Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/23130#discussion_r237062653
--- Diff:
sql/core/src/test/scala/org/apache/spark/sql/sources/SaveLoadSuite.scala ---
@@ -142,4 +144,15 @@ class SaveLoadSuite extends DataSourceTest with
SharedSQLContext with BeforeAndA
assert(e.contains(s"Partition column `$unknown` not found in schema
$schemaCatalog"))
}
}
+
+ test("skip empty files in non bucketed read") {
+ withTempDir { dir =>
+ val path = dir.getCanonicalPath
+ Files.write(Paths.get(path, "empty"), Array.empty[Byte])
+ Files.write(Paths.get(path, "notEmpty"),
"a".getBytes(StandardCharsets.UTF_8))
+ val readback = spark.read.option("wholetext", true).text(path)
+
+ assert(readback.rdd.getNumPartitions === 1)
--- End diff --
do you mean `wholetext` mode will force to create one partition per file?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
