Github user fhueske commented on a diff in the pull request:

    https://github.com/apache/flink/pull/2169#discussion_r69048813
  
    --- Diff: 
flink-libraries/flink-table/src/test/scala/org/apache/flink/api/scala/batch/table/SetOperationsITCase.scala
 ---
    @@ -139,4 +154,105 @@ class UnionITCase(
         // Must fail. Tables are bound to different TableEnvironments.
         ds1.unionAll(ds2).select('c)
       }
    +
    +  @Test
    +  def testSetMinusAll(): Unit = {
    +    val env: ExecutionEnvironment = 
ExecutionEnvironment.getExecutionEnvironment
    +    val tEnv = TableEnvironment.getTableEnvironment(env, config)
    +
    +    val ds1 = CollectionDataSets.getSmall3TupleDataSet(env).toTable(tEnv, 
'a, 'b, 'c)
    +    val ds2 = 
CollectionDataSets.getOneElement3TupleDataSet(env).toTable(tEnv, 'a, 'b, 'c)
    +
    +    val minusDs = ds1.minusAll(ds2).select('c)
    +
    +    val results = minusDs.toDataSet[Row].collect()
    +    val expected = "Hello\n" + "Hello world\n"
    +    TestBaseUtils.compareResultAsText(results.asJava, expected)
    +  }
    +
    +  @Test
    +  def testSetMinusAllWithDuplicates(): Unit = {
    +    val env: ExecutionEnvironment = 
ExecutionEnvironment.getExecutionEnvironment
    +    val tEnv = TableEnvironment.getTableEnvironment(env, config)
    +
    +    val ds1 = CollectionDataSets.getSmall3TupleDataSet(env).toTable(tEnv, 
'a, 'b, 'c)
    +    val ds2 = CollectionDataSets.getSmall3TupleDataSet(env).toTable(tEnv, 
'a, 'b, 'c)
    +    val ds3 = 
CollectionDataSets.getOneElement3TupleDataSet(env).toTable(tEnv, 'a, 'b, 'c)
    +
    +    val minusDs = ds1.unionAll(ds2).minusAll(ds3).select('c)
    +
    +    val results = minusDs.toDataSet[Row].collect()
    +    val expected = "Hello\n" + "Hello world\n" +
    +      "Hello\n" + "Hello world\n"
    +    TestBaseUtils.compareResultAsText(results.asJava, expected)
    +  }
    +
    +  @Test
    +  def testSetMinus(): Unit = {
    --- End diff --
    
    Can you combine this and the next test by using test data that covers both 
cases for different records, i.e., have some records with duplicates in this 
first, second, none, and both data sets.


---
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.
---

Reply via email to