[Summary view] [Print] [Text view]

   1  <?php
   2  
   3  /**
   4   * HTML parser implementation. It only implements links.
   5   *
   6   * @author Josep Arús
   7   *
   8   * @license http://www.gnu.org/copyleft/gpl.html GNU Public License
   9   * @package mod_wiki
  10   */
  11  include_once ("nwiki.php");
  12  
  13  class html_parser extends nwiki_parser {
  14      protected $blockrules = array();
  15  
  16      protected $section_editing = true;
  17  
  18      public function __construct() {
  19          parent::__construct();
  20          // The order is important, headers should be parsed before links.
  21          $this->tagrules = array(
  22              // Headers are considered tags here.
  23              'header' => array(
  24                  'expression' => "/<\s*h([1-$this->maxheaderdepth])\s*>(.+?)<\/h[1-$this->maxheaderdepth]>/is"
  25              ),
  26              'link' => $this->tagrules['link'],
  27              'url' => $this->tagrules['url']
  28          );
  29      }
  30  
  31      protected function before_parsing() {
  32          parent::before_parsing();
  33  
  34          $this->rules($this->string);
  35      }
  36  
  37      /**
  38       * Header tag rule
  39       * @param array $match Header regex match
  40       * @return string
  41       */
  42      protected function header_tag_rule($match) {
  43          return $this->generate_header($match[2], $match[1]);
  44      }
  45  
  46      /**
  47       * Section editing: Special for HTML Parser (It parses <h1></h1>)
  48       */
  49  
  50      public function get_section($header, $text, $clean = false) {
  51          if ($clean) {
  52              $text = preg_replace('/\r\n/', "\n", $text);
  53              $text = preg_replace('/\r/', "\n", $text);
  54              $text .= "\n\n";
  55          }
  56  
  57          $h1 = array("<\s*h1\s*>", "<\/h1>");
  58  
  59          $regex = "/(.*?)({$h1[0]}\s*".preg_quote($header, '/')."\s*{$h1[1]}.*?)((?:\n{$h1[0]}.*)|$)/is";
  60          preg_match($regex, $text, $match);
  61  
  62          if (!empty($match)) {
  63              return array($match[1], $match[2], $match[3]);
  64          } else {
  65              return false;
  66          }
  67      }
  68  
  69      protected function get_repeated_sections(&$text, $repeated = array()) {
  70          $this->repeated_sections = $repeated;
  71          return preg_replace_callback($this->tagrules['header'], array($this, 'get_repeated_sections_callback'), $text);
  72      }
  73  
  74      protected function get_repeated_sections_callback($match) {
  75          $text = trim($match[2]);
  76  
  77          if (in_array($text, $this->repeated_sections)) {
  78              $this->returnvalues['repeated_sections'][] = $text;
  79              return parser_utils::h('p', $text);
  80          } else {
  81              $this->repeated_sections[] = $text;
  82          }
  83  
  84          return $match[0];
  85      }
  86  }