UniTok 4.3.2__tar.gz → 4.3.3__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-4.3.2 → UniTok-4.3.3}/PKG-INFO +1 -1
- {UniTok-4.3.2 → UniTok-4.3.3}/UniTok.egg-info/PKG-INFO +1 -1
- {UniTok-4.3.2 → UniTok-4.3.3}/UniTok.egg-info/SOURCES.txt +6 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/setup.py +1 -1
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/utils/hub/hub.py +5 -1
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/vocabulary/vocabulary.py +4 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/LICENSE +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/README.md +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/UniTok.egg-info/dependency_links.txt +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/UniTok.egg-info/entry_points.txt +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/UniTok.egg-info/requires.txt +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/UniTok.egg-info/top_level.txt +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/UniTokv3/__init__.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/UniTokv3/__main__.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/UniTokv3/analysis/__init__.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/UniTokv3/analysis/lengths.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/UniTokv3/analysis/plot.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/UniTokv3/cols.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/UniTokv3/column.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/UniTokv3/fut.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/UniTokv3/global_setting.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/UniTokv3/meta.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/UniTokv3/tok/__init__.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/UniTokv3/tok/bert_tok.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/UniTokv3/tok/ent_tok.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/UniTokv3/tok/id_tok.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/UniTokv3/tok/number_tok.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/UniTokv3/tok/seq_tok.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/UniTokv3/tok/split_tok.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/UniTokv3/tok/tok.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/UniTokv3/unidep.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/UniTokv3/unitok.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/UniTokv3/vocab.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/UniTokv3/vocabs.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/setup.cfg +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/__init__.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/__main__.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/job.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/meta.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/selector.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/status.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/tokenizer/__init__.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/tokenizer/base_tokenizer.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/tokenizer/digit_tokenizer.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/tokenizer/entity_tokenizer.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/tokenizer/glove_tokenizer.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/tokenizer/split_tokenizer.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/tokenizer/transformers_tokenizer.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/tokenizer/union_tokenizer.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/tokenizer/unknown_tokenizer.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/unitok.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/utils/__init__.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/utils/class_pool.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/utils/data.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/utils/function.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/utils/handler/__init__.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/utils/handler/json_handler.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/utils/handler/pkl_handler.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/utils/hub/__init__.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/utils/hub/param_hub.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/utils/index_set/__init__.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/utils/index_set/index_set.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/utils/index_set/job_set.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/utils/index_set/tokenizer_set.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/utils/index_set/vocabulary_set.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/utils/instance.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/utils/map.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/utils/space.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/utils/symbol.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/utils/verbose.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/vocabulary/__init__.py +0 -0
- {UniTok-4.3.2 → UniTok-4.3.3}/unitok/vocabulary/counter.py +0 -0
@@ -36,6 +36,12 @@ unitok/meta.py
|
|
36
36
|
unitok/selector.py
|
37
37
|
unitok/status.py
|
38
38
|
unitok/unitok.py
|
39
|
+
unitok.egg-info/PKG-INFO
|
40
|
+
unitok.egg-info/SOURCES.txt
|
41
|
+
unitok.egg-info/dependency_links.txt
|
42
|
+
unitok.egg-info/entry_points.txt
|
43
|
+
unitok.egg-info/requires.txt
|
44
|
+
unitok.egg-info/top_level.txt
|
39
45
|
unitok/tokenizer/__init__.py
|
40
46
|
unitok/tokenizer/base_tokenizer.py
|
41
47
|
unitok/tokenizer/digit_tokenizer.py
|
@@ -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='4.3.
|
9
|
+
version='4.3.3',
|
10
10
|
keywords=['token', 'tokenizer', 'NLP', 'transformers', 'glove', 'bert', 'llama'],
|
11
11
|
description='Unified Tokenizer',
|
12
12
|
long_description=long_description,
|
@@ -13,10 +13,14 @@ class Hub(abc.ABC, Generic[T]):
|
|
13
13
|
@classmethod
|
14
14
|
def add(cls, key, obj: T = None):
|
15
15
|
instance = cls._instance.current()
|
16
|
-
if key in instance and instance[key]
|
16
|
+
if key in instance and cls.notequal(instance[key], obj):
|
17
17
|
raise ValueError(f'Conflict object declaration: {obj} and {instance[key]}')
|
18
18
|
instance[key] = obj
|
19
19
|
|
20
|
+
@classmethod
|
21
|
+
def notequal(cls, a: T, b: T) -> bool:
|
22
|
+
return a is not b
|
23
|
+
|
20
24
|
@classmethod
|
21
25
|
def get(cls, name: str, **kwargs) -> T:
|
22
26
|
"""
|
@@ -164,3 +164,7 @@ class VocabularyHub(Hub[Vocabulary]):
|
|
164
164
|
def add(cls, key, obj: Vocabulary = None):
|
165
165
|
key, obj = key.name, key
|
166
166
|
return super().add(key, obj)
|
167
|
+
|
168
|
+
@classmethod
|
169
|
+
def notequal(cls, a: Vocabulary, b: Vocabulary) -> bool:
|
170
|
+
return a.name != b.name or a.size != b.size
|
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
|