Datax执行命令
执行命令:
python /opt/installs/datax/datax.py /opt/installs/hdfs2ftp.json
python /opt/installs/datax/datax.py -r ftpreader -w hdfswriter
通过浏览器可以进行dataxweb的访问,具体地址如下:
http://hadoop13:9527/index.html
mysql2mysql
{
"job": {
"content": [
{
"reader": {
"name": "mysqlreader",
"parameter": { "encoding": "UTF-8",
"column": ["uid","nick_name","achievement","level","job","register_time"],
"connection": [
{
"jdbcUrl": ["jdbc:mysql://hadoop10:3306/sqoop?characterEncoding=UTF-8"],
"table": ["user_info"]
}
],
"password": "123456",
"username": "root"
}
},
"writer": {
"name": "mysqlwriter",
"parameter": { "encoding": "UTF-8",
"column": ["uid","nick_name","achievement","level","job","register_time"],
"connection": [
{
"jdbcUrl": "jdbc:mysql://hadoop13:3306/datax?characterEncoding=UTF-8",
"table": ["user_info"]
}
],
"password": "123456",
"preSql": ["truncate table user_info"],
"session": [],
"username": "root",
"writeMode": "insert"
}
}
}
],
"setting": {
"speed": {
"channel": "1"
}
}
}
}
mysql2hdfs
{
"job": {
"content": [
{
"reader": {
"name": "mysqlreader",
"parameter": {
"connection": [
{
"jdbcUrl": ["jdbc:mysql://hadoop10:3306/sqoop?characterEncoding=UTF-8"],
"querySql": [
" select device_id,profile,blog_url from user_submit;"
]
}
],
"password": "123456",
"username": "root",
}
},
"writer": {
"name": "hdfswriter",
"parameter": {
"encoding": "UTF-8",
"column": [{
"name": "d1",
"type": "STRING"
},
{
"name": "p1",
"type": "STRING"
} ,
{
"name": "b1",
"type": "STRING"
}
],
"compress": "",
"defaultFS": "hdfs://hadoop10:9000",
"fieldDelimiter": "\t",
"fileName": "user_submit",
"fileType": "text",
"path": "/in/datax/",
"writeMode": "append"
}
}
}
],
"setting": {
"speed": {
"channel": "2"
}
}
}
}
mysql2HaHdfs
{
"job": {
"content": [
{
"reader": {
"name": "mysqlreader",
"parameter": {
"connection": [
{
"jdbcUrl": ["jdbc:mysql://hadoop10:3306/sqoop?characterEncoding=UTF-8"],
"querySql": [
"select device_id,profile,blog_url from user_submit;"
]
}
],
"password": "123456",
"username": "root",
}
},
"writer": {
"name": "hdfswriter",
"parameter": {
"column": [{
"name": "d1",
"type": "STRING"
},
{
"name": "p1",
"type": "STRING"
} ,
{
"name": "b1",
"type": "STRING"
}
],
"compress": "",
"defaultFS": "hdfs://hdfs-cluster",
"hadoopConfig":{
"dfs.nameservices": "hdfs-cluster",
"dfs.ha.namenodes.hdfs-cluster": "nn1,nn2",
"dfs.namenode.rpc-address.hdfs-cluster.nn1": "hadoop11:9000",
"dfs.namenode.rpc-address.hdfs-cluster.nn2": "hadoop12:9000",
"dfs.client.failover.proxy.provider.hdfs-cluster": "org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider"
},
"fieldDelimiter": "\t",
"fileName": "mysql2HA",
"fileType": "text",
"path": "/input/datax",
"writeMode": "append"
}
}
}
],
"setting": {
"speed": {
"channel": "3"
}
}
}
}
mysql2ftp
{
"job": {
"setting": {
"speed": {
"channel": 2
}
},
"content": [
{
"reader": {
"name": "mysqlreader",
"parameter": {
"connection": [
{
"jdbcUrl": ["jdbc:mysql://hadoop10:3306/sqoop"],
"querySql": [
"select device_id,profile,blog_url from user_submit;"
]
}
],
"password": "123456",
"username": "root",
}
},
"writer": {
"name": "ftpwriter",
"parameter": {
"protocol": "sftp",
"host": "hadoop10",
"port": 22,
"username": "root",
"password": "123456",
"timeout": "60000",
"connectPattern": "PASV",
"path": "/opt/data/datax",
"fileName": "sqoop_mysql2ftp",
"writeMode": "truncate",
"fieldDelimiter": "\t",
"encoding": "UTF-8",
"nullFormat": "\\N",
"dateFormat": "yyyy-MM-dd",
"fileFormat": "csv",
"suffix": ".csv",
"header": []
}
}
}
]
}
}
hdfs2mysql
{
"job": {
"setting": {
"speed": {
"channel": 2
}
},
"content": [
{
"reader": {
"name": "hdfsreader",
"parameter": {
"path": "/in/datax/user_submit*",
"defaultFS": "hdfs://hadoop10:9000",
"column": [
{
"index": 0,
"type": "string"
},
{
"index": 1,
"type": "string"
},
{
"index": 2,
"type": "string"
}
],
"fileType": "text",
"encoding": "UTF-8",
"fieldDelimiter": "\t"
}
},
"writer": {
"name": "mysqlwriter",
"parameter": {
"column": ["device_id","profile","blog_url"],
"connection": [
{
"jdbcUrl": "jdbc:mysql://hadoop10:3306/sqoop?characterEncoding=UTF-8",
"table": ["user_submit"]
}
],
"password": "123456",
"preSql": ["truncate table user_submit"],
"session": [],
"username": "root",
"writeMode": "insert"
}
}
}
]
}
}
ftp2hdfs
{
"job": {
"setting": {
"speed": {
"channel": 2
}
},
"content": [
{
"reader": {
"name": "ftpreader",
"parameter": {
"protocol": "sftp",
"host": "hadoop10",
"port": 22,
"username": "root",
"password": "123456",
"path": [
"/opt/data/dept.txt"
],
"column": [
{
"index": 0,
"type": "string"
},
{
"index": 1,
"type": "string"
}
],
"encoding": "UTF-8",
"fieldDelimiter": ","
}
},
"writer": {
"name": "hdfswriter",
"parameter": {
"column": [{
"name": "user_id",
"type": "STRING"
},
{
"name": "user_name",
"type": "STRING"
} ],
"compress": "",
"defaultFS": "hdfs://hdfs-cluster",
"hadoopConfig":{
"dfs.nameservices": "hdfs-cluster",
"dfs.ha.namenodes.hdfs-cluster": "nn1,nn2",
"dfs.namenode.rpc-address.hdfs-cluster.nn1": "hadoop11:9000",
"dfs.namenode.rpc-address.hdfs-cluster.nn2": "hadoop12:9000",
"dfs.client.failover.proxy.provider.hdfs-cluster": "org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider"
},
"fieldDelimiter": "\t",
"fileName": "ftp_test",
"fileType": "text",
"path": "/qwer",
"writeMode": "append"
}
}
}
]
}
}