kreuzberg 4.0.8 → 4.1.0

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 (308) hide show
  1. checksums.yaml +4 -4
  2. data/Gemfile.lock +2 -2
  3. data/README.md +1 -1
  4. data/ext/kreuzberg_rb/native/Cargo.lock +94 -98
  5. data/ext/kreuzberg_rb/native/Cargo.toml +4 -2
  6. data/ext/kreuzberg_rb/native/src/batch.rs +139 -0
  7. data/ext/kreuzberg_rb/native/src/config/mod.rs +10 -0
  8. data/ext/kreuzberg_rb/native/src/config/types.rs +1058 -0
  9. data/ext/kreuzberg_rb/native/src/error_handling.rs +125 -0
  10. data/ext/kreuzberg_rb/native/src/extraction.rs +79 -0
  11. data/ext/kreuzberg_rb/native/src/gc_guarded_value.rs +35 -0
  12. data/ext/kreuzberg_rb/native/src/helpers.rs +176 -0
  13. data/ext/kreuzberg_rb/native/src/lib.rs +342 -3622
  14. data/ext/kreuzberg_rb/native/src/metadata.rs +34 -0
  15. data/ext/kreuzberg_rb/native/src/plugins/mod.rs +92 -0
  16. data/ext/kreuzberg_rb/native/src/plugins/ocr_backend.rs +159 -0
  17. data/ext/kreuzberg_rb/native/src/plugins/post_processor.rs +126 -0
  18. data/ext/kreuzberg_rb/native/src/plugins/validator.rs +99 -0
  19. data/ext/kreuzberg_rb/native/src/result.rs +326 -0
  20. data/ext/kreuzberg_rb/native/src/validation.rs +4 -0
  21. data/lib/kreuzberg/config.rb +66 -0
  22. data/lib/kreuzberg/result.rb +107 -2
  23. data/lib/kreuzberg/types.rb +104 -0
  24. data/lib/kreuzberg/version.rb +1 -1
  25. data/lib/kreuzberg.rb +0 -4
  26. data/sig/kreuzberg.rbs +105 -1
  27. data/vendor/Cargo.toml +3 -3
  28. data/vendor/kreuzberg/Cargo.toml +4 -3
  29. data/vendor/kreuzberg/README.md +1 -1
  30. data/vendor/kreuzberg/src/api/config.rs +69 -0
  31. data/vendor/kreuzberg/src/api/handlers.rs +99 -2
  32. data/vendor/kreuzberg/src/api/mod.rs +14 -7
  33. data/vendor/kreuzberg/src/api/router.rs +214 -0
  34. data/vendor/kreuzberg/src/api/startup.rs +243 -0
  35. data/vendor/kreuzberg/src/api/types.rs +78 -0
  36. data/vendor/kreuzberg/src/cache/cleanup.rs +277 -0
  37. data/vendor/kreuzberg/src/cache/core.rs +428 -0
  38. data/vendor/kreuzberg/src/cache/mod.rs +21 -843
  39. data/vendor/kreuzberg/src/cache/utilities.rs +156 -0
  40. data/vendor/kreuzberg/src/chunking/boundaries.rs +301 -0
  41. data/vendor/kreuzberg/src/chunking/builder.rs +294 -0
  42. data/vendor/kreuzberg/src/chunking/config.rs +52 -0
  43. data/vendor/kreuzberg/src/chunking/core.rs +1017 -0
  44. data/vendor/kreuzberg/src/chunking/mod.rs +14 -2211
  45. data/vendor/kreuzberg/src/chunking/processor.rs +10 -0
  46. data/vendor/kreuzberg/src/chunking/validation.rs +686 -0
  47. data/vendor/kreuzberg/src/core/config/extraction/core.rs +169 -0
  48. data/vendor/kreuzberg/src/core/config/extraction/env.rs +179 -0
  49. data/vendor/kreuzberg/src/core/config/extraction/loaders.rs +204 -0
  50. data/vendor/kreuzberg/src/core/config/extraction/mod.rs +42 -0
  51. data/vendor/kreuzberg/src/core/config/extraction/types.rs +93 -0
  52. data/vendor/kreuzberg/src/core/config/formats.rs +135 -0
  53. data/vendor/kreuzberg/src/core/config/mod.rs +20 -0
  54. data/vendor/kreuzberg/src/core/config/ocr.rs +73 -0
  55. data/vendor/kreuzberg/src/core/config/page.rs +57 -0
  56. data/vendor/kreuzberg/src/core/config/pdf.rs +111 -0
