diff --git a/phpBB/includes/diff/diff.php b/phpBB/includes/diff/diff.php new file mode 100644 index 0000000000..102f1119b2 --- /dev/null +++ b/phpBB/includes/diff/diff.php @@ -0,0 +1,779 @@ + +*/ +class diff +{ + /** + * Array of changes. + * @var array + */ + var $_edits; + + /** + * Computes diffs between sequences of strings. + * + * @param array $from_lines An array of strings. Typically these are lines from a file. + * @param array $to_lines An array of strings. + */ + function diff($from_lines, $to_lines) + { + $diff_engine = &new diff_engine(); + $this->_edits = call_user_func_array(array($diff_engine, 'diff'), array($from_lines, $to_lines)); + } + + /** + * Returns the array of differences. + */ + function get_diff() + { + return $this->_edits; + } + + /** + * Computes a reversed diff. + * + * Example: + * + * $diff = &new diff($lines1, $lines2); + * $rev = $diff->reverse(); + * + * + * @return 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 $rev; + } + + /** + * Checks for an empty diff. + * + * @return boolean True if two sequences were identical. + */ + function is_empty() + { + foreach ($this->_edits as $edit) + { + if (!is_a($edit, 'diff_op_copy')) + { + return false; + } + } + return true; + } + + /** + * Computes the length of the Longest Common Subsequence (LCS). + * + * This is mostly for diagnostic purposes. + * + * @return integer The length of the LCS. + */ + function lcs() + { + $lcs = 0; + + foreach ($this->_edits as $edit) + { + if (is_a($edit, 'diff_op_copy')) + { + $lcs += sizeof($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 get_original() + { + $lines = array(); + + foreach ($this->_edits as $edit) + { + if ($edit->orig) + { + array_splice($lines, sizeof($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 get_final() + { + $lines = array(); + + foreach ($this->_edits as $edit) + { + if ($edit->final) + { + array_splice($lines, sizeof($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 integer $key The index of the line in the array. Not used. + */ + function trim_newlines(&$line, $key) + { + $line = str_replace(array("\n", "\r"), '', $line); + } + + /** + * Checks a diff for validity. + * + * This is here only for debugging purposes. + */ + function _check($from_lines, $to_lines) + { + if (serialize($from_lines) != serialize($this->get_original())) + { + trigger_error("[diff] Reconstructed original doesn't match", E_USER_ERROR); + } + + if (serialize($to_lines) != serialize($this->get_final())) + { + trigger_error("[diff] Reconstructed final doesn't match", E_USER_ERROR); + } + + $rev = $this->reverse(); + + if (serialize($to_lines) != serialize($rev->get_original())) + { + trigger_error("[diff] Reversed original doesn't match", E_USER_ERROR); + } + + if (serialize($from_lines) != serialize($rev->get_final())) + { + trigger_error("[diff] Reversed final doesn't match", E_USER_ERROR); + } + + $prevtype = null; + + foreach ($this->_edits as $edit) + { + if ($prevtype == get_class($edit)) + { + trigger_error("[diff] Edit sequence is non-optimal", E_USER_ERROR); + } + $prevtype = get_class($edit); + } + + return true; + } +} + +/** +* @package phpBB3 +* @author Geoffrey T. Dairiki +*/ +class mapped_diff extends diff +{ + /** + * Computes a diff between sequences of strings. + * + * This can be used to compute things like case-insensitve 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 $to_lines. + */ + function mapped_diff($from_lines, $to_lines, $mapped_from_lines, $mapped_to_lines) + { + if (sizeof($from_lines) != sizeof($mapped_from_lines) || sizeof($to_lines) != sizeof($mapped_to_lines)) + { + return false; + } + + parent::diff($mapped_from_lines, $mapped_to_lines); + + $xi = $yi = 0; + for ($i = 0; $i < sizeof($this->_edits); $i++) + { + $orig = &$this->_edits[$i]->orig; + if (is_array($orig)) + { + $orig = array_slice($from_lines, $xi, sizeof($orig)); + $xi += sizeof($orig); + } + + $final = &$this->_edits[$i]->final; + if (is_array($final)) + { + $final = array_slice($to_lines, $yi, sizeof($final)); + $yi += sizeof($final); + } + } + } +} + +/** +* @package phpBB3 +* @author Geoffrey T. Dairiki +* +* @access private +*/ +class diff_op +{ + var $orig; + var $final; + + function reverse() + { + trigger_error('[diff] Abstract method', E_USER_ERROR); + } + + function norig() + { + return ($this->orig) ? sizeof($this->orig) : 0; + } + + function nfinal() + { + return ($this->final) ? sizeof($this->final) : 0; + } +} + +/** +* @package phpBB3 +* @author Geoffrey T. Dairiki +* +* @access private +*/ +class diff_op_copy extends diff_op +{ + function diff_op_copy($orig, $final = false) + { + if (!is_array($final)) + { + $final = $orig; + } + $this->orig = $orig; + $this->final = $final; + } + + function &reverse() + { + $reverse = &new diff_op_copy($this->final, $this->orig); + return $reverse; + } +} + +/** +* @package phpBB3 +* @author Geoffrey T. Dairiki +* +* @access private +*/ +class diff_op_delete extends diff_op +{ + function diff_op_delete($lines) + { + $this->orig = $lines; + $this->final = false; + } + + function &reverse() + { + $reverse = &new diff_op_add($this->orig); + return $reverse; + } +} + +/** +* @package phpBB3 +* @author Geoffrey T. Dairiki +* +* @access private +*/ +class diff_op_add extends diff_op +{ + function diff_op_add($lines) + { + $this->final = $lines; + $this->orig = false; + } + + function &reverse() + { + $reverse = &new diff_op_delete($this->final); + return $reverse; + } +} + +/** +* @package phpBB3 +* @author Geoffrey T. Dairiki +* +* @access private +*/ +class diff_op_change extends diff_op +{ + function diff_op_change($orig, $final) + { + $this->orig = $orig; + $this->final = $final; + } + + function &reverse() + { + $reverse = &new diff_op_change($this->final, $this->orig); + return $reverse; + } +} + + +/** +* A class for computing three way diffs. +* +* @package phpBB3 +* @author Geoffrey T. Dairiki +*/ +class diff3 extends diff +{ + /** + * Conflict counter. + * @var integer + */ + var $_conflicting_blocks = 0; + + /** + * Computes diff between 3 sequences of strings. + * + * @param array $orig The original lines to use. + * @param array $final1 The first version to compare to. + * @param array $final2 The second version to compare to. + */ + function diff3($orig, $final1, $final2) + { + $engine = new diff_engine(); + $this->_edits = $this->_diff3($engine->diff($orig, $final1), $engine->diff($orig, $final2)); + } + + /** + * Return merged output + * + * @param string $label1 the cvs file version/label from the original set of lines + * @param string $label2 the cvs file version/label from the new set of lines + * @param bool $get_conflicts if set to true only the number of conflicts is returned + * @param bool $merge_new if set to true the merged output will have the new file contents on a conflicting merge + * + * @return mixed the merged output + */ + function merged_output($label1 = 'CURRENT_FILE', $label2 = 'NEW_FILE', $get_conflicts = false, $merge_new = false) + { + global $user; + + if ($get_conflicts) + { + foreach ($this->_edits as $edit) + { + if ($edit->is_conflict()) + { + $this->_conflicting_blocks++; + } + } + + return $this->_conflicting_blocks; + } + + $label1 = (!empty($user->lang[$label1])) ? $user->lang[$label1] : $label1; + $label2 = (!empty($user->lang[$label2])) ? $user->lang[$label2] : $label2; + + $lines = array(); + + foreach ($this->_edits as $edit) + { + if ($edit->is_conflict()) + { + if (!$merge_new) + { + $lines = array_merge($lines, array('<<<<<<<' . ($label1 ? ' ' . $label1 : '')), $edit->final1, array('======='), $edit->final2, array('>>>>>>>' . ($label2 ? ' ' . $label2 : ''))); + } + else + { + $lines = array_merge($lines, $edit->final1); + } + $this->_conflicting_blocks++; + } + else + { + $lines = array_merge($lines, $edit->merged()); + } + } + + return $lines; + } + + /** + * Merge the output and use the new file code for conflicts + */ + function merged_new_output() + { + $lines = array(); + + foreach ($this->_edits as $edit) + { + if ($edit->is_conflict()) + { + $lines = array_merge($lines, $edit->final2); + } + else + { + $lines = array_merge($lines, $edit->merged()); + } + } + + return $lines; + } + + /** + * Merge the output and use the original file code for conflicts + */ + function merged_orig_output() + { + $lines = array(); + + foreach ($this->_edits as $edit) + { + if ($edit->is_conflict()) + { + $lines = array_merge($lines, $edit->final1); + } + else + { + $lines = array_merge($lines, $edit->merged()); + } + } + + return $lines; + } + + /** + * Get conflicting block(s) + */ + function get_conflicts() + { + $conflicts = array(); + + foreach ($this->_edits as $edit) + { + if ($edit->is_conflict()) + { + $conflicts[] = array($edit->final1, $edit->final2); + } + } + + return $conflicts; + } + + /** + * @access private + */ + function _diff3($edits1, $edits2) + { + $edits = array(); + $bb = &new diff3_block_builder(); + + $e1 = current($edits1); + $e2 = current($edits2); + + while ($e1 || $e2) + { + if ($e1 && $e2 && is_a($e1, 'diff_op_copy') && is_a($e2, 'diff_op_copy')) + { + // We have copy blocks from both diffs. This is the (only) time we want to emit a diff3 copy block. + // Flush current diff3 diff block, if any. + if ($edit = $bb->finish()) + { + $edits[] = $edit; + } + + $ncopy = min($e1->norig(), $e2->norig()); + $edits[] = &new diff3_op_copy(array_slice($e1->orig, 0, $ncopy)); + + if ($e1->norig() > $ncopy) + { + array_splice($e1->orig, 0, $ncopy); + array_splice($e1->final, 0, $ncopy); + } + else + { + $e1 = next($edits1); + } + + if ($e2->norig() > $ncopy) + { + array_splice($e2->orig, 0, $ncopy); + array_splice($e2->final, 0, $ncopy); + } + else + { + $e2 = next($edits2); + } + } + else + { + if ($e1 && $e2) + { + if ($e1->orig && $e2->orig) + { + $norig = min($e1->norig(), $e2->norig()); + $orig = array_splice($e1->orig, 0, $norig); + array_splice($e2->orig, 0, $norig); + $bb->input($orig); + } + else + { + $norig = 0; + } + + if (is_a($e1, 'diff_op_copy')) + { + $bb->out1(array_splice($e1->final, 0, $norig)); + } + + if (is_a($e2, 'diff_op_copy')) + { + $bb->out2(array_splice($e2->final, 0, $norig)); + } + } + + if ($e1 && ! $e1->orig) + { + $bb->out1($e1->final); + $e1 = next($edits1); + } + + if ($e2 && ! $e2->orig) + { + $bb->out2($e2->final); + $e2 = next($edits2); + } + } + } + + if ($edit = $bb->finish()) + { + $edits[] = $edit; + } + + return $edits; + } +} + +/** +* @package phpBB3 +* @author Geoffrey T. Dairiki +* +* @access private +*/ +class diff3_op +{ + function diff3_op($orig = false, $final1 = false, $final2 = false) + { + $this->orig = $orig ? $orig : array(); + $this->final1 = $final1 ? $final1 : array(); + $this->final2 = $final2 ? $final2 : array(); + } + + function merged() + { + if (!isset($this->_merged)) + { + if ($this->final1 === $this->final2) + { + $this->_merged = &$this->final1; + } + else if ($this->final1 === $this->orig) + { + $this->_merged = &$this->final2; + } + else if ($this->final2 === $this->orig) + { + $this->_merged = &$this->final1; + } + else + { + $this->_merged = false; + } + } + + return $this->_merged; + } + + function is_conflict() + { + return ($this->merged() === false) ? true : false; + } +} + +/** +* @package phpBB3 +* @author Geoffrey T. Dairiki +* +* @access private +*/ +class diff3_op_copy extends diff3_op +{ + function diff3_op_copy($lines = false) + { + $this->orig = $lines ? $lines : array(); + $this->final1 = &$this->orig; + $this->final2 = &$this->orig; + } + + function merged() + { + return $this->orig; + } + + function is_conflict() + { + return false; + } +} + +/** +* @package phpBB3 +* @author Geoffrey T. Dairiki +* +* @access private +*/ +class diff3_block_builder +{ + function diff3_block_builder() + { + $this->_init(); + } + + function input($lines) + { + if ($lines) + { + $this->_append($this->orig, $lines); + } + } + + function out1($lines) + { + if ($lines) + { + $this->_append($this->final1, $lines); + } + } + + function out2($lines) + { + if ($lines) + { + $this->_append($this->final2, $lines); + } + } + + function is_empty() + { + return !$this->orig && !$this->final1 && !$this->final2; + } + + function finish() + { + if ($this->is_empty()) + { + return false; + } + else + { + $edit = &new diff3_op($this->orig, $this->final1, $this->final2); + $this->_init(); + return $edit; + } + } + + function _init() + { + $this->orig = $this->final1 = $this->final2 = array(); + } + + function _append(&$array, $lines) + { + array_splice($array, sizeof($array), 0, $lines); + } +} + +?> \ No newline at end of file diff --git a/phpBB/includes/diff/engine.php b/phpBB/includes/diff/engine.php new file mode 100644 index 0000000000..c230d865cd --- /dev/null +++ b/phpBB/includes/diff/engine.php @@ -0,0 +1,512 @@ + 2, and some optimizations) are from +* Geoffrey T. Dairiki . The original PHP version of this +* code was written by him, and is used/adapted with his permission. +* +* @author Geoffrey T. Dairiki +* @package phpBB3 +* +* @access private +*/ +class diff_engine +{ + function diff($from_lines, $to_lines) + { + array_walk($from_lines, array('diff', 'trim_newlines')); + array_walk($to_lines, array('diff', 'trim_newlines')); + + $n_from = sizeof($from_lines); + $n_to = sizeof($to_lines); + + $this->xchanged = $this->ychanged = $this->xv = $this->yv = $this->xind = $this->yind = array(); + unset($this->seq, $this->in_seq, $this->lcs); + + // Skip leading common lines. + for ($skip = 0; $skip < $n_from && $skip < $n_to; $skip++) + { + if ($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. + $this->_compareseq(0, sizeof($this->xv), 0, sizeof($this->yv)); + + // Merge edits when possible. + $this->_shift_boundaries($from_lines, $this->xchanged, $this->ychanged); + $this->_shift_boundaries($to_lines, $this->ychanged, $this->xchanged); + + // Compute the edit operations. + $edits = array(); + $xi = $yi = 0; + + while ($xi < $n_from || $yi < $n_to) + { + // Skip matching "snake". + $copy = array(); + + while ($xi < $n_from && $yi < $n_to && !