474 * 475 * @throws IllegalStateException 476 * If no match has yet been attempted, 477 * or if the previous match operation failed 478 * 479 * @throws IndexOutOfBoundsException 480 * If there is no capturing group in the pattern 481 * with the given index 482 */ 483 public String group(int group) { 484 if (first < 0) 485 throw new IllegalStateException("No match found"); 486 if (group < 0 || group > groupCount()) 487 throw new IndexOutOfBoundsException("No group " + group); 488 if ((groups[group*2] == -1) || (groups[group*2+1] == -1)) 489 return null; 490 return getSubSequence(groups[group * 2], groups[group * 2 + 1]).toString(); 491 } 492 493 /** 494 * Returns the number of capturing groups in this matcher's pattern. 495 * 496 * <p> Group zero denotes the entire pattern by convention. It is not 497 * included in this count. 498 * 499 * <p> Any non-negative integer smaller than or equal to the value 500 * returned by this method is guaranteed to be a valid group index for 501 * this matcher. </p> 502 * 503 * @return The number of capturing groups in this matcher's pattern 504 */ 505 public int groupCount() { 506 return parentPattern.capturingGroupCount - 1; 507 } 508 509 /** 510 * Attempts to match the entire region against the pattern. 511 * 512 * <p> If the match succeeds then more information can be obtained via the 513 * <tt>start</tt>, <tt>end</tt>, and <tt>group</tt> methods. </p> 632 * 633 * <ol> 634 * 635 * <li><p> It reads characters from the input sequence, starting at the 636 * append position, and appends them to the given string buffer. It 637 * stops after reading the last character preceding the previous match, 638 * that is, the character at index {@link 639 * #start()} <tt>-</tt> <tt>1</tt>. </p></li> 640 * 641 * <li><p> It appends the given replacement string to the string buffer. 642 * </p></li> 643 * 644 * <li><p> It sets the append position of this matcher to the index of 645 * the last character matched, plus one, that is, to {@link #end()}. 646 * </p></li> 647 * 648 * </ol> 649 * 650 * <p> The replacement string may contain references to subsequences 651 * captured during the previous match: Each occurrence of 652 * <tt>$</tt><i>g</i><tt></tt> will be replaced by the result of 653 * evaluating {@link #group(int) group}<tt>(</tt><i>g</i><tt>)</tt>. 654 * The first number after the <tt>$</tt> is always treated as part of 655 * the group reference. Subsequent numbers are incorporated into g if 656 * they would form a legal group reference. Only the numerals '0' 657 * through '9' are considered as potential components of the group 658 * reference. If the second group matched the string <tt>"foo"</tt>, for 659 * example, then passing the replacement string <tt>"$2bar"</tt> would 660 * cause <tt>"foobar"</tt> to be appended to the string buffer. A dollar 661 * sign (<tt>$</tt>) may be included as a literal in the replacement 662 * string by preceding it with a backslash (<tt>\$</tt>). 663 * 664 * <p> Note that backslashes (<tt>\</tt>) and dollar signs (<tt>$</tt>) in 665 * the replacement string may cause the results to be different than if it 666 * were being treated as a literal replacement string. Dollar signs may be 667 * treated as references to captured subsequences as described above, and 668 * backslashes are used to escape literal characters in the replacement 669 * string. 670 * 671 * <p> This method is intended to be used in a loop together with the 672 * {@link #appendTail appendTail} and {@link #find find} methods. The 673 * following code, for example, writes <tt>one dog two dogs in the 674 * yard</tt> to the standard-output stream: </p> 678 * Matcher m = p.matcher("one cat two cats in the yard"); 679 * StringBuffer sb = new StringBuffer(); 680 * while (m.find()) { 681 * m.appendReplacement(sb, "dog"); 682 * } 683 * m.appendTail(sb); 684 * System.out.println(sb.toString());</pre></blockquote> 685 * 686 * @param sb 687 * The target string buffer 688 * 689 * @param replacement 690 * The replacement string 691 * 692 * @return This matcher 693 * 694 * @throws IllegalStateException 695 * If no match has yet been attempted, 696 * or if the previous match operation failed 697 * 698 * @throws IndexOutOfBoundsException 699 * If the replacement string refers to a capturing group 700 * that does not exist in the pattern 701 */ 702 public Matcher appendReplacement(StringBuffer sb, String replacement) { 703 704 // If no match, return error 705 if (first < 0) 706 throw new IllegalStateException("No match available"); 707 708 // Process substitution string to replace group references with groups 709 int cursor = 0; 710 StringBuilder result = new StringBuilder(); 711 712 while (cursor < replacement.length()) { 713 char nextChar = replacement.charAt(cursor); 714 if (nextChar == '\\') { 715 cursor++; 716 nextChar = replacement.charAt(cursor); 717 result.append(nextChar); 718 cursor++; 719 } else if (nextChar == '$') { 720 // Skip past $ 721 cursor++; 722 // The first number is always a group 723 int refNum = (int)replacement.charAt(cursor) - '0'; 