/**
* Computes a score factor for a simple term or a phrase.
*
* The default implementation is:
* return idfFreq(searcher.docFreq(term), searcher.maxDoc());
*
* input - the term in question or array of terms
* reader - reader the document collection being searched
* Returns a score factor for the term
*
* @param mixed $input
* @param \Zend\Search\Lucene\SearchIndexInterface $reader
* @return float a score factor for the term
*/
public function idf($input, \Zend\Search\Lucene\SearchIndexInterface $reader)
{
if (!is_array($input)) {
return $this->idfFreq($reader->docFreq($input), $reader->count());
} else {
$idf = 0.0;
foreach ($input as $term) {
$idf += $this->idfFreq($reader->docFreq($term), $reader->count());
}
return $idf;
}
}
/**
* Calculate result vector for Conjunction query
* (like '+something +another')
*
* @param \Zend\Search\Lucene\SearchIndexInterface $reader
*/
private function _calculateConjunctionResult(Lucene\SearchIndexInterface $reader)
{
$this->_resVector = null;
if (count($this->_terms) == 0) {
$this->_resVector = array();
}
// Order terms by selectivity
$docFreqs = array();
$ids = array();
foreach ($this->_terms as $id => $term) {
$docFreqs[] = $reader->docFreq($term);
$ids[] = $id; // Used to keep original order for terms with the same selectivity and omit terms comparison
}
array_multisort($docFreqs, SORT_ASC, SORT_NUMERIC,
$ids, SORT_ASC, SORT_NUMERIC,
$this->_terms);
$docsFilter = new Lucene\Index\DocsFilter();
foreach ($this->_terms as $termId => $term) {
$termDocs = $reader->termDocs($term, $docsFilter);
}
// Treat last retrieved docs vector as a result set
// (filter collects data for other terms)
$this->_resVector = array_flip($termDocs);
foreach ($this->_terms as $termId => $term) {
$this->_termsFreqs[$termId] = $reader->termFreqs($term, $docsFilter);
}
// ksort($this->_resVector, SORT_NUMERIC);
// Docs are returned ordered. Used algorithms doesn't change elements order.
}
