forked from huggingface/datasets
-
Notifications
You must be signed in to change notification settings - Fork 0
/
test_streaming_download_manager.py
715 lines (624 loc) · 25.8 KB
/
test_streaming_download_manager.py
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
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
import json
import os
import re
from pathlib import Path
import pytest
from fsspec.spec import AbstractBufferedFile, AbstractFileSystem
import datasets
from datasets.filesystems import COMPRESSION_FILESYSTEMS
from datasets.utils.streaming_download_manager import (
StreamingDownloadManager,
_as_posix,
_get_extraction_protocol,
xbasename,
xgetsize,
xglob,
xisdir,
xisfile,
xjoin,
xlistdir,
xopen,
xpathglob,
xpathjoin,
xpathname,
xpathopen,
xpathparent,
xpathrglob,
xpathstem,
xpathsuffix,
xrelpath,
xsplitext,
)
from .utils import require_lz4, require_zstandard
TEST_URL = "https://huggingface.co/datasets/lhoestq/test/raw/main/some_text.txt"
TEST_URL_CONTENT = "foo\nbar\nfoobar"
TEST_GG_DRIVE_FILENAME = "train.tsv"
TEST_GG_DRIVE_URL = "https://drive.google.com/uc?export=download&id=17bOgBDc3hRCoPZ89EYtKDzK-yXAWat94"
TEST_GG_DRIVE_GZIPPED_URL = "https://drive.google.com/uc?export=download&id=1Bt4Garpf0QLiwkJhHJzXaVa0I0H5Qhwz"
TEST_GG_DRIVE_ZIPPED_URL = "https://drive.google.com/uc?export=download&id=1k92sUfpHxKq8PXWRr7Y5aNHXwOCNUmqh"
TEST_GG_DRIVE_CONTENT = """\
pokemon_name, type
Charmander, fire
Squirtle, water
Bulbasaur, grass"""
class DummyTestFS(AbstractFileSystem):
protocol = "mock"
_file_class = AbstractBufferedFile
_fs_contents = (
{"name": "top_level", "type": "directory"},
{"name": "top_level/second_level", "type": "directory"},
{"name": "top_level/second_level/date=2019-10-01", "type": "directory"},
{
"name": "top_level/second_level/date=2019-10-01/a.parquet",
"type": "file",
"size": 100,
},
{
"name": "top_level/second_level/date=2019-10-01/b.parquet",
"type": "file",
"size": 100,
},
{"name": "top_level/second_level/date=2019-10-02", "type": "directory"},
{
"name": "top_level/second_level/date=2019-10-02/a.parquet",
"type": "file",
"size": 100,
},
{"name": "top_level/second_level/date=2019-10-04", "type": "directory"},
{
"name": "top_level/second_level/date=2019-10-04/a.parquet",
"type": "file",
"size": 100,
},
{"name": "misc", "type": "directory"},
{"name": "misc/foo.txt", "type": "file", "size": 100},
{"name": "glob_test", "type": "directory", "size": 0},
{"name": "glob_test/hat", "type": "directory", "size": 0},
{"name": "glob_test/hat/^foo.txt", "type": "file", "size": 100},
{"name": "glob_test/dollar", "type": "directory", "size": 0},
{"name": "glob_test/dollar/$foo.txt", "type": "file", "size": 100},
{"name": "glob_test/lbrace", "type": "directory", "size": 0},
{"name": "glob_test/lbrace/{foo.txt", "type": "file", "size": 100},
{"name": "glob_test/rbrace", "type": "directory", "size": 0},
{"name": "glob_test/rbrace/}foo.txt", "type": "file", "size": 100},
)
def __getitem__(self, name):
for item in self._fs_contents:
if item["name"] == name:
return item
raise IndexError(f"{name} not found!")