  57. data/vendor/kreuzberg/src/core/config/processing.rs +312 -0
  58. data/vendor/kreuzberg/src/core/config_validation/dependencies.rs +187 -0
  59. data/vendor/kreuzberg/src/core/config_validation/mod.rs +386 -0
  60. data/vendor/kreuzberg/src/core/config_validation/sections.rs +401 -0
  61. data/vendor/kreuzberg/src/core/extractor/batch.rs +246 -0
  62. data/vendor/kreuzberg/src/core/extractor/bytes.rs +116 -0
  63. data/vendor/kreuzberg/src/core/extractor/file.rs +240 -0
  64. data/vendor/kreuzberg/src/core/extractor/helpers.rs +71 -0
  65. data/vendor/kreuzberg/src/core/extractor/legacy.rs +62 -0
  66. data/vendor/kreuzberg/src/core/extractor/mod.rs +490 -0
  67. data/vendor/kreuzberg/src/core/extractor/sync.rs +208 -0
  68. data/vendor/kreuzberg/src/core/mod.rs +4 -1
  69. data/vendor/kreuzberg/src/core/pipeline/cache.rs +60 -0
  70. data/vendor/kreuzberg/src/core/pipeline/execution.rs +89 -0
  71. data/vendor/kreuzberg/src/core/pipeline/features.rs +108 -0
  72. data/vendor/kreuzberg/src/core/pipeline/format.rs +392 -0
  73. data/vendor/kreuzberg/src/core/pipeline/initialization.rs +67 -0
  74. data/vendor/kreuzberg/src/core/pipeline/mod.rs +135 -0
  75. data/vendor/kreuzberg/src/core/pipeline/tests.rs +975 -0
  76. data/vendor/kreuzberg/src/core/server_config/env.rs +90 -0
  77. data/vendor/kreuzberg/src/core/server_config/loader.rs +202 -0
  78. data/vendor/kreuzberg/src/core/server_config/mod.rs +380 -0
  79. data/vendor/kreuzberg/src/core/server_config/tests/basic_tests.rs +124 -0
  80. data/vendor/kreuzberg/src/core/server_config/tests/env_tests.rs +216 -0
  81. data/vendor/kreuzberg/src/core/server_config/tests/file_loading_tests.rs +341 -0
  82. data/vendor/kreuzberg/src/core/server_config/tests/mod.rs +5 -0
  83. data/vendor/kreuzberg/src/core/server_config/validation.rs +17 -0
  84. data/vendor/kreuzberg/src/embeddings.rs +136 -13
  85. data/vendor/kreuzberg/src/extraction/{archive.rs → archive/mod.rs} +45 -239
  86. data/vendor/kreuzberg/src/extraction/archive/sevenz.rs +98 -0
  87. data/vendor/kreuzberg/src/extraction/archive/tar.rs +118 -0
  88. data/vendor/kreuzberg/src/extraction/archive/zip.rs +101 -0
  89. data/vendor/kreuzberg/src/extraction/html/converter.rs +592 -0
  90. data/vendor/kreuzberg/src/extraction/html/image_handling.rs +95 -0
  91. data/vendor/kreuzberg/src/extraction/html/mod.rs +53 -0
  92. data/vendor/kreuzberg/src/extraction/html/processor.rs +659 -0
  93. data/vendor/kreuzberg/src/extraction/html/stack_management.rs +103 -0
  94. data/vendor/kreuzberg/src/extraction/html/types.rs +28 -0
  95. data/vendor/kreuzberg/src/extraction/mod.rs +6 -2
  96. data/vendor/kreuzberg/src/extraction/pptx/container.rs +159 -0
  97. data/vendor/kreuzberg/src/extraction/pptx/content_builder.rs +168 -0
  98. data/vendor/kreuzberg/src/extraction/pptx/elements.rs +132 -0
  99. data/vendor/kreuzberg/src/extraction/pptx/image_handling.rs +57 -0
  100. data/vendor/kreuzberg/src/extraction/pptx/metadata.rs +160 -0
  101. data/vendor/kreuzberg/src/extraction/pptx/mod.rs +558 -0
  102. data/vendor/kreuzberg/src/extraction/pptx/parser.rs +379 -0
