File size: 6,297 Bytes
75466df
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# coding=utf-8
# Copyright 2018 The Google AI Language Team Authors.
#
# 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.tokenization_bert import (
    VOCAB_FILES_NAMES,
    BasicTokenizer,
    BertTokenizer,
    BertTokenizerFast,
    WordpieceTokenizer,
    _is_control,
    _is_punctuation,
    _is_whitespace,
)

from .test_tokenization_common import TokenizerTesterMixin
from .utils import slow


class BertTokenizationTest(TokenizerTesterMixin, unittest.TestCase):

    tokenizer_class = BertTokenizer
    test_rust_tokenizer = True

    def setUp(self):
        super().setUp()

        vocab_tokens = [
            "[UNK]",
            "[CLS]",
            "[SEP]",
            "want",
            "##want",
            "##ed",
            "wa",
            "un",
            "runn",
            "##ing",
            ",",
            "low",
            "lowest",
        ]
        self.vocab_file = os.path.join(self.tmpdirname, VOCAB_FILES_NAMES["vocab_file"])
        with open(self.vocab_file, "w", encoding="utf-8") as vocab_writer:
            vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))

    def get_tokenizer(self, **kwargs):
        return BertTokenizer.from_pretrained(self.tmpdirname, **kwargs)

    def get_rust_tokenizer(self, **kwargs):
        return BertTokenizerFast.from_pretrained(self.tmpdirname, **kwargs)

    def get_input_output_texts(self):
        input_text = "UNwant\u00E9d,running"
        output_text = "unwanted, running"
        return input_text, output_text

    def test_full_tokenizer(self):
        tokenizer = self.tokenizer_class(self.vocab_file)

        tokens = tokenizer.tokenize("UNwant\u00E9d,running")
        self.assertListEqual(tokens, ["un", "##want", "##ed", ",", "runn", "##ing"])
        self.assertListEqual(tokenizer.convert_tokens_to_ids(tokens), [7, 4, 5, 10, 8, 9])

    def test_rust_and_python_full_tokenizers(self):
        if not self.test_rust_tokenizer:
            return

        tokenizer = self.get_tokenizer()
        rust_tokenizer = self.get_rust_tokenizer(add_special_tokens=False)

        sequence = "UNwant\u00E9d,running"

        tokens = tokenizer.tokenize(sequence)
        rust_tokens = rust_tokenizer.tokenize(sequence)
        self.assertListEqual(tokens, rust_tokens)

        ids = tokenizer.encode(sequence, add_special_tokens=False)
        rust_ids = rust_tokenizer.encode(sequence)
        self.assertListEqual(ids, rust_ids)

        rust_tokenizer = self.get_rust_tokenizer()
        ids = tokenizer.encode(sequence)
        rust_ids = rust_tokenizer.encode(sequence)
        self.assertListEqual(ids, rust_ids)

    def test_chinese(self):
        tokenizer = BasicTokenizer()

        self.assertListEqual(tokenizer.tokenize("ah\u535A\u63A8zz"), ["ah", "\u535A", "\u63A8", "zz"])

    def test_basic_tokenizer_lower(self):
        tokenizer = BasicTokenizer(do_lower_case=True)

        self.assertListEqual(
            tokenizer.tokenize(" \tHeLLo!how  \n Are yoU?  "), ["hello", "!", "how", "are", "you", "?"]
        )
        self.assertListEqual(tokenizer.tokenize("H\u00E9llo"), ["hello"])

    def test_basic_tokenizer_no_lower(self):
        tokenizer = BasicTokenizer(do_lower_case=False)

        self.assertListEqual(
            tokenizer.tokenize(" \tHeLLo!how  \n Are yoU?  "), ["HeLLo", "!", "how", "Are", "yoU", "?"]
        )

    def test_basic_tokenizer_respects_never_split_tokens(self):
        tokenizer = BasicTokenizer(do_lower_case=False, never_split=["[UNK]"])

        self.assertListEqual(
            tokenizer.tokenize(" \tHeLLo!how  \n Are yoU? [UNK]"), ["HeLLo", "!", "how", "Are", "yoU", "?", "[UNK]"]
        )

    def test_wordpiece_tokenizer(self):
        vocab_tokens = ["[UNK]", "[CLS]", "[SEP]", "want", "##want", "##ed", "wa", "un", "runn", "##ing"]

        vocab = {}
        for (i, token) in enumerate(vocab_tokens):
            vocab[token] = i
        tokenizer = WordpieceTokenizer(vocab=vocab, unk_token="[UNK]")

        self.assertListEqual(tokenizer.tokenize(""), [])

        self.assertListEqual(tokenizer.tokenize("unwanted running"), ["un", "##want", "##ed", "runn", "##ing"])

        self.assertListEqual(tokenizer.tokenize("unwantedX running"), ["[UNK]", "runn", "##ing"])

    def test_is_whitespace(self):
        self.assertTrue(_is_whitespace(" "))
        self.assertTrue(_is_whitespace("\t"))
        self.assertTrue(_is_whitespace("\r"))
        self.assertTrue(_is_whitespace("\n"))
        self.assertTrue(_is_whitespace("\u00A0"))

        self.assertFalse(_is_whitespace("A"))
        self.assertFalse(_is_whitespace("-"))

    def test_is_control(self):
        self.assertTrue(_is_control("\u0005"))

        self.assertFalse(_is_control("A"))
        self.assertFalse(_is_control(" "))
        self.assertFalse(_is_control("\t"))
        self.assertFalse(_is_control("\r"))

    def test_is_punctuation(self):
        self.assertTrue(_is_punctuation("-"))
        self.assertTrue(_is_punctuation("$"))
        self.assertTrue(_is_punctuation("`"))
        self.assertTrue(_is_punctuation("."))

        self.assertFalse(_is_punctuation("A"))
        self.assertFalse(_is_punctuation(" "))

    @slow
    def test_sequence_builders(self):
        tokenizer = self.tokenizer_class.from_pretrained("bert-base-uncased")

        text = tokenizer.encode("sequence builders", add_special_tokens=False)
        text_2 = tokenizer.encode("multi-sequence build", add_special_tokens=False)

        encoded_sentence = tokenizer.build_inputs_with_special_tokens(text)
        encoded_pair = tokenizer.build_inputs_with_special_tokens(text, text_2)

        assert encoded_sentence == [101] + text + [102]
        assert encoded_pair == [101] + text + [102] + text_2 + [102]