indexwriter.java

天乙代码src_531.rar 天乙代码src_531.rar 天乙代码src_531.rar 天乙代码src_531.rar

package org.apache.lucene.index;

/* ====================================================================
 * The Apache Software License, Version 1.1
 *
 * Copyright (c) 2001 The Apache Software Foundation.  All rights
 * reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 *
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 *
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in
 *    the documentation and/or other materials provided with the
 *    distribution.
 *
 * 3. The end-user documentation included with the redistribution,
 *    if any, must include the following acknowledgment:
 *       "This product includes software developed by the
 *        Apache Software Foundation (http://www.apache.org/)."
 *    Alternately, this acknowledgment may appear in the software itself,
 *    if and wherever such third-party acknowledgments normally appear.
 *
 * 4. The names "Apache" and "Apache Software Foundation" and
 *    "Apache Lucene" must not be used to endorse or promote products
 *    derived from this software without prior written permission. For
 *    written permission, please contact [e-mail].
 *
 * 5. Products derived from this software may not be called "Apache",
 *    "Apache Lucene", nor may "Apache" appear in their name, without
 *    prior written permission of the Apache Software Foundation.
 *
 * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
 * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
 * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
 * DISCLAIMED.  IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
 * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
 * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
 * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
 * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
 * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 * ====================================================================
 *
 * This software consists of voluntary contributions made by many
 * individuals on behalf of the Apache Software Foundation.  For more
 * information on the Apache Software Foundation, please see
 * <http://www.apache.org/>.
 */

import java.io.IOException;
import java.io.File;
import java.io.PrintStream;
import java.util.Vector;

import org.apache.lucene.store.Directory;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.store.Lock;
import org.apache.lucene.store.InputStream;
import org.apache.lucene.store.OutputStream;
import org.apache.lucene.document.Document;
import org.apache.lucene.analysis.Analyzer;

/**
  An IndexWriter creates and maintains an index.

  The third argument to the <a href="#IndexWriter"><b>constructor</b></a>
  determines whether a new index is created, or whether an existing index is
  opened for the addition of new documents.

  In either case, documents are added with the <a
  href="#addDocument"><b>addDocument</b></a> method.  When finished adding
  documents, <a href="#close"><b>close</b></a> should be called.

  If an index will not have more documents added for a while and optimal search
  performance is desired, then the <a href="#optimize"><b>optimize</b></a>
  method should be called before the index is closed.
  */

public final class IndexWriter {
  private Directory directory;			  // where this index resides
  private Analyzer analyzer;			  // how to analyze text

  private SegmentInfos segmentInfos = new SegmentInfos(); // the segments
  private final Directory ramDirectory = new RAMDirectory(); // for temp segs

  private Lock writeLock;

  /** Constructs an IndexWriter for the index in <code>path</code>.  Text will
    be analyzed with <code>a</code>.  If <code>create</code> is true, then a
    new, empty index will be created in <code>path</code>, replacing the index
    already there, if any. */
  public IndexWriter(String path, Analyzer a, boolean create)
       throws IOException {
    this(FSDirectory.getDirectory(path, create), a, create);
  }

  /** Constructs an IndexWriter for the index in <code>path</code>.  Text will
    be analyzed with <code>a</code>.  If <code>create</code> is true, then a
    new, empty index will be created in <code>path</code>, replacing the index
    already there, if any. */
  public IndexWriter(File path, Analyzer a, boolean create)
       throws IOException {
    this(FSDirectory.getDirectory(path, create), a, create);
  }

  /** Constructs an IndexWriter for the index in <code>d</code>.  Text will be
    analyzed with <code>a</code>.  If <code>create</code> is true, then a new,
    empty index will be created in <code>d</code>, replacing the index already
    there, if any. */
  public IndexWriter(Directory d, Analyzer a, final boolean create)
       throws IOException {
    directory = d;
    analyzer = a;

    Lock writeLock = directory.makeLock("write.lock");
    if (!writeLock.obtain())                      // obtain write lock
      throw new IOException("Index locked for write: " + writeLock);
    this.writeLock = writeLock;                   // save it

    synchronized (directory) {			  // in- & inter-process sync
      new Lock.With(directory.makeLock("commit.lock")) {
	  public Object doBody() throws IOException {
	    if (create)
	      segmentInfos.write(directory);
	    else
	      segmentInfos.read(directory);
	    return null;
	  }
	}.run();
    }
  }

  /** Flushes all changes to an index, closes all associated files, and closes
    the directory that the index is stored in. */
  public final synchronized void close() throws IOException {
    flushRamSegments();
    ramDirectory.close();
    writeLock.release();                          // release write lock
    writeLock = null;
    directory.close();
  }

  /** Release the write lock, if needed. */
  protected final void finalize() throws IOException {
    if (writeLock != null) {
      writeLock.release();                        // release write lock
      writeLock = null;
    }
  }

  /** Returns the number of documents currently in this index. */
  public final synchronized int docCount() {
    int count = 0;
    for (int i = 0; i < segmentInfos.size(); i++) {
      SegmentInfo si = segmentInfos.info(i);
      count += si.docCount;
    }
    return count;
  }

  /** The maximum number of terms that will be indexed for a single field in a
    document.  This limits the amount of memory required for indexing, so that
    collections with very large files will not crash the indexing process by
    running out of memory.

    <p>By default, no more than 10,000 terms will be indexed for a field. */
  public int maxFieldLength = 10000;

  /** Adds a document to this index.*/
  public final void addDocument(Document doc) throws IOException {
    DocumentWriter dw =
      new DocumentWriter(ramDirectory, analyzer, maxFieldLength);
    String segmentName = newSegmentName();
    dw.addDocument(segmentName, doc);
    synchronized (this) {
      segmentInfos.addElement(new SegmentInfo(segmentName, 1, ramDirectory));
      maybeMergeSegments();
    }
  }

  private final synchronized String newSegmentName() {
    return "_" + Integer.toString(segmentInfos.counter++, Character.MAX_RADIX);
  }

  /** Determines how often segment indexes are merged by addDocument().  With
   * smaller values, less RAM is used while indexing, and searches on
   * unoptimized indexes are faster, but indexing speed is slower.  With larger
   * values more RAM is used while indexing and searches on unoptimized indexes
   * are slower, but indexing is faster.  Thus larger values (> 10) are best
   * for batched index creation, and smaller values (< 10) for indexes that are
   * interactively maintained.
   *
   * <p>This must never be less than 2.  The default value is 10.*/