XS.pm000064400000006752000000000000005407 0ustar00package Algorithm::Diff::XS; use 5.006; use strict; use warnings; use vars '$VERSION'; use Algorithm::Diff; BEGIN { $VERSION = '0.04'; require XSLoader; XSLoader::load( __PACKAGE__, $VERSION ); my $code = do { open my $fh, '<', $INC{'Algorithm/Diff.pm'} or die "Cannot read $INC{'Algorithm/Diff.pm'}: $!"; local $/; <$fh>; }; { no warnings; local $@; $code =~ s/Algorithm::Diff/Algorithm::Diff::XS/g; $code =~ s/sub LCSidx/sub LCSidx_old/g; $code = "#line 1 " . __FILE__ . "\n$code"; eval $code; die $@ if $@; } no warnings 'redefine'; sub LCSidx { my $lcs = Algorithm::Diff::XS->_CREATE_; my ( @l, @r ); for my $chunk ( $lcs->_LCS_(@_) ) { push @l, $chunk->[0]; push @r, $chunk->[1]; } return ( \@l, \@r ); } } sub _line_map_ { my $ctx = shift; my %lines; push @{ $lines{ $_[$_] } }, $_ for 0 .. $#_; # values MUST be SvIOK \%lines; } sub _LCS_ { my ( $ctx, $a, $b ) = @_; my ( $amin, $amax, $bmin, $bmax ) = ( 0, $#$a, 0, $#$b ); while ( $amin <= $amax and $bmin <= $bmax and $a->[$amin] eq $b->[$bmin] ) { $amin++; $bmin++; } while ( $amin <= $amax and $bmin <= $bmax and $a->[$amax] eq $b->[$bmax] ) { $amax--; $bmax--; } my $h = $ctx->_line_map_( @$b[ $bmin .. $bmax ] ); # line numbers are off by $bmin return $amin + _core_loop_( $ctx, $a, $amin, $amax, $h ) + ( $#$a - $amax ) unless wantarray; my @lcs = _core_loop_( $ctx, $a, $amin, $amax, $h ); if ( $bmin > 0 ) { $_->[1] += $bmin for @lcs; # correct line numbers } map( [ $_ => $_ ], 0 .. ( $amin - 1 ) ), @lcs, map( [ $_ => ++$bmax ], ( $amax + 1 ) .. $#$a ); } 1; __END__ =head1 NAME Algorithm::Diff::XS - Algorithm::Diff with XS core loop =head1 SYNOPSIS # Drop-in replacement to Algorithm::Diff, but "compact_diff" # and C will run much faster for large data sets. use Algorithm::Diff::XS qw( compact_diff LCSidx ); =head1 DESCRIPTION This module is a simple re-packaging of Joe Schaefer's excellent but not very well-known L with a drop-in interface that simply re-uses the installed version of the L module. Note that only the C function is optimized in XS at the moment, which means only C will get significantly faster for large data sets, while C and C will run in identical speed as C. =head1 BENCHMARK Rate Algorithm::Diff Algorithm::Diff::XS Algorithm::Diff 14.7/s -- -98% Algorithm::Diff::XS 806/s 5402% -- The benchmarking script is as below: my @data = ([qw/a b d/ x 50], [qw/b a d c/ x 50]); cmpthese( 500, { 'Algorithm::Diff' => sub { Algorithm::Diff::compact_diff(@data) }, 'Algorithm::Diff::XS' => sub { Algorithm::Diff::XS::compact_diff(@data) }, }); =head1 SEE ALSO L, L. =head1 AUTHORS Audrey Tang Ecpan@audreyt.orgE =head1 COPYRIGHT Copyright 2008 by Audrey Tang Ecpan@audreyt.orgE. Contains derived code copyrighted 2003 by Joe Schaefer, Ejoe+cpan@sunstarsys.comE. This library is free software; you can redistribute it and/or modify it under the same terms as Perl itself. =cut Renderer/inline.php000075500000012630000000000000010247 0ustar00'; /** * Suffix for inserted text. * * @var string */ var $_ins_suffix = ''; /** * Prefix for deleted text. * * @var string */ var $_del_prefix = ''; /** * Suffix for deleted text. * * @var string */ var $_del_suffix = ''; /** * Header for each change block. * * @var string */ var $_block_header = ''; /** * Whether to split down to character-level. * * @var boolean */ var $_split_characters = false; /** * What are we currently splitting on? Used to recurse to show word-level * or character-level changes. * * @var string */ var $_split_level = 'lines'; function _blockHeader($xbeg, $xlen, $ybeg, $ylen) { return $this->_block_header; } function _startBlock($header) { return $header; } function _lines($lines, $prefix = ' ', $encode = true) { if ($encode) { array_walk($lines, array(&$this, '_encode')); } if ($this->_split_level == 'lines') { return implode("\n", $lines) . "\n"; } else { return implode('', $lines); } } function _added($lines) { array_walk($lines, array(&$this, '_encode')); $lines[0] = $this->_ins_prefix . $lines[0]; $lines[count($lines) - 1] .= $this->_ins_suffix; return $this->_lines($lines, ' ', false); } function _deleted($lines, $words = false) { array_walk($lines, array(&$this, '_encode')); $lines[0] = $this->_del_prefix . $lines[0]; $lines[count($lines) - 1] .= $this->_del_suffix; return $this->_lines($lines, ' ', false); } function _changed($orig, $final) { /* If we've already split on characters, just display. */ if ($this->_split_level == 'characters') { return $this->_deleted($orig) . $this->_added($final); } /* If we've already split on words, just display. */ if ($this->_split_level == 'words') { $prefix = ''; while ($orig[0] !== false && $final[0] !== false && substr($orig[0], 0, 1) == ' ' && substr($final[0], 0, 1) == ' ') { $prefix .= substr($orig[0], 0, 1); $orig[0] = substr($orig[0], 1); $final[0] = substr($final[0], 1); } return $prefix . $this->_deleted($orig) . $this->_added($final); } $text1 = implode("\n", $orig); $text2 = implode("\n", $final); /* Non-printing newline marker. */ $nl = "\0"; if ($this->_split_characters) { $diff = new Text_Diff('native', array(preg_split('//', $text1), preg_split('//', $text2))); } else { /* We want to split on word boundaries, but we need to preserve * whitespace as well. Therefore we split on words, but include * all blocks of whitespace in the wordlist. */ $diff = new Text_Diff('native', array($this->_splitOnWords($text1, $nl), $this->_splitOnWords($text2, $nl))); } /* Get the diff in inline format. */ $renderer = new Text_Diff_Renderer_inline (array_merge($this->getParams(), array('split_level' => $this->_split_characters ? 