Github user liutang123 commented on a diff in the pull request:
https://github.com/apache/spark/pull/19464#discussion_r144235787
--- Diff: core/src/test/scala/org/apache/spark/FileSuite.scala ---
@@ -510,4 +510,16 @@ class FileSuite extends SparkFunSuite with
LocalSparkContext {
}
}
+ test("spark.hadoop.filterOutEmptySplit") {
+ val sf = new SparkConf()
+
sf.setAppName("test").setMaster("local").set("spark.hadoop.filterOutEmptySplit",
"true")
+ sc = new SparkContext(sf)
+ val emptyRDD = sc.parallelize(Array.empty[Tuple2[String, String]], 1)
+ emptyRDD.saveAsHadoopFile[TextOutputFormat[String,
String]](tempDir.getPath + "/output")
+ assert(new File(tempDir.getPath + "/output/part-00000").exists() ===
true)
+
+ val hadoopRDD = sc.textFile(tempDir.getPath + "/output/part-00000")
+ assert(hadoopRDD.partitions.length === 0)
--- End diff --
The resources will be recycled by default in the afterEach function.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