def ls(self, path, detail=True, refresh=True, **kwargs):
if kwargs.pop("strip_proto", True):
path = self._strip_protocol(path)
files = not refresh and self._ls_from_cache(path)
if not files:
files = [file for file in self._fs_contents if path == self._parent(file["name"])]
files.sort(key=lambda file: file["name"])
self.dircache[path.rstrip("/")] = files
if detail:
return files
return [file["name"] for file in files]
@classmethod
def get_test_paths(cls, start_with=""):
"""Helper to return directory and file paths with no details"""
all = [file["name"] for file in cls._fs_contents if file["name"].startswith(start_with)]
return all
def _open(
self,
path,
mode="rb",
block_size=None,
autocommit=True,
cache_options=None,
**kwargs,
):
return self._file_class(
self,
path,
mode,
block_size,
autocommit,
cache_options=cache_options,
**kwargs,
)
@pytest.fixture
def mock_fsspec(monkeypatch):
dummy_registry = datasets.utils.streaming_download_manager.fsspec.registry.target.copy()
dummy_registry["mock"] = DummyTestFS
monkeypatch.setattr("datasets.utils.streaming_download_manager.fsspec.registry.target", dummy_registry)
def _readd_double_slash_removed_by_path(path_as_posix: str) -> str:
"""Path(...) on an url path like zip://file.txt::http://host.com/data.zip
converts the :// to :/
This function readds the ://
It handles cases like:
- https://host.com/data.zip
- C://data.zip
- zip://file.txt::https://host.com/data.zip
- zip://file.txt::/Users/username/data.zip
- zip://file.txt::C://data.zip
Args:
path_as_posix (str): output of Path(...).as_posix()
Returns:
str: the url path with :// instead of :/
"""
return re.sub("([A-z]:/)([A-z:])", r"\g<1>/\g<2>", path_as_posix)
@pytest.mark.parametrize(
"input_path, expected_path",
[("zip:/test.txt::/Users/username/bar.zip", "zip://test.txt::/Users/username/bar.zip")],
)
def test_as_posix(input_path, expected_path):
assert _as_posix(Path(input_path)) == expected_path
@pytest.mark.parametrize(
"input_path, paths_to_join, expected_path",
[
(str(Path(__file__).resolve().parent), (Path(__file__).name,), str(Path(__file__).resolve())),
("https://host.com/archive.zip", ("file.txt",), "https://host.com/archive.zip/file.txt"),
(
"zip://::https://host.com/archive.zip",
("file.txt",),
"zip://file.txt::https://host.com/archive.zip",
),
(
"zip://folder::https://host.com/archive.zip",
("file.txt",),
"zip://folder/file.txt::https://host.com/archive.zip",
),
(
".",
("file.txt",),
"file.txt",
),
(
Path().resolve().as_posix(),
("file.txt",),
(Path().resolve() / "file.txt").as_posix(),
),
],
)
def test_xjoin(input_path, paths_to_join, expected_path):
output_path = xjoin(input_path, *paths_to_join)
output_path = _readd_double_slash_removed_by_path(Path(output_path).as_posix())
assert output_path == _readd_double_slash_removed_by_path(Path(expected_path).as_posix())
output_path = xpathjoin(Path(input_path), *paths_to_join)
assert output_path == Path(expected_path)
@pytest.mark.parametrize(
"input_path, expected_path",
[
(str(Path(__file__).resolve()), str(Path(__file__).resolve().parent)),
("https://host.com/archive.zip", "https://host.com"),
(
"zip://file.txt::https://host.com/archive.zip",
"zip://::https://host.com/archive.zip",
),
(