'characters' : 'words'))); /* Run the diff and get the output. */ return str_replace($nl, "\n", $renderer->render($diff)) . "\n"; } function _splitOnWords($string, $newlineEscape = "\n") { // Ignore \0; otherwise the while loop will never finish. $string = str_replace("\0", '', $string); $words = array(); $length = strlen($string); $pos = 0; while ($pos < $length) { // Eat a word with any preceding whitespace. $spaces = strspn(substr($string, $pos), " \n"); $nextpos = strcspn(substr($string, $pos + $spaces), " \n"); $words[] = str_replace("\n", $newlineEscape, substr($string, $pos, $spaces + $nextpos)); $pos += $spaces + $nextpos; } return $words; } function _encode(&$string) { $string = htmlspecialchars($string); } } Engine/shell.php000075500000012123000000000000007534 0ustar00 * @package Text_Diff * @since 0.3.0 */ class Text_Diff_Engine_shell { /** * Path to the diff executable * * @var string */ var $_diffCommand = 'diff'; /** * Returns the array of differences. * * @param array $from_lines lines of text from old file * @param array $to_lines lines of text from new file * * @return array all changes made (array with Text_Diff_Op_* objects) */ function diff($from_lines, $to_lines) { array_walk($from_lines, array('Text_Diff', 'trimNewlines')); array_walk($to_lines, array('Text_Diff', 'trimNewlines')); $temp_dir = Text_Diff::_getTempDir(); // Execute gnu diff or similar to get a standard diff file. $from_file = tempnam($temp_dir, 'Text_Diff'); $to_file = tempnam($temp_dir, 'Text_Diff'); $fp = fopen($from_file, 'w'); fwrite($fp, implode("\n", $from_lines)); fclose($fp); $fp = fopen($to_file, 'w'); fwrite($fp, implode("\n", $to_lines)); fclose($fp); $diff = shell_exec($this->_diffCommand . ' ' . $from_file . ' ' . $to_file); unlink($from_file); unlink($to_file); if (is_null($diff)) { // No changes were made return array(new Text_Diff_Op_copy($from_lines)); } $from_line_no = 1; $to_line_no = 1; $edits = array(); // Get changed lines by parsing something like: // 0a1,2 // 1,2c4,6 // 1,5d6 preg_match_all('#^(\d+)(?:,(\d+))?([adc])(\d+)(?:,(\d+))?$#m', $diff, $matches, PREG_SET_ORDER); foreach ($matches as $match) { if (!isset($match[5])) { // This paren is not set every time (see regex). $match[5] = false; } if ($match[3] == 'a') { $from_line_no--; } if ($match[3] == 'd') { $to_line_no--; } if ($from_line_no < $match[1] || $to_line_no < $match[4]) { // copied lines assert($match[1] - $from_line_no == $match[4] - $to_line_no); array_push($edits, new Text_Diff_Op_copy( $this->_getLines($from_lines, $from_line_no, $match[1] - 1), $this->_getLines($to_lines, $to_line_no, $match[4] - 1))); } switch ($match[3]) { case 'd': // deleted lines array_push($edits, new Text_Diff_Op_delete( $this->_getLines($from_lines, $from_line_no, $match[2]))); $to_line_no++; break; case 'c': // changed lines array_push($edits, new Text_Diff_Op_change( $this->_getLines($from_lines, $from_line_no, $match[2]), $this->_getLines($to_lines, $to_line_no, $match[5]))); break; case 'a': // added lines array_push($edits, new Text_Diff_Op_add( $this->_getLines($to_lines, $to_line_no, $match[5]))); $from_line_no++; break; } } if (!empty($from_lines)) { // Some lines might still be pending. Add them as copied array_push($edits, new Text_Diff_Op_copy( $this->_getLines($from_lines, $from_line_no, $from_line_no + count($from_lines) - 1), $this->_getLines($to_lines, $to_line_no, $to_line_no + count($to_lines) - 1))); } return $edits; } /** * Get lines from either the old or new text * * @access private * * @param array $text_lines Either $from_lines or $to_lines (passed by reference). * @param int $line_no Current line number (passed by reference). * @param int $end Optional end line, when we want to chop more * than one line. * * @return array The chopped lines */ function _getLines(&$text_lines, &$line_no, $end = false) { if (!empty($end)) { $lines = array(); // We can shift even more while ($line_no <= $end) { array_push($lines, array_shift($text_lines)); $line_no++; } } else { $lines = array(array_shift($text_lines)); $line_no++; } return $lines; } } Engine/native.php000075500000037261000000000000007725 0ustar00 2, and some optimizations) are from * Geoffrey T. Dairiki . The original PHP version of this * code was written by him, and is used/adapted with his permission. * * Copyright 2004-2010 The Horde Project (http://www.horde.org/) * * See the enclosed file COPYING for license information (LGPL). If you did * not receive this file, see https://opensource.org/license/lgpl-2-1/. * * @author Geoffrey T. Dairiki * @package Text_Diff */ class Text_Diff_Engine_native { public $xchanged; public $ychanged; public $xv; public $yv; public $xind; public $yind; public $seq; public $in_seq; public $lcs; function diff($from_lines, $to_lines) { array_walk($from_lines, array('Text_Diff', 'trimNewlines')); array_walk($to_lines, array('Text_Diff', 'trimNewlines')); $n_from = count($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 $edits; } /** * Divides the Largest Common Subsequence (LCS) of the sequences (XOFF, * XLIM) and (YOFF, YLIM) into NCHUNKS approximately equally sized * segments. * * Returns (LCS, PTS). LCS is the length of the LCS. PTS is an array of * NCHUNKS+1 (X, Y) indexes giving the diving points between sub * sequences. The first sub-sequence is contained in (X0, X1), (Y0, Y1), * the second in (X1, X2), (Y1, Y2) and so on. Note that (X0, Y0) == * (XOFF, YOFF) and (X[NCHUNKS], Y[NCHUNKS]) == (XLIM, YLIM). * * This function assumes that the first lines of the specified portions of * the two files do not match, and likewise that the last lines do not * match. The caller must trim matching lines from the beginning and end * of the portions it is going to specify. */ function _diag ($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($matches); while ($y = current($matches)) { if (empty($this->in_seq[$y])) { $k = $this->_lcsPos($y); assert($k > 0); $ymids[$k] = $ymids[$k - 1]; break; } next($matches); } while ($y = current($matches)) { if ($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]; } next($matches); } } } $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; } /** * 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 = $pt2; } } } /** * Adjusts inserts/deletes of identical lines to join changes as much as * possible. * * We do something when a run of changed lines include a line at one end * and has an excluded, identical line at the other. We are free to * choose which identical line is included. `compareseq' usually chooses * the one at the beginning, but