Diff/Renderer.php 0000644 00000015226 14720640537 0007711 0 ustar 00 $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);
}
}
Diff/Renderer/inline.php 0000644 00000012630 14720640537 0011163 0 ustar 00 ';
/**
* 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);
}
}
Diff/Engine/string.php 0000644 00000020233 14720640537 0010650 0 ustar 00
* $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 $edits;
}
}
Diff/Engine/xdiff.php 0000644 00000004233 14720640537 0010444 0 ustar 00
* @package Text_Diff
*/
class Text_Diff_Engine_xdiff {
/**
*/
function diff($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;
}
}
Diff/Engine/shell.php 0000644 00000012123 14720640537 0010450 0 ustar 00
* @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;
}
}
Diff/Engine/native.php 0000644 00000037261 14720640537 0010641 0 ustar 00 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]);
}
}
}
}
Exception.php 0000644 00000000361 14720640537 0007223 0 ustar 00 , and is used/adapted with his permission.
*
* Copyright 2004 Geoffrey T. Dairiki
* 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/.
*
* @package Text_Diff
* @author Geoffrey T. Dairiki
*/
class Text_Diff {
/**
* Array of changes.
*
* @var array
*/
var $_edits;
/**
* Computes diffs between sequences of strings.
*
* @param string $engine Name of the diffing engine to use. 'auto'
* will automatically select the best.
* @param array $params Parameters to pass to the diffing engine.
* Normally an array of two arrays, each
* containing the lines from a file.
*/
function __construct( $engine, $params )
{
// Backward compatibility workaround.
if (!is_string($engine)) {
$params = array($engine, $params);
$engine = 'auto';
}
if ($engine == 'auto') {
$engine = extension_loaded('xdiff') ? 'xdiff' : 'native';
} else {
$engine = basename($engine);
}
// WP #7391
require_once dirname(__FILE__).'/Diff/Engine/' . $engine . '.php';
$class = 'Text_Diff_Engine_' . $engine;
$diff_engine = new $class();
$this->_edits = call_user_func_array(array($diff_engine, 'diff'), $params);
}
/**
* PHP4 constructor.
*/
public function Text_Diff( $engine, $params ) {
self::__construct( $engine, $params );
}
/**
* Returns the array of differences.
*/
function getDiff()
{
return $this->_edits;
}
/**
* returns the number of new (added) lines in a given diff.
*
* @since Text_Diff 1.1.0
*
* @return int The number of new lines
*/
function countAddedLines()
{
$count = 0;
foreach ($this->_edits as $edit) {
if (is_a($edit, 'Text_Diff_Op_add') ||
is_a($edit, 'Text_Diff_Op_change')) {
$count += $edit->nfinal();
}
}
return $count;
}
/**
* Returns the number of deleted (removed) lines in a given diff.
*
* @since Text_Diff 1.1.0
*
* @return int The number of deleted lines
*/
function countDeletedLines()
{
$count = 0;
foreach ($this->_edits as $edit) {
if (is_a($edit, 'Text_Diff_Op_delete') ||
is_a($edit, 'Text_Diff_Op_change')) {
$count += $edit->norig();
}
}
return $count;
}
/**
* Computes a reversed diff.
*
* Example:
*
* $diff = new Text_Diff($lines1, $lines2);
* $rev = $diff->reverse();
*
*
* @return Text_Diff A Diff object representing the inverse of the
* original diff. Note that we purposely don't return a
* reference here, since this essentially is a clone()
* method.
*/
function reverse()
{
if (version_compare(zend_version(), '2', '>')) {
$rev = clone($this);
} else {
$rev = $this;
}
$rev->_edits = array();
foreach ($this->_edits as $edit) {
$rev->_edits[] = $edit->reverse();
}
return $rev;
}
/**
* Checks for an empty diff.
*
* @return bool True if two sequences were identical.
