大数据入门第十一天——hive详解（二）基本操作与分区分桶

一、基本操作

　　1.DDL

　　　　官网的DDL语法教程：点击查看

　　　　建表语句

CREATE [EXTERNAL] TABLE [IF NOT EXISTS] table_name 
   [(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] 
   [ROW FORMAT row_format] 
   [STORED AS file_format] 
   [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)
 

数据类型