怎麼辦?用DolphinScheduler排程執行復雜的HiveSQL時無法正確識別符號

海豚调度發表於2024-09-19

在使用Apache DolphinScheduler排程執行復雜的HiveSQL時,HQL包含多種海豚無法正確識別的符號,怎麼辦?本文提供了可行的思路和方法,供使用者參考。

一、目的

在Hive中完成複雜JSON,既有物件還有陣列而且陣列中包含陣列的解析後,原本以為沒啥問題了,結果在DolphinScheduler中排程又出現了大問題,搞了一天。試了很多種方法,死了無數腦細胞,才解決了這個問題!

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、原先海豚的任務排程方式

在shell指令碼里新增HiveSQL語句

#! /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、原先方式報錯日誌

file

DolphinScheduler無法正確識別HiveSQL裡解析複雜JSON的多種符號。

五、解決方式

把HiveSQL放在一個SQL檔案裡,然後在指令碼里是執行Hive的sourceSQL檔案。

1 SQL檔案

file

--使用hurys_dc_ods資料庫
use hurys_dc_dwd;

--hive調優(必須先執行調優語句,否則部分複雜SQL執行會有問題)
set hive.vectorized.execution.enabled=false;
--開啟動態分割槽功能(預設 true,開啟)
set hive.exec.dynamic.partition=true;
--設定為非嚴格模式 nonstrict 模式表示允許所有的分割槽欄位都可以使用動態分割槽
set hive.exec.dynamic.partition.mode=nonstrict;
--在每個執行 MR 的節點上,最大可以建立多少個動態分割槽
set hive.exec.max.dynamic.partitions.pernode=1000;
--在所有執行 MR 的節點上,最大一共可以建立多少個動態分割槽。預設 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 海豚任務執行指令碼

file

#! /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 執行任務,驗證結果

file

終於解決了!以後碰到類似排程器識別不了SQL裡符號的問題,可以用這個方法,把SQL放在SQL檔案裡,然後在指令碼里執行這個SQL檔案,這樣就能規避這類問題了。

轉載自天地風雷水火山澤
原文連結:https://blog.csdn.net/tiantang2renjian/article/details/140605840

本文由 白鯨開源 提供釋出支援!

相關文章