/**
* @return CaseInsensitive
*/
private function getAnalyzerForHighlighter()
{
// используем анализатор для кодировки UTF-8 нечувствительный к регистру
$analyzer = new CaseInsensitive();
// добавляем к анализатору морфологический фильтр
$analyzer->addFilter(new MorphyFilter());
return $analyzer;
}
public function __construct()
{
parent::__construct();
$this->addFilter(new AsciiFoldingFilter());
$this->_minNGramSize = 2;
$this->_minWordSize = $this->_minNGramSize;
}
public function testUtf8NumCaseInsensitive()
{
if (@preg_match('/\\pL/u', 'a') != 1) {
// PCRE unicode support is turned off
return;
}
if (!function_exists('mb_strtolower')) {
// mbstring extension is disabled
return;
}
/** Zend_Search_Lucene_Analysis_Analyzer_Common_Utf8Num_CaseInsensitive */
$analyzer = new Utf8Num\CaseInsensitive();
// 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 AsciiFoldingFilter());
}