File Source for diff.php

<?php
/**
* $Header: /cvsroot/bitweaver/_bit_wiki/diff.php,v 1.3 2005/08/24 21:00:26 squareing Exp $
*
* A PHP diff engine for phpwiki.
*
* Copyright (c) 2004 bitweaver.org
* Copyright (c) 2003 tikwiki.org
* Copyright (c) 2000 Geoffrey T. Dairiki <dairiki@dairiki.org>
* All Rights Reserved. See copyright.txt for details and a complete list of authors.
* Licensed under the GNU LESSER GENERAL PUBLIC LICENSE. See license.txt for details
*
* $Id: diff.php,v 1.3 2005/08/24 21:00:26 squareing Exp $
* @package wiki
*/
/**
* required setup
*/
define('USE_ASSERTS', function_exists('assert'));
/**
* Class used internally by WikiDiff to actually compute the diffs.
*
* The algorithm used here is mostly lifted from the perl module
* Algorithm::Diff (version 1.06) by Ned Konz, which is available at:
* http://www.perl.com/CPAN/authors/id/N/NE/NEDKONZ/Algorithm-Diff-1.06.zip
*
* More ideas are taken from:
* http://www.ics.uci.edu/~eppstein/161/960229.html
*
* Some ideas are (and a bit of code) are from from analyze.c, from GNU
* diffutils-2.7, which can be found at:
* ftp://gnudist.gnu.org/pub/gnu/diffutils/diffutils-2.7.tar.gz
*
* Finally, some ideas (subdivision by NCHUNKS > 2, and some optimizations)
* are my own.
* @package wiki
* @subpackage WikiDiffEngine
*/
class _WikiDiffEngine
{
var $edits; // List of editing operation to convert XV to YV.
var $xv = array(), $yv = array();
var $xchanged, $ychanged;
function _WikiDiffEngine ($from_lines, $to_lines)
{
$n_from = sizeof($from_lines);
$n_to = sizeof($to_lines);
$endskip = 0;
// Ignore differences in line endings
for ($i = 0; $i < $n_from; $i++)
{
$from_lines[$i] = rtrim($from_lines[$i]);
}
for ($i = 0; $i < $n_to; $i++)
{
$to_lines[$i] = rtrim($to_lines[$i]);
}
// Ignore trailing and leading matching lines.
while ($n_from > 0 && $n_to > 0)
{
if ($from_lines[$n_from - 1] != $to_lines[$n_to - 1])
break;
$n_from--;
$n_to--;
$endskip++;
}
for ( $skip = 0; $skip < min($n_from, $n_to); $skip++)
if ($from_lines[$skip] != $to_lines[$skip])
break;
$n_from -= $skip;
$n_to -= $skip;
$xlines = array();
$ylines = array();
// Ignore lines which do not exist in both files.
for ($x = 0; $x < $n_from; $x++)
$xhash[$from_lines[$x + $skip]] = 1;
for ($y = 0; $y < $n_to; $y++)
{
$line = $to_lines[$y + $skip];
$ylines[] = $line;
if ( ($this->ychanged[$y] = empty($xhash[$line])) )
continue;
$yhash[$line] = 1;
$this->yv[] = $line;
$this->yind[] = $y;
}
for ($x = 0; $x < $n_from; $x++)
{
$line = $from_lines[$x + $skip];
$xlines[] = $line;
if ( ($this->xchanged[$x] = empty($yhash[$line])) )
continue;
$this->xv[] = $line;
$this->xind[] = $x;
}
// Find the LCS.
$this->_compareseq(0, sizeof($this->xv), 0, sizeof($this->yv));
// Merge edits when possible
$this->_shift_boundaries($xlines, $this->xchanged, $this->ychanged);
$this->_shift_boundaries($ylines, $this->ychanged, $this->xchanged);
// Compute the edit operations.
$this->edits = array();
if ($skip)
$this->edits[] = $skip;
$x = 0;
$y = 0;
while ($x < $n_from || $y < $n_to)
{
USE_ASSERTS && assert($y < $n_to || $this->xchanged[$x]);
USE_ASSERTS && assert($x < $n_from || $this->ychanged[$y]);
// Skip matching "snake".
$x0 = $x;
$ncopy = 0;
while ( $x < $n_from && $y < $n_to
&& !$this->xchanged[$x] && !$this->ychanged[$y])
{
++$x;
++$y;
++$ncopy;
}
if ($x > $x0)
$this->edits[] = $x - $x0;
// Find deletes.
$x0 = $x;
$ndelete = 0;
while ($x < $n_from && $this->xchanged[$x])
{
++$x;
++$ndelete;
}
if ($x > $x0)
$this->edits[] = -($x - $x0);
// Find adds.
if (isset($this->ychanged[$y]) && $this->ychanged[$y])
{
$adds = array();
while ($y < $n_to && $this->ychanged[$y])
$adds[] = "" . $ylines[$y++];
$this->edits[] = $adds;
}
}
if ($endskip != 0)
$this->edits[] = $endskip;
}
/* Divide the Largest Common Subsequence (LCS) of the sequences
* [XOFF, XLIM) and [YOFF, YLIM) into NCHUNKS approximately equally
* sized segments.
*
* Returns (LCS, PTS). LCS is the length of the LCS. PTS is an
* array of NCHUNKS+1 (X, Y) indexes giving the diving points between
* sub sequences. The first sub-sequence is contained in [X0, X1),
* [Y0, Y1), the second in [X1, X2), [Y1, Y2) and so on. Note
* that (X0, Y0) == (XOFF, YOFF) and
* (X[NCHUNKS], Y[NCHUNKS]) == (XLIM, YLIM).
*
* This function assumes that the first lines of the specified portions
* of the two files do not match, and likewise that the last lines do not
* match. The caller must trim matching lines from the beginning and end
* of the portions it is going to specify.
*/
function _diag ($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++)
{
$matches = $ymatches[$flip ? $this->yv[$x] : $this->xv[$x]];
if (!$matches)
continue;
reset($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]');
}
}
}
}
/**
* Class representing a diff between two files.
*
* @package wiki
* @subpackage WikiDiff
*/
class WikiDiff
{
var $edits;
/**
* Compute diff between files (or deserialize serialized WikiDiff.)
*/
function WikiDiff($from_lines = false, $to_lines = false)
{
if ($from_lines && $to_lines)
{
$compute = new _WikiDiffEngine($from_lines, $to_lines);
$this->edits = $compute->edits;
}
else if ($from_lines)
{
// $from_lines is not really from_lines, but rather
// a serialized WikiDiff.
$this->edits = unserialize($from_lines);
}
else
{
$this->edits = array();
}
}
/**
* Compute reversed WikiDiff.
*
* SYNOPSIS:
*
* $diff = new WikiDiff($lines1, $lines2);
* $rev = $diff->reverse($lines1);
*
* // reconstruct $lines1 from $lines2:
* $out = $rev->apply($lines2);
*/
function reverse ($from_lines)
{
$x = 0;
$rev = new WikiDiff;
for ( reset($this->edits);
$edit = current($this->edits);
next($this->edits<

Source for file diff.php