HIVE-29556: more explicit and "future-proof" NDV sssignment for const columns

Author: konstantinb

ql/src/java/org/apache/hadoop/hive/ql/stats/StatsUtils.java

@@ -2115,7 +2115,9 @@ private static List<Long> extractNDVGroupingColumns(List<ColStatistics> colStats
     for (ColStatistics cs : colStats) {
       if (cs != null) {
         long ndv = cs.getCountDistint();
-        if (cs.getNumNulls() > 0 && (ndv > 0 || cs.isConst())) {
+        if (cs.isConst()) {
+          ndv = 1;
+        } else if (ndv > 0 && cs.getNumNulls() > 0) {
           ndv = StatsUtils.safeAdd(ndv, 1);
         }
         ndvValues.add(ndv);

ql/src/test/org/apache/hadoop/hive/ql/stats/TestStatsUtils.java

@@ -48,6 +48,7 @@
 import org.junit.jupiter.api.Test;
 import org.junit.jupiter.params.ParameterizedTest;
 import org.junit.jupiter.params.provider.Arguments;
+import org.junit.jupiter.params.provider.CsvSource;
 import org.junit.jupiter.params.provider.MethodSource;
 
 import com.google.common.collect.Sets;
@@ -625,4 +626,28 @@ void testColStatisticsIsConstSetterAndClone() {
     assertEquals(true, clone.isConst(), "Clone should be independent of source after mutation");
   }
 
+  @ParameterizedTest(name = "isConst=true => NDV contribution = 1 (countDistint={0}, numNulls={1})")
+  @CsvSource({"1, 0", "0, 10", "1, 10", "0, 0"})
+  void testComputeNDVGroupingColumnsConstColumnContributesOne(long countDistint, long numNulls) {
+    ColStatistics cs = new ColStatistics("c", "int");
+    cs.setCountDistint(countDistint);
+    cs.setNumNulls(numNulls);
+    cs.setConst(true);
+
+    long ndv = StatsUtils.computeNDVGroupingColumns(Collections.singletonList(cs), new Statistics(), false);
+
+    assertEquals(1L, ndv);
+  }
+
+  @Test
+  void testComputeNDVGroupingColumnsNonConstWithNullsAddsOne() {
+    ColStatistics cs = new ColStatistics("c", "int");
+    cs.setCountDistint(7);
+    cs.setNumNulls(3);
+
+    long ndv = StatsUtils.computeNDVGroupingColumns(Collections.singletonList(cs), new Statistics(), false);
+
+    assertEquals(8L, ndv);
+  }
+
 }