第8章 数仓开发之DIM层¶
DIM层设计要点：
（1）DIM层的设计依据是维度建模理论，该层存储维度模型的维度表。
（2）DIM层的数据存储格式为orc列式存储+snappy压缩。
（3）DIM层表名的命名规范为dim_表名_全量表或者拉链表标识（full/zip）
8.1 章节维度表（全量）¶
1）建表语句
DROP TABLE IF EXISTS dim_chapter_full;
CREATE EXTERNAL TABLE dim_chapter_full
(
`id` STRING COMMENT '章节ID',
`chapter_name` STRING COMMENT '章节名称',
`course_id` STRING COMMENT '课程ID',
`video_id` STRING COMMENT '视频ID',
`publisher_id` STRING COMMENT '发布者ID',
`is_free` STRING COMMENT '是否免费',
`create_time` STRING COMMENT '创建时间',
`update_time` STRING COMMENT '更新时间'
) COMMENT '章节维度表'
PARTITIONED BY (`dt` STRING)
STORED AS ORC
LOCATION '/warehouse/edu/dim/dim_chapter_full/'
TBLPROPERTIES ('orc.compress' = 'snappy');
2）数据装载
insert overwrite table edu.dim_chapter_full
partition (dt = '2022-02-21')
select id,
chapter_name,
course_id,
video_id,
publisher_id,
is_free,
create_time,
update_time
from edu.ods_chapter_info_full
where deleted = '0'
and dt = '2022-02-21';
8.2 课程维度表（全量）¶
1）建表语句
DROP TABLE IF EXISTS dim_course_full;
CREATE EXTERNAL TABLE dim_course_full
(
`id` STRING COMMENT '编号',
`course_name` STRING COMMENT '课程名称',
`subject_id` STRING COMMENT '学科id',
`subject_name` STRING COMMENT '学科名称',
`category_id` STRING COMMENT '分类id',
`category_name` STRING COMMENT '分类名称',
`teacher` STRING COMMENT '讲师名称',
`publisher_id` STRING COMMENT '发布者id',
`chapter_num` BIGINT COMMENT '章节数',
`origin_price` decimal(16, 2) COMMENT '价格',
`reduce_amount` decimal(16, 2) COMMENT '优惠金额',
`actual_price` decimal(16, 2) COMMENT '实际价格',
`create_time` STRING COMMENT '创建时间',
`update_time` STRING COMMENT '更新时间',
`chapters` ARRAY<STRUCT<chapter_id : STRING,chapter_name : STRING, video_id : STRING,is_free : STRING>> COMMENT '章节'
) COMMENT '课程维度表'
PARTITIONED BY (`dt` STRING)
STORED AS ORC
LOCATION '/warehouse/edu/dim/dim_course_full/'
TBLPROPERTIES ('orc.compress' = 'snappy');
2）数据装载
with a as
(
select id, category_name
from edu.ods_base_category_info_full
where deleted = '0'
and dt = '2022-02-21'
),
b as
(
select id, subject_name, category_id
from edu.ods_base_subject_info_full
where deleted = '0'
and dt = '2022-02-21'
),
c as
(
select id,
course_name,
subject_id,
teacher,
publisher_id,
chapter_num,
origin_price,
reduce_amount,
actual_price,
create_time,
update_time
from edu.ods_course_info_full
where deleted = '0'
and dt = '2022-02-21'
),
d as
(
select course_id,
collect_set(named_struct('chapter_id', id, 'chapter_name', chapter_name, 'video_id', video_id, 'is_free', is_free)) chapters
from edu.ods_chapter_info_full
where deleted = '0'
and dt = '2022-02-21'
group by course_id
)
insert overwrite table edu.dim_course_full
partition(dt = '2022-02-21')
select c.id,
course_name,
subject_id,
subject_name,
category_id,
category_name,
teacher,
publisher_id,
chapter_num,
origin_price,
reduce_amount,
actual_price,
create_time,
update_time,
chapters
from c
left join b
on c.subject_id = b.id
left join a
on b.category_id = a.id
left join d
on c.id = d.course_id;
8.3 视频维度表（全量）¶
1）建表语句
