下載地址
下載地址:https://github.com/alibaba/DataX
實際使用
python datax.py --jvm="-Xms5G -Xmx5G" ../job/test.json -p "-Ddt=20190722 -Ddn=webA"
hive到mysql的配置文件
{
"job": {
"setting": {
"speed": {
"channel": 3
}
},
"content": [{
"reader": {
"name": "hdfsreader",
"parameter": {
"path": "/user/hive/warehouse/ads.db/ads_user_question_detail/dt=${dt}/dn=${dn}/*",
"hadoopConfig":{
"dfs.nameservices": "nameservice1",
"dfs.ha.namenodes.nameservice1": "namenode30,namenode37",
"dfs.namenode.rpc-address.nameservice1.namenode30": "hadoop001:8020",
"dfs.namenode.rpc-address.nameservice1.namenode37": "hadoop002:8020",
"dfs.client.failover.proxy.provider.nameservice1": "org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider"
},
"defaultFS": "hdfs://nameservice1",
"column": [{
"index": 0,
"type": "string"
},
{
"index": 1,
"type": "string"
},
{
"index": 2,
"type": "string"
},
{
"index": 3,
"type": "string"
},
{
"value": "${dt}",
"type": "string"
},
{
"value": "${dn}",
"type": "string"
}
],
"fileType": "text",
"encoding": "UTF-8",
"fieldDelimiter": "\t"
}
},
"writer": {
"name": "mysqlwriter",
"parameter": {
"writeMode": "insert",
"username": "root",
"password": "123456",
"column": [
"questionid",
"errcount",
"rightcount",
"rate",
"dt",
"dn"
],
"preSql": [
"delete from user_question_detail where dt=${dt}"
],
"connection": [{
"jdbcUrl": "jdbc:mysql://hadoop003:3306/qz_paper?useUnicode=true&characterEncoding=utf8&serverTimezone=Asia/Shanghai&useSSL=false",
"table": [
"user_question_detail"
]
}]
}
}
}]
}
}