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
- Asp.Net 5上传文件 (Core API方式)
参考文档 首先在控制器中注入IWebHostEnvironment IWebHostEnvironment提供有关正在运行应用程序的Web托管环境的信息. 属于命名空间Microsoft.AspNet ...
- Stream流思想和常用方法
一.IO流用于读写:Stream流用于处理数组和集合数据: 1.传统集合遍历: 2.使用Stream流的方式过滤: 其中,链式编程(返回值就是对象自己)中,filter使用的是Predicate函数式 ...
- linux 命令进阶篇之二
一.预备知识 选取init的进程. cat :由第一行开始显示文件内容 tac:由最后一行开始显示,有没有发现和cat是反过来写的 more:一页一页的显示内容 less:与more相似,但是可以往前 ...
- Docker系列（12）- 部署Tomcat
#官方的使用:我们之前的启动都是后台,停止容器后,容器还是可以看到#docker run -it --rm,一般用来测试,用完就会删除容器,镜像还在[root@localhost ~]# docker ...
- 深入HTML5第二天
sub(subscripted下标标签)和sup(superscripted上标标签) 内联元素:inline element span(范围标签):内联元素inline element 特性:没有 ...
- GoLang设计模式07 - 责任链模式
责任链模式是一种行为型设计模式.在这种模式中,会为请求创建一条由多个Handler组成的链路.每一个进入的请求,都会经过这条链路.这条链路上的Handler可以选择如下操作: 处理请求或跳过处理 决定 ...
- Windows下升级Python3.7.7后（原Python3.6.2版本）如何切换Python版本
笔者:风起怨江南 出处:https://www.cnblogs.com/mengjinxiang 笔者原创,文章欢迎转载,如果喜欢请点赞+关注,谢谢! 问题:window系统下,如果升级了最新的Pyt ...
- 自己写登陆验证及借用auth的is_authenticated验证是否登陆
一. 自己写登陆需要注册,一个session的处理,还有一个session的删除 #自定义一个闭包装饰器,来验证def checkLogin(func): def wrapper(request, * ...
- 字体小于12px 无法缩小解决方案
通过缩放进行大小控制. 缩放可能会导致元素也进行缩放.需要注意 transform: scale(0.5);
- 『Python』matplotlib实现GUI效果
1. 类RadioButtons的使用方法 类似单选框 import numpy as np import matplotlib.pyplot as plt import matplotlib as ...