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

  public int mergeFactor = 10;

  /** Determines the 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.
   *
   * <p>The default value is {@link Integer#MAX_VALUE}. */
  public int maxMergeDocs = Integer.MAX_VALUE;

  /** If non-null, information about merges will be printed to this. */
  public PrintStream infoStream = null;

  /** Merges all segments together into a single segment, optimizing an index
      for search. */
  public final synchronized void optimize() throws IOException {
    flushRamSegments();
    while (segmentInfos.size() > 1 ||
	   (segmentInfos.size() == 1 &&
	    (SegmentReader.hasDeletions(segmentInfos.info(0)) ||
             segmentInfos.info(0).dir != directory))) {
      int minSegment = segmentInfos.size() - mergeFactor;
      mergeSegments(minSegment < 0 ? 0 : minSegment);
    }
  }

  /** Merges all segments from an array of indexes into this index.
   *
   * <p>This may be used to parallelize batch indexing.  A large document
   * collection can be broken into sub-collections.  Each sub-collection can be
   * indexed in parallel, on a different thread, process or machine.  The
   * complete index can then be created by merging sub-collection indexes
   * with this method.
   *
   * <p>After this completes, the index is optimized. */
  public final synchronized void addIndexes(Directory[] dirs)
      throws IOException {
    optimize();					  // start with zero or 1 seg
    for (int i = 0; i < dirs.length; i++) {
      SegmentInfos sis = new SegmentInfos();	  // read infos from dir
      sis.read(dirs[i]);
      for (int j = 0; j < sis.size(); j++) {
	segmentInfos.addElement(sis.info(j));	  // add each info
      }
    }
    optimize();					  // final cleanup
  }

  /** Merges all RAM-resident segments. */
  private final void flushRamSegments() throws IOException {
    int minSegment = segmentInfos.size()-1;
    int docCount = 0;
    while (minSegment >= 0 &&
	   (segmentInfos.info(minSegment)).dir == ramDirectory) {
      docCount += segmentInfos.info(minSegment).docCount;
      minSegment--;
    }
    if (minSegment < 0 ||			  // add one FS segment?
	(docCount + segmentInfos.info(minSegment).docCount) > mergeFactor ||
	!(segmentInfos.info(segmentInfos.size()-1).dir == ramDirectory))
      minSegment++;
    if (minSegment >= segmentInfos.size())
      return;					  // none to merge
    mergeSegments(minSegment);
  }

  /** Incremental segment merger.  */
  private final void maybeMergeSegments() throws IOException {
    long targetMergeDocs = mergeFactor;
    while (targetMergeDocs <= maxMergeDocs) {
      // find segments smaller than current target size
      int minSegment = segmentInfos.size();
      int mergeDocs = 0;
      while (--minSegment >= 0) {
	SegmentInfo si = segmentInfos.info(minSegment);
	if (si.docCount >= targetMergeDocs)
	  break;
	mergeDocs += si.docCount;
      }

      if (mergeDocs >= targetMergeDocs)		  // found a merge to do
	mergeSegments(minSegment+1);
      else
	break;
      
      targetMergeDocs *= mergeFactor;		  // increase target size
    }
  }

  /** Pops segments off of segmentInfos stack down to minSegment, merges them,
    and pushes the merged index onto the top of the segmentInfos stack. */
  private final void mergeSegments(int minSegment)
      throws IOException {
    String mergedName = newSegmentName();
    int mergedDocCount = 0;
    if (infoStream != null) infoStream.print("merging segments");
    SegmentMerger merger = new SegmentMerger(directory, mergedName);
    final Vector segmentsToDelete = new Vector();
    for (int i = minSegment; i < segmentInfos.size(); i++) {
      SegmentInfo si = segmentInfos.info(i);
      if (infoStream != null)
	infoStream.print(" " + si.name + " (" + si.docCount + " docs)");
      SegmentReader reader = new SegmentReader(si);
      merger.add(reader);
      if ((reader.directory == this.directory) || // if we own the directory
          (reader.directory == this.ramDirectory))
	segmentsToDelete.addElement(reader);	  // queue segment for deletion
      mergedDocCount += si.docCount;
    }
    if (infoStream != null) {
      infoStream.println();
      infoStream.println(" into "+mergedName+" ("+mergedDocCount+" docs)");
    }
    merger.merge();

    segmentInfos.setSize(minSegment);		  // pop old infos & add new
    segmentInfos.addElement(new SegmentInfo(mergedName, mergedDocCount,
					    directory));
    
    synchronized (directory) {			  // in- & inter-process sync
      new Lock.With(directory.makeLock("commit.lock")) {
	  public Object doBody() throws IOException {
	    segmentInfos.write(directory);	  // commit before deleting
	    deleteSegments(segmentsToDelete);	  // delete now-unused segments
	    return null;
	  }
	}.run();
    }
  }

  /* Some operating systems (e.g. Windows) don't permit a file to be deleted
     while it is opened for read (e.g. by another process or thread).  So we
     assume that when a delete fails it is because the file is open in another
     process, and queue the file for subsequent deletion. */

  private final void deleteSegments(Vector segments) throws IOException {
    Vector deletable = new Vector();

    deleteFiles(readDeleteableFiles(), deletable); // try to delete deleteable
    
    for (int i = 0; i < segments.size(); i++) {
      SegmentReader reader = (SegmentReader)segments.elementAt(i);
      if (reader.directory == this.directory)
	deleteFiles(reader.files(), deletable);	  // try to delete our files
      else
	deleteFiles(reader.files(), reader.directory); // delete, eg, RAM files
    }

    writeDeleteableFiles(deletable);		  // note files we can't delete
  }

  private final void deleteFiles(Vector files, Directory directory)
       throws IOException {
    for (int i = 0; i < files.size(); i++)
      directory.deleteFile((String)files.elementAt(i));
  }

  private final void deleteFiles(Vector files, Vector deletable)
       throws IOException {
    for (int i = 0; i < files.size(); i++) {
      String file = (String)files.elementAt(i);
      try {
	directory.deleteFile(file);		  // try to delete each file
      } catch (IOException e) {			  // if delete fails
	if (directory.fileExists(file)) {
	  if (infoStream != null)
	    infoStream.println(e.getMessage() + "; Will re-try later.");
	  deletable.addElement(file);		  // add to deletable
	}
      }
    }
  }

  private final Vector readDeleteableFiles() throws IOException {
    Vector result = new Vector();
    if (!directory.fileExists("deletable"))
      return result;

    InputStream input = directory.openFile("deletable");
    try {
      for (int i = input.readInt(); i > 0; i--)	  // read file names
	result.addElement(input.readString());
    } finally {
      input.close();
    }
    return result;
  }

  private final void writeDeleteableFiles(Vector files) throws IOException {
    OutputStream output = directory.createFile("deleteable.new");
    try {
      output.writeInt(files.size());
      for (int i = 0; i < files.size(); i++)
	output.writeString((String)files.elementAt(i));
    } finally {
      output.close();
    }
    directory.renameFile("deleteable.new", "deletable");
  }
}