001/** 002 * Licensed to the Apache Software Foundation (ASF) under one or more 003 * contributor license agreements. See the NOTICE file distributed with 004 * this work for additional information regarding copyright ownership. 005 * The ASF licenses this file to You under the Apache License, Version 2.0 006 * (the "License"); you may not use this file except in compliance with 007 * the License. You may obtain a copy of the License at 008 * 009 * http://www.apache.org/licenses/LICENSE-2.0 010 * 011 * Unless required by applicable law or agreed to in writing, software 012 * distributed under the License is distributed on an "AS IS" BASIS, 013 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 014 * See the License for the specific language governing permissions and 015 * limitations under the License. 016 */ 017package org.apache.camel.util; 018 019import java.util.ArrayList; 020import java.util.Collections; 021import java.util.List; 022import java.util.Locale; 023import java.util.Objects; 024import java.util.Optional; 025import java.util.function.Function; 026import java.util.regex.Matcher; 027import java.util.regex.Pattern; 028 029/** 030 * Helper methods for working with Strings. 031 */ 032public final class StringHelper { 033 034 /** 035 * Constructor of utility class should be private. 036 */ 037 private StringHelper() { 038 } 039 040 /** 041 * Ensures that <code>s</code> is friendly for a URL or file system. 042 * 043 * @param s String to be sanitized. 044 * @return sanitized version of <code>s</code>. 045 * @throws NullPointerException if <code>s</code> is <code>null</code>. 046 */ 047 public static String sanitize(String s) { 048 return s 049 .replace(':', '-') 050 .replace('_', '-') 051 .replace('.', '-') 052 .replace('/', '-') 053 .replace('\\', '-'); 054 } 055 056 /** 057 * Remove carriage return and line feeds from a String, replacing them with an empty String. 058 * @param s String to be sanitized of carriage return / line feed characters 059 * @return sanitized version of <code>s</code>. 060 * @throws NullPointerException if <code>s</code> is <code>null</code>. 061 */ 062 public static String removeCRLF(String s) { 063 return s 064 .replaceAll("\r", "") 065 .replaceAll("\n", ""); 066 } 067 068 /** 069 * Counts the number of times the given char is in the string 070 * 071 * @param s the string 072 * @param ch the char 073 * @return number of times char is located in the string 074 */ 075 public static int countChar(String s, char ch) { 076 if (ObjectHelper.isEmpty(s)) { 077 return 0; 078 } 079 080 int matches = 0; 081 for (int i = 0; i < s.length(); i++) { 082 char c = s.charAt(i); 083 if (ch == c) { 084 matches++; 085 } 086 } 087 088 return matches; 089 } 090 091 /** 092 * Limits the length of a string 093 * 094 * @param s the string 095 * @param maxLength the maximum length of the returned string 096 * @return s if the length of s is less than maxLength or the first maxLength characters of s 097 */ 098 public static String limitLength(String s, int maxLength) { 099 if (ObjectHelper.isEmpty(s)) { 100 return s; 101 } 102 return s.length() <= maxLength ? s : s.substring(0, maxLength); 103 } 104 105 /** 106 * Removes all quotes (single and double) from the string 107 * 108 * @param s the string 109 * @return the string without quotes (single and double) 110 */ 111 public static String removeQuotes(String s) { 112 if (ObjectHelper.isEmpty(s)) { 113 return s; 114 } 115 116 s = replaceAll(s, "'", ""); 117 s = replaceAll(s, "\"", ""); 118 return s; 119 } 120 121 /** 122 * Removes all leading and ending quotes (single and double) from the string 123 * 124 * @param s the string 125 * @return the string without leading and ending quotes (single and double) 126 */ 127 public static String removeLeadingAndEndingQuotes(String s) { 128 if (ObjectHelper.isEmpty(s)) { 129 return s; 130 } 131 132 String copy = s.trim(); 133 if (copy.startsWith("'") && copy.endsWith("'")) { 134 return copy.substring(1, copy.length() - 1); 135 } 136 if (copy.startsWith("\"") && copy.endsWith("\"")) { 137 return copy.substring(1, copy.length() - 1); 138 } 139 140 // no quotes, so return as-is 141 return s; 142 } 143 144 /** 145 * Whether the string starts and ends with either single or double quotes. 