DataX配置MySQL到同步全量表到HDFS的一键脚本
一般该类的配置文件,我一般放在用户的bin目录下,当然工作中是没有root用户的,就是个人家目录的bin下:
[wyp@hadoop102 bin]$ vim ~/bin/gen_import_config.py
插入如下python脚本:
# coding=utf-8
import os
import sys
import MySQLdb
#MySQL相关配置,需根据实际情况作出修改
mysql_host = "hadoop102"
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 = "hadoop102"
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/module/datax/job/import"
def get_connection():
return MySQLdb.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()
cursor.execute(sql, [database, table])
fetchall = cursor.fetchall()
cursor.close()
connection.close()
return fetchall
def get_mysql_columns(database, table):
return 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 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": [{
"