# -*- coding:UTF-8 -*-
# @Time  : 2020/8/21 16:43
# @File  : search_strategy_d.py
# @email : litao@igengmei.com
# @author : litao

import hashlib
import json

import pymysql
import xlwt, datetime
import redis
# from pyhive import hive
from maintenance.func_send_email_with_file import send_file_email
from typing import Dict, List
from elasticsearch_7 import Elasticsearch
from elasticsearch_7.helpers import scan
import sys
import time
from pyspark import SparkConf
from pyspark.sql import SparkSession, DataFrame
from pyspark.sql.functions import lit
import pytispark.pytispark as pti

# db = pymysql.connect(host='172.16.40.158', port=4000, user='st_user', passwd='aqpuBLYzEV7tML5RPsN1pntUzFy',
#                      db='jerry_prod')
# cursor = db.cursor()


startTime = time.time()
sparkConf = SparkConf()
sparkConf.set("spark.sql.crossJoin.enabled", True)
sparkConf.set("spark.debug.maxToStringFields", "100")
sparkConf.set("spark.tispark.plan.allow_index_double_read", False)
sparkConf.set("spark.tispark.plan.allow_index_read", True)
sparkConf.set("spark.hive.mapred.supports.subdirectories", True)
sparkConf.set("spark.hadoop.mapreduce.input.fileinputformat.input.dir.recursive", True)
sparkConf.set("spark.serializer", "org.apache.spark.serializer.KryoSerializer")
sparkConf.set("mapreduce.output.fileoutputformat.compress", False)
sparkConf.set("mapreduce.map.output.compress", False)
sparkConf.set("prod.gold.jdbcuri",
              "jdbc:mysql://172.16.30.136/doris_prod?user=doris&password=o5gbA27hXHHm&rewriteBatchedStatements=true")
sparkConf.set("prod.mimas.jdbcuri",
              "jdbc:mysql://172.16.30.138/mimas_prod?user=mimas&password=GJL3UJe1Ck9ggL6aKnZCq4cRvM&rewriteBatchedStatements=true")
sparkConf.set("prod.gaia.jdbcuri",
              "jdbc:mysql://172.16.30.143/zhengxing?user=work&password=BJQaT9VzDcuPBqkd&rewriteBatchedStatements=true")
sparkConf.set("prod.tidb.jdbcuri",
              "jdbc:mysql://172.16.40.158:4000/eagle?user=st_user&password=aqpuBLYzEV7tML5RPsN1pntUzFy&rewriteBatchedStatements=true")
sparkConf.set("prod.jerry.jdbcuri",
              "jdbc:mysql://172.16.40.158:4000/jerry_prod?user=st_user&password=aqpuBLYzEV7tML5RPsN1pntUzFy&rewriteBatchedStatements=true")
sparkConf.set("prod.tispark.pd.addresses", "172.16.40.158:2379")
sparkConf.set("prod.tispark.pd.addresses", "172.16.40.170:4000")
sparkConf.set("prod.tidb.database", "jerry_prod")

spark = (SparkSession.builder.config(conf=sparkConf).config("spark.sql.extensions", "org.apache.spark.sql.TiExtensions")
         .config("spark.tispark.pd.addresses", "172.16.40.170:2379").appName(
    "LR PYSPARK TEST").enableHiveSupport().getOrCreate())

spark.sql("ADD JAR hdfs:///user/hive/share/lib/udf/brickhouse-0.7.1-SNAPSHOT.jar")
spark.sql("ADD JAR hdfs:///user/hive/share/lib/udf/hive-udf-1.0-SNAPSHOT.jar")
spark.sql("CREATE TEMPORARY FUNCTION json_map AS 'brickhouse.udf.json.JsonMapUDF'")
spark.sql("CREATE TEMPORARY FUNCTION is_json AS 'com.gmei.hive.common.udf.UDFJsonFormatCheck'")
spark.sql("CREATE TEMPORARY FUNCTION arrayMerge AS 'com.gmei.hive.common.udf.UDFArryMerge'")

task_list = []
task_days = 1

for t in range(0, task_days):
    day_num = 0 - t
    now = (datetime.datetime.now() + datetime.timedelta(days=day_num))
    last_30_day_str = (now + datetime.timedelta(days=-30)).strftime("%Y%m%d")
    today_str = now.strftime("%Y%m%d")
    yesterday_str = (now + datetime.timedelta(days=-1)).strftime("%Y%m%d")
    one_week_age_str = (now + datetime.timedelta(days=-7)).strftime("%Y%m%d")
    sql = """SELECT t3.query as query
            ,t3.device_os_type as device_type
            ,t3.active_type as active_type
            ,t3.channel as channel_type
            ,NVL(t3.search_pv,0) as 1_pv
            ,NVL(t3.search_uv,0) as 1_uv
            ,NVL(t4.hexin_card_click_pv,0) as 1_search_core_pv
            ,NVL(t4.neirong_card_click_pv,0) as 1_search_pv

