Hive教程（05）- Hive命令汇总（上）

hive

--退出hive
quit;   
--exit会影响之前的使用，所以需要下一句kill掉hadoop的进程
exit;   
hadoop job -kill jobid

load data local inpath '${env:HOME}/目录'
    overwrite(可选) into table table_name
    partition (分区)；

hadoop fs -cp source_path target_path
insert……directory……
e.g insert overwrite local directory '/tmp/目录'     
-- 这里指定的路径也可以是全URL路径

hive -f sql_path;
e.g hive -f /path/to/file/xxxx.hql;

source sql_path;
e.g source /path/to/file/test.sql;

hive -e "SQL语句"；
e.g.  $ hive -e "select * from mytable limit 3";

nohup hive -f insert.sql >log.log &

-- 新建数据库
create database database_name; 
-- 新建数据库 database_name;
creat database if not exists
--只是复制了表结构，并不会复制内容
create table test3 like test2; 
--复制表结构的同时，把内容也复制过来了，需要执行mapreduce
create table test2 as select name,addr from test1;
 --修改数据库的路径
create database database_name location '路径'; 

--删除空的数据库
drop database if exists database_name; 
--先删除数据库中的表再删除数据库
drop database if exists database_name cascade; 
--删除表t1
drop table t1 CASCADE(可选，忽略错误);  
--删除数据库的时候，不允许删除有数据的数据库，如果数据库里面有数据则会报错。如果要忽略这些内容，则在后面增加CASCADE关键字，则忽略报错，删除数据库。 t1;--如果存在表t1，删除表t1    
drop table if exists CASCADE 

alter table table_name rename to another_name;   --修改表名

-- 查看数据库
show databases; 
-- 查看数据库
show databases like 'h.*'; 
--查看该数据库中的所有表
show tables;  
--支持模糊查询
show tables  ‘*t*’;    
--查看指定数据库中的所有表
SHOW TABLES IN DbName; 
--查看表有哪些分区 
show partitions t1;   
--查看表的结构及表的路径
describe formatted(可选) tab_name;  
--查看数据库的描述及路径
describe database database_name; 

--使用哪个数据库
use default;    
 --移动hdfs中数据到t1表中
load data inpath '/root/inner_table.dat' into table t1;  
--上传本地数据到hdfs中
load data local inpath '/root/inner_table.dat' into table t1;  
 --查询当前linux文件夹下的文件
!ls; 
--查询当前hdfs文件系统下  '/'目录下的文件
dfs -ls /; 
--显示地展示当前使用的数据库
set hive.cli.print.current.db=true;  
--Hive显示列头
set hive.cli.print.header=true; 

CREATE [TEMPORARY] [EXTERNAL] TABLE [IF NOT EXISTS] [db_name.]table_name    -- (Note: TEMPORARY available in Hive 0.14.0 and later)
  [(col_name data_type [COMMENT col_comment], ...)]
  [COMMENT table_comment]
  [PARTITIONED BY (col_name data_type [COMMENT col_comment], ...)]
  [CLUSTERED BY (col_name, col_name, ...) [SORTED BY (col_name [ASC|DESC], ...)] INTO num_buckets BUCKETS]
  [SKEWED BY (col_name, col_name, ...)                  -- (Note: Available in Hive 0.10.0 and later)]
     ON ((col_value, col_value, ...), (col_value, col_value, ...), ...)
     [STORED AS DIRECTORIES]
  [
   [ROW FORMAT row_format] 
   [STORED AS file_format]
     | STORED BY 'storage.handler.class.name' [WITH SERDEPROPERTIES (...)]  -- (Note: Available in Hive 0.6.0 and later)
  ]
  [LOCATION hdfs_path]
  [TBLPROPERTIES (property_name=property_value, ...)]   -- (Note: Available in Hive 0.6.0 and later)
  [AS select_statement];   -- (Note: Available in Hive 0.5.0 and later; not supported for external tables)

hive> CREATE TABLE pokes (foo INT, bar STRING);        
Creates a table called pokes with two columns, the first being an integer and the other a string

hive> create table new_table like records;

hive> create table logs(ts bigint,line string) partitioned by (dt String,country String);

hive> ALTER TABLE source RENAME TO target;

hive> ALTER TABLE invites ADD COLUMNS (new_col2 INT COMMENT 'a comment');

hive> DROP TABLE records; 

hive> dfs -rmr /user/hive/warehouse/records;

hive> select * from employees;
OK
tony    1338    ["a1","a2","a3"]        {"k1":1.0,"k2":2.0,"k3":3.0}    {"street":"s1","city":"s2","state":"s3","zip":4}
mark    5453    ["a4","a5","a6"]        {"k4":4.0,"k5":5.0,"k6":6.0}    {"street":"s4","city":"s5","state":"s6","zip":6}
ivy     323     ["a7","a8","a9"]        {"k7":7.0,"k8":8.0,"k9":9.0}    {"street":"s7","city":"s8","state":"s9","zip":9}
Time taken: 10.204 seconds, Fetched: 3 row(s)

hive> select subordinates[1]  from employees;
Total MapReduce CPU Time Spent: 2 seconds 740 msec
OK
a2
a5
a8

hive> select deductions["k2"]  from employees;
OK
2.0
NULL
NULL
Time taken: 75.812 seconds, Fetched: 3 row(s)

hive> select address.city  from employees;
Total MapReduce CPU Time Spent: 2 seconds 200 msec
OK
s2
s5
s8
Time taken: 75.311 seconds, Fetched: 3 row(s)

hive> load data local inpath '/home/hadoop/input/hive/partitions/file1' into table logs partition (dt='2001-01-01',country='GB');

hive> show partitions logs;

hive> SHOW TABLES;        
lists all the tables hive> SHOW TABLES '.*s';

hive> DESCRIBE invites;   

hive> show functions;

hive> describe function substr;

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

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

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

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);

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

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

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;  

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

hive> CREATE VIEW valid_records AS SELECT * FROM records2 WHERE temperature !=9999;

hive> DESCRIBE EXTENDED valid_records;