一些hql

xiaoxiao______

已于 2022-11-10 16:15:49 修改

阅读量92

点赞数

分类专栏： worker 文章标签： hive

于 2021-03-11 23:10:38 首次发布

本文链接：https://blog.csdn.net/xiaoxiao______/article/details/114682534

版权

worker 专栏收录该内容

2 篇文章 0 订阅

订阅专栏

ODS层加载数据脚本

#!/bin/bash

APP=gmall
hive=/opt/module/hive/bin/hive

# 如果是输入的日期按照取输入日期；如果没输入日期取当前时间的前一天
if [ -n "$2" ] ;then
    do_date=$2
else 
    do_date=`date -d "-1 day" +%F`
fi

sql1=" 
load data inpath '/origin_data/$APP/db/order_info/$do_date' OVERWRITE into table ${APP}.ods_order_info partition(dt='$do_date');

load data inpath '/origin_data/$APP/db/order_detail/$do_date' OVERWRITE into table ${APP}.ods_order_detail partition(dt='$do_date');

load data inpath '/origin_data/$APP/db/sku_info/$do_date' OVERWRITE into table ${APP}.ods_sku_info partition(dt='$do_date');

load data inpath '/origin_data/$APP/db/user_info/$do_date' OVERWRITE into table ${APP}.ods_user_info partition(dt='$do_date');

load data inpath '/origin_data/$APP/db/payment_info/$do_date' OVERWRITE into table ${APP}.ods_payment_info partition(dt='$do_date');

load data inpath '/origin_data/$APP/db/base_category1/$do_date' OVERWRITE into table ${APP}.ods_base_category1 partition(dt='$do_date');

load data inpath '/origin_data/$APP/db/base_category2/$do_date' OVERWRITE into table ${APP}.ods_base_category2 partition(dt='$do_date');

load data inpath '/origin_data/$APP/db/base_category3/$do_date' OVERWRITE into table ${APP}.ods_base_category3 partition(dt='$do_date'); 

load data inpath '/origin_data/$APP/db/base_trademark/$do_date' OVERWRITE into table ${APP}.ods_base_trademark partition(dt='$do_date'); 

load data inpath '/origin_data/$APP/db/activity_info/$do_date' OVERWRITE into table ${APP}.ods_activity_info partition(dt='$do_date'); 

load data inpath '/origin_data/$APP/db/activity_order/$do_date' OVERWRITE into table ${APP}.ods_activity_order partition(dt='$do_date'); 

load data inpath '/origin_data/$APP/db/cart_info/$do_date' OVERWRITE into table ${APP}.ods_cart_info partition(dt='$do_date'); 

load data inpath '/origin_data/$APP/db/comment_info/$do_date' OVERWRITE into table ${APP}.ods_comment_info partition(dt='$do_date'); 

load data inpath '/origin_data/$APP/db/coupon_info/$do_date' OVERWRITE into table ${APP}.ods_coupon_info partition(dt='$do_date'); 

load data inpath '/origin_data/$APP/db/coupon_use/$do_date' OVERWRITE into table ${APP}.ods_coupon_use partition(dt='$do_date'); 

load data inpath '/origin_data/$APP/db/favor_info/$do_date' OVERWRITE into table ${APP}.ods_favor_info partition(dt='$do_date'); 

load data inpath '/origin_data/$APP/db/order_refund_info/$do_date' OVERWRITE into table ${APP}.ods_order_refund_info partition(dt='$do_date'); 

load data inpath '/origin_data/$APP/db/order_status_log/$do_date' OVERWRITE into table ${APP}.ods_order_status_log partition(dt='$do_date'); 

load data inpath '/origin_data/$APP/db/spu_info/$do_date' OVERWRITE into table ${APP}.ods_spu_info partition(dt='$do_date'); 

load data inpath '/origin_data/$APP/db/activity_rule/$do_date' OVERWRITE into table ${APP}.ods_activity_rule partition(dt='$do_date'); 

load data inpath '/origin_data/$APP/db/base_dic/$do_date' OVERWRITE into table ${APP}.ods_base_dic partition(dt='$do_date'); 
"

sql2=" 
load data inpath '/origin_data/$APP/db/base_province/$do_date' OVERWRITE into table ${APP}.ods_base_province;

load data inpath '/origin_data/$APP/db/base_region/$do_date' OVERWRITE into table ${APP}.ods_base_region;
"
case $1 in
"first"){
    $hive -e "$sql1"
    $hive -e "$sql2"
};;
"all"){
    $hive -e "$sql1"
};;
esac

DWD层加载数据脚本

公共字段解析，加载

#!/bin/bash

# 定义变量方便修改
APP=gmall
hive=/opt/module/hive/bin/hive

# 如果是输入的日期按照取输入日期；如果没输入日期取当前时间的前一天
if [ -n "$1" ] ;then
	do_date=$1
else 
	do_date=`date -d "-1 day" +%F`  
fi 

sql="
set hive.exec.dynamic.partition.mode=nonstrict;

insert overwrite table "$APP".dwd_start_log
PARTITION (dt='$do_date')
select 
    get_json_object(line,'$.mid') mid_id,
    get_json_object(line,'$.uid') user_id,
    get_json_object(line,'$.vc') version_code,
    get_json_object(line,'$.vn') version_name,
    get_json_object(line,'$.l') lang,
    get_json_object(line,'$.sr') source,
    get_json_object(line,'$.os') os,
    get_json_object(line,'$.ar') area,
    get_json_object(line,'$.md') model,
    get_json_object(line,'$.ba') brand,
    get_json_object(line,'$.sv') sdk_version,
    get_json_object(line,'$.g') gmail,
    get_json_object(line,'$.hw') height_width,
    get_json_object(line,'$.t') app_time,
    get_json_object(line,'$.nw') network,
    get_json_object(line,'$.ln') lng,
    get_json_object(line,'$.la') lat,
    get_json_object(line,'$.entry') entry,
    get_json_object(line,'$.open_ad_type') open_ad_type,
    get_json_object(line,'$.action') action,
    get_json_object(line,'$.loading_time') loading_time,
    get_json_object(line,'$.detail') detail,
    get_json_object(line,'$.extend1') extend1
from "$APP".ods_start_log 
where dt='$do_date';
"

$hive -e "$sql"

事件字段解析，加载

#!/bin/bash

# 定义变量方便修改
APP=gmall
hive=/opt/module/hive/bin/hive

# 如果是输入的日期按照取输入日期；如果没输入日期取当前时间的前一天
if [ -n "$1" ] ;then
	do_date=$1
else 
	do_date=`date -d "-1 day" +%F`  
fi 

sql="
use gmall;
insert overwrite table "$APP".dwd_base_event_log partition(dt='$do_date')
select
    base_analizer(line,'mid') as mid_id,
    base_analizer(line,'uid') as user_id,
    base_analizer(line,'vc') as version_code,
    base_analizer(line,'vn') as version_name,
    base_analizer(line,'l') as lang,
    base_analizer(line,'sr') as source,
    base_analizer(line,'os') as os,
    base_analizer(line,'ar') as area,
    base_analizer(line,'md') as model,
    base_analizer(line,'ba') as brand,
    base_analizer(line,'sv') as sdk_version,
    base_analizer(line,'g') as gmail,
    base_analizer(line,'hw') as height_width,
    base_analizer(line,'t') as app_time,
    base_analizer(line,'nw') as network,
    base_analizer(line,'ln') as lng,
    base_analizer(line,'la') as lat,
    event_name,
    event_json,
    base_analizer(line,'st') as server_time
from "$APP".ods_event_log lateral view flat_analizer(base_analizer(line,'et')) tem_flat as event_name,event_json
where dt='$do_date'  and base_analizer(line,'et')<>'';
"

$hive -e "$sql"
注意：使用自定义函数时，需要在执行脚本前，增加上要使用的库。例如：use gmall;

自定义UDF，UDTF

1）创建一个maven工程：hivefunction
2）创建包名：com.atguigu.udf
3）在pom.xml文件中添加如下内容

<properties>
    <hive.version>2.3.0</hive.version>
</properties>

<dependencies>
    <!--添加hive依赖-->
    <dependency>
        <groupId>org.apache.hive</groupId>
        <artifactId>hive-exec</artifactId>
        <version>${hive.version}</version>
    </dependency>
</dependencies>
<repositories>
    <repository>
        <id>spring-plugin</id>
        <url>https://repo.spring.io/plugins-release/</url>
    </repository>
</repositories>

