("abcmno", "xyz", "mno") = "abcmno"
504 * StringUtils.appendIfMissingIgnoreCase("abcXYZ", "xyz", "mno") = "abcXYZ"
505 * StringUtils.appendIfMissingIgnoreCase("abcMNO", "xyz", "mno") = "abcMNO"
506 * </pre>
507 *
508 * @param str The string.
509 * @param suffix The suffix to append to the end of the string.
510 * @param suffixes Additional suffixes that are valid terminators.
511 *
512 * @return A new String if suffix was appended, the same string otherwise.
513 *
514 * @since 3.2
515 */
516 public static String appendIfMissingIgnoreCase(final String str, final CharSequence suffix, final CharSequence... suffixes) {
517 return appendIfMissing(str, suffix, true, suffixes);
518 }
519
520 /**
521 * Capitalizes a String changing the first character to title case as
522 * per {@link Character#toTitleCase(int)}. No other characters are changed.
523 *
524 * <p>For a word based algorithm, see {@link org.apache.commons.text.WordUtils#capitalize(String)}.
525 * A {@code null} input String returns {@code null}.</p>
526 *
527 * <pre>
528 * StringUtils.capitalize(null) = null
529 * StringUtils.capitalize("") = ""
530 * StringUtils.capitalize("cat") = "Cat"
531 * StringUtils.capitalize("cAt") = "CAt"
532 * StringUtils.capitalize("'cat'") = "'cat'"
533 * </pre>
534 *
535 * @param str the String to capitalize, may be null
536 * @return the capitalized String, {@code null} if null String input
537 * @see org.apache.commons.text.WordUtils#capitalize(String)
538 * @see #uncapitalize(String)
539 * @since 2.0
540 */
541 public static String capitalize(final String str) {
542 final int strLen = length(str);
543 if (strLen == 0) {
544 return str;
545 }
546
547 final int firstCodepoint = str.codePointAt(0);
548 final int newCodePoint = Character.toTitleCase(firstCodepoint);
549 if (firstCodepoint == newCodePoint) {
550 // already capitalized
551 return str;
552 }
553
554 final int[] newCodePoints = new int[strLen]; // cannot be longer than the char array
555 int outOffset = 0;
556 newCodePoints[outOffset++] = newCodePoint; // copy the first code point
557 for (int inOffset = Character.charCount(firstCodepoint); inOffset < strLen; ) {
558 final int codePoint = str.codePointAt(inOffset);
559 newCodePoints[outOffset++] = codePoint; // copy the remaining ones
560 inOffset += Character.charCount(codePoint);
561 }
562 return new String(newCodePoints, 0, outOffset);
563 }
564
565 /**
566 * Centers a String in a larger String of size {@code size}
567 * using the space character (' ').
568 *
569 * <p>If the size is less than the String length, the original String is returned.
570 * A {@code null} String returns {@code null}.
571 * A negative size is treated as zero.</p>
572 *
573 * <p>Equivalent to {@code center(str, size, " ")}.</p>
574 *
575 * <pre>
576 * StringUtils.center(null, *) = null
577 * StringUtils.center("", 4) = " "
578 * StringUtils.center("ab", -1) = "ab"
579 * StringUtils.center("ab", 4) = " ab "
580 * StringUtils.center("abcd", 2) = "abcd"
581 * StringUtils.center("a", 4) = " a "
582 * </pre>
583 *
584 * @param str the String to center, may be null
585 * @param size the int size of new String, negative treated as zero
586 * @return centered String, {@code null} if null String input
587 */
588 public static String center(final String str, final int size) {
589 return center(str, size, ' ');
590 }
591
592 /**
593 * Centers a String in a larger String of size {@code size}.
594 * Uses a supplied character as the value to pad the String with.
595 *
596 * <p>If the size is less than the String length, the String is returned.
597 * A {@code null} String returns {@code null}.
598 * A negative size is treated as zero.</p>
599 *
600 * <pre>
601 * StringUtils.center(null, *, *) = null
602 * StringUtils.center("", 4, ' ') = " "
603 * StringUtils.center("ab", -1, ' ') = "ab"
604 * StringUtils.center("ab", 4, ' ') = " ab "
605 * StringUtils.center("abcd", 2, ' ') = "abcd"
606 * StringUtils.center("a", 4, ' ') = " a "
607 * StringUtils.center("a", 4, 'y') = "yayy"
608 * </pre>
609 *
610 * @param str the String to center, may be null
611 * @param size the int size of new String, negative treated as zero
612 * @param padChar the character to pad the new String with
613 * @return centered String, {@code null} if null String input
614 * @since 2.0
615 */
616 public static String center(String str, final int size, final char padChar) {
617 if (str == null || size <= 0) {
618 return str;
619 }
620 final int strLen = str.length();
621 final int pads = size - strLen;
622 if (pads <= 0) {
623 return str;
624 }
625 str = leftPad(str, strLen + pads / 2, padChar);
626 str = rightPad(str, size, padChar);
627 return str;
628 }
629
630 /**
631 * Centers a String in a larger String of size {@code size}.
632 * Uses a supplied String as the value to pad the String with.
633 *
634 * <p>If the size is less than the String length, the String is returned.
635 * A {@code null} String returns {@code null}.
636 * A negative size is treated as zero.</p>
637 *
638 * <pre>
639 * StringUtils.center(null, *, *) = null
640 * StringUtils.center("", 4, " ") = " "
641 * StringUtils.center("ab", -1, " ") = "ab"
642 * StringUtils.center("ab", 4, " ") = " ab "
643 * StringUtils.center("abcd", 2, " ") = "abcd"
644 * StringUtils.center("a", 4, " ") = " a "
645 * StringUtils.center("a", 4, "yz") = "yayz"
646 * StringUtils.center("abc", 7, null) = " abc "
647 * StringUtils.center("abc", 7, "") = " abc "
648 * </pre>
649 *
650 * @param str the String to center, may be null
651 * @param size the int size of new String, negative treated as zero
652 * @param padStr the String to pad the new String with, must not be null or empty
653 * @return centered String, {@code null} if null String input
654 * @throws IllegalArgumentException if padStr is {@code null} or empty
655 */
656 public static String center(String str, final int size, String padStr) {
657 if (str == null || size <= 0) {
658 return str;
659 }
660 if (isEmpty(padStr)) {
661 padStr = SPACE;
662 }
663 final int strLen = str.length();
664 final int pads = size - strLen;
665 if (pads <= 0) {
666 return str;
667 }
668 str = leftPad(str, strLen + pads / 2, padStr);
669 str = rightPad(str, size, padStr);
670 return str;
671 }
672
673 /**
674 * Removes one newline from end of a String if it's there,
675 * otherwise leave it alone. A newline is "{@code \n}",
676 * "{@code \r}", or "{@code \r\n}".
677 *
678 * <p>NOTE: This method changed in 2.0.
679 * It now more closely matches Perl chomp.</p>
680 *
681 * <pre>
682 * StringUtils.chomp(null) = null
683 * StringUtils.chomp("") = ""
684 * StringUtils.chomp("abc \r") = "abc "
685 * StringUtils.chomp("abc\n") = "abc"
686 * StringUtils.chomp("abc\r\n") = "abc"
687 * StringUtils.chomp("abc\r\n\r\n") = "abc\r\n"
688 * StringUtils.chomp("abc\n\r") = "abc\n"
689 * StringUtils.chomp("abc\n\rabc") = "abc\n\rabc"
690 * StringUtils.chomp("\r") = ""
691 * StringUtils.chomp("\n") = ""
692 * StringUtils.chomp("\r\n") = ""
693 * </pre>
694 *
695 * @param str the String to chomp a newline from, may be null
696 * @return String without newline, {@code null} if null String input
697 */
698 public static String chomp(final String str) {
699 if (isEmpty(str)) {
700 return str;
701 }
702
703 if (str.length() == 1) {
704 final char ch = str.charAt(0);
705 if (ch == CharUtils.CR || ch == CharUtils.LF) {
706 return EMPTY;
707 }
708 return str;
709 }
710
711 int lastIdx = str.length() - 1;
712 final char last = str.charAt(lastIdx);
713
714 if (last == CharUtils.LF) {
715 if (str.charAt(lastIdx - 1) == CharUtils.CR) {
716 lastIdx--;
717 }
718 } else if (last != CharUtils.CR) {
719 lastIdx++;
720 }
721 return str.substring(0, lastIdx);
722 }
723
724 /**
725 * Removes {@code separator} from the end of
726 * {@code str} if it's there, otherwise leave it alone.
727 *
728 * <p>NOTE: This method changed in version 2.0.
729 * It now more closely matches Perl chomp.
730 * For the previous behavior, use {@link #substringBeforeLast(String, String)}.
731 * This method uses {@link String#endsWith(String)}.</p>
732 *
733 * <pre>
734 * StringUtils.chomp(null, *) = null
735 * StringUtils.chomp("", *) = ""
736 * StringUtils.chomp("foobar", "bar") = "foo"
737 * StringUtils.chomp("foobar", "baz") = "foobar"
738 * StringUtils.chomp("foo", "foo") = ""
739 * StringUtils.chomp("foo ", "foo") = "foo "
740 * StringUtils.chomp(" foo", "foo") = " "
741 * StringUtils.chomp("foo", "foooo") = "foo"
742 * StringUtils.chomp("foo", "") = "foo"
743 * StringUtils.chomp("foo", null) = "foo"
744 * </pre>
745 *
746 * @param str the String to chomp from, may be null
747 * @param separator separator String, may be null
748 * @return String without trailing separator, {@code null} if null String input
749 * @deprecated This feature will be removed in Lang 4, use {@link StringUtils#removeEnd(String, String)} instead
750 */
751 @Deprecated
752 public static String chomp(final String str, final String separator) {
753 return removeEnd(str, separator);
754 }
755
756 /**
757 * Remove the last character from a String.
758 *
759 * <p>If the String ends in {@code \r\n}, then remove both
760 * of them.</p>
761 *
762 * <pre>
763 * StringUtils.chop(null) = null
764 * StringUtils.chop("") = ""
765 * StringUtils.chop("abc \r") = "abc "
766 * StringUtils.chop("abc\n") = "abc"
767 * StringUtils.chop("abc\r\n") = "abc"
768 * StringUtils.chop("abc") = "ab"
769 * StringUtils.chop("abc\nabc") = "abc\nab"
770 * StringUtils.chop("a") = ""
771 * StringUtils.chop("\r") = ""
772 * StringUtils.chop("\n") = ""
773 * StringUtils.chop("\r\n") = ""
774 * </pre>
775 *
776 * @param str the String to chop last character from, may be null
777 * @return String without last character, {@code null} if null String input
778 */
779 public static String chop(final String str) {
780 if (str == null) {
781 return null;
782 }
783 final int strLen = str.length();
784 if (strLen < 2) {
785 return EMPTY;
786 }
787 final int lastIdx = strLen - 1;
788 final String ret = str.substring(0, lastIdx);
789 final char last = str.charAt(lastIdx);
790 if (last == CharUtils.LF && ret.charAt(lastIdx - 1) == CharUtils.CR) {
791 return ret.substring(0, lastIdx - 1);
792 }
793 return ret;
794 }
795
796 /**
797 * Compare two Strings lexicographically, as per {@link String#compareTo(String)}, returning :
798 * <ul>
799 * <li>{@code int = 0}, if {@code str1} is equal to {@code str2} (or both {@code null})</li>
800 * <li>{@code int < 0}, if {@code str1} is less than {@code str2}</li>
801 * <li>{@code int > 0}, if {@code str1} is greater than {@code str2}</li>
802 * </ul>
803 *
804 * <p>This is a {@code null} safe version of :</p>
805 * <blockquote><pre>str1.compareTo(str2)</pre></blockquote>
806 *
807 * <p>{@code null} value is considered less than non-{@code null} value.
808 * Two {@code null} references are considered equal.</p>
809 *
810 * <pre>
811 * StringUtils.compare(null, null) = 0
812 * StringUtils.compare(null , "a") < 0
813 * StringUtils.compare("a", null) > 0
814 * StringUtils.compare("abc", "abc") = 0
815 * StringUtils.compare("a", "b") < 0
816 * StringUtils.compare("b", "a") > 0
817 * StringUtils.compare("a", "B") > 0
818 * StringUtils.compare("ab", "abc") < 0
819 * </pre>
820 *
821 * @see #compare(String, String, boolean)
822 * @see String#compareTo(String)
823 * @param str1 the String to compare from
824 * @param str2 the String to compare to
825 * @return < 0, 0, > 0, if {@code str1} is respectively less, equal or greater than {@code str2}
826 * @since 3.5
827 */
828 public static int compare(final String str1, final String str2) {
829 return compare(str1, str2, true);
830 }
831
832 /**
833 * Compare two Strings lexicographically, as per {@link String#compareTo(String)}, returning :
834 * <ul>
835 * <li>{@code int = 0}, if {@code str1} is equal to {@code str2} (or both {@code null})</li>
836 * <li>{@code int < 0}, if {@code str1} is less than {@code str2}</li>
837 * <li>{@code int > 0}, if {@code str1} is greater than {@code str2}</li>
838 * </ul>
839 *
840 * <p>This is a {@code null} safe version of :</p>
841 * <blockquote><pre>str1.compareTo(str2)</pre></blockquote>
842 *
843 * <p>{@code null} inputs are handled according to the {@code nullIsLess} parameter.
844 * Two {@code null} references are considered equal.</p>
845 *
846 * <pre>
847 * StringUtils.compare(null, null, *) = 0
848 * StringUtils.compare(null , "a", true) < 0
849 * StringUtils.compare(null , "a", false) > 0
850 * StringUtils.compare("a", null, true) > 0
851 * StringUtils.compare("a", null, false) < 0
852 * StringUtils.compare("abc", "abc", *) = 0
853 * StringUtils.compare("a", "b", *) < 0
854 * StringUtils.compare("b", "a", *) > 0
855 * StringUtils.compare("a", "B", *) > 0
856 * StringUtils.compare("ab", "abc", *) < 0
857 * </pre>
858 *
859 * @see String#compareTo(String)
860 * @param str1 the String to compare from
861 * @param str2 the String to compare to
862 * @param nullIsLess whether consider {@code null} value less than non-{@code null} value
863 * @return < 0, 0, > 0, if {@code str1} is respectively less, equal ou greater than {@code str2}
864 * @since 3.5
865 */
866 public static int compare(final String str1, final String str2, final boolean nullIsLess) {
867 if (str1 == str2) { // NOSONARLINT this intentionally uses == to allow for both null
868 return 0;
869 }
870 if (str1 == null) {
871 return nullIsLess ? -1 : 1;
872 }
873 if (str2 == null) {
874 return nullIsLess ? 1 : - 1;
875 }
876 return str1.compareTo(str2);
877 }
878
879 /**
880 * Compare two Strings lexicographically, ignoring case differences,
881 * as per {@link String#compareToIgnoreCase(String)}, returning :
882 * <ul>
883 * <li>{@code int = 0}, if {@code str1} is equal to {@code str2} (or both {@code null})</li>
884 * <li>{@code int < 0}, if {@code str1} is less than {@code str2}</li>
885 * <li>{@code int > 0}, if {@code str1} is greater than {@code str2}</li>
886 * </ul>
887 *
888 * <p>This is a {@code null} safe version of :</p>
889 * <blockquote><pre>str1.compareToIgnoreCase(str2)</pre></blockquote>
890 *
891 * <p>{@code null} value is considered less than non-{@code null} value.
892 * Two {@code null} references are considered equal.
893 * Comparison is case insensitive.</p>
894 *
895 * <pre>
896 * StringUtils.compareIgnoreCase(null, null) = 0
897 * StringUtils.compareIgnoreCase(null , "a") < 0
898 * StringUtils.compareIgnoreCase("a", null) > 0
899 * StringUtils.compareIgnoreCase("abc", "abc") = 0
900 * StringUtils.compareIgnoreCase("abc", "ABC") = 0
901 * StringUtils.compareIgnoreCase("a", "b") < 0
902 * StringUtils.compareIgnoreCase("b", "a") > 0
903 * StringUtils.compareIgnoreCase("a", "B") < 0
904 * StringUtils.compareIgnoreCase("A", "b") < 0
905 * StringUtils.compareIgnoreCase("ab", "ABC") < 0
906 * </pre>
907 *
908 * @see #compareIgnoreCase(String, String, boolean)
909 * @see String#compareToIgnoreCase(String)
910 * @param str1 the String to compare from
911 * @param str2 the String to compare to
912 * @return < 0, 0, > 0, if {@code str1} is respectively less, equal ou greater than {@code str2},
913 * ignoring case differences.
914 * @since 3.5
915 */
916 public static int compareIgnoreCase(final String str1, final String str2) {
917 return compareIgnoreCase(str1, str2, true);
918 }
919
920 /**
921 * Compare two Strings lexicographically, ignoring case differences,
922 * as per {@link String#compareToIgnoreCase(String)}, returning :
923 * <ul>
924 * <li>{@code int = 0}, if {@code str1} is equal to {@code str2} (or both {@code null})</li>
925 * <li>{@code int < 0}, if {@code str1} is less than {@code str2}</li>
926 * <li>{@code int > 0}, if {@code str1} is greater than {@code str2}</li>
927 * </ul>
928 *
929 * <p>This is a {@code null} safe version of :</p>
930 * <blockquote><pre>str1.compareToIgnoreCase(str2)</pre></blockquote>
931 *
932 * <p>{@code null} inputs are handled according to the {@code nullIsLess} parameter.
933 * Two {@code null} references are considered equal.
934 * Comparison is case insensitive.</p>
935 *
936 * <pre>
937 * StringUtils.compareIgnoreCase(null, null, *) = 0
938 * StringUtils.compareIgnoreCase(null , "a", true) < 0
939 * StringUtils.compareIgnoreCase(null , "a", false) > 0
940 * StringUtils.compareIgnoreCase("a", null, true) > 0
941 * StringUtils.compareIgnoreCase("a", null, false) < 0
942 * StringUtils.compareIgnoreCase("abc", "abc", *) = 0
943 * StringUtils.compareIgnoreCase("abc", "ABC", *) = 0
944 * StringUtils.compareIgnoreCase("a", "b", *) < 0
945 * StringUtils.compareIgnoreCase("b", "a", *) > 0
946 * StringUtils.compareIgnoreCase("a", "B", *) < 0
947 * StringUtils.compareIgnoreCase("A", "b", *) < 0
948 * StringUtils.compareIgnoreCase("ab", "abc", *) < 0
949 * </pre>
950 *
951 * @see String#compareToIgnoreCase(String)
952 * @param str1 the String to compare from
953 * @param str2 the String to compare to
954 * @param nullIsLess whether consider {@code null} value less than non-{@code null} value
955 * @return < 0, 0, > 0, if {@code str1} is respectively less, equal ou greater than {@code str2},
956 * ignoring case differences.
957 * @since 3.5
958 */
959 public static int compareIgnoreCase(final String str1, final String str2, final boolean nullIsLess) {
960 if (str1 == str2) { // NOSONARLINT this intentionally uses == to allow for both null
961 return 0;
962 }
963 if (str1 == null) {
964 return nullIsLess ? -1 : 1;
965 }
966 if (str2 == null) {
967 return nullIsLess ? 1 : - 1;
968 }
969 return str1.compareToIgnoreCase(str2);
970 }
971
972 /**
973 * Checks if CharSequence contains a search CharSequence, handling {@code null}.
974 * This method uses {@link String#indexOf(String)} if possible.
975 *
976 * <p>A {@code null} CharSequence will return {@code false}.</p>
977 *
978 * <pre>
979 * StringUtils.contains(null, *) = false
980 * StringUtils.contains(*, null) = false
981 * StringUtils.contains("", "") = true
982 * StringUtils.contains("abc", "") = true
983 * StringUtils.contains("abc", "a") = true
984 * StringUtils.contains("abc", "z") = false
985 * </pre>
986 *
987 * @param seq the CharSequence to check, may be null
988 * @param searchSeq the CharSequence to find, may be null
989 * @return true if the CharSequence contains the search CharSequence,
990 * false if not or {@code null} string input
991 * @since 2.0
992 * @since 3.0 Changed signature from contains(String, String) to contains(CharSequence, CharSequence)
993 */
994 public static boolean contains(final CharSequence seq, final CharSequence searchSeq) {
995 if (seq == null || searchSeq == null) {
996 return false;
997 }
998 return CharSequenceUtils.indexOf(seq, searchSeq, 0) >= 0;
999 }
1000
1001 /**
1002 * Checks if CharSequence contains a search character, handling {@code null}.
1003 * This method uses {@link String#indexOf(int)} if possible.
1004 *
1005 * <p>A {@code null} or empty ("") CharSequence will return {@code false}.</p>
1006 *
1007 * <pre>
1008 * StringUtils.contains(null, *) = false
1009 * StringUtils.contains("", *) = false
1010 * StringUtils.contains("abc", 'a') = true
1011 * StringUtils.contains("abc", 'z') = false
1012 * </pre>
1013 *
1014 * @param seq the CharSequence to check, may be null
1015 * @param searchChar the character to find
1016 * @return true if the CharSequence contains the search character,
1017 * false if not or {@code null} string input
1018 * @since 2.0
1019 * @since 3.0 Changed signature from contains(String, int) to contains(CharSequence, int)
1020 */
1021 public static boolean contains(final CharSequence seq, final int searchChar) {
1022 if (isEmpty(seq)) {
1023 return false;
1024 }
1025 return CharSequenceUtils.indexOf(seq, searchChar, 0) >= 0;
1026 }
1027
1028 /**
1029 * Checks if the CharSequence contains any character in the given
1030 * set of characters.
1031 *
1032 * <p>A {@code null} CharSequence will return {@code false}.
1033 * A {@code null} or zero length search array will return {@code false}.</p>
1034 *
1035 * <pre>
1036 * StringUtils.containsAny(null, *) = false
1037 * StringUtils.containsAny("", *) = false
1038 * StringUtils.containsAny(*, null) = false
1039 * StringUtils.containsAny(*, []) = false
1040 * StringUtils.containsAny("zzabyycdxx", ['z', 'a']) = true
1041 * StringUtils.containsAny("zzabyycdxx", ['b', 'y']) = true
1042 * StringUtils.containsAny("zzabyycdxx", ['z', 'y']) = true
1043 * StringUtils.containsAny("aba", ['z']) = false
1044 * </pre>
1045 *
1046 * @param cs the CharSequence to check, may be null
1047 * @param searchChars the chars to search for, may be null
1048 * @return the {@code true} if any of the chars are found,
1049 * {@code false} if no match or null input
1050 * @since 2.4
1051 * @since 3.0 Changed signature from containsAny(String, char[]) to containsAny(CharSequence, char...)
1052 */
1053 public static boolean containsAny(final CharSequence cs, final char... searchChars) {
1054 if (isEmpty(cs) || ArrayUtils.isEmpty(searchChars)) {
1055 return false;
1056 }
1057 final int csLength = cs.length();
1058 final int searchLength = searchChars.length;
1059 final int csLast = csLength - 1;
1060 final int searchLast = searchLength - 1;
1061 for (int i = 0; i < csLength; i++) {
1062 final char ch = cs.charAt(i);
1063 for (int j = 0; j < searchLength; j++) {
1064 if (searchChars[j] == ch) {
1065 if (!Character.isHighSurrogate(ch)) {
1066 // ch is in the Basic Multilingual Plane
1067 return true;
1068 }
1069 if (j == searchLast) {
1070 // missing low surrogate, fine, like String.indexOf(String)
1071 return true;
1072 }
1073 if (i < csLast && searchChars[j + 1] == cs.charAt(i + 1)) {
1074 return true;
1075 }
1076 }
1077 }
1078 }
1079 return false;
1080 }
1081
1082 /**
1083 * Checks if the CharSequence contains any character in the given set of characters.
1084 *
1085 * <p>
1086 * A {@code null} CharSequence will return {@code false}. A {@code null} search CharSequence will return
1087 * {@code false}.
1088 * </p>
1089 *
1090 * <pre>
1091 * StringUtils.containsAny(null, *) = false
1092 * StringUtils.containsAny("", *) = false
1093 * StringUtils.containsAny(*, null) = false
1094 * StringUtils.containsAny(*, "") = false
1095 * StringUtils.containsAny("zzabyycdxx", "za") = true
1096 * StringUtils.containsAny("zzabyycdxx", "by") = true
1097 * StringUtils.containsAny("zzabyycdxx", "zy") = true
1098 * StringUtils.containsAny("zzabyycdxx", "\tx") = true
1099 * StringUtils.containsAny("zzabyycdxx", "$.#yF") = true
1100 * StringUtils.containsAny("aba", "z") = false
1101 * </pre>
1102 *
1103 * @param cs
1104 * the CharSequence to check, may be null
1105 * @param searchChars
1106 * the chars to search for, may be null
1107 * @return the {@code true} if any of the chars are found, {@code false} if no match or null input
1108 * @since 2.4
1109 * @since 3.0 Changed signature from containsAny(String, String) to containsAny(CharSequence, CharSequence)
1110 */
1111 public static boolean containsAny(final CharSequence cs, final CharSequence searchChars) {
1112 if (searchChars == null) {
1113 return false;
1114 }
1115 return containsAny(cs, CharSequenceUtils.toCharArray(searchChars));
1116 }
1117
1118 /**
1119 * Checks if the CharSequence contains any of the CharSequences in the given array.
1120 *
1121 * <p>
1122 * A {@code null} {@code cs} CharSequence will return {@code false}. A {@code null} or zero length search array will
1123 * return {@code false}.
1124 * </p>
1125 *
1126 * <pre>
1127 * StringUtils.containsAny(null, *) = false
1128 * StringUtils.containsAny("", *) = false
1129 * StringUtils.containsAny(*, null) = false
1130 * StringUtils.containsAny(*, []) = false
1131 * StringUtils.containsAny("abcd", "ab", null) = true
1132 * StringUtils.containsAny("abcd", "ab", "cd") = true
1133 * StringUtils.containsAny("abc", "d", "abc") = true
1134 * </pre>
1135 *
1136 * @param cs The CharSequence to check, may be null
1137 * @param searchCharSequences The array of CharSequences to search for, may be null. Individual CharSequences may be
1138 * null as well.
1139 * @return {@code true} if any of the search CharSequences are found, {@code false} otherwise
1140 * @since 3.4
1141 */
1142 public static boolean containsAny(final CharSequence cs, final CharSequence... searchCharSequences) {
1143 return containsAny(StringUtils::contains, cs, searchCharSequences);
1144 }
1145
1146 /**
1147 * Checks if the CharSequence contains any of the CharSequences in the given array.
1148 *
1149 * <p>
1150 * A {@code null} {@code cs} CharSequence will return {@code false}. A {@code null} or zero length search array will
1151 * return {@code false}.
1152 * </p>
1153 *
1154 * @param cs The CharSequence to check, may be null
1155 * @param searchCharSequences The array of CharSequences to search for, may be null. Individual CharSequences may be
1156 * null as well.
1157 * @return {@code true} if any of the search CharSequences are found, {@code false} otherwise
1158 * @since 3.12.0
1159 */
1160 private static boolean containsAny(final ToBooleanBiFunction<CharSequence, CharSequence> test,
1161 final CharSequence cs, final CharSequence... searchCharSequences) {
1162 if (isEmpty(cs) || ArrayUtils.isEmpty(searchCharSequences)) {
1163 return false;
1164 }
1165 for (final CharSequence searchCharSequence : searchCharSequences) {
1166 if (test.applyAsBoolean(cs, searchCharSequence)) {
1167 return true;
1168 }
1169 }
1170 return false;
1171 }
1172
1173 /**
1174 * Checks if the CharSequence contains any of the CharSequences in the given array, ignoring case.
1175 *
1176 * <p>
1177 * A {@code null} {@code cs} CharSequence will return {@code false}. A {@code null} or zero length search array will
1178 * return {@code false}.
1179 * </p>
1180 *
1181 * <pre>
1182 * StringUtils.containsAny(null, *) = false
1183 * StringUtils.containsAny("", *) = false
1184 * StringUtils.containsAny(*, null) = false
1185 * StringUtils.containsAny(*, []) = false
1186 * StringUtils.containsAny("abcd", "ab", null) = true
1187 * StringUtils.containsAny("abcd", "ab", "cd") = true
1188 * StringUtils.containsAny("abc", "d", "abc") = true
1189 * StringUtils.containsAny("abc", "D", "ABC") = true
1190 * StringUtils.containsAny("ABC", "d", "abc") = true
1191 * </pre>
1192 *
1193 * @param cs The CharSequence to check, may be null
1194 * @param searchCharSequences The array of CharSequences to search for, may be null. Individual CharSequences may be
1195 * null as well.
1196 * @return {@code true} if any of the search CharSequences are found, {@code false} otherwise
1197 * @since 3.12.0
1198 */
1199 public static boolean containsAnyIgnoreCase(final CharSequence cs, final CharSequence... searchCharSequences) {
1200 return containsAny(StringUtils::containsIgnoreCase, cs, searchCharSequences);
1201 }
1202
1203 /**
1204 * Checks if CharSequence contains a search CharSequence irrespective of case,
1205 * handling {@code null}. Case-insensitivity is defined as by
1206 * {@link String#equalsIgnoreCase(String)}.
1207 *
1208 * <p>A {@code null} CharSequence will return {@code false}.
1209 *
1210 * <pre>
1211 * StringUtils.containsIgnoreCase(null, *) = false
1212 * StringUtils.containsIgnoreCase(*, null) = false
1213 * StringUtils.containsIgnoreCase("", "") = true
1214 * StringUtils.containsIgnoreCase("abc", "") = true
1215 * StringUtils.containsIgnoreCase("abc", "a") = true
1216 * StringUtils.containsIgnoreCase("abc", "z") = false
1217 * StringUtils.containsIgnoreCase("abc", "A") = true
1218 * StringUtils.containsIgnoreCase("abc", "Z") = false
1219 * </pre>
1220 *
1221 * @param str the CharSequence to check, may be null
1222 * @param searchStr the CharSequence to find, may be null
1223 * @return true if the CharSequence contains the search CharSequence irrespective of
1224 * case or false if not or {@code null} string input
1225 * @since 3.0 Changed signature from containsIgnoreCase(String, String) to containsIgnoreCase(CharSequence, CharSequence)
1226 */
1227 public static boolean containsIgnoreCase(final CharSequence str, final CharSequence searchStr) {
1228 if (str == null || searchStr == null) {
1229 return false;
1230 }
1231 final int len = searchStr.length();
1232 final int max = str.length() - len;
1233 for (int i = 0; i <= max; i++) {
1234 if (CharSequenceUtils.regionMatches(str, true, i, searchStr, 0, len)) {
1235 return true;
1236 }
1237 }
1238 return false;
1239 }
1240
1241 /**
1242 * Checks that the CharSequence does not contain certain characters.
1243 *
1244 * <p>A {@code null} CharSequence will return {@code true}.
1245 * A {@code null} invalid character array will return {@code true}.
1246 * An empty CharSequence (length()=0) always returns true.</p>
1247 *
1248 * <pre>
1249 * StringUtils.containsNone(null, *) = true
1250 * StringUtils.containsNone(*, null) = true
1251 * StringUtils.containsNone("", *) = true
1252 * StringUtils.containsNone("ab", '') = true
1253 * StringUtils.containsNone("abab", 'xyz') = true
1254 * StringUtils.containsNone("ab1", 'xyz') = true
1255 * StringUtils.containsNone("abz", 'xyz') = false
1256 * </pre>
1257 *
1258 * @param cs the CharSequence to check, may be null
1259 * @param searchChars an array of invalid chars, may be null
1260 * @return true if it contains none of the invalid chars, or is null
1261 * @since 2.0
1262 * @since 3.0 Changed signature from containsNone(String, char[]) to containsNone(CharSequence, char...)
1263 */
1264 public static boolean containsNone(final CharSequence cs, final char... searchChars) {
1265 if (cs == null || searchChars == null) {
1266 return true;
1267 }
1268 final int csLen = cs.length();
1269 final int csLast = csLen - 1;
1270 final int searchLen = searchChars.length;
1271 final int searchLast = searchLen - 1;
1272 for (int i = 0; i < csLen; i++) {
1273 final char ch = cs.charAt(i);
1274 for (int j = 0; j < searchLen; j++) {
1275 if (searchChars[j] == ch) {
1276 if (!Character.isHighSurrogate(ch)) {
1277 // ch is in the Basic Multilingual Plane
1278 return false;
1279 }
1280 if (j == searchLast) {
1281 // missing low surrogate, fine, like String.indexOf(String)
1282 return false;
1283 }
1284 if (i < csLast && searchChars[j + 1] == cs.charAt(i + 1)) {
1285 return false;
1286 }
1287 }
1288 }
1289 }
1290 return true;
1291 }
1292
1293 /**
1294 * Checks that the CharSequence does not contain certain characters.
1295 *
1296 * <p>A {@code null} CharSequence will return {@code true}.
1297 * A {@code null} invalid character array will return {@code true}.
1298 * An empty String ("") always returns true.</p>
1299 *
1300 * <pre>
1301 * StringUtils.containsNone(null, *) = true
1302 * StringUtils.containsNone(*, null) = true
1303 * StringUtils.containsNone("", *) = true
1304 * StringUtils.containsNone("ab", "") = true
1305 * StringUtils.containsNone("abab", "xyz") = true
1306 * StringUtils.containsNone("ab1", "xyz") = true
1307 * StringUtils.containsNone("abz", "xyz") = false
1308 * </pre>
1309 *
1310 * @param cs the CharSequence to check, may be null
1311 * @param invalidChars a String of invalid chars, may be null
1312 * @return true if it contains none of the invalid chars, or is null
1313 * @since 2.0
1314 * @since 3.0 Changed signature from containsNone(String, String) to containsNone(CharSequence, String)
1315 */
1316 public static boolean containsNone(final CharSequence cs, final String invalidChars) {
1317 if (invalidChars == null) {
1318 return true;
1319 }
1320 return containsNone(cs, invalidChars.toCharArray());
1321 }
1322
1323 /**
1324 * Checks if the CharSequence contains only certain characters.
1325 *
1326 * <p>A {@code null} CharSequence will return {@code false}.
1327 * A {@code null} valid character array will return {@code false}.
1328 * An empty CharSequence (length()=0) always returns {@code true}.</p>
1329 *
1330 * <pre>
1331 * StringUtils.containsOnly(null, *) = false
1332 * StringUtils.containsOnly(*, null) = false
1333 * StringUtils.containsOnly("", *) = true
1334 * StringUtils.containsOnly("ab", '') = false
1335 * StringUtils.containsOnly("abab", 'abc') = true
1336 * StringUtils.containsOnly("ab1", 'abc') = false
1337 * StringUtils.containsOnly("abz", 'abc') = false
1338 * </pre>
1339 *
1340 * @param cs the String to check, may be null
1341 * @param valid an array of valid chars, may be null
1342 * @return true if it only contains valid chars and is non-null
1343 * @since 3.0 Changed signature from containsOnly(String, char[]) to containsOnly(CharSequence, char...)
1344 */
1345 public static boolean containsOnly(final CharSequence cs, final char... valid) {
1346 // All these pre-checks are to maintain API with an older version
1347 if (valid == null || cs == null) {
1348 return false;
1349 }
1350 if (cs.length() == 0) {
1351 return true;
1352 }
1353 if (valid.length == 0) {
1354 return false;
1355 }
1356 return indexOfAnyBut(cs, valid) == INDEX_NOT_FOUND;
1357 }
1358
1359 /**
1360 * Checks if the CharSequence contains only certain characters.
1361 *
1362 * <p>A {@code null} CharSequence will return {@code false}.
1363 * A {@code null} valid character String will return {@code false}.
1364 * An empty String (length()=0) always returns {@code true}.</p>
1365 *
1366 * <pre>
1367 * StringUtils.containsOnly(null, *) = false
1368 * StringUtils.containsOnly(*, null) = false
1369 * StringUtils.containsOnly("", *) = true
1370 * StringUtils.containsOnly("ab", "") = false
1371 * StringUtils.containsOnly("abab", "abc") = true
1372 * StringUtils.containsOnly("ab1", "abc") = false
1373 * StringUtils.containsOnly("abz", "abc") = false
1374 * </pre>
1375 *
1376 * @param cs the CharSequence to check, may be null
1377 * @param validChars a String of valid chars, may be null
1378 * @return true if it only contains valid chars and is non-null
1379 * @since 2.0
1380 * @since 3.0 Changed signature from containsOnly(String, String) to containsOnly(CharSequence, String)
1381 */
1382 public static boolean containsOnly(final CharSequence cs, final String validChars) {
1383 if (cs == null || validChars == null) {
1384 return false;
1385 }
1386 return containsOnly(cs, validChars.toCharArray());
1387 }
1388
1389 /**
1390 * Check whether the given CharSequence contains any whitespace characters.
