natural-pdf 0.1.17__tar.gz → 0.1.19__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.
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/.gitignore +1 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/01-execute_notebooks.py +1 -0
- {natural_pdf-0.1.17/natural_pdf.egg-info → natural_pdf-0.1.19}/PKG-INFO +17 -18
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/layout-analysis/index.ipynb +422 -213
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/layout-analysis/index.md +10 -6
- natural_pdf-0.1.19/docs/tutorials/01-loading-and-extraction.ipynb +320 -0
- natural_pdf-0.1.19/docs/tutorials/02-finding-elements.ipynb +344 -0
- natural_pdf-0.1.19/docs/tutorials/03-extracting-blocks.ipynb +151 -0
- natural_pdf-0.1.19/docs/tutorials/04-table-extraction.ipynb +557 -0
- natural_pdf-0.1.19/docs/tutorials/05-excluding-content.ipynb +274 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/06-document-qa.ipynb +40 -53
- natural_pdf-0.1.19/docs/tutorials/07-layout-analysis.ipynb +615 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/07-working-with-regions.ipynb +67 -75
- natural_pdf-0.1.19/docs/tutorials/08-spatial-navigation.ipynb +512 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/09-section-extraction.ipynb +121 -157
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/10-form-field-extraction.ipynb +57 -65
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/11-enhanced-table-processing.ipynb +13 -14
- natural_pdf-0.1.19/docs/tutorials/12-ocr-integration.ipynb +4197 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/12-ocr-integration.md +0 -1
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/13-semantic-search.ipynb +134 -169
- natural_pdf-0.1.19/docs/tutorials/14-categorizing-documents.ipynb +2138 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/14-categorizing-documents.md +1 -1
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/classification/manager.py +38 -13
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/core/pdf.py +141 -32
- natural_pdf-0.1.19/natural_pdf/exporters/__init__.py +15 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/exporters/hocr.py +9 -8
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/exporters/original_pdf.py +31 -2
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/ocr/engine_surya.py +1 -2
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/ocr/ocr_manager.py +21 -4
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/search/__init__.py +20 -3
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/search/lancedb_search_service.py +13 -5
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/search/numpy_search_service.py +13 -3
- {natural_pdf-0.1.17 → natural_pdf-0.1.19/natural_pdf.egg-info}/PKG-INFO +17 -18
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf.egg-info/SOURCES.txt +3 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf.egg-info/requires.txt +17 -15
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/noxfile.py +13 -3
- natural_pdf-0.1.19/pdfs/appendix_fy2026.pdf +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pyproject.toml +23 -19
- natural_pdf-0.1.19/test_install.sh +46 -0
- natural_pdf-0.1.19/tests/test_tutorials.py +50 -0
- natural_pdf-0.1.17/docs/tutorials/01-loading-and-extraction.ipynb +0 -328
- natural_pdf-0.1.17/docs/tutorials/02-finding-elements.ipynb +0 -352
- natural_pdf-0.1.17/docs/tutorials/03-extracting-blocks.ipynb +0 -159
- natural_pdf-0.1.17/docs/tutorials/04-table-extraction.ipynb +0 -579
- natural_pdf-0.1.17/docs/tutorials/05-excluding-content.ipynb +0 -8402
- natural_pdf-0.1.17/docs/tutorials/07-layout-analysis.ipynb +0 -630
- natural_pdf-0.1.17/docs/tutorials/08-spatial-navigation.ipynb +0 -520
- natural_pdf-0.1.17/docs/tutorials/12-ocr-integration.ipynb +0 -4353
- natural_pdf-0.1.17/docs/tutorials/14-categorizing-documents.ipynb +0 -2142
- natural_pdf-0.1.17/natural_pdf/exporters/__init__.py +0 -4
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/.cursor/rules/analysis_framework.mdc +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/.cursor/rules/coding-style.mdc +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/.cursor/rules/edit-md-instead-of-ipynb.mdc +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/.cursor/rules/minimal-comments.mdc +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/.cursor/rules/natural-pdf-overview.mdc +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/.cursor/rules/user-friendly-library-code.mdc +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/.github/workflows/docs.yml +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/.pre-commit-config.yaml +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/02-run_all_tutorials.sh +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/CLAUDE.md +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/LICENSE +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/MANIFEST.in +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/README.md +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/audit_packaging.