gistfile1.php

<?php

	//Function to seperate multiple tags one line
	function fix_newlines_for_clean_html($fixthistext)
	{
		$fixthistext_array = explode("\n", $fixthistext);
		foreach ($fixthistext_array as $unfixedtextkey => $unfixedtextvalue)
		{
			//Makes sure empty lines are ignores
			if (!preg_match("/^(\s)*$/", $unfixedtextvalue))
			{
				$fixedtextvalue = preg_replace("/>(\s|\t)*</U", ">\n<", $unfixedtextvalue);
				$fixedtext_array[$unfixedtextkey] = $fixedtextvalue;
			}
		}
		return implode("\n", $fixedtext_array);
	}

	function clean_html_code($uncleanhtml)
	{
		//Set wanted indentation
		$indent = "    ";


		//Uses previous function to seperate tags
		$fixed_uncleanhtml = fix_newlines_for_clean_html($uncleanhtml);
		$uncleanhtml_array = explode("\n", $fixed_uncleanhtml);
		//Sets no indentation
		$indentlevel = 0;
		foreach ($uncleanhtml_array as $uncleanhtml_key => $currentuncleanhtml)
		{
			//Removes all indentation
			$currentuncleanhtml = preg_replace("/\t+/", "", $currentuncleanhtml);
			$currentuncleanhtml = preg_replace("/^\s+/", "", $currentuncleanhtml);

			$replaceindent = "";

			//Sets the indentation from current indentlevel
			for ($o = 0; $o < $indentlevel; $o++)
			{
				$replaceindent .= $indent;
			}

			//If self-closing tag, simply apply indent
			if (preg_match("/<(.+)\/>/", $currentuncleanhtml))
			{ 
				$cleanhtml_array[$uncleanhtml_key] = $replaceindent.$currentuncleanhtml;
			}
			//If doctype declaration, simply apply indent
			else if (preg_match("/<!(.*)>/", $currentuncleanhtml))
			{ 
				$cleanhtml_array[$uncleanhtml_key] = $replaceindent.$currentuncleanhtml;
			}
			//If opening AND closing tag on same line, simply apply indent
			else if (preg_match("/<[^\/](.*)>/", $currentuncleanhtml) && preg_match("/<\/(.*)>/", $currentuncleanhtml))
			{ 
				$cleanhtml_array[$uncleanhtml_key] = $replaceindent.$currentuncleanhtml;
			}
			//If closing HTML tag or closing JavaScript clams, decrease indentation and then apply the new level
			//If closing HTML tag or closing JavaScript clams, decrease indentation and then apply the new level
			else if (preg_match("/<\/(.*)>/", $currentuncleanhtml) || preg_match("/^(\s|\t)*\}{1}(\s|\t)*$/", $currentuncleanhtml))
			{
			    $indentlevel--;
			    $replaceindent = "";
			    for ($o = 0; $o < $indentlevel; $o++)
			    {
			        $replaceindent .= $indent;
			    }

			    // fix for textarea whitespace and in my opinion nicer looking script tags	
			    if($currentuncleanhtml == '</textarea>' || $currentuncleanhtml == '</script>')
			    {
			        $cleanhtml_array[$uncleanhtml_key] = $cleanhtml_array[($uncleanhtml_key - 1)] . $currentuncleanhtml;
			        unset($cleanhtml_array[($uncleanhtml_key - 1)]);
			    }
			    else
			    {
			        $cleanhtml_array[$uncleanhtml_key] = $replaceindent.$currentuncleanhtml;
			    }
			}
			//If opening HTML tag AND not a stand-alone tag, or opening JavaScript clams, increase indentation and then apply new level
			else if ((preg_match("/<[^\/](.*)>/", $currentuncleanhtml) && !preg_match("/<(link|meta|base|br|img|hr)(.*)>/", $currentuncleanhtml)) || preg_match("/^(\s|\t)*\{{1}(\s|\t)*$/", $currentuncleanhtml))
			{
				$cleanhtml_array[$uncleanhtml_key] = $replaceindent.$currentuncleanhtml;

				$indentlevel++;
				$replaceindent = "";
				for ($o = 0; $o < $indentlevel; $o++)
				{
					$replaceindent .= $indent;
				}
			}
			else
			//Else, only apply indentation
			{$cleanhtml_array[$uncleanhtml_key] = $replaceindent.$currentuncleanhtml;}
		}
		//Return single string seperated by newline
		return implode("\n", $cleanhtml_array);	
	}

	Class extension_html5_doctype extends Extension{

		public function about(){
			return array(
				'name' => 'HTML5 doctype',
				'description' => 'Replace any generated HTML doctype with basic HTML5 doctype',
				'version' => '1.0',
				'release-date' => '2010-07-13',
				'author' => array(
					'name' => 'Nick Dunn'
				)
			);
		}

		public function getSubscribedDelegates(){
			return array(
				array(
					'page' => '/frontend/',
					'delegate' => 'FrontendOutputPostGenerate',
					'callback' => 'parse_html'
				),
			);
		}
		
		/*private function indent($str){
			
			$str = preg_replace("/\n/", '', $str);
			
		    $ret = "";
		    $indent = 0;
		    $indentInc = 1;
		    $noIndent = false;
		
			$indent_char = "\t";
		
		    while (($l = strpos($str,"<",$i)) !== false) {
			
		        if($l!=$r && $indent>0) {
					$ret .= "\n" . str_repeat($indent_char,$indent) . substr($str,$r,($l-$r));
				}
				
		        $i = $l+1;
		
		        $r = strpos($str,">",$i)+1;
		
		        $t = substr($str,$l,($r-$l));
		
		        if(strpos($t,"/")==1){
		            $indent -= $indentInc;
		            $noIndent = true;
		        }
		        else if(($r-$l-strpos($t,"/"))==2 || substr($t,0,2)=="<?"){ $noIndent = true; }
		        if($indent<0){ $indent = 0; }
		        if($ret){ $ret .= "\n"; }
		        $ret .= str_repeat($indent_char,$indent);
		        $ret .= $t;
		        if(!$noIndent){ $indent += $indentInc; }
		        $noIndent = false;
		    }
		    //$ret .= "\n";
		    return($ret);
		}*/
		
		public function parse_html($context) {
			$html = $context['output'];
			$html = preg_replace("/<!DOCTYPE [^>]+>/", "<!DOCTYPE html>", $html);
			
			//$html = clean_html_code($html);
			
			$context['output'] = $html;
		}

	}