<build>
    <plugins>
        <plugin>
            <artifactId>maven-compiler-plugin</artifactId>
            <version>2.3.2</version>
            <configuration>
                <source>1.8</source>
                <target>1.8</target>
            </configuration>
        </plugin>
        <plugin>
            <artifactId>maven-assembly-plugin</artifactId>
            <configuration>
                <descriptorRefs>
                    <descriptorRef>jar-with-dependencies</descriptorRef>
                </descriptorRefs>
            </configuration>
            <executions>
                <execution>
                    <id>make-assembly</id>
                    <phase>package</phase>
                    <goals>
                        <goal>single</goal>
                    </goals>
                </execution>
            </executions>
        </plugin>
    </plugins>
</build>

4）UDF用于解析公共字段

package com.atguigu.udf;

import org.apache.commons.lang.StringUtils;
import org.apache.hadoop.hive.ql.exec.UDF;
import org.json.JSONException;
import org.json.JSONObject;

public class BaseFieldUDF extends UDF {

    public String evaluate(String line, String key) throws JSONException {

        String[] log = line.split("\\|");

        if (log.length != 2 || StringUtils.isBlank(log[1])) {
            return "";
        }

        JSONObject baseJson = new JSONObject(log[1].trim());

        String result = "";

        // 获取服务器时间
        if ("st".equals(key)) {
            result = log[0].trim();
        } else if ("et".equals(key)) {
            // 获取事件数组
            if (baseJson.has("et")) {
                result = baseJson.getString("et");
            }
        } else {
            JSONObject cm = baseJson.getJSONObject("cm");

            // 获取key对应公共字段的value
            if (cm.has(key)) {
                result = cm.getString(key);
            }
        }

        return result;
    }

    public static void main (String[] args) throws JSONException {

        String line = "1583776223469|{\"cm\":{\"ln\":\"-48.5\",\"sv\":\"V2.5.7\",\"os\":\"8.0.9\",\"g\":\"6F76AVD5@gmail.com\",\"mid\":\"0\",\"nw\":\"4G\",\"l\":\"pt\",\"vc\":\"3\",\"hw\":\"750*1134\",\"ar\":\"MX\",\"uid\":\"0\",\"t\":\"1583707297317\",\"la\":\"-52.9\",\"md\":\"sumsung-18\",\"vn\":\"1.2.4\",\"ba\":\"Sumsung\",\"sr\":\"V\"},\"ap\":\"app\",\"et\":[{\"ett\":\"1583705574227\",\"en\":\"display\",\"kv\":{\"goodsid\":\"0\",\"action\":\"1\",\"extend1\":\"1\",\"place\":\"0\",\"category\":\"63\"}},{\"ett\":\"1583760986259\",\"en\":\"loading\",\"kv\":{\"extend2\":\"\",\"loading_time\":\"4\",\"action\":\"3\",\"extend1\":\"\",\"type\":\"3\",\"type1\":\"\",\"loading_way\":\"1\"}},{\"ett\":\"1583746639124\",\"en\":\"ad\",\"kv\":{\"activityId\":\"1\",\"displayMills\":\"111839\",\"entry\":\"1\",\"action\":\"5\",\"contentType\":\"0\"}},{\"ett\":\"1583758016208\",\"en\":\"notification\",\"kv\":{\"ap_time\":\"1583694079866\",\"action\":\"1\",\"type\":\"3\",\"content\":\"\"}},{\"ett\":\"1583699890760\",\"en\":\"favorites\",\"kv\":{\"course_id\":4,\"id\":0,\"add_time\":\"1583730648134\",\"userid\":7}}]}";

        String mid = new BaseFieldUDF().evaluate(line, "mid");

        System.out.println(mid);
    }
}
注意：使用main函数主要用于模拟数据测试。

自定义UDTF函数来解析事件字段

1）创建包名
2）在包下创建类名：EventJsonUDTF
3）用于展开业务字段


import org.apache.commons.lang.StringUtils;
import org.apache.hadoop.hive.ql.exec.UDFArgumentException;
import org.apache.hadoop.hive.ql.metadata.HiveException;
import org.apache.hadoop.hive.ql.udf.generic.GenericUDTF;
import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector;
import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorFactory;
import org.apache.hadoop.hive.serde2.objectinspector.StructObjectInspector;
import org.apache.hadoop.hive.serde2.objectinspector.primitive.PrimitiveObjectInspectorFactory;
import org.json.JSONArray;
import org.json.JSONException;

import java.util.ArrayList;

public class EventJsonUDTF extends GenericUDTF {

    //该方法中，我们将指定输出参数的名称和参数类型：
    public StructObjectInspector initialize(StructObjectInspector argOIs) throws UDFArgumentException {

        ArrayList<String> fieldNames = new ArrayList<String>();
        ArrayList<ObjectInspector> fieldOIs = new ArrayList<ObjectInspector>();

        fieldNames.add("event_name");
        fieldOIs.add(PrimitiveObjectInspectorFactory.javaStringObjectInspector);
        fieldNames.add("event_json");
        fieldOIs.add(PrimitiveObjectInspectorFactory.javaStringObjectInspector);

        return ObjectInspectorFactory.getStandardStructObjectInspector(fieldNames, fieldOIs);
    }

    //输入1条记录，输出若干条结果
    @Override
    public void process(Object[] objects) throws HiveException {

        // 获取传入的et
        String input = objects[0].toString();

        // 如果传进来的数据为空，直接返回过滤掉该数据
        if (StringUtils.isBlank(input)) {
            return;
        } else {

            try {
                // 获取一共有几个事件（ad/facoriters）
                JSONArray ja = new JSONArray(input);

                if (ja == null)
                    return;

                // 循环遍历每一个事件
                for (int i = 0; i < ja.length(); i++) {
                    String[] result = new String[2];

                    try {
                        // 取出每个的事件名称（ad/facoriters）
                        result[0] = ja.getJSONObject(i).getString("en");

                        // 取出每一个事件整体
                        result[1] = ja.getString(i);
                    } catch (JSONException e) {
                        continue;
                    }

                    // 将结果返回
                    forward(result);
                }
            } catch (JSONException e) {
                e.printStackTrace();
            }
        }
    }

    //当没有记录处理的时候该方法会被调用，用来清理代码或者产生额外的输出
    @Override
    public void close() throws HiveException {

    }
}

2）打包

3）将hivefunction-1.0-SNAPSHOT.jar上传到HDFS的/user/hive/jars路径下
hadoop fs -mkdir -p /user/hive/jars
hadoop fs -put hivefunction-1.0-SNAPSHOT.jar /user/hive/jars
4）创建永久函数与开发好的java class关联
hive (gmall)> create function base_analizer as 'com.xxx.udf.BaseFieldUDF' using jar 'hdfs://hadoop102:9000/user/hive/jars/hivefunction-1.0-SNAPSHOT.jar';

create function flat_analizer as 'com.xxx.udtf.EventJsonUDTF' using jar 'hdfs://hadoop102:9000/user/hive/jars/hivefunction-1.0-SNAPSHOT.jar';
5）注意：如果修改了自定义函数重新生成jar包怎么处理？只需要替换HDFS路径上的旧jar包，然后重启Hive客户端即可。

DWD层加载事件表的脚本

#!/bin/bash

# 定义变量方便修改
APP=gmall
hive=/opt/module/hive/bin/hive

# 如果是输入的日期按照取输入日期；如果没输入日期取当前时间的前一天
if [ -n "$1" ] ;then
	do_date=$1
else 
	do_date=`date -d "-1 day" +%F`  
fi 

sql="
insert overwrite table "$APP".dwd_display_log
PARTITION (dt='$do_date')
select 
	mid_id,
	user_id,
	version_code,
	version_name,
	lang,
	source,
	os,
	area,
	model,
	brand,
	sdk_version,
	gmail,
	height_width,
	app_time,
	network,
	lng,
	lat,
	get_json_object(event_json,'$.kv.action') action,
	get_json_object(event_json,'$.kv.goodsid') goodsid,
	get_json_object(event_json,'$.kv.place') place,
	get_json_object(event_json,'$.kv.extend1') extend1,
	get_json_object(event_json,'$.kv.category') category,
	server_time
from "$APP".dwd_base_event_log 
where dt='$do_date' and event_name='display';


