package org.apache.lucene.index;/** * Copyright 2004 The Apache Software Foundation * * Licensed 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.Field;import org.apache.lucene.search.Similarity;import org.apache.lucene.store.Directory;import org.apache.lucene.store.FSDirectory;import org.apache.lucene.store.IndexInput;import org.apache.lucene.store.Lock;import java.io.File;import java.io.FileOutputStream;import java.io.IOException;import java.util.Arrays;import java.util.Collection;/** IndexReader is an abstract class, providing an interface for accessing an index.  Search of an index is done entirely through this abstract interface, so that any subclass which implements it is searchable. <p> Concrete subclasses of IndexReader are usually constructed with a call to one of the static <code>open()</code> methods, e.g. {@link #open(String)}. <p> For efficiency, in this API documents are often referred to via <i>document numbers</i>, non-negative integers which each name a unique document in the index.  These document numbers are ephemeral--they may change as documents are added to and deleted from an index.  Clients should thus not rely on a given document having the same number between sessions.  <p> An IndexReader can be opened on a directory for which an IndexWriter is opened already, but it cannot be used to delete documents from the index then. @author Doug Cutting @version $Id: IndexReader.java 400187 2006-05-05 21:47:58Z dnaber $*/public abstract class IndexReader {    public static final class FieldOption {    private String option;    private FieldOption() { }    private FieldOption(String option) {      this.option = option;    }     public String toString() {      return this.option;    }    // all fields    public static final FieldOption ALL = new FieldOption ("ALL");    // all indexed fields    public static final FieldOption INDEXED = new FieldOption ("INDEXED");    // all fields which are not indexed    public static final FieldOption UNINDEXED = new FieldOption ("UNINDEXED");    // all fields which are indexed with termvectors enables    public static final FieldOption INDEXED_WITH_TERMVECTOR = new FieldOption ("INDEXED_WITH_TERMVECTOR");    // all fields which are indexed but don't have termvectors enabled    public static final FieldOption INDEXED_NO_TERMVECTOR = new FieldOption ("INDEXED_NO_TERMVECTOR");    // all fields where termvectors are enabled. Please note that only standard termvector fields are returned    public static final FieldOption TERMVECTOR = new FieldOption ("TERMVECTOR");    // all field with termvectors wiht positions enabled    public static final FieldOption TERMVECTOR_WITH_POSITION = new FieldOption ("TERMVECTOR_WITH_POSITION");    // all fields where termvectors with offset position are set    public static final FieldOption TERMVECTOR_WITH_OFFSET = new FieldOption ("TERMVECTOR_WITH_OFFSET");    // all fields where termvectors with offset and position values set    public static final FieldOption TERMVECTOR_WITH_POSITION_OFFSET = new FieldOption ("TERMVECTOR_WITH_POSITION_OFFSET");  }    /**   * Constructor used if IndexReader is not owner of its directory.    * This is used for IndexReaders that are used within other IndexReaders that take care or locking directories.   *    * @param directory Directory where IndexReader files reside.   */  protected IndexReader(Directory directory) {    this.directory = directory;  }    /**   * Constructor used if IndexReader is owner of its directory.   * If IndexReader is owner of its directory, it locks its directory in case of write operations.   *    * @param directory Directory where IndexReader files reside.   * @param segmentInfos Used for write-l   * @param closeDirectory   */  IndexReader(Directory directory, SegmentInfos segmentInfos, boolean closeDirectory) {    init(directory, segmentInfos, closeDirectory, true);  }  void init(Directory directory, SegmentInfos segmentInfos, boolean closeDirectory, boolean directoryOwner) {    this.directory = directory;    this.segmentInfos = segmentInfos;    this.directoryOwner = directoryOwner;    this.closeDirectory = closeDirectory;  }  private Directory directory;  private boolean directoryOwner;  private boolean closeDirectory;  private SegmentInfos segmentInfos;  private Lock writeLock;  private boolean stale;  private boolean hasChanges;    /** Returns an IndexReader reading the index in an FSDirectory in the named   path. */  public static IndexReader open(String path) throws IOException {    return open(FSDirectory.getDirectory(path, false), true);  }  /** Returns an IndexReader reading