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/check_run_md.sh +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/api/index.md +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/assets/favicon.png +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/assets/favicon.svg +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/assets/javascripts/custom.js +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/assets/logo.svg +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/assets/sample-screen.png +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/assets/social-preview.png +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/assets/social-preview.svg +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/assets/stylesheets/custom.css +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/categorizing-documents/index.md +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/data-extraction/index.md +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/describe/index.ipynb +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/describe/index.md +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/document-qa/index.ipynb +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/document-qa/index.md +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/element-selection/index.ipynb +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/element-selection/index.md +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/finetuning/index.md +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/index.md +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/installation/index.md +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/interactive-widget/index.ipynb +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/interactive-widget/index.md +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/loops-and-groups/index.ipynb +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/loops-and-groups/index.md +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/ocr/index.md +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/pdf-navigation/index.ipynb +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/pdf-navigation/index.md +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/reflowing-pages/index.ipynb +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/reflowing-pages/index.md +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/regions/index.ipynb +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/regions/index.md +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tables/index.ipynb +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tables/index.md +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/text-analysis/index.ipynb +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/text-analysis/index.md +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/text-extraction/index.ipynb +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/text-extraction/index.md +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/01-loading-and-extraction.md +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/02-finding-elements.md +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/03-extracting-blocks.md +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/04-table-extraction.md +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/05-excluding-content.md +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/06-document-qa.md +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/07-layout-analysis.md +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/07-working-with-regions.md +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/08-spatial-navigation.md +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/09-section-extraction.md +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/10-form-field-extraction.md +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/11-enhanced-table-processing.md +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/13-semantic-search.md +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/visual-debugging/index.ipynb +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/visual-debugging/index.md +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/visual-debugging/region.png +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/mkdocs.yml +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/__init__.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/analyzers/__init__.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/analyzers/layout/__init__.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/analyzers/layout/base.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/analyzers/layout/docling.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/analyzers/layout/gemini.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/analyzers/layout/layout_analyzer.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/analyzers/layout/layout_manager.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/analyzers/layout/layout_options.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/analyzers/layout/paddle.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/analyzers/layout/pdfplumber_table_finder.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/analyzers/layout/surya.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/analyzers/layout/table_structure_utils.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/analyzers/layout/tatr.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/analyzers/layout/yolo.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/analyzers/shape_detection_mixin.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/analyzers/text_options.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/analyzers/text_structure.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/analyzers/utils.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/classification/mixin.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/classification/results.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/collections/mixins.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/collections/pdf_collection.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/core/__init__.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/core/element_manager.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/core/highlighting_service.