Repository navigation
Expand file tree
/
Copy pathurl.py
More file actions
265 lines (237 loc) · 7.96 KB
/
Copy pathurl.py
File metadata and controls
265 lines (237 loc) · 7.96 KB
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
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
"""URL."""
# standard
from functools import lru_cache
import re
from typing import Callable, Optional
from urllib.parse import parse_qs, unquote, urlsplit
# local
from .hostname import hostname
from .utils import validator
@lru_cache
def _username_regex():
return re.compile(
# extended latin
r"(^[\u0100-\u017F\u0180-\u024F]"
# dot-atom
+ r"|[-!#$%&'*+/=?^_`{}|~0-9a-z]+(\.[-!#$%&'*+/=?^_`{}|~0-9a-z]+)*$"
# non-quoted-string
+ r"|^([\001-\010\013\014\016-\037!#-\[\]-\177]|\\[\011.])*$)",
re.IGNORECASE,
)
@lru_cache
def _path_regex():
return re.compile(
# allowed symbols
r"^[\/a-z0-9\-\.\_\~\!\$\&\'\(\)\*\+\,\;\=\:\@\%"
# symbols / pictographs
+ r"\U0001F300-\U0001F5FF"
# emoticons / emoji
+ r"\U0001F600-\U0001F64F"
# multilingual unicode ranges
+ r"\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF]+$",
re.IGNORECASE,
)
def _validate_scheme(value: str):
"""Validate scheme."""
# More schemes will be considered later.
return (
value
# fmt: off
in {
"file",
"ftp",
"ftps",
"git",
"http",
"https",
"irc",
"rtmp",
"rtmps",
"rtsp",
"sftp",
"ssh",
"telnet",
}
# fmt: on
if value
else False
)
def _confirm_ipv6_skip(value: str, skip_ipv6_addr: bool):
"""Confirm skip IPv6 check."""
return skip_ipv6_addr or value.count(":") < 2 or not value.startswith("[")
def _validate_auth_segment(value: str):
"""Validate authentication segment."""
if not value:
return True
if (colon_count := value.count(":")) > 1:
# everything before @ is then considered as a username
# this is a bad practice, but syntactically valid URL
return _username_regex().match(unquote(value))
if colon_count < 1:
return _username_regex().match(value)
username, password = value.rsplit(":", 1)
return _username_regex().match(username) and all(
char_to_avoid not in password for char_to_avoid in ("/", "?", "#", "@")
)
def _validate_netloc(
value: str,
skip_ipv6_addr: bool,
skip_ipv4_addr: bool,
may_have_port: bool,
simple_host: bool,
consider_tld: bool,
private: Optional[bool],
rfc_1034: bool,
rfc_2782: bool,
):
"""Validate netloc."""
if not value or value.count("@") > 1:
return False
if value.count("@") < 1:
return hostname(
(
value
if _confirm_ipv6_skip(value, skip_ipv6_addr) or "]:" in value
else value.lstrip("[").replace("]", "", 1)
),
skip_ipv6_addr=_confirm_ipv6_skip(value, skip_ipv6_addr),
skip_ipv4_addr=skip_ipv4_addr,
may_have_port=may_have_port,
maybe_simple=simple_host,
consider_tld=consider_tld,
private=private,
rfc_1034=rfc_1034,
rfc_2782=rfc_2782,
)
basic_auth, host = value.rsplit("@", 1)
return hostname(
(
host
if _confirm_ipv6_skip(host, skip_ipv6_addr) or "]:" in value
else host.lstrip("[").replace("]", "", 1)
),
skip_ipv6_addr=_confirm_ipv6_skip(host, skip_ipv6_addr),
skip_ipv4_addr=skip_ipv4_addr,
may_have_port=may_have_port,
maybe_simple=simple_host,
consider_tld=consider_tld,
private=private,
rfc_1034=rfc_1034,
rfc_2782=rfc_2782,
) and _validate_auth_segment(basic_auth)
def _validate_optionals(path: str, query: str, fragment: str, strict_query: bool):
"""Validate path query and fragments."""
optional_segments = True
if path:
optional_segments &= bool(_path_regex().match(path))
try:
if (
query
# ref: https://github.com/python/cpython/issues/117109
and parse_qs(query, strict_parsing=strict_query, separator="&")
and parse_qs(query, strict_parsing=strict_query, separator=";")
):
optional_segments &= True
except TypeError:
# for Python < v3.9.2 (official v3.10)
if query and parse_qs(query, strict_parsing=strict_query):
optional_segments &= True
if fragment:
# See RFC3986 Section 3.5 Fragment for allowed characters
# Adding "#", see https://github.com/python-validators/validators/issues/403
optional_segments &= bool(
re.fullmatch(r"[0-9a-z?/:@\-._~%!$&'()*+,;=#]*", fragment, re.IGNORECASE)
)
return optional_segments
@validator
def url(
value: str,
/,
*,
skip_ipv6_addr: bool = False,
skip_ipv4_addr: bool = False,
may_have_port: bool = True,
simple_host: bool = False,
strict_query: bool = True,
consider_tld: bool = False,
private: Optional[bool] = None, # only for ip-addresses
rfc_1034: bool = False,
rfc_2782: bool = False,
validate_scheme: Callable[[str], bool] = _validate_scheme,
):
r"""Return whether or not given value is a valid URL.
This validator was originally inspired from [URL validator of dperini][1].
The following diagram is from [urlly][2]::
foo://admin:hunter1@example.com:8042/over/there?name=ferret#nose
\_/ \___/ \_____/ \_________/ \__/\_________/ \_________/ \__/
| | | | | | | |
scheme username password hostname port path query fragment
[1]: https://gist.github.com/dperini/729294
[2]: https://github.com/treeform/urlly
Examples:
>>> url('http://duck.com')
True
>>> url('ftp://foobar.dk')
True
>>> url('http://10.0.0.1')
True
>>> url('http://example.com/">user@example.com')
ValidationError(func=url, args={'value': 'http://example.com/">user@example.com'})
Args:
value:
URL string to validate.
skip_ipv6_addr:
When URL string cannot contain an IPv6 address.
skip_ipv4_addr:
When URL string cannot contain an IPv4 address.
may_have_port:
URL string may contain port number.
simple_host:
URL string maybe only hyphens and alpha-numerals.
strict_query:
Fail validation on query string parsing error.
consider_tld:
Restrict domain to TLDs allowed by IANA.
private:
Embedded IP address is public if `False`, private/local if `True`.
rfc_1034:
Allow trailing dot in domain/host name.
Ref: [RFC 1034](https://www.rfc-editor.org/rfc/rfc1034).
rfc_2782:
Domain/Host name is of type service record.
Ref: [RFC 2782](https://www.rfc-editor.org/rfc/rfc2782).
validate_scheme:
Function that validates URL scheme.
Returns:
(Literal[True]): If `value` is a valid url.
(ValidationError): If `value` is an invalid url.
"""
if not value or re.search(r"\s", value):
# url must not contain any white
# spaces, they must be encoded
return False
try:
scheme, netloc, path, query, fragment = urlsplit(value)
except ValueError:
return False
# RFC 8089: a "file" URL's authority is commonly empty or "localhost",
# neither of which is a hostname `_validate_netloc` would accept.
is_local_file = scheme == "file" and netloc in ("", "localhost")
return (
validate_scheme(scheme)
and (
is_local_file
or _validate_netloc(
netloc,
skip_ipv6_addr,
skip_ipv4_addr,
may_have_port,
simple_host,
consider_tld,
private,
rfc_1034,
rfc_2782,
)
)
and _validate_optionals(path, query, fragment, strict_query)
)