«Новости по теме» с помощью PHP, phpmorphy и MySQL

$lowercaseLetters = array("'а'", "'б'", "'в'", "'г'", "'д'", "'е'", "'ё'", "'ж'", "'з'", "'и'", "'й'", "'к'", "'л'", "'м'", "'н'", "'о'", "'п'", "'р'", "'с'", "'т'", "'у'", "'ф'", "'х'", "'ц'", "'ч'", "'ш'", "'щ'", "'ъ'", "'ы'", "'ь'", "'э'", "'ю'", "'я'");
$uppercaseLetters = array("'А'", "'Б'", "'В'", "'Г'", "'Д'", "'Е'", "'Ё'", "'Ж'", "'З'", "'И'", "'Й'", "'К'", "'Л'", "'М'", "'Н'", "'О'", "'П'", "'Р'", "'С'", "'Т'", "'У'", "'Ф'", "'Х'", "'Ц'", "'Ч'", "'Ш'", "'Щ'", "'Ъ'", "'Ы'", "'Ь'", "'Э'", "'Ю'", "'Я'");

function cyrUpper($str)
{
global $lowercaseLetters;
global $uppercaseLetters;

return str_replace("'", "", preg_replace($lowercaseLetters, $uppercaseLetters, $str));
}
function cyrLower($str)
{
global $lowercaseLetters;
global $uppercaseLetters;

return str_replace("'", "", preg_replace( $uppercaseLetters,$lowercaseLetters, $str));
}

function cleanUP ($new_string)

{ 
//$new_string=nl2br($new_string);
 $new_string= str_replace("-"," ",$new_string);
  $new_string= str_replace("\r\n"," ",$new_string);
  $new_string= str_replace("\r"," ",$new_string);
    $new_string= str_replace("\n"," ",$new_string);
  $new_string= str_replace("."," ",$new_string);
$new_string = ereg_replace("[^0-9 абвгдеёжзийклмнопрстуфхцчшщъыьэюяАБВГДЕЁЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯ]", "",$new_string );
return $new_string;
}

 
 
require_once( 'morphy/src/common.php');

$text=cleanUP($_REQUEST[title]." ".$_REQUEST[lead]." ".$_REQUEST[body]." ");
$aText = explode(' ',$text);
        $aPort = array();
        $aMorph = array();
        
        foreach ($aText as $word)
                 
            $aMorph[] = cyrUpper($word);//нужно в вин1251 давать не сьедение
    
 
        
        // set some options
        $opts = array(
            'storage' => PHPMORPHY_STORAGE_FILE,
            // Extend graminfo for getAllFormsWithGramInfo method call
            'with_gramtab' => false,
            // Enable prediction by suffix
            'predict_by_suffix' => true,
            // Enable prediction by prefix
            'predict_by_db' => true );
        
      $dir = 'morphy/dicts';
$lang = 'ru_RU';

        
        // Create descriptor for dictionary located in $dir directory with russian language
        $dict_bundle = new phpMorphy_FilesBundle($dir, 'rus');
        
        // Create phpMorphy instance
        try {
            $morphy = new phpMorphy($dict_bundle, $opts);
        } catch(phpMorphy_Exception $e) {
            throw new Exception('Error occured while creating stemmer instance: ' . $e->getMessage());
        }
        
        
        try {
    
        
            if($getroot==22)
                $pseudo_root = $morphy->getPseudoRoot($aMorph);//можно либо взять корни слов
            else
                $pseudo_root = $morphy->getBaseForm($aMorph);//либо базовую форму
            //для нашей задачи $getroot=TRUE
            
        } catch(phpMorphy_Exception $e) {
            throw new Exception('Error occured while text processing: ' . $e->getMessage());
        }

         

foreach ($pseudo_root as $roots){

$slovo=cyrLower($roots[0]);
if (strlen( $slovo)>3 && !in_array($slovo,$stopwords) && count($roots)==1 ) {
 
$tags.=$slovo." ";  }

}

}

This entry passed through the Full-Text RSS service — if this is your content and you're reading it on someone else's site, please read the FAQ at fivefilters.org/content-only/faq.php#publishers. Five Filters recommends: 'You Say What You Like, Because They Like What You Say' - http://www.medialens.org/index.php/alerts/alert-archive/alerts-2013/731-you-say-what-you-like-because-they-like-what-you-say.html