146 * 147 * @param s the string 148 * @return <tt>true</tt> if the string starts and ends with either single or double quotes. 149 */ 150 public static boolean isQuoted(String s) { 151 if (ObjectHelper.isEmpty(s)) { 152 return false; 153 } 154 155 if (s.startsWith("'") && s.endsWith("'")) { 156 return true; 157 } 158 if (s.startsWith("\"") && s.endsWith("\"")) { 159 return true; 160 } 161 162 return false; 163 } 164 165 /** 166 * Encodes the text into safe XML by replacing < > and & with XML tokens 167 * 168 * @param text the text 169 * @return the encoded text 170 */ 171 public static String xmlEncode(String text) { 172 if (text == null) { 173 return ""; 174 } 175 // must replace amp first, so we dont replace < to amp later 176 text = replaceAll(text, "&", "&"); 177 text = replaceAll(text, "\"", """); 178 text = replaceAll(text, "<", "<"); 179 text = replaceAll(text, ">", ">"); 180 return text; 181 } 182 183 /** 184 * Determines if the string has at least one letter in upper case 185 * @param text the text 186 * @return <tt>true</tt> if at least one letter is upper case, <tt>false</tt> otherwise 187 */ 188 public static boolean hasUpperCase(String text) { 189 if (text == null) { 190 return false; 191 } 192 193 for (int i = 0; i < text.length(); i++) { 194 char ch = text.charAt(i); 195 if (Character.isUpperCase(ch)) { 196 return true; 197 } 198 } 199 200 return false; 201 } 202 203 /** 204 * Determines if the string is a fully qualified class name 205 */ 206 public static boolean isClassName(String text) { 207 boolean result = false; 208 if (text != null) { 209 String[] split = text.split("\\."); 210 if (split.length > 0) { 211 String lastToken = split[split.length - 1]; 212 if (lastToken.length() > 0) { 213 result = Character.isUpperCase(lastToken.charAt(0)); 214 } 215 } 216 } 217 return result; 218 } 219 220 /** 221 * Does the expression have the language start token? 222 * 223 * @param expression the expression 224 * @param language the name of the language, such as simple 225 * @return <tt>true</tt> if the expression contains the start token, <tt>false</tt> otherwise 226 */ 227 public static boolean hasStartToken(String expression, String language) { 228 if (expression == null) { 229 return false; 230 } 231 232 // for the simple language the expression start token could be "${" 233 if ("simple".equalsIgnoreCase(language) && expression.contains("${")) { 234 return true; 235 } 236 237 if (language != null && expression.contains("$" + language + "{")) { 238 return true; 239 } 240 241 return false; 242 } 243 244 /** 245 * Replaces all the from tokens in the given input string. 246 * <p/> 247 * This implementation is not recursive, not does it check for tokens in the replacement string. 248 * 249 * @param input the input string 250 * @param from the from string, must <b>not</b> be <tt>null</tt> or empty 251 * @param to the replacement string, must <b>not</b> be empty 252 * @return the replaced string, or the input string if no replacement was needed 253 * @throws IllegalArgumentException if the input arguments is invalid 254 */ 255 public static String replaceAll(String input, String from, String to) { 256 if (ObjectHelper.isEmpty(input)) { 257 return input; 258 } 259 if (from == null) { 260 throw new IllegalArgumentException("from cannot be null"); 261 } 262 if (to == null) { 263 // to can be empty, so only check for null 264 throw new IllegalArgumentException("to cannot be null"); 265 } 266 267 // fast check if there is any from at all 268 if (!input.contains(from)) { 269 return input; 270 } 271 272 final int len = from.length(); 273 final int max = input.length(); 274 