--- modules/filter/filter.module.org 2008-05-06 15:18:47.000000000 +0300 +++ modules/filter/filter.module 2008-07-08 00:02:50.000000000 +0300 @@ -718,20 +718,92 @@ * ftp links, etc.) into hyperlinks. */ function _filter_url($text, $format) { - // Pass length to regexp callback - _filter_url_trim(NULL, variable_get('filter_url_length_' . $format, 72)); - - $text = ' ' . $text . ' '; + // List of tags - the content of which must be skipped. + $ignoretags = 'a|script|style|code'; + // This filter identifies and makes clickable links of 3 types of "links". + // 1) URL's like http://www.example.com. + // 2) e-mail addresses like name@example.com. + // 3) Web addresses without the "http://" protocol defined, like www.example.com. + // Each type must be processed separately, as there is no one regular expression + // that could possibly match all of the cases in one pass. + // + // Create an array which contains the regexps for each type of link. + // The key to the regexp is the name of a function that is used as + // callback function to process matches of the regexp. The callback function + // is to return the replacement for the match. + // The array is used and matching/replacement done below inside some loops. + $tasks = NULL; // Match absolute URLs. - $text = preg_replace_callback("`(

|

  • ||[ \n\r\t\(])((http://|https://|ftp://|mailto:|smb://|afp://|file://|gopher://|news://|ssl://|sslv2://|sslv3://|tls://|tcp://|udp://)([a-zA-Z0-9@:%_+*~#?&=.,/;-]*[a-zA-Z0-9@:%_+*~#&=/;-]))([.,?!]*?)(?=(

    |
    • ||[ \n\r\t\)]))`i", '_filter_url_parse_full_links', $text); - + $protocols = 'http://|https://|ftp://|mailto:|smb://|afp://|file://|gopher://|news://|ssl://|sslv2://|sslv3://|tls://|tcp://|udp://'; + $urlpattern = "(?:$protocols)(?:[a-zA-Z0-9@:%_+*~#?&=.,/;-]*[a-zA-Z0-9@:%_+*~#&=/;-])"; + $re = "`($urlpattern)([\.\,\?\!]*?)`i"; + $tasks['_filter_url_parse_full_links'] = $re; // Match e-mail addresses. - $text = preg_replace("`(

    |

  • ||[ \n\r\t\(])([A-Za-z0-9._-]+@[A-Za-z0-9._+-]+\.[A-Za-z]{2,4})([.,?!]*?)(?=(

    |
    • ||[ \n\r\t\)]))`i", '\1\2\3', $text); - + // Note: The ICANN seems to be on track towards accepting more diverse top level domains, + // so this pattern has been "future-proofed" to allow for TLD's of length 2-64. + $urlpattern = '[A-Za-z0-9._-]+@[A-Za-z0-9._+-]+\.[A-Za-z]{2,64}'; + $re = "`($urlpattern)`i"; + $tasks['_filter_url_parse_email_links'] = $re; // Match www domains/addresses. - $text = preg_replace_callback("`(

    |

  • |[ \n\r\t\(])(www\.[a-zA-Z0-9@:%_+*~#?&=.,/;-]*[a-zA-Z0-9@:%_+~#\&=/;-])([.,?!]*?)(?=(

    |
    • ||[ \n\r\t\)]))`i", '_filter_url_parse_partial_links', $text); - $text = substr($text, 1, -1); + $urlpattern = 'www\.[a-zA-Z0-9@:%_+*~#?&=.,/;-]*[a-zA-Z0-9@:%_+~#\&=/;-]'; + $re = "`($urlpattern)([\.\,\?\!]*?)`i"; + $tasks['_filter_url_parse_partial_links'] = $re; + + + // Pass length to regexp callback. + _filter_url_trim(NULL, variable_get('filter_url_length_' . $format, 72)); + + // We need to process each case of replacement type separately. + // The text must be joined and split again after each + // replacement, since replacements create new HTML tags and the new + // tags must be correctly protected before the next replacement can be done. + foreach ($tasks as $task => $re) { + // Split at all tags. + // This ensures that nothing that is a tagname or attribute will be processed. + $chunks = preg_split('/(<.+?>)/i', $text, -1, PREG_SPLIT_DELIM_CAPTURE); + // Note: PHP ensures the array consists of alternating delimiters and literals + // and begins and ends with a literal (inserting NULL as required). + // Therefore, first chunk is always text: + $chunk_type = 'text'; + // Tags to ignore are defined in $ignoretags (see above). + // If an ignoretag is found, it is stored here and removed only when the + // closing tag is found. Until the closing tag is found, no replacements are made. + $opentag = ''; + + for ($i = 0; $i < count($chunks); $i++) { + if ($chunk_type == 'text') { + // Only do replacements when there are no unclosed ignoretags. + if ($opentag == '') { + // This is the high point of this function! If there is a match, + // a link is created in the callback function named by $task. + $chunks[$i] = preg_replace_callback($re, $task, $chunks[$i]); + } + // Done processing text chunk, so next chunk is a tag. + $chunk_type = 'tag'; + } + else { + if ($opentag == '') { + // No open ignoretags. Process this tag... + if (preg_match("`<($ignoretags)(?:\s|>)`i", $chunks[$i], $matches)) { + // This matches one of the $ignoretags. + // Catch and store the tag in question. + $opentag = $matches[1]; + } + } + else { + // There is an $ignoretag open. See if this is a matching closing tag. + // Nothing else is done until we find the closing tag. + if (preg_match("`<\/$opentag>`i", $chunks[$i], $matches)) { + $opentag = ''; + } + } + // Done processing tag chunk, so next chunk is text. + $chunk_type = 'text'; + } + } + $text = implode($chunks); + } return $text; } @@ -811,23 +883,42 @@ } /** - * Make links out of absolute URLs. + * Callback function. Make links out of absolute URLs. */ function _filter_url_parse_full_links($match) { - $match[2] = decode_entities($match[2]); - $caption = check_plain(_filter_url_trim($match[2])); - $match[2] = check_url($match[2]); - return $match[1] . '' . $caption . '' . $match[5]; + // The $i:th parenthesis in the regexp contains the URL. + $i = 1; + + $match[$i] = decode_entities($match[$i]); + $caption = check_plain(_filter_url_trim($match[$i])); + $match[$i] = check_url($match[$i]); + return '' . $caption . '' . $match[$i+1]; } /** - * Make links out of domain names starting with "www." + * Callback function. Make links out of e-mail addresses. + */ +function _filter_url_parse_email_links($match) { + // The $i:th parenthesis in the regexp contains the URL. + $i = 0; + + $match[$i] = decode_entities($match[$i]); + $caption = check_plain(_filter_url_trim($match[$i])); + $match[$i] = check_url($match[$i]); + return '' . $caption . ''; +} + +/** + * Callback function. Make links out of domain names starting with "www.". */ function _filter_url_parse_partial_links($match) { - $match[2] = decode_entities($match[2]); - $caption = check_plain(_filter_url_trim($match[2])); - $match[2] = check_plain($match[2]); - return $match[1] . '' . $caption . '' . $match[3]; + // The $i:th parenthesis in the regexp contains the URL. + $i = 1; + + $match[$i] = decode_entities($match[$i]); + $caption = check_plain(_filter_url_trim($match[$i])); + $match[$i] = check_plain($match[$i]); + return '' . $caption . '' . $match[$i+1]; } /** @@ -839,8 +930,7 @@ $_length = $length; } - // Use +3 for '...' string length. - if (strlen($text) > $_length + 3) { + if (strlen($text) > $_length) { $text = substr($text, 0, $_length) . '...'; }