$this->xchanged[$xi] && !$this->ychanged[$yi]) + { + $copy[] = $from_lines[$xi++]; + $yi++; + } + + if ($copy) + { + $edits[] = &new diff_op_copy($copy); + } + + // Find deletes & adds. + $delete = array(); + while ($xi < $n_from && $this->xchanged[$xi]) + { + $delete[] = $from_lines[$xi++]; + } + + $add = array(); + while ($yi < $n_to && $this->ychanged[$yi]) + { + $add[] = $to_lines[$yi++]; + } + + if ($delete && $add) + { + $edits[] = &new diff_op_change($delete, $add); + } + else if ($delete) + { + $edits[] = &new diff_op_delete($delete); + } + else if ($add) + { + $edits[] = &new diff_op_add($add); + } + } + + return $edits; + } + + /** + * Divides the Largest Common Subsequence (LCS) of the sequences (XOFF, + * XLIM) and (YOFF, YLIM) into NCHUNKS approximately equally sized segments. + * + * Returns (LCS, PTS). LCS is the length of the LCS. PTS is an array of + * NCHUNKS+1 (X, Y) indexes giving the diving points between sub + * sequences. The first sub-sequence is contained in (X0, X1), (Y0, Y1), + * the second in (X1, X2), (Y1, Y2) and so on. Note that (X0, Y0) == + * (XOFF, YOFF) and (X[NCHUNKS], Y[NCHUNKS]) == (XLIM, YLIM). + * + * This function assumes that the first lines of the specified portions of + * the two files do not match, and likewise that the last lines do not + * match. The caller must trim matching lines from the beginning and end + * of the portions it is going to specify. + */ + function _diag($xoff, $xlim, $yoff, $ylim, $nchunks) + { + $flip = false; + + if ($xlim - $xoff > $ylim - $yoff) + { + // Things seems faster (I'm not sure I understand why) when the shortest sequence is in X. + $flip = true; + list($xoff, $xlim, $yoff, $ylim) = array($yoff, $ylim, $xoff, $xlim); + } + + if ($flip) + { + for ($i = $ylim - 1; $i >= $yoff; $i--) + { + $ymatches[$this->xv[$i]][] = $i; + } + } + else + { + for ($i = $ylim - 1; $i >= $yoff; $i--) + { + $ymatches[$this->yv[$i]][] = $i; + } + } + + $this->lcs = 0; + $this->seq[0]= $yoff - 1; + $this->in_seq = array(); + $ymids[0] = array(); + + $numer = $xlim - $xoff + $nchunks - 1; + $x = $xoff; + + for ($chunk = 0; $chunk < $nchunks; $chunk++) + { + if ($chunk > 0) + { + for ($i = 0; $i <= $this->lcs; $i++) + { + $ymids[$i][$chunk - 1] = $this->seq[$i]; + } + } + + $x1 = $xoff + (int)(($numer + ($xlim-$xoff)*$chunk) / $nchunks); + + for (; $x < $x1; $x++) + { + $line = $flip ? $this->yv[$x] : $this->xv[$x]; + if (empty($ymatches[$line])) + { + continue; + } + $matches = $ymatches[$line]; + + foreach ($matches as $y) + { + if (empty($this->in_seq[$y])) + { + $k = $this->_lcs_pos($y); + $ymids[$k] = $ymids[$k - 1]; + break; + } + } + + while (list($junk, $y) = each($matches)) + { + if ($y > $this->seq[$k - 1]) + { + // Optimization: this is a common case: next match is just replacing previous match. + $this->in_seq[$this->seq[$k]] = false; + $this->seq[$k] = $y; + $this->in_seq[$y] = 1; + } + else if (empty($this->in_seq[$y])) + { + $k = $this->_lcs_pos($y); + $ymids[$k] = $ymids[$k - 1]; + } + } + } + } + + $seps[] = $flip ? array($yoff, $xoff) : array($xoff, $yoff); + $ymid = $ymids[$this->lcs]; + + for ($n = 0; $n < $nchunks - 1; $n++) + { + $x1 = $xoff + (int)(($numer + ($xlim - $xoff) * $n) / $nchunks); + $y1 = $ymid[$n] + 1; + $seps[] = $flip ? array($y1, $x1) : array($x1, $y1); + } + $seps[] = $flip ? array($ylim, $xlim) : array($xlim, $ylim); + + return array($this->lcs, $seps); + } + + function _lcs_pos($ypos) + { + $end = $this->lcs; + + if ($end == 0 || $ypos > $this->seq[$end]) + { + $this->seq[++$this->lcs] = $ypos; + $this->in_seq[$ypos] = 1; + return $this->lcs; + } + + $beg = 1; + while ($beg < $end) + { + $mid = (int)(($beg + $end) / 2); + if ($ypos > $this->seq[$mid]) + { + $beg = $mid + 1; + } + else + { + $end = $mid; + } + } + + $this->in_seq[$this->seq[$end]] = false; + $this->seq[$end] = $ypos; + $this->in_seq[$ypos] = 1; + + return $end; + } + + /** + * Finds LCS of two sequences. + * + * The results are recorded in the vectors $this->{x,y}changed[], by + * storing a 1 in the element for each line that is an insertion or + * deletion (ie. is not in the LCS). + * + * The subsequence of file 0 is (XOFF, XLIM) and likewise for file 1. + * + * Note that XLIM, YLIM are exclusive bounds. All line numbers are + * origin-0 and discarded lines are not counted. + */ + function _compareseq($xoff, $xlim, $yoff, $ylim) + { + // Slide down the bottom initial diagonal. + while ($xoff < $xlim && $yoff < $ylim && $this->xv[$xoff] == $this->yv[$yoff]) + { + ++$xoff; + ++$yoff; + } + + // Slide up the top initial diagonal. + while ($xlim > $xoff && $ylim > $yoff && $this->xv[$xlim - 1] == $this->yv[$ylim - 1]) + { + --$xlim; + --$ylim; + } + + if ($xoff == $xlim || $yoff == $ylim) + { + $lcs = 0; + } + else + { + // This is ad hoc but seems to work well. + // $nchunks = sqrt(min($xlim - $xoff, $ylim - $yoff) / 2.5); + // $nchunks = max(2,min(8,(int)$nchunks)); + $nchunks = min(7, $xlim - $xoff, $ylim - $yoff) + 1; + list($lcs, $seps) = $this->_diag($xoff, $xlim, $yoff, $ylim, $nchunks); + } + + if ($lcs == 0) + { + // X and Y sequences have no common subsequence: mark all changed. + while ($yoff < $ylim) + { + $this->ychanged[$this->yind[$yoff++]] = 1; + } + + while ($xoff < $xlim) + { + $this->xchanged[$this->xind[$xoff++]] = 1; + } + } + else + { + // Use the partitions to split this problem into subproblems. + reset($seps); + $pt1 = $seps[0]; + + while ($pt2 = next($seps)) + { + $this->_compareseq($pt1[0], $pt2[0], $pt1[1], $pt2[1]); + $pt1 = $pt2; + } + } + } + + /** + * Adjusts inserts/deletes of identical lines to join changes as much as possible. + * + * We do something when a run of changed lines include a line at one end + * and has an excluded, identical line at the other. We are free to + * choose which identical line is included. 'compareseq' usually chooses + * the one at the beginning, but usually it is cleaner to consider the + * following identical line to be the "change". + * + * This is extracted verbatim from analyze.c (GNU diffutils-2.7). + */ + function _shift_boundaries($lines, &$changed, $other_changed) + { + $i = 0; + $j = 0; + + $len = sizeof($lines); + $other_len = sizeof($other_changed); + + while (1) + { + // Scan forward to find the beginning of another run of + // changes. Also keep track of the corresponding point in the other file. + // + // Throughout this code, $i and $j are adjusted together so that + // the first $i elements of $changed and the first $j elements of + // $other_changed both contain the same number of zeros (unchanged lines). + // + // Furthermore, $j is always kept so that $j == $other_len or $other_changed[$j] == false. + while ($j < $other_len && $other_changed[$j]) + { + $j++; + } + + while ($i < $len && ! $changed[$i]) + { + $i++; + $j++; + + while ($j < $other_len && $other_changed[$j]) + { + $j++; + } + } + + if ($i == $len) + { + break; + } + + $start = $i; + + // Find the end of this run of changes. + while (++$i < $len && $changed[$i]) + { + continue; + } + + do + { + // Record the length of this run of changes, so that we can later determine whether the run has grown. + $runlength = $i - $start; + + // Move the changed region back, so long as the previous unchanged line matches the last changed one. + // This merges with previous changed regions. + while ($start > 0 && $lines[$start - 1] == $lines[$i - 1]) + { + $changed[--$start] = 1; + $changed[--$i] = false; + + while ($start > 0 && $changed[$start - 1]) + { + $start--; + } + + while ($other_changed[--$j]) + { + continue; + } + } + + // Set CORRESPONDING to the end of the changed run, at the last point where it corresponds to a changed run in the + // other file. CORRESPONDING == LEN means no such point has been found. + $corresponding = $j < $other_len ? $i : $len; + + // Move the changed region forward, so long as the first changed line matches the following unchanged one. + // This merges with following changed regions. + // Do this second, so that if there are no merges, the changed region is moved forward as far as possible. + while ($i < $len && $lines[$start] == $lines[$i]) + { + $changed[$start++] = false; + $changed[$i++] = 1; + + while ($i < $len && $changed[$i]) + { + $i++; + } + + $j++; + if ($j < $other_len && $other_changed[$j]) + { + $corresponding = $i; + while ($j < $other_len && $other_changed[$j]) + { + $j++; + } + } + } + } + while ($runlength != $i - $start); + + // If possible, move the fully-merged run of changes back to a corresponding run in the other file. + while ($corresponding < $i) + { + $changed[--$start] = 1; + $changed[--$i] = 0; + + while ($other_changed[--$j]) + { + continue; + } + } + } + } +} + +?