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.
Files changed (244) hide show
  1. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/.gitignore +1 -0
  2. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/01-execute_notebooks.py +1 -0
  3. {natural_pdf-0.1.17/natural_pdf.egg-info → natural_pdf-0.1.19}/PKG-INFO +17 -18
  4. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/layout-analysis/index.ipynb +422 -213
  5. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/layout-analysis/index.md +10 -6
  6. natural_pdf-0.1.19/docs/tutorials/01-loading-and-extraction.ipynb +320 -0
  7. natural_pdf-0.1.19/docs/tutorials/02-finding-elements.ipynb +344 -0
  8. natural_pdf-0.1.19/docs/tutorials/03-extracting-blocks.ipynb +151 -0
  9. natural_pdf-0.1.19/docs/tutorials/04-table-extraction.ipynb +557 -0
  10. natural_pdf-0.1.19/docs/tutorials/05-excluding-content.ipynb +274 -0
  11. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/06-document-qa.ipynb +40 -53
  12. natural_pdf-0.1.19/docs/tutorials/07-layout-analysis.ipynb +615 -0
  13. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/07-working-with-regions.ipynb +67 -75
  14. natural_pdf-0.1.19/docs/tutorials/08-spatial-navigation.ipynb +512 -0
  15. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/09-section-extraction.ipynb +121 -157
  16. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/10-form-field-extraction.ipynb +57 -65
  17. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/11-enhanced-table-processing.ipynb +13 -14
  18. natural_pdf-0.1.19/docs/tutorials/12-ocr-integration.ipynb +4197 -0
  19. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/12-ocr-integration.md +0 -1
  20. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/13-semantic-search.ipynb +134 -169
  21. natural_pdf-0.1.19/docs/tutorials/14-categorizing-documents.ipynb +2138 -0
  22. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/14-categorizing-documents.md +1 -1
  23. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/classification/manager.py +38 -13
  24. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/core/pdf.py +141 -32
  25. natural_pdf-0.1.19/natural_pdf/exporters/__init__.py +15 -0
  26. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/exporters/hocr.py +9 -8
  27. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/exporters/original_pdf.py +31 -2
  28. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/ocr/engine_surya.py +1 -2
  29. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/ocr/ocr_manager.py +21 -4
  30. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/search/__init__.py +20 -3
  31. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/search/lancedb_search_service.py +13 -5
  32. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/search/numpy_search_service.py +13 -3
  33. {natural_pdf-0.1.17 → natural_pdf-0.1.19/natural_pdf.egg-info}/PKG-INFO +17 -18
  34. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf.egg-info/SOURCES.txt +3 -0
  35. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf.egg-info/requires.txt +17 -15
  36. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/noxfile.py +13 -3
  37. natural_pdf-0.1.19/pdfs/appendix_fy2026.pdf +0 -0
  38. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pyproject.toml +23 -19
  39. natural_pdf-0.1.19/test_install.sh +46 -0
  40. natural_pdf-0.1.19/tests/test_tutorials.py +50 -0
  41. natural_pdf-0.1.17/docs/tutorials/01-loading-and-extraction.ipynb +0 -328
  42. natural_pdf-0.1.17/docs/tutorials/02-finding-elements.ipynb +0 -352
  43. natural_pdf-0.1.17/docs/tutorials/03-extracting-blocks.ipynb +0 -159
  44. natural_pdf-0.1.17/docs/tutorials/04-table-extraction.ipynb +0 -579
  45. natural_pdf-0.1.17/docs/tutorials/05-excluding-content.ipynb +0 -8402
  46. natural_pdf-0.1.17/docs/tutorials/07-layout-analysis.ipynb +0 -630
  47. natural_pdf-0.1.17/docs/tutorials/08-spatial-navigation.ipynb +0 -520
  48. natural_pdf-0.1.17/docs/tutorials/12-ocr-integration.ipynb +0 -4353
  49. natural_pdf-0.1.17/docs/tutorials/14-categorizing-documents.ipynb +0 -2142
  50. natural_pdf-0.1.17/natural_pdf/exporters/__init__.py +0 -4
  51. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/.cursor/rules/analysis_framework.mdc +0 -0
  52. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/.cursor/rules/coding-style.mdc +0 -0
  53. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/.cursor/rules/edit-md-instead-of-ipynb.mdc +0 -0
  54. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/.cursor/rules/minimal-comments.mdc +0 -0
  55. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/.cursor/rules/natural-pdf-overview.mdc +0 -0
  56. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/.cursor/rules/user-friendly-library-code.mdc +0 -0
  57. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/.github/workflows/docs.yml +0 -0
  58. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/.pre-commit-config.yaml +0 -0
  59. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/02-run_all_tutorials.sh +0 -0
  60. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/CLAUDE.md +0 -0
  61. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/LICENSE +0 -0
  62. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/MANIFEST.in +0 -0
  63. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/README.md +0 -0
  64. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/audit_packaging.py +0 -0
  65. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/check_run_md.sh +0 -0
  66. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/api/index.md +0 -0
  67. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/assets/favicon.png +0 -0
  68. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/assets/favicon.svg +0 -0
  69. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/assets/javascripts/custom.js +0 -0
  70. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/assets/logo.svg +0 -0
  71. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/assets/sample-screen.png +0 -0
  72. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/assets/social-preview.png +0 -0
  73. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/assets/social-preview.svg +0 -0
  74. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/assets/stylesheets/custom.css +0 -0
  75. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/categorizing-documents/index.md +0 -0
  76. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/data-extraction/index.md +0 -0
  77. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/describe/index.ipynb +0 -0
  78. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/describe/index.md +0 -0
  79. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/document-qa/index.ipynb +0 -0
  80. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/document-qa/index.md +0 -0
  81. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/element-selection/index.ipynb +0 -0
  82. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/element-selection/index.md +0 -0
  83. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/finetuning/index.md +0 -0
  84. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/index.md +0 -0
  85. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/installation/index.md +0 -0
  86. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/interactive-widget/index.ipynb +0 -0
