Github user gatorsmile commented on a diff in the pull request:
https://github.com/apache/spark/pull/20525#discussion_r166540368
--- Diff:
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/FileFormatWriterSuite.scala
---
@@ -32,6 +33,24 @@ class FileFormatWriterSuite extends QueryTest with
SharedSQLContext {
}
}
+ test("SPARK-23271 empty dataframe when saved in parquet should write a
metadata only file") {
+ withTempDir { inputPath =>
+ withTempPath { outputPath =>
+ val anySchema = StructType(StructField("anyName", StringType) ::
Nil)
+ val df = spark.read.schema(anySchema).csv(inputPath.toString)
+ df.write.parquet(outputPath.toString)
+ val partFiles = outputPath.listFiles()
+ .filter(f => f.isFile && !f.getName.startsWith(".") &&
!f.getName.startsWith("_"))
+ assert(partFiles.length === 1)
+
+ // Now read the file.
+ val df1 = spark.read.parquet(outputPath.toString)
--- End diff --
Nit: extra space before `df1`
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