insert overwrite table "$APP".dwd_newsdetail_log
PARTITION (dt='$do_date')
select 
	mid_id,
	user_id,
	version_code,
	version_name,
	lang,
	source,
	os,
	area,
	model,
	brand,
	sdk_version,
	gmail,
	height_width,
	app_time,
	network,
	lng,
	lat,
	get_json_object(event_json,'$.kv.entry') entry,
	get_json_object(event_json,'$.kv.action') action,
	get_json_object(event_json,'$.kv.goodsid') goodsid,
	get_json_object(event_json,'$.kv.showtype') showtype,
	get_json_object(event_json,'$.kv.news_staytime') news_staytime,
	get_json_object(event_json,'$.kv.loading_time') loading_time,
	get_json_object(event_json,'$.kv.type1') type1,
	get_json_object(event_json,'$.kv.category') category,
	server_time
from "$APP".dwd_base_event_log 
where dt='$do_date' and event_name='newsdetail';


insert overwrite table "$APP".dwd_loading_log
PARTITION (dt='$do_date')
select 
	mid_id,
	user_id,
	version_code,
	version_name,
	lang,
	source,
	os,
	area,
	model,
	brand,
	sdk_version,
	gmail,
	height_width,
	app_time,
	network,
	lng,
	lat,
	get_json_object(event_json,'$.kv.action') action,
	get_json_object(event_json,'$.kv.loading_time') loading_time,
	get_json_object(event_json,'$.kv.loading_way') loading_way,
	get_json_object(event_json,'$.kv.extend1') extend1,
	get_json_object(event_json,'$.kv.extend2') extend2,
	get_json_object(event_json,'$.kv.type') type,
	get_json_object(event_json,'$.kv.type1') type1,
	server_time
from "$APP".dwd_base_event_log 
where dt='$do_date' and event_name='loading';


insert overwrite table "$APP".dwd_ad_log
PARTITION (dt='$do_date')
select 
	mid_id,
	user_id,
	version_code,
	version_name,
	lang,
	source,
	os,
	area,
	model,
	brand,
	sdk_version,
	gmail,
	height_width,
	app_time,
	network,
	lng,
	lat,
    get_json_object(event_json,'$.kv.entry') entry,
    get_json_object(event_json,'$.kv.action') action,
    get_json_object(event_json,'$.kv.contentType') contentType,
    get_json_object(event_json,'$.kv.displayMills') displayMills,
    get_json_object(event_json,'$.kv.itemId') itemId,
    get_json_object(event_json,'$.kv.activityId') activityId,
	server_time
from "$APP".dwd_base_event_log 
where dt='$do_date' and event_name='ad';


insert overwrite table "$APP".dwd_notification_log
PARTITION (dt='$do_date')
select 
	mid_id,
	user_id,
	version_code,
	version_name,
	lang,
	source,
	os,
	area,
	model,
	brand,
	sdk_version,
	gmail,
	height_width,
	app_time,
	network,
	lng,
	lat,
	get_json_object(event_json,'$.kv.action') action,
	get_json_object(event_json,'$.kv.noti_type') noti_type,
	get_json_object(event_json,'$.kv.ap_time') ap_time,
	get_json_object(event_json,'$.kv.content') content,
	server_time
from "$APP".dwd_base_event_log 
where dt='$do_date' and event_name='notification';


insert overwrite table "$APP".dwd_active_background_log
PARTITION (dt='$do_date')
select 
	mid_id,
	user_id,
	version_code,
	version_name,
	lang,
	source,
	os,
	area,
	model,
	brand,
	sdk_version,
	gmail,
	height_width,
	app_time,
	network,
	lng,
	lat,
	get_json_object(event_json,'$.kv.active_source') active_source,
	server_time
from "$APP".dwd_base_event_log 
where dt='$do_date' and event_name='active_background';


insert overwrite table "$APP".dwd_comment_log
PARTITION (dt='$do_date')
select 
	mid_id,
	user_id,
	version_code,
	version_name,
	lang,
	source,
	os,
	area,
	model,
	brand,
	sdk_version,
	gmail,
	height_width,
	app_time,
	network,
	lng,
	lat,
	get_json_object(event_json,'$.kv.comment_id') comment_id,
	get_json_object(event_json,'$.kv.userid') userid,
	get_json_object(event_json,'$.kv.p_comment_id') p_comment_id,
	get_json_object(event_json,'$.kv.content') content,
	get_json_object(event_json,'$.kv.addtime') addtime,
	get_json_object(event_json,'$.kv.other_id') other_id,
	get_json_object(event_json,'$.kv.praise_count') praise_count,
	get_json_object(event_json,'$.kv.reply_count') reply_count,
	server_time
from "$APP".dwd_base_event_log 
where dt='$do_date' and event_name='comment';


insert overwrite table "$APP".dwd_favorites_log
PARTITION (dt='$do_date')
select 
	mid_id,
	user_id,
	version_code,
	version_name,
	lang,
	source,
	os,
	area,
	model,
	brand,
	sdk_version,
	gmail,
	height_width,
	app_time,
	network,
	lng,
	lat,
	get_json_object(event_json,'$.kv.id') id,
	get_json_object(event_json,'$.kv.course_id') course_id,
	get_json_object(event_json,'$.kv.userid') userid,
	get_json_object(event_json,'$.kv.add_time') add_time,
	server_time
from "$APP".dwd_base_event_log 
where dt='$do_date' and event_name='favorites';


insert overwrite table "$APP".dwd_praise_log
PARTITION (dt='$do_date')
select 
	mid_id,
	user_id,
	version_code,
	version_name,
	lang,
	source,
	os,
	area,
	model,
	brand,
	sdk_version,
	gmail,
	height_width,
	app_time,
	network,
	lng,
	lat,
	get_json_object(event_json,'$.kv.id') id,
	get_json_object(event_json,'$.kv.userid') userid,
	get_json_object(event_json,'$.kv.target_id') target_id,
	get_json_object(event_json,'$.kv.type') type,
	get_json_object(event_json,'$.kv.add_time') add_time,
	server_time
from "$APP".dwd_base_event_log 
where dt='$do_date' and event_name='praise';


insert overwrite table "$APP".dwd_error_log
PARTITION (dt='$do_date')
select 
	mid_id,
	user_id,
	version_code,
	version_name,
	lang,
	source,
	os,
	area,
	model,
	brand,
	sdk_version,
	gmail,
	height_width,
	app_time,
	network,
	lng,
	lat,
	get_json_object(event_json,'$.kv.errorBrief') errorBrief,
	get_json_object(event_json,'$.kv.errorDetail') errorDetail,
	server_time
from "$APP".dwd_base_event_log 
where dt='$do_date' and event_name='error';
"

$hive -e "$sql"

DWD层业务数据加载脚本

#!/bin/bash

APP=gmall
hive=/opt/module/hive/bin/hive

# 如果是输入的日期按照取输入日期；如果没输入日期取当前时间的前一天
if [ -n "$2" ] ;then
    do_date=$2
else 
    do_date=`date -d "-1 day" +%F`
fi

sql1="
set hive.exec.dynamic.partition.mode=nonstrict;

insert overwrite table ${APP}.dwd_dim_sku_info partition(dt='$do_date')
select  
    sku.id,
    sku.spu_id,
    sku.price,
    sku.sku_name,
    sku.sku_desc,
    sku.weight,
    sku.tm_id,
    ob.tm_name,
    sku.category3_id,
    c2.id category2_id,
    c1.id category1_id,
    c3.name category3_name,
    c2.name category2_name,
    c1.name category1_name,
    spu.spu_name,
    sku.create_time
from
(
    select * from ${APP}.ods_sku_info where dt='$do_date'
)sku
join
(
    select * from ${APP}.ods_base_trademark where dt='$do_date'
)ob on sku.tm_id=ob.tm_id
join
(
    select * from ${APP}.ods_spu_info where dt='$do_date'
)spu on spu.id = sku.spu_id
join 
(
    select * from ${APP}.ods_base_category3 where dt='$do_date'
)c3 on sku.category3_id=c3.id
join 
(
    select * from ${APP}.ods_base_category2 where dt='$do_date'
)c2 on c3.category2_id=c2.id 
join 
(
    select * from ${APP}.ods_base_category1 where dt='$do_date'
)c1 on c2.category1_id=c1.id;

insert overwrite table ${APP}.dwd_dim_coupon_info partition(dt='$do_date')
select
    id,
    coupon_name,
    coupon_type,
    condition_amount,
    condition_num,
    activity_id,
    benefit_amount,
    benefit_discount,
    create_time,
    range_type,
    spu_id,
    tm_id,
    category3_id,
    limit_num,
    operate_time,
    expire_time
from ${APP}.ods_coupon_info
where dt='$do_date';

