Ужасы SEO с META: Keyword, Description

<?
### Ôóíêöèÿ ñîçäàåò ñïèñîê êëþ÷åâûõ ñëîâ ïî òåêñòó, à òàêæå êðàòêîå îïèñàíèå.
### Âõîäÿùèå ïàðàìåòðû:
###   - $text - Ñîîáñòâåííî òåêñò äëÿ êîòîðîãî õîòèì ïîëó÷èòü êëþ÷åâûå ñëîâà
###   - $keywords - Äîïîëíèòåëüíûå êëþ÷åâûå ñëîâà. Áóäóò äîáàâëÿòüñÿ â íà÷àëî ïîëó÷åííûõ.
###   - $description - Äîïîëíèòåëüíîå îïèñàíèå. Áóäåò äîáàâëÿòüñÿ â íà÷àëî ïîëó÷åííîãî.
###                    (Ó÷òèòå, îïèñàíèå íå áîëåå 200 ñèìâîëîâ, ïîýòîìó ïîëó÷åííîå áóäåò
###                     îáðåçàòüñÿ ñ ó÷åòîì äëèííû äîïîëíèòåëüíîãî)
###
### Âûõîäíûå ïàðàìåòðû:
###   - $meta['keywords'] - Ñîîòâåòñòâåííî êëþ÷åâûå ñëîâà
###   - $meta['description'] - è îïèñàíèå
###
### Èñïîëüçîâàíèå:
###   - $meta=create_meta($text);
###   - $meta=create_meta($text, $keywords);
###   - $meta=create_meta($text, 'äîïîëíèòåëüíûå,êëþ÷åâûå,ñëîâà');
###   - $meta=create_meta($text, $keywords, $description);
###   - $meta=create_meta($text, 'äîïîëíèòåëüíûå,êëþ÷åâûå,ñëîâà', 'äîïîëíèòåëüíîå,îïèñàíèå');
function create_meta($text, $keywords='', $description='') {
    ### Íîðìàëèçàöèÿ òåêñòà
    $text=trim(stripslashes(preg_replace('/[\r\n\t]/i', ' ', strip_tags($text))));
    ### Ôîðìèðóåì îïèñàíèå èç òåêñòà, ìàêñ.200 çà äî ïåðâîãî çíàêà ïóíêòóàöèè
    $idx=200;
    if(!empty($description)) {
        $description=trim($description).' ';
        $idx-=strlen($description);
    }
    while(!in_array($text[$idx], array('.', '!', '?')))$idx--;
    $meta['description']=$description.substr($text, 0, $idx+1);

    ### Çàãðóæàåì òàáëèöó îáùèõ ñëîâ è óäàëÿåì ýòè ñëîâà èç òåêñòà
    $name='common-words.txt';
    if(file_exists($name)) {
        if($file=fopen($name, 'r')) {
            $data='';
            while(!feof($file)){
                $word=trim(fgets($file));
                if($word[0]=='#')continue;
                $data.=' '.$word;
            }
            fclose($file);
            $data=str_replace(' ', '|', trim($data));
        }
        $text=preg_replace('/\b'.$data.'\b/i', '', $text);
    }

    ### Óäàëÿåì èç òåêñòà âñå çíàêè ïðåïèíàíèé è ïóíêòóàöèè è ïðåîáðàçóåì â ìàññèâ ñëîâ
    $text=split(' ', preg_replace('/[^\w]+/i', ' ', $text)); $data='';
    foreach($text as $key=>$word) if(strlen($word)>4)$data.=' '.strtolower($word);
    $text=split(' ', trim($data)); $size=count($text);
    $arr1=array(); $arr2=array(); $arr3=array();

    ### Ñòðîèì ìàññèâ ñëîâ îòñîðòèðîâàííûé ïî ÷àñòîòå âëîæåíèé â òåêñòå
    for($i=0; $i<$size; $i++) {
        $word=$text[$i];
        if($arr1[$word])$arr1[$word]++; else $arr1[$word]=1;
    }
    arsort($arr1);
    ### Ñòðîèì ìàññèâ ôðàç ñîñòîÿùèõ èç äâóõ ñëîâ îòñîðòèðîâàííûé ïî ÷àñòîòå âëîæåíèé â òåêñòå
    for($i=0; $i<$size-1; $i++) {
        $word=$text[$i].' '.$text[$i+1];
        if($arr2[$word])$arr2[$word]++; else $arr2[$word]=1; 
    }
    arsort($arr2);
    ### Ñòðîèì ìàññèâ ôðàç ñîñòîÿùèõ èç òðåõ ñëîâ îòñîðòèðîâàííûé ïî ÷àñòîòå âëîæåíèé â òåêñòå
    for($i=0; $i<$size-2; $i++) {
        $word=$text[$i].' '.$text[$i+1].' '.$text[$i+2];
        if($arr3[$word])$arr3[$word]++; else $arr3[$word]=1;
    }
    arsort($arr3);

