| Classes in this File | Line Coverage | Branch Coverage | Complexity | ||||
| StringUtils |
|
| 5.783333333333333;5.783 |
| 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.text.Normalizer; | |
| 21 | import java.util.ArrayList; | |
| 22 | import java.util.Arrays; | |
| 23 | import java.util.Iterator; | |
| 24 | import java.util.List; | |
| 25 | import java.util.Locale; | |
| 26 | import java.util.regex.Pattern; | |
| 27 | ||
| 28 | /** | |
| 29 | * <p>Operations on {@link java.lang.String} that are | |
| 30 | * {@code null} safe.</p> | |
| 31 | * | |
| 32 | * <ul> | |
| 33 | * <li><b>IsEmpty/IsBlank</b> | |
| 34 | * - checks if a String contains text</li> | |
| 35 | * <li><b>Trim/Strip</b> | |
| 36 | * - removes leading and trailing whitespace</li> | |
| 37 | * <li><b>Equals</b> | |
| 38 | * - compares two strings null-safe</li> | |
| 39 | * <li><b>startsWith</b> | |
| 40 | * - check if a String starts with a prefix null-safe</li> | |
| 41 | * <li><b>endsWith</b> | |
| 42 | * - check if a String ends with a suffix null-safe</li> | |
| 43 | * <li><b>IndexOf/LastIndexOf/Contains</b> | |
| 44 | * - null-safe index-of checks | |
| 45 | * <li><b>IndexOfAny/LastIndexOfAny/IndexOfAnyBut/LastIndexOfAnyBut</b> | |
| 46 | * - index-of any of a set of Strings</li> | |
| 47 | * <li><b>ContainsOnly/ContainsNone/ContainsAny</b> | |
| 48 | * - does String contains only/none/any of these characters</li> | |
| 49 | * <li><b>Substring/Left/Right/Mid</b> | |
| 50 | * - null-safe substring extractions</li> | |
| 51 | * <li><b>SubstringBefore/SubstringAfter/SubstringBetween</b> | |
| 52 | * - substring extraction relative to other strings</li> | |
| 53 | * <li><b>Split/Join</b> | |
| 54 | * - splits a String into an array of substrings and vice versa</li> | |
| 55 | * <li><b>Remove/Delete</b> | |
| 56 | * - removes part of a String</li> | |
| 57 | * <li><b>Replace/Overlay</b> | |
| 58 | * - Searches a String and replaces one String with another</li> | |
| 59 | * <li><b>Chomp/Chop</b> | |
| 60 | * - removes the last part of a String</li> | |
| 61 | * <li><b>LeftPad/RightPad/Center/Repeat</b> | |
| 62 | * - pads a String</li> | |
| 63 | * <li><b>UpperCase/LowerCase/SwapCase/Capitalize/Uncapitalize</b> | |
| 64 | * - changes the case of a String</li> | |
| 65 | * <li><b>CountMatches</b> | |
| 66 | * - counts the number of occurrences of one String in another</li> | |
| 67 | * <li><b>IsAlpha/IsNumeric/IsWhitespace/IsAsciiPrintable</b> | |
| 68 | * - checks the characters in a String</li> | |
| 69 | * <li><b>DefaultString</b> | |
| 70 | * - protects against a null input String</li> | |
| 71 | * <li><b>Reverse/ReverseDelimited</b> | |
| 72 | * - reverses a String</li> | |
| 73 | * <li><b>Abbreviate</b> | |
| 74 | * - abbreviates a string using ellipsis</li> | |
| 75 | * <li><b>Difference</b> | |
| 76 | * - compares Strings and reports on their differences</li> | |
| 77 | * <li><b>LevenshteinDistance</b> | |
| 78 | * - the number of changes needed to change one String into another</li> | |
| 79 | * </ul> | |
| 80 | * | |
| 81 | * <p>The {@code StringUtils} class defines certain words related to | |
| 82 | * String handling.</p> | |
| 83 | * | |
| 84 | * <ul> | |
| 85 | * <li>null - {@code null}</li> | |
| 86 | * <li>empty - a zero-length string ({@code ""})</li> | |
| 87 | * <li>space - the space character ({@code ' '}, char 32)</li> | |
| 88 | * <li>whitespace - the characters defined by {@link Character#isWhitespace(char)}</li> | |
| 89 | * <li>trim - the characters <= 32 as in {@link String#trim()}</li> | |
| 90 | * </ul> | |
| 91 | * | |
| 92 | * <p>{@code StringUtils} handles {@code null} input Strings quietly. | |
| 93 | * That is to say that a {@code null} input will return {@code null}. | |
| 94 | * Where a {@code boolean} or {@code int} is being returned | |
| 95 | * details vary by method.</p> | |
| 96 | * | |
| 97 | * <p>A side effect of the {@code null} handling is that a | |
| 98 | * {@code NullPointerException} should be considered a bug in | |
| 99 | * {@code StringUtils}.</p> | |
| 100 | * | |
| 101 | * <p>Methods in this class give sample code to explain their operation. | |
| 102 | * The symbol {@code *} is used to indicate any input including {@code null}.</p> | |
| 103 | * | |
| 104 | * <p>#ThreadSafe#</p> | |
| 105 | * @see java.lang.String | |
| 106 | * @since 1.0 | |
| 107 | * @version $Id: StringUtils.java 1437065 2013-01-22 17:29:33Z ggregory $ | |
| 108 | */ | |
| 109 | //@Immutable | |
| 110 | public class StringUtils { | |
| 111 | // Performance testing notes (JDK 1.4, Jul03, scolebourne) | |
| 112 | // Whitespace: | |
| 113 | // Character.isWhitespace() is faster than WHITESPACE.indexOf() | |
| 114 | // where WHITESPACE is a string of all whitespace characters | |
| 115 | // | |
| 116 | // Character access: | |
| 117 | // String.charAt(n) versus toCharArray(), then array[n] | |
| 118 | // String.charAt(n) is about 15% worse for a 10K string | |
| 119 | // They are about equal for a length 50 string | |
| 120 | // String.charAt(n) is about 4 times better for a length 3 string | |
| 121 | // String.charAt(n) is best bet overall | |
| 122 | // | |
| 123 | // Append: | |
| 124 | // String.concat about twice as fast as StringBuffer.append | |
| 125 | // (not sure who tested this) | |
| 126 | ||
| 127 | /** | |
| 128 | * A String for a space character. | |
| 129 | * | |
| 130 | * @since 3.2 | |
| 131 | */ | |
| 132 | public static final String SPACE = " "; | |
| 133 | ||
| 134 | /** | |
| 135 | * The empty String {@code ""}. | |
| 136 | * @since 2.0 | |
| 137 | */ | |
| 138 | public static final String EMPTY = ""; | |
| 139 | ||
| 140 | /** | |
| 141 | * Represents a failed index search. | |
| 142 | * @since 2.1 | |
| 143 | */ | |
| 144 | public static final int INDEX_NOT_FOUND = -1; | |
| 145 | ||
| 146 | /** | |
| 147 | * <p>The maximum size to which the padding constant(s) can expand.</p> | |
| 148 | */ | |
| 149 | private static final int PAD_LIMIT = 8192; | |
| 150 | ||
| 151 | /** | |
| 152 | * A regex pattern for recognizing blocks of whitespace characters. | |
| 153 | * The apparent convolutedness of the pattern serves the purpose of | |
| 154 | * ignoring "blocks" consisting of only a single space: the pattern | |
| 155 | * is used only to normalize whitespace, condensing "blocks" down to a | |
| 156 | * single space, thus matching the same would likely cause a great | |
| 157 | * many noop replacements. | |
| 158 | */ | |
| 159 | 1 | private static final Pattern WHITESPACE_PATTERN = Pattern.compile("(?: \\s|[\\s&&[^ ]])\\s*"); |
| 160 | ||
| 161 | /** | |
| 162 | * <p>{@code StringUtils} instances should NOT be constructed in | |
| 163 | * standard programming. Instead, the class should be used as | |
| 164 | * {@code StringUtils.trim(" foo ");}.</p> | |
| 165 | * | |
| 166 | * <p>This constructor is public to permit tools that require a JavaBean | |
| 167 | * instance to operate.</p> | |
| 168 | */ | |
| 169 | public StringUtils() { | |
| 170 | 1 | super(); |
| 171 | 1 | } |
| 172 | ||
| 173 | // Empty checks | |
| 174 | //----------------------------------------------------------------------- | |
| 175 | /** | |
| 176 | * <p>Checks if a CharSequence is empty ("") or null.</p> | |
| 177 | * | |
| 178 | * <pre> | |
| 179 | * StringUtils.isEmpty(null) = true | |
| 180 | * StringUtils.isEmpty("") = true | |
| 181 | * StringUtils.isEmpty(" ") = false | |
| 182 | * StringUtils.isEmpty("bob") = false | |
| 183 | * StringUtils.isEmpty(" bob ") = false | |
| 184 | * </pre> | |
| 185 | * | |
| 186 | * <p>NOTE: This method changed in Lang version 2.0. | |
| 187 | * It no longer trims the CharSequence. | |
| 188 | * That functionality is available in isBlank().</p> | |
| 189 | * | |
| 190 | * @param cs the CharSequence to check, may be null | |
| 191 | * @return {@code true} if the CharSequence is empty or null | |
| 192 | * @since 3.0 Changed signature from isEmpty(String) to isEmpty(CharSequence) | |
| 193 | */ | |
| 194 | public static boolean isEmpty(final CharSequence cs) { | |
| 195 | 2434 | return cs == null || cs.length() == 0; |
| 196 | } | |
| 197 | ||
| 198 | /** | |
| 199 | * <p>Checks if a CharSequence is not empty ("") and not null.</p> | |
| 200 | * | |
| 201 | * <pre> | |
| 202 | * StringUtils.isNotEmpty(null) = false | |
| 203 | * StringUtils.isNotEmpty("") = false | |
| 204 | * StringUtils.isNotEmpty(" ") = true | |
| 205 | * StringUtils.isNotEmpty("bob") = true | |
| 206 | * StringUtils.isNotEmpty(" bob ") = true | |
| 207 | * </pre> | |
| 208 | * | |
| 209 | * @param cs the CharSequence to check, may be null | |
| 210 | * @return {@code true} if the CharSequence is not empty and not null | |
| 211 | * @since 3.0 Changed signature from isNotEmpty(String) to isNotEmpty(CharSequence) | |
| 212 | */ | |
| 213 | public static boolean isNotEmpty(final CharSequence cs) { | |
| 214 | 56 | return !StringUtils.isEmpty(cs); |
| 215 | } | |
| 216 | ||
| 217 | /** | |
| 218 | * <p>Checks if a CharSequence is whitespace, empty ("") or null.</p> | |
| 219 | * | |
| 220 | * <pre> | |
| 221 | * StringUtils.isBlank(null) = true | |
| 222 | * StringUtils.isBlank("") = true | |
| 223 | * StringUtils.isBlank(" ") = true | |
| 224 | * StringUtils.isBlank("bob") = false | |
| 225 | * StringUtils.isBlank(" bob ") = false | |
| 226 | * </pre> | |
| 227 | * | |
| 228 | * @param cs the CharSequence to check, may be null | |
| 229 | * @return {@code true} if the CharSequence is null, empty or whitespace | |
| 230 | * @since 2.0 | |
| 231 | * @since 3.0 Changed signature from isBlank(String) to isBlank(CharSequence) | |
| 232 | */ | |
| 233 | public static boolean isBlank(final CharSequence cs) { | |
| 234 | int strLen; | |
| 235 | 156 | if (cs == null || (strLen = cs.length()) == 0) { |
| 236 | 17 | return true; |
| 237 | } | |
| 238 | 239 | for (int i = 0; i < strLen; i++) { |
| 239 | 228 | if (Character.isWhitespace(cs.charAt(i)) == false) { |
| 240 | 128 | return false; |
| 241 | } | |
| 242 | } | |
| 243 | 11 | return true; |
| 244 | } | |
| 245 | ||
| 246 | /** | |
| 247 | * <p>Checks if a CharSequence is not empty (""), not null and not whitespace only.</p> | |
| 248 | * | |
| 249 | * <pre> | |
| 250 | * StringUtils.isNotBlank(null) = false | |
| 251 | * StringUtils.isNotBlank("") = false | |
| 252 | * StringUtils.isNotBlank(" ") = false | |
| 253 | * StringUtils.isNotBlank("bob") = true | |
| 254 | * StringUtils.isNotBlank(" bob ") = true | |
| 255 | * </pre> | |
| 256 | * | |
| 257 | * @param cs the CharSequence to check, may be null | |
| 258 | * @return {@code true} if the CharSequence is | |
| 259 | * not empty and not null and not whitespace | |
| 260 | * @since 2.0 | |
| 261 | * @since 3.0 Changed signature from isNotBlank(String) to isNotBlank(CharSequence) | |
| 262 | */ | |
| 263 | public static boolean isNotBlank(final CharSequence cs) { | |
| 264 | 5 | return !StringUtils.isBlank(cs); |
| 265 | } | |
| 266 | ||
| 267 | // Trim | |
| 268 | //----------------------------------------------------------------------- | |
| 269 | /** | |
| 270 | * <p>Removes control characters (char <= 32) from both | |
| 271 | * ends of this String, handling {@code null} by returning | |
| 272 | * {@code null}.</p> | |
| 273 | * | |
| 274 | * <p>The String is trimmed using {@link String#trim()}. | |
| 275 | * Trim removes start and end characters <= 32. | |
| 276 | * To strip whitespace use {@link #strip(String)}.</p> | |
| 277 | * | |
| 278 | * <p>To trim your choice of characters, use the | |
| 279 | * {@link #strip(String, String)} methods.</p> | |
| 280 | * | |
| 281 | * <pre> | |
| 282 | * StringUtils.trim(null) = null | |
| 283 | * StringUtils.trim("") = "" | |
| 284 | * StringUtils.trim(" ") = "" | |
| 285 | * StringUtils.trim("abc") = "abc" | |
| 286 | * StringUtils.trim(" abc ") = "abc" | |
| 287 | * </pre> | |
| 288 | * | |
| 289 | * @param str the String to be trimmed, may be null | |
| 290 | * @return the trimmed string, {@code null} if null String input | |
| 291 | */ | |
| 292 | public static String trim(final String str) { | |
| 293 | 34 | return str == null ? null : str.trim(); |
| 294 | } | |
| 295 | ||
| 296 | /** | |
| 297 | * <p>Removes control characters (char <= 32) from both | |
| 298 | * ends of this String returning {@code null} if the String is | |
| 299 | * empty ("") after the trim or if it is {@code null}. | |
| 300 | * | |
| 301 | * <p>The String is trimmed using {@link String#trim()}. | |
| 302 | * Trim removes start and end characters <= 32. | |
| 303 | * To strip whitespace use {@link #stripToNull(String)}.</p> | |
| 304 | * | |
| 305 | * <pre> | |
| 306 | * StringUtils.trimToNull(null) = null | |
| 307 | * StringUtils.trimToNull("") = null | |
| 308 | * StringUtils.trimToNull(" ") = null | |
| 309 | * StringUtils.trimToNull("abc") = "abc" | |
| 310 | * StringUtils.trimToNull(" abc ") = "abc" | |
| 311 | * </pre> | |
| 312 | * | |
| 313 | * @param str the String to be trimmed, may be null | |
| 314 | * @return the trimmed String, | |
| 315 | * {@code null} if only chars <= 32, empty or null String input | |
| 316 | * @since 2.0 | |
| 317 | */ | |
| 318 | public static String trimToNull(final String str) { | |
| 319 | 9 | final String ts = trim(str); |
| 320 | 9 | return isEmpty(ts) ? null : ts; |
| 321 | } | |
| 322 | ||
| 323 | /** | |
| 324 | * <p>Removes control characters (char <= 32) from both | |
| 325 | * ends of this String returning an empty String ("") if the String | |
| 326 | * is empty ("") after the trim or if it is {@code null}. | |
| 327 | * | |
| 328 | * <p>The String is trimmed using {@link String#trim()}. | |
| 329 | * Trim removes start and end characters <= 32. | |
| 330 | * To strip whitespace use {@link #stripToEmpty(String)}.</p> | |
| 331 | * | |
| 332 | * <pre> | |
| 333 | * StringUtils.trimToEmpty(null) = "" | |
| 334 | * StringUtils.trimToEmpty("") = "" | |
| 335 | * StringUtils.trimToEmpty(" ") = "" | |
| 336 | * StringUtils.trimToEmpty("abc") = "abc" | |
| 337 | * StringUtils.trimToEmpty(" abc ") = "abc" | |
| 338 | * </pre> | |
| 339 | * | |
| 340 | * @param str the String to be trimmed, may be null | |
| 341 | * @return the trimmed String, or an empty String if {@code null} input | |
| 342 | * @since 2.0 | |
| 343 | */ | |
| 344 | public static String trimToEmpty(final String str) { | |
| 345 | 9 | return str == null ? EMPTY : str.trim(); |
| 346 | } | |
| 347 | ||
| 348 | // Stripping | |
| 349 | //----------------------------------------------------------------------- | |
| 350 | /** | |
| 351 | * <p>Strips whitespace from the start and end of a String.</p> | |
| 352 | * | |
| 353 | * <p>This is similar to {@link #trim(String)} but removes whitespace. | |
| 354 | * Whitespace is defined by {@link Character#isWhitespace(char)}.</p> | |
| 355 | * | |
| 356 | * <p>A {@code null} input String returns {@code null}.</p> | |
| 357 | * | |
| 358 | * <pre> | |
| 359 | * StringUtils.strip(null) = null | |
| 360 | * StringUtils.strip("") = "" | |
| 361 | * StringUtils.strip(" ") = "" | |
| 362 | * StringUtils.strip("abc") = "abc" | |
| 363 | * StringUtils.strip(" abc") = "abc" | |
| 364 | * StringUtils.strip("abc ") = "abc" | |
| 365 | * StringUtils.strip(" abc ") = "abc" | |
| 366 | * StringUtils.strip(" ab c ") = "ab c" | |
| 367 | * </pre> | |
| 368 | * | |
| 369 | * @param str the String to remove whitespace from, may be null | |
| 370 | * @return the stripped String, {@code null} if null String input | |
| 371 | */ | |
| 372 | public static String strip(final String str) { | |
| 373 | 5 | return strip(str, null); |
| 374 | } | |
| 375 | ||
| 376 | /** | |
| 377 | * <p>Strips whitespace from the start and end of a String returning | |
| 378 | * {@code null} if the String is empty ("") after the strip.</p> | |
| 379 | * | |
| 380 | * <p>This is similar to {@link #trimToNull(String)} but removes whitespace. | |
| 381 | * Whitespace is defined by {@link Character#isWhitespace(char)}.</p> | |
| 382 | * | |
| 383 | * <pre> | |
| 384 | * StringUtils.stripToNull(null) = null | |
| 385 | * StringUtils.stripToNull("") = null | |
| 386 | * StringUtils.stripToNull(" ") = null | |
| 387 | * StringUtils.stripToNull("abc") = "abc" | |
| 388 | * StringUtils.stripToNull(" abc") = "abc" | |
| 389 | * StringUtils.stripToNull("abc ") = "abc" | |
| 390 | * StringUtils.stripToNull(" abc ") = "abc" | |
| 391 | * StringUtils.stripToNull(" ab c ") = "ab c" | |
| 392 | * </pre> | |
| 393 | * | |
| 394 | * @param str the String to be stripped, may be null | |
| 395 | * @return the stripped String, | |
| 396 | * {@code null} if whitespace, empty or null String input | |
| 397 | * @since 2.0 | |
| 398 | */ | |
| 399 | public static String stripToNull(String str) { | |
| 400 | 6 | if (str == null) { |
| 401 | 1 | return null; |
| 402 | } | |
| 403 | 5 | str = strip(str, null); |
| 404 | 5 | return str.length() == 0 ? null : str; |
| 405 | } | |
| 406 | ||
| 407 | /** | |
| 408 | * <p>Strips whitespace from the start and end of a String returning | |
| 409 | * an empty String if {@code null} input.</p> | |
| 410 | * | |
| 411 | * <p>This is similar to {@link #trimToEmpty(String)} but removes whitespace. | |
| 412 | * Whitespace is defined by {@link Character#isWhitespace(char)}.</p> | |
| 413 | * | |
| 414 | * <pre> | |
| 415 | * StringUtils.stripToEmpty(null) = "" | |
| 416 | * StringUtils.stripToEmpty("") = "" | |
| 417 | * StringUtils.stripToEmpty(" ") = "" | |
| 418 | * StringUtils.stripToEmpty("abc") = "abc" | |
| 419 | * StringUtils.stripToEmpty(" abc") = "abc" | |
| 420 | * StringUtils.stripToEmpty("abc ") = "abc" | |
| 421 | * StringUtils.stripToEmpty(" abc ") = "abc" | |
| 422 | * StringUtils.stripToEmpty(" ab c ") = "ab c" | |
| 423 | * </pre> | |
| 424 | * | |
| 425 | * @param str the String to be stripped, may be null | |
| 426 | * @return the trimmed String, or an empty String if {@code null} input | |
| 427 | * @since 2.0 | |
| 428 | */ | |
| 429 | public static String stripToEmpty(final String str) { | |
| 430 | 6 | return str == null ? EMPTY : strip(str, null); |
| 431 | } | |
| 432 | ||
| 433 | /** | |
| 434 | * <p>Strips any of a set of characters from the start and end of a String. | |
| 435 | * This is similar to {@link String#trim()} but allows the characters | |
| 436 | * to be stripped to be controlled.</p> | |
| 437 | * | |
| 438 | * <p>A {@code null} input String returns {@code null}. | |
| 439 | * An empty string ("") input returns the empty string.</p> | |
| 440 | * | |
| 441 | * <p>If the stripChars String is {@code null}, whitespace is | |
| 442 | * stripped as defined by {@link Character#isWhitespace(char)}. | |
| 443 | * Alternatively use {@link #strip(String)}.</p> | |
| 444 | * | |
| 445 | * <pre> | |
| 446 | * StringUtils.strip(null, *) = null | |
| 447 | * StringUtils.strip("", *) = "" | |
| 448 | * StringUtils.strip("abc", null) = "abc" | |
| 449 | * StringUtils.strip(" abc", null) = "abc" | |
| 450 | * StringUtils.strip("abc ", null) = "abc" | |
| 451 | * StringUtils.strip(" abc ", null) = "abc" | |
| 452 | * StringUtils.strip(" abcyx", "xyz") = " abc" | |
| 453 | * </pre> | |
| 454 | * | |
| 455 | * @param str the String to remove characters from, may be null | |
| 456 | * @param stripChars the characters to remove, null treated as whitespace | |
| 457 | * @return the stripped String, {@code null} if null String input | |
| 458 | */ | |
| 459 | public static String strip(String str, final String stripChars) { | |
| 460 | 45 | if (isEmpty(str)) { |
| 461 | 13 | return str; |
| 462 | } | |
| 463 | 32 | str = stripStart(str, stripChars); |
| 464 | 32 | return stripEnd(str, stripChars); |
| 465 | } | |
| 466 | ||
| 467 | /** | |
| 468 | * <p>Strips any of a set of characters from the start of a String.</p> | |
| 469 | * | |
| 470 | * <p>A {@code null} input String returns {@code null}. | |
| 471 | * An empty string ("") input returns the empty string.</p> | |
| 472 | * | |
| 473 | * <p>If the stripChars String is {@code null}, whitespace is | |
| 474 | * stripped as defined by {@link Character#isWhitespace(char)}.</p> | |
| 475 | * | |
| 476 | * <pre> | |
| 477 | * StringUtils.stripStart(null, *) = null | |
| 478 | * StringUtils.stripStart("", *) = "" | |
| 479 | * StringUtils.stripStart("abc", "") = "abc" | |
| 480 | * StringUtils.stripStart("abc", null) = "abc" | |
| 481 | * StringUtils.stripStart(" abc", null) = "abc" | |
| 482 | * StringUtils.stripStart("abc ", null) = "abc " | |
| 483 | * StringUtils.stripStart(" abc ", null) = "abc " | |
| 484 | * StringUtils.stripStart("yxabc ", "xyz") = "abc " | |
| 485 | * </pre> | |
| 486 | * | |
| 487 | * @param str the String to remove characters from, may be null | |
| 488 | * @param stripChars the characters to remove, null treated as whitespace | |
| 489 | * @return the stripped String, {@code null} if null String input | |
| 490 | */ | |
| 491 | public static String stripStart(final String str, final String stripChars) { | |
| 492 | int strLen; | |
| 493 | 52 | if (str == null || (strLen = str.length()) == 0) { |
| 494 | 8 | return str; |
| 495 | } | |
| 496 | 44 | int start = 0; |
| 497 | 44 | if (stripChars == null) { |
| 498 | 263 | while (start != strLen && Character.isWhitespace(str.charAt(start))) { |
| 499 | 240 | start++; |
| 500 | } | |
| 501 | 21 | } else if (stripChars.length() == 0) { |
| 502 | 8 | return str; |
| 503 | } else { | |
| 504 | 41 | while (start != strLen && stripChars.indexOf(str.charAt(start)) != INDEX_NOT_FOUND) { |
| 505 | 28 | start++; |
| 506 | } | |
| 507 | } | |
| 508 | 36 | return str.substring(start); |
| 509 | } | |
| 510 | ||
| 511 | /** | |
| 512 | * <p>Strips any of a set of characters from the end of a String.</p> | |
| 513 | * | |
| 514 | * <p>A {@code null} input String returns {@code null}. | |
| 515 | * An empty string ("") input returns the empty string.</p> | |
| 516 | * | |
| 517 | * <p>If the stripChars String is {@code null}, whitespace is | |
| 518 | * stripped as defined by {@link Character#isWhitespace(char)}.</p> | |
| 519 | * | |
| 520 | * <pre> | |
| 521 | * StringUtils.stripEnd(null, *) = null | |
| 522 | * StringUtils.stripEnd("", *) = "" | |
| 523 | * StringUtils.stripEnd("abc", "") = "abc" | |
| 524 | * StringUtils.stripEnd("abc", null) = "abc" | |
| 525 | * StringUtils.stripEnd(" abc", null) = " abc" | |
| 526 | * StringUtils.stripEnd("abc ", null) = "abc" | |
| 527 | * StringUtils.stripEnd(" abc ", null) = " abc" | |
| 528 | * StringUtils.stripEnd(" abcyx", "xyz") = " abc" | |
| 529 | * StringUtils.stripEnd("120.00", ".0") = "12" | |
| 530 | * </pre> | |
| 531 | * | |
| 532 | * @param str the String to remove characters from, may be null | |
| 533 | * @param stripChars the set of characters to remove, null treated as whitespace | |
| 534 | * @return the stripped String, {@code null} if null String input | |
| 535 | */ | |
| 536 | public static String stripEnd(final String str, final String stripChars) { | |
| 537 | int end; | |
| 538 | 54 | if (str == null || (end = str.length()) == 0) { |
| 539 | 15 | return str; |
| 540 | } | |
| 541 | ||
| 542 | 39 | if (stripChars == null) { |
| 543 | 173 | while (end != 0 && Character.isWhitespace(str.charAt(end - 1))) { |
| 544 | 156 | end--; |
| 545 | } | |
| 546 | 22 | } else if (stripChars.length() == 0) { |
| 547 | 8 | return str; |
| 548 | } else { | |
| 549 | 45 | while (end != 0 && stripChars.indexOf(str.charAt(end - 1)) != INDEX_NOT_FOUND) { |
| 550 | 31 | end--; |
| 551 | } | |
| 552 | } | |
| 553 | 31 | return str.substring(0, end); |
| 554 | } | |
| 555 | ||
| 556 | // StripAll | |
| 557 | //----------------------------------------------------------------------- | |
| 558 | /** | |
| 559 | * <p>Strips whitespace from the start and end of every String in an array. | |
| 560 | * Whitespace is defined by {@link Character#isWhitespace(char)}.</p> | |
| 561 | * | |
| 562 | * <p>A new array is returned each time, except for length zero. | |
| 563 | * A {@code null} array will return {@code null}. | |
| 564 | * An empty array will return itself. | |
| 565 | * A {@code null} array entry will be ignored.</p> | |
| 566 | * | |
| 567 | * <pre> | |
| 568 | * StringUtils.stripAll(null) = null | |
| 569 | * StringUtils.stripAll([]) = [] | |
| 570 | * StringUtils.stripAll(["abc", " abc"]) = ["abc", "abc"] | |
| 571 | * StringUtils.stripAll(["abc ", null]) = ["abc", null] | |
| 572 | * </pre> | |
| 573 | * | |
| 574 | * @param strs the array to remove whitespace from, may be null | |
| 575 | * @return the stripped Strings, {@code null} if null array input | |
| 576 | */ | |
| 577 | public static String[] stripAll(final String... strs) { | |
| 578 | 5 | return stripAll(strs, null); |
| 579 | } | |
| 580 | ||
| 581 | /** | |
| 582 | * <p>Strips any of a set of characters from the start and end of every | |
| 583 | * String in an array.</p> | |
| 584 | * Whitespace is defined by {@link Character#isWhitespace(char)}.</p> | |
| 585 | * | |
| 586 | * <p>A new array is returned each time, except for length zero. | |
| 587 | * A {@code null} array will return {@code null}. | |
| 588 | * An empty array will return itself. | |
| 589 | * A {@code null} array entry will be ignored. | |
| 590 | * A {@code null} stripChars will strip whitespace as defined by | |
| 591 | * {@link Character#isWhitespace(char)}.</p> | |
| 592 | * | |
| 593 | * <pre> | |
| 594 | * StringUtils.stripAll(null, *) = null | |
| 595 | * StringUtils.stripAll([], *) = [] | |
| 596 | * StringUtils.stripAll(["abc", " abc"], null) = ["abc", "abc"] | |
| 597 | * StringUtils.stripAll(["abc ", null], null) = ["abc", null] | |
| 598 | * StringUtils.stripAll(["abc ", null], "yz") = ["abc ", null] | |
| 599 | * StringUtils.stripAll(["yabcz", null], "yz") = ["abc", null] | |
| 600 | * </pre> | |
| 601 | * | |
| 602 | * @param strs the array to remove characters from, may be null | |
| 603 | * @param stripChars the characters to remove, null treated as whitespace | |
| 604 | * @return the stripped Strings, {@code null} if null array input | |
| 605 | */ | |
| 606 | public static String[] stripAll(final String[] strs, final String stripChars) { | |
| 607 | int strsLen; | |
| 608 | 8 | if (strs == null || (strsLen = strs.length) == 0) { |
| 609 | 4 | return strs; |
| 610 | } | |
| 611 | 4 | final String[] newArr = new String[strsLen]; |
| 612 | 14 | for (int i = 0; i < strsLen; i++) { |
| 613 | 10 | newArr[i] = strip(strs[i], stripChars); |
| 614 | } | |
| 615 | 4 | return newArr; |
| 616 | } | |
| 617 | ||
| 618 | /** | |
| 619 | * <p>Removes diacritics (~= accents) from a string. The case will not be altered.</p> | |
| 620 | * <p>For instance, 'à' will be replaced by 'a'.</p> | |
| 621 | * <p>Note that ligatures will be left as is.</p> | |
| 622 | * | |
| 623 | * <pre> | |
| 624 | * StringUtils.stripAccents(null) = null | |
| 625 | * StringUtils.stripAccents("") = "" | |
| 626 | * StringUtils.stripAccents("control") = "control" | |
| 627 | * StringUtils.stripAccents("éclair") = "eclair" | |
| 628 | * </pre> | |
| 629 | * | |
| 630 | * @param input String to be stripped | |
| 631 | * @return input text with diacritics removed | |
| 632 | * | |
| 633 | * @since 3.0 | |
| 634 | */ | |
| 635 | // See also Lucene's ASCIIFoldingFilter (Lucene 2.9) that replaces accented characters by their unaccented equivalent (and uncommitted bug fix: https://issues.apache.org/jira/browse/LUCENE-1343?focusedCommentId=12858907&page=com.atlassian.jira.plugin.system.issuetabpanels%3Acomment-tabpanel#action_12858907). | |
| 636 | public static String stripAccents(final String input) { | |
| 637 | 6 | if(input == null) { |
| 638 | 1 | return null; |
| 639 | } | |
| 640 | 5 | final Pattern pattern = Pattern.compile("\\p{InCombiningDiacriticalMarks}+");//$NON-NLS-1$ |
| 641 | 5 | final String decomposed = Normalizer.normalize(input, Normalizer.Form.NFD); |
| 642 | // Note that this doesn't correctly remove ligatures... | |
| 643 | 5 | return pattern.matcher(decomposed).replaceAll("");//$NON-NLS-1$ |
| 644 | } | |
| 645 | ||
| 646 | // Equals | |
| 647 | //----------------------------------------------------------------------- | |
| 648 | /** | |
| 649 | * <p>Compares two CharSequences, returning {@code true} if they represent | |
| 650 | * equal sequences of characters.</p> | |
| 651 | * | |
| 652 | * <p>{@code null}s are handled without exceptions. Two {@code null} | |