  87. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/interactive-widget/index.md +0 -0
  88. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/loops-and-groups/index.ipynb +0 -0
  89. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/loops-and-groups/index.md +0 -0
  90. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/ocr/index.md +0 -0
  91. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/pdf-navigation/index.ipynb +0 -0
  92. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/pdf-navigation/index.md +0 -0
  93. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/reflowing-pages/index.ipynb +0 -0
  94. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/reflowing-pages/index.md +0 -0
  95. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/regions/index.ipynb +0 -0
  96. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/regions/index.md +0 -0
  97. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tables/index.ipynb +0 -0
  98. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tables/index.md +0 -0
  99. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/text-analysis/index.ipynb +0 -0
  100. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/text-analysis/index.md +0 -0
  101. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/text-extraction/index.ipynb +0 -0
  102. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/text-extraction/index.md +0 -0
  103. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/01-loading-and-extraction.md +0 -0
  104. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/02-finding-elements.md +0 -0
  105. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/03-extracting-blocks.md +0 -0
  106. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/04-table-extraction.md +0 -0
  107. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/05-excluding-content.md +0 -0
  108. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/06-document-qa.md +0 -0
  109. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/07-layout-analysis.md +0 -0
  110. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/07-working-with-regions.md +0 -0
  111. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/08-spatial-navigation.md +0 -0
  112. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/09-section-extraction.md +0 -0
  113. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/10-form-field-extraction.md +0 -0
  114. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/11-enhanced-table-processing.md +0 -0
  115. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/tutorials/13-semantic-search.md +0 -0
  116. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/visual-debugging/index.ipynb +0 -0
  117. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/visual-debugging/index.md +0 -0
  118. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/docs/visual-debugging/region.png +0 -0
  119. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/mkdocs.yml +0 -0
  120. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/__init__.py +0 -0
  121. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/analyzers/__init__.py +0 -0
  122. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/analyzers/layout/__init__.py +0 -0
  123. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/analyzers/layout/base.py +0 -0
  124. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/analyzers/layout/docling.py +0 -0
  125. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/analyzers/layout/gemini.py +0 -0
  126. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/analyzers/layout/layout_analyzer.py +0 -0
  127. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/analyzers/layout/layout_manager.py +0 -0
  128. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/analyzers/layout/layout_options.py +0 -0
  129. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/analyzers/layout/paddle.py +0 -0
  130. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/analyzers/layout/pdfplumber_table_finder.py +0 -0
  131. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/analyzers/layout/surya.py +0 -0
  132. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/analyzers/layout/table_structure_utils.py +0 -0
  133. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/analyzers/layout/tatr.py +0 -0
  134. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/analyzers/layout/yolo.py +0 -0
  135. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/analyzers/shape_detection_mixin.py +0 -0
  136. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/analyzers/text_options.py +0 -0
  137. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/analyzers/text_structure.py +0 -0
  138. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/analyzers/utils.py +0 -0
  139. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/classification/mixin.py +0 -0
  140. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/classification/results.py +0 -0
  141. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/collections/mixins.py +0 -0
  142. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/collections/pdf_collection.py +0 -0
  143. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/core/__init__.py +0 -0
  144. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/core/element_manager.py +0 -0
  145. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/core/highlighting_service.py +0 -0
  146. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/core/page.py +0 -0
  147. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/describe/__init__.py +0 -0
  148. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/describe/base.py +0 -0
  149. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/describe/elements.py +0 -0
  150. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/describe/mixin.py +0 -0
  151. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/describe/summary.py +0 -0
  152. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/elements/__init__.py +0 -0
  153. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/elements/base.py +0 -0
  154. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/elements/collections.py +0 -0
  155. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/elements/line.py +0 -0
  156. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/elements/rect.py +0 -0
  157. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/elements/region.py +0 -0
  158. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/elements/text.py +0 -0
  159. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/export/mixin.py +0 -0
  160. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/exporters/base.py +0 -0
  161. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/exporters/data/__init__.py +0 -0
  162. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/exporters/data/pdf.ttf +0 -0
  163. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/exporters/data/sRGB.icc +0 -0
  164. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/exporters/hocr_font.py +0 -0
  165. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/exporters/paddleocr.py +0 -0
  166. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/exporters/searchable_pdf.py +0 -0
  167. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/extraction/manager.py +0 -0
