【数据仓库】大数据之数据仓库的数据流程及脚本实现

矫情吗；* 2023-01-07 10:16 159阅读 0赞

##### 数据仓库的定义 #####

数据集合：

*  面向主题的（Subject Oriented）
 *  集成的（Integrated）
 *  相对稳定的（Non-Volatile）
 *  反映历史变化（Time Variant）
 *  用于支持管理决策（Decision Making Support）

##### 数据仓库和数据库的区别 #####

数据库：OLTP  
数据仓库：OLAP  
大数据的数据仓库：

*  更多更长时间的数据
 *  低成本的大数据平台
 *  更高效的数据分析能力
 *  实时+离线模式处理同一数据源

##### 数据仓库的目标 #####

*  建好数据采集、传输和存储平台
 *  在hive中分层来搭建数据仓库

##### 数据仓库所用的技术 #####

*  采集数据：Flume+Kafka
 *  存储数据：HDFS
 *  计算数据：Hive

##### 数据仓库的数据流程 #####

日志服务器生产日志  
\-> flume（采集数据，并作为生产者将数据传输给kafka）  
\-> Kafka（缓存）  
\-> Flume（作为kafka的消费者）  
\-> HDFS  
\-> Hive（分四层完成数据仓库）

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2dvbmd4aWZhY2FpX2JlbGlldmU_size_16_color_FFFFFF_t_70_pic_center]

##### 数据仓库分层 #####

ODS（Operation Data Store）：原始数据层  
DWD（Data Warehouse detail）：明细层  
DWS（Data Warehouse Service）：服务数据层  
ADS（Application Data Store）：数据应用层

##### 数据仓库集群架构 #####

<table> 
 <thead> 
  <tr> 
   <th>服务名称</th> 
   <th>子服务</th> 
   <th>服务器1</th> 
   <th>服务器2</th> 
   <th>服务器3</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <td>HDFS</td> 
   <td>NameNode</td> 
   <td>√</td> 
   <td></td> 
   <td></td> 
  </tr> 
  <tr> 
   <td></td> 
   <td>DataNode</td> 
   <td>√</td> 
   <td>√</td> 
   <td>√</td> 
  </tr> 
  <tr> 
   <td></td> 
   <td>SecondaryNameNode</td> 
   <td></td> 
   <td></td> 
   <td>√</td> 
  </tr> 
  <tr> 
   <td>Yarn</td> 
   <td>ResourceManager</td> 
   <td></td> 
   <td>√</td> 
   <td></td> 
  </tr> 
  <tr> 
   <td></td> 
   <td>NodeManager</td> 
   <td>√</td> 
   <td>√</td> 
   <td>√</td> 
  </tr> 
  <tr> 
   <td>Zookeeper</td> 
   <td>Zookeeper Server</td> 
   <td>√</td> 
   <td>√</td> 
   <td>√</td> 
  </tr> 
  <tr> 
   <td>Flume（采集日志）</td> 
   <td>Flume</td> 
   <td>√</td> 
   <td>√</td> 
   <td></td> 
  </tr> 
  <tr> 
   <td>Kafka</td> 
   <td>Kafka</td> 
   <td>√</td> 
   <td>√</td> 
   <td>√</td> 
  </tr> 
  <tr> 
   <td>Flume（消费Kafka）</td> 
   <td>Flume</td> 
   <td></td> 
   <td></td> 
   <td>√</td> 
  </tr> 
  <tr> 
   <td>Hive</td> 
   <td>Hive</td> 
   <td>√</td> 
   <td></td> 
   <td></td> 
  </tr> 
  <tr> 
   <td>MySQL</td> 
   <td>MySQL</td> 
   <td>√</td> 
   <td></td> 
   <td></td> 
  </tr> 
  <tr> 
   <td>Sqoop</td> 
   <td>Sqoop</td> 
   <td>√</td> 
   <td></td> 
   <td></td> 
  </tr> 
 </tbody> 
</table>

##### 埋点数据 #####

*  公共数据：手机包含的数据，一般是所有手机共有的数据
 *  事件数据：埋点上传的事件数据，一般是业务数据
 *  公共数据

"cm": { 
            "mid": "",  
            "uid": "",  
            "vc": "1", 
            "vn": "1.0", 
            "l": "zh",  
            "sr": "",  
            "os": "7.1.1",  
            "ar": "CN",  
            "md": "BBB100-1", 
            "ba": "blackberry",
            "sv": "V2.2.1",  
            "g": "",  
            "hw": "1620x1080",  
            "t": "1506047606608",  
            "nw": "WIFI",  
            "ln": 0,  
            "la": 0  
        }