| 653 | * references are considered to be equal. The comparison is case sensitive.</p> | |
| 654 | * | |
| 655 | * <pre> | |
| 656 | * StringUtils.equals(null, null) = true | |
| 657 | * StringUtils.equals(null, "abc") = false | |
| 658 | * StringUtils.equals("abc", null) = false | |
| 659 | * StringUtils.equals("abc", "abc") = true | |
| 660 | * StringUtils.equals("abc", "ABC") = false | |
| 661 | * </pre> | |
| 662 | * | |
| 663 | * @see Object#equals(Object) | |
| 664 | * @param cs1 the first CharSequence, may be {@code null} | |
| 665 | * @param cs2 the second CharSequence, may be {@code null} | |
| 666 | * @return {@code true} if the CharSequences are equal (case-sensitive), or both {@code null} | |
| 667 | * @since 3.0 Changed signature from equals(String, String) to equals(CharSequence, CharSequence) | |
| 668 | */ | |
| 669 | public static boolean equals(final CharSequence cs1, final CharSequence cs2) { | |
| 670 | 270 | if (cs1 == cs2) { |
| 671 | 58 | return true; |
| 672 | } | |
| 673 | 212 | if (cs1 == null || cs2 == null) { |
| 674 | 4 | return false; |
| 675 | } | |
| 676 | 208 | if (cs1 instanceof String && cs2 instanceof String) { |
| 677 | 205 | return cs1.equals(cs2); |
| 678 | } | |
| 679 | 3 | return CharSequenceUtils.regionMatches(cs1, false, 0, cs2, 0, Math.max(cs1.length(), cs2.length())); |
| 680 | } | |
| 681 | ||
| 682 | /** | |
| 683 | * <p>Compares two CharSequences, returning {@code true} if they represent | |
| 684 | * equal sequences of characters, ignoring case.</p> | |
| 685 | * | |
| 686 | * <p>{@code null}s are handled without exceptions. Two {@code null} | |
| 687 | * references are considered equal. Comparison is case insensitive.</p> | |
| 688 | * | |
| 689 | * <pre> | |
| 690 | * StringUtils.equalsIgnoreCase(null, null) = true | |
| 691 | * StringUtils.equalsIgnoreCase(null, "abc") = false | |
| 692 | * StringUtils.equalsIgnoreCase("abc", null) = false | |
| 693 | * StringUtils.equalsIgnoreCase("abc", "abc") = true | |
| 694 | * StringUtils.equalsIgnoreCase("abc", "ABC") = true | |
| 695 | * </pre> | |
| 696 | * | |
| 697 | * @param str1 the first CharSequence, may be null | |
| 698 | * @param str2 the second CharSequence, may be null | |
| 699 | * @return {@code true} if the CharSequence are equal, case insensitive, or | |
| 700 | * both {@code null} | |
| 701 | * @since 3.0 Changed signature from equalsIgnoreCase(String, String) to equalsIgnoreCase(CharSequence, CharSequence) | |
| 702 | */ | |
| 703 | public static boolean equalsIgnoreCase(final CharSequence str1, final CharSequence str2) { | |
| 704 | 9 | if (str1 == null || str2 == null) { |
| 705 | 3 | return str1 == str2; |
| 706 | 6 | } else if (str1 == str2) { |
| 707 | 2 | return true; |
| 708 | 4 | } else if (str1.length() != str2.length()) { |
| 709 | 1 | return false; |
| 710 | } else { | |
| 711 | 3 | return CharSequenceUtils.regionMatches(str1, true, 0, str2, 0, str1.length()); |
| 712 | } | |
| 713 | } | |
| 714 | ||
| 715 | // IndexOf | |
| 716 | //----------------------------------------------------------------------- | |
| 717 | /** | |
| 718 | * <p>Finds the first index within a CharSequence, handling {@code null}. | |
| 719 | * This method uses {@link String#indexOf(int, int)} if possible.</p> | |
| 720 | * | |
| 721 | * <p>A {@code null} or empty ("") CharSequence will return {@code INDEX_NOT_FOUND (-1)}.</p> | |
| 722 | * | |
| 723 | * <pre> | |
| 724 | * StringUtils.indexOf(null, *) = -1 | |
| 725 | * StringUtils.indexOf("", *) = -1 | |
| 726 | * StringUtils.indexOf("aabaabaa", 'a') = 0 | |
| 727 | * StringUtils.indexOf("aabaabaa", 'b') = 2 | |
| 728 | * </pre> | |
| 729 | * | |
| 730 | * @param seq the CharSequence to check, may be null | |
| 731 | * @param searchChar the character to find | |
| 732 | * @return the first index of the search character, | |
| 733 | * -1 if no match or {@code null} string input | |
| 734 | * @since 2.0 | |
| 735 | * @since 3.0 Changed signature from indexOf(String, int) to indexOf(CharSequence, int) | |
| 736 | */ | |
| 737 | public static int indexOf(final CharSequence seq, final int searchChar) { | |
| 738 | 5 | if (isEmpty(seq)) { |
| 739 | 2 | return INDEX_NOT_FOUND; |
| 740 | } | |
| 741 | 3 | return CharSequenceUtils.indexOf(seq, searchChar, 0); |
| 742 | } | |
| 743 | ||
| 744 | /** | |
| 745 | * <p>Finds the first index within a CharSequence from a start position, | |
| 746 | * handling {@code null}. | |
| 747 | * This method uses {@link String#indexOf(int, int)} if possible.</p> | |
| 748 | * | |
| 749 | * <p>A {@code null} or empty ("") CharSequence will return {@code (INDEX_NOT_FOUND) -1}. | |
| 750 | * A negative start position is treated as zero. | |
| 751 | * A start position greater than the string length returns {@code -1}.</p> | |
| 752 | * | |
| 753 | * <pre> | |
| 754 | * StringUtils.indexOf(null, *, *) = -1 | |
| 755 | * StringUtils.indexOf("", *, *) = -1 | |
| 756 | * StringUtils.indexOf("aabaabaa", 'b', 0) = 2 | |
| 757 | * StringUtils.indexOf("aabaabaa", 'b', 3) = 5 | |
| 758 | * StringUtils.indexOf("aabaabaa", 'b', 9) = -1 | |
| 759 | * StringUtils.indexOf("aabaabaa", 'b', -1) = 2 | |
| 760 | * </pre> | |
| 761 | * | |
| 762 | * @param seq the CharSequence to check, may be null | |
| 763 | * @param searchChar the character to find | |
| 764 | * @param startPos the start position, negative treated as zero | |
| 765 | * @return the first index of the search character, | |
| 766 | * -1 if no match or {@code null} string input | |
| 767 | * @since 2.0 | |
| 768 | * @since 3.0 Changed signature from indexOf(String, int, int) to indexOf(CharSequence, int, int) | |
| 769 | */ | |
| 770 | public static int indexOf(final CharSequence seq, final int searchChar, final int startPos) { | |
| 771 | 10 | if (isEmpty(seq)) { |
| 772 | 4 | return INDEX_NOT_FOUND; |
| 773 | } | |
| 774 | 6 | return CharSequenceUtils.indexOf(seq, searchChar, startPos); |
| 775 | } | |
| 776 | ||
| 777 | /** | |
| 778 | * <p>Finds the first index within a CharSequence, handling {@code null}. | |
| 779 | * This method uses {@link String#indexOf(String, int)} if possible.</p> | |
| 780 | * | |
| 781 | * <p>A {@code null} CharSequence will return {@code -1}.</p> | |
| 782 | * | |
| 783 | * <pre> | |
| 784 | * StringUtils.indexOf(null, *) = -1 | |
| 785 | * StringUtils.indexOf(*, null) = -1 | |
| 786 | * StringUtils.indexOf("", "") = 0 | |
| 787 | * StringUtils.indexOf("", *) = -1 (except when * = "") | |
| 788 | * StringUtils.indexOf("aabaabaa", "a") = 0 | |
| 789 | * StringUtils.indexOf("aabaabaa", "b") = 2 | |
| 790 | * StringUtils.indexOf("aabaabaa", "ab") = 1 | |
| 791 | * StringUtils.indexOf("aabaabaa", "") = 0 | |
| 792 | * </pre> | |
| 793 | * | |
| 794 | * @param seq the CharSequence to check, may be null | |
| 795 | * @param searchSeq the CharSequence to find, may be null | |
| 796 | * @return the first index of the search CharSequence, | |
| 797 | * -1 if no match or {@code null} string input | |
| 798 | * @since 2.0 | |
| 799 | * @since 3.0 Changed signature from indexOf(String, String) to indexOf(CharSequence, CharSequence) | |
| 800 | */ | |
| 801 | public static int indexOf(final CharSequence seq, final CharSequence searchSeq) { | |
| 802 | 8 | if (seq == null || searchSeq == null) { |
| 803 | 2 | return INDEX_NOT_FOUND; |
| 804 | } | |
| 805 | 6 | return CharSequenceUtils.indexOf(seq, searchSeq, 0); |
| 806 | } | |
| 807 | ||
| 808 | /** | |
| 809 | * <p>Finds the first index within a CharSequence, handling {@code null}. | |
| 810 | * This method uses {@link String#indexOf(String, int)} if possible.</p> | |
| 811 | * | |
| 812 | * <p>A {@code null} CharSequence will return {@code -1}. | |
| 813 | * A negative start position is treated as zero. | |
| 814 | * An empty ("") search CharSequence always matches. | |
| 815 | * A start position greater than the string length only matches | |
| 816 | * an empty search CharSequence.</p> | |
| 817 | * | |
| 818 | * <pre> | |
| 819 | * StringUtils.indexOf(null, *, *) = -1 | |
| 820 | * StringUtils.indexOf(*, null, *) = -1 | |
| 821 | * StringUtils.indexOf("", "", 0) = 0 | |
| 822 | * StringUtils.indexOf("", *, 0) = -1 (except when * = "") | |
| 823 | * StringUtils.indexOf("aabaabaa", "a", 0) = 0 | |
| 824 | * StringUtils.indexOf("aabaabaa", "b", 0) = 2 | |
| 825 | * StringUtils.indexOf("aabaabaa", "ab", 0) = 1 | |
| 826 | * StringUtils.indexOf("aabaabaa", "b", 3) = 5 | |
| 827 | * StringUtils.indexOf("aabaabaa", "b", 9) = -1 | |
| 828 | * StringUtils.indexOf("aabaabaa", "b", -1) = 2 | |
| 829 | * StringUtils.indexOf("aabaabaa", "", 2) = 2 | |
| 830 | * StringUtils.indexOf("abc", "", 9) = 3 | |
| 831 | * </pre> | |
| 832 | * | |
| 833 | * @param seq the CharSequence to check, may be null | |
| 834 | * @param searchSeq the CharSequence to find, may be null | |
| 835 | * @param startPos the start position, negative treated as zero | |
| 836 | * @return the first index of the search CharSequence, | |
| 837 | * -1 if no match or {@code null} string input | |
| 838 | * @since 2.0 | |
| 839 | * @since 3.0 Changed signature from indexOf(String, String, int) to indexOf(CharSequence, CharSequence, int) | |
| 840 | */ | |
| 841 | public static int indexOf(final CharSequence seq, final CharSequence searchSeq, final int startPos) { | |
| 842 | 21 | if (seq == null || searchSeq == null) { |
| 843 | 6 | return INDEX_NOT_FOUND; |
| 844 | } | |
| 845 | 15 | return CharSequenceUtils.indexOf(seq, searchSeq, startPos); |
| 846 | } | |
| 847 | ||
| 848 | /** | |
| 849 | * <p>Finds the n-th index within a CharSequence, handling {@code null}. | |
| 850 | * This method uses {@link String#indexOf(String)} if possible.</p> | |
| 851 | * | |
| 852 | * <p>A {@code null} CharSequence will return {@code -1}.</p> | |
| 853 | * | |
| 854 | * <pre> | |
| 855 | * StringUtils.ordinalIndexOf(null, *, *) = -1 | |
| 856 | * StringUtils.ordinalIndexOf(*, null, *) = -1 | |
| 857 | * StringUtils.ordinalIndexOf("", "", *) = 0 | |
| 858 | * StringUtils.ordinalIndexOf("aabaabaa", "a", 1) = 0 | |
| 859 | * StringUtils.ordinalIndexOf("aabaabaa", "a", 2) = 1 | |
| 860 | * StringUtils.ordinalIndexOf("aabaabaa", "b", 1) = 2 | |
| 861 | * StringUtils.ordinalIndexOf("aabaabaa", "b", 2) = 5 | |
| 862 | * StringUtils.ordinalIndexOf("aabaabaa", "ab", 1) = 1 | |
| 863 | * StringUtils.ordinalIndexOf("aabaabaa", "ab", 2) = 4 | |
| 864 | * StringUtils.ordinalIndexOf("aabaabaa", "", 1) = 0 | |
| 865 | * StringUtils.ordinalIndexOf("aabaabaa", "", 2) = 0 | |
| 866 | * </pre> | |
| 867 | * | |
| 868 | * <p>Note that 'head(CharSequence str, int n)' may be implemented as: </p> | |
| 869 | * | |
| 870 | * <pre> | |
| 871 | * str.substring(0, lastOrdinalIndexOf(str, "\n", n)) | |
| 872 | * </pre> | |
| 873 | * | |
| 874 | * @param str the CharSequence to check, may be null | |
| 875 | * @param searchStr the CharSequence to find, may be null | |
| 876 | * @param ordinal the n-th {@code searchStr} to find | |
| 877 | * @return the n-th index of the search CharSequence, | |
| 878 | * {@code -1} ({@code INDEX_NOT_FOUND}) if no match or {@code null} string input | |
| 879 | * @since 2.1 | |
| 880 | * @since 3.0 Changed signature from ordinalIndexOf(String, String, int) to ordinalIndexOf(CharSequence, CharSequence, int) | |
| 881 | */ | |
| 882 | public static int ordinalIndexOf(final CharSequence str, final CharSequence searchStr, final int ordinal) { | |
| 883 | 53 | return ordinalIndexOf(str, searchStr, ordinal, false); |
| 884 | } | |
| 885 | ||
| 886 | /** | |
| 887 | * <p>Finds the n-th index within a String, handling {@code null}. | |
| 888 | * This method uses {@link String#indexOf(String)} if possible.</p> | |
| 889 | * | |
| 890 | * <p>A {@code null} CharSequence will return {@code -1}.</p> | |
| 891 | * | |
| 892 | * @param str the CharSequence to check, may be null | |
| 893 | * @param searchStr the CharSequence to find, may be null | |
| 894 | * @param ordinal the n-th {@code searchStr} to find | |
| 895 | * @param lastIndex true if lastOrdinalIndexOf() otherwise false if ordinalIndexOf() | |
| 896 | * @return the n-th index of the search CharSequence, | |
| 897 | * {@code -1} ({@code INDEX_NOT_FOUND}) if no match or {@code null} string input | |
| 898 | */ | |
| 899 | // Shared code between ordinalIndexOf(String,String,int) and lastOrdinalIndexOf(String,String,int) | |
| 900 | private static int ordinalIndexOf(final CharSequence str, final CharSequence searchStr, final int ordinal, final boolean lastIndex) { | |
| 901 | 64 | if (str == null || searchStr == null || ordinal <= 0) { |
| 902 | 30 | return INDEX_NOT_FOUND; |
| 903 | } | |
| 904 | 34 | if (searchStr.length() == 0) { |
| 905 | 9 | return lastIndex ? str.length() : 0; |
| 906 | } | |
| 907 | 25 | int found = 0; |
| 908 | 25 | int index = lastIndex ? str.length() : INDEX_NOT_FOUND; |
| 909 | do { | |
| 910 | 86 | if (lastIndex) { |
| 911 | 9 | index = CharSequenceUtils.lastIndexOf(str, searchStr, index - 1); |
| 912 | } else { | |
| 913 | 77 | index = CharSequenceUtils.indexOf(str, searchStr, index + 1); |
| 914 | } | |
| 915 | 86 | if (index < 0) { |
| 916 | 4 | return index; |
| 917 | } | |
| 918 | 82 | found++; |
| 919 | 82 | } while (found < ordinal); |
| 920 | 21 | return index; |
| 921 | } | |
| 922 | ||
| 923 | /** | |
| 924 | * <p>Case in-sensitive find of the first index within a CharSequence.</p> | |
| 925 | * | |
| 926 | * <p>A {@code null} CharSequence will return {@code -1}. | |
| 927 | * A negative start position is treated as zero. | |
| 928 | * An empty ("") search CharSequence always matches. | |
| 929 | * A start position greater than the string length only matches | |
| 930 | * an empty search CharSequence.</p> | |
| 931 | * | |
| 932 | * <pre> | |
| 933 | * StringUtils.indexOfIgnoreCase(null, *) = -1 | |
| 934 | * StringUtils.indexOfIgnoreCase(*, null) = -1 | |
| 935 | * StringUtils.indexOfIgnoreCase("", "") = 0 | |
| 936 | * StringUtils.indexOfIgnoreCase("aabaabaa", "a") = 0 | |
| 937 | * StringUtils.indexOfIgnoreCase("aabaabaa", "b") = 2 | |
| 938 | * StringUtils.indexOfIgnoreCase("aabaabaa", "ab") = 1 | |
| 939 | * </pre> | |
| 940 | * | |
| 941 | * @param str the CharSequence to check, may be null | |
| 942 | * @param searchStr the CharSequence to find, may be null | |
| 943 | * @return the first index of the search CharSequence, | |
| 944 | * -1 if no match or {@code null} string input | |
| 945 | * @since 2.5 | |
| 946 | * @since 3.0 Changed signature from indexOfIgnoreCase(String, String) to indexOfIgnoreCase(CharSequence, CharSequence) | |
| 947 | */ | |
| 948 | public static int indexOfIgnoreCase(final CharSequence str, final CharSequence searchStr) { | |
| 949 | 11 | return indexOfIgnoreCase(str, searchStr, 0); |
| 950 | } | |
| 951 | ||
| 952 | /** | |
| 953 | * <p>Case in-sensitive find of the first index within a CharSequence | |
| 954 | * from the specified position.</p> | |
| 955 | * | |
| 956 | * <p>A {@code null} CharSequence will return {@code -1}. | |
| 957 | * A negative start position is treated as zero. | |
| 958 | * An empty ("") search CharSequence always matches. | |
| 959 | * A start position greater than the string length only matches | |
| 960 | * an empty search CharSequence.</p> | |
| 961 | * | |
| 962 | * <pre> | |
| 963 | * StringUtils.indexOfIgnoreCase(null, *, *) = -1 | |
| 964 | * StringUtils.indexOfIgnoreCase(*, null, *) = -1 | |
| 965 | * StringUtils.indexOfIgnoreCase("", "", 0) = 0 | |
| 966 | * StringUtils.indexOfIgnoreCase("aabaabaa", "A", 0) = 0 | |
| 967 | * StringUtils.indexOfIgnoreCase("aabaabaa", "B", 0) = 2 | |
| 968 | * StringUtils.indexOfIgnoreCase("aabaabaa", "AB", 0) = 1 | |
| 969 | * StringUtils.indexOfIgnoreCase("aabaabaa", "B", 3) = 5 | |
| 970 | * StringUtils.indexOfIgnoreCase("aabaabaa", "B", 9) = -1 | |
| 971 | * StringUtils.indexOfIgnoreCase("aabaabaa", "B", -1) = 2 | |
| 972 | * StringUtils.indexOfIgnoreCase("aabaabaa", "", 2) = 2 | |
| 973 | * StringUtils.indexOfIgnoreCase("abc", "", 9) = 3 | |
| 974 | * </pre> | |
| 975 | * | |
| 976 | * @param str the CharSequence to check, may be null | |
| 977 | * @param searchStr the CharSequence to find, may be null | |
| 978 | * @param startPos the start position, negative treated as zero | |
| 979 | * @return the first index of the search CharSequence, | |
| 980 | * -1 if no match or {@code null} string input | |
| 981 | * @since 2.5 | |
| 982 | * @since 3.0 Changed signature from indexOfIgnoreCase(String, String, int) to indexOfIgnoreCase(CharSequence, CharSequence, int) | |
| 983 | */ | |
| 984 | public static int indexOfIgnoreCase(final CharSequence str, final CharSequence searchStr, int startPos) { | |
| 985 | 25 | if (str == null || searchStr == null) { |
| 986 | 3 | return INDEX_NOT_FOUND; |
| 987 | } | |
| 988 | 22 | if (startPos < 0) { |
| 989 | 1 | startPos = 0; |
| 990 | } | |
| 991 | 22 | final int endLimit = str.length() - searchStr.length() + 1; |
| 992 | 22 | if (startPos > endLimit) { |
| 993 | 1 | return INDEX_NOT_FOUND; |
| 994 | } | |
| 995 | 21 | if (searchStr.length() == 0) { |
| 996 | 3 | return startPos; |
| 997 | } | |
| 998 | 32 | for (int i = startPos; i < endLimit; i++) { |
| 999 | 27 | if (CharSequenceUtils.regionMatches(str, true, i, searchStr, 0, searchStr.length())) { |
| 1000 | 13 | return i; |
| 1001 | } | |
| 1002 | } | |
| 1003 | 5 | return INDEX_NOT_FOUND; |
| 1004 | } | |
| 1005 | ||
| 1006 | // LastIndexOf | |
| 1007 | //----------------------------------------------------------------------- | |
| 1008 | /** | |
| 1009 | * <p>Finds the last index within a CharSequence, handling {@code null}. | |
| 1010 | * This method uses {@link String#lastIndexOf(int)} if possible.</p> | |
| 1011 | * | |
| 1012 | * <p>A {@code null} or empty ("") CharSequence will return {@code -1}.</p> | |
| 1013 | * | |
| 1014 | * <pre> | |
| 1015 | * StringUtils.lastIndexOf(null, *) = -1 | |
| 1016 | * StringUtils.lastIndexOf("", *) = -1 | |
| 1017 | * StringUtils.lastIndexOf("aabaabaa", 'a') = 7 | |
| 1018 | * StringUtils.lastIndexOf("aabaabaa", 'b') = 5 | |
| 1019 | * </pre> | |
| 1020 | * | |
| 1021 | * @param seq the CharSequence to check, may be null | |
| 1022 | * @param searchChar the character to find | |
| 1023 | * @return the last index of the search character, | |
| 1024 | * -1 if no match or {@code null} string input | |
| 1025 | * @since 2.0 | |
| 1026 | * @since 3.0 Changed signature from lastIndexOf(String, int) to lastIndexOf(CharSequence, int) | |
| 1027 | */ | |
| 1028 | public static int lastIndexOf(final CharSequence seq, final int searchChar) { | |
| 1029 | 5 | if (isEmpty(seq)) { |
| 1030 | 2 | return INDEX_NOT_FOUND; |
| 1031 | } | |
| 1032 | 3 | return CharSequenceUtils.lastIndexOf(seq, searchChar, seq.length()); |
| 1033 | } | |
| 1034 | ||
| 1035 | /** | |
| 1036 | * <p>Finds the last index within a CharSequence from a start position, | |
| 1037 | * handling {@code null}. | |
| 1038 | * This method uses {@link String#lastIndexOf(int, int)} if possible.</p> | |
| 1039 | * | |
| 1040 | * <p>A {@code null} or empty ("") CharSequence will return {@code -1}. | |
| 1041 | * A negative start position returns {@code -1}. | |
| 1042 | * A start position greater than the string length searches the whole string.</p> | |
| 1043 | * | |
| 1044 | * <pre> | |
| 1045 | * StringUtils.lastIndexOf(null, *, *) = -1 | |
| 1046 | * StringUtils.lastIndexOf("", *, *) = -1 | |
| 1047 | * StringUtils.lastIndexOf("aabaabaa", 'b', 8) = 5 | |
| 1048 | * StringUtils.lastIndexOf("aabaabaa", 'b', 4) = 2 | |
| 1049 | * StringUtils.lastIndexOf("aabaabaa", 'b', 0) = -1 | |
| 1050 | * StringUtils.lastIndexOf("aabaabaa", 'b', 9) = 5 | |
| 1051 | * StringUtils.lastIndexOf("aabaabaa", 'b', -1) = -1 | |
| 1052 | * StringUtils.lastIndexOf("aabaabaa", 'a', 0) = 0 | |
| 1053 | * </pre> | |
| 1054 | * | |
| 1055 | * @param seq the CharSequence to check, may be null | |
| 1056 | * @param searchChar the character to find | |
| 1057 | * @param startPos the start position | |
| 1058 | * @return the last index of the search character, | |
| 1059 | * -1 if no match or {@code null} string input | |
| 1060 | * @since 2.0 | |
| 1061 | * @since 3.0 Changed signature from lastIndexOf(String, int, int) to lastIndexOf(CharSequence, int, int) | |
| 1062 | */ | |
| 1063 | public static int lastIndexOf(final CharSequence seq, final int searchChar, final int startPos) { | |
| 1064 | 11 | if (isEmpty(seq)) { |
| 1065 | 4 | return INDEX_NOT_FOUND; |
| 1066 | } | |
| 1067 | 7 | return CharSequenceUtils.lastIndexOf(seq, searchChar, startPos); |
| 1068 | } | |
| 1069 | ||
| 1070 | /** | |
| 1071 | * <p>Finds the last index within a CharSequence, handling {@code null}. | |
| 1072 | * This method uses {@link String#lastIndexOf(String)} if possible.</p> | |
| 1073 | * | |
| 1074 | * <p>A {@code null} CharSequence will return {@code -1}.</p> | |
| 1075 | * | |
| 1076 | * <pre> | |
| 1077 | * StringUtils.lastIndexOf(null, *) = -1 | |
| 1078 | * StringUtils.lastIndexOf(*, null) = -1 | |
| 1079 | * StringUtils.lastIndexOf("", "") = 0 | |
| 1080 | * StringUtils.lastIndexOf("aabaabaa", "a") = 7 | |
| 1081 | * StringUtils.lastIndexOf("aabaabaa", "b") = 5 | |
| 1082 | * StringUtils.lastIndexOf("aabaabaa", "ab") = 4 | |
| 1083 | * StringUtils.lastIndexOf("aabaabaa", "") = 8 | |
| 1084 | * </pre> | |
| 1085 | * | |
| 1086 | * @param seq the CharSequence to check, may be null | |
| 1087 | * @param searchSeq the CharSequence to find, may be null | |
| 1088 | * @return the last index of the search String, | |
| 1089 | * -1 if no match or {@code null} string input | |
| 1090 | * @since 2.0 | |
| 1091 | * @since 3.0 Changed signature from lastIndexOf(String, String) to lastIndexOf(CharSequence, CharSequence) | |
| 1092 | */ | |
| 1093 | public static int lastIndexOf(final CharSequence seq, final CharSequence searchSeq) { | |
| 1094 | 9 | if (seq == null || searchSeq == null) { |
| 1095 | 2 | return INDEX_NOT_FOUND; |
| 1096 | } | |
| 1097 | 7 | return CharSequenceUtils.lastIndexOf(seq, searchSeq, seq.length()); |
| 1098 | } | |
| 1099 | ||
| 1100 | /** | |
| 1101 | * <p>Finds the n-th last index within a String, handling {@code null}. | |
| 1102 | * This method uses {@link String#lastIndexOf(String)}.</p> | |
| 1103 | * | |
| 1104 | * <p>A {@code null} String will return {@code -1}.</p> | |
| 1105 | * | |
| 1106 | * <pre> | |
| 1107 | * StringUtils.lastOrdinalIndexOf(null, *, *) = -1 | |
| 1108 | * StringUtils.lastOrdinalIndexOf(*, null, *) = -1 | |
| 1109 | * StringUtils.lastOrdinalIndexOf("", "", *) = 0 | |
| 1110 | * StringUtils.lastOrdinalIndexOf("aabaabaa", "a", 1) = 7 | |
| 1111 | * StringUtils.lastOrdinalIndexOf("aabaabaa", "a", 2) = 6 | |
| 1112 | * StringUtils.lastOrdinalIndexOf("aabaabaa", "b", 1) = 5 | |
| 1113 | * StringUtils.lastOrdinalIndexOf("aabaabaa", "b", 2) = 2 | |
| 1114 | * StringUtils.lastOrdinalIndexOf("aabaabaa", "ab", 1) = 4 | |
| 1115 | * StringUtils.lastOrdinalIndexOf("aabaabaa", "ab", 2) = 1 | |
| 1116 | * StringUtils.lastOrdinalIndexOf("aabaabaa", "", 1) = 8 | |
| 1117 | * StringUtils.lastOrdinalIndexOf("aabaabaa", "", 2) = 8 | |
| 1118 | * </pre> | |
| 1119 | * | |
| 1120 | * <p>Note that 'tail(CharSequence str, int n)' may be implemented as: </p> | |
| 1121 | * | |
| 1122 | * <pre> | |
| 1123 | * str.substring(lastOrdinalIndexOf(str, "\n", n) + 1) | |
| 1124 | * </pre> | |
| 1125 | * | |
| 1126 | * @param str the CharSequence to check, may be null | |
| 1127 | * @param searchStr the CharSequence to find, may be null | |
| 1128 | * @param ordinal the n-th last {@code searchStr} to find | |
| 1129 | * @return the n-th last index of the search CharSequence, | |
| 1130 | * {@code -1} ({@code INDEX_NOT_FOUND}) if no match or {@code null} string input | |
| 1131 | * @since 2.5 | |
| 1132 | * @since 3.0 Changed signature from lastOrdinalIndexOf(String, String, int) to lastOrdinalIndexOf(CharSequence, CharSequence, int) | |
| 1133 | */ | |
| 1134 | public static int lastOrdinalIndexOf(final CharSequence str, final CharSequence searchStr, final int ordinal) { | |
| 1135 | 11 | return ordinalIndexOf(str, searchStr, ordinal, true); |
| 1136 | } | |
| 1137 | ||
| 1138 | /** | |
| 1139 | * <p>Finds the first index within a CharSequence, handling {@code null}. | |
| 1140 | * This method uses {@link String#lastIndexOf(String, int)} if possible.</p> | |
| 1141 | * | |
| 1142 | * <p>A {@code null} CharSequence will return {@code -1}. | |
| 1143 | * A negative start position returns {@code -1}. | |
| 1144 | * An empty ("") search CharSequence always matches unless the start position is negative. | |
| 1145 | * A start position greater than the string length searches the whole string.</p> | |
| 1146 | * | |
| 1147 | * <pre> | |
| 1148 | * StringUtils.lastIndexOf(null, *, *) = -1 | |
| 1149 | * StringUtils.lastIndexOf(*, null, *) = -1 | |
| 1150 | * StringUtils.lastIndexOf("aabaabaa", "a", 8) = 7 | |
| 1151 | * StringUtils.lastIndexOf("aabaabaa", "b", 8) = 5 | |
| 1152 | * StringUtils.lastIndexOf("aabaabaa", "ab", 8) = 4 | |
| 1153 | * StringUtils.lastIndexOf("aabaabaa", "b", 9) = 5 | |
| 1154 | * StringUtils.lastIndexOf("aabaabaa", "b", -1) = -1 | |
| 1155 | * StringUtils.lastIndexOf("aabaabaa", "a", 0) = 0 | |
| 1156 | * StringUtils.lastIndexOf("aabaabaa", "b", 0) = -1 | |
| 1157 | * </pre> | |
| 1158 | * | |
| 1159 | * @param seq the CharSequence to check, may be null | |
| 1160 | * @param searchSeq the CharSequence to find, may be null | |
| 1161 | * @param startPos the start position, negative treated as zero | |
| 1162 | * @return the first index of the search CharSequence, | |
| 1163 | * -1 if no match or {@code null} string input | |
| 1164 | * @since 2.0 | |
| 1165 | * @since 3.0 Changed signature from lastIndexOf(String, String, int) to lastIndexOf(CharSequence, CharSequence, int) | |
| 1166 | */ | |
| 1167 | public static int lastIndexOf(final CharSequence seq, final CharSequence searchSeq, final int startPos) { | |
| 1168 | 21 | if (seq == null || searchSeq == null) { |
| 1169 | 6 | return INDEX_NOT_FOUND; |
| 1170 | } | |
| 1171 | 15 | return CharSequenceUtils.lastIndexOf(seq, searchSeq, startPos); |
| 1172 | } | |
| 1173 | ||
| 1174 | /** | |
| 1175 | * <p>Case in-sensitive find of the last index within a CharSequence.</p> | |
| 1176 | * | |
| 1177 | * <p>A {@code null} CharSequence will return {@code -1}. | |
| 1178 | * A negative start position returns {@code -1}. | |
| 1179 | * An empty ("") search CharSequence always matches unless the start position is negative. | |
| 1180 | * A start position greater than the string length searches the whole string.</p> | |
| 1181 | * | |
| 1182 | * <pre> | |
| 1183 | * StringUtils.lastIndexOfIgnoreCase(null, *) = -1 | |
| 1184 | * StringUtils.lastIndexOfIgnoreCase(*, null) = -1 | |
| 1185 | * StringUtils.lastIndexOfIgnoreCase("aabaabaa", "A") = 7 | |
| 1186 | * StringUtils.lastIndexOfIgnoreCase("aabaabaa", "B") = 5 | |
| 1187 | * StringUtils.lastIndexOfIgnoreCase("aabaabaa", "AB") = 4 | |
| 1188 | * </pre> | |
| 1189 | * | |
| 1190 | * @param str the CharSequence to check, may be null | |
| 1191 | * @param searchStr the CharSequence to find, may be null | |
| 1192 | * @return the first index of the search CharSequence, | |
| 1193 | * -1 if no match or {@code null} string input | |
| 1194 | * @since 2.5 | |
| 1195 | * @since 3.0 Changed signature from lastIndexOfIgnoreCase(String, String) to lastIndexOfIgnoreCase(CharSequence, CharSequence) | |
| 1196 | */ | |
| 1197 | public static int lastIndexOfIgnoreCase(final CharSequence str, final CharSequence searchStr) { | |
| 1198 | 14 | if (str == null || searchStr == null) { |
| 1199 | 3 | return INDEX_NOT_FOUND; |
| 1200 | } | |
| 1201 | 11 | return lastIndexOfIgnoreCase(str, searchStr, str.length()); |
| 1202 | } | |
| 1203 | ||
| 1204 | /** | |
| 1205 | * <p>Case in-sensitive find of the last index within a CharSequence | |
| 1206 | * from the specified position.</p> | |
| 1207 | * | |
| 1208 | * <p>A {@code null} CharSequence will return {@code -1}. | |
| 1209 | * A negative start position returns {@code -1}. | |
| 1210 | * An empty ("") search CharSequence always matches unless the start position is negative. | |
| 1211 | * A start position greater than the string length searches the whole string.</p> | |
| 1212 | * | |
| 1213 | * <pre> | |
| 1214 | * StringUtils.lastIndexOfIgnoreCase(null, *, *) = -1 | |
