Hive常用DDL操作

show databases;

USE database_name;

CREATE (DATABASE|SCHEMA) [IF NOT EXISTS] database_name   --DATABASE|SCHEMA 是等价的
  [COMMENT database_comment] --数据库注释
  [LOCATION hdfs_path] --存储在 HDFS 上的位置
  [WITH DBPROPERTIES (property_name=property_value, ...)]; --指定额外属性

CREATE DATABASE IF NOT EXISTS hive_test
  COMMENT 'hive database for test'
  WITH DBPROPERTIES ('create'='heibaiying');

DESC DATABASE [EXTENDED] db_name; --EXTENDED 表示是否显示额外属性

DESC DATABASE  EXTENDED hive_test;

DROP (DATABASE|SCHEMA) [IF EXISTS] database_name [RESTRICT|CASCADE];

  DROP DATABASE IF EXISTS hive_test CASCADE;

CREATE [TEMPORARY] [EXTERNAL] TABLE [IF NOT EXISTS] [db_name.]table_name     --表名
  [(col_name data_type [COMMENT col_comment],
    ... [constraint_specification])]  --列名 列数据类型
  [COMMENT table_comment]   --表描述
  [PARTITIONED BY (col_name data_type [COMMENT col_comment], ...)]  --分区表分区规则
  [
    CLUSTERED BY (col_name, col_name, ...) 
   [SORTED BY (col_name [ASC|DESC], ...)] INTO num_buckets BUCKETS
  ]  --分桶表分桶规则
  [SKEWED BY (col_name, col_name, ...) ON ((col_value, col_value, ...), (col_value, col_value, ...), ...)  
   [STORED AS DIRECTORIES] 
  ]  --指定倾斜列和值
  [
   [ROW FORMAT row_format]    
   [STORED AS file_format]
     | STORED BY 'storage.handler.class.name' [WITH SERDEPROPERTIES (...)]  
  ]  -- 指定行分隔符、存储文件格式或采用自定义存储格式
  [LOCATION hdfs_path]  -- 指定表的存储位置
  [TBLPROPERTIES (property_name=property_value, ...)]  --指定表的属性
  [AS select_statement];   --从查询结果创建表

  CREATE TABLE emp(
    empno INT,
    ename STRING,
    job STRING,
    mgr INT,
    hiredate TIMESTAMP,
    sal DECIMAL(7,2),
    comm DECIMAL(7,2),
    deptno INT)
    ROW FORMAT DELIMITED FIELDS TERMINATED BY "\t";

  CREATE EXTERNAL TABLE emp_external(
    empno INT,
    ename STRING,
    job STRING,
    mgr INT,
    hiredate TIMESTAMP,
    sal DECIMAL(7,2),
    comm DECIMAL(7,2),
    deptno INT)
    ROW FORMAT DELIMITED FIELDS TERMINATED BY "\t"
    LOCATION '/hive/emp_external';

  CREATE EXTERNAL TABLE emp_partition(
    empno INT,
    ename STRING,
    job STRING,
    mgr INT,
    hiredate TIMESTAMP,
    sal DECIMAL(7,2),
    comm DECIMAL(7,2)
    )
    PARTITIONED BY (deptno INT)   -- 按照部门编号进行分区
    ROW FORMAT DELIMITED FIELDS TERMINATED BY "\t"
    LOCATION '/hive/emp_partition';

  CREATE EXTERNAL TABLE emp_bucket(
    empno INT,
    ename STRING,
    job STRING,
    mgr INT,
    hiredate TIMESTAMP,
    sal DECIMAL(7,2),
    comm DECIMAL(7,2),
    deptno INT)
    CLUSTERED BY(empno) SORTED BY(empno ASC) INTO 4 BUCKETS  --按照员工编号散列到四个 bucket 中
    ROW FORMAT DELIMITED FIELDS TERMINATED BY "\t"
    LOCATION '/hive/emp_bucket';

  CREATE EXTERNAL TABLE emp_skewed(
    empno INT,
    ename STRING,
    job STRING,
    mgr INT,
    hiredate TIMESTAMP,
    sal DECIMAL(7,2),
    comm DECIMAL(7,2)
    )
    SKEWED BY (empno) ON (66,88,100)  --指定 empno 的倾斜值 66,88,100
    ROW FORMAT DELIMITED FIELDS TERMINATED BY "\t"
    LOCATION '/hive/emp_skewed';   

