content-extraction 0.4.2__tar.gz → 0.4.3__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.
Files changed (23) hide show
  1. {content_extraction-0.4.2 → content_extraction-0.4.3}/PKG-INFO +1 -1
  2. {content_extraction-0.4.2 → content_extraction-0.4.3}/pyproject.toml +1 -1
  3. {content_extraction-0.4.2 → content_extraction-0.4.3}/src/content_extraction/split_and_create_digest.py +1 -0
  4. {content_extraction-0.4.2 → content_extraction-0.4.3}/src/content_extraction.egg-info/PKG-INFO +1 -1
  5. {content_extraction-0.4.2 → content_extraction-0.4.3}/README.md +0 -0
  6. {content_extraction-0.4.2 → content_extraction-0.4.3}/setup.cfg +0 -0
  7. {content_extraction-0.4.2 → content_extraction-0.4.3}/src/content_extraction/__init__.py +0 -0
  8. {content_extraction-0.4.2 → content_extraction-0.4.3}/src/content_extraction/common_std_io.py +0 -0
  9. {content_extraction-0.4.2 → content_extraction-0.4.3}/src/content_extraction/do_ocr.py +0 -0
  10. {content_extraction-0.4.2 → content_extraction-0.4.3}/src/content_extraction/extract_from_pptx.py +0 -0
  11. {content_extraction-0.4.2 → content_extraction-0.4.3}/src/content_extraction/file_handlers.py +0 -0
  12. {content_extraction-0.4.2 → content_extraction-0.4.3}/src/content_extraction/fix_ocr.py +0 -0
  13. {content_extraction-0.4.2 → content_extraction-0.4.3}/src/content_extraction/logging_config.py +0 -0
  14. {content_extraction-0.4.2 → content_extraction-0.4.3}/src/content_extraction/parse_html.py +0 -0
  15. {content_extraction-0.4.2 → content_extraction-0.4.3}/src/content_extraction/process.py +0 -0
  16. {content_extraction-0.4.2 → content_extraction-0.4.3}/src/content_extraction/process_document.sh +0 -0
  17. {content_extraction-0.4.2 → content_extraction-0.4.3}/src/content_extraction/semantic_chunk_html.py +0 -0
  18. {content_extraction-0.4.2 → content_extraction-0.4.3}/src/content_extraction.egg-info/SOURCES.txt +0 -0
  19. {content_extraction-0.4.2 → content_extraction-0.4.3}/src/content_extraction.egg-info/dependency_links.txt +0 -0
  20. {content_extraction-0.4.2 → content_extraction-0.4.3}/src/content_extraction.egg-info/requires.txt +0 -0
  21. {content_extraction-0.4.2 → content_extraction-0.4.3}/src/content_extraction.egg-info/top_level.txt +0 -0
  22. {content_extraction-0.4.2 → content_extraction-0.4.3}/tests/test_section_parser.py +0 -0
  23. {content_extraction-0.4.2 → content_extraction-0.4.3}/tests/test_semantic_chunk_html.py +0 -0
{content_extraction-0.4.2 → content_extraction-0.4.3}/PKG-INFO RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: content_extraction
3
- Version: 0.4.2
3
+ Version: 0.4.3
4
4
  Summary: Project dedicated to content extraction from unstructured files that contain some useful information.
5
5
  Requires-Python: >=3.12
6
6
  Description-Content-Type: text/markdown
{content_extraction-0.4.2 → content_extraction-0.4.3}/pyproject.toml RENAMED
@@ -10,7 +10,7 @@ where = ["src"]
10
10
 
11
11
  [project]
12
12
  name = "content_extraction"
13
- version = "0.4.2"
13
+ version = "0.4.3"
14
14
  description = "Project dedicated to content extraction from unstructured files that contain some useful information."
15
15
  readme = "README.md"
16
16
  requires-python = ">=3.12"
{content_extraction-0.4.2 → content_extraction-0.4.3}/src/content_extraction/split_and_create_digest.py RENAMED
@@ -35,6 +35,7 @@ class ProcessResultNode:
35
35
  title: str
36
36
  text: str
37
37
  section_digest: SectionDigestNode
38
+ language: str
38
39
 
39
40
 
40
41
  def shorten_text(text: str, max_elements: int = 2, subsections: list[dict] | None = None) -> str:
{content_extraction-0.4.2 → content_extraction-0.4.3}/src/content_extraction.egg-info/PKG-INFO RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: content_extraction
3
- Version: 0.4.2
3
+ Version: 0.4.3
4
4
  Summary: Project dedicated to content extraction from unstructured files that contain some useful information.
5
5
  Requires-Python: >=3.12
6
6
  Description-Content-Type: text/markdown