*  事件数据

"et": [
             { 
                 "ett": "1506047605364",  
                 "en": "display", 
                 "kv": {   
                        "goodsid": "236",
                        "action": "1",
                        "extend1": "1",
                        "place": "2",
                        "category": "75"
                        }
               }
          ]

##### 创建启动日志表 #####

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';

##### 给启动日志表加载数据 #####

load data inpath '/origin_data/gmall/log/topic_start/2019-02-10'
    	into table 
    	gmall.ods_start_log partition(dt='2019-02-10');

##### 创建事件日志表 #####

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';

##### 给事件日志表加载数据 #####

load data inpath '/origin_data/gmall/log/topic_event/2019-02-10' 
    	into table
     	gmall.ods_event_log partition(dt='2019-02-10');

##### 配置文件及脚本 #####

## file-flume-kafka.conf
    
    a1.sources=r1
    a1.channels=c1 c2
    
    # configure source
    a1.sources.r1.type = TAILDIR
    a1.sources.r1.positionFile = /opt/module/flume/test/log_position.json
    a1.sources.r1.filegroups = f1
    a1.sources.r1.filegroups.f1 = /tmp/logs/app.+
    a1.sources.r1.fileHeader = true
    a1.sources.r1.channels = c1 c2
    
    #interceptor
    a1.sources.r1.interceptors =  i1 i2
    a1.sources.r1.interceptors.i1.type = com.gupao.flume.interceptor.LogETLInterceptor$Builder
    a1.sources.r1.interceptors.i2.type = com.gupao.flume.interceptor.LogTypeInterceptor$Builder
    
    a1.sources.r1.selector.type = multiplexing
    a1.sources.r1.selector.header = topic
    a1.sources.r1.selector.mapping.topic_start = c1
    a1.sources.r1.selector.mapping.topic_event = c2
    
    # configure channel
    a1.channels.c1.type = org.apache.flume.channel.kafka.KafkaChannel
    a1.channels.c1.kafka.bootstrap.servers = hadoop102:9092,hadoop103:9092,hadoop104:9092
    a1.channels.c1.kafka.topic = topic_start
    a1.channels.c1.parseAsFlumeEvent = false
    a1.channels.c1.kafka.consumer.group.id = flume-consumer
    
    a1.channels.c2.type = org.apache.flume.channel.kafka.KafkaChannel
    a1.channels.c2.kafka.bootstrap.servers = hadoop102:9092,hadoop103:9092,hadoop104:9092
    a1.channels.c2.kafka.topic = topic_event
    a1.channels.c2.parseAsFlumeEvent = false
    a1.channels.c2.kafka.consumer.group.id = flume-consumer

## kafka-flume-hdfs.conf
    
    ## 组件
    a1.sources=r1 r2
    a1.channels=c1 c2
    a1.sinks=k1 k2
    
    ## source1
    a1.sources.r1.type = org.apache.flume.source.kafka.KafkaSource
    a1.sources.r1.batchSize = 5000
    a1.sources.r1.batchDurationMillis = 2000
    a1.sources.r1.kafka.bootstrap.servers = hadoop102:9092,hadoop103:9092,hadoop104:9092
    a1.sources.r1.kafka.topics=topic_start
    
    ## source2
    a1.sources.r2.type = org.apache.flume.source.kafka.KafkaSource
    a1.sources.r2.batchSize = 5000
    a1.sources.r2.batchDurationMillis = 2000
    a1.sources.r2.kafka.bootstrap.servers = hadoop102:9092,hadoop103:9092,hadoop104:9092
    a1.sources.r2.kafka.topics=topic_event
    
    ## channel1
    a1.channels.c1.type = file
    a1.channels.c1.checkpointDir = /opt/module/flume/checkpoint/behavior1
    a1.channels.c1.dataDirs = /opt/module/flume/data/behavior1/
    a1.channels.c1.maxFileSize = 2146435071
    a1.channels.c1.capacity = 1000000
    a1.channels.c1.keep-alive = 6
    
    ## channel2
    a1.channels.c2.type = file
    a1.channels.c2.checkpointDir = /opt/module/flume/checkpoint/behavior2
    a1.channels.c2.dataDirs = /opt/module/flume/data/behavior2/
    a1.channels.c2.maxFileSize = 2146435071
    a1.channels.c2.capacity = 1000000
    a1.channels.c2.keep-alive = 6
    
    ## sink1
    a1.sinks.k1.type = hdfs
    a1.sinks.k1.hdfs.path = /origin_data/gmall/log/topic_start/%Y-%m-%d
    a1.sinks.k1.hdfs.filePrefix = logstart-
    a1.sinks.k1.hdfs.round = true
    a1.sinks.k1.hdfs.roundValue = 10
    a1.sinks.k1.hdfs.roundUnit = second
    
