02-开始建表_离线数仓项目

Posted 2020-12-13 mengbin0546

 

一.  建表，导数据

1. 创建库

create database gmall;

 

2. 创建表start_log，ods层表

drop table if exists ods_start_log;
CREATE EXTERNAL TABLE ods_start_log (`line` string)
PARTITIONED BY (`dt` string)
STORED AS
  INPUTFORMAT ‘com.hadoop.mapred.DeprecatedLzoTextInputFormat‘
  OUTPUTFORMAT ‘org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat‘
LOCATION ‘/warehouse/gmall/ods/ods_start_log‘;

3. 导入数据

load data inpath ‘/origin_data/gmall/log/topic_start/2020-06-29‘ into table gmall.ods_start_log partition(dt=‘2020-06-29‘);

 

创建event_log

drop table if exists ods_event_log;
CREATE EXTERNAL TABLE ods_event_log(`line` string)
PARTITIONED BY (`dt` string)
STORED AS
  INPUTFORMAT ‘com.hadoop.mapred.DeprecatedLzoTextInputFormat‘
  OUTPUTFORMAT ‘org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat‘
LOCATION ‘/warehouse/gmall/ods/ods_event_log‘;

 

 

load data inpath ‘/origin_data/gmall/log/topic_event/2020-06-29‘ into table gmall.ods_event_log partition(dt=‘2020-06-29‘);

 

二.导入数据到ods层中，通过脚本导入