我试图将两个相同的表中的多个日期范围与相同或不同的数据组合在一起。 （PostgreSql 9。*）
表格结构：
CREATE TABLE "first_activities" (
"id" int4 NOT NULL DEFAULT nextval('first_activities_id_seq'::regclass),
"start_time" timestamptz,
"end_time" timestamptz,
"activity_type" int2,
"user_id" int4
)
WITH (OIDS=FALSE);
ALTER TABLE "first_activities" ADD PRIMARY KEY ("id") NOT DEFERRABLE INITIALLY IMMEDIATE;
CREATE TABLE "second_activities" (
"id" int4 NOT NULL DEFAULT nextval('second_activities_id_seq'::regclass),
"start_time" timestamptz,
"end_time" timestamptz,
"activity_type" int2,
"user_id" int4
)
WITH (OIDS=FALSE);
ALTER TABLE "second_activities" ADD PRIMARY KEY ("id") NOT DEFERRABLE INITIALLY IMMEDIATE;
第一张表中的数据：
INSERT INTO "first_activities" VALUES
(NULL, '2014-10-31 01:00:00', '2014-10-31 02:00:00', '3', '1'),
(NULL, '2014-10-31 02:00:00', '2014-10-31 03:00:00', '4', '1'),
(NULL, '2014-10-31 03:00:00', '2014-10-31 04:00:00', '2', '1'),
(NULL, '2014-10-31 04:30:00', '2014-10-31 05:00:00', '3', '1'),
(NULL, '2014-10-31 05:30:00', '2014-11-01 06:00:00', '4', '1'),
(NULL, '2014-11-01 06:30:00', '2014-11-01 07:00:00', '2', '1'),
(NULL, '2014-11-01 07:30:00', '2014-11-01 08:00:00', '1', '1'),
(NULL, '2014-11-01 08:00:00', '2014-11-01 09:00:00', '3', '1'),
(NULL, '2014-11-01 09:00:00', '2014-11-02 10:00:00', '4', '1'),
(NULL, '2014-08-27 10:00:00', '2014-08-27 11:00:00', '2', '1'),
(NULL, '2014-08-27 11:00:00', '2014-08-27 12:00:00', '1', '1'),
第二个表格中的数据：
INSERT INTO "second_activities" VALUES
(NULL, '2014-10-31 01:00:00', '2014-10-31 02:00:00', '3', '1'),
(NULL, '2014-10-31 02:00:00', '2014-10-31 03:00:00', '4', '1'),
-- Differece from first table
(NULL, '2014-10-31 03:30:00', '2014-10-31 04:00:00', '1', '1'),
(NULL, '2014-10-31 04:25:00', '2014-10-31 04:35:00', '3', '1'),
(NULL, '2014-10-31 04:45:00', '2014-10-31 05:35:00', '3', '1'),
-- End of Difference from first table
(NULL, '2014-08-27 10:00:00', '2014-08-27 11:00:00', '2', '1'),
(NULL, '2014-08-27 11:00:00', '2014-08-27 12:00:00', '1', '1');
如何过滤从查询开始的结果集：
SELECT * FROM first_activities UNION ALL SELECT * from second_activities
ORDER BY start_time ASC;
获得最终结果集。
最终结果：
-- merge same data by user_id and activity_type and combine with
-- and split data with range intersection but not same user_id and acitvity_type
-- start_time end_time type user_id
'2014-10-31 01:00:00', '2014-10-31 02:00:00', '3', '1');
'2014-10-31 02:00:00', '2014-10-31 03:00:00', '4', '1');
--data dont merge. Splitting with range intersection
'2014-10-31 03:00:00', '2014-10-31 03:30:00', '2', '1'); -- from first table
'2014-10-31 03:30:00', '2014-10-31 04:00:00', '1', '1'); -- from second table
-- data merged by same user_id and activity_type
'2014-10-31 04:25:00', '2014-10-31 05:35:00', '3', '1');
'2014-10-31 05:30:00', '2014-11-01 06:00:00', '4', '1');
'2014-11-01 06:30:00', '2014-11-01 07:00:00', '2', '1');
'2014-11-01 07:30:00', '2014-11-01 08:00:00', '1', '1');
'2014-11-01 08:00:00', '2014-11-01 09:00:00', '3', '1');
'2014-11-01 09:00:00', '2014-11-02 10:00:00', '4', '1');
'2014-08-27 10:00:00', '2014-08-27 11:00:00', '2', '1');
'2014-08-27 11:00:00', '2014-08-27 12:00:00', '1', '1');
答案 0 :(得分：0)
The issue can be reduced to the question of how to combine (compact) a group of adjacent (overlapping) ranges into one. I had to deal with this some time ago and found it a bit complicated in plain SQL. There is a simple solution using loop in a plpgsql code, but I found also a general solution with the use of custom aggregate.
