Don't attempt to make links inside attributes clickable. Props duck_ azaozz. fixes #20418

git-svn-id: http://svn.automattic.com/wordpress/trunk@20443 1a063a9b-81f0-0310-95a4-ce76da25c4cd
This commit is contained in:
ryan 2012-04-11 21:14:13 +00:00
parent 2dd485a823
commit be5802b0f1

View File

@ -1468,49 +1468,59 @@ function _make_email_clickable_cb($matches) {
* *
* @since 0.71 * @since 0.71
* *
* @param string $ret Content to convert URIs. * @param string $text Content to convert URIs.
* @return string Content with converted URIs. * @return string Content with converted URIs.
*/ */
function make_clickable( $ret ) { function make_clickable( $text ) {
// Long strings might contain expensive edge cases ... $r = '';
if ( 10000 < strlen( $ret ) ) { $textarr = preg_split( '/(<[^<>]+>)/', $text, -1, PREG_SPLIT_DELIM_CAPTURE ); // split out HTML tags
$r = ''; foreach ( $textarr as $piece ) {
// ... break it up if ( empty( $piece ) || ( $piece[0] == '<' && ! preg_match('|^<\s*[\w]{1,20}+://|', $piece) ) ) {
foreach ( _split_str_by_whitespace( $ret, 2100 ) as $chunk ) { // 2100: Extra room for scheme and leading and trailing paretheses $r .= $piece;
if ( 2101 < strlen( $chunk ) ) { continue;
$r .= $chunk; // Too big, no whitespace: bail. }
} else {
$r .= make_clickable( $chunk ); // Long strings might contain expensive edge cases ...
} if ( 10000 < strlen( $piece ) ) {
// ... break it up
foreach ( _split_str_by_whitespace( $piece, 2100 ) as $chunk ) { // 2100: Extra room for scheme and leading and trailing paretheses
if ( 2101 < strlen( $chunk ) ) {
$r .= $chunk; // Too big, no whitespace: bail.
} else {
$r .= make_clickable( $chunk );
}
}
} else {
$ret = " $piece "; // Pad with whitespace to simplify the regexes
$url_clickable = '~
([\\s(<.,;:!?]) # 1: Leading whitespace, or punctuation
( # 2: URL
[\\w]{1,20}+:// # Scheme and hier-part prefix
(?=\S{1,2000}\s) # Limit to URLs less than about 2000 characters long
[\\w\\x80-\\xff#%\\~/@\\[\\]*(+=&$-]*+ # Non-punctuation URL character
(?: # Unroll the Loop: Only allow puctuation URL character if followed by a non-punctuation URL character
[\'.,;:!?)] # Punctuation URL character
[\\w\\x80-\\xff#%\\~/@\\[\\]*(+=&$-]++ # Non-punctuation URL character
)*
)
(\)?) # 3: Trailing closing parenthesis (for parethesis balancing post processing)
~xS'; // The regex is a non-anchored pattern and does not have a single fixed starting character.
// Tell PCRE to spend more time optimizing since, when used on a page load, it will probably be used several times.
$ret = preg_replace_callback( $url_clickable, '_make_url_clickable_cb', $ret );
$ret = preg_replace_callback( '#([\s>])((www|ftp)\.[\w\\x80-\\xff\#$%&~/.\-;:=,?@\[\]+]+)#is', '_make_web_ftp_clickable_cb', $ret );
$ret = preg_replace_callback( '#([\s>])([.0-9a-z_+-]+)@(([0-9a-z-]+\.)+[0-9a-z]{2,})#i', '_make_email_clickable_cb', $ret );
$ret = substr( $ret, 1, -1 ); // Remove our whitespace padding.
$r .= $ret;
} }
return $r;
} }
$ret = " $ret "; // Pad with whitespace to simplify the regexes
$url_clickable = '~
([\\s(<.,;:!?]) # 1: Leading whitespace, or punctuation
( # 2: URL
[\\w]{1,20}+:// # Scheme and hier-part prefix
(?=\S{1,2000}\s) # Limit to URLs less than about 2000 characters long
[\\w\\x80-\\xff#%\\~/@\\[\\]*(+=&$-]*+ # Non-punctuation URL character
(?: # Unroll the Loop: Only allow puctuation URL character if followed by a non-punctuation URL character
[\'.,;:!?)] # Punctuation URL character
[\\w\\x80-\\xff#%\\~/@\\[\\]*(+=&$-]++ # Non-punctuation URL character
)*
)
(\)?) # 3: Trailing closing parenthesis (for parethesis balancing post processing)
~xS'; // The regex is a non-anchored pattern and does not have a single fixed starting character.
// Tell PCRE to spend more time optimizing since, when used on a page load, it will probably be used several times.
$ret = preg_replace_callback( $url_clickable, '_make_url_clickable_cb', $ret );
$ret = preg_replace_callback('#([\s>])((www|ftp)\.[\w\\x80-\\xff\#$%&~/.\-;:=,?@\[\]+]+)#is', '_make_web_ftp_clickable_cb', $ret);
$ret = preg_replace_callback('#([\s>])([.0-9a-z_+-]+)@(([0-9a-z-]+\.)+[0-9a-z]{2,})#i', '_make_email_clickable_cb', $ret);
// Cleanup of accidental links within links // Cleanup of accidental links within links
$ret = preg_replace("#(<a( [^>]+?>|>))<a [^>]+?>([^>]+?)</a></a>#i", "$1$3</a>", $ret); $r = preg_replace( '#(<a( [^>]+?>|>))<a [^>]+?>([^>]+?)</a></a>#i', "$1$3</a>", $r );
return substr( $ret, 1, -1 ); // Remove our whitespace padding. return $r;
} }
/** /**