natural-pdf 0.1.3__tar.gz → 0.1.5__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.
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/.gitignore +4 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/PKG-INFO +29 -15
- natural_pdf-0.1.5/docs/tutorials/01-loading-and-extraction.ipynb +1696 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/tutorials/02-finding-elements.ipynb +42 -42
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/tutorials/03-extracting-blocks.ipynb +18 -18
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/tutorials/04-table-extraction.ipynb +12 -12
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/tutorials/05-excluding-content.ipynb +33 -37
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/tutorials/06-document-qa.ipynb +44 -44
- natural_pdf-0.1.5/docs/tutorials/07-layout-analysis.ipynb +260 -0
- natural_pdf-0.1.5/docs/tutorials/07-working-with-regions.ipynb +409 -0
- natural_pdf-0.1.5/docs/tutorials/08-spatial-navigation.ipynb +508 -0
- natural_pdf-0.1.5/docs/tutorials/09-section-extraction.ipynb +2434 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/tutorials/10-form-field-extraction.ipynb +63 -63
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/tutorials/11-enhanced-table-processing.ipynb +6 -6
- natural_pdf-0.1.5/docs/tutorials/12-ocr-integration.ipynb +586 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/tutorials/12-ocr-integration.md +3 -16
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/tutorials/13-semantic-search.ipynb +377 -397
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/execute_notebooks.py +120 -69
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/__init__.py +39 -20
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/analyzers/__init__.py +2 -1
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/analyzers/layout/base.py +32 -24
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/analyzers/layout/docling.py +131 -72
- natural_pdf-0.1.5/natural_pdf/analyzers/layout/layout_analyzer.py +298 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/analyzers/layout/layout_manager.py +98 -58
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/analyzers/layout/layout_options.py +32 -17
- natural_pdf-0.1.5/natural_pdf/analyzers/layout/paddle.py +297 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/analyzers/layout/surya.py +164 -92
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/analyzers/layout/tatr.py +149 -84
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/analyzers/layout/yolo.py +84 -44
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/analyzers/text_options.py +22 -15
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/analyzers/text_structure.py +131 -85
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/analyzers/utils.py +30 -23
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/collections/pdf_collection.py +126 -98
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/core/__init__.py +1 -1
- natural_pdf-0.1.5/natural_pdf/core/element_manager.py +536 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/core/highlighting_service.py +268 -196
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/core/page.py +910 -516
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/core/pdf.py +387 -289
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/elements/__init__.py +1 -1
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/elements/base.py +302 -214
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/elements/collections.py +714 -514
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/elements/line.py +39 -36
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/elements/rect.py +32 -30
- natural_pdf-0.1.5/natural_pdf/elements/region.py +1691 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/elements/text.py +122 -99
- natural_pdf-0.1.5/natural_pdf/exporters/searchable_pdf.py +411 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/ocr/__init__.py +23 -14
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/ocr/engine.py +17 -8
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/ocr/engine_easyocr.py +63 -47
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/ocr/engine_paddle.py +97 -68
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/ocr/engine_surya.py +54 -44
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/ocr/ocr_manager.py +88 -62
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/ocr/ocr_options.py +16 -10
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/qa/__init__.py +1 -1
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/qa/document_qa.py +119 -111
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/search/__init__.py +37 -31
- natural_pdf-0.1.5/natural_pdf/search/haystack_search_service.py +643 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/search/haystack_utils.py +186 -122
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/search/search_options.py +25 -14
