jaceklaskowski commented on a change in pull request #31296:
URL: https://github.com/apache/spark/pull/31296#discussion_r566453163



##########
File path: sql/core/src/test/scala/org/apache/spark/sql/DatasetSuite.scala
##########
@@ -2007,6 +2007,54 @@ class DatasetSuite extends QueryTest
 
     checkAnswer(withUDF, Row(Row(1), null, null) :: Row(Row(1), null, null) :: 
Nil)
   }
+
+  test("SPARK-34205: Pipe Dataset") {
+    assume(TestUtils.testCommandAvailable("cat"))
+
+    val nums = spark.range(4)
+    val piped = nums.pipe("cat", (l, printFunc) => printFunc(l.toString)).toDF
+
+    checkAnswer(piped, Row("0") :: Row("1") :: Row("2") :: Row("3") :: Nil)
+
+    val piped2 = nums.pipe("wc -l", (l, printFunc) => 
printFunc(l.toString)).toDF.collect()

Review comment:
       nit: Why `toDF`?

##########
File path: sql/core/src/test/scala/org/apache/spark/sql/DatasetSuite.scala
##########
@@ -2007,6 +2007,54 @@ class DatasetSuite extends QueryTest
 
     checkAnswer(withUDF, Row(Row(1), null, null) :: Row(Row(1), null, null) :: 
Nil)
   }
+
+  test("SPARK-34205: Pipe Dataset") {
+    assume(TestUtils.testCommandAvailable("cat"))
+
+    val nums = spark.range(4)
+    val piped = nums.pipe("cat", (l, printFunc) => printFunc(l.toString)).toDF

Review comment:
       nit: any reason for `toDF` (as `pipe` gives a `Dataset[String]`)?

##########
File path: 
sql/core/src/test/scala/org/apache/spark/sql/streaming/StreamSuite.scala
##########
@@ -1264,6 +1264,20 @@ class StreamSuite extends StreamTest {
       }
     }
   }
+
+  test("SPARK-34205: Pipe Streaming Dataset") {
+    assume(TestUtils.testCommandAvailable("cat"))
+
+    val inputData = MemoryStream[Int]
+    val piped = inputData.toDS()
+      .pipe("cat", (n, printFunc) => printFunc(n.toString)).toDF

Review comment:
       nit: Why `toDF`?




----------------------------------------------------------------
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.

For queries about this service, please contact Infrastructure at:
[email protected]



---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to