解析Json函数UDTF函数1

大数据侠客

已于 2024-03-05 09:26:30 修改

阅读量357

点赞数 7

分类专栏： UDF、UDTF函数相关文章标签： json hive udtf

于 2024-03-04 17:38:13 首次发布

本文链接：https://blog.csdn.net/weixin_41367158/article/details/136458250

版权

UDF、UDTF函数相关专栏收录该内容

9 篇文章 0 订阅

订阅专栏

实现步骤：
1.将写好的代码打包上传到hdfs目录：/user/lib/
2.执行如下命令：

drop function getJsonArrSingle;
ADD JAR hdfs://nameservice1/user/lib/JsonArrSingle.jar;
ADD JAR hdfs://nameservice1/user/lib/fastjson-1.2.83.jar;
CREATE FUNCTION getJsonArrSingle AS 'com.mingyang.GetJsonArrSingleUDTF'USING JAR 'hdfs://nameservice1/user/lib/JsonArrSingle.jar',JAR 'hdfs://nameservice1/user/lib/fastjson-1.2.83.jar';
reload functions;

3.测试：
在这里插入图片描述
4. JAR包中代码如下：

package com.mingyang;

import com.alibaba.fastjson.JSONArray;
import lombok.extern.slf4j.Slf4j;
import org.apache.commons.lang3.StringUtils;
import org.apache.hadoop.hive.ql.exec.UDFArgumentException;
import org.apache.hadoop.hive.ql.metadata.HiveException;
import org.apache.hadoop.hive.ql.udf.generic.GenericUDTF;
import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector;
import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorFactory;
import org.apache.hadoop.hive.serde2.objectinspector.StructObjectInspector;
import org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

import java.util.ArrayList;

@Slf4j
public  class GetJsonArrSingleUDTF extends GenericUDTF {
   /* private IntObjectInspector intInspector;
    private DoubleObjectInspector doubleInspector;
    private BooleanObjectInspector booleanInspector;
    private TimestampObjectInspector timestampInspector;
    private DateObjectInspector dateInspector;
    private BinaryObjectInspector binaryInspector;*/
   private static final Logger logger = LoggerFactory.getLogger(GetJsonArrSingleUDTF.class);
    @Override
    public StructObjectInspector initialize(StructObjectInspector args) throws UDFArgumentException {

        ArrayList<String> fieldNames = new ArrayList<String>();
        ArrayList<ObjectInspector> fieldInspectors = new ArrayList<>();

        // Input argument inspectors
        /*StringObjectInspector stringInspector1 = (StringObjectInspector) args[0];
        StringObjectInspector stringInspector2 = (StringObjectInspector) args[1];*/
        // Output field names and inspectors
        fieldNames.add("json");
        fieldInspectors.add(PrimitiveObjectInspectorFactory.javaStringObjectInspector);

        return ObjectInspectorFactory.getStandardStructObjectInspector(fieldNames, fieldInspectors);
    }
    @Override
    public void process(Object[] args) throws HiveException {
        if(args !=null && args.length !=0 && args[0] !=null && StringUtils.isNoneEmpty(String.valueOf(args[0]))) {
            String jsonArrStr = String.valueOf(args[0]);
            JSONArray arr = JSONArray.parseArray(jsonArrStr);
            for (int i = 0; i < arr.size(); i++) {
                forward(new String[]{String.valueOf(arr.get(i))});
            }
        }else{
            forward(new String[]{null});
        }
    }



    @Override
    public void close() throws HiveException {
        // Clean up resources, if any
    }
}