pvary commented on a change in pull request #2078:
URL: https://github.com/apache/iceberg/pull/2078#discussion_r557449942
##########
File path: mr/src/main/java/org/apache/iceberg/mr/hive/Deserializer.java
##########
@@ -78,62 +82,55 @@ Record deserialize(Object data) {
return (Record) fieldDeserializer.value(data);
}
- private Deserializer(Schema schema, ObjectInspector fieldInspector) {
- this.fieldDeserializer = DeserializerVisitor.visit(schema, fieldInspector);
+ private Deserializer(Schema schema, ObjectInspectorPair pair) {
+ this.fieldDeserializer = DeserializerVisitor.visit(schema, pair);
}
- private static class DeserializerVisitor extends
SchemaWithPartnerVisitor<ObjectInspector, FieldDeserializer> {
+ private static class DeserializerVisitor extends
SchemaWithPartnerVisitor<ObjectInspectorPair, FieldDeserializer> {
- public static FieldDeserializer visit(Schema schema, ObjectInspector
objectInspector) {
- return visit(schema, new FixNameMappingObjectInspector(schema,
objectInspector), new DeserializerVisitor(),
+ public static FieldDeserializer visit(Schema schema, ObjectInspectorPair
pair) {
+ return visit(schema, new FixNameMappingObjectInspectorPair(schema,
pair), new DeserializerVisitor(),
new PartnerObjectInspectorByNameAccessors());
}
@Override
- public FieldDeserializer schema(Schema schema, ObjectInspector inspector,
FieldDeserializer deserializer) {
+ public FieldDeserializer schema(Schema schema, ObjectInspectorPair pair,
FieldDeserializer deserializer) {
return deserializer;
}
@Override
- public FieldDeserializer field(NestedField field, ObjectInspector
inspector, FieldDeserializer deserializer) {
+ public FieldDeserializer field(NestedField field, ObjectInspectorPair
pair, FieldDeserializer deserializer) {
return deserializer;
}
@Override
- public FieldDeserializer primitive(PrimitiveType type, ObjectInspector
inspector) {
- switch (type.typeId()) {
- case BOOLEAN:
- case INTEGER:
- case LONG:
- case FLOAT:
- case DOUBLE:
- case STRING:
- // Generic conversions where Iceberg and Hive are using the same
java object
- return o -> ((PrimitiveObjectInspector)
inspector).getPrimitiveJavaObject(o);
- case UUID:
- // TODO: This will not work with Parquet. Parquet UUID expect
byte[], others are expecting UUID
- return o -> UUID.fromString(((StringObjectInspector)
inspector).getPrimitiveJavaObject(o));
- case DATE:
- case TIMESTAMP:
- case FIXED:
- case BINARY:
- case DECIMAL:
- // Iceberg specific conversions
- return o -> ((WriteObjectInspector) inspector).convert(o);
- case TIME:
- default:
- throw new IllegalArgumentException("Unsupported column type: " +
type);
- }
+ public FieldDeserializer primitive(PrimitiveType type, ObjectInspectorPair
pair) {
+ return o -> {
+ if (o == null) {
+ return null;
+ }
+
+ ObjectInspector writerFieldInspector = pair.writerInspector();
+ ObjectInspector sourceFieldInspector = pair.sourceInspector();
+
+ Object result = ((PrimitiveObjectInspector)
sourceFieldInspector).getPrimitiveJavaObject(o);
+ if (writerFieldInspector instanceof WriteObjectInspector) {
Review comment:
The original version was to use the Writable as an input for the
`convert()`. In this new version `convert()` uses the native Hive object instead
----------------------------------------------------------------
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]