insert overwrite table ${APP}.dwd_dim_activity_info partition(dt='$do_date')
select
    info.id,
    info.activity_name,
    info.activity_type,
    rule.condition_amount,
    rule.condition_num,
    rule.benefit_amount,
    rule.benefit_discount,
    rule.benefit_level,
    info.start_time,
    info.end_time,
    info.create_time
from 
(
    select * from ${APP}.ods_activity_info where dt='$do_date'
)info
left join
(
    select * from ${APP}.ods_activity_rule where dt='$do_date'
)rule on info.id = rule.activity_id;

insert overwrite table ${APP}.dwd_fact_order_detail partition(dt='$do_date')
select
    od.id,
    od.order_id,
    od.user_id,
    od.sku_id,
    od.sku_name,
    od.order_price,
    od.sku_num,
    od.create_time,
    oi.province_id,
    od.order_price*od.sku_num   
from 
(
    select * from ${APP}.ods_order_detail where dt='$do_date'
) od
join 
(
    select * from ${APP}.ods_order_info where dt='$do_date'
) oi
on od.order_id=oi.id;

insert overwrite table ${APP}.dwd_fact_payment_info partition(dt='$do_date')
select
    pi.id,
    pi.out_trade_no,
    pi.order_id,
    pi.user_id,
    pi.alipay_trade_no,
    pi.total_amount,
    pi.subject,
    pi.payment_type,
    pi.payment_time,          
    oi.province_id
from
(
    select * from ${APP}.ods_payment_info where dt='$do_date'
)pi
join
(
    select id, province_id from ${APP}.ods_order_info where dt='$do_date'
)oi
on pi.order_id = oi.id;

insert overwrite table ${APP}.dwd_fact_order_refund_info partition(dt='$do_date')
select
    id,
    user_id,
    order_id,
    sku_id,
    refund_type,
    refund_num,
    refund_amount,
    refund_reason_type,
    create_time
from ${APP}.ods_order_refund_info
where dt='$do_date';

insert overwrite table ${APP}.dwd_fact_comment_info partition(dt='$do_date')
select
    id,
    user_id,
    sku_id,
    spu_id,
    order_id,
    appraise,
    create_time
from ${APP}.ods_comment_info
where dt='$do_date';

insert overwrite table ${APP}.dwd_fact_cart_info partition(dt='$do_date')
select
    id,
    user_id,
    sku_id,
    cart_price,
    sku_num,
    sku_name,
    create_time,
    operate_time,
    is_ordered,
    order_time
from ${APP}.ods_cart_info
where dt='$do_date';

insert overwrite table ${APP}.dwd_fact_favor_info partition(dt='$do_date')
select
    id,
    user_id,
    sku_id,
    spu_id,
    is_cancel,
    create_time,
    cancel_time
from ${APP}.ods_favor_info
where dt='$do_date';

insert overwrite table ${APP}.dwd_fact_coupon_use partition(dt)
select
    if(new.id is null,old.id,new.id),
    if(new.coupon_id is null,old.coupon_id,new.coupon_id),
    if(new.user_id is null,old.user_id,new.user_id),
    if(new.order_id is null,old.order_id,new.order_id),
    if(new.coupon_status is null,old.coupon_status,new.coupon_status),
    if(new.get_time is null,old.get_time,new.get_time),
    if(new.using_time is null,old.using_time,new.using_time),
    if(new.used_time is null,old.used_time,new.used_time),
    date_format(if(new.get_time is null,old.get_time,new.get_time),'yyyy-MM-dd')
from
(
    select
        id,
        coupon_id,
        user_id,
        order_id,
        coupon_status,
        get_time,
        using_time,
        used_time
    from ${APP}.dwd_fact_coupon_use
    where dt in
    (
        select
            date_format(get_time,'yyyy-MM-dd')
        from ${APP}.ods_coupon_use
        where dt='$do_date'
    )
)old
full outer join
(
    select
        id,
        coupon_id,
        user_id,
        order_id,
        coupon_status,
        get_time,
        using_time,
        used_time
    from ${APP}.ods_coupon_use
    where dt='$do_date'
)new
on old.id=new.id;


insert overwrite table ${APP}.dwd_fact_order_info partition(dt)
select
    if(new.id is null,old.id,new.id),
    if(new.order_status is null,old.order_status,new.order_status),
    if(new.user_id is null,old.user_id,new.user_id),
    if(new.out_trade_no is null,old.out_trade_no,new.out_trade_no),
    if(new.tms['1001'] is null,old.create_time,new.tms['1001']),--1001对应未支付状态
    if(new.tms['1002'] is null,old.payment_time,new.tms['1002']),
    if(new.tms['1003'] is null,old.cancel_time,new.tms['1003']),
    if(new.tms['1004'] is null,old.finish_time,new.tms['1004']),
    if(new.tms['1005'] is null,old.refund_time,new.tms['1005']),
    if(new.tms['1006'] is null,old.refund_finish_time,new.tms['1006']),
    if(new.province_id is null,old.province_id,new.province_id),
    if(new.activity_id is null,old.activity_id,new.activity_id),
    if(new.original_total_amount is null,old.original_total_amount,new.original_total_amount),
    if(new.benefit_reduce_amount is null,old.benefit_reduce_amount,new.benefit_reduce_amount),
    if(new.feight_fee is null,old.feight_fee,new.feight_fee),
    if(new.final_total_amount is null,old.final_total_amount,new.final_total_amount),
    date_format(if(new.tms['1001'] is null,old.create_time,new.tms['1001']),'yyyy-MM-dd')
from
(
    select
        id,
        order_status,
        user_id,
        out_trade_no,
        create_time,
        payment_time,
        cancel_time,
        finish_time,
        refund_time,
        refund_finish_time,
        province_id,
        activity_id,
        original_total_amount,
        benefit_reduce_amount,
        feight_fee,
        final_total_amount
    from ${APP}.dwd_fact_order_info
    where dt
    in
    (
        select
          date_format(create_time,'yyyy-MM-dd')
        from ${APP}.ods_order_info
        where dt='$do_date'
    )
)old
full outer join
(
    select
        info.id,
        info.order_status,
        info.user_id,
        info.out_trade_no,
        info.province_id,
        act.activity_id,
        log.tms,
        info.original_total_amount,
        info.benefit_reduce_amount,
        info.feight_fee,
        info.final_total_amount
    from
    (
        select
            order_id,
            str_to_map(concat_ws(',',collect_set(concat(order_status,'=',operate_time))),',','=') tms
        from ${APP}.ods_order_status_log
        where dt='$do_date'
        group by order_id
    )log
    join
    (
        select * from ${APP}.ods_order_info where dt='$do_date'
    )info
    on log.order_id=info.id
    left join
    (
        select * from ${APP}.ods_activity_order where dt='$do_date'
    )act
    on log.order_id=act.order_id
)new
on old.id=new.id;


insert overwrite table ${APP}.dwd_dim_user_info_his_tmp
select * from 
(
    select 
        id,
        name,
        birthday,
        gender,
        email,
        user_level,
        create_time,
        operate_time,
        '$do_date' start_date,
        '9999-99-99' end_date
    from ${APP}.ods_user_info where dt='$do_date'

    union all 
    select 
        uh.id,
        uh.name,
        uh.birthday,
        uh.gender,
        uh.email,
        uh.user_level,
        uh.create_time,
        uh.operate_time,
        uh.start_date,
        if(ui.id is not null  and uh.end_date='9999-99-99', date_add(ui.dt,-1), uh.end_date) end_date
    from ${APP}.dwd_dim_user_info_his uh left join 
    (
        select
            *
        from ${APP}.ods_user_info
        where dt='$do_date'
    ) ui on uh.id=ui.id
)his 
order by his.id, start_date;

insert overwrite table ${APP}.dwd_dim_user_info_his select * from ${APP}.dwd_dim_user_info_his_tmp;
"

sql2="
insert overwrite table ${APP}.dwd_dim_base_province
select 
    bp.id,
    bp.name,
    bp.area_code,
    bp.iso_code,
    bp.region_id,
    br.region_name
from ${APP}.ods_base_province bp
join ${APP}.ods_base_region br
on bp.region_id=br.id;
"

case $1 in
"first"){
    $hive -e "$sql1"
    $hive -e "$sql2"
};;
"all"){
    $hive -e "$sql1"  
};;
esac

