natural-pdf 0.1.4__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.
Files changed (268) hide show
  1. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/.gitignore +4 -0
  2. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/PKG-INFO +15 -1
  3. natural_pdf-0.1.5/docs/tutorials/01-loading-and-extraction.ipynb +1696 -0
  4. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/tutorials/02-finding-elements.ipynb +42 -42
  5. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/tutorials/03-extracting-blocks.ipynb +18 -18
  6. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/tutorials/04-table-extraction.ipynb +12 -12
  7. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/tutorials/05-excluding-content.ipynb +32 -32
  8. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/tutorials/06-document-qa.ipynb +44 -44
  9. natural_pdf-0.1.5/docs/tutorials/07-layout-analysis.ipynb +260 -0
  10. natural_pdf-0.1.5/docs/tutorials/07-working-with-regions.ipynb +409 -0
  11. natural_pdf-0.1.5/docs/tutorials/08-spatial-navigation.ipynb +508 -0
  12. natural_pdf-0.1.5/docs/tutorials/09-section-extraction.ipynb +2434 -0
  13. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/tutorials/10-form-field-extraction.ipynb +63 -63
  14. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/tutorials/11-enhanced-table-processing.ipynb +6 -6
  15. natural_pdf-0.1.5/docs/tutorials/12-ocr-integration.ipynb +586 -0
  16. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/tutorials/13-semantic-search.ipynb +360 -376
  17. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/execute_notebooks.py +120 -69
  18. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/__init__.py +39 -20
  19. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/analyzers/__init__.py +2 -1
  20. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/analyzers/layout/base.py +32 -24
  21. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/analyzers/layout/docling.py +131 -72
  22. natural_pdf-0.1.5/natural_pdf/analyzers/layout/layout_analyzer.py +298 -0
  23. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/analyzers/layout/layout_manager.py +98 -58
  24. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/analyzers/layout/layout_options.py +32 -17
  25. natural_pdf-0.1.5/natural_pdf/analyzers/layout/paddle.py +297 -0
  26. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/analyzers/layout/surya.py +164 -92
  27. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/analyzers/layout/tatr.py +149 -84
  28. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/analyzers/layout/yolo.py +84 -44
  29. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/analyzers/text_options.py +22 -15
  30. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/analyzers/text_structure.py +131 -85
  31. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/analyzers/utils.py +30 -23
  32. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/collections/pdf_collection.py +125 -97
  33. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/core/__init__.py +1 -1
  34. natural_pdf-0.1.5/natural_pdf/core/element_manager.py +536 -0
  35. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/core/highlighting_service.py +268 -196
  36. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/core/page.py +907 -513
  37. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/core/pdf.py +385 -287
  38. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/elements/__init__.py +1 -1
  39. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/elements/base.py +302 -214
  40. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/elements/collections.py +708 -508
  41. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/elements/line.py +39 -36
  42. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/elements/rect.py +32 -30
  43. natural_pdf-0.1.5/natural_pdf/elements/region.py +1691 -0
  44. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/elements/text.py +122 -99
  45. natural_pdf-0.1.5/natural_pdf/exporters/searchable_pdf.py +411 -0
  46. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/ocr/__init__.py +23 -14
  47. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/ocr/engine.py +17 -8
