Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[SPARK-27858][SQL] Fix for avro deserialization on union types with multiple non-null types #24722

Closed
wants to merge 2 commits into from
Closed

[SPARK-27858][SQL] Fix for avro deserialization on union types with multiple non-null types #24722

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ee97960
fix for avro deserialization
May 27, 2019
4edbe09
apply minor tweaks
May 28, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion external/avro/src/main/scala/org/apache/spark/sql/avro/AvroDeserializer.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -225,6 +225,7 @@ class AvroDeserializer(rootAvroType: Schema, rootCatalystType: DataType) {
case (UNION, _) =>
val allTypes = avroType.getTypes.asScala
val nonNullTypes = allTypes.filter(_.getType != NULL)
val nonNullAvroType = Schema.createUnion(nonNullTypes.asJava)
if (nonNullTypes.nonEmpty) {
if (nonNullTypes.length == 1) {
newWriter(nonNullTypes.head, catalystType, path)
Expand Down Expand Up @@ -253,7 +254,7 @@ class AvroDeserializer(rootAvroType: Schema, rootCatalystType: DataType) {
(updater, ordinal, value) => {
val row = new SpecificInternalRow(st)
val fieldUpdater = new RowUpdater(row)
val i = GenericData.get().resolveUnion(avroType, value)
val i = GenericData.get().resolveUnion(nonNullAvroType, value)
fieldWriters(i)(fieldUpdater, i, value)
updater.set(ordinal, row)
}
Expand Down
26 changes: 26 additions & 0 deletions external/avro/src/test/scala/org/apache/spark/sql/avro/AvroSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -247,6 +247,32 @@ class AvroSuite extends QueryTest with SharedSQLContext with SQLTestUtils {
}
}

test("SPARK-27858 Union type: More than one non-null type") {
withTempDir { dir =>
val complexNullUnionType = Schema.createUnion(
List(Schema.create(Type.INT), Schema.create(Type.NULL), Schema.create(Type.STRING)).asJava)
val fields = Seq(
new Field("field1", complexNullUnionType, "doc", null.asInstanceOf[AnyVal])).asJava
val schema = Schema.createRecord("name", "docs", "namespace", false)
schema.setFields(fields)
val datumWriter = new GenericDatumWriter[GenericRecord](schema)
val dataFileWriter = new DataFileWriter[GenericRecord](datumWriter)
dataFileWriter.create(schema, new File(s"$dir.avro"))
val avroRec = new GenericData.Record(schema)
avroRec.put("field1", 42)
dataFileWriter.append(avroRec)
val avroRec2 = new GenericData.Record(schema)
avroRec2.put("field1", "Alice")
dataFileWriter.append(avroRec2)
dataFileWriter.flush()
dataFileWriter.close()

val df = spark.read.format("avro").load(s"$dir.avro")
assert(df.schema === StructType.fromDDL("field1 struct<member0: int, member1: string>"))
assert(df.collect().toSet == Set(Row(Row(42, null)), Row(Row(null, "Alice"))))
}
}

test("Complex Union Type") {
withTempPath { dir =>
val fixedSchema = Schema.createFixed("fixed_name", "doc", "namespace", 4)
Expand Down