DataX的安装及使用
DataX的安装及使用
DataX的安装
DataX不需要依赖其他服务，直接上传、解压、安装、配置环境变量即可
也可以直接在windows上解压
DataX的使用
stream2stream
编写配置文件stream2stream.json
# stream2stream.json
{
"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
}
}
}
}
执行同步任务
datax.py stream2stream.json
执行结果
mysql2mysql
需要新建student2数据库，并创建student表
编写配置文件mysql2mysql.json
{
"job": {
"content": [
{
"reader": {
"name": "mysqlreader",
"parameter": {
"username": "root",
"password": "123456",
"column": [
"id",
"name",
"age",
"gender",
"clazz",
"last_mod"
],
"splitPk": "age",
"connection": [
{
"table": [
"student"
],
"jdbcUrl": [
"jdbc:mysql://master:3306/student"
]
}
]
}
},
"writer": {
"name": "mysqlwriter",
"parameter": {
"writeMode": "insert",
"username": "root",
"password": "123456",
"column": [
"id",
"name",
"age",
"gender",
"clazz",
"last_mod"
],
"preSql": [
"truncate student2"
],
"connection": [
{
"jdbcUrl": "jdbc:mysql://master:3306/student2?useUnicode=true&characterEncoding=utf8",
"table": [
"student2"
]
}
]
}
}
}
],
"setting": {
"speed": {
"channel": 6
}
}
}
}
执行同步任务
datax.py mysql2mysql.json
mysql2hdfs
写hive跟hdfs时一样的
编写配置文件mysql2hdfs.json
{
"job": {
"content": [
{
"reader": {
"name": "mysqlreader",
"parameter": {
"username": "root",
"password": "123456",
"column": [
"id",
"name",
"age",
"gender",
"clazz",
"last_mod"
],
"splitPk": "age",
"connection": [
{
"table": [
"student"
],
"jdbcUrl": [
"jdbc:mysql://master:3306/student"
]
}
]
}
},
"writer": {
"name": "hdfswriter",
"parameter": {
"defaultFS": "hdfs://master:9000",
"fileType": "text",
"path": "/user/hive/warehouse/datax.db/students",
"fileName": "student",
"column": [
{
"name": "id",
"type": "bigint"
},
{
"name": "name",
"type": "string"
},
{
"name": "age",
"type": "INT"
},
{
"name": "gender",
"type": "string"
},
{
"name": "clazz",
"type": "string"
},
{
"name": "last_mod",
"type": "string"
}
],
"writeMode": "append",
"fieldDelimiter": ","
}
}
}
],
"setting": {
"speed": {
"channel": 6
}
}
}
}
hbase2mysql
{
"job": {
"content": [
{
"reader": {
"name": "hbase11xreader",
"parameter": {
"hbaseConfig": {
"hbase.zookeeper.quorum": "master:2181"
},
"table": "student",
"encoding": "utf-8",
"mode": "normal",
"column": [
{
"name": "rowkey",
"type": "string"
},
{
"name": "cf1:name",
"type": "string"
},
{
"name": "cf1:age",
"type": "string"
},
{
"name": "cf1:gender",
"type": "string"
},
{
"name": "cf1:clazz",
"type": "string"
}
],
"range": {
"startRowkey": "",
"endRowkey": "",
"isBinaryRowkey": false
}
}
},
"writer": {
"name": "mysqlwriter",
"parameter": {
"writeMode": "insert",
"username": "root",
"password": "123456",
"column": [
"id",
"name",
"age",
"gender",
"clazz"
],
"preSql": [
"truncate student2"
],
"connection": [
{
"jdbcUrl": "jdbc:mysql://master:3306/student2?useUnicode=true&characterEncoding=utf8",
"table": [
"student2"
]
}
]
}
}
}
],
"setting": {
"speed": {
"channel": 6
}
}
}
}
mysql2hbase
mysql中的score表需将cource_id改为course_id，并将student_id、course_id设为主键，并将所有字段的类型改为int