1391 *
1392 * <p>Whitespace is defined by {@link Character#isWhitespace(char)}.</p>
1393 *
1394 * @param seq the CharSequence to check (may be {@code null})
1395 * @return {@code true} if the CharSequence is not empty and
1396 * contains at least 1 (breaking) whitespace character
1397 * @since 3.0
1398 */
1399 // From org.springframework.util.StringUtils, under Apache License 2.0
1400 public static boolean containsWhitespace(final CharSequence seq) {
1401 if (isEmpty(seq)) {
1402 return false;
1403 }
1404 final int strLen = seq.length();
1405 for (int i = 0; i < strLen; i++) {
1406 if (Character.isWhitespace(seq.charAt(i))) {
1407 return true;
1408 }
1409 }
1410 return false;
1411 }
1412
1413 private static void convertRemainingAccentCharacters(final StringBuilder decomposed) {
1414 for (int i = 0; i < decomposed.length(); i++) {
1415 if (decomposed.charAt(i) == '\u0141') {
1416 decomposed.setCharAt(i, 'L');
1417 } else if (decomposed.charAt(i) == '\u0142') {
1418 decomposed.setCharAt(i, 'l');
1419 }
1420 }
1421 }
1422
1423 /**
1424 * Counts how many times the char appears in the given string.
1425 *
1426 * <p>A {@code null} or empty ("") String input returns {@code 0}.</p>
1427 *
1428 * <pre>
1429 * StringUtils.countMatches(null, *) = 0
1430 * StringUtils.countMatches("", *) = 0
1431 * StringUtils.countMatches("abba", 0) = 0
1432 * StringUtils.countMatches("abba", 'a') = 2
1433 * StringUtils.countMatches("abba", 'b') = 2
1434 * StringUtils.countMatches("abba", 'x') = 0
1435 * </pre>
1436 *
1437 * @param str the CharSequence to check, may be null
1438 * @param ch the char to count
1439 * @return the number of occurrences, 0 if the CharSequence is {@code null}
1440 * @since 3.4
1441 */
1442 public static int countMatches(final CharSequence str, final char ch) {
1443 if (isEmpty(str)) {
1444 return 0;
1445 }
1446 int count = 0;
1447 // We could also call str.toCharArray() for faster lookups but that would generate more garbage.
1448 for (int i = 0; i < str.length(); i++) {
1449 if (ch == str.charAt(i)) {
1450 count++;
1451 }
1452 }
1453 return count;
1454 }
1455
1456 /**
1457 * Counts how many times the substring appears in the larger string.
1458 * Note that the code only counts non-overlapping matches.
1459 *
1460 * <p>A {@code null} or empty ("") String input returns {@code 0}.</p>
1461 *
1462 * <pre>
1463 * StringUtils.countMatches(null, *) = 0
1464 * StringUtils.countMatches("", *) = 0
1465 * StringUtils.countMatches("abba", null) = 0
1466 * StringUtils.countMatches("abba", "") = 0
1467 * StringUtils.countMatches("abba", "a") = 2
1468 * StringUtils.countMatches("abba", "ab") = 1
1469 * StringUtils.countMatches("abba", "xxx") = 0
1470 * StringUtils.countMatches("ababa", "aba") = 1
1471 * </pre>
1472 *
1473 * @param str the CharSequence to check, may be null
1474 * @param sub the substring to count, may be null
1475 * @return the number of occurrences, 0 if either CharSequence is {@code null}
1476 * @since 3.0 Changed signature from countMatches(String, String) to countMatches(CharSequence, CharSequence)
1477 */
1478 public static int countMatches(final CharSequence str, final CharSequence sub) {
1479 if (isEmpty(str) || isEmpty(sub)) {
1480 return 0;
1481 }
1482 int count = 0;
1483 int idx = 0;
1484 while ((idx = CharSequenceUtils.indexOf(str, sub, idx)) != INDEX_NOT_FOUND) {
1485 count++;
1486 idx += sub.length();
1487 }
1488 return count;
1489 }
1490
1491 /**
1492 * Returns either the passed in CharSequence, or if the CharSequence is
1493 * whitespace, empty ("") or {@code null}, the value of {@code defaultStr}.
1494 *
1495 * <p>Whitespace is defined by {@link Character#isWhitespace(char)}.</p>
1496 *
1497 * <pre>
1498 * StringUtils.defaultIfBlank(null, "NULL") = "NULL"
1499 * StringUtils.defaultIfBlank("", "NULL") = "NULL"
1500 * StringUtils.defaultIfBlank(" ", "NULL") = "NULL"
1501 * StringUtils.defaultIfBlank("bat", "NULL") = "bat"
1502 * StringUtils.defaultIfBlank("", null) = null
1503 * </pre>
1504 * @param <T> the specific kind of CharSequence
1505 * @param str the CharSequence to check, may be null
1506 * @param defaultStr the default CharSequence to return
1507 * if the input is whitespace, empty ("") or {@code null}, may be null
1508 * @return the passed in CharSequence, or the default
1509 * @see StringUtils#defaultString(String, String)
1510 */
1511 public static <T extends CharSequence> T defaultIfBlank(final T str, final T defaultStr) {
1512 return isBlank(str) ? defaultStr : str;
1513 }
1514
1515 /**
1516 * Returns either the passed in CharSequence, or if the CharSequence is
1517 * empty or {@code null}, the value of {@code defaultStr}.
1518 *
1519 * <pre>
1520 * StringUtils.defaultIfEmpty(null, "NULL") = "NULL"
1521 * StringUtils.defaultIfEmpty("", "NULL") = "NULL"
1522 * StringUtils.defaultIfEmpty(" ", "NULL") = " "
1523 * StringUtils.defaultIfEmpty("bat", "NULL") = "bat"
1524 * StringUtils.defaultIfEmpty("", null) = null
1525 * </pre>
1526 * @param <T> the specific kind of CharSequence
1527 * @param str the CharSequence to check, may be null
1528 * @param defaultStr the default CharSequence to return
1529 * if the input is empty ("") or {@code null}, may be null
1530 * @return the passed in CharSequence, or the default
1531 * @see StringUtils#defaultString(String, String)
1532 */
1533 public static <T extends CharSequence> T defaultIfEmpty(final T str, final T defaultStr) {
1534 return isEmpty(str) ? defaultStr : str;
1535 }
1536
1537 /**
1538 * Returns either the passed in String,
1539 * or if the String is {@code null}, an empty String ("").
1540 *
1541 * <pre>
1542 * StringUtils.defaultString(null) = ""
1543 * StringUtils.defaultString("") = ""
1544 * StringUtils.defaultString("bat") = "bat"
1545 * </pre>
1546 *
1547 * @see Objects#toString(Object, String)
1548 * @see String#valueOf(Object)
1549 * @param str the String to check, may be null
1550 * @return the passed in String, or the empty String if it
1551 * was {@code null}
1552 */
1553 public static String defaultString(final String str) {
1554 return Objects.toString(str, EMPTY);
1555 }
1556
1557 /**
1558 * Returns either the given String, or if the String is
1559 * {@code null}, {@code nullDefault}.
1560 *
1561 * <pre>
1562 * StringUtils.defaultString(null, "NULL") = "NULL"
1563 * StringUtils.defaultString("", "NULL") = ""
1564 * StringUtils.defaultString("bat", "NULL") = "bat"
1565 * </pre>
1566 *
1567 * @see Objects#toString(Object, String)
1568 * @see String#valueOf(Object)
1569 * @param str the String to check, may be null
1570 * @param nullDefault the default String to return
1571 * if the input is {@code null}, may be null
1572 * @return the passed in String, or the default if it was {@code null}
1573 * @deprecated Use {@link Objects#toString(Object, String)}
1574 */
1575 @Deprecated
1576 public static String defaultString(final String str, final String nullDefault) {
1577 return Objects.toString(str, nullDefault);
1578 }
1579
1580 /**
1581 * Deletes all whitespaces from a String as defined by
1582 * {@link Character#isWhitespace(char)}.
1583 *
1584 * <pre>
1585 * StringUtils.deleteWhitespace(null) = null
1586 * StringUtils.deleteWhitespace("") = ""
1587 * StringUtils.deleteWhitespace("abc") = "abc"
1588 * StringUtils.deleteWhitespace(" ab c ") = "abc"
1589 * </pre>
1590 *
1591 * @param str the String to delete whitespace from, may be null
1592 * @return the String without whitespaces, {@code null} if null String input
1593 */
1594 public static String deleteWhitespace(final String str) {
1595 if (isEmpty(str)) {
1596 return str;
1597 }
1598 final int sz = str.length();
1599 final char[] chs = new char[sz];
1600 int count = 0;
1601 for (int i = 0; i < sz; i++) {
1602 if (!Character.isWhitespace(str.charAt(i))) {
1603 chs[count++] = str.charAt(i);
1604 }
1605 }
1606 if (count == sz) {
1607 return str;
1608 }
1609 if (count == 0) {
1610 return EMPTY;
1611 }
1612 return new String(chs, 0, count);
1613 }
1614
1615 /**
1616 * Compares two Strings, and returns the portion where they differ.
1617 * More precisely, return the remainder of the second String,
1618 * starting from where it's different from the first. This means that
1619 * the difference between "abc" and "ab" is the empty String and not "c".
1620 *
1621 * <p>For example,
1622 * {@code difference("i am a machine", "i am a robot") -> "robot"}.</p>
1623 *
1624 * <pre>
1625 * StringUtils.difference(null, null) = null
1626 * StringUtils.difference("", "") = ""
1627 * StringUtils.difference("", "abc") = "abc"
1628 * StringUtils.difference("abc", "") = ""
1629 * StringUtils.difference("abc", "abc") = ""
1630 * StringUtils.difference("abc", "ab") = ""
1631 * StringUtils.difference("ab", "abxyz") = "xyz"
1632 * StringUtils.difference("abcde", "abxyz") = "xyz"
1633 * StringUtils.difference("abcde", "xyz") = "xyz"
1634 * </pre>
1635 *
1636 * @param str1 the first String, may be null
1637 * @param str2 the second String, may be null
1638 * @return the portion of str2 where it differs from str1; returns the
1639 * empty String if they are equal
1640 * @see #indexOfDifference(CharSequence,CharSequence)
1641 * @since 2.0
1642 */
1643 public static String difference(final String str1, final String str2) {
1644 if (str1 == null) {
1645 return str2;
1646 }
1647 if (str2 == null) {
1648 return str1;
1649 }
1650 final int at = indexOfDifference(str1, str2);
1651 if (at == INDEX_NOT_FOUND) {
1652 return EMPTY;
1653 }
1654 return str2.substring(at);
1655 }
1656
1657 /**
1658 * Check if a CharSequence ends with a specified suffix.
1659 *
1660 * <p>{@code null}s are handled without exceptions. Two {@code null}
1661 * references are considered to be equal. The comparison is case-sensitive.</p>
1662 *
1663 * <pre>
1664 * StringUtils.endsWith(null, null) = true
1665 * StringUtils.endsWith(null, "def") = false
1666 * StringUtils.endsWith("abcdef", null) = false
1667 * StringUtils.endsWith("abcdef", "def") = true
1668 * StringUtils.endsWith("ABCDEF", "def") = false
1669 * StringUtils.endsWith("ABCDEF", "cde") = false
1670 * StringUtils.endsWith("ABCDEF", "") = true
1671 * </pre>
1672 *
1673 * @see String#endsWith(String)
1674 * @param str the CharSequence to check, may be null
1675 * @param suffix the suffix to find, may be null
1676 * @return {@code true} if the CharSequence ends with the suffix, case-sensitive, or
1677 * both {@code null}
1678 * @since 2.4
1679 * @since 3.0 Changed signature from endsWith(String, String) to endsWith(CharSequence, CharSequence)
1680 */
1681 public static boolean endsWith(final CharSequence str, final CharSequence suffix) {
1682 return endsWith(str, suffix, false);
1683 }
1684
1685 /**
1686 * Check if a CharSequence ends with a specified suffix (optionally case insensitive).
1687 *
1688 * @see String#endsWith(String)
1689 * @param str the CharSequence to check, may be null
1690 * @param suffix the suffix to find, may be null
1691 * @param ignoreCase indicates whether the compare should ignore case
1692 * (case-insensitive) or not.
1693 * @return {@code true} if the CharSequence starts with the prefix or
1694 * both {@code null}
1695 */
1696 private static boolean endsWith(final CharSequence str, final CharSequence suffix, final boolean ignoreCase) {
1697 if (str == null || suffix == null) {
1698 return str == suffix;
1699 }
1700 if (suffix.length() > str.length()) {
1701 return false;
1702 }
1703 final int strOffset = str.length() - suffix.length();
1704 return CharSequenceUtils.regionMatches(str, ignoreCase, strOffset, suffix, 0, suffix.length());
1705 }
1706
1707 /**
1708 * Check if a CharSequence ends with any of the provided case-sensitive suffixes.
1709 *
1710 * <pre>
1711 * StringUtils.endsWithAny(null, null) = false
1712 * StringUtils.endsWithAny(null, new String[] {"abc"}) = false
1713 * StringUtils.endsWithAny("abcxyz", null) = false
1714 * StringUtils.endsWithAny("abcxyz", new String[] {""}) = true
1715 * StringUtils.endsWithAny("abcxyz", new String[] {"xyz"}) = true
1716 * StringUtils.endsWithAny("abcxyz", new String[] {null, "xyz", "abc"}) = true
1717 * StringUtils.endsWithAny("abcXYZ", "def", "XYZ") = true
1718 * StringUtils.endsWithAny("abcXYZ", "def", "xyz") = false
1719 * </pre>
1720 *
1721 * @param sequence the CharSequence to check, may be null
1722 * @param searchStrings the case-sensitive CharSequences to find, may be empty or contain {@code null}
1723 * @see StringUtils#endsWith(CharSequence, CharSequence)
1724 * @return {@code true} if the input {@code sequence} is {@code null} AND no {@code searchStrings} are provided, or
1725 * the input {@code sequence} ends in any of the provided case-sensitive {@code searchStrings}.
1726 * @since 3.0
1727 */
1728 public static boolean endsWithAny(final CharSequence sequence, final CharSequence... searchStrings) {
1729 if (isEmpty(sequence) || ArrayUtils.isEmpty(searchStrings)) {
1730 return false;
1731 }
1732 for (final CharSequence searchString : searchStrings) {
1733 if (endsWith(sequence, searchString)) {
1734 return true;
1735 }
1736 }
1737 return false;
1738 }
1739
1740 /**
1741 * Case insensitive check if a CharSequence ends with a specified suffix.
1742 *
1743 * <p>{@code null}s are handled without exceptions. Two {@code null}
1744 * references are considered to be equal. The comparison is case insensitive.</p>
1745 *
1746 * <pre>
1747 * StringUtils.endsWithIgnoreCase(null, null) = true
1748 * StringUtils.endsWithIgnoreCase(null, "def") = false
1749 * StringUtils.endsWithIgnoreCase("abcdef", null) = false
1750 * StringUtils.endsWithIgnoreCase("abcdef", "def") = true
1751 * StringUtils.endsWithIgnoreCase("ABCDEF", "def") = true
1752 * StringUtils.endsWithIgnoreCase("ABCDEF", "cde") = false
1753 * </pre>
1754 *
1755 * @see String#endsWith(String)
1756 * @param str the CharSequence to check, may be null
1757 * @param suffix the suffix to find, may be null
1758 * @return {@code true} if the CharSequence ends with the suffix, case-insensitive, or
1759 * both {@code null}
1760 * @since 2.4
1761 * @since 3.0 Changed signature from endsWithIgnoreCase(String, String) to endsWithIgnoreCase(CharSequence, CharSequence)
1762 */
1763 public static boolean endsWithIgnoreCase(final CharSequence str, final CharSequence suffix) {
1764 return endsWith(str, suffix, true);
1765 }
1766
1767 /**
1768 * Compares two CharSequences, returning {@code true} if they represent
1769 * equal sequences of characters.
1770 *
1771 * <p>{@code null}s are handled without exceptions. Two {@code null}
1772 * references are considered to be equal. The comparison is <strong>case-sensitive</strong>.</p>
1773 *
1774 * <pre>
1775 * StringUtils.equals(null, null) = true
1776 * StringUtils.equals(null, "abc") = false
1777 * StringUtils.equals("abc", null) = false
1778 * StringUtils.equals("abc", "abc") = true
1779 * StringUtils.equals("abc", "ABC") = false
1780 * </pre>
1781 *
1782 * @param cs1 the first CharSequence, may be {@code null}
1783 * @param cs2 the second CharSequence, may be {@code null}
1784 * @return {@code true} if the CharSequences are equal (case-sensitive), or both {@code null}
1785 * @since 3.0 Changed signature from equals(String, String) to equals(CharSequence, CharSequence)
1786 * @see Object#equals(Object)
1787 * @see #equalsIgnoreCase(CharSequence, CharSequence)
1788 */
1789 public static boolean equals(final CharSequence cs1, final CharSequence cs2) {
1790 if (cs1 == cs2) {
1791 return true;
1792 }
1793 if (cs1 == null || cs2 == null) {
1794 return false;
1795 }
1796 if (cs1.length() != cs2.length()) {
1797 return false;
1798 }
1799 if (cs1 instanceof String && cs2 instanceof String) {
1800 return cs1.equals(cs2);
1801 }
1802 // Step-wise comparison
1803 final int length = cs1.length();
1804 for (int i = 0; i < length; i++) {
1805 if (cs1.charAt(i) != cs2.charAt(i)) {
1806 return false;
1807 }
1808 }
1809 return true;
1810 }
1811
1812 /**
1813 * Compares given {@code string} to a CharSequences vararg of {@code searchStrings},
1814 * returning {@code true} if the {@code string} is equal to any of the {@code searchStrings}.
1815 *
1816 * <pre>
1817 * StringUtils.equalsAny(null, (CharSequence[]) null) = false
1818 * StringUtils.equalsAny(null, null, null) = true
1819 * StringUtils.equalsAny(null, "abc", "def") = false
1820 * StringUtils.equalsAny("abc", null, "def") = false
1821 * StringUtils.equalsAny("abc", "abc", "def") = true
1822 * StringUtils.equalsAny("abc", "ABC", "DEF") = false
1823 * </pre>
1824 *
1825 * @param string to compare, may be {@code null}.
1826 * @param searchStrings a vararg of strings, may be {@code null}.
1827 * @return {@code true} if the string is equal (case-sensitive) to any other element of {@code searchStrings};
1828 * {@code false} if {@code searchStrings} is null or contains no matches.
1829 * @since 3.5
1830 */
1831 public static boolean equalsAny(final CharSequence string, final CharSequence... searchStrings) {
1832 if (ArrayUtils.isNotEmpty(searchStrings)) {
1833 for (final CharSequence next : searchStrings) {
1834 if (equals(string, next)) {
1835 return true;
1836 }
1837 }
1838 }
1839 return false;
1840 }
1841
1842 /**
1843 * Compares given {@code string} to a CharSequences vararg of {@code searchStrings},
1844 * returning {@code true} if the {@code string} is equal to any of the {@code searchStrings}, ignoring case.
1845 *
1846 * <pre>
1847 * StringUtils.equalsAnyIgnoreCase(null, (CharSequence[]) null) = false
1848 * StringUtils.equalsAnyIgnoreCase(null, null, null) = true
1849 * StringUtils.equalsAnyIgnoreCase(null, "abc", "def") = false
1850 * StringUtils.equalsAnyIgnoreCase("abc", null, "def") = false
1851 * StringUtils.equalsAnyIgnoreCase("abc", "abc", "def") = true
1852 * StringUtils.equalsAnyIgnoreCase("abc", "ABC", "DEF") = true
1853 * </pre>
1854 *
1855 * @param string to compare, may be {@code null}.
1856 * @param searchStrings a vararg of strings, may be {@code null}.
1857 * @return {@code true} if the string is equal (case-insensitive) to any other element of {@code searchStrings};
1858 * {@code false} if {@code searchStrings} is null or contains no matches.
1859 * @since 3.5
1860 */
1861 public static boolean equalsAnyIgnoreCase(final CharSequence string, final CharSequence...searchStrings) {
1862 if (ArrayUtils.isNotEmpty(searchStrings)) {
1863 for (final CharSequence next : searchStrings) {
1864 if (equalsIgnoreCase(string, next)) {
1865 return true;
1866 }
1867 }
1868 }
1869 return false;
1870 }
1871
1872 /**
1873 * Compares two CharSequences, returning {@code true} if they represent
1874 * equal sequences of characters, ignoring case.
1875 *
1876 * <p>{@code null}s are handled without exceptions. Two {@code null}
1877 * references are considered equal. The comparison is <strong>case insensitive</strong>.</p>
1878 *
1879 * <pre>
1880 * StringUtils.equalsIgnoreCase(null, null) = true
1881 * StringUtils.equalsIgnoreCase(null, "abc") = false
1882 * StringUtils.equalsIgnoreCase("abc", null) = false
1883 * StringUtils.equalsIgnoreCase("abc", "abc") = true
1884 * StringUtils.equalsIgnoreCase("abc", "ABC") = true
1885 * </pre>
1886 *
1887 * @param cs1 the first CharSequence, may be {@code null}
1888 * @param cs2 the second CharSequence, may be {@code null}
1889 * @return {@code true} if the CharSequences are equal (case-insensitive), or both {@code null}
1890 * @since 3.0 Changed signature from equalsIgnoreCase(String, String) to equalsIgnoreCase(CharSequence, CharSequence)
1891 * @see #equals(CharSequence, CharSequence)
1892 */
1893 public static boolean equalsIgnoreCase(final CharSequence cs1, final CharSequence cs2) {
1894 if (cs1 == cs2) {
1895 return true;
1896 }
1897 if (cs1 == null || cs2 == null) {
1898 return false;
1899 }
1900 if (cs1.length() != cs2.length()) {
1901 return false;
1902 }
1903 return CharSequenceUtils.regionMatches(cs1, true, 0, cs2, 0, cs1.length());
1904 }
1905
1906 /**
1907 * Returns the first value in the array which is not empty (""),
1908 * {@code null} or whitespace only.
1909 *
1910 * <p>Whitespace is defined by {@link Character#isWhitespace(char)}.</p>
1911 *
1912 * <p>If all values are blank or the array is {@code null}
1913 * or empty then {@code null} is returned.</p>
1914 *
1915 * <pre>
1916 * StringUtils.firstNonBlank(null, null, null) = null
1917 * StringUtils.firstNonBlank(null, "", " ") = null
1918 * StringUtils.firstNonBlank("abc") = "abc"
1919 * StringUtils.firstNonBlank(null, "xyz") = "xyz"
1920 * StringUtils.firstNonBlank(null, "", " ", "xyz") = "xyz"
1921 * StringUtils.firstNonBlank(null, "xyz", "abc") = "xyz"
1922 * StringUtils.firstNonBlank() = null
1923 * </pre>
1924 *
1925 * @param <T> the specific kind of CharSequence
1926 * @param values the values to test, may be {@code null} or empty
1927 * @return the first value from {@code values} which is not blank,
1928 * or {@code null} if there are no non-blank values
1929 * @since 3.8
1930 */
1931 @SafeVarargs
1932 public static <T extends CharSequence> T firstNonBlank(final T... values) {
1933 if (values != null) {
1934 for (final T val : values) {
1935 if (isNotBlank(val)) {
1936 return val;
1937 }
1938 }
1939 }
1940 return null;
1941 }
1942
1943 /**
1944 * Returns the first value in the array which is not empty.
1945 *
1946 * <p>If all values are empty or the array is {@code null}
1947 * or empty then {@code null} is returned.</p>
1948 *
1949 * <pre>
1950 * StringUtils.firstNonEmpty(null, null, null) = null
1951 * StringUtils.firstNonEmpty(null, null, "") = null
1952 * StringUtils.firstNonEmpty(null, "", " ") = " "
1953 * StringUtils.firstNonEmpty("abc") = "abc"
1954 * StringUtils.firstNonEmpty(null, "xyz") = "xyz"
1955 * StringUtils.firstNonEmpty("", "xyz") = "xyz"
1956 * StringUtils.firstNonEmpty(null, "xyz", "abc") = "xyz"
1957 * StringUtils.firstNonEmpty() = null
1958 * </pre>
1959 *
1960 * @param <T> the specific kind of CharSequence
1961 * @param values the values to test, may be {@code null} or empty
1962 * @return the first value from {@code values} which is not empty,
1963 * or {@code null} if there are no non-empty values
1964 * @since 3.8
1965 */
1966 @SafeVarargs
1967 public static <T extends CharSequence> T firstNonEmpty(final T... values) {
1968 if (values != null) {
1969 for (final T val : values) {
1970 if (isNotEmpty(val)) {
1971 return val;
1972 }
1973 }
1974 }
1975 return null;
1976 }
1977
1978 /**
1979 * Calls {@link String#getBytes(Charset)} in a null-safe manner.
1980 *
1981 * @param string input string
1982 * @param charset The {@link Charset} to encode the {@link String}. If null, then use the default Charset.
1983 * @return The empty byte[] if {@code string} is null, the result of {@link String#getBytes(Charset)} otherwise.
1984 * @see String#getBytes(Charset)
1985 * @since 3.10
1986 */
1987 public static byte[] getBytes(final String string, final Charset charset) {
1988 return string == null ? ArrayUtils.EMPTY_BYTE_ARRAY : string.getBytes(Charsets.toCharset(charset));
1989 }
1990
1991 /**
1992 * Calls {@link String#getBytes(String)} in a null-safe manner.
1993 *
1994 * @param string input string
1995 * @param charset The {@link Charset} name to encode the {@link String}. If null, then use the default Charset.
1996 * @return The empty byte[] if {@code string} is null, the result of {@link String#getBytes(String)} otherwise.
1997 * @throws UnsupportedEncodingException Thrown when the named charset is not supported.
1998 * @see String#getBytes(String)
1999 * @since 3.10
2000 */
2001 public static byte[] getBytes(final String string, final String charset) throws UnsupportedEncodingException {
2002 return string == null ? ArrayUtils.EMPTY_BYTE_ARRAY : string.getBytes(Charsets.toCharsetName(charset));
2003 }
2004
2005 /**
2006 * Compares all Strings in an array and returns the initial sequence of
2007 * characters that is common to all of them.
2008 *
2009 * <p>For example,
2010 * {@code getCommonPrefix(new String[] {"i am a machine", "i am a robot"}) -> "i am a "}</p>
2011 *
2012 * <pre>
2013 * StringUtils.getCommonPrefix(null) = ""
2014 * StringUtils.getCommonPrefix(new String[] {}) = ""
2015 * StringUtils.getCommonPrefix(new String[] {"abc"}) = "abc"
2016 * StringUtils.getCommonPrefix(new String[] {null, null}) = ""
2017 * StringUtils.getCommonPrefix(new String[] {"", ""}) = ""
2018 * StringUtils.getCommonPrefix(new String[] {"", null}) = ""
2019 * StringUtils.getCommonPrefix(new String[] {"abc", null, null}) = ""
2020 * StringUtils.getCommonPrefix(new String[] {null, null, "abc"}) = ""
2021 * StringUtils.getCommonPrefix(new String[] {"", "abc"}) = ""
2022 * StringUtils.getCommonPrefix(new String[] {"abc", ""}) = ""
2023 * StringUtils.getCommonPrefix(new String[] {"abc", "abc"}) = "abc"
2024 * StringUtils.getCommonPrefix(new String[] {"abc", "a"}) = "a"
2025 * StringUtils.getCommonPrefix(new String[] {"ab", "abxyz"}) = "ab"
2026 * StringUtils.getCommonPrefix(new String[] {"abcde", "abxyz"}) = "ab"
2027 * StringUtils.getCommonPrefix(new String[] {"abcde", "xyz"}) = ""
2028 * StringUtils.getCommonPrefix(new String[] {"xyz", "abcde"}) = ""
2029 * StringUtils.getCommonPrefix(new String[] {"i am a machine", "i am a robot"}) = "i am a "
2030 * </pre>
2031 *
2032 * @param strs array of String objects, entries may be null
2033 * @return the initial sequence of characters that are common to all Strings
2034 * in the array; empty String if the array is null, the elements are all null
2035 * or if there is no common prefix.
2036 * @since 2.4
2037 */
2038 public static String getCommonPrefix(final String... strs) {
2039 if (ArrayUtils.isEmpty(strs)) {
2040 return EMPTY;
2041 }
2042 final int smallestIndexOfDiff = indexOfDifference(strs);
2043 if (smallestIndexOfDiff == INDEX_NOT_FOUND) {
2044 // all strings were identical
2045 if (strs[0] == null) {
2046 return EMPTY;
2047 }
2048 return strs[0];
2049 }
2050 if (smallestIndexOfDiff == 0) {
2051 // there were no common initial characters
2052 return EMPTY;
2053 }
2054 // we found a common initial character sequence
2055 return strs[0].substring(0, smallestIndexOfDiff);
2056 }
2057
2058 /**
2059 * Checks if a String {@code str} contains Unicode digits,
2060 * if yes then concatenate all the digits in {@code str} and return it as a String.
2061 *
2062 * <p>An empty ("") String will be returned if no digits found in {@code str}.</p>
2063 *
2064 * <pre>
2065 * StringUtils.getDigits(null) = null
2066 * StringUtils.getDigits("") = ""
2067 * StringUtils.getDigits("abc") = ""
2068 * StringUtils.getDigits("1000$") = "1000"
2069 * StringUtils.getDigits("1123~45") = "112345"
2070 * StringUtils.getDigits("(541) 754-3010") = "5417543010"
2071 * StringUtils.getDigits("\u0967\u0968\u0969") = "\u0967\u0968\u0969"
2072 * </pre>
2073 *
2074 * @param str the String to extract digits from, may be null
2075 * @return String with only digits,
2076 * or an empty ("") String if no digits found,
2077 * or {@code null} String if {@code str} is null
2078 * @since 3.6
2079 */
2080 public static String getDigits(final String str) {
2081 if (isEmpty(str)) {
2082 return str;
2083 }
2084 final int sz = str.length();
2085 final StringBuilder strDigits = new StringBuilder(sz);
2086 for (int i = 0; i < sz; i++) {
2087 final char tempChar = str.charAt(i);
2088 if (Character.isDigit(tempChar)) {
2089 strDigits.append(tempChar);
2090 }
2091 }
2092 return strDigits.toString();
2093 }
2094
2095 /**
2096 * Find the Fuzzy Distance which indicates the similarity score between two Strings.
2097 *
2098 * <p>This string matching algorithm is similar to the algorithms of editors such as Sublime Text,
2099 * TextMate, Atom and others. One point is given for every matched character. Subsequent
2100 * matches yield two bonus points. A higher score indicates a higher similarity.</p>
2101 *
2102 * <pre>
2103 * StringUtils.getFuzzyDistance(null, null, null) = IllegalArgumentException
2104 * StringUtils.getFuzzyDistance("", "", Locale.ENGLISH) = 0
2105 * StringUtils.getFuzzyDistance("Workshop", "b", Locale.ENGLISH) = 0
2106 * StringUtils.getFuzzyDistance("Room", "o", Locale.ENGLISH) = 1
2107 * StringUtils.getFuzzyDistance("Workshop", "w", Locale.ENGLISH) = 1
2108 * StringUtils.getFuzzyDistance("Workshop", "ws", Locale.ENGLISH) = 2
2109 * StringUtils.getFuzzyDistance("Workshop", "wo", Locale.ENGLISH) = 4
2110 * StringUtils.getFuzzyDistance("Apache Software Foundation", "asf", Locale.ENGLISH) = 3
2111 * </pre>
2112 *
2113 * @param term a full term that should be matched against, must not be null
2114 * @param query the query that will be matched against a term, must not be null
2115 * @param locale This string matching logic is case-insensitive. A locale is necessary to normalize
2116 * both Strings to lower case.
2117 * @return result score
2118 * @throws IllegalArgumentException if either String input {@code null} or Locale input {@code null}
2119 * @since 3.4
2120 * @deprecated As of 3.6, use Apache Commons Text
2121 * <a href="https://commons.apache.org/proper/commons-text/javadocs/api-release/org/apache/commons/text/similarity/FuzzyScore.html">
2122 * FuzzyScore</a> instead
2123 */
2124 @Deprecated
2125 public static int getFuzzyDistance(final CharSequence term, final CharSequence query, final Locale locale) {
2126 if (term == null || query == null) {
2127 throw new IllegalArgumentException("Strings must not be null");
2128 }
2129 if (locale == null) {
2130 throw new IllegalArgumentException("Locale must not be null");
2131 }
2132
2133 // fuzzy logic is case-insensitive. We normalize the Strings to lower
2134 // case right from the start. Turning characters to lower case
2135 // via Character.toLowerCase(char) is unfortunately insufficient
2136 // as it does not accept a locale.
2137 final String termLowerCase = term.toString().toLowerCase(locale);
2138 final String queryLowerCase = query.toString().toLowerCase(locale);
2139
2140 // the resulting score
2141 int score = 0;
2142
2143 // the position in the term which will be scanned next for potential
2144 // query character matches
2145 int termIndex = 0;
2146
2147 // index of the previously matched character in the term
2148 int previousMatchingCharacterIndex = Integer.MIN_VALUE;
2149
2150 for (int queryIndex = 0; queryIndex < queryLowerCase.length(); queryIndex++) {
2151 final char queryChar = queryLowerCase.charAt(queryIndex);
2152
2153 boolean termCharacterMatchFound = false;
2154 for (; termIndex < termLowerCase.length() && !termCharacterMatchFound; termIndex++) {
2155 final char termChar = termLowerCase.charAt(termIndex);
2156
2157 if (queryChar == termChar) {
2158 // simple character matches result in one point
2159 score++;
2160
2161 // subsequent character matches further improve
2162 // the score.
2163 if (previousMatchingCharacterIndex + 1 == termIndex) {
2164 score += 2;
2165 }
2166
2167 previousMatchingCharacterIndex = termIndex;
2168
2169 // we can leave the nested loop. Every character in the
2170 // query can match at most one character in the term.
2171 termCharacterMatchFound = true;
2172 }
2173 }
2174 }
2175
2176 return score;
2177 }
2178
2179 /**
2180 * Returns either the passed in CharSequence, or if the CharSequence is
2181 * whitespace, empty ("") or {@code null}, the value supplied by {@code defaultStrSupplier}.
2182 *
2183 * <p>Whitespace is defined by {@link Character#isWhitespace(char)}.</p>
2184 *
2185 * <p>Caller responsible for thread-safety and exception handling of default value supplier</p>
2186 *
2187 * <pre>
2188 * {@code
2189 * StringUtils.getIfBlank(null, () -> "NULL") = "NULL"
2190 * StringUtils.getIfBlank("", () -> "NULL") = "NULL"
2191 * StringUtils.getIfBlank(" ", () -> "NULL") = "NULL"
2192 * StringUtils.getIfBlank("bat", () -> "NULL") = "bat"
2193 * StringUtils.getIfBlank("", () -> null) = null
2194 * StringUtils.getIfBlank("", null) = null
2195 * }</pre>
2196 * @param <T> the specific kind of CharSequence
2197 * @param str the CharSequence to check, may be null
2198 * @param defaultSupplier the supplier of default CharSequence to return
2199 * if the input is whitespace, empty ("") or {@code null}, may be null
2200 * @return the passed in CharSequence, or the default
2201 * @see StringUtils#defaultString(String, String)
2202 * @since 3.10
2203 */
2204 public static <T extends CharSequence> T getIfBlank(final T str, final Supplier<T> defaultSupplier) {
2205 return isBlank(str) ? Suppliers.get(defaultSupplier) : str;
2206 }
2207
2208 /**
2209 * Returns either the passed in CharSequence, or if the CharSequence is
2210 * empty or {@code null}, the value supplied by {@code defaultStrSupplier}.
2211 *
2212 * <p>Caller responsible for thread-safety and exception handling of default value supplier</p>
2213 *
2214 * <pre>
2215 * {@code
2216 * StringUtils.getIfEmpty(null, () -> "NULL") = "NULL"
2217 * StringUtils.getIfEmpty("", () -> "NULL") = "NULL"
2218 * StringUtils.getIfEmpty(" ", () -> "NULL") = " "
2219 * StringUtils.getIfEmpty("bat", () -> "NULL") = "bat"
2220 * StringUtils.getIfEmpty("", () -> null) = null
2221 * StringUtils.getIfEmpty("", null) = null
2222 * }
2223 * </pre>
2224 * @param <T> the specific kind of CharSequence
2225 * @param str the CharSequence to check, may be null
2226 * @param defaultSupplier the supplier of default CharSequence to return
2227 * if the input is empty ("") or {@code null}, may be null
2228 * @return the passed in CharSequence, or the default
2229 * @see StringUtils#defaultString(String, String)
2230 * @since 3.10
2231 */
2232 public static <T extends CharSequence> T getIfEmpty(final T str, final Supplier<T> defaultSupplier) {
2233 return isEmpty(str) ? Suppliers.get(defaultSupplier) : str;
2234 }
2235
2236 /**
2237 * Find the Jaro Winkler Distance which indicates the similarity score between two Strings.