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/core/page.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/describe/__init__.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/describe/base.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/describe/elements.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/describe/mixin.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/describe/summary.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/elements/__init__.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/elements/base.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/elements/collections.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/elements/line.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/elements/rect.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/elements/region.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/elements/text.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/export/mixin.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/exporters/base.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/exporters/data/__init__.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/exporters/data/pdf.ttf +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/exporters/data/sRGB.icc +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/exporters/hocr_font.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/exporters/paddleocr.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/exporters/searchable_pdf.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/extraction/manager.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/extraction/mixin.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/extraction/result.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/flows/__init__.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/flows/collections.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/flows/element.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/flows/flow.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/flows/region.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/ocr/__init__.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/ocr/engine.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/ocr/engine_doctr.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/ocr/engine_easyocr.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/ocr/engine_paddle.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/ocr/ocr_factory.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/ocr/ocr_options.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/ocr/utils.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/qa/__init__.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/qa/document_qa.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/search/search_options.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/search/search_service_protocol.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/search/searchable_mixin.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/selectors/__init__.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/selectors/parser.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/templates/__init__.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/templates/finetune/fine_tune_paddleocr.md +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/templates/spa/css/style.css +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/templates/spa/index.html +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/templates/spa/js/app.js +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/templates/spa/words.txt +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/utils/__init__.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/utils/debug.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/utils/highlighting.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/utils/identifiers.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/utils/locks.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/utils/packaging.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/utils/reading_order.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/utils/text_extraction.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/utils/visualization.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/widgets/__init__.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/widgets/viewer.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf.egg-info/dependency_links.txt +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf.egg-info/top_level.txt +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/.gitkeep +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/01-practice.pdf +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/0500000US42001.pdf +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/0500000US42007.pdf +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/2014 Statistics.pdf +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/2019 Statistics.pdf +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/30.pdf +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/Atlanta_Public_Schools_GA_sample.pdf +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/anexo_edital_6604_1743480-table.pdf +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/cia-doc.pdf +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/geometry.pdf +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/image.png +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/image.png.pdf +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/multicolumn.pdf +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/needs-ocr.pdf +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/red.pdf +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/tiny-ocr-2.pdf +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/tiny-ocr-3.pdf +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/tiny-ocr-small.jpg +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/tiny-ocr-wide.jpg +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/tiny-ocr.pdf +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/tiny.pdf +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/word-counter.pdf +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/publish.sh +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/sample-screen.png +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/setup.cfg +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/tests/conftest.