Index: DiffEngine.php =================================================================== RCS file: /cvs/drupal-contrib/contributions/modules/diff/DiffEngine.php,v retrieving revision 1.1 diff -u -p -r1.1 DiffEngine.php --- DiffEngine.php 31 Jan 2007 17:45:25 -0000 1.1 +++ DiffEngine.php 7 Mar 2007 08:24:27 -0000 @@ -10,116 +10,111 @@ */ /** - * @todo document - * @private - * @subpackage DifferenceEngine + * The code style has been adapted to fit Drupal's coding standards. + * Some unneeded code has been removed, mainly debugging related. + */ + +/** + * An operation of the 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; - } + 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 + * A copy operation. */ class _DiffOp_Copy extends _DiffOp { - var $type = 'copy'; + var $type = 'copy'; + + function _DiffOp_Copy ($orig, $closing = false) { + if (!is_array($closing)) { + $closing = $orig; + } + $this->orig = $orig; + $this->closing = $closing; + } - function _DiffOp_Copy ($orig, $closing = false) { - if (!is_array($closing)) - $closing = $orig; - $this->orig = $orig; - $this->closing = $closing; - } - - function reverse() { - return new _DiffOp_Copy($this->closing, $this->orig); - } + function reverse() { + return new _DiffOp_Copy($this->closing, $this->orig); + } } /** - * @todo document - * @private - * @subpackage DifferenceEngine + * A deletion operation. */ class _DiffOp_Delete extends _DiffOp { - var $type = 'delete'; + var $type = 'delete'; + + function _DiffOp_Delete ($lines) { + $this->orig = $lines; + $this->closing = false; + } - function _DiffOp_Delete ($lines) { - $this->orig = $lines; - $this->closing = false; - } - - function reverse() { - return new _DiffOp_Add($this->orig); - } + function reverse() { + return new _DiffOp_Add($this->orig); + } } /** - * @todo document - * @private - * @subpackage DifferenceEngine + * An addition operation. */ class _DiffOp_Add extends _DiffOp { - var $type = 'add'; + var $type = 'add'; - function _DiffOp_Add ($lines) { - $this->closing = $lines; - $this->orig = false; - } - - function reverse() { - return new _DiffOp_Delete($this->closing); - } + function _DiffOp_Add ($lines) { + $this->closing = $lines; + $this->orig = false; + } + + function reverse() { + return new _DiffOp_Delete($this->closing); + } } /** - * @todo document - * @private - * @subpackage DifferenceEngine + * A change operation. */ class _DiffOp_Change extends _DiffOp { - var $type = 'change'; + var $type = 'change'; - function _DiffOp_Change ($orig, $closing) { - $this->orig = $orig; - $this->closing = $closing; - } - - function reverse() { - return new _DiffOp_Change($this->closing, $this->orig); - } -} + function _DiffOp_Change ($orig, $closing) { + $this->orig = $orig; + $this->closing = $closing; + } + function reverse() { + return new _DiffOp_Change($this->closing, $this->orig); + } +} /** * Class used internally by Diff to actually compute the diffs. * * The algorithm used here is mostly lifted from the perl module * Algorithm::Diff (version 1.06) by Ned Konz, which is available at: - * http://www.perl.com/CPAN/authors/id/N/NE/NEDKONZ/Algorithm-Diff-1.06.zip + * http://www.perl.com/CPAN/authors/id/N/NE/NEDKONZ/Algorithm-Diff-1.06.zip * * More ideas are taken from: - * http://www.ics.uci.edu/~eppstein/161/960229.html + * http://www.ics.uci.edu/~eppstein/161/960229.html * * Some ideas are (and a bit of code) are from from analyze.c, from GNU * diffutils-2.7, which can be found at: - * ftp://gnudist.gnu.org/pub/gnu/diffutils/diffutils-2.7.tar.gz + * ftp://gnudist.gnu.org/pub/gnu/diffutils/diffutils-2.7.tar.gz * * closingly, some ideas (subdivision by NCHUNKS > 2, and some optimizations) * are my own. @@ -127,600 +122,736 @@ class _DiffOp_Change extends _DiffOp { * Line length limits for robustness added by Tim Starling, 2005-08-31 * * @author Geoffrey T. Dairiki, Tim Starling - * @private - * @subpackage DifferenceEngine */ class _DiffEngine { - function MAX_XREF_LENGTH() { - return 10000; + function MAX_XREF_LENGTH() { + return 10000; + } + + function diff ($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) { + + // 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 ) { + if ( strlen( $line ) > $this->MAX_XREF_LENGTH() ) { + 