2238 *
2239 * <p>The Jaro measure is the weighted sum of percentage of matched characters from each file and transposed characters.
2240 * Winkler increased this measure for matching initial characters.</p>
2241 *
2242 * <p>This implementation is based on the Jaro Winkler similarity algorithm
2243 * from <a href="https://en.wikipedia.org/wiki/Jaro%E2%80%93Winkler_distance">https://en.wikipedia.org/wiki/Jaro%E2%80%93Winkler_distance</a>.</p>
2244 *
2245 * <pre>
2246 * StringUtils.getJaroWinklerDistance(null, null) = IllegalArgumentException
2247 * StringUtils.getJaroWinklerDistance("", "") = 0.0
2248 * StringUtils.getJaroWinklerDistance("", "a") = 0.0
2249 * StringUtils.getJaroWinklerDistance("aaapppp", "") = 0.0
2250 * StringUtils.getJaroWinklerDistance("frog", "fog") = 0.93
2251 * StringUtils.getJaroWinklerDistance("fly", "ant") = 0.0
2252 * StringUtils.getJaroWinklerDistance("elephant", "hippo") = 0.44
2253 * StringUtils.getJaroWinklerDistance("hippo", "elephant") = 0.44
2254 * StringUtils.getJaroWinklerDistance("hippo", "zzzzzzzz") = 0.0
2255 * StringUtils.getJaroWinklerDistance("hello", "hallo") = 0.88
2256 * StringUtils.getJaroWinklerDistance("ABC Corporation", "ABC Corp") = 0.93
2257 * StringUtils.getJaroWinklerDistance("D N H Enterprises Inc", "D & H Enterprises, Inc.") = 0.95
2258 * StringUtils.getJaroWinklerDistance("My Gym Children's Fitness Center", "My Gym. Childrens Fitness") = 0.92
2259 * StringUtils.getJaroWinklerDistance("PENNSYLVANIA", "PENNCISYLVNIA") = 0.88
2260 * </pre>
2261 *
2262 * @param first the first String, must not be null
2263 * @param second the second String, must not be null
2264 * @return result distance
2265 * @throws IllegalArgumentException if either String input {@code null}
2266 * @since 3.3
2267 * @deprecated As of 3.6, use Apache Commons Text
2268 * <a href="https://commons.apache.org/proper/commons-text/javadocs/api-release/org/apache/commons/text/similarity/JaroWinklerDistance.html">
2269 * JaroWinklerDistance</a> instead
2270 */
2271 @Deprecated
2272 public static double getJaroWinklerDistance(final CharSequence first, final CharSequence second) {
2273 final double DEFAULT_SCALING_FACTOR = 0.1;
2274
2275 if (first == null || second == null) {
2276 throw new IllegalArgumentException("Strings must not be null");
2277 }
2278
2279 final int[] mtp = matches(first, second);
2280 final double m = mtp[0];
2281 if (m == 0) {
2282 return 0D;
2283 }
2284 final double j = (m / first.length() + m / second.length() + (m - mtp[1]) / m) / 3;
2285 final double jw = j < 0.7D ? j : j + Math.min(DEFAULT_SCALING_FACTOR, 1D / mtp[3]) * mtp[2] * (1D - j);
2286 return Math.round(jw * 100.0D) / 100.0D;
2287 }
2288
2289 /**
2290 * Find the Levenshtein distance between two Strings.
2291 *
2292 * <p>This is the number of changes needed to change one String into
2293 * another, where each change is a single character modification (deletion,
2294 * insertion or substitution).</p>
2295 *
2296 * <p>The implementation uses a single-dimensional array of length s.length() + 1. See
2297 * <a href="https://blog.softwx.net/2014/12/optimizing-levenshtein-algorithm-in-c.html">
2298 * https://blog.softwx.net/2014/12/optimizing-levenshtein-algorithm-in-c.html</a> for details.</p>
2299 *
2300 * <pre>
2301 * StringUtils.getLevenshteinDistance(null, *) = IllegalArgumentException
2302 * StringUtils.getLevenshteinDistance(*, null) = IllegalArgumentException
2303 * StringUtils.getLevenshteinDistance("", "") = 0
2304 * StringUtils.getLevenshteinDistance("", "a") = 1
2305 * StringUtils.getLevenshteinDistance("aaapppp", "") = 7
2306 * StringUtils.getLevenshteinDistance("frog", "fog") = 1
2307 * StringUtils.getLevenshteinDistance("fly", "ant") = 3
2308 * StringUtils.getLevenshteinDistance("elephant", "hippo") = 7
2309 * StringUtils.getLevenshteinDistance("hippo", "elephant") = 7
2310 * StringUtils.getLevenshteinDistance("hippo", "zzzzzzzz") = 8
2311 * StringUtils.getLevenshteinDistance("hello", "hallo") = 1
2312 * </pre>
2313 *
2314 * @param s the first String, must not be null
2315 * @param t the second String, must not be null
2316 * @return result distance
2317 * @throws IllegalArgumentException if either String input {@code null}
2318 * @since 3.0 Changed signature from getLevenshteinDistance(String, String) to
2319 * getLevenshteinDistance(CharSequence, CharSequence)
2320 * @deprecated As of 3.6, use Apache Commons Text
2321 * <a href="https://commons.apache.org/proper/commons-text/javadocs/api-release/org/apache/commons/text/similarity/LevenshteinDistance.html">
2322 * LevenshteinDistance</a> instead
2323 */
2324 @Deprecated
2325 public static int getLevenshteinDistance(CharSequence s, CharSequence t) {
2326 if (s == null || t == null) {
2327 throw new IllegalArgumentException("Strings must not be null");
2328 }
2329
2330 int n = s.length();
2331 int m = t.length();
2332
2333 if (n == 0) {
2334 return m;
2335 }
2336 if (m == 0) {
2337 return n;
2338 }
2339
2340 if (n > m) {
2341 // swap the input strings to consume less memory
2342 final CharSequence tmp = s;
2343 s = t;
2344 t = tmp;
2345 n = m;
2346 m = t.length();
2347 }
2348
2349 final int[] p = new int[n + 1];
2350 // indexes into strings s and t
2351 int i; // iterates through s
2352 int j; // iterates through t
2353 int upperleft;
2354 int upper;
2355
2356 char jOfT; // jth character of t
2357 int cost;
2358
2359 for (i = 0; i <= n; i++) {
2360 p[i] = i;
2361 }
2362
2363 for (j = 1; j <= m; j++) {
2364 upperleft = p[0];
2365 jOfT = t.charAt(j - 1);
2366 p[0] = j;
2367
2368 for (i = 1; i <= n; i++) {
2369 upper = p[i];
2370 cost = s.charAt(i - 1) == jOfT ? 0 : 1;
2371 // minimum of cell to the left+1, to the top+1, diagonally left and up +cost
2372 p[i] = Math.min(Math.min(p[i - 1] + 1, p[i] + 1), upperleft + cost);
2373 upperleft = upper;
2374 }
2375 }
2376
2377 return p[n];
2378 }
2379
2380 /**
2381 * Find the Levenshtein distance between two Strings if it's less than or equal to a given
2382 * threshold.
2383 *
2384 * <p>This is the number of changes needed to change one String into
2385 * another, where each change is a single character modification (deletion,
2386 * insertion or substitution).</p>
2387 *
2388 * <p>This implementation follows from Algorithms on Strings, Trees and Sequences by Dan Gusfield
2389 * and Chas Emerick's implementation of the Levenshtein distance algorithm from
2390 * <a href="https://web.archive.org/web/20120212021906/http%3A//www.merriampark.com/ld.htm">http://www.merriampark.com/ld.htm</a></p>
2391 *
2392 * <pre>
2393 * StringUtils.getLevenshteinDistance(null, *, *) = IllegalArgumentException
2394 * StringUtils.getLevenshteinDistance(*, null, *) = IllegalArgumentException
2395 * StringUtils.getLevenshteinDistance(*, *, -1) = IllegalArgumentException
2396 * StringUtils.getLevenshteinDistance("", "", 0) = 0
2397 * StringUtils.getLevenshteinDistance("aaapppp", "", 8) = 7
2398 * StringUtils.getLevenshteinDistance("aaapppp", "", 7) = 7
2399 * StringUtils.getLevenshteinDistance("aaapppp", "", 6)) = -1
2400 * StringUtils.getLevenshteinDistance("elephant", "hippo", 7) = 7
2401 * StringUtils.getLevenshteinDistance("elephant", "hippo", 6) = -1
2402 * StringUtils.getLevenshteinDistance("hippo", "elephant", 7) = 7
2403 * StringUtils.getLevenshteinDistance("hippo", "elephant", 6) = -1
2404 * </pre>
2405 *
2406 * @param s the first String, must not be null
2407 * @param t the second String, must not be null
2408 * @param threshold the target threshold, must not be negative
2409 * @return result distance, or {@code -1} if the distance would be greater than the threshold
2410 * @throws IllegalArgumentException if either String input {@code null} or negative threshold
2411 * @deprecated As of 3.6, use Apache Commons Text
2412 * <a href="https://commons.apache.org/proper/commons-text/javadocs/api-release/org/apache/commons/text/similarity/LevenshteinDistance.html">
2413 * LevenshteinDistance</a> instead
2414 */
2415 @Deprecated
2416 public static int getLevenshteinDistance(CharSequence s, CharSequence t, final int threshold) {
2417 if (s == null || t == null) {
2418 throw new IllegalArgumentException("Strings must not be null");
2419 }
2420 if (threshold < 0) {
2421 throw new IllegalArgumentException("Threshold must not be negative");
2422 }
2423
2424 /*
2425 This implementation only computes the distance if it's less than or equal to the
2426 threshold value, returning -1 if it's greater. The advantage is performance: unbounded
2427 distance is O(nm), but a bound of k allows us to reduce it to O(km) time by only
2428 computing a diagonal stripe of width 2k + 1 of the cost table.
2429 It is also possible to use this to compute the unbounded Levenshtein distance by starting
2430 the threshold at 1 and doubling each time until the distance is found; this is O(dm), where
2431 d is the distance.
2432
2433 One subtlety comes from needing to ignore entries on the border of our stripe
2434 eg.
2435 p[] = |#|#|#|*
2436 d[] = *|#|#|#|
2437 We must ignore the entry to the left of the leftmost member
2438 We must ignore the entry above the rightmost member
2439
2440 Another subtlety comes from our stripe running off the matrix if the strings aren't
2441 of the same size. Since string s is always swapped to be the shorter of the two,
2442 the stripe will always run off to the upper right instead of the lower left of the matrix.
2443
2444 As a concrete example, suppose s is of length 5, t is of length 7, and our threshold is 1.
2445 In this case we're going to walk a stripe of length 3. The matrix would look like so:
2446
2447 1 2 3 4 5
2448 1 |#|#| | | |
2449 2 |#|#|#| | |
2450 3 | |#|#|#| |
2451 4 | | |#|#|#|
2452 5 | | | |#|#|
2453 6 | | | | |#|
2454 7 | | | | | |
2455
2456 Note how the stripe leads off the table as there is no possible way to turn a string of length 5
2457 into one of length 7 in edit distance of 1.
2458
2459 Additionally, this implementation decreases memory usage by using two
2460 single-dimensional arrays and swapping them back and forth instead of allocating
2461 an entire n by m matrix. This requires a few minor changes, such as immediately returning
2462 when it's detected that the stripe has run off the matrix and initially filling the arrays with
2463 large values so that entries we don't compute are ignored.
2464
2465 See Algorithms on Strings, Trees and Sequences by Dan Gusfield for some discussion.
2466 */
2467
2468 int n = s.length(); // length of s
2469 int m = t.length(); // length of t
2470
2471 // if one string is empty, the edit distance is necessarily the length of the other
2472 if (n == 0) {
2473 return m <= threshold ? m : -1;
2474 }
2475 if (m == 0) {
2476 return n <= threshold ? n : -1;
2477 }
2478 if (Math.abs(n - m) > threshold) {
2479 // no need to calculate the distance if the length difference is greater than the threshold
2480 return -1;
2481 }
2482
2483 if (n > m) {
2484 // swap the two strings to consume less memory
2485 final CharSequence tmp = s;
2486 s = t;
2487 t = tmp;
2488 n = m;
2489 m = t.length();
2490 }
2491
2492 int[] p = new int[n + 1]; // 'previous' cost array, horizontally
2493 int[] d = new int[n + 1]; // cost array, horizontally
2494 int[] tmp; // placeholder to assist in swapping p and d
2495
2496 // fill in starting table values
2497 final int boundary = Math.min(n, threshold) + 1;
2498 for (int i = 0; i < boundary; i++) {
2499 p[i] = i;
2500 }
2501 // these fills ensure that the value above the rightmost entry of our
2502 // stripe will be ignored in following loop iterations
2503 Arrays.fill(p, boundary, p.length, Integer.MAX_VALUE);
2504 Arrays.fill(d, Integer.MAX_VALUE);
2505
2506 // iterates through t
2507 for (int j = 1; j <= m; j++) {
2508 final char jOfT = t.charAt(j - 1); // jth character of t
2509 d[0] = j;
2510
2511 // compute stripe indices, constrain to array size
2512 final int min = Math.max(1, j - threshold);
2513 final int max = j > Integer.MAX_VALUE - threshold ? n : Math.min(n, j + threshold);
2514
2515 // the stripe may lead off of the table if s and t are of different sizes
2516 if (min > max) {
2517 return -1;
2518 }
2519
2520 // ignore entry left of leftmost
2521 if (min > 1) {
2522 d[min - 1] = Integer.MAX_VALUE;
2523 }
2524
2525 // iterates through [min, max] in s
2526 for (int i = min; i <= max; i++) {
2527 if (s.charAt(i - 1) == jOfT) {
2528 // diagonally left and up
2529 d[i] = p[i - 1];
2530 } else {
2531 // 1 + minimum of cell to the left, to the top, diagonally left and up
2532 d[i] = 1 + Math.min(Math.min(d[i - 1], p[i]), p[i - 1]);
2533 }
2534 }
2535
2536 // copy current distance counts to 'previous row' distance counts
2537 tmp = p;
2538 p = d;
2539 d = tmp;
2540 }
2541
2542 // if p[n] is greater than the threshold, there's no guarantee on it being the correct
2543 // distance
2544 if (p[n] <= threshold) {
2545 return p[n];
2546 }
2547 return -1;
2548 }
2549
2550 /**
2551 * Finds the first index within a CharSequence, handling {@code null}.
2552 * This method uses {@link String#indexOf(String, int)} if possible.
2553 *
2554 * <p>A {@code null} CharSequence will return {@code -1}.</p>
2555 *
2556 * <pre>
2557 * StringUtils.indexOf(null, *) = -1
2558 * StringUtils.indexOf(*, null) = -1
2559 * StringUtils.indexOf("", "") = 0
2560 * StringUtils.indexOf("", *) = -1 (except when * = "")
2561 * StringUtils.indexOf("aabaabaa", "a") = 0
2562 * StringUtils.indexOf("aabaabaa", "b") = 2
2563 * StringUtils.indexOf("aabaabaa", "ab") = 1
2564 * StringUtils.indexOf("aabaabaa", "") = 0
2565 * </pre>
2566 *
2567 * @param seq the CharSequence to check, may be null
2568 * @param searchSeq the CharSequence to find, may be null
2569 * @return the first index of the search CharSequence,
2570 * -1 if no match or {@code null} string input
2571 * @since 2.0
2572 * @since 3.0 Changed signature from indexOf(String, String) to indexOf(CharSequence, CharSequence)
2573 */
2574 public static int indexOf(final CharSequence seq, final CharSequence searchSeq) {
2575 if (seq == null || searchSeq == null) {
2576 return INDEX_NOT_FOUND;
2577 }
2578 return CharSequenceUtils.indexOf(seq, searchSeq, 0);
2579 }
2580
2581 /**
2582 * Finds the first index within a CharSequence, handling {@code null}.
2583 * This method uses {@link String#indexOf(String, int)} if possible.
2584 *
2585 * <p>A {@code null} CharSequence will return {@code -1}.
2586 * A negative start position is treated as zero.
2587 * An empty ("") search CharSequence always matches.
2588 * A start position greater than the string length only matches
2589 * an empty search CharSequence.</p>
2590 *
2591 * <pre>
2592 * StringUtils.indexOf(null, *, *) = -1
2593 * StringUtils.indexOf(*, null, *) = -1
2594 * StringUtils.indexOf("", "", 0) = 0
2595 * StringUtils.indexOf("", *, 0) = -1 (except when * = "")
2596 * StringUtils.indexOf("aabaabaa", "a", 0) = 0
2597 * StringUtils.indexOf("aabaabaa", "b", 0) = 2
2598 * StringUtils.indexOf("aabaabaa", "ab", 0) = 1
2599 * StringUtils.indexOf("aabaabaa", "b", 3) = 5
2600 * StringUtils.indexOf("aabaabaa", "b", 9) = -1
2601 * StringUtils.indexOf("aabaabaa", "b", -1) = 2
2602 * StringUtils.indexOf("aabaabaa", "", 2) = 2
2603 * StringUtils.indexOf("abc", "", 9) = 3
2604 * </pre>
2605 *
2606 * @param seq the CharSequence to check, may be null
2607 * @param searchSeq the CharSequence to find, may be null
2608 * @param startPos the start position, negative treated as zero
2609 * @return the first index of the search CharSequence (always ≥ startPos),
2610 * -1 if no match or {@code null} string input
2611 * @since 2.0
2612 * @since 3.0 Changed signature from indexOf(String, String, int) to indexOf(CharSequence, CharSequence, int)
2613 */
2614 public static int indexOf(final CharSequence seq, final CharSequence searchSeq, final int startPos) {
2615 if (seq == null || searchSeq == null) {
2616 return INDEX_NOT_FOUND;
2617 }
2618 return CharSequenceUtils.indexOf(seq, searchSeq, startPos);
2619 }
2620
2621 /**
2622 * Returns the index within {@code seq} of the first occurrence of
2623 * the specified character. If a character with value
2624 * {@code searchChar} occurs in the character sequence represented by
2625 * {@code seq} {@link CharSequence} object, then the index (in Unicode
2626 * code units) of the first such occurrence is returned. For
2627 * values of {@code searchChar} in the range from 0 to 0xFFFF
2628 * (inclusive), this is the smallest value <i>k</i> such that:
2629 * <blockquote><pre>
2630 * this.charAt(<i>k</i>) == searchChar
2631 * </pre></blockquote>
2632 * is true. For other values of {@code searchChar}, it is the
2633 * smallest value <i>k</i> such that:
2634 * <blockquote><pre>
2635 * this.codePointAt(<i>k</i>) == searchChar
2636 * </pre></blockquote>
2637 * is true. In either case, if no such character occurs in {@code seq},
2638 * then {@code INDEX_NOT_FOUND (-1)} is returned.
2639 *
2640 * <p>Furthermore, a {@code null} or empty ("") CharSequence will
2641 * return {@code INDEX_NOT_FOUND (-1)}.</p>
2642 *
2643 * <pre>
2644 * StringUtils.indexOf(null, *) = -1
2645 * StringUtils.indexOf("", *) = -1
2646 * StringUtils.indexOf("aabaabaa", 'a') = 0
2647 * StringUtils.indexOf("aabaabaa", 'b') = 2
2648 * </pre>
2649 *
2650 * @param seq the CharSequence to check, may be null
2651 * @param searchChar the character to find
2652 * @return the first index of the search character,
2653 * -1 if no match or {@code null} string input
2654 * @since 2.0
2655 * @since 3.0 Changed signature from indexOf(String, int) to indexOf(CharSequence, int)
2656 * @since 3.6 Updated {@link CharSequenceUtils} call to behave more like {@link String}
2657 */
2658 public static int indexOf(final CharSequence seq, final int searchChar) {
2659 if (isEmpty(seq)) {
2660 return INDEX_NOT_FOUND;
2661 }
2662 return CharSequenceUtils.indexOf(seq, searchChar, 0);
2663 }
2664
2665 /**
2666 * Returns the index within {@code seq} of the first occurrence of the
2667 * specified character, starting the search at the specified index.
2668 * <p>
2669 * If a character with value {@code searchChar} occurs in the
2670 * character sequence represented by the {@code seq} {@link CharSequence}
2671 * object at an index no smaller than {@code startPos}, then
2672 * the index of the first such occurrence is returned. For values
2673 * of {@code searchChar} in the range from 0 to 0xFFFF (inclusive),
2674 * this is the smallest value <i>k</i> such that:
2675 * <blockquote><pre>
2676 * (this.charAt(<i>k</i>) == searchChar) && (<i>k</i> >= startPos)
2677 * </pre></blockquote>
2678 * is true. For other values of {@code searchChar}, it is the
2679 * smallest value <i>k</i> such that:
2680 * <blockquote><pre>
2681 * (this.codePointAt(<i>k</i>) == searchChar) && (<i>k</i> >= startPos)
2682 * </pre></blockquote>
2683 * is true. In either case, if no such character occurs in {@code seq}
2684 * at or after position {@code startPos}, then
2685 * {@code -1} is returned.
2686 *
2687 * <p>
2688 * There is no restriction on the value of {@code startPos}. If it
2689 * is negative, it has the same effect as if it were zero: this entire
2690 * string may be searched. If it is greater than the length of this
2691 * string, it has the same effect as if it were equal to the length of
2692 * this string: {@code (INDEX_NOT_FOUND) -1} is returned. Furthermore, a
2693 * {@code null} or empty ("") CharSequence will
2694 * return {@code (INDEX_NOT_FOUND) -1}.
2695 *
2696 * <p>All indices are specified in {@code char} values
2697 * (Unicode code units).
2698 *
2699 * <pre>
2700 * StringUtils.indexOf(null, *, *) = -1
2701 * StringUtils.indexOf("", *, *) = -1
2702 * StringUtils.indexOf("aabaabaa", 'b', 0) = 2
2703 * StringUtils.indexOf("aabaabaa", 'b', 3) = 5
2704 * StringUtils.indexOf("aabaabaa", 'b', 9) = -1
2705 * StringUtils.indexOf("aabaabaa", 'b', -1) = 2
2706 * </pre>
2707 *
2708 * @param seq the CharSequence to check, may be null
2709 * @param searchChar the character to find
2710 * @param startPos the start position, negative treated as zero
2711 * @return the first index of the search character (always ≥ startPos),
2712 * -1 if no match or {@code null} string input
2713 * @since 2.0
2714 * @since 3.0 Changed signature from indexOf(String, int, int) to indexOf(CharSequence, int, int)
2715 * @since 3.6 Updated {@link CharSequenceUtils} call to behave more like {@link String}
2716 */
2717 public static int indexOf(final CharSequence seq, final int searchChar, final int startPos) {
2718 if (isEmpty(seq)) {
2719 return INDEX_NOT_FOUND;
2720 }
2721 return CharSequenceUtils.indexOf(seq, searchChar, startPos);
2722 }
2723
2724 /**
2725 * Search a CharSequence to find the first index of any
2726 * character in the given set of characters.
2727 *
2728 * <p>A {@code null} String will return {@code -1}.
2729 * A {@code null} or zero length search array will return {@code -1}.</p>
2730 *
2731 * <pre>
2732 * StringUtils.indexOfAny(null, *) = -1
2733 * StringUtils.indexOfAny("", *) = -1
2734 * StringUtils.indexOfAny(*, null) = -1
2735 * StringUtils.indexOfAny(*, []) = -1
2736 * StringUtils.indexOfAny("zzabyycdxx", ['z', 'a']) = 0
2737 * StringUtils.indexOfAny("zzabyycdxx", ['b', 'y']) = 3
2738 * StringUtils.indexOfAny("aba", ['z']) = -1
2739 * </pre>
2740 *
2741 * @param cs the CharSequence to check, may be null
2742 * @param searchChars the chars to search for, may be null
2743 * @return the index of any of the chars, -1 if no match or null input
2744 * @since 2.0
2745 * @since 3.0 Changed signature from indexOfAny(String, char[]) to indexOfAny(CharSequence, char...)
2746 */
2747 public static int indexOfAny(final CharSequence cs, final char... searchChars) {
2748 if (isEmpty(cs) || ArrayUtils.isEmpty(searchChars)) {
2749 return INDEX_NOT_FOUND;
2750 }
2751 final int csLen = cs.length();
2752 final int csLast = csLen - 1;
2753 final int searchLen = searchChars.length;
2754 final int searchLast = searchLen - 1;
2755 for (int i = 0; i < csLen; i++) {
2756 final char ch = cs.charAt(i);
2757 for (int j = 0; j < searchLen; j++) {
2758 if (searchChars[j] == ch) {
2759 if (i >= csLast || j >= searchLast || !Character.isHighSurrogate(ch)) {
2760 return i;
2761 }
2762 // ch is a supplementary character
2763 if (searchChars[j + 1] == cs.charAt(i + 1)) {
2764 return i;
2765 }
2766 }
2767 }
2768 }
2769 return INDEX_NOT_FOUND;
2770 }
2771
2772 /**
2773 * Find the first index of any of a set of potential substrings.
2774 *
2775 * <p>A {@code null} CharSequence will return {@code -1}.
2776 * A {@code null} or zero length search array will return {@code -1}.
2777 * A {@code null} search array entry will be ignored, but a search
2778 * array containing "" will return {@code 0} if {@code str} is not
2779 * null. This method uses {@link String#indexOf(String)} if possible.</p>
2780 *
2781 * <pre>
2782 * StringUtils.indexOfAny(null, *) = -1
2783 * StringUtils.indexOfAny(*, null) = -1
2784 * StringUtils.indexOfAny(*, []) = -1
2785 * StringUtils.indexOfAny("zzabyycdxx", ["ab", "cd"]) = 2
2786 * StringUtils.indexOfAny("zzabyycdxx", ["cd", "ab"]) = 2
2787 * StringUtils.indexOfAny("zzabyycdxx", ["mn", "op"]) = -1
2788 * StringUtils.indexOfAny("zzabyycdxx", ["zab", "aby"]) = 1
2789 * StringUtils.indexOfAny("zzabyycdxx", [""]) = 0
2790 * StringUtils.indexOfAny("", [""]) = 0
2791 * StringUtils.indexOfAny("", ["a"]) = -1
2792 * </pre>
2793 *
2794 * @param str the CharSequence to check, may be null
2795 * @param searchStrs the CharSequences to search for, may be null
2796 * @return the first index of any of the searchStrs in str, -1 if no match
2797 * @since 3.0 Changed signature from indexOfAny(String, String[]) to indexOfAny(CharSequence, CharSequence...)
2798 */
2799 public static int indexOfAny(final CharSequence str, final CharSequence... searchStrs) {
2800 if (str == null || searchStrs == null) {
2801 return INDEX_NOT_FOUND;
2802 }
2803
2804 // String's can't have a MAX_VALUEth index.
2805 int ret = Integer.MAX_VALUE;
2806
2807 int tmp;
2808 for (final CharSequence search : searchStrs) {
2809 if (search == null) {
2810 continue;
2811 }
2812 tmp = CharSequenceUtils.indexOf(str, search, 0);
2813 if (tmp == INDEX_NOT_FOUND) {
2814 continue;
2815 }
2816
2817 if (tmp < ret) {
2818 ret = tmp;
2819 }
2820 }
2821
2822 return ret == Integer.MAX_VALUE ? INDEX_NOT_FOUND : ret;
2823 }
2824
2825 /**
2826 * Search a CharSequence to find the first index of any
2827 * character in the given set of characters.
2828 *
2829 * <p>A {@code null} String will return {@code -1}.
2830 * A {@code null} search string will return {@code -1}.</p>
2831 *
2832 * <pre>
2833 * StringUtils.indexOfAny(null, *) = -1
2834 * StringUtils.indexOfAny("", *) = -1
2835 * StringUtils.indexOfAny(*, null) = -1
2836 * StringUtils.indexOfAny(*, "") = -1
2837 * StringUtils.indexOfAny("zzabyycdxx", "za") = 0
2838 * StringUtils.indexOfAny("zzabyycdxx", "by") = 3
2839 * StringUtils.indexOfAny("aba", "z") = -1
2840 * </pre>
2841 *
2842 * @param cs the CharSequence to check, may be null
2843 * @param searchChars the chars to search for, may be null
2844 * @return the index of any of the chars, -1 if no match or null input
2845 * @since 2.0
2846 * @since 3.0 Changed signature from indexOfAny(String, String) to indexOfAny(CharSequence, String)
2847 */
2848 public static int indexOfAny(final CharSequence cs, final String searchChars) {
2849 if (isEmpty(cs) || isEmpty(searchChars)) {
2850 return INDEX_NOT_FOUND;
2851 }
2852 return indexOfAny(cs, searchChars.toCharArray());
2853 }
2854
2855 /**
2856 * Searches a CharSequence to find the first index of any
2857 * character not in the given set of characters.
2858 *
2859 * <p>A {@code null} CharSequence will return {@code -1}.
2860 * A {@code null} or zero length search array will return {@code -1}.</p>
2861 *
2862 * <pre>
2863 * StringUtils.indexOfAnyBut(null, *) = -1
2864 * StringUtils.indexOfAnyBut("", *) = -1
2865 * StringUtils.indexOfAnyBut(*, null) = -1
2866 * StringUtils.indexOfAnyBut(*, []) = -1
2867 * StringUtils.indexOfAnyBut("zzabyycdxx", new char[] {'z', 'a'} ) = 3
2868 * StringUtils.indexOfAnyBut("aba", new char[] {'z'} ) = 0
2869 * StringUtils.indexOfAnyBut("aba", new char[] {'a', 'b'} ) = -1
2870
2871 * </pre>
2872 *
2873 * @param cs the CharSequence to check, may be null
2874 * @param searchChars the chars to search for, may be null
2875 * @return the index of any of the chars, -1 if no match or null input
2876 * @since 2.0
2877 * @since 3.0 Changed signature from indexOfAnyBut(String, char[]) to indexOfAnyBut(CharSequence, char...)
2878 */
2879 public static int indexOfAnyBut(final CharSequence cs, final char... searchChars) {
2880 if (isEmpty(cs) || ArrayUtils.isEmpty(searchChars)) {
2881 return INDEX_NOT_FOUND;
2882 }
2883 final int csLen = cs.length();
2884 final int csLast = csLen - 1;
2885 final int searchLen = searchChars.length;
2886 final int searchLast = searchLen - 1;
2887 outer:
2888 for (int i = 0; i < csLen; i++) {
2889 final char ch = cs.charAt(i);
2890 for (int j = 0; j < searchLen; j++) {
2891 if (searchChars[j] == ch) {
2892 if (i >= csLast || j >= searchLast || !Character.isHighSurrogate(ch)) {
2893 continue outer;
2894 }
2895 if (searchChars[j + 1] == cs.charAt(i + 1)) {
2896 continue outer;
2897 }
2898 }
2899 }
2900 return i;
2901 }
2902 return INDEX_NOT_FOUND;
2903 }
2904
2905 /**
2906 * Search a CharSequence to find the first index of any
2907 * character not in the given set of characters.
2908 *
2909 * <p>A {@code null} CharSequence will return {@code -1}.
2910 * A {@code null} or empty search string will return {@code -1}.</p>
2911 *
2912 * <pre>
2913 * StringUtils.indexOfAnyBut(null, *) = -1
2914 * StringUtils.indexOfAnyBut("", *) = -1
2915 * StringUtils.indexOfAnyBut(*, null) = -1
2916 * StringUtils.indexOfAnyBut(*, "") = -1
2917 * StringUtils.indexOfAnyBut("zzabyycdxx", "za") = 3
2918 * StringUtils.indexOfAnyBut("zzabyycdxx", "") = -1
2919 * StringUtils.indexOfAnyBut("aba", "ab") = -1
2920 * </pre>
2921 *
2922 * @param seq the CharSequence to check, may be null
2923 * @param searchChars the chars to search for, may be null
2924 * @return the index of any of the chars, -1 if no match or null input
2925 * @since 2.0
2926 * @since 3.0 Changed signature from indexOfAnyBut(String, String) to indexOfAnyBut(CharSequence, CharSequence)
2927 */
2928 public static int indexOfAnyBut(final CharSequence seq, final CharSequence searchChars) {
2929 if (isEmpty(seq) || isEmpty(searchChars)) {
2930 return INDEX_NOT_FOUND;
2931 }
2932 final int strLen = seq.length();
2933 for (int i = 0; i < strLen; i++) {
2934 final char ch = seq.charAt(i);
2935 final boolean chFound = CharSequenceUtils.indexOf(searchChars, ch, 0) >= 0;
2936 if (i + 1 < strLen && Character.isHighSurrogate(ch)) {
2937 final char ch2 = seq.charAt(i + 1);
2938 if (chFound && CharSequenceUtils.indexOf(searchChars, ch2, 0) < 0) {
2939 return i;
2940 }
2941 } else if (!chFound) {
2942 return i;
2943 }
2944 }
2945 return INDEX_NOT_FOUND;
2946 }
2947
2948 /**
2949 * Compares all CharSequences in an array and returns the index at which the
2950 * CharSequences begin to differ.
2951 *
2952 * <p>For example,
2953 * {@code indexOfDifference(new String[] {"i am a machine", "i am a robot"}) -> 7}</p>
2954 *
2955 * <pre>
2956 * StringUtils.indexOfDifference(null) = -1
2957 * StringUtils.indexOfDifference(new String[] {}) = -1
2958 * StringUtils.indexOfDifference(new String[] {"abc"}) = -1
2959 * StringUtils.indexOfDifference(new String[] {null, null}) = -1
2960 * StringUtils.indexOfDifference(new String[] {"", ""}) = -1
2961 * StringUtils.indexOfDifference(new String[] {"", null}) = 0
2962 * StringUtils.indexOfDifference(new String[] {"abc", null, null}) = 0
2963 * StringUtils.indexOfDifference(new String[] {null, null, "abc"}) = 0
2964 * StringUtils.indexOfDifference(new String[] {"", "abc"}) = 0
2965 * StringUtils.indexOfDifference(new String[] {"abc", ""}) = 0
2966 * StringUtils.indexOfDifference(new String[] {"abc", "abc"}) = -1
2967 * StringUtils.indexOfDifference(new String[] {"abc", "a"}) = 1
2968 * StringUtils.indexOfDifference(new String[] {"ab", "abxyz"}) = 2
2969 * StringUtils.indexOfDifference(new String[] {"abcde", "abxyz"}) = 2
2970 * StringUtils.indexOfDifference(new String[] {"abcde", "xyz"}) = 0
2971 * StringUtils.indexOfDifference(new String[] {"xyz", "abcde"}) = 0
2972 * StringUtils.indexOfDifference(new String[] {"i am a machine", "i am a robot"}) = 7
2973 * </pre>
2974 *
2975 * @param css array of CharSequences, entries may be null
2976 * @return the index where the strings begin to differ; -1 if they are all equal
2977 * @since 2.4
2978 * @since 3.0 Changed signature from indexOfDifference(String...) to indexOfDifference(CharSequence...)
2979 */
2980 public static int indexOfDifference(final CharSequence... css) {
2981 if (ArrayUtils.getLength(css) <= 1) {
2982 return INDEX_NOT_FOUND;
2983 }
2984 boolean anyStringNull = false;
2985 boolean allStringsNull = true;
2986 final int arrayLen = css.length;
2987 int shortestStrLen = Integer.MAX_VALUE;
2988 int longestStrLen = 0;
2989
2990 // find the min and max string lengths; this avoids checking to make
2991 // sure we are not exceeding the length of the string each time through
2992 // the bottom loop.
2993 for (final CharSequence cs : css) {
2994 if (cs == null) {
2995 anyStringNull = true;
2996 shortestStrLen = 0;
2997 } else {
2998 allStringsNull = false;
2999 shortestStrLen = Math.min(cs.length(), shortestStrLen);
3000 longestStrLen = Math.max(cs.length(), longestStrLen);
3001 }
3002 }
3003
3004 // handle lists containing all nulls or all empty strings
3005 if (allStringsNull || longestStrLen == 0 && !anyStringNull) {
3006 return INDEX_NOT_FOUND;
3007 }
3008
3009 // handle lists containing some nulls or some empty strings
3010 if (shortestStrLen == 0) {
3011 return 0;
3012 }
3013
3014 // find the position with the first difference across all strings
3015 int firstDiff = -1;
3016 for (int stringPos = 0; stringPos < shortestStrLen; stringPos++) {
3017 final char comparisonChar = css[0].charAt(stringPos);
3018 for (int arrayPos = 1; arrayPos < arrayLen; arrayPos++) {
3019 if (css[arrayPos].charAt(stringPos) != comparisonChar) {
3020 firstDiff = stringPos;
3021 break;
3022 }
3023 }
3024 if (firstDiff != -1) {
3025 break;
3026 }
3027 }
3028
3029 if (firstDiff == -1 && shortestStrLen != longestStrLen) {
3030 // we compared all of the characters up to the length of the
3031 // shortest string and didn't find a match, but the string lengths
3032 // vary, so return the length of the shortest string.
