怎么办？用DolphinScheduler调度执行复杂的HiveSQL时无法正确识别符号

DolphinScheduler社区2024-09-20 11:22

在使用Apache DolphinScheduler调度执行复杂的HiveSQL时，HQL包含多种海豚无法正确识别的符号，怎么办？本文提供了可行的思路和方法，供用户参考。

一、目的

在Hive中完成复杂JSON，既有对象还有数组而且数组中包含数组的解析后，原本以为没啥问题了，结果在DolphinScheduler中调度又出现了大问题，搞了一天。试了很多种方法，死了无数脑细胞，才解决了这个问题！

二、HiveSQL

insert  overwrite  table  hurys_dc_dwd.dwd_json_statistics partition(day)
select
        t1.device_no,
        source_device_type,
        sn,
        model,
        create_time,
        cycle,
        get_json_object(coil_list,'$.laneNo')  lane_no,
        get_json_object(coil_list,'$.laneType')           lane_type,
        section_no,
        get_json_object(coil_list,'$.coilNo')             coil_no,
        get_json_object(coil_list,'$.volumeSum')          volume_sum,
        get_json_object(coil_list,'$.volumePerson')       volume_person,
        get_json_object(coil_list,'$.volumeCarNon')       volume_car_non,
        get_json_object(coil_list,'$.volumeCarSmall')     volume_car_small,
        get_json_object(coil_list,'$.volumeCarMiddle')    volume_car_middle,
        get_json_object(coil_list,'$.volumeCarBig')       volume_car_big,
        get_json_object(coil_list,'$.speedAvg')           speed_avg,
        get_json_object(coil_list,'$.speed85')            speed_85,
        get_json_object(coil_list,'$.timeOccupancy')      time_occupancy,
        get_json_object(coil_list,'$.averageHeadway')     average_headway,
        get_json_object(coil_list,'$.averageGap')         average_gap,
        substr(create_time,1,10) day
from (select
       get_json_object(statistics_json,'$.deviceNo')          device_no,
       get_json_object(statistics_json,'$.sourceDeviceType')  source_device_type,
       get_json_object(statistics_json,'$.sn')                sn,
       get_json_object(statistics_json,'$.model')             model,
       get_json_object(statistics_json,'$.createTime')        create_time ,
       get_json_object(statistics_json,'$.data.cycle')        cycle,
       get_json_object(replace(replace(section_list,':{',':[{'),'}}','}]}'),'$.sectionNo') section_no,
       section_list
from hurys_dc_ods.ods_statistics
lateral view explode(split(replace(replace(replace(get_json_object(statistics_json,'$.data.sectionList'),
    '[',''),']',''),'},{"sectionNo"','}|{"sectionNo"'),"\\|")) tf as section_list
    where day='2024-07-18' --  date_sub(current_date(), 1)   -- '2024-07-18' --
    ) as t1
lateral view explode(split(replace(replace(replace(get_json_object(replace(replace(section_list,
    ':{',':[{'),'}}','}]}'),'$.coilList'),'[',''),']',''),'},','}|'),"\\|")) tf1 as coil_list
    where substr(create_time,1,10) =  '2024-07-18' --date_sub(current_date(), 1)   --'2024-07-17'
;

三、原先海豚的任务调度方式

在shell脚本里添加HiveSQL语句

#! /bin/bash
source /etc/profile

nowdate=`date --date='0 days ago' "+%Y%m%d"`
yesdate=`date -d yesterday +%Y-%m-%d`

hive -e "
use hurys_dc_dwd;

set hive.vectorized.execution.enabled=false;

set hive.exec.dynamic.partition=true;
set hive.exec.dynamic.partition.mode=nonstrict;
set hive.exec.max.dynamic.partitions.pernode=1000;
set hive.exec.max.dynamic.partitions=1500;


