<?php
/**
*
* @package diff
* @version $Id$
* @copyright (c) 2006 phpBB Group
* @license http://opensource.org/licenses/gpl-license.php GNU Public License
*
*/

/**
* @ignore
*/
if (!defined('IN_PHPBB'))
{
	exit;
}

/**
* Code from pear.php.net, Text_Diff-1.1.0 package
* http://pear.php.net/package/Text_Diff/ (native engine)
*
* Modified by phpBB Group to meet our coding standards
* and being able to integrate into phpBB
*
* Class used internally by Text_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 taken from analyze.c, of 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@dairiki.org>. The original PHP version of this
* code was written by him, and is used/adapted with his permission.
*
* Copyright 2004-2008 The Horde Project (http://www.horde.org/)
*
* @author  Geoffrey T. Dairiki <dairiki@dairiki.org>
* @package diff
*
* @access private
*/
class diff_engine
{
	/**
	* If set to true we trim all lines before we compare them. This ensures that sole space/tab changes do not trigger diffs.
	*/
	var $skip_whitespace_changes = true;

	function diff(&$from_lines, &$to_lines, $preserve_cr = true)
	{
		// Remove empty lines...
		// If preserve_cr is true, we basically only change \r\n and bare \r to \n to get the same carriage returns for both files
		// If it is false, we try to only use \n once per line and ommit all empty lines to be able to get a proper data diff

		if (is_array($from_lines))
		{
			$from_lines = implode("\n", $from_lines);
		}

		if (is_array($to_lines))
		{
			$to_lines = implode("\n", $to_lines);
		}

		if ($preserve_cr)
		{
			$from_lines = explode("\n", str_replace("\r", "\n", str_replace("\r\n", "\n", $from_lines)));
			$to_lines = explode("\n", str_replace("\r", "\n", str_replace("\r\n", "\n", $to_lines)));
		}
		else
		{
			$from_lines = explode("\n", preg_replace('#[\n\r]+#', "\n", $from_lines));
			$to_lines = explode("\n", preg_replace('#[\n\r]+#', "\n", $to_lines));
		}

		$n_from = sizeof($from_lines);
		$n_to = sizeof($to_lines);

		$this->xchanged = $this->ychanged = $this->xv = $this->yv = $this->xind = $this->yind = array();
		unset($this->seq, $this->in_seq, $this->lcs);

		// Skip leading common lines.
		for ($skip = 0; $skip < $n_from && $skip < $n_to; $skip++)
		{
			if (trim($from_lines[$skip]) !== trim($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; $endskip++)
		{
			if (trim($from_lines[$xi]) !== trim($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; $xi++)
		{
			if ($this->skip_whitespace_changes) $xhash[trim($from_lines[$xi])] = 1; else $xhash[$from_lines[$xi]] = 1;
		}

		for ($yi = $skip; $yi < $n_to - $endskip; $yi++)
		{
			$line = ($this->skip_whitespace_changes) ? trim($to_lines[$yi]) : $to_lines[$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++)
		{
			$line = ($this->skip_whitespace_changes) ? trim($from_lines[$xi]) : $from_lines[$xi];

			if (($this->xchanged[$xi] = empty($yhash[$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.
		if ($this->skip_whitespace_changes)
		{
			$from_lines_clean = array_map('trim', $from_lines);
			$to_lines_clean = array_map('trim', $to_lines);

			$this->_shift_boundaries($from_lines_clean, $this->xchanged, $this->ychanged);
			$this->_shift_boundaries($to_lines_clean, $this->ychanged, $this->xchanged);

			unset($from_lines_clean, $to_lines_clean);
		}
		else
		{
			$this->_shift_boundaries($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)
			{
				$edits[] = new diff_op_copy($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)
			{
				$edits[] = new diff_op_change($delete, $add);
			}
			else if ($delete)
			{
				$edits[] = new diff_op_delete($delete);
			}
			else if ($add)
			{
				$edits[] = new diff_op_add($add);
			}
		}

		return $edits;
	}

	/**
	* Divides 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];

				reset($matches);
				while (list(, $y) = each($matches))
				{
					if (empty($this->in_seq[$y]))
					{
						$k = $this->_lcs_pos($y);
						$ymids[$k] = $ymids[$k - 1];
						break;
					}
				}

				// no reset() here
				while (list(, $y) = each($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 _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;
			}
		}