3033 return shortestStrLen;
3034 }
3035 return firstDiff;
3036 }
3037
3038 /**
3039 * Compares two CharSequences, and returns the index at which the
3040 * CharSequences begin to differ.
3041 *
3042 * <p>For example,
3043 * {@code indexOfDifference("i am a machine", "i am a robot") -> 7}</p>
3044 *
3045 * <pre>
3046 * StringUtils.indexOfDifference(null, null) = -1
3047 * StringUtils.indexOfDifference("", "") = -1
3048 * StringUtils.indexOfDifference("", "abc") = 0
3049 * StringUtils.indexOfDifference("abc", "") = 0
3050 * StringUtils.indexOfDifference("abc", "abc") = -1
3051 * StringUtils.indexOfDifference("ab", "abxyz") = 2
3052 * StringUtils.indexOfDifference("abcde", "abxyz") = 2
3053 * StringUtils.indexOfDifference("abcde", "xyz") = 0
3054 * </pre>
3055 *
3056 * @param cs1 the first CharSequence, may be null
3057 * @param cs2 the second CharSequence, may be null
3058 * @return the index where cs1 and cs2 begin to differ; -1 if they are equal
3059 * @since 2.0
3060 * @since 3.0 Changed signature from indexOfDifference(String, String) to
3061 * indexOfDifference(CharSequence, CharSequence)
3062 */
3063 public static int indexOfDifference(final CharSequence cs1, final CharSequence cs2) {
3064 if (cs1 == cs2) {
3065 return INDEX_NOT_FOUND;
3066 }
3067 if (cs1 == null || cs2 == null) {
3068 return 0;
3069 }
3070 int i;
3071 for (i = 0; i < cs1.length() && i < cs2.length(); ++i) {
3072 if (cs1.charAt(i) != cs2.charAt(i)) {
3073 break;
3074 }
3075 }
3076 if (i < cs2.length() || i < cs1.length()) {
3077 return i;
3078 }
3079 return INDEX_NOT_FOUND;
3080 }
3081
3082 /**
3083 * Case in-sensitive find of the first index within a CharSequence.
3084 *
3085 * <p>A {@code null} CharSequence will return {@code -1}.
3086 * A negative start position is treated as zero.
3087 * An empty ("") search CharSequence always matches.
3088 * A start position greater than the string length only matches
3089 * an empty search CharSequence.</p>
3090 *
3091 * <pre>
3092 * StringUtils.indexOfIgnoreCase(null, *) = -1
3093 * StringUtils.indexOfIgnoreCase(*, null) = -1
3094 * StringUtils.indexOfIgnoreCase("", "") = 0
3095 * StringUtils.indexOfIgnoreCase(" ", " ") = 0
3096 * StringUtils.indexOfIgnoreCase("aabaabaa", "a") = 0
3097 * StringUtils.indexOfIgnoreCase("aabaabaa", "b") = 2
3098 * StringUtils.indexOfIgnoreCase("aabaabaa", "ab") = 1
3099 * </pre>
3100 *
3101 * @param str the CharSequence to check, may be null
3102 * @param searchStr the CharSequence to find, may be null
3103 * @return the first index of the search CharSequence,
3104 * -1 if no match or {@code null} string input
3105 * @since 2.5
3106 * @since 3.0 Changed signature from indexOfIgnoreCase(String, String) to indexOfIgnoreCase(CharSequence, CharSequence)
3107 */
3108 public static int indexOfIgnoreCase(final CharSequence str, final CharSequence searchStr) {
3109 return indexOfIgnoreCase(str, searchStr, 0);
3110 }
3111
3112 /**
3113 * Case in-sensitive find of the first index within a CharSequence
3114 * from the specified position.
3115 *
3116 * <p>A {@code null} CharSequence will return {@code -1}.
3117 * A negative start position is treated as zero.
3118 * An empty ("") search CharSequence always matches.
3119 * A start position greater than the string length only matches
3120 * an empty search CharSequence.</p>
3121 *
3122 * <pre>
3123 * StringUtils.indexOfIgnoreCase(null, *, *) = -1
3124 * StringUtils.indexOfIgnoreCase(*, null, *) = -1
3125 * StringUtils.indexOfIgnoreCase("", "", 0) = 0
3126 * StringUtils.indexOfIgnoreCase("aabaabaa", "A", 0) = 0
3127 * StringUtils.indexOfIgnoreCase("aabaabaa", "B", 0) = 2
3128 * StringUtils.indexOfIgnoreCase("aabaabaa", "AB", 0) = 1
3129 * StringUtils.indexOfIgnoreCase("aabaabaa", "B", 3) = 5
3130 * StringUtils.indexOfIgnoreCase("aabaabaa", "B", 9) = -1
3131 * StringUtils.indexOfIgnoreCase("aabaabaa", "B", -1) = 2
3132 * StringUtils.indexOfIgnoreCase("aabaabaa", "", 2) = 2
3133 * StringUtils.indexOfIgnoreCase("abc", "", 9) = -1
3134 * </pre>
3135 *
3136 * @param str the CharSequence to check, may be null
3137 * @param searchStr the CharSequence to find, may be null
3138 * @param startPos the start position, negative treated as zero
3139 * @return the first index of the search CharSequence (always ≥ startPos),
3140 * -1 if no match or {@code null} string input
3141 * @since 2.5
3142 * @since 3.0 Changed signature from indexOfIgnoreCase(String, String, int) to indexOfIgnoreCase(CharSequence, CharSequence, int)
3143 */
3144 public static int indexOfIgnoreCase(final CharSequence str, final CharSequence searchStr, int startPos) {
3145 if (str == null || searchStr == null) {
3146 return INDEX_NOT_FOUND;
3147 }
3148 if (startPos < 0) {
3149 startPos = 0;
3150 }
3151 final int endLimit = str.length() - searchStr.length() + 1;
3152 if (startPos > endLimit) {
3153 return INDEX_NOT_FOUND;
3154 }
3155 if (searchStr.length() == 0) {
3156 return startPos;
3157 }
3158 for (int i = startPos; i < endLimit; i++) {
3159 if (CharSequenceUtils.regionMatches(str, true, i, searchStr, 0, searchStr.length())) {
3160 return i;
3161 }
3162 }
3163 return INDEX_NOT_FOUND;
3164 }
3165
3166 /**
3167 * Checks if all of the CharSequences are empty (""), null or whitespace only.
3168 *
3169 * <p>Whitespace is defined by {@link Character#isWhitespace(char)}.</p>
3170 *
3171 * <pre>
3172 * StringUtils.isAllBlank(null) = true
3173 * StringUtils.isAllBlank(null, "foo") = false
3174 * StringUtils.isAllBlank(null, null) = true
3175 * StringUtils.isAllBlank("", "bar") = false
3176 * StringUtils.isAllBlank("bob", "") = false
3177 * StringUtils.isAllBlank(" bob ", null) = false
3178 * StringUtils.isAllBlank(" ", "bar") = false
3179 * StringUtils.isAllBlank("foo", "bar") = false
3180 * StringUtils.isAllBlank(new String[] {}) = true
3181 * </pre>
3182 *
3183 * @param css the CharSequences to check, may be null or empty
3184 * @return {@code true} if all of the CharSequences are empty or null or whitespace only
3185 * @since 3.6
3186 */
3187 public static boolean isAllBlank(final CharSequence... css) {
3188 if (ArrayUtils.isEmpty(css)) {
3189 return true;
3190 }
3191 for (final CharSequence cs : css) {
3192 if (isNotBlank(cs)) {
3193 return false;
3194 }
3195 }
3196 return true;
3197 }
3198
3199 /**
3200 * Checks if all of the CharSequences are empty ("") or null.
3201 *
3202 * <pre>
3203 * StringUtils.isAllEmpty(null) = true
3204 * StringUtils.isAllEmpty(null, "") = true
3205 * StringUtils.isAllEmpty(new String[] {}) = true
3206 * StringUtils.isAllEmpty(null, "foo") = false
3207 * StringUtils.isAllEmpty("", "bar") = false
3208 * StringUtils.isAllEmpty("bob", "") = false
3209 * StringUtils.isAllEmpty(" bob ", null) = false
3210 * StringUtils.isAllEmpty(" ", "bar") = false
3211 * StringUtils.isAllEmpty("foo", "bar") = false
3212 * </pre>
3213 *
3214 * @param css the CharSequences to check, may be null or empty
3215 * @return {@code true} if all of the CharSequences are empty or null
3216 * @since 3.6
3217 */
3218 public static boolean isAllEmpty(final CharSequence... css) {
3219 if (ArrayUtils.isEmpty(css)) {
3220 return true;
3221 }
3222 for (final CharSequence cs : css) {
3223 if (isNotEmpty(cs)) {
3224 return false;
3225 }
3226 }
3227 return true;
3228 }
3229
3230 /**
3231 * Checks if the CharSequence contains only lowercase characters.
3232 *
3233 * <p>{@code null} will return {@code false}.
3234 * An empty CharSequence (length()=0) will return {@code false}.</p>
3235 *
3236 * <pre>
3237 * StringUtils.isAllLowerCase(null) = false
3238 * StringUtils.isAllLowerCase("") = false
3239 * StringUtils.isAllLowerCase(" ") = false
3240 * StringUtils.isAllLowerCase("abc") = true
3241 * StringUtils.isAllLowerCase("abC") = false
3242 * StringUtils.isAllLowerCase("ab c") = false
3243 * StringUtils.isAllLowerCase("ab1c") = false
3244 * StringUtils.isAllLowerCase("ab/c") = false
3245 * </pre>
3246 *
3247 * @param cs the CharSequence to check, may be null
3248 * @return {@code true} if only contains lowercase characters, and is non-null
3249 * @since 2.5
3250 * @since 3.0 Changed signature from isAllLowerCase(String) to isAllLowerCase(CharSequence)
3251 */
3252 public static boolean isAllLowerCase(final CharSequence cs) {
3253 if (isEmpty(cs)) {
3254 return false;
3255 }
3256 final int sz = cs.length();
3257 for (int i = 0; i < sz; i++) {
3258 if (!Character.isLowerCase(cs.charAt(i))) {
3259 return false;
3260 }
3261 }
3262 return true;
3263 }
3264
3265 /**
3266 * Checks if the CharSequence contains only uppercase characters.
3267 *
3268 * <p>{@code null} will return {@code false}.
3269 * An empty String (length()=0) will return {@code false}.</p>
3270 *
3271 * <pre>
3272 * StringUtils.isAllUpperCase(null) = false
3273 * StringUtils.isAllUpperCase("") = false
3274 * StringUtils.isAllUpperCase(" ") = false
3275 * StringUtils.isAllUpperCase("ABC") = true
3276 * StringUtils.isAllUpperCase("aBC") = false
3277 * StringUtils.isAllUpperCase("A C") = false
3278 * StringUtils.isAllUpperCase("A1C") = false
3279 * StringUtils.isAllUpperCase("A/C") = false
3280 * </pre>
3281 *
3282 * @param cs the CharSequence to check, may be null
3283 * @return {@code true} if only contains uppercase characters, and is non-null
3284 * @since 2.5
3285 * @since 3.0 Changed signature from isAllUpperCase(String) to isAllUpperCase(CharSequence)
3286 */
3287 public static boolean isAllUpperCase(final CharSequence cs) {
3288 if (isEmpty(cs)) {
3289 return false;
3290 }
3291 final int sz = cs.length();
3292 for (int i = 0; i < sz; i++) {
3293 if (!Character.isUpperCase(cs.charAt(i))) {
3294 return false;
3295 }
3296 }
3297 return true;
3298 }
3299
3300 /**
3301 * Checks if the CharSequence contains only Unicode letters.
3302 *
3303 * <p>{@code null} will return {@code false}.
3304 * An empty CharSequence (length()=0) will return {@code false}.</p>
3305 *
3306 * <pre>
3307 * StringUtils.isAlpha(null) = false
3308 * StringUtils.isAlpha("") = false
3309 * StringUtils.isAlpha(" ") = false
3310 * StringUtils.isAlpha("abc") = true
3311 * StringUtils.isAlpha("ab2c") = false
3312 * StringUtils.isAlpha("ab-c") = false
3313 * </pre>
3314 *
3315 * @param cs the CharSequence to check, may be null
3316 * @return {@code true} if only contains letters, and is non-null
3317 * @since 3.0 Changed signature from isAlpha(String) to isAlpha(CharSequence)
3318 * @since 3.0 Changed "" to return false and not true
3319 */
3320 public static boolean isAlpha(final CharSequence cs) {
3321 if (isEmpty(cs)) {
3322 return false;
3323 }
3324 final int sz = cs.length();
3325 for (int i = 0; i < sz; i++) {
3326 if (!Character.isLetter(cs.charAt(i))) {
3327 return false;
3328 }
3329 }
3330 return true;
3331 }
3332
3333 /**
3334 * Checks if the CharSequence contains only Unicode letters or digits.
3335 *
3336 * <p>{@code null} will return {@code false}.
3337 * An empty CharSequence (length()=0) will return {@code false}.</p>
3338 *
3339 * <pre>
3340 * StringUtils.isAlphanumeric(null) = false
3341 * StringUtils.isAlphanumeric("") = false
3342 * StringUtils.isAlphanumeric(" ") = false
3343 * StringUtils.isAlphanumeric("abc") = true
3344 * StringUtils.isAlphanumeric("ab c") = false
3345 * StringUtils.isAlphanumeric("ab2c") = true
3346 * StringUtils.isAlphanumeric("ab-c") = false
3347 * </pre>
3348 *
3349 * @param cs the CharSequence to check, may be null
3350 * @return {@code true} if only contains letters or digits,
3351 * and is non-null
3352 * @since 3.0 Changed signature from isAlphanumeric(String) to isAlphanumeric(CharSequence)
3353 * @since 3.0 Changed "" to return false and not true
3354 */
3355 public static boolean isAlphanumeric(final CharSequence cs) {
3356 if (isEmpty(cs)) {
3357 return false;
3358 }
3359 final int sz = cs.length();
3360 for (int i = 0; i < sz; i++) {
3361 if (!Character.isLetterOrDigit(cs.charAt(i))) {
3362 return false;
3363 }
3364 }
3365 return true;
3366 }
3367
3368 /**
3369 * Checks if the CharSequence contains only Unicode letters, digits
3370 * or space ({@code ' '}).
3371 *
3372 * <p>{@code null} will return {@code false}.
3373 * An empty CharSequence (length()=0) will return {@code true}.</p>
3374 *
3375 * <pre>
3376 * StringUtils.isAlphanumericSpace(null) = false
3377 * StringUtils.isAlphanumericSpace("") = true
3378 * StringUtils.isAlphanumericSpace(" ") = true
3379 * StringUtils.isAlphanumericSpace("abc") = true
3380 * StringUtils.isAlphanumericSpace("ab c") = true
3381 * StringUtils.isAlphanumericSpace("ab2c") = true
3382 * StringUtils.isAlphanumericSpace("ab-c") = false
3383 * </pre>
3384 *
3385 * @param cs the CharSequence to check, may be null
3386 * @return {@code true} if only contains letters, digits or space,
3387 * and is non-null
3388 * @since 3.0 Changed signature from isAlphanumericSpace(String) to isAlphanumericSpace(CharSequence)
3389 */
3390 public static boolean isAlphanumericSpace(final CharSequence cs) {
3391 if (cs == null) {
3392 return false;
3393 }
3394 final int sz = cs.length();
3395 for (int i = 0; i < sz; i++) {
3396 final char nowChar = cs.charAt(i);
3397 if (nowChar != ' ' && !Character.isLetterOrDigit(nowChar) ) {
3398 return false;
3399 }
3400 }
3401 return true;
3402 }
3403
3404 /**
3405 * Checks if the CharSequence contains only Unicode letters and
3406 * space (' ').
3407 *
3408 * <p>{@code null} will return {@code false}
3409 * An empty CharSequence (length()=0) will return {@code true}.</p>
3410 *
3411 * <pre>
3412 * StringUtils.isAlphaSpace(null) = false
3413 * StringUtils.isAlphaSpace("") = true
3414 * StringUtils.isAlphaSpace(" ") = true
3415 * StringUtils.isAlphaSpace("abc") = true
3416 * StringUtils.isAlphaSpace("ab c") = true
3417 * StringUtils.isAlphaSpace("ab2c") = false
3418 * StringUtils.isAlphaSpace("ab-c") = false
3419 * </pre>
3420 *
3421 * @param cs the CharSequence to check, may be null
3422 * @return {@code true} if only contains letters and space,
3423 * and is non-null
3424 * @since 3.0 Changed signature from isAlphaSpace(String) to isAlphaSpace(CharSequence)
3425 */
3426 public static boolean isAlphaSpace(final CharSequence cs) {
3427 if (cs == null) {
3428 return false;
3429 }
3430 final int sz = cs.length();
3431 for (int i = 0; i < sz; i++) {
3432 final char nowChar = cs.charAt(i);
3433 if (nowChar != ' ' && !Character.isLetter(nowChar)) {
3434 return false;
3435 }
3436 }
3437 return true;
3438 }
3439
3440 /**
3441 * Checks if any of the CharSequences are empty ("") or null or whitespace only.
3442 *
3443 * <p>Whitespace is defined by {@link Character#isWhitespace(char)}.</p>
3444 *
3445 * <pre>
3446 * StringUtils.isAnyBlank((String) null) = true
3447 * StringUtils.isAnyBlank((String[]) null) = false
3448 * StringUtils.isAnyBlank(null, "foo") = true
3449 * StringUtils.isAnyBlank(null, null) = true
3450 * StringUtils.isAnyBlank("", "bar") = true
3451 * StringUtils.isAnyBlank("bob", "") = true
3452 * StringUtils.isAnyBlank(" bob ", null) = true
3453 * StringUtils.isAnyBlank(" ", "bar") = true
3454 * StringUtils.isAnyBlank(new String[] {}) = false
3455 * StringUtils.isAnyBlank(new String[]{""}) = true
3456 * StringUtils.isAnyBlank("foo", "bar") = false
3457 * </pre>
3458 *
3459 * @param css the CharSequences to check, may be null or empty
3460 * @return {@code true} if any of the CharSequences are empty or null or whitespace only
3461 * @since 3.2
3462 */
3463 public static boolean isAnyBlank(final CharSequence... css) {
3464 if (ArrayUtils.isEmpty(css)) {
3465 return false;
3466 }
3467 for (final CharSequence cs : css) {
3468 if (isBlank(cs)) {
3469 return true;
3470 }
3471 }
3472 return false;
3473 }
3474
3475 /**
3476 * Checks if any of the CharSequences are empty ("") or null.
3477 *
3478 * <pre>
3479 * StringUtils.isAnyEmpty((String) null) = true
3480 * StringUtils.isAnyEmpty((String[]) null) = false
3481 * StringUtils.isAnyEmpty(null, "foo") = true
3482 * StringUtils.isAnyEmpty("", "bar") = true
3483 * StringUtils.isAnyEmpty("bob", "") = true
3484 * StringUtils.isAnyEmpty(" bob ", null) = true
3485 * StringUtils.isAnyEmpty(" ", "bar") = false
3486 * StringUtils.isAnyEmpty("foo", "bar") = false
3487 * StringUtils.isAnyEmpty(new String[]{}) = false
3488 * StringUtils.isAnyEmpty(new String[]{""}) = true
3489 * </pre>
3490 *
3491 * @param css the CharSequences to check, may be null or empty
3492 * @return {@code true} if any of the CharSequences are empty or null
3493 * @since 3.2
3494 */
3495 public static boolean isAnyEmpty(final CharSequence... css) {
3496 if (ArrayUtils.isEmpty(css)) {
3497 return false;
3498 }
3499 for (final CharSequence cs : css) {
3500 if (isEmpty(cs)) {
3501 return true;
3502 }
3503 }
3504 return false;
3505 }
3506
3507 /**
3508 * Checks if the CharSequence contains only ASCII printable characters.
3509 *
3510 * <p>{@code null} will return {@code false}.
3511 * An empty CharSequence (length()=0) will return {@code true}.</p>
3512 *
3513 * <pre>
3514 * StringUtils.isAsciiPrintable(null) = false
3515 * StringUtils.isAsciiPrintable("") = true
3516 * StringUtils.isAsciiPrintable(" ") = true
3517 * StringUtils.isAsciiPrintable("Ceki") = true
3518 * StringUtils.isAsciiPrintable("ab2c") = true
3519 * StringUtils.isAsciiPrintable("!ab-c~") = true
3520 * StringUtils.isAsciiPrintable("\u0020") = true
3521 * StringUtils.isAsciiPrintable("\u0021") = true
3522 * StringUtils.isAsciiPrintable("\u007e") = true
3523 * StringUtils.isAsciiPrintable("\u007f") = false
3524 * StringUtils.isAsciiPrintable("Ceki G\u00fclc\u00fc") = false
3525 * </pre>
3526 *
3527 * @param cs the CharSequence to check, may be null
3528 * @return {@code true} if every character is in the range
3529 * 32 through 126
3530 * @since 2.1
3531 * @since 3.0 Changed signature from isAsciiPrintable(String) to isAsciiPrintable(CharSequence)
3532 */
3533 public static boolean isAsciiPrintable(final CharSequence cs) {
3534 if (cs == null) {
3535 return false;
3536 }
3537 final int sz = cs.length();
3538 for (int i = 0; i < sz; i++) {
3539 if (!CharUtils.isAsciiPrintable(cs.charAt(i))) {
3540 return false;
3541 }
3542 }
3543 return true;
3544 }
3545
3546 /**
3547 * Checks if a CharSequence is empty (""), null or whitespace only.
3548 *
3549 * <p>Whitespace is defined by {@link Character#isWhitespace(char)}.</p>
3550 *
3551 * <pre>
3552 * StringUtils.isBlank(null) = true
3553 * StringUtils.isBlank("") = true
3554 * StringUtils.isBlank(" ") = true
3555 * StringUtils.isBlank("bob") = false
3556 * StringUtils.isBlank(" bob ") = false
3557 * </pre>
3558 *
3559 * @param cs the CharSequence to check, may be null
3560 * @return {@code true} if the CharSequence is null, empty or whitespace only
3561 * @since 2.0
3562 * @since 3.0 Changed signature from isBlank(String) to isBlank(CharSequence)
3563 */
3564 public static boolean isBlank(final CharSequence cs) {
3565 final int strLen = length(cs);
3566 if (strLen == 0) {
3567 return true;
3568 }
3569 for (int i = 0; i < strLen; i++) {
3570 if (!Character.isWhitespace(cs.charAt(i))) {
3571 return false;
3572 }
3573 }
3574 return true;
3575 }
3576
3577 /**
3578 * Checks if a CharSequence is empty ("") or null.
3579 *
3580 * <pre>
3581 * StringUtils.isEmpty(null) = true
3582 * StringUtils.isEmpty("") = true
3583 * StringUtils.isEmpty(" ") = false
3584 * StringUtils.isEmpty("bob") = false
3585 * StringUtils.isEmpty(" bob ") = false
3586 * </pre>
3587 *
3588 * <p>NOTE: This method changed in Lang version 2.0.
3589 * It no longer trims the CharSequence.
3590 * That functionality is available in isBlank().</p>
3591 *
3592 * @param cs the CharSequence to check, may be null
3593 * @return {@code true} if the CharSequence is empty or null
3594 * @since 3.0 Changed signature from isEmpty(String) to isEmpty(CharSequence)
3595 */
3596 public static boolean isEmpty(final CharSequence cs) {
3597 return cs == null || cs.length() == 0;
3598 }
3599
3600 /**
3601 * Checks if the CharSequence contains mixed casing of both uppercase and lowercase characters.
3602 *
3603 * <p>{@code null} will return {@code false}. An empty CharSequence ({@code length()=0}) will return
3604 * {@code false}.</p>
3605 *
3606 * <pre>
3607 * StringUtils.isMixedCase(null) = false
3608 * StringUtils.isMixedCase("") = false
3609 * StringUtils.isMixedCase(" ") = false
3610 * StringUtils.isMixedCase("ABC") = false
3611 * StringUtils.isMixedCase("abc") = false
3612 * StringUtils.isMixedCase("aBc") = true
3613 * StringUtils.isMixedCase("A c") = true
3614 * StringUtils.isMixedCase("A1c") = true
3615 * StringUtils.isMixedCase("a/C") = true
3616 * StringUtils.isMixedCase("aC\t") = true
3617 * </pre>
3618 *
3619 * @param cs the CharSequence to check, may be null
3620 * @return {@code true} if the CharSequence contains both uppercase and lowercase characters
3621 * @since 3.5
3622 */
3623 public static boolean isMixedCase(final CharSequence cs) {
3624 if (isEmpty(cs) || cs.length() == 1) {
3625 return false;
3626 }
3627 boolean containsUppercase = false;
3628 boolean containsLowercase = false;
3629 final int sz = cs.length();
3630 for (int i = 0; i < sz; i++) {
3631 if (containsUppercase && containsLowercase) {
3632 return true;
3633 }
3634 if (Character.isUpperCase(cs.charAt(i))) {
3635 containsUppercase = true;
3636 } else if (Character.isLowerCase(cs.charAt(i))) {
3637 containsLowercase = true;
3638 }
3639 }
3640 return containsUppercase && containsLowercase;
3641 }
3642
3643 /**
3644 * Checks if none of the CharSequences are empty (""), null or whitespace only.
3645 *
3646 * <p>Whitespace is defined by {@link Character#isWhitespace(char)}.</p>
3647 *
3648 * <pre>
3649 * StringUtils.isNoneBlank((String) null) = false
3650 * StringUtils.isNoneBlank((String[]) null) = true
3651 * StringUtils.isNoneBlank(null, "foo") = false
3652 * StringUtils.isNoneBlank(null, null) = false
3653 * StringUtils.isNoneBlank("", "bar") = false
3654 * StringUtils.isNoneBlank("bob", "") = false
3655 * StringUtils.isNoneBlank(" bob ", null) = false
3656 * StringUtils.isNoneBlank(" ", "bar") = false
3657 * StringUtils.isNoneBlank(new String[] {}) = true
3658 * StringUtils.isNoneBlank(new String[]{""}) = false
3659 * StringUtils.isNoneBlank("foo", "bar") = true
3660 * </pre>
3661 *
3662 * @param css the CharSequences to check, may be null or empty
3663 * @return {@code true} if none of the CharSequences are empty or null or whitespace only
3664 * @since 3.2
3665 */
3666 public static boolean isNoneBlank(final CharSequence... css) {
3667 return !isAnyBlank(css);
3668 }
3669
3670 /**
3671 * Checks if none of the CharSequences are empty ("") or null.
3672 *
3673 * <pre>
3674 * StringUtils.isNoneEmpty((String) null) = false
3675 * StringUtils.isNoneEmpty((String[]) null) = true
3676 * StringUtils.isNoneEmpty(null, "foo") = false
3677 * StringUtils.isNoneEmpty("", "bar") = false
3678 * StringUtils.isNoneEmpty("bob", "") = false
3679 * StringUtils.isNoneEmpty(" bob ", null) = false
3680 * StringUtils.isNoneEmpty(new String[] {}) = true
3681 * StringUtils.isNoneEmpty(new String[]{""}) = false
3682 * StringUtils.isNoneEmpty(" ", "bar") = true
3683 * StringUtils.isNoneEmpty("foo", "bar") = true
3684 * </pre>
3685 *
3686 * @param css the CharSequences to check, may be null or empty
3687 * @return {@code true} if none of the CharSequences are empty or null
3688 * @since 3.2
3689 */
3690 public static boolean isNoneEmpty(final CharSequence... css) {
3691 return !isAnyEmpty(css);
3692 }
3693
3694 /**
3695 * Checks if a CharSequence is not empty (""), not null and not whitespace only.
3696 *
3697 * <p>Whitespace is defined by {@link Character#isWhitespace(char)}.</p>
3698 *
3699 * <pre>
3700 * StringUtils.isNotBlank(null) = false
3701 * StringUtils.isNotBlank("") = false
3702 * StringUtils.isNotBlank(" ") = false
3703 * StringUtils.isNotBlank("bob") = true
3704 * StringUtils.isNotBlank(" bob ") = true
3705 * </pre>
3706 *
3707 * @param cs the CharSequence to check, may be null
3708 * @return {@code true} if the CharSequence is
3709 * not empty and not null and not whitespace only
3710 * @since 2.0
3711 * @since 3.0 Changed signature from isNotBlank(String) to isNotBlank(CharSequence)
3712 */
3713 public static boolean isNotBlank(final CharSequence cs) {
3714 return !isBlank(cs);
3715 }
3716
3717 /**
3718 * Checks if a CharSequence is not empty ("") and not null.
3719 *
3720 * <pre>
3721 * StringUtils.isNotEmpty(null) = false
3722 * StringUtils.isNotEmpty("") = false
3723 * StringUtils.isNotEmpty(" ") = true
3724 * StringUtils.isNotEmpty("bob") = true
3725 * StringUtils.isNotEmpty(" bob ") = true
3726 * </pre>
3727 *
3728 * @param cs the CharSequence to check, may be null
3729 * @return {@code true} if the CharSequence is not empty and not null
3730 * @since 3.0 Changed signature from isNotEmpty(String) to isNotEmpty(CharSequence)
3731 */
3732 public static boolean isNotEmpty(final CharSequence cs) {
3733 return !isEmpty(cs);
3734 }
3735
3736 /**
3737 * Checks if the CharSequence contains only Unicode digits.
3738 * A decimal point is not a Unicode digit and returns false.
3739 *
3740 * <p>{@code null} will return {@code false}.
3741 * An empty CharSequence (length()=0) will return {@code false}.</p>
3742 *
3743 * <p>Note that the method does not allow for a leading sign, either positive or negative.
3744 * Also, if a String passes the numeric test, it may still generate a NumberFormatException
3745 * when parsed by Integer.parseInt or Long.parseLong, e.g. if the value is outside the range
3746 * for int or long respectively.</p>
3747 *
3748 * <pre>
3749 * StringUtils.isNumeric(null) = false
3750 * StringUtils.isNumeric("") = false
3751 * StringUtils.isNumeric(" ") = false
3752 * StringUtils.isNumeric("123") = true
3753 * StringUtils.isNumeric("\u0967\u0968\u0969") = true
3754 * StringUtils.isNumeric("12 3") = false
3755 * StringUtils.isNumeric("ab2c") = false
3756 * StringUtils.isNumeric("12-3") = false
3757 * StringUtils.isNumeric("12.3") = false
3758 * StringUtils.isNumeric("-123") = false
3759 * StringUtils.isNumeric("+123") = false
3760 * </pre>
3761 *
3762 * @param cs the CharSequence to check, may be null
3763 * @return {@code true} if only contains digits, and is non-null
3764 * @since 3.0 Changed signature from isNumeric(String) to isNumeric(CharSequence)
3765 * @since 3.0 Changed "" to return false and not true
3766 */
3767 public static boolean isNumeric(final CharSequence cs) {
3768 if (isEmpty(cs)) {
3769 return false;
3770 }
3771 final int sz = cs.length();
3772 for (int i = 0; i < sz; i++) {
3773 if (!Character.isDigit(cs.charAt(i))) {
3774 return false;
3775 }
3776 }
3777 return true;
3778 }
3779
3780 /**
3781 * Checks if the CharSequence contains only Unicode digits or space
3782 * ({@code ' '}).
3783 * A decimal point is not a Unicode digit and returns false.
3784 *
3785 * <p>{@code null} will return {@code false}.
3786 * An empty CharSequence (length()=0) will return {@code true}.</p>
3787 *
3788 * <pre>
3789 * StringUtils.isNumericSpace(null) = false
3790 * StringUtils.isNumericSpace("") = true
3791 * StringUtils.isNumericSpace(" ") = true
3792 * StringUtils.isNumericSpace("123") = true
3793 * StringUtils.isNumericSpace("12 3") = true
3794 * StringUtils.isNumericSpace("\u0967\u0968\u0969") = true
3795 * StringUtils.isNumericSpace("\u0967\u0968 \u0969") = true
3796 * StringUtils.isNumericSpace("ab2c") = false
3797 * StringUtils.isNumericSpace("12-3") = false
3798 * StringUtils.isNumericSpace("12.3") = false
3799 * </pre>
3800 *
3801 * @param cs the CharSequence to check, may be null
3802 * @return {@code true} if only contains digits or space,
3803 * and is non-null
3804 * @since 3.0 Changed signature from isNumericSpace(String) to isNumericSpace(CharSequence)
3805 */
3806 public static boolean isNumericSpace(final CharSequence cs) {
3807 if (cs == null) {
3808 return false;
3809 }
3810 final int sz = cs.length();
3811 for (int i = 0; i < sz; i++) {
3812 final char nowChar = cs.charAt(i);
3813 if (nowChar != ' ' && !Character.isDigit(nowChar)) {
3814 return false;
3815 }
3816 }
3817 return true;
3818 }
3819
3820 /**
3821 * Checks if the CharSequence contains only whitespace.
3822 *
3823 * <p>Whitespace is defined by {@link Character#isWhitespace(char)}.</p>
3824 *
3825 * <p>{@code null} will return {@code false}.
3826 * An empty CharSequence (length()=0) will return {@code true}.</p>
3827 *
3828 * <pre>
3829 * StringUtils.isWhitespace(null) = false
3830 * StringUtils.isWhitespace("") = true
3831 * StringUtils.isWhitespace(" ") = true
3832 * StringUtils.isWhitespace("abc") = false
3833 * StringUtils.isWhitespace("ab2c") = false
3834 * StringUtils.isWhitespace("ab-c") = false
3835 * </pre>
3836 *
3837 * @param cs the CharSequence to check, may be null
3838 * @return {@code true} if only contains whitespace, and is non-null
3839 * @since 2.0
3840 * @since 3.0 Changed signature from isWhitespace(String) to isWhitespace(CharSequence)
3841 */
3842 public static boolean isWhitespace(final CharSequence cs) {
3843 if (cs == null) {
3844 return false;
3845 }
3846 final int sz = cs.length();
3847 for (int i = 0; i < sz; i++) {
3848 if (!Character.isWhitespace(cs.charAt(i))) {
3849 return false;
3850 }
3851 }
3852 return true;
3853 }
3854
3855 /**
3856 * Joins the elements of the provided array into a single String containing the provided list of elements.
3857 *
3858 * <p>
3859 * No delimiter is added before or after the list. Null objects or empty strings within the array are represented
3860 * by empty strings.
3861 * </p>
3862 *
3863 * <pre>
3864 * StringUtils.join(null, *) = null
3865 * StringUtils.join([], *) = ""
3866 * StringUtils.join([null], *) = ""
3867 * StringUtils.join([false, false], ';') = "false;false"
3868 * </pre>
3869 *
3870 * @param array
3871 * the array of values to join together, may be null
3872 * @param delimiter
3873 * the separator character to use
3874 * @return the joined String, {@code null} if null array input
3875 * @since 3.12.0
3876 */
3877 public static String join(final boolean[] array, final char delimiter) {
3878 if (array == null) {
3879 return null;
3880 }
3881 return join(array, delimiter, 0, array.length);
3882 }
3883
3884 /**
3885 * Joins the elements of the provided array into a single String containing the provided list of elements.
3886 *
3887 * <p>
3888 * No delimiter is added before or after the list. Null objects or empty strings within the array are represented
3889 * by empty strings.
3890 * </p>
3891 *
3892 * <pre>
3893 * StringUtils.join(null, *) = null
3894 * StringUtils.join([], *) = ""
3895 * StringUtils.join([null], *) = ""
3896 * StringUtils.join([true, false, true], ';') = "true;false;true"
3897 * </pre>
3898 *
3899 * @param array
3900 * the array of values to join together, may be null
3901 * @param delimiter
3902 * the separator character to use
3903 * @param startIndex
3904 * the first index to start joining from. It is an error to pass in a start index past the end of the
3905 * array
3906 * @param endIndex
3907 * the index to stop joining from (exclusive). It is an error to pass in an end index past the end of
3908 * the array
3909 * @return the joined String, {@code null} if null array input
3910 * @since 3.12.0
3911 */
3912 public static String join(final boolean[] array, final char delimiter, final int startIndex, final int endIndex) {
3913 if (array == null) {
3914 return null;
3915 }
3916 if (endIndex - startIndex <= 0) {
3917 return EMPTY;
3918 }
3919 final StringBuilder stringBuilder = new StringBuilder(array.length * 5 + array.length - 1);
3920 for (int i = startIndex; i < endIndex; i++) {
3921 stringBuilder
3922 .append(array[i])
3923 .append(delimiter);
3924 }
3925 return stringBuilder.substring(0, stringBuilder.length() - 1);
3926 }
3927
3928 /**
3929 * Joins the elements of the provided array into a single String containing the provided list of elements.