StringBuilder sb = new StringBuilder(max); 275 for (int i = 0; i < max;) { 276 if (i + len <= max) { 277 String token = input.substring(i, i + len); 278 if (from.equals(token)) { 279 sb.append(to); 280 // fast forward 281 i = i + len; 282 continue; 283 } 284 } 285 286 // append single char 287 sb.append(input.charAt(i)); 288 // forward to next 289 i++; 290 } 291 return sb.toString(); 292 } 293 294 /** 295 * Creates a json tuple with the given name/value pair. 296 * 297 * @param name the name 298 * @param value the value 299 * @param isMap whether the tuple should be map 300 * @return the json 301 */ 302 public static String toJson(String name, String value, boolean isMap) { 303 if (isMap) { 304 return "{ " + StringQuoteHelper.doubleQuote(name) + ": " + StringQuoteHelper.doubleQuote(value) + " }"; 305 } else { 306 return StringQuoteHelper.doubleQuote(name) + ": " + StringQuoteHelper.doubleQuote(value); 307 } 308 } 309 310 /** 311 * Asserts whether the string is <b>not</b> empty. 312 * 313 * @param value the string to test 314 * @param name the key that resolved the value 315 * @return the passed {@code value} as is 316 * @throws IllegalArgumentException is thrown if assertion fails 317 */ 318 public static String notEmpty(String value, String name) { 319 if (ObjectHelper.isEmpty(value)) { 320 throw new IllegalArgumentException(name + " must be specified and not empty"); 321 } 322 323 return value; 324 } 325 326 /** 327 * Asserts whether the string is <b>not</b> empty. 328 * 329 * @param value the string to test 330 * @param on additional description to indicate where this problem occurred (appended as toString()) 331 * @param name the key that resolved the value 332 * @return the passed {@code value} as is 333 * @throws IllegalArgumentException is thrown if assertion fails 334 */ 335 public static String notEmpty(String value, String name, Object on) { 336 if (on == null) { 337 ObjectHelper.notNull(value, name); 338 } else if (ObjectHelper.isEmpty(value)) { 339 throw new IllegalArgumentException(name + " must be specified and not empty on: " + on); 340 } 341 342 return value; 343 } 344 345 public static String[] splitOnCharacter(String value, String needle, int count) { 346 String rc[] = new String[count]; 347 rc[0] = value; 348 for (int i = 1; i < count; i++) { 349 String v = rc[i - 1]; 350 int p = v.indexOf(needle); 351 if (p < 0) { 352 return rc; 353 } 354 rc[i - 1] = v.substring(0, p); 355 rc[i] = v.substring(p + 1); 356 } 357 return rc; 358 } 359 360 /** 361 * Removes any starting characters on the given text which match the given 362 * character 363 * 364 * @param text the string 365 * @param ch the initial characters to remove 366 * @return either the original string or the new substring 367 */ 368 public static String removeStartingCharacters(String text, char ch) { 369 int idx = 0; 370 while (text.charAt(idx) == ch) { 371 idx++; 372 } 373 if (idx > 0) { 374 return text.substring(idx); 375 } 376 return text; 377 } 378 379 /** 380 * Capitalize the string (upper case first character) 381 * 382 * @param text the string 383 * @return the string capitalized (upper case first character) 384 */ 385 public static String capitalize(String text) { 386 return capitalize(text, false); 387 } 388 389 /** 390 * Capitalize the string (upper case first character) 391 * 392 * @param text the string 393 * @param dashToCamelCase whether to also convert dash format into camel case (hello-great-world -> helloGreatWorld) 394 * @return the string capitalized (upper case first character) 395 */ 396 public static String capitalize(String text, boolean dashToCamelCase) { 397 if (dashToCamelCase) { 398 text = dashToCamelCase(text); 399 } 400 if (text == null) { 401 return null; 402 } 403 int length = text.length(); 404 if (length == 0) { 405 return text; 406 } 407 String answer = text.substring(0, 1).toUpperCase(Locale.ENGLISH); 408 if (length > 1) { 409 answer += text.substring(1, length); 410 } 411 