Repository navigation
Expand file tree
/
Copy pathtest_mimetypes.py
More file actions
444 lines (389 loc) · 19.3 KB
/
Copy pathtest_mimetypes.py
File metadata and controls
444 lines (389 loc) · 19.3 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
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
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
import io
import mimetypes
import os
import sys
import unittest.mock
from os import linesep
from test import support
from test.support import os_helper
from test.support.script_helper import run_python_until_end
from platform import win32_edition
try:
import _winapi
except ImportError:
_winapi = None
def setUpModule():
global knownfiles
knownfiles = mimetypes.knownfiles
# Tell it we don't know about external files:
mimetypes.knownfiles = []
mimetypes.inited = False
mimetypes._default_mime_types()
def tearDownModule():
# Restore knownfiles to its initial state
mimetypes.knownfiles = knownfiles
class MimeTypesTestCase(unittest.TestCase):
def setUp(self):
self.db = mimetypes.MimeTypes()
def test_case_sensitivity(self):
eq = self.assertEqual
eq(self.db.guess_file_type("foobar.html"), ("text/html", None))
eq(self.db.guess_type("scheme:foobar.html"), ("text/html", None))
eq(self.db.guess_file_type("foobar.HTML"), ("text/html", None))
eq(self.db.guess_type("scheme:foobar.HTML"), ("text/html", None))
eq(self.db.guess_file_type("foobar.tgz"), ("application/x-tar", "gzip"))
eq(self.db.guess_type("scheme:foobar.tgz"), ("application/x-tar", "gzip"))
eq(self.db.guess_file_type("foobar.TGZ"), ("application/x-tar", "gzip"))
eq(self.db.guess_type("scheme:foobar.TGZ"), ("application/x-tar", "gzip"))
eq(self.db.guess_file_type("foobar.tar.Z"), ("application/x-tar", "compress"))
eq(self.db.guess_type("scheme:foobar.tar.Z"), ("application/x-tar", "compress"))
eq(self.db.guess_file_type("foobar.tar.z"), (None, None))
eq(self.db.guess_type("scheme:foobar.tar.z"), (None, None))
def test_default_data(self):
eq = self.assertEqual
eq(self.db.guess_file_type("foo.html"), ("text/html", None))
eq(self.db.guess_file_type("foo.HTML"), ("text/html", None))
eq(self.db.guess_file_type("foo.tgz"), ("application/x-tar", "gzip"))
eq(self.db.guess_file_type("foo.tar.gz"), ("application/x-tar", "gzip"))
eq(self.db.guess_file_type("foo.tar.Z"), ("application/x-tar", "compress"))
eq(self.db.guess_file_type("foo.tar.bz2"), ("application/x-tar", "bzip2"))
eq(self.db.guess_file_type("foo.tar.xz"), ("application/x-tar", "xz"))
def test_data_urls(self):
eq = self.assertEqual
guess_type = self.db.guess_type
eq(guess_type("data:invalidDataWithoutComma"), (None, None))
eq(guess_type("data:,thisIsTextPlain"), ("text/plain", None))
eq(guess_type("data:;base64,thisIsTextPlain"), ("text/plain", None))
eq(guess_type("data:text/x-foo,thisIsTextXFoo"), ("text/x-foo", None))
def test_file_parsing(self):
eq = self.assertEqual
sio = io.StringIO("x-application/x-unittest pyunit\n")
self.db.readfp(sio)
eq(self.db.guess_file_type("foo.pyunit"),
("x-application/x-unittest", None))
eq(self.db.guess_extension("x-application/x-unittest"), ".pyunit")
def test_read_mime_types(self):
eq = self.assertEqual
# Unreadable file returns None
self.assertIsNone(mimetypes.read_mime_types("non-existent"))
with os_helper.temp_dir() as directory:
data = "x-application/x-unittest pyunit\n"
file = os.path.join(directory, "sample.mimetype")
with open(file, 'w', encoding="utf-8") as f:
f.write(data)
mime_dict = mimetypes.read_mime_types(file)
eq(mime_dict[".pyunit"], "x-application/x-unittest")
data = "x-application/x-unittest2 pyunit2\n"
file = os.path.join(directory, "sample2.mimetype")
with open(file, 'w', encoding="utf-8") as f:
f.write(data)
mime_dict = mimetypes.read_mime_types(os_helper.FakePath(file))
eq(mime_dict[".pyunit2"], "x-application/x-unittest2")
