Commit 5554b5f2 authored by edz's avatar edz

push core

parent bcd363f6
...@@ -24,9 +24,11 @@ FROM ...@@ -24,9 +24,11 @@ FROM
LEFT JOIN LEFT JOIN
(SELECT code,is_spam,is_ai_channel,partition_day (SELECT code,is_spam,is_ai_channel,partition_day
FROM DIM.DIM_AI_CHANNEL_ZP_NEW FROM DIM.DIM_AI_CHANNEL_ZP_NEW
WHERE partition_day >='${start_date}' and partition_day<'${end_date}')tmp WHERE partition_day >=REGEXP_REPLACE(trunc(date_sub(current_date(),1),'MM'),'-','')
and partition_day<=REGEXP_REPLACE(current_date(),'-',''))tmp
on first_channel_source_type=tmp.code and m.partition_date=tmp.partition_day on first_channel_source_type=tmp.code and m.partition_date=tmp.partition_day
WHERE partition_date >= '${start_date}' and partition_date < '${end_date}' WHERE partition_date >= REGEXP_REPLACE(trunc(date_sub(current_date(),1),'MM'),'-','')
and partition_date <= REGEXP_REPLACE(current_date(),'-','')
AND active_type IN ('1','2','4') AND active_type IN ('1','2','4')
AND first_channel_source_type not IN ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3' AND first_channel_source_type not IN ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang' ,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
...@@ -61,7 +63,8 @@ FROM ...@@ -61,7 +63,8 @@ FROM
page_name, page_name,
row_number() over (partition by partition_date,cl_id,app_session_id order by time_str asc) as no row_number() over (partition by partition_date,cl_id,app_session_id order by time_str asc) as no
FROM online.bl_hdfs_maidian_updates FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= '${start_date}' and partition_date < '${end_date}' WHERE partition_date >= REGEXP_REPLACE(trunc(date_sub(current_date(),1),'MM'),'-','')
and partition_date <= REGEXP_REPLACE(current_date(),'-','')
AND page_name in ('face_scan','report_result','face_detect_result','face_simulator') AND page_name in ('face_scan','report_result','face_detect_result','face_simulator')
AND action = 'page_view' AND action = 'page_view'
GROUP BY partition_date, GROUP BY partition_date,
...@@ -99,7 +102,8 @@ FROM ...@@ -99,7 +102,8 @@ FROM
page_name, page_name,
row_number() over (partition by partition_date,cl_id,app_session_id order by time_str asc) as no row_number() over (partition by partition_date,cl_id,app_session_id order by time_str asc) as no
FROM online.bl_hdfs_maidian_updates FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= '${start_date}' and partition_date < '${end_date}' WHERE partition_date >= REGEXP_REPLACE(trunc(date_sub(current_date(),1),'MM'),'-','')
and partition_date <= REGEXP_REPLACE(current_date(),'-','')
AND page_name in ('face_scan','report_result','face_detect_result','face_simulator') AND page_name in ('face_scan','report_result','face_detect_result','face_simulator')
AND action = 'page_view' AND action = 'page_view'
GROUP BY partition_date, GROUP BY partition_date,
...@@ -124,7 +128,7 @@ FROM ...@@ -124,7 +128,7 @@ FROM
when page_name in ('post_detail','user_post_detail','doctor_post_detail') THEN 'post' when page_name in ('post_detail','user_post_detail','doctor_post_detail') THEN 'post'
when page_name in ('answer_detail') THEN 'answer' end as content_type when page_name in ('answer_detail') THEN 'answer' end as content_type
FROM ONLINE.BL_HDFS_MAIDIAN_UPDATES FROM ONLINE.BL_HDFS_MAIDIAN_UPDATES
WHERE PARTITION_DATE >= '${start_date}' WHERE PARTITION_DATE >= REGEXP_REPLACE(trunc(date_sub(current_date(),1),'MM'),'-','')
