[Note that as of 2.1, all but one of the * methods in this class are available via {@link * IndexWriter}. The one method that is not available is * {@link #deleteDocument(int)}.]
* * A class to modify an index, i.e. to delete and add documents. This * class hides {@link IndexReader} and {@link IndexWriter} so that you * do not need to care about implementation details such as that adding * documents is done via IndexWriter and deletion is done via IndexReader. * *Note that you cannot create more than one IndexModifier object
* on the same directory at the same time.
*
*
Example usage: *
Analyzer analyzer = new StandardAnalyzer();
|
Not all methods of IndexReader and IndexWriter are offered by this
* class. If you need access to additional methods, either use those classes
* directly or implement your own class that extends IndexModifier.
*
*
Although an instance of this class can be used from more than one * thread, you will not get the best performance. You might want to use * IndexReader and IndexWriter directly for that (but you will need to * care about synchronization yourself then). * *
While you can freely mix calls to add() and delete() using this class,
* you should batch you calls for best performance. For example, if you
* want to update 20 documents, you should first delete all those documents,
* then add all the new documents.
*
* @deprecated Please use {@link IndexWriter} instead.
*/
public class IndexModifier {
protected IndexWriter indexWriter = null;
protected IndexReader indexReader = null;
protected Directory directory = null;
protected Analyzer analyzer = null;
protected boolean open = false, closeDir = false;
// Lucene defaults:
protected PrintStream infoStream = null;
protected boolean useCompoundFile = true;
protected int maxBufferedDocs = IndexWriter.DEFAULT_MAX_BUFFERED_DOCS;
protected int maxFieldLength = IndexWriter.DEFAULT_MAX_FIELD_LENGTH;
protected int mergeFactor = LogMergePolicy.DEFAULT_MERGE_FACTOR;
/**
* Open an index with write access.
*
* @param directory the index directory
* @param analyzer the analyzer to use for adding new documents
* @param create true to create the index or overwrite the existing one;
* false to append to the existing index
* @throws CorruptIndexException if the index is corrupt
* @throws LockObtainFailedException if another writer
* has this index open (write.lock could not
* be obtained)
* @throws IOException if there is a low-level IO error
*/
public IndexModifier(Directory directory, Analyzer analyzer, boolean create) throws CorruptIndexException, LockObtainFailedException, IOException {
init(directory, analyzer, create);
}
/**
* Open an index with write access.
*
* @param dirName the index directory
* @param analyzer the analyzer to use for adding new documents
* @param create true to create the index or overwrite the existing one;
* false to append to the existing index
* @throws CorruptIndexException if the index is corrupt
* @throws LockObtainFailedException if another writer
* has this index open (write.lock could not
* be obtained)
* @throws IOException if there is a low-level IO error
*/
public IndexModifier(String dirName, Analyzer analyzer, boolean create) throws CorruptIndexException, LockObtainFailedException, IOException {
Directory dir = FSDirectory.open(new File(dirName));
this.closeDir = true;
init(dir, analyzer, create);
}
/**
* Open an index with write access.
*
* @param file the index directory
* @param analyzer the analyzer to use for adding new documents
* @param create true to create the index or overwrite the existing one;
* false to append to the existing index
* @throws CorruptIndexException if the index is corrupt
* @throws LockObtainFailedException if another writer
* has this index open (write.lock could not
* be obtained)
* @throws IOException if there is a low-level IO error
*/
public IndexModifier(File file, Analyzer analyzer, boolean create) throws CorruptIndexException, LockObtainFailedException, IOException {
Directory dir = FSDirectory.open(file);
this.closeDir = true;
init(dir, analyzer, create);
}
/**
* Initialize an IndexWriter.
* @throws CorruptIndexException if the index is corrupt
* @throws LockObtainFailedException if another writer
* has this index open (write.lock could not
* be obtained)
* @throws IOException if there is a low-level IO error
*/
protected void init(Directory directory, Analyzer analyzer, boolean create) throws CorruptIndexException, LockObtainFailedException, IOException {
this.directory = directory;
synchronized(this.directory) {
this.analyzer = analyzer;
indexWriter = new IndexWriter(directory, analyzer, create, IndexWriter.MaxFieldLength.LIMITED);
open = true;
}
}
/**
* Throw an IllegalStateException if the index is closed.