| 1215 | * StringUtils.lastIndexOfIgnoreCase(*, null, *) = -1 | |
| 1216 | * StringUtils.lastIndexOfIgnoreCase("aabaabaa", "A", 8) = 7 | |
| 1217 | * StringUtils.lastIndexOfIgnoreCase("aabaabaa", "B", 8) = 5 | |
| 1218 | * StringUtils.lastIndexOfIgnoreCase("aabaabaa", "AB", 8) = 4 | |
| 1219 | * StringUtils.lastIndexOfIgnoreCase("aabaabaa", "B", 9) = 5 | |
| 1220 | * StringUtils.lastIndexOfIgnoreCase("aabaabaa", "B", -1) = -1 | |
| 1221 | * StringUtils.lastIndexOfIgnoreCase("aabaabaa", "A", 0) = 0 | |
| 1222 | * StringUtils.lastIndexOfIgnoreCase("aabaabaa", "B", 0) = -1 | |
| 1223 | * </pre> | |
| 1224 | * | |
| 1225 | * @param str the CharSequence to check, may be null | |
| 1226 | * @param searchStr the CharSequence to find, may be null | |
| 1227 | * @param startPos the start position | |
| 1228 | * @return the first index of the search CharSequence, | |
| 1229 | * -1 if no match or {@code null} input | |
| 1230 | * @since 2.5 | |
| 1231 | * @since 3.0 Changed signature from lastIndexOfIgnoreCase(String, String, int) to lastIndexOfIgnoreCase(CharSequence, CharSequence, int) | |
| 1232 | */ | |
| 1233 | public static int lastIndexOfIgnoreCase(final CharSequence str, final CharSequence searchStr, int startPos) { | |
| 1234 | 32 | if (str == null || searchStr == null) { |
| 1235 | 6 | return INDEX_NOT_FOUND; |
| 1236 | } | |
| 1237 | 26 | if (startPos > str.length() - searchStr.length()) { |
| 1238 | 15 | startPos = str.length() - searchStr.length(); |
| 1239 | } | |
| 1240 | 26 | if (startPos < 0) { |
| 1241 | 5 | return INDEX_NOT_FOUND; |
| 1242 | } | |
| 1243 | 21 | if (searchStr.length() == 0) { |
| 1244 | 6 | return startPos; |
| 1245 | } | |
| 1246 | ||
| 1247 | 31 | for (int i = startPos; i >= 0; i--) { |
| 1248 | 30 | if (CharSequenceUtils.regionMatches(str, true, i, searchStr, 0, searchStr.length())) { |
| 1249 | 14 | return i; |
| 1250 | } | |
| 1251 | } | |
| 1252 | 1 | return INDEX_NOT_FOUND; |
| 1253 | } | |
| 1254 | ||
| 1255 | // Contains | |
| 1256 | //----------------------------------------------------------------------- | |
| 1257 | /** | |
| 1258 | * <p>Checks if CharSequence contains a search character, handling {@code null}. | |
| 1259 | * This method uses {@link String#indexOf(int)} if possible.</p> | |
| 1260 | * | |
| 1261 | * <p>A {@code null} or empty ("") CharSequence will return {@code false}.</p> | |
| 1262 | * | |
| 1263 | * <pre> | |
| 1264 | * StringUtils.contains(null, *) = false | |
| 1265 | * StringUtils.contains("", *) = false | |
| 1266 | * StringUtils.contains("abc", 'a') = true | |
| 1267 | * StringUtils.contains("abc", 'z') = false | |
| 1268 | * </pre> | |
| 1269 | * | |
| 1270 | * @param seq the CharSequence to check, may be null | |
| 1271 | * @param searchChar the character to find | |
| 1272 | * @return true if the CharSequence contains the search character, | |
| 1273 | * false if not or {@code null} string input | |
| 1274 | * @since 2.0 | |
| 1275 | * @since 3.0 Changed signature from contains(String, int) to contains(CharSequence, int) | |
| 1276 | */ | |
| 1277 | public static boolean contains(final CharSequence seq, final int searchChar) { | |
| 1278 | 6 | if (isEmpty(seq)) { |
| 1279 | 2 | return false; |
| 1280 | } | |
| 1281 | 4 | return CharSequenceUtils.indexOf(seq, searchChar, 0) >= 0; |
| 1282 | } | |
| 1283 | ||
| 1284 | /** | |
| 1285 | * <p>Checks if CharSequence contains a search CharSequence, handling {@code null}. | |
| 1286 | * This method uses {@link String#indexOf(String)} if possible.</p> | |
| 1287 | * | |
| 1288 | * <p>A {@code null} CharSequence will return {@code false}.</p> | |
| 1289 | * | |
| 1290 | * <pre> | |
| 1291 | * StringUtils.contains(null, *) = false | |
| 1292 | * StringUtils.contains(*, null) = false | |
| 1293 | * StringUtils.contains("", "") = true | |
| 1294 | * StringUtils.contains("abc", "") = true | |
| 1295 | * StringUtils.contains("abc", "a") = true | |
| 1296 | * StringUtils.contains("abc", "z") = false | |
| 1297 | * </pre> | |
| 1298 | * | |
| 1299 | * @param seq the CharSequence to check, may be null | |
| 1300 | * @param searchSeq the CharSequence to find, may be null | |
| 1301 | * @return true if the CharSequence contains the search CharSequence, | |
| 1302 | * false if not or {@code null} string input | |
| 1303 | * @since 2.0 | |
| 1304 | * @since 3.0 Changed signature from contains(String, String) to contains(CharSequence, CharSequence) | |
| 1305 | */ | |
| 1306 | public static boolean contains(final CharSequence seq, final CharSequence searchSeq) { | |
| 1307 | 23 | if (seq == null || searchSeq == null) { |
| 1308 | 6 | return false; |
| 1309 | } | |
| 1310 | 17 | return CharSequenceUtils.indexOf(seq, searchSeq, 0) >= 0; |
| 1311 | } | |
| 1312 | ||
| 1313 | /** | |
| 1314 | * <p>Checks if CharSequence contains a search CharSequence irrespective of case, | |
| 1315 | * handling {@code null}. Case-insensitivity is defined as by | |
| 1316 | * {@link String#equalsIgnoreCase(String)}. | |
| 1317 | * | |
| 1318 | * <p>A {@code null} CharSequence will return {@code false}.</p> | |
| 1319 | * | |
| 1320 | * <pre> | |
| 1321 | * StringUtils.contains(null, *) = false | |
| 1322 | * StringUtils.contains(*, null) = false | |
| 1323 | * StringUtils.contains("", "") = true | |
| 1324 | * StringUtils.contains("abc", "") = true | |
| 1325 | * StringUtils.contains("abc", "a") = true | |
| 1326 | * StringUtils.contains("abc", "z") = false | |
| 1327 | * StringUtils.contains("abc", "A") = true | |
| 1328 | * StringUtils.contains("abc", "Z") = false | |
| 1329 | * </pre> | |
| 1330 | * | |
| 1331 | * @param str the CharSequence to check, may be null | |
| 1332 | * @param searchStr the CharSequence to find, may be null | |
| 1333 | * @return true if the CharSequence contains the search CharSequence irrespective of | |
| 1334 | * case or false if not or {@code null} string input | |
| 1335 | * @since 3.0 Changed signature from containsIgnoreCase(String, String) to containsIgnoreCase(CharSequence, CharSequence) | |
| 1336 | */ | |
| 1337 | public static boolean containsIgnoreCase(final CharSequence str, final CharSequence searchStr) { | |
| 1338 | 40 | if (str == null || searchStr == null) { |
| 1339 | 7 | return false; |
| 1340 | } | |
| 1341 | 33 | final int len = searchStr.length(); |
| 1342 | 33 | final int max = str.length() - len; |
| 1343 | 35 | for (int i = 0; i <= max; i++) { |
| 1344 | 26 | if (CharSequenceUtils.regionMatches(str, true, i, searchStr, 0, len)) { |
| 1345 | 24 | return true; |
| 1346 | } | |
| 1347 | } | |
| 1348 | 9 | return false; |
| 1349 | } | |
| 1350 | ||
| 1351 | /** | |
| 1352 | * Check whether the given CharSequence contains any whitespace characters. | |
| 1353 | * @param seq the CharSequence to check (may be {@code null}) | |
| 1354 | * @return {@code true} if the CharSequence is not empty and | |
| 1355 | * contains at least 1 whitespace character | |
| 1356 | * @see java.lang.Character#isWhitespace | |
| 1357 | * @since 3.0 | |
| 1358 | */ | |
| 1359 | // From org.springframework.util.StringUtils, under Apache License 2.0 | |
| 1360 | public static boolean containsWhitespace(final CharSequence seq) { | |
| 1361 | 7 | if (isEmpty(seq)) { |
| 1362 | 1 | return false; |
| 1363 | } | |
| 1364 | 6 | final int strLen = seq.length(); |
| 1365 | 9 | for (int i = 0; i < strLen; i++) { |
| 1366 | 8 | if (Character.isWhitespace(seq.charAt(i))) { |
| 1367 | 5 | return true; |
| 1368 | } | |
| 1369 | } | |
| 1370 | 1 | return false; |
| 1371 | } | |
| 1372 | ||
| 1373 | // IndexOfAny chars | |
| 1374 | //----------------------------------------------------------------------- | |
| 1375 | /** | |
| 1376 | * <p>Search a CharSequence to find the first index of any | |
| 1377 | * character in the given set of characters.</p> | |
| 1378 | * | |
| 1379 | * <p>A {@code null} String will return {@code -1}. | |
| 1380 | * A {@code null} or zero length search array will return {@code -1}.</p> | |
| 1381 | * | |
| 1382 | * <pre> | |
| 1383 | * StringUtils.indexOfAny(null, *) = -1 | |
| 1384 | * StringUtils.indexOfAny("", *) = -1 | |
| 1385 | * StringUtils.indexOfAny(*, null) = -1 | |
| 1386 | * StringUtils.indexOfAny(*, []) = -1 | |
| 1387 | * StringUtils.indexOfAny("zzabyycdxx",['z','a']) = 0 | |
| 1388 | * StringUtils.indexOfAny("zzabyycdxx",['b','y']) = 3 | |
| 1389 | * StringUtils.indexOfAny("aba", ['z']) = -1 | |
| 1390 | * </pre> | |
| 1391 | * | |
| 1392 | * @param cs the CharSequence to check, may be null | |
| 1393 | * @param searchChars the chars to search for, may be null | |
| 1394 | * @return the index of any of the chars, -1 if no match or null input | |
| 1395 | * @since 2.0 | |
| 1396 | * @since 3.0 Changed signature from indexOfAny(String, char[]) to indexOfAny(CharSequence, char...) | |
| 1397 | */ | |
| 1398 | public static int indexOfAny(final CharSequence cs, final char... searchChars) { | |
| 1399 | 22 | if (isEmpty(cs) || ArrayUtils.isEmpty(searchChars)) { |
| 1400 | 8 | return INDEX_NOT_FOUND; |
| 1401 | } | |
| 1402 | 14 | final int csLen = cs.length(); |
| 1403 | 14 | final int csLast = csLen - 1; |
| 1404 | 14 | final int searchLen = searchChars.length; |
| 1405 | 14 | final int searchLast = searchLen - 1; |
| 1406 | 32 | for (int i = 0; i < csLen; i++) { |
| 1407 | 28 | final char ch = cs.charAt(i); |
| 1408 | 60 | for (int j = 0; j < searchLen; j++) { |
| 1409 | 42 | if (searchChars[j] == ch) { |
| 1410 | 14 | if (i < csLast && j < searchLast && Character.isHighSurrogate(ch)) { |
| 1411 | // ch is a supplementary character | |
| 1412 | 10 | if (searchChars[j + 1] == cs.charAt(i + 1)) { |
| 1413 | 6 | return i; |
| 1414 | } | |
| 1415 | } else { | |
| 1416 | 4 | return i; |
| 1417 | } | |
| 1418 | } | |
| 1419 | } | |
| 1420 | } | |
| 1421 | 4 | return INDEX_NOT_FOUND; |
| 1422 | } | |
| 1423 | ||
| 1424 | /** | |
| 1425 | * <p>Search a CharSequence to find the first index of any | |
| 1426 | * character in the given set of characters.</p> | |
| 1427 | * | |
| 1428 | * <p>A {@code null} String will return {@code -1}. | |
| 1429 | * A {@code null} search string will return {@code -1}.</p> | |
| 1430 | * | |
| 1431 | * <pre> | |
| 1432 | * StringUtils.indexOfAny(null, *) = -1 | |
| 1433 | * StringUtils.indexOfAny("", *) = -1 | |
| 1434 | * StringUtils.indexOfAny(*, null) = -1 | |
| 1435 | * StringUtils.indexOfAny(*, "") = -1 | |
| 1436 | * StringUtils.indexOfAny("zzabyycdxx", "za") = 0 | |
| 1437 | * StringUtils.indexOfAny("zzabyycdxx", "by") = 3 | |
| 1438 | * StringUtils.indexOfAny("aba","z") = -1 | |
| 1439 | * </pre> | |
| 1440 | * | |
| 1441 | * @param cs the CharSequence to check, may be null | |
| 1442 | * @param searchChars the chars to search for, may be null | |
| 1443 | * @return the index of any of the chars, -1 if no match or null input | |
| 1444 | * @since 2.0 | |
| 1445 | * @since 3.0 Changed signature from indexOfAny(String, String) to indexOfAny(CharSequence, String) | |
| 1446 | */ | |
| 1447 | public static int indexOfAny(final CharSequence cs, final String searchChars) { | |
| 1448 | 15 | if (isEmpty(cs) || isEmpty(searchChars)) { |
| 1449 | 8 | return INDEX_NOT_FOUND; |
| 1450 | } | |
| 1451 | 7 | return indexOfAny(cs, searchChars.toCharArray()); |
| 1452 | } | |
| 1453 | ||
| 1454 | // ContainsAny | |
| 1455 | //----------------------------------------------------------------------- | |
| 1456 | /** | |
| 1457 | * <p>Checks if the CharSequence contains any character in the given | |
| 1458 | * set of characters.</p> | |
| 1459 | * | |
| 1460 | * <p>A {@code null} CharSequence will return {@code false}. | |
| 1461 | * A {@code null} or zero length search array will return {@code false}.</p> | |
| 1462 | * | |
| 1463 | * <pre> | |
| 1464 | * StringUtils.containsAny(null, *) = false | |
| 1465 | * StringUtils.containsAny("", *) = false | |
| 1466 | * StringUtils.containsAny(*, null) = false | |
| 1467 | * StringUtils.containsAny(*, []) = false | |
| 1468 | * StringUtils.containsAny("zzabyycdxx",['z','a']) = true | |
| 1469 | * StringUtils.containsAny("zzabyycdxx",['b','y']) = true | |
| 1470 | * StringUtils.containsAny("aba", ['z']) = false | |
| 1471 | * </pre> | |
| 1472 | * | |
| 1473 | * @param cs the CharSequence to check, may be null | |
| 1474 | * @param searchChars the chars to search for, may be null | |
| 1475 | * @return the {@code true} if any of the chars are found, | |
| 1476 | * {@code false} if no match or null input | |
| 1477 | * @since 2.4 | |
| 1478 | * @since 3.0 Changed signature from containsAny(String, char[]) to containsAny(CharSequence, char...) | |
| 1479 | */ | |
| 1480 | public static boolean containsAny(final CharSequence cs, final char... searchChars) { | |
| 1481 | 51 | if (isEmpty(cs) || ArrayUtils.isEmpty(searchChars)) { |
| 1482 | 13 | return false; |
| 1483 | } | |
| 1484 | 38 | final int csLength = cs.length(); |
| 1485 | 38 | final int searchLength = searchChars.length; |
| 1486 | 38 | final int csLast = csLength - 1; |
| 1487 | 38 | final int searchLast = searchLength - 1; |
| 1488 | 119 | for (int i = 0; i < csLength; i++) { |
| 1489 | 104 | final char ch = cs.charAt(i); |
| 1490 | 340 | for (int j = 0; j < searchLength; j++) { |
| 1491 | 259 | if (searchChars[j] == ch) { |
| 1492 | 31 | if (Character.isHighSurrogate(ch)) { |
| 1493 | 16 | if (j == searchLast) { |
| 1494 | // missing low surrogate, fine, like String.indexOf(String) | |
| 1495 | 2 | return true; |
| 1496 | } | |
| 1497 | 14 | if (i < csLast && searchChars[j + 1] == cs.charAt(i + 1)) { |
| 1498 | 6 | return true; |
| 1499 | } | |
| 1500 | } else { | |
| 1501 | // ch is in the Basic Multilingual Plane | |
| 1502 | 15 | return true; |
| 1503 | } | |
| 1504 | } | |
| 1505 | } | |
| 1506 | } | |
| 1507 | 15 | return false; |
| 1508 | } | |
| 1509 | ||
| 1510 | /** | |
| 1511 | * <p> | |
| 1512 | * Checks if the CharSequence contains any character in the given set of characters. | |
| 1513 | * </p> | |
| 1514 | * | |
| 1515 | * <p> | |
| 1516 | * A {@code null} CharSequence will return {@code false}. A {@code null} search CharSequence will return | |
| 1517 | * {@code false}. | |
| 1518 | * </p> | |
| 1519 | * | |
| 1520 | * <pre> | |
| 1521 | * StringUtils.containsAny(null, *) = false | |
| 1522 | * StringUtils.containsAny("", *) = false | |
| 1523 | * StringUtils.containsAny(*, null) = false | |
| 1524 | * StringUtils.containsAny(*, "") = false | |
| 1525 | * StringUtils.containsAny("zzabyycdxx", "za") = true | |
| 1526 | * StringUtils.containsAny("zzabyycdxx", "by") = true | |
| 1527 | * StringUtils.containsAny("aba","z") = false | |
| 1528 | * </pre> | |
| 1529 | * | |
| 1530 | * @param cs | |
| 1531 | * the CharSequence to check, may be null | |
| 1532 | * @param searchChars | |
| 1533 | * the chars to search for, may be null | |
| 1534 | * @return the {@code true} if any of the chars are found, {@code false} if no match or null input | |
| 1535 | * @since 2.4 | |
| 1536 | * @since 3.0 Changed signature from containsAny(String, String) to containsAny(CharSequence, CharSequence) | |
| 1537 | */ | |
| 1538 | public static boolean containsAny(final CharSequence cs, final CharSequence searchChars) { | |
| 1539 | 20 | if (searchChars == null) { |
| 1540 | 3 | return false; |
| 1541 | } | |
| 1542 | 17 | return containsAny(cs, CharSequenceUtils.toCharArray(searchChars)); |
| 1543 | } | |
| 1544 | ||
| 1545 | // IndexOfAnyBut chars | |
| 1546 | //----------------------------------------------------------------------- | |
| 1547 | /** | |
| 1548 | * <p>Searches a CharSequence to find the first index of any | |
| 1549 | * character not in the given set of characters.</p> | |
| 1550 | * | |
| 1551 | * <p>A {@code null} CharSequence will return {@code -1}. | |
| 1552 | * A {@code null} or zero length search array will return {@code -1}.</p> | |
| 1553 | * | |
| 1554 | * <pre> | |
| 1555 | * StringUtils.indexOfAnyBut(null, *) = -1 | |
| 1556 | * StringUtils.indexOfAnyBut("", *) = -1 | |
| 1557 | * StringUtils.indexOfAnyBut(*, null) = -1 | |
| 1558 | * StringUtils.indexOfAnyBut(*, []) = -1 | |
| 1559 | * StringUtils.indexOfAnyBut("zzabyycdxx", new char[] {'z', 'a'} ) = 3 | |
| 1560 | * StringUtils.indexOfAnyBut("aba", new char[] {'z'} ) = 0 | |
| 1561 | * StringUtils.indexOfAnyBut("aba", new char[] {'a', 'b'} ) = -1 | |
| 1562 | ||
| 1563 | * </pre> | |
| 1564 | * | |
| 1565 | * @param cs the CharSequence to check, may be null | |
| 1566 | * @param searchChars the chars to search for, may be null | |
| 1567 | * @return the index of any of the chars, -1 if no match or null input | |
| 1568 | * @since 2.0 | |
| 1569 | * @since 3.0 Changed signature from indexOfAnyBut(String, char[]) to indexOfAnyBut(CharSequence, char...) | |
| 1570 | */ | |
| 1571 | public static int indexOfAnyBut(final CharSequence cs, final char... searchChars) { | |
| 1572 | 37 | if (isEmpty(cs) || ArrayUtils.isEmpty(searchChars)) { |
| 1573 | 8 | return INDEX_NOT_FOUND; |
| 1574 | } | |
| 1575 | 29 | final int csLen = cs.length(); |
| 1576 | 29 | final int csLast = csLen - 1; |
| 1577 | 29 | final int searchLen = searchChars.length; |
| 1578 | 29 | final int searchLast = searchLen - 1; |
| 1579 | outer: | |
| 1580 | 30053 | for (int i = 0; i < csLen; i++) { |
| 1581 | 30038 | final char ch = cs.charAt(i); |
| 1582 | 30065 | for (int j = 0; j < searchLen; j++) { |
| 1583 | 30051 | if (searchChars[j] == ch) { |
| 1584 | 30027 | if (i < csLast && j < searchLast && Character.isHighSurrogate(ch)) { |
| 1585 | 5 | if (searchChars[j + 1] == cs.charAt(i + 1)) { |
| 1586 | 2 | continue outer; |
| 1587 | } | |
| 1588 | } else { | |
| 1589 | continue outer; | |
| 1590 | } | |
| 1591 | } | |
| 1592 | } | |
| 1593 | 14 | return i; |
| 1594 | } | |
| 1595 | 15 | return INDEX_NOT_FOUND; |
| 1596 | } | |
| 1597 | ||
| 1598 | /** | |
| 1599 | * <p>Search a CharSequence to find the first index of any | |
| 1600 | * character not in the given set of characters.</p> | |
| 1601 | * | |
| 1602 | * <p>A {@code null} CharSequence will return {@code -1}. | |
| 1603 | * A {@code null} or empty search string will return {@code -1}.</p> | |
| 1604 | * | |
| 1605 | * <pre> | |
| 1606 | * StringUtils.indexOfAnyBut(null, *) = -1 | |
| 1607 | * StringUtils.indexOfAnyBut("", *) = -1 | |
| 1608 | * StringUtils.indexOfAnyBut(*, null) = -1 | |
| 1609 | * StringUtils.indexOfAnyBut(*, "") = -1 | |
| 1610 | * StringUtils.indexOfAnyBut("zzabyycdxx", "za") = 3 | |
| 1611 | * StringUtils.indexOfAnyBut("zzabyycdxx", "") = -1 | |
| 1612 | * StringUtils.indexOfAnyBut("aba","ab") = -1 | |
| 1613 | * </pre> | |
| 1614 | * | |
| 1615 | * @param seq the CharSequence to check, may be null | |
| 1616 | * @param searchChars the chars to search for, may be null | |
| 1617 | * @return the index of any of the chars, -1 if no match or null input | |
| 1618 | * @since 2.0 | |
| 1619 | * @since 3.0 Changed signature from indexOfAnyBut(String, String) to indexOfAnyBut(CharSequence, CharSequence) | |
| 1620 | */ | |
| 1621 | public static int indexOfAnyBut(final CharSequence seq, final CharSequence searchChars) { | |
| 1622 | 15 | if (isEmpty(seq) || isEmpty(searchChars)) { |
| 1623 | 8 | return INDEX_NOT_FOUND; |
| 1624 | } | |
| 1625 | 7 | final int strLen = seq.length(); |
| 1626 | 14 | for (int i = 0; i < strLen; i++) { |
| 1627 | 13 | final char ch = seq.charAt(i); |
| 1628 | 13 | final boolean chFound = CharSequenceUtils.indexOf(searchChars, ch, 0) >= 0; |
| 1629 | 13 | if (i + 1 < strLen && Character.isHighSurrogate(ch)) { |
| 1630 | 5 | final char ch2 = seq.charAt(i + 1); |
| 1631 | 5 | if (chFound && CharSequenceUtils.indexOf(searchChars, ch2, 0) < 0) { |
| 1632 | 3 | return i; |
| 1633 | } | |
| 1634 | 2 | } else { |
| 1635 | 8 | if (!chFound) { |
| 1636 | 3 | return i; |
| 1637 | } | |
| 1638 | } | |
| 1639 | } | |
| 1640 | 1 | return INDEX_NOT_FOUND; |
| 1641 | } | |
| 1642 | ||
| 1643 | // ContainsOnly | |
| 1644 | //----------------------------------------------------------------------- | |
| 1645 | /** | |
| 1646 | * <p>Checks if the CharSequence contains only certain characters.</p> | |
| 1647 | * | |
| 1648 | * <p>A {@code null} CharSequence will return {@code false}. | |
| 1649 | * A {@code null} valid character array will return {@code false}. | |
| 1650 | * An empty CharSequence (length()=0) always returns {@code true}.</p> | |
| 1651 | * | |
| 1652 | * <pre> | |
| 1653 | * StringUtils.containsOnly(null, *) = false | |
| 1654 | * StringUtils.containsOnly(*, null) = false | |
| 1655 | * StringUtils.containsOnly("", *) = true | |
| 1656 | * StringUtils.containsOnly("ab", '') = false | |
| 1657 | * StringUtils.containsOnly("abab", 'abc') = true | |
| 1658 | * StringUtils.containsOnly("ab1", 'abc') = false | |
| 1659 | * StringUtils.containsOnly("abz", 'abc') = false | |
| 1660 | * </pre> | |
| 1661 | * | |
| 1662 | * @param cs the String to check, may be null | |
| 1663 | * @param valid an array of valid chars, may be null | |
| 1664 | * @return true if it only contains valid chars and is non-null | |
| 1665 | * @since 3.0 Changed signature from containsOnly(String, char[]) to containsOnly(CharSequence, char...) | |
| 1666 | */ | |
| 1667 | public static boolean containsOnly(final CharSequence cs, final char... valid) { | |
| 1668 | // All these pre-checks are to maintain API with an older version | |
| 1669 | 30 | if (valid == null || cs == null) { |
| 1670 | 3 | return false; |
| 1671 | } | |
| 1672 | 27 | if (cs.length() == 0) { |
| 1673 | 4 | return true; |
| 1674 | } | |
| 1675 | 23 | if (valid.length == 0) { |
| 1676 | 2 | return false; |
| 1677 | } | |
| 1678 | 21 | return indexOfAnyBut(cs, valid) == INDEX_NOT_FOUND; |
| 1679 | } | |
| 1680 | ||
| 1681 | /** | |
| 1682 | * <p>Checks if the CharSequence contains only certain characters.</p> | |
| 1683 | * | |
| 1684 | * <p>A {@code null} CharSequence will return {@code false}. | |
| 1685 | * A {@code null} valid character String will return {@code false}. | |
| 1686 | * An empty String (length()=0) always returns {@code true}.</p> | |
| 1687 | * | |
| 1688 | * <pre> | |
| 1689 | * StringUtils.containsOnly(null, *) = false | |
| 1690 | * StringUtils.containsOnly(*, null) = false | |
| 1691 | * StringUtils.containsOnly("", *) = true | |
| 1692 | * StringUtils.containsOnly("ab", "") = false | |
| 1693 | * StringUtils.containsOnly("abab", "abc") = true | |
| 1694 | * StringUtils.containsOnly("ab1", "abc") = false | |
| 1695 | * StringUtils.containsOnly("abz", "abc") = false | |
| 1696 | * </pre> | |
| 1697 | * | |
| 1698 | * @param cs the CharSequence to check, may be null | |
| 1699 | * @param validChars a String of valid chars, may be null | |
| 1700 | * @return true if it only contains valid chars and is non-null | |
| 1701 | * @since 2.0 | |
| 1702 | * @since 3.0 Changed signature from containsOnly(String, String) to containsOnly(CharSequence, String) | |
| 1703 | */ | |
| 1704 | public static boolean containsOnly(final CharSequence cs, final String validChars) { | |
| 1705 | 15 | if (cs == null || validChars == null) { |
| 1706 | 3 | return false; |
| 1707 | } | |
| 1708 | 12 | return containsOnly(cs, validChars.toCharArray()); |
| 1709 | } | |
| 1710 | ||
| 1711 | // ContainsNone | |
| 1712 | //----------------------------------------------------------------------- | |
| 1713 | /** | |
| 1714 | * <p>Checks that the CharSequence does not contain certain characters.</p> | |
| 1715 | * | |
| 1716 | * <p>A {@code null} CharSequence will return {@code true}. | |
| 1717 | * A {@code null} invalid character array will return {@code true}. | |
| 1718 | * An empty CharSequence (length()=0) always returns true.</p> | |
| 1719 | * | |
| 1720 | * <pre> | |
| 1721 | * StringUtils.containsNone(null, *) = true | |
| 1722 | * StringUtils.containsNone(*, null) = true | |
| 1723 | * StringUtils.containsNone("", *) = true | |
| 1724 | * StringUtils.containsNone("ab", '') = true | |
| 1725 | * StringUtils.containsNone("abab", 'xyz') = true | |
| 1726 | * StringUtils.containsNone("ab1", 'xyz') = true | |
| 1727 | * StringUtils.containsNone("abz", 'xyz') = false | |
| 1728 | * </pre> | |
| 1729 | * | |
| 1730 | * @param cs the CharSequence to check, may be null | |
| 1731 | * @param searchChars an array of invalid chars, may be null | |
| 1732 | * @return true if it contains none of the invalid chars, or is null | |
| 1733 | * @since 2.0 | |
| 1734 | * @since 3.0 Changed signature from containsNone(String, char[]) to containsNone(CharSequence, char...) | |
| 1735 | */ | |
| 1736 | public static boolean containsNone(final CharSequence cs, final char... searchChars) { | |
| 1737 | 59 | if (cs == null || searchChars == null) { |
| 1738 | 3 | return true; |
| 1739 | } | |
| 1740 | 56 | final int csLen = cs.length(); |
| 1741 | 56 | final int csLast = csLen - 1; |
| 1742 | 56 | final int searchLen = searchChars.length; |
| 1743 | 56 | final int searchLast = searchLen - 1; |
| 1744 | 146 | for (int i = 0; i < csLen; i++) { |
| 1745 | 112 | final char ch = cs.charAt(i); |
| 1746 | 376 | for (int j = 0; j < searchLen; j++) { |
| 1747 | 286 | if (searchChars[j] == ch) { |
| 1748 | 30 | if (Character.isHighSurrogate(ch)) { |
| 1749 | 16 | if (j == searchLast) { |
| 1750 | // missing low surrogate, fine, like String.indexOf(String) | |
| 1751 | 2 | return false; |
| 1752 | } | |
| 1753 | 14 | if (i < csLast && searchChars[j + 1] == cs.charAt(i + 1)) { |
| 1754 | 6 | return false; |
| 1755 | } | |
| 1756 | } else { | |
| 1757 | // ch is in the Basic Multilingual Plane | |
| 1758 | 14 | return false; |
| 1759 | } | |
| 1760 | } | |
| 1761 | } | |
| 1762 | } | |
| 1763 | 34 | return true; |
| 1764 | } | |
| 1765 | ||
| 1766 | /** | |
| 1767 | * <p>Checks that the CharSequence does not contain certain characters.</p> | |
| 1768 | * | |
| 1769 | * <p>A {@code null} CharSequence will return {@code true}. | |
| 1770 | * A {@code null} invalid character array will return {@code true}. | |
| 1771 | * An empty String ("") always returns true.</p> | |
| 1772 | * | |
| 1773 | * <pre> | |
| 1774 | * StringUtils.containsNone(null, *) = true | |
| 1775 | * StringUtils.containsNone(*, null) = true | |
| 1776 | * StringUtils.containsNone("", *) = true | |
| 1777 | * StringUtils.containsNone("ab", "") = true | |
| 1778 | * StringUtils.containsNone("abab", "xyz") = true | |
| 1779 | * StringUtils.containsNone("ab1", "xyz") = true | |
| 1780 | * StringUtils.containsNone("abz", "xyz") = false | |
| 1781 | * </pre> | |
| 1782 | * | |
| 1783 | * @param cs the CharSequence to check, may be null | |
| 1784 | * @param invalidChars a String of invalid chars, may be null | |
| 1785 | * @return true if it contains none of the invalid chars, or is null | |
| 1786 | * @since 2.0 | |
| 1787 | * @since 3.0 Changed signature from containsNone(String, String) to containsNone(CharSequence, String) | |
| 1788 | */ | |
| 1789 | public static boolean containsNone(final CharSequence cs, final String invalidChars) { | |
| 1790 | 24 | if (cs == null || invalidChars == null) { |
| 1791 | 3 | return true; |
| 1792 | } | |
| 1793 | 21 | return containsNone(cs, invalidChars.toCharArray()); |
| 1794 | } | |
| 1795 | ||
| 1796 | // IndexOfAny strings | |
| 1797 | //----------------------------------------------------------------------- | |
| 1798 | /** | |
| 1799 | * <p>Find the first index of any of a set of potential substrings.</p> | |
| 1800 | * | |
| 1801 | * <p>A {@code null} CharSequence will return {@code -1}. | |
| 1802 | * A {@code null} or zero length search array will return {@code -1}. | |
| 1803 | * A {@code null} search array entry will be ignored, but a search | |
| 1804 | * array containing "" will return {@code 0} if {@code str} is not | |
| 1805 | * null. This method uses {@link String#indexOf(String)} if possible.</p> | |
| 1806 | * | |
| 1807 | * <pre> | |
| 1808 | * StringUtils.indexOfAny(null, *) = -1 | |
| 1809 | * StringUtils.indexOfAny(*, null) = -1 | |
| 1810 | * StringUtils.indexOfAny(*, []) = -1 | |
| 1811 | * StringUtils.indexOfAny("zzabyycdxx", ["ab","cd"]) = 2 | |
| 1812 | * StringUtils.indexOfAny("zzabyycdxx", ["cd","ab"]) = 2 | |
| 1813 | * StringUtils.indexOfAny("zzabyycdxx", ["mn","op"]) = -1 | |
| 1814 | * StringUtils.indexOfAny("zzabyycdxx", ["zab","aby"]) = 1 | |
| 1815 | * StringUtils.indexOfAny("zzabyycdxx", [""]) = 0 | |
| 1816 | * StringUtils.indexOfAny("", [""]) = 0 | |
| 1817 | * StringUtils.indexOfAny("", ["a"]) = -1 | |
