searchindex.java

来自「jsr170接口的java实现。是个apache的开源项目。」· Java 代码 · 共 1,046 行 · 第 1/3 页

/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *      http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */
package org.apache.jackrabbit.core.query.lucene;

import org.apache.jackrabbit.core.ItemManager;
import org.apache.jackrabbit.core.SessionImpl;
import org.apache.jackrabbit.core.NodeId;
import org.apache.jackrabbit.core.NodeIdIterator;
import org.apache.jackrabbit.core.query.AbstractQueryHandler;
import org.apache.jackrabbit.core.query.ExecutableQuery;
import org.apache.jackrabbit.core.query.QueryHandlerContext;
import org.apache.jackrabbit.core.query.QueryHandler;
import org.apache.jackrabbit.core.state.NodeState;
import org.apache.jackrabbit.core.state.NodeStateIterator;
import org.apache.jackrabbit.extractor.DefaultTextExtractor;
import org.apache.jackrabbit.extractor.TextExtractor;
import org.apache.jackrabbit.name.NoPrefixDeclaredException;
import org.apache.jackrabbit.name.QName;
import org.apache.jackrabbit.name.NameFormat;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.MultiReader;
import org.apache.lucene.search.Hits;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.Sort;
import org.apache.lucene.search.SortField;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.commons.collections.iterators.AbstractIteratorDecorator;

import javax.jcr.RepositoryException;
import javax.jcr.query.InvalidQueryException;
import java.io.IOException;
import java.io.File;
import java.util.Iterator;
import java.util.List;
import java.util.ArrayList;
import java.util.HashSet;
import java.util.Set;
import java.util.Arrays;

/**
 * Implements a {@link org.apache.jackrabbit.core.query.QueryHandler} using
 * Lucene.
 */
public class SearchIndex extends AbstractQueryHandler {

    /** The logger instance for this class */
    private static final Logger log = LoggerFactory.getLogger(SearchIndex.class);

    /**
     * Name of the file to persist search internal namespace mappings.
     */
    private static final String NS_MAPPING_FILE = "ns_mappings.properties";

    /**
     * The default value for property {@link #minMergeDocs}.
     */
    public static final int DEFAULT_MIN_MERGE_DOCS = 100;

    /**
     * The default value for property {@link #maxMergeDocs}.
     */
    public static final int DEFAULT_MAX_MERGE_DOCS = 100000;

    /**
     * the default value for property {@link #mergeFactor}.
     */
    public static final int DEFAULT_MERGE_FACTOR = 10;

    /**
     * the default value for property {@link #maxFieldLength}.
     */
    public static final int DEFAULT_MAX_FIELD_LENGTH = 10000;

    /**
     * The default value for property {@link #extractorPoolSize}.
     */
    public static final int DEFAULT_EXTRACTOR_POOL_SIZE = 0;

    /**
     * The default value for property {@link #extractorBackLog}.
     */
    public static final int DEFAULT_EXTRACTOR_BACK_LOG = 100;

    /**
     * The default timeout in milliseconds which is granted to the text
     * extraction process until fulltext indexing is deferred to a background
     * thread.
     */
    public static final long DEFAULT_EXTRACTOR_TIMEOUT = 100;

    /**
     * The actual index
     */
    private MultiIndex index;

    /**
     * The analyzer we use for indexing.
     */
    private Analyzer analyzer;

    /**
     * List of text extractor and text filter class names. The configured
     * classes will be instantiated and used to extract text content from
     * binary properties.
     */
    private String textFilterClasses =
        DefaultTextExtractor.class.getName();

    /**
     * Text extractor for extracting text content of binary properties.
     */
    private TextExtractor extractor;

    /**
     * The location of the search index.
     * <p/>
     * Note: This is a <b>mandatory</b> parameter!
     */
    private String path;

    /**
     * minMergeDocs config parameter.
     */
    private int minMergeDocs = DEFAULT_MIN_MERGE_DOCS;

    /**
     * volatileIdleTime config parameter.
     */
    private int volatileIdleTime = 3;

    /**
     * maxMergeDocs config parameter
     */
    private int maxMergeDocs = DEFAULT_MAX_MERGE_DOCS;

    /**
     * mergeFactor config parameter
     */
    private int mergeFactor = DEFAULT_MERGE_FACTOR;

    /**
     * maxFieldLength config parameter
     */
    private int maxFieldLength = DEFAULT_MAX_FIELD_LENGTH;

    /**
     * extractorPoolSize config parameter
     */
    private int extractorPoolSize = DEFAULT_EXTRACTOR_POOL_SIZE;

    /**
     * extractorBackLog config parameter
     */
    private int extractorBackLog = DEFAULT_EXTRACTOR_BACK_LOG;

    /**
     * extractorTimeout config parameter
     */
    private long extractorTimeout = DEFAULT_EXTRACTOR_TIMEOUT;

    /**
     * Number of documents that are buffered before they are added to the index.
     */
    private int bufferSize = 10;

    /**
     * Compound file flag
     */
    private boolean useCompoundFile = true;