usually it is cleaner to consider the * following identical line to be the "change". * * This is extracted verbatim from analyze.c (GNU diffutils-2.7). */ function _shiftBoundaries($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]); } } } } Engine/string.php000075500000020233000000000000007734 0ustar00 * $patch = file_get_contents('example.patch'); * $diff = new Text_Diff('string', array($patch)); * $renderer = new Text_Diff_Renderer_inline(); * echo $renderer->render($diff); * * * Copyright 2005 Örjan Persson * Copyright 2005-2010 The Horde Project (http://www.horde.org/) * * See the enclosed file COPYING for license information (LGPL). If you did * not receive this file, see https://opensource.org/license/lgpl-2-1/. * * @author Örjan Persson * @package Text_Diff * @since 0.2.0 */ class Text_Diff_Engine_string { /** * Parses a unified or context diff. * * First param contains the whole diff and the second can be used to force * a specific diff type. If the second parameter is 'autodetect', the * diff will be examined to find out which type of diff this is. * * @param string $diff The diff content. * @param string $mode The diff mode of the content in $diff. One of * 'context', 'unified', or 'autodetect'. * * @return array List of all diff operations. */ function diff($diff, $mode = 'autodetect') { // Detect line breaks. $lnbr = "\n"; if (strpos($diff, "\r\n") !== false) { $lnbr = "\r\n"; } elseif (strpos($diff, "\r") !== false) { $lnbr = "\r"; } // Make sure we have a line break at the EOF. if (substr($diff, -strlen($lnbr)) != $lnbr) { $diff .= $lnbr; } if ($mode != 'autodetect' && $mode != 'context' && $mode != 'unified') { return PEAR::raiseError('Type of diff is unsupported'); } if ($mode == 'autodetect') { $context = strpos($diff, '***'); $unified = strpos($diff, '---'); if ($context === $unified) { return PEAR::raiseError('Type of diff could not be detected'); } elseif ($context === false || $unified === false) { $mode = $context !== false ? 'context' : 'unified'; } else { $mode = $context < $unified ? 'context' : 'unified'; } } // Split by new line and remove the diff header, if there is one. $diff = explode($lnbr, $diff); if (($mode == 'context' && strpos($diff[0], '***') === 0) || ($mode == 'unified' && strpos($diff[0], '---') === 0)) { array_shift($diff); array_shift($diff); } if ($mode == 'context') { return $this->parseContextDiff($diff); } else { return $this->parseUnifiedDiff($diff); } } /** * Parses an array containing the unified diff. * * @param array $diff Array of lines. * * @return array List of all diff operations. */ function parseUnifiedDiff($diff) { $edits = array(); $end = count($diff) - 1; for ($i = 0; $i < $end;) { $diff1 = array(); switch (substr($diff[$i], 0, 1)) { case ' ': do { $diff1[] = substr($diff[$i], 1); } while (++$i < $end && substr($diff[$i], 0, 1) == ' '); $edits[] = new Text_Diff_Op_copy($diff1); break; case '+': // get all new lines do { $diff1[] = substr($diff[$i], 1); } while (++$i < $end && substr($diff[$i], 0, 1) == '+'); $edits[] = new Text_Diff_Op_add($diff1); break; case '-': // get changed or removed lines $diff2 = array(); do { $diff1[] = substr($diff[$i], 1); } while (++$i < $end && substr($diff[$i], 0, 1) == '-'); while ($i < $end && substr($diff[$i], 0, 1) == '+') { $diff2[] = substr($diff[$i++], 1); } if (count($diff2) == 0) { $edits[] = new Text_Diff_Op_delete($diff1); } else { $edits[] = new Text_Diff_Op_change($diff1, $diff2); } break; default: $i++; break; } } return $edits; } /** * Parses an array containing the context diff. * * @param array $diff Array of lines. * * @return array List of all diff operations. */ function parseContextDiff(&$diff) { $edits = array(); $i = $max_i = $j = $max_j = 0; $end = count($diff) - 1; while ($i < $end && $j < $end) { while ($i >= $max_i && $j >= $max_j) { // Find the boundaries of the diff output of the two files for ($i = $j; $i < $end && substr($diff[$i], 0, 3) == '***'; $i++); for ($max_i = $i; $max_i < $end && substr($diff[$max_i], 0, 3) != '---'; $max_i++); for ($j = $max_i; $j < $end && substr($diff[$j], 0, 3) == '---'; $j++); for ($max_j = $j; $max_j < $end && substr($diff[$max_j], 0, 3) != '***'; $max_j++); } // find what hasn't been changed $array = array(); while ($i < $max_i && $j < $max_j && strcmp($diff[$i], $diff[$j]) == 0) { $array[] = substr($diff[$i], 2); $i++; $j++; } while ($i < $max_i && ($max_j-$j) <= 1) { if ($diff[$i] != '' && substr($diff[$i], 0, 1) != ' ') { break; } $array[] = substr($diff[$i++], 2); } while ($j < $max_j && ($max_i-$i) <= 1) { if ($diff[$j] != '' && substr($diff[$j], 0, 1) != ' ') { break; } $array[] = substr($diff[$j++], 2); } if (count($array) > 0) { $edits[] = new Text_Diff_Op_copy($array); } if ($i < $max_i) { $diff1 = array(); switch (substr($diff[$i], 0, 1)) { case '!': $diff2 = array(); do { $diff1[] = substr($diff[$i], 2); if ($j < $max_j && substr($diff[$j], 0, 1) == '!') { $diff2[] = substr($diff[$j++], 2); } } while (++$i < $max_i && substr($diff[$i], 0, 1) == '!'); $edits[] = new Text_Diff_Op_change($diff1, $diff2); break; case '+': do { $diff1[] = substr($diff[$i], 2); } while (++$i < $max_i && substr($diff[$i], 0, 1) == '+'); $edits[] = new Text_Diff_Op_add($diff1); break; case '-': do { $diff1[] = substr($diff[$i], 2); } while (++$i < $max_i && substr($diff[$i], 0, 1) == '-'); $edits[] = new Text_Diff_Op_delete($diff1); break; } } if ($j < $max_j) { $diff2 = array(); switch (substr($diff[$j], 0, 1)) { case '+': do { $diff2[] = substr($diff[$j++], 2); } while ($j < $max_j && substr($diff[$j], 0, 1) == '+'); $edits[] = new Text_Diff_Op_add($diff2); break; case '-': do { $diff2[] = substr($diff[$j++], 2); } while ($j < $max_j && substr($diff[$j], 0, 1) == '-'); $edits[] = new Text_Diff_Op_delete($diff2); break; } } } return $edits; } } Engine/xdiff.php000075500000004233000000000000007530 0ustar00 * @package Text_Diff */ class Text_Diff_Engine_xdiff { /** */ function diff($from_lines, $to_lines) { array_walk($from_lines, array('Text_Diff', 'trimNewlines')); array_walk($to_lines, array('Text_Diff', 'trimNewlines')); /* 