"zip://folder/file.txt::https://host.com/archive.zip",
"zip://folder::https://host.com/archive.zip",
),
],
)
def test_xdirname(input_path, expected_path):
from datasets.utils.streaming_download_manager import xdirname
output_path = xdirname(input_path)
output_path = _readd_double_slash_removed_by_path(Path(output_path).as_posix())
assert output_path == _readd_double_slash_removed_by_path(Path(expected_path).as_posix())
@pytest.mark.parametrize(
"input_path, expected_path_and_ext",
[
(
str(Path(__file__).resolve()),
(str(Path(__file__).resolve().with_suffix("")), str(Path(__file__).resolve().suffix)),
),
("https://host.com/archive.zip", ("https://host.com/archive", ".zip")),
("zip://file.txt::https://host.com/archive.zip", ("zip://file::https://host.com/archive.zip", ".txt")),
("zip://folder::https://host.com/archive.zip", ("zip://folder::https://host.com/archive.zip", "")),
("zip://::https://host.com/archive.zip", ("zip://::https://host.com/archive.zip", "")),
],
)
def test_xsplitext(input_path, expected_path_and_ext):
output_path, ext = xsplitext(input_path)
expected_path, expected_ext = expected_path_and_ext
output_path = _readd_double_slash_removed_by_path(Path(output_path).as_posix())
expected_path = _readd_double_slash_removed_by_path(Path(expected_path).as_posix())
assert output_path == expected_path
assert ext == expected_ext
def test_xopen_local(text_path):
with xopen(text_path, "r", encoding="utf-8") as f, open(text_path, encoding="utf-8") as expected_file:
assert list(f) == list(expected_file)
with xpathopen(Path(text_path), "r", encoding="utf-8") as f, open(text_path, encoding="utf-8") as expected_file:
assert list(f) == list(expected_file)
def test_xopen_remote():
with xopen(TEST_URL, "r", encoding="utf-8") as f:
assert list(f) == TEST_URL_CONTENT.splitlines(keepends=True)
with xpathopen(Path(TEST_URL), "r", encoding="utf-8") as f:
assert list(f) == TEST_URL_CONTENT.splitlines(keepends=True)
@pytest.mark.parametrize(
"input_path, expected_paths",
[
("tmp_path", ["file1.txt", "file2.txt"]),
("mock://", ["glob_test", "misc", "top_level"]),
("mock://top_level", ["second_level"]),
("mock://top_level/second_level/date=2019-10-01", ["a.parquet", "b.parquet"]),
],
)
def test_xlistdir(input_path, expected_paths, tmp_path, mock_fsspec):
if input_path.startswith("tmp_path"):
input_path = input_path.replace("/", os.sep).replace("tmp_path", str(tmp_path))
for file in ["file1.txt", "file2.txt"]:
(tmp_path / file).touch()
output_paths = sorted(xlistdir(input_path))
assert output_paths == expected_paths
@pytest.mark.parametrize(
"input_path, isdir",
[
("tmp_path", True),
("tmp_path/file.txt", False),
("mock://", True),
("mock://top_level", True),
("mock://dir_that_doesnt_exist", False),
],
)
def test_xisdir(input_path, isdir, tmp_path, mock_fsspec):
if input_path.startswith("tmp_path"):
input_path = input_path.replace("/", os.sep).replace("tmp_path", str(tmp_path))
(tmp_path / "file.txt").touch()
assert xisdir(input_path) == isdir
@pytest.mark.parametrize(
"input_path, isfile",
[
("tmp_path/file.txt", True),
("tmp_path/file_that_doesnt_exist.txt", False),
("mock://", False),
("mock://top_level/second_level/date=2019-10-01/a.parquet", True),
],
)
def test_xisfile(input_path, isfile, tmp_path, mock_fsspec):
