segmentreader.java

一套java版本的搜索引擎源码

    } else {
      for (int i = 0; i < IndexFileNames.INDEX_EXTENSIONS.length; i++) {
        String name = segment + "." + IndexFileNames.INDEX_EXTENSIONS[i];
        if (directory().fileExists(name))
          files.addElement(name);
      }
    }

    if (si.hasDeletions()) {
      files.addElement(si.getDelFileName());
    }

    boolean addedNrm = false;
    for (int i = 0; i < fieldInfos.size(); i++) {
      String name = si.getNormFileName(i);
      if (name != null && directory().fileExists(name)) {
        if (name.endsWith("." + IndexFileNames.NORMS_EXTENSION)) {
          if (addedNrm) continue; // add .nrm just once
          addedNrm = true;
        }
        files.addElement(name);
      }
    }
    return files;
  }

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

  public TermEnum terms(Term t) throws IOException {
    return tis.terms(t);
  }

  public synchronized Document document(int n, FieldSelector fieldSelector) throws IOException {
    if (isDeleted(n))
      throw new IllegalArgumentException
              ("attempt to access a deleted document");
    return fieldsReader.doc(n, fieldSelector);
  }

  public synchronized boolean isDeleted(int n) {
    return (deletedDocs != null && deletedDocs.get(n));
  }

  public TermDocs termDocs() throws IOException {
    return new SegmentTermDocs(this);
  }

  public TermPositions termPositions() throws IOException {
    return new SegmentTermPositions(this);
  }

  public int docFreq(Term t) throws IOException {
    TermInfo ti = tis.get(t);
    if (ti != null)
      return ti.docFreq;
    else
      return 0;
  }

  public int numDocs() {
    int n = maxDoc();
    if (deletedDocs != null)
      n -= deletedDocs.count();
    return n;
  }

  public int maxDoc() {
    return si.docCount;
  }

  /**
   * @see IndexReader#getFieldNames(IndexReader.FieldOption fldOption)
   */
  public Collection getFieldNames(IndexReader.FieldOption fieldOption) {

    Set fieldSet = new HashSet();
    for (int i = 0; i < fieldInfos.size(); i++) {
      FieldInfo fi = fieldInfos.fieldInfo(i);
      if (fieldOption == IndexReader.FieldOption.ALL) {
        fieldSet.add(fi.name);
      }
      else if (!fi.isIndexed && fieldOption == IndexReader.FieldOption.UNINDEXED) {
        fieldSet.add(fi.name);
      }
      else if (fi.isIndexed && fieldOption == IndexReader.FieldOption.INDEXED) {
        fieldSet.add(fi.name);
      }
      else if (fi.isIndexed && fi.storeTermVector == false && fieldOption == IndexReader.FieldOption.INDEXED_NO_TERMVECTOR) {
        fieldSet.add(fi.name);
      }
      else if (fi.storeTermVector == true &&
               fi.storePositionWithTermVector == false &&
               fi.storeOffsetWithTermVector == false &&
               fieldOption == IndexReader.FieldOption.TERMVECTOR) {
        fieldSet.add(fi.name);
      }
      else if (fi.isIndexed && fi.storeTermVector && fieldOption == IndexReader.FieldOption.INDEXED_WITH_TERMVECTOR) {
        fieldSet.add(fi.name);
      }
      else if (fi.storePositionWithTermVector && fi.storeOffsetWithTermVector == false && fieldOption == IndexReader.FieldOption.TERMVECTOR_WITH_POSITION) {
        fieldSet.add(fi.name);
      }
      else if (fi.storeOffsetWithTermVector && fi.storePositionWithTermVector == false && fieldOption == IndexReader.FieldOption.TERMVECTOR_WITH_OFFSET) {
        fieldSet.add(fi.name);
      }
      else if ((fi.storeOffsetWithTermVector && fi.storePositionWithTermVector) &&
                fieldOption == IndexReader.FieldOption.TERMVECTOR_WITH_POSITION_OFFSET) {
        fieldSet.add(fi.name);
      }
    }
    return fieldSet;
  }


  public synchronized boolean hasNorms(String field) {
    return norms.containsKey(field);
  }

  static byte[] createFakeNorms(int size) {
    byte[] ones = new byte[size];
    Arrays.fill(ones, DefaultSimilarity.encodeNorm(1.0f));
    return ones;
  }

  private byte[] ones;
  private byte[] fakeNorms() {
    if (ones==null) ones=createFakeNorms(maxDoc());
    return ones;
  }

  // can return null if norms aren't stored
  protected synchronized byte[] getNorms(String field) throws IOException {
    Norm norm = (Norm) norms.get(field);
    if (norm == null) return null;  // not indexed, or norms not stored
    if (norm.bytes == null) {                     // value not yet read
      byte[] bytes = new byte[maxDoc()];
      norms(field, bytes, 0);
      norm.bytes = bytes;                         // cache it
    }
    return norm.bytes;
  }

