SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Enforce string-formatting with f-strings (#10980)

Browse Source 
* First third

* Styling and fix mistake

* Quality

* All the rest

* Treat %s and %d

* typo

* Missing )

* Apply suggestions from code review

Co-authored-by: Lysandre Debut <lysandre@huggingface.co>

Co-authored-by: Lysandre Debut <lysandre@huggingface.co>
This commit is contained in:
Sylvain Gugger
2021-03-31 10:00:27 -04:00
committed by GitHub
parent d0b3797a3b
commit acc3bd9d2a
224 changed files with 984 additions and 1312 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
tests/test_tokenization_tapas.py
View File

@@ -312,7 +312,7 @@ class TapasTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
def test_offsets_with_special_characters(self):
for tokenizer, pretrained_name, kwargs in self.tokenizers_list:
with self.subTest("{} ({})".format(tokenizer.__class__.__name__, pretrained_name)):
with self.subTest(f"{tokenizer.__class__.__name__} ({pretrained_name})"):
tokenizer_r = self.rust_tokenizer_class.from_pretrained(pretrained_name, **kwargs)
sentence = f"A, naïve {tokenizer_r.mask_token} AllenNLP sentence."
@@ -807,18 +807,18 @@ class TapasTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
empty_tokens = tokenizer(table, padding=True, pad_to_multiple_of=8)
normal_tokens = tokenizer(table, "This is a sample input", padding=True, pad_to_multiple_of=8)
for key, value in empty_tokens.items():
self.assertEqual(len(value) % 8, 0, "BatchEncoding.{} is not multiple of 8".format(key))
self.assertEqual(len(value) % 8, 0, f"BatchEncoding.{key} is not multiple of 8")
for key, value in normal_tokens.items():
self.assertEqual(len(value) % 8, 0, "BatchEncoding.{} is not multiple of 8".format(key))
self.assertEqual(len(value) % 8, 0, f"BatchEncoding.{key} is not multiple of 8")
normal_tokens = tokenizer(table, "This", pad_to_multiple_of=8)
for key, value in normal_tokens.items():
self.assertNotEqual(len(value) % 8, 0, "BatchEncoding.{} is not multiple of 8".format(key))
self.assertNotEqual(len(value) % 8, 0, f"BatchEncoding.{key} is not multiple of 8")
# Should also work with truncation
normal_tokens = tokenizer(table, "This", padding=True, truncation=True, pad_to_multiple_of=8)
for key, value in normal_tokens.items():
self.assertEqual(len(value) % 8, 0, "BatchEncoding.{} is not multiple of 8".format(key))
self.assertEqual(len(value) % 8, 0, f"BatchEncoding.{key} is not multiple of 8")
@unittest.skip("TAPAS cannot handle `prepare_for_model` without passing by `encode_plus` or `batch_encode_plus`")
def test_prepare_for_model(self):