* @throws IllegalStateException
*/
protected void assureOpen() {
if (!open) {
throw new IllegalStateException("Index is closed");
}
}
/**
* Close the IndexReader and open an IndexWriter.
* @throws CorruptIndexException if the index is corrupt
* @throws LockObtainFailedException if another writer
* has this index open (write.lock could not
* be obtained)
* @throws IOException if there is a low-level IO error
*/
protected void createIndexWriter() throws CorruptIndexException, LockObtainFailedException, IOException {
if (indexWriter == null) {
if (indexReader != null) {
indexReader.close();
indexReader = null;
}
indexWriter = new IndexWriter(directory, analyzer, false, new IndexWriter.MaxFieldLength(maxFieldLength));
// IndexModifier cannot use ConcurrentMergeScheduler
// because it synchronizes on the directory which can
// cause deadlock
indexWriter.setMergeScheduler(new SerialMergeScheduler());
indexWriter.setInfoStream(infoStream);
indexWriter.setUseCompoundFile(useCompoundFile);
if (maxBufferedDocs != IndexWriter.DISABLE_AUTO_FLUSH)
indexWriter.setMaxBufferedDocs(maxBufferedDocs);
indexWriter.setMergeFactor(mergeFactor);
}
}
/**
* Close the IndexWriter and open an IndexReader.
* @throws CorruptIndexException if the index is corrupt
* @throws IOException if there is a low-level IO error
*/
protected void createIndexReader() throws CorruptIndexException, IOException {
if (indexReader == null) {
if (indexWriter != null) {
indexWriter.close();
indexWriter = null;
}
indexReader = IndexReader.open(directory);
}
}
/**
* Make sure all changes are written to disk.
* @throws CorruptIndexException if the index is corrupt
* @throws LockObtainFailedException if another writer
* has this index open (write.lock could not
* be obtained)
* @throws IOException if there is a low-level IO error
*/
public void flush() throws CorruptIndexException, LockObtainFailedException, IOException {
synchronized(directory) {
assureOpen();
if (indexWriter != null) {
indexWriter.close();
indexWriter = null;
createIndexWriter();
} else {
indexReader.close();
indexReader = null;
createIndexReader();
}
}
}
/**
* Adds a document to this index, using the provided analyzer instead of the
* one specific in the constructor. If the document contains more than
* {@link #setMaxFieldLength(int)} terms for a given field, the remainder are
* discarded.
* @see IndexWriter#addDocument(Document, Analyzer)
* @throws IllegalStateException if the index is closed
* @throws CorruptIndexException if the index is corrupt
* @throws LockObtainFailedException if another writer
* has this index open (write.lock could not
* be obtained)
* @throws IOException if there is a low-level IO error
*/
public void addDocument(Document doc, Analyzer docAnalyzer) throws CorruptIndexException, LockObtainFailedException, IOException {
synchronized(directory) {
assureOpen();
createIndexWriter();
if (docAnalyzer != null)
indexWriter.addDocument(doc, docAnalyzer);
else
indexWriter.addDocument(doc);
}
}
/**
* Adds a document to this index. If the document contains more than
* {@link #setMaxFieldLength(int)} terms for a given field, the remainder are
* discarded.
* @see IndexWriter#addDocument(Document)
* @throws IllegalStateException if the index is closed
* @throws CorruptIndexException if the index is corrupt
* @throws LockObtainFailedException if another writer
* has this index open (write.lock could not
* be obtained)
* @throws IOException if there is a low-level IO error
*/
public void addDocument(Document doc) throws CorruptIndexException, LockObtainFailedException, IOException {
addDocument(doc, null);
}
/**
* 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.
* @return the number of documents deleted
* @see IndexReader#deleteDocuments(Term)
* @throws IllegalStateException if the index is closed
* @throws StaleReaderException if the index has changed
* since this reader was opened
* @throws CorruptIndexException if the index is corrupt
* @throws LockObtainFailedException if another writer
* has this index open (write.lock could not
* be obtained)
* @throws IOException if there is a low-level IO error
*/
public int deleteDocuments(Term term) throws StaleReaderException, CorruptIndexException, LockObtainFailedException, IOException {
synchronized(directory) {
assureOpen();
createIndexReader();
return indexReader.deleteDocuments(term);
}
}
/**
* Deletes the document numbered docNum.