DROP TABLE IF EXISTS dim_video_full;
CREATE EXTERNAL TABLE dim_video_full
(
`id` STRING COMMENT '编号',
`video_name` STRING COMMENT '视频名称',
`during_sec` BIGINT COMMENT '时长',
`video_status` STRING COMMENT '状态 未上传，上传中，上传完',
`video_size` BIGINT COMMENT '大小',
`version_id` STRING COMMENT '版本号',
`chapter_id` STRING COMMENT '章节id',
`chapter_name` STRING COMMENT '章节名称',
`is_free` STRING COMMENT '是否免费',
`course_id` STRING COMMENT '课程id',
`publisher_id` STRING COMMENT '发布者id',
`create_time` STRING COMMENT '创建时间',
`update_time` STRING COMMENT '更新时间'
) COMMENT '视频维度表'
PARTITIONED BY (`dt` STRING)
STORED AS ORC
LOCATION '/warehouse/edu/dim/dim_video_zip/'
TBLPROPERTIES ('orc.compress' = 'snappy');
2）数据装载
insert overwrite table edu.dim_video_full partition (dt = '2022-02-21')
select vt.id,
video_name,
during_sec,
video_status,
video_size,
version_id,
chapter_id,
chapter_name,
is_free,
course_id,
publisher_id,
create_time,
update_time
from (
select id,
video_name,
during_sec,
video_status,
video_size,
version_id,
chapter_id,
course_id,
publisher_id,
create_time,
update_time
from edu.ods_video_info_full
where dt = '2022-02-21' and deleted = '0'
) vt
join
(
select id,
chapter_name,
is_free
from edu.ods_chapter_info_full
where dt = '2022-02-21'
) cht
on vt.chapter_id = cht.id;
8.4 试卷维度表（全量）¶
1）建表语句
DROP TABLE IF EXISTS dim_paper_full;
CREATE EXTERNAL TABLE dim_paper_full
(
`id` STRING COMMENT '编号',
`paper_title` STRING COMMENT '试卷名称',
`course_id` STRING COMMENT '课程id',
`create_time` STRING COMMENT '创建时间',
`update_time` STRING COMMENT '更新时间',
`publisher_id` STRING COMMENT '发布者id',
`questions` ARRAY<STRUCT<question_id: STRING, score: DECIMAL(16, 2)>> COMMENT '题目'
) COMMENT '试卷维度表'
PARTITIONED BY (`dt` STRING)
STORED AS ORC
LOCATION '/warehouse/edu/dim/dim_paper_full/'
TBLPROPERTIES ('orc.compress' = 'snappy');
2）数据装载
insert overwrite table edu.dim_paper_full partition (dt = '2022-02-21')
select t1.id,
paper_title,
course_id,
create_time,
update_time,
publisher_id,
questions
from edu.ods_test_paper_full t1
left join
(
select paper_id,
collect_set(named_struct('question_id', question_id, 'score', score)) questions
from edu.ods_test_paper_question_full
where deleted = '0' and dt = '2022-02-21'
group by paper_id
) t2
on t1.id = t2.paper_id
where t1.deleted = '0' and t1.dt = '2022-02-21';
8.5 来源维度表（全量）¶
1）建表语句
DROP TABLE IF EXISTS dim_source_full;
CREATE EXTERNAL TABLE dim_source_full
(
`id` STRING COMMENT '编号',
`source_site` STRING COMMENT '来源'
) COMMENT '来源维度表'
PARTITIONED BY (`dt` STRING)
STORED AS ORC
LOCATION '/warehouse/edu/dim/dim_source_full/'
TBLPROPERTIES ('orc.compress' = 'snappy');
2）数据装载
insert overwrite table edu.dim_source_full partition (dt = '2022-02-21')
select id,
source_site
from edu.ods_base_source_full obsf
where dt = '2022-02-21';
8.6 题目维度表（全量）¶
1）建表语句
DROP TABLE IF EXISTS dim_question_full;
CREATE EXTERNAL TABLE dim_question_full
(
`id` STRING COMMENT '编号',
`chapter_id` STRING COMMENT '章节id',
