通过python3脚本生成datax配置文件（json）

 datax主要特点：

1、异构数据库和文件系统之间的数据交换；

2、采用Framework + plugin架构构建，Framework处理了缓冲，流控，并发，上下文加载等高速数据交换的大部分技术问题，提供了简单的接口与插件交互，
插件仅需实现对数据处理系统的访问；

3、数据传输过程在单进程内完成，全内存操作，不读写磁盘，也没有IPC；

datax是插件式的etl工具，使用的时候需要通过配置json类型的文件。

下面是我通过python脚本，查询mysql数据库中表的信息生成datax需要的json配置文件。 

#coding=utf-8
import os
import sys
import getopt
import json

import pymysql
pymysql.install_as_MySQLdb()

#MySQL相关配置，需根据实际情况作出修改
mysql_host = "hadoop101"
mysql_port = "3306"
mysql_user = "root"
mysql_passwd = "123456"

#HDFS NameNode相关配置，需根据实际情况作出修改
hdfs_nn_host = "hadoop101"
hdfs_nn_port = "8020"

#生成配置文件的目标路径，可根据实际情况作出修改
output_path = "/opt/bdp/datax/job/import"

def get_connection():
    return pymysql.connect(host=mysql_host, port=int(mysql_port), user=mysql_user, passwd=mysql_passwd)

def get_mysql_meta(database, table):
    connection = get_connection()
    cursor = connection.cursor()
    sql= "SELECT COLUMN_NAME,DATA_TYPE from information_schema.COLUMNS WHERE TABLE_SCHEMA=%s AND TABLE_NAME=%s ORDER BY ORDINAL_POSITION"
    cursor.execute(sql, [database, table])
    fetchall = cursor.fetchall()
    cursor.close()
    connection.close()
    return fetchall


def get_mysql_columns(database, table):
    return (list(map(lambda x: x[0], get_mysql_meta(database, table))))


def get_hive_columns(database, table):
    def type_mapping(mysql_type):
        mappings = {
            "bigint": "bigint",
            "int": "bigint",
            "smallint": "bigint",
            "tinyint": "bigint",
            "decimal": "string",
            "double": "double",
            "float": "float",
            "binary": "string",
            "char": "string",
            "varchar": "string",
            "datetime": "string",
            "time": "string",
            "timestamp": "string",
            "date": "string",
            "text": "string"
        }
        return mappings[mysql_type]

    meta = get_mysql_meta(database, table)
    return (list(map(lambda x: {"name": x[0], "type": type_mapping(x[1].lower())}, meta)))


def generate_json(source_database, source_table):
    job = {
        "job": {
            "setting": {
                "speed": {
                    "channel": 3
                },
                "errorLimit": {
                    "record": 0,
                    "percentage": 0.02
                }
            },
            "content": [{
                "reader": {
                    "name": "mysqlreader",
                    "parameter": {
                        "username": mysql_user,
                        "password": mysql_passwd,
                        "column": get_mysql_columns(source_database, source_table),
                        "splitPk": "",
                        "connection": [{
                            "table": [source_table],
                            "jdbcUrl": ["jdbc:mysql://" + mysql_host + ":" + mysql_port + "/" + source_database + "?useSSL=false"]
                        }]
                    }
                },
                "writer": {
                    "name": "hdfswriter",
                    "parameter": {
                        "defaultFS": "hdfs://" + hdfs_nn_host + ":" + hdfs_nn_port,
                        "fileType": "text",
                        "path": "${targetdir}",
                        "fileName": source_table,
                        "column": get_hive_columns(source_database, source_table),
                        "writeMode": "append",
                        "fieldDelimiter": "\t",
                        "compress": "gzip"
                    }
                }
            }]
        }
    }
    if not os.path.exists(output_path):
        os.makedirs(output_path)
    with open(os.path.join(output_path, ".".join([source_database, source_table, "json"])), "w") as f:
        json.dump(job, f)


def main(args):
    source_database = "[要查询的数据库]"
    source_table = "[要查询的表]"

    options, arguments = getopt.getopt(args, '-d:-t:', ['sourcedb=', 'sourcetbl='])
    for opt_name, opt_value in options:
        if opt_name in ('-d', '--sourcedb'):
            source_database = opt_value
        if opt_name in ('-t', '--sourcetbl'):
            source_table = opt_value

    generate_json(source_database, source_table)


if __name__ == '__main__':
    main(sys.argv[1:])