[
https://issues.apache.org/jira/browse/FLINK-3475?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15871698#comment-15871698
]
ASF GitHub Bot commented on FLINK-3475:
---------------------------------------
Github user fhueske commented on a diff in the pull request:
https://github.com/apache/flink/pull/3111#discussion_r101733431
--- Diff:
flink-libraries/flink-table/src/test/scala/org/apache/flink/table/api/scala/batch/sql/AggregationsITCase.scala
---
@@ -213,34 +213,45 @@ class AggregationsITCase(
TestBaseUtils.compareResultAsText(results.asJava, expected)
}
- @Test(expected = classOf[TableException])
+ @Test
def testDistinctAggregate(): Unit = {
val env = ExecutionEnvironment.getExecutionEnvironment
val tEnv = TableEnvironment.getTableEnvironment(env, config)
val sqlQuery = "SELECT sum(_1) as a, count(distinct _3) as b FROM
MyTable"
- val ds = CollectionDataSets.get3TupleDataSet(env)
- tEnv.registerDataSet("MyTable", ds)
+ val ds = env.fromElements(
+ (1, 1L, 1.0f, "Hello"),
+ (2, 2L, 1.0f, "Ciao")).toTable(tEnv)
+ tEnv.registerTable("MyTable", ds)
- // must fail. distinct aggregates are not supported
- tEnv.sql(sqlQuery).toDataSet[Row]
+ val result = tEnv.sql(sqlQuery)
+
+ val expected = "3,1"
+ val results = result.toDataSet[Row].collect()
+ TestBaseUtils.compareResultAsText(results.asJava, expected)
}
- @Test(expected = classOf[TableException])
+ @Test
def testGroupedDistinctAggregate(): Unit = {
val env = ExecutionEnvironment.getExecutionEnvironment
val tEnv = TableEnvironment.getTableEnvironment(env, config)
val sqlQuery = "SELECT _2, avg(distinct _1) as a, count(_3) as b FROM
MyTable GROUP BY _2"
- val ds = CollectionDataSets.get3TupleDataSet(env)
- tEnv.registerDataSet("MyTable", ds)
+ val ds = env.fromElements(
--- End diff --
I think it would be good to use a bit more test data here, like on of the
`CollectionDataSets`.
ITCases are rather expensive to run, so we should to get the most out of
them.
> DISTINCT aggregate function support for SQL queries
> ---------------------------------------------------
>
> Key: FLINK-3475
> URL: https://issues.apache.org/jira/browse/FLINK-3475
> Project: Flink
> Issue Type: New Feature
> Components: Table API & SQL
> Reporter: Chengxiang Li
> Assignee: Zhenghua Gao
>
> DISTINCT aggregate function may be able to reuse the aggregate function
> instead of separate implementation, and let Flink runtime take care of
> duplicate records.
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