DWS层加载数据脚本

#!/bin/bash

APP=gmall
hive=/opt/module/hive/bin/hive

# 如果是输入的日期按照取输入日期；如果没输入日期取当前时间的前一天
if [ -n "$1" ] ;then
    do_date=$1
else
    do_date=`date -d "-1 day" +%F`
fi

sql="
insert overwrite table ${APP}.dws_uv_detail_daycount partition(dt='$do_date')
select  
    mid_id,
    concat_ws('|', collect_set(user_id)) user_id,
    concat_ws('|', collect_set(version_code)) version_code,
    concat_ws('|', collect_set(version_name)) version_name,
    concat_ws('|', collect_set(lang))lang,
    concat_ws('|', collect_set(source)) source,
    concat_ws('|', collect_set(os)) os,
    concat_ws('|', collect_set(area)) area, 
    concat_ws('|', collect_set(model)) model,
    concat_ws('|', collect_set(brand)) brand,
    concat_ws('|', collect_set(sdk_version)) sdk_version,
    concat_ws('|', collect_set(gmail)) gmail,
    concat_ws('|', collect_set(height_width)) height_width,
    concat_ws('|', collect_set(app_time)) app_time,
    concat_ws('|', collect_set(network)) network,
    concat_ws('|', collect_set(lng)) lng,
    concat_ws('|', collect_set(lat)) lat,
    count(*) login_count
from ${APP}.dwd_start_log
where dt='$do_date'
group by mid_id;


with
tmp_login as
(
    select
        user_id,
        count(*) login_count
    from ${APP}.dwd_start_log
    where dt='$do_date'
    and user_id is not null
    group by user_id
),
tmp_cart as
(
    select
        user_id,
        count(*) cart_count,
        sum(cart_price*sku_num) cart_amount
    from ${APP}.dwd_fact_cart_info
    where dt='$do_date'
    and user_id is not null
    and date_format(create_time,'yyyy-MM-dd')='$do_date'
    group by user_id
),
tmp_order as
(
    select
        user_id,
        count(*) order_count,
        sum(final_total_amount) order_amount
    from ${APP}.dwd_fact_order_info
    where dt='$do_date'
    group by user_id
) ,
tmp_payment as
(
    select
        user_id,
        count(*) payment_count,
        sum(payment_amount) payment_amount
    from ${APP}.dwd_fact_payment_info
    where dt='$do_date'
    group by user_id
)

insert overwrite table ${APP}.dws_user_action_daycount partition(dt='$do_date')
select
    user_actions.user_id,
    sum(user_actions.login_count),
    sum(user_actions.cart_count),
    sum(user_actions.cart_amount),
    sum(user_actions.order_count),
    sum(user_actions.order_amount),
    sum(user_actions.payment_count),
    sum(user_actions.payment_amount)
from 
(
    select
        user_id,
        login_count,
        0 cart_count,
        0 cart_amount,
        0 order_count,
        0 order_amount,
        0 payment_count,
        0 payment_amount
    from 
    tmp_login
    union all
    select
        user_id,
        0 login_count,
        cart_count,
        cart_amount,
        0 order_count,
        0 order_amount,
        0 payment_count,
        0 payment_amount
    from 
    tmp_cart
    union all
    select
        user_id,
        0 login_count,
        0 cart_count,
        0 cart_amount,
        order_count,
        order_amount,
        0 payment_count,
        0 payment_amount
    from tmp_order
    union all
    select
        user_id,
        0 login_count,
        0 cart_count,
        0 cart_amount,
        0 order_count,
        0 order_amount,
        payment_count,
        payment_amount
    from tmp_payment
 ) user_actions
group by user_id;


with 
tmp_order as
(
    select
        sku_id,
        count(*) order_count,
        sum(sku_num) order_num,
        sum(total_amount) order_amount
    from ${APP}.dwd_fact_order_detail
    where dt='$do_date'
    group by sku_id
),
tmp_payment as
(
    select
        sku_id,
        count(*) payment_count,
        sum(sku_num) payment_num,
        sum(total_amount) payment_amount
    from ${APP}.dwd_fact_order_detail
    where dt='$do_date'
    and order_id in
    (
        select
            id
        from ${APP}.dwd_fact_order_info
        where (dt='$do_date' or dt=date_add('$do_date',-1))
        and date_format(payment_time,'yyyy-MM-dd')='$do_date'
    )
    group by sku_id
),
tmp_refund as
(
    select
        sku_id,
        count(*) refund_count,
        sum(refund_num) refund_num,
        sum(refund_amount) refund_amount
    from ${APP}.dwd_fact_order_refund_info
    where dt='$do_date'
    group by sku_id
),
tmp_cart as
(
    select
        sku_id,
        count(*) cart_count,
        sum(sku_num) cart_num
    from ${APP}.dwd_fact_cart_info
    where dt='$do_date'
    and date_format(create_time,'yyyy-MM-dd')='$do_date'
    group by sku_id
),
tmp_favor as
(
    select
        sku_id,
        count(*) favor_count
    from ${APP}.dwd_fact_favor_info
    where dt='$do_date'
    and date_format(create_time,'yyyy-MM-dd')='$do_date'
    group by sku_id
),
tmp_appraise as
(
    select
        sku_id,
        sum(if(appraise='1201',1,0)) appraise_good_count,
        sum(if(appraise='1202',1,0)) appraise_mid_count,
        sum(if(appraise='1203',1,0)) appraise_bad_count,
        sum(if(appraise='1204',1,0)) appraise_default_count
    from ${APP}.dwd_fact_comment_info
    where dt='$do_date'
    group by sku_id
)

insert overwrite table ${APP}.dws_sku_action_daycount partition(dt='$do_date')
select
    sku_id,
    sum(order_count),
    sum(order_num),
    sum(order_amount),
    sum(payment_count),
    sum(payment_num),
    sum(payment_amount),
    sum(refund_count),
    sum(refund_num),
    sum(refund_amount),
    sum(cart_count),
    sum(cart_num),
    sum(favor_count),
    sum(appraise_good_count),
    sum(appraise_mid_count),
    sum(appraise_bad_count),
    sum(appraise_default_count)
from
(
    select
        sku_id,
        order_count,
        order_num,
        order_amount,
        0 payment_count,
        0 payment_num,
        0 payment_amount,
        0 refund_count,
        0 refund_num,
        0 refund_amount,
        0 cart_count,
        0 cart_num,
        0 favor_count,
        0 appraise_good_count,
        0 appraise_mid_count,
        0 appraise_bad_count,
        0 appraise_default_count
    from tmp_order
    union all
    select
        sku_id,
        0 order_count,
        0 order_num,
        0 order_amount,
        payment_count,
        payment_num,
        payment_amount,
        0 refund_count,
        0 refund_num,
        0 refund_amount,
        0 cart_count,
        0 cart_num,
        0 favor_count,
        0 appraise_good_count,
        0 appraise_mid_count,
        0 appraise_bad_count,
        0 appraise_default_count
    from tmp_payment
    union all
    select
        sku_id,
        0 order_count,
        0 order_num,
        0 order_amount,
        0 payment_count,
        0 payment_num,
        0 payment_amount,
        refund_count,
        refund_num,
        refund_amount,
        0 cart_count,
        0 cart_num,
        0 favor_count,
        0 appraise_good_count,
        0 appraise_mid_count,
        0 appraise_bad_count,
        0 appraise_default_count        
    from tmp_refund
    union all
    select
        sku_id,
        0 order_count,
        0 order_num,
        0 order_amount,
        0 payment_count,
        0 payment_num,
        0 payment_amount,
        0 refund_count,
        0 refund_num,
        0 refund_amount,
        cart_count,
        cart_num,
        0 favor_count,
        0 appraise_good_count,
        0 appraise_mid_count,
        0 appraise_bad_count,
        0 appraise_default_count
    from tmp_cart
    union all
    select
        sku_id,
        0 order_count,
        0 order_num,
        0 order_amount,
        0 payment_count,
        0 payment_num,
        0 payment_amount,
        0 refund_count,
        0 refund_num,
        0 refund_amount,
        0 cart_count,
        0 cart_num,
        favor_count,
        0 appraise_good_count,
        0 appraise_mid_count,
        0 appraise_bad_count,
        0 appraise_default_count
    from tmp_favor
    union all
    select
        sku_id,
        0 order_count,
        0 order_num,
        0 order_amount,
        0 payment_count,
        0 payment_num,
        0 payment_amount,
        0 refund_count,
        0 refund_num,
        0 refund_amount,
        0 cart_count,
        0 cart_num,
        0 favor_count,
        appraise_good_count,
        appraise_mid_count,
        appraise_bad_count,
        appraise_default_count
    from tmp_appraise
)tmp
group by sku_id;