* @see IndexReader#deleteDocument(int)
* @throws StaleReaderException if the index has changed
* since this reader was opened
* @throws CorruptIndexException if the index is corrupt
* @throws LockObtainFailedException if another writer
* has this index open (write.lock could not
* be obtained)
* @throws IllegalStateException if the index is closed
*/
public void deleteDocument(int docNum) throws StaleReaderException, CorruptIndexException, LockObtainFailedException, IOException {
synchronized(directory) {
assureOpen();
createIndexReader();
indexReader.deleteDocument(docNum);
}
}
/**
* Returns the number of documents currently in this
* index. If the writer is currently open, this returns
* {@link IndexWriter#docCount()}, else {@link
* IndexReader#numDocs()}. But, note that {@link
* IndexWriter#docCount()} does not take deletions into
* account, unlike {@link IndexReader#numDocs}.
* @throws IllegalStateException if the index is closed
*/
public int numDocs() throws java.io.IOException {
synchronized(directory) {
assureOpen();
if (indexWriter != null) {
return indexWriter.numDocs();
} else {
return indexReader.numDocs();
}
}
}
/**
* Merges all segments together into a single segment, optimizing an index
* for search.
* @see IndexWriter#optimize()
* @throws IllegalStateException if the index is closed
* @throws CorruptIndexException if the index is corrupt
* @throws LockObtainFailedException if another writer
* has this index open (write.lock could not
* be obtained)
* @throws IOException if there is a low-level IO error
*/
public void optimize() throws CorruptIndexException, LockObtainFailedException, IOException {
synchronized(directory) {
assureOpen();
createIndexWriter();
indexWriter.optimize();
}
}
/**
* If non-null, information about merges and a message when
* {@link #getMaxFieldLength()} is reached will be printed to this.
*
Example: index.setInfoStream(System.err);
* @see IndexWriter#setInfoStream(PrintStream)
* @throws IllegalStateException if the index is closed
*/
public void setInfoStream(PrintStream infoStream) throws java.io.IOException {
synchronized(directory) {
assureOpen();
if (indexWriter != null) {
indexWriter.setInfoStream(infoStream);
}
this.infoStream = infoStream;
}
}
/**
* @see IndexModifier#setInfoStream(PrintStream)
* @throws CorruptIndexException if the index is corrupt
* @throws LockObtainFailedException if another writer
* has this index open (write.lock could not
* be obtained)
* @throws IOException if there is a low-level IO error
*/
public PrintStream getInfoStream() throws CorruptIndexException, LockObtainFailedException, IOException {
synchronized(directory) {
assureOpen();
createIndexWriter();
return indexWriter.getInfoStream();
}
}
/**
* Setting to turn on usage of a compound file. When on, multiple files
* for each segment are merged into a single file once the segment creation
* is finished. This is done regardless of what directory is in use.
* @see IndexWriter#setUseCompoundFile(boolean)
* @throws IllegalStateException if the index is closed
*/
public void setUseCompoundFile(boolean useCompoundFile) {
synchronized(directory) {
assureOpen();
if (indexWriter != null) {
indexWriter.setUseCompoundFile(useCompoundFile);
}
this.useCompoundFile = useCompoundFile;
}
}
/**
* @see IndexModifier#setUseCompoundFile(boolean)
* @throws CorruptIndexException if the index is corrupt
* @throws LockObtainFailedException if another writer
* has this index open (write.lock could not
* be obtained)
* @throws IOException if there is a low-level IO error
*/
public boolean getUseCompoundFile() throws CorruptIndexException, LockObtainFailedException, IOException {
synchronized(directory) {
assureOpen();
createIndexWriter();
return indexWriter.getUseCompoundFile();
}
}
/**
* The maximum number of terms that will be indexed for a single field in a
* document. This limits the amount of memory required for indexing, so that
* collections with very large files will not crash the indexing process by
* running out of memory.
write.lock could not
* be obtained)
* @throws IOException if there is a low-level IO error
*/
public int getMaxFieldLength() throws CorruptIndexException, LockObtainFailedException, IOException {
synchronized(directory) {
assureOpen();
createIndexWriter();
return indexWriter.getMaxFieldLength();
}
}
/**
* Determines the minimal number of documents required before the buffered
* in-memory documents are merging and a new Segment is created.