    LEFT JOIN
    (
        SELECT query,active_type,device_os_type,channel,search_pv,search_uv
        FROM
        (
            SELECT query,active_type,device_os_type,channel
                    ,count(t1.cl_id) as search_pv
                    ,count(distinct t1.cl_id) as search_uv
            FROM
            (
                SELECT partition_date
                        ,params['query'] as query
                        ,cl_id
                FROM online.bl_hdfs_maidian_updates
                WHERE partition_date >= {yesterday_str} 
                AND partition_date < {today_str}
                AND action in ('do_search','search_result_click_search')
    
                UNION ALL
                SELECT partition_date,params['query'] as query,cl_id
                FROM online.bl_hdfs_maidian_updates
                WHERE partition_date >= {yesterday_str} 
                AND partition_date < {today_str}
                AND action = 'on_click_card'
                AND params['page_name']='search_home'
    
                UNION ALL
                SELECT partition_date
                        ,params['card_name'] as query
                        ,cl_id
                FROM online.bl_hdfs_maidian_updates
                WHERE partition_date >= {yesterday_str} 
                AND partition_date < {today_str}
                AND action = 'on_click_card'
                AND params['in_page_pos']='猜你喜欢'
                AND params['tab_name']='精选'
                AND params['card_type']='search_word'
               
    
                UNION ALL
                SELECT partition_date
                        ,params['card_name'] as query
                        ,cl_id
                FROM online.bl_hdfs_maidian_updates
                WHERE partition_date >= {yesterday_str} 
                AND partition_date < {today_str}
                AND action = 'on_click_card'
                AND page_name='welfare_home'
                AND params['card_type'] ='search_word'
                AND params['in_page_pos']='大家都在搜'
    
                UNION ALL
                SELECT partition_date
                        ,params['card_name'] as query
                        ,cl_id
                FROM online.bl_hdfs_maidian_updates
                WHERE partition_date >= {yesterday_str} 
                AND partition_date < {today_str}
                AND int(split(app_version,'\\.')[1]) >= 27
                AND action='on_click_card'
                AND params['card_type']='highlight_word'
            )t1
            JOIN
            (
                SELECT partition_date,device_id,t2.active_type,t2.channel,t2.device_os_type
                FROM
                (
                    SELECT
                    partition_date,m.device_id
                    ,array(device_os_type ,'合计') as device_os_type
                    ,array(case WHEN active_type = '4'  THEN '老活' 
                          WHEN active_type  in ('1','2')  then '新增' END ,'合计') as active_type 
                    ,array(CASE WHEN is_ai_channel = 'true' THEN 'AI'  ELSE '其他' END , '合计') as channel
                    FROM online.ml_device_day_active_status m
                        LEFT JOIN 
                        (SELECT code,is_ai_channel,partition_day
                         FROM DIM.DIM_AI_CHANNEL_ZP_NEW
                         WHERE partition_day>= {yesterday_str}  
                         AND partition_day < {today_str}) tmp
                        ON  m.partition_date=tmp.partition_day AND first_channel_source_type=code
                    WHERE partition_date >= {yesterday_str} 
                    AND partition_date < {today_str}
                    AND active_type in ('1','2','4')
                ) mas
                LATERAL VIEW explode(mas.channel) t2 AS channel
                LATERAL VIEW explode(mas.device_os_type) t2 AS device_os_type
                LATERAL VIEW explode(mas.active_type) t2 AS active_type
            )t2
            on t1.cl_id=t2.device_id AND t1.partition_date = t2.partition_date
            GROUP BY query,active_type,device_os_type,channel
        )t
    )t3
    on t1.query=t3.query and t1.active_type=t3.active_type and t1.device_os_type = t3.device_os_type AND t1.channel = t3.channel
    