724 if ((refNum < 0)||(refNum > 9)) 725 throw new IllegalArgumentException( 726 "Illegal group reference"); 727 cursor++; 728 729 // Capture the largest legal group string 730 boolean done = false; 731 while (!done) { 732 if (cursor >= replacement.length()) { 733 break; 734 } 735 int nextDigit = replacement.charAt(cursor) - '0'; 736 if ((nextDigit < 0)||(nextDigit > 9)) { // not a number 737 break; 738 } 739 int newRefNum = (refNum * 10) + nextDigit; 740 if (groupCount() < newRefNum) { 741 done = true; 742 } else { 743 refNum = newRefNum; 744 cursor++; 745 } 746 } 747 // Append group 748 if (start(refNum) != -1 && end(refNum) != -1) 749 result.append(text, start(refNum), end(refNum)); 750 } else { 751 result.append(nextChar); 752 cursor++; 753 } 754 } 755 // Append the intervening text 756 sb.append(text, lastAppendPosition, first); 757 // Append the match substitution 758 sb.append(result); 759 760 lastAppendPosition = last; 761 return this; 762 } 763 764 /** 765 * Implements a terminal append-and-replace step. 766 * | 474 * 475 * @throws IllegalStateException 476 * If no match has yet been attempted, 477 * or if the previous match operation failed 478 * 479 * @throws IndexOutOfBoundsException 480 * If there is no capturing group in the pattern 481 * with the given index 482 */ 483 public String group(int group) { 484 if (first < 0) 485 throw new IllegalStateException("No match found"); 486 if (group < 0 || group > groupCount()) 487 throw new IndexOutOfBoundsException("No group " + group); 488 if ((groups[group*2] == -1) || (groups[group*2+1] == -1)) 489 return null; 490 return getSubSequence(groups[group * 2], groups[group * 2 + 1]).toString(); 491 } 492 493 /** 494 * Returns the input subsequence captured by the given 495 * <a href="Pattern.html#groupname">named-capturing group</a> during the previous 496 * match operation. 497 * 498 * <p> If the match was successful but the group specified failed to match 499 * any part of the input sequence, then <tt>null</tt> is returned. Note 500 * that some groups, for example <tt>(a*)</tt>, match the empty string. 501 * This method will return the empty string when such a group successfully 502 * matches the empty string in the input. </p> 503 * 504 * @param name 505 * The name of a named-capturing group in this matcher's pattern 506 * 507 * @return The (possibly empty) subsequence captured by the named group 508 * during the previous match, or <tt>null</tt> if the group 509 * failed to match part of the input 510 * 511 * @throws IllegalStateException 512 * If no match has yet been attempted, 513 * or if the previous match operation failed 514 * 515 * @throws IllegalArgumentException 516 * If there is no capturing group in the pattern 517 * with the given name 518 */ 519 public String group(String name) { 520 if (name == null) 521 throw new NullPointerException("Null group name"); 522 if (first < 0) 523 throw new IllegalStateException("No match found"); 524 if (!parentPattern.namedGroups().containsKey(name)) 525 throw new IllegalArgumentException("No group with name <" + name + ">"); 526 int group = parentPattern.namedGroups().get(name); 527 if ((groups[group*2] == -1) || (groups[group*2+1] == -1)) 528 return null; 529 return getSubSequence(groups[group * 2], groups[group * 2 + 1]).toString(); 530 } 531 532 /** 533 * Returns the number of capturing groups in this matcher's pattern. 534 * 535 * <p> Group zero denotes the entire pattern by convention. It is not 536 * included in this count. 537 * 538 * <p> Any non-negative integer smaller than or equal to the value 539 * returned by this method is guaranteed to be a valid group index for 540 * this matcher. </p> 541 * 542 * @return The number of capturing groups in this matcher's pattern 543 */ 544 public int groupCount() { 545 return parentPattern.capturingGroupCount - 1; 546 } 547 548 /** 549 * Attempts to match the entire region against the pattern. 550 * 551 * <p> If the match succeeds then more information can be obtained via the 552 * <tt>start</tt>, <tt>end</tt>, and <tt>group</tt> methods. </p> 671 * 672 * <ol> 673 * 674 * <li><p> It reads characters from the input sequence, starting at the 675 * append position, and appends them to the given string buffer. It 676 * stops after reading the last character preceding the previous match, 677 * that is, the character at index {@link 678 * #start()} <tt>-</tt> <tt>1</tt>. </p></li> 679 * 680 * <li><p> It appends the given replacement string to the string buffer. 681 * </p></li> 682 * 683 * <li><p> It sets the append position of this matcher to the index of 684 * the last character matched, plus one, that is, to {@link #end()}. 