`course_id` STRING COMMENT '课程id',
`question_type` BIGINT COMMENT '题目类型',
`create_time` STRING COMMENT '创建时间',
`update_time` STRING COMMENT '更新时间',
`publisher_id` STRING COMMENT '发布者id'
) COMMENT '题目维度表'
PARTITIONED BY (`dt` STRING)
STORED AS ORC
LOCATION '/warehouse/edu/dim/dim_question_full/'
TBLPROPERTIES ('orc.compress' = 'snappy');
2）数据装载
insert overwrite table edu.dim_question_full
partition (dt = '2022-02-21')
select id,
chapter_id,
course_id,
question_type,
create_time,
update_time,
publisher_id
from edu.ods_test_question_info_full
where deleted = '0'
and dt = '2022-02-21';
8.7 地区维度表（全量）¶
1）建表语句
DROP TABLE IF EXISTS dim_province_full;
CREATE EXTERNAL TABLE dim_province_full
(
`id` STRING COMMENT '编号',
`name` STRING COMMENT '省名称',
`region_id` STRING COMMENT '地区id',
`area_code` STRING COMMENT '行政区位码',
`iso_code` STRING COMMENT '国际编码',
`iso_3166_2` STRING COMMENT 'ISO3166编码'
) COMMENT '地区维度表'
PARTITIONED BY (`dt` STRING)
STORED AS ORC
LOCATION '/warehouse/edu/dim/dim_province_full/'
TBLPROPERTIES ('orc.compress' = 'snappy');
2）数据装载
insert overwrite table edu.dim_province_full partition (dt = '2022-02-21')
select id,
name,
region_id,
area_code,
iso_code,
iso_3166_2
from edu.ods_base_province_full
where dt = '2022-02-21';
8.8 时间维度表（特殊）¶
1）建表语句
DROP TABLE IF EXISTS dim_date;
CREATE EXTERNAL TABLE dim_date
(
`date_id` STRING COMMENT '日期id',
`week_id` STRING COMMENT '周id,一年中的第几周',
`week_day` STRING COMMENT '周几',
`day` STRING COMMENT '每月的第几天',
`month` STRING COMMENT '一年中的第几月',
`quarter` STRING COMMENT '一年中的第几季度',
`year` STRING COMMENT '年份',
`is_workday` STRING COMMENT '是否是工作日',
`holiday_id` STRING COMMENT '节假日'
) COMMENT '时间维度表'
STORED AS ORC
LOCATION '/warehouse/edu/dim/dim_date/'
TBLPROPERTIES ('orc.compress' = 'snappy');
2）创建临时表
DROP TABLE IF EXISTS tmp_dim_date_info;
CREATE EXTERNAL TABLE tmp_dim_date_info (
`date_id` STRING COMMENT '日',
`week_id` STRING COMMENT '周id',
`week_day` STRING COMMENT '周几',
`day` STRING COMMENT '每月的第几天',
`month` STRING COMMENT '第几月',
`quarter` STRING COMMENT '第几季度',
`year` STRING COMMENT '年',
`is_workday` STRING COMMENT '是否是工作日',
`holiday_id` STRING COMMENT '节假日'
) COMMENT '时间维度表'
ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t'
LOCATION '/warehouse/edu/tmp/tmp_dim_date_info/';
3）上传date.info文件
将数据文件date.info（在本书提供的资料中可以找到）上传到HFDS上临时表指定路径/warehouse/edu/tmp/tmp_dim_date_info/。
4）执行以下语句将其导入时间维度表。
5）检查数据是否导入成功。
8.9 用户维度表（拉链表）¶
1）建表语句
DROP TABLE IF EXISTS dim_user_zip;
CREATE EXTERNAL TABLE dim_user_zip
(
`id` STRING COMMENT '编号',
`login_name` STRING COMMENT '用户名称',
`nick_name` STRING COMMENT '用户昵称',
`real_name` STRING COMMENT '用户姓名',
`phone_num` STRING COMMENT '手机号',
`email` STRING COMMENT '邮箱',
`user_level` STRING COMMENT '用户级别',
`birthday` STRING COMMENT '用户生日',
`gender` STRING COMMENT '性别 M男,F女',
`create_time` STRING COMMENT '创建时间',
`operate_time` STRING COMMENT '修改时间',
`status` STRING COMMENT '状态',
`start_date` STRING COMMENT '开始日期',
`end_date` STRING COMMENT '结束日期'