# bpo-41048: read_mime_types should read the rule file with 'utf-8' encoding.
# Not with locale encoding. _bootlocale has been imported because io.open(...)
# uses it.
data = "application/no-mans-land Fran\u00E7ais"
filename = "filename"
fp = io.StringIO(data)
with unittest.mock.patch.object(mimetypes, 'open',
return_value=fp) as mock_open:
mime_dict = mimetypes.read_mime_types(filename)
mock_open.assert_called_with(filename, encoding='utf-8')
eq(mime_dict[".Français"], "application/no-mans-land")
def test_non_standard_types(self):
eq = self.assertEqual
# First try strict
eq(self.db.guess_file_type('foo.xul', strict=True), (None, None))
eq(self.db.guess_extension('image/jpg', strict=True), None)
# And then non-strict
eq(self.db.guess_file_type('foo.xul', strict=False), ('text/xul', None))
eq(self.db.guess_file_type('foo.XUL', strict=False), ('text/xul', None))
eq(self.db.guess_file_type('foo.invalid', strict=False), (None, None))
eq(self.db.guess_extension('image/jpg', strict=False), '.jpg')
eq(self.db.guess_extension('image/JPG', strict=False), '.jpg')
def test_filename_with_url_delimiters(self):
# bpo-38449: URL delimiters cases should be handled also.
# They would have different mime types if interpreted as URL as
# compared to when interpreted as filename because of the semicolon.
eq = self.assertEqual
gzip_expected = ('application/x-tar', 'gzip')
for name in (
';1.tar.gz',
'?1.tar.gz',
'#1.tar.gz',
'#1#.tar.gz',
';1#.tar.gz',
';&1=123;?.tar.gz',
'?k1=v1&k2=v2.tar.gz',
):
for prefix in ('', '/', '\\',
'c:', 'c:/', 'c:\\', 'c:/d/', 'c:\\d\\',
'//share/server/', '\\\\share\\server\\'):
path = prefix + name
with self.subTest(path=path):
eq(self.db.guess_file_type(path), gzip_expected)
eq(self.db.guess_type(path), gzip_expected)
expected = (None, None) if os.name == 'nt' else gzip_expected
for prefix in ('//', '\\\\', '//share/', '\\\\share\\'):
path = prefix + name
with self.subTest(path=path):
eq(self.db.guess_file_type(path), expected)
eq(self.db.guess_type(path), expected)
eq(self.db.guess_file_type(r" \"\`;b&b&c |.tar.gz"), gzip_expected)
eq(self.db.guess_type(r" \"\`;b&b&c |.tar.gz"), gzip_expected)
eq(self.db.guess_file_type(r'foo/.tar.gz'), (None, 'gzip'))
eq(self.db.guess_type(r'foo/.tar.gz'), (None, 'gzip'))
expected = (None, 'gzip') if os.name == 'nt' else gzip_expected
eq(self.db.guess_file_type(r'foo\.tar.gz'), expected)
eq(self.db.guess_type(r'foo\.tar.gz'), expected)
eq(self.db.guess_type(r'scheme:foo\.tar.gz'), gzip_expected)
def test_url(self):
result = self.db.guess_type('http://example.com/host.html')
result = self.db.guess_type('http://host.html')
msg = 'URL only has a host name, not a file'
self.assertSequenceEqual(result, (None, None), msg)
result = self.db.guess_type('http://example.com/host.html')
msg = 'Should be text/html'
self.assertSequenceEqual(result, ('text/html', None), msg)
result = self.db.guess_type('http://example.com/host.html#x.tar')
self.assertSequenceEqual(result, ('text/html', None))
result = self.db.guess_type('http://example.com/host.html?q=x.tar')
self.assertSequenceEqual(result, ('text/html', None))
def test_guess_all_types(self):
