DiffEngine.php 31 KB
Newer Older
1 2 3 4 5 6 7 8 9 10
<?php

/**
 * @file
 * A PHP diff engine for phpwiki. (Taken from phpwiki-1.3.3)
 *
 * Copyright (C) 2000, 2001 Geoffrey T. Dairiki <dairiki@dairiki.org>
 * You may copy this code freely under the conditions of the GPL.
 */

11
use Drupal\Component\Utility\Settings;
12 13 14 15
use Drupal\Component\Utility\String;
use Drupal\Component\Utility\Unicode;

define('USE_ASSERTS', FALSE);
16

17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244
/**
 * @todo document
 * @private
 * @subpackage DifferenceEngine
 */
class _DiffOp {
  var $type;
  var $orig;
  var $closing;

  function reverse() {
    trigger_error('pure virtual', E_USER_ERROR);
  }

  function norig() {
    return $this->orig ? sizeof($this->orig) : 0;
  }

  function nclosing() {
    return $this->closing ? sizeof($this->closing) : 0;
  }
}

/**
 * @todo document
 * @private
 * @subpackage DifferenceEngine
 */
class _DiffOp_Copy extends _DiffOp {
  var $type = 'copy';

  function _DiffOp_Copy($orig, $closing = FALSE) {
    if (!is_array($closing)) {
      $closing = $orig;
    }
    $this->orig = $orig;
    $this->closing = $closing;
  }

  function reverse() {
    return new _DiffOp_Copy($this->closing, $this->orig);
  }
}

/**
 * @todo document
 * @private
 * @subpackage DifferenceEngine
 */
class _DiffOp_Delete extends _DiffOp {
  var $type = 'delete';

  function _DiffOp_Delete($lines) {
    $this->orig = $lines;
    $this->closing = FALSE;
  }

  function reverse() {
    return new _DiffOp_Add($this->orig);
  }
}

/**
 * @todo document
 * @private
 * @subpackage DifferenceEngine
 */
class _DiffOp_Add extends _DiffOp {
  var $type = 'add';

  function _DiffOp_Add($lines) {
    $this->closing = $lines;
    $this->orig = FALSE;
  }

  function reverse() {
    return new _DiffOp_Delete($this->closing);
  }
}

/**
 * @todo document
 * @private
 * @subpackage DifferenceEngine
 */
class _DiffOp_Change extends _DiffOp {
  var $type = 'change';

  function _DiffOp_Change($orig, $closing) {
    $this->orig = $orig;
    $this->closing = $closing;
  }

  function reverse() {
    return new _DiffOp_Change($this->closing, $this->orig);
  }
}


/**
 * Class used internally by Diff to actually compute the diffs.
 *
 * The algorithm used here is mostly lifted from the perl module
 * Algorithm::Diff (version 1.06) by Ned Konz, which is available at:
 *   http://www.perl.com/CPAN/authors/id/N/NE/NEDKONZ/Algorithm-Diff-1.06.zip
 *
 * More ideas are taken from:
 *   http://www.ics.uci.edu/~eppstein/161/960229.html
 *
 * Some ideas are (and a bit of code) are from from analyze.c, from GNU
 * diffutils-2.7, which can be found at:
 *   ftp://gnudist.gnu.org/pub/gnu/diffutils/diffutils-2.7.tar.gz
 *
 * closingly, some ideas (subdivision by NCHUNKS > 2, and some optimizations)
 * are my own.
 *
 * Line length limits for robustness added by Tim Starling, 2005-08-31
 *
 * @author Geoffrey T. Dairiki, Tim Starling
 * @private
 * @subpackage DifferenceEngine
 */
class _DiffEngine {
  function MAX_XREF_LENGTH() {
    return 10000;
  }

  function diff($from_lines, $to_lines) {

    $n_from = sizeof($from_lines);
    $n_to = sizeof($to_lines);

    $this->xchanged = $this->ychanged = array();
    $this->xv = $this->yv = array();
    $this->xind = $this->yind = array();
    unset($this->seq);
    unset($this->in_seq);
    unset($this->lcs);

    // Skip leading common lines.
    for ($skip = 0; $skip < $n_from && $skip < $n_to; $skip++) {
      if ($from_lines[$skip] !== $to_lines[$skip]) {
        break;
      }
      $this->xchanged[$skip] = $this->ychanged[$skip] = FALSE;
    }
    // Skip trailing common lines.
    $xi = $n_from;
    $yi = $n_to;
    for ($endskip = 0; --$xi > $skip && --$yi > $skip; $endskip++) {
      if ($from_lines[$xi] !== $to_lines[$yi]) {
        break;
      }
      $this->xchanged[$xi] = $this->ychanged[$yi] = FALSE;
    }