and page_name in ('diary_detail','topic_detail','post_detail','user_post_detail','doctor_post_detail','question_detail','answer_detail','question_answer_detail', and page_name in ('diary_detail','topic_detail','post_detail','user_post_detail','doctor_post_detail','question_detail','answer_detail','question_answer_detail',
'video_steep','article_detail') 'video_steep','article_detail')
and (referrer in ('report_result','face_detect_result','float_tag_detail') or and (referrer in ('report_result','face_detect_result','float_tag_detail') or
...@@ -142,7 +146,7 @@ FROM ...@@ -142,7 +146,7 @@ FROM
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','') WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND is_spam = 'false' --排除疑似广告 AND is_spam = 'false' --排除疑似广告
and is_online='true' and is_online='true'
and regexp_replace(substr(reply_date,1,10),'-','') >= '${start_date}' and regexp_replace(substr(reply_date,1,10),'-','') >= REGEXP_REPLACE(trunc(date_sub(current_date(),1),'MM'),'-','')
group by id,problem_id,user_id,reply_date group by id,problem_id,user_id,reply_date
)t1 )t1
JOIN JOIN
...@@ -166,7 +170,7 @@ FROM ...@@ -166,7 +170,7 @@ FROM
AND answer_id is not NULL AND answer_id is not NULL
and is_online='true' and is_online='true'
and is_spam = 'false' --排除疑似广告 and is_spam = 'false' --排除疑似广告
and regexp_replace(substr(create_time,1,10),'-','') >= '${start_date}' and regexp_replace(substr(create_time,1,10),'-','') >= REGEXP_REPLACE(trunc(date_sub(current_date(),1),'MM'),'-','')
group by answer_id,user_id,create_time group by answer_id,user_id,create_time
UNION ALL UNION ALL
...@@ -175,7 +179,7 @@ FROM ...@@ -175,7 +179,7 @@ FROM
SELECT tractate_id as content_id,'post' as type,user_id,regexp_replace(substr(create_time,1,10),'-','') as create_date SELECT tractate_id as content_id,'post' as type,user_id,regexp_replace(substr(create_time,1,10),'-','') as create_date
FROM online.tl_hdfs_api_tractate_reply_view FROM online.tl_hdfs_api_tractate_reply_view
WHERE partition_date =regexp_replace(DATE_SUB(current_date,1) ,'-','') WHERE partition_date =regexp_replace(DATE_SUB(current_date,1) ,'-','')
and regexp_replace(substr(create_time,1,10),'-','') >= '${start_date}' and regexp_replace(substr(create_time,1,10),'-','') >= REGEXP_REPLACE(trunc(date_sub(current_date(),1),'MM'),'-','')
and is_online='true' and is_online='true'
group by tractate_id,user_id,create_time group by tractate_id,user_id,create_time
)b )b
...@@ -197,7 +201,8 @@ FROM ...@@ -197,7 +201,8 @@ FROM
SELECT concat_ws('-',substr(partition_date,1,4),substr(partition_date,5,2),substr(partition_date,7,2)) as partition_date,cl_id,count(distinct business_id) as gc_num SELECT concat_ws('-',substr(partition_date,1,4),substr(partition_date,5,2),substr(partition_date,7,2)) as partition_date,cl_id,count(distinct business_id) as gc_num
FROM online.bl_hdfs_maidian_updates FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= '${start_date}' and partition_date < '${end_date}' WHERE partition_date >= REGEXP_REPLACE(trunc(date_sub(current_date(),1),'MM'),'-','')
and partition_date <= regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND ((action in ('welfare_multiattribute_click_add','welfare_multiattribute_click_buy','on_click_navbar_cart') AND page_name = 'welfare_detail')--点击加车 AND ((action in ('welfare_multiattribute_click_add','welfare_multiattribute_click_buy','on_click_navbar_cart') AND page_name = 'welfare_detail')--点击加车
or action = 'welfare_detail_click_message'--点击私信 or action = 'welfare_detail_click_message'--点击私信
