-
Notifications
You must be signed in to change notification settings - Fork 28.4k
/
Copy pathtest_tokenization_xlm_prophetnet.py
157 lines (133 loc) · 7.48 KB
/
test_tokenization_xlm_prophetnet.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
# coding=utf-8
# Copyright 2020 The HuggingFace Inc. team, The Microsoft Research team.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import os
import unittest
from transformers.file_utils import cached_property
from transformers.models.xlm_prophetnet.tokenization_xlm_prophetnet import SPIECE_UNDERLINE, XLMProphetNetTokenizer
from transformers.testing_utils import require_sentencepiece, slow
from .test_tokenization_common import TokenizerTesterMixin
SAMPLE_VOCAB = os.path.join(os.path.dirname(os.path.abspath(__file__)), "fixtures/test_sentencepiece.model")
@require_sentencepiece
class XLMProphetNetTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
tokenizer_class = XLMProphetNetTokenizer
test_rust_tokenizer = False
test_sentencepiece = True
def setUp(self):
super().setUp()
# We have a SentencePiece fixture for testing
tokenizer = XLMProphetNetTokenizer(SAMPLE_VOCAB, keep_accents=True)
tokenizer.save_pretrained(self.tmpdirname)
def test_convert_token_and_id(self):
"""Test ``_convert_token_to_id`` and ``_convert_id_to_token``."""
token = "[PAD]"
token_id = 0
self.assertEqual(self.get_tokenizer()._convert_token_to_id(token), token_id)
self.assertEqual(self.get_tokenizer()._convert_id_to_token(token_id), token)
def test_get_vocab(self):
vocab_keys = list(self.get_tokenizer().get_vocab().keys())
self.assertEqual(vocab_keys[0], "[PAD]")
self.assertEqual(vocab_keys[1], "[CLS]")
self.assertEqual(vocab_keys[-1], "j")
self.assertEqual(len(vocab_keys), 1_012)
def test_vocab_size(self):
self.assertEqual(self.get_tokenizer().vocab_size, 1_012)
def test_full_tokenizer(self):
tokenizer = XLMProphetNetTokenizer(SAMPLE_VOCAB, keep_accents=True)
tokens = tokenizer.tokenize("This is a test")
self.assertListEqual(tokens, ["▁This", "▁is", "▁a", "▁t", "est"])
self.assertListEqual(
tokenizer.convert_tokens_to_ids(tokens),
[value + tokenizer.fairseq_offset for value in [285, 46, 10, 170, 382]],
)
tokens = tokenizer.tokenize("I was born in 92000, and this is falsé.")
self.assertListEqual(
tokens,
[
SPIECE_UNDERLINE + "I",
SPIECE_UNDERLINE + "was",
SPIECE_UNDERLINE + "b",
"or",
"n",
SPIECE_UNDERLINE + "in",
SPIECE_UNDERLINE + "",
"9",
"2",
"0",
"0",
"0",
",",
SPIECE_UNDERLINE + "and",
SPIECE_UNDERLINE + "this",
SPIECE_UNDERLINE + "is",
SPIECE_UNDERLINE + "f",
"al",
"s",
"é",
".",
],
)
ids = tokenizer.convert_tokens_to_ids(tokens)
self.assertListEqual(
ids,
[
value + tokenizer.fairseq_offset
for value in [8, 21, 84, 55, 24, 19, 7, -9, 602, 347, 347, 347, 3, 12, 66, 46, 72, 80, 6, -9, 4]
],
)
back_tokens = tokenizer.convert_ids_to_tokens(ids)
self.assertListEqual(
back_tokens,
[
SPIECE_UNDERLINE + "I",
SPIECE_UNDERLINE + "was",
SPIECE_UNDERLINE + "b",
"or",
"n",
SPIECE_UNDERLINE + "in",
SPIECE_UNDERLINE + "",
"[UNK]",
"2",
"0",
"0",
"0",
",",
SPIECE_UNDERLINE + "and",
SPIECE_UNDERLINE + "this",
SPIECE_UNDERLINE + "is",
SPIECE_UNDERLINE + "f",
"al",
"s",
"[UNK]",
".",
],
)
@cached_property
def big_tokenizer(self):
return XLMProphetNetTokenizer.from_pretrained("microsoft/xprophetnet-large-wiki100-cased")
@slow
def test_tokenization_base_easy_symbols(self):
symbols = "Hello World!"
original_tokenizer_encodings = [35389, 6672, 49, 2]
self.assertListEqual(original_tokenizer_encodings, self.big_tokenizer.encode(symbols))
@slow
def test_tokenizer_integration(self):
# fmt: off
expected_encoding = {'input_ids': [[11073, 82783, 18, 26, 82783, 549, 51540, 248, 17209, 1301, 217, 20, 215186, 1325, 147, 17209, 1301, 217, 20, 56370, 53, 122020, 20, 16477, 27, 87355, 4548, 20, 4728, 78392, 17, 159969, 18, 26, 24491, 629, 15, 538, 22704, 5439, 15, 2788, 24491, 9885, 15, 43534, 605, 15, 814, 18403, 33200, 29, 15, 43534, 24458, 12410, 111, 24966, 83669, 9637, 144068, 26, 850, 22346, 27, 147, 24966, 83669, 83490, 26, 39113, 735, 27, 689, 656, 2800, 1339, 4600, 53, 122020, 115785, 34, 816, 1339, 46887, 18, 147, 53905, 1951, 42238, 41170, 17732, 834, 436, 15, 27523, 98733, 217, 147, 5542, 4981, 930, 17347, 16, 2], [20091, 629, 94, 82786, 58, 490, 20, 1528, 84, 53905, 344, 80592, 110128, 18822, 5267, 1306, 62, 152537, 308, 7997, 401, 124427, 549, 35442, 225, 109, 15055, 25748, 147, 7119, 43712, 34, 767, 135366, 18, 16, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [592, 63784, 119466, 17, 147808, 88214, 18, 656, 81, 32, 3296, 10280, 16, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]], 'attention_mask': [[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0], [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]]} # noqa: E501
# fmt: on
self.tokenizer_integration_test_util(
expected_encoding=expected_encoding,
model_name="microsoft/xprophetnet-large-wiki100-cased",
revision="1acad1643ddd54a44df6a1b797ada8373685d90e",
)