| 1818 | * </pre> | |
| 1819 | * | |
| 1820 | * @param str the CharSequence to check, may be null | |
| 1821 | * @param searchStrs the CharSequences to search for, may be null | |
| 1822 | * @return the first index of any of the searchStrs in str, -1 if no match | |
| 1823 | * @since 3.0 Changed signature from indexOfAny(String, String[]) to indexOfAny(CharSequence, CharSequence...) | |
| 1824 | */ | |
| 1825 | public static int indexOfAny(final CharSequence str, final CharSequence... searchStrs) { | |
| 1826 | 14 | if (str == null || searchStrs == null) { |
| 1827 | 5 | return INDEX_NOT_FOUND; |
| 1828 | } | |
| 1829 | 9 | final int sz = searchStrs.length; |
| 1830 | ||
| 1831 | // String's can't have a MAX_VALUEth index. | |
| 1832 | 9 | int ret = Integer.MAX_VALUE; |
| 1833 | ||
| 1834 | 9 | int tmp = 0; |
| 1835 | 17 | for (int i = 0; i < sz; i++) { |
| 1836 | 8 | final CharSequence search = searchStrs[i]; |
| 1837 | 8 | if (search == null) { |
| 1838 | 2 | continue; |
| 1839 | } | |
| 1840 | 6 | tmp = CharSequenceUtils.indexOf(str, search, 0); |
| 1841 | 6 | if (tmp == INDEX_NOT_FOUND) { |
| 1842 | 2 | continue; |
| 1843 | } | |
| 1844 | ||
| 1845 | 4 | if (tmp < ret) { |
| 1846 | 3 | ret = tmp; |
| 1847 | } | |
| 1848 | } | |
| 1849 | ||
| 1850 | 9 | return ret == Integer.MAX_VALUE ? INDEX_NOT_FOUND : ret; |
| 1851 | } | |
| 1852 | ||
| 1853 | /** | |
| 1854 | * <p>Find the latest index of any of a set of potential substrings.</p> | |
| 1855 | * | |
| 1856 | * <p>A {@code null} CharSequence will return {@code -1}. | |
| 1857 | * A {@code null} search array will return {@code -1}. | |
| 1858 | * A {@code null} or zero length search array entry will be ignored, | |
| 1859 | * but a search array containing "" will return the length of {@code str} | |
| 1860 | * if {@code str} is not null. This method uses {@link String#indexOf(String)} if possible</p> | |
| 1861 | * | |
| 1862 | * <pre> | |
| 1863 | * StringUtils.lastIndexOfAny(null, *) = -1 | |
| 1864 | * StringUtils.lastIndexOfAny(*, null) = -1 | |
| 1865 | * StringUtils.lastIndexOfAny(*, []) = -1 | |
| 1866 | * StringUtils.lastIndexOfAny(*, [null]) = -1 | |
| 1867 | * StringUtils.lastIndexOfAny("zzabyycdxx", ["ab","cd"]) = 6 | |
| 1868 | * StringUtils.lastIndexOfAny("zzabyycdxx", ["cd","ab"]) = 6 | |
| 1869 | * StringUtils.lastIndexOfAny("zzabyycdxx", ["mn","op"]) = -1 | |
| 1870 | * StringUtils.lastIndexOfAny("zzabyycdxx", ["mn","op"]) = -1 | |
| 1871 | * StringUtils.lastIndexOfAny("zzabyycdxx", ["mn",""]) = 10 | |
| 1872 | * </pre> | |
| 1873 | * | |
| 1874 | * @param str the CharSequence to check, may be null | |
| 1875 | * @param searchStrs the CharSequences to search for, may be null | |
| 1876 | * @return the last index of any of the CharSequences, -1 if no match | |
| 1877 | * @since 3.0 Changed signature from lastIndexOfAny(String, String[]) to lastIndexOfAny(CharSequence, CharSequence) | |
| 1878 | */ | |
| 1879 | public static int lastIndexOfAny(final CharSequence str, final CharSequence... searchStrs) { | |
| 1880 | 18 | if (str == null || searchStrs == null) { |
| 1881 | 7 | return INDEX_NOT_FOUND; |
| 1882 | } | |
| 1883 | 11 | final int sz = searchStrs.length; |
| 1884 | 11 | int ret = INDEX_NOT_FOUND; |
| 1885 | 11 | int tmp = 0; |
| 1886 | 20 | for (int i = 0; i < sz; i++) { |
| 1887 | 9 | final CharSequence search = searchStrs[i]; |
| 1888 | 9 | if (search == null) { |
| 1889 | 3 | continue; |
| 1890 | } | |
| 1891 | 6 | tmp = CharSequenceUtils.lastIndexOf(str, search, str.length()); |
| 1892 | 6 | if (tmp > ret) { |
| 1893 | 4 | ret = tmp; |
| 1894 | } | |
| 1895 | } | |
| 1896 | 11 | return ret; |
| 1897 | } | |
| 1898 | ||
| 1899 | // Substring | |
| 1900 | //----------------------------------------------------------------------- | |
| 1901 | /** | |
| 1902 | * <p>Gets a substring from the specified String avoiding exceptions.</p> | |
| 1903 | * | |
| 1904 | * <p>A negative start position can be used to start {@code n} | |
| 1905 | * characters from the end of the String.</p> | |
| 1906 | * | |
| 1907 | * <p>A {@code null} String will return {@code null}. | |
| 1908 | * An empty ("") String will return "".</p> | |
| 1909 | * | |
| 1910 | * <pre> | |
| 1911 | * StringUtils.substring(null, *) = null | |
| 1912 | * StringUtils.substring("", *) = "" | |
| 1913 | * StringUtils.substring("abc", 0) = "abc" | |
| 1914 | * StringUtils.substring("abc", 2) = "c" | |
| 1915 | * StringUtils.substring("abc", 4) = "" | |
| 1916 | * StringUtils.substring("abc", -2) = "bc" | |
| 1917 | * StringUtils.substring("abc", -4) = "abc" | |
| 1918 | * </pre> | |
| 1919 | * | |
| 1920 | * @param str the String to get the substring from, may be null | |
| 1921 | * @param start the position to start from, negative means | |
| 1922 | * count back from the end of the String by this many characters | |
| 1923 | * @return substring from start position, {@code null} if null String input | |
| 1924 | */ | |
| 1925 | public static String substring(final String str, int start) { | |
| 1926 | 16 | if (str == null) { |
| 1927 | 1 | return null; |
| 1928 | } | |
| 1929 | ||
| 1930 | // handle negatives, which means last n characters | |
| 1931 | 15 | if (start < 0) { |
| 1932 | 5 | start = str.length() + start; // remember start is negative |
| 1933 | } | |
| 1934 | ||
| 1935 | 15 | if (start < 0) { |
| 1936 | 1 | start = 0; |
| 1937 | } | |
| 1938 | 15 | if (start > str.length()) { |
| 1939 | 3 | return EMPTY; |
| 1940 | } | |
| 1941 | ||
| 1942 | 12 | return str.substring(start); |
| 1943 | } | |
| 1944 | ||
| 1945 | /** | |
| 1946 | * <p>Gets a substring from the specified String avoiding exceptions.</p> | |
| 1947 | * | |
| 1948 | * <p>A negative start position can be used to start/end {@code n} | |
| 1949 | * characters from the end of the String.</p> | |
| 1950 | * | |
| 1951 | * <p>The returned substring starts with the character in the {@code start} | |
| 1952 | * position and ends before the {@code end} position. All position counting is | |
| 1953 | * zero-based -- i.e., to start at the beginning of the string use | |
| 1954 | * {@code start = 0}. Negative start and end positions can be used to | |
| 1955 | * specify offsets relative to the end of the String.</p> | |
| 1956 | * | |
| 1957 | * <p>If {@code start} is not strictly to the left of {@code end}, "" | |
| 1958 | * is returned.</p> | |
| 1959 | * | |
| 1960 | * <pre> | |
| 1961 | * StringUtils.substring(null, *, *) = null | |
| 1962 | * StringUtils.substring("", * , *) = ""; | |
| 1963 | * StringUtils.substring("abc", 0, 2) = "ab" | |
| 1964 | * StringUtils.substring("abc", 2, 0) = "" | |
| 1965 | * StringUtils.substring("abc", 2, 4) = "c" | |
| 1966 | * StringUtils.substring("abc", 4, 6) = "" | |
| 1967 | * StringUtils.substring("abc", 2, 2) = "" | |
| 1968 | * StringUtils.substring("abc", -2, -1) = "b" | |
| 1969 | * StringUtils.substring("abc", -4, 2) = "ab" | |
| 1970 | * </pre> | |
| 1971 | * | |
| 1972 | * @param str the String to get the substring from, may be null | |
| 1973 | * @param start the position to start from, negative means | |
| 1974 | * count back from the end of the String by this many characters | |
| 1975 | * @param end the position to end at (exclusive), negative means | |
| 1976 | * count back from the end of the String by this many characters | |
| 1977 | * @return substring from start position to end position, | |
| 1978 | * {@code null} if null String input | |
| 1979 | */ | |
| 1980 | public static String substring(final String str, int start, int end) { | |
| 1981 | 13 | if (str == null) { |
| 1982 | 2 | return null; |
| 1983 | } | |
| 1984 | ||
| 1985 | // handle negatives | |
| 1986 | 11 | if (end < 0) { |
| 1987 | 4 | end = str.length() + end; // remember end is negative |
| 1988 | } | |
| 1989 | 11 | if (start < 0) { |
| 1990 | 4 | start = str.length() + start; // remember start is negative |
| 1991 | } | |
| 1992 | ||
| 1993 | // check length next | |
| 1994 | 11 | if (end > str.length()) { |
| 1995 | 2 | end = str.length(); |
| 1996 | } | |
| 1997 | ||
| 1998 | // if start is greater than end, return "" | |
| 1999 | 11 | if (start > end) { |
| 2000 | 2 | return EMPTY; |
| 2001 | } | |
| 2002 | ||
| 2003 | 9 | if (start < 0) { |
| 2004 | 1 | start = 0; |
| 2005 | } | |
| 2006 | 9 | if (end < 0) { |
| 2007 | 1 | end = 0; |
| 2008 | } | |
| 2009 | ||
| 2010 | 9 | return str.substring(start, end); |
| 2011 | } | |
| 2012 | ||
| 2013 | // Left/Right/Mid | |
| 2014 | //----------------------------------------------------------------------- | |
| 2015 | /** | |
| 2016 | * <p>Gets the leftmost {@code len} characters of a String.</p> | |
| 2017 | * | |
| 2018 | * <p>If {@code len} characters are not available, or the | |
| 2019 | * String is {@code null}, the String will be returned without | |
| 2020 | * an exception. An empty String is returned if len is negative.</p> | |
| 2021 | * | |
| 2022 | * <pre> | |
| 2023 | * StringUtils.left(null, *) = null | |
| 2024 | * StringUtils.left(*, -ve) = "" | |
| 2025 | * StringUtils.left("", *) = "" | |
| 2026 | * StringUtils.left("abc", 0) = "" | |
| 2027 | * StringUtils.left("abc", 2) = "ab" | |
| 2028 | * StringUtils.left("abc", 4) = "abc" | |
| 2029 | * </pre> | |
| 2030 | * | |
| 2031 | * @param str the String to get the leftmost characters from, may be null | |
| 2032 | * @param len the length of the required String | |
| 2033 | * @return the leftmost characters, {@code null} if null String input | |
| 2034 | */ | |
| 2035 | public static String left(final String str, final int len) { | |
| 2036 | 10 | if (str == null) { |
| 2037 | 3 | return null; |
| 2038 | } | |
| 2039 | 7 | if (len < 0) { |
| 2040 | 2 | return EMPTY; |
| 2041 | } | |
| 2042 | 5 | if (str.length() <= len) { |
| 2043 | 3 | return str; |
| 2044 | } | |
| 2045 | 2 | return str.substring(0, len); |
| 2046 | } | |
| 2047 | ||
| 2048 | /** | |
| 2049 | * <p>Gets the rightmost {@code len} characters of a String.</p> | |
| 2050 | * | |
| 2051 | * <p>If {@code len} characters are not available, or the String | |
| 2052 | * is {@code null}, the String will be returned without an | |
| 2053 | * an exception. An empty String is returned if len is negative.</p> | |
| 2054 | * | |
| 2055 | * <pre> | |
| 2056 | * StringUtils.right(null, *) = null | |
| 2057 | * StringUtils.right(*, -ve) = "" | |
| 2058 | * StringUtils.right("", *) = "" | |
| 2059 | * StringUtils.right("abc", 0) = "" | |
| 2060 | * StringUtils.right("abc", 2) = "bc" | |
| 2061 | * StringUtils.right("abc", 4) = "abc" | |
| 2062 | * </pre> | |
| 2063 | * | |
| 2064 | * @param str the String to get the rightmost characters from, may be null | |
| 2065 | * @param len the length of the required String | |
| 2066 | * @return the rightmost characters, {@code null} if null String input | |
| 2067 | */ | |
| 2068 | public static String right(final String str, final int len) { | |
| 2069 | 10 | if (str == null) { |
| 2070 | 3 | return null; |
| 2071 | } | |
| 2072 | 7 | if (len < 0) { |
| 2073 | 2 | return EMPTY; |
| 2074 | } | |
| 2075 | 5 | if (str.length() <= len) { |
| 2076 | 3 | return str; |
| 2077 | } | |
| 2078 | 2 | return str.substring(str.length() - len); |
| 2079 | } | |
| 2080 | ||
| 2081 | /** | |
| 2082 | * <p>Gets {@code len} characters from the middle of a String.</p> | |
| 2083 | * | |
| 2084 | * <p>If {@code len} characters are not available, the remainder | |
| 2085 | * of the String will be returned without an exception. If the | |
| 2086 | * String is {@code null}, {@code null} will be returned. | |
| 2087 | * An empty String is returned if len is negative or exceeds the | |
| 2088 | * length of {@code str}.</p> | |
| 2089 | * | |
| 2090 | * <pre> | |
| 2091 | * StringUtils.mid(null, *, *) = null | |
| 2092 | * StringUtils.mid(*, *, -ve) = "" | |
| 2093 | * StringUtils.mid("", 0, *) = "" | |
| 2094 | * StringUtils.mid("abc", 0, 2) = "ab" | |
| 2095 | * StringUtils.mid("abc", 0, 4) = "abc" | |
| 2096 | * StringUtils.mid("abc", 2, 4) = "c" | |
| 2097 | * StringUtils.mid("abc", 4, 2) = "" | |
| 2098 | * StringUtils.mid("abc", -2, 2) = "ab" | |
| 2099 | * </pre> | |
| 2100 | * | |
| 2101 | * @param str the String to get the characters from, may be null | |
| 2102 | * @param pos the position to start from, negative treated as zero | |
| 2103 | * @param len the length of the required String | |
| 2104 | * @return the middle characters, {@code null} if null String input | |
| 2105 | */ | |
| 2106 | public static String mid(final String str, int pos, final int len) { | |
| 2107 | 16 | if (str == null) { |
| 2108 | 4 | return null; |
| 2109 | } | |
| 2110 | 12 | if (len < 0 || pos > str.length()) { |
| 2111 | 3 | return EMPTY; |
| 2112 | } | |
| 2113 | 9 | if (pos < 0) { |
| 2114 | 1 | pos = 0; |
| 2115 | } | |
| 2116 | 9 | if (str.length() <= pos + len) { |
| 2117 | 5 | return str.substring(pos); |
| 2118 | } | |
| 2119 | 4 | return str.substring(pos, pos + len); |
| 2120 | } | |
| 2121 | ||
| 2122 | // SubStringAfter/SubStringBefore | |
| 2123 | //----------------------------------------------------------------------- | |
| 2124 | /** | |
| 2125 | * <p>Gets the substring before the first occurrence of a separator. | |
| 2126 | * The separator is not returned.</p> | |
| 2127 | * | |
| 2128 | * <p>A {@code null} string input will return {@code null}. | |
| 2129 | * An empty ("") string input will return the empty string. | |
| 2130 | * A {@code null} separator will return the input string.</p> | |
| 2131 | * | |
| 2132 | * <p>If nothing is found, the string input is returned.</p> | |
| 2133 | * | |
| 2134 | * <pre> | |
| 2135 | * StringUtils.substringBefore(null, *) = null | |
| 2136 | * StringUtils.substringBefore("", *) = "" | |
| 2137 | * StringUtils.substringBefore("abc", "a") = "" | |
| 2138 | * StringUtils.substringBefore("abcba", "b") = "a" | |
| 2139 | * StringUtils.substringBefore("abc", "c") = "ab" | |
| 2140 | * StringUtils.substringBefore("abc", "d") = "abc" | |
| 2141 | * StringUtils.substringBefore("abc", "") = "" | |
| 2142 | * StringUtils.substringBefore("abc", null) = "abc" | |
| 2143 | * </pre> | |
| 2144 | * | |
| 2145 | * @param str the String to get a substring from, may be null | |
| 2146 | * @param separator the String to search for, may be null | |
| 2147 | * @return the substring before the first occurrence of the separator, | |
| 2148 | * {@code null} if null String input | |
| 2149 | * @since 2.0 | |
| 2150 | */ | |
| 2151 | public static String substringBefore(final String str, final String separator) { | |
| 2152 | 14 | if (isEmpty(str) || separator == null) { |
| 2153 | 7 | return str; |
| 2154 | } | |
| 2155 | 7 | if (separator.length() == 0) { |
| 2156 | 1 | return EMPTY; |
| 2157 | } | |
| 2158 | 6 | final int pos = str.indexOf(separator); |
| 2159 | 6 | if (pos == INDEX_NOT_FOUND) { |
| 2160 | 1 | return str; |
| 2161 | } | |
| 2162 | 5 | return str.substring(0, pos); |
| 2163 | } | |
| 2164 | ||
| 2165 | /** | |
| 2166 | * <p>Gets the substring after the first occurrence of a separator. | |
| 2167 | * The separator is not returned.</p> | |
| 2168 | * | |
| 2169 | * <p>A {@code null} string input will return {@code null}. | |
| 2170 | * An empty ("") string input will return the empty string. | |
| 2171 | * A {@code null} separator will return the empty string if the | |
| 2172 | * input string is not {@code null}.</p> | |
| 2173 | * | |
| 2174 | * <p>If nothing is found, the empty string is returned.</p> | |
| 2175 | * | |
| 2176 | * <pre> | |
| 2177 | * StringUtils.substringAfter(null, *) = null | |
| 2178 | * StringUtils.substringAfter("", *) = "" | |
| 2179 | * StringUtils.substringAfter(*, null) = "" | |
| 2180 | * StringUtils.substringAfter("abc", "a") = "bc" | |
| 2181 | * StringUtils.substringAfter("abcba", "b") = "cba" | |
| 2182 | * StringUtils.substringAfter("abc", "c") = "" | |
| 2183 | * StringUtils.substringAfter("abc", "d") = "" | |
| 2184 | * StringUtils.substringAfter("abc", "") = "abc" | |
| 2185 | * </pre> | |
| 2186 | * | |
| 2187 | * @param str the String to get a substring from, may be null | |
| 2188 | * @param separator the String to search for, may be null | |
| 2189 | * @return the substring after the first occurrence of the separator, | |
| 2190 | * {@code null} if null String input | |
| 2191 | * @since 2.0 | |
| 2192 | */ | |
| 2193 | public static String substringAfter(final String str, final String separator) { | |
| 2194 | 14 | if (isEmpty(str)) { |
| 2195 | 6 | return str; |
| 2196 | } | |
| 2197 | 8 | if (separator == null) { |
| 2198 | 1 | return EMPTY; |
| 2199 | } | |
| 2200 | 7 | final int pos = str.indexOf(separator); |
| 2201 | 7 | if (pos == INDEX_NOT_FOUND) { |
| 2202 | 1 | return EMPTY; |
| 2203 | } | |
| 2204 | 6 | return str.substring(pos + separator.length()); |
| 2205 | } | |
| 2206 | ||
| 2207 | /** | |
| 2208 | * <p>Gets the substring before the last occurrence of a separator. | |
| 2209 | * The separator is not returned.</p> | |
| 2210 | * | |
| 2211 | * <p>A {@code null} string input will return {@code null}. | |
| 2212 | * An empty ("") string input will return the empty string. | |
| 2213 | * An empty or {@code null} separator will return the input string.</p> | |
| 2214 | * | |
| 2215 | * <p>If nothing is found, the string input is returned.</p> | |
| 2216 | * | |
| 2217 | * <pre> | |
| 2218 | * StringUtils.substringBeforeLast(null, *) = null | |
| 2219 | * StringUtils.substringBeforeLast("", *) = "" | |
| 2220 | * StringUtils.substringBeforeLast("abcba", "b") = "abc" | |
| 2221 | * StringUtils.substringBeforeLast("abc", "c") = "ab" | |
| 2222 | * StringUtils.substringBeforeLast("a", "a") = "" | |
| 2223 | * StringUtils.substringBeforeLast("a", "z") = "a" | |
| 2224 | * StringUtils.substringBeforeLast("a", null) = "a" | |
| 2225 | * StringUtils.substringBeforeLast("a", "") = "a" | |
| 2226 | * </pre> | |
| 2227 | * | |
| 2228 | * @param str the String to get a substring from, may be null | |
| 2229 | * @param separator the String to search for, may be null | |
| 2230 | * @return the substring before the last occurrence of the separator, | |
| 2231 | * {@code null} if null String input | |
| 2232 | * @since 2.0 | |
| 2233 | */ | |
| 2234 | public static String substringBeforeLast(final String str, final String separator) { | |
| 2235 | 18 | if (isEmpty(str) || isEmpty(separator)) { |
| 2236 | 9 | return str; |
| 2237 | } | |
| 2238 | 9 | final int pos = str.lastIndexOf(separator); |
| 2239 | 9 | if (pos == INDEX_NOT_FOUND) { |
| 2240 | 2 | return str; |
| 2241 | } | |
| 2242 | 7 | return str.substring(0, pos); |
| 2243 | } | |
| 2244 | ||
| 2245 | /** | |
| 2246 | * <p>Gets the substring after the last occurrence of a separator. | |
| 2247 | * The separator is not returned.</p> | |
| 2248 | * | |
| 2249 | * <p>A {@code null} string input will return {@code null}. | |
| 2250 | * An empty ("") string input will return the empty string. | |
| 2251 | * An empty or {@code null} separator will return the empty string if | |
| 2252 | * the input string is not {@code null}.</p> | |
| 2253 | * | |
| 2254 | * <p>If nothing is found, the empty string is returned.</p> | |
| 2255 | * | |
| 2256 | * <pre> | |
| 2257 | * StringUtils.substringAfterLast(null, *) = null | |
| 2258 | * StringUtils.substringAfterLast("", *) = "" | |
| 2259 | * StringUtils.substringAfterLast(*, "") = "" | |
| 2260 | * StringUtils.substringAfterLast(*, null) = "" | |
| 2261 | * StringUtils.substringAfterLast("abc", "a") = "bc" | |
| 2262 | * StringUtils.substringAfterLast("abcba", "b") = "a" | |
| 2263 | * StringUtils.substringAfterLast("abc", "c") = "" | |
| 2264 | * StringUtils.substringAfterLast("a", "a") = "" | |
| 2265 | * StringUtils.substringAfterLast("a", "z") = "" | |
| 2266 | * </pre> | |
| 2267 | * | |
| 2268 | * @param str the String to get a substring from, may be null | |
| 2269 | * @param separator the String to search for, may be null | |
| 2270 | * @return the substring after the last occurrence of the separator, | |
| 2271 | * {@code null} if null String input | |
| 2272 | * @since 2.0 | |
| 2273 | */ | |
| 2274 | public static String substringAfterLast(final String str, final String separator) { | |
| 2275 | 15 | if (isEmpty(str)) { |
| 2276 | 7 | return str; |
| 2277 | } | |
| 2278 | 8 | if (isEmpty(separator)) { |
| 2279 | 2 | return EMPTY; |
| 2280 | } | |
| 2281 | 6 | final int pos = str.lastIndexOf(separator); |
| 2282 | 6 | if (pos == INDEX_NOT_FOUND || pos == str.length() - separator.length()) { |
| 2283 | 2 | return EMPTY; |
| 2284 | } | |
| 2285 | 4 | return str.substring(pos + separator.length()); |
| 2286 | } | |
| 2287 | ||
| 2288 | // Substring between | |
| 2289 | //----------------------------------------------------------------------- | |
| 2290 | /** | |
| 2291 | * <p>Gets the String that is nested in between two instances of the | |
| 2292 | * same String.</p> | |
| 2293 | * | |
| 2294 | * <p>A {@code null} input String returns {@code null}. | |
| 2295 | * A {@code null} tag returns {@code null}.</p> | |
| 2296 | * | |
| 2297 | * <pre> | |
| 2298 | * StringUtils.substringBetween(null, *) = null | |
| 2299 | * StringUtils.substringBetween("", "") = "" | |
| 2300 | * StringUtils.substringBetween("", "tag") = null | |
| 2301 | * StringUtils.substringBetween("tagabctag", null) = null | |
| 2302 | * StringUtils.substringBetween("tagabctag", "") = "" | |
| 2303 | * StringUtils.substringBetween("tagabctag", "tag") = "abc" | |
| 2304 | * </pre> | |
| 2305 | * | |
| 2306 | * @param str the String containing the substring, may be null | |
| 2307 | * @param tag the String before and after the substring, may be null | |
| 2308 | * @return the substring, {@code null} if no match | |
| 2309 | * @since 2.0 | |
| 2310 | */ | |
| 2311 | public static String substringBetween(final String str, final String tag) { | |
| 2312 | 10 | return substringBetween(str, tag, tag); |
| 2313 | } | |
| 2314 | ||
| 2315 | /** | |
| 2316 | * <p>Gets the String that is nested in between two Strings. | |
| 2317 | * Only the first match is returned.</p> | |
| 2318 | * | |
| 2319 | * <p>A {@code null} input String returns {@code null}. | |
| 2320 | * A {@code null} open/close returns {@code null} (no match). | |
| 2321 | * An empty ("") open and close returns an empty string.</p> | |
| 2322 | * | |
| 2323 | * <pre> | |
| 2324 | * StringUtils.substringBetween("wx[b]yz", "[", "]") = "b" | |
| 2325 | * StringUtils.substringBetween(null, *, *) = null | |
| 2326 | * StringUtils.substringBetween(*, null, *) = null | |
| 2327 | * StringUtils.substringBetween(*, *, null) = null | |
| 2328 | * StringUtils.substringBetween("", "", "") = "" | |
| 2329 | * StringUtils.substringBetween("", "", "]") = null | |
| 2330 | * StringUtils.substringBetween("", "[", "]") = null | |
| 2331 | * StringUtils.substringBetween("yabcz", "", "") = "" | |
| 2332 | * StringUtils.substringBetween("yabcz", "y", "z") = "abc" | |
| 2333 | * StringUtils.substringBetween("yabczyabcz", "y", "z") = "abc" | |
| 2334 | * </pre> | |
| 2335 | * | |
| 2336 | * @param str the String containing the substring, may be null | |
| 2337 | * @param open the String before the substring, may be null | |
| 2338 | * @param close the String after the substring, may be null | |
| 2339 | * @return the substring, {@code null} if no match | |
| 2340 | * @since 2.0 | |
| 2341 | */ | |
| 2342 | public static String substringBetween(final String str, final String open, final String close) { | |
| 2343 | 19 | if (str == null || open == null || close == null) { |
| 2344 | 5 | return null; |
| 2345 | } | |
| 2346 | 14 | final int start = str.indexOf(open); |
| 2347 | 14 | if (start != INDEX_NOT_FOUND) { |
| 2348 | 12 | final int end = str.indexOf(close, start + open.length()); |
| 2349 | 12 | if (end != INDEX_NOT_FOUND) { |
| 2350 | 10 | return str.substring(start + open.length(), end); |
| 2351 | } | |
| 2352 | } | |
| 2353 | 4 | return null; |
| 2354 | } | |
| 2355 | ||
| 2356 | /** | |
| 2357 | * <p>Searches a String for substrings delimited by a start and end tag, | |
| 2358 | * returning all matching substrings in an array.</p> | |
| 2359 | * | |
| 2360 | * <p>A {@code null} input String returns {@code null}. | |
| 2361 | * A {@code null} open/close returns {@code null} (no match). | |
| 2362 | * An empty ("") open/close returns {@code null} (no match).</p> | |
| 2363 | * | |
| 2364 | * <pre> | |
| 2365 | * StringUtils.substringsBetween("[a][b][c]", "[", "]") = ["a","b","c"] | |
| 2366 | * StringUtils.substringsBetween(null, *, *) = null | |
| 2367 | * StringUtils.substringsBetween(*, null, *) = null | |
| 2368 | * StringUtils.substringsBetween(*, *, null) = null | |
| 2369 | * StringUtils.substringsBetween("", "[", "]") = [] | |
| 2370 | * </pre> | |
| 2371 | * | |
| 2372 | * @param str the String containing the substrings, null returns null, empty returns empty | |
| 2373 | * @param open the String identifying the start of the substring, empty returns null | |
| 2374 | * @param close the String identifying the end of the substring, empty returns null | |
| 2375 | * @return a String Array of substrings, or {@code null} if no match | |
| 2376 | * @since 2.3 | |
| 2377 | */ | |
| 2378 | public static String[] substringsBetween(final String str, final String open, final String close) { | |
| 2379 | 14 | if (str == null || isEmpty(open) || isEmpty(close)) { |
| 2380 | 4 | return null; |
| 2381 | } | |
| 2382 | 10 | final int strLen = str.length(); |
| 2383 | 10 | if (strLen == 0) { |
| 2384 | 1 | return ArrayUtils.EMPTY_STRING_ARRAY; |
| 2385 | } | |
| 2386 | 9 | final int closeLen = close.length(); |
| 2387 | 9 | final int openLen = open.length(); |
| 2388 | 9 | final List<String> list = new ArrayList<String>(); |
| 2389 | 9 | int pos = 0; |
| 2390 | 19 | while (pos < strLen - closeLen) { |
| 2391 | 17 | int start = str.indexOf(open, pos); |
| 2392 | 17 | if (start < 0) { |
| 2393 | 6 | break; |
| 2394 | } | |
| 2395 | 11 | start += openLen; |
| 2396 | 11 | final int end = str.indexOf(close, start); |
| 2397 | 11 | if (end < 0) { |
| 2398 | 1 | break; |
| 2399 | } | |
| 2400 | 10 | list.add(str.substring(start, end)); |
| 2401 | 10 | pos = end + closeLen; |
| 2402 | 10 | } |
| 2403 | 9 | if (list.isEmpty()) { |
| 2404 | 3 | return null; |
| 2405 | } | |
| 2406 | 6 | return list.toArray(new String [list.size()]); |
| 2407 | } | |
| 2408 | ||
| 2409 | // Nested extraction | |
| 2410 | //----------------------------------------------------------------------- | |
| 2411 | ||
| 2412 | // Splitting | |
| 2413 | //----------------------------------------------------------------------- | |
| 2414 | /** | |
| 2415 | * <p>Splits the provided text into an array, using whitespace as the | |
| 2416 | * separator. | |
| 2417 | * Whitespace is defined by {@link Character#isWhitespace(char)}.</p> | |
| 2418 | * | |
| 2419 | * <p>The separator is not included in the returned String array. | |
| 2420 | * Adjacent separators are treated as one separator. | |
| 2421 | * For more control over the split use the StrTokenizer class.</p> | |
| 2422 | * | |
| 2423 | * <p>A {@code null} input String returns {@code null}.</p> | |
| 2424 | * | |
| 2425 | * <pre> | |
| 2426 | * StringUtils.split(null) = null | |
| 2427 | * StringUtils.split("") = [] | |
| 2428 | * StringUtils.split("abc def") = ["abc", "def"] | |
| 2429 | * StringUtils.split("abc def") = ["abc", "def"] | |
| 2430 | * StringUtils.split(" abc ") = ["abc"] | |
| 2431 | * </pre> | |
| 2432 | * | |
| 2433 | * @param str the String to parse, may be null | |
| 2434 | * @return an array of parsed Strings, {@code null} if null String input | |
| 2435 | */ | |
| 2436 | public static String[] split(final String str) { | |
| 2437 | 5 | return split(str, null, -1); |
| 2438 | } | |
| 2439 | ||
| 2440 | /** | |
| 2441 | * <p>Splits the provided text into an array, separator specified. | |
| 2442 | * This is an alternative to using StringTokenizer.</p> | |
| 2443 | * | |
| 2444 | * <p>The separator is not included in the returned String array. | |
| 2445 | * Adjacent separators are treated as one separator. | |
| 2446 | * For more control over the split use the StrTokenizer class.</p> | |
| 2447 | * | |
| 2448 | * <p>A {@code null} input String returns {@code null}.</p> | |
| 2449 | * | |
| 2450 | * <pre> | |
| 2451 | * StringUtils.split(null, *) = null | |
