indexreader.java

lucene-2.4.0 是一个全文收索的工具包

      throw new UnsupportedOperationException("This reader does not support this method.");  
    }
  }

  /**
   * Returns the time the index in the named directory was last modified.
   * Do not use this to check whether the reader is still up-to-date, use
   * {@link #isCurrent()} instead. 
   * @throws CorruptIndexException if the index is corrupt
   * @throws IOException if there is a low-level IO error
   */
  public static long lastModified(String directory) throws CorruptIndexException, IOException {
    return lastModified(new File(directory));
  }

  /**
   * Returns the time the index in the named directory was last modified. 
   * Do not use this to check whether the reader is still up-to-date, use
   * {@link #isCurrent()} instead. 
   * @throws CorruptIndexException if the index is corrupt
   * @throws IOException if there is a low-level IO error
   */
  public static long lastModified(File fileDirectory) throws CorruptIndexException, IOException {
    return ((Long) new SegmentInfos.FindSegmentsFile(fileDirectory) {
        public Object doBody(String segmentFileName) {
          return new Long(FSDirectory.fileModified(fileDirectory, segmentFileName));
        }
      }.run()).longValue();
  }

  /**
   * Returns the time the index in the named directory was last modified. 
   * Do not use this to check whether the reader is still up-to-date, use
   * {@link #isCurrent()} instead. 
   * @throws CorruptIndexException if the index is corrupt
   * @throws IOException if there is a low-level IO error
   */
  public static long lastModified(final Directory directory2) throws CorruptIndexException, IOException {
    return ((Long) new SegmentInfos.FindSegmentsFile(directory2) {
        public Object doBody(String segmentFileName) throws IOException {
          return new Long(directory2.fileModified(segmentFileName));
        }
      }.run()).longValue();
  }

  /**
   * Reads version number from segments files. The version number is
   * initialized with a timestamp and then increased by one for each change of
   * the index.
   * 
   * @param directory where the index resides.
   * @return version number.
   * @throws CorruptIndexException if the index is corrupt
   * @throws IOException if there is a low-level IO error
   */
  public static long getCurrentVersion(String directory) throws CorruptIndexException, IOException {
    return getCurrentVersion(new File(directory));
  }

  /**
   * Reads version number from segments files. The version number is
   * initialized with a timestamp and then increased by one for each change of
   * the index.
   * 
   * @param directory where the index resides.
   * @return version number.
   * @throws CorruptIndexException if the index is corrupt
   * @throws IOException if there is a low-level IO error
   */
  public static long getCurrentVersion(File directory) throws CorruptIndexException, IOException {
    Directory dir = FSDirectory.getDirectory(directory);
    long version = getCurrentVersion(dir);
    dir.close();
    return version;
  }

  /**
   * Reads version number from segments files. The version number is
   * initialized with a timestamp and then increased by one for each change of
   * the index.
   * 
   * @param directory where the index resides.
   * @return version number.
   * @throws CorruptIndexException if the index is corrupt
   * @throws IOException if there is a low-level IO error
   */
  public static long getCurrentVersion(Directory directory) throws CorruptIndexException, IOException {
    return SegmentInfos.readCurrentVersion(directory);
  }

  /**
   * Version number when this IndexReader was opened. Not implemented in the IndexReader base class.
   * @throws UnsupportedOperationException unless overridden in subclass
   */
  public long getVersion() {
    throw new UnsupportedOperationException("This reader does not support this method.");
  }

  /**<p>For IndexReader implementations that use
   * TermInfosReader to read terms, this sets the
   * indexDivisor to subsample the number of indexed terms
   * loaded into memory.  This has the same effect as {@link
   * IndexWriter#setTermIndexInterval} except that setting
   * must be done at indexing time while this setting can be
   * set per reader.  When set to N, then one in every
   * N*termIndexInterval terms in the index is loaded into
   * memory.  By setting this to a value > 1 you can reduce
   * memory usage, at the expense of higher latency when
   * loading a TermInfo.  The default value is 1.</p>
   *
   * <b>NOTE:</b> you must call this before the term
   * index is loaded.  If the index is already loaded, 
   * an IllegalStateException is thrown.
   * @throws IllegalStateException if the term index has already been loaded into memory
   */
  public void setTermInfosIndexDivisor(int indexDivisor) throws IllegalStateException {
    throw new UnsupportedOperationException("This reader does not support this method.");
  }

  /** <p>For IndexReader implementations that use
   *  TermInfosReader to read terms, this returns the
   *  current indexDivisor.
   *  @see #setTermInfosIndexDivisor */
  public int getTermInfosIndexDivisor() {
    throw new UnsupportedOperationException("This reader does not support this method.");
  }