> \ No newline at end of file diff --git a/phpBB/includes/diff/renderer.php b/phpBB/includes/diff/renderer.php new file mode 100644 index 0000000000..408addb858 --- /dev/null +++ b/phpBB/includes/diff/renderer.php @@ -0,0 +1,832 @@ + $value) + { + $v = '_' . $param; + if (isset($this->$v)) + { + $this->$v = $value; + } + } + } + + /** + * Get any renderer parameters. + * + * @return array All parameters of this renderer object. + */ + function get_params() + { + $params = array(); + foreach (get_object_vars($this) as $k => $v) + { + if ($k[0] == '_') + { + $params[substr($k, 1)] = $v; + } + } + + return $params; + } + + /** + * Renders a diff. + * + * @param diff $diff A diff object. + * + * @return string The formatted output. + */ + function render(&$diff) + { + $xi = $yi = 1; + $block = false; + $context = array(); + + // Create a new diff object if it is a 3-way diff + if (is_a($diff, 'diff3')) + { + $diff3 = &$diff; + $diff = &new diff($diff3->get_original(), $diff3->merged_output()); + unset($diff3); + } + + $nlead = $this->_leading_context_lines; + $ntrail = $this->_trailing_context_lines; + + $output = $this->_start_diff(); + $diffs = $diff->get_diff(); + + foreach ($diffs as $i => $edit) + { + if (is_a($edit, 'diff_op_copy')) + { + if (is_array($block)) + { + $keep = ($i == sizeof($diffs) - 1) ? $ntrail : $nlead + $ntrail; + if (sizeof($edit->orig) <= $keep) + { + $block[] = $edit; + } + else + { + if ($ntrail) + { + $context = array_slice($edit->orig, 0, $ntrail); + $block[] = &new diff_op_copy($context); + } + + $output .= $this->_block($x0, $ntrail + $xi - $x0, $y0, $ntrail + $yi - $y0, $block); + $block = false; + } + } + $context = $edit->orig; + } + else + { + if (!is_array($block)) + { + $context = array_slice($context, sizeof($context) - $nlead); + $x0 = $xi - sizeof($context); + $y0 = $yi - sizeof($context); + $block = array(); + + if ($context) + { + $block[] = &new diff_op_copy($context); + } + } + $block[] = $edit; + } + + $xi += ($edit->orig) ? sizeof($edit->orig) : 0; + $yi += ($edit->final) ? sizeof($edit->final) : 0; + } + + if (is_array($block)) + { + $output .= $this->_block($x0, $xi - $x0, $y0, $yi - $y0, $block); + } + + return $output . $this->_end_diff(); + } + + function _block($xbeg, $xlen, $ybeg, $ylen, &$edits) + { + $output = $this->_start_block($this->_block_header($xbeg, $xlen, $ybeg, $ylen)); + + foreach ($edits as $edit) + { + switch (get_class($edit)) + { + case 'diff_op_copy': + $output .= $this->_context($edit->orig); + break; + + case 'diff_op_add': + $output .= $this->_added($edit->final); + break; + + case 'diff_op_delete': + $output .= $this->_deleted($edit->orig); + break; + + case 'diff_op_change': + $output .= $this->_changed($edit->orig, $edit->final); + break; + } + } + + return $output . $this->_end_block(); + } + + function _start_diff() + { + return ''; + } + + function _end_diff() + { + return ''; + } + + function _block_header($xbeg, $xlen, $ybeg, $ylen) + { + if ($xlen > 1) + { + $xbeg .= ',' . ($xbeg + $xlen - 1); + } + + if ($ylen > 1) + { + $ybeg .= ',' . ($ybeg + $ylen - 1); + } + + return $xbeg . ($xlen ? ($ylen ? 'c' : 'd') : 'a') . $ybeg; + } + + function _start_block($header) + { + return $header . "\n"; + } + + function _end_block() + { + return ''; + } + + function _lines($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); + } + + /** + * Our function to get the diff + */ + function get_diff_content($diff) + { + return $this->render($diff); + } +} + +/** +* Renders a unified diff +* @package phpBB3 +*/ +class diff_renderer_unified extends diff_renderer +{ + var $_leading_context_lines = 4; + var $_trailing_context_lines = 4; + + /** + * Our function to get the diff + */ + function get_diff_content($diff) + { + return nl2br($this->render($diff)); + } + + function _block_header($xbeg, $xlen, $ybeg, $ylen) + { + if ($xlen != 1) + { + $xbeg .= ',' . $xlen; + } + + if ($ylen != 1) + { + $ybeg .= ',' . $ylen; + } + return '
@@ -' . $xbeg . ' +' . $ybeg . ' @@
'; + } + + function _context($lines) + { + return '
' . htmlspecialchars($this->_lines($lines, ' ')) . '
'; + } + + function _added($lines) + { + return '
' . htmlspecialchars($this->_lines($lines, '+')) . '
'; + } + + function _deleted($lines) + { + return '
' . htmlspecialchars($this->_lines($lines, '-')) . '
'; + } + + function _changed($orig, $final) + { + return $this->_deleted($orig) . $this->_added($final); + } + + function _start_diff() + { + $start = '
'; + + return $start; + } + + function _end_diff() + { + return '
'; + } + + function _end_block() + { + return ''; + } +} + +/** +* "Inline" diff renderer. +* +* This class renders diffs in the Wiki-style "inline" format. +* +* @author Ciprian Popovici +* @package phpBB3 +*/ +class diff_renderer_inline extends diff_renderer +{ + var $_leading_context_lines = 10000; + var $_trailing_context_lines = 10000; + + // Prefix and suffix for inserted text + var $_ins_prefix = ''; + var $_ins_suffix = ''; + + // Prefix and suffix for deleted text + var $_del_prefix = ''; + var $_del_suffix = ''; + + var $_block_head = ''; + + // What are we currently splitting on? Used to recurse to show word-level + var $_split_level = 'lines'; + + /** + * Our function to get the diff + */ + function get_diff_content($diff) + { + return '
