File	Doc	Category	Size	Date	Package
IndexReader.java	API Doc	Apache Lucene 1.4.3	22305	Wed Apr 21 18:46:30 BST 2004	org.apache.lucene.index

IndexReader

• java.lang.Object

Fields Summary
private final Directory	directory
private final boolean	directoryOwner
private final SegmentInfos	segmentInfos
private Lock	writeLock
private boolean	stale
private boolean	hasChanges
private final boolean	closeDirectory

Constructors Summary
protected IndexReader(Directory directory) 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. this.directory = directory; segmentInfos = null; directoryOwner = false; closeDirectory = false; stale = false; hasChanges = false; writeLock = null;
IndexReader(Directory directory, SegmentInfos segmentInfos, boolean closeDirectory) 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 this.directory = directory; this.segmentInfos = segmentInfos; directoryOwner = true; this.closeDirectory = closeDirectory; stale = false; hasChanges = false; writeLock = null;

Methods Summary
private void	aquireWriteLock() Trys 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. if (stale) throw new IOException("IndexReader out of date and no longer valid for delete, undelete, or setNorm operations"); if (writeLock == null) { Lock writeLock = directory.makeLock(IndexWriter.WRITE_LOCK_NAME); if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 // if so, this reader is no longer valid for deletion if (SegmentInfos.readCurrentVersion(directory) 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{ stale = true; this.writeLock.release(); this.writeLock = null; throw new IOException("IndexReader out of date and no longer valid for delete, undelete, or setNorm operations"); } }
public final synchronized void	close() Closes files associated with this index. Also saves any new deletions to disk. No other methods should be called after this has been called. commit(); doClose(); if(closeDirectory) directory.close();
protected final synchronized void	commit() Commit changes resulting from delete, undeleteAll, or setNorm operations 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;
public final synchronized void	delete(int docNum) Deletes the document numbered docNum. 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. if(directoryOwner) aquireWriteLock(); doDelete(docNum); hasChanges = true;
public final int	delete(org.apache.lucene.index.Term term) Deletes all documents containing term. 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. Returns the number of documents deleted. TermDocs docs = termDocs(term); if (docs == null) return 0; int n = 0; try { while (docs.next()) { delete(docs.doc()); n++; } } finally { docs.close(); } return n;
public org.apache.lucene.store.Directory	directory() Returns the directory this index resides in. return directory;
protected abstract void	doClose() Implements close.
protected abstract void	doCommit() Implements commit.
protected abstract void	doDelete(int docNum) Implements deletion of the document numbered docNum. Applications should call {@link #delete(int)} or {@link #delete(Term)}.
protected abstract void	doSetNorm(int doc, java.lang.String field, byte value) Implements setNorm in subclass.
protected abstract void	doUndeleteAll() Implements actual undeleteAll() in subclass.
public abstract int	docFreq(org.apache.lucene.index.Term t) Returns the number of documents containing the term t.
public abstract org.apache.lucene.document.Document	document(int n) Returns the stored fields of the nth Document in this index.
protected final void	finalize() Release the write lock, if needed. if (writeLock != null) { writeLock.release(); // release write lock writeLock = null; }
public static long	getCurrentVersion(java.lang.String directory) Reads version number from segments files. The version number counts the number of changes of the index. param directory where the index resides. return version number. throws IOException if segments file cannot be read return getCurrentVersion(new File(directory));
public static long	getCurrentVersion(java.io.File directory) Reads version number from segments files. The version number counts the number of changes of the index. param directory where the index resides. return version number. throws IOException if segments file cannot be read Directory dir = FSDirectory.getDirectory(directory, false); long version = getCurrentVersion(dir); dir.close(); return version;
public static long	getCurrentVersion(org.apache.lucene.store.Directory directory) Reads version number from segments files. The version number counts the number of changes of the index. param directory where the index resides. return version number. throws IOException if segments file cannot be read. return SegmentInfos.readCurrentVersion(directory);
public abstract java.util.Collection	getFieldNames() Returns a list of all unique field names that exist in the index pointed to by this IndexReader. return Collection of Strings indicating the names of the fields throws IOException if there is a problem with accessing the index
public abstract java.util.Collection	getFieldNames(boolean indexed) Returns a list of all unique field names that exist in the index pointed to by this IndexReader. The boolean argument specifies whether the fields returned are indexed or not. param indexed true if only indexed fields should be returned; false if only unindexed fields should be returned. return Collection of Strings indicating the names of the fields throws IOException if there is a problem with accessing the index
public abstract java.util.Collection	getIndexedFieldNames(boolean storedTermVector) param storedTermVector if true, returns only Indexed fields that have term vector info, else only indexed fields without term vector info return Collection of Strings indicating the names of the fields
public abstract org.apache.lucene.index.TermFreqVector	getTermFreqVector(int docNumber, java.lang.String field) Return a term frequency vector for the specified document and field. The vector returned contains terms and frequencies for those 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. see Field#isTermVectorStored()
public abstract org.apache.lucene.index.TermFreqVector[]	getTermFreqVectors(int docNumber) 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. see Field#isTermVectorStored()
public abstract boolean	hasDeletions() Returns true if any documents have been deleted
public static boolean	indexExists(java.lang.String directory) Returns true if an index exists at the specified directory. If the directory does not exist or if there is no index in it. false is returned. param directory the directory to check for an index return true if an index exists; false otherwise return (new File(directory, "segments")).exists();
