datax实现MySQL数据库迁移
(1)生成python脚本
bash
# coding=utf-8
import json
import getopt
import os
import sys
import MySQLdb
#MySQL相关配置,需根据实际情况作出修改
mysql_host = "xxxx"
mysql_port = "3306"
mysql_user = "xxxx"
mysql_passwd = "xxxx"
# MYSQL Destination
dest_mysql_host = "xxxx"
dest_mysql_port = "3306"
dest_mysql_user = "xxxx"
dest_mysql_passwd = "xxxx"
#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/databaseName"
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()
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 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",
"mediumint": "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": 15
},
"errorLimit": {
"record": 0,
"percentage": 0.02
}
},
"content": [{
"reader": {
"name": "mysqlreader",
"batchSize": "8192",
"batchByteSize": "33554432",
"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+"?userCompress=true&useCursorFetch=true&useUnicode=true&characterEncoding=utf-8&useSSL=false"]
}]
}
},
"writer": {
"name": "mysqlwriter",
"batchSize": "8192",
"batchByteSize": "33554432",
"parameter": {
"writeMode": "replace",
"username": dest_mysql_user,
"password": dest_mysql_passwd,
"column": get_mysql_columns(source_database, source_table),
"connection": [
{
"jdbcUrl": "jdbc:mysql://"+dest_mysql_host+":"+dest_mysql_port+ "/" + source_database + "?userCompress=true&useCursorFetch=true&useUnicode=true&characterEncoding=utf-8&useSSL=false",
"table": [source_table],
}
]
}
},
"transformer": [
{
"name": "dx_groovy",
"parameter": {
"code": "for(int i=0;i<record.getColumnNumber();i++){if(record.getColumn(i).getByteSize()!=0){Column column = record.getColumn(i); def str = column.asString(); def newStr=null; newStr=str.replaceAll(\"[\\r\\n]\",\"\"); record.setColumn(i, new StringColumn(newStr)); };};return record;",
"extraPackage":[]
}
}
]
}]
}
}
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 = ""
source_table = ""
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:])
sh脚本
bash
#!/bin/bash
python ~/bin/new_lms_mysql_gen_import_config.py -d database -t table
mysq到mysql脚本
bash
#! /bin/bash
case $1 in
"course_groups")
python /opt/module/datax/bin/datax.py /opt/module/datax/job/import/database/database.table.json
;;
"all")
python /opt/module/datax/bin/datax.py /opt/module/datax/job/import/database/database.table.json
;;
esac