3930 *
3931 * <p>
3932 * No delimiter is added before or after the list. Null objects or empty strings within the array are represented
3933 * by empty strings.
3934 * </p>
3935 *
3936 * <pre>
3937 * StringUtils.join(null, *) = null
3938 * StringUtils.join([], *) = ""
3939 * StringUtils.join([null], *) = ""
3940 * StringUtils.join([1, 2, 3], ';') = "1;2;3"
3941 * StringUtils.join([1, 2, 3], null) = "123"
3942 * </pre>
3943 *
3944 * @param array
3945 * the array of values to join together, may be null
3946 * @param delimiter
3947 * the separator character to use
3948 * @return the joined String, {@code null} if null array input
3949 * @since 3.2
3950 */
3951 public static String join(final byte[] array, final char delimiter) {
3952 if (array == null) {
3953 return null;
3954 }
3955 return join(array, delimiter, 0, array.length);
3956 }
3957
3958 /**
3959 * Joins the elements of the provided array into a single String containing the provided list of elements.
3960 *
3961 * <p>
3962 * No delimiter is added before or after the list. Null objects or empty strings within the array are represented
3963 * by empty strings.
3964 * </p>
3965 *
3966 * <pre>
3967 * StringUtils.join(null, *) = null
3968 * StringUtils.join([], *) = ""
3969 * StringUtils.join([null], *) = ""
3970 * StringUtils.join([1, 2, 3], ';') = "1;2;3"
3971 * StringUtils.join([1, 2, 3], null) = "123"
3972 * </pre>
3973 *
3974 * @param array
3975 * the array of values to join together, may be null
3976 * @param delimiter
3977 * the separator character to use
3978 * @param startIndex
3979 * the first index to start joining from. It is an error to pass in a start index past the end of the
3980 * array
3981 * @param endIndex
3982 * the index to stop joining from (exclusive). It is an error to pass in an end index past the end of
3983 * the array
3984 * @return the joined String, {@code null} if null array input
3985 * @since 3.2
3986 */
3987 public static String join(final byte[] array, final char delimiter, final int startIndex, final int endIndex) {
3988 if (array == null) {
3989 return null;
3990 }
3991 if (endIndex - startIndex <= 0) {
3992 return EMPTY;
3993 }
3994 final StringBuilder stringBuilder = new StringBuilder();
3995 for (int i = startIndex; i < endIndex; i++) {
3996 stringBuilder
3997 .append(array[i])
3998 .append(delimiter);
3999 }
4000 return stringBuilder.substring(0, stringBuilder.length() - 1);
4001 }
4002
4003 /**
4004 * Joins the elements of the provided array into a single String containing the provided list of elements.
4005 *
4006 * <p>
4007 * No delimiter is added before or after the list. Null objects or empty strings within the array are represented
4008 * by empty strings.
4009 * </p>
4010 *
4011 * <pre>
4012 * StringUtils.join(null, *) = null
4013 * StringUtils.join([], *) = ""
4014 * StringUtils.join([null], *) = ""
4015 * StringUtils.join([1, 2, 3], ';') = "1;2;3"
4016 * StringUtils.join([1, 2, 3], null) = "123"
4017 * </pre>
4018 *
4019 * @param array
4020 * the array of values to join together, may be null
4021 * @param delimiter
4022 * the separator character to use
4023 * @return the joined String, {@code null} if null array input
4024 * @since 3.2
4025 */
4026 public static String join(final char[] array, final char delimiter) {
4027 if (array == null) {
4028 return null;
4029 }
4030 return join(array, delimiter, 0, array.length);
4031 }
4032
4033 /**
4034 * Joins the elements of the provided array into a single String containing the provided list of elements.
4035 *
4036 * <p>
4037 * No delimiter is added before or after the list. Null objects or empty strings within the array are represented
4038 * by empty strings.
4039 * </p>
4040 *
4041 * <pre>
4042 * StringUtils.join(null, *) = null
4043 * StringUtils.join([], *) = ""
4044 * StringUtils.join([null], *) = ""
4045 * StringUtils.join([1, 2, 3], ';') = "1;2;3"
4046 * StringUtils.join([1, 2, 3], null) = "123"
4047 * </pre>
4048 *
4049 * @param array
4050 * the array of values to join together, may be null
4051 * @param delimiter
4052 * the separator character to use
4053 * @param startIndex
4054 * the first index to start joining from. It is an error to pass in a start index past the end of the
4055 * array
4056 * @param endIndex
4057 * the index to stop joining from (exclusive). It is an error to pass in an end index past the end of
4058 * the array
4059 * @return the joined String, {@code null} if null array input
4060 * @since 3.2
4061 */
4062 public static String join(final char[] array, final char delimiter, final int startIndex, final int endIndex) {
4063 if (array == null) {
4064 return null;
4065 }
4066 if (endIndex - startIndex <= 0) {
4067 return EMPTY;
4068 }
4069 final StringBuilder stringBuilder = new StringBuilder(array.length * 2 - 1);
4070 for (int i = startIndex; i < endIndex; i++) {
4071 stringBuilder
4072 .append(array[i])
4073 .append(delimiter);
4074 }
4075 return stringBuilder.substring(0, stringBuilder.length() - 1);
4076 }
4077
4078 /**
4079 * Joins the elements of the provided array into a single String containing the provided list of elements.
4080 *
4081 * <p>
4082 * No delimiter is added before or after the list. Null objects or empty strings within the array are represented
4083 * by empty strings.
4084 * </p>
4085 *
4086 * <pre>
4087 * StringUtils.join(null, *) = null
4088 * StringUtils.join([], *) = ""
4089 * StringUtils.join([null], *) = ""
4090 * StringUtils.join([1, 2, 3], ';') = "1;2;3"
4091 * StringUtils.join([1, 2, 3], null) = "123"
4092 * </pre>
4093 *
4094 * @param array
4095 * the array of values to join together, may be null
4096 * @param delimiter
4097 * the separator character to use
4098 * @return the joined String, {@code null} if null array input
4099 * @since 3.2
4100 */
4101 public static String join(final double[] array, final char delimiter) {
4102 if (array == null) {
4103 return null;
4104 }
4105 return join(array, delimiter, 0, array.length);
4106 }
4107
4108 /**
4109 * Joins the elements of the provided array into a single String containing the provided list of elements.
4110 *
4111 * <p>
4112 * No delimiter is added before or after the list. Null objects or empty strings within the array are represented
4113 * by empty strings.
4114 * </p>
4115 *
4116 * <pre>
4117 * StringUtils.join(null, *) = null
4118 * StringUtils.join([], *) = ""
4119 * StringUtils.join([null], *) = ""
4120 * StringUtils.join([1, 2, 3], ';') = "1;2;3"
4121 * StringUtils.join([1, 2, 3], null) = "123"
4122 * </pre>
4123 *
4124 * @param array
4125 * the array of values to join together, may be null
4126 * @param delimiter
4127 * the separator character to use
4128 * @param startIndex
4129 * the first index to start joining from. It is an error to pass in a start index past the end of the
4130 * array
4131 * @param endIndex
4132 * the index to stop joining from (exclusive). It is an error to pass in an end index past the end of
4133 * the array
4134 * @return the joined String, {@code null} if null array input
4135 * @since 3.2
4136 */
4137 public static String join(final double[] array, final char delimiter, final int startIndex, final int endIndex) {
4138 if (array == null) {
4139 return null;
4140 }
4141 if (endIndex - startIndex <= 0) {
4142 return EMPTY;
4143 }
4144 final StringBuilder stringBuilder = new StringBuilder();
4145 for (int i = startIndex; i < endIndex; i++) {
4146 stringBuilder
4147 .append(array[i])
4148 .append(delimiter);
4149 }
4150 return stringBuilder.substring(0, stringBuilder.length() - 1);
4151 }
4152
4153 /**
4154 * Joins the elements of the provided array into a single String containing the provided list of elements.
4155 *
4156 * <p>
4157 * No delimiter is added before or after the list. Null objects or empty strings within the array are represented
4158 * by empty strings.
4159 * </p>
4160 *
4161 * <pre>
4162 * StringUtils.join(null, *) = null
4163 * StringUtils.join([], *) = ""
4164 * StringUtils.join([null], *) = ""
4165 * StringUtils.join([1, 2, 3], ';') = "1;2;3"
4166 * StringUtils.join([1, 2, 3], null) = "123"
4167 * </pre>
4168 *
4169 * @param array
4170 * the array of values to join together, may be null
4171 * @param delimiter
4172 * the separator character to use
4173 * @return the joined String, {@code null} if null array input
4174 * @since 3.2
4175 */
4176 public static String join(final float[] array, final char delimiter) {
4177 if (array == null) {
4178 return null;
4179 }
4180 return join(array, delimiter, 0, array.length);
4181 }
4182
4183 /**
4184 * Joins the elements of the provided array into a single String containing the provided list of elements.
4185 *
4186 * <p>
4187 * No delimiter is added before or after the list. Null objects or empty strings within the array are represented
4188 * by empty strings.
4189 * </p>
4190 *
4191 * <pre>
4192 * StringUtils.join(null, *) = null
4193 * StringUtils.join([], *) = ""
4194 * StringUtils.join([null], *) = ""
4195 * StringUtils.join([1, 2, 3], ';') = "1;2;3"
4196 * StringUtils.join([1, 2, 3], null) = "123"
4197 * </pre>
4198 *
4199 * @param array
4200 * the array of values to join together, may be null
4201 * @param delimiter
4202 * the separator character to use
4203 * @param startIndex
4204 * the first index to start joining from. It is an error to pass in a start index past the end of the
4205 * array
4206 * @param endIndex
4207 * the index to stop joining from (exclusive). It is an error to pass in an end index past the end of
4208 * the array
4209 * @return the joined String, {@code null} if null array input
4210 * @since 3.2
4211 */
4212 public static String join(final float[] array, final char delimiter, final int startIndex, final int endIndex) {
4213 if (array == null) {
4214 return null;
4215 }
4216 if (endIndex - startIndex <= 0) {
4217 return EMPTY;
4218 }
4219 final StringBuilder stringBuilder = new StringBuilder();
4220 for (int i = startIndex; i < endIndex; i++) {
4221 stringBuilder
4222 .append(array[i])
4223 .append(delimiter);
4224 }
4225 return stringBuilder.substring(0, stringBuilder.length() - 1);
4226 }
4227
4228 /**
4229 * Joins the elements of the provided array into a single String containing the provided list of elements.
4230 *
4231 * <p>
4232 * No delimiter is added before or after the list. Null objects or empty strings within the array are represented
4233 * by empty strings.
4234 * </p>
4235 *
4236 * <pre>
4237 * StringUtils.join(null, *) = null
4238 * StringUtils.join([], *) = ""
4239 * StringUtils.join([null], *) = ""
4240 * StringUtils.join([1, 2, 3], ';') = "1;2;3"
4241 * StringUtils.join([1, 2, 3], null) = "123"
4242 * </pre>
4243 *
4244 * @param array
4245 * the array of values to join together, may be null
4246 * @param separator
4247 * the separator character to use
4248 * @return the joined String, {@code null} if null array input
4249 * @since 3.2
4250 */
4251 public static String join(final int[] array, final char separator) {
4252 if (array == null) {
4253 return null;
4254 }
4255 return join(array, separator, 0, array.length);
4256 }
4257
4258 /**
4259 * Joins the elements of the provided array into a single String containing the provided list of elements.
4260 *
4261 * <p>
4262 * No delimiter is added before or after the list. Null objects or empty strings within the array are represented
4263 * by empty strings.
4264 * </p>
4265 *
4266 * <pre>
4267 * StringUtils.join(null, *) = null
4268 * StringUtils.join([], *) = ""
4269 * StringUtils.join([null], *) = ""
4270 * StringUtils.join([1, 2, 3], ';') = "1;2;3"
4271 * StringUtils.join([1, 2, 3], null) = "123"
4272 * </pre>
4273 *
4274 * @param array
4275 * the array of values to join together, may be null
4276 * @param delimiter
4277 * the separator character to use
4278 * @param startIndex
4279 * the first index to start joining from. It is an error to pass in a start index past the end of the
4280 * array
4281 * @param endIndex
4282 * the index to stop joining from (exclusive). It is an error to pass in an end index past the end of
4283 * the array
4284 * @return the joined String, {@code null} if null array input
4285 * @since 3.2
4286 */
4287 public static String join(final int[] array, final char delimiter, final int startIndex, final int endIndex) {
4288 if (array == null) {
4289 return null;
4290 }
4291 if (endIndex - startIndex <= 0) {
4292 return EMPTY;
4293 }
4294 final StringBuilder stringBuilder = new StringBuilder();
4295 for (int i = startIndex; i < endIndex; i++) {
4296 stringBuilder
4297 .append(array[i])
4298 .append(delimiter);
4299 }
4300 return stringBuilder.substring(0, stringBuilder.length() - 1);
4301 }
4302
4303 /**
4304 * Joins the elements of the provided {@link Iterable} into
4305 * a single String containing the provided elements.
4306 *
4307 * <p>No delimiter is added before or after the list. Null objects or empty
4308 * strings within the iteration are represented by empty strings.</p>
4309 *
4310 * <p>See the examples here: {@link #join(Object[],char)}.</p>
4311 *
4312 * @param iterable the {@link Iterable} providing the values to join together, may be null
4313 * @param separator the separator character to use
4314 * @return the joined String, {@code null} if null iterator input
4315 * @since 2.3
4316 */
4317 public static String join(final Iterable<?> iterable, final char separator) {
4318 return iterable != null ? join(iterable.iterator(), separator) : null;
4319 }
4320
4321 /**
4322 * Joins the elements of the provided {@link Iterable} into
4323 * a single String containing the provided elements.
4324 *
4325 * <p>No delimiter is added before or after the list.
4326 * A {@code null} separator is the same as an empty String ("").</p>
4327 *
4328 * <p>See the examples here: {@link #join(Object[],String)}.</p>
4329 *
4330 * @param iterable the {@link Iterable} providing the values to join together, may be null
4331 * @param separator the separator character to use, null treated as ""
4332 * @return the joined String, {@code null} if null iterator input
4333 * @since 2.3
4334 */
4335 public static String join(final Iterable<?> iterable, final String separator) {
4336 return iterable != null ? join(iterable.iterator(), separator) : null;
4337 }
4338
4339 /**
4340 * Joins the elements of the provided {@link Iterator} into
4341 * a single String containing the provided elements.
4342 *
4343 * <p>No delimiter is added before or after the list. Null objects or empty
4344 * strings within the iteration are represented by empty strings.</p>
4345 *
4346 * <p>See the examples here: {@link #join(Object[],char)}.</p>
4347 *
4348 * @param iterator the {@link Iterator} of values to join together, may be null
4349 * @param separator the separator character to use
4350 * @return the joined String, {@code null} if null iterator input
4351 * @since 2.0
4352 */
4353 public static String join(final Iterator<?> iterator, final char separator) {
4354 // handle null, zero and one elements before building a buffer
4355 if (iterator == null) {
4356 return null;
4357 }
4358 if (!iterator.hasNext()) {
4359 return EMPTY;
4360 }
4361 return Streams.of(iterator).collect(LangCollectors.joining(toStringOrEmpty(String.valueOf(separator)), EMPTY, EMPTY, StringUtils::toStringOrEmpty));
4362 }
4363
4364 /**
4365 * Joins the elements of the provided {@link Iterator} into
4366 * a single String containing the provided elements.
4367 *
4368 * <p>No delimiter is added before or after the list.
4369 * A {@code null} separator is the same as an empty String ("").</p>
4370 *
4371 * <p>See the examples here: {@link #join(Object[],String)}.</p>
4372 *
4373 * @param iterator the {@link Iterator} of values to join together, may be null
4374 * @param separator the separator character to use, null treated as ""
4375 * @return the joined String, {@code null} if null iterator input
4376 */
4377 public static String join(final Iterator<?> iterator, final String separator) {
4378 // handle null, zero and one elements before building a buffer
4379 if (iterator == null) {
4380 return null;
4381 }
4382 if (!iterator.hasNext()) {
4383 return EMPTY;
4384 }
4385 return Streams.of(iterator).collect(LangCollectors.joining(toStringOrEmpty(separator), EMPTY, EMPTY, StringUtils::toStringOrEmpty));
4386 }
4387
4388 /**
4389 * Joins the elements of the provided {@link List} into a single String
4390 * containing the provided list of elements.
4391 *
4392 * <p>No delimiter is added before or after the list.
4393 * Null objects or empty strings within the array are represented by
4394 * empty strings.</p>
4395 *
4396 * <pre>
4397 * StringUtils.join(null, *) = null
4398 * StringUtils.join([], *) = ""
4399 * StringUtils.join([null], *) = ""
4400 * StringUtils.join(["a", "b", "c"], ';') = "a;b;c"
4401 * StringUtils.join(["a", "b", "c"], null) = "abc"
4402 * StringUtils.join([null, "", "a"], ';') = ";;a"
4403 * </pre>
4404 *
4405 * @param list the {@link List} of values to join together, may be null
4406 * @param separator the separator character to use
4407 * @param startIndex the first index to start joining from. It is
4408 * an error to pass in a start index past the end of the list
4409 * @param endIndex the index to stop joining from (exclusive). It is
4410 * an error to pass in an end index past the end of the list
4411 * @return the joined String, {@code null} if null list input
4412 * @since 3.8
4413 */
4414 public static String join(final List<?> list, final char separator, final int startIndex, final int endIndex) {
4415 if (list == null) {
4416 return null;
4417 }
4418 final int noOfItems = endIndex - startIndex;
4419 if (noOfItems <= 0) {
4420 return EMPTY;
4421 }
4422 final List<?> subList = list.subList(startIndex, endIndex);
4423 return join(subList.iterator(), separator);
4424 }
4425
4426 /**
4427 * Joins the elements of the provided {@link List} into a single String
4428 * containing the provided list of elements.
4429 *
4430 * <p>No delimiter is added before or after the list.
4431 * Null objects or empty strings within the array are represented by
4432 * empty strings.</p>
4433 *
4434 * <pre>
4435 * StringUtils.join(null, *) = null
4436 * StringUtils.join([], *) = ""
4437 * StringUtils.join([null], *) = ""
4438 * StringUtils.join(["a", "b", "c"], ';') = "a;b;c"
4439 * StringUtils.join(["a", "b", "c"], null) = "abc"
4440 * StringUtils.join([null, "", "a"], ';') = ";;a"
4441 * </pre>
4442 *
4443 * @param list the {@link List} of values to join together, may be null
4444 * @param separator the separator character to use
4445 * @param startIndex the first index to start joining from. It is
4446 * an error to pass in a start index past the end of the list
4447 * @param endIndex the index to stop joining from (exclusive). It is
4448 * an error to pass in an end index past the end of the list
4449 * @return the joined String, {@code null} if null list input
4450 * @since 3.8
4451 */
4452 public static String join(final List<?> list, final String separator, final int startIndex, final int endIndex) {
4453 if (list == null) {
4454 return null;
4455 }
4456 final int noOfItems = endIndex - startIndex;
4457 if (noOfItems <= 0) {
4458 return EMPTY;
4459 }
4460 final List<?> subList = list.subList(startIndex, endIndex);
4461 return join(subList.iterator(), separator);
4462 }
4463
4464
4465 /**
4466 * Joins the elements of the provided array into a single String containing the provided list of elements.
4467 *
4468 * <p>
4469 * No delimiter is added before or after the list. Null objects or empty strings within the array are represented
4470 * by empty strings.
4471 * </p>
4472 *
4473 * <pre>
4474 * StringUtils.join(null, *) = null
4475 * StringUtils.join([], *) = ""
4476 * StringUtils.join([null], *) = ""
4477 * StringUtils.join([1, 2, 3], ';') = "1;2;3"
4478 * StringUtils.join([1, 2, 3], null) = "123"
4479 * </pre>
4480 *
4481 * @param array
4482 * the array of values to join together, may be null
4483 * @param separator
4484 * the separator character to use
4485 * @return the joined String, {@code null} if null array input
4486 * @since 3.2
4487 */
4488 public static String join(final long[] array, final char separator) {
4489 if (array == null) {
4490 return null;
4491 }
4492 return join(array, separator, 0, array.length);
4493 }
4494
4495 /**
4496 * Joins the elements of the provided array into a single String containing the provided list of elements.
4497 *
4498 * <p>
4499 * No delimiter is added before or after the list. Null objects or empty strings within the array are represented
4500 * by empty strings.
4501 * </p>
4502 *
4503 * <pre>
4504 * StringUtils.join(null, *) = null
4505 * StringUtils.join([], *) = ""
4506 * StringUtils.join([null], *) = ""
4507 * StringUtils.join([1, 2, 3], ';') = "1;2;3"
4508 * StringUtils.join([1, 2, 3], null) = "123"
4509 * </pre>
4510 *
4511 * @param array
4512 * the array of values to join together, may be null
4513 * @param delimiter
4514 * the separator character to use
4515 * @param startIndex
4516 * the first index to start joining from. It is an error to pass in a start index past the end of the
4517 * array
4518 * @param endIndex
4519 * the index to stop joining from (exclusive). It is an error to pass in an end index past the end of
4520 * the array
4521 * @return the joined String, {@code null} if null array input
4522 * @since 3.2
4523 */
4524 public static String join(final long[] array, final char delimiter, final int startIndex, final int endIndex) {
4525 if (array == null) {
4526 return null;
4527 }
4528 if (endIndex - startIndex <= 0) {
4529 return EMPTY;
4530 }
4531 final StringBuilder stringBuilder = new StringBuilder();
4532 for (int i = startIndex; i < endIndex; i++) {
4533 stringBuilder
4534 .append(array[i])
4535 .append(delimiter);
4536 }
4537 return stringBuilder.substring(0, stringBuilder.length() - 1);
4538 }
4539
4540 /**
4541 * Joins the elements of the provided array into a single String
4542 * containing the provided list of elements.
4543 *
4544 * <p>No delimiter is added before or after the list.
4545 * Null objects or empty strings within the array are represented by
4546 * empty strings.</p>
4547 *
4548 * <pre>
4549 * StringUtils.join(null, *) = null
4550 * StringUtils.join([], *) = ""
4551 * StringUtils.join([null], *) = ""
4552 * StringUtils.join(["a", "b", "c"], ';') = "a;b;c"
4553 * StringUtils.join(["a", "b", "c"], null) = "abc"
4554 * StringUtils.join([null, "", "a"], ';') = ";;a"
4555 * </pre>
4556 *
4557 * @param array the array of values to join together, may be null
4558 * @param delimiter the separator character to use
4559 * @return the joined String, {@code null} if null array input
4560 * @since 2.0
4561 */
4562 public static String join(final Object[] array, final char delimiter) {
4563 if (array == null) {
4564 return null;
4565 }
4566 return join(array, delimiter, 0, array.length);
4567 }
4568
4569 /**
4570 * Joins the elements of the provided array into a single String
4571 * containing the provided list of elements.
4572 *
4573 * <p>No delimiter is added before or after the list.
4574 * Null objects or empty strings within the array are represented by
4575 * empty strings.</p>
4576 *
4577 * <pre>
4578 * StringUtils.join(null, *) = null
4579 * StringUtils.join([], *) = ""
4580 * StringUtils.join([null], *) = ""
4581 * StringUtils.join(["a", "b", "c"], ';') = "a;b;c"
4582 * StringUtils.join(["a", "b", "c"], null) = "abc"
4583 * StringUtils.join([null, "", "a"], ';') = ";;a"
4584 * </pre>
4585 *
4586 * @param array the array of values to join together, may be null
4587 * @param delimiter the separator character to use
4588 * @param startIndex the first index to start joining from. It is
4589 * an error to pass in a start index past the end of the array
4590 * @param endIndex the index to stop joining from (exclusive). It is
4591 * an error to pass in an end index past the end of the array
4592 * @return the joined String, {@code null} if null array input
4593 * @since 2.0
4594 */
4595 public static String join(final Object[] array, final char delimiter, final int startIndex, final int endIndex) {
4596 return join(array, String.valueOf(delimiter), startIndex, endIndex);
4597 }
4598
4599 /**
4600 * Joins the elements of the provided array into a single String
4601 * containing the provided list of elements.
4602 *
4603 * <p>No delimiter is added before or after the list.
4604 * A {@code null} separator is the same as an empty String ("").
4605 * Null objects or empty strings within the array are represented by
4606 * empty strings.</p>
4607 *
4608 * <pre>
4609 * StringUtils.join(null, *) = null
4610 * StringUtils.join([], *) = ""
4611 * StringUtils.join([null], *) = ""
4612 * StringUtils.join(["a", "b", "c"], "--") = "a--b--c"
4613 * StringUtils.join(["a", "b", "c"], null) = "abc"
4614 * StringUtils.join(["a", "b", "c"], "") = "abc"
4615 * StringUtils.join([null, "", "a"], ',') = ",,a"
4616 * </pre>
4617 *
4618 * @param array the array of values to join together, may be null
4619 * @param delimiter the separator character to use, null treated as ""
4620 * @return the joined String, {@code null} if null array input
4621 */
4622 public static String join(final Object[] array, final String delimiter) {
4623 return array != null ? join(array, toStringOrEmpty(delimiter), 0, array.length) : null;
4624 }
4625
4626 /**
4627 * Joins the elements of the provided array into a single String
4628 * containing the provided list of elements.
4629 *
4630 * <p>No delimiter is added before or after the list.
4631 * A {@code null} separator is the same as an empty String ("").
4632 * Null objects or empty strings within the array are represented by
4633 * empty strings.</p>
4634 *
4635 * <pre>
4636 * StringUtils.join(null, *, *, *) = null
4637 * StringUtils.join([], *, *, *) = ""
4638 * StringUtils.join([null], *, *, *) = ""
4639 * StringUtils.join(["a", "b", "c"], "--", 0, 3) = "a--b--c"
4640 * StringUtils.join(["a", "b", "c"], "--", 1, 3) = "b--c"
4641 * StringUtils.join(["a", "b", "c"], "--", 2, 3) = "c"
4642 * StringUtils.join(["a", "b", "c"], "--", 2, 2) = ""
4643 * StringUtils.join(["a", "b", "c"], null, 0, 3) = "abc"
4644 * StringUtils.join(["a", "b", "c"], "", 0, 3) = "abc"
4645 * StringUtils.join([null, "", "a"], ',', 0, 3) = ",,a"
4646 * </pre>
4647 *
4648 * @param array the array of values to join together, may be null
4649 * @param delimiter the separator character to use, null treated as ""
4650 * @param startIndex the first index to start joining from.
4651 * @param endIndex the index to stop joining from (exclusive).
4652 * @return the joined String, {@code null} if null array input; or the empty string
4653 * if {@code endIndex - startIndex <= 0}. The number of joined entries is given by
4654 * {@code endIndex - startIndex}
4655 * @throws ArrayIndexOutOfBoundsException ife<br>
4656 * {@code startIndex < 0} or <br>
4657 * {@code startIndex >= array.length()} or <br>
4658 * {@code endIndex < 0} or <br>
4659 * {@code endIndex > array.length()}
4660 */
4661 public static String join(final Object[] array, final String delimiter, final int startIndex, final int endIndex) {
4662 return array != null ? Streams.of(array).skip(startIndex).limit(Math.max(0, endIndex - startIndex))
4663 .collect(LangCollectors.joining(delimiter, EMPTY, EMPTY, StringUtils::toStringOrEmpty)) : null;
4664 }
4665
4666 /**
4667 * Joins the elements of the provided array into a single String containing the provided list of elements.
4668 *
4669 * <p>
4670 * No delimiter is added before or after the list. Null objects or empty strings within the array are represented
4671 * by empty strings.
4672 * </p>
4673 *
4674 * <pre>
4675 * StringUtils.join(null, *) = null
4676 * StringUtils.join([], *) = ""
4677 * StringUtils.join([null], *) = ""
4678 * StringUtils.join([1, 2, 3], ';') = "1;2;3"
4679 * StringUtils.join([1, 2, 3], null) = "123"
4680 * </pre>
4681 *
4682 * @param array
4683 * the array of values to join together, may be null
4684 * @param delimiter
4685 * the separator character to use
4686 * @return the joined String, {@code null} if null array input
4687 * @since 3.2
4688 */
4689 public static String join(final short[] array, final char delimiter) {
4690 if (array == null) {
4691 return null;
4692 }
4693 return join(array, delimiter, 0, array.length);
4694 }
4695
4696 /**
4697 * Joins the elements of the provided array into a single String containing the provided list of elements.
4698 *
4699 * <p>
4700 * No delimiter is added before or after the list. Null objects or empty strings within the array are represented
4701 * by empty strings.
4702 * </p>
4703 *
4704 * <pre>
4705 * StringUtils.join(null, *) = null
4706 * StringUtils.join([], *) = ""
4707 * StringUtils.join([null], *) = ""
4708 * StringUtils.join([1, 2, 3], ';') = "1;2;3"
4709 * StringUtils.join([1, 2, 3], null) = "123"
4710 * </pre>
4711 *
4712 * @param array
4713 * the array of values to join together, may be null
4714 * @param delimiter
4715 * the separator character to use
4716 * @param startIndex
4717 * the first index to start joining from. It is an error to pass in a start index past the end of the
4718 * array
4719 * @param endIndex
4720 * the index to stop joining from (exclusive). It is an error to pass in an end index past the end of
4721 * the array
4722 * @return the joined String, {@code null} if null array input
4723 * @since 3.2
4724 */
4725 public static String join(final short[] array, final char delimiter, final int startIndex, final int endIndex) {
4726 if (array == null) {
4727 return null;
4728 }
4729 if (endIndex - startIndex <= 0) {
4730 return EMPTY;
4731 }
4732 final StringBuilder stringBuilder = new StringBuilder();
4733 for (int i = startIndex; i < endIndex; i++) {
4734 stringBuilder
4735 .append(array[i])
4736 .append(delimiter);
4737 }
4738 return stringBuilder.substring(0, stringBuilder.length() - 1);
4739 }
4740
4741 /**
4742 * Joins the elements of the provided array into a single String
4743 * containing the provided list of elements.
4744 *
4745 * <p>No separator is added to the joined String.
4746 * Null objects or empty strings within the array are represented by
4747 * empty strings.</p>
4748 *
4749 * <pre>
4750 * StringUtils.join(null) = null
4751 * StringUtils.join([]) = ""
4752 * StringUtils.join([null]) = ""
4753 * StringUtils.join(["a", "b", "c"]) = "abc"
4754 * StringUtils.join([null, "", "a"]) = "a"
4755 * </pre>
4756 *
4757 * @param <T> the specific type of values to join together
4758 * @param elements the values to join together, may be null
4759 * @return the joined String, {@code null} if null array input
4760 * @since 2.0
4761 * @since 3.0 Changed signature to use varargs
4762 */
4763 @SafeVarargs
4764 public static <T> String join(final T... elements) {
4765 return join(elements, null);
4766 }
4767
4768 /**
4769 * Joins the elements of the provided varargs into a
4770 * single String containing the provided elements.
4771 *
4772 * <p>No delimiter is added before or after the list.
4773 * {@code null} elements and separator are treated as empty Strings ("").</p>
4774 *
4775 * <pre>
4776 * StringUtils.joinWith(",", {"a", "b"}) = "a,b"
4777 * StringUtils.joinWith(",", {"a", "b",""}) = "a,b,"
4778 * StringUtils.joinWith(",", {"a", null, "b"}) = "a,,b"
4779 * StringUtils.joinWith(null, {"a", "b"}) = "ab"
4780 * </pre>
4781 *
4782 * @param delimiter the separator character to use, null treated as ""
4783 * @param array the varargs providing the values to join together. {@code null} elements are treated as ""
4784 * @return the joined String.
4785 * @throws IllegalArgumentException if a null varargs is provided
4786 * @since 3.5
4787 */
4788 public static String joinWith(final String delimiter, final Object... array) {
4789 if (array == null) {
4790 throw new IllegalArgumentException("Object varargs must not be null");
4791 }
4792 return join(array, delimiter);
4793 }
4794
4795 /**
4796 * Finds the last index within a CharSequence, handling {@code null}.
4797 * This method uses {@link String#lastIndexOf(String)} if possible.
4798 *
4799 * <p>A {@code null} CharSequence will return {@code -1}.</p>
4800 *
4801 * <pre>
4802 * StringUtils.lastIndexOf(null, *) = -1
4803 * StringUtils.lastIndexOf(*, null) = -1
4804 * StringUtils.lastIndexOf("", "") = 0
4805 * StringUtils.lastIndexOf("aabaabaa", "a") = 7
4806 * StringUtils.lastIndexOf("aabaabaa", "b") = 5
4807 * StringUtils.lastIndexOf("aabaabaa", "ab") = 4
4808 * StringUtils.lastIndexOf("aabaabaa", "") = 8
4809 * </pre>
4810 *
4811 * @param seq the CharSequence to check, may be null
4812 * @param searchSeq the CharSequence to find, may be null
4813 * @return the last index of the search String,
4814 * -1 if no match or {@code null} string input
4815 * @since 2.0
4816 * @since 3.0 Changed signature from lastIndexOf(String, String) to lastIndexOf(CharSequence, CharSequence)
4817 */
4818 public static int lastIndexOf(final CharSequence seq, final CharSequence searchSeq) {
4819 if (seq == null) {
4820 return INDEX_NOT_FOUND;
4821 }
4822 return CharSequenceUtils.lastIndexOf(seq, searchSeq, seq.length());
4823 }
4824
4825 /**
4826 * Finds the last index within a CharSequence, handling {@code null}.
4827 * This method uses {@link String#lastIndexOf(String, int)} if possible.
4828 *
4829 * <p>A {@code null} CharSequence will return {@code -1}.
4830 * A negative start position returns {@code -1}.
4831 * An empty ("") search CharSequence always matches unless the start position is negative.
4832 * A start position greater than the string length searches the whole string.
4833 * The search starts at the startPos and works backwards; matches starting after the start
4834 * position are ignored.
4835 * </p>
4836 *
4837 * <pre>
4838 * StringUtils.lastIndexOf(null, *, *) = -1
4839 * StringUtils.lastIndexOf(*, null, *) = -1
4840 * StringUtils.lastIndexOf("aabaabaa", "a", 8) = 7
4841 * StringUtils.lastIndexOf("aabaabaa", "b", 8) = 5
4842 * StringUtils.lastIndexOf("aabaabaa", "ab", 8) = 4
4843 * StringUtils.lastIndexOf("aabaabaa", "b", 9) = 5
4844 * StringUtils.lastIndexOf("aabaabaa", "b", -1) = -1
4845 * StringUtils.lastIndexOf("aabaabaa", "a", 0) = 0
4846 * StringUtils.lastIndexOf("aabaabaa", "b", 0) = -1
4847 * StringUtils.lastIndexOf("aabaabaa", "b", 1) = -1
4848 * StringUtils.lastIndexOf("aabaabaa", "b", 2) = 2
4849 * StringUtils.lastIndexOf("aabaabaa", "ba", 2) = 2
4850 * </pre>
4851 *
4852 * @param seq the CharSequence to check, may be null
4853 * @param searchSeq the CharSequence to find, may be null
4854 * @param startPos the start position, negative treated as zero
4855 * @return the last index of the search CharSequence (always ≤ startPos),
4856 * -1 if no match or {@code null} string input
4857 * @since 2.0
4858 * @since 3.0 Changed signature from lastIndexOf(String, String, int) to lastIndexOf(CharSequence, CharSequence, int)
4859 */
4860 public static int lastIndexOf(final CharSequence seq, final CharSequence searchSeq, final int startPos) {
4861 return CharSequenceUtils.lastIndexOf(seq, searchSeq, startPos);
4862 }
4863
4864 /**
4865 * Returns the index within {@code seq} of the last occurrence of
4866 * the specified character. For values of {@code searchChar} in the
4867 * range from 0 to 0xFFFF (inclusive), the index (in Unicode code
4868 * units) returned is the largest value <i>k</i> such that:
4869 * <blockquote><pre>
4870 * this.charAt(<i>k</i>) == searchChar
4871 * </pre></blockquote>
4872 * is true. For other values of {@code searchChar}, it is the
4873 * largest value <i>k</i> such that:
4874 * <blockquote><pre>
4875 * this.codePointAt(<i>k</i>) == searchChar
4876 * </pre></blockquote>
4877 * is true. In either case, if no such character occurs in this
4878 * string, then {@code -1} is returned. Furthermore, a {@code null} or empty ("")
4879 * {@link CharSequence} will return {@code -1}. The
4880 * {@code seq} {@link CharSequence} object is searched backwards
4881 * starting at the last character.