hbase需先创建score表：create 'score','cf1'
{
"job": {
"content": [
{
"reader": {
"name": "mysqlreader",
"parameter": {
"username": "root",
"password": "123456",
"column": [
"student_id",
"course_id",
"score"
],
"splitPk": "course_id",
"connection": [
{
"table": [
"score"
],
"jdbcUrl": [
"jdbc:mysql://master:3306/student"
]
}
]
}
},
"writer": {
"name": "hbase11xwriter",
"parameter": {
"hbaseConfig": {
"hbase.zookeeper.quorum": "master:2181"
},
"table": "score",
"mode": "normal",
"rowkeyColumn": [
{
"index":0,
"type":"string"
},
{
"index":-1,
"type":"string",
"value":"_"
},
{
"index":1,
"type":"string"
}
],
"column": [
{
"index":2,
"name": "cf1:score",
"type": "int"
}
],
"encoding": "utf-8"
}
}
}
],
"setting": {
"speed": {
"channel": 6
}
}
}
}
mysql2Phoenix
在Phoenix中创建STUDENT表
CREATE TABLE IF NOT EXISTS STUDENT (
ID VARCHAR NOT NULL PRIMARY KEY,
NAME VARCHAR,
AGE BIGINT,
GENDER VARCHAR ,
CLAZZ VARCHAR
);
编写配置文件MySQLToPhoenix.json
{
"job": {
"setting": {
"speed": {
"channel": 3
},
"errorLimit": {
"record": 0,
"percentage": 0.02
}
},
"content": [
{
"reader": {
"name": "mysqlreader",
"parameter": {
"username": "root",
"password": "123456",
"column": [
"id",
"name",
"age",
"gender",
"clazz"
],
"splitPk": "id",
"connection": [
{
"table": [
"student"
],
"jdbcUrl": [
"jdbc:mysql://master:3306/student?useSSL=false"
]
}
]
}
},
"writer": {
"name": "hbase11xsqlwriter",
"parameter": {
"batchSize": "256",
"column": [
"ID",
"NAME",
"AGE",
"GENDER",
"CLAZZ"
],
"hbaseConfig": {
"hbase.zookeeper.quorum": "master,node1,node2",
"zookeeper.znode.parent": "/hbase"
},
"nullMode": "skip",
"table": "STUDENT"
}
}
}
]
}
}
HDFSToHBase
将students.txt数据上传至HDFS的
/data/student1/目录在HBase中创建datax表：
create 'datax','cf1'
{
"job": {
"setting": {
"speed": {
"channel": 3
},
"errorLimit": {
"record": 0,
"percentage": 0.02
}
},
"content": [
{
"reader": {
"name": "hdfsreader",
"parameter": {
"path": "/data/student1/",
"defaultFS": "hdfs://master:9000",
"column": [
{
"index": 0,
"type": "string"
},
{
"index": 1,
"type": "string"
},
{
"index": 2,
"type": "string"
},
{
"index": 3,
"type": "string"
},
{
"index": 4,
"type": "string"
},
{
"index": 5,
"type": "string"
}
],
"fileType": "text",
"encoding": "UTF-8",
"fieldDelimiter": ","
}
},
"writer": {
"name": "hbase11xwriter",
"parameter": {
"hbaseConfig": {
"hbase.zookeeper.quorum": "master,node1,node2"
},
"table": "datax",
"mode": "normal",
"rowkeyColumn": [
{
"index": 0,
"type": "string"
},
{
"index": -1,
"type": "string",
"value": "_"
},
{
"index": 1,
"type": "string"
}
],
"column": [
{
"index": 2,
"name": "cf1:age",
"type": "string"
},
{
"index": 3,
"name": "cf1:gender",
"type": "string"
},
{
"index": 4,
"name": "cf1:clazz",
"type": "string"
},
{
"index": 5,
"name": "cf1:ts",
"type": "string"
}
],
"versionColumn": {
"index": 5
},
"encoding": "utf-8"
}
}
}
]
}
}
DataX的安装及使用的更多相关文章
- DataX的安装
DataX的安装 1. 可下载tar包 https://github.com/alibaba/DataX/blob/master/userGuid.md 2. 下载源码自己编译 git clone h ...
