kreuzberg 4.0.0.rc2 → 4.0.0

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 (446) hide show
  1. checksums.yaml +4 -4
  2. data/.gitignore +14 -14
  3. data/.rspec +3 -3
  4. data/.rubocop.yaml +1 -1
  5. data/.rubocop.yml +543 -538
  6. data/Gemfile +8 -8
  7. data/Gemfile.lock +194 -6
  8. data/README.md +396 -426
  9. data/Rakefile +34 -25
  10. data/Steepfile +51 -47
  11. data/examples/async_patterns.rb +283 -341
  12. data/ext/kreuzberg_rb/extconf.rb +65 -45
  13. data/ext/kreuzberg_rb/native/.cargo/config.toml +23 -0
  14. data/ext/kreuzberg_rb/native/Cargo.lock +7619 -6535
  15. data/ext/kreuzberg_rb/native/Cargo.toml +75 -44
  16. data/ext/kreuzberg_rb/native/README.md +425 -425
  17. data/ext/kreuzberg_rb/native/build.rs +15 -15
  18. data/ext/kreuzberg_rb/native/include/ieeefp.h +11 -11
  19. data/ext/kreuzberg_rb/native/include/msvc_compat/strings.h +14 -14
  20. data/ext/kreuzberg_rb/native/include/strings.h +20 -20
  21. data/ext/kreuzberg_rb/native/include/unistd.h +47 -47
  22. data/ext/kreuzberg_rb/native/src/lib.rs +3802 -2998
  23. data/extconf.rb +60 -28
  24. data/kreuzberg.gemspec +199 -148
  25. data/lib/kreuzberg/api_proxy.rb +126 -142
  26. data/lib/kreuzberg/cache_api.rb +67 -46
  27. data/lib/kreuzberg/cli.rb +47 -55
  28. data/lib/kreuzberg/cli_proxy.rb +117 -127
  29. data/lib/kreuzberg/config.rb +936 -691
  30. data/lib/kreuzberg/error_context.rb +136 -32
  31. data/lib/kreuzberg/errors.rb +116 -118
  32. data/lib/kreuzberg/extraction_api.rb +313 -85
  33. data/lib/kreuzberg/mcp_proxy.rb +177 -186
  34. data/lib/kreuzberg/ocr_backend_protocol.rb +40 -113
  35. data/lib/kreuzberg/post_processor_protocol.rb +15 -86
  36. data/lib/kreuzberg/result.rb +334 -216
  37. data/lib/kreuzberg/setup_lib_path.rb +99 -80
  38. data/lib/kreuzberg/types.rb +170 -0
  39. data/lib/kreuzberg/validator_protocol.rb +16 -89
  40. data/lib/kreuzberg/version.rb +5 -5
  41. data/lib/kreuzberg.rb +96 -103
  42. data/lib/libpdfium.so +0 -0
  43. data/sig/kreuzberg/internal.rbs +184 -184
  44. data/sig/kreuzberg.rbs +561 -520
  45. data/spec/binding/async_operations_spec.rb +473 -0
  46. data/spec/binding/batch_operations_spec.rb +595 -0
  47. data/spec/binding/batch_spec.rb +359 -0
  48. data/spec/binding/cache_spec.rb +227 -227
  49. data/spec/binding/cli_proxy_spec.rb +85 -85
  50. data/spec/binding/cli_spec.rb +55 -55
  51. data/spec/binding/config_result_spec.rb +377 -0
  52. data/spec/binding/config_spec.rb +419 -345
  53. data/spec/binding/config_validation_spec.rb +377 -283
  54. data/spec/binding/embeddings_spec.rb +816 -0
  55. data/spec/binding/error_handling_spec.rb +399 -213
  56. data/spec/binding/error_recovery_spec.rb +488 -0
  57. data/spec/binding/errors_spec.rb +66 -66
  58. data/spec/binding/font_config_spec.rb +220 -0
  59. data/spec/binding/images_spec.rb +738 -0
  60. data/spec/binding/keywords_extraction_spec.rb +600 -0
  61. data/spec/binding/metadata_types_spec.rb +1228 -0
  62. data/spec/binding/pages_extraction_spec.rb +471 -0
  63. data/spec/binding/plugins/ocr_backend_spec.rb +307 -307
  64. data/spec/binding/plugins/postprocessor_spec.rb +269 -269
  65. data/spec/binding/plugins/validator_spec.rb +273 -274