or (action = 'on_click_button' AND page_name = 'welfare_detail' AND params['button_name'] in ('question_tag','appointment'))--点击人工咨询+预约面诊 or (action = 'on_click_button' AND page_name = 'welfare_detail' AND params['button_name'] in ('question_tag','appointment'))--点击人工咨询+预约面诊
...@@ -221,7 +226,8 @@ FROM ...@@ -221,7 +226,8 @@ FROM
--在结果页的去别的功能以及视频面诊按钮 --在结果页的去别的功能以及视频面诊按钮
SELECT concat_ws('-',substr(partition_date,1,4),substr(partition_date,5,2),substr(partition_date,7,2)) as partition_date,cl_id,count(distinct time_str) as gc_num SELECT concat_ws('-',substr(partition_date,1,4),substr(partition_date,5,2),substr(partition_date,7,2)) as partition_date,cl_id,count(distinct time_str) as gc_num
FROM online.bl_hdfs_maidian_updates FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= '${start_date}' and partition_date < '${end_date}' WHERE partition_date >= REGEXP_REPLACE(trunc(date_sub(current_date(),1),'MM'),'-','')
and partition_date <= regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND action = 'on_click_button' AND action = 'on_click_button'
and params['page_name'] in ('report_result','face_detect_result') --测肤结果页点击完成、再测一次、扫脸、视频面诊 and params['page_name'] in ('report_result','face_detect_result') --测肤结果页点击完成、再测一次、扫脸、视频面诊
AND params['button_name'] in ('ai_function','video_interview','AI测肤质','视频面诊','AI测颜值') AND params['button_name'] in ('ai_function','video_interview','AI测肤质','视频面诊','AI测颜值')
...@@ -233,7 +239,8 @@ FROM ...@@ -233,7 +239,8 @@ FROM
select concat_ws('-',substr(partition_date,1,4),substr(partition_date,5,2),substr(partition_date,7,2)) as partition_date,cl_id,count(distinct business_id) as gc_num select concat_ws('-',substr(partition_date,1,4),substr(partition_date,5,2),substr(partition_date,7,2)) as partition_date,cl_id,count(distinct business_id) as gc_num
from online.bl_hdfs_maidian_updates from online.bl_hdfs_maidian_updates
where partition_date >= '${start_date}' and partition_date < '${end_date}' where partition_date >= REGEXP_REPLACE(trunc(date_sub(current_date(),1),'MM'),'-','')
and partition_date <= regexp_replace(DATE_SUB(current_date,1) ,'-','')
and ((action='page_view' and page_stay>=20) and ((action='page_view' and page_stay>=20)
or (action='on_click_card' and params['card_type']='card')) or (action='on_click_card' and params['card_type']='card'))
and page_name in ('search_result_question_answer','topic_aggregation') and page_name in ('search_result_question_answer','topic_aggregation')
...@@ -248,7 +255,8 @@ FROM ...@@ -248,7 +255,8 @@ FROM
select concat_ws('-',substr(partition_date,1,4),substr(partition_date,5,2),substr(partition_date,7,2)) as partition_date,cl_id,count(distinct time_str) as gc_num select concat_ws('-',substr(partition_date,1,4),substr(partition_date,5,2),substr(partition_date,7,2)) as partition_date,cl_id,count(distinct time_str) as gc_num
from online.bl_hdfs_maidian_updates from online.bl_hdfs_maidian_updates
where partition_date >= '${start_date}' and partition_date < '${end_date}' where partition_date >= REGEXP_REPLACE(trunc(date_sub(current_date(),1),'MM'),'-','')
and partition_date <= regexp_replace(DATE_SUB(current_date,1) ,'-','')
and action='on_click_button' and action='on_click_button'
and page_name = 'float_tag_detail' and page_name = 'float_tag_detail'
and params['button_name'] in ('consult','bargain','commodity_ranking') and params['button_name'] in ('consult','bargain','commodity_ranking')
......