The function compact_ranges(anyrange, anyrange) returns the sum of ranges if they are adjacent (overlapping) or the second range otherwise:
create or replace function compact_ranges(anyrange, anyrange)
returns anyrange language sql as $$
select case
when $1 && $2 or $1 -|- $2 then $1+ $2
else $2
end
$$;
create aggregate compact_ranges_agg (anyrange) (
sfunc = compact_ranges,
stype = anyrange
);
The aggregate has a narrow scope of usage, it should be called as a progressive window function like in the example:
with test(rng) as (
values
('[ 1, 2)'::int4range),
('[ 3, 7)'), -- group 1
('[ 5, 10)'), -- group 1
('[ 6, 8)'), -- group 1
('[11, 17)'), -- group 2
('[12, 16)'), -- group 2
('[15, 16)'), -- group 2
('[18, 19)')
)
select distinct on (lower(new_rng)) new_rng
from (
select *, compact_ranges_agg(rng) over (order by rng) new_rng
from test
) s
order by lower(new_rng), new_rng desc;
new_rng
---------
[1,2)
[3,10)
[11,17)
[18,19)
(4 rows)
In the same way you can use it for your tables:
with merged as (
select tstzrange(start_time, end_time) rng, activity_type, user_id
from first_activities
union
select tstzrange(start_time, end_time) rng, activity_type, user_id
from second_activities
),
compacted as (
select distinct on (user_id, activity_type, lower(new_rng))
lower(new_rng) start_time,
upper(new_rng) end_time,
activity_type,
user_id
from (
select
user_id, activity_type,
compact_ranges_agg(rng) over (partition by user_id, activity_type order by rng) new_rng
from merged
) s
order by user_id, activity_type, lower(new_rng), new_rng desc
)
select
start_time,
case when end_time > lead(start_time) over w then lead(start_time) over w else end_time end,
activity_type,
user_id
from compacted
window w as (order by start_time)
order by start_time;
The result:
start_time | end_time | activity_type | user_id
------------------------+------------------------+---------------+---------
2014-08-27 10:00:00+02 | 2014-08-27 11:00:00+02 | 2 | 1
2014-08-27 11:00:00+02 | 2014-08-27 12:00:00+02 | 1 | 1
2014-10-31 01:00:00+01 | 2014-10-31 02:00:00+01 | 3 | 1
2014-10-31 02:00:00+01 | 2014-10-31 03:00:00+01 | 4 | 1
2014-10-31 03:00:00+01 | 2014-10-31 03:30:00+01 | 2 | 1
2014-10-31 03:30:00+01 | 2014-10-31 04:00:00+01 | 1 | 1
2014-10-31 04:25:00+01 | 2014-10-31 05:30:00+01 | 3 | 1
2014-10-31 05:30:00+01 | 2014-11-01 06:00:00+01 | 4 | 1
2014-11-01 06:30:00+01 | 2014-11-01 07:00:00+01 | 2 | 1
2014-11-01 07:30:00+01 | 2014-11-01 08:00:00+01 | 1 | 1
2014-11-01 08:00:00+01 | 2014-11-01 09:00:00+01 | 3 | 1
2014-11-01 09:00:00+01 | 2014-11-02 10:00:00+01 | 4 | 1
(12 rows)