官方Hello入门例子
{
"job": {
"content": [
{
"reader": {
"name": "streamreader",
"parameter": {
"sliceRecordCount": 10,
"column": [
{
"type": "long",
"value": "10"
},
{
"type": "string",
"value": "hello,你好,世界-DataX"
}
]
}
},
"writer": {
"name": "streamwriter",
"parameter": {
"encoding": "UTF-8",
"print": true
}
}
}
],
"setting": {
"speed": {
"channel": 5
}
}
}
}
运行命令:
python /data/tools/datax/bin/datax.py ./hello_datax.json
java调用datax 参考:
ublic class TestDatax {
public static void main(String[] args) {
try {
WebLogs.info("start");
String windowcmd = "cmd /c python datax.py D:\\Software\\install\\Environment\\DataX\\datax\\job\\mysql2mysql.json";
WebLogs.info(windowcmd);
//.exec("你的命令",null,new File("datax安装路径"));
Process pr = Runtime.getRuntime().exec(windowcmd,null,new File("D:\\Software\\install\\Environment\\DataX\\datax\\bin"));
BufferedReader in = new BufferedReader(new InputStreamReader(pr.getInputStream()));
String line = null;
while ((line = in.readLine()) != null) {
WebLogs.info(line);
}
in.close();
pr.waitFor();
WebLogs.info("end");
} catch (Exception e) {
e.printStackTrace();
}
}
}
网上一个mysql2mysql的例子
{
"job": {
"content": [
{
"reader": {
"name": "mysqlreader",
"parameter": {
"column": [
"id",
"name"
],
"connection": [
{
"jdbcUrl": ["jdbc:mysql://127.0.0.1:3306/dq"],
"table": ["table1"]
}
],
"password": "123456",
"username": "root"
}
},
"writer": {
"name": "mysqlwriter",
"parameter": {
"column": [
"id",
"name"
],
"connection": [
{
"jdbcUrl": "jdbc:mysql://ip地址:端口/test",
"table": ["table2"]
}
],
"password": "123456",
"username": "root"
}
}
}
],
"setting": {
"speed": {
"channel": "1"
}
}
}
}
mysql到本地:
{
"job": {
"content": [
{
"reader": {
"name": "mysqlreader",
"parameter": {
"username": "root",
"password": "root",
"column": ["ID","VISIT_IP"],
"connection": [
{
"table": [
"visit_log"
],
"jdbcUrl": [
"jdbc:mysql://192.168.0.197:3306/qyyx_test"
]
}
]
}
},
"writer": {
"name": "streamwriter",
"parameter": {
"print": false,
"encoding": "UTF-8"
}
}
}
]
}
}
本地方件到本地文件:
{
"setting": {},
"job": {
"setting": {
"speed": {
"channel": 2
}
},
"content": [
{
"reader": {
"name": "txtfilereader",
"parameter": {
"path": ["/home/haiwei.luo/case00/data"],
"encoding": "UTF-8",
"column": ["*"],
"fieldDelimiter": ","
}
},
"writer": {
"name": "txtfilewriter",
"parameter": {
"path": "/home/haiwei.luo/case00/result",
"fileName": "luohw",
"writeMode": "truncate",
"format": "yyyy-MM-dd"
}
}
}
]
}
}
HDFS打印到本地控制台
{
"job": {
"setting": {
"speed": {
"channel": 3
}
},
"content": [
{
"reader": {
"name": "hdfsreader",
"parameter": {
"path": "/user/hive/warehouse/test.db/nnn/*",
"defaultFS": "hdfs://192.168.200.45:8020",
"column": ["*"],
"fileType": "orc",
"encoding": "UTF-8",
"fieldDelimiter": ","
}
},
"writer": {
"name": "streamwriter",
"parameter": {
"print": true
}
}
}
]
}
}
oracle到本地文件
{
"job": {
"content": [
{
"reader": {
"name": "mysqlreader",
"parameter": {
"username": "root",
"password": "root",
"column": ["ID","VISIT_IP","BEF_URL","NOW_URL","CORP_CODE","PROMOTE_NO","PLATFORM","COOKIE_EANBLED","USER_AGENT","APP_VERSION","APP_NAME","COLOR","SCREEN","JAVA_ENABLED","JS_VERSION","SID","CREATE_BY","CREATE_TIME","MODIFY_BY","MODIFY_TIME"],
"connection": [
{
"table": [
"visit_log"
],
"jdbcUrl": [
"jdbc:mysql://192.168.0.197:3306/qyyx_test"
]
}
]
}
},
"writer": {
"name": "txtfilewriter",
"parameter": {
"path": "/opt/result/",
"fileName": "shun",
"writeMode": "truncate",
"format": "yyyy-MM-dd"
}
}
}
],
"setting": {
"speed": {
"channel": 10
}
}
}
}
本地文件到HDFS
orcle打印到Linux
{
"job": {
"setting": {
"speed": {
"channel": 5
}
},
"content": [
{
"reader": {
"name": "oraclereader",
"parameter": {
"username": "edw_src",
"password": "123456",
"where": "",
"connection": [
{
"querySql": [
"select * from ORDER_DETAIL_BAK"
],
"jdbcUrl": [
"jdbc:oracle:thin:@192.168.0.197:1521:orcl"
]
}
]
}
},
"writer": {
"name": "streamwriter",
"parameter": {
"visible": true,
"encoding": "UTF-8"
}
}
}
]
}
}
oracle到HDFS
oracle到本地文件
{
"job": {
"setting": {
"speed": {
"channel": 200
}
},
"content": [
{
"reader": {
"name": "oraclereader",
"parameter": {
"username": "edw_src",
"password": "123456",
"where": "",
"connection": [
{
"querySql": [
"select * from ORDER_DETAIL_BAK"
],
"jdbcUrl": [
"jdbc:oracle:thin:@192.168.0.197:1521:orcl"
]
}
]
}
},
"writer": {
"name": "txtfilewriter",
"parameter": {
"path": "/opt/result/",
"fileName": "shun",
"writeMode": "truncate",
"format": "yyyy-MM-dd"
}
}
}
]
}
}