File: test_whitenoise.py

package info (click to toggle)
python-whitenoise 6.8.2-1
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid, trixie
  • size: 472 kB
  • sloc: python: 2,040; makefile: 132; javascript: 10
file content (383 lines) | stat: -rw-r--r-- 12,684 bytes parent folder | download
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
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
from __future__ import annotations

import os
import re
import shutil
import stat
import sys
import tempfile
import warnings
from contextlib import closing
from urllib.parse import urljoin
from wsgiref.headers import Headers
from wsgiref.simple_server import demo_app

import pytest

from tests.utils import AppServer
from tests.utils import Files
from whitenoise import WhiteNoise
from whitenoise.responders import StaticFile


@pytest.fixture(scope="module")
def files():
    return Files(
        "assets",
        js="subdir/javascript.js",
        gzip="compressed.css",
        gzipped="compressed.css.gz",
        custom_mime="custom-mime.foobar",
        index="with-index/index.html",
    )


@pytest.fixture(params=[True, False], scope="module")
def application(request, files):
    # When run all test the application with autorefresh enabled and disabled
    # When testing autorefresh mode we first initialise the application with an
    # empty temporary directory and then copy in the files afterwards so we can
    # test that files added after initialisation are picked up correctly
    if request.param:
        tmp = tempfile.mkdtemp()
        app = _init_application(tmp, autorefresh=True)
        copytree(files.directory, tmp)
        yield app
        shutil.rmtree(tmp)
    else:
        yield _init_application(files.directory)


def _init_application(directory, **kwargs):
    def custom_headers(headers, path, url):
        if url.endswith(".css"):
            headers["X-Is-Css-File"] = "True"

    return WhiteNoise(
        demo_app,
        root=directory,
        max_age=1000,
        mimetypes={".foobar": "application/x-foo-bar"},
        add_headers_function=custom_headers,
        index_file=True,
        **kwargs,
    )


@pytest.fixture(scope="module")
def server(application):
    app_server = AppServer(application)
    with closing(app_server):
        yield app_server


def assert_is_default_response(response):
    assert "Hello world!" in response.text


def test_get_file(server, files):
    response = server.get(files.js_url)
    assert response.content == files.js_content
    assert re.search(r"text/javascript\b", response.headers["Content-Type"])
    assert re.search(r'.*\bcharset="utf-8"', response.headers["Content-Type"])


def test_get_not_accept_gzip(server, files):
    response = server.get(files.gzip_url, headers={"Accept-Encoding": ""})
    assert response.content == files.gzip_content
    assert "Content-Encoding" not in response.headers
    assert response.headers["Vary"] == "Accept-Encoding"


def test_get_accept_star(server, files):
    response = server.get(files.gzip_url, headers={"Accept-Encoding": "*"})
    assert response.content == files.gzip_content
    assert "Content-Encoding" not in response.headers
    assert response.headers["Vary"] == "Accept-Encoding"


def test_get_accept_missing(server, files):
    response = server.get(
        files.gzip_url,
        # Using None is required to override requests’ default Accept-Encoding
        headers={"Accept-Encoding": None},
    )
    assert response.content == files.gzip_content
    assert "Content-Encoding" not in response.headers
    assert response.headers["Vary"] == "Accept-Encoding"


def test_get_accept_gzip(server, files):
    response = server.get(files.gzip_url)
    assert response.content == files.gzip_content
    assert response.headers["Content-Encoding"] == "gzip"
    assert response.headers["Vary"] == "Accept-Encoding"


def test_cannot_directly_request_gzipped_file(server, files):
    response = server.get(files.gzip_url + ".gz")
    assert_is_default_response(response)


def test_not_modified_exact(server, files):
    response = server.get(files.js_url)
    last_mod = response.headers["Last-Modified"]
    response = server.get(files.js_url, headers={"If-Modified-Since": last_mod})
    assert response.status_code == 304


def test_not_modified_future(server, files):
    last_mod = "Fri, 11 Apr 2100 11:47:06 GMT"
    response = server.get(files.js_url, headers={"If-Modified-Since": last_mod})
    assert response.status_code == 304