  103. data/vendor/kreuzberg/src/extraction/transform/content.rs +205 -0
  104. data/vendor/kreuzberg/src/extraction/transform/elements.rs +211 -0
  105. data/vendor/kreuzberg/src/extraction/transform/mod.rs +480 -0
  106. data/vendor/kreuzberg/src/extraction/transform/types.rs +27 -0
  107. data/vendor/kreuzberg/src/extractors/archive.rs +2 -0
  108. data/vendor/kreuzberg/src/extractors/bibtex.rs +2 -0
  109. data/vendor/kreuzberg/src/extractors/djot_format/attributes.rs +134 -0
  110. data/vendor/kreuzberg/src/extractors/djot_format/conversion.rs +223 -0
  111. data/vendor/kreuzberg/src/extractors/djot_format/extractor.rs +172 -0
  112. data/vendor/kreuzberg/src/extractors/djot_format/mod.rs +24 -0
  113. data/vendor/kreuzberg/src/extractors/djot_format/parsing/block_handlers.rs +271 -0
  114. data/vendor/kreuzberg/src/extractors/djot_format/parsing/content_extraction.rs +257 -0
  115. data/vendor/kreuzberg/src/extractors/djot_format/parsing/event_handlers.rs +101 -0
  116. data/vendor/kreuzberg/src/extractors/djot_format/parsing/inline_handlers.rs +201 -0
  117. data/vendor/kreuzberg/src/extractors/djot_format/parsing/mod.rs +16 -0
  118. data/vendor/kreuzberg/src/extractors/djot_format/parsing/state.rs +78 -0
  119. data/vendor/kreuzberg/src/extractors/djot_format/parsing/table_extraction.rs +68 -0
  120. data/vendor/kreuzberg/src/extractors/djot_format/parsing/text_extraction.rs +61 -0
  121. data/vendor/kreuzberg/src/extractors/djot_format/rendering.rs +452 -0
  122. data/vendor/kreuzberg/src/extractors/docbook.rs +2 -0
  123. data/vendor/kreuzberg/src/extractors/docx.rs +12 -1
  124. data/vendor/kreuzberg/src/extractors/email.rs +2 -0
  125. data/vendor/kreuzberg/src/extractors/epub/content.rs +333 -0
  126. data/vendor/kreuzberg/src/extractors/epub/metadata.rs +137 -0
  127. data/vendor/kreuzberg/src/extractors/epub/mod.rs +186 -0
  128. data/vendor/kreuzberg/src/extractors/epub/parsing.rs +86 -0
  129. data/vendor/kreuzberg/src/extractors/excel.rs +4 -0
  130. data/vendor/kreuzberg/src/extractors/fictionbook.rs +2 -0
  131. data/vendor/kreuzberg/src/extractors/frontmatter_utils.rs +466 -0
  132. data/vendor/kreuzberg/src/extractors/html.rs +80 -8
  133. data/vendor/kreuzberg/src/extractors/image.rs +8 -1
  134. data/vendor/kreuzberg/src/extractors/jats/elements.rs +350 -0
  135. data/vendor/kreuzberg/src/extractors/jats/metadata.rs +21 -0
  136. data/vendor/kreuzberg/src/extractors/{jats.rs → jats/mod.rs} +10 -412
  137. data/vendor/kreuzberg/src/extractors/jats/parser.rs +52 -0
  138. data/vendor/kreuzberg/src/extractors/jupyter.rs +2 -0
  139. data/vendor/kreuzberg/src/extractors/latex/commands.rs +93 -0
  140. data/vendor/kreuzberg/src/extractors/latex/environments.rs +157 -0
  141. data/vendor/kreuzberg/src/extractors/latex/metadata.rs +27 -0
  142. data/vendor/kreuzberg/src/extractors/latex/mod.rs +146 -0
  143. data/vendor/kreuzberg/src/extractors/latex/parser.rs +231 -0
  144. data/vendor/kreuzberg/src/extractors/latex/utilities.rs +126 -0
  145. data/vendor/kreuzberg/src/extractors/markdown.rs +39 -162
  146. data/vendor/kreuzberg/src/extractors/mod.rs +9 -1
  147. data/vendor/kreuzberg/src/extractors/odt.rs +2 -0