		$this->in_seq[$this->seq[$end]] = false;
		$this->seq[$end] = $ypos;
		$this->in_seq[$ypos] = 1;

		return $end;
	}

	/**
	* Finds 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;
			}
		}
	}

	/**
	* Adjusts 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 (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])
			{
				$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;
				}
			}
		}
	}
}

?> href='#n232'>232</a>
<a id='n233' href='#n233'>233</a>
<a id='n234' href='#n234'>234</a>
<a id='n235' href='#n235'>235</a>
<a id='n236' href='#n236'>236</a>
<a id='n237' href='#n237'>237</a>
<a id='n238' href='#n238'>238</a>
<a id='n239' href='#n239'>239</a>
<a id='n240' href='#n240'>240</a>
<a id='n241' href='#n241'>241</a>
<a id='n242' href='#n242'>242</a>
<a id='n243' href='#n243'>243</a>
<a id='n244' href='#n244'>244</a>
<a id='n245' href='#n245'>245</a>
<a id='n246' href='#n246'>246</a>
<a id='n247' href='#n247'>247</a>
<a id='n248' href='#n248'>248</a>
<a id='n249' href='#n249'>249</a>
<a id='n250' href='#n250'>250</a>
<a id='n251' href='#n251'>251</a>
<a id='n252' href='#n252'>252</a>
<a id='n253' href='#n253'>253</a>
<a id='n254' href='#n254'>254</a>
<a id='n255' href='#n255'>255</a>
<a id='n256' href='#n256'>256</a>
<a id='n257' href='#n257'>257</a>
<a id='n258' href='#n258'>258</a>
<a id='n259' href='#n259'>259</a>
<a id='n260' href='#n260'>260</a>
<a id='n261' href='#n261'>261</a>
<a id='n262' href='#n262'>262</a>
<a id='n263' href='#n263'>263</a>
<a id='n264' href='#n264'>264</a>
<a id='n265' href='#n265'>265</a>
<a id='n266' href='#n266'>266</a>
<a id='n267' href='#n267'>267</a>
<a id='n268' href='#n268'>268</a>
<a id='n269' href='#n269'>269</a>
<a id='n270' href='#n270'>270</a>
<a id='n271' href='#n271'>271</a>
<a id='n272' href='#n272'>272</a>
<a id='n273' href='#n273'>273</a>
<a id='n274' href='#n274'>274</a>
<a id='n275' href='#n275'>275</a>
<a id='n276' href='#n276'>276</a>
<a id='n277' href='#n277'>277</a>
<a id='n278' href='#n278'>278</a>
<a id='n279' href='#n279'>279</a>
<a id='n280' href='#n280'>280</a>
<a id='n281' href='#n281'>281</a>
<a id='n282' href='#n282'>282</a>
<a id='n283' href='#n283'>283</a>
<a id='n284' href='#n284'>284</a>
<a id='n285' href='#n285'>285</a>
<a id='n286' href='#n286'>286</a>
<a id='n287' href='#n287'>287</a>
<a id='n288' href='#n288'>288</a>
<a id='n289' href='#n289'>289</a>
<a id='n290' href='#n290'>290</a>
<a id='n291' href='#n291'>291</a>
<a id='n292' href='#n292'>292</a>
<a id='n293' href='#n293'>293</a>
<a id='n294' href='#n294'>294</a>
<a id='n295' href='#n295'>295</a>
<a id='n296' href='#n296'>296</a>
<a id='n297' href='#n297'>297</a>
<a id='n298' href='#n298'>298</a>
<a id='n299' href='#n299'>299</a>
<a id='n300' href='#n300'>300</a>
<a id='n301' href='#n301'>301</a>
<a id='n302' href='#n302'>302</a>
<a id='n303' href='#n303'>303</a>
<a id='n304' href='#n304'>304</a>
<a id='n305' href='#n305'>305</a>
<a id='n306' href='#n306'>306</a>
<a id='n307' href='#n307'>307</a>
<a id='n308' href='#n308'>308</a>
<a id='n309' href='#n309'>309</a>
<a id='n310' href='#n310'>310</a>
<a id='n311' href='#n311'>311</a>
<a id='n312' href='#n312'>312</a>
<a id='n313' href='#n313'>313</a>
<a id='n314' href='#n314'>314</a>
<a id='n315' href='#n315'>315</a>
<a id='n316' href='#n316'>316</a>
<a id='n317' href='#n317'>317</a>
