hive 英文月份转数字

Posted 2023-04-27

参考技术A 日期变换：
(1)dt转日期
to_date(from_unixtime(unix_timestamp('$dt','yyyyMMdd')))
(2)日期转dt
regexp_replace('$date','-','')
(3)dt转当月1号日期
to_date(from_unixtime(unix_timestamp(concat(substr('$dt',1,6),'01'),'yyyyMMdd')))
trunc(to_date(from_unixtime(unix_timestamp('$dt','yyyyMMdd'))),'MM')
-- 下月1号日期
trunc(add_months(to_date(from_unixtime(unix_timestamp('$dt','yyyyMMdd'))),1),'MM')
(4)dt转当周星期一日期
next_day(date_add(to_date(from_unixtime(unix_timestamp('$dt','yyyyMMdd'))), -7), 'Mo')
date_sub(next_day(to_date(from_unixtime(unix_timestamp('$dt','yyyyMMdd'))),'MO'),7)
-- 下周星期一日期
next_day(to_date(from_unixtime(unix_timestamp('$dt','yyyyMMdd'))),'MO')
(5)dt前六天日期(dt为星期天时得到的是本周周一的日期)
date_add(to_date(from_unixtime(unix_timestamp('$dt','yyyyMMdd'))), -6)
(5)dt转当季第一天日期
if(length(floor(substr('$dt',5,2)/3.1)*3+1)=1,concat(substr('$dt',1,4),'-0',floor(substr('$dt',5,2)/3.1)*3+1,'-01'),concat(substr('$dt',1,4),'-',floor(substr('$dt',5,2)/3.1)*3+1,'-01'))
(6)dt转半年第一天日期
if(length(floor(substr('$dt',5,2)/6.1)*6+1)=1,concat(substr('$dt',1,4),'-0',floor(substr('$dt',5,2)/6.1)*6+1,'-01'),concat(substr('$dt',1,4),'-',floor(substr('$dt',5,2)/6.1)*6+1,'-01'))
(7)dt转当年1号日期
concat(substr('$dt',1,4),'-01-01')(8)在同时有日周月粒度时要注意数据的时间范围，有时每月的第一个自然周会跨月，比如2019年3月的第一周的日期是20190225-20190303where agent_business_date between date_add_day('$dt',-31) and to_date(from_unixtime(unix_timestamp('$dt','yyyyMMdd')))where dt between regexp_replace(date_add_day('$dt',-31),'-','') and '$dt'

------------------------------------------------------------------------------------------
-- 日期维度表表结构edw_public.dim_esf_edw_pub_date
------------------------------------------------------------------------------------------
col_name data_type comment
------------------------------------------------------------------------
calendar_date 　　string 日期，格式为"YYYY-MM-DD"
week_english_name string 星期英文名
week_chinese_name string 星期中文名
day_of_week_number int 所属一周当中的第几天
calendar_month_code string 日期所属月份，格式为"YYYY-MM"
calendar_month_number 　　int 所属月份数字
month_english_name string 月份英文名
month_chinese_name string 月份中文名
day_of_month_number int 所属月份当中的第几天
calendar_quater_code 　　string 日期所属季度，格式为"YYYY-QT"
calendar_quater_number 　　int 所属季度数字
day_of_quater_number 　　int 所属季度当中的第几天
calendar_half_year_code 　　string 日期所属半年，格式为"YYYY-HY"
calendar_half_year_number int 所属半年数字，1为上半年，2为下半年
calendar_year_code string 日期所属年份，格式为"YYYY"
day_of_year_number int 所属年份当中的第几天
work_day_flag 　　string 工作日标志: Y - 是/ N - 否
holiday_flag 　　string 节假日标志: Y - 是/ N - 否

-- 日期维度表的使用
-- 当天日期
SELECT
calendar_date
FROM
edw_public.dim_esf_edw_pub_date
WHERE
calendar_date = regexp_replace('$dt','(\\d4)(\\d2)(\\d2)','$1-$2-$3')