* Since Documents are merged in a {@link org.apache.lucene.store.RAMDirectory},
* large value gives faster indexing. At the same time, mergeFactor limits
* the number of files open in a FSDirectory.
*
* The default value is 10.
*
* @see IndexWriter#setMaxBufferedDocs(int)
* @throws IllegalStateException if the index is closed
* @throws IllegalArgumentException if maxBufferedDocs is smaller than 2
*/
public void setMaxBufferedDocs(int maxBufferedDocs) {
synchronized(directory) {
assureOpen();
if (indexWriter != null) {
indexWriter.setMaxBufferedDocs(maxBufferedDocs);
}
this.maxBufferedDocs = maxBufferedDocs;
}
}
/**
* @see IndexModifier#setMaxBufferedDocs(int)
* @throws CorruptIndexException if the index is corrupt
* @throws LockObtainFailedException if another writer
* has this index open (write.lock could not
* be obtained)
* @throws IOException if there is a low-level IO error
*/
public int getMaxBufferedDocs() throws CorruptIndexException, LockObtainFailedException, IOException {
synchronized(directory) {
assureOpen();
createIndexWriter();
return indexWriter.getMaxBufferedDocs();
}
}
/**
* Determines how often segment indices are merged by addDocument(). With
* smaller values, less RAM is used while indexing, and searches on
* unoptimized indices are faster, but indexing speed is slower. With larger
* values, more RAM is used during indexing, and while searches on unoptimized
* indices are slower, indexing is faster. Thus larger values (> 10) are best
* for batch index creation, and smaller values (< 10) for indices that are
* interactively maintained.
*
This must never be less than 2. The default value is 10.
*
* @see IndexWriter#setMergeFactor(int)
* @throws IllegalStateException if the index is closed
*/
public void setMergeFactor(int mergeFactor) {
synchronized(directory) {
assureOpen();
if (indexWriter != null) {
indexWriter.setMergeFactor(mergeFactor);
}
this.mergeFactor = mergeFactor;
}
}
/**
* @see IndexModifier#setMergeFactor(int)
* @throws CorruptIndexException if the index is corrupt
* @throws LockObtainFailedException if another writer
* has this index open (write.lock could not
* be obtained)
* @throws IOException if there is a low-level IO error
*/
public int getMergeFactor() throws CorruptIndexException, LockObtainFailedException, IOException {
synchronized(directory) {
assureOpen();
createIndexWriter();
return indexWriter.getMergeFactor();
}
}
/**
* Close this index, writing all pending changes to disk.
*
* @throws IllegalStateException if the index has been closed before already
* @throws CorruptIndexException if the index is corrupt
* @throws IOException if there is a low-level IO error
*/
public void close() throws CorruptIndexException, IOException {
synchronized(directory) {
if (!open)
throw new IllegalStateException("Index is closed already");
if (indexWriter != null) {
indexWriter.close();
indexWriter = null;
} else if (indexReader != null) {
indexReader.close();
indexReader = null;
}
open = false;
if (closeDir) {
directory.close();
}
closeDir = false;
}
}
public String toString() {
return "Index@" + directory;
}
/*
// used as an example in the javadoc:
public static void main(String[] args) throws IOException {
Analyzer analyzer = new StandardAnalyzer();
// create an index in /tmp/index, overwriting an existing one:
IndexModifier indexModifier = new IndexModifier("/tmp/index", analyzer, true);
Document doc = new Document();
doc.add(new Fieldable("id", "1", Fieldable.Store.YES, Fieldable.Index.NOT_ANALYZED));
doc.add(new Fieldable("body", "a simple test", Fieldable.Store.YES, Fieldable.Index.ANALYZED));
indexModifier.addDocument(doc);
int deleted = indexModifier.delete(new Term("id", "1"));
System.out.println("Deleted " + deleted + " document");
indexModifier.flush();
System.out.println(indexModifier.docCount() + " docs in index");
indexModifier.close();
}*/
}