Hive Hsql 常用命令

川长思鸟来 2022-05-08 06:18 263阅读 0赞

## 简介 ##

Hive是基于Hadoop的一个数据仓库工具，可以将结构化的数据文件映射为一张数据库表，并提供简单的sql查询功能，可以将sql语句转换为MapReduce任务进行运行。 其优点是学习成本低，可以通过类SQL语句快速实现简单的MapReduce统计。以下介绍常用的Hive的类SQL语句。

##### 创建表： #####

hive>create table tablename(id int,name string,password string);

##### 创建表时指定分隔符 #####

hive> create table tablename(name string,password string)row format delimited fields terminated by ‘,’;  
(指定源数据的分隔符为"逗号")

##### 加载表 #####

hive> load data inpath ‘/user/hadoop/output7/part-r-00000’ into table tablename;

##### 创建一个新表，结构与某表一样 #####

hive> create table table02 like table01;

##### 创建分区表 #####

hive> create table tablename(id int,line string) partitioned by (dt string,country string);

##### 显示表里有多少条记录(count 数大于50的有多少条记录) #####

hive>select count(\*) from tablename where count>50;

##### 排序用法order by (查询count 数大于50并排序) #####

select \* from tablename where count > 50 order by count;

##### 显示表中有多少分区 #####

hive> show partitions tablename;

##### 显示所有表 #####

hive> show tables;

##### 显示所有与t开头的表 #####

hive> show tables ‘t\*’;

##### 显示表的结构信息 #####

hive> describe tablename;

##### 修改表名字 #####

hive> alter table table01 rename to table02;

##### 在原表上新添加一列 #####

hive> alter table tablename add columns(new\_col2 int comment ‘a commment’);

hive> alter table tablename add columns(new\_col3 int);

##### 删除表 #####

hive> drop table tablename;

##### 从本地文件加载数据： #####

hive> LOAD DATA LOCAL INPATH ‘/home/hadoop/input/sample.txt’ OVERWRITE INTO TABLE records;

##### 加载分区表 #####

hive> load data inpath ‘/user/hive/warehouse/part-r-00000’ overwrite into table clickstream\_log PARTITION(dt = ‘2018-11-30’);

##### 显示所有函数 #####

hive> show functions;

##### 查看函数的用法 #####

hive> describe function substr;

##### 查看数组、map、结构 #####

hive> select col1\[0\],col2\[‘b’\],col3.c from complex;

##### 查看数组、map、结构 #####

hive> select col1\[0\],col2\[‘b’\],col3.c from complex;

##### 内连接： #####

hive> SELECT sales., things. FROM sales JOIN things ON ([sales.id][] = [things.id][]);

##### 查看hive为某个查询使用多少个MapReduce作业 #####

hive> Explain SELECT sales., things. FROM sales JOIN things ON ([sales.id][] = [things.id][]);

##### 外连接： #####

hive> SELECT sales., things. FROM sales LEFT OUTER JOIN things ON ([sales.id][] = [things.id][]);  
　　hive> SELECT sales., things. FROM sales RIGHT OUTER JOIN things ON ([sales.id][] = [things.id][]);  
　　hive> SELECT sales., things. FROM sales FULL OUTER JOIN things ON ([sales.id][] = [things.id][]);

##### in查询：Hive不支持，但可以使用LEFT SEMI JOIN #####

hive> SELECT \* FROM things LEFT SEMI JOIN sales ON ([sales.id][] = [things.id][]);

##### Map连接：Hive可以把较小的表放入每个Mapper的内存来执行连接操作 #####

hive> SELECT /+ MAPJOIN(things) / sales., things. FROM sales JOIN things ON ([sales.id][] = [things.id][]);

##### INSERT OVERWRITE TABLE …SELECT：新表预先存在 #####

hive> FROM records2  
　　> INSERT OVERWRITE TABLE stations\_by\_year SELECT year, COUNT(DISTINCT station) GROUP BY year  
　　> INSERT OVERWRITE TABLE records\_by\_year SELECT year, COUNT(1) GROUP BY year  
　　> INSERT OVERWRITE TABLE good\_records\_by\_year SELECT year, COUNT(1) WHERE temperature != 9999 AND (quality = 0 OR quality = 1 OR quality = 4 OR quality = 5 OR quality = 9) GROUP BY year;

##### CREATE TABLE … AS SELECT：新表表预先不存在 #####

hive>CREATE TABLE target AS SELECT col1,col2 FROM source;

##### 创建视图： #####

hive> CREATE VIEW valid\_records AS SELECT \* FROM records2 WHERE temperature !=9999;

##### 查看视图详细信息： #####

hive> DESCRIBE EXTENDED valid\_records;

[sales.id]: http://sales.id
[things.id]: http://things.id