indexreader.java

lucene2.2.0版本

package org.apache.lucene.index;

/**
 * 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.
 */

import org.apache.lucene.document.Document;
import org.apache.lucene.document.FieldSelector;
import org.apache.lucene.search.Similarity;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.store.IndexInput;
import org.apache.lucene.store.Lock;
import org.apache.lucene.store.LockObtainFailedException;
import org.apache.lucene.store.AlreadyClosedException;

import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.util.Arrays;
import java.util.Collection;

/** IndexReader is an abstract class, providing an interface for accessing an
 index.  Search of an index is done entirely through this abstract interface,
 so that any subclass which implements it is searchable.

 <p> Concrete subclasses of IndexReader are usually constructed with a call to
 one of the static <code>open()</code> methods, e.g. {@link #open(String)}.

 <p> For efficiency, in this API documents are often referred to via
 <i>document numbers</i>, non-negative integers which each name a unique
 document in the index.  These document numbers are ephemeral--they may change
 as documents are added to and deleted from an index.  Clients should thus not
 rely on a given document having the same number between sessions.

 <p> An IndexReader can be opened on a directory for which an IndexWriter is
 opened already, but it cannot be used to delete documents from the index then.

 @author Doug Cutting
 @version $Id: IndexReader.java 543620 2007-06-01 21:18:56Z dnaber $
*/
public abstract class IndexReader {

  public static final class FieldOption {
    private String option;
    private FieldOption() { }
    private FieldOption(String option) {
      this.option = option;
    }
    public String toString() {
      return this.option;
    }
    // all fields
    public static final FieldOption ALL = new FieldOption ("ALL");
    // all indexed fields
    public static final FieldOption INDEXED = new FieldOption ("INDEXED");
    // all fields that store payloads
    public static final FieldOption STORES_PAYLOADS = new FieldOption ("STORES_PAYLOADS");
    // all fields which are not indexed
    public static final FieldOption UNINDEXED = new FieldOption ("UNINDEXED");
    // all fields which are indexed with termvectors enables
    public static final FieldOption INDEXED_WITH_TERMVECTOR = new FieldOption ("INDEXED_WITH_TERMVECTOR");
    // all fields which are indexed but don't have termvectors enabled
    public static final FieldOption INDEXED_NO_TERMVECTOR = new FieldOption ("INDEXED_NO_TERMVECTOR");
    // all fields where termvectors are enabled. Please note that only standard termvector fields are returned
    public static final FieldOption TERMVECTOR = new FieldOption ("TERMVECTOR");
    // all field with termvectors wiht positions enabled
    public static final FieldOption TERMVECTOR_WITH_POSITION = new FieldOption ("TERMVECTOR_WITH_POSITION");
    // all fields where termvectors with offset position are set
    public static final FieldOption TERMVECTOR_WITH_OFFSET = new FieldOption ("TERMVECTOR_WITH_OFFSET");
    // all fields where termvectors with offset and position values set
    public static final FieldOption TERMVECTOR_WITH_POSITION_OFFSET = new FieldOption ("TERMVECTOR_WITH_POSITION_OFFSET");
  }

  /**
   * Constructor used if IndexReader is not owner of its directory. 
   * This is used for IndexReaders that are used within other IndexReaders that take care or locking directories.
   * 
   * @param directory Directory where IndexReader files reside.
   */
  protected IndexReader(Directory directory) {
    this.directory = directory;
  }

  /**
   * Constructor used if IndexReader is owner of its directory.
   * If IndexReader is owner of its directory, it locks its directory in case of write operations.
   * 
   * @param directory Directory where IndexReader files reside.
   * @param segmentInfos Used for write-l
   * @param closeDirectory
   */
  IndexReader(Directory directory, SegmentInfos segmentInfos, boolean closeDirectory) {
    init(directory, segmentInfos, closeDirectory, true);
  }

  void init(Directory directory, SegmentInfos segmentInfos, boolean closeDirectory, boolean directoryOwner) {
    this.directory = directory;
    this.segmentInfos = segmentInfos;
    this.directoryOwner = directoryOwner;
    this.closeDirectory = closeDirectory;
  }

  private Directory directory;
  private boolean directoryOwner;
  private boolean closeDirectory;
  private IndexDeletionPolicy deletionPolicy;
  private boolean closed;

  /**
   * @throws AlreadyClosedException if this IndexReader is closed
   */
  protected final void ensureOpen() throws AlreadyClosedException {
    if (closed) {
      throw new AlreadyClosedException("this IndexReader is closed");
    }
  }

  private SegmentInfos segmentInfos;
  private Lock writeLock;
  private boolean stale;
  private boolean hasChanges;

  /** Used by commit() to record pre-commit state in case
   * rollback is necessary */
  private boolean rollbackHasChanges;
  private SegmentInfos rollbackSegmentInfos;

  /** Returns an IndexReader reading the index in an FSDirectory in the named
   path.
   * @throws CorruptIndexException if the index is corrupt
   * @throws IOException if there is a low-level IO error
   * @param path the path to the index directory */
  public static IndexReader open(String path) throws CorruptIndexException, IOException {
    return open(FSDirectory.getDirectory(path), true, null);
  }

  /** Returns an IndexReader reading the index in an FSDirectory in the named
   * path.
   * @param path the path to the index directory
   * @throws CorruptIndexException if the index is corrupt
   * @throws IOException if there is a low-level IO error
   */
  public static IndexReader open(File path) throws CorruptIndexException, IOException {
    return open(FSDirectory.getDirectory(path), true, null);
  }

