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
|
import logging
import mimetypes
import os
import pathlib
from typing import Callable, Iterable, Optional, Tuple
from pip._internal.models.candidate import InstallationCandidate
from pip._internal.models.link import Link
from pip._internal.utils.urls import path_to_url, url_to_path
from pip._internal.vcs import is_url
logger = logging.getLogger(__name__)
FoundCandidates = Iterable[InstallationCandidate]
FoundLinks = Iterable[Link]
CandidatesFromPage = Callable[[Link], Iterable[InstallationCandidate]]
PageValidator = Callable[[Link], bool]
class LinkSource:
@property
def link(self) -> Optional[Link]:
"""Returns the underlying link, if there's one."""
raise NotImplementedError()
def page_candidates(self) -> FoundCandidates:
"""Candidates found by parsing an archive listing HTML file."""
raise NotImplementedError()
def file_links(self) -> FoundLinks:
"""Links found by specifying archives directly."""
raise NotImplementedError()
def _is_html_file(file_url: str) -> bool:
return mimetypes.guess_type(file_url, strict=False)[0] == "text/html"
class _FlatDirectorySource(LinkSource):
"""Link source specified by ``--find-links=<path-to-dir>``.
This looks the content of the directory, and returns:
* ``page_candidates``: Links listed on each HTML file in the directory.
* ``file_candidates``: Archives in the directory.
"""
def __init__(
self,
candidates_from_page: CandidatesFromPage,
path: str,
) -> None:
self._candidates_from_page = candidates_from_page
self._path = pathlib.Path(os.path.realpath(path))
@property
def link(self) -> Optional[Link]:
return None
def page_candidates(self) -> FoundCandidates:
for path in self._path.iterdir():
url = path_to_url(str(path))
if not _is_html_file(url):
continue
yield from self._candidates_from_page(Link(url))
def file_links(self) -> FoundLinks:
for path in self._path.iterdir():
url = path_to_url(str(path))
if _is_html_file(url):
continue
yield Link(url)
class _LocalFileSource(LinkSource):
"""``--find-links=<path-or-url>`` or ``--[extra-]index-url=<path-or-url>``.
If a URL is supplied, it must be a ``file:`` URL. If a path is supplied to
the option, it is converted to a URL first. This returns:
* ``page_candidates``: Links listed on an HTML file.
* ``file_candidates``: The non-HTML file.
"""
def __init__(
self,
candidates_from_page: CandidatesFromPage,
link: Link,
) -> None:
self._candidates_from_page = candidates_from_page
self._link = link
@property
def link(self) -> Optional[Link]:
return self._link
def page_candidates(self) -> FoundCandidates:
if not _is_html_file(self._link.url):
return
yield from self._candidates_from_page(self._link)
def file_links(self) -> FoundLinks:
if _is_html_file(self._link.url):
return
yield self._link
class _RemoteFileSource(LinkSource):
"""``--find-links=<url>`` or ``--[extra-]index-url=<url>``.
This returns:
* ``page_candidates``: Links listed on an HTML file.
* ``file_candidates``: The non-HTML file.
"""
def __init__(
self,
candidates_from_page: CandidatesFromPage,
page_validator: PageValidator,
link: Link,
) -> None:
self._candidates_from_page = candidates_from_page
self._page_validator = page_validator
self._link = link
@property
def link(self) -> Optional[Link]:
return self._link
def page_candidates(self) -> FoundCandidates:
if not self._page_validator(self._link):
return
yield from self._candidates_from_page(self._link)
def file_links(self) -> FoundLinks:
yield self._link
class _IndexDirectorySource(LinkSource):
"""``--[extra-]index-url=<path-to-directory>``.
This is treated like a remote URL; ``candidates_from_page`` contains logic
for this by appending ``index.html`` to the link.
"""
def __init__(
self,
candidates_from_page: CandidatesFromPage,
link: Link,
) -> None:
self._candidates_from_page = candidates_from_page
self._link = link
@property
def link(self) -> Optional[Link]:
return self._link
def page_candidates(self) -> FoundCandidates:
yield from self._candidates_from_page(self._link)
def file_links(self) -> FoundLinks:
return ()
def build_source(
location: str,
*,
candidates_from_page: CandidatesFromPage,
page_validator: PageValidator,
expand_dir: bool,
cache_link_parsing: bool,
) -> Tuple[Optional[str], Optional[LinkSource]]:
path: Optional[str] = None
url: Optional[str] = None
if os.path.exists(location): # Is a local path.
url = path_to_url(location)
path = location
elif location.startswith("file:"): # A file: URL.
url = location
path = url_to_path(location)
elif is_url(location):
url = location
if url is None:
msg = (
"Location '%s' is ignored: "
"it is either a non-existing path or lacks a specific scheme."
)
logger.warning(msg, location)
return (None, None)
if path is None:
source: LinkSource = _RemoteFileSource(
candidates_from_page=candidates_from_page,
page_validator=page_validator,
link=Link(url, cache_link_parsing=cache_link_parsing),
)
return (url, source)
if os.path.isdir(path):
if expand_dir:
source = _FlatDirectorySource(
candidates_from_page=candidates_from_page,
path=path,
)
else:
source = _IndexDirectorySource(
candidates_from_page=candidates_from_page,
link=Link(url, cache_link_parsing=cache_link_parsing),
)
return (url, source)
elif os.path.isfile(path):
source = _LocalFileSource(
candidates_from_page=candidates_from_page,
link=Link(url, cache_link_parsing=cache_link_parsing),
)
return (url, source)
logger.warning(
"Location '%s' is ignored: it is neither a file nor a directory.",
location,
)
return (url, None)
|