) COMMENT '用户表'
PARTITIONED BY (`dt` STRING)
STORED AS ORC
LOCATION '/warehouse/edu/dim/dim_user_zip/'
TBLPROPERTIES ('orc.compress' = 'snappy');
2）分区规划
3）数据装载
（1）数据装载过程
（2）数据流向
（3）首日装载
insert overwrite table edu.dim_user_zip
partition (dt = '9999-12-31')
select data.id,
data.login_name,
data.nick_name,
md5(data.real_name),
md5(if(data.phone_num regexp '^(13[0-9]|14[01456879]|15[0-35-9]|16[2567]|17[0-8]|18[0-9]|19[0-35-9])\\d{8}$',data.phone_num,null)),
md5(if(data.email regexp '^[a-zA-Z0-9_-]+@[a-zA-Z0-9_-]+(\\.[a-zA-Z0-9_-]+)+$',data.email,null)),
data.user_level,
data.birthday,
data.gender,
data.create_time,
data.operate_time,
data.status,
'2022-02-21' start_date,
'9999-12-31' end_date
from edu.ods_user_info_inc
where dt = '2022-02-21'
and type = 'bootstrap-insert';
（4）每日装载
装载思路
装载语句
set hive.exec.dynamic.partition.mode=nonstrict;
insert overwrite table edu.dim_user_zip
partition(dt)
select
id,
login_name,
nick_name,
real_name,
phone_num,
email,
user_level,
birthday,
gender,
create_time,
operate_time,
status,
start_date,
if(rn=1,'9999-12-31',date_sub('2022-02-22',1)) end_date,
if(rn=1,'9999-12-31',date_sub('2022-02-22',1)) dt
from
(
select
id,
login_name,
nick_name,
real_name,
phone_num,
email,
user_level,
birthday,
gender,
create_time,
operate_time,
status,
start_date,
end_date,
row_number() over (partition by id order by start_date desc) rn
from
(
select
id,
login_name,
nick_name,
real_name,
phone_num,
email,
user_level,
birthday,
gender,
create_time,
operate_time,
status,
start_date,
end_date
from edu.dim_user_zip
where dt='9999-12-31'
union
select
id,
login_name,
nick_name,
real_name,
phone_num,
email,
user_level,
birthday,
gender,
create_time,
operate_time,
status,
'2020-02-22' start_date,
'9999-12-31' end_date
from
(
select
data.id,
data.login_name,
data.nick_name,
md5(data.real_name) real_name,
md5(if(data.phone_num regexp '^(13[0-9]|14[01456879]|15[0-35-9]|16[2567]|17[0-8]|18[0-9]|19[0-35-9])\\d{8}$',data.phone_num,null)) phone_num,
md5(if(data.email regexp '^[a-zA-Z0-9_-]+@[a-zA-Z0-9_-]+(\\.[a-zA-Z0-9_-]+)+$',data.email,null)) email,
data.user_level,
data.birthday,
data.gender,
data.create_time,
data.operate_time,
data.status,
row_number() over (partition by data.id order by ts desc) rn
from edu.ods_user_info_inc
where dt='2022-02-22'
)t1
where rn=1
)t2
)t3;
8.10 数据装载脚本¶
8.10.1 首日装载脚本¶
1）在hadoop102的/home/atguigu/bin目录下创建ods_to_dim_init.sh
2）编写如下内容
#!/bin/bash
if [ -n "$2" ] ;then
do_date=$2
else
echo "请传入日期参数"
exit
fi
APP=edu
dim_chapter_full="
insert overwrite table ${APP}.dim_chapter_full
partition (dt = '$do_date')
select id,
chapter_name,
course_id,
video_id,
publisher_id,
is_free,
create_time,
update_time
from ${APP}.ods_chapter_info_full
where deleted = '0'
and dt = '$do_date';"
dim_course_full="
with a as
(
select id, category_name
from ${APP}.ods_base_category_info_full
where deleted = '0'
and dt = '$do_date'
),
b as
(
select id, subject_name, category_id
