gengliangwang commented on a change in pull request #26780: [SPARK-27506][SQL]
Allow deserialization of Avro data using compatible schemas
URL: https://github.com/apache/spark/pull/26780#discussion_r356221108
##########
File path:
external/avro/src/test/scala/org/apache/spark/sql/avro/AvroFunctionsSuite.scala
##########
@@ -153,4 +153,79 @@ class AvroFunctionsSuite extends QueryTest with
SharedSparkSession {
assert(df.collect().map(_.get(0)) === Seq(Row("one"), Row("two"),
Row("three"), Row("four")))
}
}
+
+ test("SPARK-27506: roundtrip in to_avro and from_avro with different
compatible schemas") {
+ val df = spark.range(10).select(
+ struct('id.as("col1"), 'id.cast("string").as("col2")).as("struct")
+ )
+ val avroStructDF = df.select(functions.to_avro('struct).as("avro"))
+ val actualAvroSchema = s"""
+ |{
+ | "type": "record",
+ | "name": "struct",
+ | "fields": [
+ | {"name": "col1", "type": "int"},
+ | {"name": "col2", "type": "string"}
+ | ]
+ |}
Review comment:
Yes please update it. I check out the code and in IDE it looks like the way
in Github
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
