【发布时间】:2021-02-18 22:39:07
【问题描述】:
基本上我需要在雪花任务中自动执行以下所有操作
- 在 Snowflake 中创建/替换 csv 文件格式和阶段
- 运行任务查询(每隔几天运行一次以获取一些统计信息)
- 每次运行到 Stage csv 时都将查询结果卸载
- 将舞台 csv 的内容下载到我机器上的本地文件中
我不能正确的是COPY INTO阶段,我如何将每次运行的任务结果卸载到阶段?
我不知道在 FROM 语句中放什么 - 无法识别 TITANLOADSUCCESSVSFAIL 但这是任务的名称
COPY INTO @TitanLoadStage/unload/ FROM TITANLOADSUCCESSVSFAIL FILE_FORMAT = TitanLoadSevenDays
第一次使用 stage,并使用 SF 在本地下载,因此感谢任何有关如何启动和运行它的建议!
谢谢, 尼克
完整代码:
-- create a csv file format
CREATE OR REPLACE FILE FORMAT TitanLoadSevenDays
type = 'CSV'
field_delimiter = '|';
--create a snowflake staging table using the csv
CREATE OR REPLACE STAGE TitanLoadStage
file_format = TitanLoadSevenDays;
CREATE TASK IF NOT EXISTS TitanLoadSuccessVsFail
WAREHOUSE = ITSM_LWH
SCHEDULE = 'USING CRON 1 * * * * Australia/Canberra' --every minute for testing purposes
COMMENT = 'Last 7 days of Titan game success vs fail load %'
AS
WITH SUCCESSCTE AS (
SELECT CLIENTNAME
, COUNT(EVENTTYPE) AS SuccessLoad --count success load events for that game
FROM vw_fact_gameload60
WHERE EVENTTYPE = 103 --success load events
AND USERTYPE = 1 --real users
AND APPID = 2 --titan games
AND EVENTARRIVALDATE >= DATEADD(DAY, -7, CAST(GETDATE() AS DATE)) --only looking at the last week
GROUP BY CLIENTNAME
),
FAILCTE AS ( --same as above but for failed loads
SELECT CLIENTNAME
, COUNT(EVENTTYPE) AS FailedLoads -- count failed load events for that game
FROM vw_fact_gameload60
WHERE EVENTTYPE = 106 -- failed load events
AND USERTYPE = 1 -- real users
AND APPID = 2 -- Titan games
AND EVENTARRIVALDATE >= DATEADD(DAY, -7, CAST(GETDATE() AS DATE)) -- last 7 days
--AND FACTEVENTARRIVALDATE BETWEEN DATEADD(DAY, -7, GETDATE())AND GETDATE() -- last 7 days
GROUP BY CLIENTNAME
)
SELECT COALESCE(s.CLIENTNAME, f.CLIENTNAME) AS ClientName
, ZEROIFNULL(s.SuccessLoad) + ZEROIFNULL(f.FailedLoads) AS TotalLoads --sum the success and failed loads found for 103, 106 events only, calculated in CTEs
, ZEROIFNULL(s.SuccessLoad) AS Cnt_SuccessLoad --count from success cte
, ZEROIFNULL(f.FailedLoads) AS Cnt_FailedLoads --count from fail cte
, CONCAT(ZEROIFNULL(ROUND(s.SuccessLoad * 100.0 / TotalLoads,2)) , '%') As Pct_Success --percentage of SuccessLoads against total
, CONCAT(ZEROIFNULL(ROUND(f.FailedLoads * 100.0 / TotalLoads,2)), '%') AS Pct_Fail---percentage of failedLoads against total
FROM SUCCESSCTE s
FULL OUTER JOIN FAILCTE f -- outer join in the fail CTE by game name, outer required because some titan games sucess or fail events are NULL
ON s.CLIENTNAME = f.Clientname
ORDER BY CLIENTNAME ASC
--copy the results from the query to the snowflake staging table created above
COPY INTO @TitanLoadStage/unload/ FROM TITANLOADSUCCESSVSFAIL FILE_FORMAT = TitanLoadSevenDays
-- export the stage data to csv located in common folder
GET @TitanLoadStage/unload/data_0_0_0.csv.gz file:\\itsm\group\ITS%20Management\Common\All%20Staff\SMD\Games\Snowflake%20and%20GamesDNA\Snowflake\SnowflakeCSV\TitanLoad.csv
-- start the task
ALTER TASK IF EXISTS TitanLoadSuccessVsFail RESUME
【问题讨论】:
标签: scheduled-tasks snowflake-cloud-data-platform file-format stage