UniTok 4.4.1__tar.gz → 4.4.3__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {UniTok-4.4.1 → UniTok-4.4.3}/PKG-INFO +1 -1
- {UniTok-4.4.1 → UniTok-4.4.3}/UniTok.egg-info/PKG-INFO +1 -1
- {UniTok-4.4.1 → UniTok-4.4.3}/setup.py +1 -1
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/meta.py +5 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/tokenizer/union_tokenizer.py +3 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/utils/index_set/feature_set.py +2 -1
- {UniTok-4.4.1 → UniTok-4.4.3}/LICENSE +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/README.md +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/UniTok.egg-info/SOURCES.txt +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/UniTok.egg-info/dependency_links.txt +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/UniTok.egg-info/entry_points.txt +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/UniTok.egg-info/requires.txt +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/UniTok.egg-info/top_level.txt +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/UniTokv3/__init__.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/UniTokv3/__main__.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/UniTokv3/analysis/__init__.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/UniTokv3/analysis/lengths.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/UniTokv3/analysis/plot.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/UniTokv3/cols.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/UniTokv3/column.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/UniTokv3/fut.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/UniTokv3/global_setting.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/UniTokv3/meta.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/UniTokv3/tok/__init__.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/UniTokv3/tok/bert_tok.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/UniTokv3/tok/ent_tok.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/UniTokv3/tok/id_tok.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/UniTokv3/tok/number_tok.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/UniTokv3/tok/seq_tok.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/UniTokv3/tok/split_tok.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/UniTokv3/tok/tok.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/UniTokv3/unidep.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/UniTokv3/unitok.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/UniTokv3/vocab.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/UniTokv3/vocabs.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/setup.cfg +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/__init__.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/__main__.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/feature.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/job.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/selector.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/status.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/tokenizer/__init__.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/tokenizer/base_tokenizer.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/tokenizer/digit_tokenizer.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/tokenizer/entity_tokenizer.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/tokenizer/glove_tokenizer.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/tokenizer/split_tokenizer.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/tokenizer/transformers_tokenizer.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/tokenizer/unknown_tokenizer.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/unitok.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/utils/__init__.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/utils/class_pool.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/utils/data.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/utils/function.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/utils/handler/__init__.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/utils/handler/json_handler.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/utils/handler/pkl_handler.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/utils/hub/__init__.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/utils/hub/hub.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/utils/hub/param_hub.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/utils/index_set/__init__.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/utils/index_set/index_set.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/utils/index_set/job_set.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/utils/index_set/tokenizer_set.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/utils/index_set/vocabulary_set.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/utils/instance.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/utils/map.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/utils/space.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/utils/symbol.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/utils/verbose.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/vocabulary/__init__.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/vocabulary/counter.py +0 -0
- {UniTok-4.4.1 → UniTok-4.4.3}/unitok/vocabulary/vocabulary.py +0 -0
@@ -6,7 +6,7 @@ long_description = (this_directory / "README.md").read_text(encoding='utf8')
|
|
6
6
|
|
7
7
|
setup(
|
8
8
|
name='UniTok',
|
9
|
-
version='4.4.
|
9
|
+
version='4.4.3',
|
10
10
|
keywords=['token', 'tokenizer', 'NLP', 'transformers', 'glove', 'bert', 'llama'],
|
11
11
|
description='Unified Tokenizer',
|
12
12
|
long_description=long_description,
|
@@ -27,6 +27,11 @@ class Meta:
|
|
27
27
|
self.tokenizers = TokenizerSet()
|
28
28
|
self.features = FeatureSet()
|
29
29
|
|
30
|
+
@property
|
31
|
+
def jobs(self):
|
32
|
+
warnings.warn('`jobs` is deprecated, use `features` instead.', DeprecationWarning, stacklevel=2)
|
33
|
+
return self.features
|
34
|
+
|
30
35
|
@staticmethod
|
31
36
|
def parse_vocabulary(name: str, **kwargs):
|
32
37
|
return Vocab(name)
|
@@ -12,6 +12,9 @@ class UnionTokenizer(BaseTokenizer):
|
|
12
12
|
self.tokenizer = tokenizer
|
13
13
|
self.classname = self.tokenizer._detailed_classname
|
14
14
|
|
15
|
+
def __call__(self, obj):
|
16
|
+
raise NotImplementedError('UnionTokenizer is used as a placeholder and should not be called.')
|
17
|
+
|
15
18
|
@property
|
16
19
|
def _detailed_classname(self):
|
17
20
|
return f'{self.__class__.__name__}[{self.classname}]'
|
@@ -22,4 +22,5 @@ class FeatureSet(IndexSet[Feature]):
|
|
22
22
|
raise ValueError(f'Merge unprocessed feature: {feature}')
|
23
23
|
if self.has(self._get_key(feature)):
|
24
24
|
raise ValueError(f'Conflict feature name: {feature.name}')
|
25
|
-
self.add(feature.clone(order=next_order, tokenizer=UnionTokenizer(feature.tokenizer)))
|
25
|
+
# self.add(feature.clone(order=next_order, tokenizer=UnionTokenizer(feature.tokenizer)))
|
26
|
+
self.add(feature.clone(order=next_order))
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|