public function testUtf8Num()
{
if (@preg_match('/\pL/u', 'a') != 1) {
// PCRE unicode support is turned off
return;
}
/** Zend_Search_Lucene_Analysis_Analyzer_Common_Utf8Num */
$analyzer = new Common\Utf8Num();
// UTF-8 text with a cyrillic symbols
$tokenList = $analyzer->tokenize('Слово1 Слово2 ДругоеСлово', 'UTF-8');
$this->assertEquals(count($tokenList), 3);
$this->assertEquals($tokenList[0]->getTermText(), 'Слово1');
$this->assertEquals($tokenList[0]->getStartOffset(), 0);
$this->assertEquals($tokenList[0]->getEndOffset(), 6);
$this->assertEquals($tokenList[0]->getPositionIncrement(), 1);
$this->assertEquals($tokenList[1]->getTermText(), 'Слово2');
$this->assertEquals($tokenList[1]->getStartOffset(), 7);
$this->assertEquals($tokenList[1]->getEndOffset(), 13);
$this->assertEquals($tokenList[1]->getPositionIncrement(), 1);
$this->assertEquals($tokenList[2]->getTermText(), 'ДругоеСлово');
$this->assertEquals($tokenList[2]->getStartOffset(), 14);
$this->assertEquals($tokenList[2]->getEndOffset(), 25);
$this->assertEquals($tokenList[2]->getPositionIncrement(), 1);
}
public function __construct()
{
parent::__construct();
$this->addFilter(new TokenFilter\LowerCaseUtf8());
}