685 * </p></li> 686 * 687 * </ol> 688 * 689 * <p> The replacement string may contain references to subsequences 690 * captured during the previous match: Each occurrence of 691 * <tt>$</tt><<i>name</i>> or <tt>$</tt><i>g</i> 692 * will be replaced by the result of evaluating the corresponding 693 * {@link #group(String) group(name)} or {@link #group(int) group(g)</tt>} 694 * respectively. For <tt>$</tt><i>g</i><tt></tt>, 695 * the first number after the <tt>$</tt> is always treated as part of 696 * the group reference. Subsequent numbers are incorporated into g if 697 * they would form a legal group reference. Only the numerals '0' 698 * through '9' are considered as potential components of the group 699 * reference. If the second group matched the string <tt>"foo"</tt>, for 700 * example, then passing the replacement string <tt>"$2bar"</tt> would 701 * cause <tt>"foobar"</tt> to be appended to the string buffer. A dollar 702 * sign (<tt>$</tt>) may be included as a literal in the replacement 703 * string by preceding it with a backslash (<tt>\$</tt>). 704 * 705 * <p> Note that backslashes (<tt>\</tt>) and dollar signs (<tt>$</tt>) in 706 * the replacement string may cause the results to be different than if it 707 * were being treated as a literal replacement string. Dollar signs may be 708 * treated as references to captured subsequences as described above, and 709 * backslashes are used to escape literal characters in the replacement 710 * string. 711 * 712 * <p> This method is intended to be used in a loop together with the 713 * {@link #appendTail appendTail} and {@link #find find} methods. The 714 * following code, for example, writes <tt>one dog two dogs in the 715 * yard</tt> to the standard-output stream: </p> 719 * Matcher m = p.matcher("one cat two cats in the yard"); 720 * StringBuffer sb = new StringBuffer(); 721 * while (m.find()) { 722 * m.appendReplacement(sb, "dog"); 723 * } 724 * m.appendTail(sb); 725 * System.out.println(sb.toString());</pre></blockquote> 726 * 727 * @param sb 728 * The target string buffer 729 * 730 * @param replacement 731 * The replacement string 732 * 733 * @return This matcher 734 * 735 * @throws IllegalStateException 736 * If no match has yet been attempted, 737 * or if the previous match operation failed 738 * 739 * @throws IllegalArgumentException 740 * If the replacement string refers to a named-capturing 741 * group that does not exist in the pattern 742 * 743 * @throws IndexOutOfBoundsException 744 * If the replacement string refers to a capturing group 745 * that does not exist in the pattern 746 */ 747 public Matcher appendReplacement(StringBuffer sb, String replacement) { 748 749 // If no match, return error 750 if (first < 0) 751 throw new IllegalStateException("No match available"); 752 753 // Process substitution string to replace group references with groups 754 int cursor = 0; 755 StringBuilder result = new StringBuilder(); 756 757 while (cursor < replacement.length()) { 758 char nextChar = replacement.charAt(cursor); 759 if (nextChar == '\\') { 760 cursor++; 761 nextChar = replacement.charAt(cursor); 762 result.append(nextChar); 763 cursor++; 764 } else if (nextChar == '$') { 765 // Skip past $ 766 cursor++; 767 // A StringIndexOutOfBoundsException is thrown if 768 // this "$" is the last character in replacement 769 // string in current implementation, a IAE might be 770 // more appropriate. 771 nextChar = replacement.charAt(cursor); 772 int refNum = -1; 773 if (nextChar == '<') { 774 cursor++; 775 StringBuilder gsb = new StringBuilder(); 776 while (cursor < replacement.length()) { 777 nextChar = replacement.charAt(cursor); 778 if (ASCII.isLower(nextChar) || 779 ASCII.isUpper(nextChar) || 780 ASCII.isDigit(nextChar)) { 781 gsb.append(nextChar); 782 cursor++; 783 } else { 784 break; 785 } 786 } 787 if (gsb.length() == 0) 788 throw new IllegalArgumentException( 789 "named capturing group has 0 length name"); 790 if (nextChar != '>') 791 throw new IllegalArgumentException( 792 "named capturing group is missing trailing '>'"); 793 String gname = gsb.toString(); 794 if (!parentPattern.namedGroups().containsKey(gname)) 795 throw new IllegalArgumentException( 796 "No group with name <" + gname + ">"); 797 refNum = parentPattern.namedGroups().get(gname); 798 cursor++; 799 } else { 800 // The first number is always a group 801 refNum = (int)nextChar - '0'; 802 if ((refNum < 0)||(refNum > 9)) 803 throw new IllegalArgumentException( 804 "Illegal group reference"); 805 cursor++; 806 // Capture the largest legal group string 807 boolean done = false; 808 while (!done) { 809 if (cursor >= replacement.length()) { 810 break; 811 } 812 int nextDigit = replacement.charAt(cursor) - '0'; 813 if ((nextDigit < 0)||(nextDigit > 9)) { // not a number 814 break; 815 } 816 int newRefNum = (refNum * 10) + nextDigit; 817 if (groupCount() < newRefNum) { 818 done = true; 819 } else { 820 refNum = newRefNum; 821 cursor++; 822 } 823 } 824 } 825 // Append group 826 if (start(refNum) != -1 && end(refNum) != -1) 827 result.append(text, start(refNum), end(refNum)); 828 } else { 829 result.append(nextChar); 830 cursor++; 831 } 832 } 833 // Append the intervening text 834 sb.append(text, lastAppendPosition, first); 835 // Append the match substitution 836 sb.append(result); 837 838 lastAppendPosition = last; 839 return this; 840 } 841 842 /** 843 * Implements a terminal append-and-replace step. 844 * |