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); + $ymids[$k] = $ymids[$k-1]; + break; + } + } + while (list ($junk, $y) = each($matches)) { + if ($y > $this->seq[$k-1]) { + // 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; + } + else if (empty($this->in_seq[$y])) { + $k = $this->_lcs_pos($y); + $ymids[$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, $seps); } - function diff ($from_lines, $to_lines) { + function _lcs_pos ($ypos) { - $n_from = sizeof($from_lines); - $n_to = sizeof($to_lines); + $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; + } + } + + $this->in_seq[$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) { - $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 ) { - if ( strlen( $line ) > $this->MAX_XREF_LENGTH() ) { - 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; - } else if (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]'); - } - } - } + // 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; + + $len = sizeof($lines); + $other_len = sizeof($other_changed); + + while (TRUE) { + /* + * 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]) { + $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]) { + $start--; + } + while ($other_changed[--$j]) { + continue; + } + } + + /* + * 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++; + } + + $j++; + if ($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; + while ($other_changed[--$j]) { + continue; + } + } + } + } } /** * 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); - } + /** + * List of edit operations. + */ + 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); + } + + /** + * 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; + } + } + /** - * FIXME: bad name. - * @todo document - * @private - * @subpackage DifferenceEngine + * Class representing a 'diff' between two sequences of strings. + * The sequence of strings which is compared may be different than + * the sequence of strings whose diff is shown. */ 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); - } - } - } + /** + * 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 diff between the individual words of the line sequence. + */ +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"; + } + if ( strlen( $line ) > $this->MAX_LINE_LENGTH() ) { + $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; + } +} + +/** + * Helper class for WordLevelDiff. + */ +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') { + $this->_line .= '' . + check_plain ( $this->_group ) . ''; + } + else { + $this->_line .= check_plain ( $this->_group ); + } + } + $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, ' ' ); + } + $this->_line = ''; + } + + function addWords ($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); + $word = substr($word, 1); + } + assert(!strstr($word, "\n")); + $this->_group .= $word; + } + } + + function getLines() { + $this->_flushLine('~done'); + return $this->_lines; + } } /** @@ -729,393 +860,374 @@ class MappedDiff extends Diff * 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(); - 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 $header; - } - - function _end_block() { - } - - function _lines($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); - } -} + /** + * 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; -/** - * Additions by Axel Boldt follow, partly taken from diff.php, phpwiki-1.3.3 - * - */ + /** + * 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; -define('NBSP', ' '); // iso-8859-x non-breaking space. + /** + * Format a diff. + * + * @param $diff object A Diff object. + * @return string The formatted output. + */ + function format($diff) { -/** - * @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') - $this->_line .= '' . - check_plain ( $this->_group ) . ''; - else - $this->_line .= check_plain ( $this->_group ); - } - $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); - $word = substr($word, 1); - } - assert(!strstr($word, "\n")); - $this->_group .