# First try strict. Use a set here for testing the results because if
# test_urllib2 is run before test_mimetypes, global state is modified
# such that the 'all' set will have more items in it.
all = self.db.guess_all_extensions('text/plain', strict=True)
self.assertTrue(set(all) >= {'.bat', '.c', '.h', '.ksh', '.pl', '.txt'})
self.assertEqual(len(set(all)), len(all)) # no duplicates
# And now non-strict
all = self.db.guess_all_extensions('image/jpg', strict=False)
self.assertEqual(all, ['.jpg'])
# And now for no hits
all = self.db.guess_all_extensions('image/jpg', strict=True)
self.assertEqual(all, [])
# And now for type existing in both strict and non-strict mappings.
self.db.add_type('test-type', '.strict-ext')
self.db.add_type('test-type', '.non-strict-ext', strict=False)
all = self.db.guess_all_extensions('test-type', strict=False)
self.assertEqual(all, ['.strict-ext', '.non-strict-ext'])
all = self.db.guess_all_extensions('test-type')
self.assertEqual(all, ['.strict-ext'])
# Test that changing the result list does not affect the global state
all.append('.no-such-ext')
all = self.db.guess_all_extensions('test-type')
self.assertNotIn('.no-such-ext', all)
def test_encoding(self):
filename = support.findfile("mime.types")
mimes = mimetypes.MimeTypes([filename])
exts = mimes.guess_all_extensions('application/vnd.geocube+xml',
strict=True)
self.assertEqual(exts, ['.g3', '.g\xb3'])
def test_init_reinitializes(self):
# Issue 4936: make sure an init starts clean
# First, put some poison into the types table
mimetypes.add_type('foo/bar', '.foobar')
self.assertEqual(mimetypes.guess_extension('foo/bar'), '.foobar')
# Reinitialize
mimetypes.init()
# Poison should be gone.
self.assertEqual(mimetypes.guess_extension('foo/bar'), None)
@unittest.skipIf(sys.platform.startswith("win"), "Non-Windows only")
def test_guess_known_extensions(self):
# Issue 37529
# The test fails on Windows because Windows adds mime types from the Registry
# and that creates some duplicates.
from mimetypes import types_map
for v in types_map.values():
self.assertIsNotNone(mimetypes.guess_extension(v))
def test_preferred_extension(self):
def check_extensions():
for mime_type, ext in (
("application/epub+zip", ".epub"),
("application/octet-stream", ".bin"),
("application/ogg", ".ogx"),
("application/postscript", ".ps"),
("application/vnd.apple.mpegurl", ".m3u"),
("application/vnd.ms-excel", ".xls"),
("application/vnd.ms-fontobject", ".eot"),
("application/vnd.ms-powerpoint", ".ppt"),
("application/vnd.oasis.opendocument.graphics", ".odg"),
("application/vnd.oasis.opendocument.presentation", ".odp"),
("application/vnd.oasis.opendocument.spreadsheet", ".ods"),
("application/vnd.oasis.opendocument.text", ".odt"),
("application/vnd.openxmlformats-officedocument.presentationml.presentation", ".pptx"),
("application/vnd.openxmlformats-officedocument.spreadsheetml.sheet", ".xlsx"),
("application/vnd.openxmlformats-officedocument.wordprocessingml.document", ".docx"),
("application/x-texinfo", ".texi"),
("application/x-troff", ".roff"),
("application/xml", ".xsl"),
("audio/flac", ".flac"),
("audio/matroska", ".mka"),
("audio/mp4", ".m4a"),
("audio/mpeg", ".mp3"),
("audio/ogg", ".ogg"),
("audio/vnd.wave", ".wav"),
("audio/webm", ".weba"),
("font/otf", ".otf"),
("font/ttf", ".ttf"),
("font/woff", ".woff"),
("font/woff2", ".woff2"),
("image/avif", ".avif"),
("image/emf", ".emf"),
("image/fits", ".fits"),