...@@ -75,9 +75,11 @@ FROM ...@@ -75,9 +75,11 @@ FROM
LEFT JOIN LEFT JOIN
(SELECT code,is_ai_channel,partition_day (SELECT code,is_ai_channel,partition_day
FROM DIM.DIM_AI_CHANNEL_ZP_NEW FROM DIM.DIM_AI_CHANNEL_ZP_NEW
WHERE partition_day>= '${start_date}' AND partition_day <= regexp_replace(DATE_SUB(current_date,1) ,'-','')) tmp WHERE partition_day>= REGEXP_REPLACE(trunc(date_sub(current_date(),1),'MM'),'-','')
AND partition_day <= regexp_replace(DATE_SUB(current_date,1) ,'-','')) tmp
ON partition_date=tmp.partition_day AND first_channel_source_type=code ON partition_date=tmp.partition_day AND first_channel_source_type=code
WHERE partition_date >= '${start_date}' and partition_date <= regexp_replace(DATE_SUB(current_date,1) ,'-','') WHERE partition_date >= REGEXP_REPLACE(trunc(date_sub(current_date(),1),'MM'),'-','')
and partition_date <= regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND active_type IN ('1','2','4') AND active_type IN ('1','2','4')
AND first_channel_source_type not IN ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3' AND first_channel_source_type not IN ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang' ,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
...@@ -103,7 +105,8 @@ FROM ...@@ -103,7 +105,8 @@ FROM
SELECT concat_ws('-',substr(partition_date,1,4),substr(partition_date,5,2),substr(partition_date,7,2)) as partition_date SELECT concat_ws('-',substr(partition_date,1,4),substr(partition_date,5,2),substr(partition_date,7,2)) as partition_date
,cl_id as device_id ,cl_id as device_id
FROM online.bl_hdfs_maidian_updates FROM online.bl_hdfs_maidian_updates
where partition_date>='${start_date}' and partition_date<=regexp_replace(DATE_SUB(current_date,1) ,'-','') where partition_date>=REGEXP_REPLACE(trunc(date_sub(current_date(),1),'MM'),'-','')
and partition_date<=regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND action = 'page_view' AND action = 'page_view'
AND page_name='home' AND page_name='home'
group by concat_ws('-',substr(partition_date,1,4),substr(partition_date,5,2),substr(partition_date,7,2)),cl_id,params['card_id'] group by concat_ws('-',substr(partition_date,1,4),substr(partition_date,5,2),substr(partition_date,7,2)),cl_id,params['card_id']
...@@ -117,7 +120,8 @@ FROM ...@@ -117,7 +120,8 @@ FROM
,params['card_id'] as card_id ,params['card_id'] as card_id
,count(distinct array(params['card_id'],app_session_id)) as click_pv ,count(distinct array(params['card_id'],app_session_id)) as click_pv
FROM online.bl_hdfs_maidian_updates FROM online.bl_hdfs_maidian_updates
where partition_date>='${start_date}' and partition_date<=regexp_replace(DATE_SUB(current_date,1) ,'-','') where partition_date>=REGEXP_REPLACE(trunc(date_sub(current_date(),1),'MM'),'-','')
and partition_date<=regexp_replace(DATE_SUB(current_date,1) ,'-','')
and action='on_click_card' and action='on_click_card'
and page_name='home' and page_name='home'
and params['card_type']='card' and params['card_type']='card'
...@@ -133,7 +137,8 @@ FROM ...@@ -133,7 +137,8 @@ FROM
,params['business_id'] as card_id ,params['business_id'] as card_id
,count(distinct array(params['card_id'],app_session_id)) as click_pv ,count(distinct array(params['card_id'],app_session_id)) as click_pv
