创建库
create database if not exists xxuu_test;
查询库
show databases;
show databases like 'xxuu_*'
库信息
//查询库的hdfs路径
desc database xxuu_test;
desc database extended xxuu_test;
删除库
drop database if exists xxuu_test;
切换库
use xxuu_test;
创建表
(内部表,外部表,分区表,分桶表)
语法说明:
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]
1. 创建Table 内部表
create table if not exists dim_wd_djzclx(
djzclxdl_dm string,
djzclxdlmc string,
djzclxzl_dm string,
djzclxzlmc string,
djzclxxl_dm string,
djzclxxlmc string,
gybz string
)
ROW FORMAT DELIMITED
FIELDS TERMINATED BY ','
STORED AS TEXTFILE;
2. 创建External Table 外部表
create EXTERNAL table if not exists ext_dim_wd_djzclx(
djzclxdl_dm string,
djzclxdlmc string,
djzclxzl_dm string,
djzclxzlmc string,
djzclxxl_dm string,
djzclxxlmc string,
gybz string
)
ROW FORMAT DELIMITED
FIELDS TERMINATED BY ','
LOCATION '/opt/gengxu/external/ext_dim_wd_djzclx';
3. 创建Partition 分区表
create table if not exists par_dim_wd_djzclx(
djzclxdl_dm string,
djzclxdlmc string,
djzclxzl_dm string,
djzclxzlmc string,
djzclxxl_dm string,
djzclxxlmc string,
gybz string
)
partitioned by (djzclxdl_dm string)
ROW FORMAT DELIMITED
FIELDS TERMINATED BY ',';
4. 创建Bucket Table 桶表
删除表
drop table dim_wd_djzclx
导出数据
INSERT OVERWRITE LOCAL DIRECTORY '/app/hadoop_output_data/dim_wd_djzclx' ROW FORMAT DELIMITED FIELDS TERMINATED by ',' select * from dim_wd_djzclx;
查询数据
cat /app/hadoop_output_data/dim_wd_djzclx/000000_0
导入数据
load data local inpath '/opt/gengxu/hadoop_output_data/dim_wd_djzclx/000000_0' overwrite into table dim_wd_djzclx;