  /**
   * Check whether this IndexReader is still using the
   * current (i.e., most recently committed) version of the
   * index.  If a writer has committed any changes to the
   * index since this reader was opened, this will return
   * <code>false</code>, in which case you must open a new
   * IndexReader in order to see the changes.  See the
   * description of the <a href="IndexWriter.html#autoCommit"><code>autoCommit</code></a>
   * flag which controls when the {@link IndexWriter}
   * actually commits changes to the index.
   * 
   * <p>
   * Not implemented in the IndexReader base class.
   * </p>
   * @throws CorruptIndexException if the index is corrupt
   * @throws IOException if there is a low-level IO error
   * @throws UnsupportedOperationException unless overridden in subclass
   */
  public boolean isCurrent() throws CorruptIndexException, IOException {
    throw new UnsupportedOperationException("This reader does not support this method.");
  }

  /**
   * Checks is the index is optimized (if it has a single segment and 
   * no deletions).  Not implemented in the IndexReader base class.
   * @return <code>true</code> if the index is optimized; <code>false</code> otherwise
   * @throws UnsupportedOperationException unless overridden in subclass
   */
  public boolean isOptimized() {
    throw new UnsupportedOperationException("This reader does not support this method.");
  }
  
  /**
   *  Return an array of term frequency vectors for the specified document.
   *  The array contains a vector for each vectorized field in the document.
   *  Each vector contains terms and frequencies for all terms in a given vectorized field.
   *  If no such fields existed, the method returns null. The term vectors that are
   * returned my either be of type TermFreqVector or of type TermPositionsVector if
   * positions or offsets have been stored.
   * 
   * @param docNumber document for which term frequency vectors are returned
   * @return array of term frequency vectors. May be null if no term vectors have been
   *  stored for the specified document.
   * @throws IOException if index cannot be accessed
   * @see org.apache.lucene.document.Field.TermVector
   */
  abstract public TermFreqVector[] getTermFreqVectors(int docNumber)
          throws IOException;


  /**
   *  Return a term frequency vector for the specified document and field. The
   *  returned vector contains terms and frequencies for the terms in
   *  the specified field of this document, if the field had the storeTermVector
   *  flag set. If termvectors had been stored with positions or offsets, a 
   *  TermPositionsVector is returned.
   * 
   * @param docNumber document for which the term frequency vector is returned
   * @param field field for which the term frequency vector is returned.
   * @return term frequency vector May be null if field does not exist in the specified
   * document or term vector was not stored.
   * @throws IOException if index cannot be accessed
   * @see org.apache.lucene.document.Field.TermVector
   */
  abstract public TermFreqVector getTermFreqVector(int docNumber, String field)
          throws IOException;

  /**
   * Load the Term Vector into a user-defined data structure instead of relying on the parallel arrays of
   * the {@link TermFreqVector}.
   * @param docNumber The number of the document to load the vector for
   * @param field The name of the field to load
   * @param mapper The {@link TermVectorMapper} to process the vector.  Must not be null
   * @throws IOException if term vectors cannot be accessed or if they do not exist on the field and doc. specified.
   * 
   */
  abstract public void getTermFreqVector(int docNumber, String field, TermVectorMapper mapper) throws IOException;

  /**
   * Map all the term vectors for all fields in a Document
   * @param docNumber The number of the document to load the vector for
   * @param mapper The {@link TermVectorMapper} to process the vector.  Must not be null
   * @throws IOException if term vectors cannot be accessed or if they do not exist on the field and doc. specified.
   */
  abstract public void getTermFreqVector(int docNumber, TermVectorMapper mapper) throws IOException;

  /**
   * Returns <code>true</code> if an index exists at the specified directory.
   * If the directory does not exist or if there is no index in it.
   * <code>false</code> is returned.
   * @param  directory the directory to check for an index
   * @return <code>true</code> if an index exists; <code>false</code> otherwise
   */
  public static boolean indexExists(String directory) {
    return indexExists(new File(directory));
  }

  /**
   * Returns <code>true</code> if an index exists at the specified directory.
   * If the directory does not exist or if there is no index in it.
   * @param  directory the directory to check for an index
   * @return <code>true</code> if an index exists; <code>false</code> otherwise
   */

  public static boolean indexExists(File directory) {
    return SegmentInfos.getCurrentSegmentGeneration(directory.list()) != -1;
  }

  /**
   * Returns <code>true</code> if an index exists at the specified directory.
   * If the directory does not exist or if there is no index in it.
   * @param  directory the directory to check for an index
   * @return <code>true</code> if an index exists; <code>false</code> otherwise
   * @throws IOException if there is a problem with accessing the index
   */
  public static boolean indexExists(Directory directory) throws IOException {
    return SegmentInfos.getCurrentSegmentGeneration(directory) != -1;
  }

