Saving all output to "!!{outputDirectory}!!/bucketizedhiveinputformat_auto.q.raw". Enter "record" with no arguments to stop it. >>> !run !!{qFileDirectory}!!/bucketizedhiveinputformat_auto.q >>> CREATE TABLE bucket_small (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE; No rows affected >>> load data local inpath '../data/files/srcsortbucket1outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-08'); No rows affected >>> load data local inpath '../data/files/srcsortbucket2outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-08'); No rows affected >>> >>> CREATE TABLE bucket_big (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE; No rows affected >>> load data local inpath '../data/files/srcsortbucket1outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08'); No rows affected >>> load data local inpath '../data/files/srcsortbucket2outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08'); No rows affected >>> load data local inpath '../data/files/srcsortbucket3outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08'); No rows affected >>> load data local inpath '../data/files/srcsortbucket4outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08'); No rows affected >>> >>> load data local inpath '../data/files/srcsortbucket1outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09'); No rows affected >>> load data local inpath '../data/files/srcsortbucket2outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09'); No rows affected >>> load data local inpath '../data/files/srcsortbucket3outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09'); No rows affected >>> load data local inpath '../data/files/srcsortbucket4outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09'); No rows affected >>> >>> set hive.optimize.bucketmapjoin = true; No rows affected >>> select /* + MAPJOIN(a) */ count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key; '_c1' '928' 1 row selected >>> >>> set hive.optimize.bucketmapjoin.sortedmerge = true; No rows affected >>> select /* + MAPJOIN(a) */ count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key; '_c1' '928' 1 row selected >>> >>> set hive.input.format = org.apache.hadoop.hive.ql.io.HiveInputFormat; No rows affected >>> select /* + MAPJOIN(a) */ count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key; '_c1' '928' 1 row selected >>> !record