yaooqinn commented on code in PR #47212:
URL: https://github.com/apache/spark/pull/47212#discussion_r1671641309
##########
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/csv/CSVSuite.scala:
##########
@@ -3170,22 +3172,24 @@ abstract class CSVSuite
}
}
- test("SPARK-42237: change binary to unsupported dataType") {
- withTempPath { path =>
- val colName: String = "value"
- checkError(
- exception = intercept[AnalysisException] {
- Seq(Array[Byte](1, 2))
- .toDF(colName)
- .write
- .csv(path.getCanonicalPath)
- },
- errorClass = "UNSUPPORTED_DATA_TYPE_FOR_DATASOURCE",
- parameters = Map(
- "columnName" -> s"`$colName`",
- "columnType" -> "\"BINARY\"",
- "format" -> "CSV")
- )
+ test("SPARK-48807: Binary support for csv") {
+ BinaryOutputStyle.values.foreach { style =>
+ withTempPath { path =>
+ withSQLConf(SQLConf.BINARY_OUTPUT_STYLE.key -> style.toString) {
+ val df = Seq((1, "Spark SQL".getBytes())).toDF("id", "value")
+ df.write
+ .option("ds_option", "value")
+ .format(dataSourceFormat)
+ .save(path.getCanonicalPath)
+ val expectedStr = ToStringBase.getBinaryFormatter("Spark
SQL".getBytes())
Review Comment:
This helper method gets a binary formatter based on BINARY_OUTPUT_STYLE and
converts the raw bytes here to both UTF8 and non-UTF8 outputs
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
