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

Skip tests properly (#31308)

Browse Source 
* Skip tests properly

* [test_all]

* Add 'reason' as kwarg for skipTest

* [test_all] Fix up

* [test_all]
This commit is contained in:
amyeroberts
2024-06-26 21:59:08 +01:00
committed by GitHub
parent 1f9f57ab4c
commit 1de7dc7403
254 changed files with 1721 additions and 1298 deletions
Download Patch File Download Diff File Expand all files Collapse all files

50
tests/models/layoutlmv2/test_tokenization_layoutlmv2.py
View File

@@ -195,7 +195,7 @@ class LayoutLMv2TokenizationTest(TokenizerTesterMixin, unittest.TestCase):
tokenizer.tokenize(" \tHeLLo!how \n Are yoU? [UNK]"), ["HeLLo", "!", "how", "Are", "yoU", "?", "[UNK]"]
)
@unittest.skip("Chat template tests don't play well with table/layout models.")
@unittest.skip(reason="Chat template tests don't play well with table/layout models.")
def test_chat_template_batched(self):
pass
@@ -385,11 +385,11 @@ class LayoutLMv2TokenizationTest(TokenizerTesterMixin, unittest.TestCase):
decoded = tokenizer.decode(encoded, spaces_between_special_tokens=self.space_between_special_tokens)
self.assertIn(decoded, [output, output.lower()])
@unittest.skip("Not implemented")
@unittest.skip(reason="Not implemented")
def test_right_and_left_truncation(self):
pass
@unittest.skip("Not implemented")
@unittest.skip(reason="Not implemented")
def test_split_special_tokens(self):
pass
@@ -814,7 +814,7 @@ class LayoutLMv2TokenizationTest(TokenizerTesterMixin, unittest.TestCase):
def test_padding_warning_message_fast_tokenizer(self):
if not self.test_rust_tokenizer:
return
self.skipTest(reason="test_rust_tokenizer is set to False")
words, boxes = self.get_words_and_boxes_batch()
@@ -835,7 +835,7 @@ class LayoutLMv2TokenizationTest(TokenizerTesterMixin, unittest.TestCase):
)
if not self.test_slow_tokenizer:
return
self.skipTest(reason="test_slow_tokenizer is set to False")
tokenizer_slow = self.get_tokenizer()
@@ -942,7 +942,7 @@ class LayoutLMv2TokenizationTest(TokenizerTesterMixin, unittest.TestCase):
encoded_sequences_batch_padded_2[key],
)
@unittest.skip("batch_encode_plus does not handle overflowing tokens.")
@unittest.skip(reason="batch_encode_plus does not handle overflowing tokens.")
def test_batch_encode_plus_overflowing_tokens(self):
pass
@@ -1003,7 +1003,7 @@ class LayoutLMv2TokenizationTest(TokenizerTesterMixin, unittest.TestCase):
for tokenizer in tokenizers:
with self.subTest(f"{tokenizer.__class__.__name__}"):
if tokenizer.pad_token is None:
self.skipTest("No padding token.")
self.skipTest(reason="No padding token.")
else:
words, boxes = self.get_words_and_boxes()
@@ -1046,7 +1046,7 @@ class LayoutLMv2TokenizationTest(TokenizerTesterMixin, unittest.TestCase):
def test_build_inputs_with_special_tokens(self):
if not self.test_slow_tokenizer:
# as we don't have a slow version, we can't compare the outputs between slow and fast versions
return
self.skipTest(reason="test_slow_tokenizer is set to False")
for tokenizer, pretrained_name, kwargs in self.tokenizers_list:
with self.subTest(f"{tokenizer.__class__.__name__} ({pretrained_name})"):
@@ -1290,13 +1290,13 @@ class LayoutLMv2TokenizationTest(TokenizerTesterMixin, unittest.TestCase):
for tokenizer in tokenizers:
with self.subTest(f"{tokenizer.__class__.__name__}"):
if tokenizer.__class__ not in MODEL_TOKENIZER_MAPPING:
return
self.skipTest(f"{tokenizer.__class__} is not in the MODEL_TOKENIZER_MAPPING")
config_class, model_class = MODEL_TOKENIZER_MAPPING[tokenizer.__class__]
config = config_class()
if config.is_encoder_decoder or config.pad_token_id is None:
return
self.skipTest(reason="Model is an encoder-decoder or has no pad token id set.")
model = model_class(config)
@@ -1327,11 +1327,11 @@ class LayoutLMv2TokenizationTest(TokenizerTesterMixin, unittest.TestCase):
def test_rust_and_python_full_tokenizers(self):
if not self.test_rust_tokenizer:
return
self.skipTest(reason="test_rust_tokenizer is set to False")
if not self.test_slow_tokenizer:
# as we don't have a slow version, we can't compare the outputs between slow and fast versions
return
self.skipTest(reason="test_slow_tokenizer is set to False")
tokenizer = self.get_tokenizer()
rust_tokenizer = self.get_rust_tokenizer()
@@ -1349,7 +1349,7 @@ class LayoutLMv2TokenizationTest(TokenizerTesterMixin, unittest.TestCase):
def test_tokenization_python_rust_equals(self):
if not self.test_slow_tokenizer:
# as we don't have a slow version, we can't compare the outputs between slow and fast versions
return
self.skipTest(reason="test_slow_tokenizer is set to False")