insert overwrite table ${APP}.dws_coupon_use_daycount partition(dt='$do_date')
select
    cu.coupon_id,
    ci.coupon_name,
    ci.coupon_type,
    ci.condition_amount,
    ci.condition_num,
    ci.activity_id,
    ci.benefit_amount,
    ci.benefit_discount,
    ci.create_time,
    ci.range_type,
    ci.spu_id,
    ci.tm_id,
    ci.category3_id,
    ci.limit_num,
    cu.get_count,
    cu.using_count,
    cu.used_count
from 
(
    select
        coupon_id,
        sum(if(date_format(get_time,'yyyy-MM-dd')='$do_date',1,0)) get_count,
        sum(if(date_format(using_time,'yyyy-MM-dd')='$do_date',1,0)) using_count,
        sum(if(date_format(used_time,'yyyy-MM-dd')='$do_date',1,0)) used_count
    from ${APP}.dwd_fact_coupon_use
    where dt='$do_date'
    group by coupon_id
)cu
left join
(
    select
        *
    from ${APP}.dwd_dim_coupon_info
    where dt='$do_date'
)ci on cu.coupon_id=ci.id;

insert overwrite table ${APP}.dws_activity_info_daycount partition(dt='$do_date')
select
    oi.activity_id,
    ai.activity_name,
    ai.activity_type,
    ai.start_time,
    ai.end_time,
    ai.create_time,
    oi.order_count,
    oi.payment_count
from
(
    select
        activity_id,
        sum(if(date_format(create_time,'yyyy-MM-dd')='$do_date',1,0)) order_count,
        sum(if(date_format(payment_time,'yyyy-MM-dd')='$do_date',1,0)) payment_count
    from ${APP}.dwd_fact_order_info
    where (dt='$do_date' or dt=date_add('$do_date',-1))
    and activity_id is not null
    group by activity_id
)oi
join
(
    select
        *
    from ${APP}.dwd_dim_activity_info
    where dt='$do_date'
)ai
on oi.activity_id=ai.id;

insert overwrite table ${APP}.dws_sale_detail_daycount partition(dt='$do_date')
select
    op.user_id,
    op.sku_id,
    ui.gender,
    months_between('$do_date', ui.birthday)/12  age, 
    ui.user_level,
    si.price,
    si.sku_name,
    si.tm_id,
    si.category3_id,
    si.category2_id,
    si.category1_id,
    si.category3_name,
    si.category2_name,
    si.category1_name,
    si.spu_id,
    op.sku_num,
    op.order_count,
    op.order_amount 
from
(
    select
        user_id,
        sku_id,
        sum(sku_num) sku_num,
        count(*) order_count,
        sum(total_amount) order_amount
    from ${APP}.dwd_fact_order_detail
    where dt='$do_date'
    group by user_id, sku_id
)op
join
(
    select
        *
    from ${APP}.dwd_dim_user_info_his
    where end_date='9999-99-99'
)ui on op.user_id = ui.id
join
(
    select
        *
    from ${APP}.dwd_dim_sku_info
    where dt='$do_date'
)si on op.sku_id = si.id;

"

$hive -e "$sql"

DM层加载数据脚本

#!/bin/bash

APP=gmall
hive=/opt/module/hive/bin/hive

# 如果是输入的日期按照取输入日期；如果没输入日期取当前时间的前一天
if [ -n "$1" ] ;then
    do_date=$1
else 
    do_date=`date -d "-1 day" +%F`
fi

sql="
insert overwrite table ${APP}.dwt_uv_topic
select
    nvl(new.mid_id,old.mid_id),
    nvl(new.user_id,old.user_id),
    nvl(new.version_code,old.version_code),
    nvl(new.version_name,old.version_name),
    nvl(new.lang,old.lang),
    nvl(new.source,old.source),
    nvl(new.os,old.os),
    nvl(new.area,old.area),
    nvl(new.model,old.model),
    nvl(new.brand,old.brand),
    nvl(new.sdk_version,old.sdk_version),
    nvl(new.gmail,old.gmail),
    nvl(new.height_width,old.height_width),
    nvl(new.app_time,old.app_time),
    nvl(new.network,old.network),
    nvl(new.lng,old.lng),
    nvl(new.lat,old.lat),
    nvl(old.login_date_first,'$do_date'),
    if(new.login_count>0,'$do_date',old.login_date_last),
    nvl(new.login_count,0),
    nvl(new.login_count,0)+nvl(old.login_count,0)
from
(
    select
        *
    from ${APP}.dwt_uv_topic
)old
full outer join
(
    select
        *
    from ${APP}.dws_uv_detail_daycount
    where dt='$do_date'
)new
on old.mid_id=new.mid_id;

insert overwrite table ${APP}.dwt_user_topic
select
    nvl(new.user_id,old.user_id),
    if(old.login_date_first is null and new.login_count>0,'$do_date',old.login_date_first),
    if(new.login_count>0,'$do_date',old.login_date_last),
    nvl(old.login_count,0)+if(new.login_count>0,1,0),
    nvl(new.login_last_30d_count,0),
    if(old.order_date_first is null and new.order_count>0,'$do_date',old.order_date_first),
    if(new.order_count>0,'$do_date',old.order_date_last),
    nvl(old.order_count,0)+nvl(new.order_count,0),
    nvl(old.order_amount,0)+nvl(new.order_amount,0),
    nvl(new.order_last_30d_count,0),
    nvl(new.order_last_30d_amount,0),
    if(old.payment_date_first is null and new.payment_count>0,'$do_date',old.payment_date_first),
    if(new.payment_count>0,'$do_date',old.payment_date_last),
    nvl(old.payment_count,0)+nvl(new.payment_count,0),
    nvl(old.payment_amount,0)+nvl(new.payment_amount,0),
    nvl(new.payment_last_30d_count,0),
    nvl(new.payment_last_30d_amount,0)
from
(
    select 
        *
    from ${APP}.dwt_user_topic
)old
full outer join
(
    select
        user_id,
        sum(if(dt='$do_date',login_count,0)) login_count,
        sum(if(dt='$do_date',order_count,0)) order_count,
        sum(if(dt='$do_date',order_amount,0)) order_amount,
        sum(if(dt='$do_date',payment_count,0)) payment_count,
        sum(if(dt='$do_date',payment_amount,0)) payment_amount,
        sum(if(order_count>0,1,0)) login_last_30d_count,
        sum(order_count) order_last_30d_count,
        sum(order_amount) order_last_30d_amount,
        sum(payment_count) payment_last_30d_count,
        sum(payment_amount) payment_last_30d_amount
    from ${APP}.dws_user_action_daycount
    where dt>=date_add( '$do_date',-30)
    group by user_id
)new
on old.user_id=new.user_id;

