def test_special_tokens_initialization(self):
for tokenizer, pretrained_name, kwargs in self.tokenizers_list:
with self.subTest(f"{tokenizer.__class__.__name__} ({pretrained_name})"):
added_tokens = [AddedToken("<special>", lstrip=True)]
tokenizer_r = self.rust_tokenizer_class.from_pretrained(
pretrained_name, additional_special_tokens=added_tokens, **kwargs
)
r_output = tokenizer_r.encode("Hey this is a <special> token")
special_token_id = tokenizer_r.encode("<special>", add_special_tokens=False)[0]
self.assertTrue(special_token_id in r_output)
if self.test_slow_tokenizer:
tokenizer_p = self.tokenizer_class.from_pretrained(
pretrained_name, additional_special_tokens=added_tokens, **kwargs
)
p_output = tokenizer_p.encode("Hey this is a <special> token")
cr_output = tokenizer_r.encode("Hey this is a <special> token")
self.assertEqual(p_output, r_output)
self.assertEqual(cr_output, r_output)
self.assertTrue(special_token_id in p_output)
self.assertTrue(special_token_id in cr_output)
def __init__(
self,
vocab_file,
merges_file,
errors="replace",
bos_token="<BOS>",
eos_token="<EOS>",
sep_token="<&&&>",
cls_token="<s>",
unk_token="<UNK>",
pad_token="<PAD>",
mask_token="<MASK>",
visual_token="<VISUAL>",
add_prefix_space=False,
**kwargs
):
visual_token = AddedToken(visual_token, lstrip=False, rstrip=False) if isinstance(visual_token, str) else visual_token
super().__init__(
vocab_file=vocab_file,
merges_file=merges_file,
errors=errors,
bos_token=bos_token,
eos_token=eos_token,
unk_token=unk_token,
sep_token=sep_token,
cls_token=cls_token,
pad_token=pad_token,
mask_token=mask_token,
add_prefix_space=add_prefix_space,
**kwargs,
)
def test_special_tokens_initialization_with_non_empty_additional_special_tokens(self):
tokenizer_list = []
if self.test_slow_tokenizer:
tokenizer_list.append((self.tokenizer_class, self.get_tokenizer()))
if self.test_rust_tokenizer:
tokenizer_list.append((self.rust_tokenizer_class, self.get_rust_tokenizer()))
for tokenizer_class, tokenizer_utils in tokenizer_list:
with tempfile.TemporaryDirectory() as tmp_dir:
tokenizer_utils.save_pretrained(tmp_dir)
with open(os.path.join(tmp_dir, "special_tokens_map.json"), encoding="utf-8") as json_file:
special_tokens_map = json.load(json_file)
with open(os.path.join(tmp_dir, "tokenizer_config.json"), encoding="utf-8") as json_file:
tokenizer_config = json.load(json_file)
# a special token for Canine can be defined as follows:
NEW_TOKEN = 0xE006
new_token_1 = chr(NEW_TOKEN)
special_tokens_map["additional_special_tokens"] = [new_token_1]
tokenizer_config["additional_special_tokens"] = [new_token_1]
with open(os.path.join(tmp_dir, "special_tokens_map.json"), "w", encoding="utf-8") as outfile:
json.dump(special_tokens_map, outfile)
with open(os.path.join(tmp_dir, "tokenizer_config.json"), "w", encoding="utf-8") as outfile:
json.dump(tokenizer_config, outfile)
# the following checks allow us to verify that our test works as expected, i.e. that the tokenizer takes
# into account the new value of additional_special_tokens given in the "tokenizer_config.json" and
# "special_tokens_map.json" files
tokenizer_without_change_in_init = tokenizer_class.from_pretrained(tmp_dir, extra_ids=0)
self.assertIn(new_token_1, tokenizer_without_change_in_init.additional_special_tokens)
# self.assertIn("an_additional_special_token",tokenizer_without_change_in_init.get_vocab()) # ByT5Tokenization no vocab
self.assertEqual(
[new_token_1],
tokenizer_without_change_in_init.convert_ids_to_tokens(
tokenizer_without_change_in_init.convert_tokens_to_ids([new_token_1])
),
)
NEW_TOKEN = 0xE007
new_token_2 = chr(NEW_TOKEN)
# Now we test that we can change the value of additional_special_tokens in the from_pretrained
new_added_tokens = [AddedToken(new_token_2, lstrip=True)]
tokenizer = tokenizer_class.from_pretrained(
tmp_dir, additional_special_tokens=new_added_tokens, extra_ids=0
)
self.assertIn(new_token_2, tokenizer.additional_special_tokens)
# self.assertIn(new_token_2,tokenizer.get_vocab()) # ByT5Tokenization no vocab
self.assertEqual(
[new_token_2], tokenizer.convert_ids_to_tokens(tokenizer.convert_tokens_to_ids([new_token_2]))
)
def test_added_token_serializable(self):
tokenizers = self.get_tokenizers(do_lower_case=False)
for tokenizer in tokenizers:
with self.subTest(f"{tokenizer.__class__.__name__}"):
# a special token for Canine can be defined as follows:
NEW_TOKEN = 0xE006
new_token = chr(NEW_TOKEN)
new_token = AddedToken(new_token, lstrip=True)
tokenizer.add_special_tokens({"additional_special_tokens": [new_token]})
with tempfile.TemporaryDirectory() as tmp_dir_name:
tokenizer.save_pretrained(tmp_dir_name)
tokenizer.from_pretrained(tmp_dir_name)
def __init__(self,
vocab_file,
do_lower_case=False,
remove_space=True,
keep_accents=False,
bos_token="[CLS]",
eos_token="[SEP]",
unk_token="[UNK]",
sep_token="[SEP]",
pad_token="[PAD]",
cls_token="[CLS]",
mask_token="[MASK]",
additional_special_tokens=None,
sp_model_kwargs: Optional[Dict[str, Any]] = None,
**kwargs) -> None:
# Mask token behave like a normal word, i.e. include the space before it
mask_token = AddedToken(mask_token,
lstrip=True, rstrip=False) if isinstance(
mask_token, str) else mask_token
self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
super().__init__(
vocab_file,
do_lower_case=do_lower_case,
remove_space=remove_space,
keep_accents=keep_accents,
bos_token=bos_token,
eos_token=eos_token,
unk_token=unk_token,
sep_token=sep_token,
pad_token=pad_token,
cls_token=cls_token,
mask_token=mask_token,
additional_special_tokens=additional_special_tokens,
sp_model_kwargs=self.sp_model_kwargs,
**kwargs,
)
self._pad_token_type_id = 0