  66. data/spec/binding/tables_spec.rb +641 -0
  67. data/spec/fixtures/config.toml +38 -39
  68. data/spec/fixtures/config.yaml +41 -41
  69. data/spec/fixtures/invalid_config.toml +3 -4
  70. data/spec/smoke/package_spec.rb +177 -178
  71. data/spec/spec_helper.rb +40 -42
  72. data/spec/unit/config/chunking_config_spec.rb +213 -0
  73. data/spec/unit/config/embedding_config_spec.rb +343 -0
  74. data/spec/unit/config/extraction_config_spec.rb +438 -0
  75. data/spec/unit/config/font_config_spec.rb +285 -0
  76. data/spec/unit/config/hierarchy_config_spec.rb +314 -0
  77. data/spec/unit/config/image_extraction_config_spec.rb +209 -0
  78. data/spec/unit/config/image_preprocessing_config_spec.rb +249 -0
  79. data/spec/unit/config/keyword_config_spec.rb +229 -0
  80. data/spec/unit/config/language_detection_config_spec.rb +258 -0
  81. data/spec/unit/config/ocr_config_spec.rb +171 -0
  82. data/spec/unit/config/page_config_spec.rb +221 -0
  83. data/spec/unit/config/pdf_config_spec.rb +267 -0
  84. data/spec/unit/config/postprocessor_config_spec.rb +290 -0
  85. data/spec/unit/config/tesseract_config_spec.rb +181 -0
  86. data/spec/unit/config/token_reduction_config_spec.rb +251 -0
  87. data/test/metadata_types_test.rb +959 -0
  88. data/vendor/Cargo.toml +61 -0
  89. data/vendor/kreuzberg/Cargo.toml +259 -204
  90. data/vendor/kreuzberg/README.md +263 -175
  91. data/vendor/kreuzberg/build.rs +782 -474
  92. data/vendor/kreuzberg/examples/bench_fixes.rs +71 -0
  93. data/vendor/kreuzberg/examples/test_pdfium_fork.rs +62 -0
  94. data/vendor/kreuzberg/src/api/error.rs +81 -81
  95. data/vendor/kreuzberg/src/api/handlers.rs +320 -199
  96. data/vendor/kreuzberg/src/api/mod.rs +94 -79
  97. data/vendor/kreuzberg/src/api/server.rs +518 -353
  98. data/vendor/kreuzberg/src/api/types.rs +206 -170
  99. data/vendor/kreuzberg/src/cache/mod.rs +1167 -1167
  100. data/vendor/kreuzberg/src/chunking/mod.rs +2303 -677
  101. data/vendor/kreuzberg/src/chunking/processor.rs +219 -0
  102. data/vendor/kreuzberg/src/core/batch_mode.rs +95 -95
  103. data/vendor/kreuzberg/src/core/batch_optimizations.rs +385 -0
  104. data/vendor/kreuzberg/src/core/config.rs +1914 -1032
  105. data/vendor/kreuzberg/src/core/config_validation.rs +949 -0
  106. data/vendor/kreuzberg/src/core/extractor.rs +1200 -1024
  107. data/vendor/kreuzberg/src/core/formats.rs +235 -0
  108. data/vendor/kreuzberg/src/core/io.rs +329 -329
  109. data/vendor/kreuzberg/src/core/mime.rs +605 -605
  110. data/vendor/kreuzberg/src/core/mod.rs +61 -45
  111. data/vendor/kreuzberg/src/core/pipeline.rs +1223 -984
  112. data/vendor/kreuzberg/src/core/server_config.rs +1220 -0
  113. data/vendor/kreuzberg/src/embeddings.rs +471 -432
  114. data/vendor/kreuzberg/src/error.rs +431 -431
  115. data/vendor/kreuzberg/src/extraction/archive.rs +959 -954
  116. data/vendor/kreuzberg/src/extraction/capacity.rs +263 -0
  117. data/vendor/kreuzberg/src/extraction/docx.rs +404 -40
  118. data/vendor/kreuzberg/src/extraction/email.rs +855 -854
  119. data/vendor/kreuzberg/src/extraction/excel.rs +697 -688
  120. data/vendor/kreuzberg/src/extraction/html.rs +1830 -553
  121. data/vendor/kreuzberg/src/extraction/image.rs +492 -368