FROM online.bl_hdfs_maidian_updates FROM online.bl_hdfs_maidian_updates
where partition_date>='${start_date}' and partition_date<=regexp_replace(DATE_SUB(current_date,1) ,'-','') where partition_date>=REGEXP_REPLACE(trunc(date_sub(current_date(),1),'MM'),'-','')
and partition_date<=regexp_replace(DATE_SUB(current_date,1) ,'-','')
and action='page_view' and action='page_view'
and (referrer in ('home') or and (referrer in ('home') or
(params['referrer_link'] like '%[%' and (params['referrer_link'] like '%[%' and
...@@ -155,7 +160,7 @@ FROM ...@@ -155,7 +160,7 @@ FROM
when page_name in ('post_detail','user_post_detail','doctor_post_detail') THEN 'post' when page_name in ('post_detail','user_post_detail','doctor_post_detail') THEN 'post'
when page_name in ('answer_detail') THEN 'answer' end content_type when page_name in ('answer_detail') THEN 'answer' end content_type
FROM ONLINE.BL_HDFS_MAIDIAN_UPDATES FROM ONLINE.BL_HDFS_MAIDIAN_UPDATES
WHERE PARTITION_DATE >= '${start_date}' WHERE PARTITION_DATE >= REGEXP_REPLACE(trunc(date_sub(current_date(),1),'MM'),'-','')
and (referrer='home' or and (referrer='home' or
(params['referrer_link'] like '%[%' and (params['referrer_link'] like '%[%' and
json_split(params['referrer_link'])[size(json_split(params['referrer_link']))-1]='home')) json_split(params['referrer_link'])[size(json_split(params['referrer_link']))-1]='home'))
...@@ -173,7 +178,7 @@ FROM ...@@ -173,7 +178,7 @@ FROM
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','') WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND is_spam = 'false' --排除疑似广告 AND is_spam = 'false' --排除疑似广告
and is_online='true' and is_online='true'
and regexp_replace(substr(reply_date,1,10),'-','') >= '${start_date}' and regexp_replace(substr(reply_date,1,10),'-','') >= REGEXP_REPLACE(trunc(date_sub(current_date(),1),'MM'),'-','')
group by id,problem_id,user_id,reply_date group by id,problem_id,user_id,reply_date
)t1 )t1
JOIN JOIN
...@@ -197,7 +202,7 @@ FROM ...@@ -197,7 +202,7 @@ FROM
AND answer_id is not NULL AND answer_id is not NULL
and is_online='true' and is_online='true'
and is_spam = 'false' --排除疑似广告 and is_spam = 'false' --排除疑似广告
and regexp_replace(substr(create_time,1,10),'-','') >= '${start_date}' and regexp_replace(substr(create_time,1,10),'-','') >= REGEXP_REPLACE(trunc(date_sub(current_date(),1),'MM'),'-','')
group by answer_id,user_id,create_time group by answer_id,user_id,create_time
UNION ALL UNION ALL
...@@ -206,7 +211,7 @@ FROM ...@@ -206,7 +211,7 @@ FROM
SELECT tractate_id as content_id,'post' as type,user_id,regexp_replace(substr(create_time,1,10),'-','') as create_date SELECT tractate_id as content_id,'post' as type,user_id,regexp_replace(substr(create_time,1,10),'-','') as create_date
FROM online.tl_hdfs_api_tractate_reply_view FROM online.tl_hdfs_api_tractate_reply_view
WHERE partition_date =regexp_replace(DATE_SUB(current_date,1) ,'-','') WHERE partition_date =regexp_replace(DATE_SUB(current_date,1) ,'-','')
and regexp_replace(substr(create_time,1,10),'-','') >= '${start_date}' and regexp_replace(substr(create_time,1,10),'-','') >= REGEXP_REPLACE(trunc(date_sub(current_date(),1),'MM'),'-','')
and is_online='true' and is_online='true'
group by tractate_id,user_id,create_time group by tractate_id,user_id,create_time
)b )b
......