  148. data/vendor/kreuzberg/src/extractors/opml/core.rs +165 -0
  149. data/vendor/kreuzberg/src/extractors/opml/mod.rs +31 -0
  150. data/vendor/kreuzberg/src/extractors/opml/parser.rs +479 -0
  151. data/vendor/kreuzberg/src/extractors/orgmode.rs +2 -0
  152. data/vendor/kreuzberg/src/extractors/pdf/extraction.rs +106 -0
  153. data/vendor/kreuzberg/src/extractors/{pdf.rs → pdf/mod.rs} +25 -324
  154. data/vendor/kreuzberg/src/extractors/pdf/ocr.rs +214 -0
  155. data/vendor/kreuzberg/src/extractors/pdf/pages.rs +51 -0
  156. data/vendor/kreuzberg/src/extractors/pptx.rs +9 -2
  157. data/vendor/kreuzberg/src/extractors/rst.rs +2 -0
  158. data/vendor/kreuzberg/src/extractors/rtf/encoding.rs +116 -0
  159. data/vendor/kreuzberg/src/extractors/rtf/formatting.rs +24 -0
  160. data/vendor/kreuzberg/src/extractors/rtf/images.rs +72 -0
  161. data/vendor/kreuzberg/src/extractors/rtf/metadata.rs +216 -0
  162. data/vendor/kreuzberg/src/extractors/rtf/mod.rs +142 -0
  163. data/vendor/kreuzberg/src/extractors/rtf/parser.rs +259 -0
  164. data/vendor/kreuzberg/src/extractors/rtf/tables.rs +83 -0
  165. data/vendor/kreuzberg/src/extractors/structured.rs +2 -0
  166. data/vendor/kreuzberg/src/extractors/text.rs +4 -0
  167. data/vendor/kreuzberg/src/extractors/typst.rs +2 -0
  168. data/vendor/kreuzberg/src/extractors/xml.rs +2 -0
  169. data/vendor/kreuzberg/src/keywords/processor.rs +14 -0
  170. data/vendor/kreuzberg/src/language_detection/processor.rs +10 -0
  171. data/vendor/kreuzberg/src/lib.rs +2 -2
  172. data/vendor/kreuzberg/src/mcp/errors.rs +312 -0
  173. data/vendor/kreuzberg/src/mcp/format.rs +211 -0
  174. data/vendor/kreuzberg/src/mcp/mod.rs +9 -3
  175. data/vendor/kreuzberg/src/mcp/params.rs +196 -0
  176. data/vendor/kreuzberg/src/mcp/server.rs +39 -1438
  177. data/vendor/kreuzberg/src/mcp/tools/cache.rs +179 -0
  178. data/vendor/kreuzberg/src/mcp/tools/extraction.rs +403 -0
  179. data/vendor/kreuzberg/src/mcp/tools/mime.rs +150 -0
  180. data/vendor/kreuzberg/src/mcp/tools/mod.rs +11 -0
  181. data/vendor/kreuzberg/src/ocr/backends/easyocr.rs +96 -0
  182. data/vendor/kreuzberg/src/ocr/backends/mod.rs +7 -0
  183. data/vendor/kreuzberg/src/ocr/backends/paddleocr.rs +27 -0
  184. data/vendor/kreuzberg/src/ocr/backends/tesseract.rs +134 -0
  185. data/vendor/kreuzberg/src/ocr/hocr.rs +60 -16
  186. data/vendor/kreuzberg/src/ocr/language_registry.rs +11 -235
  187. data/vendor/kreuzberg/src/ocr/mod.rs +1 -0
  188. data/vendor/kreuzberg/src/ocr/processor/config.rs +203 -0
  189. data/vendor/kreuzberg/src/ocr/processor/execution.rs +494 -0
  190. data/vendor/kreuzberg/src/ocr/processor/mod.rs +265 -0
  191. data/vendor/kreuzberg/src/ocr/processor/validation.rs +145 -0
  192. data/vendor/kreuzberg/src/ocr/tesseract_backend.rs +41 -24
  193. data/vendor/kreuzberg/src/pdf/bindings.rs +21 -8
  194. data/vendor/kreuzberg/src/pdf/hierarchy/bounding_box.rs +289 -0
  195. data/vendor/kreuzberg/src/pdf/hierarchy/clustering.rs +199 -0
  196. data/vendor/kreuzberg/src/pdf/{hierarchy.rs → hierarchy/extraction.rs} +6 -346
  197. data/vendor/kreuzberg/src/pdf/hierarchy/mod.rs +18 -0
  198. data/vendor/kreuzberg/src/plugins/extractor/mod.rs +319 -0