public static boolean	indexExists(java.io.File directory) Returns true 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 true if an index exists; false otherwise return (new File(directory, "segments")).exists();
public static boolean	indexExists(org.apache.lucene.store.Directory directory) Returns true 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 true if an index exists; false otherwise throws IOException if there is a problem with accessing the index return directory.fileExists("segments");
public abstract boolean	isDeleted(int n) Returns true if document n has been deleted
public static boolean	isLocked(org.apache.lucene.store.Directory directory) Returns true 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 return directory.makeLock(IndexWriter.WRITE_LOCK_NAME).isLocked() || directory.makeLock(IndexWriter.COMMIT_LOCK_NAME).isLocked();
public static boolean	isLocked(java.lang.String directory) Returns true 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 Directory dir = FSDirectory.getDirectory(directory, false); boolean result = isLocked(dir); dir.close(); return result;
public static long	lastModified(org.apache.lucene.store.Directory directory) Returns the time the index in the named directory was last modified. Synchronization of IndexReader and IndexWriter instances is no longer done via time stamps of the segments file since the time resolution depends on the hardware platform. Instead, a version number is maintained within the segments file, which is incremented everytime when the index is changed. deprecated Replaced by {@link #getCurrentVersion(Directory)} return directory.fileModified("segments");
public static long	lastModified(java.lang.String directory) Returns the time the index in the named directory was last modified. Synchronization of IndexReader and IndexWriter instances is no longer done via time stamps of the segments file since the time resolution depends on the hardware platform. Instead, a version number is maintained within the segments file, which is incremented everytime when the index is changed. deprecated Replaced by {@link #getCurrentVersion(String)} return lastModified(new File(directory));
public static long	lastModified(java.io.File directory) Returns the time the index in the named directory was last modified. Synchronization of IndexReader and IndexWriter instances is no longer done via time stamps of the segments file since the time resolution depends on the hardware platform. Instead, a version number is maintained within the segments file, which is incremented everytime when the index is changed. deprecated Replaced by {@link #getCurrentVersion(File)} return FSDirectory.fileModified(directory, "segments");
public abstract int	maxDoc() 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 byte[]	norms(java.lang.String field) Returns 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(java.lang.String field, byte[] bytes, int offset) 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 int	numDocs() Returns the number of documents in this index.
public static org.apache.lucene.index.IndexReader	open(java.lang.String path) Returns an IndexReader reading the index in an FSDirectory in the named path. return open(FSDirectory.getDirectory(path, false), true);
public static org.apache.lucene.index.IndexReader	open(java.io.File path) Returns an IndexReader reading the index in an FSDirectory in the named path. return open(FSDirectory.getDirectory(path, false), true);
public static org.apache.lucene.index.IndexReader	open(org.apache.lucene.store.Directory directory) Returns an IndexReader reading the index in the given Directory. return open(directory, false);
private static org.apache.lucene.index.IndexReader	open(org.apache.lucene.store.Directory directory, boolean closeDirectory) 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 new SegmentReader(infos, infos.info(0), closeDirectory); } else { IndexReader[] readers = new IndexReader[infos.size()]; for (int i = 0; i < infos.size(); i++) readers[i] = new SegmentReader(infos.info(i)); return new MultiReader(directory, infos, closeDirectory, readers); } } }.run(); }
public final synchronized void	setNorm(int doc, java.lang.String field, byte value) 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) if(directoryOwner) aquireWriteLock(); doSetNorm(doc, field, value); hasChanges = true;
public void	setNorm(int doc, java.lang.String field, float value) Expert: Resets the normalization factor for the named field of the named document. see #norms(String) see Similarity#decodeNorm(byte) setNorm(doc, field, Similarity.encodeNorm(value));
public org.apache.lucene.index.TermDocs	termDocs(org.apache.lucene.index.Term term) Returns an enumeration of all the documents which contain term. 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: Term    =>    <docNum, freq>* The enumeration is ordered by document number. Each document number is greater than all that precede it in the enumeration. TermDocs termDocs = termDocs(); termDocs.seek(term); return termDocs;
public abstract org.apache.lucene.index.TermDocs	termDocs() Returns an unpositioned {@link TermDocs} enumerator.
public org.apache.lucene.index.TermPositions	termPositions(org.apache.lucene.index.Term term) Returns an enumeration of all the documents which contain term. 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: Term    =>    <docNum, freq, <pos1, pos2, ... posfreq-1> >* This positional information faciliates phrase and proximity searching. The enumeration is ordered by document number. Each document number is greater than all that precede it in the enumeration. TermPositions termPositions = termPositions(); termPositions.seek(term); return termPositions;
public abstract org.apache.lucene.index.TermPositions	termPositions() Returns an unpositioned {@link TermPositions} enumerator.
public abstract org.apache.lucene.index.TermEnum	terms() 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 org.apache.lucene.index.TermEnum	terms(org.apache.lucene.index.Term t) 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 final synchronized void	undeleteAll() Undeletes all documents currently marked as deleted in this index. if(directoryOwner) aquireWriteLock(); doUndeleteAll(); hasChanges = true;
public static void	unlock(org.apache.lucene.store.Directory directory) Forcibly unlocks the index in the named directory. 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. directory.makeLock(IndexWriter.WRITE_LOCK_NAME).release(); directory.makeLock(IndexWriter.COMMIT_LOCK_NAME).release();