mirror of
https://github.com/huggingface/transformers.git
synced 2025-07-06 06:10:04 +06:00
fcad801825
* add test_vocab_size for sentencepiece tok. * add test_get_vocab for sentencepiece tok. * add test_convert_token_and_id for sentencepiece tok. * add test_tokenize_and_convert_tokens_to_string for all tok. * improve test_tokenize_and_convert_tokens_to_string for sp. tok. * add common tokenizer integration tests - for albert - for barthez * add tokenizer integration tests to bert gen. * add most tokenizer integration tests * fix camembert tokenizer integration test * add tokenizer integration test to marian * add tokenizer integration test to reformer * add typing and doc to tokenizer_integration_test_util * fix tokenizer integration test of reformer * improve test_sentencepiece_tokenize_and_convert_tokens_to_string * empty commit to trigger CI * fix tokenizer integration test of reformer * remove code not needed anymore * empty commit to trigger CI * empty commit to trigger CI
158 lines
7.5 KiB
Python
158 lines
7.5 KiB
Python
# 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",
|
|
)
|