[lucene] branch main updated: Fix rare test failures in TestSortOptimization.

[jp...@apache.org]

This is an automated email from the ASF dual-hosted git repository.

jpountz pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/lucene.git


The following commit(s) were added to refs/heads/main by this push:
     new 8476ac1f6ac Fix rare test failures in TestSortOptimization.
8476ac1f6ac is described below

commit 8476ac1f6ac5258052f93e85278f70770fe3dfd5
Author: Adrien Grand <jp...@gmail.com>
AuthorDate: Tue May 10 17:09:15 2022 +0200

    Fix rare test failures in TestSortOptimization.
    
    The skipping logic relies on the points index telling us by how much we can
    reduce the candidate set by applying a filter that only matches documents that
    compare better than the bottom value.
    
    Some randomized points formats have large numbers of points per leaf, and
    produce estimates of point counts for range queries that are way above the
    actual value, which in-turn doesn't enable skipping when we think it should. To
    avoid running into this corner case, this change forces the default codec on
    this test.
---
 .../apache/lucene/search/TestSortOptimization.java | 29 +++++++++++++++++++---
 1 file changed, 25 insertions(+), 4 deletions(-)

diff --git a/lucene/core/src/test/org/apache/lucene/search/TestSortOptimization.java b/lucene/core/src/test/org/apache/lucene/search/TestSortOptimization.java
index f5265f709c4..419cc055d47 100644
--- a/lucene/core/src/test/org/apache/lucene/search/TestSortOptimization.java
+++ b/lucene/core/src/test/org/apache/lucene/search/TestSortOptimization.java
@@ -43,6 +43,7 @@ import org.apache.lucene.index.Term;
 import org.apache.lucene.store.Directory;
 import org.apache.lucene.tests.index.RandomIndexWriter;
 import org.apache.lucene.tests.util.LuceneTestCase;
+import org.apache.lucene.tests.util.TestUtil;
 import org.apache.lucene.util.IOUtils;
 
 public class TestSortOptimization extends LuceneTestCase {
@@ -50,7 +51,12 @@ public class TestSortOptimization extends LuceneTestCase {
   public void testLongSortOptimization() throws IOException {
 
     final Directory dir = newDirectory();
-    final IndexWriter writer = new IndexWriter(dir, new IndexWriterConfig());
+    IndexWriterConfig config =
+        new IndexWriterConfig()
+            // Make sure to use the default codec, otherwise some random points formats that have
+            // large values for maxPointsPerLeaf might not enable skipping with only 10k docs
+            .setCodec(TestUtil.getDefaultCodec());
+    final IndexWriter writer = new IndexWriter(dir, config);
     final int numDocs = atLeast(10000);
     for (int i = 0; i < numDocs; ++i) {
       final Document doc = new Document();
@@ -170,7 +176,12 @@ public class TestSortOptimization extends LuceneTestCase {
 
   public void testSortOptimizationWithMissingValues() throws IOException {
     final Directory dir = newDirectory();
-    final IndexWriter writer = new IndexWriter(dir, new IndexWriterConfig());
+    IndexWriterConfig config =
+        new IndexWriterConfig()
+            // Make sure to use the default codec, otherwise some random points formats that have
+            // large values for maxPointsPerLeaf might not enable skipping with only 10k docs
+            .setCodec(TestUtil.getDefaultCodec());
+    final IndexWriter writer = new IndexWriter(dir, config);
     final int numDocs = atLeast(10000);
     for (int i = 0; i < numDocs; ++i) {
       final Document doc = new Document();
@@ -218,7 +229,12 @@ public class TestSortOptimization extends LuceneTestCase {
 
   public void testSortOptimizationEqualValues() throws IOException {
     final Directory dir = newDirectory();
-    final IndexWriter writer = new IndexWriter(dir, new IndexWriterConfig());
+    IndexWriterConfig config =
+        new IndexWriterConfig()
+            // Make sure to use the default codec, otherwise some random points formats that have
+            // large values for maxPointsPerLeaf might not enable skipping with only 10k docs
+            .setCodec(TestUtil.getDefaultCodec());
+    final IndexWriter writer = new IndexWriter(dir, config);
     final int numDocs = atLeast(TEST_NIGHTLY ? 50_000 : 10_000);
     for (int i = 1; i <= numDocs; ++i) {
       final Document doc = new Document();
@@ -345,7 +361,12 @@ public class TestSortOptimization extends LuceneTestCase {
     IndexReader[] readers = new IndexReader[numIndices];
     for (int i = 0; i < numIndices; i++) {
       dirs[i] = newDirectory();
-      try (IndexWriter writer = new IndexWriter(dirs[i], new IndexWriterConfig())) {
+      IndexWriterConfig config =
+          new IndexWriterConfig()
+              // Make sure to use the default codec, otherwise some random points formats that have
+              // large values for maxPointsPerLeaf might not enable skipping with only 10k docs
+              .setCodec(TestUtil.getDefaultCodec());
+      try (IndexWriter writer = new IndexWriter(dirs[i], config)) {
         for (int docID = 0; docID < numDocsInIndex; docID++) {
           final Document doc = new Document();
           doc.add(new NumericDocValuesField("my_field", docID * numIndices + i));