[
https://issues.apache.org/jira/browse/SPARK-27027?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Hyukjin Kwon updated SPARK-27027:
---------------------------------
Description:
{{from_avro}} function produces wrong output of a struct field. See the output
at the bottom of the description
{code}
import org.apache.spark.sql.types._
import org.apache.spark.sql.avro._
import org.apache.spark.sql.functions._
spark.version
val df = Seq((1, "John Doe", 30), (2, "Mary Jane", 25), (3, "Josh Duke",
50)).toDF("id", "name", "age")
val dfStruct = df.withColumn("value", struct("name","age"))
dfStruct.show
dfStruct.printSchema
val dfKV = dfStruct.select(to_avro('id).as("key"), to_avro('value).as("value"))
val expectedSchema = StructType(Seq(StructField("name", StringType,
true),StructField("age", IntegerType, false)))
val avroTypeStruct = SchemaConverters.toAvroType(expectedSchema).toString
val avroTypeStr = s"""
|{
| "type": "int",
| "name": "key"
|}
""".stripMargin
dfKV.select(from_avro('key, avroTypeStr)).show
dfKV.select(from_avro('value, avroTypeStruct)).show
// output for the last statement and that is not correct
+---------------------------------------------+
|from_avro(value, struct<name:string,age:int>)|
+---------------------------------------------+
| [Josh Duke, 50]|
| [Josh Duke, 50]|
| [Josh Duke, 50]|
+---------------------------------------------+
{code}
was:
from_avro function produces wrong output of a struct field. See the output at
the bottom of the description
=====================================================
import org.apache.spark.sql.types._
import org.apache.spark.sql.avro._
import org.apache.spark.sql.functions._
spark.version
val df = Seq((1, "John Doe", 30), (2, "Mary Jane", 25), (3, "Josh Duke",
50)).toDF("id", "name", "age")
val dfStruct = df.withColumn("value", struct("name","age"))
dfStruct.show
dfStruct.printSchema
val dfKV = dfStruct.select(to_avro('id).as("key"), to_avro('value).as("value"))
val expectedSchema = StructType(Seq(StructField("name", StringType,
true),StructField("age", IntegerType, false)))
val avroTypeStruct = SchemaConverters.toAvroType(expectedSchema).toString
val avroTypeStr = s"""
|{
| "type": "int",
| "name": "key"
|}
""".stripMargin
dfKV.select(from_avro('key, avroTypeStr)).show
dfKV.select(from_avro('value, avroTypeStruct)).show
// output for the last statement and that is not correct
+---------------------------------------------+
|from_avro(value, struct<name:string,age:int>)|
+---------------------------------------------+
| [Josh Duke, 50]|
| [Josh Duke, 50]|
| [Josh Duke, 50]|
+---------------------------------------------+
> from_avro function does not deserialize the Avro record of a struct column
> type correctly
> -----------------------------------------------------------------------------------------
>
> Key: SPARK-27027
> URL: https://issues.apache.org/jira/browse/SPARK-27027
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 2.4.0
> Reporter: Hien Luu
> Priority: Minor
>
> {{from_avro}} function produces wrong output of a struct field. See the
> output at the bottom of the description
> {code}
> import org.apache.spark.sql.types._
> import org.apache.spark.sql.avro._
> import org.apache.spark.sql.functions._
> spark.version
> val df = Seq((1, "John Doe", 30), (2, "Mary Jane", 25), (3, "Josh Duke",
> 50)).toDF("id", "name", "age")
> val dfStruct = df.withColumn("value", struct("name","age"))
> dfStruct.show
> dfStruct.printSchema
> val dfKV = dfStruct.select(to_avro('id).as("key"),
> to_avro('value).as("value"))
> val expectedSchema = StructType(Seq(StructField("name", StringType,
> true),StructField("age", IntegerType, false)))
> val avroTypeStruct = SchemaConverters.toAvroType(expectedSchema).toString
> val avroTypeStr = s"""
> |{
> | "type": "int",
> | "name": "key"
> |}
> """.stripMargin
> dfKV.select(from_avro('key, avroTypeStr)).show
> dfKV.select(from_avro('value, avroTypeStruct)).show
> // output for the last statement and that is not correct
> +---------------------------------------------+
> |from_avro(value, struct<name:string,age:int>)|
> +---------------------------------------------+
> | [Josh Duke, 50]|
> | [Josh Duke, 50]|
> | [Josh Duke, 50]|
> +---------------------------------------------+
> {code}
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