  48. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/ocr/engine_easyocr.py +63 -47
  49. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/ocr/engine_paddle.py +97 -68
  50. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/ocr/engine_surya.py +54 -44
  51. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/ocr/ocr_manager.py +88 -62
  52. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/ocr/ocr_options.py +16 -10
  53. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/qa/__init__.py +1 -1
  54. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/qa/document_qa.py +119 -111
  55. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/search/__init__.py +37 -31
  56. natural_pdf-0.1.5/natural_pdf/search/haystack_search_service.py +643 -0
  57. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/search/haystack_utils.py +186 -122
  58. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/search/search_options.py +25 -14
  59. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/search/search_service_protocol.py +12 -6
  60. natural_pdf-0.1.5/natural_pdf/search/searchable_mixin.py +549 -0
  61. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/selectors/__init__.py +2 -1
  62. natural_pdf-0.1.5/natural_pdf/selectors/parser.py +411 -0
  63. natural_pdf-0.1.5/natural_pdf/templates/__init__.py +1 -0
  64. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/utils/highlighting.py +8 -2
  65. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/utils/reading_order.py +65 -63
  66. natural_pdf-0.1.5/natural_pdf/utils/text_extraction.py +195 -0
  67. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/utils/visualization.py +70 -61
  68. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/widgets/__init__.py +2 -3
  69. natural_pdf-0.1.5/natural_pdf/widgets/viewer.py +796 -0
  70. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf.egg-info/PKG-INFO +15 -1
  71. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf.egg-info/SOURCES.txt +5 -102
  72. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf.egg-info/requires.txt +16 -0
  73. natural_pdf-0.1.5/natural_pdf.egg-info/top_level.txt +9 -0
  74. natural_pdf-0.1.5/noxfile.py +78 -0
  75. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/pyproject.toml +26 -2
  76. natural_pdf-0.1.5/tests/test_loading.py +50 -0
  77. natural_pdf-0.1.5/tests/test_optional_deps.py +298 -0
  78. natural_pdf-0.1.4/docs/tutorials/01-loading-and-extraction.ipynb +0 -1700
  79. natural_pdf-0.1.4/docs/tutorials/07-layout-analysis.ipynb +0 -260
  80. natural_pdf-0.1.4/docs/tutorials/07-working-with-regions.ipynb +0 -409
  81. natural_pdf-0.1.4/docs/tutorials/08-spatial-navigation.ipynb +0 -508
  82. natural_pdf-0.1.4/docs/tutorials/09-section-extraction.ipynb +0 -2428
  83. natural_pdf-0.1.4/docs/tutorials/12-ocr-integration.ipynb +0 -601
  84. natural_pdf-0.1.4/natural_pdf/analyzers/layout/layout_analyzer.py +0 -255
  85. natural_pdf-0.1.4/natural_pdf/analyzers/layout/paddle.py +0 -240
  86. natural_pdf-0.1.4/natural_pdf/core/element_manager.py +0 -457
  87. natural_pdf-0.1.4/natural_pdf/elements/region.py +0 -1720
  88. natural_pdf-0.1.4/natural_pdf/exporters/__init__.py +0 -1
  89. natural_pdf-0.1.4/natural_pdf/exporters/searchable_pdf.py +0 -252
  90. natural_pdf-0.1.4/natural_pdf/search/haystack_search_service.py +0 -520
  91. natural_pdf-0.1.4/natural_pdf/search/searchable_mixin.py +0 -464
  92. natural_pdf-0.1.4/natural_pdf/selectors/parser.py +0 -568
  93. natural_pdf-0.1.4/natural_pdf/templates/__init__.py +0 -1
  94. natural_pdf-0.1.4/natural_pdf/widgets/viewer.py +0 -765
  95. natural_pdf-0.1.4/natural_pdf.egg-info/top_level.txt +0 -1
  96. natural_pdf-0.1.4/output/all_detected_regions.png +0 -0
  97. natural_pdf-0.1.4/output/all_elements.png +0 -0
  98. natural_pdf-0.1.4/output/basic_highlighting.png +0 -0
  99. natural_pdf-0.1.4/output/chainable_layout.png +0 -0
  100. natural_pdf-0.1.4/output/chained_analysis.png +0 -0
  101. natural_pdf-0.1.4/output/color_names.png +0 -0
  102. natural_pdf-0.1.4/output/color_names_with_boxes.png +0 -0
  103. natural_pdf-0.1.4/output/conf_display_highlight_all.png +0 -0
  104. natural_pdf-0.1.4/output/conf_display_highlight_layout.png +0 -0
