我有这个示例表
PK_HASH | PERSON_ID | VALID_FROM | VALID_TO | CREATION_DATE | NAME | SURNAME | ------------------------------------------------------------------------------ 456a8ed1| 000001 | 01.01.2016 | 31.01.2016| 03.01.2016 | John | Smith | a48e4b22| 000001 | 01.01.2016 | 31.01.2016| 04.01.2016 | James | Smith | 788fee89| 000001 | 01.01.2016 | 31.01.2016| 05.01.2016 | James | null | 42cba184| 000001 | 01.01.2016 | 31.01.2016| 12.01.2016 | null | null | 5bcc48ad| 000002 | 01.01.2016 | 31.01.2016| 03.01.2016 | Mike | Legend | e48da448| 000003 | 01.01.2016 | 31.01.2016| 03.01.2016 | Karl | Rogel | 889775ea| 000003 | 01.01.2016 | 31.01.2016| 05.01.2016 | Carl | null |
是否可以为Oracle准备一些合并SQL-Command，其结果将是
PK_HASH | PERSON_ID | VALID_FROM | VALID_TO | CREATION_DATE | NAME | SURNAME | ------------------------------------------------------------------------------ 456a8ed1| 000001 | 01.01.2016 | 31.01.2016| 03.01.2016 | James | Smith | 5bcc48ad| 000002 | 01.01.2016 | 31.01.2016| 03.01.2016 | Mike | Legend | e48da448| 000003 | 01.01.2016 | 31.01.2016| 03.01.2016 | Carl | Rogel |
含义：
我尝试准备一些MERGE命令，但实际上不确定是否可以使用它。
我需要更改表的内容，我不需要一些结果集。因此，需要进行一些更新和删除。
@Please不要试图理解表中的数据。它是虚构的，仅用于描述有问题的
非常感谢您的每一次帮助
答案 0 :(得分：2)
这很容易通过使用分析函数来实现：
with sample_data as (select '456a8ed1' pk_hash, 1 person_id, to_date('01/01/2016', 'dd/mm/yyyy') valid_from, to_date('31/01/2016', 'dd/mm/yyyy') valid_to, to_date('03/01/2016', 'dd/mm/yyyy') creation_date, 'John' name, 'Smith' surname from dual union all
select 'a48e4b22' pk_hash, 1 person_id, to_date('01/01/2016', 'dd/mm/yyyy') valid_from, to_date('31/01/2016', 'dd/mm/yyyy') valid_to, to_date('04/01/2016', 'dd/mm/yyyy') creation_date, 'James' name, 'Smith' surname from dual union all
select '788fee89' pk_hash, 1 person_id, to_date('01/01/2016', 'dd/mm/yyyy') valid_from, to_date('31/01/2016', 'dd/mm/yyyy') valid_to, to_date('05/01/2016', 'dd/mm/yyyy') creation_date, 'James' name, null surname from dual union all
select '42cba184' pk_hash, 1 person_id, to_date('01/01/2016', 'dd/mm/yyyy') valid_from, to_date('31/01/2016', 'dd/mm/yyyy') valid_to, to_date('12/01/2016', 'dd/mm/yyyy') creation_date, null name, null surname from dual union all
select '5bcc48ad' pk_hash, 2 person_id, to_date('01/01/2016', 'dd/mm/yyyy') valid_from, to_date('31/01/2016', 'dd/mm/yyyy') valid_to, to_date('03/01/2016', 'dd/mm/yyyy') creation_date, 'Mike' name, 'Legend' surname from dual union all
select 'e48da448' pk_hash, 3 person_id, to_date('01/01/2016', 'dd/mm/yyyy') valid_from, to_date('31/01/2016', 'dd/mm/yyyy') valid_to, to_date('03/01/2016', 'dd/mm/yyyy') creation_date, 'Karl' name, 'Rogel' surname from dual union all
select '889775ea' pk_hash, 3 person_id, to_date('01/01/2016', 'dd/mm/yyyy') valid_from, to_date('31/01/2016', 'dd/mm/yyyy') valid_to, to_date('05/01/2016', 'dd/mm/yyyy') creation_date, 'Carl' name, null surname from dual)
-- end of mimicking a table called "sample_data" containing your data. You wouldn't need this, since you have your table.
