indexreader.java

lucene完整源码

   * every document.  This is used by the search code to score documents.
   *
   * @see 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 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
   * Field#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)
   */
  public final synchronized  void setNorm(int doc, String field, byte value)
          throws IOException{
    if(directoryOwner)
      aquireWriteLock();
    doSetNorm(doc, field, value);
    hasChanges = true;
  }
          
  /** Implements setNorm in subclass.*/
  protected abstract void doSetNorm(int doc, String field, byte value) 
          throws IOException;

  /** Expert: Resets the normalization factor for the named field of the named
   * document.
   *
   * @see #norms(String)
   * @see Similarity#decodeNorm(byte)
   */
  public void setNorm(int doc, String field, float value)
          throws IOException {
    setNorm(doc, field, Similarity.encodeNorm(value));
  }

  /** Returns an enumeration of all the terms in the index.
   * The enumeration is ordered by Term.compareTo().  Each term
   * is greater than all that precede it in the enumeration.
   */
  public abstract TermEnum terms() throws IOException;

  /** Returns an enumeration of all terms after a given term.
   * The enumeration is ordered by Term.compareTo().  Each term
   * is greater than all that precede it in the enumeration.
   */
  public abstract TermEnum terms(Term t) throws IOException;

  /** Returns the number of documents containing the term <code>t</code>. */
  public abstract int docFreq(Term t) throws IOException;

  /** Returns an enumeration of all the documents which contain
   * <code>term</code>. For each document, the document number, the frequency of
   * the term in that document is also provided, for use in search scoring.
   * Thus, this method implements the mapping:
   * <p><ul>
   * Term &nbsp;&nbsp; =&gt; &nbsp;&nbsp; &lt;docNum, freq&gt;<sup>*</sup>
   * </ul>
   * <p>The enumeration is ordered by document number.  Each document number
   * is greater than all that precede it in the enumeration.
   */
  public TermDocs termDocs(Term term) throws IOException {
    TermDocs termDocs = termDocs();
    termDocs.seek(term);
    return termDocs;
  }

  /** Returns an unpositioned {@link TermDocs} enumerator. */
  public abstract TermDocs termDocs() throws IOException;

  /** Returns an enumeration of all the documents which contain
   * <code>term</code>.  For each document, in addition to the document number
   * and frequency of the term in that document, a list of all of the ordinal
   * positions of the term in the document is available.  Thus, this method
   * implements the mapping:
   *
   * <p><ul>
   * Term &nbsp;&nbsp; =&gt; &nbsp;&nbsp; &lt;docNum, freq,
   * &lt;pos<sub>1</sub>, pos<sub>2</sub>, ...
   * pos<sub>freq-1</sub>&gt;
   * &gt;<sup>*</sup>
   * </ul>
   * <p> This positional information faciliates phrase and proximity searching.
   * <p>The enumeration is ordered by document number.  Each document number is
   * greater than all that precede it in the enumeration.
   */
  public TermPositions termPositions(Term term) throws IOException {
    TermPositions termPositions = termPositions();
    termPositions.seek(term);
    return termPositions;
  }

  /** Returns an unpositioned {@link TermPositions} enumerator. */
  public abstract TermPositions termPositions() throws IOException;

  /**
   * Tries to acquire the WriteLock on this directory.
   * this method is only valid if this IndexReader is directory owner.
   * 
   * @throws IOException If WriteLock cannot be acquired.
   */
  private void aquireWriteLock() throws IOException {
    if (stale)
      throw new IOException("IndexReader out of date and no longer valid for delete, undelete, or setNorm operations");

    if (writeLock == null) {
      Lock writeLock = directory.makeLock(IndexWriter.WRITE_LOCK_NAME);
      if (!writeLock.obtain(IndexWriter.WRITE_LOCK_TIMEOUT)) // obtain write lock
        throw new IOException("Index locked for write: " + writeLock);
      this.writeLock = writeLock;

      // we have to check whether index has changed since this reader was opened.
      // if so, this reader is no longer valid for deletion
      if (SegmentInfos.readCurrentVersion(directory) > segmentInfos.getVersion()) {
        stale = true;
        this.writeLock.release();
        this.writeLock = null;
        throw new IOException("IndexReader out of date and no longer valid for delete, undelete, or setNorm operations");
      }
    }
  }


  /** Deletes the document numbered <code>docNum</code>.  Once a document is
   * deleted it will not appear in TermDocs or TermPostitions enumerations.
   * Attempts to read its field with the {@link #document}
   * method will result in an error.  The presence of this document may still be
   * reflected in the {@link #docFreq} statistic, though
   * this will be corrected eventually as the index is further modified.
   */
  public final synchronized void deleteDocument(int docNum) throws IOException {
    if(directoryOwner)
      aquireWriteLock();
    doDelete(docNum);
    hasChanges = true;
  }


  /** Implements deletion of the document numbered <code>docNum</code>.
   * Applications should call {@link #deleteDocument(int)} or {@link #deleteDocuments(Term)}.
   */
  protected abstract void doDelete(int docNum) throws IOException;


  /** Deletes all documents containing <code>term</code>.
   * This is useful if one uses a document field to hold a unique ID string for
   * the document.  Then to delete such a document, one merely constructs a
   * term with the appropriate field and the unique ID string as its text and
   * passes it to this method.
   * See {@link #deleteDocument(int)} for information about when this deletion will 
   * become effective.
   * @return the number of documents deleted
   */
  public final int deleteDocuments(Term term) throws IOException {
    TermDocs docs = termDocs(term);
    if (docs == null) return 0;
    int n = 0;
    try {
      while (docs.next()) {
        deleteDocument(docs.doc());
        n++;
      }
    } finally {
      docs.close();
    }
    return n;
  }

