create table tb (id int, name String, age int);  

create table ez_part_test (  id int,   col1 string,   col2 string) partitioned by   (type int) stored as orc  

外部表（HDFS）

create external table example_csv_tb (  id int,  col1 string,  col2 string) ROW FORMAT   delimited fields terminated by ','   lines terminated by '\n'  stored as textfile location "/ez/example"  

1,java,20
2,c,40
3,Golang,8
4,Perl,35
5,PHP,20  

create external table lang (  id int,  name string,  field1 int) ROW FORMAT  delimited   fields terminated by ','  lines terminated by '\n'  stored as textfile   location "/ez/example/lang.csv"  

文件第一列是数字，我们定义为id列，第二列定义为name，第三列随便指定个名字为field。列与列间用逗号隔开。一行记录结束用换行符 ‘\n’结尾。于是后面的ROW FORMAT row_format子句定义整个格式行为，如下：

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, ...)]  

stored as file_format声明存储的文件为什么格式。


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  

这里我们配置TEXTFILE（文本文件），也是默认的Hive外部表存储格式。

location hdfs_path子句意思很明显了，数据文件存储的位置，注：必须是HDFS文件路径。
至此一个最简单的外部表就创建完成了。可以直接使用如下语句查询试试：

select * from lang;  

注意：这里我们没有指定数据库，所以这个表将创建在default数据库中，Hive默认内置的一个数据库。

2、内部表
例如，我们没有数据文件，只是想创建一个Hive表，这个Hive表以后用于存储数据用，或从其他数据源导入，或程序写入等。内部表看起来就像RDBMS的数据表，Hive有足够大的权限可以操纵表里的数据，包括删除。
创建外部表时，使用的语句是create external table。而默认情况下，不使用external则是默认创建内部表。

以下是创建表语法：

    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  

三、创建分区表

create table partition_tb (
id int, col1 string, col2 string)
partitioned by (type int)
stored as ORC  

这里需要注意，当指定分区列时，分区列不能是数据列。上面type列就没有出现在数据列（id，col1，col2）中。而在查询和写入语句中，type列完全可以像普通数据列一样使用，放在where子句，放在select列中。

ALTER TABLE table_name ADD [IF NOT EXISTS] PARTITION partition_spec   [LOCATION 'location1'] partition_spec [LOCATION 'location2'] ...;  partition_spec:  : (partition_column = partition_col_value, partition_column = partition_col_value, ...)  

alter table partition_tb add partition (type = 1)  

注意：这里也可以指定LOCATION子句，这样分区目录将创建到LOCATION下。但之前的数据将还存在这个表中。

DROP TABLE [IF EXISTS] table_name [PURGE];     -- (Note: PURGE available in Hive 0.14.0 and later)  

下一篇将记录表操作CURD及笔者倒腾Hive遇到的一些坑。