-- See SQL below:
select pk_hash,
person_id,
valid_from,
valid_to,
creation_date,
latest_name name,
latest_surname surname
from (select pk_hash,
person_id,
valid_from,
valid_to,
creation_date,
row_number() over (partition by person_id, valid_from order by creation_date) rn,
last_value(name ignore nulls) over (partition by person_id, valid_from order by creation_date
rows between unbounded preceding and unbounded following) latest_name,
last_value(surname ignore nulls) over (partition by person_id, valid_from order by creation_date
rows between unbounded preceding and unbounded following) latest_surname
from sample_data)
where rn = 1;
PK_HASH PERSON_ID VALID_FROM VALID_TO CREATION_DATE NAME SURNAME
-------- ---------- ---------- ---------- ------------- ----- -------
456a8ed1 1 01.01.2016 31.01.2016 03.01.2016 James Smith
5bcc48ad 2 01.01.2016 31.01.2016 03.01.2016 Mike Legend
e48da448 3 01.01.2016 31.01.2016 03.01.2016 Carl Rogel
The `row_number()` function labels each row in the set (in this case, the set is across person_id and valid_from, and ordered by creation_date) with a number.
The `last_value()` function is simply finding the last non-null value in the specified columns across all rows in the set, ordered by the creation_date.
Then you just filter the results to pick the first row.
以下是一个测试用例，展示了如何使用上述查询作为merge语句的一部分进行更新/删除：
创建包含数据的表格：
create table sample_data as
select '456a8ed1' pk_hash, 1 person_id, to_date('01/01/2016', 'dd/mm/yyyy') valid_from, to_date('31/01/2016', 'dd/mm/yyyy') valid_to, to_date('03/01/2016', 'dd/mm/yyyy') creation_date, 'John' name, 'Smith' surname from dual union all
select 'a48e4b22' pk_hash, 1 person_id, to_date('01/01/2016', 'dd/mm/yyyy') valid_from, to_date('31/01/2016', 'dd/mm/yyyy') valid_to, to_date('04/01/2016', 'dd/mm/yyyy') creation_date, 'James' name, 'Smith' surname from dual union all
select '788fee89' pk_hash, 1 person_id, to_date('01/01/2016', 'dd/mm/yyyy') valid_from, to_date('31/01/2016', 'dd/mm/yyyy') valid_to, to_date('05/01/2016', 'dd/mm/yyyy') creation_date, 'James' name, null surname from dual union all
select '42cba184' pk_hash, 1 person_id, to_date('01/01/2016', 'dd/mm/yyyy') valid_from, to_date('31/01/2016', 'dd/mm/yyyy') valid_to, to_date('12/01/2016', 'dd/mm/yyyy') creation_date, null name, null surname from dual union all
select '5bcc48ad' pk_hash, 2 person_id, to_date('01/01/2016', 'dd/mm/yyyy') valid_from, to_date('31/01/2016', 'dd/mm/yyyy') valid_to, to_date('03/01/2016', 'dd/mm/yyyy') creation_date, 'Mike' name, 'Legend' surname from dual union all
select 'e48da448' pk_hash, 3 person_id, to_date('01/01/2016', 'dd/mm/yyyy') valid_from, to_date('31/01/2016', 'dd/mm/yyyy') valid_to, to_date('03/01/2016', 'dd/mm/yyyy') creation_date, 'Karl' name, 'Rogel' surname from dual union all
select '889775ea' pk_hash, 3 person_id, to_date('01/01/2016', 'dd/mm/yyyy') valid_from, to_date('31/01/2016', 'dd/mm/yyyy') valid_to, to_date('05/01/2016', 'dd/mm/yyyy') creation_date, 'Carl' name, null surname from dual;
运行merge语句进行更新并删除：
merge into sample_data tgt
using (select pk_hash,
person_id,
valid_from,
valid_to,
creation_date,
row_number() over (partition by person_id, valid_from order by creation_date) rn,
last_value(name ignore nulls) over (partition by person_id, valid_from order by creation_date
rows between unbounded preceding and unbounded following) latest_name,
last_value(surname ignore nulls) over (partition by person_id, valid_from order by creation_date
rows between unbounded preceding and unbounded following) latest_surname
from sample_data) src
on (tgt.pk_hash = src.pk_hash)
when matched then
update set tgt.name = src.latest_name,
tgt.surname = src.latest_surname
-- need to update all the rows, in order to delete the ones we're not interested in, otherwise they
-- won't be seen by the delete statement since we're basing the delete on the src.rn column:
delete where src.rn != 1;
commit;
<强>输出：
select * from sample_data;
PK_HASH PERSON_ID VALID_FROM VALID_TO CREATION_DATE NAME SURNAME
-------- ---------- ---------- ---------- ------------- ----- -------
456a8ed1 1 01.01.2016 31.01.2016 03.01.2016 James Smith
5bcc48ad 2 01.01.2016 31.01.2016 03.01.2016 Mike Legend
e48da448 3 01.01.2016 31.01.2016 03.01.2016 Carl Rogel