LantaoJin commented on code in PR #16739: URL: https://github.com/apache/lucene/pull/16739#discussion_r4152318652
########## lucene/core/src/test/org/apache/lucene/util/hnsw/TestIncrementalHnswGraphMergerBaseSelection.java: ########## @@ -0,0 +1,118 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You 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. + */ +package org.apache.lucene.util.hnsw; + +import java.io.IOException; +import java.util.List; +import org.apache.lucene.codecs.lucene99.Lucene99HnswVectorsFormat; +import org.apache.lucene.document.Document; +import org.apache.lucene.document.Field; +import org.apache.lucene.document.KnnFloatVectorField; +import org.apache.lucene.document.StringField; +import org.apache.lucene.index.CodecReader; +import org.apache.lucene.index.DirectoryReader; +import org.apache.lucene.index.FieldInfo; +import org.apache.lucene.index.IndexWriter; +import org.apache.lucene.index.IndexWriterConfig; +import org.apache.lucene.index.LeafReaderContext; +import org.apache.lucene.index.NoMergePolicy; +import org.apache.lucene.index.Term; +import org.apache.lucene.store.Directory; +import org.apache.lucene.tests.util.LuceneTestCase; +import org.apache.lucene.tests.util.TestUtil; + +/** + * Tests which source graph {@link IncrementalHnswGraphMerger} picks as the base graph when some + * candidates carry deletions. + */ +public class TestIncrementalHnswGraphMergerBaseSelection extends LuceneTestCase { + + private static final int DIM = 16; + private static final String FIELD = "v"; + + /** + * Segment A has 1000 nodes of which 300 are deleted (700 live, 30% deleted, under the 40% + * threshold); segment B has 900 nodes and no deletions. B holds more live vectors, so it must be + * chosen as the base regardless of the order in which the readers are added. + */ + public void testBaseGraphChosenByLiveCount() throws IOException { + try (Directory dir = newDirectory()) { + IndexWriterConfig cfg = new IndexWriterConfig(); + cfg.setCodec(TestUtil.alwaysKnnVectorsFormat(new Lucene99HnswVectorsFormat(16, 100, 0))); + cfg.setMergePolicy(NoMergePolicy.INSTANCE); + try (IndexWriter w = new IndexWriter(dir, cfg)) { + addSegment(w, "a", 1000); Review Comment: done -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