from ${APP}.ods_base_subject_info_full
where deleted = '0'
and dt = '$do_date'
),
c as
(
select id,
course_name,
subject_id,
teacher,
publisher_id,
chapter_num,
origin_price,
reduce_amount,
actual_price,
create_time,
update_time
from ${APP}.ods_course_info_full
where deleted = '0'
and dt = '$do_date'
),
d as
(
select course_id,
collect_set(named_struct('chapter_id', id, 'chapter_name', chapter_name, 'video_id', video_id, 'is_free', is_free)) chapters
from ${APP}.ods_chapter_info_full
where deleted = '0'
and dt = '$do_date'
group by course_id
)
insert overwrite table ${APP}.dim_course_full
partition(dt = '$do_date')
select c.id,
course_name,
subject_id,
subject_name,
category_id,
category_name,
teacher,
publisher_id,
chapter_num,
origin_price,
reduce_amount,
actual_price,
create_time,
update_time,
chapters
from c
left join b
on c.subject_id = b.id
left join a
on b.category_id = a.id
left join d
on c.id = d.course_id;"
dim_video_full="
insert overwrite table ${APP}.dim_video_full partition (dt = '$do_date')
select vt.id,
video_name,
during_sec,
video_status,
video_size,
version_id,
chapter_id,
chapter_name,
is_free,
course_id,
publisher_id,
create_time,
update_time
from (
select id,
video_name,
during_sec,
video_status,
video_size,
version_id,
chapter_id,
course_id,
publisher_id,
create_time,
update_time
from ${APP}.ods_video_info_full
where dt = '$do_date' and deleted = '0'
) vt
join
(
select id,
chapter_name,
is_free
from ${APP}.ods_chapter_info_full
where dt = '$do_date'
) cht
on vt.chapter_id = cht.id;"
dim_paper_full="
insert overwrite table ${APP}.dim_paper_full partition (dt = '$do_date')
select t1.id,
paper_title,
course_id,
create_time,
update_time,
publisher_id,
questions
from ${APP}.ods_test_paper_full t1
left join
(
select paper_id,
collect_set(named_struct('question_id', question_id, 'score', score)) questions
from ${APP}.ods_test_paper_question_full
where deleted = '0' and dt = '$do_date'
group by paper_id
) t2
on t1.id = t2.paper_id
where t1.deleted = '0' and t1.dt = '$do_date';"
dim_source_full="
insert overwrite table ${APP}.dim_source_full partition (dt = '$do_date')
select id,
source_site
from ${APP}.ods_base_source_full obsf
where dt = '$do_date';"
dim_question_full="
insert overwrite table ${APP}.dim_question_full
partition (dt = '$do_date')
select id,
chapter_id,
course_id,
question_type,
create_time,
update_time,
publisher_id
from ${APP}.ods_test_question_info_full
where deleted = '0'
and dt = '$do_date';"
dim_province_full="
insert overwrite table ${APP}.dim_province_full partition (dt = '$do_date')
select id,
name,
region_id,
area_code,
iso_code,
iso_3166_2
from ${APP}.ods_base_province_full
where dt = '$do_date';"
dim_user_zip="
insert overwrite table ${APP}.dim_user_zip
partition (dt = '9999-12-31')
select data.id,
data.login_name,
data.nick_name,
md5(data.real_name),
md5(if(data.phone_num regexp '^(13[0-9]|14[01456879]|15[0-35-9]|16[2567]|17[0-8]|18[0-9]|19[0-35-9])\\d{8}$',data.phone_num,null)),