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 $line) { if (!strlen($line)) { continue; } 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; } } Renderer.php000075500000015226000000000000006775 0ustar00 $value) { $v = '_' . $param; if (isset($this->$v)) { $this->$v = $value; } } } /** * PHP4 constructor. */ public function Text_Diff_Renderer( $params = array() ) { self::__construct( $params ); } /** * Get any renderer parameters. * * @return array All parameters of this renderer object. */ function getParams() { $params = array(); foreach (get_object_vars($this) as $k => $v) { if ($k[0] == '_') { $params[substr($k, 1)] = $v; } } return $params; } /** * Renders a diff. * * @param Text_Diff $diff A Text_Diff object. * * @return string The formatted output. */ function render($diff) { $xi = $yi = 1; $block = false; $context = array(); $nlead = $this->_leading_context_lines; $ntrail = $this->_trailing_context_lines; $output = $this->_startDiff(); $diffs = $diff->getDiff(); foreach ($diffs as $i => $edit) { /* If these are unchanged (copied) lines, and we want to keep * leading or trailing context lines, extract them from the copy * block. */ if (is_a($edit, 'Text_Diff_Op_copy')) { /* Do we have any diff blocks yet? */ if (is_array($block)) { /* How many lines to keep as context from the copy * block. */ $keep = $i == count($diffs) - 1 ? $ntrail : $nlead + $ntrail; if (count($edit->orig) <= $keep) { /* We have less lines in the block than we want for * context => keep the whole block. */ $block[] = $edit; } else { if ($ntrail) { /* Create a new block with as many lines as we need * for the trailing context. */ $context = array_slice($edit->orig, 0, $ntrail); $block[] = new Text_Diff_Op_copy($context); } /* @todo */ $output .= $this->_block($x0, $ntrail + $xi - $x0, $y0, $ntrail + $yi - $y0, $block); $block = false; } } /* Keep the copy block as the context for the next block. */ $context = $edit->orig; } else { /* Don't we have any diff blocks yet? */ if (!is_array($block)) { /* Extract context lines from the preceding copy block. */ $context = array_slice($context, count($context) - $nlead); $x0 = $xi - count($context); $y0 = $yi - count($context); $block = array(); if ($context) { $block[] = new Text_Diff_Op_copy($context); } } $block[] = $edit; } if ($edit->orig) { $xi += count($edit->orig); } if ($edit->final) { $yi += count($edit->final); } } if (is_array($block)) { $output .= $this->_block($x0, $xi - $x0, $y0, $yi - $y0, $block); } return $output . $this->_endDiff(); } function _block($xbeg, $xlen, $ybeg, $ylen, &$edits) { $output = $this->_startBlock($this->_blockHeader($xbeg, $xlen, $ybeg, $ylen)); foreach ($edits as $edit) { switch (strtolower(get_class($edit))) { case 'text_diff_op_copy': $output .= $this->_context($edit->orig); break; case 'text_diff_op_add': $output .= $this->_added($edit->final); break; case 'text_diff_op_delete': $output .= $this->_deleted($edit->orig); break; case 'text_diff_op_change': $output .= $this->_changed($edit->orig, $edit->final); break; } } return $output . $this->_endBlock(); } function _startDiff() { return ''; } function _endDiff() { return ''; } function _blockHeader($xbeg, $xlen, $ybeg, $ylen) { if ($xlen > 1) { $xbeg .= ',' . ($xbeg + $xlen - 1); } if ($ylen > 1) { $ybeg .= ',' . ($ybeg + $ylen - 1); } // this matches the GNU Diff behaviour if ($xlen && !$ylen) { $ybeg--; } elseif (!$xlen) { $xbeg--; } return $xbeg . ($xlen ? ($ylen ? 'c' : 'd') : 'a') . $ybeg; } function _startBlock($header) { return $header . "\n"; } function _endBlock() { return ''; } function _lines($lines, $prefix = ' ') { return $prefix . implode("\n$prefix", $lines) . "\n"; } function _context($lines) { return $this->_lines($lines, ' '); } function _added($lines) { return $this->_lines($lines, '> '); } function _deleted($lines) { return $this->_lines($lines, '< '); } function _changed($orig, $final) { return $this->_deleted($orig) . "---\n" . $this->_added($final); } } SequenceMatcher.php000075500000042720000000000000010302 0ustar00 * * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: * * - Redistributions of source code must retain the above copyright notice, * this list of conditions and the following disclaimer. * - Redistributions in binary form must reproduce the above copyright notice, * this list of conditions and the following disclaimer in the documentation * and/or other materials provided with the distribution. * - Neither the name of the Chris Boulton nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE * POSSIBILITY OF SUCH DAMAGE. * * @package Diff * @author Chris Boulton * @copyright (c) 2009 Chris Boulton * @license New BSD License http://www.opensource.org/licenses/bsd-license.php * @version 1.1 * @link http://github.com/chrisboulton/php-diff */ class Diff_SequenceMatcher { /** * @var string|array Either a string or an array containing a callback function to determine if a line is "junk" or not. */ private $junkCallback = null; /** * @var array The first sequence to compare against. */ private $a = null; /** * @var array The second sequence. */ private $b = null; /** * @var array Array of characters that are considered junk from the second sequence. Characters are the array key. */ private $junkDict = array(); /** * @var array Array of indices that do not contain junk elements. */ private $b2j = array(); private $options = array(); private $defaultOptions = array( 'ignoreNewLines' => false, 'ignoreWhitespace' => false, 'ignoreCase' => false ); private $matchingBlocks = null; private $opCodes = null; private $fullBCount = null; /** * The constructor. With the sequences being passed, they'll be set for the * sequence matcher and it will perform a basic cleanup & calculate junk * elements. * * @param string|array $a A string or array containing the lines to compare against. * @param string|array $b A string or array containing the lines to compare. * @param string|array $junkCallback Either an array or string that references a callback function (if there is one) to determine 'junk' characters. */ public function __construct($a, $b, $junkCallback=null, $options=array()) { $this->a = null; $this->b = null; $this->junkCallback = $junkCallback; $this->setOptions($options); $this->setSequences($a, $b); } public function setOptions($options) { $this->options = array_merge($this->defaultOptions, $options); } /** * Set the first and second sequences to use with the sequence matcher. * * @param string|array $a A string or array containing the lines to compare against. * @param string|array $b A string or array containing the lines to compare. */ public function setSequences($a, $b) { $this->setSeq1($a); $this->setSeq2($b); } /** * Set the first sequence ($a) and reset any internal caches to indicate that * when calling the calculation methods, we need to recalculate them. * * @param string|array $a The sequence to set as the first sequence. */ public function setSeq1($a) { if(!is_array($a)) { $a = str_split($a); } if($a == $this->a) { return; } $this->a= $a; $this->matchingBlocks = null; $this->opCodes = null; } /** * Set the second sequence ($b) and reset any internal caches to indicate that * when calling the calculation methods, we need to recalculate them. * * @param string|array $b The sequence to set as the second sequence. */ public function setSeq2($b) { if(!is_array($b)) { $b = str_split($b); } if($b == $this->b) { return; } $this->b = $b; $this->matchingBlocks = null; $this->opCodes = null; $this->fullBCount = null; $this->chainB(); } /** * Generate the internal arrays containing the list of junk and non-junk * characters for the second ($b) sequence. */ private function chainB() { $length = count ($this->b); $this->b2j = array(); $popularDict = array(); for($i = 0; $i < $length; ++$i) { $char = $this->b[$i]; if(isset($this->b2j[$char])) { if($length >= 200 && count($this->b2j[$char]) * 100 > $length) { $popularDict[$char] = 1; unset($this->b2j[$char]); } else { $this->b2j[$char][] = $i; } } else { $this->b2j[$char] = array( $i ); } } // Remove leftovers foreach(array_keys($popularDict) as $char) { unset($this->b2j[$char]); } $this->junkDict = array(); if(is_callable($this->junkCallback)) { foreach(array_keys($popularDict) as $char) { if(call_user_func($this->junkCallback, $char)) { $this->junkDict[$char] = 1; unset($popularDict[$char]); } } foreach(array_keys($this->b2j) as $char) { if(call_user_func($this->junkCallback, $char)) { $this->junkDict[$char] = 1; unset($this->b2j[$char]); } } } } /** * Checks if a particular character is in the junk dictionary * for the list of junk characters. * * @return boolean $b True if the character is considered junk. False if not. */ private function isBJunk($b) { if(isset($this->juncDict[$b])) { return true; } return false; } /** * Find the longest matching block in the two sequences, as defined by the * lower and upper constraints for each sequence. (for the first sequence, * $alo - $ahi and for the second sequence, $blo - $bhi) * * Essentially, of all of the maximal matching blocks, return the one that * startest earliest in $a, and all of those maximal matching blocks that * start earliest in $a, return the one that starts earliest in $b. * * If the junk callback is defined, do the above but with the restriction * that the junk element appears in the block. Extend it as far as possible * by matching only junk elements in both $a and $b. * * @param int $alo The lower constraint for the first sequence. * @param int $ahi The upper constraint for the first sequence. * @param int $blo The lower constraint for the second sequence. * @param int $bhi The upper constraint for the second sequence. * @return array Array containing the longest match that includes the starting position in $a, start in $b and the length/size. */ public function findLongestMatch($alo, $ahi, $blo, $bhi) { $a = $this->a; $b = $this->b; $bestI = $alo; $bestJ = $blo; $bestSize = 0; $j2Len = array(); $nothing = array(); for($i = $alo; $i < $ahi; ++$i) { $newJ2Len = array(); $jDict = $this->arrayGetDefault($this->b2j, $a[$i], $nothing); foreach($jDict as $jKey => $j) { if($j < $blo) { continue; } else if($j >= $bhi) { break; } $k = $this->arrayGetDefault($j2Len, $j -1, 0) + 1; $newJ2Len[$j] = $k; if($k > $bestSize) { $bestI = $i - $k + 1; $bestJ = $j - $k + 1; $bestSize = $k; } } $j2Len = $newJ2Len; } while($bestI > $alo && $bestJ > $blo && !$this->isBJunk($b[$bestJ - 1]) && !$this->linesAreDifferent($bestI - 1, $bestJ - 1)) { --$bestI; --$bestJ; ++$bestSize; } while($bestI + $bestSize < $ahi && ($bestJ + $bestSize) < $bhi && !$this->isBJunk($b[$bestJ + $bestSize]) && !$this->linesAreDifferent($bestI + $bestSize, $bestJ + $bestSize)) { ++$bestSize; } while($bestI > $alo && $bestJ > $blo && $this->isBJunk($b[$bestJ - 1]) && !$this->isLineDifferent($bestI - 1, $bestJ - 1)) { --$bestI; --$bestJ; ++$bestSize; } while($bestI + $bestSize < $ahi && $bestJ + $bestSize < $bhi && $this->isBJunk($b[$bestJ + $bestSize]) && !$this->linesAreDifferent($bestI + $bestSize, $bestJ + $bestSize)) { ++$bestSize; } return array( $bestI, $bestJ, $bestSize ); } /** * Check if the two lines at the given indexes are different or not. * * @param int $aIndex Line number to check against in a. * @param int $bIndex Line number to check against in b. * @return boolean True if the lines are different and false if not. */ public function linesAreDifferent($aIndex, $bIndex) { $lineA = $this->a[$aIndex]; $lineB = $this->b[$bIndex]; if($this->options['ignoreWhitespace']) { $replace = array("\t", ' '); $lineA = str_replace($replace, '', $lineA); $lineB = str_replace($replace, '', $lineB); } if($this->options['ignoreCase']) { $lineA = strtolower($lineA); $lineB = strtolower($lineB); } if($lineA != $lineB) { return true; } return false; } /** * Return a nested set of arrays for all of the matching sub-sequences * in the strings $a and $b. * * Each block contains the lower constraint of the block in $a, the lower * constraint of the block in $b and finally the number of lines that the * block continues for. * * @return array Nested array of the matching blocks, as described by the function. */ public function