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
|
import os.path
from functools import partial
from torchtext._internal.module_utils import is_module_available
from torchtext.data.datasets_utils import (
_create_dataset_directory,
)
if is_module_available("torchdata"):
from torchdata.datapipes.iter import FileOpener, IterableWrapper
from torchtext._download_hooks import HttpReader
URL = "http://data.statmt.org/cc-100/%s.txt.xz"
VALID_CODES = {
"am",
"ar",
"as",
"az",
"be",
"bg",
"bn",
"bn_rom",
"br",
"bs",
"ca",
"cs",
"cy",
"da",
"de",
"el",
"en",
"eo",
"es",
"et",
"eu",
"fa",
"ff",
"fi",
"fr",
"fy",
"ga",
"gd",
"gl",
"gn",
"gu",
"ha",
"he",
"hi",
"hi_rom",
"hr",
"ht",
"hu",
"hy",
"id",
"ig",
"is",
"it",
"ja",
"jv",
"ka",
"kk",
"km",
"kn",
"ko",
"ku",
"ky",
"la",
"lg",
"li",
"ln",
"lo",
"lt",
"lv",
"mg",
"mk",
"ml",
"mn",
"mr",
"ms",
"my",
"my_zaw",
"ne",
"nl",
"no",
"ns",
"om",
"or",
"pa",
"pl",
"ps",
"pt",
"qu",
"rm",
"ro",
"ru",
"sa",
"si",
"sc",
"sd",
"sk",
"sl",
"so",
"sq",
"sr",
"ss",
"su",
"sv",
"sw",
"ta",
"ta_rom",
"te",
"te_rom",
"th",
"tl",
"tn",
"tr",
"ug",
"uk",
"ur",
"ur_rom",
"uz",
"vi",
"wo",
"xh",
"yi",
"yo",
"zh-Hans",
"zh-Hant",
"zu",
}
NUM_LINES = None
MD5 = None
DATASET_NAME = "CC100"
def _filepath_fn(root, url, _=None):
return os.path.join(root, os.path.basename(url))
def _decompressed_filepath_fn(root, x):
return os.path.join(root, os.path.basename(x).rstrip(".xz"))
def _modify_res(language_code, x):
return language_code, x
@_create_dataset_directory(dataset_name=DATASET_NAME)
def CC100(root: str, language_code: str = "en"):
"""CC100 Dataset
.. warning::
using datapipes is still currently subject to a few caveats. if you wish
to use this dataset with shuffling, multi-processing, or distributed
learning, please see :ref:`this note <datapipes_warnings>` for further
instructions.
For additional details refer to https://data.statmt.org/cc-100/
Args:
root: Directory where the datasets are saved. Default: os.path.expanduser('~/.torchtext/cache')
language_code: the language of the dataset
:returns: DataPipe that yields tuple of language code and text
:rtype: (str, str)
"""
if language_code not in VALID_CODES:
raise ValueError(f"Invalid language code {language_code}")
url = URL % language_code
url_dp = IterableWrapper([url])
cache_compressed_dp = url_dp.on_disk_cache(filepath_fn=partial(_filepath_fn, root, url))
cache_compressed_dp = HttpReader(cache_compressed_dp)
cache_compressed_dp = cache_compressed_dp.end_caching(mode="wb", same_filepath_fn=True)
cache_decompressed_dp = cache_compressed_dp.on_disk_cache(filepath_fn=partial(_decompressed_filepath_fn, root))
cache_decompressed_dp = FileOpener(cache_decompressed_dp, mode="b").load_from_xz()
cache_decompressed_dp = cache_decompressed_dp.end_caching(mode="wb")
data_dp = FileOpener(cache_decompressed_dp, encoding="utf-8").readlines(return_path=False)
return data_dp.map(partial(_modify_res, language_code)).shuffle().set_shuffle(False).sharding_filter()
|