    ##sink2
    a1.sinks.k2.type = hdfs
    a1.sinks.k2.hdfs.path = /origin_data/gmall/log/topic_event/%Y-%m-%d
    a1.sinks.k2.hdfs.filePrefix = logevent-
    a1.sinks.k2.hdfs.round = true
    a1.sinks.k2.hdfs.roundValue = 10
    a1.sinks.k2.hdfs.roundUnit = second
    
    ## 不要产生大量小文件
    a1.sinks.k1.hdfs.rollInterval = 10
    a1.sinks.k1.hdfs.rollSize = 134217728
    a1.sinks.k1.hdfs.rollCount = 0
    
    a1.sinks.k2.hdfs.rollInterval = 10
    a1.sinks.k2.hdfs.rollSize = 134217728
    a1.sinks.k2.hdfs.rollCount = 0
    
    ## 控制输出文件是原生文件。
    a1.sinks.k1.hdfs.fileType = CompressedStream 
    a1.sinks.k2.hdfs.fileType = CompressedStream 
    
    a1.sinks.k1.hdfs.codeC = lzop
    a1.sinks.k2.hdfs.codeC = lzop
    
    ## 拼装
    a1.sources.r1.channels = c1
    a1.sinks.k1.channel= c1
    
    a1.sources.r2.channels = c2
    a1.sinks.k2.channel= c2

## ods_log.sh
    
    #!/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 
    
    echo "===日志日期为 $do_date==="
    sql=" load data inpath '/origin_data/gmall/log/topic_start/$do_date' into table "$APP".ods_start_log partition(dt='$do_date'); load data inpath '/origin_data/gmall/log/topic_event/$do_date' into table "$APP".ods_event_log partition(dt='$do_date'); "
    
    $hive -e "$sql"

## dwd_base_log.sh
    
    #!/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=" add jar /opt/module/hive/hivefunction-1.0-SNAPSHOT.jar; create temporary function base_analizer as 'com.gupao.udf.BaseFieldUDF'; create temporary function flat_analizer as 'com.gupao.udtf.EventJsonUDTF'; set hive.exec.dynamic.partition.mode=nonstrict; insert overwrite table "$APP".dwd_base_event_log PARTITION (dt='$do_date') select mid_id, user_id, version_code, version_name, lang, source , os , area , model , brand , sdk_version , gmail , height_width , network , lng , lat , app_time , event_name , event_json , server_time from ( select split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[0] as mid_id, split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[1] as user_id, split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[2] as version_code, split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[3] as version_name, split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[4] as lang, split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[5] as source, split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[6] as os, split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[7] as area, split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[8] as model, split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[9] as brand, split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[10] as sdk_version, split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[11] as gmail, split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[12] as height_width, split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[13] as app_time, split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[14] as network, split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[15] as lng, split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[16] as lat, split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[17] as ops, split(base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la'),'\t')[18] as server_time from "$APP".ods_event_log where dt='$do_date' and base_analizer(line,'mid,uid,vc,vn,l,sr,os,ar,md,ba,sv,g,hw,t,nw,ln,la')<>'' ) sdk_log lateral view flat_analizer(ops) tmp_k as event_name, event_json; "
    
    $hive -e "$sql"

## dwd_start_log.sh
    
    #!/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"

## dwd_event_log.sh
    
    #!/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 "$APP".dwd_display_log PARTITION (dt='$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,'$.kv.content') content, get_json_object(event_json,'$.kv.detail') detail, get_json_object(event_json,'$.kv.source') ad_source, get_json_object(event_json,'$.kv.behavior') behavior, get_json_object(event_json,'$.kv.newstype') newstype, get_json_object(event_json,'$.kv.show_style') show_style, 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 "$APP".dwd_active_foreground_log PARTITION (dt='$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,'$.kv.push_id') push_id, get_json_object(event_json,'$.kv.access') access, server_time from "$APP".dwd_base_event_log where dt='$do_date' and event_name='active_foreground'; 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_db.sh
    
