lucene.php

来自「PHP 知识管理系统（基于树结构的知识管理系统）, 英文原版的PHP源码。」· PHP 代码 · 共 1,038 行 · 第 1/3 页

     * Default value is null
     *
     * @param string $fieldName
     */
    static public function setDefaultSearchField($fieldName)
    {
        self::$_defaultSearchField = $fieldName;
    }

    /**
     * Get default search field.
     *
     * Null means, that search is performed through all fields by default
     *
     * @return string
     */
    static public function getDefaultSearchField()
    {
        return self::$_defaultSearchField;
    }

    /**
     * Retrieve index maxBufferedDocs option
     *
     * maxBufferedDocs is a minimal number of documents required before
     * the buffered in-memory documents are written into a new Segment
     *
     * Default value is 10
     *
     * @return integer
     */
    public function getMaxBufferedDocs()
    {
        return $this->getIndexWriter()->maxBufferedDocs;
    }

    /**
     * Set index maxBufferedDocs option
     *
     * maxBufferedDocs is a minimal number of documents required before
     * the buffered in-memory documents are written into a new Segment
     *
     * Default value is 10
     *
     * @param integer $maxBufferedDocs
     */
    public function setMaxBufferedDocs($maxBufferedDocs)
    {
        $this->getIndexWriter()->maxBufferedDocs = $maxBufferedDocs;
    }

    /**
     * Retrieve index maxMergeDocs option
     *
     * maxMergeDocs is a largest number of documents ever merged by addDocument().
     * Small values (e.g., less than 10,000) are best for interactive indexing,
     * as this limits the length of pauses while indexing to a few seconds.
     * Larger values are best for batched indexing and speedier searches.
     *
     * Default value is PHP_INT_MAX
     *
     * @return integer
     */
    public function getMaxMergeDocs()
    {
        return $this->getIndexWriter()->maxMergeDocs;
    }

    /**
     * Set index maxMergeDocs option
     *
     * maxMergeDocs is a largest number of documents ever merged by addDocument().
     * Small values (e.g., less than 10,000) are best for interactive indexing,
     * as this limits the length of pauses while indexing to a few seconds.
     * Larger values are best for batched indexing and speedier searches.
     *
     * Default value is PHP_INT_MAX
     *
     * @param integer $maxMergeDocs
     */
    public function setMaxMergeDocs($maxMergeDocs)
    {
        $this->getIndexWriter()->maxMergeDocs = $maxMergeDocs;
    }

    /**
     * Retrieve index mergeFactor option
     *
     * mergeFactor determines how often segment indices are merged by addDocument().
     * With smaller values, less RAM is used while indexing,
     * and searches on unoptimized indices are faster,
     * but indexing speed is slower.
     * With larger values, more RAM is used during indexing,
     * and while searches on unoptimized indices are slower,
     * indexing is faster.
     * Thus larger values (> 10) are best for batch index creation,
     * and smaller values (< 10) for indices that are interactively maintained.
     *
     * Default value is 10
     *
     * @return integer
     */
    public function getMergeFactor()
    {
        return $this->getIndexWriter()->mergeFactor;
    }

    /**
     * Set index mergeFactor option
     *
     * mergeFactor determines how often segment indices are merged by addDocument().
     * With smaller values, less RAM is used while indexing,
     * and searches on unoptimized indices are faster,
     * but indexing speed is slower.
     * With larger values, more RAM is used during indexing,
     * and while searches on unoptimized indices are slower,
     * indexing is faster.
     * Thus larger values (> 10) are best for batch index creation,
     * and smaller values (< 10) for indices that are interactively maintained.
     *
     * Default value is 10
     *
     * @param integer $maxMergeDocs
     */
    public function setMergeFactor($mergeFactor)
    {
        $this->getIndexWriter()->mergeFactor = $mergeFactor;
    }

    /**
     * Performs a query against the index and returns an array
     * of Zend_Search_Lucene_Search_QueryHit objects.
     * Input is a string or Zend_Search_Lucene_Search_Query.
     *
     * @param mixed $query
     * @return array Zend_Search_Lucene_Search_QueryHit
     * @throws Zend_Search_Lucene_Exception
     */
    public function find($query)
    {
        if (is_string($query)) {
            $query = Zend_Search_Lucene_Search_QueryParser::parse($query);
        }

        if (!$query instanceof Zend_Search_Lucene_Search_Query) {
            throw new Zend_Search_Lucene_Exception('Query must be a string or Zend_Search_Lucene_Search_Query object');
        }

        $this->commit();

        $hits   = array();
        $scores = array();
        $ids    = array();

        $query = $query->rewrite($this)->optimize($this);

        $query->execute($this);

        $topScore = 0;

        foreach ($query->matchedDocs() as $id => $num) {
            $docScore = $query->score($id, $this);
            if( $docScore != 0 ) {
                $hit = new Zend_Search_Lucene_Search_QueryHit($this);
                $hit->id = $id;
                $hit->score = $docScore;

