segmentreader.java

lucene2.2.0版本

package org.apache.lucene.index;

/**
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

import org.apache.lucene.document.Document;
import org.apache.lucene.document.FieldSelector;
import org.apache.lucene.search.DefaultSimilarity;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.IndexInput;
import org.apache.lucene.store.IndexOutput;
import org.apache.lucene.store.BufferedIndexInput;
import org.apache.lucene.util.BitVector;

import java.io.IOException;
import java.util.*;

/**
 * @version $Id: SegmentReader.java 542561 2007-05-29 15:14:07Z mikemccand $
 */
class SegmentReader extends IndexReader {
  private String segment;
  private SegmentInfo si;

  FieldInfos fieldInfos;
  private FieldsReader fieldsReader;

  TermInfosReader tis;
  TermVectorsReader termVectorsReaderOrig = null;
  ThreadLocal termVectorsLocal = new ThreadLocal();

  BitVector deletedDocs = null;
  private boolean deletedDocsDirty = false;
  private boolean normsDirty = false;
  private boolean undeleteAll = false;

  private boolean rollbackDeletedDocsDirty = false;
  private boolean rollbackNormsDirty = false;
  private boolean rollbackUndeleteAll = false;

  IndexInput freqStream;
  IndexInput proxStream;

  // optionally used for the .nrm file shared by multiple norms
  private IndexInput singleNormStream;

  // Compound File Reader when based on a compound file segment
  CompoundFileReader cfsReader = null;

  private class Norm {
    public Norm(IndexInput in, int number, long normSeek)
    {
      this.in = in;
      this.number = number;
      this.normSeek = normSeek;
    }

    private IndexInput in;
    private byte[] bytes;
    private boolean dirty;
    private int number;
    private long normSeek;
    private boolean rollbackDirty;

    private void reWrite(SegmentInfo si) throws IOException {
      // NOTE: norms are re-written in regular directory, not cfs
      si.advanceNormGen(this.number);
      IndexOutput out = directory().createOutput(si.getNormFileName(this.number));
      try {
        out.writeBytes(bytes, maxDoc());
      } finally {
        out.close();
      }
      this.dirty = false;
    }

    /** Closes the underlying IndexInput for this norm.
     * It is still valid to access all other norm properties after close is called.
     * @throws IOException
     */
    public void close() throws IOException {
      if (in != null && in != singleNormStream) {
        in.close();
      }
      in = null;
    }
  }

  private Hashtable norms = new Hashtable();

  /** The class which implements SegmentReader. */
  private static Class IMPL;
  static {
    try {
      String name =
        System.getProperty("org.apache.lucene.SegmentReader.class",
                           SegmentReader.class.getName());
      IMPL = Class.forName(name);
    } catch (ClassNotFoundException e) {
      throw new RuntimeException("cannot load SegmentReader class: " + e, e);
    } catch (SecurityException se) {
      try {
        IMPL = Class.forName(SegmentReader.class.getName());
      } catch (ClassNotFoundException e) {
        throw new RuntimeException("cannot load default SegmentReader class: " + e, e);
      }
    }
  }

  protected SegmentReader() { super(null); }

  /**
   * @throws CorruptIndexException if the index is corrupt
   * @throws IOException if there is a low-level IO error
   */
  public static SegmentReader get(SegmentInfo si) throws CorruptIndexException, IOException {
    return get(si.dir, si, null, false, false, BufferedIndexInput.BUFFER_SIZE);
  }

  /**
   * @throws CorruptIndexException if the index is corrupt
   * @throws IOException if there is a low-level IO error
   */
  public static SegmentReader get(SegmentInfo si, int readBufferSize) throws CorruptIndexException, IOException {
    return get(si.dir, si, null, false, false, readBufferSize);
  }

  /**
   * @throws CorruptIndexException if the index is corrupt
   * @throws IOException if there is a low-level IO error
   */
  public static SegmentReader get(SegmentInfos sis, SegmentInfo si,
                                  boolean closeDir) throws CorruptIndexException, IOException {
    return get(si.dir, si, sis, closeDir, true, BufferedIndexInput.BUFFER_SIZE);
  }

  /**
   * @throws CorruptIndexException if the index is corrupt
   * @throws IOException if there is a low-level IO error
   */
  public static SegmentReader get(Directory dir, SegmentInfo si,
                                  SegmentInfos sis,
                                  boolean closeDir, boolean ownDir,
                                  int readBufferSize)
    throws CorruptIndexException, IOException {
    SegmentReader instance;
    try {
      instance = (SegmentReader)IMPL.newInstance();
    } catch (Exception e) {
      throw new RuntimeException("cannot load SegmentReader class: " + e, e);
    }
    instance.init(dir, sis, closeDir, ownDir);
    instance.initialize(si, readBufferSize);
    return instance;
  }

  private void initialize(SegmentInfo si, int readBufferSize) throws CorruptIndexException, IOException {
    segment = si.name;
    this.si = si;

    boolean success = false;

    try {
      // Use compound file directory for some files, if it exists
      Directory cfsDir = directory();
      if (si.getUseCompoundFile()) {
        cfsReader = new CompoundFileReader(directory(), segment + ".cfs", readBufferSize);
        cfsDir = cfsReader;
      }

