Hive官方手册学习(二)Hive数据定义语言DDL

一、数据库相关操作(DATABASE)

1.1 创建数据库(create)

CREATE DATABASE [IF NOT EXISTS] database_name
  [COMMENT database_comment]
  [LOCATION hdfs_path]
  [WITH DBPROPERTIES (property_name=property_value, ...)];

默认地址:/user/hive/warehouse/db_name.db/table_name/partition_name/…

1.2 使用数据库(use)

USE database_name;

注意:只有use时不用写DATABASE关键字

1.3 删除数据库(drop)

DROP DATABASE [IF EXISTS] database_name [RESTRICT|CASCADE];

1.4 修改数据库(alter)

1.4.1 修改数据库属性

ALTER DATABASE database_name SET DBPROPERTIES (property_name=property_value, …);

1.4.2 修改数据库所有者

ALTER DATABASE database_name SET OWNER [USER|ROLE] user_or_role;

二、新建和删除数据表(Create/Drop/Truncate Table)

2.1 创建数据表(create)

# 手动建表
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)

# 复制表结构
CREATE [TEMPORARY] [EXTERNAL] TABLE [IF NOT EXISTS] [db_name.]table_name
  LIKE existing_table_or_view_name
  [LOCATION hdfs_path];

数据类型
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
  | 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)

# 行列分隔符 
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, ...)]

# 文件存储格式 
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

2.1.1 行格式,文件存储格式,SerDe

ROW FORMAT DELIMITED FIELDS TERMINATED BY ‘\001’ STORED AS SEQUENCEFILE;
ROW FORMAT SERDE … STORED AS SEQUENCEFILE;

RegEx SerDe

CREATE TABLE apachelog (
  host STRING,
  identity STRING,
  user STRING,
  time STRING,
  request STRING,
  status STRING,
  size STRING,
  referer STRING,
  agent STRING)
ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.RegexSerDe'
WITH SERDEPROPERTIES (
  "input.regex" = "([^]*) ([^]*) ([^]*) (-|\\[^\\]*\\]) ([^ \"]*|\"[^\"]*\") (-|[0-9]*) (-|[0-9]*)(?: ([^ \"]*|\".*\") ([^ \"]*|\".*\"))?"
)
STORED AS TEXTFILE;

2.1.2 分区表(partitioned by)

CREATE TABLE page_view(viewTime INT, userid BIGINT,
     page_url STRING, referrer_url STRING,
     ip STRING COMMENT 
  • 2
    点赞
  • 5
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值