drop table kv_input;
create table kv_input(k string, v string)
	row format delimited
	fields terminated by '\t'
  stored as textfile
;

drop table kv_condensed;
create table kv_condensed(k string, v string)
	stored as sequencefile
;

load data local inpath '/Users/larry/kv_input.txt' overwrite into table kv_input;

add file /Users/larry/identity.pl;
add file /Users/larry/condense.pl;

from (
  from kv_input
  MAP k, v
  USING './identity.pl'
  as k, v
 cluster by k) map_output
insert overwrite table kv_condensed
reduce k, v
  using './condense.pl'
;