UniTok 4.3.3__tar.gz → 4.3.4__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-4.3.3 → UniTok-4.3.4}/PKG-INFO +1 -1
- {UniTok-4.3.3 → UniTok-4.3.4}/UniTok.egg-info/PKG-INFO +1 -1
- {UniTok-4.3.3 → UniTok-4.3.4}/setup.py +1 -1
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/unitok.py +15 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/LICENSE +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/README.md +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/UniTok.egg-info/SOURCES.txt +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/UniTok.egg-info/dependency_links.txt +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/UniTok.egg-info/entry_points.txt +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/UniTok.egg-info/requires.txt +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/UniTok.egg-info/top_level.txt +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/UniTokv3/__init__.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/UniTokv3/__main__.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/UniTokv3/analysis/__init__.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/UniTokv3/analysis/lengths.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/UniTokv3/analysis/plot.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/UniTokv3/cols.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/UniTokv3/column.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/UniTokv3/fut.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/UniTokv3/global_setting.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/UniTokv3/meta.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/UniTokv3/tok/__init__.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/UniTokv3/tok/bert_tok.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/UniTokv3/tok/ent_tok.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/UniTokv3/tok/id_tok.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/UniTokv3/tok/number_tok.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/UniTokv3/tok/seq_tok.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/UniTokv3/tok/split_tok.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/UniTokv3/tok/tok.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/UniTokv3/unidep.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/UniTokv3/unitok.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/UniTokv3/vocab.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/UniTokv3/vocabs.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/setup.cfg +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/__init__.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/__main__.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/job.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/meta.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/selector.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/status.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/tokenizer/__init__.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/tokenizer/base_tokenizer.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/tokenizer/digit_tokenizer.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/tokenizer/entity_tokenizer.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/tokenizer/glove_tokenizer.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/tokenizer/split_tokenizer.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/tokenizer/transformers_tokenizer.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/tokenizer/union_tokenizer.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/tokenizer/unknown_tokenizer.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/utils/__init__.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/utils/class_pool.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/utils/data.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/utils/function.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/utils/handler/__init__.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/utils/handler/json_handler.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/utils/handler/pkl_handler.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/utils/hub/__init__.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/utils/hub/hub.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/utils/hub/param_hub.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/utils/index_set/__init__.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/utils/index_set/index_set.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/utils/index_set/job_set.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/utils/index_set/tokenizer_set.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/utils/index_set/vocabulary_set.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/utils/instance.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/utils/map.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/utils/space.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/utils/symbol.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/utils/verbose.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/vocabulary/__init__.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/unitok/vocabulary/counter.py +0 -0
- {UniTok-4.3.3 → UniTok-4.3.4}/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='4.3.4',
|
10
10
|
keywords=['token', 'tokenizer', 'NLP', 'transformers', 'glove', 'bert', 'llama'],
|
11
11
|
description='Unified Tokenizer',
|
12
12
|
long_description=long_description,
|
@@ -276,6 +276,21 @@ class UniTok(Status):
|
|
276
276
|
if job is not other.key_job:
|
277
277
|
self.data[job.name] = union_data[job.name]
|
278
278
|
|
279
|
+
@Status.require_not_initialized
|
280
|
+
@Status.to_organized
|
281
|
+
def replicate(self, job: Union[Job, str], new_name: str):
|
282
|
+
if isinstance(job, str):
|
283
|
+
job = self.meta.jobs[job]
|
284
|
+
|
285
|
+
if not job.is_processed:
|
286
|
+
raise ValueError(f'job {job.name} is not processed')
|
287
|
+
|
288
|
+
if job.from_union and self.is_soft_union:
|
289
|
+
raise ValueError(f'job {job.name} is from a soft union, please use hard union or save-and-load the unitok.')
|
290
|
+
|
291
|
+
new_job = job.clone(name=new_name)
|
292
|
+
self.data[new_job.name] = self.data[job.name]
|
293
|
+
|
279
294
|
@Status.require_not_initialized
|
280
295
|
def summarize(self):
|
281
296
|
console = Console()
|
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
|