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/search/search_service_protocol.py +12 -6
- natural_pdf-0.1.5/natural_pdf/search/searchable_mixin.py +549 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/selectors/__init__.py +2 -1
- natural_pdf-0.1.5/natural_pdf/selectors/parser.py +411 -0
- natural_pdf-0.1.5/natural_pdf/templates/__init__.py +1 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/utils/highlighting.py +8 -2
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/utils/reading_order.py +65 -63
- natural_pdf-0.1.5/natural_pdf/utils/text_extraction.py +195 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/utils/visualization.py +70 -61
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/widgets/__init__.py +2 -3
- natural_pdf-0.1.5/natural_pdf/widgets/viewer.py +796 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf.egg-info/PKG-INFO +29 -15
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf.egg-info/SOURCES.txt +5 -102
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf.egg-info/requires.txt +29 -13
- natural_pdf-0.1.5/natural_pdf.egg-info/top_level.txt +9 -0
- natural_pdf-0.1.5/noxfile.py +78 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/pyproject.toml +41 -18
- natural_pdf-0.1.5/tests/test_loading.py +50 -0
- natural_pdf-0.1.5/tests/test_optional_deps.py +298 -0
- natural_pdf-0.1.3/docs/tutorials/01-loading-and-extraction.ipynb +0 -1658
- natural_pdf-0.1.3/docs/tutorials/07-layout-analysis.ipynb +0 -260
- natural_pdf-0.1.3/docs/tutorials/07-working-with-regions.ipynb +0 -409
- natural_pdf-0.1.3/docs/tutorials/08-spatial-navigation.ipynb +0 -508
- natural_pdf-0.1.3/docs/tutorials/09-section-extraction.ipynb +0 -2428
- natural_pdf-0.1.3/docs/tutorials/12-ocr-integration.ipynb +0 -635
- natural_pdf-0.1.3/natural_pdf/analyzers/layout/layout_analyzer.py +0 -255
- natural_pdf-0.1.3/natural_pdf/analyzers/layout/paddle.py +0 -240
- natural_pdf-0.1.3/natural_pdf/core/element_manager.py +0 -457
- natural_pdf-0.1.3/natural_pdf/elements/region.py +0 -1720
- natural_pdf-0.1.3/natural_pdf/exporters/__init__.py +0 -1
- natural_pdf-0.1.3/natural_pdf/exporters/searchable_pdf.py +0 -252
- natural_pdf-0.1.3/natural_pdf/search/haystack_search_service.py +0 -520
- natural_pdf-0.1.3/natural_pdf/search/searchable_mixin.py +0 -464
- natural_pdf-0.1.3/natural_pdf/selectors/parser.py +0 -568
- natural_pdf-0.1.3/natural_pdf/templates/__init__.py +0 -1
- natural_pdf-0.1.3/natural_pdf/widgets/viewer.py +0 -765
- natural_pdf-0.1.3/natural_pdf.egg-info/top_level.txt +0 -1
- natural_pdf-0.1.3/output/all_detected_regions.png +0 -0
- natural_pdf-0.1.3/output/all_elements.png +0 -0
- natural_pdf-0.1.3/output/basic_highlighting.png +0 -0
- natural_pdf-0.1.3/output/chainable_layout.png +0 -0
- natural_pdf-0.1.3/output/chained_analysis.png +0 -0
- natural_pdf-0.1.3/output/color_names.png +0 -0
- natural_pdf-0.1.3/output/color_names_with_boxes.png +0 -0
- natural_pdf-0.1.3/output/conf_display_highlight_all.png +0 -0
- natural_pdf-0.1.3/output/conf_display_highlight_layout.png +0 -0
- natural_pdf-0.1.3/output/conf_display_layout_only.png +0 -0
- natural_pdf-0.1.3/output/confidence_color_coded.png +0 -0
- natural_pdf-0.1.3/output/debug_page_image.png +0 -0
- natural_pdf-0.1.3/output/detected_table.png +0 -0
- natural_pdf-0.1.3/output/dimension_analysis.txt +0 -48
- natural_pdf-0.1.3/output/direct_ocr_debug.png +0 -0
- natural_pdf-0.1.3/output/easyocr_debug_input.png +0 -0
- natural_pdf-0.1.3/output/easyocr_results.png +0 -0
- natural_pdf-0.1.3/output/easyocr_test_input.png +0 -0
- natural_pdf-0.1.3/output/exclusion_optimization_regions.png +0 -0
- natural_pdf-0.1.3/output/explicit_confidence_display.png +0 -0
- natural_pdf-0.1.3/output/footer_overlap_test.png +0 -0
- natural_pdf-0.1.3/output/highlight_all.png +0 -0
- natural_pdf-0.1.3/output/highlight_all_styles.png +0 -0
- natural_pdf-0.1.3/output/highlight_all_with_all_layouts.png +0 -0
- natural_pdf-0.1.3/output/highlight_all_with_attrs.png +0 -0
- natural_pdf-0.1.3/output/highlight_all_with_yolo.png +0 -0
- natural_pdf-0.1.3/output/highlight_by_confidence.png +0 -0
- natural_pdf-0.1.3/output/highlight_color_test_1.png +0 -0
- natural_pdf-0.1.3/output/highlight_color_test_2.png +0 -0
- natural_pdf-0.1.3/output/highlight_color_test_3.png +0 -0
- natural_pdf-0.1.3/output/highlight_color_test_4.png +0 -0
- natural_pdf-0.1.3/output/highlight_layout_method.png +0 -0
- natural_pdf-0.1.3/output/highlight_multiple.png +0 -0
- natural_pdf-0.1.3/output/highlight_no_attrs.png +0 -0
- natural_pdf-0.1.3/output/highlight_region.png +0 -0
- natural_pdf-0.1.3/output/highlight_single.png +0 -0
- natural_pdf-0.1.3/output/highlight_specific_types.png +0 -0
- natural_pdf-0.1.3/output/highlight_specific_types_with_boxes.png +0 -0
- natural_pdf-0.1.3/output/highlight_specific_types_with_tables.png +0 -0
- natural_pdf-0.1.3/output/highlight_test.png +0 -0
