_DiffEngine Class Reference

Collaboration diagram for _DiffEngine:

Public Member Functions
	diff ($from_lines, $to_lines)
	_line_hash ($line)
	Returns the whole line if it's small enough, or the MD5 hash otherwise. More...
	_diag ($xoff, $xlim, $yoff, $ylim, $nchunks)
	_lcs_pos ($ypos)
	_compareseq ($xoff, $xlim, $yoff, $ylim)
	_shift_boundaries ($lines, &$changed, $other_changed)

Data Fields
const	MAX_XREF_LENGTH = 10000

Detailed Description

Definition at line 844 of file class.WordLevelDiff.php.

Member Function Documentation

_compareseq()

_DiffEngine::_compareseq	(		$xoff,
			$xlim,
			$yoff,
			$ylim
	)

Definition at line 1109 of file class.WordLevelDiff.php.

    {
        $fname = '_DiffEngine::_compareseq';
        //wfProfileIn( $fname );
 
        // 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;
            }
        }
        //wfProfileOut( $fname );
    }

References _compareseq(), and _diag().

Referenced by _compareseq(), and diff().

Here is the call graph for this function:

Here is the caller graph for this function:

_diag()

_DiffEngine::_diag	(		$xoff,
			$xlim,
			$yoff,
			$ylim,
			$nchunks
	)

Definition at line 980 of file class.WordLevelDiff.php.

    {
        $fname = '_DiffEngine::_diag';
        //wfProfileIn( $fname );
        $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; $chunk++) {
            //wfProfileIn( "$fname-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($matches);
                foreach ($matches as $junk => $y) {
                    if (empty($this->in_seq[$y])) {
                        $k = $this->_lcs_pos($y);
                        USE_ASSERTS && assert($k > 0);
                        $ymids[$k] = $ymids[$k - 1];
                        break;
                    }
                }
                foreach ($matches as $y) {
                    if ($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];
                    }
                }
            }
            //wfProfileOut( "$fname-chunk" );
        }
 
        $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);
 
        //wfProfileOut( $fname );
        return array($this->lcs, $seps);
    }

References $i, $n, _lcs_pos(), and USE_ASSERTS.

Referenced by _compareseq().

Here is the call graph for this function:

Here is the caller graph for this function:

_lcs_pos()

_DiffEngine::_lcs_pos

(

$ypos

)

Definition at line 1066 of file class.WordLevelDiff.php.

    {
        $fname = '_DiffEngine::_lcs_pos';
        //wfProfileIn( $fname );
 
        $end = $this->lcs;
        if ($end == 0 || $ypos > $this->seq[$end]) {
            $this->seq[++$this->lcs] = $ypos;
            $this->in_seq[$ypos] = 1;
            //wfProfileOut( $fname );
            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;
        //wfProfileOut( $fname );
        return $end;
    }

References USE_ASSERTS.

Referenced by _diag().

Here is the caller graph for this function:

_line_hash()

_DiffEngine::_line_hash

(

$line

)

Returns the whole line if it's small enough, or the MD5 hash otherwise.

Definition at line 954 of file class.WordLevelDiff.php.

    {
        if (strlen($line) > self::MAX_XREF_LENGTH) {
            return md5($line);
        } else {
            return $line;
        }
    }

Referenced by diff().

Here is the caller graph for this function:

_shift_boundaries()

_DiffEngine::_shift_boundaries	(		$lines,
		&	$changed,
			$other_changed
	)

Definition at line 1172 of file class.WordLevelDiff.php.

    {
        $fname = '_DiffEngine::_shift_boundaries';
        //wfProfileIn( $fname );
        $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]);
            }
        }
        //wfProfileOut( $fname );
    }

References $changed, $i, and USE_ASSERTS.

Referenced by diff().

Here is the caller graph for this function:

diff()

_DiffEngine::diff	(		$from_lines,
			$to_lines
	)

Definition at line 848 of file class.WordLevelDiff.php.

    {
        $fname = '_DiffEngine::diff';
        //wfProfileIn( $fname );
 
        $n_from = sizeof($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);
            }
        }
        //wfProfileOut( $fname );
        return $edits;
    }

References _compareseq(), _line_hash(), _shift_boundaries(), and USE_ASSERTS.

Referenced by Diff\__construct().

Here is the call graph for this function:

Here is the caller graph for this function:

Field Documentation

MAX_XREF_LENGTH

const _DiffEngine::MAX_XREF_LENGTH = 10000

Definition at line 846 of file class.WordLevelDiff.php.

---

The documentation for this class was generated from the following file:

• Services/COPage/mediawikidiff/class.WordLevelDiff.php