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
150
151
152
153
154
155
156
157
158
159
160
|
# pylint:disable=line-too-long
"""
The tool to check the availability or syntax of domain, IP or URL.
::
██████╗ ██╗ ██╗███████╗██╗ ██╗███╗ ██╗ ██████╗███████╗██████╗ ██╗ ███████╗
██╔══██╗╚██╗ ██╔╝██╔════╝██║ ██║████╗ ██║██╔════╝██╔════╝██╔══██╗██║ ██╔════╝
██████╔╝ ╚████╔╝ █████╗ ██║ ██║██╔██╗ ██║██║ █████╗ ██████╔╝██║ █████╗
██╔═══╝ ╚██╔╝ ██╔══╝ ██║ ██║██║╚██╗██║██║ ██╔══╝ ██╔══██╗██║ ██╔══╝
██║ ██║ ██║ ╚██████╔╝██║ ╚████║╚██████╗███████╗██████╔╝███████╗███████╗
╚═╝ ╚═╝ ╚═╝ ╚═════╝ ╚═╝ ╚═══╝ ╚═════╝╚══════╝╚═════╝ ╚══════╝╚══════╝
Provides the default input line converter.
Author:
Nissar Chababy, @funilrys, contactTATAfunilrysTODTODcom
Special thanks:
https://pyfunceble.github.io/#/special-thanks
Contributors:
https://pyfunceble.github.io/#/contributors
Project link:
https://github.com/funilrys/PyFunceble
Project documentation:
https://docs.pyfunceble.com
Project homepage:
https://pyfunceble.github.io/
License:
::
Copyright 2017, 2018, 2019, 2020, 2022, 2023, 2024 Nissar Chababy
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
https://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
"""
from typing import Any, List
from PyFunceble.checker.syntax.ip import IPSyntaxChecker
from PyFunceble.converter.base import ConverterBase
from PyFunceble.converter.url2netloc import Url2Netloc
class InputLine2Subject(ConverterBase):
"""
Converts/Extract the subjcts to test from an inputed line.
"""
COMMENT: str = "#"
PARTICULAR_COMMENT: List[str] = ["!"]
SPACE: str = " "
NSLOOKUP_SPACE: str = "\\032"
TAB: str = "\t"
@ConverterBase.data_to_convert.setter
def data_to_convert(self, value: Any) -> None:
"""
Overrites the default behavior.
:raise TypeError:
When the given data to convert is not :py:class:`str`
"""
if not isinstance(value, str):
raise TypeError(f"<value> should be {str}, {type(value)} given.")
# pylint: disable=no-member
super(InputLine2Subject, self.__class__).data_to_convert.fset(self, value)
def get_converted(self) -> List[str]:
"""
Provides the subject to test.
"""
return self.convert(self.data_to_convert, aggressive=self.aggressive)
@staticmethod
def extract_base(subject: str) -> str:
"""
Extracts the base of the given subject - assuming that it may be a URL.
:param subject:
The subject to work with.
"""
try:
return Url2Netloc(subject).get_converted()
except ValueError:
return subject
def convert(self, data: Any, *, aggressive: bool = False) -> List[str]:
"""
Converts the given dataset.
:param data:
The data to convert.
:param bool aggressive:
Whether we should aggressively decode subjects.
"""
result = []
subject = data.strip()
if subject and (
not subject.startswith(self.COMMENT)
and any(not subject.startswith(x) for x in self.PARTICULAR_COMMENT)
):
if self.COMMENT in subject:
subject = subject[: subject.find(self.COMMENT)].strip()
if self.NSLOOKUP_SPACE in subject:
# Comply with RFC 6367:
# Note that nslookup escapes spaces as "\032" for display
# purposes, but a graphical DNS-SD browser should not.
subject = subject.replace(self.NSLOOKUP_SPACE, self.SPACE)
if self.SPACE in subject or self.TAB in subject:
splitted = subject.split()
if IPSyntaxChecker(splitted[0]).is_valid():
# This is for the hosts format.
# If the first entry is an IP, we will only extract
# the entries after the first one.
datasets = splitted[1:]
if aggressive:
datasets = [self.extract_base(x) for x in datasets]
result.extend(datasets)
else:
if aggressive:
splitted = [self.extract_base(x) for x in splitted]
# All other cases, we extract every entries.
result.extend(splitted)
else:
if aggressive:
subject = self.extract_base(subject)
result.append(subject)
return result
|