4882 *
4883 * <pre>
4884 * StringUtils.lastIndexOf(null, *) = -1
4885 * StringUtils.lastIndexOf("", *) = -1
4886 * StringUtils.lastIndexOf("aabaabaa", 'a') = 7
4887 * StringUtils.lastIndexOf("aabaabaa", 'b') = 5
4888 * </pre>
4889 *
4890 * @param seq the {@link CharSequence} to check, may be null
4891 * @param searchChar the character to find
4892 * @return the last index of the search character,
4893 * -1 if no match or {@code null} string input
4894 * @since 2.0
4895 * @since 3.0 Changed signature from lastIndexOf(String, int) to lastIndexOf(CharSequence, int)
4896 * @since 3.6 Updated {@link CharSequenceUtils} call to behave more like {@link String}
4897 */
4898 public static int lastIndexOf(final CharSequence seq, final int searchChar) {
4899 if (isEmpty(seq)) {
4900 return INDEX_NOT_FOUND;
4901 }
4902 return CharSequenceUtils.lastIndexOf(seq, searchChar, seq.length());
4903 }
4904
4905 /**
4906 * Returns the index within {@code seq} of the last occurrence of
4907 * the specified character, searching backward starting at the
4908 * specified index. For values of {@code searchChar} in the range
4909 * from 0 to 0xFFFF (inclusive), the index returned is the largest
4910 * value <i>k</i> such that:
4911 * <blockquote><pre>
4912 * (this.charAt(<i>k</i>) == searchChar) && (<i>k</i> <= startPos)
4913 * </pre></blockquote>
4914 * is true. For other values of {@code searchChar}, it is the
4915 * largest value <i>k</i> such that:
4916 * <blockquote><pre>
4917 * (this.codePointAt(<i>k</i>) == searchChar) && (<i>k</i> <= startPos)
4918 * </pre></blockquote>
4919 * is true. In either case, if no such character occurs in {@code seq}
4920 * at or before position {@code startPos}, then
4921 * {@code -1} is returned. Furthermore, a {@code null} or empty ("")
4922 * {@link CharSequence} will return {@code -1}. A start position greater
4923 * than the string length searches the whole string.
4924 * The search starts at the {@code startPos} and works backwards;
4925 * matches starting after the start position are ignored.
4926 *
4927 * <p>All indices are specified in {@code char} values
4928 * (Unicode code units).
4929 *
4930 * <pre>
4931 * StringUtils.lastIndexOf(null, *, *) = -1
4932 * StringUtils.lastIndexOf("", *, *) = -1
4933 * StringUtils.lastIndexOf("aabaabaa", 'b', 8) = 5
4934 * StringUtils.lastIndexOf("aabaabaa", 'b', 4) = 2
4935 * StringUtils.lastIndexOf("aabaabaa", 'b', 0) = -1
4936 * StringUtils.lastIndexOf("aabaabaa", 'b', 9) = 5
4937 * StringUtils.lastIndexOf("aabaabaa", 'b', -1) = -1
4938 * StringUtils.lastIndexOf("aabaabaa", 'a', 0) = 0
4939 * </pre>
4940 *
4941 * @param seq the CharSequence to check, may be null
4942 * @param searchChar the character to find
4943 * @param startPos the start position
4944 * @return the last index of the search character (always ≤ startPos),
4945 * -1 if no match or {@code null} string input
4946 * @since 2.0
4947 * @since 3.0 Changed signature from lastIndexOf(String, int, int) to lastIndexOf(CharSequence, int, int)
4948 */
4949 public static int lastIndexOf(final CharSequence seq, final int searchChar, final int startPos) {
4950 if (isEmpty(seq)) {
4951 return INDEX_NOT_FOUND;
4952 }
4953 return CharSequenceUtils.lastIndexOf(seq, searchChar, startPos);
4954 }
4955
4956 /**
4957 * Find the latest index of any substring in a set of potential substrings.
4958 *
4959 * <p>A {@code null} CharSequence will return {@code -1}.
4960 * A {@code null} search array will return {@code -1}.
4961 * A {@code null} or zero length search array entry will be ignored,
4962 * but a search array containing "" will return the length of {@code str}
4963 * if {@code str} is not null. This method uses {@link String#indexOf(String)} if possible</p>
4964 *
4965 * <pre>
4966 * StringUtils.lastIndexOfAny(null, *) = -1
4967 * StringUtils.lastIndexOfAny(*, null) = -1
4968 * StringUtils.lastIndexOfAny(*, []) = -1
4969 * StringUtils.lastIndexOfAny(*, [null]) = -1
4970 * StringUtils.lastIndexOfAny("zzabyycdxx", ["ab", "cd"]) = 6
4971 * StringUtils.lastIndexOfAny("zzabyycdxx", ["cd", "ab"]) = 6
4972 * StringUtils.lastIndexOfAny("zzabyycdxx", ["mn", "op"]) = -1
4973 * StringUtils.lastIndexOfAny("zzabyycdxx", ["mn", "op"]) = -1
4974 * StringUtils.lastIndexOfAny("zzabyycdxx", ["mn", ""]) = 10
4975 * </pre>
4976 *
4977 * @param str the CharSequence to check, may be null
4978 * @param searchStrs the CharSequences to search for, may be null
4979 * @return the last index of any of the CharSequences, -1 if no match
4980 * @since 3.0 Changed signature from lastIndexOfAny(String, String[]) to lastIndexOfAny(CharSequence, CharSequence)
4981 */
4982 public static int lastIndexOfAny(final CharSequence str, final CharSequence... searchStrs) {
4983 if (str == null || searchStrs == null) {
4984 return INDEX_NOT_FOUND;
4985 }
4986 int ret = INDEX_NOT_FOUND;
4987 int tmp;
4988 for (final CharSequence search : searchStrs) {
4989 if (search == null) {
4990 continue;
4991 }
4992 tmp = CharSequenceUtils.lastIndexOf(str, search, str.length());
4993 if (tmp > ret) {
4994 ret = tmp;
4995 }
4996 }
4997 return ret;
4998 }
4999
5000 /**
5001 * Case in-sensitive find of the last index within a CharSequence.
5002 *
5003 * <p>A {@code null} CharSequence will return {@code -1}.
5004 * A negative start position returns {@code -1}.
5005 * An empty ("") search CharSequence always matches unless the start position is negative.
5006 * A start position greater than the string length searches the whole string.</p>
5007 *
5008 * <pre>
5009 * StringUtils.lastIndexOfIgnoreCase(null, *) = -1
5010 * StringUtils.lastIndexOfIgnoreCase(*, null) = -1
5011 * StringUtils.lastIndexOfIgnoreCase("aabaabaa", "A") = 7
5012 * StringUtils.lastIndexOfIgnoreCase("aabaabaa", "B") = 5
5013 * StringUtils.lastIndexOfIgnoreCase("aabaabaa", "AB") = 4
5014 * </pre>
5015 *
5016 * @param str the CharSequence to check, may be null
5017 * @param searchStr the CharSequence to find, may be null
5018 * @return the first index of the search CharSequence,
5019 * -1 if no match or {@code null} string input
5020 * @since 2.5
5021 * @since 3.0 Changed signature from lastIndexOfIgnoreCase(String, String) to lastIndexOfIgnoreCase(CharSequence, CharSequence)
5022 */
5023 public static int lastIndexOfIgnoreCase(final CharSequence str, final CharSequence searchStr) {
5024 if (str == null || searchStr == null) {
5025 return INDEX_NOT_FOUND;
5026 }
5027 return lastIndexOfIgnoreCase(str, searchStr, str.length());
5028 }
5029
5030 /**
5031 * Case in-sensitive find of the last index within a CharSequence
5032 * from the specified position.
5033 *
5034 * <p>A {@code null} CharSequence will return {@code -1}.
5035 * A negative start position returns {@code -1}.
5036 * An empty ("") search CharSequence always matches unless the start position is negative.
5037 * A start position greater than the string length searches the whole string.
5038 * The search starts at the startPos and works backwards; matches starting after the start
5039 * position are ignored.
5040 * </p>
5041 *
5042 * <pre>
5043 * StringUtils.lastIndexOfIgnoreCase(null, *, *) = -1
5044 * StringUtils.lastIndexOfIgnoreCase(*, null, *) = -1
5045 * StringUtils.lastIndexOfIgnoreCase("aabaabaa", "A", 8) = 7
5046 * StringUtils.lastIndexOfIgnoreCase("aabaabaa", "B", 8) = 5
5047 * StringUtils.lastIndexOfIgnoreCase("aabaabaa", "AB", 8) = 4
5048 * StringUtils.lastIndexOfIgnoreCase("aabaabaa", "B", 9) = 5
5049 * StringUtils.lastIndexOfIgnoreCase("aabaabaa", "B", -1) = -1
5050 * StringUtils.lastIndexOfIgnoreCase("aabaabaa", "A", 0) = 0
5051 * StringUtils.lastIndexOfIgnoreCase("aabaabaa", "B", 0) = -1
5052 * </pre>
5053 *
5054 * @param str the CharSequence to check, may be null
5055 * @param searchStr the CharSequence to find, may be null
5056 * @param startPos the start position
5057 * @return the last index of the search CharSequence (always ≤ startPos),
5058 * -1 if no match or {@code null} input
5059 * @since 2.5
5060 * @since 3.0 Changed signature from lastIndexOfIgnoreCase(String, String, int) to lastIndexOfIgnoreCase(CharSequence, CharSequence, int)
5061 */
5062 public static int lastIndexOfIgnoreCase(final CharSequence str, final CharSequence searchStr, int startPos) {
5063 if (str == null || searchStr == null) {
5064 return INDEX_NOT_FOUND;
5065 }
5066 final int searchStrLength = searchStr.length();
5067 final int strLength = str.length();
5068 if (startPos > strLength - searchStrLength) {
5069 startPos = strLength - searchStrLength;
5070 }
5071 if (startPos < 0) {
5072 return INDEX_NOT_FOUND;
5073 }
5074 if (searchStrLength == 0) {
5075 return startPos;
5076 }
5077
5078 for (int i = startPos; i >= 0; i--) {
5079 if (CharSequenceUtils.regionMatches(str, true, i, searchStr, 0, searchStrLength)) {
5080 return i;
5081 }
5082 }
5083 return INDEX_NOT_FOUND;
5084 }
5085
5086 /**
5087 * Finds the n-th last index within a String, handling {@code null}.
5088 * This method uses {@link String#lastIndexOf(String)}.
5089 *
5090 * <p>A {@code null} String will return {@code -1}.</p>
5091 *
5092 * <pre>
5093 * StringUtils.lastOrdinalIndexOf(null, *, *) = -1
5094 * StringUtils.lastOrdinalIndexOf(*, null, *) = -1
5095 * StringUtils.lastOrdinalIndexOf("", "", *) = 0
5096 * StringUtils.lastOrdinalIndexOf("aabaabaa", "a", 1) = 7
5097 * StringUtils.lastOrdinalIndexOf("aabaabaa", "a", 2) = 6
5098 * StringUtils.lastOrdinalIndexOf("aabaabaa", "b", 1) = 5
5099 * StringUtils.lastOrdinalIndexOf("aabaabaa", "b", 2) = 2
5100 * StringUtils.lastOrdinalIndexOf("aabaabaa", "ab", 1) = 4
5101 * StringUtils.lastOrdinalIndexOf("aabaabaa", "ab", 2) = 1
5102 * StringUtils.lastOrdinalIndexOf("aabaabaa", "", 1) = 8
5103 * StringUtils.lastOrdinalIndexOf("aabaabaa", "", 2) = 8
5104 * </pre>
5105 *
5106 * <p>Note that 'tail(CharSequence str, int n)' may be implemented as: </p>
5107 *
5108 * <pre>
5109 * str.substring(lastOrdinalIndexOf(str, "\n", n) + 1)
5110 * </pre>
5111 *
5112 * @param str the CharSequence to check, may be null
5113 * @param searchStr the CharSequence to find, may be null
5114 * @param ordinal the n-th last {@code searchStr} to find
5115 * @return the n-th last index of the search CharSequence,
5116 * {@code -1} ({@code INDEX_NOT_FOUND}) if no match or {@code null} string input
5117 * @since 2.5
5118 * @since 3.0 Changed signature from lastOrdinalIndexOf(String, String, int) to lastOrdinalIndexOf(CharSequence, CharSequence, int)
5119 */
5120 public static int lastOrdinalIndexOf(final CharSequence str, final CharSequence searchStr, final int ordinal) {
5121 return ordinalIndexOf(str, searchStr, ordinal, true);
5122 }
5123
5124 /**
5125 * Gets the leftmost {@code len} characters of a String.
5126 *
5127 * <p>If {@code len} characters are not available, or the
5128 * String is {@code null}, the String will be returned without
5129 * an exception. An empty String is returned if len is negative.</p>
5130 *
5131 * <pre>
5132 * StringUtils.left(null, *) = null
5133 * StringUtils.left(*, -ve) = ""
5134 * StringUtils.left("", *) = ""
5135 * StringUtils.left("abc", 0) = ""
5136 * StringUtils.left("abc", 2) = "ab"
5137 * StringUtils.left("abc", 4) = "abc"
5138 * </pre>
5139 *
5140 * @param str the String to get the leftmost characters from, may be null
5141 * @param len the length of the required String
5142 * @return the leftmost characters, {@code null} if null String input
5143 */
5144 public static String left(final String str, final int len) {
5145 if (str == null) {
5146 return null;
5147 }
5148 if (len < 0) {
5149 return EMPTY;
5150 }
5151 if (str.length() <= len) {
5152 return str;
5153 }
5154 return str.substring(0, len);
5155 }
5156
5157 /**
5158 * Left pad a String with spaces (' ').
5159 *
5160 * <p>The String is padded to the size of {@code size}.</p>
5161 *
5162 * <pre>
5163 * StringUtils.leftPad(null, *) = null
5164 * StringUtils.leftPad("", 3) = " "
5165 * StringUtils.leftPad("bat", 3) = "bat"
5166 * StringUtils.leftPad("bat", 5) = " bat"
5167 * StringUtils.leftPad("bat", 1) = "bat"
5168 * StringUtils.leftPad("bat", -1) = "bat"
5169 * </pre>
5170 *
5171 * @param str the String to pad out, may be null
5172 * @param size the size to pad to
5173 * @return left padded String or original String if no padding is necessary,
5174 * {@code null} if null String input
5175 */
5176 public static String leftPad(final String str, final int size) {
5177 return leftPad(str, size, ' ');
5178 }
5179
5180 /**
5181 * Left pad a String with a specified character.
5182 *
5183 * <p>Pad to a size of {@code size}.</p>
5184 *
5185 * <pre>
5186 * StringUtils.leftPad(null, *, *) = null
5187 * StringUtils.leftPad("", 3, 'z') = "zzz"
5188 * StringUtils.leftPad("bat", 3, 'z') = "bat"
5189 * StringUtils.leftPad("bat", 5, 'z') = "zzbat"
5190 * StringUtils.leftPad("bat", 1, 'z') = "bat"
5191 * StringUtils.leftPad("bat", -1, 'z') = "bat"
5192 * </pre>
5193 *
5194 * @param str the String to pad out, may be null
5195 * @param size the size to pad to
5196 * @param padChar the character to pad with
5197 * @return left padded String or original String if no padding is necessary,
5198 * {@code null} if null String input
5199 * @since 2.0
5200 */
5201 public static String leftPad(final String str, final int size, final char padChar) {
5202 if (str == null) {
5203 return null;
5204 }
5205 final int pads = size - str.length();
5206 if (pads <= 0) {
5207 return str; // returns original String when possible
5208 }
5209 if (pads > PAD_LIMIT) {
5210 return leftPad(str, size, String.valueOf(padChar));
5211 }
5212 return repeat(padChar, pads).concat(str);
5213 }
5214
5215 /**
5216 * Left pad a String with a specified String.
5217 *
5218 * <p>Pad to a size of {@code size}.</p>
5219 *
5220 * <pre>
5221 * StringUtils.leftPad(null, *, *) = null
5222 * StringUtils.leftPad("", 3, "z") = "zzz"
5223 * StringUtils.leftPad("bat", 3, "yz") = "bat"
5224 * StringUtils.leftPad("bat", 5, "yz") = "yzbat"
5225 * StringUtils.leftPad("bat", 8, "yz") = "yzyzybat"
5226 * StringUtils.leftPad("bat", 1, "yz") = "bat"
5227 * StringUtils.leftPad("bat", -1, "yz") = "bat"
5228 * StringUtils.leftPad("bat", 5, null) = " bat"
5229 * StringUtils.leftPad("bat", 5, "") = " bat"
5230 * </pre>
5231 *
5232 * @param str the String to pad out, may be null
5233 * @param size the size to pad to
5234 * @param padStr the String to pad with, null or empty treated as single space
5235 * @return left padded String or original String if no padding is necessary,
5236 * {@code null} if null String input
5237 */
5238 public static String leftPad(final String str, final int size, String padStr) {
5239 if (str == null) {
5240 return null;
5241 }
5242 if (isEmpty(padStr)) {
5243 padStr = SPACE;
5244 }
5245 final int padLen = padStr.length();
5246 final int strLen = str.length();
5247 final int pads = size - strLen;
5248 if (pads <= 0) {
5249 return str; // returns original String when possible
5250 }
5251 if (padLen == 1 && pads <= PAD_LIMIT) {
5252 return leftPad(str, size, padStr.charAt(0));
5253 }
5254
5255 if (pads == padLen) {
5256 return padStr.concat(str);
5257 }
5258 if (pads < padLen) {
5259 return padStr.substring(0, pads).concat(str);
5260 }
5261 final char[] padding = new char[pads];
5262 final char[] padChars = padStr.toCharArray();
5263 for (int i = 0; i < pads; i++) {
5264 padding[i] = padChars[i % padLen];
5265 }
5266 return new String(padding).concat(str);
5267 }
5268
5269 /**
5270 * Gets a CharSequence length or {@code 0} if the CharSequence is
5271 * {@code null}.
5272 *
5273 * @param cs
5274 * a CharSequence or {@code null}
5275 * @return CharSequence length or {@code 0} if the CharSequence is
5276 * {@code null}.
5277 * @since 2.4
5278 * @since 3.0 Changed signature from length(String) to length(CharSequence)
5279 */
5280 public static int length(final CharSequence cs) {
5281 return cs == null ? 0 : cs.length();
5282 }
5283
5284 /**
5285 * Converts a String to lower case as per {@link String#toLowerCase()}.
5286 *
5287 * <p>A {@code null} input String returns {@code null}.</p>
5288 *
5289 * <pre>
5290 * StringUtils.lowerCase(null) = null
5291 * StringUtils.lowerCase("") = ""
5292 * StringUtils.lowerCase("aBc") = "abc"
5293 * </pre>
5294 *
5295 * <p><strong>Note:</strong> As described in the documentation for {@link String#toLowerCase()},
5296 * the result of this method is affected by the current locale.
5297 * For platform-independent case transformations, the method {@link #lowerCase(String, Locale)}
5298 * should be used with a specific locale (e.g. {@link Locale#ENGLISH}).</p>
5299 *
5300 * @param str the String to lower case, may be null
5301 * @return the lower cased String, {@code null} if null String input
5302 */
5303 public static String lowerCase(final String str) {
5304 if (str == null) {
5305 return null;
5306 }
5307 return str.toLowerCase();
5308 }
5309
5310 /**
5311 * Converts a String to lower case as per {@link String#toLowerCase(Locale)}.
5312 *
5313 * <p>A {@code null} input String returns {@code null}.</p>
5314 *
5315 * <pre>
5316 * StringUtils.lowerCase(null, Locale.ENGLISH) = null
5317 * StringUtils.lowerCase("", Locale.ENGLISH) = ""
5318 * StringUtils.lowerCase("aBc", Locale.ENGLISH) = "abc"
5319 * </pre>
5320 *
5321 * @param str the String to lower case, may be null
5322 * @param locale the locale that defines the case transformation rules, must not be null
5323 * @return the lower cased String, {@code null} if null String input
5324 * @since 2.5
5325 */
5326 public static String lowerCase(final String str, final Locale locale) {
5327 if (str == null) {
5328 return null;
5329 }
5330 return str.toLowerCase(LocaleUtils.toLocale(locale));
5331 }
5332
5333 private static int[] matches(final CharSequence first, final CharSequence second) {
5334 final CharSequence max;
5335 final CharSequence min;
5336 if (first.length() > second.length()) {
5337 max = first;
5338 min = second;
5339 } else {
5340 max = second;
5341 min = first;
5342 }
5343 final int range = Math.max(max.length() / 2 - 1, 0);
5344 final int[] matchIndexes = new int[min.length()];
5345 Arrays.fill(matchIndexes, -1);
5346 final boolean[] matchFlags = new boolean[max.length()];
5347 int matches = 0;
5348 for (int mi = 0; mi < min.length(); mi++) {
5349 final char c1 = min.charAt(mi);
5350 for (int xi = Math.max(mi - range, 0), xn = Math.min(mi + range + 1, max.length()); xi < xn; xi++) {
5351 if (!matchFlags[xi] && c1 == max.charAt(xi)) {
5352 matchIndexes[mi] = xi;
5353 matchFlags[xi] = true;
5354 matches++;
5355 break;
5356 }
5357 }
5358 }
5359 final char[] ms1 = new char[matches];
5360 final char[] ms2 = new char[matches];
5361 for (int i = 0, si = 0; i < min.length(); i++) {
5362 if (matchIndexes[i] != -1) {
5363 ms1[si] = min.charAt(i);
5364 si++;
5365 }
5366 }
5367 for (int i = 0, si = 0; i < max.length(); i++) {
5368 if (matchFlags[i]) {
5369 ms2[si] = max.charAt(i);
5370 si++;
5371 }
5372 }
5373 int transpositions = 0;
5374 for (int mi = 0; mi < ms1.length; mi++) {
5375 if (ms1[mi] != ms2[mi]) {
5376 transpositions++;
5377 }
5378 }
5379 int prefix = 0;
5380 for (int mi = 0; mi < min.length(); mi++) {
5381 if (first.charAt(mi) != second.charAt(mi)) {
5382 break;
5383 }
5384 prefix++;
5385 }
5386 return new int[] { matches, transpositions / 2, prefix, max.length() };
5387 }
5388
5389 /**
5390 * Gets {@code len} characters from the middle of a String.
5391 *
5392 * <p>If {@code len} characters are not available, the remainder
5393 * of the String will be returned without an exception. If the
5394 * String is {@code null}, {@code null} will be returned.
5395 * An empty String is returned if len is negative or exceeds the
5396 * length of {@code str}.</p>
5397 *
5398 * <pre>
5399 * StringUtils.mid(null, *, *) = null
5400 * StringUtils.mid(*, *, -ve) = ""
5401 * StringUtils.mid("", 0, *) = ""
5402 * StringUtils.mid("abc", 0, 2) = "ab"
5403 * StringUtils.mid("abc", 0, 4) = "abc"
5404 * StringUtils.mid("abc", 2, 4) = "c"
5405 * StringUtils.mid("abc", 4, 2) = ""
5406 * StringUtils.mid("abc", -2, 2) = "ab"
5407 * </pre>
5408 *
5409 * @param str the String to get the characters from, may be null
5410 * @param pos the position to start from, negative treated as zero
5411 * @param len the length of the required String
5412 * @return the middle characters, {@code null} if null String input
5413 */
5414 public static String mid(final String str, int pos, final int len) {
5415 if (str == null) {
5416 return null;
5417 }
5418 if (len < 0 || pos > str.length()) {
5419 return EMPTY;
5420 }
5421 if (pos < 0) {
5422 pos = 0;
5423 }
5424 if (str.length() <= pos + len) {
5425 return str.substring(pos);
5426 }
5427 return str.substring(pos, pos + len);
5428 }
5429
5430 /**
5431 * Similar to <a
5432 * href="https://www.w3.org/TR/xpath/#function-normalize-space">https://www.w3.org/TR/xpath/#function-normalize
5433 * -space</a>
5434 *
5435 * <p>
5436 * The function returns the argument string with whitespace normalized by using
5437 * {@code {@link #trim(String)}} to remove leading and trailing whitespace
5438 * and then replacing sequences of whitespace characters by a single space.
5439 * </p>
5440 * In XML Whitespace characters are the same as those allowed by the <a
5441 * href="https://www.w3.org/TR/REC-xml/#NT-S">S</a> production, which is S ::= (#x20 | #x9 | #xD | #xA)+
5442 * <p>
5443 * Java's regexp pattern \s defines whitespace as [ \t\n\x0B\f\r]
5444 *
5445 * <p>For reference:</p>
5446 * <ul>
5447 * <li>\x0B = vertical tab</li>
5448 * <li>\f = #xC = form feed</li>
5449 * <li>#x20 = space</li>
5450 * <li>#x9 = \t</li>
5451 * <li>#xA = \n</li>
5452 * <li>#xD = \r</li>
5453 * </ul>
5454 *
5455 * <p>
5456 * The difference is that Java's whitespace includes vertical tab and form feed, which this functional will also
5457 * normalize. Additionally {@code {@link #trim(String)}} removes control characters (char <= 32) from both
5458 * ends of this String.
5459 * </p>
5460 *
5461 * @see Pattern
5462 * @see #trim(String)
5463 * @see <a
5464 * href="https://www.w3.org/TR/xpath/#function-normalize-space">https://www.w3.org/TR/xpath/#function-normalize-space</a>
5465 * @param str the source String to normalize whitespaces from, may be null
5466 * @return the modified string with whitespace normalized, {@code null} if null String input
5467 *
5468 * @since 3.0
5469 */
5470 public static String normalizeSpace(final String str) {
5471 // LANG-1020: Improved performance significantly by normalizing manually instead of using regex
5472 // See https://github.com/librucha/commons-lang-normalizespaces-benchmark for performance test
5473 if (isEmpty(str)) {
5474 return str;
5475 }
5476 final int size = str.length();
5477 final char[] newChars = new char[size];
5478 int count = 0;
5479 int whitespacesCount = 0;
5480 boolean startWhitespaces = true;
5481 for (int i = 0; i < size; i++) {
5482 final char actualChar = str.charAt(i);
5483 final boolean isWhitespace = Character.isWhitespace(actualChar);
5484 if (isWhitespace) {
5485 if (whitespacesCount == 0 && !startWhitespaces) {
5486 newChars[count++] = SPACE.charAt(0);
5487 }
5488 whitespacesCount++;
5489 } else {
5490 startWhitespaces = false;
5491 newChars[count++] = actualChar == 160 ? 32 : actualChar;
5492 whitespacesCount = 0;
5493 }
5494 }
5495 if (startWhitespaces) {
5496 return EMPTY;
5497 }
5498 return new String(newChars, 0, count - (whitespacesCount > 0 ? 1 : 0)).trim();
5499 }
5500
5501 /**
5502 * Finds the n-th index within a CharSequence, handling {@code null}.
5503 * This method uses {@link String#indexOf(String)} if possible.
5504 * <p><b>Note:</b> The code starts looking for a match at the start of the target,
5505 * incrementing the starting index by one after each successful match
5506 * (unless {@code searchStr} is an empty string in which case the position
5507 * is never incremented and {@code 0} is returned immediately).
5508 * This means that matches may overlap.</p>
5509 * <p>A {@code null} CharSequence will return {@code -1}.</p>
5510 *
5511 * <pre>
5512 * StringUtils.ordinalIndexOf(null, *, *) = -1
5513 * StringUtils.ordinalIndexOf(*, null, *) = -1
5514 * StringUtils.ordinalIndexOf("", "", *) = 0
5515 * StringUtils.ordinalIndexOf("aabaabaa", "a", 1) = 0
5516 * StringUtils.ordinalIndexOf("aabaabaa", "a", 2) = 1
5517 * StringUtils.ordinalIndexOf("aabaabaa", "b", 1) = 2
5518 * StringUtils.ordinalIndexOf("aabaabaa", "b", 2) = 5
5519 * StringUtils.ordinalIndexOf("aabaabaa", "ab", 1) = 1
5520 * StringUtils.ordinalIndexOf("aabaabaa", "ab", 2) = 4
5521 * StringUtils.ordinalIndexOf("aabaabaa", "", 1) = 0
5522 * StringUtils.ordinalIndexOf("aabaabaa", "", 2) = 0
5523 * </pre>
5524 *
5525 * <p>Matches may overlap:</p>
5526 * <pre>
5527 * StringUtils.ordinalIndexOf("ababab", "aba", 1) = 0
5528 * StringUtils.ordinalIndexOf("ababab", "aba", 2) = 2
5529 * StringUtils.ordinalIndexOf("ababab", "aba", 3) = -1
5530 *
5531 * StringUtils.ordinalIndexOf("abababab", "abab", 1) = 0
5532 * StringUtils.ordinalIndexOf("abababab", "abab", 2) = 2
5533 * StringUtils.ordinalIndexOf("abababab", "abab", 3) = 4
5534 * StringUtils.ordinalIndexOf("abababab", "abab", 4) = -1
5535 * </pre>
5536 *
5537 * <p>Note that 'head(CharSequence str, int n)' may be implemented as: </p>
5538 *
5539 * <pre>
5540 * str.substring(0, lastOrdinalIndexOf(str, "\n", n))
5541 * </pre>
5542 *
5543 * @param str the CharSequence to check, may be null
5544 * @param searchStr the CharSequence to find, may be null
5545 * @param ordinal the n-th {@code searchStr} to find
5546 * @return the n-th index of the search CharSequence,
5547 * {@code -1} ({@code INDEX_NOT_FOUND}) if no match or {@code null} string input
5548 * @since 2.1
5549 * @since 3.0 Changed signature from ordinalIndexOf(String, String, int) to ordinalIndexOf(CharSequence, CharSequence, int)
5550 */
5551 public static int ordinalIndexOf(final CharSequence str, final CharSequence searchStr, final int ordinal) {
5552 return ordinalIndexOf(str, searchStr, ordinal, false);
5553 }
5554
5555 /**
5556 * Finds the n-th index within a String, handling {@code null}.
5557 * This method uses {@link String#indexOf(String)} if possible.
5558 * <p>Note that matches may overlap<p>
5559 *
5560 * <p>A {@code null} CharSequence will return {@code -1}.</p>
5561 *
5562 * @param str the CharSequence to check, may be null
5563 * @param searchStr the CharSequence to find, may be null
5564 * @param ordinal the n-th {@code searchStr} to find, overlapping matches are allowed.
5565 * @param lastIndex true if lastOrdinalIndexOf() otherwise false if ordinalIndexOf()
5566 * @return the n-th index of the search CharSequence,
5567 * {@code -1} ({@code INDEX_NOT_FOUND}) if no match or {@code null} string input
5568 */
5569 // Shared code between ordinalIndexOf(String, String, int) and lastOrdinalIndexOf(String, String, int)
5570 private static int ordinalIndexOf(final CharSequence str, final CharSequence searchStr, final int ordinal, final boolean lastIndex) {
5571 if (str == null || searchStr == null || ordinal <= 0) {
5572 return INDEX_NOT_FOUND;
5573 }
5574 if (searchStr.length() == 0) {
5575 return lastIndex ? str.length() : 0;
5576 }
5577 int found = 0;
5578 // set the initial index beyond the end of the string
5579 // this is to allow for the initial index decrement/increment
5580 int index = lastIndex ? str.length() : INDEX_NOT_FOUND;
5581 do {
5582 if (lastIndex) {
5583 index = CharSequenceUtils.lastIndexOf(str, searchStr, index - 1); // step backwards through string
5584 } else {
5585 index = CharSequenceUtils.indexOf(str, searchStr, index + 1); // step forwards through string
5586 }
5587 if (index < 0) {
5588 return index;
5589 }
5590 found++;
5591 } while (found < ordinal);
5592 return index;
5593 }
5594
5595 /**
5596 * Overlays part of a String with another String.
5597 *
5598 * <p>A {@code null} string input returns {@code null}.
5599 * A negative index is treated as zero.
5600 * An index greater than the string length is treated as the string length.
5601 * The start index is always the smaller of the two indices.</p>
5602 *
5603 * <pre>
5604 * StringUtils.overlay(null, *, *, *) = null
5605 * StringUtils.overlay("", "abc", 0, 0) = "abc"
5606 * StringUtils.overlay("abcdef", null, 2, 4) = "abef"
5607 * StringUtils.overlay("abcdef", "", 2, 4) = "abef"
5608 * StringUtils.overlay("abcdef", "", 4, 2) = "abef"
5609 * StringUtils.overlay("abcdef", "zzzz", 2, 4) = "abzzzzef"
5610 * StringUtils.overlay("abcdef", "zzzz", 4, 2) = "abzzzzef"
5611 * StringUtils.overlay("abcdef", "zzzz", -1, 4) = "zzzzef"
5612 * StringUtils.overlay("abcdef", "zzzz", 2, 8) = "abzzzz"
5613 * StringUtils.overlay("abcdef", "zzzz", -2, -3) = "zzzzabcdef"
5614 * StringUtils.overlay("abcdef", "zzzz", 8, 10) = "abcdefzzzz"
5615 * </pre>
5616 *
5617 * @param str the String to do overlaying in, may be null
5618 * @param overlay the String to overlay, may be null
5619 * @param start the position to start overlaying at
5620 * @param end the position to stop overlaying before
5621 * @return overlayed String, {@code null} if null String input
5622 * @since 2.0
5623 */
5624 public static String overlay(final String str, String overlay, int start, int end) {
5625 if (str == null) {
5626 return null;
5627 }
5628 if (overlay == null) {
5629 overlay = EMPTY;
5630 }
5631 final int len = str.length();
5632 if (start < 0) {
5633 start = 0;
5634 }
5635 if (start > len) {
5636 start = len;
5637 }
5638 if (end < 0) {
5639 end = 0;
5640 }
5641 if (end > len) {
5642 end = len;
5643 }
5644 if (start > end) {
5645 final int temp = start;
5646 start = end;
5647 end = temp;
5648 }
5649 return str.substring(0, start) +
5650 overlay +
5651 str.substring(end);
5652 }
5653
5654 /**
5655 * Prepends the prefix to the start of the string if the string does not
5656 * already start with any of the prefixes.
5657 *
5658 * @param str The string.
5659 * @param prefix The prefix to prepend to the start of the string.
5660 * @param ignoreCase Indicates whether the compare should ignore case.
5661 * @param prefixes Additional prefixes that are valid (optional).
5662 *
5663 * @return A new String if prefix was prepended, the same string otherwise.
5664 */
5665 private static String prependIfMissing(final String str, final CharSequence prefix, final boolean ignoreCase, final CharSequence... prefixes) {
5666 if (str == null || isEmpty(prefix) || startsWith(str, prefix, ignoreCase)) {
5667 return str;
5668 }
5669 if (ArrayUtils.isNotEmpty(prefixes)) {
5670 for (final CharSequence p : prefixes) {
5671 if (startsWith(str, p, ignoreCase)) {
5672 return str;
5673 }
5674 }
5675 }
5676 return prefix.toString() + str;
5677 }
5678
5679 /**
5680 * Prepends the prefix to the start of the string if the string does not
5681 * already start with any of the prefixes.
5682 *
5683 * <pre>
5684 * StringUtils.prependIfMissing(null, null) = null
5685 * StringUtils.prependIfMissing("abc", null) = "abc"
5686 * StringUtils.prependIfMissing("", "xyz") = "xyz"
5687 * StringUtils.prependIfMissing("abc", "xyz") = "xyzabc"
5688 * StringUtils.prependIfMissing("xyzabc", "xyz") = "xyzabc"
5689 * StringUtils.prependIfMissing("XYZabc", "xyz") = "xyzXYZabc"
5690 * </pre>
5691 * <p>With additional prefixes,</p>
5692 * <pre>
5693 * StringUtils.prependIfMissing(null, null, null) = null
5694 * StringUtils.prependIfMissing("abc", null, null) = "abc"
5695 * StringUtils.prependIfMissing("", "xyz", null) = "xyz"
5696 * StringUtils.prependIfMissing("abc", "xyz", new CharSequence[]{null}) = "xyzabc"
5697 * StringUtils.prependIfMissing("abc", "xyz", "") = "abc"
5698 * StringUtils.prependIfMissing("abc", "xyz", "mno") = "xyzabc"
5699 * StringUtils.prependIfMissing("xyzabc", "xyz", "mno") = "xyzabc"
5700 * StringUtils.prependIfMissing("mnoabc", "xyz", "mno") = "mnoabc"
5701 * StringUtils.prependIfMissing("XYZabc", "xyz", "mno") = "xyzXYZabc"
5702 * StringUtils.prependIfMissing("MNOabc", "xyz", "mno") = "xyzMNOabc"
5703 * </pre>
5704 *
5705 * @param str The string.
5706 * @param prefix The prefix to prepend to the start of the string.
5707 * @param prefixes Additional prefixes that are valid.
5708 *
5709 * @return A new String if prefix was prepended, the same string otherwise.
