indexwriter.java

Lucene a java open-source SearchEngine Framework

   *  <p>Note that this method is a convenience method: it
   *  just calls mergePolicy.getUseCompoundFile as long as
   *  mergePolicy is an instance of {@link LogMergePolicy}.
   *  Otherwise an IllegalArgumentException is thrown.</p>
   *
   *  @see #setUseCompoundFile(boolean)
   */
  public boolean getUseCompoundFile() {
    return getLogMergePolicy().getUseCompoundFile();
  }

  /** <p>Setting to turn on usage of a compound file. When on,
   *  multiple files for each segment are merged into a
   *  single file when a new segment is flushed.</p>
   *
   *  <p>Note that this method is a convenience method: it
   *  just calls mergePolicy.setUseCompoundFile as long as
   *  mergePolicy is an instance of {@link LogMergePolicy}.
   *  Otherwise an IllegalArgumentException is thrown.</p>
   */
  public void setUseCompoundFile(boolean value) {
    getLogMergePolicy().setUseCompoundFile(value);
    getLogMergePolicy().setUseCompoundDocStore(value);
  }

  /** Expert: Set the Similarity implementation used by this IndexWriter.
   *
   * @see Similarity#setDefault(Similarity)
   */
  public void setSimilarity(Similarity similarity) {
    ensureOpen();
    this.similarity = similarity;
  }

  /** Expert: Return the Similarity implementation used by this IndexWriter.
   *
   * <p>This defaults to the current value of {@link Similarity#getDefault()}.
   */
  public Similarity getSimilarity() {
    ensureOpen();
    return this.similarity;
  }

  /** Expert: Set the interval between indexed terms.  Large values cause less
   * memory to be used by IndexReader, but slow random-access to terms.  Small
   * values cause more memory to be used by an IndexReader, and speed
   * random-access to terms.
   *
   * This parameter determines the amount of computation required per query
   * term, regardless of the number of documents that contain that term.  In
   * particular, it is the maximum number of other terms that must be
   * scanned before a term is located and its frequency and position information
   * may be processed.  In a large index with user-entered query terms, query
   * processing time is likely to be dominated not by term lookup but rather
   * by the processing of frequency and positional data.  In a small index
   * or when many uncommon query terms are generated (e.g., by wildcard
   * queries) term lookup may become a dominant cost.
   *
   * In particular, <code>numUniqueTerms/interval</code> terms are read into
   * memory by an IndexReader, and, on average, <code>interval/2</code> terms
   * must be scanned for each random term access.
   *
   * @see #DEFAULT_TERM_INDEX_INTERVAL
   */
  public void setTermIndexInterval(int interval) {
    ensureOpen();
    this.termIndexInterval = interval;
  }

  /** Expert: Return the interval between indexed terms.
   *
   * @see #setTermIndexInterval(int)
   */
  public int getTermIndexInterval() {
    ensureOpen();
    return termIndexInterval;
  }

  /**
   * 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(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;
    setMessageID();

    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();