- natural_pdf-0.1.3/output/highlight_test_colors.png +0 -0
- natural_pdf-0.1.3/output/highlight_test_individual.png +0 -0
- natural_pdf-0.1.3/output/highlight_test_individual_annotated.png +0 -0
- natural_pdf-0.1.3/output/highlight_test_individual_with_structure.png +0 -0
- natural_pdf-0.1.3/output/highlight_test_individual_with_structure_yolo.png +0 -0
- natural_pdf-0.1.3/output/highlight_test_individual_with_tables.png +0 -0
- natural_pdf-0.1.3/output/highlight_with_attrs.png +0 -0
- natural_pdf-0.1.3/output/layout_conf_default.png +0 -0
- natural_pdf-0.1.3/output/layout_detection.png +0 -0
- natural_pdf-0.1.3/output/layout_fix_test.png +0 -0
- natural_pdf-0.1.3/output/layout_fix_test2.png +0 -0
- natural_pdf-0.1.3/output/layout_fix_test3.png +0 -0
- natural_pdf-0.1.3/output/layout_fix_test4.png +0 -0
- natural_pdf-0.1.3/output/model_comparison.png +0 -0
- natural_pdf-0.1.3/output/multiple_attributes_display.png +0 -0
- natural_pdf-0.1.3/output/ocr_confidence_visualization.png +0 -0
- natural_pdf-0.1.3/output/ocr_debug.png +0 -0
- natural_pdf-0.1.3/output/ocr_debug_page.html +0 -517
- natural_pdf-0.1.3/output/ocr_highlight_all_test.png +0 -0
- natural_pdf-0.1.3/output/ocr_highlight_test.png +0 -0
- natural_pdf-0.1.3/output/ocr_highlighted.png +0 -0
- natural_pdf-0.1.3/output/ocr_simplified.png +0 -0
- natural_pdf-0.1.3/output/ocr_threshold_comparison.png +0 -0
- natural_pdf-0.1.3/output/ocr_visualization_clean.png +0 -0
- natural_pdf-0.1.3/output/ocr_visualization_highlights.png +0 -0
- natural_pdf-0.1.3/output/ocr_visualization_text.png +0 -0
- natural_pdf-0.1.3/output/paddle_layout_detection.png +0 -0
- natural_pdf-0.1.3/output/paddle_layout_polygons.png +0 -0
- natural_pdf-0.1.3/output/paddle_layout_sources.png +0 -0
- natural_pdf-0.1.3/output/paddle_layout_with_text.png +0 -0
- natural_pdf-0.1.3/output/paddle_layout_without_text.png +0 -0
- natural_pdf-0.1.3/output/paddleocr_highlights.png +0 -0
- natural_pdf-0.1.3/output/paddleocr_results.png +0 -0
- natural_pdf-0.1.3/output/paddleocr_test_input.png +0 -0
- natural_pdf-0.1.3/output/page_1_for_ocr.png +0 -0
- natural_pdf-0.1.3/output/page_4_for_ocr.png +0 -0
- natural_pdf-0.1.3/output/region_exclusion_test.png +0 -0
- natural_pdf-0.1.3/output/region_management_test.png +0 -0
- natural_pdf-0.1.3/output/region_ocr_cropped.png +0 -0
- natural_pdf-0.1.3/output/region_ocr_debug.png +0 -0
- natural_pdf-0.1.3/output/region_ocr_full_page.png +0 -0
- natural_pdf-0.1.3/output/region_ocr_highlighted.png +0 -0
- natural_pdf-0.1.3/output/spatial_navigation.png +0 -0
- natural_pdf-0.1.3/output/standard_highlight_all.png +0 -0
- natural_pdf-0.1.3/output/table_no_ocr.csv +0 -54
- natural_pdf-0.1.3/output/table_structure.png +0 -0
- natural_pdf-0.1.3/output/table_structure_detail.png +0 -0
- natural_pdf-0.1.3/output/table_with_ocr.csv +0 -54
- natural_pdf-0.1.3/output/tatr_cells_test.png +0 -0
- natural_pdf-0.1.3/output/tatr_ocr_table_test.png +0 -0
- natural_pdf-0.1.3/output/tatr_regions.png +0 -0
- natural_pdf-0.1.3/output/tatr_regions.txt +0 -16
- natural_pdf-0.1.3/output/text_styles.png +0 -0
- natural_pdf-0.1.3/output/titles_only.png +0 -0
- natural_pdf-0.1.3/output/width_1200px.png +0 -0
- natural_pdf-0.1.3/output/width_800px.png +0 -0
- natural_pdf-0.1.3/output/width_default.png +0 -0
- natural_pdf-0.1.3/output/width_with_scale.png +0 -0
- natural_pdf-0.1.3/output/yolo_regions.png +0 -0
- natural_pdf-0.1.3/output/yolo_regions.txt +0 -9
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/.github/workflows/docs.yml +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/CLAUDE.md +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/LICENSE +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/MANIFEST.in +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/README.md +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/check_run_md.sh +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/api/index.md +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/assets/favicon.png +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/assets/favicon.svg +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/assets/javascripts/custom.js +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/assets/logo.svg +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/assets/sample-screen.png +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/assets/social-preview.png +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/assets/social-preview.svg +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/assets/stylesheets/custom.css +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/document-qa/index.ipynb +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/document-qa/index.md +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/element-selection/index.ipynb +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/element-selection/index.md +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/index.md +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/installation/index.md +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/interactive-widget/index.ipynb +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/interactive-widget/index.md +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/layout-analysis/index.ipynb +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/layout-analysis/index.md +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/ocr/index.md +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/pdf-navigation/index.ipynb +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/pdf-navigation/index.md +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/regions/index.ipynb +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/regions/index.md +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/tables/index.ipynb +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/tables/index.md +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/text-analysis/index.ipynb +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/text-analysis/index.md +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/text-extraction/index.ipynb +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/text-extraction/index.md +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/tutorials/01-loading-and-extraction.md +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/tutorials/02-finding-elements.md +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/tutorials/03-extracting-blocks.md +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/tutorials/04-table-extraction.md +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/tutorials/05-excluding-content.md +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/tutorials/06-document-qa.md +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/tutorials/07-layout-analysis.md +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/tutorials/07-working-with-regions.md +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/tutorials/08-spatial-navigation.md +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/tutorials/09-section-extraction.md +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/tutorials/10-form-field-extraction.md +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/tutorials/11-enhanced-table-processing.md +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/tutorials/13-semantic-search.md +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/visual-debugging/index.ipynb +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/visual-debugging/index.md +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/docs/visual-debugging/region.png +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/mkdocs.yml +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/analyzers/layout/__init__.py +0 -0
- /natural_pdf-0.1.3/output/layout_conf_high.png → /natural_pdf-0.1.5/natural_pdf/exporters/__init__.py +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/templates/ocr_debug.html +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/utils/__init__.py +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf/widgets/frontend/viewer.js +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/natural_pdf.egg-info/dependency_links.txt +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/notebooks/Examples.ipynb +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/pdfs/.gitkeep +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/pdfs/01-practice.pdf +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/pdfs/0500000US42001.pdf +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/pdfs/0500000US42007.pdf +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/pdfs/2014 Statistics.pdf +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/pdfs/2019 Statistics.pdf +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/pdfs/Atlanta_Public_Schools_GA_sample.pdf +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/pdfs/needs-ocr.pdf +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/publish.sh +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/run_all_tutorials.sh +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/sample-screen.png +0 -0
- {natural_pdf-0.1.3 → natural_pdf-0.1.5}/setup.cfg +0 -0
@@ -1,4 +1,6 @@
|
|
1
1
|
.notebook_cache.json
|
2
|
+
.venv
|
3
|
+
output
|
2
4
|
Untitled.ipynb
|
3
5
|
conversation.md
|
4
6
|
docs/tutorials/pdfs
|
@@ -10,6 +12,8 @@ results
|
|
10
12
|
docs/tutorials/needs-ocr-searchable.pdf
|
11
13
|
sample.py
|
12
14
|
sample2.py
|
15
|
+
pdfs/hidden
|
16
|
+
*.hocr
|
13
17
|
|
14
18
|
# Created by https://www.toptal.com/developers/gitignore/api/python,macos,visualstudiocode,jupyternotebooks
|
15
19
|
# Edit at https://www.toptal.com/developers/gitignore?templates=python,macos,visualstudiocode,jupyternotebooks
|
@@ -1,6 +1,6 @@
|
|
1
1
|
Metadata-Version: 2.4
|
2
2
|
Name: natural-pdf
|
3
|
-
Version: 0.1.
