Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/16395#discussion_r101655854
--- Diff:
sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/statsEstimation/FilterEstimationSuite.scala
---
@@ -0,0 +1,376 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.sql.catalyst.statsEstimation
+
+import java.sql.{Date, Timestamp}
+
+import org.apache.spark.sql.catalyst.expressions._
+import org.apache.spark.sql.catalyst.plans.logical._
+import
org.apache.spark.sql.catalyst.plans.logical.statsEstimation.EstimationUtils._
+import org.apache.spark.sql.catalyst.util.DateTimeUtils
+import org.apache.spark.sql.types._
+
+/**
+ * In this test suite, we test predicates containing the following
operators:
+ * =, <, <=, >, >=, AND, OR, IS NULL, IS NOT NULL, IN, NOT IN
+ */
+class FilterEstimationSuite extends StatsEstimationTestBase {
+
+ // Suppose our test table has 10 rows and 6 columns.
+ // First column cint has values: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10
+ // Hence, distinctCount:10, min:1, max:10, nullCount:0, avgLen:4,
maxLen:4
+ val arInt = AttributeReference("cint", IntegerType)()
+ val childColStatInt = ColumnStat(distinctCount = 10, min = Some(1), max
= Some(10),
+ nullCount = 0, avgLen = 4, maxLen = 4)
+
+ // Second column cdate has 10 values from 2017-01-01 through 2017-01-10.
+ val dMin = Date.valueOf("2017-01-01")
+ val dMax = Date.valueOf("2017-01-10")
+ val arDate = AttributeReference("cdate", DateType)()
+ val childColStatDate = ColumnStat(distinctCount = 10, min = Some(dMin),
max = Some(dMax),
+ nullCount = 0, avgLen = 4, maxLen = 4)
+
+ // Third column ctimestamp has 10 values from "2017-01-01 01:00:00"
through
+ // "2017-01-01 10:00:00" for 10 distinct timestamps (or hours).
+ val tsMin = Timestamp.valueOf("2017-01-01 01:00:00")
+ val tsMax = Timestamp.valueOf("2017-01-01 10:00:00")
+ val arTimestamp = AttributeReference("ctimestamp", TimestampType)()
+ val childColStatTimestamp = ColumnStat(distinctCount = 10, min =
Some(tsMin), max = Some(tsMax),
+ nullCount = 0, avgLen = 8, maxLen = 8)
+
+ // Fourth column cdate has 10 values from 0.20 through 2.00 at increment
of 0.2.
+ val decMin = new java.math.BigDecimal("0.200000000000000000")
+ val decMax = new java.math.BigDecimal("2.000000000000000000")
+ val arDecimal = AttributeReference("cdecimal", DecimalType(12, 2))()
+ val childColStatDecimal = ColumnStat(distinctCount = 10, min =
Some(decMin), max = Some(decMax),
+ nullCount = 0, avgLen = 8, maxLen = 8)
+
+ // Fifth column cfloat has 10 float values: 1.0, 2.0, 3.0, 4.0, 5.0,
6.0, 7.0, 8.0, 9.0, 10.0
+ val arFloat = AttributeReference("cfloat", FloatType)()
--- End diff --
FloatType and DoubleType have the same code path, we should only test one
of them
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
