- $comment_regex =
- '!' // Start of comment, after the <.
- . '(?:' // Unroll the loop: Consume everything until --> is found.
- . '-(?!->)' // Dash not followed by end of comment.
- . '[^\-]*+' // Consume non-dashes.
- . ')*+' // Loop possessively.
- . '(?:-->)?'; // End of comment. If not found, match all input.
-
- $regex =
- '/(' // Capture the entire match.
- . '<' // Find start of element.
- . '(?(?=!--)' // Is this a comment?
- . $comment_regex // Find end of comment.
- . '|'
- . '[^>]*>?' // Find end of element. If not found, match all input.
- . ')'
- . ')/s';
-
- $textarr = preg_split( $regex, $content, -1, PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_NO_EMPTY );