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

56
tests/models/layoutxlm/test_tokenization_layoutxlm.py
View File

@@ -107,7 +107,7 @@ class LayoutXLMTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
output_text = "unwanted, running"
return input_text, output_text
@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
@@ -115,7 +115,7 @@ class LayoutXLMTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
# this tokenizer
def test_save_sentencepiece_tokenizer(self) -> None:
if not self.test_sentencepiece or not self.test_slow_tokenizer:
return
self.skipTest(reason="test_sentencepiece or test_slow_tokenizer is set to False")
# We want to verify that we will be able to save the tokenizer even if the original files that were used to
# build the tokenizer have been deleted in the meantime.
words, boxes = self.get_words_and_boxes()
@@ -745,7 +745,7 @@ class LayoutXLMTokenizationTest(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()
@@ -766,7 +766,7 @@ class LayoutXLMTokenizationTest(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()
@@ -873,7 +873,7 @@ class LayoutXLMTokenizationTest(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
@@ -934,7 +934,7 @@ class LayoutXLMTokenizationTest(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()
@@ -977,7 +977,7 @@ class LayoutXLMTokenizationTest(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})"):
@@ -1066,7 +1066,7 @@ class LayoutXLMTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
shutil.rmtree(tmpdirname)
@unittest.skip("Not implemented")
@unittest.skip(reason="Not implemented")
def test_right_and_left_truncation(self):
pass
@@ -1224,13 +1224,13 @@ class LayoutXLMTokenizationTest(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)
@@ -1256,11 +1256,11 @@ class LayoutXLMTokenizationTest(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()
@@ -1278,7 +1278,7 @@ class LayoutXLMTokenizationTest(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})"):
@@ -1332,7 +1332,7 @@ class LayoutXLMTokenizationTest(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})"):
@@ -1522,7 +1522,7 @@ class LayoutXLMTokenizationTest(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)
@@ -1559,7 +1559,7 @@ class LayoutXLMTokenizationTest(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
@@ -1672,7 +1672,7 @@ class LayoutXLMTokenizationTest(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})"):
@@ -1770,7 +1770,7 @@ class LayoutXLMTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
def test_save_pretrained(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")
self.tokenizers_list[0] = (self.rust_tokenizer_class, "hf-internal-testing/tiny-random-layoutxlm", {})
for tokenizer, pretrained_name, kwargs in self.tokenizers_list:
@@ -1838,27 +1838,27 @@ class LayoutXLMTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
shutil.rmtree(tmpdirname2)
@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
@unittest.skip("layoutxlm tokenizer requires boxes besides sequences.")
@unittest.skip(reason="layoutxlm tokenizer requires boxes besides sequences.")
def test_maximum_encoding_length_pair_input(self):
pass
@unittest.skip("layoutxlm tokenizer requires boxes besides sequences.")
@unittest.skip(reason="layoutxlm tokenizer requires boxes besides sequences.")
def test_maximum_encoding_length_single_input(self):
pass
@unittest.skip("layoutxlm tokenizer requires boxes besides sequences.")
@unittest.skip(reason="layoutxlm tokenizer requires boxes besides sequences.")
def test_pretokenized_inputs(self):
pass
@unittest.skip("layoutxlm tokenizer always expects pretokenized inputs.")
@unittest.skip(reason="layoutxlm tokenizer always expects pretokenized inputs.")
def test_compare_pretokenized_inputs(self):
pass
@unittest.skip("layoutxlm fast tokenizer does not support prepare_for_model")
@unittest.skip(reason="layoutxlm fast tokenizer does not support prepare_for_model")
def test_compare_prepare_for_model(self):
pass
@@ -1962,18 +1962,18 @@ class LayoutXLMTokenizationTest(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("Doesn't use SentencePiece")
@unittest.skip(reason="Doesn't use SentencePiece")
def test_sentencepiece_tokenize_and_convert_tokens_to_string(self):
pass
@unittest.skip("Doesn't use SentencePiece")
@unittest.skip(reason="Doesn't use SentencePiece")
def test_sentencepiece_tokenize_and_decode(self):
pass
@unittest.skip("Chat is not supported")
@unittest.skip(reason="Chat is not supported")
def test_chat_template(self):
pass