the index in an FSDirectory in the named   path. */  public static IndexReader open(File path) throws IOException {    return open(FSDirectory.getDirectory(path, false), true);  }    /** Returns an IndexReader reading the index in the given Directory. */  public static IndexReader open(final Directory directory) throws IOException {    return open(directory, false);  }  private static IndexReader open(final Directory directory, final boolean closeDirectory) throws IOException {    synchronized (directory) {			  // in- & inter-process sync      return (IndexReader)new Lock.With(          directory.makeLock(IndexWriter.COMMIT_LOCK_NAME),          IndexWriter.COMMIT_LOCK_TIMEOUT) {          public Object doBody() throws IOException {            SegmentInfos infos = new SegmentInfos();            infos.read(directory);            if (infos.size() == 1) {		  // index is optimized              return SegmentReader.get(infos, infos.info(0), closeDirectory);            }            IndexReader[] readers = new IndexReader[infos.size()];            for (int i = 0; i < infos.size(); i++)              readers[i] = SegmentReader.get(infos.info(i));            return new MultiReader(directory, infos, closeDirectory, readers);                      }        }.run();    }  }  /** Returns the directory this index resides in. */  public Directory directory() { return 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.    */  public static long lastModified(String directory) throws 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.    */  public static long lastModified(File directory) throws IOException {    return FSDirectory.fileModified(directory, IndexFileNames.SEGMENTS);  }  /**    * 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.    */  public static long lastModified(Directory directory) throws IOException {    return directory.fileModified(IndexFileNames.SEGMENTS);  }  /**   * 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 IOException if segments file cannot be read   */  public static long getCurrentVersion(String directory) throws 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 IOException if segments file cannot be read   */  public static long getCurrentVersion(File directory) throws IOException {    Directory dir = FSDirectory.getDirectory(directory, false);    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 IOException if segments file cannot be read.   */  public static long getCurrentVersion(Directory directory) throws IOException {    synchronized (directory) {                 // in- & inter-process sync      Lock commitLock=directory.makeLock(IndexWriter.COMMIT_LOCK_NAME);            boolean locked=false;            try {         locked=commitLock.obtain(IndexWriter.COMMIT_LOCK_TIMEOUT);                  return SegmentInfos.readCurrentVersion(directory);      } finally {        if (locked) {          commitLock.release();        }      }    }  }    /**   * Version number when this IndexReader was opened.   */  public long getVersion() {    return segmentInfos.getVersion();  }  /**   * Check whether this IndexReader still works on a current version of the index.   * If this is not the case you will need to re-open the IndexReader to   * make sure you see the latest changes made to the index.   *    * @throws IOException   */  public boolean isCurrent() throws IOException {    synchronized (directory) {                 // in- & inter-process sync      Lock commitLock=directory.makeLock(IndexWriter.COMMIT_LOCK_NAME);            boolean locked=false;            try {         locked=commitLock.obtain(IndexWriter.COMMIT_LOCK_TIMEOUT);                  return SegmentInfos.readCurrentVersion(directory) == segmentInfos.getVersion();      } finally {        if (locked) {          commitLock.release();        }      }    }  }  /**   *  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;   /**   * 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 (new File(directory, IndexFileNames.SEGMENTS)).exists();  }  /**   * 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 (new File(directory, IndexFileNames.SEGMENTS)).exists();  }  /**   * 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 directory.fileExists(IndexFileNames.SEGMENTS);  }  /** 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 stored fields of the <code>n</code><sup>th</sup>   <code>Document</code> in this index. */  public abstract Document document(int n) throws 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.    return norms(field) != null;  }  /** Returns the byte-encoded normalization factor for the named field of