  122. data/vendor/kreuzberg/src/extraction/libreoffice.rs +574 -563
  123. data/vendor/kreuzberg/src/extraction/markdown.rs +216 -213
  124. data/vendor/kreuzberg/src/extraction/mod.rs +93 -81
  125. data/vendor/kreuzberg/src/extraction/office_metadata/app_properties.rs +398 -398
  126. data/vendor/kreuzberg/src/extraction/office_metadata/core_properties.rs +247 -247
  127. data/vendor/kreuzberg/src/extraction/office_metadata/custom_properties.rs +240 -240
  128. data/vendor/kreuzberg/src/extraction/office_metadata/mod.rs +130 -130
  129. data/vendor/kreuzberg/src/extraction/office_metadata/odt_properties.rs +284 -287
  130. data/vendor/kreuzberg/src/extraction/pptx.rs +3102 -3000
  131. data/vendor/kreuzberg/src/extraction/structured.rs +491 -490
  132. data/vendor/kreuzberg/src/extraction/table.rs +329 -328
  133. data/vendor/kreuzberg/src/extraction/text.rs +277 -269
  134. data/vendor/kreuzberg/src/extraction/xml.rs +333 -333
  135. data/vendor/kreuzberg/src/extractors/archive.rs +447 -446
  136. data/vendor/kreuzberg/src/extractors/bibtex.rs +470 -469
  137. data/vendor/kreuzberg/src/extractors/docbook.rs +504 -502
  138. data/vendor/kreuzberg/src/extractors/docx.rs +400 -367
  139. data/vendor/kreuzberg/src/extractors/email.rs +157 -143
  140. data/vendor/kreuzberg/src/extractors/epub.rs +696 -707
  141. data/vendor/kreuzberg/src/extractors/excel.rs +385 -343
  142. data/vendor/kreuzberg/src/extractors/fictionbook.rs +492 -491
  143. data/vendor/kreuzberg/src/extractors/html.rs +419 -393
  144. data/vendor/kreuzberg/src/extractors/image.rs +219 -198
  145. data/vendor/kreuzberg/src/extractors/jats.rs +1054 -1051
  146. data/vendor/kreuzberg/src/extractors/jupyter.rs +368 -367
  147. data/vendor/kreuzberg/src/extractors/latex.rs +653 -652
  148. data/vendor/kreuzberg/src/extractors/markdown.rs +701 -700
  149. data/vendor/kreuzberg/src/extractors/mod.rs +429 -365
  150. data/vendor/kreuzberg/src/extractors/odt.rs +628 -628
  151. data/vendor/kreuzberg/src/extractors/opml.rs +635 -634
  152. data/vendor/kreuzberg/src/extractors/orgmode.rs +529 -528
  153. data/vendor/kreuzberg/src/extractors/pdf.rs +761 -493
  154. data/vendor/kreuzberg/src/extractors/pptx.rs +279 -248
  155. data/vendor/kreuzberg/src/extractors/rst.rs +577 -576
  156. data/vendor/kreuzberg/src/extractors/rtf.rs +809 -810
  157. data/vendor/kreuzberg/src/extractors/security.rs +484 -484
  158. data/vendor/kreuzberg/src/extractors/security_tests.rs +367 -367
  159. data/vendor/kreuzberg/src/extractors/structured.rs +142 -140
  160. data/vendor/kreuzberg/src/extractors/text.rs +265 -260
  161. data/vendor/kreuzberg/src/extractors/typst.rs +651 -650
  162. data/vendor/kreuzberg/src/extractors/xml.rs +147 -135
  163. data/vendor/kreuzberg/src/image/dpi.rs +164 -164
  164. data/vendor/kreuzberg/src/image/mod.rs +6 -6
  165. data/vendor/kreuzberg/src/image/preprocessing.rs +417 -417
  166. data/vendor/kreuzberg/src/image/resize.rs +89 -89
  167. data/vendor/kreuzberg/src/keywords/config.rs +154 -154
  168. data/vendor/kreuzberg/src/keywords/mod.rs +237 -237
  169. data/vendor/kreuzberg/src/keywords/processor.rs +275 -267
  170. data/vendor/kreuzberg/src/keywords/rake.rs +293 -293
  171. data/vendor/kreuzberg/src/keywords/types.rs +68 -68
