indexwriter.java

lucene2.2.0版本

   * @param path the path to the index directory
   * @param a the analyzer to use
   * @param create <code>true</code> to create the index or overwrite
   *  the existing one; <code>false</code> to append to the existing
   *  index
   * @throws CorruptIndexException if the index is corrupt
   * @throws LockObtainFailedException if another writer
   *  has this index open (<code>write.lock</code> could not
   *  be obtained)
   * @throws IOException if the directory cannot be read/written to, or
   *  if it does not exist and <code>create</code> is
   *  <code>false</code> or if there is any other low-level
   *  IO error
   */
  public IndexWriter(String path, Analyzer a, boolean create)
       throws CorruptIndexException, LockObtainFailedException, IOException {
    init(FSDirectory.getDirectory(path), a, create, true, null, true);
  }

  /**
   * 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.
   *
   * @param path the path to the index directory
   * @param a the analyzer to use
   * @param create <code>true</code> to create the index or overwrite
   *  the existing one; <code>false</code> to append to the existing
   *  index
   * @throws CorruptIndexException if the index is corrupt
   * @throws LockObtainFailedException if another writer
   *  has this index open (<code>write.lock</code> could not
   *  be obtained)
   * @throws IOException if the directory cannot be read/written to, or
   *  if it does not exist and <code>create</code> is
   *  <code>false</code> or if there is any other low-level
   *  IO error
   */
  public IndexWriter(File path, Analyzer a, boolean create)
       throws CorruptIndexException, LockObtainFailedException, IOException {
    init(FSDirectory.getDirectory(path), a, create, true, null, true);
  }

  /**
   * 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.
   *
   * @param d the index directory
   * @param a the analyzer to use
   * @param create <code>true</code> to create the index or overwrite
   *  the existing one; <code>false</code> to append to the existing
   *  index
   * @throws CorruptIndexException if the index is corrupt
   * @throws LockObtainFailedException if another writer
   *  has this index open (<code>write.lock</code> could not
   *  be obtained)
   * @throws IOException if the directory cannot be read/written to, or
   *  if it does not exist and <code>create</code> is
   *  <code>false</code> or if there is any other low-level
   *  IO error
   */
  public IndexWriter(Directory d, Analyzer a, boolean create)
       throws CorruptIndexException, LockObtainFailedException, IOException {
    init(d, a, create, false, null, true);
  }

  /**
   * Constructs an IndexWriter for the index in
   * <code>path</code>, first creating it if it does not
   * already exist.  Text will be analyzed with
   * <code>a</code>.
   *
   * @param path the path to the index directory
   * @param a the analyzer to use
   * @throws CorruptIndexException if the index is corrupt
   * @throws LockObtainFailedException if another writer
   *  has this index open (<code>write.lock</code> could not
   *  be obtained)
   * @throws IOException if the directory cannot be
   *  read/written to or if there is any other low-level
   *  IO error
   */
  public IndexWriter(String path, Analyzer a) 
    throws CorruptIndexException, LockObtainFailedException, IOException {
    init(FSDirectory.getDirectory(path), a, true, null, true);
  }

  /**
   * Constructs an IndexWriter for the index in
   * <code>path</code>, first creating it if it does not
   * already exist.  Text will be analyzed with
   * <code>a</code>.
   *
   * @param path the path to the index directory
   * @param a the analyzer to use
   * @throws CorruptIndexException if the index is corrupt
   * @throws LockObtainFailedException if another writer
   *  has this index open (<code>write.lock</code> could not
   *  be obtained)
   * @throws IOException if the directory cannot be
   *  read/written to or if there is any other low-level
   *  IO error
   */
  public IndexWriter(File path, Analyzer a) 
    throws CorruptIndexException, LockObtainFailedException, IOException {
    init(FSDirectory.getDirectory(path), a, true, null, true);
  }

  /**
   * Constructs an IndexWriter for the index in
   * <code>d</code>, first creating it if it does not
   * already exist.  Text will be analyzed with
   * <code>a</code>.
   *
   * @param d the index directory
   * @param a the analyzer to use
   * @throws CorruptIndexException if the index is corrupt
   * @throws LockObtainFailedException if another writer
   *  has this index open (<code>write.lock</code> could not
   *  be obtained)
   * @throws IOException if the directory cannot be
   *  read/written to or if there is any other low-level
   *  IO error
   */
  public IndexWriter(Directory d, Analyzer a) 
    throws CorruptIndexException, LockObtainFailedException, IOException {
    init(d, a, false, null, true);
  }

  /**
   * Constructs an IndexWriter for the index in
   * <code>d</code>, first creating it if it does not
   * already exist.  Text will be analyzed with
   * <code>a</code>.
   *
   * @param d the index directory
   * @param autoCommit see <a href="#autoCommit">above</a>
   * @param a the analyzer to use
   * @throws CorruptIndexException if the index is corrupt
   * @throws LockObtainFailedException if another writer
   *  has this index open (<code>write.lock</code> could not
   *  be obtained)
   * @throws IOException if the directory cannot be
   *  read/written to or if there is any other low-level
   *  IO error
   */
  public IndexWriter(Directory d, boolean autoCommit, Analyzer a) 
    throws CorruptIndexException, LockObtainFailedException, IOException {
    init(d, a, false, null, autoCommit);
  }

