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

removing test for long sequences error following #337

Browse Source
This commit is contained in:
thomwolf
2019-03-06 10:10:41 +01:00
parent 5c85fc3977
commit 2dd8f524f5
1 changed files with 0 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
tests/tokenization_test.py
View File

@@ -46,24 +46,6 @@ class TokenizationTest(unittest.TestCase):
self.assertListEqual( self.assertListEqual(
tokenizer.convert_tokens_to_ids(tokens), [7, 4, 5, 10, 8, 9]) tokenizer.convert_tokens_to_ids(tokens), [7, 4, 5, 10, 8, 9])
def test_full_tokenizer_raises_error_for_long_sequences(self):
vocab_tokens = [
"[UNK]", "[CLS]", "[SEP]", "want", "##want", "##ed", "wa", "un", "runn",
"##ing", ","
]
with open("/tmp/bert_tokenizer_test.txt", "w", encoding='utf-8') as vocab_writer:
vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))
vocab_file = vocab_writer.name
tokenizer = BertTokenizer(vocab_file, max_len=10)
os.remove(vocab_file)
tokens = tokenizer.tokenize(u"the cat sat on the mat in the summer time")
indices = tokenizer.convert_tokens_to_ids(tokens)
self.assertListEqual(indices, [0 for _ in range(10)])
tokens = tokenizer.tokenize(u"the cat sat on the mat in the summer time .")
self.assertRaises(ValueError, tokenizer.convert_tokens_to_ids, tokens)
def test_chinese(self): def test_chinese(self):
tokenizer = BasicTokenizer() tokenizer = BasicTokenizer()