= $word; - } - } - - function getLines() { - $this->_flushLine('~done'); - return $this->_lines; - } + $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(); + 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 $header; + } + } + + function _end_block() { + } + + function _lines($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); + } } /** - * @todo document + * Wikipedia Table style diff formatter. * @private * @subpackage DifferenceEngine */ -class WordLevelDiff extends MappedDiff +class TableDiffFormatter extends DiffFormatter { - function MAX_LINE_LENGTH() { - return 10000; + function TableDiffFormatter() { + $this->leading_context_lines = 2; + $this->trailing_context_lines = 2; } - function WordLevelDiff ($orig_lines, $closing_lines) { + function _block_header( $xbeg, $xlen, $ybeg, $ylen ) { + $r = 'Line '.$xbeg."\n" . + 'Line '.$ybeg."\n"; + return $r; + } - list ($orig_words, $orig_stripped) = $this->_split($orig_lines); - list ($closing_words, $closing_stripped) = $this->_split($closing_lines); + function _start_block( $header ) { + if ($this->show_header) { + echo $header; + } + } - $this->MappedDiff($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"; - } - if ( strlen( $line ) > $this->MAX_LINE_LENGTH() ) { - $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; - } + function _end_block() { + } + + function _lines( $lines, $prefix=' ', $color='white' ) { + } + + /** + * Note: you should HTML-escape parameter before calling this. + */ + function addedLine($line) { + return "+{$line}"; + } + + /** + * Note: you should HTML-escape parameter before calling this. + */ + function deletedLine($line) { + return "-{$line}"; + } + + /** + * Note: you should HTML-escape parameter before calling this. + */ + function contextLine($line) { + return " {$line}"; + } + + function emptyLine() { + return ' '; + } + + function _added($lines) { + foreach ($lines as $line) { + echo '' . $this->emptyLine() . + $this->addedLine( check_plain ( $line ) ) . "\n"; + } + } + + function _deleted($lines) { + foreach ($lines as $line) { + echo '' . $this->deletedLine( check_plain ( $line ) ) . + $this->emptyLine() . "\n"; + } + } + + function _context($lines) { + foreach ($lines as $line) { + echo '' . + $this->contextLine( check_plain ( $line ) ) . + $this->contextLine( check_plain ( $line ) ) . "\n"; + } + } + + function _changed($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 ); + echo '' . $this->deletedLine( $line ) . + $this->addedLine( $aline ) . "\n"; + } + foreach ($add as $line) { // If any leftovers + echo '' . $this->emptyLine() . + $this->addedLine( $line ) . "\n"; + } + } } + /** - * Wikipedia Table style diff formatter. - * @todo document + * Diff formatter which uses Drupal theme functions. * @private * @subpackage DifferenceEngine */ -class TableDiffFormatter extends DiffFormatter +class DrupalDiffFormatter extends DiffFormatter { - function TableDiffFormatter() { - $this->leading_context_lines = 2; - $this->trailing_context_lines = 2; - } - - function _block_header( $xbeg, $xlen, $ybeg, $ylen ) { - $r = 'Line '.$xbeg."\n" . - 'Line '.$ybeg."\n"; - return $r; - } - - function _start_block( $header ) { - if ($this->show_header) - echo $header; - } - - function _end_block() { - } - - function _lines( $lines, $prefix=' ', $color='white' ) { - } - - # HTML-escape parameter before calling this - function addedLine( $line ) { - return "+{$line}"; - } - - # HTML-escape parameter before calling this - function deletedLine( $line ) { - return "-{$line}"; - } - - # HTML-escape parameter before calling this - function contextLine( $line ) { - return " {$line}"; - } - - function emptyLine() { - return ' '; - } - - function _added( $lines ) { - foreach ($lines as $line) { - echo '' . $this->emptyLine() . - $this->addedLine( check_plain ( $line ) ) . "\n"; - } - } - - function _deleted($lines) { - foreach ($lines as $line) { - echo '' . $this->deletedLine( check_plain ( $line ) ) . - $this->emptyLine() . "\n"; - } - } - - function _context( $lines ) { - foreach ($lines as $line) { - echo '' . - $this->contextLine( check_plain ( $line ) ) . - $this->contextLine( check_plain ( $line ) ) . "\n"; - } - } - - 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 ); - echo '' . $this->deletedLine( $line ) . - $this->addedLine( $aline ) . "\n"; - } - foreach ($add as $line) { # If any leftovers - echo '' . $this->emptyLine() . - $this->addedLine( $line ) . "\n"; - } - } + function