...@@ -109,9 +109,11 @@ FROM ...@@ -109,9 +109,11 @@ FROM
LEFT JOIN LEFT JOIN
(SELECT code,is_ai_channel,partition_day (SELECT code,is_ai_channel,partition_day
FROM DIM.DIM_AI_CHANNEL_ZP_NEW FROM DIM.DIM_AI_CHANNEL_ZP_NEW
WHERE partition_day>= '${start_date}' AND partition_day <= regexp_replace(DATE_SUB(current_date,1) ,'-','')) tmp WHERE partition_day>= REGEXP_REPLACE(trunc(date_sub(current_date(),1),'MM'),'-','')
AND partition_day <= regexp_replace(DATE_SUB(current_date,1) ,'-','')) tmp
ON partition_date=tmp.partition_day AND first_channel_source_type=code ON partition_date=tmp.partition_day AND first_channel_source_type=code
WHERE partition_date >= '${start_date}' and partition_date <= regexp_replace(DATE_SUB(current_date,1) ,'-','') WHERE partition_date >= REGEXP_REPLACE(trunc(date_sub(current_date(),1),'MM'),'-','')
and partition_date <= regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND active_type IN ('1','2','4') AND active_type IN ('1','2','4')
AND first_channel_source_type not IN ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3' AND first_channel_source_type not IN ('yqxiu1','yqxiu2','yqxiu3','yqxiu4','yqxiu5','mxyc1','mxyc2','mxyc3'
,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang' ,'wanpu','jinshan','jx','maimai','zhuoyi','huatian','suopingjingling','mocha','mizhe','meika','lamabang'
...@@ -149,7 +151,7 @@ FROM ...@@ -149,7 +151,7 @@ FROM
,count(distinct CASE WHEN page_name='search_result_post' THEN array(params['card_id']) END) as post_click_pv ,count(distinct CASE WHEN page_name='search_result_post' THEN array(params['card_id']) END) as post_click_pv
,count(distinct CASE WHEN page_name='search_result_wiki' THEN array(params['card_id']) END) as wiki_click_pv ,count(distinct CASE WHEN page_name='search_result_wiki' THEN array(params['card_id']) END) as wiki_click_pv
FROM online.bl_hdfs_maidian_updates FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= '${start_date}' WHERE partition_date >= REGEXP_REPLACE(trunc(date_sub(current_date(),1),'MM'),'-','')
AND partition_date <=regexp_replace(DATE_SUB(current_date,1) ,'-','') AND partition_date <=regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND ((action = 'on_click_card' AND params['card_content_type'] in ('answer','diary','question','qa', AND ((action = 'on_click_card' AND params['card_content_type'] in ('answer','diary','question','qa',
'wiki_collect','wiki_item','wiki_brand','wiki_material','wiki_drug','wiki_instrument')) 'wiki_collect','wiki_item','wiki_brand','wiki_material','wiki_drug','wiki_instrument'))
...@@ -178,7 +180,7 @@ FROM ...@@ -178,7 +180,7 @@ FROM
,count(distinct CASE WHEN page_name in ('post_detail','user_post_detail','doctor_post_detail') and referrer='search_result_post' THEN time_str END) as post_click_pv ,count(distinct CASE WHEN page_name in ('post_detail','user_post_detail','doctor_post_detail') and referrer='search_result_post' THEN time_str END) as post_click_pv
,count(distinct CASE WHEN page_name in ('wiki_detail','wiki_collect','product_detail','wiki_brand') THEN time_str end)as wiki_click_pv ,count(distinct CASE WHEN page_name in ('wiki_detail','wiki_collect','product_detail','wiki_brand') THEN time_str end)as wiki_click_pv
FROM online.bl_hdfs_maidian_updates FROM online.bl_hdfs_maidian_updates