for tokenizer, pretrained_name, kwargs in self.tokenizers_list:
with self.subTest(f"{tokenizer.__class__.__name__} ({pretrained_name})"):
@@ -1403,7 +1403,7 @@ class LayoutLMv2TokenizationTest(TokenizerTesterMixin, unittest.TestCase):
def test_embeded_special_tokens(self):
if not self.test_slow_tokenizer:
# as we don't have a slow version, we can't compare the outputs between slow and fast versions
return
self.skipTest(reason="test_slow_tokenizer is set to False")
for tokenizer, pretrained_name, kwargs in self.tokenizers_list:
with self.subTest(f"{tokenizer.__class__.__name__} ({pretrained_name})"):
@@ -1593,7 +1593,7 @@ class LayoutLMv2TokenizationTest(TokenizerTesterMixin, unittest.TestCase):
def test_training_new_tokenizer(self):
# This feature only exists for fast tokenizers
if not self.test_rust_tokenizer:
return
self.skipTest(reason="test_rust_tokenizer is set to False")
tokenizer = self.get_rust_tokenizer()
new_tokenizer = tokenizer.train_new_from_iterator(SMALL_TRAINING_CORPUS, 100)
@@ -1630,7 +1630,7 @@ class LayoutLMv2TokenizationTest(TokenizerTesterMixin, unittest.TestCase):
def test_training_new_tokenizer_with_special_tokens_change(self):
# This feature only exists for fast tokenizers
if not self.test_rust_tokenizer:
return
self.skipTest(reason="test_rust_tokenizer is set to False")
tokenizer = self.get_rust_tokenizer()
# Test with a special tokens map
@@ -1743,7 +1743,7 @@ class LayoutLMv2TokenizationTest(TokenizerTesterMixin, unittest.TestCase):
def test_padding_different_model_input_name(self):
if not self.test_slow_tokenizer:
# as we don't have a slow version, we can't compare the outputs between slow and fast versions
return
self.skipTest(reason="test_slow_tokenizer is set to False")
for tokenizer, pretrained_name, kwargs in self.tokenizers_list:
with self.subTest(f"{tokenizer.__class__.__name__} ({pretrained_name})"):
@@ -1837,7 +1837,7 @@ class LayoutLMv2TokenizationTest(TokenizerTesterMixin, unittest.TestCase):
self.assertEqual(len(tokens[key].shape), 3)
self.assertEqual(tokens[key].shape[-1], 4)
@unittest.skip("TO DO: overwrite this very extensive test.")
@unittest.skip(reason="TO DO: overwrite this very extensive test.")
def test_alignement_methods(self):
pass
@@ -1875,7 +1875,7 @@ class LayoutLMv2TokenizationTest(TokenizerTesterMixin, unittest.TestCase):
return words, boxes, output_ids
# @unittest.skip("LayoutLMv2 tokenizer requires boxes besides sequences.")
# @unittest.skip(reason="LayoutLMv2 tokenizer requires boxes besides sequences.")
def test_maximum_encoding_length_pair_input(self):
tokenizers = self.get_tokenizers(do_lower_case=False, model_max_length=100)
for tokenizer in tokenizers:
@@ -2237,7 +2237,7 @@ class LayoutLMv2TokenizationTest(TokenizerTesterMixin, unittest.TestCase):
self.assertEqual(bbox, bbox_second_sequence)
self.assertEqual(overflowing_bbox, overflowing_token_bbox_second_sequence_slow)
# @unittest.skip("LayoutLMv2 tokenizer requires boxes besides sequences.")
# @unittest.skip(reason="LayoutLMv2 tokenizer requires boxes besides sequences.")
def test_maximum_encoding_length_single_input(self):
tokenizers = self.get_tokenizers(do_lower_case=False, model_max_length=100)
for tokenizer in tokenizers:
@@ -2359,15 +2359,15 @@ class LayoutLMv2TokenizationTest(TokenizerTesterMixin, unittest.TestCase):
self.assertEqual(bbox, sequence["bbox"][:-2])
self.assertEqual(overflowing_bbox, sequence["bbox"][-(2 + stride) :])
@unittest.skip("LayoutLMv2 tokenizer requires boxes besides sequences.")
@unittest.skip(reason="LayoutLMv2 tokenizer requires boxes besides sequences.")
def test_pretokenized_inputs(self):
pass
@unittest.skip("LayoutLMv2 tokenizer always expects pretokenized inputs.")
@unittest.skip(reason="LayoutLMv2 tokenizer always expects pretokenized inputs.")
def test_compare_pretokenized_inputs(self):
pass
@unittest.skip("LayoutLMv2 fast tokenizer does not support prepare_for_model")
@unittest.skip(reason="LayoutLMv2 fast tokenizer does not support prepare_for_model")
def test_compare_prepare_for_model(self):
pass
@@ -2476,10 +2476,10 @@ class LayoutLMv2TokenizationTest(TokenizerTesterMixin, unittest.TestCase):
self.assertDictEqual(dict(encoding_p), expected_results)
self.assertDictEqual(dict(encoding_r), expected_results)
@unittest.skip("Doesn't support another framework than PyTorch")
@unittest.skip(reason="Doesn't support another framework than PyTorch")
def test_np_encode_plus_sent_to_model(self):
pass
@unittest.skip("Chat is not supported")
@unittest.skip(reason="Chat is not supported")
def test_chat_template(self):
pass