LUCENE-10674: Ensure BitSetConjDISI returns NO_MORE_DOCS when sub-ite…

…rator exhausts. (#1068) Signed-off-by: John Mazanec <jmazane@amazon.com>
apache · Sep 15, 2022 · 891a696 · 891a696
1 parent 133598a
commit 891a696
Show file tree

Hide file tree

Showing 3 changed files with 33 additions and 4 deletions.
diff --git a/lucene/CHANGES.txt b/lucene/CHANGES.txt
@@ -12,11 +12,12 @@ API Changes
 
 Bug Fixes
 ---------------------
-
 * GITHUB#11726: Indexing term vectors on large documents could fail due to
   trying to apply a dictionary whose size is greater than the maximum supported
   window size for LZ4. (Adrien Grand)
 
+* LUCENE-10674: Ensure BitSetConjDISI returns NO_MORE_DOCS when sub-iterator exhausts. (Jack Mazanec)
+
 Other
 ---------------------
 * LUCENE-10423: Remove usages of System.currentTimeMillis() from tests. (Marios Trivyzas)

diff --git a/lucene/core/src/java/org/apache/lucene/search/ConjunctionDISI.java b/lucene/core/src/java/org/apache/lucene/search/ConjunctionDISI.java
@@ -281,6 +281,9 @@ private int doNext(int doc) throws IOException {
       advanceLead:
       for (; ; doc = lead.nextDoc()) {
         if (doc >= minLength) {
+          if (doc != NO_MORE_DOCS) {
+            lead.advance(NO_MORE_DOCS);
+          }
           return NO_MORE_DOCS;
         }
         for (BitSet bitSet : bitSets) {

diff --git a/lucene/core/src/test/org/apache/lucene/search/TestConjunctionDISI.java b/lucene/core/src/test/org/apache/lucene/search/TestConjunctionDISI.java
@@ -16,6 +16,8 @@
  */
 package org.apache.lucene.search;
 
+import static org.apache.lucene.search.DocIdSetIterator.NO_MORE_DOCS;
+
 import java.io.IOException;
 import java.util.Arrays;
 import java.util.Collections;
@@ -213,9 +215,7 @@ private static FixedBitSet intersect(FixedBitSet[] bitSets) {
 
   private static FixedBitSet toBitSet(int maxDoc, DocIdSetIterator iterator) throws IOException {
     final FixedBitSet set = new FixedBitSet(maxDoc);
-    for (int doc = iterator.nextDoc();
-        doc != DocIdSetIterator.NO_MORE_DOCS;
-        doc = iterator.nextDoc()) {
+    for (int doc = iterator.nextDoc(); doc != NO_MORE_DOCS; doc = iterator.nextDoc()) {
       set.set(doc);
     }
     return set;
@@ -459,4 +459,29 @@ public void testIllegalAdvancementOfSubIteratorsTripsAssertion() throws IOExcept
     AssertionError ex = expectThrows(AssertionError.class, () -> conjunction.nextDoc());
     assertEquals("Sub-iterators of ConjunctionDISI are not on the same document!", ex.getMessage());
   }
+
+  public void testBitSetConjunctionDISIDocIDOnExhaust() throws IOException {
+    int numBitSetIterators = TestUtil.nextInt(random(), 2, 5);
+    DocIdSetIterator[] iterators = new DocIdSetIterator[numBitSetIterators + 1];
+
+    // Create sparse DocIdSetIterator with a single match that is greater than lengths of bitset
+    // iterators
+    int maxBitSetLength = 1000;
+    int minBitSetLength = 2;
+    int leadMaxDoc = maxBitSetLength + 1;
+    iterators[iterators.length - 1] = DocIdSetIterator.range(leadMaxDoc, leadMaxDoc + 1);
+
+    for (int i = 0; i < numBitSetIterators; i++) {
+      int bitSetLength = TestUtil.nextInt(random(), minBitSetLength, maxBitSetLength);
+      FixedBitSet bitSet = new FixedBitSet(bitSetLength);
+      bitSet.set(0, bitSetLength - 1);
+      iterators[i] = new BitDocIdSet(bitSet).iterator();
+    }
+
+    final DocIdSetIterator conjunction =
+        ConjunctionUtils.intersectIterators(Arrays.asList(iterators));
+
+    assertEquals(NO_MORE_DOCS, conjunction.nextDoc());
+    assertEquals(NO_MORE_DOCS, conjunction.docID());
+  }
 }