wpseek.com
A WordPress-centric search engine for devs and theme authors



make_clickable › WordPress Function

Since0.71
Deprecatedn/a
make_clickable ( $text )
Parameters:
  • (string) $text Content to convert URIs.
    Required: Yes
Returns:
  • (string) Content with converted URIs.
Defined at:
Codex:

Converts plaintext URI to HTML links.

Converts URI, www and ftp, and email addresses. Finishes by fixing links within links.


Source

function make_clickable( $text ) {
	$r               = '';
	$textarr         = preg_split( '/(<[^<>]+>)/', $text, -1, PREG_SPLIT_DELIM_CAPTURE ); // Split out HTML tags.
	$nested_code_pre = 0; // Keep track of how many levels link is nested inside <pre> or <code>.
	foreach ( $textarr as $piece ) {

		if ( preg_match( '|^<code[\s>]|i', $piece )
			|| preg_match( '|^<pre[\s>]|i', $piece )
			|| preg_match( '|^<script[\s>]|i', $piece )
			|| preg_match( '|^<style[\s>]|i', $piece )
		) {
			++$nested_code_pre;
		} elseif ( $nested_code_pre
			&& ( '</code>' === strtolower( $piece )
				|| '</pre>' === strtolower( $piece )
				|| '</script>' === strtolower( $piece )
				|| '</style>' === strtolower( $piece )
			)
		) {
			--$nested_code_pre;
		}

		if ( $nested_code_pre
			|| empty( $piece )
			|| ( '<' === $piece[0] && ! preg_match( '|^<\s*[\w]{1,20}+://|', $piece ) )
		) {
			$r .= $piece;
			continue;
		}

		// 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 parentheses.
				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 punctuation 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 parenthesis balancing post processing).
				(\\.\\w{2,6})?                                 # 4: Allowing file extensions (e.g., .jpg, .png).
			~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;
		}
	}

	// Cleanup of accidental links within links.
	return preg_replace( '#(<a([ \r\n\t]+[^>]+?>|>))<a [^>]+?>([^>]+?)</a></a>#i', '$1$3</a>', $r );
}