  199. data/vendor/kreuzberg/src/plugins/extractor/registry.rs +434 -0
  200. data/vendor/kreuzberg/src/plugins/extractor/trait.rs +391 -0
  201. data/vendor/kreuzberg/src/plugins/mod.rs +13 -0
  202. data/vendor/kreuzberg/src/plugins/ocr.rs +11 -0
  203. data/vendor/kreuzberg/src/plugins/processor/mod.rs +365 -0
  204. data/vendor/kreuzberg/src/plugins/processor/registry.rs +37 -0
  205. data/vendor/kreuzberg/src/plugins/processor/trait.rs +284 -0
  206. data/vendor/kreuzberg/src/plugins/registry/extractor.rs +416 -0
  207. data/vendor/kreuzberg/src/plugins/registry/mod.rs +116 -0
  208. data/vendor/kreuzberg/src/plugins/registry/ocr.rs +293 -0
  209. data/vendor/kreuzberg/src/plugins/registry/processor.rs +304 -0
  210. data/vendor/kreuzberg/src/plugins/registry/validator.rs +238 -0
  211. data/vendor/kreuzberg/src/plugins/validator/mod.rs +424 -0
  212. data/vendor/kreuzberg/src/plugins/validator/registry.rs +355 -0
  213. data/vendor/kreuzberg/src/plugins/validator/trait.rs +276 -0
  214. data/vendor/kreuzberg/src/stopwords/languages/asian.rs +40 -0
  215. data/vendor/kreuzberg/src/stopwords/languages/germanic.rs +36 -0
  216. data/vendor/kreuzberg/src/stopwords/languages/mod.rs +10 -0
  217. data/vendor/kreuzberg/src/stopwords/languages/other.rs +44 -0
  218. data/vendor/kreuzberg/src/stopwords/languages/romance.rs +36 -0
  219. data/vendor/kreuzberg/src/stopwords/languages/slavic.rs +36 -0
  220. data/vendor/kreuzberg/src/stopwords/mod.rs +7 -33
  221. data/vendor/kreuzberg/src/text/quality.rs +1 -1
  222. data/vendor/kreuzberg/src/text/quality_processor.rs +10 -0
  223. data/vendor/kreuzberg/src/text/token_reduction/core/analysis.rs +238 -0
  224. data/vendor/kreuzberg/src/text/token_reduction/core/mod.rs +8 -0
  225. data/vendor/kreuzberg/src/text/token_reduction/core/punctuation.rs +54 -0
  226. data/vendor/kreuzberg/src/text/token_reduction/core/reducer.rs +384 -0
  227. data/vendor/kreuzberg/src/text/token_reduction/core/sentence_selection.rs +68 -0
  228. data/vendor/kreuzberg/src/text/token_reduction/core/word_filtering.rs +156 -0
  229. data/vendor/kreuzberg/src/text/token_reduction/filters/general.rs +377 -0
  230. data/vendor/kreuzberg/src/text/token_reduction/filters/html.rs +51 -0
  231. data/vendor/kreuzberg/src/text/token_reduction/filters/markdown.rs +285 -0
  232. data/vendor/kreuzberg/src/text/token_reduction/filters.rs +131 -246
  233. data/vendor/kreuzberg/src/types/djot.rs +209 -0
  234. data/vendor/kreuzberg/src/types/extraction.rs +301 -0
  235. data/vendor/kreuzberg/src/types/formats.rs +443 -0
  236. data/vendor/kreuzberg/src/types/metadata.rs +560 -0
  237. data/vendor/kreuzberg/src/types/mod.rs +281 -0
  238. data/vendor/kreuzberg/src/types/page.rs +182 -0
  239. data/vendor/kreuzberg/src/types/serde_helpers.rs +132 -0
  240. data/vendor/kreuzberg/src/types/tables.rs +39 -0
  241. data/vendor/kreuzberg/src/utils/quality/heuristics.rs +58 -0
  242. data/vendor/kreuzberg/src/utils/{quality.rs → quality/mod.rs} +168 -489
  243. data/vendor/kreuzberg/src/utils/quality/patterns.rs +117 -0
  244. data/vendor/kreuzberg/src/utils/quality/scoring.rs +178 -0
