转 hive表操作

https://cwiki.apache.org/confluence/display/Hive/LanguageManual+DDL#LanguageManualDDL-CreateTableCreate/Drop/TruncateTable

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], ... [constraint_specification])]
  [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)

CREATE [TEMPORARY] [EXTERNAL] TABLE [IF NOT EXISTS] [db_name.]table_name
  LIKE existing_table_or_view_name
  [LOCATION hdfs_path];

data_type
  : primitive_type
  | array_type
  | map_type
  | struct_type
  | union_type  -- (Note: Available in Hive 0.7.0 and later)

primitive_type
  : TINYINT
  | SMALLINT
  | INT
  | BIGINT
  | BOOLEAN
  | FLOAT
  | DOUBLE
  | DOUBLE PRECISION -- (Note: Available in Hive 2.2.0 and later)
  | STRING
  | BINARY      -- (Note: Available in Hive 0.8.0 and later)
  | TIMESTAMP   -- (Note: Available in Hive 0.8.0 and later)
  | DECIMAL     -- (Note: Available in Hive 0.11.0 and later)
  | DECIMAL(precision, scale)  -- (Note: Available in Hive 0.13.0 and later)
  | DATE        -- (Note: Available in Hive 0.12.0 and later)
  | VARCHAR     -- (Note: Available in Hive 0.12.0 and later)
  | CHAR        -- (Note: Available in Hive 0.13.0 and later)

array_type
  : ARRAY < data_type >

map_type
  : MAP < primitive_type, data_type >

struct_type
  : STRUCT < col_name : data_type [COMMENT col_comment], ...>

union_type
   : UNIONTYPE < data_type, data_type, ... >  -- (Note: Available in Hive 0.7.0 and later)

row_format
  : DELIMITED [FIELDS TERMINATED BY char [ESCAPED BY char]] [COLLECTION ITEMS TERMINATED BY char]
        [MAP KEYS TERMINATED BY char] [LINES TERMINATED BY char]
        [NULL DEFINED AS char]   -- (Note: Available in Hive 0.13 and later)
  | SERDE serde_name [WITH SERDEPROPERTIES (property_name=property_value, property_name=property_value, ...)]

file_format:
  : SEQUENCEFILE
  | TEXTFILE    -- (Default, depending on hive.default.fileformat configuration)
  | RCFILE      -- (Note: Available in Hive 0.6.0 and later)
  | ORC         -- (Note: Available in Hive 0.11.0 and later)
  | PARQUET     -- (Note: Available in Hive 0.13.0 and later)
  | AVRO        -- (Note: Available in Hive 0.14.0 and later)
  | INPUTFORMAT input_format_classname OUTPUTFORMAT output_format_classname

constraint_specification:
  : [, PRIMARY KEY (col_name, ...) DISABLE NOVALIDATE ]
    [, CONSTRAINT constraint_name FOREIGN KEY (col_name, ...) REFERENCES table_name(col_name, ...) DISABLE NOVALIDATE 

一、创建表方式1

create table hive.emp(
empno int, 
ename string, 
job string, 
mgr int, 
hiredate string, 
sal double, 
comm double, 
deptno int
)
COMMENT 'The table belong to hive database'
row format delimited fields terminated by '	';

创建了一个emp表，这个表存属于hive数据库，如果不指定就默认属于default数据库。还为这张表加了注释（The table belong to hive database），指定字段与字段之间的分隔符为 。

下面将emp.txt文件内容加载到emp中

 [root@hadoop001 data]# cat emp.txt
7369    SMITH   CLERK   7902    1980-12-17      800.00          20
7499    ALLEN   SALESMAN        7698    1981-2-20       1600.00 300.00  30
7521    WARD    SALESMAN        7698    1981-2-22       1250.00 500.00  30
7566    JONES   MANAGER 7839    1981-4-2        2975.00         20
7654    MARTIN  SALESMAN        7698    1981-9-28       1250.00 1400.00 30
7698    BLAKE   MANAGER 7839    1981-5-1        2850.00         30
7782    CLARK   MANAGER 7839    1981-6-9        2450.00         10
7788    SCOTT   ANALYST 7566    1987-4-19       3000.00         20
7839    KING    PRESIDENT               1981-11-17      5000.00         10
7844    TURNER  SALESMAN        7698    1981-9-8        1500.00 0.00    30
7876    ADAMS   CLERK   7788    1987-5-23       1100.00         20
7900    JAMES   CLERK   7698    1981-12-3       950.00          30
7902    FORD    ANALYST 7566    1981-12-3       3000.00         20
7934    MILLER  CLERK   7782    1982-1-23       1300.00         10
8888    HIVE    PROGRAM 7839    1988-1-23       10300.00   