with t1 as(
select
       get_json_object(statistics_json,'$.deviceNo')          device_no,
       get_json_object(statistics_json,'$.sourceDeviceType')  source_device_type,
       get_json_object(statistics_json,'$.sn')                sn,
       get_json_object(statistics_json,'$.model')             model,
       get_json_object(statistics_json,'$.createTime')        create_time ,
       get_json_object(statistics_json,'$.data.cycle')        cycle,
       get_json_object(replace(replace(section_list,':{',':[{'),'}}','}]}'),'$.sectionNo') section_no,
       section_list
from hurys_dc_ods.ods_statistics
lateral view explode(split(replace(replace(replace(get_json_object(statistics_json,'$.data.sectionList'),'[',''),']',''),'},{"sectionNo"','}|{"sectionNo"'),"\\\\|")) tf as section_list
    where day='$yesdate'
)
insert  overwrite  table  hurys_dc_dwd.dwd_json_statistics partition(day)
select
        t1.device_no,
        source_device_type,
        sn,
        model,
        substr(create_time,1,19)                          create_time ,
        cycle,
        get_json_object(coil_list,'$.laneNo')  lane_no,
        get_json_object(coil_list,'$.laneType')           lane_type,
        section_no,
        get_json_object(coil_list,'$.coilNo')             coil_no,
        get_json_object(coil_list,'$.volumeSum')          volume_sum,
        get_json_object(coil_list,'$.volumePerson')       volume_person,
        get_json_object(coil_list,'$.volumeCarNon')       volume_car_non,
        get_json_object(coil_list,'$.volumeCarSmall')     volume_car_small,
        get_json_object(coil_list,'$.volumeCarMiddle')    volume_car_middle,
        get_json_object(coil_list,'$.volumeCarBig')       volume_car_big,
        get_json_object(coil_list,'$.speedAvg')           speed_avg,
        get_json_object(coil_list,'$.speed85')            speed_85,
        get_json_object(coil_list,'$.timeOccupancy')      time_occupancy,
        get_json_object(coil_list,'$.averageHeadway')     average_headway,
        get_json_object(coil_list,'$.averageGap')         average_gap,
        substr(create_time,1,10) day
from t1
lateral view explode(split(replace(replace(replace(get_json_object(replace(replace(section_list,':{',':[{'),'}}','}]}'),'$.coilList'),'[',''),']',''),'},','}|'),"\\\\|")) tf1 as coil_list
    where  substr(create_time,1,10) ='$yesdate'
"

四、原先方式报错日志

DolphinScheduler无法正确识别HiveSQL里解析复杂JSON的多种符号。

五、解决方式

把HiveSQL放在一个SQL文件里，然后在脚本里是执行Hive的sourceSQL文件。

1 SQL文件

--使用hurys_dc_ods数据库 use hurys_dc_dwd;

--hive调优（必须先执行调优语句，否则部分复杂SQL运行会有问题） set hive.vectorized.execution.enabled=false; --开启动态分区功能（默认 true，开启） set hive.exec.dynamic.partition=true; --设置为非严格模式 nonstrict 模式表示允许所有的分区字段都可以使用动态分区 set hive.exec.dynamic.partition.mode=nonstrict; --在每个执行 MR 的节点上，最大可以创建多少个动态分区 set hive.exec.max.dynamic.partitions.pernode=1000; --在所有执行 MR 的节点上，最大一共可以创建多少个动态分区。默认 1000 set hive.exec.max.dynamic.partitions=1500;

