Hi,
I'm sending a patch which should help to fix a problem using the new method IndexReader.getCurrentVersion(). As far as i understand the current lucene documentation, developers should use this new method to verify if an index is out of date. The older method IndexReader.lastModified() is deprecated and therefore a possible candidate for deletion.
The problem with getCurrentVersion is, that it's base is 0, when creating a new index. Therefore the version number will be identical if you delete an index and recreate a new one, using the same document set, doesn't matter if there is a change in the document content or a different analyzer is used. The idea of the patch is to intialize the version number with the current time in millis as base when creating a new SegmentInfos object. So it's "nearly" impossible to get the same version number again.
Without this patch, it's impossible for developers to store an IndexReader in cache and check it's validity thru getCurrentVersion.
In the attachment is the patch and a JUnit TestCase which tests the scenario with a sample implementation for an IndexReader cache.
As far as i can see, there are no negativ side effects when implementing this patch. But let's see what the lucene-specialists will see ;-)
best regards Bernhard
Index: src/java/org/apache/lucene/index/SegmentInfos.java =================================================================== RCS file: /home/cvspublic/jakarta-lucene/src/java/org/apache/lucene/index/SegmentInfos.java,v retrieving revision 1.5 diff -r1.5 SegmentInfos.java 32c32,37 < private long version = 0; //counts how often the index has been changed by adding or deleting docs --- > > /** > * counts how often the index has been changed by adding or deleting docs. > * starting with the current time in milliseconds forces to create unique version > numbers. > */ > private long version = System.currentTimeMillis();
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 java.io.IOException; import java.util.Hashtable; import junit.framework.Test; import junit.framework.TestCase; import junit.framework.TestSuite; import org.apache.lucene.analysis.Analyzer; import org.apache.lucene.analysis.SimpleAnalyzer; import org.apache.lucene.document.Document; import org.apache.lucene.document.Field; import org.apache.lucene.index.IndexReader; import org.apache.lucene.index.IndexWriter; import org.apache.lucene.queryParser.QueryParser; import org.apache.lucene.search.Hits; import org.apache.lucene.search.IndexSearcher; import org.apache.lucene.search.Query; import org.apache.lucene.search.Searcher; import org.apache.lucene.store.Directory; import org.apache.lucene.store.FSDirectory; class CachedIndex { // an entry in the cache IndexReader reader; long version; CachedIndex(String name) throws IOException { version = IndexReader.getCurrentVersion(name); reader = IndexReader.open(name); // open reader } } public class TestIndexReaderVersion extends TestCase { public TestIndexReaderVersion (String name) { super(name); } static final Hashtable indexCache = new Hashtable(); public static Test suite () { TestSuite suite = new TestSuite(TestIndexReaderVersion.class); for (int i = 1; i < 100; i++) suite.addTest(new TestSuite(TestIndexReaderVersion.class)); return suite; } public void testVersion() { Analyzer analyzer = new SimpleAnalyzer(); String name = "/tmp/lucy"; String[] docs = { "a", "a b" }; String[] titles = docs; String q = "+a +b"; testVersionControl(analyzer, name, docs, titles, q); String[] docs2 = { "c", "c d" }; String[] titles2 = docs; q = "+c +d"; testVersionControl(analyzer, name, docs2, titles2, q); } synchronized private IndexReader getReader(String name) { CachedIndex index = (CachedIndex) indexCache.get(name); // look in cache try { if (index != null // check up-to-date && index.version == IndexReader.getCurrentVersion(name)) { //System.out.println("IndexReader cache hit (maxDocs=" + index.reader.maxDoc() + ")"); return index.reader; // cache hit } else { // Index was open but is not up-to-date, close it before creating a new one if (index != null) { //System.out.println( // "IndexReader not up-to-date, creating new"); try { index.reader.close(); } catch (IOException ignore) { System.err.println( "IndexReader was already closed by third party."); } } else { //System.out.println( // "IndexReader does not exist, creating new"); } index = new CachedIndex(name); // cache miss } } catch (IOException e) { System.err.println(e); } indexCache.put(name, index); // add to cache return index.reader; } private void testVersionControl( Analyzer analyzer, String indexName, String[] docs, String[] titles, String queryString) { try { assertEquals(docs.length, titles.length); Directory directory = FSDirectory.getDirectory(indexName, true); IndexWriter indexer = new IndexWriter(directory, analyzer, true); indexer.setUseCompoundFile(true); //for (int y = 0; y < 500; y++) for (int z = 0; z < docs.length; z++) { Document d = new Document(); Field field = new Field("body", docs[z], true, true, true); d.add(field); field = new Field("title", titles[z], true, true, true); d.add(field); indexer.addDocument(d); } indexer.optimize(); indexer.close(); Hits hits = null; QueryParser parser = new QueryParser("body", analyzer); /** try to get an reader from cache */ IndexReader reader = getReader(indexName); /** create a new searcher */ Searcher searcher = new IndexSearcher(reader); Query query = parser.parse(queryString); hits = searcher.search(query); //System.out.println(" doc's found: " + hits.length()); assertEquals (1, hits.length()); searcher.close(); } catch (Exception e) { System.out.println( " caught a " + e.getClass() + "\n with message: " + e.getMessage()); } } }
--------------------------------------------------------------------- To unsubscribe, e-mail: [EMAIL PROTECTED] For additional commands, e-mail: [EMAIL PROTECTED]