with
sku_act as
(
select 
    sku_id,
    sum(if(dt='$do_date', order_count,0 )) order_count,
    sum(if(dt='$do_date',order_num ,0 ))  order_num, 
    sum(if(dt='$do_date',order_amount,0 )) order_amount ,
    sum(if(dt='$do_date',payment_count,0 )) payment_count,
    sum(if(dt='$do_date',payment_num,0 )) payment_num,
    sum(if(dt='$do_date',payment_amount,0 )) payment_amount,
    sum(if(dt='$do_date',refund_count,0 )) refund_count,
    sum(if(dt='$do_date',refund_num,0 )) refund_num,
    sum(if(dt='$do_date',refund_amount,0 )) refund_amount,  
    sum(if(dt='$do_date',cart_count,0 )) cart_count,
    sum(if(dt='$do_date',cart_num,0 )) cart_num,
    sum(if(dt='$do_date',favor_count,0 )) favor_count,
    sum(if(dt='$do_date',appraise_good_count,0 )) appraise_good_count,  
    sum(if(dt='$do_date',appraise_mid_count,0 ) ) appraise_mid_count ,
    sum(if(dt='$do_date',appraise_bad_count,0 )) appraise_bad_count,  
    sum(if(dt='$do_date',appraise_default_count,0 )) appraise_default_count,
    sum( order_count  ) order_count30 ,
    sum( order_num  )  order_num30,
    sum(order_amount ) order_amount30,
    sum(payment_count ) payment_count30,
    sum(payment_num ) payment_num30,
    sum(payment_amount ) payment_amount30,
    sum(refund_count  ) refund_count30,
    sum(refund_num ) refund_num30,
    sum(refund_amount ) refund_amount30,
    sum(cart_count  ) cart_count30,
    sum(cart_num ) cart_num30,
    sum(favor_count ) favor_count30,
    sum(appraise_good_count ) appraise_good_count30,
    sum(appraise_mid_count  ) appraise_mid_count30,
    sum(appraise_bad_count ) appraise_bad_count30,
    sum(appraise_default_count )  appraise_default_count30 
from ${APP}.dws_sku_action_daycount
where dt>=date_add ( '$do_date',-30)
group by sku_id
),
sku_topic
as 
(
select
    sku_id,
    spu_id,
    order_last_30d_count,
    order_last_30d_num,
    order_last_30d_amount,
    order_count,
    order_num,
    order_amount  ,
    payment_last_30d_count,
    payment_last_30d_num,
    payment_last_30d_amount,
    payment_count,
    payment_num,
    payment_amount,
    refund_last_30d_count,
    refund_last_30d_num,
    refund_last_30d_amount ,
    refund_count  ,
    refund_num ,
    refund_amount  ,
    cart_last_30d_count  ,
    cart_last_30d_num  ,
    cart_count  ,
    cart_num  ,
    favor_last_30d_count  ,
    favor_count  ,
    appraise_last_30d_good_count  ,
    appraise_last_30d_mid_count  ,
    appraise_last_30d_bad_count  ,
    appraise_last_30d_default_count  ,
    appraise_good_count  ,
    appraise_mid_count  ,
    appraise_bad_count  ,
    appraise_default_count 
from ${APP}.dwt_sku_topic
)
insert overwrite table ${APP}.dwt_sku_topic
select 
    nvl(sku_act.sku_id,sku_topic.sku_id) ,
    sku_info.spu_id,
    nvl (sku_act.order_count30,0)      ,
    nvl (sku_act.order_num30,0)   ,
    nvl (sku_act.order_amount30,0)   ,
    nvl(sku_topic.order_count,0)+ nvl (sku_act.order_count,0) ,
    nvl(sku_topic.order_num,0)+ nvl (sku_act.order_num,0)   ,
    nvl(sku_topic.order_amount,0)+ nvl (sku_act.order_amount,0),
    nvl (sku_act.payment_count30,0),
    nvl (sku_act.payment_num30,0),
    nvl (sku_act.payment_amount30,0),
    nvl(sku_topic.payment_count,0)+ nvl (sku_act.payment_count,0) ,
    nvl(sku_topic.payment_num,0)+ nvl (sku_act.payment_count,0)  ,
    nvl(sku_topic.payment_amount,0)+ nvl (sku_act.payment_count,0)  ,
    nvl (refund_count30,0),
    nvl (sku_act.refund_num30,0),
    nvl (sku_act.refund_amount30,0),
    nvl(sku_topic.refund_count,0)+ nvl (sku_act.refund_count,0),
    nvl(sku_topic.refund_num,0)+ nvl (sku_act.refund_num,0),
    nvl(sku_topic.refund_amount,0)+ nvl (sku_act.refund_amount,0),
    nvl(sku_act.cart_count30,0)  ,
    nvl(sku_act.cart_num30,0)  ,
    nvl(sku_topic.cart_count  ,0)+ nvl (sku_act.cart_count,0),
    nvl( sku_topic.cart_num  ,0)+ nvl (sku_act.cart_num,0),
    nvl(sku_act.favor_count30 ,0)  ,
    nvl (sku_topic.favor_count  ,0)+ nvl (sku_act.favor_count,0),
    nvl (sku_act.appraise_good_count30 ,0)  ,
    nvl (sku_act.appraise_mid_count30 ,0)  ,
    nvl (sku_act.appraise_bad_count30 ,0)  ,
    nvl (sku_act.appraise_default_count30 ,0)  ,
    nvl (sku_topic.appraise_good_count  ,0)+ nvl (sku_act.appraise_good_count,0)  ,
    nvl (sku_topic.appraise_mid_count   ,0)+ nvl (sku_act.appraise_mid_count,0) ,
    nvl (sku_topic.appraise_bad_count  ,0)+ nvl (sku_act.appraise_bad_count,0)  ,
    nvl (sku_topic.appraise_default_count  ,0)+ nvl (sku_act.appraise_default_count,0) 
from sku_act
full outer join sku_topic
on sku_act.sku_id =sku_topic.sku_id
left join
(select * from ${APP}.dwd_dim_sku_info where dt='$do_date') sku_info
on nvl(sku_topic.sku_id,sku_act.sku_id)= sku_info.id;

insert overwrite table ${APP}.dwt_coupon_topic
select
    nvl(new.coupon_id,old.coupon_id),
    nvl(new.get_count,0),
    nvl(new.using_count,0),
    nvl(new.used_count,0),
    nvl(old.get_count,0)+nvl(new.get_count,0),
    nvl(old.using_count,0)+nvl(new.using_count,0),
    nvl(old.used_count,0)+nvl(new.used_count,0)
from
(
    select
        *
    from ${APP}.dwt_coupon_topic
)old
full outer join
(
    select
        coupon_id,
        get_count,
        using_count,
        used_count
    from ${APP}.dws_coupon_use_daycount
    where dt='$do_date'
)new
on old.coupon_id=new.coupon_id;

insert overwrite table ${APP}.dwt_activity_topic
select
    nvl(new.id,old.id),
    nvl(new.activity_name,old.activity_name),
    nvl(new.order_count,0),
    nvl(new.payment_count,0),
    nvl(old.order_count,0)+nvl(new.order_count,0),
    nvl(old.payment_count,0)+nvl(new.payment_count,0)
from
(
    select
        *
    from ${APP}.dwt_activity_topic
)old
full outer join
(
    select
        id,
        activity_name,
        order_count,
        payment_count
    from ${APP}.dws_activity_info_daycount
    where dt='$do_date'
)new
on old.id=new.id;
"

$hive -e "$sql"

ADS层加载数据脚本

#!/bin/bash

hive=/opt/module/hive/bin/hive

# 如果是输入的日期按照取输入日期；如果没输入日期取当前时间的前一天
if [ -n "$1" ] ;then
    do_date=$1
else 
    do_date=`date -d "-1 day" +%F`
fi

sql="use gmall;
insert into table ads_uv_count
select
    '$do_date',
    sum(if(login_date_last='$do_date',1,0)),
    sum(if(login_date_last>=date_add(next_day('$do_date','monday'),-7) and login_date_last<=date_add(next_day('$do_date','monday'),-1) ,1,0)),
    sum(if(date_format(login_date_last,'yyyy-MM')=date_format('$do_date','yyyy-MM'),1,0)),
    if('$do_date'=date_add(next_day('$do_date','monday'),-1),'Y','N'),
    if('$do_date'=last_day('$do_date'),'Y','N')
from dwt_uv_topic;

insert into table ads_new_mid_count
select
    '$do_date',
    count(*)
from dwt_uv_topic
where login_date_first='$do_date';

insert into table ads_silent_count
select
    '$do_date',
    count(*) 
from dwt_uv_topic
where login_date_first=login_date_last
and login_date_last<=date_add('$do_date',-7);

insert into table ads_back_count
select
    '$do_date',
    concat(date_add(next_day('2020-03-10','MO'),-7),'_',date_add(next_day('2020-03-10','MO'),-1)),
    count(*)
from
(
    select
        mid_id
    from dwt_uv_topic
    where login_date_last>=date_add(next_day('$do_date','MO'),-7) 
    and login_date_last<= date_add(next_day('$do_date','MO'),-1)
    and login_date_first<date_add(next_day('$do_date','MO'),-7)
)current_wk
left join
(
    select
        mid_id
    from dws_uv_detail_daycount
    where dt>=date_add(next_day('$do_date','MO'),-7*2) 
    and dt<= date_add(next_day('$do_date','MO'),-7-1) 
    group by mid_id
)last_wk
on current_wk.mid_id=last_wk.mid_id
where last_wk.mid_id is null;


insert into table ads_wastage_count
select
    '$do_date',
    count(*)
from dwt_uv_topic
where login_date_last<=date_add('$do_date',-7);

