semantic-compressor 1.4__tar.gz → 1.5__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.
Files changed (21) hide show
  1. {semantic_compressor-1.4/semantic_compressor.egg-info → semantic_compressor-1.5}/PKG-INFO +1 -1
  2. {semantic_compressor-1.4 → semantic_compressor-1.5}/compressor/semantic.py +10 -3
  3. {semantic_compressor-1.4 → semantic_compressor-1.5}/pyproject.toml +1 -1
  4. {semantic_compressor-1.4 → semantic_compressor-1.5/semantic_compressor.egg-info}/PKG-INFO +1 -1
  5. {semantic_compressor-1.4 → semantic_compressor-1.5}/setup.py +1 -1
  6. {semantic_compressor-1.4 → semantic_compressor-1.5}/LICENSE +0 -0
  7. {semantic_compressor-1.4 → semantic_compressor-1.5}/README.md +0 -0
  8. {semantic_compressor-1.4 → semantic_compressor-1.5}/compressor/__init__.py +0 -0
  9. {semantic_compressor-1.4 → semantic_compressor-1.5}/compressor/minbpe/__init__.py +0 -0
  10. {semantic_compressor-1.4 → semantic_compressor-1.5}/compressor/minbpe/base.py +0 -0
  11. {semantic_compressor-1.4 → semantic_compressor-1.5}/compressor/minbpe/basic.py +0 -0
  12. {semantic_compressor-1.4 → semantic_compressor-1.5}/compressor/minbpe/regex.py +0 -0
  13. {semantic_compressor-1.4 → semantic_compressor-1.5}/compressor/resources/embedding_model.onnx +0 -0
  14. {semantic_compressor-1.4 → semantic_compressor-1.5}/compressor/resources/en_stopwords.pkl +0 -0
  15. {semantic_compressor-1.4 → semantic_compressor-1.5}/compressor/resources/lid.176.ftz +0 -0
  16. {semantic_compressor-1.4 → semantic_compressor-1.5}/compressor/resources/pt_stopwords.pkl +0 -0
  17. {semantic_compressor-1.4 → semantic_compressor-1.5}/semantic_compressor.egg-info/SOURCES.txt +0 -0
  18. {semantic_compressor-1.4 → semantic_compressor-1.5}/semantic_compressor.egg-info/dependency_links.txt +0 -0
  19. {semantic_compressor-1.4 → semantic_compressor-1.5}/semantic_compressor.egg-info/requires.txt +0 -0
  20. {semantic_compressor-1.4 → semantic_compressor-1.5}/semantic_compressor.egg-info/top_level.txt +0 -0
  21. {semantic_compressor-1.4 → semantic_compressor-1.5}/setup.cfg +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: semantic_compressor
3
- Version: 1.4
3
+ Version: 1.5
4
4
  Author: Carlo Moro
5
5
  Author-email: Carlo Moro <cnmoro@gmail.com>
6
6
  Classifier: Programming Language :: Python :: 3
@@ -250,11 +250,18 @@ def stem_text(text, lang='en'):
250
250
 
251
251
  return stemmed_text
252
252
 
253
- def correct_spelling(frase, detected_lang="pt"):
253
+ def correct_spelling(sentence, detected_lang="pt"):
254
254
  spell = SpellChecker(language=detected_lang)
255
- words = frase.split()
255
+ words = sentence.split()
256
256
  fixed = [spell.correction(word) for word in words]
257
- return " ".join(fixed)
257
+
258
+ final_words = []
259
+
260
+ # Interpolate original words with fixed words (each word could be "None" in "fixed" when no correction is needed)
261
+ for original, fixed_word in zip(words, fixed):
262
+ final_words.append(fixed_word if fixed_word is not None else original)
263
+
264
+ return " ".join(final_words)
258
265
 
259
266
  def find_needle_in_haystack(
260
267
  *, haystack: str, needle: str, block_size = 300,
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
4
4
 
5
5
  [project]
6
6
  name = "semantic_compressor"
7
- version = "1.4"
7
+ version = "1.5"
8
8
  authors = [
9
9
  { name="Carlo Moro", email="cnmoro@gmail.com" },
10
10
  ]
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: semantic_compressor
3
- Version: 1.4
3
+ Version: 1.5
4
4
  Author: Carlo Moro
5
5
  Author-email: Carlo Moro <cnmoro@gmail.com>
6
6
  Classifier: Programming Language :: Python :: 3
@@ -2,7 +2,7 @@ from setuptools import setup, find_packages
2
2
 
3
3
  setup(
4
4
  name='semantic_compressor',
5
- version='1.4',
5
+ version='1.5',
6
6
  author='Carlo Moro',
7
7
  author_email='cnmoro@gmail.com',
8
8
  description="Semantic text compression",