  245. data/vendor/kreuzberg/src/utils/string_pool/buffer_pool.rs +325 -0
  246. data/vendor/kreuzberg/src/utils/string_pool/interned.rs +102 -0
  247. data/vendor/kreuzberg/src/utils/string_pool/language_pool.rs +119 -0
  248. data/vendor/kreuzberg/src/utils/string_pool/mime_pool.rs +235 -0
  249. data/vendor/kreuzberg/src/utils/string_pool/mod.rs +41 -0
  250. data/vendor/kreuzberg/tests/api_chunk.rs +313 -0
  251. data/vendor/kreuzberg/tests/api_embed.rs +6 -9
  252. data/vendor/kreuzberg/tests/batch_orchestration.rs +1 -0
  253. data/vendor/kreuzberg/tests/concurrency_stress.rs +7 -0
  254. data/vendor/kreuzberg/tests/core_integration.rs +1 -0
  255. data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +130 -0
  256. data/vendor/kreuzberg/tests/epub_native_extractor_tests.rs +5 -14
  257. data/vendor/kreuzberg/tests/format_integration.rs +2 -0
  258. data/vendor/kreuzberg/tests/helpers/mod.rs +1 -0
  259. data/vendor/kreuzberg/tests/html_table_test.rs +11 -11
  260. data/vendor/kreuzberg/tests/ocr_configuration.rs +16 -0
  261. data/vendor/kreuzberg/tests/ocr_errors.rs +18 -0
  262. data/vendor/kreuzberg/tests/ocr_quality.rs +9 -0
  263. data/vendor/kreuzberg/tests/ocr_stress.rs +1 -0
  264. data/vendor/kreuzberg/tests/pipeline_integration.rs +50 -0
  265. data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +13 -0
  266. data/vendor/kreuzberg/tests/plugin_system.rs +12 -0
  267. data/vendor/kreuzberg/tests/registry_integration_tests.rs +2 -0
  268. data/vendor/kreuzberg-ffi/Cargo.toml +2 -1
  269. data/vendor/kreuzberg-ffi/benches/result_view_benchmark.rs +2 -0
  270. data/vendor/kreuzberg-ffi/kreuzberg.h +347 -178
  271. data/vendor/kreuzberg-ffi/src/config/html.rs +318 -0
  272. data/vendor/kreuzberg-ffi/src/config/loader.rs +154 -0
  273. data/vendor/kreuzberg-ffi/src/config/merge.rs +104 -0
  274. data/vendor/kreuzberg-ffi/src/config/mod.rs +385 -0
  275. data/vendor/kreuzberg-ffi/src/config/parse.rs +91 -0
  276. data/vendor/kreuzberg-ffi/src/config/serialize.rs +118 -0
  277. data/vendor/kreuzberg-ffi/src/config_builder.rs +598 -0
  278. data/vendor/kreuzberg-ffi/src/error.rs +46 -14
  279. data/vendor/kreuzberg-ffi/src/helpers.rs +10 -0
  280. data/vendor/kreuzberg-ffi/src/html_options.rs +421 -0
  281. data/vendor/kreuzberg-ffi/src/lib.rs +16 -0
  282. data/vendor/kreuzberg-ffi/src/panic_shield.rs +11 -0
  283. data/vendor/kreuzberg-ffi/src/plugins/ocr_backend.rs +2 -0
  284. data/vendor/kreuzberg-ffi/src/result.rs +148 -122
  285. data/vendor/kreuzberg-ffi/src/result_view.rs +4 -0
  286. data/vendor/kreuzberg-tesseract/Cargo.toml +2 -2
  287. metadata +200 -28
  288. data/vendor/kreuzberg/src/api/server.rs +0 -518
  289. data/vendor/kreuzberg/src/core/config.rs +0 -1914
  290. data/vendor/kreuzberg/src/core/config_validation.rs +0 -949
  291. data/vendor/kreuzberg/src/core/extractor.rs +0 -1200
  292. data/vendor/kreuzberg/src/core/pipeline.rs +0 -1223
  293. data/vendor/kreuzberg/src/core/server_config.rs +0 -1220
  294. data/vendor/kreuzberg/src/extraction/html.rs +0 -1830
  295. data/vendor/kreuzberg/src/extraction/pptx.rs +0 -3102
  296. data/vendor/kreuzberg/src/extractors/epub.rs +0 -696