    // Ignore lines which do not exist in both files.
    for ($xi = $skip; $xi < $n_from - $endskip; $xi++) {
      $xhash[$this->_line_hash($from_lines[$xi])] = 1;
    }

    for ($yi = $skip; $yi < $n_to - $endskip; $yi++) {
      $line = $to_lines[$yi];
      if ($this->ychanged[$yi] = empty($xhash[$this->_line_hash($line)])) {
        continue;
      }
      $yhash[$this->_line_hash($line)] = 1;
      $this->yv[] = $line;
      $this->yind[] = $yi;
    }
    for ($xi = $skip; $xi < $n_from - $endskip; $xi++) {
      $line = $from_lines[$xi];
      if ($this->xchanged[$xi] = empty($yhash[$this->_line_hash($line)])) {
        continue;
      }
      $this->xv[] = $line;
      $this->xind[] = $xi;
    }

    // Find the LCS.
    $this->_compareseq(0, sizeof($this->xv), 0, sizeof($this->yv));

    // Merge edits when possible
    $this->_shift_boundaries($from_lines, $this->xchanged, $this->ychanged);
    $this->_shift_boundaries($to_lines, $this->ychanged, $this->xchanged);

    // Compute the edit operations.
    $edits = array();
    $xi = $yi = 0;
    while ($xi < $n_from || $yi < $n_to) {
      USE_ASSERTS && assert($yi < $n_to || $this->xchanged[$xi]);
      USE_ASSERTS && assert($xi < $n_from || $this->ychanged[$yi]);

      // Skip matching "snake".
      $copy = array();
      while ( $xi < $n_from && $yi < $n_to && !$this->xchanged[$xi] && !$this->ychanged[$yi]) {
        $copy[] = $from_lines[$xi++];
        ++$yi;
      }
      if ($copy) {
        $edits[] = new _DiffOp_Copy($copy);
      }
      // Find deletes & adds.
      $delete = array();
      while ($xi < $n_from && $this->xchanged[$xi]) {
        $delete[] = $from_lines[$xi++];
      }
      $add = array();
      while ($yi < $n_to && $this->ychanged[$yi]) {
        $add[] = $to_lines[$yi++];
      }
      if ($delete && $add) {
        $edits[] = new _DiffOp_Change($delete, $add);
      }
      elseif ($delete) {
        $edits[] = new _DiffOp_Delete($delete);
      }
      elseif ($add) {
        $edits[] = new _DiffOp_Add($add);
      }
    }
    return $edits;
  }

  /**
   * Returns the whole line if it's small enough, or the MD5 hash otherwise.
   */
  function _line_hash($line) {
245
    if (Unicode::strlen($line) > $this->MAX_XREF_LENGTH()) {
246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966
      return md5($line);
    }
    else {
      return $line;
    }
  }


  /**
   * Divide the Largest Common Subsequence (LCS) of the sequences
   * [XOFF, XLIM) and [YOFF, YLIM) into NCHUNKS approximately equally
   * sized segments.
   *
   * Returns (LCS, PTS).  LCS is the length of the LCS. PTS is an
   * array of NCHUNKS+1 (X, Y) indexes giving the diving points between
   * sub sequences.  The first sub-sequence is contained in [X0, X1),
   * [Y0, Y1), the second in [X1, X2), [Y1, Y2) and so on.  Note
   * that (X0, Y0) == (XOFF, YOFF) and
   * (X[NCHUNKS], Y[NCHUNKS]) == (XLIM, YLIM).
   *
   * This function assumes that the first lines of the specified portions
   * of the two files do not match, and likewise that the last lines do not
   * match.  The caller must trim matching lines from the beginning and end
   * of the portions it is going to specify.
   */
  function _diag($xoff, $xlim, $yoff, $ylim, $nchunks) {
    $flip = FALSE;

    if ($xlim - $xoff > $ylim - $yoff) {
      // Things seems faster (I'm not sure I understand why)
      // when the shortest sequence in X.
      $flip = TRUE;
      list($xoff, $xlim, $yoff, $ylim) = array($yoff, $ylim, $xoff, $xlim);
    }

    if ($flip) {
      for ($i = $ylim - 1; $i >= $yoff; $i--) {
        $ymatches[$this->xv[$i]][] = $i;
      }
    }
    else {
      for ($i = $ylim - 1; $i >= $yoff; $i--) {
        $ymatches[$this->yv[$i]][] = $i;
      }
    }
    $this->lcs = 0;
    $this->seq[0]= $yoff - 1;
    $this->in_seq = array();
    $ymids[0] = array();