  172. data/vendor/kreuzberg/src/keywords/yake.rs +163 -163
  173. data/vendor/kreuzberg/src/language_detection/mod.rs +985 -942
  174. data/vendor/kreuzberg/src/language_detection/processor.rs +218 -0
  175. data/vendor/kreuzberg/src/lib.rs +114 -105
  176. data/vendor/kreuzberg/src/mcp/mod.rs +35 -32
  177. data/vendor/kreuzberg/src/mcp/server.rs +2090 -1968
  178. data/vendor/kreuzberg/src/ocr/cache.rs +469 -469
  179. data/vendor/kreuzberg/src/ocr/error.rs +37 -37
  180. data/vendor/kreuzberg/src/ocr/hocr.rs +216 -216
  181. data/vendor/kreuzberg/src/ocr/language_registry.rs +520 -0
  182. data/vendor/kreuzberg/src/ocr/mod.rs +60 -58
  183. data/vendor/kreuzberg/src/ocr/processor.rs +858 -863
  184. data/vendor/kreuzberg/src/ocr/table/mod.rs +4 -4
  185. data/vendor/kreuzberg/src/ocr/table/tsv_parser.rs +144 -144
  186. data/vendor/kreuzberg/src/ocr/tesseract_backend.rs +456 -450
  187. data/vendor/kreuzberg/src/ocr/types.rs +393 -393
  188. data/vendor/kreuzberg/src/ocr/utils.rs +47 -47
  189. data/vendor/kreuzberg/src/ocr/validation.rs +206 -206
  190. data/vendor/kreuzberg/src/panic_context.rs +154 -154
  191. data/vendor/kreuzberg/src/pdf/bindings.rs +306 -0
  192. data/vendor/kreuzberg/src/pdf/bundled.rs +408 -0
  193. data/vendor/kreuzberg/src/pdf/error.rs +214 -122
  194. data/vendor/kreuzberg/src/pdf/fonts.rs +358 -0
  195. data/vendor/kreuzberg/src/pdf/hierarchy.rs +903 -0
  196. data/vendor/kreuzberg/src/pdf/images.rs +139 -139
  197. data/vendor/kreuzberg/src/pdf/metadata.rs +509 -346
  198. data/vendor/kreuzberg/src/pdf/mod.rs +81 -50
  199. data/vendor/kreuzberg/src/pdf/rendering.rs +369 -369
  200. data/vendor/kreuzberg/src/pdf/table.rs +417 -393
  201. data/vendor/kreuzberg/src/pdf/text.rs +553 -158
  202. data/vendor/kreuzberg/src/plugins/extractor.rs +1042 -1013
  203. data/vendor/kreuzberg/src/plugins/mod.rs +212 -209
  204. data/vendor/kreuzberg/src/plugins/ocr.rs +637 -620
  205. data/vendor/kreuzberg/src/plugins/processor.rs +650 -642
  206. data/vendor/kreuzberg/src/plugins/registry.rs +1339 -1337
  207. data/vendor/kreuzberg/src/plugins/traits.rs +258 -258
  208. data/vendor/kreuzberg/src/plugins/validator.rs +967 -956
  209. data/vendor/kreuzberg/src/stopwords/mod.rs +1470 -1470
  210. data/vendor/kreuzberg/src/text/mod.rs +27 -19
  211. data/vendor/kreuzberg/src/text/quality.rs +710 -697
  212. data/vendor/kreuzberg/src/text/quality_processor.rs +231 -0
  213. data/vendor/kreuzberg/src/text/string_utils.rs +229 -217
  214. data/vendor/kreuzberg/src/text/token_reduction/cjk_utils.rs +164 -164
  215. data/vendor/kreuzberg/src/text/token_reduction/config.rs +100 -100
  216. data/vendor/kreuzberg/src/text/token_reduction/core.rs +832 -796
  217. data/vendor/kreuzberg/src/text/token_reduction/filters.rs +923 -902
  218. data/vendor/kreuzberg/src/text/token_reduction/mod.rs +160 -160
  219. data/vendor/kreuzberg/src/text/token_reduction/semantic.rs +619 -619
  220. data/vendor/kreuzberg/src/text/token_reduction/simd_text.rs +148 -147
  221. data/vendor/kreuzberg/src/text/utf8_validation.rs +193 -0
  222. data/vendor/kreuzberg/src/types.rs +1713 -903
  223. data/vendor/kreuzberg/src/utils/mod.rs +31 -17
