프로그래밍

pyparsing을 사용한 bacula 설정 파서

warpmemory 2016. 10. 19. 14:34
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
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
import pprint
from pyparsing import Word, Literal, Forward, Group, ZeroOrMore
from pyparsing import alphas, printables
 
class Parser:
    def __init__(self, conf_file):
        self.conf_file = conf_file
 
    def get_str_conf(self):
        conf_lines = []
        str_conf = open(self.conf_file, "r").read()
        for line in str_conf.strip().split("\n"):
            index = line.find("#")
            if index > -1:
                line = line[:index].strip()
            if line.find(";") > -1:
                conf_lines += line.split(";")
            else:
                conf_lines.append(line)
        conf_lines.insert(0, "conf {")
        conf_lines.append("}")
        return "\n".join(conf_lines)
 
    def syntax(self):
        lbr = Literal( '{' ).suppress()
        rbr = Literal( '}' ).suppress()
        equals = Literal("=").suppress()
        nonequals = "".join( [ c for c in printables if c != "=" ] ) + " \t"
        topic = Word( alphas )
        key = Word( alphas + " \t")
        value = Word ( nonequals )
        expr = Forward()
        opt = Group(expr) | key + equals + value
        opts = ZeroOrMore(opt)
        expr << topic + Group(lbr + opts + rbr)
        return expr
 
    def parse(self):
        conf = {
            'jobs': [],
            'pools': [],
            'clients': [],
            'schedules': [],
            'filesets': []
        }
        str_conf = self.get_str_conf()
        expr = self.syntax()
        result = expr.parseString(str_conf).asList()
        for i in range(len(result[1])):
            conf_name = result[1][i][0].strip().lower().replace(" ", "_")
            if conf_name in ["job", "pool", "client"]:
                keys = [x.strip().lower().replace(" ", "_") for x in result[1][i][1][0::2]]
                values = result[1][i][1][1::2]
                data = dict(zip(keys, values))
                if conf_name == "job":
                    conf['jobs'].append(data)
                elif conf_name == "pool":
                    conf['pools'].append(data)
                elif conf_name == "client":
                    conf['clients'].append(data)
            elif conf_name == "schedule":
                keys = [x.strip().lower().replace(" ", "_") for x in result[1][i][1][0::2]]
                values = result[1][i][1][1::2]
                run_ids = []
                index = 0
                for key in keys:
                    if key == "run":
                        run_ids.append(index)
                    index += 1
                run_ids.reverse()
                runs = []
                for id in run_ids:
                    keys.pop(id)
                    runs.append(values.pop(id))
                data = dict(zip(keys, values))
                data['runs'] = runs
                conf['schedules'].append(data)
            elif conf_name == "fileset":
                data = {
                    'name': "",
                    'include': {
                        'option': {},
                        'files': []
                    },
                    'exclude': {
                        'files': []
                    }
                }
                for j in range(len(result[1][i][1])):
                    if type(result[1][i][1][j]) == str:
                        i_key = result[1][i][1][j].strip().lower().replace(" ", "_")
                        if i_key == "name":
                            data['name'] = result[1][i][1][j+1]
                    elif type(result[1][i][1][j]) == list:
                        j_key = result[1][i][1][j][0].strip().lower().replace(" ", "_")
                        if j_key == "include":
                            option_data = {}
                            temp = []
                            for k in range(len(result[1][i][1][j][1])):
                                if type(result[1][i][1][j][1][k]) == list:
                                    k_key = result[1][i][1][j][1][k][0].strip().lower().replace(" ", "_")
                                    if k_key == "options":
                                        keys = [x.strip().lower().replace(" ", "_") for x in result[1][i][1][j][1][k][1][0::2]]
                                        values = result[1][i][1][j][1][k][1][1::2]
                                        option_data = dict(zip(keys, values))
                                else:
                                    temp.append(result[1][i][1][j][1][k])
                            keys = [x.strip().lower().replace(" ", "_") for x in temp[0::2]]
                            values = temp[1::2]
 
                            file_ids = []
                            index = 0
                            for key in keys:
                                if key == "file":
                                    file_ids.append(index)
                                index += 1
                            file_ids.reverse()
                            files = []
                            for id in file_ids:
                                keys.pop(id)
                                files.append(values.pop(id))
                            include_data = dict(zip(keys, values))
                            include_data['files'] = files
                            include_data['option'] = option_data
                            data['include'] = include_data
                        if j_key == "exclude":
                            keys = [x.strip().lower().replace(" ", "_") for x in result[1][i][1][j][1][0::2]]
                            values = result[1][i][1][j][1][1::2]
 
                            file_ids = []
                            index = 0
                            for key in keys:
                                if key == "file":
                                    file_ids.append(index)
                                index += 1
                            file_ids.reverse()
                            files = []
                            for id in file_ids:
                                keys.pop(id)
                                files.append(values.pop(id))
                            exclude_data = dict(zip(keys, values))
                            exclude_data['files'] = files
                            data['exclude'] = exclude_data
                conf['filesets'].append(data)
        return conf
 
if __name__ == "__main__":
    parser = Parser("bacula-test.conf")
    pprint.pprint(parser.parse())
cs