    LEFT JOIN
    (
        SELECT t1.query,active_type,device_os_type,channel
                ,sum(hexin) as hexin_card_click_pv
                ,sum(neirong) as neirong_card_click_pv
        FROM
        (
            SELECT NVL(t2.partition_date,t3.partition_date) as partition_date
            ,NVL(t2.cl_id,t3.cl_id) as cl_id
            ,NVL(t2.query,t3.query) as query
            ,NVL(t2.pv,0) as hexin
            ,NVL(t3.pv,0) as neirong
            FROM
            (
                SELECT partition_date
                        ,params['query'] as query
                        ,cl_id
                        ,count(1) as pv
                FROM online.bl_hdfs_maidian_updates
                WHERE partition_date >= {yesterday_str} 
                AND partition_date < {today_str}
                AND ((action in ('search_result_click_recommend_item','search_result_welfare_click_item','search_result_hospital_click_item','search_result_doctor_click_item','on_click_doctor_card', 'on_click_hospital_card')
                        AND page_name in ('search_result_more','search_result_welfare','search_result_hospital','search_result_doctor'))
                 or (action = 'goto_welfare_detail' AND params [ 'from' ] = 'search_result_welfare_recommend')
                 or (action = 'on_click_card' AND params['card_content_type'] in ('service','hospital','doctor') AND page_name in ('search_result_more','search_result_welfare','search_result_hospital','search_result_doctor'))
                 or (action = 'on_click_button' AND params['button_name'] = 'check_plan' AND page_name = 'search_result_more'))
                GROUP BY partition_date
                        ,params['query']
                        ,cl_id
            )t2
            FULL JOIN
            (
                SELECT partition_date
                        ,params['query'] as query
                        ,cl_id
                        ,count(1) as pv
                FROM online.bl_hdfs_maidian_updates
                WHERE partition_date >= {yesterday_str} 
                AND partition_date < {today_str}
                AND ((action in ('on_click_topic_card','on_click_diary_card','search_result_click_infomation_item')
                        AND page_name in ('search_result_more','search_result_diary','search_result_post'))
                    or (action = 'on_click_card' AND params['card_content_type'] in ('answer','diary') AND page_name in ('search_result_more','search_result_diary','search_result_question_answer')))
                GROUP BY partition_date
                        ,params['query']
                        ,cl_id		
            )t3
            on t3.partition_date=t2.partition_date
                AND t3.query=t2.query
                AND t3.cl_id=t2.cl_id
        )t1
        JOIN
        (
            SELECT partition_date,device_id,t2.active_type,t2.channel,t2.device_os_type
            FROM
            (
                SELECT
                    partition_date,m.device_id
                    ,array(device_os_type ,'合计') as device_os_type
                    ,array(case WHEN active_type = '4'  THEN '老活' 
                          WHEN active_type  in ('1','2')  then '新增' END ,'合计') as active_type 
                    ,array(CASE WHEN is_ai_channel = 'true' THEN 'AI'  ELSE '其他' END , '合计') as channel
                    FROM online.ml_device_day_active_status m
                        LEFT JOIN 
                        (SELECT code,is_ai_channel,partition_day
                         FROM DIM.DIM_AI_CHANNEL_ZP_NEW
                         WHERE partition_day>= {yesterday_str}  
                         AND partition_day < {today_str}) tmp
                        ON  m.partition_date=tmp.partition_day AND first_channel_source_type=code
                    WHERE partition_date >= {yesterday_str} 
                    AND partition_date < {today_str}
                    AND active_type in ('1','2','4')
            ) mas
            LATERAL VIEW explode(mas.channel) t2 AS channel
            LATERAL VIEW explode(mas.device_os_type) t2 AS device_os_type
            LATERAL VIEW explode(mas.active_type) t2 AS active_type
        )dev
        on t1.cl_id=dev.device_id and t1.partition_date = dev.partition_date
        GROUP BY t1.query,active_type,device_os_type,channel
    )t4
    on t1.query=t4.query and t1.active_type=t4.active_type and t1.device_os_type = t4.device_os_type AND t1.channel = t4.channel
    
    
""".format(today_str=today_str,yesterday_str=yesterday_str,)
    device_df = spark.sql(sql)
    device_df.createOrReplaceTempView("data_table")


    collects_sql = """
    SELECT *,if(NVL(sum(1_uv),0) <> 0 ,concat(cast((NVL(sum(1_search_core_pv),0)/NVL(sum(1_uv),0)) as decimal(18,2)),'') , '-') as 1_core_pv_division_uv 
    ,if(NVL(sum(1_uv),0) <> 0 ,concat(cast((NVL(sum(1_search_pv),0)/NVL(sum(1_uv),0)) as decimal(18,2)),'') , '-') as 1_pv_division_uv
    FROM data_table GROUP BY device_type,active_type,channel_type
    """
    finnal_df = spark.sql(collects_sql)

    finnal_df.show(1, False)
    sql_res = finnal_df.collect()
    for res in sql_res:
        print(res)