attilapiros commented on a change in pull request #31133:
URL: https://github.com/apache/spark/pull/31133#discussion_r558813362
##########
File path:
sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveDDLSuite.scala
##########
@@ -1883,6 +1883,60 @@ class HiveDDLSuite
}
}
+ test("SPARK-26836: support Avro schema evolution") {
+ withTable("t") {
+ val originalSchema =
+ """
+ |{
+ | "namespace": "test",
+ | "name": "some_schema",
+ | "type": "record",
+ | "fields": [
+ | {
+ | "name": "col2",
+ | "type": "string"
+ | }
+ | ]
+ |}
+ """.stripMargin
+ sql(
+ s"""
+ |CREATE TABLE t PARTITIONED BY (ds string)
+ |ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.avro.AvroSerDe'
+ |WITH SERDEPROPERTIES ('avro.schema.literal'='$originalSchema')
+ |STORED AS
+ |INPUTFORMAT
'org.apache.hadoop.hive.ql.io.avro.AvroContainerInputFormat'
+ |OUTPUTFORMAT
'org.apache.hadoop.hive.ql.io.avro.AvroContainerOutputFormat'
+ """.stripMargin)
+ sql("INSERT INTO t partition (ds='1981-01-07') VALUES ('col2_value')")
+ val evolvedSchema =
+ """
+ |{
+ | "namespace": "test",
+ | "name": "some_schema",
+ | "type": "record",
+ | "fields": [
+ | {
+ | "name": "col1",
+ | "type": "string",
+ | "default": "col1_default"
+ | },
+ | {
+ | "name": "col2",
+ | "type": "string"
+ | }
+ | ]
+ |}
+ """.stripMargin
+ sql(s"""ALTER TABLE t SET SERDEPROPERTIES
('avro.schema.literal'='$evolvedSchema')""")
+ sql("INSERT INTO t partition (ds='1983-04-27') VALUES ('col1_value',
'col2_value')")
+ withSQLConf(SQLConf.HIVE_AVRO_SCHEMA_EVOLUTION_ENABLED.key -> "true") {
+ checkAnswer(spark.table("t"), Row("col1_default", "col2_value",
"1981-01-07")
+ :: Row("col1_value", "col2_value", "1983-04-27") :: Nil)
+ }
Review comment:
During the development of our new test I realized to use default value
of the schema is only possible via adding a new column. As NULL is different
from the missing value thus will not be mapped to default but to the "null"
value in the file.
And INSERT always requires to have a value specified for each of the column.
Based on these new findings I am removing
`spark.sql.hive.avroSchemaEvolution.enabled` and always use the table schema
when available.
----------------------------------------------------------------
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