insert  overwrite  table  hurys_dc_dwd.dwd_json_statistics partition(day)
select
        t1.device_no,
        source_device_type,
        sn,
        model,
        create_time,
        cycle,
        get_json_object(coil_list,'$.laneNo')  lane_no,
        get_json_object(coil_list,'$.laneType')           lane_type,
        section_no,
        get_json_object(coil_list,'$.coilNo')             coil_no,
        get_json_object(coil_list,'$.volumeSum')          volume_sum,
        get_json_object(coil_list,'$.volumePerson')       volume_person,
        get_json_object(coil_list,'$.volumeCarNon')       volume_car_non,
        get_json_object(coil_list,'$.volumeCarSmall')     volume_car_small,
        get_json_object(coil_list,'$.volumeCarMiddle')    volume_car_middle,
        get_json_object(coil_list,'$.volumeCarBig')       volume_car_big,
        get_json_object(coil_list,'$.speedAvg')           speed_avg,
        get_json_object(coil_list,'$.speed85')            speed_85,
        get_json_object(coil_list,'$.timeOccupancy')      time_occupancy,
        get_json_object(coil_list,'$.averageHeadway')     average_headway,
        get_json_object(coil_list,'$.averageGap')         average_gap,
        substr(create_time,1,10) day
from (select
       get_json_object(statistics_json,'$.deviceNo')          device_no,
       get_json_object(statistics_json,'$.sourceDeviceType')  source_device_type,
       get_json_object(statistics_json,'$.sn')                sn,
       get_json_object(statistics_json,'$.model')             model,
       get_json_object(statistics_json,'$.createTime')        create_time ,
       get_json_object(statistics_json,'$.data.cycle')        cycle,
       get_json_object(replace(replace(section_list,':{',':[{'),'}}','}]}'),'$.sectionNo') section_no,
       section_list
from hurys_dc_ods.ods_statistics
lateral view explode(split(replace(replace(replace(get_json_object(statistics_json,'$.data.sectionList'),'[',''),']',''),'},{"sectionNo"','}|{"sectionNo"'),"\\|")) tf as section_list
    where day= date_sub(current_date(), 1)
    ) as t1
lateral view explode(split(replace(replace(replace(get_json_object(replace(replace(section_list,':{',':[{'),'}}','}]}'),'$.coilList'),'[',''),']',''),'},','}|'),"\\|")) tf1 as coil_list
where substr(create_time,1,10) =  date_sub(current_date(), 1)
;

2 海豚任务执行脚本

#! /bin/bash
source /etc/profile

nowdate=`date --date='0 days ago' "+%Y-%m-%d"`
yesdate=`date -d yesterday +%Y-%m-%d`

hive -e "
source   dwd_json_statistics.sql
"

3 执行任务，验证结果

终于解决了！以后碰到类似调度器识别不了SQL里符号的问题，可以用这个方法，把SQL放在SQL文件里，然后在脚本里执行这个SQL文件，这样就能规避这类问题了。

转载自天地风雷水火山泽 原文链接：https://blog.csdn.net/tiantang2renjian/article/details/140605840

本文由 白鲸开源科技 提供发布支持！

相关推荐
成长的小牛2331 小时前
es使用knn向量检索中numCandidates和k应该如何配比更合适
大数据·elasticsearch·搜索引擎
goTsHgo1 小时前
在 Spark 上实现 Graph Embedding
大数据·spark·embedding
程序猿小柒1 小时前
【Spark】Spark SQL执行计划-精简版
大数据·sql·spark
隔着天花板看星星1 小时前
Spark-Streaming集成Kafka
大数据·分布式·中间件·spark·kafka
奥顺1 小时前
PHPUnit使用指南：编写高效的单元测试
大数据·mysql·开源·php
小屁孩大帅-杨一凡1 小时前
Flink 简介和简单的demo
大数据·flink
天冬忘忧2 小时前
Flink调优----反压处理
大数据·flink
sinat_307021532 小时前
大数据政策文件——职业道德（山东省大数据职称考试）
大数据·职场和发展
SeaTunnel2 小时前
某医疗行业用户基于Apache SeaTunnel从调研选型到企业数据集成框架的落地实践
大数据
Elastic 中国社区官方博客2 小时前
Elasticsearch：什么是查询语言？
大数据·数据库·elasticsearch·搜索引擎·oracle
热门推荐
01〔AI 绘画〕Stable Diffusion 之 解决绘制多人或面部很小的人物时面部崩坏问题 篇02YOLOv8训练好模型后，追加轮数继续训练、或者提前终止训练，缩减训练轮数03玄机平台应急响应—webshell查杀04机器人编程怎么入门？05HCIA-datacom数通题库和录播视频资料06Docker 夺命连环 15 问07SQL 主从数据库实时备份08校验 GPT-4 真实性的三个经典问题：快速区分 GPT-3.5 与 GPT-4，并提供免费测试网站09(欧拉)openEuler系统添加网卡文件配置流程、(欧拉)openEuler系统手动配置ipv6地址流程、(欧拉)openEuler系统网络管理说明10VSCode插件 —— Cody AI （免费AI助手！）