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
- 新版idea无法导入mavenweb模板
目前没有任何办法,最好是下个旧版的
- blender Text on Curve Text on Sphere
Text on Curve Shift + A 添加一个 BezierCurve Shift + A 添加一个 Text,Tab 编辑,再次 Tab 退回 Object Mode 选中 Text,Ad ...
- 聊聊 Jmeter 如何并发执行 Python 脚本
1. 前言 大家好,我是安果! 最近有小伙伴后台给我留言,说自己用 Django 写了一个大文件上传的 Api 接口,现在想本地检验一下接口并发的稳定性,问我有没有好的方案 本篇文章以文件上传为例,聊 ...
- Appium问题解决方案（6）- Java堆栈错误：java.lag.ClassNotFoundException:org.eclipse.swt.widets.Control
背景 运行脚本出现 SWT folder '..\lib\location of your Java installation.' does not exist. Please set ANDROID ...
- VUE003. 解决data中使用vue-i18n不更新视图问题（computed属性）
案例 在国际化开发中,有一部分需要国际化的文字是由数据驱动的储存在data中,然而VUE的data存在很多无法实时更新视图的问题,比如v-for循环的标签,当数据层次过深,通过源数据数组的索引改变它的 ...
- 查询同一张表符合条件的某些数据的id拼接成一个字段返回
同一张表存在类似多级菜单的上下级关系的数据,查询出符合条件的某些数据的id拼接成一个字段返回: SELECT CONCAT(a.pid, ',', b.subid) AS studentIDS FRO ...
- shell编程之免交互
目录: 一.Here Document 免交互 二.Expect 一.Here Document 免交互 使用I/O重定向的方式将命令列表提供给交互式程序或命令, 比如 ftp.cat 或 read ...
- c++ if语句讲解&例题
一.if语句 1.基本语法: if(条件 布尔型){ 当条件符合执行的语句 } 2.例子: #include <iostream> using namespace std; int mai ...
- http升级https遇到的问题
1. 功能请求失效: 可能是链接为http请求,导致出现问题 2.浏览器网址左边出现黄色感叹号: 这是由于网页中存在http的图片链接,需要根据实际情况修改; 3.将网页内的http请求变为https ...
- jquery .play()报错is not a function
报错原因:play()方法属于DOM对象方法,$('#audio')为jquery对象解决办法:将jquery对象转换为DOM对象首先打印jquery对象$('#audio') 两种转换方式将一个jQ ...