像这样的东西
create table t1 (group_id varchar2(20), value varchar2(20));
create table t2 (group_id varchar2(20), value varchar2(20));
insert into t1 values ('A','FOO');
insert into t1 values ('A','BAR');
insert into t1 values ('X','HHH');
insert into t1 values ('X','ZOO');
insert into t2 values ('C','FOO');
insert into t2 values ('C','BAR');
insert into t2 values ('B','ZOO');
select t1.group_id t1_group,t2.group_id t2_group,
--t1.all_val, t2.all_val,
case when t1.all_val = t2.all_val then 'match' else 'no match' end coll_match
from
(select 'T1' tab_id, group_id, collect(value) all_val,
min(value) min_val, max(value) max_val, count(distinct value) cnt_val
from t1 group by group_id) t1
full outer join
(select 'T2' tab_id, group_id, collect(value) all_val,
min(value) min_val, max(value) max_val, count(distinct value) cnt_val
from t2 group by group_id) t2
on t1.min_val = t2.min_val and t1.max_val = t2.max_val and t1.cnt_val = t2.cnt_val
/
我已经根据每组中不同值的最小值、最大值和数量进行了初步消除,这将有助于处理大型数据集。如果数据集足够小,您可能不需要它们。
这告诉你比赛。您只需将其推出一个额外的步骤即可找到没有任何匹配项的组
select t1_group
from
(
select t1.group_id t1_group,t2.group_id t2_group,
--t1.all_val, t2.all_val,
case when t1.all_val = t2.all_val then 'match' end coll_match
from
(select 'T1' tab_id, group_id, collect(value) all_val
from t1 group by group_id) t1
cross join
(select 'T2' tab_id, group_id, collect(value) all_val
from t2 group by group_id) t2
)
group by t1_group
having min(coll_match) is null
/
select t2_group
from
(
select t1.group_id t1_group,t2.group_id t2_group,
--t1.all_val, t2.all_val,
case when t1.all_val = t2.all_val then 'match' end coll_match
from
(select 'T1' tab_id, group_id, collect(value) all_val
from t1 group by group_id) t1
cross join
(select 'T2' tab_id, group_id, collect(value) all_val
from t2 group by group_id) t2
)
group by t2_group
having min(coll_match) is null
/