  /**
   * 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.
   *
   * @param d the index directory
   * @param autoCommit see <a href="#autoCommit">above</a>
   * @param a the analyzer to use
   * @param create <code>true</code> to create the index or overwrite
   *  the existing one; <code>false</code> to append to the existing
   *  index
   * @throws CorruptIndexException if the index is corrupt
   * @throws LockObtainFailedException if another writer
   *  has this index open (<code>write.lock</code> could not
   *  be obtained)
   * @throws IOException if the directory cannot be read/written to, or
   *  if it does not exist and <code>create</code> is
   *  <code>false</code> or if there is any other low-level
   *  IO error
   */
  public IndexWriter(Directory d, boolean autoCommit, Analyzer a, boolean create)
       throws CorruptIndexException, LockObtainFailedException, IOException {
    init(d, a, create, false, null, autoCommit);
  }

  /**
   * Expert: constructs an IndexWriter with a custom {@link
   * IndexDeletionPolicy}, for the index in <code>d</code>,
   * first creating it if it does not already exist.  Text
   * will be analyzed with <code>a</code>.
   *
   * @param d the index directory
   * @param autoCommit see <a href="#autoCommit">above</a>
   * @param a the analyzer to use
   * @param deletionPolicy see <a href="#deletionPolicy">above</a>
   * @throws CorruptIndexException if the index is corrupt
   * @throws LockObtainFailedException if another writer
   *  has this index open (<code>write.lock</code> could not
   *  be obtained)
   * @throws IOException if the directory cannot be
   *  read/written to or if there is any other low-level
   *  IO error
   */
  public IndexWriter(Directory d, boolean autoCommit, Analyzer a, IndexDeletionPolicy deletionPolicy) 
    throws CorruptIndexException, LockObtainFailedException, IOException {
    init(d, a, false, deletionPolicy, autoCommit);
  }

  /**
   * Expert: constructs an IndexWriter with a custom {@link
   * IndexDeletionPolicy}, 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.
   *
   * @param d the index directory
   * @param autoCommit see <a href="#autoCommit">above</a>
   * @param a the analyzer to use
   * @param create <code>true</code> to create the index or overwrite
   *  the existing one; <code>false</code> to append to the existing
   *  index
   * @param deletionPolicy see <a href="#deletionPolicy">above</a>
   * @throws CorruptIndexException if the index is corrupt
   * @throws LockObtainFailedException if another writer
   *  has this index open (<code>write.lock</code> could not
   *  be obtained)
   * @throws IOException if the directory cannot be read/written to, or
   *  if it does not exist and <code>create</code> is
   *  <code>false</code> or if there is any other low-level
   *  IO error
   */
  public IndexWriter(Directory d, boolean autoCommit, Analyzer a, boolean create, IndexDeletionPolicy deletionPolicy)
       throws CorruptIndexException, LockObtainFailedException, IOException {
    init(d, a, create, false, deletionPolicy, autoCommit);
  }

  private void init(Directory d, Analyzer a, boolean closeDir, IndexDeletionPolicy deletionPolicy, boolean autoCommit)
    throws CorruptIndexException, LockObtainFailedException, IOException {
    if (IndexReader.indexExists(d)) {
      init(d, a, false, closeDir, deletionPolicy, autoCommit);
    } else {
      init(d, a, true, closeDir, deletionPolicy, autoCommit);
    }
  }

  private void init(Directory d, Analyzer a, final boolean create, boolean closeDir, IndexDeletionPolicy deletionPolicy, boolean autoCommit)
    throws CorruptIndexException, LockObtainFailedException, IOException {
    this.closeDir = closeDir;
    directory = d;
    analyzer = a;
    this.infoStream = defaultInfoStream;

    if (create) {
      // Clear the write lock in case it's leftover:
      directory.clearLock(IndexWriter.WRITE_LOCK_NAME);
    }

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

    try {
      if (create) {
        // Try to read first.  This is to allow create
        // against an index that's currently open for
        // searching.  In this case we write the next
        // segments_N file with no segments:
        try {
          segmentInfos.read(directory);
          segmentInfos.clear();
        } catch (IOException e) {
          // Likely this means it's a fresh directory
        }
        segmentInfos.write(directory);
      } else {
        segmentInfos.read(directory);
      }

      this.autoCommit = autoCommit;
      if (!autoCommit) {
        rollbackSegmentInfos = (SegmentInfos) segmentInfos.clone();
      }

      // Default deleter (for backwards compatibility) is
      // KeepOnlyLastCommitDeleter:
      deleter = new IndexFileDeleter(directory,
                                     deletionPolicy == null ? new KeepOnlyLastCommitDeletionPolicy() : deletionPolicy,
                                     segmentInfos, infoStream);

    } catch (IOException e) {
      this.writeLock.release();
      this.writeLock = null;
      throw e;
    }
  }

  /** 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 void setMaxMergeDocs(int maxMergeDocs) {
    ensureOpen();
    this.maxMergeDocs = maxMergeDocs;
  }

  /**
   * Returns the largest number of documents allowed in a
   * single segment.
   * @see #setMaxMergeDocs
   */
  public int getMaxMergeDocs() {
    ensureOpen();
    return maxMergeDocs;
  }

  /**
   * 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.
   */
  public void setMaxFieldLength(int maxFieldLength) {
    ensureOpen();
    this.maxFieldLength = maxFieldLength;
  }

  /**
   * Returns the maximum number of terms that will be
   * indexed for a single field in a document.
   * @see #setMaxFieldLength
   */
  public int getMaxFieldLength() {
    ensureOpen();
    return maxFieldLength;
  }

  /** Determines the minimal number of documents required before the buffered