' . nl2br($this->render($diff)) . '
'; + } + + function _start_diff() + { + return ''; + } + + function _end_diff() + { + return ''; + } + + function _block_header($xbeg, $xlen, $ybeg, $ylen) + { + return $this->_block_head; + } + + function _start_block($header) + { + return $header; + } + + function _lines($lines, $prefix = ' ', $encode = true) + { + if ($encode) + { + array_walk($lines, array(&$this, '_encode')); + } + + if ($this->_split_level == 'words') + { + return implode('', $lines); + } + else + { + return implode("\n", $lines) . "\n"; + } + } + + function _added($lines) + { + array_walk($lines, array(&$this, '_encode')); + $lines[0] = $this->_ins_prefix . $lines[0]; + $lines[sizeof($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]; + $lines[sizeof($lines) - 1] .= $this->_del_suffix; + return $this->_lines($lines, ' ', false); + } + + function _changed($orig, $final) + { + // If we've already split on words, don't try to do so again - just display. + if ($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"; + + // 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. + $diff = &new diff($this->_split_on_words($text1, $nl), $this->_split_on_words($text2, $nl)); + + // Get the diff in inline format. + $renderer = &new diff_renderer_inline(array_merge($this->get_params(), array('split_level' => 'words'))); + + // Run the diff and get the output. + return str_replace($nl, "\n", $renderer->render($diff)) . "\n"; + } + + function _split_on_words($string, $newline_escape = "\n") + { + // Ignore \0; otherwise the while loop will never finish. + $string = str_replace("\0", '', $string); + + $words = array(); + $length = strlen($string); + $pos = 0; + + $tab_there = true; + while ($pos < $length) + { + // Check for tabs... do not include them + if ($tab_there && substr($string, $pos, 1) === "\t") + { + $words[] = "\t"; + $pos++; + + continue; + } + else + { + $tab_there = false; + } + + // Eat a word with any preceding whitespace. + $spaces = strspn(substr($string, $pos), " \n"); + $nextpos = strcspn(substr($string, $pos + $spaces), " \n"); + $words[] = str_replace("\n", $newline_escape, substr($string, $pos, $spaces + $nextpos)); + $pos += $spaces + $nextpos; + } + + return $words; + } + + function _encode(&$string) + { + $string = htmlspecialchars($string); + } +} + +/** +* "raw" diff renderer. +* This class could be used to output a raw unified patch file +* +* @package phpBB3 +*/ +class diff_renderer_raw extends diff_renderer +{ + var $_leading_context_lines = 4; + var $_trailing_context_lines = 4; + + /** + * Our function to get the diff + */ + function get_diff_content($diff) + { + return ''; + } + + function _block_header($xbeg, $xlen, $ybeg, $ylen) + { + if ($xlen != 1) + { + $xbeg .= ',' . $xlen; + } + + if ($ylen != 1) + { + $ybeg .= ',' . $ylen; + } + return '@@ -' . $xbeg . ' +' . $ybeg . ' @@'; + } + + function _context($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) . $this->_added($final); + } +} + +/** +* "chora (Horde)" diff renderer - similar style. +* This renderer class is a modified human_readable function from the Horde Framework. +* +* @package phpBB3 +*/ +class diff_renderer_side_by_side extends diff_renderer +{ + var $_leading_context_lines = 3; + var $_trailing_context_lines = 3; + + var $lines = array(); + + // Hold the left and right columns of lines for change blocks. + var $cols; + var $state; + + var $data = false; + + /** + * Our function to get the diff + */ + function get_diff_content($diff) + { + global $user; + + $output = ''; + $output .= ' + + +'; + + $this->render($diff); + + // Is the diff empty? + if (!sizeof($this->lines)) + { + $output .= ''; + } + else + { + // Iterate through every header block of changes + foreach ($this->lines as $header) + { + $output .= ''; + + // Each header block consists of a number of changes (add, remove, change). + $current_context = ''; + + foreach ($header['contents'] as $change) + { + if (!empty($current_context) && $change['type'] != 'empty') + { + $line = $current_context; + $current_context = ''; + + $output .= ' + '; + } + + switch ($change['type']) + { + case 'add': + $line = ''; + + foreach ($change['lines'] as $_line) + { + $line .= htmlspecialchars($_line) . '
'; + } + + $output .= ''; + break; + + case 'remove': + $line = ''; + + foreach ($change['lines'] as $_line) + { + $line .= htmlspecialchars($_line) . '
