Clean String

clean-string.php

<?php 


	function clean_string( $input ){

		// Clean HTML (From: http://nadeausoftware.com/articles/2007/09/php_tip_how_strip_html_tags_web_page)
		$input = preg_replace(
	        array(
	          // Remove invisible content
	            '@<head[^>]*?>.*?</head>@siu',
	            '@<style[^>]*?>.*?</style>@siu',
	            '@<script[^>]*?.*?</script>@siu',
	            '@<object[^>]*?.*?</object>@siu',
	            '@<embed[^>]*?.*?</embed>@siu',
	            '@<applet[^>]*?.*?</applet>@siu',
	            '@<noframes[^>]*?.*?</noframes>@siu',
	            '@<noscript[^>]*?.*?</noscript>@siu',
	            '@<noembed[^>]*?.*?</noembed>@siu',
	          // Add line breaks before and after blocks
	            '@</?((address)|(blockquote)|(center)|(del))@iu',
	            '@</?((div)|(h[1-9])|(ins)|(isindex)|(p)|(pre))@iu',
	            '@</?((dir)|(dl)|(dt)|(dd)|(li)|(menu)|(ol)|(ul))@iu',
	            '@</?((table)|(th)|(td)|(caption))@iu',
	            '@</?((form)|(button)|(fieldset)|(legend)|(input))@iu',
	            '@</?((label)|(select)|(optgroup)|(option)|(textarea))@iu',
	            '@</?((frameset)|(frame)|(iframe))@iu',
	        ),
	        array(
	            ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ', ' ',
	            "\n\$0", "\n\$0", "\n\$0", "\n\$0", "\n\$0", "\n\$0",
	            "\n\$0", "\n\$0",
	        ),
	        $input 
		);

		// From: http://stackoverflow.com/a/20766625/164230
  		$input = strip_tags( $input );

  		$input = trim($input);
 		$input = iconv("UTF-8", "UTF-8//IGNORE", $input); // drop all non utf-8 characters

 		// this is some bad utf-8 byte sequence that makes mysql complain - control and formatting i think
 		$input = preg_replace('/(?>[\x00-\x1F]|\xC2[\x80-\x9F]|\xE2[\x80-\x8F]{2}|\xE2\x80[\xA4-\xA8]|\xE2\x81[\x9F-\xAF])/', ' ', $input);

 		$input = preg_replace('/\s+/', ' ', $input); // reduce all multiple whitespace to a single space

 		return $input;

	}


?>