*/
function isEmpty()
{
foreach ($this->_edits as $edit) {
if (!is_a($edit, 'Text_Diff_Op_copy')) {
return false;
}
}
return true;
}
/**
* Computes the length of the Longest Common Subsequence (LCS).
*
* This is mostly for diagnostic purposes.
*
* @return int The length of the LCS.
*/
function lcs()
{
$lcs = 0;
foreach ($this->_edits as $edit) {
if (is_a($edit, 'Text_Diff_Op_copy')) {
$lcs += count($edit->orig);
}
}
return $lcs;
}
/**
* Gets the original set of lines.
*
* This reconstructs the $from_lines parameter passed to the constructor.
*
* @return array The original sequence of strings.
*/
function getOriginal()
{
$lines = array();
foreach ($this->_edits as $edit) {
if ($edit->orig) {
array_splice($lines, count($lines), 0, $edit->orig);
}
}
return $lines;
}
/**
* Gets the final set of lines.
*
* This reconstructs the $to_lines parameter passed to the constructor.
*
* @return array The sequence of strings.
*/
function getFinal()
{
$lines = array();
foreach ($this->_edits as $edit) {
if ($edit->final) {
array_splice($lines, count($lines), 0, $edit->final);
}
}
return $lines;
}
/**
* Removes trailing newlines from a line of text. This is meant to be used
* with array_walk().
*
* @param string $line The line to trim.
* @param int $key The index of the line in the array. Not used.
*/
static function trimNewlines(&$line, $key)
{
$line = str_replace(array("\n", "\r"), '', $line);
}
/**
* Determines the location of the system temporary directory.
*
* @access protected
*
* @return string A directory name which can be used for temp files.
* Returns false if one could not be found.
*/
static function _getTempDir()
{
$tmp_locations = array('/tmp', '/var/tmp', 'c:\WUTemp', 'c:\temp',
'c:\windows\temp', 'c:\winnt\temp');
/* Try PHP's upload_tmp_dir directive. */
$tmp = ini_get('upload_tmp_dir');
/* Otherwise, try to determine the TMPDIR environment variable. */
if (!strlen($tmp)) {
$tmp = getenv('TMPDIR');
}
/* If we still cannot determine a value, then cycle through a list of
* preset possibilities. */
while (!strlen($tmp) && count($tmp_locations)) {
$tmp_check = array_shift($tmp_locations);
if (@is_dir($tmp_check)) {
$tmp = $tmp_check;
}
}
/* If it is still empty, we have failed, so return false; otherwise
* return the directory determined. */
return strlen($tmp) ? $tmp : false;
}
/**
* Checks a diff for validity.
*
* This is here only for debugging purposes.
*/
function _check($from_lines, $to_lines)
{
if (serialize($from_lines) != serialize($this->getOriginal())) {
throw new Text_Exception("Reconstructed original does not match");
}
if (serialize($to_lines) != serialize($this->getFinal())) {
throw new Text_Exception("Reconstructed final does not match");
}
$rev = $this->reverse();
if (serialize($to_lines) != serialize($rev->getOriginal())) {
throw new Text_Exception("Reversed original does not match");
}
if (serialize($from_lines) != serialize($rev->getFinal())) {
throw new Text_Exception("Reversed final does not match");
}
$prevtype = null;
foreach ($this->_edits as $edit) {
if ($prevtype !== null && $edit instanceof $prevtype) {
throw new Text_Exception("Edit sequence is non-optimal");
}
$prevtype = get_class($edit);
}
return true;
}
}
/**
* @package Text_Diff
* @author Geoffrey T. Dairiki
*/
class Text_MappedDiff extends Text_Diff {
/**
* Computes a diff between sequences of strings.
*
* This can be used to compute things like case-insensitive diffs, or diffs
* which ignore changes in white-space.
*
* @param array $from_lines An array of strings.
* @param array $to_lines An array of strings.