DrupalDiffFormatter() { + $this->leading_context_lines = 2; + $this->trailing_context_lines = 2; + } + + function _block_header( $xbeg, $xlen, $ybeg, $ylen ) { + return theme('diff_title_row', t('Line %nr', array('%nr' => $xbeg)), t('Line %nr', array('%nr' => $ybeg))); + } + + function _start_block( $header ) { + if ($this->show_header) { + echo $header; + } + } + + function _end_block() { + } + + function _lines( $lines, $prefix=' ', $color='white' ) { + } + + /** + * Note: you should HTML-escape parameter before calling this. + */ + function addedLine($line) { + return array( + 'data' => $line, + 'class' => 'diff-addedline', + 'mark' => '+' + ); + } + + /** + * Note: you should HTML-escape parameter before calling this. + */ + function deletedLine($line) { + return array( + 'data' => $line, + 'class' => 'diff-deletedline', + 'mark' => '-' + ); + } + + /** + * Note: you should HTML-escape parameter before calling this. + */ + function contextLine($line) { + return array( + 'data' => $line, + 'class' => 'diff-context', + 'mark' => ' ' + ); + } + + function emptyLine() { + return array( + 'data' => ' ', + 'mark' => ' ' + ); + } + + function _added($lines) { + foreach ($lines as $line) { + echo theme('diff_data_row', $this->emptyLine(), $this->addedLine(check_plain($line))); + } + } + + function _deleted($lines) { + foreach ($lines as $line) { + echo theme('diff_data_row', $this->deletedLine(check_plain ($line)), $this->emptyLine()); + } + } + + function _context($lines) { + foreach ($lines as $line) { + echo theme('diff_data_row', $this->contextLine(check_plain($line)), $this->contextLine(check_plain($line))); + } + } + + 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 ); + echo theme('diff_data_row', $this->deletedLine($line), $this->addedLine($aline)); + } + foreach ($add as $line) { // If any leftovers + echo theme('diff_data_row', $this->emptyLine(), $this->addedLine($line)); + } + } } Index: diff.module =================================================================== RCS file: /cvs/drupal-contrib/contributions/modules/diff/diff.module,v retrieving revision 1.15 diff -u -p -r1.15 diff.module --- diff.module 3 Feb 2007 19:47:58 -0000 1.15 +++ diff.module 7 Mar 2007 08:24:27 -0000 @@ -1,5 +1,5 @@ '; - $output .= ''. $old_header .''. $new_header .''; - if ($new_log || $old_log) { - $output .= ''. $old_log .''. $new_log .''; - } - $output .= ''. $prev_link .''. $next_link .''; - $output .= _diff_table_body($old_node, $new_node); - $output .= ''; - $output .= '
'; + $output .= theme('diff_header', $old_header, $new_header); + if ($old_log || $new_log) { + $output .= theme('diff_data_row', + array('data' => $old_log), + array('data' => $new_log) + ); + } + $output .= theme('diff_data_row', + array('data' => $prev_link, 'class' => 'diff-prevlink'), + array('data' => $next_link, 'class' => 'diff-nextlink') + ); + $output .= _diff_body_output($old_node, $new_node); + $output .= theme('diff_footer'); if ($node->vid == $new_vid) { $output .= '
'. t('Current revision:') .'
'; @@ -346,10 +349,13 @@ function diff_diffs_show(&$node, $old_vi * Create the table body of the diff between $old_node and $new_node. * The result is a html table part enclosed in tags. */ -function _diff_table_body(&$old_node, &$new_node) { - drupal_add_css(drupal_get_path('module', 'diff') .'/diff.css', 'module', 'all', FALSE); +function _diff_body_output(&$old_node, &$new_node) { + drupal_add_css(drupal_get_path('module', 'diff') . '/diff.css', 'module', 'all', FALSE); include_once('DiffEngine.php'); include_once('node.inc'); + if (module_exists('taxonomy')) { + include_once('taxonomy.inc'); + } if (module_exists('upload')) { include_once('upload.inc'); } @@ -357,26 +363,24 @@ function _diff_table_body(&$old_node, &$ include_once('cck.inc'); } - $output = ''; $any_visible_change = false; $node_diffs = module_invoke_all('diff', $old_node, $new_node); foreach($node_diffs as $node_diff) { $diff = new Diff($node_diff['old'], $node_diff['new']); - $formatter = new TableDiffFormatter(); + $formatter = new DrupalDiffFormatter(); if (isset($node_diff['format'])) { $formatter->show_header = $node_diff['format']['show_header']; } $formatter_output = $formatter->format($diff); if ($formatter_output) { - $output .