datax MySql --> Hive实现
配置文件
{
"job": {
"setting": {
"speed": {
"channel":3
},
"errorLimit": {
"record": 0,
"percentage": 0.02
}
},
"content": [
{
"reader": {
"name": "mysqlreader",
"parameter": {
"username": "root",
"password": "123456",
"column": [
"id",
"name",
"age",
"sex",
"clazz"
],
"splitPk": "id",
"connection": [
{
"table": [
"students"
],
"jdbcUrl": [
"jdbc:mysql://master:3306/bigdata"
]
}
]
}
},
"writer": {
"name": "hdfswriter",
"parameter": {
"defaultFS": "hdfs://master:9000",
"fileType": "text",
"path": "/user/hive/warehouse/bigdata32.db/students",
"fileName": "students",
"column": [
{
"name": "id",
"type": "INT"
},
{
"name": "name",
"type": "string"
},
{
"name": "age",
"type": "INT"
},
{
"name": "sex",
"type": "string"
},
{
"name": "clazz",
"type": "string"
}
],
"writeMode": "append",
"fieldDelimiter": ","
}
}
}
]
}
}
hive 建表
create table IF NOT EXISTS students
(
id bigint,
name string,
age int,
sex string,
clazz string
)
ROW FORMAT DELIMITED FIELDS TERMINATED BY ',';
表路径
vim MySQLToHive.json
datax.py MySQLToHive.json
成功