if input_path.startswith("tmp_path"):
input_path = input_path.replace("/", os.sep).replace("tmp_path", str(tmp_path))
(tmp_path / "file.txt").touch()
assert xisfile(input_path) == isfile
@pytest.mark.parametrize(
"input_path, size",
[
("tmp_path/file.txt", 100),
("mock://", 0),
("mock://top_level/second_level/date=2019-10-01/a.parquet", 100),
],
)
def test_xgetsize(input_path, size, tmp_path, mock_fsspec):
if input_path.startswith("tmp_path"):
input_path = input_path.replace("/", os.sep).replace("tmp_path", str(tmp_path))
(tmp_path / "file.txt").touch()
(tmp_path / "file.txt").write_bytes(b"x" * 100)
assert xgetsize(input_path) == size
@pytest.mark.parametrize(
"input_path, expected_paths",
[
("tmp_path/*.txt", ["file1.txt", "file2.txt"]),
("mock://*", ["mock://glob_test", "mock://misc", "mock://top_level"]),
("mock://top_*", ["mock://top_level"]),
(
"mock://top_level/second_level/date=2019-10-0[1-4]",
[
"mock://top_level/second_level/date=2019-10-01",
"mock://top_level/second_level/date=2019-10-02",
"mock://top_level/second_level/date=2019-10-04",
],
),
(
"mock://top_level/second_level/date=2019-10-0[1-4]/*",
[
"mock://top_level/second_level/date=2019-10-01/a.parquet",
"mock://top_level/second_level/date=2019-10-01/b.parquet",
"mock://top_level/second_level/date=2019-10-02/a.parquet",
"mock://top_level/second_level/date=2019-10-04/a.parquet",
],
),
],
)
def test_xglob(input_path, expected_paths, tmp_path, mock_fsspec):
if input_path.startswith("tmp_path"):
input_path = input_path.replace("/", os.sep).replace("tmp_path", str(tmp_path))
expected_paths = [str(tmp_path / file) for file in expected_paths]
for file in ["file1.txt", "file2.txt", "README.md"]:
(tmp_path / file).touch()
output_paths = sorted(xglob(input_path))
assert output_paths == expected_paths
@pytest.mark.parametrize(
"input_path, start_path, expected_path",
[
("dir1/dir2/file.txt".replace("/", os.path.sep), "dir1", "dir2/file.txt".replace("/", os.path.sep)),
("dir1/dir2/file.txt".replace("/", os.path.sep), "dir1/dir2".replace("/", os.path.sep), "file.txt"),
("zip://file.txt::https://host.com/archive.zip", "zip://::https://host.com/archive.zip", "file.txt"),
(
"zip://folder/file.txt::https://host.com/archive.zip",
"zip://::https://host.com/archive.zip",
"folder/file.txt",
),
(
"zip://folder/file.txt::https://host.com/archive.zip",
"zip://folder::https://host.com/archive.zip",
"file.txt",
),
],
)
def test_xrelpath(input_path, start_path, expected_path):
output_path = xrelpath(input_path, start=start_path)
assert output_path == expected_path
@pytest.mark.parametrize(
"input_path, pattern, expected_paths",
[
("tmp_path", "*.txt", ["file1.txt", "file2.txt"]),
("mock://", "*", ["mock://glob_test", "mock://misc", "mock://top_level"]),
("mock://", "top_*", ["mock://top_level"]),
(
"mock://top_level/second_level",
"date=2019-10-0[1-4]",
[
"mock://top_level/second_level/date=2019-10-01",
"mock://top_level/second_level/date=2019-10-02",
"mock://top_level/second_level/date=2019-10-04",
],
),
(
"mock://top_level/second_level",
"date=2019-10-0[1-4]/*",
[
"mock://top_level/second_level/date=2019-10-01/a.parquet",
"mock://top_level/second_level/date=2019-10-01/b.parquet",