  168. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/extraction/mixin.py +0 -0
  169. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/extraction/result.py +0 -0
  170. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/flows/__init__.py +0 -0
  171. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/flows/collections.py +0 -0
  172. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/flows/element.py +0 -0
  173. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/flows/flow.py +0 -0
  174. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/flows/region.py +0 -0
  175. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/ocr/__init__.py +0 -0
  176. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/ocr/engine.py +0 -0
  177. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/ocr/engine_doctr.py +0 -0
  178. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/ocr/engine_easyocr.py +0 -0
  179. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/ocr/engine_paddle.py +0 -0
  180. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/ocr/ocr_factory.py +0 -0
  181. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/ocr/ocr_options.py +0 -0
  182. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/ocr/utils.py +0 -0
  183. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/qa/__init__.py +0 -0
  184. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/qa/document_qa.py +0 -0
  185. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/search/search_options.py +0 -0
  186. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/search/search_service_protocol.py +0 -0
  187. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/search/searchable_mixin.py +0 -0
  188. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/selectors/__init__.py +0 -0
  189. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/selectors/parser.py +0 -0
  190. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/templates/__init__.py +0 -0
  191. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/templates/finetune/fine_tune_paddleocr.md +0 -0
  192. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/templates/spa/css/style.css +0 -0
  193. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/templates/spa/index.html +0 -0
  194. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/templates/spa/js/app.js +0 -0
  195. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/templates/spa/words.txt +0 -0
  196. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/utils/__init__.py +0 -0
  197. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/utils/debug.py +0 -0
  198. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/utils/highlighting.py +0 -0
  199. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/utils/identifiers.py +0 -0
  200. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/utils/locks.py +0 -0
  201. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/utils/packaging.py +0 -0
  202. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/utils/reading_order.py +0 -0
  203. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/utils/text_extraction.py +0 -0
  204. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/utils/visualization.py +0 -0
  205. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/widgets/__init__.py +0 -0
  206. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf/widgets/viewer.py +0 -0
  207. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf.egg-info/dependency_links.txt +0 -0
  208. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/natural_pdf.egg-info/top_level.txt +0 -0
  209. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/.gitkeep +0 -0
  210. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/01-practice.pdf +0 -0
  211. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/0500000US42001.pdf +0 -0
  212. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/0500000US42007.pdf +0 -0
  213. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/2014 Statistics.pdf +0 -0
  214. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/2019 Statistics.pdf +0 -0
  215. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/30.pdf +0 -0
  216. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/Atlanta_Public_Schools_GA_sample.pdf +0 -0
  217. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/anexo_edital_6604_1743480-table.pdf +0 -0
  218. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/cia-doc.pdf +0 -0
  219. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/geometry.pdf +0 -0
  220. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/image.png +0 -0
  221. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/image.png.pdf +0 -0
  222. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/multicolumn.pdf +0 -0
  223. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/needs-ocr.pdf +0 -0
  224. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/red.pdf +0 -0
  225. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/tiny-ocr-2.pdf +0 -0
  226. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/tiny-ocr-3.pdf +0 -0
  227. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/tiny-ocr-small.jpg +0 -0
  228. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/tiny-ocr-wide.jpg +0 -0
  229. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/tiny-ocr.pdf +0 -0
  230. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/tiny.pdf +0 -0
  231. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/pdfs/word-counter.pdf +0 -0
  232. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/publish.sh +0 -0
  233. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/sample-screen.png +0 -0
  234. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/setup.cfg +0 -0
  235. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/tests/conftest.py +0 -0
  236. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/tests/exporters/test_paddleocr_exporter.py +0 -0
  237. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/tests/test_core/test_containment_geometry.py +0 -0
  238. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/tests/test_core/test_elements.py +0 -0
  239. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/tests/test_core/test_loading.py +0 -0
  240. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/tests/test_core/test_spatial.py +0 -0
  241. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/tests/test_core/test_text_extraction.py +0 -0
  242. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/tests/test_loading_original.py +0 -0
  243. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/tests/test_optional_deps.py +0 -0
  244. {natural_pdf-0.1.17 → natural_pdf-0.1.19}/uv.lock +0 -0
@@ -1,3 +1,4 @@
1
+ importtime_output.txt
1
2
  .notebook_cache.json
2
3
  .venv
3
4
  output
@@ -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: 0.1.17
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>=9.7.0
24
+ Requires-Dist: pikepdf
24
25
  Requires-Dist: scipy
25
26
  Requires-Dist: torch
26
27
  Requires-Dist: torchvision
27
- Requires-Dist: transformers[sentencepiece]<=4.34.1
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[search]; extra == "favorites"
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[addons]; extra == "all"
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