                $hits[]   = $hit;
                $ids[]    = $id;
                $scores[] = $docScore;

                if ($docScore > $topScore) {
                    $topScore = $docScore;
                }
            }
        }

        if (count($hits) == 0) {
            // skip sorting, which may cause a error on empty index
        	return array();
        }

        if ($topScore > 1) {
            $normalizedScores = array();

            foreach ($scores as $score) {
                $normalizedScores[] = $score/$topScore;
            }

            $scores = $normalizedScores;
        }

        if (func_num_args() == 1) {
            // sort by scores
            array_multisort($scores, SORT_DESC, SORT_NUMERIC,
                            $ids,    SORT_ASC,  SORT_NUMERIC,
                            $hits);
        } else {
            // sort by given field names

            $argList    = func_get_args();
            $fieldNames = $this->getFieldNames();
            $sortArgs   = array();

            for ($count = 1; $count < count($argList); $count++) {
                $fieldName = $argList[$count];

                if (!is_string($fieldName)) {
                    throw new Zend_Search_Lucene_Exception('Field name must be a string.');
                }

                if (!in_array($fieldName, $fieldNames)) {
                    throw new Zend_Search_Lucene_Exception('Wrong field name.');
                }

                $valuesArray = array();
                foreach ($hits as $hit) {
                    try {
                        $value = $hit->getDocument()->getFieldValue($fieldName);
                    } catch (Zend_Search_Lucene_Exception $e) {
                        if (strpos($e->getMessage(), 'not found') === false) {
                            throw $e;
                        } else {
                            $value = null;
                        }
                    }

                    $valuesArray[] = $value;
                }

                $sortArgs[] = $valuesArray;

                if ($count + 1 < count($argList)  &&  is_integer($argList[$count+1])) {
                    $count++;
                    $sortArgs[] = $argList[$count];

                    if ($count + 1 < count($argList)  &&  is_integer($argList[$count+1])) {
                        $count++;
                        $sortArgs[] = $argList[$count];
                    } else {
                        if ($argList[$count] == SORT_ASC  || $argList[$count] == SORT_DESC) {
                            $sortArgs[] = SORT_REGULAR;
                        } else {
                            $sortArgs[] = SORT_ASC;
                        }
                    }
                } else {
                    $sortArgs[] = SORT_ASC;
                    $sortArgs[] = SORT_REGULAR;
                }
            }

            // Sort by id's if values are equal
            $sortArgs[] = $ids;
            $sortArgs[] = SORT_ASC;
            $sortArgs[] = SORT_NUMERIC;

            // Array to be sorted
            $sortArgs[] = &$hits;

            // Do sort
            call_user_func_array('array_multisort', $sortArgs);
        }

        return $hits;
    }


    /**
     * Returns a list of all unique field names that exist in this index.
     *
     * @param boolean $indexed
     * @return array
     */
    public function getFieldNames($indexed = false)
    {
        $result = array();
        foreach( $this->_segmentInfos as $segmentInfo ) {
            $result = array_merge($result, $segmentInfo->getFields($indexed));
        }
        return $result;
    }


    /**
     * Returns a Zend_Search_Lucene_Document object for the document
     * number $id in this index.
     *
     * @param integer|Zend_Search_Lucene_Search_QueryHit $id
     * @return Zend_Search_Lucene_Document
     */
    public function getDocument($id)
    {
        if ($id instanceof Zend_Search_Lucene_Search_QueryHit) {
            /* @var $id Zend_Search_Lucene_Search_QueryHit */
            $id = $id->id;
        }

        if ($id >= $this->_docCount) {
            throw new Zend_Search_Lucene_Exception('Document id is out of the range.');
        }

        $segmentStartId = 0;
        foreach ($this->_segmentInfos as $segmentInfo) {
            if ($segmentStartId + $segmentInfo->count() > $id) {
                break;
            }

            $segmentStartId += $segmentInfo->count();
        }

        $fdxFile = $segmentInfo->openCompoundFile('.fdx');
        $fdxFile->seek( ($id-$segmentStartId)*8, SEEK_CUR );
        $fieldValuesPosition = $fdxFile->readLong();

        $fdtFile = $segmentInfo->openCompoundFile('.fdt');
        $fdtFile->seek($fieldValuesPosition, SEEK_CUR);
        $fieldCount = $fdtFile->readVInt();

        $doc = new Zend_Search_Lucene_Document();
        for ($count = 0; $count < $fieldCount; $count++) {
            $fieldNum = $fdtFile->readVInt();
            $bits = $fdtFile->readByte();

            $fieldInfo = $segmentInfo->getField($fieldNum);

            if (!($bits & 2)) { // Text data
                $field = new Zend_Search_Lucene_Field($fieldInfo->name,
                                                      $fdtFile->readString(),
                                                      'UTF-8',
                                                      true,
                                                      $fieldInfo->isIndexed,
                                                      $bits & 1 );
            } else {            // Binary data
                $field = new Zend_Search_Lucene_Field($fieldInfo->name,
                                                      $fdtFile->readBinary(),
                                                      '',
                                                      true,
                                                      $fieldInfo->isIndexed,
                                                      $bits & 1,
                                                      true );
            }

            $doc->addField($field);
        }