|
3
|
+
Version: 0.1.5
|
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
|
@@ -8,26 +8,27 @@ Project-URL: Homepage, https://github.com/jsoma/natural-pdf
|
|
8
8
|
Project-URL: Repository, https://github.com/jsoma/natural-pdf
|
9
9
|
Classifier: Programming Language :: Python :: 3
|
10
10
|
Classifier: Operating System :: OS Independent
|
11
|
-
Requires-Python: >=3.
|
11
|
+
Requires-Python: >=3.9
|
12
12
|
Description-Content-Type: text/markdown
|
13
13
|
License-File: LICENSE
|
14
|
-
Requires-Dist: pdfplumber
|
15
|
-
Requires-Dist: Pillow
|
16
|
-
Requires-Dist: colour
|
17
|
-
Requires-Dist: numpy
|
18
|
-
Requires-Dist: urllib3
|
19
|
-
Requires-Dist: torch
|
20
|
-
Requires-Dist: torchvision
|
21
|
-
Requires-Dist: transformers
|
22
|
-
Requires-Dist: huggingface_hub
|
23
|
-
Requires-Dist: ocrmypdf
|
24
|
-
Requires-Dist: pikepdf
|
14
|
+
Requires-Dist: pdfplumber
|
15
|
+
Requires-Dist: Pillow
|
16
|
+
Requires-Dist: colour
|
17
|
+
Requires-Dist: numpy
|
18
|
+
Requires-Dist: urllib3
|
19
|
+
Requires-Dist: torch
|
20
|
+
Requires-Dist: torchvision
|
21
|
+
Requires-Dist: transformers
|
22
|
+
Requires-Dist: huggingface_hub
|
23
|
+
Requires-Dist: ocrmypdf
|
24
|
+
Requires-Dist: pikepdf
|
25
25
|
Provides-Extra: interactive
|
26
26
|
Requires-Dist: ipywidgets<9.0.0,>=7.0.0; extra == "interactive"
|
27
27
|
Provides-Extra: haystack
|
28
|
-
Requires-Dist: haystack-ai
|
28
|
+
Requires-Dist: haystack-ai; extra == "haystack"
|
29
29
|
Requires-Dist: chroma-haystack; extra == "haystack"
|
30
30
|
Requires-Dist: sentence-transformers; extra == "haystack"
|
31
|
+
Requires-Dist: protobuf<4; extra == "haystack"
|
31
32
|
Provides-Extra: easyocr
|
32
33
|
Requires-Dist: easyocr; extra == "easyocr"
|
33
34
|
Provides-Extra: paddle
|
@@ -38,6 +39,17 @@ Requires-Dist: doclayout_yolo; extra == "layout-yolo"
|
|
38
39
|
Provides-Extra: surya
|
39
40
|
Requires-Dist: surya-ocr; extra == "surya"
|
40
41
|
Provides-Extra: qa
|
42
|
+
Provides-Extra: test
|
43
|
+
Requires-Dist: pytest; extra == "test"
|
44
|
+
Provides-Extra: dev
|
45
|
+
Requires-Dist: black; extra == "dev"
|
46
|
+
Requires-Dist: isort; extra == "dev"
|
47
|
+
Requires-Dist: mypy; extra == "dev"
|
48
|
+
Requires-Dist: pytest; extra == "dev"
|
49
|
+
Requires-Dist: nox; extra == "dev"
|
50
|
+
Requires-Dist: nox-uv; extra == "dev"
|
51
|
+
Requires-Dist: build; extra == "dev"
|
52
|
+
Requires-Dist: uv; extra == "dev"
|
41
53
|
Provides-Extra: all
|
42
54
|
Requires-Dist: ipywidgets<9.0.0,>=7.0.0; extra == "all"
|
43
55
|
Requires-Dist: easyocr; extra == "all"
|
@@ -45,9 +57,11 @@ Requires-Dist: paddlepaddle; extra == "all"
|
|
45
57
|
Requires-Dist: paddleocr; extra == "all"
|
46
58
|
Requires-Dist: doclayout_yolo; extra == "all"
|
47
59
|
Requires-Dist: surya-ocr; extra == "all"
|
48
|
-
Requires-Dist: haystack-ai
|
60
|
+
Requires-Dist: haystack-ai; extra == "all"
|
49
61
|
Requires-Dist: chroma-haystack; extra == "all"
|
50
62
|
Requires-Dist: sentence-transformers; extra == "all"
|
63
|
+
Requires-Dist: protobuf<4; extra == "all"
|
64
|
+
Requires-Dist: pytest; extra == "all"
|
51
65
|
Dynamic: license-file
|
52
66
|
|
53
67
|
# Natural PDF
|