數據集成平台：datax將MySQL數據以query方式同步到hive

數據集成平台：datax將MySQL數據以query方式同步到hive

1.py腳本

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

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

# HDFS NameNode相关配置，需根据实际情况作出修改
hdfs_nn_host = "mycluster"
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
def get_connection():
    return MySQLdb.connect(host=mysql_host, port=int(mysql_port), user=mysql_user, passwd=mysql_passwd)


def get_hive_columns(database, table, source_columns):
    return [{"name": col, "type": "string"} for col in source_columns]


def generate_json(source_database, source_table, source_querySql, columns_list):
    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,
                        "connection": [{
                            "querySql": [source_querySql],
                            "jdbcUrl": [
                                "jdbc:mysql://" + mysql_host + ":" + mysql_port + "/" + source_database + "?userCompress=true&useCursorFetch=true&useUnicode=true&characterEncoding=utf-8&useSSL=false"]
                        }]
                    }
                },
                "writer": {
                    "name": "hdfswriter",
                    "batchSize": "8192",
                    "batchByteSize": "33554432",
                    "parameter": {
                        "defaultFS": "hdfs://" + hdfs_nn_host + ":" + hdfs_nn_port,
                        "fileType": "text",
                        "path": "${targetdir}",
                        "fileName": source_table,
                        "column": get_hive_columns(source_database, source_table, columns_list),
                        "writeMode": "append",
                        "fieldDelimiter": u"\u0001",
                        "compress": "gzip"
                    }
                },
                "transformer": [

                    {
                        "name": "dx_groovy",
                        "parameter": {
                            "code": "for(int i=0;i\"[\\r\\n]\",\"\"); record.setColumn(i, new StringColumn(newStr)); };};return record;",
                            "extraPackage": []
                        }
                    }
                ]
            }]
        }
    }
    output_path = "/opt/module/datax/job/import/" + source_database

    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 = ""
    source_querySql = ""

    options, arguments = getopt.getopt(args, 'd:t:s:', ['sourcedb=', 'querysql='])
    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
        if opt_name in ('-s', '--querysql'):
            source_querySql = opt_value

    match = re.search(r"select(.*?)from", source_querySql, re.DOTALL | re.IGNORECASE)
    selected_columns = match.group(1).strip()
    # 去掉所有空格和换行
    selected_columns_cleaned = re.sub(r'\s+', '', selected_columns)
    # 分割字段
    columns_list = re.split(r',', selected_columns_cleaned)
    print(columns_list)

    generate_json(source_database, source_table, source_querySql, columns_list)
    #print(source_database, source_table, source_querySql)


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

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120

2.sh腳本

#!/bin/bash
python ~/bin/sap_gateway_query_gen_import_config.py -d sap_gateway -t test2 -s “querySql”
1
2