| 2452 | * StringUtils.split("", *) = [] | |
| 2453 | * StringUtils.split("a.b.c", '.') = ["a", "b", "c"] | |
| 2454 | * StringUtils.split("a..b.c", '.') = ["a", "b", "c"] | |
| 2455 | * StringUtils.split("a:b:c", '.') = ["a:b:c"] | |
| 2456 | * StringUtils.split("a b c", ' ') = ["a", "b", "c"] | |
| 2457 | * </pre> | |
| 2458 | * | |
| 2459 | * @param str the String to parse, may be null | |
| 2460 | * @param separatorChar the character used as the delimiter | |
| 2461 | * @return an array of parsed Strings, {@code null} if null String input | |
| 2462 | * @since 2.0 | |
| 2463 | */ | |
| 2464 | public static String[] split(final String str, final char separatorChar) { | |
| 2465 | 9 | return splitWorker(str, separatorChar, false); |
| 2466 | } | |
| 2467 | ||
| 2468 | /** | |
| 2469 | * <p>Splits the provided text into an array, separators specified. | |
| 2470 | * This is an alternative to using StringTokenizer.</p> | |
| 2471 | * | |
| 2472 | * <p>The separator is not included in the returned String array. | |
| 2473 | * Adjacent separators are treated as one separator. | |
| 2474 | * For more control over the split use the StrTokenizer class.</p> | |
| 2475 | * | |
| 2476 | * <p>A {@code null} input String returns {@code null}. | |
| 2477 | * A {@code null} separatorChars splits on whitespace.</p> | |
| 2478 | * | |
| 2479 | * <pre> | |
| 2480 | * StringUtils.split(null, *) = null | |
| 2481 | * StringUtils.split("", *) = [] | |
| 2482 | * StringUtils.split("abc def", null) = ["abc", "def"] | |
| 2483 | * StringUtils.split("abc def", " ") = ["abc", "def"] | |
| 2484 | * StringUtils.split("abc def", " ") = ["abc", "def"] | |
| 2485 | * StringUtils.split("ab:cd:ef", ":") = ["ab", "cd", "ef"] | |
| 2486 | * </pre> | |
| 2487 | * | |
| 2488 | * @param str the String to parse, may be null | |
| 2489 | * @param separatorChars the characters used as the delimiters, | |
| 2490 | * {@code null} splits on whitespace | |
| 2491 | * @return an array of parsed Strings, {@code null} if null String input | |
| 2492 | */ | |
| 2493 | public static String[] split(final String str, final String separatorChars) { | |
| 2494 | 3128 | return splitWorker(str, separatorChars, -1, false); |
| 2495 | } | |
| 2496 | ||
| 2497 | /** | |
| 2498 | * <p>Splits the provided text into an array with a maximum length, | |
| 2499 | * separators specified.</p> | |
| 2500 | * | |
| 2501 | * <p>The separator is not included in the returned String array. | |
| 2502 | * Adjacent separators are treated as one separator.</p> | |
| 2503 | * | |
| 2504 | * <p>A {@code null} input String returns {@code null}. | |
| 2505 | * A {@code null} separatorChars splits on whitespace.</p> | |
| 2506 | * | |
| 2507 | * <p>If more than {@code max} delimited substrings are found, the last | |
| 2508 | * returned string includes all characters after the first {@code max - 1} | |
| 2509 | * returned strings (including separator characters).</p> | |
| 2510 | * | |
| 2511 | * <pre> | |
| 2512 | * StringUtils.split(null, *, *) = null | |
| 2513 | * StringUtils.split("", *, *) = [] | |
| 2514 | * StringUtils.split("ab cd ef", null, 0) = ["ab", "cd", "ef"] | |
| 2515 | * StringUtils.split("ab cd ef", null, 0) = ["ab", "cd", "ef"] | |
| 2516 | * StringUtils.split("ab:cd:ef", ":", 0) = ["ab", "cd", "ef"] | |
| 2517 | * StringUtils.split("ab:cd:ef", ":", 2) = ["ab", "cd:ef"] | |
| 2518 | * </pre> | |
| 2519 | * | |
| 2520 | * @param str the String to parse, may be null | |
| 2521 | * @param separatorChars the characters used as the delimiters, | |
| 2522 | * {@code null} splits on whitespace | |
| 2523 | * @param max the maximum number of elements to include in the | |
| 2524 | * array. A zero or negative value implies no limit | |
| 2525 | * @return an array of parsed Strings, {@code null} if null String input | |
| 2526 | */ | |
| 2527 | public static String[] split(final String str, final String separatorChars, final int max) { | |
| 2528 | 6261 | return splitWorker(str, separatorChars, max, false); |
| 2529 | } | |
| 2530 | ||
| 2531 | /** | |
| 2532 | * <p>Splits the provided text into an array, separator string specified.</p> | |
| 2533 | * | |
| 2534 | * <p>The separator(s) will not be included in the returned String array. | |
| 2535 | * Adjacent separators are treated as one separator.</p> | |
| 2536 | * | |
| 2537 | * <p>A {@code null} input String returns {@code null}. | |
| 2538 | * A {@code null} separator splits on whitespace.</p> | |
| 2539 | * | |
| 2540 | * <pre> | |
| 2541 | * StringUtils.splitByWholeSeparator(null, *) = null | |
| 2542 | * StringUtils.splitByWholeSeparator("", *) = [] | |
| 2543 | * StringUtils.splitByWholeSeparator("ab de fg", null) = ["ab", "de", "fg"] | |
| 2544 | * StringUtils.splitByWholeSeparator("ab de fg", null) = ["ab", "de", "fg"] | |
| 2545 | * StringUtils.splitByWholeSeparator("ab:cd:ef", ":") = ["ab", "cd", "ef"] | |
| 2546 | * StringUtils.splitByWholeSeparator("ab-!-cd-!-ef", "-!-") = ["ab", "cd", "ef"] | |
| 2547 | * </pre> | |
| 2548 | * | |
| 2549 | * @param str the String to parse, may be null | |
| 2550 | * @param separator String containing the String to be used as a delimiter, | |
| 2551 | * {@code null} splits on whitespace | |
| 2552 | * @return an array of parsed Strings, {@code null} if null String was input | |
| 2553 | */ | |
| 2554 | public static String[] splitByWholeSeparator(final String str, final String separator) { | |
| 2555 | 5 | return splitByWholeSeparatorWorker( str, separator, -1, false ) ; |
| 2556 | } | |
| 2557 | ||
| 2558 | /** | |
| 2559 | * <p>Splits the provided text into an array, separator string specified. | |
| 2560 | * Returns a maximum of {@code max} substrings.</p> | |
| 2561 | * | |
| 2562 | * <p>The separator(s) will not be included in the returned String array. | |
| 2563 | * Adjacent separators are treated as one separator.</p> | |
| 2564 | * | |
| 2565 | * <p>A {@code null} input String returns {@code null}. | |
| 2566 | * A {@code null} separator splits on whitespace.</p> | |
| 2567 | * | |
| 2568 | * <pre> | |
| 2569 | * StringUtils.splitByWholeSeparator(null, *, *) = null | |
| 2570 | * StringUtils.splitByWholeSeparator("", *, *) = [] | |
| 2571 | * StringUtils.splitByWholeSeparator("ab de fg", null, 0) = ["ab", "de", "fg"] | |
| 2572 | * StringUtils.splitByWholeSeparator("ab de fg", null, 0) = ["ab", "de", "fg"] | |
| 2573 | * StringUtils.splitByWholeSeparator("ab:cd:ef", ":", 2) = ["ab", "cd:ef"] | |
| 2574 | * StringUtils.splitByWholeSeparator("ab-!-cd-!-ef", "-!-", 5) = ["ab", "cd", "ef"] | |
| 2575 | * StringUtils.splitByWholeSeparator("ab-!-cd-!-ef", "-!-", 2) = ["ab", "cd-!-ef"] | |
| 2576 | * </pre> | |
| 2577 | * | |
| 2578 | * @param str the String to parse, may be null | |
| 2579 | * @param separator String containing the String to be used as a delimiter, | |
| 2580 | * {@code null} splits on whitespace | |
| 2581 | * @param max the maximum number of elements to include in the returned | |
| 2582 | * array. A zero or negative value implies no limit. | |
| 2583 | * @return an array of parsed Strings, {@code null} if null String was input | |
| 2584 | */ | |
| 2585 | public static String[] splitByWholeSeparator( final String str, final String separator, final int max ) { | |
| 2586 | 4 | return splitByWholeSeparatorWorker(str, separator, max, false); |
| 2587 | } | |
| 2588 | ||
| 2589 | /** | |
| 2590 | * <p>Splits the provided text into an array, separator string specified. </p> | |
| 2591 | * | |
| 2592 | * <p>The separator is not included in the returned String array. | |
| 2593 | * Adjacent separators are treated as separators for empty tokens. | |
| 2594 | * For more control over the split use the StrTokenizer class.</p> | |
| 2595 | * | |
| 2596 | * <p>A {@code null} input String returns {@code null}. | |
| 2597 | * A {@code null} separator splits on whitespace.</p> | |
| 2598 | * | |
| 2599 | * <pre> | |
| 2600 | * StringUtils.splitByWholeSeparatorPreserveAllTokens(null, *) = null | |
| 2601 | * StringUtils.splitByWholeSeparatorPreserveAllTokens("", *) = [] | |
| 2602 | * StringUtils.splitByWholeSeparatorPreserveAllTokens("ab de fg", null) = ["ab", "de", "fg"] | |
| 2603 | * StringUtils.splitByWholeSeparatorPreserveAllTokens("ab de fg", null) = ["ab", "", "", "de", "fg"] | |
| 2604 | * StringUtils.splitByWholeSeparatorPreserveAllTokens("ab:cd:ef", ":") = ["ab", "cd", "ef"] | |
| 2605 | * StringUtils.splitByWholeSeparatorPreserveAllTokens("ab-!-cd-!-ef", "-!-") = ["ab", "cd", "ef"] | |
| 2606 | * </pre> | |
| 2607 | * | |
| 2608 | * @param str the String to parse, may be null | |
| 2609 | * @param separator String containing the String to be used as a delimiter, | |
| 2610 | * {@code null} splits on whitespace | |
| 2611 | * @return an array of parsed Strings, {@code null} if null String was input | |
| 2612 | * @since 2.4 | |
| 2613 | */ | |
| 2614 | public static String[] splitByWholeSeparatorPreserveAllTokens(final String str, final String separator) { | |
| 2615 | 0 | return splitByWholeSeparatorWorker(str, separator, -1, true); |
| 2616 | } | |
| 2617 | ||
| 2618 | /** | |
| 2619 | * <p>Splits the provided text into an array, separator string specified. | |
| 2620 | * Returns a maximum of {@code max} substrings.</p> | |
| 2621 | * | |
| 2622 | * <p>The separator is not included in the returned String array. | |
| 2623 | * Adjacent separators are treated as separators for empty tokens. | |
| 2624 | * For more control over the split use the StrTokenizer class.</p> | |
| 2625 | * | |
| 2626 | * <p>A {@code null} input String returns {@code null}. | |
| 2627 | * A {@code null} separator splits on whitespace.</p> | |
| 2628 | * | |
| 2629 | * <pre> | |
| 2630 | * StringUtils.splitByWholeSeparatorPreserveAllTokens(null, *, *) = null | |
| 2631 | * StringUtils.splitByWholeSeparatorPreserveAllTokens("", *, *) = [] | |
| 2632 | * StringUtils.splitByWholeSeparatorPreserveAllTokens("ab de fg", null, 0) = ["ab", "de", "fg"] | |
| 2633 | * StringUtils.splitByWholeSeparatorPreserveAllTokens("ab de fg", null, 0) = ["ab", "", "", "de", "fg"] | |
| 2634 | * StringUtils.splitByWholeSeparatorPreserveAllTokens("ab:cd:ef", ":", 2) = ["ab", "cd:ef"] | |
| 2635 | * StringUtils.splitByWholeSeparatorPreserveAllTokens("ab-!-cd-!-ef", "-!-", 5) = ["ab", "cd", "ef"] | |
| 2636 | * StringUtils.splitByWholeSeparatorPreserveAllTokens("ab-!-cd-!-ef", "-!-", 2) = ["ab", "cd-!-ef"] | |
| 2637 | * </pre> | |
| 2638 | * | |
| 2639 | * @param str the String to parse, may be null | |
| 2640 | * @param separator String containing the String to be used as a delimiter, | |
| 2641 | * {@code null} splits on whitespace | |
| 2642 | * @param max the maximum number of elements to include in the returned | |
| 2643 | * array. A zero or negative value implies no limit. | |
| 2644 | * @return an array of parsed Strings, {@code null} if null String was input | |
| 2645 | * @since 2.4 | |
| 2646 | */ | |
| 2647 | public static String[] splitByWholeSeparatorPreserveAllTokens(final String str, final String separator, final int max) { | |
| 2648 | 6 | return splitByWholeSeparatorWorker(str, separator, max, true); |
| 2649 | } | |
| 2650 | ||
| 2651 | /** | |
| 2652 | * Performs the logic for the {@code splitByWholeSeparatorPreserveAllTokens} methods. | |
| 2653 | * | |
| 2654 | * @param str the String to parse, may be {@code null} | |
| 2655 | * @param separator String containing the String to be used as a delimiter, | |
| 2656 | * {@code null} splits on whitespace | |
| 2657 | * @param max the maximum number of elements to include in the returned | |
| 2658 | * array. A zero or negative value implies no limit. | |
| 2659 | * @param preserveAllTokens if {@code true}, adjacent separators are | |
| 2660 | * treated as empty token separators; if {@code false}, adjacent | |
| 2661 | * separators are treated as one separator. | |
| 2662 | * @return an array of parsed Strings, {@code null} if null String input | |
| 2663 | * @since 2.4 | |
| 2664 | */ | |
| 2665 | private static String[] splitByWholeSeparatorWorker( | |
| 2666 | final String str, final String separator, final int max, final boolean preserveAllTokens) { | |
| 2667 | 15 | if (str == null) { |
| 2668 | 3 | return null; |
| 2669 | } | |
| 2670 | ||
| 2671 | 12 | final int len = str.length(); |
| 2672 | ||
| 2673 | 12 | if (len == 0) { |
| 2674 | 3 | return ArrayUtils.EMPTY_STRING_ARRAY; |
| 2675 | } | |
| 2676 | ||
| 2677 | 9 | if (separator == null || EMPTY.equals(separator)) { |
| 2678 | // Split on whitespace. | |
| 2679 | 3 | return splitWorker(str, null, max, preserveAllTokens); |
| 2680 | } | |
| 2681 | ||
| 2682 | 6 | final int separatorLength = separator.length(); |
| 2683 | ||
| 2684 | 6 | final ArrayList<String> substrings = new ArrayList<String>(); |
| 2685 | 6 | int numberOfSubstrings = 0; |
| 2686 | 6 | int beg = 0; |
| 2687 | 6 | int end = 0; |
| 2688 | 33 | while (end < len) { |
| 2689 | 27 | end = str.indexOf(separator, beg); |
| 2690 | ||
| 2691 | 27 | if (end > -1) { |
| 2692 | 23 | if (end > beg) { |
| 2693 | 13 | numberOfSubstrings += 1; |
| 2694 | ||
| 2695 | 13 | if (numberOfSubstrings == max) { |
| 2696 | 1 | end = len; |
| 2697 | 1 | substrings.add(str.substring(beg)); |
| 2698 | } else { | |
| 2699 | // The following is OK, because String.substring( beg, end ) excludes | |
| 2700 | // the character at the position 'end'. | |
| 2701 | 12 | substrings.add(str.substring(beg, end)); |
| 2702 | ||
| 2703 | // Set the starting point for the next search. | |
| 2704 | // The following is equivalent to beg = end + (separatorLength - 1) + 1, | |
| 2705 | // which is the right calculation: | |
| 2706 | 12 | beg = end + separatorLength; |
| 2707 | } | |
| 2708 | } else { | |
| 2709 | // We found a consecutive occurrence of the separator, so skip it. | |
| 2710 | 10 | if (preserveAllTokens) { |
| 2711 | 9 | numberOfSubstrings += 1; |
| 2712 | 9 | if (numberOfSubstrings == max) { |
| 2713 | 1 | end = len; |
| 2714 | 1 | substrings.add(str.substring(beg)); |
| 2715 | } else { | |
| 2716 | 8 | substrings.add(EMPTY); |
| 2717 | } | |
| 2718 | } | |
| 2719 | 10 | beg = end + separatorLength; |
| 2720 | } | |
| 2721 | } else { | |
| 2722 | // String.substring( beg ) goes from 'beg' to the end of the String. | |
| 2723 | 4 | substrings.add(str.substring(beg)); |
| 2724 | 4 | end = len; |
| 2725 | } | |
| 2726 | } | |
| 2727 | ||
| 2728 | 6 | return substrings.toArray(new String[substrings.size()]); |
| 2729 | } | |
| 2730 | ||
| 2731 | // ----------------------------------------------------------------------- | |
| 2732 | /** | |
| 2733 | * <p>Splits the provided text into an array, using whitespace as the | |
| 2734 | * separator, preserving all tokens, including empty tokens created by | |
| 2735 | * adjacent separators. This is an alternative to using StringTokenizer. | |
| 2736 | * Whitespace is defined by {@link Character#isWhitespace(char)}.</p> | |
| 2737 | * | |
| 2738 | * <p>The separator is not included in the returned String array. | |
| 2739 | * Adjacent separators are treated as separators for empty tokens. | |
| 2740 | * For more control over the split use the StrTokenizer class.</p> | |
| 2741 | * | |
| 2742 | * <p>A {@code null} input String returns {@code null}.</p> | |
| 2743 | * | |
| 2744 | * <pre> | |
| 2745 | * StringUtils.splitPreserveAllTokens(null) = null | |
| 2746 | * StringUtils.splitPreserveAllTokens("") = [] | |
| 2747 | * StringUtils.splitPreserveAllTokens("abc def") = ["abc", "def"] | |
| 2748 | * StringUtils.splitPreserveAllTokens("abc def") = ["abc", "", "def"] | |
| 2749 | * StringUtils.splitPreserveAllTokens(" abc ") = ["", "abc", ""] | |
| 2750 | * </pre> | |
| 2751 | * | |
| 2752 | * @param str the String to parse, may be {@code null} | |
| 2753 | * @return an array of parsed Strings, {@code null} if null String input | |
| 2754 | * @since 2.1 | |
| 2755 | */ | |
| 2756 | public static String[] splitPreserveAllTokens(final String str) { | |
| 2757 | 11 | return splitWorker(str, null, -1, true); |
| 2758 | } | |
| 2759 | ||
| 2760 | /** | |
| 2761 | * <p>Splits the provided text into an array, separator specified, | |
| 2762 | * preserving all tokens, including empty tokens created by adjacent | |
| 2763 | * separators. This is an alternative to using StringTokenizer.</p> | |
| 2764 | * | |
| 2765 | * <p>The separator is not included in the returned String array. | |
| 2766 | * Adjacent separators are treated as separators for empty tokens. | |
| 2767 | * For more control over the split use the StrTokenizer class.</p> | |
| 2768 | * | |
| 2769 | * <p>A {@code null} input String returns {@code null}.</p> | |
| 2770 | * | |
| 2771 | * <pre> | |
| 2772 | * StringUtils.splitPreserveAllTokens(null, *) = null | |
| 2773 | * StringUtils.splitPreserveAllTokens("", *) = [] | |
| 2774 | * StringUtils.splitPreserveAllTokens("a.b.c", '.') = ["a", "b", "c"] | |
| 2775 | * StringUtils.splitPreserveAllTokens("a..b.c", '.') = ["a", "", "b", "c"] | |
| 2776 | * StringUtils.splitPreserveAllTokens("a:b:c", '.') = ["a:b:c"] | |
| 2777 | * StringUtils.splitPreserveAllTokens("a\tb\nc", null) = ["a", "b", "c"] | |
| 2778 | * StringUtils.splitPreserveAllTokens("a b c", ' ') = ["a", "b", "c"] | |
| 2779 | * StringUtils.splitPreserveAllTokens("a b c ", ' ') = ["a", "b", "c", ""] | |
| 2780 | * StringUtils.splitPreserveAllTokens("a b c ", ' ') = ["a", "b", "c", "", ""] | |
| 2781 | * StringUtils.splitPreserveAllTokens(" a b c", ' ') = ["", a", "b", "c"] | |
| 2782 | * StringUtils.splitPreserveAllTokens(" a b c", ' ') = ["", "", a", "b", "c"] | |
| 2783 | * StringUtils.splitPreserveAllTokens(" a b c ", ' ') = ["", a", "b", "c", ""] | |
| 2784 | * </pre> | |
| 2785 | * | |
| 2786 | * @param str the String to parse, may be {@code null} | |
| 2787 | * @param separatorChar the character used as the delimiter, | |
| 2788 | * {@code null} splits on whitespace | |
| 2789 | * @return an array of parsed Strings, {@code null} if null String input | |
| 2790 | * @since 2.1 | |
| 2791 | */ | |
| 2792 | public static String[] splitPreserveAllTokens(final String str, final char separatorChar) { | |
| 2793 | 15 | return splitWorker(str, separatorChar, true); |
| 2794 | } | |
| 2795 | ||
| 2796 | /** | |
| 2797 | * Performs the logic for the {@code split} and | |
| 2798 | * {@code splitPreserveAllTokens} methods that do not return a | |
| 2799 | * maximum array length. | |
| 2800 | * | |
| 2801 | * @param str the String to parse, may be {@code null} | |
| 2802 | * @param separatorChar the separate character | |
| 2803 | * @param preserveAllTokens if {@code true}, adjacent separators are | |
| 2804 | * treated as empty token separators; if {@code false}, adjacent | |
| 2805 | * separators are treated as one separator. | |
| 2806 | * @return an array of parsed Strings, {@code null} if null String input | |
| 2807 | */ | |
| 2808 | private static String[] splitWorker(final String str, final char separatorChar, final boolean preserveAllTokens) { | |
| 2809 | // Performance tuned for 2.0 (JDK1.4) | |
| 2810 | ||
| 2811 | 24 | if (str == null) { |
| 2812 | 2 | return null; |
| 2813 | } | |
| 2814 | 22 | final int len = str.length(); |
| 2815 | 22 | if (len == 0) { |
| 2816 | 4 | return ArrayUtils.EMPTY_STRING_ARRAY; |
| 2817 | } | |
| 2818 | 18 | final List<String> list = new ArrayList<String>(); |
| 2819 | 18 | int i = 0, start = 0; |
| 2820 | 18 | boolean match = false; |
| 2821 | 18 | boolean lastMatch = false; |
| 2822 | 114 | while (i < len) { |
| 2823 | 96 | if (str.charAt(i) == separatorChar) { |
| 2824 | 47 | if (match || preserveAllTokens) { |
| 2825 | 45 | list.add(str.substring(start, i)); |
| 2826 | 45 | match = false; |
| 2827 | 45 | lastMatch = true; |
| 2828 | } | |
| 2829 | 47 | start = ++i; |
| 2830 | 47 | continue; |
| 2831 | } | |
| 2832 | 49 | lastMatch = false; |
| 2833 | 49 | match = true; |
| 2834 | 49 | i++; |
| 2835 | } | |
| 2836 | 18 | if (match || preserveAllTokens && lastMatch) { |
| 2837 | 17 | list.add(str.substring(start, i)); |
| 2838 | } | |
| 2839 | 18 | return list.toArray(new String[list.size()]); |
| 2840 | } | |
| 2841 | ||
| 2842 | /** | |
| 2843 | * <p>Splits the provided text into an array, separators specified, | |
| 2844 | * preserving all tokens, including empty tokens created by adjacent | |
| 2845 | * separators. This is an alternative to using StringTokenizer.</p> | |
| 2846 | * | |
| 2847 | * <p>The separator is not included in the returned String array. | |
| 2848 | * Adjacent separators are treated as separators for empty tokens. | |
| 2849 | * For more control over the split use the StrTokenizer class.</p> | |
| 2850 | * | |
| 2851 | * <p>A {@code null} input String returns {@code null}. | |
| 2852 | * A {@code null} separatorChars splits on whitespace.</p> | |
| 2853 | * | |
| 2854 | * <pre> | |
| 2855 | * StringUtils.splitPreserveAllTokens(null, *) = null | |
| 2856 | * StringUtils.splitPreserveAllTokens("", *) = [] | |
| 2857 | * StringUtils.splitPreserveAllTokens("abc def", null) = ["abc", "def"] | |
| 2858 | * StringUtils.splitPreserveAllTokens("abc def", " ") = ["abc", "def"] | |
| 2859 | * StringUtils.splitPreserveAllTokens("abc def", " ") = ["abc", "", def"] | |
| 2860 | * StringUtils.splitPreserveAllTokens("ab:cd:ef", ":") = ["ab", "cd", "ef"] | |
| 2861 | * StringUtils.splitPreserveAllTokens("ab:cd:ef:", ":") = ["ab", "cd", "ef", ""] | |
| 2862 | * StringUtils.splitPreserveAllTokens("ab:cd:ef::", ":") = ["ab", "cd", "ef", "", ""] | |
| 2863 | * StringUtils.splitPreserveAllTokens("ab::cd:ef", ":") = ["ab", "", cd", "ef"] | |
| 2864 | * StringUtils.splitPreserveAllTokens(":cd:ef", ":") = ["", cd", "ef"] | |
| 2865 | * StringUtils.splitPreserveAllTokens("::cd:ef", ":") = ["", "", cd", "ef"] | |
| 2866 | * StringUtils.splitPreserveAllTokens(":cd:ef:", ":") = ["", cd", "ef", ""] | |
| 2867 | * </pre> | |
| 2868 | * | |
| 2869 | * @param str the String to parse, may be {@code null} | |
| 2870 | * @param separatorChars the characters used as the delimiters, | |
| 2871 | * {@code null} splits on whitespace | |
| 2872 | * @return an array of parsed Strings, {@code null} if null String input | |
| 2873 | * @since 2.1 | |
| 2874 | */ | |
| 2875 | public static String[] splitPreserveAllTokens(final String str, final String separatorChars) { | |
| 2876 | 3128 | return splitWorker(str, separatorChars, -1, true); |
| 2877 | } | |
| 2878 | ||
| 2879 | /** | |
| 2880 | * <p>Splits the provided text into an array with a maximum length, | |
| 2881 | * separators specified, preserving all tokens, including empty tokens | |
| 2882 | * created by adjacent separators.</p> | |
| 2883 | * | |
| 2884 | * <p>The separator is not included in the returned String array. | |
| 2885 | * Adjacent separators are treated as separators for empty tokens. | |
| 2886 | * Adjacent separators are treated as one separator.</p> | |
| 2887 | * | |
| 2888 | * <p>A {@code null} input String returns {@code null}. | |
| 2889 | * A {@code null} separatorChars splits on whitespace.</p> | |
| 2890 | * | |
| 2891 | * <p>If more than {@code max} delimited substrings are found, the last | |
| 2892 | * returned string includes all characters after the first {@code max - 1} | |
| 2893 | * returned strings (including separator characters).</p> | |
| 2894 | * | |
| 2895 | * <pre> | |
| 2896 | * StringUtils.splitPreserveAllTokens(null, *, *) = null | |
| 2897 | * StringUtils.splitPreserveAllTokens("", *, *) = [] | |
| 2898 | * StringUtils.splitPreserveAllTokens("ab de fg", null, 0) = ["ab", "cd", "ef"] | |
| 2899 | * StringUtils.splitPreserveAllTokens("ab de fg", null, 0) = ["ab", "cd", "ef"] | |
| 2900 | * StringUtils.splitPreserveAllTokens("ab:cd:ef", ":", 0) = ["ab", "cd", "ef"] | |
| 2901 | * StringUtils.splitPreserveAllTokens("ab:cd:ef", ":", 2) = ["ab", "cd:ef"] | |
| 2902 | * StringUtils.splitPreserveAllTokens("ab de fg", null, 2) = ["ab", " de fg"] | |
| 2903 | * StringUtils.splitPreserveAllTokens("ab de fg", null, 3) = ["ab", "", " de fg"] | |
| 2904 | * StringUtils.splitPreserveAllTokens("ab de fg", null, 4) = ["ab", "", "", "de fg"] | |
| 2905 | * </pre> | |
| 2906 | * | |
| 2907 | * @param str the String to parse, may be {@code null} | |
| 2908 | * @param separatorChars the characters used as the delimiters, | |
| 2909 | * {@code null} splits on whitespace | |
| 2910 | * @param max the maximum number of elements to include in the | |
| 2911 | * array. A zero or negative value implies no limit | |
| 2912 | * @return an array of parsed Strings, {@code null} if null String input | |
| 2913 | * @since 2.1 | |
| 2914 | */ | |
| 2915 | public static String[] splitPreserveAllTokens(final String str, final String separatorChars, final int max) { | |
| 2916 | 6265 | return splitWorker(str, separatorChars, max, true); |
| 2917 | } | |
| 2918 | ||
| 2919 | /** | |
| 2920 | * Performs the logic for the {@code split} and | |
| 2921 | * {@code splitPreserveAllTokens} methods that return a maximum array | |
| 2922 | * length. | |
| 2923 | * | |
| 2924 | * @param str the String to parse, may be {@code null} | |
| 2925 | * @param separatorChars the separate character | |
| 2926 | * @param max the maximum number of elements to include in the | |
| 2927 | * array. A zero or negative value implies no limit. | |
| 2928 | * @param preserveAllTokens if {@code true}, adjacent separators are | |
| 2929 | * treated as empty token separators; if {@code false}, adjacent | |
| 2930 | * separators are treated as one separator. | |
| 2931 | * @return an array of parsed Strings, {@code null} if null String input | |
| 2932 | */ | |
| 2933 | private static String[] splitWorker(final String str, final String separatorChars, final int max, final boolean preserveAllTokens) { | |
| 2934 | // Performance tuned for 2.0 (JDK1.4) | |
| 2935 | // Direct code is quicker than StringTokenizer. | |
| 2936 | // Also, StringTokenizer uses isSpace() not isWhitespace() | |
| 2937 | ||
| 2938 | 18796 | if (str == null) { |
| 2939 | 6 | return null; |
| 2940 | } | |
| 2941 | 18790 | final int len = str.length(); |
| 2942 | 18790 | if (len == 0) { |
| 2943 | 6 | return ArrayUtils.EMPTY_STRING_ARRAY; |
| 2944 | } | |
| 2945 | 18784 | final List<String> list = new ArrayList<String>(); |
| 2946 | 18784 | int sizePlus1 = 1; |
| 2947 | 18784 | int i = 0, start = 0; |
| 2948 | 18784 | boolean match = false; |
| 2949 | 18784 | boolean lastMatch = false; |
| 2950 | 18784 | if (separatorChars == null) { |
| 2951 | // Null separator means use whitespace | |
| 2952 | 56417 | while (i < len) { |
| 2953 | 47037 | if (Character.isWhitespace(str.charAt(i))) { |
| 2954 | 21944 | if (match || preserveAllTokens) { |
| 2955 | 18791 | lastMatch = true; |
| 2956 | 18791 | if (sizePlus1++ == max) { |
| 2957 | 3126 | i = len; |
| 2958 | 3126 | lastMatch = false; |
| 2959 | } | |
| 2960 | 18791 | list.add(str.substring(start, i)); |
| 2961 | 18791 | match = false; |
| 2962 | } | |
| 2963 | 21944 | start = ++i; |
| 2964 | 21944 | continue; |
| 2965 | } | |
| 2966 | 25093 | lastMatch = false; |
| 2967 | 25093 | match = true; |
| 2968 | 25093 | i++; |
| 2969 | } | |
| 2970 | 9404 | } else if (separatorChars.length() == 1) { |
| 2971 | // Optimise 1 character case | |
| 2972 | 9392 | final char sep = separatorChars.charAt(0); |
| 2973 | 56364 | while (i < len) { |
| 2974 | 46972 | if (str.charAt(i) == sep) { |
| 2975 | 21922 | if (match || preserveAllTokens) { |
| 2976 | 18794 | lastMatch = true; |
| 2977 | 18794 | if (sizePlus1++ == max) { |
| 2978 | 3136 | i = len; |
| 2979 | 3136 | lastMatch = false; |
| 2980 | } | |
| 2981 | 18794 | list.add(str.substring(start, i)); |
| 2982 | 18794 | match = false; |
| 2983 | } | |
| 2984 | 21922 | start = ++i; |
| 2985 | 21922 | continue; |
| 2986 | } | |
| 2987 | 25050 | lastMatch = false; |
| 2988 | 25050 | match = true; |
| 2989 | 25050 | i++; |
| 2990 | } | |
| 2991 | 9392 | } else { |
| 2992 | // standard case | |
| 2993 | 72 | while (i < len) { |
| 2994 | 60 | if (separatorChars.indexOf(str.charAt(i)) >= 0) { |
| 2995 | 28 | if (match || preserveAllTokens) { |
| 2996 | 24 | lastMatch = true; |
| 2997 | 24 | if (sizePlus1++ == max) { |
| 2998 | 4 | i = len; |
| 2999 | 4 | lastMatch = false; |
| 3000 | } | |
| 3001 | 24 | list.add(str.substring(start, i)); |
| 3002 | 24 | match = false; |
| 3003 | } | |
| 3004 | 28 | start = ++i; |
| 3005 | 28 | continue; |
| 3006 | } | |
