关于大数据T+1执行流程

前提：搭建好大数据环境（hadoop hive hbase sqoop zookeeper oozie hue）

1.将所有数据库的数据汇总到hive (这里有三种数据源 ORACLE MYSQL SEQSERVER)

全量数据抽取示例：

ORACLE（注意表名必须大写！！！）

sqoop import --connect jdbc:oracle:thin:@//10.11.22.33:1521/LPDR.china.com.hh --username root --password 1234 
--table DATABASENAME.TABLENAME --hive-overwrite --hive-import --hive-database bgda_hw --hive-table lp_tablename 
--target-dir /user/hadouser_hw/tmp/lp_tablename --delete-target-dir 
--null-non-string '\N' --null-string '\N' 
--hive-drop-import-delims --verbose --m 1

MYSQL:

sqoop import --connect jdbc:mysql://10.33.44.55:3306/DATABASEBANE --username ROOT --password 1234 
--query 'select * from DEMO t where t.DATE1 < current_date and $CONDITIONS' 
--hive-overwrite --hive-import --hive-database bgda_hw --hive-table DEMO 
--target-dir /user/hadouser_hw/tmp/DEMO --delete-target-dir 
--null-non-string '\N' --null-string '\N' 
--hive-drop-import-delims --verbose --m 1

SQLSERVER:

sqoop import --connect 'jdbc:sqlserver://10.55.66.15:1433;username=ROOT;password=ROOT;database=db_DD' 
--query 'select * from TABLE t where t.tasktime < convert(varchar(10),getdate(),120) and $CONDITIONS' 
--hive-overwrite --hive-import --hive-database bgda_hw --hive-table TABLENAME 
--target-dir /user/hadouser_hw/tmp/TABLENAME --delete-target-dir 
--null-non-string '\N' --null-string '\N' 
--hive-drop-import-delims --verbose --m 1

2.　　编写hive脚本，对数据进行处理

说明：

data 存储T+1跑出来的数据信息，只存一天的数据量

data_bak : 存储所有的数据信息

（初始化脚本）

use bgda_hw;
set hive.auto.convert.join=false;

drop table data_bak;
create table data_bak(
 scanopt   string 
 ,scanoptname   string 
 ,statisdate   string 
) row format delimited fields terminated by '01'; 



insert overwrite table data_bak
SELECT 
a.scanopt 
,x0.name  as scanoptname
,to_date(a.scandate) as statisdate
from bgda_hw.scan  a 
left outer join bgda_hw.user x0 on x0.userid = a.scanopt 
where 1=1  
and datediff(a.scandate,'2019-01-01' )>=0
and datediff(a.scandate,'2019-09-20' )<0
GROUP BY  a.scanopt,x0.name,a.scandate
order by a.scandate
;

（t+1脚本）

use bgda_hw; 
set hive.auto.convert.join=false;

drop table data;
create table data(
 scanopt   string 
 ,scanoptname   string 
 ,statisdate   string 
) row format delimited fields terminated by '01'; 


insert overwrite table data
SELECT 
a.scanopt 
,x0.name  as scanoptname
,to_date(a.scandate) as statisdate
from bgda_hw.scan  a 
left outer join bgda_hw.user x0 on x0.userid = a.scanopt 
where 1=1 
and a.scandate<date_add(from_unixtime(unix_timestamp(),'yyyy-MM-dd'),0)
and a.scandate>=date_add(from_unixtime(unix_timestamp(),'yyyy-MM-dd'),-1)
GROUP BY  a.scanopt,x0.name,a.scandate
order by a.scandate
;

insert into table data_bak
select * from data
;

3.将结果数据抽取到结果库里

sqoop export 
--connect jdbc:mysql://10.6.11.11:3306/report 
--username root 
--password 1234 
--table data 
--export-dir /user/hive/warehouse/bgda_hw.db/data 
--columns scanopt,scanoptname,statisdate 
--fields-terminated-by '01' 
--lines-terminated-by '
' 
--input-null-string '\N' 
--input-null-non-string '\N'

抽數腳本示例（腳本中的insert.hql 則是上方定義的hive腳本信息）

#!/bin/bash

export CDH_PARCEL=/var/opt/cloudera/parcels/CDH/bin/
export PATH=${PATH}:${CDH_PARCEL}
export PYTHON_EGG_CACHE=~/.python-eggs

#kinit to user hadouser_hw
kinit -kt hadouser_hw.keytab hadouser@HADOOP-AD-ROOT.DC

echo "$CDH_PARCEL: {CDH_PARCEL} "
echo "$PATH: {PATH} "
echo "$PYTHON_EGG_CACHE: {PYTHON_EGG_CACHE} "

#sqoop import full data from mssql database to hdfs
set -x

beeline -u "jdbc:hive2://10.20.33.44:10000/default;principal=hive/sssssss012@HADOOP-AD-ROOT.DC" -f insert.hql

# 将数据抽取到mysql 结果数据 原数据
sqoop export 
--connect jdbc:mysql://10.6.11.15:3306/report 
--username root 
--password 1234 
--table rs_kpitime_psdata 
--export-dir /user/hive/warehouse/bgda_hw_stg.db/rs_kpitime_psdata_bak 
--columns aplcustno,isapprv,statisdate,statisyear,statisquarter,statismonth,countdate 
--fields-terminated-by '01' 
--lines-terminated-by '
' 
--input-null-string '\N' 
--input-null-non-string '\N'

ret=$?
set +x

if [[ $ret -eq 0 ]];then
  echo "insert table OK"
else
  echo "insert table failed!!!Please check!!!"
  exit $ret
fi