  /** Undeletes all documents currently marked as deleted in this index.*/
  public final synchronized void undeleteAll() throws IOException{
    if(directoryOwner)
      aquireWriteLock();
    doUndeleteAll();
    hasChanges = true;
  }
  
  /** Implements actual undeleteAll() in subclass. */
  protected abstract void doUndeleteAll() throws IOException;

  /**
   * Commit changes resulting from delete, undeleteAll, or setNorm operations
   * 
   * @throws IOException
   */
  protected final synchronized void commit() throws IOException{
    if(hasChanges){
      if(directoryOwner){
        synchronized (directory) {      // in- & inter-process sync
           new Lock.With(directory.makeLock(IndexWriter.COMMIT_LOCK_NAME),
                   IndexWriter.COMMIT_LOCK_TIMEOUT) {
             public Object doBody() throws IOException {
               doCommit();
               segmentInfos.write(directory);
               return null;
             }
           }.run();
         }
        if (writeLock != null) {
          writeLock.release();  // release write lock
          writeLock = null;
        }
      }
      else
        doCommit();
    }
    hasChanges = false;
  }
  
  /** Implements commit. */
  protected abstract void doCommit() throws IOException;
  
  /**
   * Closes files associated with this index.
   * Also saves any new deletions to disk.
   * No other methods should be called after this has been called.
   */
  public final synchronized void close() throws IOException {
    commit();
    doClose();
    if(closeDirectory)
      directory.close();
  }

  /** Implements close. */
  protected abstract void doClose() throws IOException;

  /** Release the write lock, if needed. */
  protected void finalize() {
    if (writeLock != null) {
      writeLock.release();                        // release write lock
      writeLock = null;
    }
  }

  
  /**
   * Get a list of unique field names that exist in this index and have the specified
   * field option information.
   * @param fldOption specifies which field option should be available for the returned fields
   * @return Collection of Strings indicating the names of the fields.
   * @see IndexReader.FieldOption
   */
  public abstract Collection getFieldNames(FieldOption fldOption);

  /**
   * Returns <code>true</code> iff the index in the named directory is
   * currently locked.
   * @param directory the directory to check for a lock
   * @throws IOException if there is a problem with accessing the index
   */
  public static boolean isLocked(Directory directory) throws IOException {
    return
            directory.makeLock(IndexWriter.WRITE_LOCK_NAME).isLocked() ||
            directory.makeLock(IndexWriter.COMMIT_LOCK_NAME).isLocked();
  }

  /**
   * Returns <code>true</code> iff the index in the named directory is
   * currently locked.
   * @param directory the directory to check for a lock
   * @throws IOException if there is a problem with accessing the index
   */
  public static boolean isLocked(String directory) throws IOException {
    Directory dir = FSDirectory.getDirectory(directory, false);
    boolean result = isLocked(dir);
    dir.close();
    return result;
  }

  /**
   * Forcibly unlocks the index in the named directory.
   * <P>
   * Caution: this should only be used by failure recovery code,
   * when it is known that no other process nor thread is in fact
   * currently accessing this index.
   */
  public static void unlock(Directory directory) throws IOException {
    directory.makeLock(IndexWriter.WRITE_LOCK_NAME).release();
    directory.makeLock(IndexWriter.COMMIT_LOCK_NAME).release();
  }
  
  /**
   * Prints the filename and size of each file within a given compound file.
   * Add the -extract flag to extract files to the current working directory.
   * In order to make the extracted version of the index work, you have to copy
   * the segments file from the compound index into the directory where the extracted files are stored.
   * @param args Usage: org.apache.lucene.index.IndexReader [-extract] &lt;cfsfile&gt;
   */
  public static void main(String [] args) {
    String filename = null;
    boolean extract = false;

    for (int i = 0; i < args.length; ++i) {
      if (args[i].equals("-extract")) {
        extract = true;
      } else if (filename == null) {
        filename = args[i];
      }
    }

    if (filename == null) {
      System.out.println("Usage: org.apache.lucene.index.IndexReader [-extract] <cfsfile>");
      return;
    }

    Directory dir = null;
    CompoundFileReader cfr = null;
      
    try {
      File file = new File(filename);
      String dirname = file.getAbsoluteFile().getParent();
      filename = file.getName();
      dir = FSDirectory.getDirectory(dirname, false);
      cfr = new CompoundFileReader(dir, filename);

      String [] files = cfr.list();
      Arrays.sort(files);   // sort the array of filename so that the output is more readable
      
      for (int i = 0; i < files.length; ++i) {
        long len = cfr.fileLength(files[i]);

        if (extract) {
          System.out.println("extract " + files[i] + " with " + len + " bytes to local directory...");
          IndexInput ii = cfr.openInput(files[i]);

          FileOutputStream f = new FileOutputStream(files[i]);
          
          // read and write with a small buffer, which is more effectiv than reading byte by byte
          byte[] buffer = new byte[1024];
          int chunk = buffer.length;
          while(len > 0) {
            final int bufLen = (int) Math.min(chunk, len);
            ii.readBytes(buffer, 0, bufLen);
            f.write(buffer, 0, bufLen);
            len -= bufLen;
          }
          
          f.close();
          ii.close();
        }
        else
          System.out.println(files[i] + ": " + len + " bytes");
      }
    } catch (IOException ioe) {
      ioe.printStackTrace();
    }
    finally {
      try {
        if (dir != null)
          dir.close();
        if (cfr != null)
          cfr.close();
      }
      catch (IOException ioe) {
        ioe.printStackTrace();
      }
    }
  }
}