You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by at...@apache.org on 2025/04/17 18:28:29 UTC
(lucene) 10/18: Continued cleanups
This is an automated email from the ASF dual-hosted git repository.
atri pushed a commit to branch new_index_query_include
in repository https://gitbox.apache.org/repos/asf/lucene.git
commit 66ef86399fb28a93bbbef3a49eb1a07b38fbae04
Author: Atri Sharma <at...@192.168.1.75>
AuthorDate: Thu Apr 17 02:40:42 2025 +0530
Continued cleanups
---
.../benchmark/jmh/IndexingLatencyBenchmark.java | 147 ---------------------
.../org/apache/lucene/codecs/BinMapReader.java | 2 -
.../apache/lucene/search/BinBoostCalculator.java | 1 -
3 files changed, 150 deletions(-)
diff --git a/lucene/benchmark-jmh/src/java/org/apache/lucene/benchmark/jmh/IndexingLatencyBenchmark.java b/lucene/benchmark-jmh/src/java/org/apache/lucene/benchmark/jmh/IndexingLatencyBenchmark.java
deleted file mode 100644
index 3fe148e84e7..00000000000
--- a/lucene/benchmark-jmh/src/java/org/apache/lucene/benchmark/jmh/IndexingLatencyBenchmark.java
+++ /dev/null
@@ -1,147 +0,0 @@
-/*
- * 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.benchmark.jmh;
-
-import java.io.IOException;
-import java.io.Reader;
-import java.nio.file.Files;
-import java.nio.file.Path;
-import java.util.Comparator;
-import java.util.concurrent.TimeUnit;
-import org.apache.lucene.analysis.Analyzer;
-import org.apache.lucene.analysis.Tokenizer;
-import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
-import org.apache.lucene.codecs.lucene101.Lucene101Codec;
-import org.apache.lucene.document.Document;
-import org.apache.lucene.document.Field;
-import org.apache.lucene.document.FieldType;
-import org.apache.lucene.document.TextField;
-import org.apache.lucene.index.IndexOptions;
-import org.apache.lucene.index.IndexWriter;
-import org.apache.lucene.index.IndexWriterConfig;
-import org.apache.lucene.store.Directory;
-import org.apache.lucene.store.MMapDirectory;
-import org.openjdk.jmh.annotations.Benchmark;
-import org.openjdk.jmh.annotations.BenchmarkMode;
-import org.openjdk.jmh.annotations.Fork;
-import org.openjdk.jmh.annotations.Level;
-import org.openjdk.jmh.annotations.Measurement;
-import org.openjdk.jmh.annotations.Mode;
-import org.openjdk.jmh.annotations.OutputTimeUnit;
-import org.openjdk.jmh.annotations.Param;
-import org.openjdk.jmh.annotations.Scope;
-import org.openjdk.jmh.annotations.Setup;
-import org.openjdk.jmh.annotations.State;
-import org.openjdk.jmh.annotations.Warmup;
-
-@BenchmarkMode(Mode.AverageTime)
-@OutputTimeUnit(TimeUnit.MILLISECONDS)
-@State(Scope.Thread)
-@Warmup(iterations = 2)
-@Measurement(iterations = 5)
-@Fork(1)
-public class IndexingLatencyBenchmark {
-
- @Param({"true", "false"})
- private String binningFlag;
-
- @Param({"1000", "10000"})
- private int docCount;
-
- private boolean binningEnabled;
- private FieldType fieldType;
- private Path tempDir;
-
- @Setup(Level.Trial)
- public void setup() {
- binningEnabled = Boolean.parseBoolean(binningFlag);
- fieldType = new FieldType(TextField.TYPE_NOT_STORED);
- fieldType.setTokenized(true);
- fieldType.setIndexOptions(IndexOptions.DOCS_AND_FREQS_AND_POSITIONS);
- if (binningEnabled) {
- fieldType.putAttribute("postingsFormat", "Lucene101");
- fieldType.putAttribute("doBinning", "true");
- fieldType.putAttribute("bin.count", "4");
- }
- fieldType.freeze();
- }
-
- @Benchmark
- public void indexBatch() throws IOException {
- tempDir = Files.createTempDirectory("lucene-indexing-benchmark");
- try (Directory dir = new MMapDirectory(tempDir)) {
- IndexWriterConfig config = new IndexWriterConfig(new SingleTokenAnalyzer());
- config.setCodec(new Lucene101Codec());
- config.setUseCompoundFile(false);
- try (IndexWriter writer = new IndexWriter(dir, config)) {
- for (int i = 0; i < docCount; i++) {
- Document doc = new Document();
- String content = (i % 200 == 0) ? "lucene high quality text" : "noise filler token " + i;
- doc.add(new Field("field", content, fieldType));
- writer.addDocument(doc);
- }
- writer.commit();
- }
- } finally {
- Files.walk(tempDir)
- .sorted(Comparator.reverseOrder())
- .forEach(
- path -> {
- try {
- Files.deleteIfExists(path);
- } catch (IOException ignored) {
- // best-effort cleanup
- }
- });
- }
- }
-
- /** Analyzer that emits a single token to avoid dependency on analyzer modules. */
- private static final class SingleTokenAnalyzer extends Analyzer {
- @Override
- protected TokenStreamComponents createComponents(String fieldName) {
- Tokenizer tokenizer =
- new Tokenizer() {
- private final CharTermAttribute attr = addAttribute(CharTermAttribute.class);
- private boolean emitted = false;
-
- @Override
- public boolean incrementToken() {
- if (emitted) {
- return false;
- }
- clearAttributes();
- attr.append("lucene");
- emitted = true;
- return true;
- }
-
- @Override
- public void reset() throws IOException {
- super.reset();
- emitted = false;
- }
- };
- return new TokenStreamComponents(tokenizer);
- }
-
- @Override
- protected Reader initReader(String fieldName, Reader reader) {
- return reader;
- }
- }
-}
diff --git a/lucene/core/src/java/org/apache/lucene/codecs/BinMapReader.java b/lucene/core/src/java/org/apache/lucene/codecs/BinMapReader.java
index 908b391291f..4d39c8d43cf 100644
--- a/lucene/core/src/java/org/apache/lucene/codecs/BinMapReader.java
+++ b/lucene/core/src/java/org/apache/lucene/codecs/BinMapReader.java
@@ -12,13 +12,11 @@ package org.apache.lucene.codecs;
import java.io.Closeable;
import java.io.IOException;
-import java.util.Arrays;
import org.apache.lucene.index.IndexFileNames;
import org.apache.lucene.index.SegmentReadState;
import org.apache.lucene.store.ChecksumIndexInput;
import org.apache.lucene.store.Directory;
-import org.apache.lucene.util.ArrayUtil;
/**
* Reads the binmap file for a segment and exposes per-document bin assignments.
diff --git a/lucene/core/src/java/org/apache/lucene/search/BinBoostCalculator.java b/lucene/core/src/java/org/apache/lucene/search/BinBoostCalculator.java
index 210438e8c42..da0657eedf2 100644
--- a/lucene/core/src/java/org/apache/lucene/search/BinBoostCalculator.java
+++ b/lucene/core/src/java/org/apache/lucene/search/BinBoostCalculator.java
@@ -17,7 +17,6 @@
package org.apache.lucene.search;
import java.io.IOException;
-import java.util.Arrays;
import org.apache.lucene.index.BinScoreLeafReader;
import org.apache.lucene.index.BinScoreReader;