def test_modified(server, files):
    last_mod = "Fri, 11 Apr 2001 11:47:06 GMT"
    response = server.get(files.js_url, headers={"If-Modified-Since": last_mod})
    assert response.status_code == 200


def test_modified_mangled_date_firefox_91_0b3(server, files):
    last_mod = "Fri, 16 Jul 2021 09:09:1626426577S GMT"
    response = server.get(files.js_url, headers={"If-Modified-Since": last_mod})
    assert response.status_code == 200


def test_etag_matches(server, files):
    response = server.get(files.js_url)
    etag = response.headers["ETag"]
    response = server.get(files.js_url, headers={"If-None-Match": etag})
    assert response.status_code == 304


def test_etag_doesnt_match(server, files):
    etag = '"594bd1d1-36"'
    response = server.get(files.js_url, headers={"If-None-Match": etag})
    assert response.status_code == 200


def test_etag_overrules_modified_since(server, files):
    """
    Browsers send both headers so it's important that the ETag takes precedence
    over the last modified time, so that deploy-rollbacks are handled correctly.
    """
    headers = {
        "If-None-Match": '"594bd1d1-36"',
        "If-Modified-Since": "Fri, 11 Apr 2100 11:47:06 GMT",
    }
    response = server.get(files.js_url, headers=headers)
    assert response.status_code == 200


def test_max_age(server, files):
    response = server.get(files.js_url)
    assert response.headers["Cache-Control"], "max-age=1000 == public"


def test_other_requests_passed_through(server):
    response = server.get("/%s/not/static" % AppServer.PREFIX)
    assert_is_default_response(response)


def test_non_ascii_requests_safely_ignored(server):
    response = server.get(f"/{AppServer.PREFIX}/test\u263A")
    assert_is_default_response(response)


def test_add_under_prefix(server, files, application):
    prefix = "/prefix"
    application.add_files(files.directory, prefix=prefix)
    response = server.get(f"/{AppServer.PREFIX}{prefix}/{files.js_path}")
    assert response.content == files.js_content


def test_response_has_allow_origin_header(server, files):
    response = server.get(files.js_url)
    assert response.headers.get("Access-Control-Allow-Origin") == "*"


def test_response_has_correct_content_length_header(server, files):
    response = server.get(files.js_url)
    length = int(response.headers["Content-Length"])
    assert length == len(files.js_content)


def test_gzip_response_has_correct_content_length_header(server, files):
    response = server.get(files.gzip_url)
    length = int(response.headers["Content-Length"])
    assert length == len(files.gzipped_content)


def test_post_request_returns_405(server, files):
    response = server.request("post", files.js_url)
    assert response.status_code == 405


def test_head_request_has_no_body(server, files):
    response = server.request("head", files.js_url)
    assert response.status_code == 200
    assert not response.content


def test_custom_mimetype(server, files):
    response = server.get(files.custom_mime_url)
    assert re.search(r"application/x-foo-bar\b", response.headers["Content-Type"])


def test_custom_headers(server, files):
    response = server.get(files.gzip_url)
    assert response.headers["x-is-css-file"] == "True"


def test_index_file_served_at_directory_path(server, files):
    directory_url = files.index_url.rpartition("/")[0] + "/"
    response = server.get(directory_url)
    assert response.content == files.index_content


def test_index_file_path_redirected(server, files):
    directory_url = files.index_url.rpartition("/")[0] + "/"
    response = server.get(files.index_url, allow_redirects=False)
    location = urljoin(files.index_url, response.headers["Location"])
    assert response.status_code == 302
    assert location == directory_url


def test_directory_path_without_trailing_slash_redirected(server, files):
    directory_url = files.index_url.rpartition("/")[0] + "/"
    no_slash_url = directory_url.rstrip("/")
    response = server.get(no_slash_url, allow_redirects=False)
    location = urljoin(no_slash_url, response.headers["Location"])
    assert response.status_code == 302
    assert location == directory_url


def test_request_initial_bytes(server, files):
    response = server.get(files.js_url, headers={"Range": "bytes=0-13"})
    assert response.content == files.js_content[0:14]


