steffen: server/kolab-horde-framework/kolab-horde-framework/Text_Diff Diff.php, NONE, 1.1 Diff3.php, NONE, 1.1 package.xml, NONE, 1.1

cvs at intevation.de cvs at intevation.de
Fri Oct 14 16:33:14 CEST 2005


Author: steffen

Update of /kolabrepository/server/kolab-horde-framework/kolab-horde-framework/Text_Diff
In directory doto:/tmp/cvs-serv28903/kolab-horde-framework/kolab-horde-framework/Text_Diff

Added Files:
	Diff.php Diff3.php package.xml 
Log Message:
Separated Horde Framework from kolab-resource-handlers

--- NEW FILE: Diff.php ---
<?php
/**
 * Text_Diff
 *
 * General API for generating and formatting diffs - the differences
 * between two sequences of strings.
 *
 * The PHP diff code used in this package was originally written by
 * Geoffrey T. Dairiki and is used with his permission.
 *
 * $Horde: framework/Text_Diff/Diff.php,v 1.6 2004/05/13 15:06:32 chuck Exp $
 *
 * @package Text_Diff
 * @author  Geoffrey T. Dairiki <dairiki at dairiki.org>
 */
class Text_Diff {

    /**
     * Array of changes.
     *
     * @var array $_edits
     */
    var $_edits;

    /**
     * Computes diff between sequences of strings.
     *
     * @param $from_lines array An array of strings.
     *        (Typically these are lines from a file.)
     * @param $to_lines array An array of strings.
     */
    function Text_Diff($from_lines, $to_lines)
    {
        array_walk($from_lines, array($this, '_trimNewlines'));
        array_walk($to_lines, array($this, '_trimNewlines'));

        if (extension_loaded('xdiff')) {
            $engine = &new Text_Diff_Engine_xdiff();
        } else {
            $engine = &new Text_Diff_Engine_native();
        }

        $this->_edits = $engine->diff($from_lines, $to_lines);
    }

    /**
     * Return the array of differences.
     */
    function getDiff()
    {
        return $this->_edits;
    }

    /**
     * Compute reversed diff.
     *
     * SYNOPSIS:
     *
     * $diff = &new Text_Diff($lines1, $lines2);
     * $rev = $diff->reverse();
     *
     * @return object  A Diff object representing the inverse of the
     *                 original diff. Note that we purposely don't return
     *                 a reference here, since this essentially is a
     *                 clone() method.
     */
    function reverse()
    {
        $rev = $this;
        $rev->_edits = array();
        foreach ($this->_edits as $edit) {
            $rev->_edits[] = $edit->reverse();
        }
        return $rev;
    }

    /**
     * Check for empty diff.
     *
     * @return boolean  True iff two sequences were identical.
     */
    function isEmpty()
    {
        foreach ($this->_edits as $edit) {
            if (!is_a($edit, 'Text_Diff_Op_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 $edit) {
            if (is_a($edit, 'Text_Diff_Op_copy')) {
                $lcs += count($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 getOriginal()
    {
        $lines = array();
        foreach ($this->_edits as $edit) {
            if ($edit->orig) {
                array_splice($lines, count($lines), 0, $edit->orig);
            }
        }
        return $lines;
    }

    /**
     * Get the final set of lines.
     *
     * This reconstructs the $to_lines parameter passed to the
     * constructor.
     *
     * @return array  The sequence of strings.
     */
    function getFinal()
    {
        $lines = array();
        foreach ($this->_edits as $edit) {
            if ($edit->final) {
                array_splice($lines, count($lines), 0, $edit->final);
            }
        }
        return $lines;
    }

    /**
     * Remove trailing newlines from a line of text. This is meant to
     * be used with array_walk().
     *
     * @param string  &$line  The line to trim.
     * @param integer $key    The index of the line in the array. Not used.
     */
    function _trimNewlines(&$line, $key)
    {
        $line = str_replace(array("\n", "\r", "\r\n"), '', $line);
    }

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

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

        $prevtype = null;
        foreach ($this->_edits as $edit) {
            if ($prevtype == get_class($edit)) {
                trigger_error("Edit sequence is non-optimal", E_USER_ERROR);
            }
            $prevtype = get_class($edit);
        }

        return true;
    }

}

/**
 * $Horde: framework/Text_Diff/Diff.php,v 1.6 2004/05/13 15:06:32 chuck Exp $
 *
 * @package Text_Diff
 * @author  Geoffrey T. Dairiki <dairiki at dairiki.org>
 */
class Text_MappedDiff extends Text_Diff {

