【DataX 增量同步】读取Mysql数据到HDFS

如果是第一次操作的同学不知道的可以看我之前写的博客，操作过一次后面基本是相同的了

在目录三：https://blog.csdn.net/Zsigner/article/details/108362724

1、生成hdfswriter plugins 修改pom.xml

//原始的里面是所有很全的，不过一般都是按需install
   
        common
        core
        transformer
 
        
        mysqlreader
        
 
        
       
        hdfswriter
        
 
        
        plugin-rdbms-util
        plugin-unstructured-storage-util
        hbase20xsqlreader
        hbase20xsqlwriter
    

2、编译生成elasticsearchwriter 插件

mvn clean install -Dmaven.test.skip=true

3、复制生成的文件到 /datax/plugin/，注意区分reader 跟writer

cp -r /usr/local/DataX-master/hdfswriter/target/datax/plugin/writer/hdfswriter /usr/local/data/datax/datax/plugin/writer

4、编写脚本 test.json

{
  "job": {
    "setting": {
      "speed": {
        "channel": 1
      }
    },
    "content": [
      {
        "reader": {
          "name": "mysqlreader",
          "parameter": {
            "username": "datax",
            "password": "123456",
            "where": "updated_at>='${start_time}' and updated_at<='${end_time}'",
            "column": [
              "app_id",
              "created_at",
              "id",
              "in_id",
              "is_deleted",
              "resource_id"
            ],
            "connection": [
              {
                "jdbcUrl": [
                  "jdbc:mysql://127.0.0.1:3306/test?com.mysql.jdbc.faultInjection.serverCharsetIndex=45"
                ],
                "table": [
                  "test"
                ]
              }
            ]
          }
        },
        "writer": {
          "name": "hdfswriter",
          "parameter": {
            "defaultFS": "hdfs://127.0.0.1:4007",
            "fileType": "orc",
            "path": "/usr/hive/warehouse/db/test/statdate=${statdate}",
            "fileName": "part-m-",
            "column": [
              {
                "name": "app_id",
                "type": "String"
              },
              {
                "name": "created_at",
                "type": "String"
              },
              {
                "name": "id",
                "type": "int"
              },
              {
                "name": "in_id",
                "type": "String"
              },
              {
                "name": "is_deleted",
                "type": "int"
              },
              {
                "name": "resource_id",
                "type": "String"
              }
            ],
            "writeMode": "append",
            "fieldDelimiter": "\u0001",
            "compress":"NONE"
          }
        }
      }
    ]
  }
}

5、运行脚本

python /usr/local/datax/bin/datax.py ./test.json -p "-Dstart_time=2020-09-05 -Dend_time=2020-09-05"