return answer; 412 } 413 414 /** 415 * Converts the string from dash format into camel case (hello-great-world -> helloGreatWorld) 416 * 417 * @param text the string 418 * @return the string camel cased 419 */ 420 public static String dashToCamelCase(String text) { 421 if (text == null) { 422 return null; 423 } 424 int length = text.length(); 425 if (length == 0) { 426 return text; 427 } 428 if (text.indexOf('-') == -1) { 429 return text; 430 } 431 432 StringBuilder sb = new StringBuilder(); 433 434 for (int i = 0; i < text.length(); i++) { 435 char c = text.charAt(i); 436 if (c == '-') { 437 i++; 438 sb.append(Character.toUpperCase(text.charAt(i))); 439 } else { 440 sb.append(c); 441 } 442 } 443 return sb.toString(); 444 } 445 446 /** 447 * Returns the string after the given token 448 * 449 * @param text the text 450 * @param after the token 451 * @return the text after the token, or <tt>null</tt> if text does not contain the token 452 */ 453 public static String after(String text, String after) { 454 if (!text.contains(after)) { 455 return null; 456 } 457 return text.substring(text.indexOf(after) + after.length()); 458 } 459 460 /** 461 * Returns an object after the given token 462 * 463 * @param text the text 464 * @param after the token 465 * @param mapper a mapping function to convert the string after the token to type T 466 * @return an Optional describing the result of applying a mapping function to the text after the token. 467 */ 468 public static <T> Optional<T> after(String text, String after, Function<String, T> mapper) { 469 String result = after(text, after); 470 if (result == null) { 471 return Optional.empty(); 472 } else { 473 return Optional.ofNullable(mapper.apply(result)); 474 } 475 } 476 477 /** 478 * Returns the string before the given token 479 * 480 * @param text the text 481 * @param before the token 482 * @return the text before the token, or <tt>null</tt> if text does not 483 * contain the token 484 */ 485 public static String before(String text, String before) { 486 if (!text.contains(before)) { 487 return null; 488 } 489 return text.substring(0, text.indexOf(before)); 490 } 491 492 /** 493 * Returns an object before the given token 494 * 495 * @param text the text 496 * @param before the token 497 * @param mapper a mapping function to convert the string before the token to type T 498 * @return an Optional describing the result of applying a mapping function to the text before the token. 499 */ 500 public static <T> Optional<T> before(String text, String before, Function<String, T> mapper) { 501 String result = before(text, before); 502 if (result == null) { 503 return Optional.empty(); 504 } else { 505 return Optional.ofNullable(mapper.apply(result)); 506 } 507 } 508 509 /** 510 * Returns the string between the given tokens 511 * 512 * @param text the text 513 * @param after the before token 514 * @param before the after token 515 * @return the text between the tokens, or <tt>null</tt> if text does not contain the tokens 516 */ 517 public static String between(String text, String after, String before) { 518 text = after(text, after); 519 if (text == null) { 520 return null; 521 } 522 return before(text, before); 523 } 524 525 /** 526 * Returns an object between the given token 527 * 528 * @param text the text 529 * @param after the before token 530 * @param before the after token 531 * @param mapper a mapping function to convert the string between the token to type T 532 * @return an Optional describing the result of applying a mapping function to the text between the token. 533 */ 534 public static <T> Optional<T> between(String text, String after, String before, Function<String, T> mapper) { 535 String result = between(text, after, before); 536 if (result == null) { 537 return Optional.empty(); 538 } else { 539 return Optional.ofNullable(mapper.apply(result)); 540 } 541 } 542 543 /** 544 * Returns the string between the most outer pair of tokens 545 * <p/> 546 * The number of token pairs must be evenly, eg there must be same number of before and after tokens, otherwise <tt>null</tt> is returned 547 * <p/> 548 * This implementation skips matching when the text is either single or double quoted. 