  297. data/vendor/kreuzberg/src/extractors/latex.rs +0 -653
  298. data/vendor/kreuzberg/src/extractors/opml.rs +0 -635
  299. data/vendor/kreuzberg/src/extractors/rtf.rs +0 -809
  300. data/vendor/kreuzberg/src/ocr/processor.rs +0 -858
  301. data/vendor/kreuzberg/src/plugins/extractor.rs +0 -1042
  302. data/vendor/kreuzberg/src/plugins/processor.rs +0 -650
  303. data/vendor/kreuzberg/src/plugins/registry.rs +0 -1339
  304. data/vendor/kreuzberg/src/plugins/validator.rs +0 -967
  305. data/vendor/kreuzberg/src/text/token_reduction/core.rs +0 -832
  306. data/vendor/kreuzberg/src/types.rs +0 -1713
  307. data/vendor/kreuzberg/src/utils/string_pool.rs +0 -762
  308. data/vendor/kreuzberg-ffi/src/config.rs +0 -1341
@@ -0,0 +1,160 @@
1
+ //! Metadata extraction and notes handling.
2
+ //!
3
+ //! This module provides functionality for extracting metadata from PPTX files
4
+ //! and extracting notes from slides.
5
+
6
+ use std::collections::HashMap;
7
+ use std::fs::File;
8
+ use zip::ZipArchive;
9
+
10
+ use crate::error::Result;
11
+ use crate::text::utf8_validation;
12
+ use crate::types::metadata::PptxMetadata;
13
+ use roxmltree::Document;
14
+
15
+ #[cfg(feature = "office")]
16
+ use crate::extraction::office_metadata::{
17
+ extract_core_properties, extract_custom_properties, extract_pptx_app_properties,
18
+ };
19
+ #[cfg(feature = "office")]
20
+ use serde_json::Value;
21
+
22
+ use super::container::PptxContainer;
23
+
24
+ /// Extract comprehensive metadata from PPTX using office_metadata module
25
+ pub(super) fn extract_metadata(archive: &mut ZipArchive<File>) -> PptxMetadata {
26
+ #[cfg(feature = "office")]
27
+ {
28
+ let mut metadata_map = HashMap::new();
29
+ let mut slide_count = 0;
30
+ let mut slide_names = Vec::new();
31
+
32
+ if let Ok(core) = extract_core_properties(archive) {
33
+ if let Some(title) = core.title {
34
+ metadata_map.insert("title".to_string(), title);
35
+ }
36
+ if let Some(creator) = core.creator {
37
+ metadata_map.insert("author".to_string(), creator.clone());
38
+ metadata_map.insert("created_by".to_string(), creator);
39
+ }
40
+ if let Some(subject) = core.subject {
41
+ metadata_map.insert("subject".to_string(), subject.clone());
42
+ metadata_map.insert("summary".to_string(), subject);
43
+ }
44
+ if let Some(keywords) = core.keywords {
45
+ metadata_map.insert("keywords".to_string(), keywords);
46
+ }
47
+ if let Some(description) = core.description {
48
+ metadata_map.insert("description".to_string(), description);
49
+ }
50
+ if let Some(modified_by) = core.last_modified_by {
51
+ metadata_map.insert("modified_by".to_string(), modified_by);
52
+ }
53
+ if let Some(created) = core.created {
54
+ metadata_map.insert("created_at".to_string(), created);
55
+ }
56
+ if let Some(modified) = core.modified {
57
+ metadata_map.insert("modified_at".to_string(), modified);
58
+ }
59
+ if let Some(revision) = core.revision {
60
+ metadata_map.insert("revision".to_string(), revision);
61
+ }
62
+ if let Some(category) = core.category {
63
+ metadata_map.insert("category".to_string(), category);
64
+ }
65
+ }
66
+
67
+ if let Ok(app) = extract_pptx_app_properties(archive) {