'; + } + + $output .= ''; + break; + + case 'empty': + $current_context .= htmlspecialchars($change['line']) . '
'; + break; + + case 'change': + // Pop the old/new stacks one by one, until both are empty. + $oldsize = sizeof($change['old']); + $newsize = sizeof($change['new']); + $left = $right = ''; + + for ($row = 0, $row_max = max($oldsize, $newsize); $row < $row_max; ++$row) + { + $left .= isset($change['old'][$row]) ? htmlspecialchars($change['old'][$row]) : ''; + $left .= '
'; + $right .= isset($change['new'][$row]) ? htmlspecialchars($change['new'][$row]) : ''; + $right .= '
'; + } + + $output .= ''; + + if (!empty($left)) + { + $output .= ''; + } + else if ($row < $oldsize) + { + $output .= ''; + } + else + { + $output .= ''; + } + + if (!empty($right)) + { + $output .= ''; + } + else if ($row < $newsize) + { + $output .= ''; + } + else + { + $output .= ''; + } + + $output .= ''; + break; + } + } + + if (!empty($current_context)) + { + $line = $current_context; + $current_context = ''; + + $output .= ''; + $output .= ''; + } + } + } + + $output .= '
+   ' . $user->lang['LINE_UNMODIFIED'] . ' +   ' . $user->lang['LINE_ADDED'] . ' +   ' . $user->lang['LINE_MODIFIED'] . ' +   ' . $user->lang['LINE_REMOVED'] . ' +
' . $user->lang['NO_VISIBLE_CHANGES'] . '
Line ' . $header['oldline'] . '' . $user->lang['LINE'] . ' ' . $header['newline'] . '
' . ((strlen($line)) ? $line : ' ') . '
' . ((strlen($line)) ? $line : ' ') . '
 
' . ((strlen($line)) ? $line : ' ') . '
' . ((strlen($line)) ? $line : ' ') . '
 
' . $left . '
  
' . $right . '
  
' . ((strlen($line)) ? $line : ' ') . '
' . ((strlen($line)) ? $line : ' ') . '
'; + + return $output; + } + + function _start_diff() + { + $this->lines = array(); + + $this->data = false; + $this->cols = array(array(), array()); + $this->state = 'empty'; + + return ''; + } + + function _end_diff() + { + // Just flush any remaining entries in the columns stack. + switch ($this->state) + { + case 'add': + $this->data['contents'][] = array('type' => 'add', 'lines' => $this->cols[0]); + break; + + case 'remove': + // We have some removal lines pending in our stack, so flush them. + $this->data['contents'][] = array('type' => 'remove', 'lines' => $this->cols[0]); + break; + + case 'change': + // We have both remove and addition lines, so this is a change block. + $this->data['contents'][] = array('type' => 'change', 'old' => $this->cols[0], 'new' => $this->cols[1]); + break; + } + + if ($this->data !== false) + { + $this->lines[] = $this->data; + } + + return ''; + } + + function _block_header($xbeg, $xlen, $ybeg, $ylen) + { + // Push any previous header information to the return stack. + if ($this->data !== false) + { + $this->lines[] = $this->data; + } + + $this->data = array('type' => 'header', 'oldline' => $xbeg, 'newline' => $ybeg, 'contents' => array()); + $this->state = 'dump'; + } + + function _added($lines) + { + array_walk($lines, array(&$this, '_perform_add')); + } + + function _perform_add($line) + { + if ($this->state == 'empty') + { + return ''; + } + + // This is just an addition line. + if ($this->state == 'dump' || $this->state == 'add') + { + // Start adding to the addition stack. + $this->cols[0][] = $line; + $this->state = 'add'; + } + else + { + // This is inside a change block, so start accumulating lines. + $this->state = 'change'; + $this->cols[1][] = $line; + } + } + + function _deleted($lines) + { + array_walk($lines, array(&$this, '_perform_delete')); + } + + function _perform_delete($line) + { + // This is a removal line. + $this->state = 'remove'; + $this->cols[0][] = $line; + } + + function _context($lines) + { + array_walk($lines, array(&$this, '_perform_context')); + } + + function _perform_context($line) + { + // An empty block with no action. + switch ($this->state) + { + case 'add': + $this->data['contents'][] = array('type' => 'add', 'lines' => $this->cols[0]); + break; + + case 'remove': + // We have some removal lines pending in our stack, so flush them. + $this->data['contents'][] = array('type' => 'remove', 'lines' => $this->cols[0]); + break; + + case 'change': + // We have both remove and addition lines, so this is a change block. + $this->data['contents'][] = array('type' => 'change', 'old' => $this->cols[0], 'new' => $this->cols[1]); + break; + } + + $this->cols = array(array(), array()); + $this->data['contents'][] = array('type' => 'empty', 'line' => $line); + $this->state = 'dump'; + } + + function _changed($orig, $final) + { + return $this->_deleted($orig) . $this->_added($final); + } + +} + +?> \ No newline at end of file