    $numer = $xlim - $xoff + $nchunks - 1;
    $x = $xoff;
    for ($chunk = 0; $chunk < $nchunks; $chunk++) {
      if ($chunk > 0) {
        for ($i = 0; $i <= $this->lcs; $i++) {
          $ymids[$i][$chunk-1] = $this->seq[$i];
        }
      }

      $x1 = $xoff + (int)(($numer + ($xlim-$xoff)*$chunk) / $nchunks);
      for ( ; $x < $x1; $x++) {
        $line = $flip ? $this->yv[$x] : $this->xv[$x];
        if (empty($ymatches[$line])) {
          continue;
        }
        $matches = $ymatches[$line];
        reset($matches);
        while (list ($junk, $y) = each($matches)) {
          if (empty($this->in_seq[$y])) {
            $k = $this->_lcs_pos($y);
            USE_ASSERTS && assert($k > 0);
            $ymids[$k] = $ymids[$k-1];
            break;
          }
        }
        while (list ($junk, $y) = each($matches)) {
          if ($y > $this->seq[$k-1]) {
            USE_ASSERTS && assert($y < $this->seq[$k]);
            // Optimization: this is a common case:
            // next match is just replacing previous match.
            $this->in_seq[$this->seq[$k]] = FALSE;
            $this->seq[$k] = $y;
            $this->in_seq[$y] = 1;
          }
          elseif (empty($this->in_seq[$y])) {
            $k = $this->_lcs_pos($y);
            USE_ASSERTS && assert($k > 0);
            $ymids[$k] = $ymids[$k-1];
          }
        }
      }
    }

    $seps[] = $flip ? array($yoff, $xoff) : array($xoff, $yoff);
    $ymid = $ymids[$this->lcs];
    for ($n = 0; $n < $nchunks - 1; $n++) {
      $x1 = $xoff + (int)(($numer + ($xlim - $xoff) * $n) / $nchunks);
      $y1 = $ymid[$n] + 1;
      $seps[] = $flip ? array($y1, $x1) : array($x1, $y1);
    }
    $seps[] = $flip ? array($ylim, $xlim) : array($xlim, $ylim);

    return array($this->lcs, $seps);
  }

  function _lcs_pos($ypos) {

    $end = $this->lcs;
    if ($end == 0 || $ypos > $this->seq[$end]) {
      $this->seq[++$this->lcs] = $ypos;
      $this->in_seq[$ypos] = 1;
      return $this->lcs;
    }

    $beg = 1;
    while ($beg < $end) {
      $mid = (int)(($beg + $end) / 2);
      if ($ypos > $this->seq[$mid]) {
        $beg = $mid + 1;
      }
      else {
        $end = $mid;
      }
    }

    USE_ASSERTS && assert($ypos != $this->seq[$end]);

    $this->in_seq[$this->seq[$end]] = FALSE;
    $this->seq[$end] = $ypos;
    $this->in_seq[$ypos] = 1;
    return $end;
  }

  /**
   * Find LCS of two sequences.
   *
   * The results are recorded in the vectors $this->{x,y}changed[], by
   * storing a 1 in the element for each line that is an insertion
   * or deletion (ie. is not in the LCS).
   *
   * The subsequence of file 0 is [XOFF, XLIM) and likewise for file 1.
   *
   * Note that XLIM, YLIM are exclusive bounds.
   * All line numbers are origin-0 and discarded lines are not counted.
   */
  function _compareseq($xoff, $xlim, $yoff, $ylim) {

    // Slide down the bottom initial diagonal.
    while ($xoff < $xlim && $yoff < $ylim && $this->xv[$xoff] == $this->yv[$yoff]) {
      ++$xoff;
      ++$yoff;
    }