    /**
     * Computes a 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.
     * @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 $to_lines.
     */
    function Text_MappedDiff($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::Text_Diff($mapped_from_lines, $mapped_to_lines);

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

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

}

/**
 * Class used internally by Diff to actually compute the diffs.  This class
 * uses the xdiff PECL package (http://pecl.php.net/package/xdiff) to compute
 * the differences between the two input arrays.
 *
 * @author  Jon Parise <jon at horde.org>
 * @package Text_Diff
 * @access  private
 */
class Text_Diff_Engine_xdiff {

    function diff($from_lines, $to_lines)
    {
        /* Convert the two input arrays into strings for xdiff processing. */
        $from_string = implode("\n", $from_lines);
        $to_string = implode("\n", $to_lines);

        /* Diff the two strings and convert the result to an array. */
        $diff = xdiff_string_diff($from_string, $to_string, count($to_lines));
        $diff = explode("\n", $diff);

        /* Walk through the diff one line at a time.  We build the
         * $edits array of diff operations by reading the first
         * character of the xdiff output (which is in the "unified
         * diff" format).
         *
         * Note that we don't have enough information to detect
         * "changed" lines using this approach, so we can't add
         * Text_Diff_Op_changed instances to the $edits array.  The
         * result is still perfectly valid, albeit a little less
         * descriptive and efficient. */
        $edits = array();
        foreach ($diff as $line) {
            switch ($line[0]) {
            case ' ':
                $edits[] = &new Text_Diff_Op_copy(array(substr($line, 1)));
                break;

            case '+':
                $edits[] = &new Text_Diff_Op_add(array(substr($line, 1)));
                break;

            case '-':
                $edits[] = &new Text_Diff_Op_delete(array(substr($line, 1)));
                break;
            }
        }

        return $edits;
    }

}

/**
 * Class used internally by Diff to actually compute the diffs.  This class
 * is implemented using native PHP code.
 *
 * The algorithm used here is mostly lifted from the perl module
 * Algorithm::Diff (version 1.06) by Ned Konz, which is available at:
 * http://www.perl.com/CPAN/authors/id/N/NE/NEDKONZ/Algorithm-Diff-1.06.zip
 *
 * More ideas are taken from:
 * http://www.ics.uci.edu/~eppstein/161/960229.html
 *
 * Some ideas (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
 *
 * Some ideas (subdivision by NCHUNKS > 2, and some optimizations) are
 * from Geoffrey T. Dairiki <dairiki at dairiki.org>. The original PHP
 * version of this code was writting by him, and is used/adapted with
 * his permission.
 *
 * @author  Geoffrey T. Dairiki <dairiki at dairiki.org>
 * @package Text_Diff
 * @access  private
 */
class Text_Diff_Engine_native {

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

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

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

        // Compute the edit operations.
        $edits = array();
        $xi = $yi = 0;
        while ($xi < $n_from || $yi < $n_to) {
            assert($yi < $n_to || $this->xchanged[$xi]);
            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) {
                $edits[] = &new Text_Diff_Op_copy($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) {
                $edits[] = &new Text_Diff_Op_change($delete, $add);
            } elseif ($delete) {
                $edits[] = &new Text_Diff_Op_delete($delete);
            } elseif ($add) {
                $edits[] = &new Text_Diff_Op_add($add);
            }
        }

        return $edits;
    }

    /**
     * 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 is 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];
                foreach ($matches as $y) {
                    if (empty($this->in_seq[$y])) {
                        $k = $this->_lcsPos($y);
                        assert($k > 0);
                        $ymids[$k] = $ymids[$k-1];
                        break;
                    }
                }

                while (list($junk, $y) = each($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[] = $flip ? array($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 _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 $this->{x,y}changed[],
     * by storing a 1 in the element for each line that is an
     * insertion or deletion (ie. is not in the LCS).
     *
     * The subsequence of file 0 is [XOFF, XLIM) and likewise for file
     * 1.
     *
     * Note that XLIM, YLIM are exclusive bounds.  All line numbers
     * are origin-0 and discarded lines are not counted.
     */
    function _compareseq ($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 _shiftBoundaries($lines, &$changed, $other_changed)
    {
        $i = 0;
        $j = 0;

        assert('count($lines) == count($changed)');
        $len = count($lines);
        $other_len = count($other_changed);

        while (1) {
            /* Scan forward to find the 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]) {
                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]) {
                        $start--;
                    }
                    assert('$j > 0');
                    while ($other_changed[--$j]) {
                        continue;
                    }
                    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++;
                    }

