hivesterix/resource/tpch/q3_shipping_priority.hive

DROP TABLE orders;
DROP TABLE lineitem;
DROP TABLE customer;
DROP TABLE q3_shipping_priority;

-- create tables and load 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/10/lineitem';
create external table orders (O_ORDERKEY INT, O_CUSTKEY INT, O_ORDERSTATUS STRING, O_TOTALPRICE DOUBLE, O_ORDERDATE STRING, O_ORDERPRIORITY STRING, O_CLERK STRING, O_SHIPPRIORITY INT, O_COMMENT STRING) ROW FORMAT DELIMITED FIELDS TERMINATED BY '|' STORED AS TEXTFILE LOCATION '/tpch/10/orders';
create external table customer (C_CUSTKEY INT, C_NAME STRING, C_ADDRESS STRING, C_NATIONKEY INT, C_PHONE STRING, C_ACCTBAL DOUBLE, C_MKTSEGMENT STRING, C_COMMENT STRING) ROW FORMAT DELIMITED FIELDS TERMINATED BY '|' STORED AS TEXTFILE LOCATION '/tpch/10/customer';

-- create the target table
create table q3_shipping_priority (l_orderkey int, revenue double, o_orderdate string, o_shippriority int);

set mapred.min.split.size=536870912;
set hive.exec.reducers.bytes.per.reducer=1024000000;

-- the query
Insert overwrite table q3_shipping_priority
select
  l_orderkey, sum(l_extendedprice*(1-l_discount)) as revenue, o_orderdate, o_shippriority
from
  customer c join orders o
    on c.c_mktsegment = 'BUILDING' and c.c_custkey = o.o_custkey
  join lineitem l
    on l.l_orderkey = o.o_orderkey
where
  o_orderdate < '1995-03-15' and l_shipdate > '1995-03-15'
group by l_orderkey, o_orderdate, o_shippriority
order by revenue desc, o_orderdate
limit 10;