    // Slide up the top initial diagonal.
    while ($xlim > $xoff && $ylim > $yoff && $this->xv[$xlim - 1] == $this->yv[$ylim - 1]) {
      --$xlim;
      --$ylim;
    }

    if ($xoff == $xlim || $yoff == $ylim) {
      $lcs = 0;
    }
    else {
      // This is ad hoc but seems to work well.
      //$nchunks = sqrt(min($xlim - $xoff, $ylim - $yoff) / 2.5);
      //$nchunks = max(2, min(8, (int)$nchunks));
      $nchunks = min(7, $xlim - $xoff, $ylim - $yoff) + 1;
      list($lcs, $seps)
      = $this->_diag($xoff, $xlim, $yoff, $ylim, $nchunks);
    }

    if ($lcs == 0) {
      // X and Y sequences have no common subsequence:
      // mark all changed.
      while ($yoff < $ylim) {
        $this->ychanged[$this->yind[$yoff++]] = 1;
      }
      while ($xoff < $xlim) {
        $this->xchanged[$this->xind[$xoff++]] = 1;
      }
    }
    else {
      // Use the partitions to split this problem into subproblems.
      reset($seps);
      $pt1 = $seps[0];
      while ($pt2 = next($seps)) {
        $this->_compareseq ($pt1[0], $pt2[0], $pt1[1], $pt2[1]);
        $pt1 = $pt2;
      }
    }
  }

  /**
   * Adjust inserts/deletes of identical lines to join changes
   * as much as possible.
   *
   * We do something when a run of changed lines include a
   * line at one end and has an excluded, identical line at the other.
   * We are free to choose which identical line is included.
   * `compareseq' usually chooses the one at the beginning,
   * but usually it is cleaner to consider the following identical line
   * to be the "change".
   *
   * This is extracted verbatim from analyze.c (GNU diffutils-2.7).
   */
  function _shift_boundaries($lines, &$changed, $other_changed) {
    $i = 0;
    $j = 0;

    USE_ASSERTS && assert('sizeof($lines) == sizeof($changed)');
    $len = sizeof($lines);
    $other_len = sizeof($other_changed);

    while (1) {
      /*
       * Scan forwards to find beginning of another run of changes.
       * Also keep track of the corresponding point in the other file.
       *
       * Throughout this code, $i and $j are adjusted together so that
       * the first $i elements of $changed and the first $j elements
       * of $other_changed both contain the same number of zeros
       * (unchanged lines).
       * Furthermore, $j is always kept so that $j == $other_len or
       * $other_changed[$j] == FALSE.
       */
      while ($j < $other_len && $other_changed[$j]) {
        $j++;
      }
      while ($i < $len && ! $changed[$i]) {
        USE_ASSERTS && assert('$j < $other_len && ! $other_changed[$j]');
        $i++;
        $j++;
        while ($j < $other_len && $other_changed[$j]) {
          $j++;
        }
      }

      if ($i == $len) {
        break;
      }
      $start = $i;

      // Find the end of this run of changes.
      while (++$i < $len && $changed[$i]) {
        continue;
      }

      do {
        /*
         * Record the length of this run of changes, so that
         * we can later determine whether the run has grown.
         */
        $runlength = $i - $start;

        /*
         * Move the changed region back, so long as the
         * previous unchanged line matches the last changed one.
         * This merges with previous changed regions.
         */
        while ($start > 0 && $lines[$start - 1] == $lines[$i - 1]) {
          $changed[--$start] = 1;
          $changed[--$i] = FALSE;
          while ($start > 0 && $changed[$start - 1]) {
            $start--;
          }
          USE_ASSERTS && assert('$j > 0');
          while ($other_changed[--$j]) {
            continue;
          }
          USE_ASSERTS && assert('$j >= 0 && !$other_changed[$j]');
        }

        /*
         * Set CORRESPONDING to the end of the changed run, at the last
         * point where it corresponds to a changed run in the other file.
         * CORRESPONDING == LEN means no such point has been found.
         */
        $corresponding = $j < $other_len ? $i : $len;

        /*
         * Move the changed region forward, so long as the
         * first changed line matches the following unchanged one.
         * This merges with following changed regions.
         * Do this second, so that if there are no merges,
         * the changed region is moved forward as far as possible.
         */
        while ($i < $len && $lines[$start] == $lines[$i]) {
          $changed[$start++] = FALSE;
          $changed[$i++] = 1;
          while ($i < $len && $changed[$i]) {
            $i++;
          }
          USE_ASSERTS && assert('$j < $other_len && ! $other_changed[$j]');
          $j++;
          if ($j < $other_len && $other_changed[$j]) {
            $corresponding = $i;
            while ($j < $other_len && $other_changed[$j]) {
              $j++;
            }
          }
        }
      } while ($runlength != $i - $start);