md5(if(data.email regexp '^[a-zA-Z0-9_-]+@[a-zA-Z0-9_-]+(\\.[a-zA-Z0-9_-]+)+$',data.email,null)),
data.user_level,
data.birthday,
data.gender,
data.create_time,
data.operate_time,
data.status,
'$do_date' start_date,
'9999-12-31' end_date
from ${APP}.ods_user_info_inc
where dt = '$do_date'
and type = 'bootstrap-insert';"
case $1 in
dim_chapter_full|dim_course_full|dim_video_full|dim_paper_full|dim_source_full|dim_question_full|dim_province_full|dim_user_zip)
eval "hive -e \"\$$1\""
;;
"all" )
hive -e "${dim_chapter_full}${dim_course_full}${dim_video_full}${dim_paper_full}${dim_source_full}${dim_question_full}${dim_province_full}${dim_user_zip}"
;;
esac
3）增加脚本执行权限
4）脚本用法
8.10.2 每日装载脚本¶
1）在hadoop102的/home/atguigu/bin目录下创建ods_to_dim.sh
2）编写如下内容
#!/bin/bash
if [ -n "$2" ] ;then
do_date=$2
else
do_date=`date -d "-1 day" +%F`
fi
APP=edu
dim_chapter_full="
insert overwrite table ${APP}.dim_chapter_full
partition (dt = '$do_date')
select id,
chapter_name,
course_id,
video_id,
publisher_id,
is_free,
create_time,
update_time
from ${APP}.ods_chapter_info_full
where deleted = '0'
and dt = '$do_date';"
dim_course_full="
with a as
(
select id, category_name
from ${APP}.ods_base_category_info_full
where deleted = '0'
and dt = '$do_date'
),
b as
(
select id, subject_name, category_id
from ${APP}.ods_base_subject_info_full
where deleted = '0'
and dt = '$do_date'
),
c as
(
select id,
course_name,
subject_id,
teacher,
publisher_id,
chapter_num,
origin_price,
reduce_amount,
actual_price,
create_time,
update_time
from ${APP}.ods_course_info_full
where deleted = '0'
and dt = '$do_date'
),
d as
(
select course_id,
collect_set(named_struct('chapter_id', id, 'chapter_name', chapter_name, 'video_id', video_id, 'is_free', is_free)) chapters
from ${APP}.ods_chapter_info_full
where deleted = '0'
and dt = '$do_date'
group by course_id
)
insert overwrite table ${APP}.dim_course_full
partition(dt = '$do_date')
select c.id,
course_name,
subject_id,
subject_name,
category_id,
category_name,
teacher,
publisher_id,
chapter_num,
origin_price,
reduce_amount,
actual_price,
create_time,
update_time,
chapters
from c
left join b
on c.subject_id = b.id
left join a
on b.category_id = a.id
left join d
on c.id = d.course_id;"
dim_video_full="
insert overwrite table ${APP}.dim_video_full partition (dt = '$do_date')
select vt.id,
video_name,
during_sec,
video_status,
video_size,
version_id,
chapter_id,
chapter_name,
is_free,
course_id,
publisher_id,
create_time,
update_time
from (
select id,
video_name,
during_sec,
video_status,
video_size,
version_id,
chapter_id,
course_id,
publisher_id,
create_time,
update_time
from ${APP}.ods_video_info_full
where dt = '$do_date' and deleted = '0'
) vt
join
(
select id,
chapter_name,
is_free
from ${APP}.ods_chapter_info_full
where dt = '$do_date'
) cht
on vt.chapter_id = cht.id;"
dim_paper_full="
insert overwrite table ${APP}.dim_paper_full partition (dt = '$do_date')
select t1.id,
