* @ingroup DifferenceEngine
*/
class DiffEngine {
- const MAX_XREF_LENGTH = 10000;
-
protected $xchanged, $ychanged;
- protected $xv = [], $yv = [];
- protected $xind = [], $yind = [];
-
- protected $seq = [], $in_seq = [];
-
- protected $lcs = 0;
-
/**
* @param string[] $from_lines
* @param string[] $to_lines
* @param string[] $to_lines
*/
private function diffLocal( $from_lines, $to_lines ) {
- global $wgExternalDiffEngine;
-
- if ( $wgExternalDiffEngine == 'wikidiff3' ) {
- // wikidiff3
- $wikidiff3 = new WikiDiff3();
- $wikidiff3->diff( $from_lines, $to_lines );
- $this->xchanged = $wikidiff3->removed;
- $this->ychanged = $wikidiff3->added;
- unset( $wikidiff3 );
- } else {
- // old diff
- $n_from = count( $from_lines );
- $n_to = count( $to_lines );
- $this->xchanged = $this->ychanged = [];
- $this->xv = $this->yv = [];
- $this->xind = $this->yind = [];
- $this->seq = [];
- $this->in_seq = [];
- $this->lcs = 0;
-
- // 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->lineHash( $from_lines[$xi] )] = 1;
- }
-
- for ( $yi = $skip; $yi < $n_to - $endskip; $yi++ ) {
- $line = $to_lines[$yi];
- $this->ychanged[$yi] = empty( $xhash[$this->lineHash( $line )] );
- if ( $this->ychanged[$yi] ) {
- continue;
- }
- $yhash[$this->lineHash( $line )] = 1;
- $this->yv[] = $line;
- $this->yind[] = $yi;
- }
- for ( $xi = $skip; $xi < $n_from - $endskip; $xi++ ) {
- $line = $from_lines[$xi];
- $this->xchanged[$xi] = empty( $yhash[$this->lineHash( $line )] );
- if ( $this->xchanged[$xi] ) {
- continue;
- }
- $this->xv[] = $line;
- $this->xind[] = $xi;
- }
-
- // Find the LCS.
- $this->compareSeq( 0, count( $this->xv ), 0, count( $this->yv ) );
- }
- }
-
- /**
- * Returns the whole line if it's small enough, or the MD5 hash otherwise
- *
- * @param string $line
- *
- * @return string
- */
- private function lineHash( $line ) {
- if ( strlen( $line ) > self::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.
- *
- * @param int $xoff
- * @param int $xlim
- * @param int $yoff
- * @param int $ylim
- * @param int $nchunks
- *
- * @return array List of two elements, integer and array[].
- */
- private 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 ) = [ $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 = [];
- $ymids[0] = [];
-
- $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 );
- // @codingStandardsIgnoreStart Ignore Squiz.WhiteSpace.SemicolonSpacing.Incorrect
- for ( ; $x < $x1; $x++ ) {
- // @codingStandardsIgnoreEnd
- $line = $flip ? $this->yv[$x] : $this->xv[$x];
- if ( empty( $ymatches[$line] ) ) {
- continue;
- }
-
- $k = 0;
- $matches = $ymatches[$line];
- reset( $matches );
- while ( list( , $y ) = each( $matches ) ) {
- if ( empty( $this->in_seq[$y] ) ) {
- $k = $this->lcsPos( $y );
- assert( $k > 0 );
- $ymids[$k] = $ymids[$k - 1];
- break;
- }
- }
-
- while ( list( , $y ) = each( $matches ) ) {
- if ( $y > $this->seq[$k - 1] ) {
- 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->lcsPos( $y );
- assert( $k > 0 );
- $ymids[$k] = $ymids[$k - 1];
- }
- }
- }
- }
-
- $seps[] = $flip ? [ $yoff, $xoff ] : [ $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 ? [ $y1, $x1 ] : [ $x1, $y1 ];
- }
- $seps[] = $flip ? [ $ylim, $xlim ] : [ $xlim, $ylim ];
-
- return [ $this->lcs, $seps ];
- }
-
- /**
- * @param int $ypos
- *
- * @return int
- */
- private function lcsPos( $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;
- }
- }
-
- 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.
- *
- * @param int $xoff
- * @param int $xlim
- * @param int $yoff
- * @param int $ylim
- */
- private 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;
- }
- }
+ $wikidiff3 = new WikiDiff3();
+ $wikidiff3->diff( $from_lines, $to_lines );
+ $this->xchanged = $wikidiff3->removed;
+ $this->ychanged = $wikidiff3->added;
}
/**
}
/**
- * @todo document, bad name.
- * @private
- * @ingroup 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 string[] $from_lines An array of strings.
- * Typically these are lines from a file.
- * @param string[] $to_lines An array of strings.
- * @param string[] $mapped_from_lines 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 string[] $mapped_to_lines This array should
- * have the same number of elements as $to_lines.