insert into table ads_user_retention_day_rate
select
    '$do_date',
    date_add('$do_date',-3),
    3,
    sum(if(login_date_first=date_add('$do_date',-3) and login_date_last='$do_date',1,0)),
    sum(if(login_date_first=date_add('$do_date',-3),1,0)),
    sum(if(login_date_first=date_add('$do_date',-3) and login_date_last='$do_date',1,0))/sum(if(login_date_first=date_add('$do_date',-3),1,0))*100
from dwt_uv_topic
union all 
select
    '$do_date',
    date_add('$do_date',-2),
    2,
    sum(if(login_date_first=date_add('$do_date',-2) and login_date_last='$do_date',1,0)),
    sum(if(login_date_first=date_add('$do_date',-2),1,0)),
    sum(if(login_date_first=date_add('$do_date',-2) and login_date_last='$do_date',1,0))/sum(if(login_date_first=date_add('$do_date',-2),1,0))*100
from dwt_uv_topic
union all
select
    '$do_date',
    date_add('$do_date',-1),
    1,
    sum(if(login_date_first=date_add('$do_date',-1) and login_date_last='$do_date',1,0)),
    sum(if(login_date_first=date_add('$do_date',-1),1,0)),
    sum(if(login_date_first=date_add('$do_date',-1) and login_date_last='$do_date',1,0))/sum(if(login_date_first=date_add('$do_date',-1),1,0))*100
from dwt_uv_topic;


insert into table ads_continuity_wk_count
select
    '$do_date',
    concat(date_add(next_day('$do_date','MO'),-7*3),'_',date_add(next_day('$do_date','MO'),-1)),
    count(*)
from
(
    select
        mid_id
    from
    (
        select
            mid_id
        from dws_uv_detail_daycount
        where dt>=date_add(next_day('$do_date','monday'),-7)
        and dt<=date_add(next_day('$do_date','monday'),-1)
        group by mid_id

        union all

        select
            mid_id
        from dws_uv_detail_daycount
        where dt>=date_add(next_day('$do_date','monday'),-7*2)
        and dt<=date_add(next_day('$do_date','monday'),-7-1)
        group by mid_id

        union all

        select
            mid_id
        from dws_uv_detail_daycount
        where dt>=date_add(next_day('$do_date','monday'),-7*3)
        and dt<=date_add(next_day('$do_date','monday'),-7*2-1)
        group by mid_id
    )t1
    group by mid_id
    having count(*)=3
)t2;

insert into table ads_continuity_uv_count
select
    '$do_date',
    concat(date_add('$do_date',-6),'_','$do_date'),
    count(*)
from
(
    select mid_id
    from
    (
        select mid_id      
        from
        (
            select 
                mid_id,
                date_sub(dt,rank) date_dif
            from
            (
                select 
                    mid_id,
                    dt,
                    rank() over(partition by mid_id order by dt) rank
                from dws_uv_detail_daycount
                where dt>=date_add('$do_date',-6) and dt<='$do_date'
            )t1
        )t2 
        group by mid_id,date_dif
        having count(*)>=3
    )t3 
    group by mid_id
)t4;

insert into table ads_user_topic
select
    '$do_date',
    sum(if(login_date_last='$do_date',1,0)),
    sum(if(login_date_first='$do_date',1,0)),
    sum(if(payment_date_first='$do_date',1,0)),
    sum(if(payment_count>0,1,0)),
    count(*),
    sum(if(login_date_last='$do_date',1,0))/count(*),
    sum(if(payment_count>0,1,0))/count(*),
    sum(if(login_date_first='$do_date',1,0))/sum(if(login_date_last='$do_date',1,0))
from dwt_user_topic;

insert into table ads_user_action_convert_day
select 
    '$do_date',
    uv.day_count,
    ua.cart_count,
    ua.cart_count/uv.day_count*100 visitor2cart_convert_ratio,
    ua.order_count,
    ua.order_count/ua.cart_count*100  visitor2order_convert_ratio,
    ua.payment_count,
    ua.payment_count/ua.order_count*100 order2payment_convert_ratio
from  
(
    select 
        '$do_date' dt,
        sum(if(cart_count>0,1,0)) cart_count,
        sum(if(order_count>0,1,0)) order_count,
        sum(if(payment_count>0,1,0)) payment_count
    from dws_user_action_daycount
    where dt='$do_date'
)ua join ads_uv_count uv on uv.dt=ua.dt;


insert into table ads_product_info
select
    '$do_date' dt,
    sku_num,
    spu_num
from
(
    select
        '$do_date' dt,
        count(*) sku_num
    from
        dwt_sku_topic
) tmp_sku_num
join
(
    select
        '$do_date' dt,
        count(*) spu_num
    from
    (
        select
            spu_id
        from
            dwt_sku_topic
        group by
            spu_id
    ) tmp_spu_id
) tmp_spu_num
on tmp_sku_num.dt=tmp_spu_num.dt;


insert into table ads_product_sale_topN
select
    '$do_date',
    sku_id,
    payment_amount
from dws_sku_action_daycount
where dt='$do_date'
order by payment_amount desc
limit 10;


insert into table ads_product_favor_topN
select
    '$do_date',
    sku_id,
    favor_count
from dws_sku_action_daycount
where dt='$do_date'
order by favor_count
limit 10;


insert into table ads_product_cart_topN
select
    '$do_date' dt,
    sku_id,
    cart_num
from dws_sku_action_daycount
where dt='$do_date'
order by cart_num
limit 10;

insert into table ads_product_refund_topN
select
    '$do_date',
    sku_id,
    refund_last_30d_count/payment_last_30d_count*100 refund_ratio
from dwt_sku_topic
order by refund_ratio desc
limit 10;

insert into table ads_appraise_bad_topN
select
    '$do_date' dt,
    sku_id,
    appraise_bad_count/(appraise_bad_count+appraise_good_count+appraise_mid_count+appraise_default_count)*100 appraise_bad_ratio
from dws_sku_action_daycount
where dt='$do_date'
order by appraise_bad_ratio desc
limit 10;


insert into table ads_order_daycount
select
    '$do_date',
    sum(order_count),
    sum(order_amount),
    sum(if(order_count>0,1,0))
from dws_user_action_daycount
where dt='$do_date';

insert into table ads_payment_daycount
select
    tmp_payment.dt,
    tmp_payment.payment_count,
    tmp_payment.payment_amount,
    tmp_payment.payment_user_count,
    tmp_skucount.payment_sku_count,
    tmp_time.payment_avg_time
from
(
    select
        '$do_date' dt,
        sum(payment_count) payment_count,
        sum(payment_amount) payment_amount,
        sum(if(payment_count>0,1,0)) payment_user_count
    from dws_user_action_daycount
    where dt='$do_date'
)tmp_payment
join
(
    select
        '$do_date' dt,
        sum(if(payment_count>0,1,0)) payment_sku_count 
    from dws_sku_action_daycount
    where dt='$do_date'
)tmp_skucount on tmp_payment.dt=tmp_skucount.dt
join
(
    select
        '$do_date' dt,
        sum(unix_timestamp(payment_time)-unix_timestamp(create_time))/count(*)/60 payment_avg_time
    from dwd_fact_order_info
    where dt='$do_date'
    and payment_time is not null
)tmp_time on tmp_payment.dt=tmp_time.dt;

insert into table ads_sale_tm_category1_stat_mn
select   
    mn.sku_tm_id,
    mn.sku_category1_id,
    mn.sku_category1_name,
    sum(if(mn.order_count>=1,1,0)) buycount,
    sum(if(mn.order_count>=2,1,0)) buyTwiceLast,
    sum(if(mn.order_count>=2,1,0))/sum( if(mn.order_count>=1,1,0)) buyTwiceLastRatio,
    sum(if(mn.order_count>=3,1,0))  buy3timeLast  ,
    sum(if(mn.order_count>=3,1,0))/sum( if(mn.order_count>=1,1,0)) buy3timeLastRatio ,
    date_format('$do_date' ,'yyyy-MM') stat_mn,
    '$do_date' stat_date
from 
(
    select 
        user_id, 
        sd.sku_tm_id,
        sd.sku_category1_id,
        sd.sku_category1_name,
        sum(order_count) order_count
    from dws_sale_detail_daycount sd 
    where date_format(dt,'yyyy-MM')=date_format('$do_date' ,'yyyy-MM')
    group by user_id, sd.sku_tm_id, sd.sku_category1_id, sd.sku_category1_name
) mn
group by mn.sku_tm_id, mn.sku_category1_id, mn.sku_category1_name;
"

$hive -e "$sql"

xiaoxiao______

关注

0
点赞
踩
0

收藏

觉得还不错? 一键收藏
0
评论
一些hql

ODS层加载数据脚本#!/bin/bashAPP=gmallhive=/opt/module/hive/bin/hive# 如果是输入的日期按照取输入日期；如果没输入日期取当前时间的前一天if [ -n "$2" ] ;then do_date=$2else do_date=`date -d "-1 day" +%F`fisql1=" load data inpath '/origin_data/$APP/db/order_info/$do_date' OVERWR
复制链接

扫一扫