Search in sources :

Example 6 with LogicalTypeAnnotation

use of org.apache.parquet.schema.LogicalTypeAnnotation in project hive by apache.

the class DataWritableWriter method createWriter.

/**
 * Creates a writer for the specific object inspector. The returned writer will be used
 * to call Parquet API for the specific data type.
 * @param inspector The object inspector used to get the correct value type.
 * @param type Type that contains information about the type schema.
 * @return A ParquetWriter object used to call the Parquet API fo the specific data type.
 */
private DataWriter createWriter(ObjectInspector inspector, Type type) {
    if (type.isPrimitive()) {
        checkInspectorCategory(inspector, ObjectInspector.Category.PRIMITIVE);
        PrimitiveObjectInspector primitiveInspector = (PrimitiveObjectInspector) inspector;
        switch(primitiveInspector.getPrimitiveCategory()) {
            case BOOLEAN:
                return new BooleanDataWriter((BooleanObjectInspector) inspector);
            case BYTE:
                return new ByteDataWriter((ByteObjectInspector) inspector);
            case SHORT:
                return new ShortDataWriter((ShortObjectInspector) inspector);
            case INT:
                return new IntDataWriter((IntObjectInspector) inspector);
            case LONG:
                return new LongDataWriter((LongObjectInspector) inspector);
            case FLOAT:
                return new FloatDataWriter((FloatObjectInspector) inspector);
            case DOUBLE:
                return new DoubleDataWriter((DoubleObjectInspector) inspector);
            case STRING:
                return new StringDataWriter((StringObjectInspector) inspector);
            case CHAR:
                return new CharDataWriter((HiveCharObjectInspector) inspector);
            case VARCHAR:
                return new VarcharDataWriter((HiveVarcharObjectInspector) inspector);
            case BINARY:
                return new BinaryDataWriter((BinaryObjectInspector) inspector);
            case TIMESTAMP:
                return new TimestampDataWriter((TimestampObjectInspector) inspector);
            case DECIMAL:
                return new DecimalDataWriter((HiveDecimalObjectInspector) inspector);
            case DATE:
                return new DateDataWriter((DateObjectInspector) inspector);
            default:
                throw new IllegalArgumentException("Unsupported primitive data type: " + primitiveInspector.getPrimitiveCategory());
        }
    } else {
        GroupType groupType = type.asGroupType();
        LogicalTypeAnnotation logicalType = type.getLogicalTypeAnnotation();
        if (logicalType != null && logicalType instanceof ListLogicalTypeAnnotation) {
            checkInspectorCategory(inspector, ObjectInspector.Category.LIST);
            return new ListDataWriter((ListObjectInspector) inspector, groupType);
        } else if (logicalType != null && logicalType instanceof MapLogicalTypeAnnotation) {
            checkInspectorCategory(inspector, ObjectInspector.Category.MAP);
            return new MapDataWriter((MapObjectInspector) inspector, groupType);
        } else {
            checkInspectorCategory(inspector, ObjectInspector.Category.STRUCT);
            return new StructDataWriter((StructObjectInspector) inspector, groupType);
        }
    }
}
Also used : MapLogicalTypeAnnotation(org.apache.parquet.schema.LogicalTypeAnnotation.MapLogicalTypeAnnotation) LogicalTypeAnnotation(org.apache.parquet.schema.LogicalTypeAnnotation) ListLogicalTypeAnnotation(org.apache.parquet.schema.LogicalTypeAnnotation.ListLogicalTypeAnnotation) MapObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.MapObjectInspector) MapLogicalTypeAnnotation(org.apache.parquet.schema.LogicalTypeAnnotation.MapLogicalTypeAnnotation) GroupType(org.apache.parquet.schema.GroupType) ListLogicalTypeAnnotation(org.apache.parquet.schema.LogicalTypeAnnotation.ListLogicalTypeAnnotation) PrimitiveObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.PrimitiveObjectInspector) StructObjectInspector(org.apache.hadoop.hive.serde2.objectinspector.StructObjectInspector)

Aggregations

LogicalTypeAnnotation (org.apache.parquet.schema.LogicalTypeAnnotation)6 TypeInfo (org.apache.hadoop.hive.serde2.typeinfo.TypeInfo)4 CharTypeInfo (org.apache.hadoop.hive.serde2.typeinfo.CharTypeInfo)2 DecimalTypeInfo (org.apache.hadoop.hive.serde2.typeinfo.DecimalTypeInfo)2 ListTypeInfo (org.apache.hadoop.hive.serde2.typeinfo.ListTypeInfo)2 MapTypeInfo (org.apache.hadoop.hive.serde2.typeinfo.MapTypeInfo)2 PrimitiveTypeInfo (org.apache.hadoop.hive.serde2.typeinfo.PrimitiveTypeInfo)2 VarcharTypeInfo (org.apache.hadoop.hive.serde2.typeinfo.VarcharTypeInfo)2 GroupType (org.apache.parquet.schema.GroupType)2 DecimalLogicalTypeAnnotation (org.apache.parquet.schema.LogicalTypeAnnotation.DecimalLogicalTypeAnnotation)2 StringLogicalTypeAnnotation (org.apache.parquet.schema.LogicalTypeAnnotation.StringLogicalTypeAnnotation)2 TimestampLogicalTypeAnnotation (org.apache.parquet.schema.LogicalTypeAnnotation.TimestampLogicalTypeAnnotation)2 MessageType (org.apache.parquet.schema.MessageType)2 Type (org.apache.parquet.schema.Type)2 ZoneId (java.time.ZoneId)1 Optional (java.util.Optional)1 ArrayType (org.apache.flink.table.types.logical.ArrayType)1 DecimalType (org.apache.flink.table.types.logical.DecimalType)1 LocalZonedTimestampType (org.apache.flink.table.types.logical.LocalZonedTimestampType)1 MapType (org.apache.flink.table.types.logical.MapType)1