("image/g3fax", ".g3"),
("image/jp2", ".jp2"),
("image/jpeg", ".jpg"),
("image/jpm", ".jpm"),
("image/t38", ".t38"),
("image/tiff", ".tiff"),
("image/tiff-fx", ".tfx"),
("image/webp", ".webp"),
("image/wmf", ".wmf"),
("message/rfc822", ".eml"),
("text/html", ".html"),
("text/plain", ".txt"),
("text/rtf", ".rtf"),
("text/x-rst", ".rst"),
("video/matroska", ".mkv"),
("video/matroska-3d", ".mk3d"),
("video/mpeg", ".mpeg"),
("video/ogg", ".ogv"),
("video/quicktime", ".mov"),
("video/vnd.avi", ".avi"),
):
with self.subTest(mime_type=mime_type, ext=ext):
self.assertEqual(mimetypes.guess_extension(mime_type), ext)
check_extensions()
mimetypes.init()
check_extensions()
def test_init_stability(self):
mimetypes.init()
suffix_map = mimetypes.suffix_map
encodings_map = mimetypes.encodings_map
types_map = mimetypes.types_map
common_types = mimetypes.common_types
mimetypes.init()
self.assertIsNot(suffix_map, mimetypes.suffix_map)
self.assertIsNot(encodings_map, mimetypes.encodings_map)
self.assertIsNot(types_map, mimetypes.types_map)
self.assertIsNot(common_types, mimetypes.common_types)
self.assertEqual(suffix_map, mimetypes.suffix_map)
self.assertEqual(encodings_map, mimetypes.encodings_map)
self.assertEqual(types_map, mimetypes.types_map)
self.assertEqual(common_types, mimetypes.common_types)
def test_path_like_ob(self):
filename = "LICENSE.txt"
filepath = os_helper.FakePath(filename)
filepath_with_abs_dir = os_helper.FakePath('/dir/'+filename)
filepath_relative = os_helper.FakePath('../dir/'+filename)
path_dir = os_helper.FakePath('./')
expected = self.db.guess_file_type(filename)
self.assertEqual(self.db.guess_file_type(filepath), expected)
self.assertEqual(self.db.guess_type(filepath), expected)
self.assertEqual(self.db.guess_file_type(
filepath_with_abs_dir), expected)
self.assertEqual(self.db.guess_type(
filepath_with_abs_dir), expected)
self.assertEqual(self.db.guess_file_type(filepath_relative), expected)
self.assertEqual(self.db.guess_type(filepath_relative), expected)
self.assertEqual(self.db.guess_file_type(path_dir), (None, None))
self.assertEqual(self.db.guess_type(path_dir), (None, None))
def test_bytes_path(self):
self.assertEqual(self.db.guess_file_type(b'foo.html'),
self.db.guess_file_type('foo.html'))
self.assertEqual(self.db.guess_file_type(b'foo.tar.gz'),
self.db.guess_file_type('foo.tar.gz'))
self.assertEqual(self.db.guess_file_type(b'foo.tgz'),
self.db.guess_file_type('foo.tgz'))
def test_keywords_args_api(self):
self.assertEqual(self.db.guess_file_type(
path="foo.html", strict=True), ("text/html", None))
self.assertEqual(self.db.guess_type(
url="scheme:foo.html", strict=True), ("text/html", None))
self.assertEqual(self.db.guess_all_extensions(
type='image/jpg', strict=True), [])
self.assertEqual(self.db.guess_extension(
type='image/jpg', strict=False), '.jpg')
@unittest.skipUnless(sys.platform.startswith("win"), "Windows only")
class Win32MimeTypesTestCase(unittest.TestCase):
def setUp(self):
# ensure all entries actually come from the Windows registry
self.original_types_map = mimetypes.types_map.copy()
mimetypes.types_map.clear()
mimetypes.init()
self.db = mimetypes.MimeTypes()
def tearDown(self):
# restore default settings
mimetypes.types_map.clear()
mimetypes.types_map.update(self.original_types_map)
@unittest.skipIf(win32_edition() in ('NanoServer', 'WindowsCoreHeadless', 'IoTEdgeOS'),
"MIME types registry keys unavailable")
def test_registry_parsing(self):