使用load加载数据

hive> load data local inpath '/root/data/emp.txt' overwrite into table hive.emp;
Loading data to table hive.emp
OK
Time taken: 2.296 seconds

此时查看hive表已有了数据了

hive> select * from hive.emp;
OK
7369    SMITH   CLERK   7902    1980-12-17      800.0   NULL    20
7499    ALLEN   SALESMAN        7698    1981-2-20       1600.0  300.0   30
7521    WARD    SALESMAN        7698    1981-2-22       1250.0  500.0   30
7566    JONES   MANAGER 7839    1981-4-2        2975.0  NULL    20
7654    MARTIN  SALESMAN        7698    1981-9-28       1250.0  1400.0  30
7698    BLAKE   MANAGER 7839    1981-5-1        2850.0  NULL    30
7782    CLARK   MANAGER 7839    1981-6-9        2450.0  NULL    10
7788    SCOTT   ANALYST 7566    1987-4-19       3000.0  NULL    20
7839    KING    PRESIDENT       NULL    1981-11-17      5000.0  NULL    10
7844    TURNER  SALESMAN        7698    1981-9-8        1500.0  0.0     30
7876    ADAMS   CLERK   7788    1987-5-23       1100.0  NULL    20
7900    JAMES   CLERK   7698    1981-12-3       950.0   NULL    30
7902    FORD    ANALYST 7566    1981-12-3       3000.0  NULL    20
7934    MILLER  CLERK   7782    1982-1-23       1300.0  NULL    10
8888    HIVE    PROGRAM 7839    1988-1-23       10300.0 NULL    NULL
Time taken: 2.762 seconds, Fetched: 15 row(s)

二、创建表方式2 
创建一个和emp结构和数据相同的表emp2

create table emp2 as  select * from emp;

hive> select * from  emp2;
OK
7369    SMITH   CLERK   7902    1980-12-17      800.0   NULL    20
7499    ALLEN   SALESMAN        7698    1981-2-20       1600.0  300.0   30
7521    WARD    SALESMAN        7698    1981-2-22       1250.0  500.0   30
7566    JONES   MANAGER 7839    1981-4-2        2975.0  NULL    20
7654    MARTIN  SALESMAN        7698    1981-9-28       1250.0  1400.0  30
7698    BLAKE   MANAGER 7839    1981-5-1        2850.0  NULL    30
7782    CLARK   MANAGER 7839    1981-6-9        2450.0  NULL    10
7788    SCOTT   ANALYST 7566    1987-4-19       3000.0  NULL    20
7839    KING    PRESIDENT       NULL    1981-11-17      5000.0  NULL    10
7844    TURNER  SALESMAN        7698    1981-9-8        1500.0  0.0     30
7876    ADAMS   CLERK   7788    1987-5-23       1100.0  NULL    20
7900    JAMES   CLERK   7698    1981-12-3       950.0   NULL    30
7902    FORD    ANALYST 7566    1981-12-3       3000.0  NULL    20
7934    MILLER  CLERK   7782    1982-1-23       1300.0  NULL    10
8888    HIVE    PROGRAM 7839    1988-1-23       10300.0 NULL    NULL
Time taken: 0.189 seconds, Fetched: 15 row(s)

三、创建表方式3 
创建一个和emp相同结构的表emp3

hive (hive)> create table emp3 like emp;
OK
Time taken: 0.992 seconds

like 只复制结构，不复制内容

四、删除表

hive (hive)> drop table emp2;
OK
Time taken: 0.197 seconds

五、清除表中数据，保留结构

hive (hive)> truncate table emp2;
OK
Time taken: 0.197 seconds
原文 ：http://blog.csdn.net/gavin_chun/article/details/78009340