| 3007 | 32 | lastMatch = false; |
| 3008 | 32 | match = true; |
| 3009 | 32 | i++; |
| 3010 | } | |
| 3011 | } | |
| 3012 | 18784 | if (match || preserveAllTokens && lastMatch) { |
| 3013 | 10954 | list.add(str.substring(start, i)); |
| 3014 | } | |
| 3015 | 18784 | return list.toArray(new String[list.size()]); |
| 3016 | } | |
| 3017 | ||
| 3018 | /** | |
| 3019 | * <p>Splits a String by Character type as returned by | |
| 3020 | * {@code java.lang.Character.getType(char)}. Groups of contiguous | |
| 3021 | * characters of the same type are returned as complete tokens. | |
| 3022 | * <pre> | |
| 3023 | * StringUtils.splitByCharacterType(null) = null | |
| 3024 | * StringUtils.splitByCharacterType("") = [] | |
| 3025 | * StringUtils.splitByCharacterType("ab de fg") = ["ab", " ", "de", " ", "fg"] | |
| 3026 | * StringUtils.splitByCharacterType("ab de fg") = ["ab", " ", "de", " ", "fg"] | |
| 3027 | * StringUtils.splitByCharacterType("ab:cd:ef") = ["ab", ":", "cd", ":", "ef"] | |
| 3028 | * StringUtils.splitByCharacterType("number5") = ["number", "5"] | |
| 3029 | * StringUtils.splitByCharacterType("fooBar") = ["foo", "B", "ar"] | |
| 3030 | * StringUtils.splitByCharacterType("foo200Bar") = ["foo", "200", "B", "ar"] | |
| 3031 | * StringUtils.splitByCharacterType("ASFRules") = ["ASFR", "ules"] | |
| 3032 | * </pre> | |
| 3033 | * @param str the String to split, may be {@code null} | |
| 3034 | * @return an array of parsed Strings, {@code null} if null String input | |
| 3035 | * @since 2.4 | |
| 3036 | */ | |
| 3037 | public static String[] splitByCharacterType(final String str) { | |
| 3038 | 9 | return splitByCharacterType(str, false); |
| 3039 | } | |
| 3040 | ||
| 3041 | /** | |
| 3042 | * <p>Splits a String by Character type as returned by | |
| 3043 | * {@code java.lang.Character.getType(char)}. Groups of contiguous | |
| 3044 | * characters of the same type are returned as complete tokens, with the | |
| 3045 | * following exception: the character of type | |
| 3046 | * {@code Character.UPPERCASE_LETTER}, if any, immediately | |
| 3047 | * preceding a token of type {@code Character.LOWERCASE_LETTER} | |
| 3048 | * will belong to the following token rather than to the preceding, if any, | |
| 3049 | * {@code Character.UPPERCASE_LETTER} token. | |
| 3050 | * <pre> | |
| 3051 | * StringUtils.splitByCharacterTypeCamelCase(null) = null | |
| 3052 | * StringUtils.splitByCharacterTypeCamelCase("") = [] | |
| 3053 | * StringUtils.splitByCharacterTypeCamelCase("ab de fg") = ["ab", " ", "de", " ", "fg"] | |
| 3054 | * StringUtils.splitByCharacterTypeCamelCase("ab de fg") = ["ab", " ", "de", " ", "fg"] | |
| 3055 | * StringUtils.splitByCharacterTypeCamelCase("ab:cd:ef") = ["ab", ":", "cd", ":", "ef"] | |
| 3056 | * StringUtils.splitByCharacterTypeCamelCase("number5") = ["number", "5"] | |
| 3057 | * StringUtils.splitByCharacterTypeCamelCase("fooBar") = ["foo", "Bar"] | |
| 3058 | * StringUtils.splitByCharacterTypeCamelCase("foo200Bar") = ["foo", "200", "Bar"] | |
| 3059 | * StringUtils.splitByCharacterTypeCamelCase("ASFRules") = ["ASF", "Rules"] | |
| 3060 | * </pre> | |
| 3061 | * @param str the String to split, may be {@code null} | |
| 3062 | * @return an array of parsed Strings, {@code null} if null String input | |
| 3063 | * @since 2.4 | |
| 3064 | */ | |
| 3065 | public static String[] splitByCharacterTypeCamelCase(final String str) { | |
| 3066 | 9 | return splitByCharacterType(str, true); |
| 3067 | } | |
| 3068 | ||
| 3069 | /** | |
| 3070 | * <p>Splits a String by Character type as returned by | |
| 3071 | * {@code java.lang.Character.getType(char)}. Groups of contiguous | |
| 3072 | * characters of the same type are returned as complete tokens, with the | |
| 3073 | * following exception: if {@code camelCase} is {@code true}, | |
| 3074 | * the character of type {@code Character.UPPERCASE_LETTER}, if any, | |
| 3075 | * immediately preceding a token of type {@code Character.LOWERCASE_LETTER} | |
| 3076 | * will belong to the following token rather than to the preceding, if any, | |
| 3077 | * {@code Character.UPPERCASE_LETTER} token. | |
| 3078 | * @param str the String to split, may be {@code null} | |
| 3079 | * @param camelCase whether to use so-called "camel-case" for letter types | |
| 3080 | * @return an array of parsed Strings, {@code null} if null String input | |
| 3081 | * @since 2.4 | |
| 3082 | */ | |
| 3083 | private static String[] splitByCharacterType(final String str, final boolean camelCase) { | |
| 3084 | 18 | if (str == null) { |
| 3085 | 2 | return null; |
| 3086 | } | |
| 3087 | 16 | if (str.length() == 0) { |
| 3088 | 2 | return ArrayUtils.EMPTY_STRING_ARRAY; |
| 3089 | } | |
| 3090 | 14 | final char[] c = str.toCharArray(); |
| 3091 | 14 | final List<String> list = new ArrayList<String>(); |
| 3092 | 14 | int tokenStart = 0; |
| 3093 | 14 | int currentType = Character.getType(c[tokenStart]); |
| 3094 | 112 | for (int pos = tokenStart + 1; pos < c.length; pos++) { |
| 3095 | 98 | final int type = Character.getType(c[pos]); |
| 3096 | 98 | if (type == currentType) { |
| 3097 | 60 | continue; |
| 3098 | } | |
| 3099 | 38 | if (camelCase && type == Character.LOWERCASE_LETTER && currentType == Character.UPPERCASE_LETTER) { |
| 3100 | 3 | final int newTokenStart = pos - 1; |
| 3101 | 3 | if (newTokenStart != tokenStart) { |
| 3102 | 1 | list.add(new String(c, tokenStart, newTokenStart - tokenStart)); |
| 3103 | 1 | tokenStart = newTokenStart; |
| 3104 | } | |
| 3105 | 3 | } else { |
| 3106 | 35 | list.add(new String(c, tokenStart, pos - tokenStart)); |
| 3107 | 35 | tokenStart = pos; |
| 3108 | } | |
| 3109 | 38 | currentType = type; |
| 3110 | } | |
| 3111 | 14 | list.add(new String(c, tokenStart, c.length - tokenStart)); |
| 3112 | 14 | return list.toArray(new String[list.size()]); |
| 3113 | } | |
| 3114 | ||
| 3115 | // Joining | |
| 3116 | //----------------------------------------------------------------------- | |
| 3117 | /** | |
| 3118 | * <p>Joins the elements of the provided array into a single String | |
| 3119 | * containing the provided list of elements.</p> | |
| 3120 | * | |
| 3121 | * <p>No separator is added to the joined String. | |
| 3122 | * Null objects or empty strings within the array are represented by | |
| 3123 | * empty strings.</p> | |
| 3124 | * | |
| 3125 | * <pre> | |
| 3126 | * StringUtils.join(null) = null | |
| 3127 | * StringUtils.join([]) = "" | |
| 3128 | * StringUtils.join([null]) = "" | |
| 3129 | * StringUtils.join(["a", "b", "c"]) = "abc" | |
| 3130 | * StringUtils.join([null, "", "a"]) = "a" | |
| 3131 | * </pre> | |
| 3132 | * | |
| 3133 | * @param <T> the specific type of values to join together | |
| 3134 | * @param elements the values to join together, may be null | |
| 3135 | * @return the joined String, {@code null} if null array input | |
| 3136 | * @since 2.0 | |
| 3137 | * @since 3.0 Changed signature to use varargs | |
| 3138 | */ | |
| 3139 | public static <T> String join(final T... elements) { | |
| 3140 | 24 | return join(elements, null); |
| 3141 | } | |
| 3142 | ||
| 3143 | /** | |
| 3144 | * <p>Joins the elements of the provided array into a single String | |
| 3145 | * containing the provided list of elements.</p> | |
| 3146 | * | |
| 3147 | * <p>No delimiter is added before or after the list. | |
| 3148 | * Null objects or empty strings within the array are represented by | |
| 3149 | * empty strings.</p> | |
| 3150 | * | |
| 3151 | * <pre> | |
| 3152 | * StringUtils.join(null, *) = null | |
| 3153 | * StringUtils.join([], *) = "" | |
| 3154 | * StringUtils.join([null], *) = "" | |
| 3155 | * StringUtils.join(["a", "b", "c"], ';') = "a;b;c" | |
| 3156 | * StringUtils.join(["a", "b", "c"], null) = "abc" | |
| 3157 | * StringUtils.join([null, "", "a"], ';') = ";;a" | |
| 3158 | * </pre> | |
| 3159 | * | |
| 3160 | * @param array the array of values to join together, may be null | |
| 3161 | * @param separator the separator character to use | |
| 3162 | * @return the joined String, {@code null} if null array input | |
| 3163 | * @since 2.0 | |
| 3164 | */ | |
| 3165 | public static String join(final Object[] array, final char separator) { | |
| 3166 | 9 | if (array == null) { |
| 3167 | 1 | return null; |
| 3168 | } | |
| 3169 | 8 | return join(array, separator, 0, array.length); |
| 3170 | } | |
| 3171 | ||
| 3172 | /** | |
| 3173 | * <p> | |
| 3174 | * Joins the elements of the provided array into a single String containing the provided list of elements. | |
| 3175 | * </p> | |
| 3176 | * | |
| 3177 | * <p> | |
| 3178 | * No delimiter is added before or after the list. Null objects or empty strings within the array are represented | |
| 3179 | * by empty strings. | |
| 3180 | * </p> | |
| 3181 | * | |
| 3182 | * <pre> | |
| 3183 | * StringUtils.join(null, *) = null | |
| 3184 | * StringUtils.join([], *) = "" | |
| 3185 | * StringUtils.join([null], *) = "" | |
| 3186 | * StringUtils.join([1, 2, 3], ';') = "1;2;3" | |
| 3187 | * StringUtils.join([1, 2, 3], null) = "123" | |
| 3188 | * </pre> | |
| 3189 | * | |
| 3190 | * @param array | |
| 3191 | * the array of values to join together, may be null | |
| 3192 | * @param separator | |
| 3193 | * the separator character to use | |
| 3194 | * @return the joined String, {@code null} if null array input | |
| 3195 | * @since 3.2 | |
| 3196 | */ | |
| 3197 | public static String join(final long[] array, final char separator) { | |
| 3198 | 2 | if (array == null) { |
| 3199 | 1 | return null; |
| 3200 | } | |
| 3201 | 1 | return join(array, separator, 0, array.length); |
| 3202 | } | |
| 3203 | ||
| 3204 | /** | |
| 3205 | * <p> | |
| 3206 | * Joins the elements of the provided array into a single String containing the provided list of elements. | |
| 3207 | * </p> | |
| 3208 | * | |
| 3209 | * <p> | |
| 3210 | * No delimiter is added before or after the list. Null objects or empty strings within the array are represented | |
| 3211 | * by empty strings. | |
| 3212 | * </p> | |
| 3213 | * | |
| 3214 | * <pre> | |
| 3215 | * StringUtils.join(null, *) = null | |
| 3216 | * StringUtils.join([], *) = "" | |
| 3217 | * StringUtils.join([null], *) = "" | |
| 3218 | * StringUtils.join([1, 2, 3], ';') = "1;2;3" | |
| 3219 | * StringUtils.join([1, 2, 3], null) = "123" | |
| 3220 | * </pre> | |
| 3221 | * | |
| 3222 | * @param array | |
| 3223 | * the array of values to join together, may be null | |
| 3224 | * @param separator | |
| 3225 | * the separator character to use | |
| 3226 | * @return the joined String, {@code null} if null array input | |
| 3227 | * @since 3.2 | |
| 3228 | */ | |
| 3229 | public static String join(final int[] array, final char separator) { | |
| 3230 | 2 | if (array == null) { |
| 3231 | 1 | return null; |
| 3232 | } | |
| 3233 | 1 | return join(array, separator, 0, array.length); |
| 3234 | } | |
| 3235 | ||
| 3236 | /** | |
| 3237 | * <p> | |
| 3238 | * Joins the elements of the provided array into a single String containing the provided list of elements. | |
| 3239 | * </p> | |
| 3240 | * | |
| 3241 | * <p> | |
| 3242 | * No delimiter is added before or after the list. Null objects or empty strings within the array are represented | |
| 3243 | * by empty strings. | |
| 3244 | * </p> | |
| 3245 | * | |
| 3246 | * <pre> | |
| 3247 | * StringUtils.join(null, *) = null | |
| 3248 | * StringUtils.join([], *) = "" | |
| 3249 | * StringUtils.join([null], *) = "" | |
| 3250 | * StringUtils.join([1, 2, 3], ';') = "1;2;3" | |
| 3251 | * StringUtils.join([1, 2, 3], null) = "123" | |
| 3252 | * </pre> | |
| 3253 | * | |
| 3254 | * @param array | |
| 3255 | * the array of values to join together, may be null | |
| 3256 | * @param separator | |
| 3257 | * the separator character to use | |
| 3258 | * @return the joined String, {@code null} if null array input | |
| 3259 | * @since 3.2 | |
| 3260 | */ | |
| 3261 | public static String join(final short[] array, final char separator) { | |
| 3262 | 2 | if (array == null) { |
| 3263 | 1 | return null; |
| 3264 | } | |
| 3265 | 1 | return join(array, separator, 0, array.length); |
| 3266 | } | |
| 3267 | ||
| 3268 | /** | |
| 3269 | * <p> | |
| 3270 | * Joins the elements of the provided array into a single String containing the provided list of elements. | |
| 3271 | * </p> | |
| 3272 | * | |
| 3273 | * <p> | |
| 3274 | * No delimiter is added before or after the list. Null objects or empty strings within the array are represented | |
| 3275 | * by empty strings. | |
| 3276 | * </p> | |
| 3277 | * | |
| 3278 | * <pre> | |
| 3279 | * StringUtils.join(null, *) = null | |
| 3280 | * StringUtils.join([], *) = "" | |
| 3281 | * StringUtils.join([null], *) = "" | |
| 3282 | * StringUtils.join([1, 2, 3], ';') = "1;2;3" | |
| 3283 | * StringUtils.join([1, 2, 3], null) = "123" | |
| 3284 | * </pre> | |
| 3285 | * | |
| 3286 | * @param array | |
| 3287 | * the array of values to join together, may be null | |
| 3288 | * @param separator | |
| 3289 | * the separator character to use | |
| 3290 | * @return the joined String, {@code null} if null array input | |
| 3291 | * @since 3.2 | |
| 3292 | */ | |
| 3293 | public static String join(final byte[] array, final char separator) { | |
| 3294 | 2 | if (array == null) { |
| 3295 | 1 | return null; |
| 3296 | } | |
| 3297 | 1 | return join(array, separator, 0, array.length); |
| 3298 | } | |
| 3299 | ||
| 3300 | /** | |
| 3301 | * <p> | |
| 3302 | * Joins the elements of the provided array into a single String containing the provided list of elements. | |
| 3303 | * </p> | |
| 3304 | * | |
| 3305 | * <p> | |
| 3306 | * No delimiter is added before or after the list. Null objects or empty strings within the array are represented | |
| 3307 | * by empty strings. | |
| 3308 | * </p> | |
| 3309 | * | |
| 3310 | * <pre> | |
| 3311 | * StringUtils.join(null, *) = null | |
| 3312 | * StringUtils.join([], *) = "" | |
| 3313 | * StringUtils.join([null], *) = "" | |
| 3314 | * StringUtils.join([1, 2, 3], ';') = "1;2;3" | |
| 3315 | * StringUtils.join([1, 2, 3], null) = "123" | |
| 3316 | * </pre> | |
| 3317 | * | |
| 3318 | * @param array | |
| 3319 | * the array of values to join together, may be null | |
| 3320 | * @param separator | |
| 3321 | * the separator character to use | |
| 3322 | * @return the joined String, {@code null} if null array input | |
| 3323 | * @since 3.2 | |
| 3324 | */ | |
| 3325 | public static String join(final char[] array, final char separator) { | |
| 3326 | 2 | if (array == null) { |
| 3327 | 1 | return null; |
| 3328 | } | |
| 3329 | 1 | return join(array, separator, 0, array.length); |
| 3330 | } | |
| 3331 | ||
| 3332 | /** | |
| 3333 | * <p> | |
| 3334 | * Joins the elements of the provided array into a single String containing the provided list of elements. | |
| 3335 | * </p> | |
| 3336 | * | |
| 3337 | * <p> | |
| 3338 | * No delimiter is added before or after the list. Null objects or empty strings within the array are represented | |
| 3339 | * by empty strings. | |
| 3340 | * </p> | |
| 3341 | * | |
| 3342 | * <pre> | |
| 3343 | * StringUtils.join(null, *) = null | |
| 3344 | * StringUtils.join([], *) = "" | |
| 3345 | * StringUtils.join([null], *) = "" | |
| 3346 | * StringUtils.join([1, 2, 3], ';') = "1;2;3" | |
| 3347 | * StringUtils.join([1, 2, 3], null) = "123" | |
| 3348 | * </pre> | |
| 3349 | * | |
| 3350 | * @param array | |
| 3351 | * the array of values to join together, may be null | |
| 3352 | * @param separator | |
| 3353 | * the separator character to use | |
| 3354 | * @return the joined String, {@code null} if null array input | |
| 3355 | * @since 3.2 | |
| 3356 | */ | |
| 3357 | public static String join(final float[] array, final char separator) { | |
| 3358 | 2 | if (array == null) { |
| 3359 | 1 | return null; |
| 3360 | } | |
| 3361 | 1 | return join(array, separator, 0, array.length); |
| 3362 | } | |
| 3363 | ||
| 3364 | /** | |
| 3365 | * <p> | |
| 3366 | * Joins the elements of the provided array into a single String containing the provided list of elements. | |
| 3367 | * </p> | |
| 3368 | * | |
| 3369 | * <p> | |
| 3370 | * No delimiter is added before or after the list. Null objects or empty strings within the array are represented | |
| 3371 | * by empty strings. | |
| 3372 | * </p> | |
| 3373 | * | |
| 3374 | * <pre> | |
| 3375 | * StringUtils.join(null, *) = null | |
| 3376 | * StringUtils.join([], *) = "" | |
| 3377 | * StringUtils.join([null], *) = "" | |
| 3378 | * StringUtils.join([1, 2, 3], ';') = "1;2;3" | |
| 3379 | * StringUtils.join([1, 2, 3], null) = "123" | |
| 3380 | * </pre> | |
| 3381 | * | |
| 3382 | * @param array | |
| 3383 | * the array of values to join together, may be null | |
| 3384 | * @param separator | |
| 3385 | * the separator character to use | |
| 3386 | * @return the joined String, {@code null} if null array input | |
| 3387 | * @since 3.2 | |
| 3388 | */ | |
| 3389 | public static String join(final double[] array, final char separator) { | |
| 3390 | 2 | if (array == null) { |
| 3391 | 1 | return null; |
| 3392 | } | |
| 3393 | 1 | return join(array, separator, 0, array.length); |
| 3394 | } | |
| 3395 | ||
| 3396 | ||
| 3397 | /** | |
| 3398 | * <p>Joins the elements of the provided array into a single String | |
| 3399 | * containing the provided list of elements.</p> | |
| 3400 | * | |
| 3401 | * <p>No delimiter is added before or after the list. | |
| 3402 | * Null objects or empty strings within the array are represented by | |
| 3403 | * empty strings.</p> | |
| 3404 | * | |
| 3405 | * <pre> | |
| 3406 | * StringUtils.join(null, *) = null | |
| 3407 | * StringUtils.join([], *) = "" | |
| 3408 | * StringUtils.join([null], *) = "" | |
| 3409 | * StringUtils.join(["a", "b", "c"], ';') = "a;b;c" | |
| 3410 | * StringUtils.join(["a", "b", "c"], null) = "abc" | |
| 3411 | * StringUtils.join([null, "", "a"], ';') = ";;a" | |
| 3412 | * </pre> | |
| 3413 | * | |
| 3414 | * @param array the array of values to join together, may be null | |
| 3415 | * @param separator the separator character to use | |
| 3416 | * @param startIndex the first index to start joining from. It is | |
| 3417 | * an error to pass in an end index past the end of the array | |
| 3418 | * @param endIndex the index to stop joining from (exclusive). It is | |
| 3419 | * an error to pass in an end index past the end of the array | |
| 3420 | * @return the joined String, {@code null} if null array input | |
| 3421 | * @since 2.0 | |
| 3422 | */ | |
| 3423 | public static String join(final Object[] array, final char separator, final int startIndex, final int endIndex) { | |
| 3424 | 14 | if (array == null) { |
| 3425 | 0 | return null; |
| 3426 | } | |
| 3427 | 14 | final int noOfItems = endIndex - startIndex; |
| 3428 | 14 | if (noOfItems <= 0) { |
| 3429 | 4 | return EMPTY; |
| 3430 | } | |
| 3431 | 10 | final StringBuilder buf = new StringBuilder(noOfItems * 16); |
| 3432 | 29 | for (int i = startIndex; i < endIndex; i++) { |
| 3433 | 19 | if (i > startIndex) { |
| 3434 | 9 | buf.append(separator); |
| 3435 | } | |
| 3436 | 19 | if (array[i] != null) { |
| 3437 | 17 | buf.append(array[i]); |
| 3438 | } | |
| 3439 | } | |
| 3440 | 10 | return buf.toString(); |
| 3441 | } | |
| 3442 | ||
| 3443 | /** | |
| 3444 | * <p> | |
| 3445 | * Joins the elements of the provided array into a single String containing the provided list of elements. | |
| 3446 | * </p> | |
| 3447 | * | |
| 3448 | * <p> | |
| 3449 | * No delimiter is added before or after the list. Null objects or empty strings within the array are represented | |
| 3450 | * by empty strings. | |
| 3451 | * </p> | |
| 3452 | * | |
| 3453 | * <pre> | |
| 3454 | * StringUtils.join(null, *) = null | |
| 3455 | * StringUtils.join([], *) = "" | |
| 3456 | * StringUtils.join([null], *) = "" | |
| 3457 | * StringUtils.join([1, 2, 3], ';') = "1;2;3" | |
| 3458 | * StringUtils.join([1, 2, 3], null) = "123" | |
| 3459 | * </pre> | |
| 3460 | * | |
| 3461 | * @param array | |
| 3462 | * the array of values to join together, may be null | |
| 3463 | * @param separator | |
| 3464 | * the separator character to use | |
| 3465 | * @param startIndex | |
| 3466 | * the first index to start joining from. It is an error to pass in an end index past the end of the | |
| 3467 | * array | |
| 3468 | * @param endIndex | |
| 3469 | * the index to stop joining from (exclusive). It is an error to pass in an end index past the end of | |
| 3470 | * the array | |
| 3471 | * @return the joined String, {@code null} if null array input | |
| 3472 | * @since 3.2 | |
| 3473 | */ | |
| 3474 | public static String join(final long[] array, final char separator, final int startIndex, final int endIndex) { | |
| 3475 | 2 | if (array == null) { |
| 3476 | 0 | return null; |
| 3477 | } | |
| 3478 | 2 | final int noOfItems = endIndex - startIndex; |
| 3479 | 2 | if (noOfItems <= 0) { |
| 3480 | 0 | return EMPTY; |
| 3481 | } | |
| 3482 | 2 | final StringBuilder buf = new StringBuilder(noOfItems * 16); |
| 3483 | 5 | for (int i = startIndex; i < endIndex; i++) { |
| 3484 | 3 | if (i > startIndex) { |
| 3485 | 1 | buf.append(separator); |
| 3486 | } | |
| 3487 | 3 | buf.append(array[i]); |
| 3488 | } | |
| 3489 | 2 | return buf.toString(); |
| 3490 | } | |
| 3491 | ||
| 3492 | /** | |
| 3493 | * <p> | |
| 3494 | * Joins the elements of the provided array into a single String containing the provided list of elements. | |
| 3495 | * </p> | |
| 3496 | * | |
| 3497 | * <p> | |
| 3498 | * No delimiter is added before or after the list. Null objects or empty strings within the array are represented | |
| 3499 | * by empty strings. | |
| 3500 | * </p> | |
| 3501 | * | |
| 3502 | * <pre> | |
| 3503 | * StringUtils.join(null, *) = null | |
| 3504 | * StringUtils.join([], *) = "" | |
| 3505 | * StringUtils.join([null], *) = "" | |
| 3506 | * StringUtils.join([1, 2, 3], ';') = "1;2;3" | |
| 3507 | * StringUtils.join([1, 2, 3], null) = "123" | |
| 3508 | * </pre> | |
| 3509 | * | |
| 3510 | * @param array | |
| 3511 | * the array of values to join together, may be null | |
| 3512 | * @param separator | |
| 3513 | * the separator character to use | |
| 3514 | * @param startIndex | |
| 3515 | * the first index to start joining from. It is an error to pass in an end index past the end of the | |
| 3516 | * array | |
| 3517 | * @param endIndex | |
| 3518 | * the index to stop joining from (exclusive). It is an error to pass in an end index past the end of | |
| 3519 | * the array | |
| 3520 | * @return the joined String, {@code null} if null array input | |
| 3521 | * @since 3.2 | |
| 3522 | */ | |
| 3523 | public static String join(final int[] array, final char separator, final int startIndex, final int endIndex) { | |
| 3524 | 2 | if (array == null) { |
| 3525 | 0 | return null; |
| 3526 | } | |
| 3527 | 2 | final int noOfItems = endIndex - startIndex; |
| 3528 | 2 | if (noOfItems <= 0) { |
| 3529 | 0 | return EMPTY; |
| 3530 | } | |
| 3531 | 2 | final StringBuilder buf = new StringBuilder(noOfItems * 16); |
| 3532 | 5 | for (int i = startIndex; i < endIndex; i++) { |
| 3533 | 3 | if (i > startIndex) { |
| 3534 | 1 | buf.append(separator); |
| 3535 | } | |
| 3536 | 3 | buf.append(array[i]); |
| 3537 | } | |
| 3538 | 2 | return buf.toString(); |
| 3539 | } | |
| 3540 | ||
| 3541 | /** | |
| 3542 | * <p> | |
| 3543 | * Joins the elements of the provided array into a single String containing the provided list of elements. | |
| 3544 | * </p> | |
| 3545 | * | |
| 3546 | * <p> | |
| 3547 | * No delimiter is added before or after the list. Null objects or empty strings within the array are represented | |
| 3548 | * by empty strings. | |
| 3549 | * </p> | |
| 3550 | * | |
| 3551 | * <pre> | |
| 3552 | * StringUtils.join(null, *) = null | |
| 3553 | * StringUtils.join([], *) = "" | |
| 3554 | * StringUtils.join([null], *) = "" | |
| 3555 | * StringUtils.join([1, 2, 3], ';') = "1;2;3" | |
| 3556 | * StringUtils.join([1, 2, 3], null) = "123" | |
| 3557 | * </pre> | |
| 3558 | * | |
| 3559 | * @param array | |
| 3560 | * the array of values to join together, may be null | |
| 3561 | * @param separator | |
| 3562 | * the separator character to use | |
| 3563 | * @param startIndex | |
| 3564 | * the first index to start joining from. It is an error to pass in an end index past the end of the | |
| 3565 | * array | |
| 3566 | * @param endIndex | |
| 3567 | * the index to stop joining from (exclusive). It is an error to pass in an end index past the end of | |
| 3568 | * the array | |
| 3569 | * @return the joined String, {@code null} if null array input | |
| 3570 | * @since 3.2 | |
| 3571 | */ | |
| 3572 | public static String join(final byte[] array, final char separator, final int startIndex, final int endIndex) { | |
| 3573 | 2 | if (array == null) { |
| 3574 | 0 | return null; |
| 3575 | } | |
| 3576 | 2 | final int noOfItems = endIndex - startIndex; |
| 3577 | 2 | if (noOfItems <= 0) { |
| 3578 | 0 | return EMPTY; |
| 3579 | } | |
| 3580 | 2 | final StringBuilder buf = new StringBuilder(noOfItems * 16); |
| 3581 | 5 | for (int i = startIndex; i < endIndex; i++) { |
| 3582 | 3 | if (i > startIndex) { |
| 3583 | 1 | buf.append(separator); |
| 3584 | } | |
| 3585 | 3 | buf.append(array[i]); |
| 3586 | } | |
| 3587 | 2 | return buf.toString(); |
| 3588 | } | |
| 3589 | ||
| 3590 | /** | |
| 3591 | * <p> | |
| 3592 | * Joins the elements of the provided array into a single String containing the provided list of elements. | |
| 3593 | * </p> | |
| 3594 | * | |
| 3595 | * <p> | |
| 3596 | * No delimiter is added before or after the list. Null objects or empty strings within the array are represented | |
| 3597 | * by empty strings. | |
| 3598 | * </p> | |
| 3599 | * | |
| 3600 | * <pre> | |
| 3601 | * StringUtils.join(null, *) = null | |
| 3602 | * StringUtils.join([], *) = "" | |
| 3603 | * StringUtils.join([null], *) = "" | |
| 3604 | * StringUtils.join([1, 2, 3], ';') = "1;2;3" | |
| 3605 | * StringUtils.join([1, 2, 3], null) = "123" | |
| 3606 | * </pre> | |
| 3607 | * | |
| 3608 | * @param array | |
| 3609 | * the array of values to join together, may be null | |
| 3610 | * @param separator | |
| 3611 | * the separator character to use | |
| 3612 | * @param startIndex | |
| 3613 | * the first index to start joining from. It is an error to pass in an end index past the end of the | |
| 3614 | * array | |
| 3615 | * @param endIndex | |
| 3616 | * the index to stop joining from (exclusive). It is an error to pass in an end index past the end of | |
| 3617 | * the array | |
| 3618 | * @return the joined String, {@code null} if null array input | |
| 3619 | * @since 3.2 | |
| 3620 | */ | |
| 3621 | public static String join(final short[] array, final char separator, final int startIndex, final int endIndex) { | |
| 3622 | 2 | if (array == null) { |
| 3623 | 0 | return null; |
| 3624 | } | |
| 3625 | 2 | final int noOfItems = endIndex - startIndex; |
| 3626 | 2 | if (noOfItems <= 0) { |
| 3627 | 0 | return EMPTY; |
| 3628 | } | |
| 3629 | 2 | final StringBuilder buf = new StringBuilder(noOfItems * 16); |
| 3630 | 5 | for (int i = startIndex; i < endIndex; i++) { |
| 3631 | 3 | if (i > startIndex) { |
| 3632 | 1 | buf.append(separator); |
| 3633 | } | |
| 3634 | 3 | buf.append(array[i]); |
| 3635 | } | |
| 3636 | 2 | return buf.toString(); |
| 3637 | } | |
| 3638 | ||
| 3639 | /** | |
| 3640 | * <p> | |
| 3641 | * Joins the elements of the provided array into a single String containing the provided list of elements. | |
| 3642 | * </p> | |
| 3643 | * | |
| 3644 | * <p> | |
| 3645 | * No delimiter is added before or after the list. Null objects or empty strings within the array are represented | |
| 3646 | * by empty strings. | |
| 3647 | * </p> | |
| 3648 | * | |
| 3649 | * <pre> | |
| 3650 | * StringUtils.join(null, *) = null | |
| 3651 | * StringUtils.join([], *) = "" | |
| 3652 | * StringUtils.join([null], *) = "" | |
| 3653 | * StringUtils.join([1, 2, 3], ';') = "1;2;3" | |
| 3654 | * StringUtils.join([1, 2, 3], null) = "123" | |
| 3655 | * </pre> | |
| 3656 | * | |
| 3657 | * @param array | |
| 3658 | * the array of values to join together, may be null | |
| 3659 | * @param separator | |
| 3660 | * the separator character to use | |
| 3661 | * @param startIndex | |
| 3662 | * the first index to start joining from. It is an error to pass in an end index past the end of the | |
