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
|
import os
import posixpath
import re
import urllib.parse
from typing import TYPE_CHECKING
from pip._internal.utils.filetypes import WHEEL_EXTENSION
from pip._internal.utils.misc import (
redact_auth_from_url,
split_auth_from_netloc,
splitext,
)
from pip._internal.utils.models import KeyBasedCompareMixin
from pip._internal.utils.urls import path_to_url, url_to_path
if TYPE_CHECKING:
from typing import Optional, Tuple, Union
from pip._internal.index.collector import HTMLPage
from pip._internal.utils.hashes import Hashes
class Link(KeyBasedCompareMixin):
"""Represents a parsed link from a Package Index's simple URL
"""
__slots__ = [
"_parsed_url",
"_url",
"comes_from",
"requires_python",
"yanked_reason",
"cache_link_parsing",
]
def __init__(
self,
url, # type: str
comes_from=None, # type: Optional[Union[str, HTMLPage]]
requires_python=None, # type: Optional[str]
yanked_reason=None, # type: Optional[str]
cache_link_parsing=True, # type: bool
):
# type: (...) -> None
"""
:param url: url of the resource pointed to (href of the link)
:param comes_from: instance of HTMLPage where the link was found,
or string.
:param requires_python: String containing the `Requires-Python`
metadata field, specified in PEP 345. This may be specified by
a data-requires-python attribute in the HTML link tag, as
described in PEP 503.
:param yanked_reason: the reason the file has been yanked, if the
file has been yanked, or None if the file hasn't been yanked.
This is the value of the "data-yanked" attribute, if present, in
a simple repository HTML link. If the file has been yanked but
no reason was provided, this should be the empty string. See
PEP 592 for more information and the specification.
:param cache_link_parsing: A flag that is used elsewhere to determine
whether resources retrieved from this link
should be cached. PyPI index urls should
generally have this set to False, for
example.
"""
# url can be a UNC windows share
if url.startswith('\\\\'):
url = path_to_url(url)
self._parsed_url = urllib.parse.urlsplit(url)
# Store the url as a private attribute to prevent accidentally
# trying to set a new value.
self._url = url
self.comes_from = comes_from
self.requires_python = requires_python if requires_python else None
self.yanked_reason = yanked_reason
super().__init__(key=url, defining_class=Link)
self.cache_link_parsing = cache_link_parsing
def __str__(self):
# type: () -> str
if self.requires_python:
rp = f' (requires-python:{self.requires_python})'
else:
rp = ''
if self.comes_from:
return '{} (from {}){}'.format(
redact_auth_from_url(self._url), self.comes_from, rp)
else:
return redact_auth_from_url(str(self._url))
def __repr__(self):
# type: () -> str
return f'<Link {self}>'
@property
def url(self):
# type: () -> str
return self._url
@property
def filename(self):
# type: () -> str
path = self.path.rstrip('/')
name = posixpath.basename(path)
if not name:
# Make sure we don't leak auth information if the netloc
# includes a username and password.
netloc, user_pass = split_auth_from_netloc(self.netloc)
return netloc
name = urllib.parse.unquote(name)
assert name, (
'URL {self._url!r} produced no filename'.format(**locals()))
return name
@property
def file_path(self):
# type: () -> str
return url_to_path(self.url)
@property
def scheme(self):
# type: () -> str
return self._parsed_url.scheme
@property
def netloc(self):
# type: () -> str
"""
This can contain auth information.
"""
return self._parsed_url.netloc
@property
def path(self):
# type: () -> str
return urllib.parse.unquote(self._parsed_url.path)
def splitext(self):
# type: () -> Tuple[str, str]
return splitext(posixpath.basename(self.path.rstrip('/')))
@property
def ext(self):
# type: () -> str
return self.splitext()[1]
@property
def url_without_fragment(self):
# type: () -> str
scheme, netloc, path, query, fragment = self._parsed_url
return urllib.parse.urlunsplit((scheme, netloc, path, query, None))
_egg_fragment_re = re.compile(r'[#&]egg=([^&]*)')
@property
def egg_fragment(self):
# type: () -> Optional[str]
match = self._egg_fragment_re.search(self._url)
if not match:
return None
return match.group(1)
_subdirectory_fragment_re = re.compile(r'[#&]subdirectory=([^&]*)')
@property
def subdirectory_fragment(self):
# type: () -> Optional[str]
match = self._subdirectory_fragment_re.search(self._url)
if not match:
return None
return match.group(1)
_hash_re = re.compile(
r'(sha1|sha224|sha384|sha256|sha512|md5)=([a-f0-9]+)'
)
@property
def hash(self):
# type: () -> Optional[str]
match = self._hash_re.search(self._url)
if match:
return match.group(2)
return None
@property
def hash_name(self):
# type: () -> Optional[str]
match = self._hash_re.search(self._url)
if match:
return match.group(1)
return None
@property
def show_url(self):
# type: () -> str
return posixpath.basename(self._url.split('#', 1)[0].split('?', 1)[0])
@property
def is_file(self):
# type: () -> bool
return self.scheme == 'file'
def is_existing_dir(self):
# type: () -> bool
return self.is_file and os.path.isdir(self.file_path)
@property
def is_wheel(self):
# type: () -> bool
return self.ext == WHEEL_EXTENSION
@property
def is_vcs(self):
# type: () -> bool
from pip._internal.vcs import vcs
return self.scheme in vcs.all_schemes
@property
def is_yanked(self):
# type: () -> bool
return self.yanked_reason is not None
@property
def has_hash(self):
# type: () -> bool
return self.hash_name is not None
def is_hash_allowed(self, hashes):
# type: (Optional[Hashes]) -> bool
"""
Return True if the link has a hash and it is allowed.
"""
if hashes is None or not self.has_hash:
return False
# Assert non-None so mypy knows self.hash_name and self.hash are str.
assert self.hash_name is not None
assert self.hash is not None
return hashes.is_hash_allowed(self.hash_name, hex_digest=self.hash)
|
