脚本宝典收集整理的这篇文章主要介绍了DataX安装及使用,脚本宝典觉得挺不错的,现在分享给大家,也给大家做个参考。
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
# 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
}
}
}
}
datax.py stream2stream.json
需要新建student2数据库,并创建student表
{
"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
}
}
}
}
datax.py mysql2mysql.json
写hive跟hdfs时一样的
{
"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
}
}
}
}
{
"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
}
}
}
}
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
}
}
}
}
CREATE TABLE IF NOT EXISTS STUDENT (
ID VArchAR NOT NULL Primary KEY,
NAME VARCHAR,
AGE BIginT,
GENDER VARCHAR ,
CLAZZ VARCHAR
);
{
"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"
}
}
}
]
}
}
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"
}
}
}
]
}
}
以上是脚本宝典为你收集整理的DataX安装及使用全部内容,希望文章能够帮你解决DataX安装及使用所遇到的问题。
本图文内容来源于网友网络收集整理提供,作为学习参考使用,版权属于原作者。
如您有任何意见或建议可联系处理。小编QQ:384754419,请注明来意。