  CREATE TEMPORARY TABLE emp_temp(
    empno INT,
    ename STRING,
    job STRING,
    mgr INT,
    hiredate TIMESTAMP,
    sal DECIMAL(7,2),
    comm DECIMAL(7,2)
    )
    ROW FORMAT DELIMITED FIELDS TERMINATED BY "\t";

CREATE TABLE emp_copy AS SELECT * FROM emp WHERE deptno='20';

CREATE [TEMPORARY] [EXTERNAL] TABLE [IF NOT EXISTS] [db_name.]table_name  --创建表表名
   LIKE existing_table_or_view_name  --被复制表的表名
   [LOCATION hdfs_path]; --存储位置

CREATE TEMPORARY EXTERNAL TABLE  IF NOT EXISTS  emp_co  LIKE emp

-- 加载数据到 emp 表中
load data local inpath "/usr/file/emp.txt" into table emp;

7369	SMITH	CLERK	7902	1980-12-17 00:00:00	800.00		20
7499	ALLEN	SALESMAN	7698	1981-02-20 00:00:00	1600.00	300.00	30
7521	WARD	SALESMAN	7698	1981-02-22 00:00:00	1250.00	500.00	30
7566	JONES	MANAGER	7839	1981-04-02 00:00:00	2975.00		20
7654	MARTIN	SALESMAN	7698	1981-09-28 00:00:00	1250.00	1400.00	30
7698	BLAKE	MANAGER	7839	1981-05-01 00:00:00	2850.00		30
7782	CLARK	MANAGER	7839	1981-06-09 00:00:00	2450.00		10
7788	SCOTT	ANALYST	7566	1987-04-19 00:00:00	1500.00		20
7839	KING	PRESIDENT		1981-11-17 00:00:00	5000.00		10
7844	TURNER	SALESMAN	7698	1981-09-08 00:00:00	1500.00	0.00	30
7876	ADAMS	CLERK	7788	1987-05-23 00:00:00	1100.00		20
7900	JAMES	CLERK	7698	1981-12-03 00:00:00	950.00		30
7902	FORD	ANALYST	7566	1981-12-03 00:00:00	3000.00		20
7934	MILLER	CLERK	7782	1982-01-23 00:00:00	1300.00		10

ALTER TABLE table_name RENAME TO new_table_name;

ALTER TABLE emp_temp RENAME TO new_emp; --把 emp_temp 表重命名为 new_emp

ALTER TABLE table_name [PARTITION partition_spec] CHANGE [COLUMN] col_old_name col_new_name column_type
  [COMMENT col_comment] [FIRST|AFTER column_name] [CASCADE|RESTRICT];

-- 修改字段名和类型
ALTER TABLE emp_temp CHANGE empno empno_new INT;
 
-- 修改字段 sal 的名称 并将其放置到 empno 字段后
ALTER TABLE emp_temp CHANGE sal sal_new decimal(7,2)  AFTER ename;

-- 为字段增加注释
ALTER TABLE emp_temp CHANGE mgr mgr_new INT COMMENT 'this is column mgr';

ALTER TABLE emp_temp ADD COLUMNS (address STRING COMMENT 'home address');

-- 清空整个表或表指定分区中的数据
TRUNCATE TABLE table_name [PARTITION (partition_column = partition_col_value,  ...)];

TRUNCATE TABLE emp_mgt_ptn PARTITION (deptno=20);

DROP TABLE [IF EXISTS] table_name [PURGE]; 

DESCRIBE|Desc DATABASE [EXTENDED] db_name;  --EXTENDED 是否显示额外属性

DESCRIBE|Desc [EXTENDED|FORMATTED] table_name --FORMATTED 以友好的展现方式查看表详情

-- 语法
SHOW (DATABASES|SCHEMAS) [LIKE 'identifier_with_wildcards'];

-- 示例：
SHOW DATABASES like 'hive*';

-- 语法
SHOW TABLES [IN database_name] ['identifier_with_wildcards'];

-- 示例
SHOW TABLES IN default;

SHOW VIEWS [IN/FROM database_name] [LIKE 'pattern_with_wildcards'];   --仅支持 Hive 2.2.0 +

SHOW PARTITIONS table_name;

SHOW CREATE TABLE ([db_name.]table_name|view_name);