= ''. t('Changes to %name', array('%name' => $node_diff['name'])) .''; + $output .= theme('diff_title_row', t('Changes to %name', array('%name' => $node_diff['name']))); $output .= $formatter_output; $any_visible_change = true; } } if (!$any_visible_change) { - $output .= '' .t('No visible changes') .''; + $output .= theme('diff_title_row', t('No visible changes')); } - $output .= ''; return $output; } @@ -412,21 +416,79 @@ function _diff_get_previous_vid(&$node_r /** * Implementation of hook_form_alter(). - * Used to add a 'Preview changes' button on the node edit form. */ function diff_form_alter($form_id, &$form) { if (isset($form['type']) && $form['type']['#value'] .'_node_form' == $form_id) { - if (user_access('view revisions') && $form['nid']['#value'] > 0) { + // Node editing form: Add a 'Preview changes' button on the node edit form. + if (variable_get('show_preview_changes_'.$form['type']['#value'], TRUE) && $form['nid']['#value'] > 0) { $form['preview_changes'] = array('#type' => 'button', '#value' => t('Preview changes'), '#weight' => 41); // Change the form render callback to display the new button $form['#theme'] = 'diff_node_form'; // Hijack the callback to handle showing of the diff if requested. $form['#after_build'] = array('diff_node_form_add_changes'); } - } + } + elseif ($form_id == 'node_type_form' && isset($form['identity']['type']) && module_exists('comment')) { + // Node edit form + // Add checkbox to activate 'preview changes' button per node type + $form['workflow']['show_preview_changes'] = array( + '#type' => 'checkbox', + '#title' => t('Show %preview_changes button on node edit form', array('%preview_changes' => t('Preview changes'))), + '#prefix' => '' . t('Diff') . '', + '#weight' => 10, + '#default_value' => variable_get('show_preview_changes_'.$form['#node_type']->type, TRUE), + ); + } + elseif ($form_id == 'filter_admin_configure') { + // Filter configuration form + // The fourth path entry is the format id (admin/settings/filter/#nr/configure) + $format_id = arg(3); + $form['diff'] = array( + '#type' => 'fieldset', + '#title' => t('Difference type'), + '#weight' => -5, + ); + $form['diff']["diff_format_type_$format_id"] = array( + '#type' => 'radios', + '#title' => 'Diff display type', + '#options' => array( + 'source' => t('Source diff: The text will be compared as entered. Select this for markup formats.'), + 'html' => t('HTML diff: Tags will be stripped before comparison. Select this for HTML or WYSIWYG formats.')), + '#default_value' => variable_get("diff_format_type_$format_id", 'source'), + '#description' => t('Select the type of diff which is made on the body of nodes wich use this input format.') + ); + } } /** + * Callback for node edit form to prepend the changes or preview to the form. + */ +function diff_node_form_add_changes($form) { + global $form_values; + + $op = isset($form_values['op']) ? $form_values['op'] : ''; + if ($op == t('Preview changes')) { + // Diff module excpects node as object, thus the form values are casted into an object. + $node = (object)$form_values; + // Create diff of old node and edited node + $changes = theme('diff_header'); + $changes .= _diff_body_output(node_load($form_values['nid']), $node); + $changes .= theme('diff_footer'); + // Prepend diff to edit form + $form['#prefix'] = isset($form['#prefix']) ? $changes . $form['#prefix'] : $changes; + return $form; + } + else { + // call original function from node module + return node_form_add_preview($form); + } +} + +/* + * Theme functions + */ + +/** * A copy of the 'theme_node_form' function with the addition of the new button * to show a diff of the changes. */ @@ -470,22 +532,88 @@ function theme_diff_node_form($form) { } /** - * Callback for node edit form to prepend the changes or preview to the form. + * Header of a diff. */ -function diff_node_form_add_changes($form) { - global $form_values; +function theme_diff_header($old_header = NULL, $new_header = NULL) { + $output .= ''; + if ($old_header || $new_header) { + $output .= ''; + } + return $output; +} - $op = isset($form_values['op']) ? $form_values['op'] : ''; - if ($op == t('Preview changes')) { - $node = (object)$form_values; - $changes = '
'. $old_header .''. $new_header .'