    ### Âûáèðàåì 15 ïåðâûõ ñëîâ ñ ìàêñèìàëüíîé ÷àñòîòîé âëîæåíèé
    $data=array(); $i=0;
    foreach($arr1 as $word=>$count) {
        $data[$word]=$count;
        if($i++==16)break;
    }
    ### Âûáèðàåì 8 ïåðâûõ ôðàç ñîñòîÿùèõ èç äâóõ ñëîâ ñ ìàêñèìàëüíîé ÷àñòîòîé âëîæåíèé
    $i=0;
    foreach($arr2 as $word=>$count) {
        $data[$word]=$count;
        if($i++==8)break;
    }
    ### Âûáèðàåì 4 ïåðâûõ ôðàç ñîñòîÿùèõ èç òðåõ ñëîâ ñ ìàêñèìàëüíîé ÷àñòîòîé âëîæåíèé
    $i=0;
    foreach($arr3 as $word=>$count) {
        $data[$word]=$count;
        if($i++==4)break;
    }
    arsort($data); $text='';

    ### Ïåðåâîäèì ìàññèâ ôðàç â òåêñò, îïÿòü òàêè ñ ó÷åòîì ÷àñòîò âëîæåíèé
    foreach($data as $word=>$count) $text.=','.$word; $text=substr($text, 1);
    if(!empty($keywords))$keywords=preg_replace('/,$/i', '', $keywords).',';
    $meta['keywords']=$keywords.$text;

    ### Âîçâðàùàåì ïîëó÷åííûé ðåçóëüòàò
    return $meta;
}
?>

# Ñïèñîê îáùèõ ñëîâ äëÿ keyword ãåíåðàòîðà.
# Äîïóñêàåòñÿ îäíî îáùåå ñëîâî íà ëèíèþ.
# Ñïèñîê ìîæåò ñîñòîÿòü êàê èç àíãëèéñêèõ òàê è èç ðóññêèõ ñëîâ. Âëèÿåò òîëüêî íà ïðîèçâîäèòåëüíîñòü.
a
the
because
òàêæå
íèáóäü
ýòîãî
íåêîòîðûå
êîòîðîé
êîòîðûé
íàîáîðîò
òîëüêî
ìíîãî
íåêòî
íàøåé
íàøåãî
òîãäà
ïîñëå
âñåãî
ïèñàëè

/****************************************************<?
* Name: PageKeywords
* Version 0.3 - just fixed a truncation error 18. Aug. 2006
* Desc: returns a list of words from the document's content
* created by Paul Paulousek [email protected]
* date Aug, 17. 2006
* based on tagcloud of Marc Hinse, [email protected], www.modxcms.de
* Version: 1.1.
*
* Usage: [[PageKeywords?min=`2`]]
* Parameters: 
*	min: Minimum occurrences of a word to be displayed (defaults to 1)
*   if a chunk named "cloudwords" exists, the snippet will take the content of it for building the cloud
*   the chunk must contain a comma-separated list of words and phrases.
* ***************************************************/

$min = isset($min)? $min : "1";

$include =  $modx->getChunk('cloudwords');
$include = explode(",",$include);
//try to get a Chunk for the include-words
if (sizeof($include)<2) {
$include = array('blog','method','edit','content','design','links','quickedit','MODx','customize'); 
//include list (sample, put in your words here)
}
//try to get a Chunk for the include-words
if (!isset($include)) {
$include = array('blog','method','edit','content','design','links','quickedit','MODx','customize'); 
}

$zeichen = array(',','.',':');		//array of chars to be deleted
if (strpos($parent,',')){
	$parent= explode(',',$parent);
}
$cid = $modx->documentIdentifier; //current document
$contents = $modx->getDocument($cid);
// get the normal content
$content=$contents['content'];

// get the TVs
$tvcontent = $modx->getTemplateVarOutput('*', $cid);
// clear the content-TV
$tvcontent['content'] = "";


//put them together

foreach($tvcontent as $key => $value) 
{
		$content.= strip_tags($value)." ";	
	}
		

$output='';
//all to lower and without HTML

$words=array();
	foreach($include as $incword) 
	{
	$wert = substr_count($content,$incword);
		if($wert>=$min) 
		{ 	//look if the word counts the required minimum and is in the include list 
			$words[$incword] = $wert;	//put them in a new array
		}
	} 

ksort($words);	//sort them alphabetically (just comment that out, then they will be unsorted
foreach($words as $key => $wert) {
		$output.= $key.',';	
	}
$output = substr($output,0,strlen($output)-1); //delete last comma and space	
return $output;