hive 自定义 udf udtf 函数

最新推荐文章于 2023-02-24 16:14:24 发布

cherish-zp

最新推荐文章于 2023-02-24 16:14:24 发布

阅读量227

点赞数

分类专栏： spark 大数据 hive 文章标签： spark

本文链接：https://blog.csdn.net/zp1220/article/details/105641142

版权

大数据同时被 3 个专栏收录

5 篇文章 0 订阅

订阅专栏

spark

4 篇文章 0 订阅

订阅专栏

hive

3 篇文章 0 订阅

订阅专栏

hive 自定义UDF 函数

package com.atguigu.udf;

import com.alibaba.fastjson.JSON;
import com.alibaba.fastjson.JSONObject;
import org.apache.hadoop.hive.ql.exec.UDF;


/**
 * @author cherish
 * @create 2020-04-15 10:49
 */
public class BaseFieldUDF  extends UDF {

    public String evaluate(String line , String jsonkeysString) {

        //event name , even_json
        String[] split = line.split("\\|");
        String t = split[0];
        String jsonString = split[1];



        JSONObject jsonObject = JSON.parseObject(jsonString);
        String cm = jsonObject.getString("cm");

        JSONObject cmObject = JSON.parseObject(cm);
        String[] keys = jsonkeysString.split(",");
        StringBuffer buffer = new StringBuffer();
        for (String key : keys) {
            if (cmObject.containsKey(key)) {
                buffer.append(cmObject.getString(key)).append("\t");
            }else {
                buffer.append("\t");
            }
        }
        buffer.append(jsonObject.getString("et")).append("\t");
        buffer.append(t).append("\t");

        return buffer.toString();
    }

    public static void main(String[] args) {
        String line = "1541217850324|{\"cm\":{\"mid\":\"m7856\",\"uid\":\"u8739\",\"ln\":\"-74.8\",\"sv\":\"V2.2.2\",\"os\":\"8.1.3\",\"g\":\"P7XC9126@gmail.com\",\"nw\":\"3G\",\"l\":\"es\",\"vc\":\"6\",\"hw\":\"640*960\",\"ar\":\"MX\",\"t\":\"1541204134250\",\"la\":\"-31.7\",\"md\":\"huawei-17\",\"vn\":\"1.1.2\",\"sr\":\"O\",\"ba\":\"Huawei\"},\"ap\":\"weather\",\"et\":[{\"ett\":\"1541146624055\",\"en\":\"display\",\"kv\":{\"goodsid\":\"n4195\",\"copyright\":\"ESPN\",\"content_provider\":\"CNN\",\"extend2\":\"5\",\"action\":\"2\",\"extend1\":\"2\",\"place\":\"3\",\"showtype\":\"2\",\"category\":\"72\",\"newstype\":\"5\"}},{\"ett\":\"1541213331817\",\"en\":\"loading\",\"kv\":{\"extend2\":\"\",\"loading_time\":\"15\",\"action\":\"3\",\"extend1\":\"\",\"type1\":\"\",\"type\":\"3\",\"loading_way\":\"1\"}},{\"ett\":\"1541126195645\",\"en\":\"ad\",\"kv\":{\"entry\":\"3\",\"show_style\":\"0\",\"action\":\"2\",\"detail\":\"325\",\"source\":\"4\",\"behavior\":\"2\",\"content\":\"1\",\"newstype\":\"5\"}},{\"ett\":\"1541202678812\",\"en\":\"notification\",\"kv\":{\"ap_time\":\"1541184614380\",\"action\":\"3\",\"type\":\"4\",\"content\":\"\"}},{\"ett\":\"1541194686688\",\"en\":\"active_background\",\"kv\":{\"active_source\":\"3\"}}]}";
        String x = new BaseFieldUDF().evaluate(line, "mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,nw,ln,la,t");
        System.out.println(x);
    }

}