  /** Returns the number of documents in this index. */
  public abstract int numDocs();

  /** Returns one greater than the largest possible document number.
   * This may be used to, e.g., determine how big to allocate an array which
   * will have an element for every document number in an index.
   */
  public abstract int maxDoc();

  /** Returns the number of deleted documents. */
  public int numDeletedDocs() {
    return maxDoc() - numDocs();
  }

  /** Returns the stored fields of the <code>n</code><sup>th</sup>
   <code>Document</code> in this index.
   * @throws CorruptIndexException if the index is corrupt
   * @throws IOException if there is a low-level IO error
   */
  public Document document(int n) throws CorruptIndexException, IOException {
    ensureOpen();
    return document(n, null);
  }

  /**
   * Get the {@link org.apache.lucene.document.Document} at the <code>n</code><sup>th</sup> position. The {@link org.apache.lucene.document.FieldSelector}
   * may be used to determine what {@link org.apache.lucene.document.Field}s to load and how they should be loaded.
   * 
   * <b>NOTE:</b> If this Reader (more specifically, the underlying <code>FieldsReader</code>) is closed before the lazy {@link org.apache.lucene.document.Field} is
   * loaded an exception may be thrown.  If you want the value of a lazy {@link org.apache.lucene.document.Field} to be available after closing you must
   * explicitly load it or fetch the Document again with a new loader.
   * 
   *  
   * @param n Get the document at the <code>n</code><sup>th</sup> position
   * @param fieldSelector The {@link org.apache.lucene.document.FieldSelector} to use to determine what Fields should be loaded on the Document.  May be null, in which case all Fields will be loaded.
   * @return The stored fields of the {@link org.apache.lucene.document.Document} at the nth position
   * @throws CorruptIndexException if the index is corrupt
   * @throws IOException if there is a low-level IO error
   * 
   * @see org.apache.lucene.document.Fieldable
   * @see org.apache.lucene.document.FieldSelector
   * @see org.apache.lucene.document.SetBasedFieldSelector
   * @see org.apache.lucene.document.LoadFirstFieldSelector
   */
  //When we convert to JDK 1.5 make this Set<String>
  public abstract Document document(int n, FieldSelector fieldSelector) throws CorruptIndexException, IOException;
  
  

  /** Returns true if document <i>n</i> has been deleted */
  public abstract boolean isDeleted(int n);

  /** Returns true if any documents have been deleted */
  public abstract boolean hasDeletions();

  /** Returns true if there are norms stored for this field. */
  public boolean hasNorms(String field) throws IOException {
    // backward compatible implementation.
    // SegmentReader has an efficient implementation.
    ensureOpen();
    return norms(field) != null;
  }

  /** Returns the byte-encoded normalization factor for the named field of
   * every document.  This is used by the search code to score documents.
   *
   * @see org.apache.lucene.document.Field#setBoost(float)
   */
  public abstract byte[] norms(String field) throws IOException;

  /** Reads the byte-encoded normalization factor for the named field of every
   *  document.  This is used by the search code to score documents.
   *
   * @see org.apache.lucene.document.Field#setBoost(float)
   */
  public abstract void norms(String field, byte[] bytes, int offset)
    throws IOException;

  /** Expert: Resets the normalization factor for the named field of the named
   * document.  The norm represents the product of the field's {@link
   * org.apache.lucene.document.Fieldable#setBoost(float) boost} and its {@link Similarity#lengthNorm(String,
   * int) length normalization}.  Thus, to preserve the length normalization
   * values when resetting this, one should base the new value upon the old.
   *
   * @see #norms(String)
   * @see Similarity#decodeNorm(byte)
   * @throws StaleReaderException if the index has changed
   *  since this reader was opened
   * @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 there is a low-level IO error
   */
  public synchronized  void setNorm(int doc, String field, byte value)
          throws StaleReaderException, CorruptIndexException, LockObtainFailedException, IOException {
    ensureOpen();
    acquireWriteLock();
    hasChanges = true;
    doSetNorm(doc, field, value);
  }

  /** Implements setNorm in subclass.*/
  protected abstract void doSetNorm(int doc, String field, byte value)
          throws CorruptIndexException, IOException;

  /** Expert: Resets the normalization factor for the named field of the named
   * document.
   *
   * @see #norms(String)
   * @see Similarity#decodeNorm(byte)
   * 
   * @throws StaleReaderException if the index has changed
   *  since this reader was opened
   * @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 there is a low-level IO error
   */
  public void setNorm(int doc, String field, float value)
          throws StaleReaderException, CorruptIndexException, LockObtainFailedException, IOException {
    ensureOpen();