getMatchingBlocks() { if(!empty($this->matchingBlocks)) { return $this->matchingBlocks; } $aLength = count($this->a); $bLength = count($this->b); $queue = array( array( 0, $aLength, 0, $bLength ) ); $matchingBlocks = array(); while(!empty($queue)) { list($alo, $ahi, $blo, $bhi) = array_pop($queue); $x = $this->findLongestMatch($alo, $ahi, $blo, $bhi); list($i, $j, $k) = $x; if($k) { $matchingBlocks[] = $x; if($alo < $i && $blo < $j) { $queue[] = array( $alo, $i, $blo, $j ); } if($i + $k < $ahi && $j + $k < $bhi) { $queue[] = array( $i + $k, $ahi, $j + $k, $bhi ); } } } usort($matchingBlocks, array($this, 'tupleSort')); $i1 = 0; $j1 = 0; $k1 = 0; $nonAdjacent = array(); foreach($matchingBlocks as $block) { list($i2, $j2, $k2) = $block; if($i1 + $k1 == $i2 && $j1 + $k1 == $j2) { $k1 += $k2; } else { if($k1) { $nonAdjacent[] = array( $i1, $j1, $k1 ); } $i1 = $i2; $j1 = $j2; $k1 = $k2; } } if($k1) { $nonAdjacent[] = array( $i1, $j1, $k1 ); } $nonAdjacent[] = array( $aLength, $bLength, 0 ); $this->matchingBlocks = $nonAdjacent; return $this->matchingBlocks; } /** * Return a list of all of the opcodes for the differences between the * two strings. * * The nested array returned contains an array describing the opcode * which includes: * 0 - The type of tag (as described below) for the opcode. * 1 - The beginning line in the first sequence. * 2 - The end line in the first sequence. * 3 - The beginning line in the second sequence. * 4 - The end line in the second sequence. * * The different types of tags include: * replace - The string from $i1 to $i2 in $a should be replaced by * the string in $b from $j1 to $j2. * delete - The string in $a from $i1 to $j2 should be deleted. * insert - The string in $b from $j1 to $j2 should be inserted at * $i1 in $a. * equal - The two strings with the specified ranges are equal. * * @return array Array of the opcodes describing the differences between the strings. */ public function getOpCodes() { if(!empty($this->opCodes)) { return $this->opCodes; } $i = 0; $j = 0; $this->opCodes = array(); $blocks = $this->getMatchingBlocks(); foreach($blocks as $block) { list($ai, $bj, $size) = $block; $tag = ''; if($i < $ai && $j < $bj) { $tag = 'replace'; } else if($i < $ai) { $tag = 'delete'; } else if($j < $bj) { $tag = 'insert'; } if($tag) { $this->opCodes[] = array( $tag, $i, $ai, $j, $bj ); } $i = $ai + $size; $j = $bj + $size; if($size) { $this->opCodes[] = array( 'equal', $ai, $i, $bj, $j ); } } return $this->opCodes; } /** * Return a series of nested arrays containing different groups of generated * opcodes for the differences between the strings with up to $context lines * of surrounding content. * * Essentially what happens here is any big equal blocks of strings are stripped * out, the smaller subsets of changes are then arranged in to their groups. * This means that the sequence matcher and diffs do not need to include the full * content of the different files but can still provide context as to where the * changes are. * * @param int $context The number of lines of context to provide around the groups. * @return array Nested array of all of the grouped opcodes. */ public function getGroupedOpcodes($context=3) { $opCodes = $this->getOpCodes(); if(empty($opCodes)) { $opCodes = array( array( 'equal', 0, 1, 0, 1 ) ); } if($opCodes[0][0] == 'equal') { $opCodes[0] = array( $opCodes[0][0], max($opCodes[0][1], $opCodes[0][2] - $context), $opCodes[0][2], max($opCodes[0][3], $opCodes[0][4] - $context), $opCodes[0][4] ); } $lastItem = count($opCodes) - 1; if($opCodes[$lastItem][0] == 'equal') { list($tag, $i1, $i2, $j1, $j2) = $opCodes[$lastItem]; $opCodes[$lastItem] = array( $tag, $i1, min($i2, $i1 + $context), $j1, min($j2, $j1 + $context) ); } $maxRange = $context * 2; $groups = array(); $group = array(); foreach($opCodes as $code) { list($tag, $i1, $i2, $j1, $j2) = $code; if($tag == 'equal' && $i2 - $i1 > $maxRange) { $group[] = array( $tag, $i1, min($i2, $i1 + $context), $j1, min($j2, $j1 + $context) ); $groups[] = $group; $group = array(); $i1 = max($i1, $i2 - $context); $j1 = max($j1, $j2 - $context); } $group[] = array( $tag, $i1, $i2, $j1, $j2 ); } if(!empty($group) && !(count($group) == 1 && $group[0][0] == 'equal')) { $groups[] = $group; } return $groups; } /** * Return a measure of the similarity between the two sequences. * This will be a float value between 0 and 1. * * Out of all of the ratio calculation functions, this is the most * expensive to call if getMatchingBlocks or getOpCodes is yet to be * called. The other calculation methods (quickRatio and realquickRatio) * can be used to perform quicker calculations but may be less accurate. * * The ratio is calculated as (2 * number of matches) / total number of * elements in both sequences. * * @return float The calculated ratio. */ public function Ratio() { $matches = array_reduce($this->getMatchingBlocks(), array($this, 'ratioReduce'), 0); return $this->calculateRatio($matches, count ($this->a) + count ($this->b)); } /** * Helper function to calculate the number of matches for Ratio(). * * @param int $sum The running total for the number of matches. * @param array $triple Array containing the matching block triple to add to the running total. * @return int The new running total for the number of matches. */ private function ratioReduce($sum, $triple) { return $sum + ($triple[count($triple) - 1]); } /** * Helper function for calculating the ratio to measure similarity for the strings. * The ratio is defined as being 2 * (number of matches / total length) * * @param int $matches The number of matches in the two strings. * @param int $length The length of the two strings. * @return float The calculated ratio. */ private function calculateRatio($matches, $length=0) { if($length) { return 2 * ($matches / $length); } else { return 1; } } /** * Helper function that provides the ability to return the value for a key * in an array of it exists, or if it doesn't then return a default value. * Essentially cleaner than doing a series of if(isset()) {} else {} calls. * * @param array $array The array to search. * @param string $key The key to check that exists. * @param mixed $default The value to return as the default value if the key doesn't exist. * @return mixed The value from the array if the key exists or otherwise the default. */ private function arrayGetDefault($array, $key, $default) { if(isset($array[$key])) { return $array[$key]; } else { return $default; } } /** * Sort an array by the nested arrays it contains. Helper function for getMatchingBlocks * * @param array $a First array to compare. * @param array $b Second array to compare. * @return int -1, 0 or 1, as expected by the usort function. */ private function tupleSort($a, $b) { $max = max(count($a), count($b)); for($i = 0; $i < $max; ++$i) { if($a[$i] < $b[$i]) { return -1; } else if($a[$i] > $b[$i]) { return 1; } } if(count($a) == count($b)) { return 0; } else if(count($a) < count($b)) { return -1; } else { return 1; } } } Renderer/Abstract.php000075500000005752000000000000010543 0ustar00 * * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: * * - Redistributions of source code must retain the above copyright notice, * this list of conditions and the following disclaimer. * - Redistributions in binary form must reproduce the above copyright notice, * this list of conditions and the following disclaimer in the documentation * and/or other materials provided with the distribution. * - Neither the name of the Chris Boulton nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE * POSSIBILITY OF SUCH DAMAGE. * * @package DiffLib * @author Chris Boulton * @copyright (c) 2009 Chris Boulton * @license New BSD License http://www.opensource.org/licenses/bsd-license.php * @version 1.1 * @link http://github.com/chrisboulton/php-diff */ abstract class Diff_Renderer_Abstract { /** * @var object Instance of the diff class that this renderer is generating the rendered diff for. */ public $diff; /** * @var array Array of the default options that apply to this renderer. */ protected $defaultOptions = array(); /** * @var array Array containing the user applied and merged default options for the renderer. */ protected $options = array(); /** * The constructor. Instantiates the rendering engine and if options are passed, * sets the options for the renderer. * * @param array $options Optionally, an array of the options for the renderer. */ public function __construct(array $options = array()) { $this->setOptions($options); } /** * Set the options of the renderer to those supplied in the passed in array. * Options are merged with the default to ensure that there aren't any missing * options. * * @param array $options Array of options to set. */ public function setOptions(array $options) { $this->options = array_merge($this->defaultOptions, $options); } }Renderer/Html/SideBySide.php000075500000013660000000000000011665 0ustar00 * * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: * * - Redistributions of source code must retain the above copyright notice, * this list of conditions and the following disclaimer. * - Redistributions in binary form must reproduce the above copyright notice, * this list of conditions and the following disclaimer in the documentation * and/or other materials provided with the distribution. * - Neither the name of the Chris Boulton nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE * POSSIBILITY OF SUCH DAMAGE. * * @package DiffLib * @author Chris Boulton * @copyright (c) 2009 Chris Boulton * @license New BSD License http://www.opensource.org/licenses/bsd-license.php * @version 1.1 * @link http://github.com/chrisboulton/php-diff */ require_once(dirname(__FILE__) . '/Array.php'); class Diff_Renderer_Html_SideBySide extends Diff_Renderer_Html_Array { /** * Render a and return diff with changes between the two sequences * displayed side by side. * * @return string The generated side by side diff. */ public function render() { $changes = parent::render(); $html = ''; if(empty($changes)) { return $html; } $html .= ''; $html .= ''; $html .= ''; $html .= ''; $html .= ''; $html .= ''; $html .= ''; foreach($changes as $i => $blocks) { if($i > 0) { $html .= ''; $html .= ''; $html .= ''; $html .= ''; } foreach($blocks as $change) { $html .= ''; // Equal changes should be shown on both sides of the diff if($change['tag'] == 'equal') { foreach($change['base']['lines'] as $no => $line) { $fromLine = $change['base']['offset'] + $no + 1; $toLine = $change['changed']['offset'] + $no + 1; $html .= ''; $html .= ''; $html .= ''; $html .= ''; $html .= ''; $html .= ''; } } // Added lines only on the right side else if($change['tag'] == 'insert') { foreach($change['changed']['lines'] as $no => $line) { $toLine = $change['changed']['offset'] + $no + 1; $html .= ''; $html .= ''; $html .= ''; $html .= ''; $html .= ''; $html .= ''; } } // Show deleted lines only on the left side else if($change['tag'] == 'delete') { foreach($change['base']['lines'] as $no => $line) { $fromLine = $change['base']['offset'] + $no + 1; $html .= ''; $html .= ''; $html .= ''; $html .= ''; $html .= ''; $html .= ''; } } // Show modified lines on both sides else if($change['tag'] == 'replace') { if(count($change['base']['lines']) >= count($change['changed']['lines'])) { foreach($change['base']['lines'] as $no => $line) { $fromLine = $change['base']['offset'] + $no + 1; $html .= ''; $html .= ''; $html .= ''; if(!isset($change['changed']['lines'][$no])) { $toLine = ' '; $changedLine = ' '; } else { $toLine = $change['base']['offset'] + $no + 1; $changedLine = ''.$change['changed']['lines'][$no].''; } $html .= ''; $html .= ''; $html .= ''; } } else { foreach($change['changed']['lines'] as $no => $changedLine) { if(!isset($change['base']['lines'][$no])) { $fromLine = ' '; $line = ' '; } else { $fromLine = $change['base']['offset'] + $no + 1; $line = ''.$change['base']['lines'][$no].''; } $html .= ''; $html .= ''; $html .= ''; $toLine = $change['changed']['offset'] + $no + 1; $html .= ''; $html .= ''; $html .= ''; } } } $html .= ''; } } $html .= '
The Original Version of the fileThe Modified Version on your WordPress system
… … 
'.$fromLine.''.$line.' '.$toLine.''.$line.' 