      /*
       * If possible, move the fully-merged run of changes
       * back to a corresponding run in the other file.
       */
      while ($corresponding < $i) {
        $changed[--$start] = 1;
        $changed[--$i] = 0;
        USE_ASSERTS && assert('$j > 0');
        while ($other_changed[--$j]) {
          continue;
        }
        USE_ASSERTS && assert('$j >= 0 && !$other_changed[$j]');
      }
    }
  }
}

/**
 * Class representing a 'diff' between two sequences of strings.
 * @todo document
 * @private
 * @subpackage DifferenceEngine
 */
class Diff {
  var $edits;

  /**
   * Constructor.
   * Computes diff between sequences of strings.
   *
   * @param $from_lines array An array of strings.
   *      (Typically these are lines from a file.)
   * @param $to_lines array An array of strings.
   */
  function Diff($from_lines, $to_lines) {
    $eng = new _DiffEngine;
    $this->edits = $eng->diff($from_lines, $to_lines);
    //$this->_check($from_lines, $to_lines);
  }

  /**
   * Compute reversed Diff.
   *
   * SYNOPSIS:
   *
   *  $diff = new Diff($lines1, $lines2);
   *  $rev = $diff->reverse();
   * @return object A Diff object representing the inverse of the
   *          original diff.
   */
  function reverse() {
    $rev = $this;
    $rev->edits = array();
    foreach ($this->edits as $edit) {
      $rev->edits[] = $edit->reverse();
    }
    return $rev;
  }

  /**
   * Check for empty diff.
   *
   * @return bool True iff two sequences were identical.
   */
  function isEmpty() {
    foreach ($this->edits as $edit) {
      if ($edit->type != 'copy') {
        return FALSE;
      }
    }
    return TRUE;
  }

  /**
   * Compute the length of the Longest Common Subsequence (LCS).
   *
   * This is mostly for diagnostic purposed.
   *
   * @return int The length of the LCS.
   */
  function lcs() {
    $lcs = 0;
    foreach ($this->edits as $edit) {
      if ($edit->type == 'copy') {
        $lcs += sizeof($edit->orig);
      }
    }
    return $lcs;
  }

  /**
   * Get the original set of lines.
   *
   * This reconstructs the $from_lines parameter passed to the
   * constructor.
   *
   * @return array The original sequence of strings.
   */
  function orig() {
    $lines = array();

    foreach ($this->edits as $edit) {
      if ($edit->orig) {
        array_splice($lines, sizeof($lines), 0, $edit->orig);
      }
    }
    return $lines;
  }

  /**
   * Get the closing set of lines.
   *
   * This reconstructs the $to_lines parameter passed to the
   * constructor.
   *
   * @return array The sequence of strings.
   */
  function closing() {
    $lines = array();

    foreach ($this->edits as $edit) {
      if ($edit->closing) {
        array_splice($lines, sizeof($lines), 0, $edit->closing);
      }
    }
    return $lines;
  }

  /**
   * Check a Diff for validity.
   *
   * This is here only for debugging purposes.
   */
  function _check($from_lines, $to_lines) {
    if (serialize($from_lines) != serialize($this->orig())) {
      trigger_error("Reconstructed original doesn't match", E_USER_ERROR);
    }
    if (serialize($to_lines) != serialize($this->closing())) {
      trigger_error("Reconstructed closing doesn't match", E_USER_ERROR);
    }

    $rev = $this->reverse();
    if (serialize($to_lines) != serialize($rev->orig())) {
      trigger_error("Reversed original doesn't match", E_USER_ERROR);
    }
    if (serialize($from_lines) != serialize($rev->closing())) {
      trigger_error("Reversed closing doesn't match", E_USER_ERROR);
    }


    $prevtype = 'none';
    foreach ($this->edits as $edit) {
      if ( $prevtype == $edit->type ) {
        trigger_error("Edit sequence is non-optimal", E_USER_ERROR);
      }
      $prevtype = $edit->type;
    }

    $lcs = $this->lcs();
    trigger_error('Diff okay: LCS = ' . $lcs, E_USER_NOTICE);
  }
}