  105. natural_pdf-0.1.4/output/conf_display_layout_only.png +0 -0
  106. natural_pdf-0.1.4/output/confidence_color_coded.png +0 -0
  107. natural_pdf-0.1.4/output/debug_page_image.png +0 -0
  108. natural_pdf-0.1.4/output/detected_table.png +0 -0
  109. natural_pdf-0.1.4/output/dimension_analysis.txt +0 -48
  110. natural_pdf-0.1.4/output/direct_ocr_debug.png +0 -0
  111. natural_pdf-0.1.4/output/easyocr_debug_input.png +0 -0
  112. natural_pdf-0.1.4/output/easyocr_results.png +0 -0
  113. natural_pdf-0.1.4/output/easyocr_test_input.png +0 -0
  114. natural_pdf-0.1.4/output/exclusion_optimization_regions.png +0 -0
  115. natural_pdf-0.1.4/output/explicit_confidence_display.png +0 -0
  116. natural_pdf-0.1.4/output/footer_overlap_test.png +0 -0
  117. natural_pdf-0.1.4/output/highlight_all.png +0 -0
  118. natural_pdf-0.1.4/output/highlight_all_styles.png +0 -0
  119. natural_pdf-0.1.4/output/highlight_all_with_all_layouts.png +0 -0
  120. natural_pdf-0.1.4/output/highlight_all_with_attrs.png +0 -0
  121. natural_pdf-0.1.4/output/highlight_all_with_yolo.png +0 -0
  122. natural_pdf-0.1.4/output/highlight_by_confidence.png +0 -0
  123. natural_pdf-0.1.4/output/highlight_color_test_1.png +0 -0
  124. natural_pdf-0.1.4/output/highlight_color_test_2.png +0 -0
  125. natural_pdf-0.1.4/output/highlight_color_test_3.png +0 -0
  126. natural_pdf-0.1.4/output/highlight_color_test_4.png +0 -0
  127. natural_pdf-0.1.4/output/highlight_layout_method.png +0 -0
  128. natural_pdf-0.1.4/output/highlight_multiple.png +0 -0
  129. natural_pdf-0.1.4/output/highlight_no_attrs.png +0 -0
  130. natural_pdf-0.1.4/output/highlight_region.png +0 -0
  131. natural_pdf-0.1.4/output/highlight_single.png +0 -0
  132. natural_pdf-0.1.4/output/highlight_specific_types.png +0 -0
  133. natural_pdf-0.1.4/output/highlight_specific_types_with_boxes.png +0 -0
  134. natural_pdf-0.1.4/output/highlight_specific_types_with_tables.png +0 -0
  135. natural_pdf-0.1.4/output/highlight_test.png +0 -0
  136. natural_pdf-0.1.4/output/highlight_test_colors.png +0 -0
  137. natural_pdf-0.1.4/output/highlight_test_individual.png +0 -0
  138. natural_pdf-0.1.4/output/highlight_test_individual_annotated.png +0 -0
  139. natural_pdf-0.1.4/output/highlight_test_individual_with_structure.png +0 -0
  140. natural_pdf-0.1.4/output/highlight_test_individual_with_structure_yolo.png +0 -0
  141. natural_pdf-0.1.4/output/highlight_test_individual_with_tables.png +0 -0
  142. natural_pdf-0.1.4/output/highlight_with_attrs.png +0 -0
  143. natural_pdf-0.1.4/output/layout_conf_default.png +0 -0
  144. natural_pdf-0.1.4/output/layout_detection.png +0 -0
  145. natural_pdf-0.1.4/output/layout_fix_test.png +0 -0
  146. natural_pdf-0.1.4/output/layout_fix_test2.png +0 -0
  147. natural_pdf-0.1.4/output/layout_fix_test3.png +0 -0
  148. natural_pdf-0.1.4/output/layout_fix_test4.png +0 -0
  149. natural_pdf-0.1.4/output/model_comparison.png +0 -0
  150. natural_pdf-0.1.4/output/multiple_attributes_display.png +0 -0
  151. natural_pdf-0.1.4/output/ocr_confidence_visualization.png +0 -0
  152. natural_pdf-0.1.4/output/ocr_debug.png +0 -0
  153. natural_pdf-0.1.4/output/ocr_debug_page.html +0 -517
  154. natural_pdf-0.1.4/output/ocr_highlight_all_test.png +0 -0
  155. natural_pdf-0.1.4/output/ocr_highlight_test.png +0 -0
  156. natural_pdf-0.1.4/output/ocr_highlighted.png +0 -0
  157. natural_pdf-0.1.4/output/ocr_simplified.png +0 -0
  158. natural_pdf-0.1.4/output/ocr_threshold_comparison.png +0 -0
  159. natural_pdf-0.1.4/output/ocr_visualization_clean.png +0 -0
  160. natural_pdf-0.1.4/output/ocr_visualization_highlights.png +0 -0
  161. natural_pdf-0.1.4/output/ocr_visualization_text.png +0 -0
  162. natural_pdf-0.1.4/output/paddle_layout_detection.png +0 -0
  163. natural_pdf-0.1.4/output/paddle_layout_polygons.png +0 -0
  164. natural_pdf-0.1.4/output/paddle_layout_sources.png +0 -0
  165. natural_pdf-0.1.4/output/paddle_layout_with_text.png +0 -0
  166. natural_pdf-0.1.4/output/paddle_layout_without_text.png +0 -0
  167. natural_pdf-0.1.4/output/paddleocr_highlights.png +0 -0
  168. natural_pdf-0.1.4/output/paddleocr_results.png +0 -0
  169. natural_pdf-0.1.4/output/paddleocr_test_input.png +0 -0