                    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;
                assert('$j > 0');
                while ($other_changed[--$j]) {
                    continue;
                }
                assert('$j >= 0 && !$other_changed[$j]');
            }
        }
    }

}

/**
 * @package Text_Diff
 * @author  Geoffrey T. Dairiki <dairiki at dairiki.org>
 * @access  private
 */
class Text_Diff_Op {

    var $orig;
    var $final;

    function reverse()
    {
        trigger_error('Abstract method', E_USER_ERROR);
    }

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

    function nfinal()
    {
        return $this->final ? count($this->final) : 0;
    }

}

/**
 * @package Text_Diff
 * @author  Geoffrey T. Dairiki <dairiki at dairiki.org>
 * @access  private
 */
class Text_Diff_Op_copy extends Text_Diff_Op {

    function Text_Diff_Op_copy($orig, $final = false)
    {
        if (!is_array($final)) {
            $final = $orig;
        }
        $this->orig = $orig;
        $this->final = $final;
    }

    function &reverse()
    {
        return new Text_Diff_Op_copy($this->final, $this->orig);
    }

}

/**
 * @package Text_Diff
 * @author  Geoffrey T. Dairiki <dairiki at dairiki.org>
 * @access  private
 */
class Text_Diff_Op_delete extends Text_Diff_Op {

    function Text_Diff_Op_delete($lines)
    {
        $this->orig = $lines;
        $this->final = false;
    }

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

}

/**
 * @package Text_Diff
 * @author  Geoffrey T. Dairiki <dairiki at dairiki.org>
 * @access  private
 */
class Text_Diff_Op_add extends Text_Diff_Op {

    function Text_Diff_Op_add($lines)
    {
        $this->final = $lines;
        $this->orig = false;
    }

    function &reverse()
    {
        return new Text_Diff_Op_delete($this->final);
    }

}

/**
 * @package Text_Diff
 * @author  Geoffrey T. Dairiki <dairiki at dairiki.org>
 * @access  private
 */
class Text_Diff_Op_change extends Text_Diff_Op {

    function Text_Diff_Op_change($orig, $final)
    {
        $this->orig = $orig;
        $this->final = $final;
    }

    function &reverse()
    {
        return new Text_Diff_Op_change($this->final, $this->orig);
    }

}

--- NEW FILE: Diff3.php ---
<?php

require_once 'Text/Diff.php';

/**
 * A class for computing three way diffs.
 *
 * $Horde: framework/Text_Diff/Diff3.php,v 1.1 2004/03/19 18:53:11 chuck Exp $
 *
 * @package Text_Diff
 * @author  Geoffrey T. Dairiki <dairiki at dairiki.org>
 */
class Text_Diff3 extends Text_Diff {

    /**
     * Conflict counter.
     *
     * @var integer $_conflictCounter
     */
    var $_conflictingBlocks = 0;

    /**
     * Computes diff between 3 sequences of strings.
     *
     * @param array $orig    The original lines to use.
     * @param array $final1  The first version to compare to.
     * @param array $final2  The second version to compare to.
     */
    function Text_Diff3($orig, $final1, $final2)
    {
        if (extension_loaded('xdiff')) {
            $engine = &new Text_Diff_Engine_xdiff();
        } else {
            $engine = &new Text_Diff_Engine_native();
        }

