UniTok 4.3.7__tar.gz → 4.3.9__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-4.3.7 → UniTok-4.3.9}/PKG-INFO +1 -1
- {UniTok-4.3.7 → UniTok-4.3.9}/UniTok.egg-info/PKG-INFO +1 -1
- {UniTok-4.3.7 → UniTok-4.3.9}/setup.py +1 -1
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/tokenizer/digit_tokenizer.py +1 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/unitok.py +5 -4
- {UniTok-4.3.7 → UniTok-4.3.9}/LICENSE +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/README.md +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/UniTok.egg-info/SOURCES.txt +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/UniTok.egg-info/dependency_links.txt +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/UniTok.egg-info/entry_points.txt +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/UniTok.egg-info/requires.txt +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/UniTok.egg-info/top_level.txt +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/UniTokv3/__init__.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/UniTokv3/__main__.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/UniTokv3/analysis/__init__.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/UniTokv3/analysis/lengths.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/UniTokv3/analysis/plot.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/UniTokv3/cols.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/UniTokv3/column.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/UniTokv3/fut.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/UniTokv3/global_setting.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/UniTokv3/meta.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/UniTokv3/tok/__init__.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/UniTokv3/tok/bert_tok.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/UniTokv3/tok/ent_tok.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/UniTokv3/tok/id_tok.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/UniTokv3/tok/number_tok.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/UniTokv3/tok/seq_tok.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/UniTokv3/tok/split_tok.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/UniTokv3/tok/tok.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/UniTokv3/unidep.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/UniTokv3/unitok.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/UniTokv3/vocab.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/UniTokv3/vocabs.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/setup.cfg +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/__init__.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/__main__.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/job.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/meta.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/selector.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/status.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/tokenizer/__init__.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/tokenizer/base_tokenizer.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/tokenizer/entity_tokenizer.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/tokenizer/glove_tokenizer.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/tokenizer/split_tokenizer.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/tokenizer/transformers_tokenizer.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/tokenizer/union_tokenizer.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/tokenizer/unknown_tokenizer.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/utils/__init__.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/utils/class_pool.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/utils/data.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/utils/function.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/utils/handler/__init__.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/utils/handler/json_handler.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/utils/handler/pkl_handler.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/utils/hub/__init__.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/utils/hub/hub.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/utils/hub/param_hub.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/utils/index_set/__init__.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/utils/index_set/index_set.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/utils/index_set/job_set.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/utils/index_set/tokenizer_set.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/utils/index_set/vocabulary_set.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/utils/instance.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/utils/map.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/utils/space.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/utils/symbol.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/utils/verbose.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/vocabulary/__init__.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/unitok/vocabulary/counter.py +0 -0
- {UniTok-4.3.7 → UniTok-4.3.9}/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='4.3.
|
9
|
+
version='4.3.9',
|
10
10
|
keywords=['token', 'tokenizer', 'NLP', 'transformers', 'glove', 'bert', 'llama'],
|
11
11
|
description='Unified Tokenizer',
|
12
12
|
long_description=long_description,
|
@@ -373,10 +373,11 @@ class UniTok(Status):
|
|
373
373
|
if len(index) != 2:
|
374
374
|
raise ValueError('index should be tuple with 2 elements: (index, selector)')
|
375
375
|
index, selector = index
|
376
|
-
if not
|
377
|
-
if not isinstance(selector,
|
378
|
-
|
379
|
-
|
376
|
+
if selector is not None:
|
377
|
+
if not isinstance(selector, Selector):
|
378
|
+
if not isinstance(selector, tuple):
|
379
|
+
selector = (selector,)
|
380
|
+
selector = Selector(self.meta, *selector)
|
380
381
|
|
381
382
|
if isinstance(index, str):
|
382
383
|
# key_id is used
|
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
|