  // returns fake norms if norms aren't available
  public synchronized byte[] norms(String field) throws IOException {
    byte[] bytes = getNorms(field);
    if (bytes==null) bytes=fakeNorms();
    return bytes;
  }

  protected void doSetNorm(int doc, String field, byte value)
          throws IOException {
    Norm norm = (Norm) norms.get(field);
    if (norm == null)                             // not an indexed field
      return;
    norm.dirty = true;                            // mark it dirty
    normsDirty = true;

    norms(field)[doc] = value;                    // set the value
  }

  /** Read norms into a pre-allocated array. */
  public synchronized void norms(String field, byte[] bytes, int offset)
    throws IOException {

    Norm norm = (Norm) norms.get(field);
    if (norm == null) {
      System.arraycopy(fakeNorms(), 0, bytes, offset, maxDoc());
      return;
    }

    if (norm.bytes != null) {                     // can copy from cache
      System.arraycopy(norm.bytes, 0, bytes, offset, maxDoc());
      return;
    }

    IndexInput normStream = (IndexInput) norm.in.clone();
    try {                                         // read from disk
      normStream.seek(norm.normSeek);
      normStream.readBytes(bytes, offset, maxDoc());
    } finally {
      normStream.close();
    }
  }


  private void openNorms(Directory cfsDir) throws IOException {
    long nextNormSeek = SegmentMerger.NORMS_HEADER.length; //skip header (header unused for now)
    int maxDoc = maxDoc();
    for (int i = 0; i < fieldInfos.size(); i++) {
      FieldInfo fi = fieldInfos.fieldInfo(i);
      if (fi.isIndexed && !fi.omitNorms) {
        Directory d = directory();
        String fileName = si.getNormFileName(fi.number);
        if (!si.hasSeparateNorms(fi.number)) {
          d = cfsDir;
        }
        long normSeek = (fileName.endsWith("." + IndexFileNames.NORMS_EXTENSION) ? nextNormSeek : 0);
        norms.put(fi.name, new Norm(d.openInput(fileName), fi.number, normSeek));
        nextNormSeek += maxDoc; // increment also if some norms are separate
      }
    }
  }

  private void closeNorms() throws IOException {
    synchronized (norms) {
      Enumeration enumerator = norms.elements();
      while (enumerator.hasMoreElements()) {
        Norm norm = (Norm) enumerator.nextElement();
        norm.in.close();
      }
    }
  }
  
  /**
   * Create a clone from the initial TermVectorsReader and store it in the ThreadLocal.
   * @return TermVectorsReader
   */
  private TermVectorsReader getTermVectorsReader() {
    TermVectorsReader tvReader = (TermVectorsReader)termVectorsLocal.get();
    if (tvReader == null) {
      tvReader = (TermVectorsReader)termVectorsReaderOrig.clone();
      termVectorsLocal.set(tvReader);
    }
    return tvReader;
  }
  
  /** Return a term frequency vector for the specified document and field. The
   *  vector returned contains term numbers and frequencies for all terms in
   *  the specified field of this document, if the field had storeTermVector
   *  flag set.  If the flag was not set, the method returns null.
   * @throws IOException
   */
  public TermFreqVector getTermFreqVector(int docNumber, String field) throws IOException {
    // Check if this field is invalid or has no stored term vector
    FieldInfo fi = fieldInfos.fieldInfo(field);
    if (fi == null || !fi.storeTermVector || termVectorsReaderOrig == null) 
      return null;
    
    TermVectorsReader termVectorsReader = getTermVectorsReader();
    if (termVectorsReader == null)
      return null;
    
    return termVectorsReader.get(docNumber, field);
  }


  /** 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 vector contains term numbers and frequencies for all terms
   *  in a given vectorized field.
   *  If no such fields existed, the method returns null.
   * @throws IOException
   */
  public TermFreqVector[] getTermFreqVectors(int docNumber) throws IOException {
    if (termVectorsReaderOrig == null)
      return null;
    
    TermVectorsReader termVectorsReader = getTermVectorsReader();
    if (termVectorsReader == null)
      return null;
    
    return termVectorsReader.get(docNumber);
  }

  /**
   * Return the name of the segment this reader is reading.
   */
  String getSegmentName() {
    return segment;
  }

  void setSegmentInfo(SegmentInfo info) {
    si = info;
  }

  void startCommit() {
    super.startCommit();
    rollbackDeletedDocsDirty = deletedDocsDirty;
    rollbackNormsDirty = normsDirty;
    rollbackUndeleteAll = undeleteAll;
    Enumeration values = norms.elements();
    while (values.hasMoreElements()) {
      Norm norm = (Norm) values.nextElement();
      norm.rollbackDirty = norm.dirty;
    }
  }

  void rollbackCommit() {
    super.rollbackCommit();
    deletedDocsDirty = rollbackDeletedDocsDirty;
    normsDirty = rollbackNormsDirty;
    undeleteAll = rollbackUndeleteAll;
    Enumeration values = norms.elements();
    while (values.hasMoreElements()) {
      Norm norm = (Norm) values.nextElement();
      norm.dirty = norm.rollbackDirty;
    }
  }
}