- */
- public function __construct( $from_lines, $to_lines,
- $mapped_from_lines, $mapped_to_lines ) {
-
- assert( count( $from_lines ) == count( $mapped_from_lines ) );
- assert( count( $to_lines ) == count( $mapped_to_lines ) );
-
- parent::__construct( $mapped_from_lines, $mapped_to_lines );
-
- $xi = $yi = 0;
- $editCount = count( $this->edits );
- for ( $i = 0; $i < $editCount; $i++ ) {
- $orig = &$this->edits[$i]->orig;
- if ( is_array( $orig ) ) {
- $orig = array_slice( $from_lines, $xi, count( $orig ) );
- $xi += count( $orig );
- }
-
- $closing = &$this->edits[$i]->closing;
- if ( is_array( $closing ) ) {
- $closing = array_slice( $to_lines, $yi, count( $closing ) );
- $yi += count( $closing );
- }
- }
- }
-}
-
-/**
- * Additions by Axel Boldt follow, partly taken from diff.php, phpwiki-1.3.3
- */
-
-/**
- * @todo document
- * @private
- * @ingroup DifferenceEngine
- */
-class HWLDFWordAccumulator {
- public $insClass = ' class="diffchange diffchange-inline"';
- public $delClass = ' class="diffchange diffchange-inline"';
-
- private $lines = [];
- private $line = '';
- private $group = '';
- private $tag = '';
-
- /**
- * @param string $new_tag
- */
- private function flushGroup( $new_tag ) {
- if ( $this->group !== '' ) {
- if ( $this->tag == 'ins' ) {
- $this->line .= "<ins{$this->insClass}>" .
- htmlspecialchars( $this->group ) . '</ins>';
- } elseif ( $this->tag == 'del' ) {
- $this->line .= "<del{$this->delClass}>" .
- htmlspecialchars( $this->group ) . '</del>';
- } else {
- $this->line .= htmlspecialchars( $this->group );
- }
- }
- $this->group = '';
- $this->tag = $new_tag;
- }
-
- /**
- * @param string $new_tag
- */
- private 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 = '';
- }
-
- /**
- * @param string[] $words
- * @param string $tag
- */
- public 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;
- }
- }
-
- /**
- * @return string[]
- */
- public function getLines() {
- $this->flushLine( '~done' );
-
- return $this->lines;
- }
-}
-
-/**
- * @todo document
- * @private
- * @ingroup DifferenceEngine
+ * @deprecated Alias for WordAccumulator, to be soon removed
*/
-class WordLevelDiff extends MappedDiff {
- const MAX_LINE_LENGTH = 10000;
-
- /**
- * @param string[] $orig_lines
- * @param string[] $closing_lines
- */
- public function __construct( $orig_lines, $closing_lines ) {
-
- list( $orig_words, $orig_stripped ) = $this->split( $orig_lines );
- list( $closing_words, $closing_stripped ) = $this->split( $closing_lines );
-
- parent::__construct( $orig_words, $closing_words,
- $orig_stripped, $closing_stripped );
- }
-
- /**
- * @param string[] $lines
- *
- * @return array[]
- */
- private function split( $lines ) {
-
- $words = [];
- $stripped = [];
- $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 ) > self::MAX_LINE_LENGTH ) {
- $words[] = $line;
- $stripped[] = $line;
- } else {
- $m = [];
- if ( preg_match_all( '/ ( [^\S\n]+ | [0-9_A-Za-z\x80-\xff]+ | . ) (?: (?!< \n) [^\S\n])? /xs',
- $line, $m )
- ) {
- foreach ( $m[0] as $word ) {
- $words[] = $word;
- }
- foreach ( $m[1] as $stripped_word ) {
- $stripped[] = $stripped_word;
- }
- }
- }
- }
-
- return [ $words, $stripped ];
- }
-
- /**
- * @return string[]
- */
- public function orig() {
- $orig = new HWLDFWordAccumulator;
-
- foreach ( $this->edits as $edit ) {
- if ( $edit->type == 'copy' ) {
- $orig->addWords( $edit->orig );
- } elseif ( $edit->orig ) {
- $orig->addWords( $edit->orig, 'del' );
- }
- }
- $lines = $orig->getLines();
-
- return $lines;
- }
-
- /**
- * @return string[]
- */
- public function closing() {
- $closing = new HWLDFWordAccumulator;
-
- foreach ( $this->edits as $edit ) {
- if ( $edit->type == 'copy' ) {
- $closing->addWords( $edit->closing );
- } elseif ( $edit->closing ) {
- $closing->addWords( $edit->closing, 'ins' );
- }
- }
- $lines = $closing->getLines();
-
- return $lines;
- }
-
+class HWLDFWordAccumulator extends MediaWiki\Diff\WordAccumulator {
}