  170. natural_pdf-0.1.4/output/page_1_for_ocr.png +0 -0
  171. natural_pdf-0.1.4/output/page_4_for_ocr.png +0 -0
  172. natural_pdf-0.1.4/output/region_exclusion_test.png +0 -0
  173. natural_pdf-0.1.4/output/region_management_test.png +0 -0
  174. natural_pdf-0.1.4/output/region_ocr_cropped.png +0 -0
  175. natural_pdf-0.1.4/output/region_ocr_debug.png +0 -0
  176. natural_pdf-0.1.4/output/region_ocr_full_page.png +0 -0
  177. natural_pdf-0.1.4/output/region_ocr_highlighted.png +0 -0
  178. natural_pdf-0.1.4/output/spatial_navigation.png +0 -0
  179. natural_pdf-0.1.4/output/standard_highlight_all.png +0 -0
  180. natural_pdf-0.1.4/output/table_no_ocr.csv +0 -54
  181. natural_pdf-0.1.4/output/table_structure.png +0 -0
  182. natural_pdf-0.1.4/output/table_structure_detail.png +0 -0
  183. natural_pdf-0.1.4/output/table_with_ocr.csv +0 -54
  184. natural_pdf-0.1.4/output/tatr_cells_test.png +0 -0
  185. natural_pdf-0.1.4/output/tatr_ocr_table_test.png +0 -0
  186. natural_pdf-0.1.4/output/tatr_regions.png +0 -0
  187. natural_pdf-0.1.4/output/tatr_regions.txt +0 -16
  188. natural_pdf-0.1.4/output/text_styles.png +0 -0
  189. natural_pdf-0.1.4/output/titles_only.png +0 -0
  190. natural_pdf-0.1.4/output/width_1200px.png +0 -0
  191. natural_pdf-0.1.4/output/width_800px.png +0 -0
  192. natural_pdf-0.1.4/output/width_default.png +0 -0
  193. natural_pdf-0.1.4/output/width_with_scale.png +0 -0
  194. natural_pdf-0.1.4/output/yolo_regions.png +0 -0
  195. natural_pdf-0.1.4/output/yolo_regions.txt +0 -9
  196. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/.github/workflows/docs.yml +0 -0
  197. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/CLAUDE.md +0 -0
  198. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/LICENSE +0 -0
  199. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/MANIFEST.in +0 -0
  200. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/README.md +0 -0
  201. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/check_run_md.sh +0 -0
  202. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/api/index.md +0 -0
  203. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/assets/favicon.png +0 -0
  204. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/assets/favicon.svg +0 -0
  205. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/assets/javascripts/custom.js +0 -0
  206. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/assets/logo.svg +0 -0
  207. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/assets/sample-screen.png +0 -0
  208. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/assets/social-preview.png +0 -0
  209. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/assets/social-preview.svg +0 -0
  210. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/assets/stylesheets/custom.css +0 -0
  211. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/document-qa/index.ipynb +0 -0
  212. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/document-qa/index.md +0 -0
  213. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/element-selection/index.ipynb +0 -0
  214. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/element-selection/index.md +0 -0
  215. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/index.md +0 -0
  216. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/installation/index.md +0 -0
  217. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/interactive-widget/index.ipynb +0 -0
  218. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/interactive-widget/index.md +0 -0
  219. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/layout-analysis/index.ipynb +0 -0
  220. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/layout-analysis/index.md +0 -0
  221. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/ocr/index.md +0 -0
  222. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/pdf-navigation/index.ipynb +0 -0
  223. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/pdf-navigation/index.md +0 -0
  224. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/regions/index.ipynb +0 -0
  225. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/regions/index.md +0 -0
  226. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/tables/index.ipynb +0 -0