        $this->_edits = $this->_diff3($engine->diff($orig, $final1),
                                      $engine->diff($orig, $final2));
    }

    function mergedOutput($label1 = false, $label2 = false)
    {
        $lines = array();
        foreach ($this->_edits as $edit) {
            if ($edit->isConflict()) {
                // FIXME: this should probably be moved somewhere
                // else.
                $lines = array_merge($lines,
                                     array('<<<<<<<' . ($label1 ? ' ' . $label1 : '')),
                                     $edit->final1,
                                     array("======="),
                                     $edit->final2,
                                     array('>>>>>>>' . ($label2 ? ' ' . $label2 : '')));
                $this->_conflictingBlocks++;
            } else {
                $lines = array_merge($lines, $edit->merged());
            }
        }

        return $lines;
    }

    /**
     * @access private
     */
    function _diff3($edits1, $edits2)
    {
        $edits = array();
        $bb = &new Text_Diff3_BlockBuilder();

        $e1 = current($edits1);
        $e2 = current($edits2);
        while ($e1 || $e2) {
            if ($e1 && $e2 && is_a($e1, 'Text_Diff_Op_copy') && is_a($e2, 'Text_Diff_Op_copy')) {
                // We have copy blocks from both diffs. This is the
                // (only) time we want to emit a diff3 copy block.
                // Flush current diff3 diff block, if any.
                if ($edit = $bb->finish()) {
                    $edits[] = $edit;
                }

                $ncopy = min($e1->norig(), $e2->norig());
                assert($ncopy > 0);
                $edits[] = &new Text_Diff3_Op_copy(array_slice($e1->orig, 0, $ncopy));

                if ($e1->norig() > $ncopy) {
                    array_splice($e1->orig, 0, $ncopy);
                    array_splice($e1->final, 0, $ncopy);
                } else {
                    $e1 = next($edits1);
                }

                if ($e2->norig() > $ncopy) {
                    array_splice($e2->orig, 0, $ncopy);
                    array_splice($e2->final, 0, $ncopy);
                } else {
                    $e2 = next($edits2);
                }
            } else {
                if ($e1 && $e2) {
                    if ($e1->orig && $e2->orig) {
                        $norig = min($e1->norig(), $e2->norig());
                        $orig = array_splice($e1->orig, 0, $norig);
                        array_splice($e2->orig, 0, $norig);
                        $bb->input($orig);
                    }

                    if (is_a($e1, 'Text_Diff_Op_copy')) {
                        $bb->out1(array_splice($e1->final, 0, $norig));
                    }

                    if (is_a($e2, 'Text_Diff_Op_copy')) {
                        $bb->out2(array_splice($e2->final, 0, $norig));
                    }
                }

                if ($e1 && ! $e1->orig) {
                    $bb->out1($e1->final);
                    $e1 = next($edits1);
                }
                if ($e2 && ! $e2->orig) {
                    $bb->out2($e2->final);
                    $e2 = next($edits2);
                }
            }
        }

        if ($edit = $bb->finish()) {
            $edits[] = $edit;
        }

        return $edits;
    }

}

/**
 * @package Text_Diff
 * @author  Geoffrey T. Dairiki <dairiki at dairiki.org>
 * @access  private
 */
class Text_Diff3_Op {

    function Text_Diff3_Op($orig = false, $final1 = false, $final2 = false)
    {
        $this->orig = $orig ? $orig : array();
        $this->final1 = $final1 ? $final1 : array();
        $this->final2 = $final2 ? $final2 : array();
    }

    function merged()
    {
        if (!isset($this->_merged)) {
            if ($this->final1 === $this->final2) {
                $this->_merged = &$this->final1;
            } elseif ($this->final1 === $this->orig) {
                $this->_merged = &$this->final2;
            } elseif ($this->final2 === $this->orig) {
                $this->_merged = &$this->final1;
            } else {
                $this->_merged = false;
            }
        }

        return $this->_merged;
    }

    function isConflict()
    {
        return $this->merged() === false;
    }

}

/**
 * @package Text_Diff
 * @author  Geoffrey T. Dairiki <dairiki at dairiki.org>
 * @access  private
 */
class Text_Diff3_Op_copy extends Text_Diff3_Op {

    function Text_Diff3_Op_Copy($lines = false)
    {
        $this->orig = $lines ? $lines : array();
        $this->final1 = &$this->orig;
        $this->final2 = &$this->orig;
    }

    function merged()
    {
        return $this->orig;
    }

    function isConflict()
    {
        return false;
    }

}

/**
 * @package Text_Diff
 * @author  Geoffrey T. Dairiki <dairiki at dairiki.org>
 * @access  private
 */
class Text_Diff3_BlockBuilder {

