File size: 11,894 Bytes
b381930
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# Copyright 2018 HuggingFace Inc. 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 tempfile
import unittest
from tempfile import TemporaryDirectory

from transformers import AddedToken, CamembertTokenizer, CamembertTokenizerFast
from transformers.testing_utils import get_tests_dir, require_sentencepiece, require_tokenizers, slow
from transformers.utils import is_torch_available

from ...test_tokenization_common import TokenizerTesterMixin


SAMPLE_VOCAB = get_tests_dir("fixtures/test_sentencepiece.model")
SAMPLE_BPE_VOCAB = get_tests_dir("fixtures/test_sentencepiece_bpe.model")

FRAMEWORK = "pt" if is_torch_available() else "tf"


@require_sentencepiece
@require_tokenizers
class CamembertTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
    from_pretrained_id = "almanach/camembert-base"
    tokenizer_class = CamembertTokenizer
    rust_tokenizer_class = CamembertTokenizerFast
    test_rust_tokenizer = True
    test_sentencepiece = True

    @classmethod
    def setUpClass(cls):
        super().setUpClass()

        # We have a SentencePiece fixture for testing
        tokenizer = CamembertTokenizer(SAMPLE_VOCAB)
        tokenizer.save_pretrained(cls.tmpdirname)

    @unittest.skip(
        "Token maps are not equal because someone set the probability of ('<unk>NOTUSED', -100), so it's never encoded for fast"
    )
    def test_special_tokens_map_equal(self):
        return

    def test_convert_token_and_id(self):
        """Test ``_convert_token_to_id`` and ``_convert_id_to_token``."""
        token = "<pad>"
        token_id = 1  # 1 is the offset id, but in the spm vocab it's 3

        self.assertEqual(self.get_tokenizer().convert_tokens_to_ids(token), token_id)
        self.assertEqual(self.get_tokenizer().convert_ids_to_tokens(token_id), token)

    def test_get_vocab(self):
        vocab_keys = list(self.get_tokenizer().get_vocab().keys())

        self.assertEqual(vocab_keys[0], "<s>NOTUSED")
        self.assertEqual(vocab_keys[1], "<pad>")
        self.assertEqual(vocab_keys[-1], "<mask>")
        self.assertEqual(len(vocab_keys), 1_005)

    def test_vocab_size(self):
        self.assertEqual(self.get_tokenizer().vocab_size, 1_000)

    def test_rust_and_python_bpe_tokenizers(self):
        tokenizer = CamembertTokenizer(SAMPLE_BPE_VOCAB)
        with TemporaryDirectory() as tmpdirname:
            tokenizer.save_pretrained(tmpdirname)
            rust_tokenizer = CamembertTokenizerFast.from_pretrained(tmpdirname)

        sequence = "I was born in 92000, and this is falsé."

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

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

        # <unk> tokens are not the same for `rust` than for `slow`.
        # Because spm gives back raw token instead of `unk` in EncodeAsPieces
        # tokens = tokenizer.tokenize(sequence)
        tokens = tokenizer.convert_ids_to_tokens(ids)
        rust_tokens = rust_tokenizer.tokenize(sequence)
        self.assertListEqual(tokens, rust_tokens)

    def test_rust_and_python_full_tokenizers(self):
        if not self.test_rust_tokenizer:
            self.skipTest(reason="test_rust_tokenizer is set to False")

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

        sequence = "I was born in 92000, and this is falsé."

        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, add_special_tokens=False)
        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)

    @slow
    def test_tokenizer_integration(self):
        expected_encoding = {'input_ids': [[5, 54, 7196, 297, 30, 23, 776, 18, 11, 3215, 3705, 8252, 22, 3164, 1181, 2116, 29, 16, 813, 25, 791, 3314, 20, 3446, 38, 27575, 120, 6, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1], [5, 468, 17, 11, 9088, 20, 1517, 8, 22804, 18818, 10, 38, 629, 607, 607, 142, 19, 7196, 867, 56, 10326, 24, 2267, 20, 416, 5072, 15612, 233, 734, 7, 2399, 27, 16, 3015, 1649, 7, 24, 20, 4338, 2399, 27, 13, 3400, 14, 13, 6189, 8, 930, 9, 6]], '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, 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, 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]]}  # fmt: skip

        # camembert is a french model. So we also use french texts.
        sequences = [
            "Le transformeur est un modèle d'apprentissage profond introduit en 2017, "
            "utilisé principalement dans le domaine du traitement automatique des langues (TAL).",
            "À l'instar des réseaux de neurones récurrents (RNN), les transformeurs sont conçus "
            "pour gérer des données séquentielles, telles que le langage naturel, pour des tâches "
            "telles que la traduction et la synthèse de texte.",
        ]

        self.tokenizer_integration_test_util(
            expected_encoding=expected_encoding,
            model_name="almanach/camembert-base",
            revision="3a0641d9a1aeb7e848a74299e7e4c4bca216b4cf",
            sequences=sequences,
        )

