Metadata-Version: 2.4
Name: ureca_document_parser
Version: 0.0.1
Summary: Multi-format document parser and converter (HWP, HWPX, PDF, Image)
Project-URL: Homepage, https://ureca-corp.github.io/document_parser/
Project-URL: Documentation, https://ureca-corp.github.io/document_parser/
Project-URL: Repository, https://github.com/ureca-corp/document_parser
Project-URL: Issues, https://github.com/ureca-corp/document_parser/issues
Author-email: Ureca Enterprise Corp <andy@ureca.im>
License: MIT
Keywords: converter,document,hwp,hwpx,markdown,parser
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Text Processing :: Markup
Requires-Python: >=3.12
Requires-Dist: olefile>=0.47
Provides-Extra: all
Requires-Dist: langchain-core>=0.2; extra == 'all'
Requires-Dist: langchain-text-splitters>=0.2; extra == 'all'
Requires-Dist: mkdocs-material>=9.5; extra == 'all'
Requires-Dist: mkdocs>=1.6; extra == 'all'
Requires-Dist: mkdocstrings[python]>=0.27; extra == 'all'
Requires-Dist: pillow>=10.0; extra == 'all'
Requires-Dist: pymupdf>=1.24; extra == 'all'
Requires-Dist: pytesseract>=0.3; extra == 'all'
Provides-Extra: dev
Requires-Dist: mypy>=1.10; extra == 'dev'
Requires-Dist: pytest-cov>=5.0; extra == 'dev'
Requires-Dist: pytest>=8.0; extra == 'dev'
Requires-Dist: ruff>=0.4; extra == 'dev'
Provides-Extra: docs
Requires-Dist: mkdocs-material>=9.5; extra == 'docs'
Requires-Dist: mkdocs>=1.6; extra == 'docs'
Requires-Dist: mkdocstrings[python]>=0.27; extra == 'docs'
Provides-Extra: langchain
Requires-Dist: langchain-core>=0.2; extra == 'langchain'
Requires-Dist: langchain-text-splitters>=0.2; extra == 'langchain'
Provides-Extra: ocr
Requires-Dist: pillow>=10.0; extra == 'ocr'
Requires-Dist: pytesseract>=0.3; extra == 'ocr'
Provides-Extra: pdf
Requires-Dist: pymupdf>=1.24; extra == 'pdf'