"mock://top_level/second_level/date=2019-10-02/a.parquet",
"mock://top_level/second_level/date=2019-10-04/a.parquet",
],
),
],
)
def test_xpathglob(input_path, pattern, expected_paths, tmp_path, mock_fsspec):
if input_path == "tmp_path":
input_path = tmp_path
expected_paths = [tmp_path / file for file in expected_paths]
for file in ["file1.txt", "file2.txt", "README.md"]:
(tmp_path / file).touch()
else:
expected_paths = [Path(file) for file in expected_paths]
output_paths = sorted(xpathglob(Path(input_path), pattern))
assert output_paths == expected_paths
@pytest.mark.parametrize(
"input_path, pattern, expected_paths",
[
("tmp_path", "*.txt", ["file1.txt", "file2.txt"]),
(
"mock://",
"date=2019-10-0[1-4]",
[
"mock://top_level/second_level/date=2019-10-01",
"mock://top_level/second_level/date=2019-10-02",
"mock://top_level/second_level/date=2019-10-04",
],
),
(
"mock://top_level",
"date=2019-10-0[1-4]",
[
"mock://top_level/second_level/date=2019-10-01",
"mock://top_level/second_level/date=2019-10-02",
"mock://top_level/second_level/date=2019-10-04",
],
),
(
"mock://",
"date=2019-10-0[1-4]/*",
[
"mock://top_level/second_level/date=2019-10-01/a.parquet",
"mock://top_level/second_level/date=2019-10-01/b.parquet",
"mock://top_level/second_level/date=2019-10-02/a.parquet",
"mock://top_level/second_level/date=2019-10-04/a.parquet",
],
),
(
"mock://top_level",
"date=2019-10-0[1-4]/*",
[
"mock://top_level/second_level/date=2019-10-01/a.parquet",
"mock://top_level/second_level/date=2019-10-01/b.parquet",
"mock://top_level/second_level/date=2019-10-02/a.parquet",
"mock://top_level/second_level/date=2019-10-04/a.parquet",
],
),
],
)
def test_xpathrglob(input_path, pattern, expected_paths, tmp_path, mock_fsspec):
if input_path == "tmp_path":
input_path = tmp_path
dir_path = tmp_path / "dir"
dir_path.mkdir()
expected_paths = [dir_path / file for file in expected_paths]
for file in ["file1.txt", "file2.txt", "README.md"]:
(dir_path / file).touch()
else:
expected_paths = [Path(file) for file in expected_paths]
output_paths = sorted(xpathrglob(Path(input_path), pattern))
assert output_paths == expected_paths
@pytest.mark.parametrize(
"input_path, expected_path",
[
(Path(__file__).resolve(), Path(__file__).resolve().parent),
(Path("https://host.com/archive.zip"), Path("https://host.com")),
(
Path("zip://file.txt::https://host.com/archive.zip"),
Path("zip://::https://host.com/archive.zip"),
),
(
Path("zip://folder/file.txt::https://host.com/archive.zip"),
Path("zip://folder::https://host.com/archive.zip"),
),
],
)
def test_xpathparent(input_path, expected_path):
output_path = xpathparent(input_path)
output_path = _readd_double_slash_removed_by_path(output_path.as_posix())
assert output_path == _readd_double_slash_removed_by_path(expected_path.as_posix())
@pytest.mark.parametrize(
"input_path, expected",
[
("zip://file.txt::https://host.com/archive.zip", "file.txt"),
("datasets/file.txt", "file.txt"),
((Path().resolve() / "file.txt").as_posix(), "file.txt"),
],
)
def test_xpathname(input_path, expected):
assert xpathname(Path(input_path)) == expected
@pytest.mark.parametrize(
"input_path, expected",
[
("zip://file.txt::https://host.com/archive.zip", "file"),
("file.txt", "file"),
