関連ニュースPHP、phpmorphy、MySQLの使用

 $lowercaseLetters = array("''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''"); $uppercaseLetters = array("''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''", "''"); function cyrUpper($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); $new_string = ereg_replace("[^0-9 ]", "",$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);//  1251    // 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);//     else $pseudo_root = $morphy->getBaseForm($aMorph);//   //   $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." "; } } }