-- Finereport中日周月季半年年 各周期末日期的算法
select
$if(粒度 == 1," case when date(max(calendar_date))>=date(date_add('day',-1,current_date)) then date(date_add('day',-1,current_date)) else date(max(calendar_date)) end as period_end_date","")
$if(粒度 == 2," distinct case when day_of_week_number = 1 and date_add('day',6,date(calendar_date)) >=date(date_add('day',-1,current_date)) then date(date_add('day',-1,current_date)) when day_of_week_number = 7 and date(calendar_date) >=date(date_add('day',-1,current_date)) then date(date_add('day',-1,current_date)) when day_of_week_number = 1 then date_add('day',6,date(calendar_date)) when day_of_week_number = 7 then date(calendar_date) else date(calendar_date) end as period_end_date ","")
$if(粒度 == 3," case when date(max(calendar_date))>=date(date_add('day',-1,current_date)) then date(date_add('day',-1,current_date)) else date(max(calendar_date)) end as period_end_date ","")
$if(粒度 == 4," case when date(max(calendar_date))>=date(date_add('day',-1,current_date)) then date(date_add('day',-1,current_date)) else date(max(calendar_date)) end as period_end_date ","")
$if(粒度 == 5," case when date(max(calendar_date))>=date(date_add('day',-1,current_date)) then date(date_add('day',-1,current_date)) else date(max(calendar_date)) end as period_end_date ","")
$if(粒度 == 6," case when date(max(calendar_date))>=date(date_add('day',-1,current_date)) then date(date_add('day',-1,current_date)) else date(max(calendar_date)) end as period_end_date ","")
from
edw_public.dim_esf_edw_pub_date
where calendar_date >= '$开始时间' and calendar_date <= '$结束时间'
$if(粒度 == 1," group by calendar_date ","")
$if(粒度 == 2," and day_of_week_number in (1,7) ","")
$if(粒度 == 3," group by calendar_month_code ","")
$if(粒度 == 4," group by calendar_quater_code ","")
$if(粒度 == 5," group by calendar_year_code ","")
$if(粒度 == 6," group by calendar_half_year_code ","")

-- Finereport中日周月季半年年 各周期期初期末日期的算法(这种计算方法当前日期是20190330，输入的日期范围是2019-03-01至2091-03-28则输出的月日期范围是2019-03-29)
select
$if(粒度 == 1,"date(calendar_date) as period_start_date, date(calendar_date) as period_end_date ","")
$if(粒度 == 2,"case when day_of_week_number = 1 then date(calendar_date) when day_of_week_number = 7 then date_add('day',-6, date(calendar_date)) end as period_start_date, case when day_of_week_number = 1 and date_add('day',6, date(calendar_date)) >=date(date_add('day',-1,current_date)) then date(date_add('day',-1,current_date)) when day_of_week_number = 7 and date(calendar_date)>=date(date_add('day',-1,current_date)) then date(date_add('day',-1,current_date)) when day_of_week_number = 1 then date_add('day',6, date(calendar_date)) when day_of_week_number = 7 then date(calendar_date) end as period_end_date ","")
$if(粒度 == 3,"date(calendar_date) as period_start_date, case when date_add('day',-day(date(calendar_date)),date_add('month',1,(date(calendar_date))))>=date(date_add('day',-1,current_date)) then date(date_add('day',-1,current_date)) else date_add('day',-day(date(calendar_date)),date_add('month',1,(date(calendar_date)))) end as period_end_date ","")
$if(粒度 == 4,"calendar_date as period_start_date,date_add('day',-1,date_add('month',1,date(substr(calendar_date,1,4)||'-'||cast(cast(floor(cast(substr(calendar_date,6,2) as int)/3.1)*3+3 as int) as varchar)||'-01'))) as period_end_date ","")
$if(粒度 == 5,"date(concat(substr(calendar_date,1,4),'-01','-01')) as period_start_date,case when date(concat(substr(calendar_date,1,4),'-12','-31'))>= date(date_add('day',-1,current_date)) then date(date_add('day',-1,current_date)) else date(concat(substr(calendar_date,1,4),'-12','-31')) end as period_end_date","")
$if(粒度 == 6,"date(min(calendar_date)) as period_start_date,case when date(max(calendar_date))>= date(date_add('day',-1,current_date)) then date(date_add('day',-1,current_date)) else date(max(calendar_date)) end as period_end_date","")
from
edw_public.dim_esf_edw_pub_date
where calendar_date >= '$开始时间' and calendar_date <= '$结束时间'
$if(粒度 == 1," and 1 = 1 ","")
$if(粒度 == 2," and day_of_week_number in (1,7) ","")
$if(粒度 == 3," and day_of_month_number = 1","")
$if(粒度 == 4," and day_of_quater_number = 1","")
$if(粒度 == 5," and day_of_year_number = 1","")
$if(粒度 == 6," group by calendar_half_year_code ","")

------------------------------------------------------------------------------------------------
-- 根据输入的时间范围计算期末日期
------------------------------------------------------------------------------------------------
select t1.*
from
-- 日周月季年半年不同粒度的统计数据各存为了一张表
edw_reports.adm_xf_edw_house_sub_project_report_00$dtypely_di t1--日报
join
(
-- 日
SELECT
calendar_date
FROM
edw_public.dim_esf_edw_pub_date
WHERE
calendar_date BETWEEN '$bdt' AND '$edt'
AND '$dtype' = '1_dai'
UNION
-- 月
SELECT
MAX(calendar_date) AS calendar_date
FROM
edw_public.dim_esf_edw_pub_date
WHERE
calendar_date BETWEEN '$bdt' AND '$edt'
AND '$dtype' = '2_dai'
GROUP BY
calendar_month_number

