Github user HyukjinKwon commented on a diff in the pull request:
https://github.com/apache/spark/pull/16928#discussion_r102490842
--- Diff:
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/csv/CSVSuite.scala
---
@@ -958,4 +959,59 @@ class CSVSuite extends QueryTest with SharedSQLContext
with SQLTestUtils {
checkAnswer(df, Row(1, null))
}
}
+
+ test("SPARK-18699 put malformed records in a `columnNameOfCorruptRecord`
field") {
+ val schema = new StructType().add("a", IntegerType).add("b",
TimestampType)
+ val df1 = spark
+ .read
+ .option("mode", "PERMISSIVE")
+ .schema(schema)
+ .csv(testFile(valueMalformedFile))
+ checkAnswer(df1,
+ Row(null, null) ::
+ Row(1, java.sql.Date.valueOf("1983-08-04")) ::
+ Nil)
+
+ // If `schema` has `columnNameOfCorruptRecord`, it should handle
corrupt records
+ val columnNameOfCorruptRecord = "_unparsed"
+ val schemaWithCorrField1 = schema.add(columnNameOfCorruptRecord,
StringType)
+ val df2 = spark
+ .read
+ .option("mode", "PERMISSIVE")
+ .option("columnNameOfCorruptRecord", columnNameOfCorruptRecord)
+ .schema(schemaWithCorrField1)
+ .csv(testFile(valueMalformedFile))
+ checkAnswer(df2,
+ Row(null, null, "0,2013-111-11 12:13:14") ::
+ Row(1, java.sql.Date.valueOf("1983-08-04"), null) ::
+ Nil)
+
+ // We put a `columnNameOfCorruptRecord` field in the middle of a schema
+ new StructType
--- End diff --
It seems mistakenly added.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