      // No compound file exists - use the multi-file format
      fieldInfos = new FieldInfos(cfsDir, segment + ".fnm");
      fieldsReader = new FieldsReader(cfsDir, segment, fieldInfos, readBufferSize);

      // Verify two sources of "maxDoc" agree:
      if (fieldsReader.size() != si.docCount) {
        throw new CorruptIndexException("doc counts differ for segment " + si.name + ": fieldsReader shows " + fieldsReader.size() + " but segmentInfo shows " + si.docCount);
      }

      tis = new TermInfosReader(cfsDir, segment, fieldInfos, readBufferSize);
      
      // NOTE: the bitvector is stored using the regular directory, not cfs
      if (hasDeletions(si)) {
        deletedDocs = new BitVector(directory(), si.getDelFileName());

        // Verify # deletes does not exceed maxDoc for this segment:
        if (deletedDocs.count() > maxDoc()) {
          throw new CorruptIndexException("number of deletes (" + deletedDocs.count() + ") exceeds max doc (" + maxDoc() + ") for segment " + si.name);
        }
      }

      // make sure that all index files have been read or are kept open
      // so that if an index update removes them we'll still have them
      freqStream = cfsDir.openInput(segment + ".frq", readBufferSize);
      proxStream = cfsDir.openInput(segment + ".prx", readBufferSize);
      openNorms(cfsDir, readBufferSize);

      if (fieldInfos.hasVectors()) { // open term vector files only as needed
        termVectorsReaderOrig = new TermVectorsReader(cfsDir, segment, fieldInfos, readBufferSize);
      }
      success = true;
    } finally {

      // With lock-less commits, it's entirely possible (and
      // fine) to hit a FileNotFound exception above.  In
      // this case, we want to explicitly close any subset
      // of things that were opened so that we don't have to
      // wait for a GC to do so.
      if (!success) {
        doClose();
      }
    }
  }

  protected void doCommit() throws IOException {
    if (deletedDocsDirty) {               // re-write deleted
      si.advanceDelGen();

      // We can write directly to the actual name (vs to a
      // .tmp & renaming it) because the file is not live
      // until segments file is written:
      deletedDocs.write(directory(), si.getDelFileName());
    }
    if (undeleteAll && si.hasDeletions()) {
      si.clearDelGen();
    }
    if (normsDirty) {               // re-write norms
      si.setNumFields(fieldInfos.size());
      Enumeration values = norms.elements();
      while (values.hasMoreElements()) {
        Norm norm = (Norm) values.nextElement();
        if (norm.dirty) {
          norm.reWrite(si);
        }
      }
    }
    deletedDocsDirty = false;
    normsDirty = false;
    undeleteAll = false;
  }

  protected void doClose() throws IOException {
    if (fieldsReader != null) {
      fieldsReader.close();
    }
    if (tis != null) {
      tis.close();
    }

    if (freqStream != null)
      freqStream.close();
    if (proxStream != null)
      proxStream.close();

    closeNorms();

    if (termVectorsReaderOrig != null)
      termVectorsReaderOrig.close();

    if (cfsReader != null)
      cfsReader.close();
  }

  static boolean hasDeletions(SegmentInfo si) throws IOException {
    // Don't call ensureOpen() here (it could affect performance)
    return si.hasDeletions();
  }

  public boolean hasDeletions() {
    // Don't call ensureOpen() here (it could affect performance)
    return deletedDocs != null;
  }

  static boolean usesCompoundFile(SegmentInfo si) throws IOException {
    return si.getUseCompoundFile();
  }

  static boolean hasSeparateNorms(SegmentInfo si) throws IOException {
    return si.hasSeparateNorms();
  }

  protected void doDelete(int docNum) {
    if (deletedDocs == null)
      deletedDocs = new BitVector(maxDoc());
    deletedDocsDirty = true;
    undeleteAll = false;
    deletedDocs.set(docNum);
  }

  protected void doUndeleteAll() {
      deletedDocs = null;
      deletedDocsDirty = false;
      undeleteAll = true;
  }

  Vector files() throws IOException {
    return new Vector(si.files());
  }

  public TermEnum terms() {
    ensureOpen();
    return tis.terms();
  }

  public TermEnum terms(Term t) throws IOException {
    ensureOpen();