'; - $changes .= _diff_table_body(node_load($form_values['nid']), $node); - $changes .= '
'; - $form['#prefix'] = isset($form['#prefix']) ? $changes . $form['#prefix'] : $changes; - return $form; +/** + * Title row of diff. If $right_title is NULL, then the title is for both versions. + * + * @param $left_title + * Title shown on side of old node + * @param $right_title + * Title shown on side of new node + */ +function theme_diff_title_row($left_title, $right_title = NULL) { + if (is_null($right_title)) { + return '' . $left_title .''; } else { - // call original function from node module - return node_form_add_preview($form); + return '' . $left_title .'' . $right_title .''; } } + +/** + * Data row of diff. The data arrays have three keys: + * 'data': The data of the cell (required) + * 'class': The css class of the cell (optional) + * 'mark': A mark for the cell, either '+' or '-' for added or deleted lines respectively (optional) + * @param $left_content + * data array for old node + * @param $right_content + * data array for new node + */ +function theme_diff_data_row($left_content, $right_content) { + $output = ''; + if (is_array($left_content)) { + $output .= ''; + if (isset($left_content['mark'])) { + $output .= $left_content['mark']; + } + $output .= ''; + if (isset($left_content['class'])) { + $output .= ''; + } + else { + $output .= ''; + } + $output .= $left_content['data']; + $output .= ''; + } + else { + $output .= '' . $left_content . ''; + } + if (is_array($right_content)) { + $output .= ''; + if (isset($right_content['mark'])) { + $output .= $right_content['mark']; + } + $output .= ''; + if (isset($right_content['class'])) { + $output .= ''; + } + else { + $output .= ''; + } + $output .= $right_content['data']; + $output .= ''; + } + else { + $output .= '' . $right_content . ''; + } + $output .= ''; + return $output; +} + +/** + * Footer of diff. + */ +function theme_diff_footer() { + return ''; +} Index: node.inc =================================================================== RCS file: /cvs/drupal-contrib/contributions/modules/diff/node.inc,v retrieving revision 1.1 diff -u -p -r1.1 node.inc --- node.inc 31 Jan 2007 17:45:25 -0000 1.1 +++ node.inc 7 Mar 2007 08:24:27 -0000 @@ -14,10 +14,56 @@ function node_diff(&$old_node, &$new_nod 'show_header' => false, ) ); - $result[] = array( - 'name' => t('Body'), - 'old' => explode("\n", $old_node->body), - 'new' => explode("\n", $new_node->body), - ); + // Make a diff depending on the diff type of the node. + if (variable_get("diff_format_type_$new_node->format", 'source') == 'source') { + $result[] = array( + 'name' => t('Body'), + 'old' => explode("\n", $old_node->body), + 'new' => explode("\n", $new_node->body), + ); + } + else { + $result[] = array( + 'name' => t('Body'), + 'old' => node_diff_strip_html($old_node->body), + 'new' => node_diff_strip_html($new_node->body), + ); + } return $result; } + +/** + * Insert newlines in HTML, replace special characters and remove all tags. + */ +function node_diff_strip_html($text) { + // Replace  : with newlines + $text = str_replace(" ", " ", $text); + // Todo: maybe implement a generic solution for encoded symbols using html_entity_decode() + + // Replace HTML breaks with newlines + $text = str_replace("
", "\n", $text); + // Replace list elements with newlies + $text = str_replace("", "\n", $text); + // Replace paragraphs with newlies + $text = str_replace("

", "\n", $text); + // Replace table cells with newlines + $text = str_replace("", "\n", $text); + // Replace divs with newlines + $text = str_replace("", "\n", $text); + + // Replace image tags with the image location + // Todo: maybe alt and title attribute can also be displayed + $text = preg_replace('##', '[image:$3]', $text); + + // Replace link tags with the link location + // Todo: maybe title attribute can also be displayed + $text = preg_replace('#]*)>#', '[link:$3]', $text); + // Replace link endings + $text = str_replace("", "[link]", $text); + + // Todo: check if other tags need special treatment as well + // Strip all remaining tags + $text = preg_replace("#]*)?>#", "", $text); + // Diff are done line by line + return explode("\n", $text); +} Index: taxonomy.inc =================================================================== RCS file: /cvs/drupal-contrib/contributions/modules/diff/taxonomy.inc,v retrieving revision 1.2 diff -u -p -r1.2 taxonomy.inc --- taxonomy.inc 7 Feb 2007 06:56:35 -0000 1.2 +++ taxonomy.inc 7 Mar 2007 08:24:27 -0000 @@ -1,5 +1,5 @@ taxonomy) { foreach($new_node->taxonomy as $id => $entry) { - if (is_array($entry)) { + if (isset($new_node->preview)) { // During editing the taxonomy is built up as a list of vocabulary ids as keys // and a list of term ids per array entry. if (is_numeric($id)) { Index: upload.inc =================================================================== RCS file: /cvs/drupal-contrib/contributions/modules/diff/upload.inc,v retrieving revision 1.2 diff -u -p -r1.2 upload.inc --- upload.inc 7 Feb 2007 06:56:35 -0000 1.2 +++ upload.inc 7 Mar 2007 08:24:27 -0000 @@ -1,5 +1,5 @@ files)) { foreach($new_node->files as $key => $file) { - if (is_array($file)) { + if (isset($new_node->preview)) { // During editing the files are stored as arrays, not objects. if ($file['remove']) { // It looks better if a blank line is inserted for removed files.