string.php000064400000020233147207051540006570 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 $edits; } } xdiff.php000064400000004233147207051540006364 0ustar00 * @package Text_Diff */ class Text_Diff_Engine_xdiff { /** */ function diff($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; } } shell.php000064400000012123147207051540006370 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; } } native.php000064400000037261147207051540006561 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]); } } } }