DeToc.php

   1 <?php
   2 /*
   3  * Copyright (c) 2015      Marcin Cieślak (saper.info)
   4  *
   5  * DeToc is free software: you can redistribute it and/or modify
   6  * it under the terms of the GNU General Public License as published by
   7  * the Free Software Foundation, either version 3 of the License, or
   8  * (at your option) any later version.
   9  *
  10  * DeToc is distributed in the hope that it will be useful,
  11  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  12  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  13  * GNU General Public License for more details.
  14  *
  15  * You should have received a copy of the GNU General Public License
  16  * along with DeToc.  If not, see <http://www.gnu.org/licenses/>.
  17  */
  18
  19 /**
  20  * DeToc extension
  21  *
  22  * @file
  23  * @ingroup Extensions
  24  * @license http://www.gnu.org/copyleft/gpl.html GNU General Public License 3.0 or later
  25  */
  26
  27 class DeToc {
  28         public static function RemoveToc($body, &$extracted_toc) {
  29                 $extracted_toc = '';
  30                 $last_toc_ptr = 0;
  31                 $new_body = '';
  32                 while ( preg_match( '/<div id="toc".*?>(.*)/s',
  33                                 $body, $toc_matches,
  34                                 PREG_OFFSET_CAPTURE, $last_toc_ptr ) === 1 ) {
  35
  36                         $toc_offset = $toc_matches[0][1];
  37
  38                         $rest = $toc_matches[1][0];
  39                         $rest_ptr = $toc_matches[1][1];
  40
  41                         $divlevel = 1;
  42                         $endtoc_ptr = $rest_ptr;
  43                         while ( $divlevel > 0 && strlen($rest) > 0) {
  44                                 if ( preg_match(',<(/?)div.*?>(.*),s',
  45                                          $rest, $div_matches,
  46                                          PREG_OFFSET_CAPTURE ) === 1 ) {
  47
  48                                         $rest = $div_matches[2][0];
  49
  50                                         if ( $div_matches[1][0] === '/' ) {
  51                                                 $divlevel = $divlevel - 1;
  52                                                 if ( $divlevel > 0 ) {
  53                                                         $endtoc_ptr += $div_matches[2][1];
  54                                                 } else {
  55                                                     /* We skip the first <div>, so we need to skip the closing one */
  56                                                         $endtoc_ptr += $div_matches[0][1];
  57                                                 }
  58                                         } else {
  59                                                 $divlevel = $divlevel + 1;
  60                                                 $endtoc_ptr += $div_matches[2][1];
  61                                         }
  62                                 } else {
  63                                         $rest = '';
  64                                 }
  65                         }
  66                         $extracted_toc .= substr( $body,
  67                                 $last_toc_ptr + $rest_ptr, $endtoc_ptr - $rest_ptr );
  68
  69                         $new_body .= substr( $body, $last_toc_ptr, $toc_offset );
  70                         $last_toc_ptr += $endtoc_ptr;
  71                 }
  72                 $new_body .= substr( $body, $last_toc_ptr );
  73                 return $new_body;
  74         }
  75 }