((Path().resolve() / "file.txt").as_posix(), "file"),
],
)
def test_xpathstem(input_path, expected):
assert xpathstem(Path(input_path)) == expected
@pytest.mark.parametrize(
"input_path, expected",
[
("zip://file.txt::https://host.com/archive.zip", ".txt"),
("file.txt", ".txt"),
((Path().resolve() / "file.txt").as_posix(), ".txt"),
],
)
def test_xpathsuffix(input_path, expected):
assert xpathsuffix(Path(input_path)) == expected
@pytest.mark.parametrize("urlpath", [r"C:\\foo\bar.txt", "/foo/bar.txt", "https://f.oo/bar.txt"])
def test_streaming_dl_manager_download_dummy_path(urlpath):
dl_manager = StreamingDownloadManager()
assert dl_manager.download(urlpath) == urlpath
def test_streaming_dl_manager_download(text_path):
dl_manager = StreamingDownloadManager()
out = dl_manager.download(text_path)
assert out == text_path
with xopen(out, encoding="utf-8") as f, open(text_path, encoding="utf-8") as expected_file:
assert f.read() == expected_file.read()
@pytest.mark.parametrize("urlpath", [r"C:\\foo\bar.txt", "/foo/bar.txt", "https://f.oo/bar.txt"])
def test_streaming_dl_manager_download_and_extract_no_extraction(urlpath):
dl_manager = StreamingDownloadManager()
assert dl_manager.download_and_extract(urlpath) == urlpath
def test_streaming_dl_manager_extract(text_gz_path, text_path):
dl_manager = StreamingDownloadManager()
output_path = dl_manager.extract(text_gz_path)
path = os.path.basename(text_gz_path)
path = path[: path.rindex(".")]
assert output_path == f"gzip://{path}::{text_gz_path}"
fsspec_open_file = xopen(output_path, encoding="utf-8")
with fsspec_open_file as f, open(text_path, encoding="utf-8") as expected_file:
assert f.read() == expected_file.read()
def test_streaming_dl_manager_download_and_extract_with_extraction(text_gz_path, text_path):
dl_manager = StreamingDownloadManager()
output_path = dl_manager.download_and_extract(text_gz_path)
path = os.path.basename(text_gz_path)
path = path[: path.rindex(".")]
assert output_path == f"gzip://{path}::{text_gz_path}"
fsspec_open_file = xopen(output_path, encoding="utf-8")
with fsspec_open_file as f, open(text_path, encoding="utf-8") as expected_file:
assert f.read() == expected_file.read()
@pytest.mark.parametrize(
"input_path, filename, expected_path",
[("https://domain.org/archive.zip", "filename.jsonl", "zip://filename.jsonl::https://domain.org/archive.zip")],
)
def test_streaming_dl_manager_download_and_extract_with_join(input_path, filename, expected_path):
dl_manager = StreamingDownloadManager()
extracted_path = dl_manager.download_and_extract(input_path)
output_path = xjoin(extracted_path, filename)
assert output_path == expected_path
@require_zstandard
@require_lz4
@pytest.mark.parametrize("compression_fs_class", COMPRESSION_FILESYSTEMS)
def test_streaming_dl_manager_extract_all_supported_single_file_compression_types(
compression_fs_class, gz_file, xz_file, zstd_file, bz2_file, lz4_file, text_file
):
input_paths = {"gzip": gz_file, "xz": xz_file, "zstd": zstd_file, "bz2": bz2_file, "lz4": lz4_file}
input_path = str(input_paths[compression_fs_class.protocol])
dl_manager = StreamingDownloadManager()
output_path = dl_manager.extract(input_path)
path = os.path.basename(input_path)
path = path[: path.rindex(".")]