  227. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/tables/index.md +0 -0
  228. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/text-analysis/index.ipynb +0 -0
  229. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/text-analysis/index.md +0 -0
  230. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/text-extraction/index.ipynb +0 -0
  231. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/text-extraction/index.md +0 -0
  232. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/tutorials/01-loading-and-extraction.md +0 -0
  233. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/tutorials/02-finding-elements.md +0 -0
  234. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/tutorials/03-extracting-blocks.md +0 -0
  235. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/tutorials/04-table-extraction.md +0 -0
  236. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/tutorials/05-excluding-content.md +0 -0
  237. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/tutorials/06-document-qa.md +0 -0
  238. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/tutorials/07-layout-analysis.md +0 -0
  239. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/tutorials/07-working-with-regions.md +0 -0
  240. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/tutorials/08-spatial-navigation.md +0 -0
  241. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/tutorials/09-section-extraction.md +0 -0
  242. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/tutorials/10-form-field-extraction.md +0 -0
  243. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/tutorials/11-enhanced-table-processing.md +0 -0
  244. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/tutorials/12-ocr-integration.md +0 -0
  245. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/tutorials/13-semantic-search.md +0 -0
  246. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/visual-debugging/index.ipynb +0 -0
  247. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/visual-debugging/index.md +0 -0
  248. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/docs/visual-debugging/region.png +0 -0
  249. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/mkdocs.yml +0 -0
  250. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/analyzers/layout/__init__.py +0 -0
  251. /natural_pdf-0.1.4/output/layout_conf_high.png → /natural_pdf-0.1.5/natural_pdf/exporters/__init__.py +0 -0
  252. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/templates/ocr_debug.html +0 -0
  253. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/utils/__init__.py +0 -0
  254. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf/widgets/frontend/viewer.js +0 -0
  255. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/natural_pdf.egg-info/dependency_links.txt +0 -0
  256. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/notebooks/Examples.ipynb +0 -0
  257. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/pdfs/.gitkeep +0 -0
  258. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/pdfs/01-practice.pdf +0 -0
  259. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/pdfs/0500000US42001.pdf +0 -0
  260. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/pdfs/0500000US42007.pdf +0 -0
  261. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/pdfs/2014 Statistics.pdf +0 -0
  262. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/pdfs/2019 Statistics.pdf +0 -0
  263. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/pdfs/Atlanta_Public_Schools_GA_sample.pdf +0 -0
  264. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/pdfs/needs-ocr.pdf +0 -0
  265. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/publish.sh +0 -0
  266. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/run_all_tutorials.sh +0 -0
  267. {natural_pdf-0.1.4 → natural_pdf-0.1.5}/sample-screen.png +0 -0
  268. {natural_pdf-0.1.4 → 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: 0.1.4
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
@@ -28,6 +28,7 @@ Provides-Extra: haystack
28
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"
@@ -48,6 +60,8 @@ Requires-Dist: surya-ocr; extra == "all"
48
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