atris commented on a change in pull request #754: LUCENE-8875: Introduce Optimized Collector For Large Number Of Hits URL: https://github.com/apache/lucene-solr/pull/754#discussion_r301065408
########## File path: lucene/sandbox/src/test/org/apache/lucene/search/TestLargeNumHitsTopDocsCollector.java ########## @@ -0,0 +1,133 @@ +/* + * 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.search; + +import java.io.IOException; + +import org.apache.lucene.document.Document; +import org.apache.lucene.index.IndexReader; +import org.apache.lucene.index.RandomIndexWriter; +import org.apache.lucene.store.Directory; +import org.apache.lucene.util.LuceneTestCase; + +public class TestLargeNumHitsTopDocsCollector extends LuceneTestCase { + private Directory dir; + private IndexReader reader; + + @Override + public void setUp() throws Exception { + super.setUp(); + dir = newDirectory(); + RandomIndexWriter writer = new RandomIndexWriter(random(), dir); + for (int i = 0; i < 200_000; i++) { + writer.addDocument(new Document()); + } + reader = writer.getReader(); + writer.close(); + } + + @Override + public void tearDown() throws Exception { + reader.close(); + dir.close(); + dir = null; + super.tearDown(); + } + public void testLargeNumAndSparseHits() throws Exception { + runNumHits(100_000); + } + + public void testSingleNumHit() throws Exception { + runNumHits(1); + } + + public void testLowNumberOfHits() throws Exception { + runNumHits(25); + } + + public void testIllegalArguments() throws IOException { + Query q = new MatchAllDocsQuery(); + IndexSearcher searcher = newSearcher(reader); + LargeNumHitsTopDocsCollector largeCollector = new LargeNumHitsTopDocsCollector(15); + TopScoreDocCollector regularCollector = TopScoreDocCollector.create(15, null, Integer.MAX_VALUE); + + searcher.search(q, largeCollector); + searcher.search(q, regularCollector); + + assertEquals(largeCollector.totalHits, regularCollector.totalHits); + + expectThrows(IllegalArgumentException.class, () -> { + largeCollector.topDocs(350_000); + }); + } + + public void testNoPQBuild() throws IOException { + Query q = new MatchAllDocsQuery(); + IndexSearcher searcher = newSearcher(reader); + LargeNumHitsTopDocsCollector largeCollector = new LargeNumHitsTopDocsCollector(250_000); + TopScoreDocCollector regularCollector = TopScoreDocCollector.create(250_000, null, Integer.MAX_VALUE); + + searcher.search(q, largeCollector); + searcher.search(q, regularCollector); + + assertEquals(largeCollector.totalHits, regularCollector.totalHits); + + assertEquals(largeCollector.pq, null); + assertEquals(largeCollector.pqTop, null); + } + + public void testPQBuild() throws IOException { + Query q = new MatchAllDocsQuery(); + IndexSearcher searcher = newSearcher(reader); + LargeNumHitsTopDocsCollector largeCollector = new LargeNumHitsTopDocsCollector(100_000); + TopScoreDocCollector regularCollector = TopScoreDocCollector.create(100_000, null, Integer.MAX_VALUE); + + searcher.search(q, largeCollector); + searcher.search(q, regularCollector); + + assertEquals(largeCollector.totalHits, regularCollector.totalHits); + + assertNotEquals(largeCollector.pq, null); + assertNotEquals(largeCollector.pqTop, null); + } + + private void runNumHits(int numHits) throws IOException { + Query q = new MatchAllDocsQuery(); Review comment: +1, updated ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: dev-unsubscr...@lucene.apache.org For additional commands, e-mail: dev-h...@lucene.apache.org