    /**
     * Flag indicating whether document order is enable as the default ordering.
     */
    private boolean documentOrder = true;

    /**
     * If set <code>true</code> the index is checked for consistency on startup.
     * If <code>false</code> a consistency check is only performed when there
     * are entries in the redo log on startup.
     * <p/>
     * Default value is: <code>false</code>.
     */
    private boolean forceConsistencyCheck = false;

    /**
     * If set <code>true</code> errors detected by the consistency check are
     * repaired. If <code>false</code> the errors are only reported in the log.
     * <p/>
     * Default value is: <code>true</code>.
     */
    private boolean autoRepair = true;

    /**
     * The uuid resolver cache size.
     * <p/>
     * Default value is: <code>1000</code>.
     */
    private int cacheSize = 1000;

    /**
     * The number of documents that are pre fetched when a query is executed.
     * <p/>
     * Default value is: {@link Integer#MAX_VALUE}.
     */
    private int resultFetchSize = Integer.MAX_VALUE;

    /**
     * If set to <code>true</code> the fulltext field is stored and and a term
     * vector is created with offset information.
     * <p/>
     * Default value is: <code>false</code>.
     */
    private boolean supportHighlighting = false;

    /**
     * The excerpt provider class. Implements {@link ExcerptProvider}.
     */
    private Class excerptProviderClass = DefaultXMLExcerpt.class;

    /**
     * Indicates if this <code>SearchIndex</code> is closed and cannot be used
     * anymore.
     */
    private boolean closed = false;

    /**
     * Default constructor.
     */
    public SearchIndex() {
        this.analyzer = new StandardAnalyzer(new String[]{});
    }

    /**
     * Initializes this <code>QueryHandler</code>. This implementation requires
     * that a path parameter is set in the configuration. If this condition
     * is not met, a <code>IOException</code> is thrown.
     *
     * @throws IOException if an error occurs while initializing this handler.
     */
    protected void doInit() throws IOException {
        QueryHandlerContext context = getContext();
        if (path == null) {
            throw new IOException("SearchIndex requires 'path' parameter in configuration!");
        }

        Set excludedIDs = new HashSet();
        if (context.getExcludedNodeId() != null) {
            excludedIDs.add(context.getExcludedNodeId());
        }

        extractor = createTextExtractor();

        File indexDir = new File(path);

        NamespaceMappings nsMappings;
        if (context.getParentHandler() instanceof SearchIndex) {
            // use system namespace mappings
            SearchIndex sysIndex = (SearchIndex) context.getParentHandler();
            nsMappings = sysIndex.getNamespaceMappings();
        } else {
            // read local namespace mappings
            File mapFile = new File(indexDir, NS_MAPPING_FILE);
            if (mapFile.exists()) {
                // be backward compatible and use ns_mappings.properties from
                // index folder
                nsMappings = new FileBasedNamespaceMappings(mapFile);
            } else {
                // otherwise use repository wide stable index prefix from
                // namespace registry
                nsMappings = new NSRegistryBasedNamespaceMappings(
                        context.getNamespaceRegistry());
            }
        }

        index = new MultiIndex(indexDir, this, context.getItemStateManager(),
                context.getRootId(), excludedIDs, nsMappings);
        if (index.getRedoLogApplied() || forceConsistencyCheck) {
            log.info("Running consistency check...");
            try {
                ConsistencyCheck check = ConsistencyCheck.run(index,
                        context.getItemStateManager());
                if (autoRepair) {
                    check.repair(true);
                } else {
                    List errors = check.getErrors();
                    if (errors.size() == 0) {
                        log.info("No errors detected.");
                    }
                    for (Iterator it = errors.iterator(); it.hasNext();) {
                        ConsistencyCheckError err = (ConsistencyCheckError) it.next();
                        log.info(err.toString());
                    }
                }
            } catch (Exception e) {
                log.warn("Failed to run consistency check on index: " + e);
            }
        }
        log.info("Index initialized: " + path);
    }

    /**
     * Adds the <code>node</code> to the search index.
     * @param node the node to add.
     * @throws RepositoryException if an error occurs while indexing the node.
     * @throws IOException if an error occurs while adding the node to the index.
     */
    public void addNode(NodeState node) throws RepositoryException, IOException {
        throw new UnsupportedOperationException("addNode");
    }

    /**
     * Removes the node with <code>uuid</code> from the search index.
     * @param id the id of the node to remove from the index.
     * @throws IOException if an error occurs while removing the node from
     * the index.
     */
    public void deleteNode(NodeId id) throws IOException {
        throw new UnsupportedOperationException("deleteNode");
    }

    /**
     * This implementation forwards the call to
     * {@link MultiIndex#update(java.util.Iterator, java.util.Iterator)} and
     * transforms the two iterators to the required types.
     *
     * @param remove uuids of nodes to remove.
     * @param add    NodeStates to add. Calls to <code>next()</code> on this
     *               iterator may return <code>null</code>, to indicate that a
     *               node could not be indexed successfully.