    #!/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 "$APP".dwd_order_info partition(dt) select * from "$APP".ods_order_info where dt='$do_date' and id is not null; insert overwrite table "$APP".dwd_order_detail partition(dt) select * from "$APP".ods_order_detail where dt='$do_date' and id is not null; insert overwrite table "$APP".dwd_user_info partition(dt) select * from "$APP".ods_user_info where dt='$do_date' and id is not null; insert overwrite table "$APP".dwd_payment_info partition(dt) select * from "$APP".ods_payment_info where dt='$do_date' and id is not null; insert overwrite table "$APP".dwd_sku_info partition(dt) select sku.id, sku.spu_id, sku.price, sku.sku_name, sku.sku_desc, sku.weight, sku.tm_id, sku.category3_id, c2.id category2_id, c1.id category1_id, c3.name category3_name, c2.name category2_name, c1.name category1_name, sku.create_time, sku.dt from "$APP".ods_sku_info sku join "$APP".ods_base_category3 c3 on sku.category3_id=c3.id join "$APP".ods_base_category2 c2 on c3.category2_id=c2.id join "$APP".ods_base_category1 c1 on c2.category1_id=c1.id where sku.dt='$do_date' and c2.dt='$do_date' and c3.dt='$do_date' and c1.dt='$do_date' and sku.id is not null; "
    
    $hive -e "$sql"

## dws_uv_log.sh
    
    #!/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 "$APP".dws_uv_detail_day partition(dt='$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 from "$APP".dwd_start_log where dt='$do_date' group by mid_id; insert overwrite table "$APP".dws_uv_detail_wk partition(wk_dt) select mid_id, concat_ws('|', collect_set(user_id)) user_id, concat_ws('|', collect_set(version_code)) version_code, concat_ws('|', collect_set(version_name)) version_name, concat_ws('|', collect_set(lang)) lang, concat_ws('|', collect_set(source)) source, concat_ws('|', collect_set(os)) os, concat_ws('|', collect_set(area)) area, concat_ws('|', collect_set(model)) model, concat_ws('|', collect_set(brand)) brand, concat_ws('|', collect_set(sdk_version)) sdk_version, concat_ws('|', collect_set(gmail)) gmail, concat_ws('|', collect_set(height_width)) height_width, concat_ws('|', collect_set(app_time)) app_time, concat_ws('|', collect_set(network)) network, concat_ws('|', collect_set(lng)) lng, concat_ws('|', collect_set(lat)) lat, date_add(next_day('$do_date','MO'),-7), date_add(next_day('$do_date','MO'),-1), concat(date_add( next_day('$do_date','MO'),-7), '_' , date_add(next_day('$do_date','MO'),-1) ) from "$APP".dws_uv_detail_day where dt>=date_add(next_day('$do_date','MO'),-7) and dt<=date_add(next_day('$do_date','MO'),-1) group by mid_id; insert overwrite table "$APP".dws_uv_detail_mn partition(mn) select mid_id, concat_ws('|', collect_set(user_id)) user_id, concat_ws('|', collect_set(version_code)) version_code, concat_ws('|', collect_set(version_name)) version_name, concat_ws('|', collect_set(lang))lang, concat_ws('|', collect_set(source)) source, concat_ws('|', collect_set(os)) os, concat_ws('|', collect_set(area)) area, concat_ws('|', collect_set(model)) model, concat_ws('|', collect_set(brand)) brand, concat_ws('|', collect_set(sdk_version)) sdk_version, concat_ws('|', collect_set(gmail)) gmail, concat_ws('|', collect_set(height_width)) height_width, concat_ws('|', collect_set(app_time)) app_time, concat_ws('|', collect_set(network)) network, concat_ws('|', collect_set(lng)) lng, concat_ws('|', collect_set(lat)) lat, date_format('$do_date','yyyy-MM') from "$APP".dws_uv_detail_day where date_format(dt,'yyyy-MM') = date_format('$do_date','yyyy-MM') group by mid_id; "
    
    $hive -e "$sql"

## ads_uv_log.sh
    
    #!/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 into table "$APP".ads_uv_count select '$do_date' dt, daycount.ct, wkcount.ct, mncount.ct, if(date_add(next_day('$do_date','MO'),-1)='$do_date','Y','N') , if(last_day('$do_date')='$do_date','Y','N') from ( select '$do_date' dt, count(*) ct from "$APP".dws_uv_detail_day where dt='$do_date' )daycount join ( select '$do_date' dt, count (*) ct from "$APP".dws_uv_detail_wk where wk_dt=concat(date_add(next_day('$do_date','MO'),-7),'_' ,date_add(next_day('$do_date','MO'),-1) ) ) wkcount on daycount.dt=wkcount.dt join ( select '$do_date' dt, count (*) ct from "$APP".dws_uv_detail_mn where mn=date_format('$do_date','yyyy-MM') )mncount on daycount.dt=mncount.dt; "
    
    $hive -e "$sql"

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2dvbmd4aWZhY2FpX2JlbGlldmU_size_16_color_FFFFFF_t_70_pic_center]: /images/20221119/f2bdaa541f6f48608ac3156d94b766b6.png