- [大数据技术]datax的安装以及使用
1.datax简述 DataX 是阿里巴巴集团内被广泛使用的离线数据同步工具/平台,实现包括 MySQL.Oracle.SqlServer.Postgre.HDFS.Hive.ADS.HBase.Ta ...
- dataX windows10安装
按照视频课程,从Github上下载文件:https://github.com/alibaba/DataX 然后将下载的压缩包解压即可,不过需要的前提Python环境是要求python2,于是在pyth ...
- datax的安装和使用（windows）
github官方文档和项目:https://github.com/alibaba/DataX 下载后在windows环境下是可以直接用python编译执行的,但从github上下载的版本只支持pyth ...
- 在datax之前版本中添加filewriter并创建job时出现问题
问题描述:
- DataX的使用——大数据同步技术
准备工作: 1.视频教学http://113.31.104.47/portal/#/course/dashboard/b34d160db64624732ef152a1118af11a 2.DataX的 ...
- Pyhton开源框架(加强版)
info:Djangourl:https://www.oschina.net/p/djangodetail: Django 是 Python 编程语言驱动的一个开源模型-视图-控制器(MVC)风格的 ...
- Python开源框架
info:更多Django信息url:https://www.oschina.net/p/djangodetail: Django 是 Python 编程语言驱动的一个开源模型-视图-控制器(MVC) ...
- DataX的简单编译安装测试
搭建环境: Java > =1.6 Python>=2.6 <3 Ant Rpmbuild G++ 编译DataX: 进入rpm文件夹 ...
随机推荐
- inotify与rsync实现实时同步记录文档
目录 安装 配置 参考链接 安装 安装rsync yum -y install rsync 安装inotify-tools 这是一个实时监听文件变换的工具 wget -O /etc/yum.repos ...
- 连接Redis服务
1.命令 redis-cli -h host -p port -a password 2.参数 host:远程redis服务器host port:远程redis服务端口 password:远程redi ...
- docker一分钟搭建nginx服务器
运行nginx服务 拉取: docker pull nginx:1.17.9 运行: docker run -d --name nginx -P 80:80 nginx:1.17.9 -d表示在后台启 ...
- .net Core 基于EF Core 实现数据库上下文
在做项目时,需要将某一些功能的实体建立在另一个数据库中,连接不同的数据库用以存储记录.通过查找资料,实现EF Core上下文. 下面是实现上下文后的解决方案的目录: 1.UpAndDownDbCont ...
- plsql报ora-00911错误的解决
论不作死就不会死的过程,楼主之前因为得了一个oralce9i的精简版的客户端安装包,我也分享过给其他人使用这个安装包,没听人反馈过说有问题,所以这次换了电脑后果断就安装这个客户端.然后问题就来了. 反 ...
- js根据日期获取所在周
一.获取时间所在周的周一.周五 function getFirstLastDay (time) { let date = new Date(time) let Time = date.getTime( ...
- 【Python学习】print语句
一.print 可以向屏幕上输出信息,print 后面一个空格再加上''中间放入要输出的内容. 二.print可以用逗号分隔语句,但是每有一个逗号就会出来一个空格. 1 >>> pr ...
- symfony generate:bundle出现提示: Checking that the bundle is autoloaded
可以参考官方文档给出来的解决办法 http://symfonychina.com/doc/current/bundles/SensioGeneratorBundle/commands/generate ...
- SQLSTATE[HY000]: General error: 1366 Incorrect string value: '\xF0\x9F\x90\xA3\xF0\x9F...' for column
在做微信公众号保存用户数据时出现这种错误,一直不知道是哪里的原因,后来发现那个用户昵称带着一只兔子表情,由于数据库编码限制不能保存数据,所有需要先编码, 用PHP的函数就是base64_encode, ...
- openldap 双主模式部署
规划两台机器 系统版本centos7.5 master1上部署ldap: 一.安装启动openldap软件 yum -y install openldap compat-openldap openld ...