ql/src/test/queries/clientpositive/cbo_semijoin.q - hive - Git at Google

 --! qt:dataset:cbo_t3
 --! qt:dataset:cbo_t2
 --! qt:dataset:cbo_t1
 set hive.mapred.mode=nonstrict;
 set hive.cbo.enable=true;
 set hive.exec.check.crossproducts=false;

 set hive.stats.fetch.column.stats=true;
 set hive.auto.convert.join=false;

 -- 12. SemiJoin
 select cbo_t1.c_int           from cbo_t1 left semi join   cbo_t2 on cbo_t1.key=cbo_t2.key;
 select cbo_t1.c_int           from cbo_t1 left semi join   cbo_t2 on cbo_t1.key=cbo_t2.key where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0);
 select * from (select c, b, a from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1  where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 left semi join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2  where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p left semi join cbo_t3 on cbo_t1.a=key where (b + 1 == 2) and (b > 0 or c >= 0)) R where  (b + 1 = 2) and (R.b > 0 or c >= 0);
 select * from (select cbo_t3.c_int, cbo_t1.c, b from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1  where (cbo_t1.c_int + 1 = 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 left semi join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2  where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p left outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t3.c_int  == 2) and (b > 0 or c_int >= 0)) R where  (R.c_int + 1 = 2) and (R.b > 0 or c_int >= 0);
 select * from (select c_int, b, cbo_t1.c from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1  where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 left semi join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2  where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p right outer join cbo_t3 on cbo_t1.a=key where (b + 1 == 2) and (b > 0 or c_int >= 0)) R where  (c + 1 = 2) and (R.b > 0 or c_int >= 0);
 select * from (select c_int, b, cbo_t1.c from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1  where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 left semi join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2  where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p full outer join cbo_t3 on cbo_t1.a=key where (b + 1 == 2) and (b > 0 or c_int >= 0)) R where  (c + 1 = 2) and (R.b > 0 or c_int >= 0);
 select a, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)  group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by a+b desc, c asc) cbo_t1 left semi join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)  group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by q+r/10 desc, p) cbo_t2 on cbo_t1.a=p left semi join cbo_t3 on cbo_t1.a=key where (b + 1  >= 0) and (b > 0 or a >= 0) group by a, c  having a > 0 and (a >=1 or c >= 1) and (a + c) >= 0 order by c, a;
 select a, c, count(*)  from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)  group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by a+b desc, c asc limit 5) cbo_t1 left semi join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)  group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by q+r/10 desc, p limit 5) cbo_t2 on cbo_t1.a=p left semi join cbo_t3 on cbo_t1.a=key where (b + 1  >= 0) and (b > 0 or a >= 0) group by a, c  having a > 0 and (a >=1 or c >= 1) and (a + c) >= 0 order by c, a;
	--! qt:dataset:cbo_t3
	--! qt:dataset:cbo_t2
	--! qt:dataset:cbo_t1
	set hive.mapred.mode=nonstrict;
	set hive.cbo.enable=true;
	set hive.exec.check.crossproducts=false;

	set hive.stats.fetch.column.stats=true;
	set hive.auto.convert.join=false;

	-- 12. SemiJoin
	select cbo_t1.c_int from cbo_t1 left semi join cbo_t2 on cbo_t1.key=cbo_t2.key;
	select cbo_t1.c_int from cbo_t1 left semi join cbo_t2 on cbo_t1.key=cbo_t2.key where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0);
	select * from (select c, b, a from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 left semi join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p left semi join cbo_t3 on cbo_t1.a=key where (b + 1 == 2) and (b > 0 or c >= 0)) R where (b + 1 = 2) and (R.b > 0 or c >= 0);
	select * from (select cbo_t3.c_int, cbo_t1.c, b from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 = 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 left semi join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p left outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t3.c_int == 2) and (b > 0 or c_int >= 0)) R where (R.c_int + 1 = 2) and (R.b > 0 or c_int >= 0);
	select * from (select c_int, b, cbo_t1.c from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 left semi join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p right outer join cbo_t3 on cbo_t1.a=key where (b + 1 == 2) and (b > 0 or c_int >= 0)) R where (c + 1 = 2) and (R.b > 0 or c_int >= 0);
	select * from (select c_int, b, cbo_t1.c from (select key as a, c_int as b, cbo_t1.c_float as c from cbo_t1 where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)) cbo_t1 left semi join (select cbo_t2.key as p, cbo_t2.c_int as q, c_float as r from cbo_t2 where (cbo_t2.c_int + 1 == 2) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0)) cbo_t2 on cbo_t1.a=p full outer join cbo_t3 on cbo_t1.a=key where (b + 1 == 2) and (b > 0 or c_int >= 0)) R where (c + 1 = 2) and (R.b > 0 or c_int >= 0);
	select a, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by a+b desc, c asc) cbo_t1 left semi join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by q+r/10 desc, p) cbo_t2 on cbo_t1.a=p left semi join cbo_t3 on cbo_t1.a=key where (b + 1 >= 0) and (b > 0 or a >= 0) group by a, c having a > 0 and (a >=1 or c >= 1) and (a + c) >= 0 order by c, a;
	select a, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by a+b desc, c asc limit 5) cbo_t1 left semi join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by q+r/10 desc, p limit 5) cbo_t2 on cbo_t1.a=p left semi join cbo_t3 on cbo_t1.a=key where (b + 1 >= 0) and (b > 0 or a >= 0) group by a, c having a > 0 and (a >=1 or c >= 1) and (a + c) >= 0 order by c, a;