/**
 * FIXME: bad name.
 * @todo document
 * @private
 * @subpackage DifferenceEngine
 */
class MappedDiff extends Diff {
  /**
   * Constructor.
   *
   * Computes diff between sequences of strings.
   *
   * This can be used to compute things like
   * case-insensitve diffs, or diffs which ignore
   * changes in white-space.
   *
   * @param $from_lines array An array of strings.
   *  (Typically these are lines from a file.)
   *
   * @param $to_lines array An array of strings.
   *
   * @param $mapped_from_lines array This array should
   *  have the same size number of elements as $from_lines.
   *  The elements in $mapped_from_lines and
   *  $mapped_to_lines are what is actually compared
   *  when computing the diff.
   *
   * @param $mapped_to_lines array This array should
   *  have the same number of elements as $to_lines.
   */
  function MappedDiff($from_lines, $to_lines, $mapped_from_lines, $mapped_to_lines) {

    assert(sizeof($from_lines) == sizeof($mapped_from_lines));
    assert(sizeof($to_lines) == sizeof($mapped_to_lines));

    $this->Diff($mapped_from_lines, $mapped_to_lines);

    $xi = $yi = 0;
    for ($i = 0; $i < sizeof($this->edits); $i++) {
      $orig = &$this->edits[$i]->orig;
      if (is_array($orig)) {
        $orig = array_slice($from_lines, $xi, sizeof($orig));
        $xi += sizeof($orig);
      }

      $closing = &$this->edits[$i]->closing;
      if (is_array($closing)) {
        $closing = array_slice($to_lines, $yi, sizeof($closing));
        $yi += sizeof($closing);
      }
    }
  }
}

/**
 * A class to format Diffs
 *
 * This class formats the diff in classic diff format.
 * It is intended that this class be customized via inheritance,
 * to obtain fancier outputs.
 * @todo document
 * @private
 * @subpackage DifferenceEngine
 */
class DiffFormatter {
  /**
   * Should a block header be shown?
   */
  var $show_header = TRUE;

  /**
   * Number of leading context "lines" to preserve.
   *
   * This should be left at zero for this class, but subclasses
   * may want to set this to other values.
   */
  var $leading_context_lines = 0;

  /**
   * Number of trailing context "lines" to preserve.
   *
   * This should be left at zero for this class, but subclasses
   * may want to set this to other values.
   */
  var $trailing_context_lines = 0;

  /**
   * Format a diff.
   *
   * @param $diff object A Diff object.
   * @return string The formatted output.
   */
  function format($diff) {
    $xi = $yi = 1;
    $block = FALSE;
    $context = array();

    $nlead = $this->leading_context_lines;
    $ntrail = $this->trailing_context_lines;

    $this->_start_diff();

    foreach ($diff->edits as $edit) {
      if ($edit->type == 'copy') {
        if (is_array($block)) {
          if (sizeof($edit->orig) <= $nlead + $ntrail) {
            $block[] = $edit;
          }
          else {
            if ($ntrail) {
              $context = array_slice($edit->orig, 0, $ntrail);
              $block[] = new _DiffOp_Copy($context);
            }
            $this->_block($x0, $ntrail + $xi - $x0, $y0, $ntrail + $yi - $y0, $block);
            $block = FALSE;
          }
        }
        $context = $edit->orig;
      }
      else {
        if (! is_array($block)) {
          $context = array_slice($context, sizeof($context) - $nlead);
          $x0 = $xi - sizeof($context);
          $y0 = $yi - sizeof($context);
          $block = array();
          if ($context) {
            $block[] = new _DiffOp_Copy($context);
          }
        }
        $block[] = $edit;
      }

      if ($edit->orig) {
        $xi += sizeof($edit->orig);
      }
      if ($edit->closing) {
        $yi += sizeof($edit->closing);
      }
    }

    if (is_array($block)) {
      $this->_block($x0, $xi - $x0, $y0, $yi - $y0, $block);
    }
    $end = $this->_end_diff();

    if (!empty($xi)) {
      $this->line_stats['counter']['x'] += $xi;
    }
    if (!empty($yi)) {
      $this->line_stats['counter']['y'] += $yi;
    }

    return $end;
  }

  function _block($xbeg, $xlen, $ybeg, $ylen, &$edits) {
    $this->_start_block($this->_block_header($xbeg, $xlen, $ybeg, $ylen));
    foreach ($edits as $edit) {
      if ($edit->type == 'copy') {
        $this->_context($edit->orig);
      }
      elseif ($edit->type == 'add') {
        $this->_added($edit->closing);
      }
      elseif ($edit->type == 'delete') {
        $this->_deleted($edit->orig);
      }
      elseif ($edit->type == 'change') {
        $this->_changed($edit->orig, $edit->closing);
      }
      else {
        trigger_error('Unknown edit type', E_USER_ERROR);
      }
    }
    $this->_end_block();
  }