<a id='n318' href='#n318'>318</a>
<a id='n319' href='#n319'>319</a>
<a id='n320' href='#n320'>320</a>
<a id='n321' href='#n321'>321</a>
<a id='n322' href='#n322'>322</a>
<a id='n323' href='#n323'>323</a>
<a id='n324' href='#n324'>324</a>
<a id='n325' href='#n325'>325</a>
<a id='n326' href='#n326'>326</a>
<a id='n327' href='#n327'>327</a>
<a id='n328' href='#n328'>328</a>
<a id='n329' href='#n329'>329</a>
<a id='n330' href='#n330'>330</a>
<a id='n331' href='#n331'>331</a>
<a id='n332' href='#n332'>332</a>
<a id='n333' href='#n333'>333</a>
<a id='n334' href='#n334'>334</a>
<a id='n335' href='#n335'>335</a>
<a id='n336' href='#n336'>336</a>
<a id='n337' href='#n337'>337</a>
<a id='n338' href='#n338'>338</a>
<a id='n339' href='#n339'>339</a>
<a id='n340' href='#n340'>340</a>
<a id='n341' href='#n341'>341</a>
<a id='n342' href='#n342'>342</a>
<a id='n343' href='#n343'>343</a>
<a id='n344' href='#n344'>344</a>
<a id='n345' href='#n345'>345</a>
<a id='n346' href='#n346'>346</a>
<a id='n347' href='#n347'>347</a>
<a id='n348' href='#n348'>348</a>
<a id='n349' href='#n349'>349</a>
<a id='n350' href='#n350'>350</a>
<a id='n351' href='#n351'>351</a>
<a id='n352' href='#n352'>352</a>
<a id='n353' href='#n353'>353</a>
<a id='n354' href='#n354'>354</a>
<a id='n355' href='#n355'>355</a>
<a id='n356' href='#n356'>356</a>
<a id='n357' href='#n357'>357</a>
<a id='n358' href='#n358'>358</a>
<a id='n359' href='#n359'>359</a>
<a id='n360' href='#n360'>360</a>
<a id='n361' href='#n361'>361</a>
<a id='n362' href='#n362'>362</a>
<a id='n363' href='#n363'>363</a>
<a id='n364' href='#n364'>364</a>
<a id='n365' href='#n365'>365</a>
<a id='n366' href='#n366'>366</a>
<a id='n367' href='#n367'>367</a>
<a id='n368' href='#n368'>368</a>
<a id='n369' href='#n369'>369</a>
<a id='n370' href='#n370'>370</a>
<a id='n371' href='#n371'>371</a>
<a id='n372' href='#n372'>372</a>
<a id='n373' href='#n373'>373</a>
<a id='n374' href='#n374'>374</a>
<a id='n375' href='#n375'>375</a>
<a id='n376' href='#n376'>376</a>
<a id='n377' href='#n377'>377</a>
<a id='n378' href='#n378'>378</a>
<a id='n379' href='#n379'>379</a>
<a id='n380' href='#n380'>380</a>
<a id='n381' href='#n381'>381</a>
<a id='n382' href='#n382'>382</a>
<a id='n383' href='#n383'>383</a>
<a id='n384' href='#n384'>384</a>
<a id='n385' href='#n385'>385</a>
<a id='n386' href='#n386'>386</a>
<a id='n387' href='#n387'>387</a>
<a id='n388' href='#n388'>388</a>
<a id='n389' href='#n389'>389</a>
<a id='n390' href='#n390'>390</a>
<a id='n391' href='#n391'>391</a>
<a id='n392' href='#n392'>392</a>
<a id='n393' href='#n393'>393</a>
<a id='n394' href='#n394'>394</a>
<a id='n395' href='#n395'>395</a>
<a id='n396' href='#n396'>396</a>
<a id='n397' href='#n397'>397</a>
<a id='n398' href='#n398'>398</a>
<a id='n399' href='#n399'>399</a>
<a id='n400' href='#n400'>400</a>
<a id='n401' href='#n401'>401</a>
<a id='n402' href='#n402'>402</a>
<a id='n403' href='#n403'>403</a>
<a id='n404' href='#n404'>404</a>
<a id='n405' href='#n405'>405</a>
<a id='n406' href='#n406'>406</a>
<a id='n407' href='#n407'>407</a>
<a id='n408' href='#n408'>408</a>
<a id='n409' href='#n409'>409</a>
<a id='n410' href='#n410'>410</a>
<a id='n411' href='#n411'>411</a>
<a id='n412' href='#n412'>412</a>
<a id='n413' href='#n413'>413</a>
</pre></td>
<td class='lines'><pre><code>