549 * For example: 550 * <tt>${body.matches("foo('bar')")</tt> 551 * Will not match the parenthesis from the quoted text. 552 * 553 * @param text the text 554 * @param after the before token 555 * @param before the after token 556 * @return the text between the outer most tokens, or <tt>null</tt> if text does not contain the tokens 557 */ 558 public static String betweenOuterPair(String text, char before, char after) { 559 if (text == null) { 560 return null; 561 } 562 563 int pos = -1; 564 int pos2 = -1; 565 int count = 0; 566 int count2 = 0; 567 568 boolean singleQuoted = false; 569 boolean doubleQuoted = false; 570 for (int i = 0; i < text.length(); i++) { 571 char ch = text.charAt(i); 572 if (!doubleQuoted && ch == '\'') { 573 singleQuoted = !singleQuoted; 574 } else if (!singleQuoted && ch == '\"') { 575 doubleQuoted = !doubleQuoted; 576 } 577 if (singleQuoted || doubleQuoted) { 578 continue; 579 } 580 581 if (ch == before) { 582 count++; 583 } else if (ch == after) { 584 count2++; 585 } 586 587 if (ch == before && pos == -1) { 588 pos = i; 589 } else if (ch == after) { 590 pos2 = i; 591 } 592 } 593 594 if (pos == -1 || pos2 == -1) { 595 return null; 596 } 597 598 // must be even paris 599 if (count != count2) { 600 return null; 601 } 602 603 return text.substring(pos + 1, pos2); 604 } 605 606 /** 607 * Returns an object between the most outer pair of tokens 608 * 609 * @param text the text 610 * @param after the before token 611 * @param before the after token 612 * @param mapper a mapping function to convert the string between the most outer pair of tokens to type T 613 * @return an Optional describing the result of applying a mapping function to the text between the most outer pair of tokens. 614 */ 615 public static <T> Optional<T> betweenOuterPair(String text, char before, char after, Function<String, T> mapper) { 616 String result = betweenOuterPair(text, before, after); 617 if (result == null) { 618 return Optional.empty(); 619 } else { 620 return Optional.ofNullable(mapper.apply(result)); 621 } 622 } 623 624 /** 625 * Returns true if the given name is a valid java identifier 626 */ 627 public static boolean isJavaIdentifier(String name) { 628 if (name == null) { 629 return false; 630 } 631 int size = name.length(); 632 if (size < 1) { 633 return false; 634 } 635 if (Character.isJavaIdentifierStart(name.charAt(0))) { 636 for (int i = 1; i < size; i++) { 637 if (!Character.isJavaIdentifierPart(name.charAt(i))) { 638 return false; 639 } 640 } 641 return true; 642 } 643 return false; 644 } 645 646 /** 647 * Cleans the string to a pure Java identifier so we can use it for loading class names. 648 * <p/> 649 * Especially from Spring DSL people can have \n \t or other characters that otherwise 650 * would result in ClassNotFoundException 651 * 652 * @param name the class name 653 * @return normalized classname that can be load by a class loader. 654 */ 655 public static String normalizeClassName(String name) { 656 StringBuilder sb = new StringBuilder(name.length()); 657 for (char ch : name.toCharArray()) { 658 if (ch == '.' || ch == '[' || ch == ']' || ch == '-' || Character.isJavaIdentifierPart(ch)) { 659 sb.append(ch); 660 } 661 } 662 return sb.toString(); 663 } 664 665 /** 666 * Compares old and new text content and report back which lines are changed 667 * 668 * @param oldText the old text 669 * @param newText the new text 670 * @return a list of line numbers that are changed in the new text 671 */ 672 public static List<Integer> changedLines(String oldText, String newText) { 673 if (oldText == null || oldText.equals(newText)) { 674 return Collections.emptyList(); 675 } 676 677 List<Integer> changed = new ArrayList<>(); 678 