  function _start_diff() {
    ob_start();
  }

  function _end_diff() {
    $val = ob_get_contents();
    ob_end_clean();
    return $val;
  }

  function _block_header($xbeg, $xlen, $ybeg, $ylen) {
    if ($xlen > 1) {
      $xbeg .= "," . ($xbeg + $xlen - 1);
    }
    if ($ylen > 1) {
      $ybeg .= "," . ($ybeg + $ylen - 1);
    }

    return $xbeg . ($xlen ? ($ylen ? 'c' : 'd') : 'a') . $ybeg;
  }

  function _start_block($header) {
    if ($this->show_header) {
      echo $header . "\n";
    }
  }

  function _end_block() {
  }

  function _lines($lines, $prefix = ' ') {
    foreach ($lines as $line) {
      echo "$prefix $line\n";
    }
  }

  function _context($lines) {
    $this->_lines($lines);
  }

  function _added($lines) {
    $this->_lines($lines, '>');
  }
  function _deleted($lines) {
    $this->_lines($lines, '<');
  }

  function _changed($orig, $closing) {
    $this->_deleted($orig);
    echo "---\n";
    $this->_added($closing);
  }
}


/**
 *  Additions by Axel Boldt follow, partly taken from diff.php, phpwiki-1.3.3
 *
 */

define('NBSP', '&#160;');      // iso-8859-x non-breaking space.

/**
 * @todo document
 * @private
 * @subpackage DifferenceEngine
 */
class _HWLDF_WordAccumulator {
  function _HWLDF_WordAccumulator() {
    $this->_lines = array();
    $this->_line = '';
    $this->_group = '';
    $this->_tag = '';
  }

  function _flushGroup($new_tag) {
    if ($this->_group !== '') {
      if ($this->_tag == 'mark') {
967
        $this->_line .= '<span class="diffchange">' . String::checkPlain($this->_group) . '</span>';
968 969
      }
      else {
970
        $this->_line .= String::checkPlain($this->_group);
971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999
      }
    }
    $this->_group = '';
    $this->_tag = $new_tag;
  }

  function _flushLine($new_tag) {
    $this->_flushGroup($new_tag);
    if ($this->_line != '') {
      array_push($this->_lines, $this->_line);
    }
    else {
      // make empty lines visible by inserting an NBSP
      array_push($this->_lines, NBSP);
    }
    $this->_line = '';
  }

  function addWords($words, $tag = '') {
    if ($tag != $this->_tag) {
      $this->_flushGroup($tag);
    }
    foreach ($words as $word) {
      // new-line should only come as first char of word.
      if ($word == '') {
        continue;
      }
      if ($word[0] == "\n") {
        $this->_flushLine($tag);
1000
        $word = Unicode::substr($word, 1);
1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043
      }
      assert(!strstr($word, "\n"));
      $this->_group .= $word;
    }
  }

  function getLines() {
    $this->_flushLine('~done');
    return $this->_lines;
  }
}

/**
 * @todo document
 * @private
 * @subpackage DifferenceEngine
 */
class WordLevelDiff extends MappedDiff {
  function MAX_LINE_LENGTH() {
    return 10000;
  }

  function WordLevelDiff($orig_lines, $closing_lines) {
    list($orig_words, $orig_stripped) = $this->_split($orig_lines);
    list($closing_words, $closing_stripped) = $this->_split($closing_lines);

    $this->MappedDiff($orig_words, $closing_words, $orig_stripped, $closing_stripped);
  }

  function _split($lines) {
    $words = array();
    $stripped = array();
    $first = TRUE;
    foreach ($lines as $line) {
      // If the line is too long, just pretend the entire line is one big word
      // This prevents resource exhaustion problems
      if ( $first ) {
        $first = FALSE;
      }
      else {
        $words[] = "\n";
        $stripped[] = "\n";
      }
1044
      if ( Unicode::strlen( $line ) > $this->MAX_LINE_LENGTH() ) {
1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102
        $words[] = $line;
        $stripped[] = $line;
      }
      else {
        if (preg_match_all('/ ( [^\S\n]+ | [0-9_A-Za-z\x80-\xff]+ | . ) (?: (?!< \n) [^\S\n])? /xs', $line, $m)) {
          $words = array_merge($words, $m[0]);
          $stripped = array_merge($stripped, $m[1]);
        }
      }
    }
    return array($words, $stripped);
  }

