? urlfilter-161217-46.patch
? urlfilter.patch
Index: modules/filter/filter.module
===================================================================
RCS file: /cvs/drupal/drupal/modules/filter/filter.module,v
retrieving revision 1.213
diff -u -p -r1.213 filter.module
--- modules/filter/filter.module 6 May 2008 12:18:47 -0000 1.213
+++ modules/filter/filter.module 10 Jun 2008 09:33:48 -0000
@@ -718,20 +718,75 @@ function _filter_url_settings($format) {
* ftp links, etc.) into hyperlinks.
*/
function _filter_url($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';
- // 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);
+ // Pass length to regexp callback.
+ _filter_url_trim(NULL, variable_get('filter_url_length_' . $format, 72));
- // 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', $text);
+ // Need to process each case of replacement type separately (see switch in
+ // the middle of loops). The text must be joined and split again after each
+ // replacement, since they create new HTML tags.
+ for ($task = 1; $task <= 3; $task++) {
+ // 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).
+
+ // If an ignoretag is found, it is stored here and removed when the
+ // closing tag is found. Until then no replacements are made.
+ // Think of this as a stack that always has 0 or 1 items.
+ $opentag = '';
+ for ($i = 0; $i < count($chunks); $i++) {
+ // Even numbers are text, odd numbers are tags.
+ if ($i % 2 == 0) {
+ // Only do replacements when there are no unclosed ignoretags.
+ if ($opentag == '') {
+ switch ($task) {
+ case 1:
+ // Match absolute URLs.
+ $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";
+ $chunks[$i] = preg_replace_callback($re, '_filter_url_parse_full_links', $chunks[$i] );
+ break;
+
+ case 2:
+ // Match e-mail addresses.
+ $urlpattern = '[A-Za-z0-9._-]+@[A-Za-z0-9._+-]+\.[A-Za-z]{2,4}';
+ $re = "`($urlpattern)`i";
+ $chunks[$i] = preg_replace($re, '\1', $chunks[$i]);
+ break;
+
+ case 3:
+ // Match www domains/addresses.
+ $urlpattern = 'www\.[a-zA-Z0-9@:%_+*~#?&=.,/;-]*[a-zA-Z0-9@:%_+~#\&=/;-]';
+ $re = "`($urlpattern)([\.\,\?\!]*?)`i";
+ $chunks[$i] = preg_replace_callback($re, '_filter_url_parse_partial_links', $chunks[$i]);
+ break;
+ }
+ }
+ }
+ else {
+ if ($opentag == '') {
+ // No opening ignoretags.
+ if (preg_match( "`<($ignoretags)(?:\s|>)`i", $chunks[$i], $matches)) {
+ // Catch and store the tag in question.
+ $opentag = $matches[1];
+ }
+ }
+ else {
+ // Nothing happens until we find a matching closing tag.
+ if (preg_match("`<\/$opentag>`i", $chunks[$i], $matches)) {
+ $opentag = '';
+ }
+ }
+ }
+ }
- // 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);
+ $text = implode($chunks);
+ }
return $text;
}
@@ -811,23 +866,27 @@ function _filter_htmlcorrector($text) {
}
/**
- * 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];
+ // Find the capturing parenthesis in the regexp containing 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 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];
+ // Find the parenthesis in the regexp containing 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 +898,7 @@ function _filter_url_trim($text, $length
$_length = $length;
}
- // Use +3 for '...' string length.
- if (strlen($text) > $_length + 3) {
+ if (strlen($text) > $_length) {
$text = substr($text, 0, $_length) . '...';
}