def test_request_trailing_bytes(server, files):
    response = server.get(files.js_url, headers={"Range": "bytes=-3"})
    assert response.content == files.js_content[-3:]


def test_request_middle_bytes(server, files):
    response = server.get(files.js_url, headers={"Range": "bytes=21-30"})
    assert response.content == files.js_content[21:31]


def test_overlong_ranges_truncated(server, files):
    response = server.get(files.js_url, headers={"Range": "bytes=21-100000"})
    assert response.content == files.js_content[21:]


def test_overlong_trailing_ranges_return_entire_file(server, files):
    response = server.get(files.js_url, headers={"Range": "bytes=-100000"})
    assert response.content == files.js_content


def test_out_of_range_error(server, files):
    response = server.get(files.js_url, headers={"Range": "bytes=10000-11000"})
    assert response.status_code == 416
    assert response.headers["Content-Range"] == "bytes */%s" % len(files.js_content)


def test_warn_about_missing_directories(application):
    # This is the one minor behavioural difference when autorefresh is
    # enabled: we don't warn about missing directories as these can be
    # created after the application is started
    if application.autorefresh:
        pytest.skip()
    with warnings.catch_warnings(record=True) as warning_list:
        application.add_files("/dev/null/nosuchdir\u2713")
    assert len(warning_list) == 1


def test_handles_missing_path_info_key(application):
    response = application(environ={}, start_response=lambda *args: None)
    assert response


def test_cant_read_absolute_paths_on_windows(server):
    response = server.get(rf"/{AppServer.PREFIX}/C:/Windows/System.ini")
    assert_is_default_response(response)


def test_no_error_on_very_long_filename(server):
    response = server.get("/blah" * 1000)
    assert response.status_code != 500


def copytree(src, dst):
    for name in os.listdir(src):
        src_path = os.path.join(src, name)
        dst_path = os.path.join(dst, name)
        if os.path.isdir(src_path):
            shutil.copytree(src_path, dst_path)
        else:
            shutil.copy2(src_path, dst_path)


def test_immutable_file_test_accepts_regex():
    instance = WhiteNoise(None, immutable_file_test=r"\.test$")
    assert instance.immutable_file_test("", "/myfile.test")
    assert not instance.immutable_file_test("", "file.test.txt")


@pytest.mark.skipif(sys.version_info < (3, 4), reason="Pathlib was added in Python 3.4")
def test_directory_path_can_be_pathlib_instance():
    from pathlib import Path

    root = Path(Files("root").directory)
    # Check we can construct instance without it blowing up
    WhiteNoise(None, root=root, autorefresh=True)


def fake_stat_entry(
    st_mode: int = stat.S_IFREG, st_size: int = 1024, st_mtime: int = 0
) -> os.stat_result:
    return os.stat_result(
        (
            st_mode,
            0,  # st_ino
            0,  # st_dev
            0,  # st_nlink
            0,  # st_uid
            0,  # st_gid
            st_size,
            0,  # st_atime
            st_mtime,
            0,  # st_ctime
        )
    )


def test_last_modified_not_set_when_mtime_is_zero():
    stat_cache = {__file__: fake_stat_entry()}
    responder = StaticFile(__file__, [], stat_cache=stat_cache)
    response = responder.get_response("GET", {})
    response.file.close()
    headers_dict = Headers(response.headers)
    assert "Last-Modified" not in headers_dict
    assert "ETag" not in headers_dict


def test_file_size_matches_range_with_range_header():
    stat_cache = {__file__: fake_stat_entry()}
    responder = StaticFile(__file__, [], stat_cache=stat_cache)
    response = responder.get_response("GET", {"HTTP_RANGE": "bytes=0-13"})
    file_size = len(response.file.read())
    assert file_size == 14


def test_chunked_file_size_matches_range_with_range_header():
    stat_cache = {__file__: fake_stat_entry()}
    responder = StaticFile(__file__, [], stat_cache=stat_cache)
    response = responder.get_response("GET", {"HTTP_RANGE": "bytes=0-13"})
    file_size = 0
    assert response.file is not None
    while response.file.read(1):
        file_size += 1
    assert file_size == 14