  '.$toLine.''.$line.' 
'.$fromLine.''.$line.'   
'.$fromLine.''.$line.' '.$toLine.''.$changedLine.'
'.$fromLine.''.$line.' '.$toLine.''.$changedLine.'
'; return $html; } } Renderer/Html/Array.php000075500000017074000000000000010762 0ustar00 * * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: * * - Redistributions of source code must retain the above copyright notice, * this list of conditions and the following disclaimer. * - Redistributions in binary form must reproduce the above copyright notice, * this list of conditions and the following disclaimer in the documentation * and/or other materials provided with the distribution. * - Neither the name of the Chris Boulton nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE * POSSIBILITY OF SUCH DAMAGE. * * @package DiffLib * @author Chris Boulton * @copyright (c) 2009 Chris Boulton * @license New BSD License http://www.opensource.org/licenses/bsd-license.php * @version 1.1 * @link http://github.com/chrisboulton/php-diff */ require_once(dirname(__FILE__) . '/../Abstract.php'); class Diff_Renderer_Html_Array extends Diff_Renderer_Abstract { /** * @var array Array of the default options that apply to this renderer. */ protected $defaultOptions = array( 'tabSize' => 4 ); /** * Render and return an array structure suitable for generating HTML * based differences. Generally called by subclasses that generate a * HTML based diff and return an array of the changes to show in the diff. * * @return array An array of the generated chances, suitable for presentation in HTML. */ public function render() { // As we'll be modifying a & b to include our change markers, // we need to get the contents and store them here. That way // we're not going to destroy the original data $a = $this->diff->getA(); $b = $this->diff->getB(); $changes = array(); $opCodes = $this->diff->getGroupedOpcodes(); foreach($opCodes as $group) { $blocks = array(); $lastTag = null; $lastBlock = 0; foreach($group as $code) { list($tag, $i1, $i2, $j1, $j2) = $code; if($tag == 'replace' && $i2 - $i1 == $j2 - $j1) { for($i = 0; $i < ($i2 - $i1); ++$i) { $fromLine = $a[$i1 + $i]; $toLine = $b[$j1 + $i]; list($start, $end) = $this->getChangeExtent($fromLine, $toLine); if($start != 0 || $end != 0) { $last = $end + strlen($fromLine); $fromLine = substr_replace($fromLine, "\0", $start, 0); $fromLine = substr_replace($fromLine, "\1", $last + 1, 0); $last = $end + strlen($toLine); $toLine = substr_replace($toLine, "\0", $start, 0); $toLine = substr_replace($toLine, "\1", $last + 1, 0); $a[$i1 + $i] = $fromLine; $b[$j1 + $i] = $toLine; } } } if($tag != $lastTag) { $blocks[] = array( 'tag' => $tag, 'base' => array( 'offset' => $i1, 'lines' => array() ), 'changed' => array( 'offset' => $j1, 'lines' => array() ) ); $lastBlock = count($blocks)-1; } $lastTag = $tag; if($tag == 'equal') { $lines = array_slice($a, $i1, ($i2 - $i1)); $blocks[$lastBlock]['base']['lines'] += $this->formatLines($lines); $lines = array_slice($b, $j1, ($j2 - $j1)); $blocks[$lastBlock]['changed']['lines'] += $this->formatLines($lines); } else { if($tag == 'replace' || $tag == 'delete') { $lines = array_slice($a, $i1, ($i2 - $i1)); $lines = $this->formatLines($lines); $lines = str_replace(array("\0", "\1"), array('', ''), $lines); $blocks[$lastBlock]['base']['lines'] += $lines; } if($tag == 'replace' || $tag == 'insert') { $lines = array_slice($b, $j1, ($j2 - $j1)); $lines = $this->formatLines($lines); $lines = str_replace(array("\0", "\1"), array('', ''), $lines); $blocks[$lastBlock]['changed']['lines'] += $lines; } } } $changes[] = $blocks; } return $changes; } /** * Given two strings, determine where the changes in the two strings * begin, and where the changes in the two strings end. * * @param string $fromLine The first string. * @param string $toLine The second string. * @return array Array containing the starting position (0 by default) and the ending position (-1 by default) */ private function getChangeExtent($fromLine, $toLine) { $start = 0; $limit = min(strlen($fromLine), strlen($toLine)); while($start < $limit && $fromLine[$start] == $toLine[$start]) { ++$start; } $end = -1; $limit = $limit - $start; while(-$end <= $limit && substr($fromLine, $end, 1) == substr($toLine, $end, 1)) { --$end; } return array( $start, $end + 1 ); } /** * Format a series of lines suitable for output in a HTML rendered diff. * This involves replacing tab characters with spaces, making the HTML safe * for output, ensuring that double spaces are replaced with   etc. * * @param array $lines Array of lines to format. * @return array Array of the formatted lines. */ private function formatLines($lines) { $lines = array_map(array($this, 'ExpandTabs'), $lines); $lines = array_map(array($this, 'HtmlSafe'), $lines); foreach($lines as &$line) { $line = preg_replace_callback('# ( +)|^ #', array($this, 'fixSpacesCallback'), $line); } return $lines; } /** * Using a callback here instead of the /e modifier in preg_replace (now deprecated). * * @param $matches * @return string */ private function fixSpacesCallback($matches) { $spaces = (isset($matches[1]) ? $matches[1] : ''); return $this->fixSpaces($spaces); } /** * Replace a string containing spaces with a HTML representation using  . * * @param string $spaces The string of spaces. * @return string The HTML representation of the string. */ function fixSpaces($spaces='') { $count = strlen($spaces); if($count == 0) { return ''; } $div = floor($count / 2); $mod = $count % 2; return str_repeat('  ', $div).str_repeat(' ', $mod); } /** * Replace tabs in a single line with a number of spaces as defined by the tabSize option. * * @param string $line The containing tabs to convert. * @return string The line with the tabs converted to spaces. */ private function expandTabs($line) { return str_replace("\t", str_repeat(' ', $this->options['tabSize']), $line); } /** * Make a string containing HTML safe for output on a page. * * @param string $string The string. * @return string The string with the HTML characters replaced by entities. */ private function htmlSafe($string) { if (!is_string($string)) { return ''; } return htmlspecialchars($string, ENT_NOQUOTES, 'UTF-8'); } }