hivesterix/resource/tpch100/q15_top_supplier.hive

-- create the tables and load the data
create external table lineitem (L_ORDERKEY INT, L_PARTKEY INT, L_SUPPKEY INT, L_LINENUMBER INT, L_QUANTITY DOUBLE, L_EXTENDEDPRICE DOUBLE, L_DISCOUNT DOUBLE, L_TAX DOUBLE, L_RETURNFLAG STRING, L_LINESTATUS STRING, L_SHIPDATE STRING, L_COMMITDATE STRING, L_RECEIPTDATE STRING, L_SHIPINSTRUCT STRING, L_SHIPMODE STRING, L_COMMENT STRING) ROW FORMAT DELIMITED FIELDS TERMINATED BY '|' STORED AS TEXTFILE LOCATION '/tpch/100/lineitem';
create external table supplier (S_SUPPKEY INT, S_NAME STRING, S_ADDRESS STRING, S_NATIONKEY INT, S_PHONE STRING, S_ACCTBAL DOUBLE, S_COMMENT STRING) ROW FORMAT DELIMITED FIELDS TERMINATED BY '|' STORED AS TEXTFILE LOCATION '/tpch/100/supplier';

-- create result tables
create table revenue(supplier_no int, total_revenue double); 
create table max_revenue(max_revenue double); 
create table q15_top_supplier(s_suppkey int, s_name string, s_address string, s_phone string, total_revenue double);


set mapred.min.split.size=536870912;

-- the query
insert overwrite table revenue
select 
  l_suppkey as supplier_no, sum(l_extendedprice * (1 - l_discount)) as total_revenue
from 
  lineitem
where 
  l_shipdate >= '1996-01-01' and l_shipdate < '1996-04-01'
group by l_suppkey;

insert overwrite table max_revenue
select 
  max(total_revenue)
from 
  revenue;

insert overwrite table q15_top_supplier
select 
  s_suppkey, s_name, s_address, s_phone, total_revenue
from supplier s join revenue r 
  on 
    s.s_suppkey = r.supplier_no
  join max_revenue m 
  on 
    r.total_revenue = m.max_revenue
order by s_suppkey;

DROP TABLE lineitem;
DROP TABLE supplier;
DROP TABLE revenue;
DROP TABLE max_revenue;
DROP TABLE q15_top_supplier;