在Hive中创建日期维度表

基础知识

datediff操作

select datediff("2020-01-10", "2020-01-01")
输出：
9

repeat操作

select repeat("o", 9);
输出：ooooooooo

split操作

select split("ooooooooo",  "o");
输出：["","","","","","","","","",""]

posexplode操作

select posexplode(split("ooooooooo", "o"));
输出：
pos，val
0,""
1,""
2,""
3,""
4,""
5,""
6,""
7,""
8,""
9,""

得到连续的日期

with dates as(
    select date_add("2020-01-01", a.pos) as d
    from (select posexplode(split(repeat("o", datediff("2020-01-10", "2020-01-01")), "o"))) a
)
select * from dates;
输出：
2020-01-01
2020-01-02
2020-01-03
2020-01-04
2020-01-05
2020-01-06
2020-01-07
2020-01-08
2020-01-09
2020-01-10

日期维度

with dates as (
    select date_add("2020-01-01", a.pos) as d
    from (
        select posexplode(split(repeat("o", datediff("2020-01-10", "2020-01-01")), "o"))) a
)
select
d as d
,year(d) as year
,month(d) as month
,day(d) as day
,date_format(d, 'u') as daynumber_of_week
,date_format(d, 'EEEE') as dayname_of_week
,date_format(d, 'D') as daynumber_of_year
from dates
order by d;

小时维度表

with dates as (
  select date_add("2020-01-01", a.pos) as d
  from (select posexplode(split(repeat("o", datediff("2020-01-10", "2020-01-01")), "o"))) a
),
hours as (
  select a.pos as h
  from (select posexplode(split(repeat("o", 23), "o"))) a
)
select
    from_unixtime(unix_timestamp(cast(d as timestamp)) + (h * 3600)) as dt
  , d as d
  , year(d) as year
  , month(d) as month
  , day(d) as day
  , h as hour
  , date_format(d, 'u') as daynumber_of_week
  , date_format(d, 'EEEE') as dayname_of_week
  , date_format(d, 'D') as daynumber_of_year

from dates
join hours
sort by dt
;