Hive的数据类型

–: primitive_type
–| array_type
–| map_type
–| struct_type
–：primitive_type
–|TINYINT
–| SMALLINT
–| INT
–| BIGINT
–| BOOLEAN
–| FLOAT
–| DOUBLE
–| STRING

Hive完整的DDL

–CREATE [EXTERNAL] TABLE [IF NOT EXISTS] [db_name.]table_name
–[(col_namedata_type[COMMENT col_comment], ...)]
–[COMMENT table_comment]
–[PARTITIONED BY (col_namedata_type[COMMENT col_comment], ...)]
–[CLUSTERED BY (col_name, col_name, ...) [SORTED BY (col_name[ASC|DESC], ...)] INTO num_bucketsBUCKETS]
–[SKEWED BY (col_name, col_name, ...) ON ([(col_value, col_value, ...), ...|col_value, col_value, ...]) (Note: only available starting with 0.10.0)]
–[ [ROW FORMAT row_format] [STORED AS file_format]
–| STORED BY 'storage.handler.class.name' [WITH SERDEPROPERTIES (...)] (Note: only available starting with 0.6.0) ]
–[LOCATION hdfs_path]
–[TBLPROPERTIES (property_name=property_value, ...)] (Note: only available starting with 0.6.0)
–[AS select_statement] (Note: this feature is only available starting with 0.5.0, and is not supported when creating external tables.)###Hive常用的DDL
–CREATE [EXTERNAL] TABLE [IF NOT EXISTS] [db_name.]table_name
–LIKE existing_table_or_view_name
–[LOCATION hdfs_path]###Hive建表
–create table person(
–id int,
–name string,
–age int,
–likes array<string>,
–address map<string,string>
–)
–row format delimited
–FIELDS TERMINATED BY ','
–COLLECTION ITEMS TERMINATED BY '-'
–MAP KEYS TERMINATED BY ':'
–lines terminated by '\n';
–Select address[‘city’] from person where name=‘zs’###创建分区表
-partition分区放在ROW FORMAT 之前
-分区地段不能出现之前定义的字段之内
–Load分区数据###Hive常用的DDL删除表
–DROP TABLE table_name

Hive导入数据

Load data [local] inpath 'student.txt' overwrite into table student.
- 添加local 说明在数据文件在搭建集群的文件系统上
- 没有local 说明在集群的hdfs上

Hive的内表和外表
External关键字
内表删除表或者分区元数据和数据都删了
外表删除表元数据删除，数据保留

HIve的分区partition

• 必须在表定义时创建partition
  • 单分区建表语句：create table day_table(id int, content string) partitioned by (dt string)
    • 单分区表，按天分区，在表结构中存在id，content，dt三列。
    • 以dt为文件夹区分
  • 双分区建表语句：create table day_hour_table(id int, content string) partitioned by (dt string, hour string)
    • 双分区表，按天和小时分区，在表结构中新增加了dt和hour两列。
    • 先以dt为文件夹，再以hour子文件夹区分
• Hive添加分区表语法
  • （表已创建，在此基础上添加分区）：ALTER TABLE table_name ADD partition_spec[ LOCATION 'location1' ]partition_spec[ LOCATION 'location2' ] ...
  • ALTER TABLE day_table ADD PARTITION (dt='2008-08-08', hour='08') location '/path/pv1.txt'
• Hive删除分区语法
  • ALTER TABLE table_name  DROP  partition_spec, partition_spec,...
  • 用户可以用ALTER TABLE DROP PARTITION 来删除分区。分区的元数据和数据将被一并删除。例：
    • ALTER TABLE day_hour_table  DROP  PARTITION (dt='2008-08-08', hour='09');
• Hive数据加载进分区表中语法
  • LOAD DATA [LOCAL] INPATH 'filepath' [OVERWRITE] INTO TABLE tablename [PARTITION (partcol1=val1, partcol2=val2 ...)]
  • 例如：LOAD DATA INPATH '/user/pv.txt' INTO TABLE day_hour_table PARTITION(dt='2008-08-08', hour='08'); LOAD DATA local INPATH '/user/hua/*' INTO TABLE day_hourpartition(dt='2010-07-07');当数据被加载至表中时，不会对数据进行任何转换。Load操作只是将数据复制至Hive表对应的位置。数据加载时在表下自动创建一个目录基于分区的查询的语句：SELECT day_table.* FROM day_tableWHERE day_table.dt>= '2008-08-08';
• Hive查看分区语句
  • hive> show partitions day_hour_table; OK dt=2008-08-08/hour=08 dt=2008-08-08/hour=09 dt=2008-08-09/hour=09

HQL

create database test;
show databases;
use databases;###--psn
#1,xiaoming1,man,book-shejian-shoot,beijing:wudaokou-huoxing:weizhi-shanghai:songjiang
#2,xiaoming2,man,shejian-shoot,beijing:wudaokou-huoxing:weizhi
#3,xiaoming3,man,book,beijing:wudaokou-huoxing:weizhi
#4,xiaoming4,man,book-shoot,beijing:wudaokou-huoxing:weizhi
####创建表psn
create table psn(id int, name string, sex string, likes ARRAY<string>, address map<string,string>)
ROW FORMAT DELIMITED
FIELDS TERMINATED BY ','
COLLECTION ITEMS TERMINATED BY '-'
MAP KEYS TERMINATED BY ':';
#加载数据
load data local inpath '/tmp/psn' overwrite into table psn;
#创建外表
create EXTERNAL table psn2
(id int, name string, sex string, likes ARRAY<string>, address map<string,string>)
ROW FORMAT DELIMITED
FIELDS TERMINATED BY ','
COLLECTION ITEMS TERMINATED BY '-'
MAP KEYS TERMINATED BY ':'
location '/test/psn2';create table psn3 as select * from psn;create table psn4 like psn;create EXTERNAL table psn5
(id int, name string, sex string, likes ARRAY<string>, address map<string,string>)
PARTITIONED BY (age int, weight int)
ROW FORMAT DELIMITED
FIELDS TERMINATED BY ','
COLLECTION ITEMS TERMINATED BY '-'
MAP KEYS TERMINATED BY ':' ;create table psn7
(id int, name string, sex string, likes ARRAY<string>, address map<string,string>)
ROW FORMAT DELIMITED
FIELDS TERMINATED BY ','
COLLECTION ITEMS TERMINATED BY '-'
MAP KEYS TERMINATED BY ':';from psn6 p
insert into table psn7select p.id, p.name, p.sex, p.likes, p.address;from psn6 p
insert OVERWRITE table psn7select p.id, p.name, p.sex, p.likes, p.address;