- Fix handling of <title> tag for cases where (malformed) HTML content contains more than one <title> tag
| | |
| | | // special replacements (not properly handled by washtml class) |
| | | $html_search = array( |
| | | '/(<\/nobr>)(\s+)(<nobr>)/i', // space(s) between <NOBR> |
| | | '/<title[^>]*>.*<\/title>/i', // PHP bug #32547 workaround: remove title tag |
| | | '/<title[^>]*>[^<]*<\/title>/i', // PHP bug #32547 workaround: remove title tag |
| | | '/^(\0\0\xFE\xFF|\xFF\xFE\0\0|\xFE\xFF|\xFF\xFE|\xEF\xBB\xBF)/', // byte-order mark (only outlook?) |
| | | '/<html\s[^>]+>/i', // washtml/DOMDocument cannot handle xml namespaces |
| | | ); |