35401fe50f
* Switch to plain unittest for skipping slow tests.
Add a RUN_SLOW environment variable for running them.
* Switch to plain unittest for PyTorch dependency.
* Switch to plain unittest for TensorFlow dependency.
* Avoid leaking open files in the test suite.
This prevents spurious warnings when running tests.
* Fix unicode warning on Python 2 when running tests.
The warning was:
UnicodeWarning: Unicode equal comparison failed to convert both arguments to Unicode - interpreting them as being unequal
* Support running PyTorch tests on a GPU.
Reverts 27e015bd.
* Tests no longer require pytest.
* Make tests pass on cuda
51 lines
1.8 KiB
Python
51 lines
1.8 KiB
Python
# coding=utf-8
|
|
# Copyright 2018 HuggingFace Inc..
|
|
#
|
|
# 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.
|
|
from __future__ import absolute_import
|
|
from __future__ import division
|
|
from __future__ import print_function
|
|
|
|
import unittest
|
|
import six
|
|
|
|
from transformers import PreTrainedTokenizer
|
|
from transformers.tokenization_gpt2 import GPT2Tokenizer
|
|
|
|
from .utils import slow
|
|
|
|
class TokenizerUtilsTest(unittest.TestCase):
|
|
|
|
def check_tokenizer_from_pretrained(self, tokenizer_class):
|
|
s3_models = list(tokenizer_class.max_model_input_sizes.keys())
|
|
for model_name in s3_models[:1]:
|
|
tokenizer = tokenizer_class.from_pretrained(model_name)
|
|
self.assertIsNotNone(tokenizer)
|
|
self.assertIsInstance(tokenizer, tokenizer_class)
|
|
self.assertIsInstance(tokenizer, PreTrainedTokenizer)
|
|
|
|
for special_tok in tokenizer.all_special_tokens:
|
|
if six.PY2:
|
|
self.assertIsInstance(special_tok, unicode)
|
|
else:
|
|
self.assertIsInstance(special_tok, str)
|
|
special_tok_id = tokenizer.convert_tokens_to_ids(special_tok)
|
|
self.assertIsInstance(special_tok_id, int)
|
|
|
|
@slow
|
|
def test_pretrained_tokenizers(self):
|
|
self.check_tokenizer_from_pretrained(GPT2Tokenizer)
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|