WHERE partition_date >= '${start_date}' WHERE partition_date >= REGEXP_REPLACE(trunc(date_sub(current_date(),1),'MM'),'-','')
AND partition_date <=regexp_replace(DATE_SUB(current_date,1) ,'-','') AND partition_date <=regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND action='page_view' AND action='page_view'
AND referrer in ('search_result_diary','search_result_question_answer','search_result_post','search_result_wiki') AND referrer in ('search_result_diary','search_result_question_answer','search_result_post','search_result_wiki')
...@@ -206,7 +208,7 @@ FROM ...@@ -206,7 +208,7 @@ FROM
when page_name in ('post_detail','user_post_detail','doctor_post_detail') THEN 'post' when page_name in ('post_detail','user_post_detail','doctor_post_detail') THEN 'post'
end content_type end content_type
FROM ONLINE.BL_HDFS_MAIDIAN_UPDATES FROM ONLINE.BL_HDFS_MAIDIAN_UPDATES
WHERE PARTITION_DATE >= '${start_date}' WHERE PARTITION_DATE >= REGEXP_REPLACE(trunc(date_sub(current_date(),1),'MM'),'-','')
and (referrer in ('search_result_diary') or and (referrer in ('search_result_diary') or
(params['referrer_link'] like '%[%' and (params['referrer_link'] like '%[%' and
json_split(params['referrer_link'])[size(json_split(params['referrer_link']))-1] in ('search_result_diary'))) json_split(params['referrer_link'])[size(json_split(params['referrer_link']))-1] in ('search_result_diary')))
...@@ -223,7 +225,7 @@ FROM ...@@ -223,7 +225,7 @@ FROM
WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','') WHERE partition_date = regexp_replace(DATE_SUB(current_date,1) ,'-','')
AND is_spam = 'false' --排除疑似广告 AND is_spam = 'false' --排除疑似广告
and is_online='true' and is_online='true'
and regexp_replace(substr(reply_date,1,10),'-','') >= '${start_date}' and regexp_replace(substr(reply_date,1,10),'-','') >= REGEXP_REPLACE(trunc(date_sub(current_date(),1),'MM'),'-','')
group by id,problem_id,user_id,reply_date group by id,problem_id,user_id,reply_date
)t1 )t1
JOIN JOIN
...@@ -242,7 +244,7 @@ FROM ...@@ -242,7 +244,7 @@ FROM
SELECT tractate_id as content_id,'post' as type,user_id,regexp_replace(substr(create_time,1,10),'-','') as create_date SELECT tractate_id as content_id,'post' as type,user_id,regexp_replace(substr(create_time,1,10),'-','') as create_date
FROM online.tl_hdfs_api_tractate_reply_view FROM online.tl_hdfs_api_tractate_reply_view
WHERE partition_date =regexp_replace(DATE_SUB(current_date,1) ,'-','') WHERE partition_date =regexp_replace(DATE_SUB(current_date,1) ,'-','')
and regexp_replace(substr(create_time,1,10),'-','') >= '${start_date}' and regexp_replace(substr(create_time,1,10),'-','') >= REGEXP_REPLACE(trunc(date_sub(current_date(),1),'MM'),'-','')
and is_online='true' and is_online='true'
group by tractate_id,user_id,create_time group by tractate_id,user_id,create_time
)b )b
...@@ -268,7 +270,7 @@ FROM ...@@ -268,7 +270,7 @@ FROM
( (
select * select *
FROM ONLINE.BL_HDFS_MAIDIAN_UPDATES FROM ONLINE.BL_HDFS_MAIDIAN_UPDATES
WHERE PARTITION_DATE >= '${start_date}' WHERE PARTITION_DATE >= REGEXP_REPLACE(trunc(date_sub(current_date(),1),'MM'),'-','')
and (referrer in ('search_result_question_answer') or and (referrer in ('search_result_question_answer') or
(params['referrer_link'] like '%[%' and (params['referrer_link'] like '%[%' and
