indexwriter.java

中文分词,中科院分词的改装版。使用java调用dll来实现的。

      writeLock = null;
    }
  }

  /** Returns the Directory used by this index. */
  public Directory getDirectory() {
      return directory;
  }

  /** Returns the analyzer used by this index. */
  public Analyzer getAnalyzer() {
      return analyzer;
  }


  /** Returns the number of documents currently in this index. */
  public 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/>
   * Note that this effectively truncates large documents, excluding from the
   * index terms that occur further in the document.  If you know your source
   * documents are large, be sure to set this value high enough to accomodate
   * the expected size.  If you set it to Integer.MAX_VALUE, then the only limit
   * is your memory, but you should anticipate an OutOfMemoryError.<p/>
   * By default, no more than 10,000 terms will be indexed for a field.
   *
   */
  private int maxFieldLength = DEFAULT_MAX_FIELD_LENGTH;

  /**
   * Adds a document to this index.  If the document contains more than
   * {@link #setMaxFieldLength(int)} terms for a given field, the remainder are
   * discarded.
   */
  public void addDocument(Document doc) throws IOException {
    addDocument(doc, analyzer);
  }

  /**
   * Adds a document to this index, using the provided analyzer instead of the
   * value of {@link #getAnalyzer()}.  If the document contains more than
   * {@link #setMaxFieldLength(int)} terms for a given field, the remainder are
   * discarded.
   */
  public void addDocument(Document doc, Analyzer analyzer) throws IOException {
    DocumentWriter dw =
      new DocumentWriter(ramDirectory, analyzer, this);
    dw.setInfoStream(infoStream);
    String segmentName = newSegmentName();
    dw.addDocument(segmentName, doc);
    synchronized (this) {
      segmentInfos.addElement(new SegmentInfo(segmentName, 1, ramDirectory));
      maybeMergeSegments();
    }
  }

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

  /** 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.
   *
   * <p>This must never be less than 2.  The default value is {@link #DEFAULT_MERGE_FACTOR}.

   */
  private int mergeFactor = DEFAULT_MERGE_FACTOR;

  /** Determines the minimal number of documents required before the buffered
   * in-memory documents are merging and a new Segment is created.
   * Since Documents are merged in a {@link org.apache.lucene.store.RAMDirectory},
   * large value gives faster indexing.  At the same time, mergeFactor limits
   * the number of files open in a FSDirectory.
   *
   * <p> The default value is {@link #DEFAULT_MAX_BUFFERED_DOCS}.

   */
  private int minMergeDocs = DEFAULT_MAX_BUFFERED_DOCS;


  /** 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 #DEFAULT_MAX_MERGE_DOCS}.

   */
  private int maxMergeDocs = DEFAULT_MAX_MERGE_DOCS;

  /** If non-null, information about merges will be printed to this.

   */
  private PrintStream infoStream = null;

  /** Merges all segments together into a single segment, optimizing an index
      for search. */
  public synchronized void optimize() throws IOException {
    flushRamSegments();
    while (segmentInfos.size() > 1 ||
           (segmentInfos.size() == 1 &&
            (SegmentReader.hasDeletions(segmentInfos.info(0)) ||
             segmentInfos.info(0).dir != directory ||
             (useCompoundFile &&
              (!SegmentReader.usesCompoundFile(segmentInfos.info(0)) ||
                SegmentReader.hasSeparateNorms(segmentInfos.info(0))))))) {
      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 synchronized void addIndexes(Directory[] dirs)
      throws IOException {
    optimize();					  // start with zero or 1 seg

    int start = segmentInfos.size();

    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
      }
    }
    
    // merge newly added segments in log(n) passes
    while (segmentInfos.size() > start+mergeFactor) {
      for (int base = start; base < segmentInfos.size(); base++) {
        int end = Math.min(segmentInfos.size(), base+mergeFactor);
        if (end-base > 1)
          mergeSegments(base, end);
      }
    }

    optimize();					  // final cleanup
  }

  /** Merges the provided indexes into this index.
   * <p>After this completes, the index is optimized. </p>
   * <p>The provided IndexReaders are not closed.</p>
   */
  public synchronized void addIndexes(IndexReader[] readers)
    throws IOException {

    optimize();					  // start with zero or 1 seg

    final String mergedName = newSegmentName();
    SegmentMerger merger = new SegmentMerger(this, mergedName);