  function orig() {
    $orig = new _HWLDF_WordAccumulator;

    foreach ($this->edits as $edit) {
      if ($edit->type == 'copy') {
        $orig->addWords($edit->orig);
      }
      elseif ($edit->orig) {
        $orig->addWords($edit->orig, 'mark');
      }
    }
    $lines = $orig->getLines();
    return $lines;
  }

  function closing() {
    $closing = new _HWLDF_WordAccumulator;

    foreach ($this->edits as $edit) {
      if ($edit->type == 'copy') {
        $closing->addWords($edit->closing);
      }
      elseif ($edit->closing) {
        $closing->addWords($edit->closing, 'mark');
      }
    }
    $lines = $closing->getLines();
    return $lines;
  }
}

/**
 * Diff formatter which uses Drupal theme functions.
 * @private
 * @subpackage DifferenceEngine
 */
class DrupalDiffFormatter extends DiffFormatter {

  var $rows;
  var $line_stats = array(
    'counter' => array('x' => 0, 'y' => 0),
    'offset' => array('x' => 0, 'y' => 0),
  );

  function DrupalDiffFormatter() {
1103 1104
    $this->leading_context_lines = Settings::get('diff_context_lines_leading', 2);
    $this->trailing_context_lines = Settings::get('diff_context_lines_trailing', 2);
1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117
  }

  function _start_diff() {
    $this->rows = array();
  }

  function _end_diff() {
    return $this->rows;
  }

  function _block_header($xbeg, $xlen, $ybeg, $ylen) {
    return array(
      array(
1118
        'data' => $xbeg + $this->line_stats['offset']['x'],
1119 1120 1121
        'colspan' => 2,
      ),
      array(
1122
        'data' => $ybeg + $this->line_stats['offset']['y'],
1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149
        'colspan' => 2,
      )
    );
  }

  function _start_block($header) {
    if ($this->show_header) {
      $this->rows[] = $header;
    }
  }

  function _end_block() {
  }

  function _lines($lines, $prefix=' ', $color='white') {
  }

  /**
   * Note: you should HTML-escape parameter before calling this.
   */
  function addedLine($line) {
    return array(
      array(
        'data' => '+',
        'class' => 'diff-marker',
      ),
      array(
1150
        'data' => $line,
1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165
        'class' => 'diff-context diff-addedline',
      )
    );
  }

  /**
   * Note: you should HTML-escape parameter before calling this.
   */
  function deletedLine($line) {
    return array(
      array(
        'data' => '-',
        'class' => 'diff-marker',
      ),
      array(
1166
        'data' => $line,
1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178
        'class' => 'diff-context diff-deletedline',
      )
    );
  }

  /**
   * Note: you should HTML-escape parameter before calling this.
   */
  function contextLine($line) {
    return array(
      '&nbsp;',
      array(
1179
        'data' => $line,
1180 1181 1182 1183 1184 1185 1186 1187
        'class' => 'diff-context',
      )
    );
  }

  function emptyLine() {
    return array(
      '&nbsp;',
1188
      '&nbsp;',
1189 1190 1191 1192 1193
    );
  }

  function _added($lines) {
    foreach ($lines as $line) {
1194
      $this->rows[] = array_merge($this->emptyLine(), $this->addedLine(String::checkPlain($line)));
1195 1196 1197 1198 1199
    }
  }

  function _deleted($lines) {
    foreach ($lines as $line) {
1200
      $this->rows[] = array_merge($this->deletedLine(String::checkPlain($line)), $this->emptyLine());
1201 1202 1203 1204 1205
    }
  }

  function _context($lines) {
    foreach ($lines as $line) {
1206
      $this->rows[] = array_merge($this->contextLine(String::checkPlain($line)), $this->contextLine(String::checkPlain($line)));
1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226
    }
  }

  function _changed($orig, $closing) {
    $diff = new WordLevelDiff($orig, $closing);
    $del = $diff->orig();
    $add = $diff->closing();

    // Notice that WordLevelDiff returns HTML-escaped output.
    // Hence, we will be calling addedLine/deletedLine without HTML-escaping.

    while ($line = array_shift($del)) {
      $aline = array_shift( $add );
      $this->rows[] = array_merge($this->deletedLine($line), isset($aline) ? $this->addedLine($aline) : $this->emptyLine());
    }
    foreach ($add as $line) {  // If any leftovers
      $this->rows[] = array_merge($this->emptyLine(), $this->addedLine($line));
    }
  }
}