| 3663 | * array | |
| 3664 | * @param endIndex | |
| 3665 | * the index to stop joining from (exclusive). It is an error to pass in an end index past the end of | |
| 3666 | * the array | |
| 3667 | * @return the joined String, {@code null} if null array input | |
| 3668 | * @since 3.2 | |
| 3669 | */ | |
| 3670 | public static String join(final char[] array, final char separator, final int startIndex, final int endIndex) { | |
| 3671 | 2 | if (array == null) { |
| 3672 | 0 | return null; |
| 3673 | } | |
| 3674 | 2 | final int noOfItems = endIndex - startIndex; |
| 3675 | 2 | if (noOfItems <= 0) { |
| 3676 | 0 | return EMPTY; |
| 3677 | } | |
| 3678 | 2 | final StringBuilder buf = new StringBuilder(noOfItems * 16); |
| 3679 | 5 | for (int i = startIndex; i < endIndex; i++) { |
| 3680 | 3 | if (i > startIndex) { |
| 3681 | 1 | buf.append(separator); |
| 3682 | } | |
| 3683 | 3 | buf.append(array[i]); |
| 3684 | } | |
| 3685 | 2 | return buf.toString(); |
| 3686 | } | |
| 3687 | ||
| 3688 | /** | |
| 3689 | * <p> | |
| 3690 | * Joins the elements of the provided array into a single String containing the provided list of elements. | |
| 3691 | * </p> | |
| 3692 | * | |
| 3693 | * <p> | |
| 3694 | * No delimiter is added before or after the list. Null objects or empty strings within the array are represented | |
| 3695 | * by empty strings. | |
| 3696 | * </p> | |
| 3697 | * | |
| 3698 | * <pre> | |
| 3699 | * StringUtils.join(null, *) = null | |
| 3700 | * StringUtils.join([], *) = "" | |
| 3701 | * StringUtils.join([null], *) = "" | |
| 3702 | * StringUtils.join([1, 2, 3], ';') = "1;2;3" | |
| 3703 | * StringUtils.join([1, 2, 3], null) = "123" | |
| 3704 | * </pre> | |
| 3705 | * | |
| 3706 | * @param array | |
| 3707 | * the array of values to join together, may be null | |
| 3708 | * @param separator | |
| 3709 | * the separator character to use | |
| 3710 | * @param startIndex | |
| 3711 | * the first index to start joining from. It is an error to pass in an end index past the end of the | |
| 3712 | * array | |
| 3713 | * @param endIndex | |
| 3714 | * the index to stop joining from (exclusive). It is an error to pass in an end index past the end of | |
| 3715 | * the array | |
| 3716 | * @return the joined String, {@code null} if null array input | |
| 3717 | * @since 3.2 | |
| 3718 | */ | |
| 3719 | public static String join(final double[] array, final char separator, final int startIndex, final int endIndex) { | |
| 3720 | 2 | if (array == null) { |
| 3721 | 0 | return null; |
| 3722 | } | |
| 3723 | 2 | final int noOfItems = endIndex - startIndex; |
| 3724 | 2 | if (noOfItems <= 0) { |
| 3725 | 0 | return EMPTY; |
| 3726 | } | |
| 3727 | 2 | final StringBuilder buf = new StringBuilder(noOfItems * 16); |
| 3728 | 5 | for (int i = startIndex; i < endIndex; i++) { |
| 3729 | 3 | if (i > startIndex) { |
| 3730 | 1 | buf.append(separator); |
| 3731 | } | |
| 3732 | 3 | buf.append(array[i]); |
| 3733 | } | |
| 3734 | 2 | return buf.toString(); |
| 3735 | } | |
| 3736 | ||
| 3737 | /** | |
| 3738 | * <p> | |
| 3739 | * Joins the elements of the provided array into a single String containing the provided list of elements. | |
| 3740 | * </p> | |
| 3741 | * | |
| 3742 | * <p> | |
| 3743 | * No delimiter is added before or after the list. Null objects or empty strings within the array are represented | |
| 3744 | * by empty strings. | |
| 3745 | * </p> | |
| 3746 | * | |
| 3747 | * <pre> | |
| 3748 | * StringUtils.join(null, *) = null | |
| 3749 | * StringUtils.join([], *) = "" | |
| 3750 | * StringUtils.join([null], *) = "" | |
| 3751 | * StringUtils.join([1, 2, 3], ';') = "1;2;3" | |
| 3752 | * StringUtils.join([1, 2, 3], null) = "123" | |
| 3753 | * </pre> | |
| 3754 | * | |
| 3755 | * @param array | |
| 3756 | * the array of values to join together, may be null | |
| 3757 | * @param separator | |
| 3758 | * the separator character to use | |
| 3759 | * @param startIndex | |
| 3760 | * the first index to start joining from. It is an error to pass in an end index past the end of the | |
| 3761 | * array | |
| 3762 | * @param endIndex | |
| 3763 | * the index to stop joining from (exclusive). It is an error to pass in an end index past the end of | |
| 3764 | * the array | |
| 3765 | * @return the joined String, {@code null} if null array input | |
| 3766 | * @since 3.2 | |
| 3767 | */ | |
| 3768 | public static String join(final float[] array, final char separator, final int startIndex, final int endIndex) { | |
| 3769 | 2 | if (array == null) { |
| 3770 | 0 | return null; |
| 3771 | } | |
| 3772 | 2 | final int noOfItems = endIndex - startIndex; |
| 3773 | 2 | if (noOfItems <= 0) { |
| 3774 | 0 | return EMPTY; |
| 3775 | } | |
| 3776 | 2 | final StringBuilder buf = new StringBuilder(noOfItems * 16); |
| 3777 | 5 | for (int i = startIndex; i < endIndex; i++) { |
| 3778 | 3 | if (i > startIndex) { |
| 3779 | 1 | buf.append(separator); |
| 3780 | } | |
| 3781 | 3 | buf.append(array[i]); |
| 3782 | } | |
| 3783 | 2 | return buf.toString(); |
| 3784 | } | |
| 3785 | ||
| 3786 | ||
| 3787 | /** | |
| 3788 | * <p>Joins the elements of the provided array into a single String | |
| 3789 | * containing the provided list of elements.</p> | |
| 3790 | * | |
| 3791 | * <p>No delimiter is added before or after the list. | |
| 3792 | * A {@code null} separator is the same as an empty String (""). | |
| 3793 | * Null objects or empty strings within the array are represented by | |
| 3794 | * empty strings.</p> | |
| 3795 | * | |
| 3796 | * <pre> | |
| 3797 | * StringUtils.join(null, *) = null | |
| 3798 | * StringUtils.join([], *) = "" | |
| 3799 | * StringUtils.join([null], *) = "" | |
| 3800 | * StringUtils.join(["a", "b", "c"], "--") = "a--b--c" | |
| 3801 | * StringUtils.join(["a", "b", "c"], null) = "abc" | |
| 3802 | * StringUtils.join(["a", "b", "c"], "") = "abc" | |
| 3803 | * StringUtils.join([null, "", "a"], ',') = ",,a" | |
| 3804 | * </pre> | |
| 3805 | * | |
| 3806 | * @param array the array of values to join together, may be null | |
| 3807 | * @param separator the separator character to use, null treated as "" | |
| 3808 | * @return the joined String, {@code null} if null array input | |
| 3809 | */ | |
| 3810 | public static String join(final Object[] array, final String separator) { | |
| 3811 | 34 | if (array == null) { |
| 3812 | 3 | return null; |
| 3813 | } | |
| 3814 | 31 | return join(array, separator, 0, array.length); |
| 3815 | } | |
| 3816 | ||
| 3817 | /** | |
| 3818 | * <p>Joins the elements of the provided array into a single String | |
| 3819 | * containing the provided list of elements.</p> | |
| 3820 | * | |
| 3821 | * <p>No delimiter is added before or after the list. | |
| 3822 | * A {@code null} separator is the same as an empty String (""). | |
| 3823 | * Null objects or empty strings within the array are represented by | |
| 3824 | * empty strings.</p> | |
| 3825 | * | |
| 3826 | * <pre> | |
| 3827 | * StringUtils.join(null, *, *, *) = null | |
| 3828 | * StringUtils.join([], *, *, *) = "" | |
| 3829 | * StringUtils.join([null], *, *, *) = "" | |
| 3830 | * StringUtils.join(["a", "b", "c"], "--", 0, 3) = "a--b--c" | |
| 3831 | * StringUtils.join(["a", "b", "c"], "--", 1, 3) = "b--c" | |
| 3832 | * StringUtils.join(["a", "b", "c"], "--", 2, 3) = "c" | |
| 3833 | * StringUtils.join(["a", "b", "c"], "--", 2, 2) = "" | |
| 3834 | * StringUtils.join(["a", "b", "c"], null, 0, 3) = "abc" | |
| 3835 | * StringUtils.join(["a", "b", "c"], "", 0, 3) = "abc" | |
| 3836 | * StringUtils.join([null, "", "a"], ',', 0, 3) = ",,a" | |
| 3837 | * </pre> | |
| 3838 | * | |
| 3839 | * @param array the array of values to join together, may be null | |
| 3840 | * @param separator the separator character to use, null treated as "" | |
| 3841 | * @param startIndex the first index to start joining from. | |
| 3842 | * @param endIndex the index to stop joining from (exclusive). | |
| 3843 | * @return the joined String, {@code null} if null array input; or the empty string | |
| 3844 | * if {@code endIndex - startIndex <= 0}. The number of joined entries is given by | |
| 3845 | * {@code endIndex - startIndex} | |
| 3846 | * @throws ArrayIndexOutOfBoundsException ife<br/> | |
| 3847 | * {@code startIndex < 0} or <br/> | |
| 3848 | * {@code startIndex >= array.length()} or <br/> | |
| 3849 | * {@code endIndex < 0} or <br/> | |
| 3850 | * {@code endIndex > array.length()} | |
| 3851 | */ | |
| 3852 | public static String join(final Object[] array, String separator, final int startIndex, final int endIndex) { | |
| 3853 | 37 | if (array == null) { |
| 3854 | 0 | return null; |
| 3855 | } | |
| 3856 | 37 | if (separator == null) { |
| 3857 | 25 | separator = EMPTY; |
| 3858 | } | |
| 3859 | ||
| 3860 | // endIndex - startIndex > 0: Len = NofStrings *(len(firstString) + len(separator)) | |
| 3861 | // (Assuming that all Strings are roughly equally long) | |
| 3862 | 37 | final int noOfItems = endIndex - startIndex; |
| 3863 | 37 | if (noOfItems <= 0) { |
| 3864 | 10 | return EMPTY; |
| 3865 | } | |
| 3866 | ||
| 3867 | 27 | final StringBuilder buf = new StringBuilder(noOfItems * 16); |
| 3868 | ||
| 3869 | 102 | for (int i = startIndex; i < endIndex; i++) { |
| 3870 | 75 | if (i > startIndex) { |
| 3871 | 48 | buf.append(separator); |
| 3872 | } | |
| 3873 | 75 | if (array[i] != null) { |
| 3874 | 66 | buf.append(array[i]); |
| 3875 | } | |
| 3876 | } | |
| 3877 | 27 | return buf.toString(); |
| 3878 | } | |
| 3879 | ||
| 3880 | /** | |
| 3881 | * <p>Joins the elements of the provided {@code Iterator} into | |
| 3882 | * a single String containing the provided elements.</p> | |
| 3883 | * | |
| 3884 | * <p>No delimiter is added before or after the list. Null objects or empty | |
| 3885 | * strings within the iteration are represented by empty strings.</p> | |
| 3886 | * | |
| 3887 | * <p>See the examples here: {@link #join(Object[],char)}. </p> | |
| 3888 | * | |
| 3889 | * @param iterator the {@code Iterator} of values to join together, may be null | |
| 3890 | * @param separator the separator character to use | |
| 3891 | * @return the joined String, {@code null} if null iterator input | |
| 3892 | * @since 2.0 | |
| 3893 | */ | |
| 3894 | public static String join(final Iterator<?> iterator, final char separator) { | |
| 3895 | ||
| 3896 | // handle null, zero and one elements before building a buffer | |
| 3897 | 9 | if (iterator == null) { |
| 3898 | 1 | return null; |
| 3899 | } | |
| 3900 | 8 | if (!iterator.hasNext()) { |
| 3901 | 2 | return EMPTY; |
| 3902 | } | |
| 3903 | 6 | final Object first = iterator.next(); |
| 3904 | 6 | if (!iterator.hasNext()) { |
| 3905 | 4 | return ObjectUtils.toString(first); |
| 3906 | } | |
| 3907 | ||
| 3908 | // two or more elements | |
| 3909 | 2 | final StringBuilder buf = new StringBuilder(256); // Java default is 16, probably too small |
| 3910 | 2 | if (first != null) { |
| 3911 | 2 | buf.append(first); |
| 3912 | } | |
| 3913 | ||
| 3914 | 6 | while (iterator.hasNext()) { |
| 3915 | 4 | buf.append(separator); |
| 3916 | 4 | final Object obj = iterator.next(); |
| 3917 | 4 | if (obj != null) { |
| 3918 | 4 | buf.append(obj); |
| 3919 | } | |
| 3920 | 4 | } |
| 3921 | ||
| 3922 | 2 | return buf.toString(); |
| 3923 | } | |
| 3924 | ||
| 3925 | /** | |
| 3926 | * <p>Joins the elements of the provided {@code Iterator} into | |
| 3927 | * a single String containing the provided elements.</p> | |
| 3928 | * | |
| 3929 | * <p>No delimiter is added before or after the list. | |
| 3930 | * A {@code null} separator is the same as an empty String ("").</p> | |
| 3931 | * | |
| 3932 | * <p>See the examples here: {@link #join(Object[],String)}. </p> | |
| 3933 | * | |
| 3934 | * @param iterator the {@code Iterator} of values to join together, may be null | |
| 3935 | * @param separator the separator character to use, null treated as "" | |
| 3936 | * @return the joined String, {@code null} if null iterator input | |
| 3937 | */ | |
| 3938 | public static String join(final Iterator<?> iterator, final String separator) { | |
| 3939 | ||
| 3940 | // handle null, zero and one elements before building a buffer | |
| 3941 | 19 | if (iterator == null) { |
| 3942 | 1 | return null; |
| 3943 | } | |
| 3944 | 18 | if (!iterator.hasNext()) { |
| 3945 | 6 | return EMPTY; |
| 3946 | } | |
| 3947 | 12 | final Object first = iterator.next(); |
| 3948 | 12 | if (!iterator.hasNext()) { |
| 3949 | 6 | return ObjectUtils.toString(first); |
| 3950 | } | |
| 3951 | ||
| 3952 | // two or more elements | |
| 3953 | 6 | final StringBuilder buf = new StringBuilder(256); // Java default is 16, probably too small |
| 3954 | 6 | if (first != null) { |
| 3955 | 6 | buf.append(first); |
| 3956 | } | |
| 3957 | ||
| 3958 | 18 | while (iterator.hasNext()) { |
| 3959 | 12 | if (separator != null) { |
| 3960 | 8 | buf.append(separator); |
| 3961 | } | |
| 3962 | 12 | final Object obj = iterator.next(); |
| 3963 | 12 | if (obj != null) { |
| 3964 | 12 | buf.append(obj); |
| 3965 | } | |
| 3966 | 12 | } |
| 3967 | 6 | return buf.toString(); |
| 3968 | } | |
| 3969 | ||
| 3970 | /** | |
| 3971 | * <p>Joins the elements of the provided {@code Iterable} into | |
| 3972 | * a single String containing the provided elements.</p> | |
| 3973 | * | |
| 3974 | * <p>No delimiter is added before or after the list. Null objects or empty | |
| 3975 | * strings within the iteration are represented by empty strings.</p> | |
| 3976 | * | |
| 3977 | * <p>See the examples here: {@link #join(Object[],char)}. </p> | |
| 3978 | * | |
| 3979 | * @param iterable the {@code Iterable} providing the values to join together, may be null | |
| 3980 | * @param separator the separator character to use | |
| 3981 | * @return the joined String, {@code null} if null iterator input | |
| 3982 | * @since 2.3 | |
| 3983 | */ | |
| 3984 | public static String join(final Iterable<?> iterable, final char separator) { | |
| 3985 | 5 | if (iterable == null) { |
| 3986 | 1 | return null; |
| 3987 | } | |
| 3988 | 4 | return join(iterable.iterator(), separator); |
| 3989 | } | |
| 3990 | ||
| 3991 | /** | |
| 3992 | * <p>Joins the elements of the provided {@code Iterable} into | |
| 3993 | * a single String containing the provided elements.</p> | |
| 3994 | * | |
| 3995 | * <p>No delimiter is added before or after the list. | |
| 3996 | * A {@code null} separator is the same as an empty String ("").</p> | |
| 3997 | * | |
| 3998 | * <p>See the examples here: {@link #join(Object[],String)}. </p> | |
| 3999 | * | |
| 4000 | * @param iterable the {@code Iterable} providing the values to join together, may be null | |
| 4001 | * @param separator the separator character to use, null treated as "" | |
| 4002 | * @return the joined String, {@code null} if null iterator input | |
| 4003 | * @since 2.3 | |
| 4004 | */ | |
| 4005 | public static String join(final Iterable<?> iterable, final String separator) { | |
| 4006 | 10 | if (iterable == null) { |
| 4007 | 1 | return null; |
| 4008 | } | |
| 4009 | 9 | return join(iterable.iterator(), separator); |
| 4010 | } | |
| 4011 | ||
| 4012 | // Delete | |
| 4013 | //----------------------------------------------------------------------- | |
| 4014 | /** | |
| 4015 | * <p>Deletes all whitespaces from a String as defined by | |
| 4016 | * {@link Character#isWhitespace(char)}.</p> | |
| 4017 | * | |
| 4018 | * <pre> | |
| 4019 | * StringUtils.deleteWhitespace(null) = null | |
| 4020 | * StringUtils.deleteWhitespace("") = "" | |
| 4021 | * StringUtils.deleteWhitespace("abc") = "abc" | |
| 4022 | * StringUtils.deleteWhitespace(" ab c ") = "abc" | |
| 4023 | * </pre> | |
| 4024 | * | |
| 4025 | * @param str the String to delete whitespace from, may be null | |
| 4026 | * @return the String without whitespaces, {@code null} if null String input | |
| 4027 | */ | |
| 4028 | public static String deleteWhitespace(final String str) { | |
| 4029 | 134 | if (isEmpty(str)) { |
| 4030 | 3 | return str; |
| 4031 | } | |
| 4032 | 131 | final int sz = str.length(); |
| 4033 | 131 | final char[] chs = new char[sz]; |
| 4034 | 131 | int count = 0; |
| 4035 | 2950 | for (int i = 0; i < sz; i++) { |
| 4036 | 2819 | if (!Character.isWhitespace(str.charAt(i))) { |
| 4037 | 2721 | chs[count++] = str.charAt(i); |
| 4038 | } | |
| 4039 | } | |
| 4040 | 131 | if (count == sz) { |
| 4041 | 123 | return str; |
| 4042 | } | |
| 4043 | 8 | return new String(chs, 0, count); |
| 4044 | } | |
| 4045 | ||
| 4046 | // Remove | |
| 4047 | //----------------------------------------------------------------------- | |
| 4048 | /** | |
| 4049 | * <p>Removes a substring only if it is at the beginning of a source string, | |
| 4050 | * otherwise returns the source string.</p> | |
| 4051 | * | |
| 4052 | * <p>A {@code null} source string will return {@code null}. | |
| 4053 | * An empty ("") source string will return the empty string. | |
| 4054 | * A {@code null} search string will return the source string.</p> | |
| 4055 | * | |
| 4056 | * <pre> | |
| 4057 | * StringUtils.removeStart(null, *) = null | |
| 4058 | * StringUtils.removeStart("", *) = "" | |
| 4059 | * StringUtils.removeStart(*, null) = * | |
| 4060 | * StringUtils.removeStart("www.domain.com", "www.") = "domain.com" | |
| 4061 | * StringUtils.removeStart("domain.com", "www.") = "domain.com" | |
| 4062 | * StringUtils.removeStart("www.domain.com", "domain") = "www.domain.com" | |
| 4063 | * StringUtils.removeStart("abc", "") = "abc" | |
| 4064 | * </pre> | |
| 4065 | * | |
| 4066 | * @param str the source String to search, may be null | |
| 4067 | * @param remove the String to search for and remove, may be null | |
| 4068 | * @return the substring with the string removed if found, | |
| 4069 | * {@code null} if null String input | |
| 4070 | * @since 2.1 | |
| 4071 | */ | |
| 4072 | public static String removeStart(final String str, final String remove) { | |
| 4073 | 10 | if (isEmpty(str) || isEmpty(remove)) { |
| 4074 | 8 | return str; |
| 4075 | } | |
| 4076 | 2 | if (str.startsWith(remove)){ |
| 4077 | 1 | return str.substring(remove.length()); |
| 4078 | } | |
| 4079 | 1 | return str; |
| 4080 | } | |
| 4081 | ||
| 4082 | /** | |
| 4083 | * <p>Case insensitive removal of a substring if it is at the beginning of a source string, | |
| 4084 | * otherwise returns the source string.</p> | |
| 4085 | * | |
| 4086 | * <p>A {@code null} source string will return {@code null}. | |
| 4087 | * An empty ("") source string will return the empty string. | |
| 4088 | * A {@code null} search string will return the source string.</p> | |
| 4089 | * | |
| 4090 | * <pre> | |
| 4091 | * StringUtils.removeStartIgnoreCase(null, *) = null | |
| 4092 | * StringUtils.removeStartIgnoreCase("", *) = "" | |
| 4093 | * StringUtils.removeStartIgnoreCase(*, null) = * | |
| 4094 | * StringUtils.removeStartIgnoreCase("www.domain.com", "www.") = "domain.com" | |
| 4095 | * StringUtils.removeStartIgnoreCase("www.domain.com", "WWW.") = "domain.com" | |
| 4096 | * StringUtils.removeStartIgnoreCase("domain.com", "www.") = "domain.com" | |
| 4097 | * StringUtils.removeStartIgnoreCase("www.domain.com", "domain") = "www.domain.com" | |
| 4098 | * StringUtils.removeStartIgnoreCase("abc", "") = "abc" | |
| 4099 | * </pre> | |
| 4100 | * | |
| 4101 | * @param str the source String to search, may be null | |
| 4102 | * @param remove the String to search for (case insensitive) and remove, may be null | |
| 4103 | * @return the substring with the string removed if found, | |
| 4104 | * {@code null} if null String input | |
| 4105 | * @since 2.4 | |
| 4106 | */ | |
| 4107 | public static String removeStartIgnoreCase(final String str, final String remove) { | |
| 4108 | 11 | if (isEmpty(str) || isEmpty(remove)) { |
| 4109 | 8 | return str; |
| 4110 | } | |
| 4111 | 3 | if (startsWithIgnoreCase(str, remove)) { |
| 4112 | 2 | return str.substring(remove.length()); |
| 4113 | } | |
| 4114 | 1 | return str; |
| 4115 | } | |
| 4116 | ||
| 4117 | /** | |
| 4118 | * <p>Removes a substring only if it is at the end of a source string, | |
| 4119 | * otherwise returns the source string.</p> | |
| 4120 | * | |
| 4121 | * <p>A {@code null} source string will return {@code null}. | |
| 4122 | * An empty ("") source string will return the empty string. | |
| 4123 | * A {@code null} search string will return the source string.</p> | |
| 4124 | * | |
| 4125 | * <pre> | |
| 4126 | * StringUtils.removeEnd(null, *) = null | |
| 4127 | * StringUtils.removeEnd("", *) = "" | |
| 4128 | * StringUtils.removeEnd(*, null) = * | |
| 4129 | * StringUtils.removeEnd("www.domain.com", ".com.") = "www.domain.com" | |
| 4130 | * StringUtils.removeEnd("www.domain.com", ".com") = "www.domain" | |
| 4131 | * StringUtils.removeEnd("www.domain.com", "domain") = "www.domain.com" | |
| 4132 | * StringUtils.removeEnd("abc", "") = "abc" | |
| 4133 | * </pre> | |
| 4134 | * | |
| 4135 | * @param str the source String to search, may be null | |
| 4136 | * @param remove the String to search for and remove, may be null | |
| 4137 | * @return the substring with the string removed if found, | |
| 4138 | * {@code null} if null String input | |
| 4139 | * @since 2.1 | |
| 4140 | */ | |
| 4141 | public static String removeEnd(final String str, final String remove) { | |
| 4142 | 29 | if (isEmpty(str) || isEmpty(remove)) { |
| 4143 | 18 | return str; |
| 4144 | } | |
| 4145 | 11 | if (str.endsWith(remove)) { |
| 4146 | 6 | return str.substring(0, str.length() - remove.length()); |
| 4147 | } | |
| 4148 | 5 | return str; |
| 4149 | } | |
| 4150 | ||
| 4151 | /** | |
| 4152 | * <p>Case insensitive removal of a substring if it is at the end of a source string, | |
| 4153 | * otherwise returns the source string.</p> | |
| 4154 | * | |
| 4155 | * <p>A {@code null} source string will return {@code null}. | |
| 4156 | * An empty ("") source string will return the empty string. | |
| 4157 | * A {@code null} search string will return the source string.</p> | |
| 4158 | * | |
| 4159 | * <pre> | |
| 4160 | * StringUtils.removeEndIgnoreCase(null, *) = null | |
| 4161 | * StringUtils.removeEndIgnoreCase("", *) = "" | |
| 4162 | * StringUtils.removeEndIgnoreCase(*, null) = * | |
| 4163 | * StringUtils.removeEndIgnoreCase("www.domain.com", ".com.") = "www.domain.com" | |
| 4164 | * StringUtils.removeEndIgnoreCase("www.domain.com", ".com") = "www.domain" | |
| 4165 | * StringUtils.removeEndIgnoreCase("www.domain.com", "domain") = "www.domain.com" | |
| 4166 | * StringUtils.removeEndIgnoreCase("abc", "") = "abc" | |
| 4167 | * StringUtils.removeEndIgnoreCase("www.domain.com", ".COM") = "www.domain") | |
| 4168 | * StringUtils.removeEndIgnoreCase("www.domain.COM", ".com") = "www.domain") | |
| 4169 | * </pre> | |
| 4170 | * | |
| 4171 | * @param str the source String to search, may be null | |
| 4172 | * @param remove the String to search for (case insensitive) and remove, may be null | |
| 4173 | * @return the substring with the string removed if found, | |
| 4174 | * {@code null} if null String input | |
| 4175 | * @since 2.4 | |
| 4176 | */ | |
| 4177 | public static String removeEndIgnoreCase(final String str, final String remove) { | |
| 4178 | 13 | if (isEmpty(str) || isEmpty(remove)) { |
| 4179 | 8 | return str; |
| 4180 | } | |
| 4181 | 5 | if (endsWithIgnoreCase(str, remove)) { |
| 4182 | 3 | return str.substring(0, str.length() - remove.length()); |
| 4183 | } | |
| 4184 | 2 | return str; |
| 4185 | } | |
| 4186 | ||
| 4187 | /** | |
| 4188 | * <p>Removes all occurrences of a substring from within the source string.</p> | |
| 4189 | * | |
| 4190 | * <p>A {@code null} source string will return {@code null}. | |
| 4191 | * An empty ("") source string will return the empty string. | |
| 4192 | * A {@code null} remove string will return the source string. | |
| 4193 | * An empty ("") remove string will return the source string.</p> | |
| 4194 | * | |
| 4195 | * <pre> | |
| 4196 | * StringUtils.remove(null, *) = null | |
| 4197 | * StringUtils.remove("", *) = "" | |
| 4198 | * StringUtils.remove(*, null) = * | |
| 4199 | * StringUtils.remove(*, "") = * | |
| 4200 | * StringUtils.remove("queued", "ue") = "qd" | |
| 4201 | * StringUtils.remove("queued", "zz") = "queued" | |
| 4202 | * </pre> | |
| 4203 | * | |
| 4204 | * @param str the source String to search, may be null | |
| 4205 | * @param remove the String to search for and remove, may be null | |
| 4206 | * @return the substring with the string removed if found, | |
| 4207 | * {@code null} if null String input | |
| 4208 | * @since 2.1 | |
| 4209 | */ | |
| 4210 | public static String remove(final String str, final String remove) { | |
| 4211 | 14 | if (isEmpty(str) || isEmpty(remove)) { |
| 4212 | 12 | return str; |
| 4213 | } | |
| 4214 | 2 | return replace(str, remove, EMPTY, -1); |
| 4215 | } | |
| 4216 | ||
| 4217 | /** | |
| 4218 | * <p>Removes all occurrences of a character from within the source string.</p> | |
| 4219 | * | |
| 4220 | * <p>A {@code null} source string will return {@code null}. | |
| 4221 | * An empty ("") source string will return the empty string.</p> | |
| 4222 | * | |
| 4223 | * <pre> | |
| 4224 | * StringUtils.remove(null, *) = null | |
| 4225 | * StringUtils.remove("", *) = "" | |
| 4226 | * StringUtils.remove("queued", 'u') = "qeed" | |
| 4227 | * StringUtils.remove("queued", 'z') = "queued" | |
| 4228 | * </pre> | |
| 4229 | * | |
| 4230 | * @param str the source String to search, may be null | |
| 4231 | * @param remove the char to search for and remove, may be null | |
| 4232 | * @return the substring with the char removed if found, | |
| 4233 | * {@code null} if null String input | |
| 4234 | * @since 2.1 | |
| 4235 | */ | |
| 4236 | public static String remove(final String str, final char remove) { | |
| 4237 | 8 | if (isEmpty(str) || str.indexOf(remove) == INDEX_NOT_FOUND) { |
| 4238 | 7 | return str; |
| 4239 | } | |
| 4240 | 1 | final char[] chars = str.toCharArray(); |
| 4241 | 1 | int pos = 0; |
| 4242 | 7 | for (int i = 0; i < chars.length; i++) { |
| 4243 | 6 | if (chars[i] != remove) { |
| 4244 | 4 | chars[pos++] = chars[i]; |
| 4245 | } | |
| 4246 | } | |
| 4247 | 1 | return new String(chars, 0, pos); |
| 4248 | } | |
| 4249 | ||
| 4250 | // Replacing | |
| 4251 | //----------------------------------------------------------------------- | |
| 4252 | /** | |
| 4253 | * <p>Replaces a String with another String inside a larger String, once.</p> | |
| 4254 | * | |
| 4255 | * <p>A {@code null} reference passed to this method is a no-op.</p> | |
| 4256 | * | |
| 4257 | * <pre> | |
| 4258 | * StringUtils.replaceOnce(null, *, *) = null | |
| 4259 | * StringUtils.replaceOnce("", *, *) = "" | |
| 4260 | * StringUtils.replaceOnce("any", null, *) = "any" | |
| 4261 | * StringUtils.replaceOnce("any", *, null) = "any" | |
| 4262 | * StringUtils.replaceOnce("any", "", *) = "any" | |
| 4263 | * StringUtils.replaceOnce("aba", "a", null) = "aba" | |
| 4264 | * StringUtils.replaceOnce("aba", "a", "") = "ba" | |
| 4265 | * StringUtils.replaceOnce("aba", "a", "z") = "zba" | |
| 4266 | * </pre> | |
| 4267 | * | |
| 4268 | * @see #replace(String text, String searchString, String replacement, int max) | |
| 4269 | * @param text text to search and replace in, may be null | |
| 4270 | * @param searchString the String to search for, may be null | |
| 4271 | * @param replacement the String to replace with, may be null | |
| 4272 | * @return the text with any replacements processed, | |
| 4273 | * {@code null} if null String input | |
| 4274 | */ | |
| 4275 | public static String replaceOnce(final String text, final String searchString, final String replacement) { | |
| 4276 | 341 | return replace(text, searchString, replacement, 1); |
| 4277 | } | |
| 4278 | ||
| 4279 | /** | |
| 4280 | * Replaces each substring of the source String that matches the given regular expression with the given | |
| 4281 | * replacement using the {@link Pattern#DOTALL} option. DOTALL is also know as single-line mode in Perl. This call | |
| 4282 | * is also equivalent to: | |
| 4283 | * <ul> | |
| 4284 | * <li>{@code source.replaceAll("(?s)" + regex, replacement)}</li> | |
| 4285 | * <li>{@code Pattern.compile(regex, Pattern.DOTALL).matcher(source).replaceAll(replacement)}</li> | |
| 4286 | * </ul> | |