paper_title,
course_id,
create_time,
update_time,
publisher_id,
questions
from ${APP}.ods_test_paper_full t1
left join
(
select paper_id,
collect_set(named_struct('question_id', question_id, 'score', score)) questions
from ${APP}.ods_test_paper_question_full
where deleted = '0' and dt = '$do_date'
group by paper_id
) t2
on t1.id = t2.paper_id
where t1.deleted = '0' and t1.dt = '$do_date';"
dim_source_full="
insert overwrite table ${APP}.dim_source_full partition (dt = '$do_date')
select id,
source_site
from ${APP}.ods_base_source_full obsf
where dt = '$do_date';"
dim_question_full="
insert overwrite table ${APP}.dim_question_full
partition (dt = '$do_date')
select id,
chapter_id,
course_id,
question_type,
create_time,
update_time,
publisher_id
from ${APP}.ods_test_question_info_full
where deleted = '0'
and dt = '$do_date';"
dim_province_full="
insert overwrite table ${APP}.dim_province_full partition (dt = '$do_date')
select id,
name,
region_id,
area_code,
iso_code,
iso_3166_2
from ${APP}.ods_base_province_full
where dt = '$do_date';"
dim_user_zip="
set hive.exec.dynamic.partition.mode=nonstrict;
insert overwrite table ${APP}.dim_user_zip
partition(dt)
select
id,
login_name,
nick_name,
real_name,
phone_num,
email,
user_level,
birthday,
gender,
create_time,
operate_time,
status,
start_date,
if(rn=1,'9999-12-31',date_sub('$do_date',1)) end_date,
if(rn=1,'9999-12-31',date_sub('$do_date',1)) dt
from
(
select
id,
login_name,
nick_name,
real_name,
phone_num,
email,
user_level,
birthday,
gender,
create_time,
operate_time,
status,
start_date,
end_date,
row_number() over (partition by id order by start_date desc) rn
from
(
select
id,
login_name,
nick_name,
real_name,
phone_num,
email,
user_level,
birthday,
gender,
create_time,
operate_time,
status,
start_date,
end_date
from ${APP}.dim_user_zip
where dt='9999-12-31'
union
select
id,
login_name,
nick_name,
real_name,
phone_num,
email,
user_level,
birthday,
gender,
create_time,
operate_time,
status,
'2020-02-22' start_date,
'9999-12-31' end_date
from
(
select
data.id,
data.login_name,
data.nick_name,
md5(data.real_name) real_name,
md5(if(data.phone_num regexp '^(13[0-9]|14[01456879]|15[0-35-9]|16[2567]|17[0-8]|18[0-9]|19[0-35-9])\\d{8}$',data.phone_num,null)) phone_num,
md5(if(data.email regexp '^[a-zA-Z0-9_-]+@[a-zA-Z0-9_-]+(\\.[a-zA-Z0-9_-]+)+$',data.email,null)) email,
data.user_level,
data.birthday,
data.gender,
data.create_time,
data.operate_time,
data.status,
row_number() over (partition by data.id order by ts desc) rn
from ${APP}.ods_user_info_inc
where dt='$do_date'
)t1
where rn=1
)t2
)t3;"
case $1 in
dim_chapter_full|dim_course_full|dim_video_full|dim_paper_full|dim_source_full|dim_question_full|dim_province_full|dim_user_zip)
eval "hive -e \"\$$1\""
;;
"all" )
hive -e "${dim_chapter_full}${dim_course_full}${dim_video_full}${dim_paper_full}${dim_source_full}${dim_question_full}${dim_province_full}${dim_user_zip}"
;;
esac
3）增加脚本执行权限
4）脚本用法