68
+ if let Some(slides) = app.slides {
69
+ metadata_map.insert("slide_count".to_string(), slides.to_string());
70
+ slide_count = slides.max(0) as usize;
71
+ }
72
+ if let Some(notes) = app.notes {
73
+ metadata_map.insert("notes_count".to_string(), notes.to_string());
74
+ }
75
+ if let Some(hidden_slides) = app.hidden_slides {
76
+ metadata_map.insert("hidden_slides".to_string(), hidden_slides.to_string());
77
+ }
78
+ if !app.slide_titles.is_empty() {
79
+ slide_names = app.slide_titles.clone();
80
+ metadata_map.insert("slide_titles".to_string(), app.slide_titles.join(", "));
81
+ }
82
+ if let Some(presentation_format) = app.presentation_format {
83
+ metadata_map.insert("presentation_format".to_string(), presentation_format);
84
+ }
85
+ if let Some(company) = app.company {
86
+ metadata_map.insert("organization".to_string(), company);
87
+ }
88
+ if let Some(application) = app.application {
89
+ metadata_map.insert("application".to_string(), application);
90
+ }
91
+ if let Some(app_version) = app.app_version {
92
+ metadata_map.insert("application_version".to_string(), app_version);
93
+ }
94
+ }
95
+
96
+ if let Ok(custom) = extract_custom_properties(archive) {
97
+ for (key, value) in custom {
98
+ let value_str = match value {
99
+ Value::String(s) => s,
100
+ Value::Number(n) => n.to_string(),
101
+ Value::Bool(b) => b.to_string(),
102
+ Value::Null => "null".to_string(),
103
+ Value::Array(_) | Value::Object(_) => value.to_string(),
104
+ };
105
+ metadata_map.insert(format!("custom_{}", key), value_str);
106
+ }
107
+ }
108
+
109
+ PptxMetadata {
110
+ slide_count,
111
+ slide_names,
112
+ }
113
+ }
114
+
115
+ #[cfg(not(feature = "office"))]
116
+ {
117
+ PptxMetadata {
118
+ slide_count: 0,
119
+ slide_names: Vec::new(),
120
+ }
121
+ }
122
+ }
123
+
124
+ pub(super) fn extract_all_notes(container: &mut PptxContainer) -> Result<HashMap<u32, String>> {
125
+ let mut notes = HashMap::new();
126
+
127
+ let slide_paths: Vec<String> = container.slide_paths().to_vec();
128
+
129
+ for (i, slide_path) in slide_paths.iter().enumerate() {
130
+ let notes_path = slide_path.replace("slides/slide", "notesSlides/notesSlide");
131
+ if let Ok(notes_xml) = container.read_file(&notes_path)
132
+ && let Ok(note_text) = extract_notes_text(&notes_xml)
133
+ {
134
+ notes.insert((i + 1) as u32, note_text);
135
+ }
136
+ }
137
+
138
+ Ok(notes)
139
+ }
140
+
141
+ fn extract_notes_text(notes_xml: &[u8]) -> Result<String> {
142
+ let xml_str = utf8_validation::from_utf8(notes_xml)
143
+ .map_err(|e| crate::error::KreuzbergError::parsing(format!("Invalid UTF-8 in notes XML: {}", e)))?;
144
+
145
+ let doc = Document::parse(xml_str)
146
+ .map_err(|e| crate::error::KreuzbergError::parsing(format!("Failed to parse notes XML: {}", e)))?;
147
+
148
+ let mut text_parts = Vec::with_capacity(16);
149
+ const DRAWINGML_NS: &str = "http://schemas.openxmlformats.org/drawingml/2006/main";
150
+
151
+ for node in doc.descendants() {
152
+ if node.has_tag_name((DRAWINGML_NS, "t"))
153
+ && let Some(text) = node.text()
154
+ {
155
+ text_parts.push(text);
156
+ }
157
+ }
158
+
159
+ Ok(text_parts.join(" "))
160
+ }