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/tests/exporters/test_paddleocr_exporter.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/tests/test_core/test_containment_geometry.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/tests/test_core/test_elements.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/tests/test_core/test_loading.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/tests/test_core/test_spatial.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/tests/test_core/test_text_extraction.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/tests/test_loading_original.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/tests/test_optional_deps.py +0 -0
- {natural_pdf-0.1.17 → natural_pdf-0.1.19}/uv.lock +0 -0
@@ -23,6 +23,7 @@ DOCS_DIR = Path("docs")
|
|
23
23
|
CACHE_FILE = Path(".notebook_cache.json")
|
24
24
|
# Add relative paths or glob patterns from DOCS_DIR, e.g., 'api/', '**/_*.md'
|
25
25
|
EXCLUDE_PATTERNS = [
|
26
|
+
"describe/index.md",
|
26
27
|
"installation/index.md",
|
27
28
|
"ocr/index.md",
|
28
29
|
"explanations",
|
@@ -1,6 +1,6 @@
|
|
1
1
|
Metadata-Version: 2.4
|
2
2
|
Name: natural-pdf
|
3
|
-
Version: 0.1.
|
3
|
+
Version: 0.1.19
|
4
4
|
Summary: A more intuitive interface for working with PDFs
|
5
5
|
Author-email: Jonathan Soma <jonathan.soma@gmail.com>
|
6
6
|
License-Expression: MIT
|
@@ -11,6 +11,7 @@ Classifier: Operating System :: OS Independent
|
|
11
11
|
Requires-Python: >=3.9
|
12
12
|
Description-Content-Type: text/markdown
|
13
13
|
License-File: LICENSE
|
14
|
+
Requires-Dist: pandas
|
14
15
|
Requires-Dist: pdfplumber
|
15
16
|
Requires-Dist: colormath2
|
16
17
|
Requires-Dist: pillow
|
@@ -20,14 +21,15 @@ Requires-Dist: urllib3
|
|
20
21
|
Requires-Dist: tqdm
|
21
22
|
Requires-Dist: pydantic
|
22
23
|
Requires-Dist: jenkspy
|
23
|
-
Requires-Dist: pikepdf
|
24
|
+
Requires-Dist: pikepdf
|
24
25
|
Requires-Dist: scipy
|
25
26
|
Requires-Dist: torch
|
26
27
|
Requires-Dist: torchvision
|
27
|
-
Requires-Dist: transformers[sentencepiece]
|
28
|
+
Requires-Dist: transformers[sentencepiece]
|
28
29
|
Requires-Dist: huggingface_hub>=0.29.3
|
29
30
|
Requires-Dist: sentence-transformers
|
30
31
|
Requires-Dist: timm
|
32
|
+
Requires-Dist: ipywidgets>=7.0.0
|
31
33
|
Provides-Extra: test
|
32
34
|
Requires-Dist: pytest; extra == "test"
|
33
35
|
Requires-Dist: pytest-xdist; extra == "test"
|
@@ -38,9 +40,7 @@ Requires-Dist: pyarrow; extra == "search"
|
|
38
40
|
Provides-Extra: favorites
|
39
41
|
Requires-Dist: natural-pdf[deskew]; extra == "favorites"
|
40
42
|
Requires-Dist: natural-pdf[ocr-export]; extra == "favorites"
|
41
|
-
Requires-Dist: natural-pdf[
|
42
|
-
Requires-Dist: ipywidgets; extra == "favorites"
|
43
|
-
Requires-Dist: surya-ocr; extra == "favorites"
|
43
|
+
Requires-Dist: natural-pdf[paddle]; extra == "favorites"
|
44
44
|
Provides-Extra: dev
|
45
45
|
Requires-Dist: black; extra == "dev"
|
46
46
|
Requires-Dist: isort; extra == "dev"
|
@@ -61,23 +61,22 @@ Requires-Dist: setuptools; extra == "dev"
|
|
61
61
|
Provides-Extra: deskew
|
62
62
|
Requires-Dist: deskew>=1.5; extra == "deskew"
|
63
63
|
Requires-Dist: img2pdf; extra == "deskew"
|
64
|
-
Provides-Extra: addons
|
65
|
-
Requires-Dist: surya-ocr; extra == "addons"
|
66
|
-
Requires-Dist: doclayout_yolo; extra == "addons"
|
67
|
-
Requires-Dist: paddlepaddle>=3.0.0; extra == "addons"
|
68
|
-
Requires-Dist: paddleocr>=3.0.0; extra == "addons"
|
69
|
-
Requires-Dist: ipywidgets>=7.0.0; extra == "addons"
|
70
|
-
Requires-Dist: easyocr; extra == "addons"
|
71
|
-
Requires-Dist: surya-ocr; extra == "addons"
|
72
|
-
Requires-Dist: doclayout_yolo; extra == "addons"
|
73
|
-
Requires-Dist: python-doctr[torch]; extra == "addons"
|
74
|
-
Requires-Dist: docling; extra == "addons"
|
75
64
|
Provides-Extra: all
|
76
65
|
Requires-Dist: natural-pdf[ocr-export]; extra == "all"
|
77
66
|
Requires-Dist: natural-pdf[deskew]; extra == "all"
|
78
67
|
Requires-Dist: natural-pdf[test]; extra == "all"
|
79
68
|
Requires-Dist: natural-pdf[search]; extra == "all"
|
80
|
-
Requires-Dist: natural-pdf[
|
69
|
+
Requires-Dist: natural-pdf[extras]; extra == "all"
|
70
|
+
Requires-Dist: natural-pdf[favorites]; extra == "all"
|
71
|
+
Provides-Extra: paddle
|
72
|
+
Requires-Dist: paddlepaddle>=3.0.0; extra == "paddle"
|
73
|
+
Requires-Dist: paddleocr>=3.0.1; extra == "paddle"
|
74
|
+
Requires-Dist: paddlex>=3.0.1; extra == "paddle"
|
75
|
+
Provides-Extra: extras
|
76
|
+
Requires-Dist: surya-ocr>=0.13.0; extra == "extras"
|
77
|
+
Requires-Dist: doclayout_yolo; extra == "extras"
|
78
|
+
Requires-Dist: easyocr; extra == "extras"
|
79
|
+
Requires-Dist: natural-pdf[paddle]; extra == "extras"
|
81
80
|
Provides-Extra: ocr-export
|
82
81
|
Requires-Dist: pikepdf; extra == "ocr-export"
|
83
82
|
Provides-Extra: export-extras
|