    # Overwritten because we have to use from slow (online pretrained is wrong, the tokenizer.json has a whole)
    def test_added_tokens_serialization(self):
        self.maxDiff = None

        # Utility to test the added vocab
        def _test_added_vocab_and_eos(expected, tokenizer_class, expected_eos, temp_dir):
            tokenizer = tokenizer_class.from_pretrained(temp_dir)
            self.assertTrue(str(expected_eos) not in tokenizer.additional_special_tokens)
            self.assertIn(new_eos, tokenizer.added_tokens_decoder.values())
            self.assertEqual(tokenizer.added_tokens_decoder[tokenizer.eos_token_id], new_eos)
            self.assertTrue(all(item in tokenizer.added_tokens_decoder.items() for item in expected.items()))
            return tokenizer

        new_eos = AddedToken("[NEW_EOS]", rstrip=False, lstrip=True, normalized=False, special=True)
        for tokenizer, pretrained_name, kwargs in self.tokenizers_list:
            with self.subTest(f"{tokenizer.__class__.__name__} ({pretrained_name})"):
                # Load a slow tokenizer from the hub, init with the new token for fast to also include it
                tokenizer = self.get_tokenizer(pretrained_name, eos_token=new_eos)
                EXPECTED_ADDED_TOKENS_DECODER = tokenizer.added_tokens_decoder
                with self.subTest("Hub -> Slow: Test loading a slow tokenizer from the hub)"):
                    self.assertEqual(tokenizer._special_tokens_map["eos_token"], new_eos)
                    self.assertIn(new_eos, list(tokenizer.added_tokens_decoder.values()))

                with tempfile.TemporaryDirectory() as tmp_dir_2:
                    tokenizer.save_pretrained(tmp_dir_2)
                    with self.subTest(
                        "Hub -> Slow -> Slow: Test saving this slow tokenizer and reloading it in the fast class"
                    ):
                        _test_added_vocab_and_eos(
                            EXPECTED_ADDED_TOKENS_DECODER, self.tokenizer_class, new_eos, tmp_dir_2
                        )

                    if self.rust_tokenizer_class is not None:
                        with self.subTest(
                            "Hub -> Slow -> Fast: Test saving this slow tokenizer and reloading it in the fast class"
                        ):
                            tokenizer_fast = _test_added_vocab_and_eos(
                                EXPECTED_ADDED_TOKENS_DECODER, self.rust_tokenizer_class, new_eos, tmp_dir_2
                            )
                            with tempfile.TemporaryDirectory() as tmp_dir_3:
                                tokenizer_fast.save_pretrained(tmp_dir_3)
                                with self.subTest(
                                    "Hub -> Slow -> Fast -> Fast: Test saving this fast tokenizer and reloading it in the fast class"
                                ):
                                    _test_added_vocab_and_eos(
                                        EXPECTED_ADDED_TOKENS_DECODER, self.rust_tokenizer_class, new_eos, tmp_dir_3
                                    )

                                with self.subTest(
                                    "Hub -> Slow -> Fast -> Slow: Test saving this slow tokenizer and reloading it in the slow class"
                                ):
                                    _test_added_vocab_and_eos(
                                        EXPECTED_ADDED_TOKENS_DECODER, self.rust_tokenizer_class, new_eos, tmp_dir_3
                                    )

                with self.subTest("Hub -> Fast: Test loading a fast tokenizer from the hub)"):
                    if self.rust_tokenizer_class is not None:
                        tokenizer_fast = self.get_rust_tokenizer(pretrained_name, eos_token=new_eos, from_slow=True)
                        self.assertEqual(tokenizer_fast._special_tokens_map["eos_token"], new_eos)
                        self.assertIn(new_eos, list(tokenizer_fast.added_tokens_decoder.values()))
                        # We can't test the following because for BC we kept the default rstrip lstrip in slow not fast. Will comment once normalization is alright
                        with self.subTest("Hub -> Fast == Hub -> Slow: make sure slow and fast tokenizer match"):
                            with self.subTest("Hub -> Fast == Hub -> Slow: make sure slow and fast tokenizer match"):
                                self.assertTrue(
                                    all(
                                        item in tokenizer.added_tokens_decoder.items()
                                        for item in EXPECTED_ADDED_TOKENS_DECODER.items()
                                    )
                                )

                        EXPECTED_ADDED_TOKENS_DECODER = tokenizer_fast.added_tokens_decoder
                        with tempfile.TemporaryDirectory() as tmp_dir_4:
                            tokenizer_fast.save_pretrained(tmp_dir_4)
                            with self.subTest("Hub -> Fast -> Fast: saving Fast1 locally and loading"):
                                _test_added_vocab_and_eos(
                                    EXPECTED_ADDED_TOKENS_DECODER, self.rust_tokenizer_class, new_eos, tmp_dir_4
                                )

                            with self.subTest("Hub -> Fast -> Slow: saving Fast1 locally and loading"):
                                _test_added_vocab_and_eos(
                                    EXPECTED_ADDED_TOKENS_DECODER, self.tokenizer_class, new_eos, tmp_dir_4
                                )