用hql来做wordcount
有以下文本文件:
hello tom hello jim
hello rose hello tom
tom love rose rose love jim
jim love tom love is what
what is love
需要用hive做wordcount
-- 建表映射
create table t_wc(sentence string);
-- 导入数据
load data local inpath '/root/hivetest/xx.txt' into table t_wc;
--hql:
SELECT word
,count(1) as cnts
FROM (
SELECT explode(split(sentence, ' ')) AS word
FROM t_wc
) tmp
GROUP BY word
order by cnts desc
;