  /** Returns an IndexReader reading the index in the given Directory.
   * @param directory the index directory
   * @throws CorruptIndexException if the index is corrupt
   * @throws IOException if there is a low-level IO error
   */
  public static IndexReader open(final Directory directory) throws CorruptIndexException, IOException {
    return open(directory, false, null);
  }

  /** Expert: returns an IndexReader reading the index in the given
   * Directory, with a custom {@link IndexDeletionPolicy}.
   * @param directory the index directory
   * @param deletionPolicy a custom deletion policy (only used
   *  if you use this reader to perform deletes or to set
   *  norms); see {@link IndexWriter} for details.
   * @throws CorruptIndexException if the index is corrupt
   * @throws IOException if there is a low-level IO error
   */
  public static IndexReader open(final Directory directory, IndexDeletionPolicy deletionPolicy) throws CorruptIndexException, IOException {
    return open(directory, false, deletionPolicy);
  }

  private static IndexReader open(final Directory directory, final boolean closeDirectory, final IndexDeletionPolicy deletionPolicy) throws CorruptIndexException, IOException {

    return (IndexReader) new SegmentInfos.FindSegmentsFile(directory) {

      protected Object doBody(String segmentFileName) throws CorruptIndexException, IOException {

        SegmentInfos infos = new SegmentInfos();
        infos.read(directory, segmentFileName);

        IndexReader reader;

        if (infos.size() == 1) {		  // index is optimized
          reader = SegmentReader.get(infos, infos.info(0), closeDirectory);
        } else {

          // To reduce the chance of hitting FileNotFound
          // (and having to retry), we open segments in
          // reverse because IndexWriter merges & deletes
          // the newest segments first.

          IndexReader[] readers = new IndexReader[infos.size()];
          for (int i = infos.size()-1; i >= 0; i--) {
            try {
              readers[i] = SegmentReader.get(infos.info(i));
            } catch (IOException e) {
              // Close all readers we had opened:
              for(i++;i<infos.size();i++) {
                readers[i].close();
              }
              throw e;
            }
          }

          reader = new MultiReader(directory, infos, closeDirectory, readers);
        }
        reader.deletionPolicy = deletionPolicy;
        return reader;
      }
    }.run();
  }

  /** Returns the directory this index resides in.
   */
  public Directory directory() {
    ensureOpen();
    return directory;
  }

  /**
   * Returns the time the index in the named directory was last modified.
   * Do not use this to check whether the reader is still up-to-date, use
   * {@link #isCurrent()} instead. 
   * @throws CorruptIndexException if the index is corrupt
   * @throws IOException if there is a low-level IO error
   */
  public static long lastModified(String directory) throws CorruptIndexException, IOException {
    return lastModified(new File(directory));
  }

  /**
   * Returns the time the index in the named directory was last modified. 
   * Do not use this to check whether the reader is still up-to-date, use
   * {@link #isCurrent()} instead. 
   * @throws CorruptIndexException if the index is corrupt
   * @throws IOException if there is a low-level IO error
   */
  public static long lastModified(File fileDirectory) throws CorruptIndexException, IOException {
    return ((Long) new SegmentInfos.FindSegmentsFile(fileDirectory) {
        public Object doBody(String segmentFileName) {
          return new Long(FSDirectory.fileModified(fileDirectory, segmentFileName));
        }
      }.run()).longValue();
  }

  /**
   * Returns the time the index in the named directory was last modified. 
   * Do not use this to check whether the reader is still up-to-date, use
   * {@link #isCurrent()} instead. 
   * @throws CorruptIndexException if the index is corrupt
   * @throws IOException if there is a low-level IO error
   */
  public static long lastModified(final Directory directory2) throws CorruptIndexException, IOException {
    return ((Long) new SegmentInfos.FindSegmentsFile(directory2) {
        public Object doBody(String segmentFileName) throws IOException {
          return new Long(directory2.fileModified(segmentFileName));
        }
      }.run()).longValue();
  }

  /**
   * Reads version number from segments files. The version number is
   * initialized with a timestamp and then increased by one for each change of
   * the index.
   * 
   * @param directory where the index resides.
   * @return version number.
   * @throws CorruptIndexException if the index is corrupt
   * @throws IOException if there is a low-level IO error
   */
  public static long getCurrentVersion(String directory) throws CorruptIndexException, IOException {
    return getCurrentVersion(new File(directory));
  }

  /**
   * Reads version number from segments files. The version number is
   * initialized with a timestamp and then increased by one for each change of
   * the index.
   * 
   * @param directory where the index resides.
   * @return version number.
   * @throws CorruptIndexException if the index is corrupt
   * @throws IOException if there is a low-level IO error
   */
  public static long getCurrentVersion(File directory) throws CorruptIndexException, IOException {
    Directory dir = FSDirectory.getDirectory(directory);
    long version = getCurrentVersion(dir);
    dir.close();
    return version;
  }

  /**
   * Reads version number from segments files. The version number is
   * initialized with a timestamp and then increased by one for each change of
   * the index.
   * 
   * @param directory where the index resides.
   * @return version number.
   * @throws CorruptIndexException if the index is corrupt
   * @throws IOException if there is a low-level IO error
   */
  public static long getCurrentVersion(Directory directory) throws CorruptIndexException, IOException {
    return SegmentInfos.readCurrentVersion(directory);
  }

  /**
   * Version number when this IndexReader was opened.
   */
  public long getVersion() {
    ensureOpen();
    return segmentInfos.getVersion();
  }

  /**
   * Check whether this IndexReader is still using the
   * current (i.e., most recently committed) version of the
   * index.  If a writer has committed any changes to the
   * index since this reader was opened, this will return
   * <code>false</code>, in which case you must open a new