json_split(params['referrer_link'])[size(json_split(params['referrer_link']))-1] in ('search_result_question_answer'))) json_split(params['referrer_link'])[size(json_split(params['referrer_link']))-1] in ('search_result_question_answer')))
...@@ -285,7 +287,7 @@ FROM ...@@ -285,7 +287,7 @@ FROM
AND answer_id is not NULL AND answer_id is not NULL
and is_online='true' and is_online='true'
and is_spam = 'false' --排除疑似广告 and is_spam = 'false' --排除疑似广告
and regexp_replace(substr(create_time,1,10),'-','') >= '${start_date}' and regexp_replace(substr(create_time,1,10),'-','') >= REGEXP_REPLACE(trunc(date_sub(current_date(),1),'MM'),'-','')
group by answer_id,user_id,create_time group by answer_id,user_id,create_time
)b )b
...@@ -312,7 +314,7 @@ FROM ...@@ -312,7 +314,7 @@ FROM
select *,case when page_name in ('post_detail','user_post_detail','doctor_post_detail') THEN 'post' select *,case when page_name in ('post_detail','user_post_detail','doctor_post_detail') THEN 'post'
end content_type end content_type
FROM ONLINE.BL_HDFS_MAIDIAN_UPDATES FROM ONLINE.BL_HDFS_MAIDIAN_UPDATES
WHERE PARTITION_DATE >= '${start_date}' WHERE PARTITION_DATE >= REGEXP_REPLACE(trunc(date_sub(current_date(),1),'MM'),'-','')
and (referrer in ('search_result_post') or and (referrer in ('search_result_post') or
(params['referrer_link'] like '%[%' and (params['referrer_link'] like '%[%' and
json_split(params['referrer_link'])[size(json_split(params['referrer_link']))-1] in ('search_result_post'))) json_split(params['referrer_link'])[size(json_split(params['referrer_link']))-1] in ('search_result_post')))
...@@ -324,7 +326,7 @@ FROM ...@@ -324,7 +326,7 @@ FROM
SELECT tractate_id as content_id,'post' as type,user_id,regexp_replace(substr(create_time,1,10),'-','') as create_date SELECT tractate_id as content_id,'post' as type,user_id,regexp_replace(substr(create_time,1,10),'-','') as create_date
FROM online.tl_hdfs_api_tractate_reply_view FROM online.tl_hdfs_api_tractate_reply_view
WHERE partition_date =regexp_replace(DATE_SUB(current_date,1) ,'-','') WHERE partition_date =regexp_replace(DATE_SUB(current_date,1) ,'-','')
and regexp_replace(substr(create_time,1,10),'-','') >= '${start_date}' and regexp_replace(substr(create_time,1,10),'-','') >= REGEXP_REPLACE(trunc(date_sub(current_date(),1),'MM'),'-','')
and is_online='true' and is_online='true'
group by tractate_id,user_id,create_time group by tractate_id,user_id,create_time
)b )b
...@@ -351,7 +353,7 @@ FROM ...@@ -351,7 +353,7 @@ FROM
select *,case when page_name in ('wiki_detail','wiki_collect','product_detail','wiki_brand') THEN 'wiki' select *,case when page_name in ('wiki_detail','wiki_collect','product_detail','wiki_brand') THEN 'wiki'
end content_type end content_type
FROM ONLINE.BL_HDFS_MAIDIAN_UPDATES FROM ONLINE.BL_HDFS_MAIDIAN_UPDATES
WHERE PARTITION_DATE >= '${start_date}' WHERE PARTITION_DATE >= REGEXP_REPLACE(trunc(date_sub(current_date(),1),'MM'),'-','')
and (referrer in ('search_result_wiki') or and (referrer in ('search_result_wiki') or
(params['referrer_link'] like '%[%' and (params['referrer_link'] like '%[%' and
json_split(params['referrer_link'])[size(json_split(params['referrer_link']))-1] in ('search_result_wiki'))) json_split(params['referrer_link'])[size(json_split(params['referrer_link']))-1] in ('search_result_wiki')))
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment