UDF,UDTF

UDTF

package com.amazon.udtf;
import org.apache.commons.lang.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.json.JSONArray;

import java.util.ArrayList;

import org.json.JSONException;
/**
 * @Author qiao
 * @Date 2019/11/7 20:51
 * @Version 1.0
 */
public class EventJsonUDTF extends GenericUDTF {
    //该方法中，我们将指定输出参数的名称和参数类型：
    @Override
    public StructObjectInspector initialize(ObjectInspector[] argOIs) throws UDFArgumentException {

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

        fieldNames.add("event_name");
        fieldOIs.add(PrimitiveObjectInspectorFactory.javaStringObjectInspector);
        fieldNames.add("event_json");
        fieldOIs.add(PrimitiveObjectInspectorFactory.javaStringObjectInspector);

        return ObjectInspectorFactory.getStandardStructObjectInspector(fieldNames, fieldOIs);
    }

    //输入1条记录，输出若干条结果
    @Override
    public void process(Object[] objects) throws HiveException {

        // 获取传入的et
        String input = objects[0].toString();

        // 如果传进来的数据为空，直接返回过滤掉该数据
        if (StringUtils.isBlank(input)) {
            return;
        } else {

            try {
                // 获取一共有几个事件（ad/facoriters）
                JSONArray ja = new JSONArray(input);

                if (ja == null)
                    return;

                // 循环遍历每一个事件
                for (int i = 0; i < ja.length(); i++) {
                    String[] result = new String[2];

                    try {
                        // 取出每个的事件名称（ad/facoriters）
                        result[0] = ja.getJSONObject(i).getString("en");

                        // 取出每一个事件整体
                        result[1] = ja.getString(i);
                    } catch (JSONException e) {
                        continue;
                    }

                    // 将结果返回
                    forward(result);
                }
            } catch (JSONException e) {
                e.printStackTrace();
            }
        }
    }

    //当没有记录处理的时候该方法会被调用，用来清理代码或者产生额外的输出
    @Override
    public void close() throws HiveException {

    }
}

UDF

package com.amazon.utf;


import org.apache.commons.lang.StringUtils;
import org.apache.hadoop.hive.ql.exec.UDF;
import org.json.JSONException;
import org.json.JSONObject;

/**
 * @Author qiao
 * @Date 2019/11/7 20:38
 * @Version 1.0
 */
public class BaseFieldUDF extends UDF {

    public String evaluate(String line, String key) throws JSONException {


        // 1 处理line   服务器时间 | json
        String[] log = line.split("\\|");

        //2 合法性校验
        if (log.length != 2 || StringUtils.isBlank(log[1])) {
            return "";
        }

        // 3 开始处理json
        JSONObject baseJson = new JSONObject(log[1].trim());

        String result = "";

        // 4 根据传进来的key查找相应的value
        if ("et".equals(key)) {
            if (baseJson.has("et")) {
                result = baseJson.getString("et");
            }
        } else if ("st".equals(key)) {
            result = log[0].trim();
        } else {
            JSONObject cm = baseJson.getJSONObject("cm");
            if (cm.has(key)) {
                result = cm.getString(key);
            }
        }
        return result;
    }

    /**
     * 自测方法
     *
     * @param args
     * @throws JSONException
     */
    public static void main(String[] args) throws JSONException {

        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");
        System.out.println(x);
    }
}