UDAF 사례

10093 단어 데이터 창고Java

30 분 동안 action 수집id, list 로 집합



    4.0.0

    netease.bigdata.course
    etl
    pom
    1.0-SNAPSHOT


    
        UTF-8
        UTF-8
    

    
        
            org.apache.hadoop
            hadoop-client
            2.7.6
            provided 
        
        
            com.alibaba
            fastjson
            1.2.4
        
        
            org.anarres.lzo
            lzo-hadoop
            1.0.0
        
        
            org.apache.hive
            hive-exec
            1.2.2
            provided
        
        
            org.apache.hive
            hive-contrib
            1.2.2
            provided
        
        
            junit
            junit
            4.12
        
    

    
        src/main/java
        
            
                org.apache.maven.plugins
                maven-assembly-plugin
                
                    
                        jar-with-dependencies
                    
                
                
                    
                        make-assembly
                        package
                        
                            single
                        
                    
                
            
            
                org.apache.maven.plugins
                maven-compiler-plugin
                
                    6
                    6
                
            
        
    

package com.bigdata.etl.udf;

import com.google.common.collect.Lists;
import com.google.common.collect.Maps;
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.PrimitiveObjectInspector;
import org.apache.hadoop.hive.serde2.objectinspector.StandardMapObjectInspector;
import org.apache.hadoop.hive.serde2.typeinfo.TypeInfo;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;

import java.util.Collections;
import java.util.Comparator;
import java.util.HashMap;
import java.util.List;
import java.util.Map;

public class UDAFCollectIn30Minutes extends AbstractGenericUDAFResolver {
    @Override
    public GenericUDAFEvaluator getEvaluator(TypeInfo[] info) throws SemanticException {
        if (info.length != 2) {
            throw new UDFArgumentTypeException(info.length - 1, "Exactly two arguments is expected.");
        }
        if (info[0].getCategory() != ObjectInspector.Category.PRIMITIVE) {
            throw new UDFArgumentTypeException(0, "Only primitive type arguments are accepted.");
        }
        if (info[1].getCategory() != ObjectInspector.Category.PRIMITIVE) {
            throw new UDFArgumentTypeException(0, "Only primitive type arguments are accepted.");
        }
        return new CollectActiveNameUDAFEvaluator();
    }

    public static class CollectActiveNameUDAFEvaluator extends GenericUDAFEvaluator {

        protected PrimitiveObjectInspector inputKeyOI;                         //     0
        protected PrimitiveObjectInspector inputValueOI;                       //     1
        protected StandardMapObjectInspector internalMergeOI;

        @Override
        public ObjectInspector init(Mode m, ObjectInspector[] parameters) throws HiveException {
            super.init(m, parameters);
            if (m == Mode.PARTIAL1) {
                inputKeyOI = (PrimitiveObjectInspector) parameters[0];
                inputValueOI = (PrimitiveObjectInspector) parameters[1];
                return ObjectInspectorFactory.getStandardMapObjectInspector(ObjectInspectorUtils.getStandardObjectInspector(inputKeyOI), ObjectInspectorUtils.getStandardObjectInspector(inputValueOI));
            } else if (m == Mode.PARTIAL2) {
                internalMergeOI = (StandardMapObjectInspector) parameters[0];
                inputKeyOI = (PrimitiveObjectInspector) internalMergeOI.getMapKeyObjectInspector();
                inputValueOI = (PrimitiveObjectInspector) internalMergeOI.getMapValueObjectInspector();
                return ObjectInspectorUtils.getStandardObjectInspector(internalMergeOI);
            } else if (m == Mode.FINAL) {
                internalMergeOI = (StandardMapObjectInspector) parameters[0];
                inputKeyOI = (PrimitiveObjectInspector) internalMergeOI.getMapKeyObjectInspector();
                inputValueOI = (PrimitiveObjectInspector) internalMergeOI.getMapValueObjectInspector();
                return ObjectInspectorFactory.getStandardListObjectInspector(inputValueOI);
            } else {   // COMPLETE         timeTag active_name
                inputKeyOI = (PrimitiveObjectInspector) parameters[0];
                inputValueOI = (PrimitiveObjectInspector) parameters[1];
                return ObjectInspectorFactory.getStandardListObjectInspector(inputValueOI);
            }
        }

        static class activeNameMapTimeAgg extends AbstractAggregationBuffer {
            Map container = Maps.newHashMap();
        }

        public AbstractAggregationBuffer getNewAggregationBuffer() {
            activeNameMapTimeAgg ret = new activeNameMapTimeAgg();
            return ret;
        }

        public void reset(AggregationBuffer agg) {
            ((activeNameMapTimeAgg) agg).container.clear();
        }

        public void iterate(AggregationBuffer agg, Object[] parameters) {
            assert (parameters.length == 2);
            Object key = parameters[0];
            Object value = parameters[1];
            if (key != null && value != null) {
                activeNameMapTimeAgg my_agg = (activeNameMapTimeAgg) agg;
                Object kCopy = ObjectInspectorUtils.copyToStandardObject(key, this.inputKeyOI);
                Object vCopy = ObjectInspectorUtils.copyToStandardObject(value, this.inputValueOI);
                my_agg.container.put(kCopy, vCopy);
            }
        }

        public Object terminatePartial(AggregationBuffer agg) {
            activeNameMapTimeAgg my_agg = (activeNameMapTimeAgg) agg;
            Map ret = Maps.newHashMap(my_agg.container);
            return ret;
        }

        public void merge(AggregationBuffer agg, Object partial) {
            assert (partial != null);
            activeNameMapTimeAgg my_agg = (activeNameMapTimeAgg) agg;
            Map partialResult = (Map) internalMergeOI.getMap(partial);
            for (Map.Entry entry : partialResult.entrySet()) {
                Object kCopy = ObjectInspectorUtils.copyToStandardObject(entry.getKey(), this.inputKeyOI);
                Object vCopy = ObjectInspectorUtils.copyToStandardObject(entry.getValue(), this.inputValueOI);
                my_agg.container.put(kCopy, vCopy);
            }
        }

        public Object terminate(AggregationBuffer agg) {
            activeNameMapTimeAgg my_agg = (activeNameMapTimeAgg) agg;
            Map map = new HashMap(my_agg.container.size());
            map.putAll(my_agg.container);

            List> listData = Lists.newArrayList(map.entrySet());
            Collections.sort(listData, new Comparator>() {
                public int compare(Map.Entry o1, Map.Entry o2) {
                    return (o1.getKey().compareTo(o2.getKey()));
                }
            });

            List result = Lists.newArrayList();
            LongWritable currTime = listData.get(listData.size() - 1).getKey();
            for (Map.Entry entry : listData) {
                Long timeInterval = (currTime.get() - entry.getKey().get()) / 60000;
                if (timeInterval <= 30) {
                    result.add(entry.getValue());
                }
            }

            return result;
        }
    }
}

좋은 웹페이지 즐겨찾기