Merge branch 'main' into optimize_caseless_regexp

apache · Feb 5, 2025 · ed0955b · ed0955b
2 parents 608c58a + 4cd4f8e
commit ed0955b
Show file tree

Hide file tree

Showing 3 changed files with 8 additions and 4 deletions.
diff --git a/gradle/validation/error-prone.gradle b/gradle/validation/error-prone.gradle
@@ -25,6 +25,8 @@ if (!propertyOrDefault("validation.errorprone", isCIBuild).asBoolean()) {
   skipReason = "skipped on builds not running inside CI environments, pass -Pvalidation.errorprone=true to enable"
 }
 
+skipReason = "failing in CI builds with NoSuchMethodError due to use of internal compiler APIs"
+
 if (skipReason) {
   configure(rootProject) {
     task errorProneSkipped() {

diff --git a/lucene/core/src/java/org/apache/lucene/analysis/package-info.java b/lucene/core/src/java/org/apache/lucene/analysis/package-info.java
@@ -343,7 +343,7 @@
  *       undefined as long as they both leave from the same position. As result, all synonyms of a
  *       token would be considered to appear in exactly the same position as that token, and so
  *       would they be seen by phrase and proximity searches. For multi-token synonyms to work
- *       correctly, you should use {@code SynoymGraphFilter} at search time only.
+ *       correctly, you should use {@code SynonymGraphFilter} at search time only.
  * </ol>
  *
  * <h3>Token Position Length</h3>

diff --git a/lucene/core/src/java/org/apache/lucene/search/SeededKnnVectorQuery.java b/lucene/core/src/java/org/apache/lucene/search/SeededKnnVectorQuery.java
@@ -229,10 +229,11 @@ private static class TopDocsDISI extends DocIdSetIterator {
     private final int[] sortedDocIds;
     private int idx = -1;
 
-    private TopDocsDISI(TopDocs topDocs) {
+    private TopDocsDISI(TopDocs topDocs, LeafReaderContext ctx) {
       sortedDocIds = new int[topDocs.scoreDocs.length];
       for (int i = 0; i < topDocs.scoreDocs.length; i++) {
-        sortedDocIds[i] = topDocs.scoreDocs[i].doc;
+        // Remove the doc base as added by the collector
+        sortedDocIds[i] = topDocs.scoreDocs[i].doc - ctx.docBase;
       }
       Arrays.sort(sortedDocIds);
     }
@@ -311,7 +312,8 @@ public KnnCollector newCollector(
       }
       // Most underlying iterators are indexed, so we can map the seed docs to the vector docs
       if (vectorIterator instanceof KnnVectorValues.DocIndexIterator indexIterator) {
-        DocIdSetIterator seedDocs = new MappedDISI(indexIterator, new TopDocsDISI(seedTopDocs));
+        DocIdSetIterator seedDocs =
+            new MappedDISI(indexIterator, new TopDocsDISI(seedTopDocs, ctx));
         return knnCollectorManager.newCollector(
             visitLimit, new KnnSearchStrategy.Seeded(seedDocs, seedTopDocs.scoreDocs.length), ctx);
       }