679 String[] oldLines = oldText.split("\n"); 680 String[] newLines = newText.split("\n"); 681 682 for (int i = 0; i < newLines.length; i++) { 683 String newLine = newLines[i]; 684 String oldLine = i < oldLines.length ? oldLines[i] : null; 685 if (oldLine == null) { 686 changed.add(i); 687 } else if (!newLine.equals(oldLine)) { 688 changed.add(i); 689 } 690 } 691 692 return changed; 693 } 694 695 /** 696 * Removes the leading and trailing whitespace and if the resulting 697 * string is empty returns {@code null}. Examples: 698 * <p> 699 * Examples: 700 * <blockquote><pre> 701 * trimToNull("abc") -> "abc" 702 * trimToNull(" abc") -> "abc" 703 * trimToNull(" abc ") -> "abc" 704 * trimToNull(" ") -> null 705 * trimToNull("") -> null 706 * </pre></blockquote> 707 */ 708 public static String trimToNull(final String given) { 709 if (given == null) { 710 return null; 711 } 712 713 final String trimmed = given.trim(); 714 715 if (trimmed.isEmpty()) { 716 return null; 717 } 718 719 return trimmed; 720 } 721 722 /** 723 * Checks if the src string contains what 724 * 725 * @param src is the source string to be checked 726 * @param what is the string which will be looked up in the src argument 727 * @return true/false 728 */ 729 public static boolean containsIgnoreCase(String src, String what) { 730 if (src == null || what == null) { 731 return false; 732 } 733 734 final int length = what.length(); 735 if (length == 0) { 736 return true; // Empty string is contained 737 } 738 739 final char firstLo = Character.toLowerCase(what.charAt(0)); 740 final char firstUp = Character.toUpperCase(what.charAt(0)); 741 742 for (int i = src.length() - length; i >= 0; i--) { 743 // Quick check before calling the more expensive regionMatches() method: 744 final char ch = src.charAt(i); 745 if (ch != firstLo && ch != firstUp) { 746 continue; 747 } 748 749 if (src.regionMatches(true, i, what, 0, length)) { 750 return true; 751 } 752 } 753 754 return false; 755 } 756 757 /** 758 * Outputs the bytes in human readable format in units of KB,MB,GB etc. 759 * 760 * @param locale The locale to apply during formatting. If l is {@code null} then no localization is applied. 761 * @param bytes number of bytes 762 * @return human readable output 763 * @see java.lang.String#format(Locale, String, Object...) 764 */ 765 public static String humanReadableBytes(Locale locale, long bytes) { 766 int unit = 1024; 767 if (bytes < unit) { 768 return bytes + " B"; 769 } 770 int exp = (int) (Math.log(bytes) / Math.log(unit)); 771 String pre = "KMGTPE".charAt(exp - 1) + ""; 772 return String.format(locale, "%.1f %sB", bytes / Math.pow(unit, exp), pre); 773 } 774 775 /** 776 * Outputs the bytes in human readable format in units of KB,MB,GB etc. 777 * 778 * The locale always used is the one returned by {@link java.util.Locale#getDefault()}. 779 * 780 * @param bytes number of bytes 781 * @return human readable output 782 * @see org.apache.camel.util.StringHelper#humanReadableBytes(Locale, long) 783 */ 784 public static String humanReadableBytes(long bytes) { 785 return humanReadableBytes(Locale.getDefault(), bytes); 786 } 787 788 /** 789 * Check for string pattern matching with a number of strategies in the 790 * following order: 791 * 792 * - equals 793 * - null pattern always matches 794 * - * always matches 795 * - Ant style matching 796 * - Regexp 797 * 798 * @param patter the pattern 799 * @param target the string to test 800 * @return true if target matches the pattern 801 */ 802 public static boolean matches(String patter, String target) { 803 if (Objects.equals(patter, target)) { 804 return true; 805 } 806 807 if (Objects.isNull(patter)) { 808 return true; 809 } 810 811 if (Objects.equals("*", patter)) { 812 return true; 813 } 814 815 if (AntPathMatcher.INSTANCE.match(patter, target)) { 816 return true; 817 } 818 819 Pattern p = Pattern.compile(patter); 820 Matcher m = p.matcher(target); 821 822 return m.matches(); 823 } 824 825}