thomasrebele commented on code in PR #6746:
URL: https://github.com/apache/hive/pull/6746#discussion_r4033400096
##########
ql/src/test/org/apache/hadoop/hive/ql/optimizer/calcite/stats/TestFilterSelectivityEstimator.java:
##########
@@ -1202,4 +1210,184 @@ private static long timestampMillis(String timestamp) {
private static long timestamp(String timestamp) {
return timestampMillis(timestamp) / 1000;
}
+
+ private static final int INTEGER_FIELD_INDEX = 6; // f_integer
+ private static final int DATE_FIELD_INDEX = 9; // f_date
+
+ private void setupMinMaxNoHistogram(float min, float max) {
+ setupMinMaxNoHistogram(min, max, 0);
+ }
+
+ private void setupMinMaxNoHistogram(float min, float max, long numNulls) {
+ stats = new ColStatistics();
+ stats.setHistogram(null);
+ stats.setRange(min, max);
+ stats.setNumNulls(numNulls);
+ currentInputRef = REX_BUILDER.makeInputRef(scan, INTEGER_FIELD_INDEX);
+ doReturn(Collections.singletonList(stats)).when(tableMock)
+ .getColStat(Collections.singletonList(INTEGER_FIELD_INDEX));
+ }
+
+ private RelNode createScanWithPlanner(HiveConf conf) {
+ RelOptPlanner planner = CalcitePlanner.createPlanner(conf);
+ RelOptCluster cluster = RelOptCluster.create(planner, REX_BUILDER);
+ RelBuilder relBuilder = HiveRelFactories.HIVE_BUILDER.create(cluster,
schemaMock);
+ HiveTableScan tableScan =
+ new HiveTableScan(cluster, cluster.traitSetOf(HiveRelNode.CONVENTION),
tableMock, "table", null, false, false);
+ return relBuilder.push(tableScan).build();
+ }
+
+ @Test
+ public void testComparisonMinMaxNoHistogram() {
+ setupMinMaxNoHistogram(0, 100);
+ RexNode int50 = REX_BUILDER.makeLiteral(50,
TYPE_FACTORY.createSqlType(INTEGER), true);
+ RexNode filter =
REX_BUILDER.makeCall(SqlStdOperatorTable.LESS_THAN_OR_EQUAL, currentInputRef,
int50);
+ FilterSelectivityEstimator estimator = new
FilterSelectivityEstimator(scan, mq);
+ Assert.assertEquals(0.5, estimator.estimateSelectivity(filter), DELTA);
Review Comment:
Yes, I think it makes sense to adapt the expected values so that we get the
true counts for integers and dates. I propose to wait for feedback from Hive
committers.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
