1.导出脚本
#!/bin/bash
#cdh
export HADOOP_USER_NAME=hive
db_name=gmall
export_data() {
/opt/module/sqoop/bin/sqoop export \
--connect "jdbc:mysql://hadoop102:3306/${db_name}?useUnicode=true&characterEncoding=utf-8" \
--username root \
--password 000000 \
--table $1 \
--num-mappers 1 \
--export-dir /warehouse/$db_name/ads/$1 \
--input-fields-terminated-by "\t" \
--update-mode allowinsert \
--update-key $2 \
--input-null-string '\\N' \
--input-null-non-string '\\N'
}
case $1 in
"ads_uv_count")
export_data "ads_uv_count" "dt"
;;
"ads_user_action_convert_day")
export_data "ads_user_action_convert_day" "dt"
;;
"ads_gmv_sum_day")
export_data "ads_gmv_sum_day" "dt"
;;
"all")
export_data "ads_uv_count" "dt"
export_data "ads_user_action_convert_day" "dt"
export_data "ads_gmv_sum_day" "dt"
;;
esac
关于导出update还是insert的问题
–update-mode:
- updateonly 只更新,无法插入新数据
- allowinsert 允许新增
–update-key:允许更新的情况下,指定哪些字段匹配视为同一条数据,进行更新而不增加。多个字段用逗号分隔。
–input-null-string和–input-null-non-string:分别表示,将字符串列和非字符串列的空串和“null”转义。
2.导入脚本
#!/bin/bash
#cdh
export HADOOP_USER_NAME=hive
db_date=$2
echo $db_date
db_name=gmall
import_data() {
/opt/module/sqoop/bin/sqoop import \
--connect jdbc:mysql://hadoop102:3306/$db_name \
--username root \
--password 000000 \
--target-dir /origin_data/$db_name/db/$1/$db_date \
--delete-target-dir \
--num-mappers 1 \
--fields-terminated-by "\t" \
--query "$2"' and $CONDITIONS;'
}
import_sku_info(){
import_data "sku_info" "select
id, spu_id, price, sku_name, sku_desc, weight, tm_id,
category3_id, create_time
from sku_info where 1=1"
}
import_user_info(){
import_data "user_info" "select
id, name, birthday, gender, email, user_level,
create_time
from user_info where 1=1"
}
import_base_category1(){
import_data "base_category1" "select
id, name from base_category1 where 1=1"
}
import_base_category2(){
import_data "base_category2" "select
id, name, category1_id from base_category2 where 1=1"
}
import_base_category3(){
import_data "base_category3" "select id, name, category2_id from base_category3 where 1=1"
}
import_order_detail(){
import_data "order_detail" "select
od.id,
order_id,
user_id,
sku_id,
sku_name,
order_price,
sku_num,
o.create_time
from order_info o, order_detail od
where o.id=od.order_id
and DATE_FORMAT(create_time,'%Y-%m-%d')='$db_date'"
}
import_payment_info(){
import_data "payment_info" "select
id,
out_trade_no,
order_id,
user_id,
alipay_trade_no,
total_amount,
subject,
payment_type,
payment_time
from payment_info
where DATE_FORMAT(payment_time,'%Y-%m-%d')='$db_date'"
}
import_order_info(){
import_data "order_info" "select
id,
total_amount,
order_status,
user_id,
payment_way,
out_trade_no,
create_time,
operate_time
from order_info
where (DATE_FORMAT(create_time,'%Y-%m-%d')='$db_date' or DATE_FORMAT(operate_time,'%Y-%m-%d')='$db_date')"
}
case $1 in
"base_category1")
import_base_category1
;;
"base_category2")
import_base_category2
;;
"base_category3")
import_base_category3
;;
"order_info")
import_order_info
;;
"order_detail")
import_order_detail
;;
"sku_info")
import_sku_info
;;
"user_info")
import_user_info
;;
"payment_info")
import_payment_info
;;
"all")
import_base_category1
import_base_category2
import_base_category3
import_order_info
import_order_detail
import_sku_info
import_user_info
import_payment_info
;;
esac
1)问题描述:执行Sqoop导入数据脚本时,发生如下异常
java.sql.SQLException: Streaming result set com.mysql.jdbc.RowDataDynamic@65d6b83b is still active. No statements may be issued when any streaming result sets are open and in use on a given connection. Ensure that you have called .close() on any active streaming result sets before attempting more queries.
at com.mysql.jdbc.SQLError.createSQLException(SQLError.java:930)
at com.mysql.jdbc.MysqlIO.checkForOutstandingStreamingData(MysqlIO.java:2646)
at com.mysql.jdbc.MysqlIO.sendCommand(MysqlIO.java:1861)
at com.mysql.jdbc.MysqlIO.sqlQueryDirect(MysqlIO.java:2101)
at com.mysql.jdbc.ConnectionImpl.execSQL(ConnectionImpl.java:2548)
at com.mysql.jdbc.ConnectionImpl.execSQL(ConnectionImpl.java:2477)
at com.mysql.jdbc.StatementImpl.executeQuery(StatementImpl.java:1422)
at com.mysql.jdbc.ConnectionImpl.getMaxBytesPerChar(ConnectionImpl.java:2945)
at com.mysql.jdbc.Field.getMaxBytesPerCharacter(Field.java:582)
2)问题解决方案:增加如下导入参数
--driver com.mysql.jdbc.Driver \