COLLECT_SET() in Hive, keep duplicates?

后端未结

关注

 9  1520

离开以前 2020-12-12 17:06

Is there a way to keep the duplicates in a collected set in Hive, or simulate the sort of aggregate collection that Hive provides using some other method? I want to aggregat

9条回答

自闭症患者 (楼主)

2020-12-12 17:49

Modified Jeff Mc's code to remove the restriction (presumably inherited from collect_set) that input must be primitive types. This version can collect structs, maps and arrays as well as primitives.

package com.example;

import java.util.ArrayList;
import org.apache.hadoop.hive.ql.exec.UDFArgumentTypeException;
import org.apache.hadoop.hive.ql.metadata.HiveException;
import org.apache.hadoop.hive.ql.parse.SemanticException;
import org.apache.hadoop.hive.ql.udf.generic.AbstractGenericUDAFResolver;
import org.apache.hadoop.hive.ql.udf.generic.GenericUDAFEvaluator;
import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector;
import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorFactory;
import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorUtils;
import org.apache.hadoop.hive.serde2.objectinspector.StandardListObjectInspector;
import org.apache.hadoop.hive.serde2.typeinfo.TypeInfo;

public class CollectAll extends AbstractGenericUDAFResolver
{
    @Override
    public GenericUDAFEvaluator getEvaluator(TypeInfo[] tis)
            throws SemanticException
    {
        if (tis.length != 1)
        {
            throw new UDFArgumentTypeException(tis.length - 1, "Exactly one argument is expected.");
        }
        return new CollectAllEvaluator();
    }

    public static class CollectAllEvaluator extends GenericUDAFEvaluator
    {
        private ObjectInspector inputOI;
        private StandardListObjectInspector loi;
        private StandardListObjectInspector internalMergeOI;

        @Override
        public ObjectInspector init(Mode m, ObjectInspector[] parameters)
                throws HiveException
        {
            super.init(m, parameters);
            if (m == Mode.PARTIAL1)
            {
                inputOI = parameters[0];
                return ObjectInspectorFactory
                        .getStandardListObjectInspector(ObjectInspectorUtils
                        .getStandardObjectInspector(inputOI));
            }
            else
            {
                if (!(parameters[0] instanceof StandardListObjectInspector))
                {
                    inputOI = ObjectInspectorUtils
                            .getStandardObjectInspector(parameters[0]);
                    return (StandardListObjectInspector) ObjectInspectorFactory
                            .getStandardListObjectInspector(inputOI);
                }
                else
                {
                    internalMergeOI = (StandardListObjectInspector) parameters[0];
                    inputOI = internalMergeOI.getListElementObjectInspector();
                    loi = (StandardListObjectInspector) ObjectInspectorUtils.getStandardObjectInspector(internalMergeOI);
                    return loi;
                }
            }
        }

        static class ArrayAggregationBuffer implements AggregationBuffer
        {
            ArrayList