assert output_path == f"{compression_fs_class.protocol}://{path}::{input_path}"
fsspec_open_file = xopen(output_path, encoding="utf-8")
with fsspec_open_file as f, open(text_file, encoding="utf-8") as expected_file:
assert f.read() == expected_file.read()
@pytest.mark.parametrize(
"urlpath, expected_protocol",
[
("zip://train-00000.json.gz::https://foo.bar/data.zip", "gzip"),
("https://foo.bar/train.json.gz?dl=1", "gzip"),
("http://opus.nlpl.eu/download.php?f=Bianet/v1/moses/en-ku.txt.zip", "zip"),
("https://github.com/user/what-time-is-it/blob/master/gutenberg_time_phrases.zip?raw=true", "zip"),
("https://github.com/user/repo/blob/master/data/morph_train.tsv?raw=true", None),
("https://repo.org/bitstream/handle/20.500.12185/346/annotated_corpus.zip?sequence=3&isAllowed=y", "zip"),
("https://zenodo.org/record/2787612/files/SICK.zip?download=1", "zip"),
(TEST_GG_DRIVE_GZIPPED_URL, "gzip"),
(TEST_GG_DRIVE_ZIPPED_URL, "zip"),
],
)
def test_streaming_dl_manager_get_extraction_protocol(urlpath, expected_protocol):
assert _get_extraction_protocol(urlpath) == expected_protocol
@pytest.mark.parametrize(
"urlpath",
[
"zip://train-00000.tar.gz::https://foo.bar/data.zip",
"https://foo.bar/train.tar.gz",
"https://foo.bar/train.tar",
],
)
@pytest.mark.xfail(raises=NotImplementedError)
def test_streaming_dl_manager_get_extraction_protocol_throws(urlpath):
_get_extraction_protocol(urlpath)
def test_streaming_gg_drive():
with xopen(TEST_GG_DRIVE_URL) as f:
assert f.read() == TEST_GG_DRIVE_CONTENT
def test_streaming_gg_drive_no_extract():
urlpath = StreamingDownloadManager().download_and_extract(TEST_GG_DRIVE_URL)
with xopen(urlpath) as f:
assert f.read() == TEST_GG_DRIVE_CONTENT
def test_streaming_gg_drive_gzipped():
urlpath = StreamingDownloadManager().download_and_extract(TEST_GG_DRIVE_GZIPPED_URL)
with xopen(urlpath) as f:
assert f.read() == TEST_GG_DRIVE_CONTENT
def test_streaming_gg_drive_zipped():
urlpath = StreamingDownloadManager().download_and_extract(TEST_GG_DRIVE_ZIPPED_URL)
all_files = list(xglob(xjoin(urlpath, "*")))
assert len(all_files) == 1
assert xbasename(all_files[0]) == TEST_GG_DRIVE_FILENAME
with xopen(all_files[0]) as f:
assert f.read() == TEST_GG_DRIVE_CONTENT
def _test_jsonl(path, file):
assert path.endswith(".jsonl")
for num_items, line in enumerate(file, start=1):
item = json.loads(line.decode("utf-8"))
assert item.keys() == {"col_1", "col_2", "col_3"}
assert num_items == 4
def test_iter_archive_path(tar_jsonl_path):
dl_manager = StreamingDownloadManager()
archive_iterable = dl_manager.iter_archive(str(tar_jsonl_path))
num_jsonl = 0
for num_jsonl, (path, file) in enumerate(archive_iterable, start=1):
_test_jsonl(path, file)
assert num_jsonl == 2
# do it twice to make sure it's reset correctly
num_jsonl = 0
for num_jsonl, (path, file) in enumerate(archive_iterable, start=1):
_test_jsonl(path, file)
assert num_jsonl == 2
def test_iter_archive_file(tar_nested_jsonl_path):
dl_manager = StreamingDownloadManager()
files_iterable = dl_manager.iter_archive(str(tar_nested_jsonl_path))
num_tar, num_jsonl = 0, 0
for num_tar, (path, file) in enumerate(files_iterable, start=1):
for num_jsonl, (subpath, subfile) in enumerate(dl_manager.iter_archive(file), start=1):
_test_jsonl(subpath, subfile)
assert num_tar == 1
assert num_jsonl == 2
# do it twice to make sure it's reset correctly
num_tar, num_jsonl = 0, 0
for num_tar, (path, file) in enumerate(files_iterable, start=1):
for num_jsonl, (subpath, subfile) in enumerate(dl_manager.iter_archive(file), start=1):
_test_jsonl(subpath, subfile)
assert num_tar == 1
assert num_jsonl == 2