    final Vector segmentsToDelete = new Vector();
    IndexReader sReader = null;
    if (segmentInfos.size() == 1){ // add existing index, if any
        sReader = SegmentReader.get(segmentInfos.info(0));
        merger.add(sReader);
        segmentsToDelete.addElement(sReader);   // queue segment for deletion
    }
      
    for (int i = 0; i < readers.length; i++)      // add new indexes
      merger.add(readers[i]);

    int docCount = merger.merge();                // merge 'em

    segmentInfos.setSize(0);                      // pop old infos & add new
    segmentInfos.addElement(new SegmentInfo(mergedName, docCount, directory));
    
    if(sReader != null)
        sReader.close();

    synchronized (directory) {			  // in- & inter-process sync
      new Lock.With(directory.makeLock(COMMIT_LOCK_NAME), commitLockTimeout) {
	  public Object doBody() throws IOException {
	    segmentInfos.write(directory);	  // commit changes
	    return null;
	  }
	}.run();
    }
    
    deleteSegments(segmentsToDelete);  // delete now-unused segments

    if (useCompoundFile) {
      final Vector filesToDelete = merger.createCompoundFile(mergedName + ".tmp");
      synchronized (directory) { // in- & inter-process sync
        new Lock.With(directory.makeLock(COMMIT_LOCK_NAME), commitLockTimeout) {
          public Object doBody() throws IOException {
            // make compound file visible for SegmentReaders
            directory.renameFile(mergedName + ".tmp", mergedName + ".cfs");
            return null;
          }
        }.run();
      }

      // delete now unused files of segment 
      deleteFiles(filesToDelete);   
    }
  }

  /** 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 = minMergeDocs;
    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 {
    mergeSegments(minSegment, segmentInfos.size());
  }

  /** Merges the named range of segments, replacing them in the stack with a
   * single segment. */
  private final void mergeSegments(int minSegment, int end)
    throws IOException {
    final String mergedName = newSegmentName();
    if (infoStream != null) infoStream.print("merging segments");
    SegmentMerger merger = new SegmentMerger(this, mergedName);

    final Vector segmentsToDelete = new Vector();
    for (int i = minSegment; i < end; i++) {
      SegmentInfo si = segmentInfos.info(i);
      if (infoStream != null)
        infoStream.print(" " + si.name + " (" + si.docCount + " docs)");
      IndexReader reader = SegmentReader.get(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
    }

    int mergedDocCount = merger.merge();

    if (infoStream != null) {
      infoStream.println(" into "+mergedName+" ("+mergedDocCount+" docs)");
    }

    for (int i = end-1; i > minSegment; i--)     // remove old infos & add new
      segmentInfos.remove(i);
    segmentInfos.set(minSegment, new SegmentInfo(mergedName, mergedDocCount,
                                            directory));

    // close readers before we attempt to delete now-obsolete segments
    merger.closeReaders();

    synchronized (directory) {                 // in- & inter-process sync
      new Lock.With(directory.makeLock(COMMIT_LOCK_NAME), commitLockTimeout) {
          public Object doBody() throws IOException {
            segmentInfos.write(directory);     // commit before deleting
            return null;
          }
        }.run();
    }
    
    deleteSegments(segmentsToDelete);  // delete now-unused segments

    if (useCompoundFile) {
      final Vector filesToDelete = merger.createCompoundFile(mergedName + ".tmp");
      synchronized (directory) { // in- & inter-process sync
        new Lock.With(directory.makeLock(COMMIT_LOCK_NAME), commitLockTimeout) {
          public Object doBody() throws IOException {
            // make compound file visible for SegmentReaders
            directory.renameFile(mergedName + ".tmp", mergedName + ".cfs");
            return null;
          }
        }.run();
      }

      // delete now unused files of segment 
      deleteFiles(filesToDelete);   
    }
  }

  /*
   * 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 other files
    }

    writeDeleteableFiles(deletable);		  // note files we can't delete
  }
  
  private final void deleteFiles(Vector files) throws IOException {
    Vector deletable = new Vector();
    deleteFiles(readDeleteableFiles(), deletable); // try to delete deleteable
    deleteFiles(files, deletable);     // try to delete our 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.toString() + "; Will re-try later.");
          deletable.addElement(file);		  // add to deletable
        }
      }
    }
  }

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

    IndexInput input = directory.openInput(IndexFileNames.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 {
    IndexOutput output = directory.createOutput("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", IndexFileNames.DELETABLE);
  }
}