Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/19464#discussion_r144604878
--- Diff: core/src/test/scala/org/apache/spark/FileSuite.scala ---
@@ -510,4 +510,87 @@ class FileSuite extends SparkFunSuite with
LocalSparkContext {
}
}
+ test("spark.files.ignoreEmptySplits work correctly (old Hadoop API)") {
+ val conf = new SparkConf()
+ conf.setAppName("test").setMaster("local").set(IGNORE_EMPTY_SPLITS,
true)
+ sc = new SparkContext(conf)
+
+ def testIgnoreEmptySplits(
+ data: Array[Tuple2[String, String]],
+ actualPartitionNum: Int,
+ expectedPart: String,
+ expectedPartitionNum: Int): Unit = {
+ val output = new File(tempDir, "output")
+ sc.parallelize(data, actualPartitionNum)
+ .saveAsHadoopFile[TextOutputFormat[String, String]](output.getPath)
+ assert(new File(output, expectedPart).exists() === true)
--- End diff --
I don't think we need the `expectedPart` parameter, just
```
for (i <- 0 until actualPartitionNum) {
assert(new File(output, s"part-0000$i").exists() === true)
}
```
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