5710 *
5711 * @since 3.2
5712 */
5713 public static String prependIfMissing(final String str, final CharSequence prefix, final CharSequence... prefixes) {
5714 return prependIfMissing(str, prefix, false, prefixes);
5715 }
5716
5717 /**
5718 * Prepends the prefix to the start of the string if the string does not
5719 * already start, case-insensitive, with any of the prefixes.
5720 *
5721 * <pre>
5722 * StringUtils.prependIfMissingIgnoreCase(null, null) = null
5723 * StringUtils.prependIfMissingIgnoreCase("abc", null) = "abc"
5724 * StringUtils.prependIfMissingIgnoreCase("", "xyz") = "xyz"
5725 * StringUtils.prependIfMissingIgnoreCase("abc", "xyz") = "xyzabc"
5726 * StringUtils.prependIfMissingIgnoreCase("xyzabc", "xyz") = "xyzabc"
5727 * StringUtils.prependIfMissingIgnoreCase("XYZabc", "xyz") = "XYZabc"
5728 * </pre>
5729 * <p>With additional prefixes,</p>
5730 * <pre>
5731 * StringUtils.prependIfMissingIgnoreCase(null, null, null) = null
5732 * StringUtils.prependIfMissingIgnoreCase("abc", null, null) = "abc"
5733 * StringUtils.prependIfMissingIgnoreCase("", "xyz", null) = "xyz"
5734 * StringUtils.prependIfMissingIgnoreCase("abc", "xyz", new CharSequence[]{null}) = "xyzabc"
5735 * StringUtils.prependIfMissingIgnoreCase("abc", "xyz", "") = "abc"
5736 * StringUtils.prependIfMissingIgnoreCase("abc", "xyz", "mno") = "xyzabc"
5737 * StringUtils.prependIfMissingIgnoreCase("xyzabc", "xyz", "mno") = "xyzabc"
5738 * StringUtils.prependIfMissingIgnoreCase("mnoabc", "xyz", "mno") = "mnoabc"
5739 * StringUtils.prependIfMissingIgnoreCase("XYZabc", "xyz", "mno") = "XYZabc"
5740 * StringUtils.prependIfMissingIgnoreCase("MNOabc", "xyz", "mno") = "MNOabc"
5741 * </pre>
5742 *
5743 * @param str The string.
5744 * @param prefix The prefix to prepend to the start of the string.
5745 * @param prefixes Additional prefixes that are valid (optional).
5746 *
5747 * @return A new String if prefix was prepended, the same string otherwise.
5748 *
5749 * @since 3.2
5750 */
5751 public static String prependIfMissingIgnoreCase(final String str, final CharSequence prefix, final CharSequence... prefixes) {
5752 return prependIfMissing(str, prefix, true, prefixes);
5753 }
5754
5755 /**
5756 * Removes all occurrences of a character from within the source string.
5757 *
5758 * <p>A {@code null} source string will return {@code null}.
5759 * An empty ("") source string will return the empty string.</p>
5760 *
5761 * <pre>
5762 * StringUtils.remove(null, *) = null
5763 * StringUtils.remove("", *) = ""
5764 * StringUtils.remove("queued", 'u') = "qeed"
5765 * StringUtils.remove("queued", 'z') = "queued"
5766 * </pre>
5767 *
5768 * @param str the source String to search, may be null
5769 * @param remove the char to search for and remove, may be null
5770 * @return the substring with the char removed if found,
5771 * {@code null} if null String input
5772 * @since 2.1
5773 */
5774 public static String remove(final String str, final char remove) {
5775 if (isEmpty(str) || str.indexOf(remove) == INDEX_NOT_FOUND) {
5776 return str;
5777 }
5778 final char[] chars = str.toCharArray();
5779 int pos = 0;
5780 for (int i = 0; i < chars.length; i++) {
5781 if (chars[i] != remove) {
5782 chars[pos++] = chars[i];
5783 }
5784 }
5785 return new String(chars, 0, pos);
5786 }
5787
5788 /**
5789 * Removes all occurrences of a substring from within the source string.
5790 *
5791 * <p>A {@code null} source string will return {@code null}.
5792 * An empty ("") source string will return the empty string.
5793 * A {@code null} remove string will return the source string.
5794 * An empty ("") remove string will return the source string.</p>
5795 *
5796 * <pre>
5797 * StringUtils.remove(null, *) = null
5798 * StringUtils.remove("", *) = ""
5799 * StringUtils.remove(*, null) = *
5800 * StringUtils.remove(*, "") = *
5801 * StringUtils.remove("queued", "ue") = "qd"
5802 * StringUtils.remove("queued", "zz") = "queued"
5803 * </pre>
5804 *
5805 * @param str the source String to search, may be null
5806 * @param remove the String to search for and remove, may be null
5807 * @return the substring with the string removed if found,
5808 * {@code null} if null String input
5809 * @since 2.1
5810 */
5811 public static String remove(final String str, final String remove) {
5812 if (isEmpty(str) || isEmpty(remove)) {
5813 return str;
5814 }
5815 return replace(str, remove, EMPTY, -1);
5816 }
5817
5818 /**
5819 * Removes each substring of the text String that matches the given regular expression.
5820 *
5821 * This method is a {@code null} safe equivalent to:
5822 * <ul>
5823 * <li>{@code text.replaceAll(regex, StringUtils.EMPTY)}</li>
5824 * <li>{@code Pattern.compile(regex).matcher(text).replaceAll(StringUtils.EMPTY)}</li>
5825 * </ul>
5826 *
5827 * <p>A {@code null} reference passed to this method is a no-op.</p>
5828 *
5829 * <p>Unlike in the {@link #removePattern(String, String)} method, the {@link Pattern#DOTALL} option
5830 * is NOT automatically added.
5831 * To use the DOTALL option prepend {@code "(?s)"} to the regex.
5832 * DOTALL is also known as single-line mode in Perl.</p>
5833 *
5834 * <pre>
5835 * StringUtils.removeAll(null, *) = null
5836 * StringUtils.removeAll("any", (String) null) = "any"
5837 * StringUtils.removeAll("any", "") = "any"
5838 * StringUtils.removeAll("any", ".*") = ""
5839 * StringUtils.removeAll("any", ".+") = ""
5840 * StringUtils.removeAll("abc", ".?") = ""
5841 * StringUtils.removeAll("A<__>\n<__>B", "<.*>") = "A\nB"
5842 * StringUtils.removeAll("A<__>\n<__>B", "(?s)<.*>") = "AB"
5843 * StringUtils.removeAll("ABCabc123abc", "[a-z]") = "ABC123"
5844 * </pre>
5845 *
5846 * @param text text to remove from, may be null
5847 * @param regex the regular expression to which this string is to be matched
5848 * @return the text with any removes processed,
5849 * {@code null} if null String input
5850 *
5851 * @throws java.util.regex.PatternSyntaxException
5852 * if the regular expression's syntax is invalid
5853 *
5854 * @see #replaceAll(String, String, String)
5855 * @see #removePattern(String, String)
5856 * @see String#replaceAll(String, String)
5857 * @see java.util.regex.Pattern
5858 * @see java.util.regex.Pattern#DOTALL
5859 * @since 3.5
5860 *
5861 * @deprecated Moved to RegExUtils.
5862 */
5863 @Deprecated
5864 public static String removeAll(final String text, final String regex) {
5865 return RegExUtils.removeAll(text, regex);
5866 }
5867
5868 /**
5869 * Removes a substring only if it is at the end of a source string,
5870 * otherwise returns the source string.
5871 *
5872 * <p>A {@code null} source string will return {@code null}.
5873 * An empty ("") source string will return the empty string.
5874 * A {@code null} search string will return the source string.</p>
5875 *
5876 * <pre>
5877 * StringUtils.removeEnd(null, *) = null
5878 * StringUtils.removeEnd("", *) = ""
5879 * StringUtils.removeEnd(*, null) = *
5880 * StringUtils.removeEnd("www.domain.com", ".com.") = "www.domain.com"
5881 * StringUtils.removeEnd("www.domain.com", ".com") = "www.domain"
5882 * StringUtils.removeEnd("www.domain.com", "domain") = "www.domain.com"
5883 * StringUtils.removeEnd("abc", "") = "abc"
5884 * </pre>
5885 *
5886 * @param str the source String to search, may be null
5887 * @param remove the String to search for and remove, may be null
5888 * @return the substring with the string removed if found,
5889 * {@code null} if null String input
5890 * @since 2.1
5891 */
5892 public static String removeEnd(final String str, final String remove) {
5893 if (isEmpty(str) || isEmpty(remove)) {
5894 return str;
5895 }
5896 if (str.endsWith(remove)) {
5897 return str.substring(0, str.length() - remove.length());
5898 }
5899 return str;
5900 }
5901
5902 /**
5903 * Case insensitive removal of a substring if it is at the end of a source string,
5904 * otherwise returns the source string.
5905 *
5906 * <p>A {@code null} source string will return {@code null}.
5907 * An empty ("") source string will return the empty string.
5908 * A {@code null} search string will return the source string.</p>
5909 *
5910 * <pre>
5911 * StringUtils.removeEndIgnoreCase(null, *) = null
5912 * StringUtils.removeEndIgnoreCase("", *) = ""
5913 * StringUtils.removeEndIgnoreCase(*, null) = *
5914 * StringUtils.removeEndIgnoreCase("www.domain.com", ".com.") = "www.domain.com"
5915 * StringUtils.removeEndIgnoreCase("www.domain.com", ".com") = "www.domain"
5916 * StringUtils.removeEndIgnoreCase("www.domain.com", "domain") = "www.domain.com"
5917 * StringUtils.removeEndIgnoreCase("abc", "") = "abc"
5918 * StringUtils.removeEndIgnoreCase("www.domain.com", ".COM") = "www.domain")
5919 * StringUtils.removeEndIgnoreCase("www.domain.COM", ".com") = "www.domain")
5920 * </pre>
5921 *
5922 * @param str the source String to search, may be null
5923 * @param remove the String to search for (case-insensitive) and remove, may be null
5924 * @return the substring with the string removed if found,
5925 * {@code null} if null String input
5926 * @since 2.4
5927 */
5928 public static String removeEndIgnoreCase(final String str, final String remove) {
5929 if (isEmpty(str) || isEmpty(remove)) {
5930 return str;
5931 }
5932 if (endsWithIgnoreCase(str, remove)) {
5933 return str.substring(0, str.length() - remove.length());
5934 }
5935 return str;
5936 }
5937
5938 /**
5939 * Removes the first substring of the text string that matches the given regular expression.
5940 *
5941 * This method is a {@code null} safe equivalent to:
5942 * <ul>
5943 * <li>{@code text.replaceFirst(regex, StringUtils.EMPTY)}</li>
5944 * <li>{@code Pattern.compile(regex).matcher(text).replaceFirst(StringUtils.EMPTY)}</li>
5945 * </ul>
5946 *
5947 * <p>A {@code null} reference passed to this method is a no-op.</p>
5948 *
5949 * <p>The {@link Pattern#DOTALL} option is NOT automatically added.
5950 * To use the DOTALL option prepend {@code "(?s)"} to the regex.
5951 * DOTALL is also known as single-line mode in Perl.</p>
5952 *
5953 * <pre>
5954 * StringUtils.removeFirst(null, *) = null
5955 * StringUtils.removeFirst("any", (String) null) = "any"
5956 * StringUtils.removeFirst("any", "") = "any"
5957 * StringUtils.removeFirst("any", ".*") = ""
5958 * StringUtils.removeFirst("any", ".+") = ""
5959 * StringUtils.removeFirst("abc", ".?") = "bc"
5960 * StringUtils.removeFirst("A<__>\n<__>B", "<.*>") = "A\n<__>B"
5961 * StringUtils.removeFirst("A<__>\n<__>B", "(?s)<.*>") = "AB"
5962 * StringUtils.removeFirst("ABCabc123", "[a-z]") = "ABCbc123"
5963 * StringUtils.removeFirst("ABCabc123abc", "[a-z]+") = "ABC123abc"
5964 * </pre>
5965 *
5966 * @param text text to remove from, may be null
5967 * @param regex the regular expression to which this string is to be matched
5968 * @return the text with the first replacement processed,
5969 * {@code null} if null String input
5970 *
5971 * @throws java.util.regex.PatternSyntaxException
5972 * if the regular expression's syntax is invalid
5973 *
5974 * @see #replaceFirst(String, String, String)
5975 * @see String#replaceFirst(String, String)
5976 * @see java.util.regex.Pattern
5977 * @see java.util.regex.Pattern#DOTALL
5978 * @since 3.5
5979 *
5980 * @deprecated Moved to RegExUtils.
5981 */
5982 @Deprecated
5983 public static String removeFirst(final String text, final String regex) {
5984 return replaceFirst(text, regex, EMPTY);
5985 }
5986
5987 /**
5988 * Case insensitive removal of all occurrences of a substring from within
5989 * the source string.
5990 *
5991 * <p>
5992 * A {@code null} source string will return {@code null}. An empty ("")
5993 * source string will return the empty string. A {@code null} remove string
5994 * will return the source string. An empty ("") remove string will return
5995 * the source string.
5996 * </p>
5997 *
5998 * <pre>
5999 * StringUtils.removeIgnoreCase(null, *) = null
6000 * StringUtils.removeIgnoreCase("", *) = ""
6001 * StringUtils.removeIgnoreCase(*, null) = *
6002 * StringUtils.removeIgnoreCase(*, "") = *
6003 * StringUtils.removeIgnoreCase("queued", "ue") = "qd"
6004 * StringUtils.removeIgnoreCase("queued", "zz") = "queued"
6005 * StringUtils.removeIgnoreCase("quEUed", "UE") = "qd"
6006 * StringUtils.removeIgnoreCase("queued", "zZ") = "queued"
6007 * </pre>
6008 *
6009 * @param str
6010 * the source String to search, may be null
6011 * @param remove
6012 * the String to search for (case-insensitive) and remove, may be
6013 * null
6014 * @return the substring with the string removed if found, {@code null} if
6015 * null String input
6016 * @since 3.5
6017 */
6018 public static String removeIgnoreCase(final String str, final String remove) {
6019 return replaceIgnoreCase(str, remove, EMPTY, -1);
6020 }
6021
6022 /**
6023 * Removes each substring of the source String that matches the given regular expression using the DOTALL option.
6024 *
6025 * This call is a {@code null} safe equivalent to:
6026 * <ul>
6027 * <li>{@code source.replaceAll("(?s)" + regex, StringUtils.EMPTY)}</li>
6028 * <li>{@code Pattern.compile(regex, Pattern.DOTALL).matcher(source).replaceAll(StringUtils.EMPTY)}</li>
6029 * </ul>
6030 *
6031 * <p>A {@code null} reference passed to this method is a no-op.</p>
6032 *
6033 * <pre>
6034 * StringUtils.removePattern(null, *) = null
6035 * StringUtils.removePattern("any", (String) null) = "any"
6036 * StringUtils.removePattern("A<__>\n<__>B", "<.*>") = "AB"
6037 * StringUtils.removePattern("ABCabc123", "[a-z]") = "ABC123"
6038 * </pre>
6039 *
6040 * @param source
6041 * the source string
6042 * @param regex
6043 * the regular expression to which this string is to be matched
6044 * @return The resulting {@link String}
6045 * @see #replacePattern(String, String, String)
6046 * @see String#replaceAll(String, String)
6047 * @see Pattern#DOTALL
6048 * @since 3.2
6049 * @since 3.5 Changed {@code null} reference passed to this method is a no-op.
6050 *
6051 * @deprecated Moved to RegExUtils.
6052 */
6053 @Deprecated
6054 public static String removePattern(final String source, final String regex) {
6055 return RegExUtils.removePattern(source, regex);
6056 }
6057
6058 /**
6059 * Removes a char only if it is at the beginning of a source string,
6060 * otherwise returns the source string.
6061 *
6062 * <p>A {@code null} source string will return {@code null}.
6063 * An empty ("") source string will return the empty string.
6064 * A {@code null} search char will return the source string.</p>
6065 *
6066 * <pre>
6067 * StringUtils.removeStart(null, *) = null
6068 * StringUtils.removeStart("", *) = ""
6069 * StringUtils.removeStart(*, null) = *
6070 * StringUtils.removeStart("/path", '/') = "path"
6071 * StringUtils.removeStart("path", '/') = "path"
6072 * StringUtils.removeStart("path", 0) = "path"
6073 * </pre>
6074 *
6075 * @param str the source String to search, may be null.
6076 * @param remove the char to search for and remove.
6077 * @return the substring with the char removed if found,
6078 * {@code null} if null String input.
6079 * @since 3.13.0
6080 */
6081 public static String removeStart(final String str, final char remove) {
6082 if (isEmpty(str)) {
6083 return str;
6084 }
6085 return str.charAt(0) == remove ? str.substring(1) : str;
6086 }
6087
6088 /**
6089 * Removes a substring only if it is at the beginning of a source string,
6090 * otherwise returns the source string.
6091 *
6092 * <p>A {@code null} source string will return {@code null}.
6093 * An empty ("") source string will return the empty string.
6094 * A {@code null} search string will return the source string.</p>
6095 *
6096 * <pre>
6097 * StringUtils.removeStart(null, *) = null
6098 * StringUtils.removeStart("", *) = ""
6099 * StringUtils.removeStart(*, null) = *
6100 * StringUtils.removeStart("www.domain.com", "www.") = "domain.com"
6101 * StringUtils.removeStart("domain.com", "www.") = "domain.com"
6102 * StringUtils.removeStart("www.domain.com", "domain") = "www.domain.com"
6103 * StringUtils.removeStart("abc", "") = "abc"
6104 * </pre>
6105 *
6106 * @param str the source String to search, may be null
6107 * @param remove the String to search for and remove, may be null
6108 * @return the substring with the string removed if found,
6109 * {@code null} if null String input
6110 * @since 2.1
6111 */
6112 public static String removeStart(final String str, final String remove) {
6113 if (isEmpty(str) || isEmpty(remove)) {
6114 return str;
6115 }
6116 if (str.startsWith(remove)) {
6117 return str.substring(remove.length());
6118 }
6119 return str;
6120 }
6121
6122 /**
6123 * Case insensitive removal of a substring if it is at the beginning of a source string,
6124 * otherwise returns the source string.
6125 *
6126 * <p>A {@code null} source string will return {@code null}.
6127 * An empty ("") source string will return the empty string.
6128 * A {@code null} search string will return the source string.</p>
6129 *
6130 * <pre>
6131 * StringUtils.removeStartIgnoreCase(null, *) = null
6132 * StringUtils.removeStartIgnoreCase("", *) = ""
6133 * StringUtils.removeStartIgnoreCase(*, null) = *
6134 * StringUtils.removeStartIgnoreCase("www.domain.com", "www.") = "domain.com"
6135 * StringUtils.removeStartIgnoreCase("www.domain.com", "WWW.") = "domain.com"
6136 * StringUtils.removeStartIgnoreCase("domain.com", "www.") = "domain.com"
6137 * StringUtils.removeStartIgnoreCase("www.domain.com", "domain") = "www.domain.com"
6138 * StringUtils.removeStartIgnoreCase("abc", "") = "abc"
6139 * </pre>
6140 *
6141 * @param str the source String to search, may be null
6142 * @param remove the String to search for (case-insensitive) and remove, may be null
6143 * @return the substring with the string removed if found,
6144 * {@code null} if null String input
6145 * @since 2.4
6146 */
6147 public static String removeStartIgnoreCase(final String str, final String remove) {
6148 if (str != null && startsWithIgnoreCase(str, remove)) {
6149 return str.substring(length(remove));
6150 }
6151 return str;
6152 }
6153
6154 /**
6155 * Returns padding using the specified delimiter repeated
6156 * to a given length.
6157 *
6158 * <pre>
6159 * StringUtils.repeat('e', 0) = ""
6160 * StringUtils.repeat('e', 3) = "eee"
6161 * StringUtils.repeat('e', -2) = ""
6162 * </pre>
6163 *
6164 * <p>Note: this method does not support padding with
6165 * <a href="https://www.unicode.org/glossary/#supplementary_character">Unicode Supplementary Characters</a>
6166 * as they require a pair of {@code char}s to be represented.
6167 * If you are needing to support full I18N of your applications
6168 * consider using {@link #repeat(String, int)} instead.
6169 * </p>
6170 *
6171 * @param ch character to repeat
6172 * @param repeat number of times to repeat char, negative treated as zero
6173 * @return String with repeated character
6174 * @see #repeat(String, int)
6175 */
6176 public static String repeat(final char ch, final int repeat) {
6177 if (repeat <= 0) {
6178 return EMPTY;
6179 }
6180 final char[] buf = new char[repeat];
6181 Arrays.fill(buf, ch);
6182 return new String(buf);
6183 }
6184
6185 /**
6186 * Repeat a String {@code repeat} times to form a
6187 * new String.
6188 *
6189 * <pre>
6190 * StringUtils.repeat(null, 2) = null
6191 * StringUtils.repeat("", 0) = ""
6192 * StringUtils.repeat("", 2) = ""
6193 * StringUtils.repeat("a", 3) = "aaa"
6194 * StringUtils.repeat("ab", 2) = "abab"
6195 * StringUtils.repeat("a", -2) = ""
6196 * </pre>
6197 *
6198 * @param str the String to repeat, may be null
6199 * @param repeat number of times to repeat str, negative treated as zero
6200 * @return a new String consisting of the original String repeated,
6201 * {@code null} if null String input
6202 */
6203 public static String repeat(final String str, final int repeat) {
6204 // Performance tuned for 2.0 (JDK1.4)
6205 if (str == null) {
6206 return null;
6207 }
6208 if (repeat <= 0) {
6209 return EMPTY;
6210 }
6211 final int inputLength = str.length();
6212 if (repeat == 1 || inputLength == 0) {
6213 return str;
6214 }
6215 if (inputLength == 1 && repeat <= PAD_LIMIT) {
6216 return repeat(str.charAt(0), repeat);
6217 }
6218
6219 final int outputLength = inputLength * repeat;
6220 switch (inputLength) {
6221 case 1 :
6222 return repeat(str.charAt(0), repeat);
6223 case 2 :
6224 final char ch0 = str.charAt(0);
6225 final char ch1 = str.charAt(1);
6226 final char[] output2 = new char[outputLength];
6227 for (int i = repeat * 2 - 2; i >= 0; i--, i--) {
6228 output2[i] = ch0;
6229 output2[i + 1] = ch1;
6230 }
6231 return new String(output2);
6232 default :
6233 final StringBuilder buf = new StringBuilder(outputLength);
6234 for (int i = 0; i < repeat; i++) {
6235 buf.append(str);
6236 }
6237 return buf.toString();
6238 }
6239 }
6240
6241 /**
6242 * Repeat a String {@code repeat} times to form a
6243 * new String, with a String separator injected each time.
6244 *
6245 * <pre>
6246 * StringUtils.repeat(null, null, 2) = null
6247 * StringUtils.repeat(null, "x", 2) = null
6248 * StringUtils.repeat("", null, 0) = ""
6249 * StringUtils.repeat("", "", 2) = ""
6250 * StringUtils.repeat("", "x", 3) = "xx"
6251 * StringUtils.repeat("?", ", ", 3) = "?, ?, ?"
6252 * </pre>
6253 *
6254 * @param str the String to repeat, may be null
6255 * @param separator the String to inject, may be null
6256 * @param repeat number of times to repeat str, negative treated as zero
6257 * @return a new String consisting of the original String repeated,
6258 * {@code null} if null String input
6259 * @since 2.5
6260 */
6261 public static String repeat(final String str, final String separator, final int repeat) {
6262 if (str == null || separator == null) {
6263 return repeat(str, repeat);
6264 }
6265 // given that repeat(String, int) is quite optimized, better to rely on it than try and splice this into it
6266 final String result = repeat(str + separator, repeat);
6267 return removeEnd(result, separator);
6268 }
6269
6270 /**
6271 * Replaces all occurrences of a String within another String.
6272 *
6273 * <p>A {@code null} reference passed to this method is a no-op.</p>
6274 *
6275 * <pre>
6276 * StringUtils.replace(null, *, *) = null
6277 * StringUtils.replace("", *, *) = ""
6278 * StringUtils.replace("any", null, *) = "any"
6279 * StringUtils.replace("any", *, null) = "any"
6280 * StringUtils.replace("any", "", *) = "any"
6281 * StringUtils.replace("aba", "a", null) = "aba"
6282 * StringUtils.replace("aba", "a", "") = "b"
6283 * StringUtils.replace("aba", "a", "z") = "zbz"
6284 * </pre>
6285 *
6286 * @see #replace(String text, String searchString, String replacement, int max)
6287 * @param text text to search and replace in, may be null
6288 * @param searchString the String to search for, may be null
6289 * @param replacement the String to replace it with, may be null
6290 * @return the text with any replacements processed,
6291 * {@code null} if null String input
6292 */
6293 public static String replace(final String text, final String searchString, final String replacement) {
6294 return replace(text, searchString, replacement, -1);
6295 }
6296
6297 /**
6298 * Replaces a String with another String inside a larger String,
6299 * for the first {@code max} values of the search String.
6300 *
6301 * <p>A {@code null} reference passed to this method is a no-op.</p>
6302 *
6303 * <pre>
6304 * StringUtils.replace(null, *, *, *) = null
6305 * StringUtils.replace("", *, *, *) = ""
6306 * StringUtils.replace("any", null, *, *) = "any"
6307 * StringUtils.replace("any", *, null, *) = "any"
6308 * StringUtils.replace("any", "", *, *) = "any"
6309 * StringUtils.replace("any", *, *, 0) = "any"
6310 * StringUtils.replace("abaa", "a", null, -1) = "abaa"
6311 * StringUtils.replace("abaa", "a", "", -1) = "b"
6312 * StringUtils.replace("abaa", "a", "z", 0) = "abaa"
6313 * StringUtils.replace("abaa", "a", "z", 1) = "zbaa"
6314 * StringUtils.replace("abaa", "a", "z", 2) = "zbza"
6315 * StringUtils.replace("abaa", "a", "z", -1) = "zbzz"
6316 * </pre>
6317 *
6318 * @param text text to search and replace in, may be null
6319 * @param searchString the String to search for, may be null
6320 * @param replacement the String to replace it with, may be null
6321 * @param max maximum number of values to replace, or {@code -1} if no maximum
6322 * @return the text with any replacements processed,
6323 * {@code null} if null String input
6324 */
6325 public static String replace(final String text, final String searchString, final String replacement, final int max) {
6326 return replace(text, searchString, replacement, max, false);
6327 }
6328
6329 /**
6330 * Replaces a String with another String inside a larger String,
6331 * for the first {@code max} values of the search String,
6332 * case-sensitively/insensitively based on {@code ignoreCase} value.
6333 *
6334 * <p>A {@code null} reference passed to this method is a no-op.</p>
6335 *
6336 * <pre>
6337 * StringUtils.replace(null, *, *, *, false) = null
6338 * StringUtils.replace("", *, *, *, false) = ""
6339 * StringUtils.replace("any", null, *, *, false) = "any"
6340 * StringUtils.replace("any", *, null, *, false) = "any"
6341 * StringUtils.replace("any", "", *, *, false) = "any"
6342 * StringUtils.replace("any", *, *, 0, false) = "any"
6343 * StringUtils.replace("abaa", "a", null, -1, false) = "abaa"
6344 * StringUtils.replace("abaa", "a", "", -1, false) = "b"
6345 * StringUtils.replace("abaa", "a", "z", 0, false) = "abaa"
6346 * StringUtils.replace("abaa", "A", "z", 1, false) = "abaa"
6347 * StringUtils.replace("abaa", "A", "z", 1, true) = "zbaa"
6348 * StringUtils.replace("abAa", "a", "z", 2, true) = "zbza"
6349 * StringUtils.replace("abAa", "a", "z", -1, true) = "zbzz"
6350 * </pre>
6351 *
6352 * @param text text to search and replace in, may be null
6353 * @param searchString the String to search for (case-insensitive), may be null
6354 * @param replacement the String to replace it with, may be null
6355 * @param max maximum number of values to replace, or {@code -1} if no maximum
6356 * @param ignoreCase if true replace is case-insensitive, otherwise case-sensitive
6357 * @return the text with any replacements processed,
6358 * {@code null} if null String input
6359 */
6360 private static String replace(final String text, String searchString, final String replacement, int max, final boolean ignoreCase) {
6361 if (isEmpty(text) || isEmpty(searchString) || replacement == null || max == 0) {
6362 return text;
6363 }
6364 if (ignoreCase) {
6365 searchString = searchString.toLowerCase();
6366 }
6367 int start = 0;
6368 int end = ignoreCase ? indexOfIgnoreCase(text, searchString, start) : indexOf(text, searchString, start);
6369 if (end == INDEX_NOT_FOUND) {
6370 return text;
6371 }
6372 final int replLength = searchString.length();
6373 int increase = Math.max(replacement.length() - replLength, 0);
6374 increase *= max < 0 ? 16 : Math.min(max, 64);
6375 final StringBuilder buf = new StringBuilder(text.length() + increase);
6376 while (end != INDEX_NOT_FOUND) {
6377 buf.append(text, start, end).append(replacement);
6378 start = end + replLength;
6379 if (--max == 0) {
6380 break;
6381 }
6382 end = ignoreCase ? indexOfIgnoreCase(text, searchString, start) : indexOf(text, searchString, start);
6383 }
6384 buf.append(text, start, text.length());
6385 return buf.toString();
6386 }
6387
6388 /**
6389 * Replaces each substring of the text String that matches the given regular expression
6390 * with the given replacement.
6391 *
6392 * This method is a {@code null} safe equivalent to:
6393 * <ul>
6394 * <li>{@code text.replaceAll(regex, replacement)}</li>
6395 * <li>{@code Pattern.compile(regex).matcher(text).replaceAll(replacement)}</li>
6396 * </ul>
6397 *
6398 * <p>A {@code null} reference passed to this method is a no-op.</p>
6399 *
6400 * <p>Unlike in the {@link #replacePattern(String, String, String)} method, the {@link Pattern#DOTALL} option
6401 * is NOT automatically added.
6402 * To use the DOTALL option prepend {@code "(?s)"} to the regex.
6403 * DOTALL is also known as single-line mode in Perl.</p>
6404 *
6405 * <pre>
6406 * StringUtils.replaceAll(null, *, *) = null
6407 * StringUtils.replaceAll("any", (String) null, *) = "any"
6408 * StringUtils.replaceAll("any", *, null) = "any"
6409 * StringUtils.replaceAll("", "", "zzz") = "zzz"
6410 * StringUtils.replaceAll("", ".*", "zzz") = "zzz"
6411 * StringUtils.replaceAll("", ".+", "zzz") = ""
6412 * StringUtils.replaceAll("abc", "", "ZZ") = "ZZaZZbZZcZZ"
6413 * StringUtils.replaceAll("<__>\n<__>", "<.*>", "z") = "z\nz"
6414 * StringUtils.replaceAll("<__>\n<__>", "(?s)<.*>", "z") = "z"
6415 * StringUtils.replaceAll("ABCabc123", "[a-z]", "_") = "ABC___123"
6416 * StringUtils.replaceAll("ABCabc123", "[^A-Z0-9]+", "_") = "ABC_123"
6417 * StringUtils.replaceAll("ABCabc123", "[^A-Z0-9]+", "") = "ABC123"
6418 * StringUtils.replaceAll("Lorem ipsum dolor sit", "( +)([a-z]+)", "_$2") = "Lorem_ipsum_dolor_sit"
6419 * </pre>
6420 *
6421 * @param text text to search and replace in, may be null
6422 * @param regex the regular expression to which this string is to be matched
6423 * @param replacement the string to be substituted for each match
6424 * @return the text with any replacements processed,
6425 * {@code null} if null String input
6426 *
6427 * @throws java.util.regex.PatternSyntaxException
6428 * if the regular expression's syntax is invalid
6429 *
6430 * @see #replacePattern(String, String, String)
6431 * @see String#replaceAll(String, String)
6432 * @see java.util.regex.Pattern
6433 * @see java.util.regex.Pattern#DOTALL
6434 * @since 3.5
6435 *
6436 * @deprecated Moved to RegExUtils.
6437 */
6438 @Deprecated
6439 public static String replaceAll(final String text, final String regex, final String replacement) {
6440 return RegExUtils.replaceAll(text, regex, replacement);
6441 }
6442
6443 /**
6444 * Replaces all occurrences of a character in a String with another.
6445 * This is a null-safe version of {@link String#replace(char, char)}.
6446 *
6447 * <p>A {@code null} string input returns {@code null}.
6448 * An empty ("") string input returns an empty string.</p>
6449 *
6450 * <pre>
6451 * StringUtils.replaceChars(null, *, *) = null
6452 * StringUtils.replaceChars("", *, *) = ""
6453 * StringUtils.replaceChars("abcba", 'b', 'y') = "aycya"
6454 * StringUtils.replaceChars("abcba", 'z', 'y') = "abcba"
6455 * </pre>
6456 *
6457 * @param str String to replace characters in, may be null
6458 * @param searchChar the character to search for, may be null
6459 * @param replaceChar the character to replace, may be null
6460 * @return modified String, {@code null} if null string input
6461 * @since 2.0
6462 */
6463 public static String replaceChars(final String str, final char searchChar, final char replaceChar) {
6464 if (str == null) {
6465 return null;
6466 }
6467 return str.replace(searchChar, replaceChar);
6468 }
6469
6470 /**
6471 * Replaces multiple characters in a String in one go.
6472 * This method can also be used to delete characters.
6473 *
6474 * <p>For example:<br>
6475 * {@code replaceChars("hello", "ho", "jy") = jelly}.</p>
6476 *
6477 * <p>A {@code null} string input returns {@code null}.
6478 * An empty ("") string input returns an empty string.
6479 * A null or empty set of search characters returns the input string.</p>
6480 *
6481 * <p>The length of the search characters should normally equal the length
6482 * of the replace characters.
6483 * If the search characters is longer, then the extra search characters
6484 * are deleted.
6485 * If the search characters is shorter, then the extra replace characters
6486 * are ignored.</p>
6487 *
6488 * <pre>
6489 * StringUtils.replaceChars(null, *, *) = null
6490 * StringUtils.replaceChars("", *, *) = ""
6491 * StringUtils.replaceChars("abc", null, *) = "abc"
6492 * StringUtils.replaceChars("abc", "", *) = "abc"
6493 * StringUtils.replaceChars("abc", "b", null) = "ac"
6494 * StringUtils.replaceChars("abc", "b", "") = "ac"
6495 * StringUtils.replaceChars("abcba", "bc", "yz") = "ayzya"
6496 * StringUtils.replaceChars("abcba", "bc", "y") = "ayya"
6497 * StringUtils.replaceChars("abcba", "bc", "yzx") = "ayzya"
6498 * </pre>
6499 *
6500 * @param str String to replace characters in, may be null
6501 * @param searchChars a set of characters to search for, may be null
6502 * @param replaceChars a set of characters to replace, may be null
6503 * @return modified String, {@code null} if null string input
6504 * @since 2.0
6505 */
6506 public static String replaceChars(final String str, final String searchChars, String replaceChars) {
6507 if (isEmpty(str) || isEmpty(searchChars)) {
6508 return str;
6509 }
6510 if (replaceChars == null) {
6511 replaceChars = EMPTY;
6512 }
6513 boolean modified = false;
6514 final int replaceCharsLength = replaceChars.length();
6515 final int strLength = str.length();
6516 final StringBuilder buf = new StringBuilder(strLength);
6517 for (int i = 0; i < strLength; i++) {
6518 final char ch = str.charAt(i);
6519 final int index = searchChars.indexOf(ch);
6520 if (index >= 0) {
6521 modified = true;
6522 if (index < replaceCharsLength) {
6523 buf.append(replaceChars.charAt(index));
6524 }
6525 } else {
6526 buf.append(ch);
6527 }
6528 }
6529 if (modified) {
6530 return buf.toString();
6531 }
6532 return str;
6533 }
6534
6535 /**
6536 * Replaces all occurrences of Strings within another String.
6537 *
6538 * <p>
6539 * A {@code null} reference passed to this method is a no-op, or if
6540 * any "search string" or "string to replace" is null, that replace will be
6541 * ignored. This will not repeat. For repeating replaces, call the
6542 * overloaded method.