UNION
-- 周
SELECT
calendar_date
FROM
edw_public.dim_esf_edw_pub_date
WHERE
calendar_date BETWEEN '$bdt' AND '$edt'
AND day_of_week_number = 7
AND '$dtype' = '3_dai'

UNION
-- 季
SELECT
MAX(calendar_date) AS calendar_date
FROM
edw_public.dim_esf_edw_pub_date
WHERE
calendar_date BETWEEN '$bdt' AND '$edt'
AND '$dtype' = '4_dai'
GROUP BY
calendar_quater_code

UNION
-- 年
SELECT
MAX(calendar_date) AS calendar_date
FROM
edw_public.dim_esf_edw_pub_date
WHERE
calendar_date BETWEEN '$bdt' AND '$edt'
AND '$dtype' = '5_dai'
GROUP BY
calendar_year_code

UNION
-- 半年
SELECT
MAX(calendar_date) AS calendar_date
FROM
edw_public.dim_esf_edw_pub_date
WHERE
calendar_date BETWEEN '$bdt' AND '$edt'
AND '$dtype' = '6_dai'
GROUP BY
calendar_half_year_code

UNION
SELECT
MAX(calendar_date) AS calendar_date
FROM
edw_public.dim_esf_edw_pub_date
WHERE
calendar_date BETWEEN '$bdt' AND '$edt'
ORDER BY
calendar_date
) t2
on t1.statistic_date = t2.calendar_date
where
statistic_date between '$bdt' and '$edt'
$if(len(tenant_name) == 0,"","and house_sub_project_organization_short_name = '" + tenant_name + "'")
$if(len(status) == 0,"","and house_sub_project_cooperation_status_code = " + status)
$if(len(tenant_type) == 0,"","and house_sub_project_organization_business_type_code= " + tenant_type)
$if(len(project_type) == 0,"","and house_sub_project_cooperation_type_code= " + project_type)
order by statistic_date

用hive写一个获取本日期的季度初的sql

由于项目需要获取(本季度的的发生额总和)／（本季度经历的天数）的数据(还有月均，年均的数据)。

判断季度的时候是一个难点，开始的时候写了一堆case when 来判断月份，后来写着写着发现，这样也太笨了。于是就开始想办法。

突然灵机一动，一个季度都是以3个月份为一个体的。何不先算出本日是第几季度，然后再乘以3就是季度初啊。

因为3月份除以3就等于1了.必须除一个比3大的数，而且月份的数字只会到12.不用担心除以3.1会出什么乱子。

下面是计算第几季度的sql

select floor(substr(‘2017-02-04‘,6,2)/3.1)+1

出来了第几季度之后就简单了。直接*3呗  就是季度的初始日期了。

select (floor(substr(‘2017-02-04‘,6,2)/3.1)*3)+1

 

具体源代码：

select bill_no,

sum(case when part_dt >= concat(substr(‘${START_DATE}‘,1,7),‘-01‘) and part_dt<=‘${START_DATE}‘ then nvl(amt,0) else 0 end)/((DATEDIFF(‘${START_DATE}‘,CONCAT(SUBSTR(‘${START_DATE}‘,1,7),‘-01‘))+1)) month_da,

sum(case when part_dt >= concat(substr(‘${START_DATE}‘,1,4),‘-‘,substr(concat(‘00‘,floor(substr(‘${START_DATE}‘,6,2)/3.1)*3+1),-2),‘-01‘) and part_dt<=‘${START_DATE}‘ then nvl(amt,0) else 0 end)/((DATEDIFF(‘${START_DATE}‘,CONCAT(SUBSTR(‘${START_DATE}‘,1,4),‘-‘,SUBSTR(CONCAT(‘00‘,FLOOR(SUBSTR(‘${START_DATE}‘,6,2)/3.1)*3+1),-2),‘-01‘))+1)) quarter_da,

sum(case when part_dt >= concat(substr(‘${START_DATE}‘,1,4),‘-01-01‘) and part_dt<=‘${START_DATE}‘ then nvl(amt,0) else 0 end)/((DATEDIFF(‘${START_DATE}‘,CONCAT(SUBSTR(‘${START_DATE}‘,1,4),‘-01-01‘))+1)) year_da

from xxxx_table_xxxx dlt

group by bill_no