* @param array $mapped_from_lines This array should have the same size
* number of elements as $from_lines. The
* elements in $mapped_from_lines and
* $mapped_to_lines are what is actually
* compared when computing the diff.
* @param array $mapped_to_lines This array should have the same number
* of elements as $to_lines.
*/
function __construct($from_lines, $to_lines,
$mapped_from_lines, $mapped_to_lines)
{
assert(count($from_lines) == count($mapped_from_lines));
assert(count($to_lines) == count($mapped_to_lines));
parent::Text_Diff($mapped_from_lines, $mapped_to_lines);
$xi = $yi = 0;
for ($i = 0; $i < count($this->_edits); $i++) {
$orig = &$this->_edits[$i]->orig;
if (is_array($orig)) {
$orig = array_slice($from_lines, $xi, count($orig));
$xi += count($orig);
}
$final = &$this->_edits[$i]->final;
if (is_array($final)) {
$final = array_slice($to_lines, $yi, count($final));
$yi += count($final);
}
}
}
/**
* PHP4 constructor.
*/
public function Text_MappedDiff( $from_lines, $to_lines,
$mapped_from_lines, $mapped_to_lines ) {
self::__construct( $from_lines, $to_lines,
$mapped_from_lines, $mapped_to_lines );
}
}
/**
* @package Text_Diff
* @author Geoffrey T. Dairiki
*
* @access private
*/
abstract class Text_Diff_Op {
var $orig;
var $final;
abstract function &reverse();
function norig()
{
return $this->orig ? count($this->orig) : 0;
}
function nfinal()
{
return $this->final ? count($this->final) : 0;
}
}
/**
* @package Text_Diff
* @author Geoffrey T. Dairiki
*
* @access private
*/
class Text_Diff_Op_copy extends Text_Diff_Op {
/**
* PHP5 constructor.
*/
function __construct( $orig, $final = false )
{
if (!is_array($final)) {
$final = $orig;
}
$this->orig = $orig;
$this->final = $final;
}
/**
* PHP4 constructor.
*/
public function Text_Diff_Op_copy( $orig, $final = false ) {
self::__construct( $orig, $final );
}
function &reverse()
{
$reverse = new Text_Diff_Op_copy($this->final, $this->orig);
return $reverse;
}
}
/**
* @package Text_Diff
* @author Geoffrey T. Dairiki
*
* @access private
*/
class Text_Diff_Op_delete extends Text_Diff_Op {
/**
* PHP5 constructor.
*/
function __construct( $lines )
{
$this->orig = $lines;
$this->final = false;
}
/**
* PHP4 constructor.
*/
public function Text_Diff_Op_delete( $lines ) {
self::__construct( $lines );
}
function &reverse()
{
$reverse = new Text_Diff_Op_add($this->orig);
return $reverse;
}
}
/**
* @package Text_Diff
* @author Geoffrey T. Dairiki
*
* @access private
*/
class Text_Diff_Op_add extends Text_Diff_Op {
/**
* PHP5 constructor.
*/
function __construct( $lines )
{
$this->final = $lines;
$this->orig = false;
}
/**
* PHP4 constructor.
*/
public function Text_Diff_Op_add( $lines ) {
self::__construct( $lines );
}
function &reverse()
{
$reverse = new Text_Diff_Op_delete($this->final);
return $reverse;
}
}
/**
* @package Text_Diff
* @author Geoffrey T. Dairiki
*
* @access private
*/
class Text_Diff_Op_change extends Text_Diff_Op {
/**
* PHP5 constructor.
*/
function __construct( $orig, $final )
{
$this->orig = $orig;
$this->final = $final;
}
/**
* PHP4 constructor.
*/
public function Text_Diff_Op_change( $orig, $final ) {
self::__construct( $orig, $final );
}
function &reverse()
{
$reverse = new Text_Diff_Op_change($this->final, $this->orig);
return $reverse;
}
}