6543 * </p>
6544 *
6545 * <pre>
6546 * StringUtils.replaceEach(null, *, *) = null
6547 * StringUtils.replaceEach("", *, *) = ""
6548 * StringUtils.replaceEach("aba", null, null) = "aba"
6549 * StringUtils.replaceEach("aba", new String[0], null) = "aba"
6550 * StringUtils.replaceEach("aba", null, new String[0]) = "aba"
6551 * StringUtils.replaceEach("aba", new String[]{"a"}, null) = "aba"
6552 * StringUtils.replaceEach("aba", new String[]{"a"}, new String[]{""}) = "b"
6553 * StringUtils.replaceEach("aba", new String[]{null}, new String[]{"a"}) = "aba"
6554 * StringUtils.replaceEach("abcde", new String[]{"ab", "d"}, new String[]{"w", "t"}) = "wcte"
6555 * (example of how it does not repeat)
6556 * StringUtils.replaceEach("abcde", new String[]{"ab", "d"}, new String[]{"d", "t"}) = "dcte"
6557 * </pre>
6558 *
6559 * @param text
6560 * text to search and replace in, no-op if null
6561 * @param searchList
6562 * the Strings to search for, no-op if null
6563 * @param replacementList
6564 * the Strings to replace them with, no-op if null
6565 * @return the text with any replacements processed, {@code null} if
6566 * null String input
6567 * @throws IllegalArgumentException
6568 * if the lengths of the arrays are not the same (null is ok,
6569 * and/or size 0)
6570 * @since 2.4
6571 */
6572 public static String replaceEach(final String text, final String[] searchList, final String[] replacementList) {
6573 return replaceEach(text, searchList, replacementList, false, 0);
6574 }
6575
6576 /**
6577 * Replace all occurrences of Strings within another String.
6578 * This is a private recursive helper method for {@link #replaceEachRepeatedly(String, String[], String[])} and
6579 * {@link #replaceEach(String, String[], String[])}
6580 *
6581 * <p>
6582 * A {@code null} reference passed to this method is a no-op, or if
6583 * any "search string" or "string to replace" is null, that replace will be
6584 * ignored.
6585 * </p>
6586 *
6587 * <pre>
6588 * StringUtils.replaceEach(null, *, *, *, *) = null
6589 * StringUtils.replaceEach("", *, *, *, *) = ""
6590 * StringUtils.replaceEach("aba", null, null, *, *) = "aba"
6591 * StringUtils.replaceEach("aba", new String[0], null, *, *) = "aba"
6592 * StringUtils.replaceEach("aba", null, new String[0], *, *) = "aba"
6593 * StringUtils.replaceEach("aba", new String[]{"a"}, null, *, *) = "aba"
6594 * StringUtils.replaceEach("aba", new String[]{"a"}, new String[]{""}, *, >=0) = "b"
6595 * StringUtils.replaceEach("aba", new String[]{null}, new String[]{"a"}, *, >=0) = "aba"
6596 * StringUtils.replaceEach("abcde", new String[]{"ab", "d"}, new String[]{"w", "t"}, *, >=0) = "wcte"
6597 * (example of how it repeats)
6598 * StringUtils.replaceEach("abcde", new String[]{"ab", "d"}, new String[]{"d", "t"}, false, >=0) = "dcte"
6599 * StringUtils.replaceEach("abcde", new String[]{"ab", "d"}, new String[]{"d", "t"}, true, >=2) = "tcte"
6600 * StringUtils.replaceEach("abcde", new String[]{"ab", "d"}, new String[]{"d", "ab"}, *, *) = IllegalStateException
6601 * </pre>
6602 *
6603 * @param text
6604 * text to search and replace in, no-op if null
6605 * @param searchList
6606 * the Strings to search for, no-op if null
6607 * @param replacementList
6608 * the Strings to replace them with, no-op if null
6609 * @param repeat if true, then replace repeatedly
6610 * until there are no more possible replacements or timeToLive < 0
6611 * @param timeToLive
6612 * if less than 0 then there is a circular reference and endless
6613 * loop
6614 * @return the text with any replacements processed, {@code null} if
6615 * null String input
6616 * @throws IllegalStateException
6617 * if the search is repeating and there is an endless loop due
6618 * to outputs of one being inputs to another
6619 * @throws IllegalArgumentException
6620 * if the lengths of the arrays are not the same (null is ok,
6621 * and/or size 0)
6622 * @since 2.4
6623 */
6624 private static String replaceEach(
6625 final String text, final String[] searchList, final String[] replacementList, final boolean repeat, final int timeToLive) {
6626
6627 // mchyzer Performance note: This creates very few new objects (one major goal)
6628 // let me know if there are performance requests, we can create a harness to measure
6629
6630 // if recursing, this shouldn't be less than 0
6631 if (timeToLive < 0) {
6632 final Set<String> searchSet = new HashSet<>(Arrays.asList(searchList));
6633 final Set<String> replacementSet = new HashSet<>(Arrays.asList(replacementList));
6634 searchSet.retainAll(replacementSet);
6635 if (!searchSet.isEmpty()) {
6636 throw new IllegalStateException("Aborting to protect against StackOverflowError - " +
6637 "output of one loop is the input of another");
6638 }
6639 }
6640
6641 if (isEmpty(text) || ArrayUtils.isEmpty(searchList) || ArrayUtils.isEmpty(replacementList) || ArrayUtils.isNotEmpty(searchList) && timeToLive == -1) {
6642 return text;
6643 }
6644
6645 final int searchLength = searchList.length;
6646 final int replacementLength = replacementList.length;
6647
6648 // make sure lengths are ok, these need to be equal
6649 if (searchLength != replacementLength) {
6650 throw new IllegalArgumentException("Search and Replace array lengths don't match: "
6651 + searchLength
6652 + " vs "
6653 + replacementLength);
6654 }
6655
6656 // keep track of which still have matches
6657 final boolean[] noMoreMatchesForReplIndex = new boolean[searchLength];
6658
6659 // index on index that the match was found
6660 int textIndex = -1;
6661 int replaceIndex = -1;
6662 int tempIndex;
6663
6664 // index of replace array that will replace the search string found
6665 // NOTE: logic duplicated below START
6666 for (int i = 0; i < searchLength; i++) {
6667 if (noMoreMatchesForReplIndex[i] || isEmpty(searchList[i]) || replacementList[i] == null) {
6668 continue;
6669 }
6670 tempIndex = text.indexOf(searchList[i]);
6671
6672 // see if we need to keep searching for this
6673 if (tempIndex == -1) {
6674 noMoreMatchesForReplIndex[i] = true;
6675 } else if (textIndex == -1 || tempIndex < textIndex) {
6676 textIndex = tempIndex;
6677 replaceIndex = i;
6678 }
6679 }
6680 // NOTE: logic mostly below END
6681
6682 // no search strings found, we are done
6683 if (textIndex == -1) {
6684 return text;
6685 }
6686
6687 int start = 0;
6688
6689 // get a good guess on the size of the result buffer so it doesn't have to double if it goes over a bit
6690 int increase = 0;
6691
6692 // count the replacement text elements that are larger than their corresponding text being replaced
6693 for (int i = 0; i < searchList.length; i++) {
6694 if (searchList[i] == null || replacementList[i] == null) {
6695 continue;
6696 }
6697 final int greater = replacementList[i].length() - searchList[i].length();
6698 if (greater > 0) {
6699 increase += 3 * greater; // assume 3 matches
6700 }
6701 }
6702 // have upper-bound at 20% increase, then let Java take over
6703 increase = Math.min(increase, text.length() / 5);
6704
6705 final StringBuilder buf = new StringBuilder(text.length() + increase);
6706
6707 while (textIndex != -1) {
6708
6709 for (int i = start; i < textIndex; i++) {
6710 buf.append(text.charAt(i));
6711 }
6712 buf.append(replacementList[replaceIndex]);
6713
6714 start = textIndex + searchList[replaceIndex].length();
6715
6716 textIndex = -1;
6717 replaceIndex = -1;
6718 // find the next earliest match
6719 // NOTE: logic mostly duplicated above START
6720 for (int i = 0; i < searchLength; i++) {
6721 if (noMoreMatchesForReplIndex[i] || isEmpty(searchList[i]) || replacementList[i] == null) {
6722 continue;
6723 }
6724 tempIndex = text.indexOf(searchList[i], start);
6725
6726 // see if we need to keep searching for this
6727 if (tempIndex == -1) {
6728 noMoreMatchesForReplIndex[i] = true;
6729 } else if (textIndex == -1 || tempIndex < textIndex) {
6730 textIndex = tempIndex;
6731 replaceIndex = i;
6732 }
6733 }
6734 // NOTE: logic duplicated above END
6735
6736 }
6737 final int textLength = text.length();
6738 for (int i = start; i < textLength; i++) {
6739 buf.append(text.charAt(i));
6740 }
6741 final String result = buf.toString();
6742 if (!repeat) {
6743 return result;
6744 }
6745
6746 return replaceEach(result, searchList, replacementList, repeat, timeToLive - 1);
6747 }
6748
6749 /**
6750 * Replaces all occurrences of Strings within another String.
6751 *
6752 * <p>
6753 * A {@code null} reference passed to this method is a no-op, or if
6754 * any "search string" or "string to replace" is null, that replace will be
6755 * ignored.
6756 * </p>
6757 *
6758 * <pre>
6759 * StringUtils.replaceEachRepeatedly(null, *, *) = null
6760 * StringUtils.replaceEachRepeatedly("", *, *) = ""
6761 * StringUtils.replaceEachRepeatedly("aba", null, null) = "aba"
6762 * StringUtils.replaceEachRepeatedly("aba", new String[0], null) = "aba"
6763 * StringUtils.replaceEachRepeatedly("aba", null, new String[0]) = "aba"
6764 * StringUtils.replaceEachRepeatedly("aba", new String[]{"a"}, null) = "aba"
6765 * StringUtils.replaceEachRepeatedly("aba", new String[]{"a"}, new String[]{""}) = "b"
6766 * StringUtils.replaceEachRepeatedly("aba", new String[]{null}, new String[]{"a"}) = "aba"
6767 * StringUtils.replaceEachRepeatedly("abcde", new String[]{"ab", "d"}, new String[]{"w", "t"}) = "wcte"
6768 * (example of how it repeats)
6769 * StringUtils.replaceEachRepeatedly("abcde", new String[]{"ab", "d"}, new String[]{"d", "t"}) = "tcte"
6770 * StringUtils.replaceEachRepeatedly("abcde", new String[]{"ab", "d"}, new String[]{"d", "ab"}) = IllegalStateException
6771 * </pre>
6772 *
6773 * @param text
6774 * text to search and replace in, no-op if null
6775 * @param searchList
6776 * the Strings to search for, no-op if null
6777 * @param replacementList
6778 * the Strings to replace them with, no-op if null
6779 * @return the text with any replacements processed, {@code null} if
6780 * null String input
6781 * @throws IllegalStateException
6782 * if the search is repeating and there is an endless loop due
6783 * to outputs of one being inputs to another
6784 * @throws IllegalArgumentException
6785 * if the lengths of the arrays are not the same (null is ok,
6786 * and/or size 0)
6787 * @since 2.4
6788 */
6789 public static String replaceEachRepeatedly(final String text, final String[] searchList, final String[] replacementList) {
6790 return replaceEach(text, searchList, replacementList, true, ArrayUtils.getLength(searchList));
6791 }
6792
6793 /**
6794 * Replaces the first substring of the text string that matches the given regular expression
6795 * with the given replacement.
6796 *
6797 * This method is a {@code null} safe equivalent to:
6798 * <ul>
6799 * <li>{@code text.replaceFirst(regex, replacement)}</li>
6800 * <li>{@code Pattern.compile(regex).matcher(text).replaceFirst(replacement)}</li>
6801 * </ul>
6802 *
6803 * <p>A {@code null} reference passed to this method is a no-op.</p>
6804 *
6805 * <p>The {@link Pattern#DOTALL} option is NOT automatically added.
6806 * To use the DOTALL option prepend {@code "(?s)"} to the regex.
6807 * DOTALL is also known as single-line mode in Perl.</p>
6808 *
6809 * <pre>
6810 * StringUtils.replaceFirst(null, *, *) = null
6811 * StringUtils.replaceFirst("any", (String) null, *) = "any"
6812 * StringUtils.replaceFirst("any", *, null) = "any"
6813 * StringUtils.replaceFirst("", "", "zzz") = "zzz"
6814 * StringUtils.replaceFirst("", ".*", "zzz") = "zzz"
6815 * StringUtils.replaceFirst("", ".+", "zzz") = ""
6816 * StringUtils.replaceFirst("abc", "", "ZZ") = "ZZabc"
6817 * StringUtils.replaceFirst("<__>\n<__>", "<.*>", "z") = "z\n<__>"
6818 * StringUtils.replaceFirst("<__>\n<__>", "(?s)<.*>", "z") = "z"
6819 * StringUtils.replaceFirst("ABCabc123", "[a-z]", "_") = "ABC_bc123"
6820 * StringUtils.replaceFirst("ABCabc123abc", "[^A-Z0-9]+", "_") = "ABC_123abc"
6821 * StringUtils.replaceFirst("ABCabc123abc", "[^A-Z0-9]+", "") = "ABC123abc"
6822 * StringUtils.replaceFirst("Lorem ipsum dolor sit", "( +)([a-z]+)", "_$2") = "Lorem_ipsum dolor sit"
6823 * </pre>
6824 *
6825 * @param text text to search and replace in, may be null
6826 * @param regex the regular expression to which this string is to be matched
6827 * @param replacement the string to be substituted for the first match
6828 * @return the text with the first replacement processed,
6829 * {@code null} if null String input
6830 *
6831 * @throws java.util.regex.PatternSyntaxException
6832 * if the regular expression's syntax is invalid
6833 *
6834 * @see String#replaceFirst(String, String)
6835 * @see java.util.regex.Pattern
6836 * @see java.util.regex.Pattern#DOTALL
6837 * @since 3.5
6838 *
6839 * @deprecated Moved to RegExUtils.
6840 */
6841 @Deprecated
6842 public static String replaceFirst(final String text, final String regex, final String replacement) {
6843 return RegExUtils.replaceFirst(text, regex, replacement);
6844 }
6845
6846 /**
6847 * Case insensitively replaces all occurrences of a String within another String.
6848 *
6849 * <p>A {@code null} reference passed to this method is a no-op.</p>
6850 *
6851 * <pre>
6852 * StringUtils.replaceIgnoreCase(null, *, *) = null
6853 * StringUtils.replaceIgnoreCase("", *, *) = ""
6854 * StringUtils.replaceIgnoreCase("any", null, *) = "any"
6855 * StringUtils.replaceIgnoreCase("any", *, null) = "any"
6856 * StringUtils.replaceIgnoreCase("any", "", *) = "any"
6857 * StringUtils.replaceIgnoreCase("aba", "a", null) = "aba"
6858 * StringUtils.replaceIgnoreCase("abA", "A", "") = "b"
6859 * StringUtils.replaceIgnoreCase("aba", "A", "z") = "zbz"
6860 * </pre>
6861 *
6862 * @see #replaceIgnoreCase(String text, String searchString, String replacement, int max)
6863 * @param text text to search and replace in, may be null
6864 * @param searchString the String to search for (case-insensitive), may be null
6865 * @param replacement the String to replace it with, may be null
6866 * @return the text with any replacements processed,
6867 * {@code null} if null String input
6868 * @since 3.5
6869 */
6870 public static String replaceIgnoreCase(final String text, final String searchString, final String replacement) {
6871 return replaceIgnoreCase(text, searchString, replacement, -1);
6872 }
6873
6874 /**
6875 * Case insensitively replaces a String with another String inside a larger String,
6876 * for the first {@code max} values of the search String.
6877 *
6878 * <p>A {@code null} reference passed to this method is a no-op.</p>
6879 *
6880 * <pre>
6881 * StringUtils.replaceIgnoreCase(null, *, *, *) = null
6882 * StringUtils.replaceIgnoreCase("", *, *, *) = ""
6883 * StringUtils.replaceIgnoreCase("any", null, *, *) = "any"
6884 * StringUtils.replaceIgnoreCase("any", *, null, *) = "any"
6885 * StringUtils.replaceIgnoreCase("any", "", *, *) = "any"
6886 * StringUtils.replaceIgnoreCase("any", *, *, 0) = "any"
6887 * StringUtils.replaceIgnoreCase("abaa", "a", null, -1) = "abaa"
6888 * StringUtils.replaceIgnoreCase("abaa", "a", "", -1) = "b"
6889 * StringUtils.replaceIgnoreCase("abaa", "a", "z", 0) = "abaa"
6890 * StringUtils.replaceIgnoreCase("abaa", "A", "z", 1) = "zbaa"
6891 * StringUtils.replaceIgnoreCase("abAa", "a", "z", 2) = "zbza"
6892 * StringUtils.replaceIgnoreCase("abAa", "a", "z", -1) = "zbzz"
6893 * </pre>
6894 *
6895 * @param text text to search and replace in, may be null
6896 * @param searchString the String to search for (case-insensitive), may be null
6897 * @param replacement the String to replace it with, may be null
6898 * @param max maximum number of values to replace, or {@code -1} if no maximum
6899 * @return the text with any replacements processed,
6900 * {@code null} if null String input
6901 * @since 3.5
6902 */
6903 public static String replaceIgnoreCase(final String text, final String searchString, final String replacement, final int max) {
6904 return replace(text, searchString, replacement, max, true);
6905 }
6906
6907 /**
6908 * Replaces a String with another String inside a larger String, once.
6909 *
6910 * <p>A {@code null} reference passed to this method is a no-op.</p>
6911 *
6912 * <pre>
6913 * StringUtils.replaceOnce(null, *, *) = null
6914 * StringUtils.replaceOnce("", *, *) = ""
6915 * StringUtils.replaceOnce("any", null, *) = "any"
6916 * StringUtils.replaceOnce("any", *, null) = "any"
6917 * StringUtils.replaceOnce("any", "", *) = "any"
6918 * StringUtils.replaceOnce("aba", "a", null) = "aba"
6919 * StringUtils.replaceOnce("aba", "a", "") = "ba"
6920 * StringUtils.replaceOnce("aba", "a", "z") = "zba"
6921 * </pre>
6922 *
6923 * @see #replace(String text, String searchString, String replacement, int max)
6924 * @param text text to search and replace in, may be null
6925 * @param searchString the String to search for, may be null
6926 * @param replacement the String to replace with, may be null
6927 * @return the text with any replacements processed,
6928 * {@code null} if null String input
6929 */
6930 public static String replaceOnce(final String text, final String searchString, final String replacement) {
6931 return replace(text, searchString, replacement, 1);
6932 }
6933
6934 /**
6935 * Case insensitively replaces a String with another String inside a larger String, once.
6936 *
6937 * <p>A {@code null} reference passed to this method is a no-op.</p>
6938 *
6939 * <pre>
6940 * StringUtils.replaceOnceIgnoreCase(null, *, *) = null
6941 * StringUtils.replaceOnceIgnoreCase("", *, *) = ""
6942 * StringUtils.replaceOnceIgnoreCase("any", null, *) = "any"
6943 * StringUtils.replaceOnceIgnoreCase("any", *, null) = "any"
6944 * StringUtils.replaceOnceIgnoreCase("any", "", *) = "any"
6945 * StringUtils.replaceOnceIgnoreCase("aba", "a", null) = "aba"
6946 * StringUtils.replaceOnceIgnoreCase("aba", "a", "") = "ba"
6947 * StringUtils.replaceOnceIgnoreCase("aba", "a", "z") = "zba"
6948 * StringUtils.replaceOnceIgnoreCase("FoOFoofoo", "foo", "") = "Foofoo"
6949 * </pre>
6950 *
6951 * @see #replaceIgnoreCase(String text, String searchString, String replacement, int max)
6952 * @param text text to search and replace in, may be null
6953 * @param searchString the String to search for (case-insensitive), may be null
6954 * @param replacement the String to replace with, may be null
6955 * @return the text with any replacements processed,
6956 * {@code null} if null String input
6957 * @since 3.5
6958 */
6959 public static String replaceOnceIgnoreCase(final String text, final String searchString, final String replacement) {
6960 return replaceIgnoreCase(text, searchString, replacement, 1);
6961 }
6962
6963 /**
6964 * Replaces each substring of the source String that matches the given regular expression with the given
6965 * replacement using the {@link Pattern#DOTALL} option. DOTALL is also known as single-line mode in Perl.
6966 *
6967 * This call is a {@code null} safe equivalent to:
6968 * <ul>
6969 * <li>{@code source.replaceAll("(?s)" + regex, replacement)}</li>
6970 * <li>{@code Pattern.compile(regex, Pattern.DOTALL).matcher(source).replaceAll(replacement)}</li>
6971 * </ul>
6972 *
6973 * <p>A {@code null} reference passed to this method is a no-op.</p>
6974 *
6975 * <pre>
6976 * StringUtils.replacePattern(null, *, *) = null
6977 * StringUtils.replacePattern("any", (String) null, *) = "any"
6978 * StringUtils.replacePattern("any", *, null) = "any"
6979 * StringUtils.replacePattern("", "", "zzz") = "zzz"
6980 * StringUtils.replacePattern("", ".*", "zzz") = "zzz"
6981 * StringUtils.replacePattern("", ".+", "zzz") = ""
6982 * StringUtils.replacePattern("<__>\n<__>", "<.*>", "z") = "z"
6983 * StringUtils.replacePattern("ABCabc123", "[a-z]", "_") = "ABC___123"
6984 * StringUtils.replacePattern("ABCabc123", "[^A-Z0-9]+", "_") = "ABC_123"
6985 * StringUtils.replacePattern("ABCabc123", "[^A-Z0-9]+", "") = "ABC123"
6986 * StringUtils.replacePattern("Lorem ipsum dolor sit", "( +)([a-z]+)", "_$2") = "Lorem_ipsum_dolor_sit"
6987 * </pre>
6988 *
6989 * @param source
6990 * the source string
6991 * @param regex
6992 * the regular expression to which this string is to be matched
6993 * @param replacement
6994 * the string to be substituted for each match
6995 * @return The resulting {@link String}
6996 * @see #replaceAll(String, String, String)
6997 * @see String#replaceAll(String, String)
6998 * @see Pattern#DOTALL
6999 * @since 3.2
7000 * @since 3.5 Changed {@code null} reference passed to this method is a no-op.
7001 *
7002 * @deprecated Moved to RegExUtils.
7003 */
7004 @Deprecated
7005 public static String replacePattern(final String source, final String regex, final String replacement) {
7006 return RegExUtils.replacePattern(source, regex, replacement);
7007 }
7008
7009 /**
7010 * Reverses a String as per {@link StringBuilder#reverse()}.
7011 *
7012 * <p>A {@code null} String returns {@code null}.</p>
7013 *
7014 * <pre>
7015 * StringUtils.reverse(null) = null
7016 * StringUtils.reverse("") = ""
7017 * StringUtils.reverse("bat") = "tab"
7018 * </pre>
7019 *
7020 * @param str the String to reverse, may be null
7021 * @return the reversed String, {@code null} if null String input
7022 */
7023 public static String reverse(final String str) {
7024 if (str == null) {
7025 return null;
7026 }
7027 return new StringBuilder(str).reverse().toString();
7028 }
7029
7030 /**
7031 * Reverses a String that is delimited by a specific character.
7032 *
7033 * <p>The Strings between the delimiters are not reversed.
7034 * Thus java.lang.String becomes String.lang.java (if the delimiter
7035 * is {@code '.'}).</p>
7036 *
7037 * <pre>
7038 * StringUtils.reverseDelimited(null, *) = null
7039 * StringUtils.reverseDelimited("", *) = ""
7040 * StringUtils.reverseDelimited("a.b.c", 'x') = "a.b.c"
7041 * StringUtils.reverseDelimited("a.b.c", ".") = "c.b.a"
7042 * </pre>
7043 *
7044 * @param str the String to reverse, may be null
7045 * @param separatorChar the separator character to use
7046 * @return the reversed String, {@code null} if null String input
7047 * @since 2.0
7048 */
7049 public static String reverseDelimited(final String str, final char separatorChar) {
7050 if (str == null) {
7051 return null;
7052 }
7053 // could implement manually, but simple way is to reuse other,
7054 // probably slower, methods.
7055 final String[] strs = split(str, separatorChar);
7056 ArrayUtils.reverse(strs);
7057 return join(strs, separatorChar);
7058 }
7059
7060 /**
7061 * Gets the rightmost {@code len} characters of a String.
7062 *
7063 * <p>If {@code len} characters are not available, or the String
7064 * is {@code null}, the String will be returned without an
7065 * an exception. An empty String is returned if len is negative.</p>
7066 *
7067 * <pre>
7068 * StringUtils.right(null, *) = null
7069 * StringUtils.right(*, -ve) = ""
7070 * StringUtils.right("", *) = ""
7071 * StringUtils.right("abc", 0) = ""
7072 * StringUtils.right("abc", 2) = "bc"
7073 * StringUtils.right("abc", 4) = "abc"
7074 * </pre>
7075 *
7076 * @param str the String to get the rightmost characters from, may be null
7077 * @param len the length of the required String
7078 * @return the rightmost characters, {@code null} if null String input
7079 */
7080 public static String right(final String str, final int len) {
7081 if (str == null) {
7082 return null;
7083 }
7084 if (len < 0) {
7085 return EMPTY;
7086 }
7087 if (str.length() <= len) {
7088 return str;
7089 }
7090 return str.substring(str.length() - len);
7091 }
7092
7093 /**
7094 * Right pad a String with spaces (' ').
7095 *
7096 * <p>The String is padded to the size of {@code size}.</p>
7097 *
7098 * <pre>
7099 * StringUtils.rightPad(null, *) = null
7100 * StringUtils.rightPad("", 3) = " "
7101 * StringUtils.rightPad("bat", 3) = "bat"
7102 * StringUtils.rightPad("bat", 5) = "bat "
7103 * StringUtils.rightPad("bat", 1) = "bat"
7104 * StringUtils.rightPad("bat", -1) = "bat"
7105 * </pre>
7106 *
7107 * @param str the String to pad out, may be null
7108 * @param size the size to pad to
7109 * @return right padded String or original String if no padding is necessary,
7110 * {@code null} if null String input
7111 */
7112 public static String rightPad(final String str, final int size) {
7113 return rightPad(str, size, ' ');
7114 }
7115
7116 /**
7117 * Right pad a String with a specified character.
7118 *
7119 * <p>The String is padded to the size of {@code size}.</p>
7120 *
7121 * <pre>
7122 * StringUtils.rightPad(null, *, *) = null
7123 * StringUtils.rightPad("", 3, 'z') = "zzz"
7124 * StringUtils.rightPad("bat", 3, 'z') = "bat"
7125 * StringUtils.rightPad("bat", 5, 'z') = "batzz"
7126 * StringUtils.rightPad("bat", 1, 'z') = "bat"
7127 * StringUtils.rightPad("bat", -1, 'z') = "bat"
7128 * </pre>
7129 *
7130 * @param str the String to pad out, may be null
7131 * @param size the size to pad to
7132 * @param padChar the character to pad with
7133 * @return right padded String or original String if no padding is necessary,
7134 * {@code null} if null String input
7135 * @since 2.0
7136 */
7137 public static String rightPad(final String str, final int size, final char padChar) {
7138 if (str == null) {
7139 return null;
7140 }
7141 final int pads = size - str.length();
7142 if (pads <= 0) {
7143 return str; // returns original String when possible
7144 }
7145 if (pads > PAD_LIMIT) {
7146 return rightPad(str, size, String.valueOf(padChar));
7147 }
7148 return str.concat(repeat(padChar, pads));
7149 }
7150
7151 /**
7152 * Right pad a String with a specified String.
7153 *
7154 * <p>The String is padded to the size of {@code size}.</p>
7155 *
7156 * <pre>
7157 * StringUtils.rightPad(null, *, *) = null
7158 * StringUtils.rightPad("", 3, "z") = "zzz"
7159 * StringUtils.rightPad("bat", 3, "yz") = "bat"
7160 * StringUtils.rightPad("bat", 5, "yz") = "batyz"
7161 * StringUtils.rightPad("bat", 8, "yz") = "batyzyzy"
7162 * StringUtils.rightPad("bat", 1, "yz") = "bat"
7163 * StringUtils.rightPad("bat", -1, "yz") = "bat"
7164 * StringUtils.rightPad("bat", 5, null) = "bat "
7165 * StringUtils.rightPad("bat", 5, "") = "bat "
7166 * </pre>
7167 *
7168 * @param str the String to pad out, may be null
7169 * @param size the size to pad to
7170 * @param padStr the String to pad with, null or empty treated as single space
7171 * @return right padded String or original String if no padding is necessary,
7172 * {@code null} if null String input
7173 */
7174 public static String rightPad(final String str, final int size, String padStr) {
7175 if (str == null) {
7176 return null;
7177 }
7178 if (isEmpty(padStr)) {
7179 padStr = SPACE;
7180 }
7181 final int padLen = padStr.length();
7182 final int strLen = str.length();
7183 final int pads = size - strLen;
7184 if (pads <= 0) {
7185 return str; // returns original String when possible
7186 }
7187 if (padLen == 1 && pads <= PAD_LIMIT) {
7188 return rightPad(str, size, padStr.charAt(0));
7189 }
7190
7191 if (pads == padLen) {
7192 return str.concat(padStr);
7193 }
7194 if (pads < padLen) {
7195 return str.concat(padStr.substring(0, pads));
7196 }
7197 final char[] padding = new char[pads];
7198 final char[] padChars = padStr.toCharArray();
7199 for (int i = 0; i < pads; i++) {
7200 padding[i] = padChars[i % padLen];
7201 }
7202 return str.concat(new String(padding));
7203 }
7204
7205 /**
7206 * Rotate (circular shift) a String of {@code shift} characters.
7207 * <ul>
7208 * <li>If {@code shift > 0}, right circular shift (ex : ABCDEF => FABCDE)</li>
7209 * <li>If {@code shift < 0}, left circular shift (ex : ABCDEF => BCDEFA)</li>
7210 * </ul>
7211 *
7212 * <pre>
7213 * StringUtils.rotate(null, *) = null
7214 * StringUtils.rotate("", *) = ""
7215 * StringUtils.rotate("abcdefg", 0) = "abcdefg"
7216 * StringUtils.rotate("abcdefg", 2) = "fgabcde"
7217 * StringUtils.rotate("abcdefg", -2) = "cdefgab"
7218 * StringUtils.rotate("abcdefg", 7) = "abcdefg"
7219 * StringUtils.rotate("abcdefg", -7) = "abcdefg"
7220 * StringUtils.rotate("abcdefg", 9) = "fgabcde"
7221 * StringUtils.rotate("abcdefg", -9) = "cdefgab"
7222 * </pre>
7223 *
7224 * @param str the String to rotate, may be null
7225 * @param shift number of time to shift (positive : right shift, negative : left shift)
7226 * @return the rotated String,
7227 * or the original String if {@code shift == 0},
7228 * or {@code null} if null String input
7229 * @since 3.5
7230 */
7231 public static String rotate(final String str, final int shift) {
7232 if (str == null) {
7233 return null;
7234 }
7235
7236 final int strLen = str.length();
7237 if (shift == 0 || strLen == 0 || shift % strLen == 0) {
7238 return str;
7239 }
7240
7241 final StringBuilder builder = new StringBuilder(strLen);
7242 final int offset = - (shift % strLen);
7243 builder.append(substring(str, offset));
7244 builder.append(substring(str, 0, offset));
7245 return builder.toString();
7246 }
7247
7248 /**
7249 * Splits the provided text into an array, using whitespace as the
7250 * separator.
7251 * Whitespace is defined by {@link Character#isWhitespace(char)}.
7252 *
7253 * <p>The separator is not included in the returned String array.
7254 * Adjacent separators are treated as one separator.
7255 * For more control over the split use the StrTokenizer class.</p>
7256 *
7257 * <p>A {@code null} input String returns {@code null}.</p>
7258 *
7259 * <pre>
7260 * StringUtils.split(null) = null
7261 * StringUtils.split("") = []
7262 * StringUtils.split("abc def") = ["abc", "def"]
7263 * StringUtils.split("abc def") = ["abc", "def"]
7264 * StringUtils.split(" abc ") = ["abc"]
7265 * </pre>
7266 *
7267 * @param str the String to parse, may be null
7268 * @return an array of parsed Strings, {@code null} if null String input
7269 */
7270 public static String[] split(final String str) {
7271 return split(str, null, -1);
7272 }
7273
7274 /**
7275 * Splits the provided text into an array, separator specified.
7276 * This is an alternative to using StringTokenizer.
7277 *
7278 * <p>The separator is not included in the returned String array.
7279 * Adjacent separators are treated as one separator.
7280 * For more control over the split use the StrTokenizer class.</p>
7281 *
7282 * <p>A {@code null} input String returns {@code null}.</p>
7283 *
7284 * <pre>
7285 * StringUtils.split(null, *) = null
7286 * StringUtils.split("", *) = []
7287 * StringUtils.split("a.b.c", '.') = ["a", "b", "c"]
7288 * StringUtils.split("a..b.c", '.') = ["a", "b", "c"]
7289 * StringUtils.split("a:b:c", '.') = ["a:b:c"]
7290 * StringUtils.split("a b c", ' ') = ["a", "b", "c"]
7291 * </pre>
7292 *
7293 * @param str the String to parse, may be null
7294 * @param separatorChar the character used as the delimiter
7295 * @return an array of parsed Strings, {@code null} if null String input
7296 * @since 2.0
7297 */
7298 public static String[] split(final String str, final char separatorChar) {
7299 return splitWorker(str, separatorChar, false);
7300 }
7301
7302 /**
7303 * Splits the provided text into an array, separators specified.
7304 * This is an alternative to using StringTokenizer.
7305 *
7306 * <p>The separator is not included in the returned String array.
7307 * Adjacent separators are treated as one separator.
7308 * For more control over the split use the StrTokenizer class.</p>
7309 *
7310 * <p>A {@code null} input String returns {@code null}.
7311 * A {@code null} separatorChars splits on whitespace.</p>
7312 *
7313 * <pre>
7314 * StringUtils.split(null, *) = null
7315 * StringUtils.split("", *) = []
7316 * StringUtils.split("abc def", null) = ["abc", "def"]
7317 * StringUtils.split("abc def", " ") = ["abc", "def"]
7318 * StringUtils.split("abc def", " ") = ["abc", "def"]
7319 * StringUtils.split("ab:cd:ef", ":") = ["ab", "cd", "ef"]
7320 * </pre>
7321 *
7322 * @param str the String to parse, may be null
7323 * @param separatorChars the characters used as the delimiters,
7324 * {@code null} splits on whitespace
7325 * @return an array of parsed Strings, {@code null} if null String input
7326 */
7327 public static String[] split(final String str, final String separatorChars) {
7328 return splitWorker(str, separatorChars, -1, false);
7329 }
7330
7331 /**
7332 * Splits the provided text into an array with a maximum length,
7333 * separators specified.
7334 *
7335 * <p>The separator is not included in the returned String array.
7336 * Adjacent separators are treated as one separator.</p>
7337 *
7338 * <p>A {@code null} input String returns {@code null}.
7339 * A {@code null} separatorChars splits on whitespace.</p>
7340 *
7341 * <p>If more than {@code max} delimited substrings are found, the last
7342 * returned string includes all characters after the first {@code max - 1}
7343 * returned strings (including separator characters).</p>
7344 *
7345 * <pre>
7346 * StringUtils.split(null, *, *) = null
7347 * StringUtils.split("", *, *) = []
7348 * StringUtils.split("ab cd ef", null, 0) = ["ab", "cd", "ef"]
7349 * StringUtils.split("ab cd ef", null, 0) = ["ab", "cd", "ef"]
7350 * StringUtils.split("ab:cd:ef", ":", 0) = ["ab", "cd", "ef"]
7351 * StringUtils.split("ab:cd:ef", ":", 2) = ["ab", "cd:ef"]
7352 * </pre>
7353 *
7354 * @param str the String to parse, may be null
7355 * @param separatorChars the characters used as the delimiters,
7356 * {@code null} splits on whitespace
7357 * @param max the maximum number of elements to include in the
7358 * array. A zero or negative value implies no limit
7359 * @return an array of parsed Strings, {@code null} if null String input
7360 */
7361 public static String[] split(final String str, final String separatorChars, final int max) {
7362 return splitWorker(str, separatorChars, max, false);
7363 }
7364
7365 /**
7366 * Splits a String by Character type as returned by
7367 * {@code java.lang.Character.getType(char)}. Groups of contiguous
7368 * characters of the same type are returned as complete tokens.
7369 * <pre>
7370 * StringUtils.splitByCharacterType(null) = null
7371 * StringUtils.splitByCharacterType("") = []
7372 * StringUtils.splitByCharacterType("ab de fg") = ["ab", " ", "de", " ", "fg"]
7373 * StringUtils.splitByCharacterType("ab de fg") = ["ab", " ", "de", " ", "fg"]
7374 * StringUtils.splitByCharacterType("ab:cd:ef") = ["ab", ":", "cd", ":", "ef"]
7375 * StringUtils.splitByCharacterType("number5") = ["number", "5"]
7376 * StringUtils.splitByCharacterType("fooBar") = ["foo", "B", "ar"]
7377 * StringUtils.splitByCharacterType("foo200Bar") = ["foo", "200"