# the original, minimum contents of the MIME database in the
# Windows registry is undocumented AFAIK.
# Use file types that should *always* exist:
eq = self.assertEqual
eq(self.db.guess_type("foo.txt"), ("text/plain", None))
eq(self.db.guess_type("image.jpg"), ("image/jpeg", None))
eq(self.db.guess_type("image.png"), ("image/png", None))
@unittest.skipIf(not hasattr(_winapi, "_mimetypes_read_windows_registry"),
"read_windows_registry accelerator unavailable")
def test_registry_accelerator(self):
from_accel = {}
from_reg = {}
_winapi._mimetypes_read_windows_registry(
lambda v, k: from_accel.setdefault(k, set()).add(v)
)
mimetypes.MimeTypes._read_windows_registry(
lambda v, k: from_reg.setdefault(k, set()).add(v)
)
self.assertEqual(list(from_reg), list(from_accel))
for k in from_reg:
self.assertEqual(from_reg[k], from_accel[k])
class MiscTestCase(unittest.TestCase):
def test__all__(self):
support.check__all__(self, mimetypes)
class MimetypesCliTestCase(unittest.TestCase):
def mimetypes_cmd(cls, *args, **kwargs):
result, _ = run_python_until_end('-m', 'mimetypes', *args)
return result.rc, result.out.decode(), result.err.decode()
def test_help_option(self):
retcode, out, err = self.mimetypes_cmd('-h')
self.assertEqual(retcode, 0)
self.assertStartsWith(out, 'usage: ')
self.assertEqual(err, '')
def test_invalid_option(self):
retcode, out, err = self.mimetypes_cmd('--invalid')
self.assertEqual(retcode, 2)
self.assertEqual(out, '')
self.assertStartsWith(err, 'usage: ')
def test_guess_extension(self):
retcode, out, err = self.mimetypes_cmd('-l', '-e', 'image/jpg')
self.assertEqual(retcode, 0)
self.assertEqual(out, f'.jpg{linesep}')
self.assertEqual(err, '')
retcode, out, err = self.mimetypes_cmd('-e', 'image/jpg')
self.assertEqual(retcode, 1)
self.assertEqual(out, '')
self.assertEqual(err, f'error: unknown type image/jpg{linesep}')
retcode, out, err = self.mimetypes_cmd('-e', 'image/jpeg')
self.assertEqual(retcode, 0)
self.assertEqual(out, f'.jpg{linesep}')
self.assertEqual(err, '')
def test_guess_type(self):
retcode, out, err = self.mimetypes_cmd('-l', 'foo.webp')
self.assertEqual(retcode, 0)
self.assertEqual(out, f'type: image/webp encoding: None{linesep}')
self.assertEqual(err, '')
@unittest.skipIf(
sys.platform == 'darwin',
'macOS lists common_types in mime.types thus making them always known'
)
def test_guess_type_conflicting_with_mimetypes(self):
retcode, out, err = self.mimetypes_cmd('foo.pic')
self.assertEqual(retcode, 1)
self.assertEqual(out, '')
self.assertEqual(err, f'error: media type unknown for foo.pic{linesep}')
if __name__ == "__main__":
unittest.main()