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

update ruff version (#30932)

Browse Source 
* update ruff version

* fix research projects

* Empty

* Fix errors

---------

Co-authored-by: Lysandre <lysandre@huggingface.co>
This commit is contained in:
Arthur
2024-05-22 06:40:15 +02:00
committed by GitHub
parent 60bb571e99
commit 673440d073
1172 changed files with 1555 additions and 1861 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
tests/models/layoutlmv2/test_modeling_layoutlmv2.py
View File

@@ -12,8 +12,7 @@
# 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.
""" Testing suite for the PyTorch LayoutLMv2 model. """
"""Testing suite for the PyTorch LayoutLMv2 model."""
import unittest

14
tests/models/layoutlmv2/test_tokenization_layoutlmv2.py
View File

@@ -126,14 +126,14 @@ class LayoutLMv2TokenizationTest(TokenizerTesterMixin, unittest.TestCase):
vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))
def get_input_output_texts(self, tokenizer):
input_text = "UNwant\u00E9d,running"
input_text = "UNwant\u00e9d,running"
output_text = "unwanted, running"
return input_text, output_text
def test_chinese(self):
tokenizer = BasicTokenizer()
self.assertListEqual(tokenizer.tokenize("ah\u535A\u63A8zz"), ["ah", "\u535A", "\u63A8", "zz"])
self.assertListEqual(tokenizer.tokenize("ah\u535a\u63a8zz"), ["ah", "\u535a", "\u63a8", "zz"])
def test_basic_tokenizer_lower(self):
tokenizer = BasicTokenizer(do_lower_case=True)
@@ -141,7 +141,7 @@ class LayoutLMv2TokenizationTest(TokenizerTesterMixin, unittest.TestCase):
self.assertListEqual(
tokenizer.tokenize(" \tHeLLo!how \n Are yoU? "), ["hello", "!", "how", "are", "you", "?"]
)
self.assertListEqual(tokenizer.tokenize("H\u00E9llo"), ["hello"])
self.assertListEqual(tokenizer.tokenize("H\u00e9llo"), ["hello"])
def test_basic_tokenizer_lower_strip_accents_false(self):
tokenizer = BasicTokenizer(do_lower_case=True, strip_accents=False)
@@ -149,7 +149,7 @@ class LayoutLMv2TokenizationTest(TokenizerTesterMixin, unittest.TestCase):
self.assertListEqual(
tokenizer.tokenize(" \tHäLLo!how \n Are yoU? "), ["hällo", "!", "how", "are", "you", "?"]
)
self.assertListEqual(tokenizer.tokenize("H\u00E9llo"), ["h\u00E9llo"])
self.assertListEqual(tokenizer.tokenize("H\u00e9llo"), ["h\u00e9llo"])
def test_basic_tokenizer_lower_strip_accents_true(self):
tokenizer = BasicTokenizer(do_lower_case=True, strip_accents=True)
@@ -157,7 +157,7 @@ class LayoutLMv2TokenizationTest(TokenizerTesterMixin, unittest.TestCase):
self.assertListEqual(
tokenizer.tokenize(" \tHäLLo!how \n Are yoU? "), ["hallo", "!", "how", "are", "you", "?"]
)
self.assertListEqual(tokenizer.tokenize("H\u00E9llo"), ["hello"])
self.assertListEqual(tokenizer.tokenize("H\u00e9llo"), ["hello"])
def test_basic_tokenizer_lower_strip_accents_default(self):
tokenizer = BasicTokenizer(do_lower_case=True)
@@ -165,7 +165,7 @@ class LayoutLMv2TokenizationTest(TokenizerTesterMixin, unittest.TestCase):
self.assertListEqual(
tokenizer.tokenize(" \tHäLLo!how \n Are yoU? "), ["hallo", "!", "how", "are", "you", "?"]
)
self.assertListEqual(tokenizer.tokenize("H\u00E9llo"), ["hello"])
self.assertListEqual(tokenizer.tokenize("H\u00e9llo"), ["hello"])
def test_basic_tokenizer_no_lower(self):
tokenizer = BasicTokenizer(do_lower_case=False)
@@ -218,7 +218,7 @@ class LayoutLMv2TokenizationTest(TokenizerTesterMixin, unittest.TestCase):
self.assertTrue(_is_whitespace("\t"))
self.assertTrue(_is_whitespace("\r"))
self.assertTrue(_is_whitespace("\n"))
self.assertTrue(_is_whitespace("\u00A0"))
self.assertTrue(_is_whitespace("\u00a0"))
self.assertFalse(_is_whitespace("A"))
self.assertFalse(_is_whitespace("-"))