| 4287 | * | |
| 4288 | * @param source | |
| 4289 | * the source string | |
| 4290 | * @param regex | |
| 4291 | * the regular expression to which this string is to be matched | |
| 4292 | * @param replacement | |
| 4293 | * the string to be substituted for each match | |
| 4294 | * @return The resulting {@code String} | |
| 4295 | * @see String#replaceAll(String, String) | |
| 4296 | * @see Pattern#DOTALL | |
| 4297 | * @since 3.2 | |
| 4298 | */ | |
| 4299 | public static String replacePattern(final String source, final String regex, final String replacement) { | |
| 4300 | 2 | return Pattern.compile(regex, Pattern.DOTALL).matcher(source).replaceAll(replacement); |
| 4301 | } | |
| 4302 | ||
| 4303 | /** | |
| 4304 | * Removes each substring of the source String that matches the given regular expression using the DOTALL option. | |
| 4305 | * | |
| 4306 | * @param source | |
| 4307 | * the source string | |
| 4308 | * @param regex | |
| 4309 | * the regular expression to which this string is to be matched | |
| 4310 | * @return The resulting {@code String} | |
| 4311 | * @see String#replaceAll(String, String) | |
| 4312 | * @see Pattern#DOTALL | |
| 4313 | * @since 3.2 | |
| 4314 | */ | |
| 4315 | public static String removePattern(final String source, final String regex) { | |
| 4316 | 1 | return replacePattern(source, regex, StringUtils.EMPTY); |
| 4317 | } | |
| 4318 | ||
| 4319 | /** | |
| 4320 | * <p>Replaces all occurrences of a String within another String.</p> | |
| 4321 | * | |
| 4322 | * <p>A {@code null} reference passed to this method is a no-op.</p> | |
| 4323 | * | |
| 4324 | * <pre> | |
| 4325 | * StringUtils.replace(null, *, *) = null | |
| 4326 | * StringUtils.replace("", *, *) = "" | |
| 4327 | * StringUtils.replace("any", null, *) = "any" | |
| 4328 | * StringUtils.replace("any", *, null) = "any" | |
| 4329 | * StringUtils.replace("any", "", *) = "any" | |
| 4330 | * StringUtils.replace("aba", "a", null) = "aba" | |
| 4331 | * StringUtils.replace("aba", "a", "") = "b" | |
| 4332 | * StringUtils.replace("aba", "a", "z") = "zbz" | |
| 4333 | * </pre> | |
| 4334 | * | |
| 4335 | * @see #replace(String text, String searchString, String replacement, int max) | |
| 4336 | * @param text text to search and replace in, may be null | |
| 4337 | * @param searchString the String to search for, may be null | |
| 4338 | * @param replacement the String to replace it with, may be null | |
| 4339 | * @return the text with any replacements processed, | |
| 4340 | * {@code null} if null String input | |
| 4341 | */ | |
| 4342 | public static String replace(final String text, final String searchString, final String replacement) { | |
| 4343 | 31 | return replace(text, searchString, replacement, -1); |
| 4344 | } | |
| 4345 | ||
| 4346 | /** | |
| 4347 | * <p>Replaces a String with another String inside a larger String, | |
| 4348 | * for the first {@code max} values of the search String.</p> | |
| 4349 | * | |
| 4350 | * <p>A {@code null} reference passed to this method is a no-op.</p> | |
| 4351 | * | |
| 4352 | * <pre> | |
| 4353 | * StringUtils.replace(null, *, *, *) = null | |
| 4354 | * StringUtils.replace("", *, *, *) = "" | |
| 4355 | * StringUtils.replace("any", null, *, *) = "any" | |
| 4356 | * StringUtils.replace("any", *, null, *) = "any" | |
| 4357 | * StringUtils.replace("any", "", *, *) = "any" | |
| 4358 | * StringUtils.replace("any", *, *, 0) = "any" | |
| 4359 | * StringUtils.replace("abaa", "a", null, -1) = "abaa" | |
| 4360 | * StringUtils.replace("abaa", "a", "", -1) = "b" | |
| 4361 | * StringUtils.replace("abaa", "a", "z", 0) = "abaa" | |
| 4362 | * StringUtils.replace("abaa", "a", "z", 1) = "zbaa" | |
| 4363 | * StringUtils.replace("abaa", "a", "z", 2) = "zbza" | |
| 4364 | * StringUtils.replace("abaa", "a", "z", -1) = "zbzz" | |
| 4365 | * </pre> | |
| 4366 | * | |
| 4367 | * @param text text to search and replace in, may be null | |
| 4368 | * @param searchString the String to search for, may be null | |
| 4369 | * @param replacement the String to replace it with, may be null | |
| 4370 | * @param max maximum number of values to replace, or {@code -1} if no maximum | |
| 4371 | * @return the text with any replacements processed, | |
| 4372 | * {@code null} if null String input | |
| 4373 | */ | |
| 4374 | public static String replace(final String text, final String searchString, final String replacement, int max) { | |
| 4375 | 391 | if (isEmpty(text) || isEmpty(searchString) || replacement == null || max == 0) { |
| 4376 | 33 | return text; |
| 4377 | } | |
| 4378 | 358 | int start = 0; |
| 4379 | 358 | int end = text.indexOf(searchString, start); |
| 4380 | 358 | if (end == INDEX_NOT_FOUND) { |
| 4381 | 281 | return text; |
| 4382 | } | |
| 4383 | 77 | final int replLength = searchString.length(); |
| 4384 | 77 | int increase = replacement.length() - replLength; |
| 4385 | 77 | increase = increase < 0 ? 0 : increase; |
| 4386 | 77 | increase *= max < 0 ? 16 : max > 64 ? 64 : max; |
| 4387 | 77 | final StringBuilder buf = new StringBuilder(text.length() + increase); |
| 4388 | 110 | while (end != INDEX_NOT_FOUND) { |
| 4389 | 99 | buf.append(text.substring(start, end)).append(replacement); |
| 4390 | 99 | start = end + replLength; |
| 4391 | 99 | if (--max == 0) { |
| 4392 | 66 | break; |
| 4393 | } | |
| 4394 | 33 | end = text.indexOf(searchString, start); |
| 4395 | } | |
| 4396 | 77 | buf.append(text.substring(start)); |
| 4397 | 77 | return buf.toString(); |
| 4398 | } | |
| 4399 | ||
| 4400 | /** | |
| 4401 | * <p> | |
| 4402 | * Replaces all occurrences of Strings within another String. | |
| 4403 | * </p> | |
| 4404 | * | |
| 4405 | * <p> | |
| 4406 | * A {@code null} reference passed to this method is a no-op, or if | |
| 4407 | * any "search string" or "string to replace" is null, that replace will be | |
| 4408 | * ignored. This will not repeat. For repeating replaces, call the | |
| 4409 | * overloaded method. | |
| 4410 | * </p> | |
| 4411 | * | |
| 4412 | * <pre> | |
| 4413 | * StringUtils.replaceEach(null, *, *) = null | |
| 4414 | * StringUtils.replaceEach("", *, *) = "" | |
| 4415 | * StringUtils.replaceEach("aba", null, null) = "aba" | |
| 4416 | * StringUtils.replaceEach("aba", new String[0], null) = "aba" | |
| 4417 | * StringUtils.replaceEach("aba", null, new String[0]) = "aba" | |
| 4418 | * StringUtils.replaceEach("aba", new String[]{"a"}, null) = "aba" | |
| 4419 | * StringUtils.replaceEach("aba", new String[]{"a"}, new String[]{""}) = "b" | |
| 4420 | * StringUtils.replaceEach("aba", new String[]{null}, new String[]{"a"}) = "aba" | |
| 4421 | * StringUtils.replaceEach("abcde", new String[]{"ab", "d"}, new String[]{"w", "t"}) = "wcte" | |
| 4422 | * (example of how it does not repeat) | |
| 4423 | * StringUtils.replaceEach("abcde", new String[]{"ab", "d"}, new String[]{"d", "t"}) = "dcte" | |
| 4424 | * </pre> | |
| 4425 | * | |
| 4426 | * @param text | |
| 4427 | * text to search and replace in, no-op if null | |
| 4428 | * @param searchList | |
| 4429 | * the Strings to search for, no-op if null | |
| 4430 | * @param replacementList | |
| 4431 | * the Strings to replace them with, no-op if null | |
| 4432 | * @return the text with any replacements processed, {@code null} if | |
| 4433 | * null String input | |
| 4434 | * @throws IllegalArgumentException | |
| 4435 | * if the lengths of the arrays are not the same (null is ok, | |
| 4436 | * and/or size 0) | |
| 4437 | * @since 2.4 | |
| 4438 | */ | |
| 4439 | public static String replaceEach(final String text, final String[] searchList, final String[] replacementList) { | |
| 4440 | 14 | return replaceEach(text, searchList, replacementList, false, 0); |
| 4441 | } | |
| 4442 | ||
| 4443 | /** | |
| 4444 | * <p> | |
| 4445 | * Replaces all occurrences of Strings within another String. | |
| 4446 | * </p> | |
| 4447 | * | |
| 4448 | * <p> | |
| 4449 | * A {@code null} reference passed to this method is a no-op, or if | |
| 4450 | * any "search string" or "string to replace" is null, that replace will be | |
| 4451 | * ignored. | |
| 4452 | * </p> | |
| 4453 | * | |
| 4454 | * <pre> | |
| 4455 | * StringUtils.replaceEach(null, *, *, *) = null | |
| 4456 | * StringUtils.replaceEach("", *, *, *) = "" | |
| 4457 | * StringUtils.replaceEach("aba", null, null, *) = "aba" | |
| 4458 | * StringUtils.replaceEach("aba", new String[0], null, *) = "aba" | |
| 4459 | * StringUtils.replaceEach("aba", null, new String[0], *) = "aba" | |
| 4460 | * StringUtils.replaceEach("aba", new String[]{"a"}, null, *) = "aba" | |
| 4461 | * StringUtils.replaceEach("aba", new String[]{"a"}, new String[]{""}, *) = "b" | |
| 4462 | * StringUtils.replaceEach("aba", new String[]{null}, new String[]{"a"}, *) = "aba" | |
| 4463 | * StringUtils.replaceEach("abcde", new String[]{"ab", "d"}, new String[]{"w", "t"}, *) = "wcte" | |
| 4464 | * (example of how it repeats) | |
| 4465 | * StringUtils.replaceEach("abcde", new String[]{"ab", "d"}, new String[]{"d", "t"}, false) = "dcte" | |
| 4466 | * StringUtils.replaceEach("abcde", new String[]{"ab", "d"}, new String[]{"d", "t"}, true) = "tcte" | |
| 4467 | * StringUtils.replaceEach("abcde", new String[]{"ab", "d"}, new String[]{"d", "ab"}, true) = IllegalStateException | |
| 4468 | * StringUtils.replaceEach("abcde", new String[]{"ab", "d"}, new String[]{"d", "ab"}, false) = "dcabe" | |
| 4469 | * </pre> | |
| 4470 | * | |
| 4471 | * @param text | |
| 4472 | * text to search and replace in, no-op if null | |
| 4473 | * @param searchList | |
| 4474 | * the Strings to search for, no-op if null | |
| 4475 | * @param replacementList | |
| 4476 | * the Strings to replace them with, no-op if null | |
| 4477 | * @return the text with any replacements processed, {@code null} if | |
| 4478 | * null String input | |
| 4479 | * @throws IllegalStateException | |
| 4480 | * if the search is repeating and there is an endless loop due | |
| 4481 | * to outputs of one being inputs to another | |
| 4482 | * @throws IllegalArgumentException | |
| 4483 | * if the lengths of the arrays are not the same (null is ok, | |
| 4484 | * and/or size 0) | |
| 4485 | * @since 2.4 | |
| 4486 | */ | |
| 4487 | public static String replaceEachRepeatedly(final String text, final String[] searchList, final String[] replacementList) { | |
| 4488 | // timeToLive should be 0 if not used or nothing to replace, else it's | |
| 4489 | // the length of the replace array | |
| 4490 | 11 | final int timeToLive = searchList == null ? 0 : searchList.length; |
| 4491 | 11 | return replaceEach(text, searchList, replacementList, true, timeToLive); |
| 4492 | } | |
| 4493 | ||
| 4494 | /** | |
| 4495 | * <p> | |
| 4496 | * Replaces all occurrences of Strings within another String. | |
| 4497 | * </p> | |
| 4498 | * | |
| 4499 | * <p> | |
| 4500 | * A {@code null} reference passed to this method is a no-op, or if | |
| 4501 | * any "search string" or "string to replace" is null, that replace will be | |
| 4502 | * ignored. | |
| 4503 | * </p> | |
| 4504 | * | |
| 4505 | * <pre> | |
| 4506 | * StringUtils.replaceEach(null, *, *, *) = null | |
| 4507 | * StringUtils.replaceEach("", *, *, *) = "" | |
| 4508 | * StringUtils.replaceEach("aba", null, null, *) = "aba" | |
| 4509 | * StringUtils.replaceEach("aba", new String[0], null, *) = "aba" | |
| 4510 | * StringUtils.replaceEach("aba", null, new String[0], *) = "aba" | |
| 4511 | * StringUtils.replaceEach("aba", new String[]{"a"}, null, *) = "aba" | |
| 4512 | * StringUtils.replaceEach("aba", new String[]{"a"}, new String[]{""}, *) = "b" | |
| 4513 | * StringUtils.replaceEach("aba", new String[]{null}, new String[]{"a"}, *) = "aba" | |
| 4514 | * StringUtils.replaceEach("abcde", new String[]{"ab", "d"}, new String[]{"w", "t"}, *) = "wcte" | |
| 4515 | * (example of how it repeats) | |
| 4516 | * StringUtils.replaceEach("abcde", new String[]{"ab", "d"}, new String[]{"d", "t"}, false) = "dcte" | |
| 4517 | * StringUtils.replaceEach("abcde", new String[]{"ab", "d"}, new String[]{"d", "t"}, true) = "tcte" | |
| 4518 | * StringUtils.replaceEach("abcde", new String[]{"ab", "d"}, new String[]{"d", "ab"}, *) = IllegalStateException | |
| 4519 | * </pre> | |
| 4520 | * | |
| 4521 | * @param text | |
| 4522 | * text to search and replace in, no-op if null | |
| 4523 | * @param searchList | |
| 4524 | * the Strings to search for, no-op if null | |
| 4525 | * @param replacementList | |
| 4526 | * the Strings to replace them with, no-op if null | |
| 4527 | * @param repeat if true, then replace repeatedly | |
| 4528 | * until there are no more possible replacements or timeToLive < 0 | |
| 4529 | * @param timeToLive | |
| 4530 | * if less than 0 then there is a circular reference and endless | |
| 4531 | * loop | |
| 4532 | * @return the text with any replacements processed, {@code null} if | |
| 4533 | * null String input | |
| 4534 | * @throws IllegalStateException | |
| 4535 | * if the search is repeating and there is an endless loop due | |
| 4536 | * to outputs of one being inputs to another | |
| 4537 | * @throws IllegalArgumentException | |
| 4538 | * if the lengths of the arrays are not the same (null is ok, | |
| 4539 | * and/or size 0) | |
| 4540 | * @since 2.4 | |
| 4541 | */ | |
| 4542 | private static String replaceEach( | |
| 4543 | final String text, final String[] searchList, final String[] replacementList, final boolean repeat, final int timeToLive) { | |
| 4544 | ||
| 4545 | // mchyzer Performance note: This creates very few new objects (one major goal) | |
| 4546 | // let me know if there are performance requests, we can create a harness to measure | |
| 4547 | ||
| 4548 | 32 | if (text == null || text.length() == 0 || searchList == null || |
| 4549 | searchList.length == 0 || replacementList == null || replacementList.length == 0) { | |
| 4550 | 12 | return text; |
| 4551 | } | |
| 4552 | ||
| 4553 | // if recursing, this shouldn't be less than 0 | |
| 4554 | 20 | if (timeToLive < 0) { |
| 4555 | 1 | throw new IllegalStateException("Aborting to protect against StackOverflowError - " + |
| 4556 | "output of one loop is the input of another"); | |
| 4557 | } | |
| 4558 | ||
| 4559 | 19 | final int searchLength = searchList.length; |
| 4560 | 19 | final int replacementLength = replacementList.length; |
| 4561 | ||
| 4562 | // make sure lengths are ok, these need to be equal | |
| 4563 | 19 | if (searchLength != replacementLength) { |
| 4564 | 0 | throw new IllegalArgumentException("Search and Replace array lengths don't match: " |
| 4565 | + searchLength | |
| 4566 | + " vs " | |
| 4567 | + replacementLength); | |
| 4568 | } | |
| 4569 | ||
| 4570 | // keep track of which still have matches | |
| 4571 | 19 | final boolean[] noMoreMatchesForReplIndex = new boolean[searchLength]; |
| 4572 | ||
| 4573 | // index on index that the match was found | |
| 4574 | 19 | int textIndex = -1; |
| 4575 | 19 | int replaceIndex = -1; |
| 4576 | 19 | int tempIndex = -1; |
| 4577 | ||
| 4578 | // index of replace array that will replace the search string found | |
| 4579 | // NOTE: logic duplicated below START | |
| 4580 | 110 | for (int i = 0; i < searchLength; i++) { |
| 4581 | 91 | if (noMoreMatchesForReplIndex[i] || searchList[i] == null || |
| 4582 | searchList[i].length() == 0 || replacementList[i] == null) { | |
| 4583 | 2 | continue; |
| 4584 | } | |
| 4585 | 87 | tempIndex = text.indexOf(searchList[i]); |
| 4586 | ||
| 4587 | // see if we need to keep searching for this | |
| 4588 | 87 | if (tempIndex == -1) { |
| 4589 | 59 | noMoreMatchesForReplIndex[i] = true; |
| 4590 | } else { | |
| 4591 | 28 | if (textIndex == -1 || tempIndex < textIndex) { |
| 4592 | 14 | textIndex = tempIndex; |
| 4593 | 14 | replaceIndex = i; |
| 4594 | } | |
| 4595 | } | |
| 4596 | } | |
| 4597 | // NOTE: logic mostly below END | |
| 4598 | ||
| 4599 | // no search strings found, we are done | |
| 4600 | 19 | if (textIndex == -1) { |
| 4601 | 6 | return text; |
| 4602 | } | |
| 4603 | ||
| 4604 | 13 | int start = 0; |
| 4605 | ||
| 4606 | // get a good guess on the size of the result buffer so it doesn't have to double if it goes over a bit | |
| 4607 | 13 | int increase = 0; |
| 4608 | ||
| 4609 | // count the replacement text elements that are larger than their corresponding text being replaced | |
| 4610 | 96 | for (int i = 0; i < searchList.length; i++) { |
| 4611 | 83 | if (searchList[i] == null || replacementList[i] == null) { |
| 4612 | 1 | continue; |
| 4613 | } | |
| 4614 | 82 | final int greater = replacementList[i].length() - searchList[i].length(); |
| 4615 | 82 | if (greater > 0) { |
| 4616 | 3 | increase += 3 * greater; // assume 3 matches |
| 4617 | } | |
| 4618 | } | |
| 4619 | // have upper-bound at 20% increase, then let Java take over | |
| 4620 | 13 | increase = Math.min(increase, text.length() / 5); |
| 4621 | ||
| 4622 | 13 | final StringBuilder buf = new StringBuilder(text.length() + increase); |
| 4623 | ||
| 4624 | 46 | while (textIndex != -1) { |
| 4625 | ||
| 4626 | 45 | for (int i = start; i < textIndex; i++) { |
| 4627 | 12 | buf.append(text.charAt(i)); |
| 4628 | } | |
| 4629 | 33 | buf.append(replacementList[replaceIndex]); |
| 4630 | ||
| 4631 | 33 | start = textIndex + searchList[replaceIndex].length(); |
| 4632 | ||
| 4633 | 33 | textIndex = -1; |
| 4634 | 33 | replaceIndex = -1; |
| 4635 | 33 | tempIndex = -1; |
| 4636 | // find the next earliest match | |
| 4637 | // NOTE: logic mostly duplicated above START | |
| 4638 | 685 | for (int i = 0; i < searchLength; i++) { |
| 4639 | 652 | if (noMoreMatchesForReplIndex[i] || searchList[i] == null || |
| 4640 | searchList[i].length() == 0 || replacementList[i] == null) { | |
| 4641 | 2 | continue; |
| 4642 | } | |
| 4643 | 81 | tempIndex = text.indexOf(searchList[i], start); |
| 4644 | ||
| 4645 | // see if we need to keep searching for this | |
| 4646 | 81 | if (tempIndex == -1) { |
| 4647 | 28 | noMoreMatchesForReplIndex[i] = true; |
| 4648 | } else { | |
| 4649 | 53 | if (textIndex == -1 || tempIndex < textIndex) { |
| 4650 | 34 | textIndex = tempIndex; |
| 4651 | 34 | replaceIndex = i; |
| 4652 | } | |
| 4653 | } | |
| 4654 | } | |
| 4655 | // NOTE: logic duplicated above END | |
| 4656 | ||
| 4657 | } | |
| 4658 | 13 | final int textLength = text.length(); |
| 4659 | 24 | for (int i = start; i < textLength; i++) { |
| 4660 | 11 | buf.append(text.charAt(i)); |
| 4661 | } | |
| 4662 | 13 | final String result = buf.toString(); |
| 4663 | 13 | if (!repeat) { |
| 4664 | 6 | return result; |
| 4665 | } | |
| 4666 | ||
| 4667 | 7 | return replaceEach(result, searchList, replacementList, repeat, timeToLive - 1); |
| 4668 | } | |
| 4669 | ||
| 4670 | // Replace, character based | |
| 4671 | //----------------------------------------------------------------------- | |
| 4672 | /** | |
| 4673 | * <p>Replaces all occurrences of a character in a String with another. | |
| 4674 | * This is a null-safe version of {@link String#replace(char, char)}.</p> | |
| 4675 | * | |
| 4676 | * <p>A {@code null} string input returns {@code null}. | |
| 4677 | * An empty ("") string input returns an empty string.</p> | |
| 4678 | * | |
| 4679 | * <pre> | |
| 4680 | * StringUtils.replaceChars(null, *, *) = null | |
| 4681 | * StringUtils.replaceChars("", *, *) = "" | |
| 4682 | * StringUtils.replaceChars("abcba", 'b', 'y') = "aycya" | |
| 4683 | * StringUtils.replaceChars("abcba", 'z', 'y') = "abcba" | |
| 4684 | * </pre> | |
| 4685 | * | |
| 4686 | * @param str String to replace characters in, may be null | |
| 4687 | * @param searchChar the character to search for, may be null | |
| 4688 | * @param replaceChar the character to replace, may be null | |
| 4689 | * @return modified String, {@code null} if null string input | |
| 4690 | * @since 2.0 | |
| 4691 | */ | |
| 4692 | public static String replaceChars(final String str, final char searchChar, final char replaceChar) { | |
| 4693 | 6 | if (str == null) { |
| 4694 | 1 | return null; |
| 4695 | } | |
| 4696 | 5 | return str.replace(searchChar, replaceChar); |
| 4697 | } | |
| 4698 | ||
| 4699 | /** | |
| 4700 | * <p>Replaces multiple characters in a String in one go. | |
| 4701 | * This method can also be used to delete characters.</p> | |
| 4702 | * | |
| 4703 | * <p>For example:<br /> | |
| 4704 | * <code>replaceChars("hello", "ho", "jy") = jelly</code>.</p> | |
| 4705 | * | |
| 4706 | * <p>A {@code null} string input returns {@code null}. | |
| 4707 | * An empty ("") string input returns an empty string. | |
| 4708 | * A null or empty set of search characters returns the input string.</p> | |
| 4709 | * | |
| 4710 | * <p>The length of the search characters should normally equal the length | |
| 4711 | * of the replace characters. | |
| 4712 | * If the search characters is longer, then the extra search characters | |
| 4713 | * are deleted. | |
| 4714 | * If the search characters is shorter, then the extra replace characters | |
| 4715 | * are ignored.</p> | |
| 4716 | * | |
| 4717 | * <pre> | |
| 4718 | * StringUtils.replaceChars(null, *, *) = null | |
| 4719 | * StringUtils.replaceChars("", *, *) = "" | |
| 4720 | * StringUtils.replaceChars("abc", null, *) = "abc" | |
| 4721 | * StringUtils.replaceChars("abc", "", *) = "abc" | |
| 4722 | * StringUtils.replaceChars("abc", "b", null) = "ac" | |
| 4723 | * StringUtils.replaceChars("abc", "b", "") = "ac" | |
| 4724 | * StringUtils.replaceChars("abcba", "bc", "yz") = "ayzya" | |
| 4725 | * StringUtils.replaceChars("abcba", "bc", "y") = "ayya" | |
| 4726 | * StringUtils.replaceChars("abcba", "bc", "yzx") = "ayzya" | |
| 4727 | * </pre> | |
| 4728 | * | |
| 4729 | * @param str String to replace characters in, may be null | |
| 4730 | * @param searchChars a set of characters to search for, may be null | |
| 4731 | * @param replaceChars a set of characters to replace, may be null | |
| 4732 | * @return modified String, {@code null} if null string input | |
| 4733 | * @since 2.0 | |
| 4734 | */ | |
| 4735 | public static String replaceChars(final String str, final String searchChars, String replaceChars) { | |
| 4736 | 30 | if (isEmpty(str) || isEmpty(searchChars)) { |
| 4737 | 16 | return str; |
| 4738 | } | |
| 4739 | 14 | if (replaceChars == null) { |
| 4740 | 1 | replaceChars = EMPTY; |
| 4741 | } | |
| 4742 | 14 | boolean modified = false; |
| 4743 | 14 | final int replaceCharsLength = replaceChars.length(); |
| 4744 | 14 | final int strLength = str.length(); |
| 4745 | 14 | final StringBuilder buf = new StringBuilder(strLength); |
| 4746 | 83 | for (int i = 0; i < strLength; i++) { |
| 4747 | 69 | final char ch = str.charAt(i); |
| 4748 | 69 | final int index = searchChars.indexOf(ch); |
| 4749 | 69 | if (index >= 0) { |
| 4750 | 35 | modified = true; |
| 4751 | 35 | if (index < replaceCharsLength) { |
| 4752 | 31 | buf.append(replaceChars.charAt(index)); |
| 4753 | } | |
| 4754 | } else { | |
| 4755 | 34 | buf.append(ch); |
| 4756 | } | |
| 4757 | } | |
| 4758 | 14 | if (modified) { |
| 4759 | 12 | return buf.toString(); |
| 4760 | } | |
| 4761 | 2 | return str; |
| 4762 | } | |
| 4763 | ||
| 4764 | // Overlay | |
| 4765 | //----------------------------------------------------------------------- | |
| 4766 | /** | |
| 4767 | * <p>Overlays part of a String with another String.</p> | |
| 4768 | * | |
| 4769 | * <p>A {@code null} string input returns {@code null}. | |
| 4770 | * A negative index is treated as zero. | |
| 4771 | * An index greater than the string length is treated as the string length. | |
| 4772 | * The start index is always the smaller of the two indices.</p> | |
| 4773 | * | |
| 4774 | * <pre> | |
| 4775 | * StringUtils.overlay(null, *, *, *) = null | |
| 4776 | * StringUtils.overlay("", "abc", 0, 0) = "abc" | |
| 4777 | * StringUtils.overlay("abcdef", null, 2, 4) = "abef" | |
| 4778 | * StringUtils.overlay("abcdef", "", 2, 4) = "abef" | |
| 4779 | * StringUtils.overlay("abcdef", "", 4, 2) = "abef" | |
| 4780 | * StringUtils.overlay("abcdef", "zzzz", 2, 4) = "abzzzzef" | |
| 4781 | * StringUtils.overlay("abcdef", "zzzz", 4, 2) = "abzzzzef" | |
| 4782 | * StringUtils.overlay("abcdef", "zzzz", -1, 4) = "zzzzef" | |
| 4783 | * StringUtils.overlay("abcdef", "zzzz", 2, 8) = "abzzzz" | |
| 4784 | * StringUtils.overlay("abcdef", "zzzz", -2, -3) = "zzzzabcdef" | |
| 4785 | * StringUtils.overlay("abcdef", "zzzz", 8, 10) = "abcdefzzzz" | |
| 4786 | * </pre> | |
| 4787 | * | |
| 4788 | * @param str the String to do overlaying in, may be null | |
| 4789 | * @param overlay the String to overlay, may be null | |
| 4790 | * @param start the position to start overlaying at | |
| 4791 | * @param end the position to stop overlaying before | |
| 4792 | * @return overlayed String, {@code null} if null String input | |
| 4793 | * @since 2.0 | |
| 4794 | */ | |
| 4795 | public static String overlay(final String str, String overlay, int start, int end) { | |
| 4796 | 21 | if (str == null) { |
| 4797 | 2 | return null; |
| 4798 | } | |
| 4799 | 19 | if (overlay == null) { |
| 4800 | 3 | overlay = EMPTY; |
| 4801 | } | |
| 4802 | 19 | final int len = str.length(); |
| 4803 | 19 | if (start < 0) { |
| 4804 | 4 | start = 0; |
| 4805 | } | |
| 4806 | 19 | if (start > len) { |
| 4807 | 4 | start = len; |
| 4808 | } | |
| 4809 | 19 | if (end < 0) { |
| 4810 | 4 | end = 0; |
| 4811 | } | |
| 4812 | 19 | if (end > len) { |
| 4813 | 4 | end = len; |
| 4814 | } | |
| 4815 | 19 | if (start > end) { |
| 4816 | 5 | final int temp = start; |
| 4817 | 5 | start = end; |
| 4818 | 5 | end = temp; |
| 4819 | } | |
| 4820 | 19 | return new StringBuilder(len + start - end + overlay.length() + 1) |
| 4821 | .append(str.substring(0, start)) | |
| 4822 | .append(overlay) | |
| 4823 | .append(str.substring(end)) | |
| 4824 | .toString(); | |
| 4825 | } | |
| 4826 | ||
| 4827 | // Chomping | |
| 4828 | //----------------------------------------------------------------------- | |
| 4829 | /** | |
| 4830 | * <p>Removes one newline from end of a String if it's there, | |
| 4831 | * otherwise leave it alone. A newline is "{@code \n}", | |
| 4832 | * "{@code \r}", or "{@code \r\n}".</p> | |
| 4833 | * | |
| 4834 | * <p>NOTE: This method changed in 2.0. | |
| 4835 | * It now more closely matches Perl chomp.</p> | |
| 4836 | * | |
| 4837 | * <pre> | |
| 4838 | * StringUtils.chomp(null) = null | |
| 4839 | * StringUtils.chomp("") = "" | |
| 4840 | * StringUtils.chomp("abc \r") = "abc " | |
| 4841 | * StringUtils.chomp("abc\n") = "abc" | |
| 4842 | * StringUtils.chomp("abc\r\n") = "abc" | |
| 4843 | * StringUtils.chomp("abc\r\n\r\n") = "abc\r\n" | |
| 4844 | * StringUtils.chomp("abc\n\r") = "abc\n" | |
| 4845 | * StringUtils.chomp("abc\n\rabc") = "abc\n\rabc" | |
| 4846 | * StringUtils.chomp("\r") = "" | |
| 4847 | * StringUtils.chomp("\n") = "" | |
| 4848 | * StringUtils.chomp("\r\n") = "" | |
| 4849 | * </pre> | |
| 4850 | * | |
| 4851 | * @param str the String to chomp a newline from, may be null | |
| 4852 | * @return String without newline, {@code null} if null String input | |
| 4853 | */ | |
| 4854 | public static String chomp(final String str) { | |
| 4855 | 16 | if (isEmpty(str)) { |
| 4856 | 2 | return str; |
| 4857 | } | |
| 4858 | ||
| 4859 | 14 | if (str.length() == 1) { |
| 4860 | 3 | final char ch = str.charAt(0); |
| 4861 | 3 | if (ch == CharUtils.CR || ch == CharUtils.LF) { |
| 4862 | 2 | return EMPTY; |
| 4863 | } | |
| 4864 | 1 | return str; |
| 4865 | } | |
| 4866 | ||
| 4867 | 11 | int lastIdx = str.length() - 1; |
| 4868 | 11 | final char last = str.charAt(lastIdx); |
| 4869 | ||
| 4870 | 11 | if (last == CharUtils.LF) { |
| 4871 | 5 | if (str.charAt(lastIdx - 1) == CharUtils.CR) { |
| 4872 | 3 | lastIdx--; |
| 4873 | } | |
| 4874 | 6 | } else if (last != CharUtils.CR) { |
| 4875 | 3 | lastIdx++; |
| 4876 | } | |
| 4877 | 11 | return str.substring(0, lastIdx); |
| 4878 | } | |
| 4879 | ||
| 4880 | /** | |
| 4881 | * <p>Removes {@code separator} from the end of | |
| 4882 | * {@code str} if it's there, otherwise leave it alone.</p> | |
| 4883 | * | |
| 4884 | * <p>NOTE: This method changed in version 2.0. | |
| 4885 | * It now more closely matches Perl chomp. | |
| 4886 | * For the previous behavior, use {@link #substringBeforeLast(String, String)}. | |
| 4887 | * This method uses {@link String#endsWith(String)}.</p> | |
| 4888 | * | |
| 4889 | * <pre> | |
| 4890 |