    function Text_Diff3_BlockBuilder()
    {
        $this->_init();
    }

    function input($lines)
    {
        if ($lines) {
            $this->_append($this->orig, $lines);
        }
    }

    function out1($lines)
    {
        if ($lines) {
            $this->_append($this->final1, $lines);
        }
    }

    function out2($lines)
    {
        if ($lines) {
            $this->_append($this->final2, $lines);
        }
    }

    function isEmpty()
    {
        return !$this->orig && !$this->final1 && !$this->final2;
    }

    function finish()
    {
        if ($this->isEmpty()) {
            return false;
        } else {
            $edit = &new Text_Diff3_Op($this->orig, $this->final1, $this->final2);
            $this->_init();
            return $edit;
        }
    }

    function _init()
    {
        $this->orig = $this->final1 = $this->final2 = array();
    }

    function _append(&$array, $lines)
    {
        array_splice($array, sizeof($array), 0, $lines);
    }

}

--- NEW FILE: package.xml ---
<?xml version="1.0" encoding="ISO-8859-1" ?>
<!-- $Horde: framework/Text_Diff/package.xml,v 1.11 2004/05/13 15:06:32 chuck Exp $ -->
<!DOCTYPE package SYSTEM "http://pear.php.net/dtd/package-1.0">
<package version="1.0">
  <name>Text_Diff</name>
  <summary>Engine for performing and rendering text diffs</summary>
  <description>This package provides a text-based diff engine and renderers for multiple diff output formats.</description>
  <license>LGPL</license>

  <maintainers>
    <maintainer>
      <user>chagenbu</user>
      <role>lead</role>
      <name>Chuck Hagenbuch</name>
      <email>chuck at horde.org</email>
    </maintainer>
    <maintainer>
      <user>jon</user>
      <role>lead</role>
      <name>Jon Parise</name>
      <email>jon at horde.org</email>
    </maintainer>
    <maintainer>
      <user>pmjones</user>
      <role>lead</role>
      <name>Paul M Jones</name>
      <email>pmjones at memphis.edu</email>
    </maintainer>
    <maintainer>
      <user>yunosh</user>
      <role>lead</role>
      <name>Jan Schneider</name>
      <email>jan at horde.org</email>
    </maintainer>
  </maintainers>

  <release>
    <version>0.0.3</version>
    <date>2004-05-13</date>
    <state>beta</state>
    <notes>Renamed final() and orig() methods to avoid conflict with final keyword in PHP5</notes>

    <filelist>
      <file role="php" baseinstalldir="/Text" name="Diff.php" />
      <file role="php" baseinstalldir="/Text" name="Diff3.php" />
      <dir role="php" baseinstalldir="/Text" name="Diff">
        <file name="Renderer.php" />
	    <dir role="php" name="Renderer">
	      <file name="unified.php" />
	    </dir>
      </dir>

      <dir role="doc" name="docs">
        <dir name="examples">
          <file name="diff.php"/>
          <file name="1.txt"/>
          <file name="2.txt"/>
        </dir>
      </dir>

      <dir role="test" name="tests">
        <file name="1.txt" />
        <file name="2.txt" />
        <file name="diff.phpt" />
        <file name="unified.phpt" />
      </dir>
    </filelist>

    <deps>
      <dep type="php" rel="ge" version="4.2.0+" />
      <dep type="ext" rel="has" optional="yes">xdiff</dep>
    </deps>

    <provides type="class" name="Text_Diff" />
    <provides type="class" name="Text_Diff3" />
    <provides type="class" name="Text_MappedDiff" />
    <provides type="class" name="Text_Diff_Renderer" />
  </release>

  <changelog>
    <release>
      <version>0.0.3</version>
      <date>2004-05-13</date>
      <state>alpha</state>
      <notes>Renamed final() and orig() methods to avoid conflict with final keyword in PHP5</notes>
    </release>

    <release>
      <version>0.0.2</version>
      <date>2004-03-16</date>
      <state>alpha</state>
      <notes>Added optional xdiff support</notes>
    </release>

    <release>
      <version>0.0.1</version>
      <date>2004-01-09</date>
      <state>alpha</state>
      <notes>Initial package release</notes>
    </release>
  </changelog>

</package>





More information about the commits mailing list