hivesterix/resource/tpch/q19_discounted_revenue.hive

DROP TABLE lineitem;
DROP TABLE part;
DROP TABLE q19_discounted_revenue;

-- 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/10/lineitem';
create external table part (P_PARTKEY INT, P_NAME STRING, P_MFGR STRING, P_BRAND STRING, P_TYPE STRING, P_SIZE INT, P_CONTAINER STRING, P_RETAILPRICE DOUBLE, P_COMMENT STRING) ROW FORMAT DELIMITED FIELDS TERMINATED BY '|' STORED AS TEXTFILE LOCATION '/tpch/10/part';

-- create the result table
create table q19_discounted_revenue(revenue double);

set mapred.min.split.size=268435456;
set hive.exec.reducers.bytes.per.reducer=1040000000;

-- the query
insert overwrite table q19_discounted_revenue
select
  sum(l_extendedprice * (1 - l_discount) ) as revenue
from
  lineitem l join part p
  on 
    p.p_partkey = l.l_partkey    
where
  (
    p_brand = 'Brand#12'
	and p_container REGEXP 'SM CASE||SM BOX||SM PACK||SM PKG'
	and l_quantity >= 1 and l_quantity <= 11
	and p_size >= 1 and p_size <= 5
	and l_shipmode REGEXP 'AIR||AIR REG'
	and l_shipinstruct = 'DELIVER IN PERSON'
  ) 
  or 
  (
    p_brand = 'Brand#23'
	and p_container REGEXP 'MED BAG||MED BOX||MED PKG||MED PACK'
	and l_quantity >= 10 and l_quantity <= 20
	and p_size >= 1 and p_size <= 10
	and l_shipmode REGEXP 'AIR||AIR REG'
	and l_shipinstruct = 'DELIVER IN PERSON'
  )
  or
  (
	p_brand = 'Brand#34'
	and p_container REGEXP 'LG CASE||LG BOX||LG PACK||LG PKG'
	and l_quantity >= 20 and l_quantity <= 30
	and p_size >= 1 and p_size <= 15
	and l_shipmode REGEXP 'AIR||AIR REG'
	and l_shipinstruct = 'DELIVER IN PERSON'
  );