  224. data/vendor/kreuzberg/src/utils/pool.rs +503 -0
  225. data/vendor/kreuzberg/src/utils/pool_sizing.rs +364 -0
  226. data/vendor/kreuzberg/src/utils/quality.rs +968 -959
  227. data/vendor/kreuzberg/src/utils/string_pool.rs +761 -0
  228. data/vendor/kreuzberg/src/utils/string_utils.rs +381 -381
  229. data/vendor/kreuzberg/stopwords/af_stopwords.json +53 -53
  230. data/vendor/kreuzberg/stopwords/ar_stopwords.json +482 -482
  231. data/vendor/kreuzberg/stopwords/bg_stopwords.json +261 -261
  232. data/vendor/kreuzberg/stopwords/bn_stopwords.json +400 -400
  233. data/vendor/kreuzberg/stopwords/br_stopwords.json +1205 -1205
  234. data/vendor/kreuzberg/stopwords/ca_stopwords.json +280 -280
  235. data/vendor/kreuzberg/stopwords/cs_stopwords.json +425 -425
  236. data/vendor/kreuzberg/stopwords/da_stopwords.json +172 -172
  237. data/vendor/kreuzberg/stopwords/de_stopwords.json +622 -622
  238. data/vendor/kreuzberg/stopwords/el_stopwords.json +849 -849
  239. data/vendor/kreuzberg/stopwords/en_stopwords.json +1300 -1300
  240. data/vendor/kreuzberg/stopwords/eo_stopwords.json +175 -175
  241. data/vendor/kreuzberg/stopwords/es_stopwords.json +734 -734
  242. data/vendor/kreuzberg/stopwords/et_stopwords.json +37 -37
  243. data/vendor/kreuzberg/stopwords/eu_stopwords.json +100 -100
  244. data/vendor/kreuzberg/stopwords/fa_stopwords.json +801 -801
  245. data/vendor/kreuzberg/stopwords/fi_stopwords.json +849 -849
  246. data/vendor/kreuzberg/stopwords/fr_stopwords.json +693 -693
  247. data/vendor/kreuzberg/stopwords/ga_stopwords.json +111 -111
  248. data/vendor/kreuzberg/stopwords/gl_stopwords.json +162 -162
  249. data/vendor/kreuzberg/stopwords/gu_stopwords.json +226 -226
  250. data/vendor/kreuzberg/stopwords/ha_stopwords.json +41 -41
  251. data/vendor/kreuzberg/stopwords/he_stopwords.json +196 -196
  252. data/vendor/kreuzberg/stopwords/hi_stopwords.json +227 -227
  253. data/vendor/kreuzberg/stopwords/hr_stopwords.json +181 -181
  254. data/vendor/kreuzberg/stopwords/hu_stopwords.json +791 -791
  255. data/vendor/kreuzberg/stopwords/hy_stopwords.json +47 -47
  256. data/vendor/kreuzberg/stopwords/id_stopwords.json +760 -760
  257. data/vendor/kreuzberg/stopwords/it_stopwords.json +634 -634
  258. data/vendor/kreuzberg/stopwords/ja_stopwords.json +136 -136
  259. data/vendor/kreuzberg/stopwords/kn_stopwords.json +84 -84
  260. data/vendor/kreuzberg/stopwords/ko_stopwords.json +681 -681
  261. data/vendor/kreuzberg/stopwords/ku_stopwords.json +64 -64
  262. data/vendor/kreuzberg/stopwords/la_stopwords.json +51 -51
  263. data/vendor/kreuzberg/stopwords/lt_stopwords.json +476 -476
  264. data/vendor/kreuzberg/stopwords/lv_stopwords.json +163 -163
  265. data/vendor/kreuzberg/stopwords/ml_stopwords.json +1 -1
  266. data/vendor/kreuzberg/stopwords/mr_stopwords.json +101 -101
  267. data/vendor/kreuzberg/stopwords/ms_stopwords.json +477 -477
  268. data/vendor/kreuzberg/stopwords/ne_stopwords.json +490 -490
  269. data/vendor/kreuzberg/stopwords/nl_stopwords.json +415 -415
  270. data/vendor/kreuzberg/stopwords/no_stopwords.json +223 -223
  271. data/vendor/kreuzberg/stopwords/pl_stopwords.json +331 -331
  272. data/vendor/kreuzberg/stopwords/pt_stopwords.json +562 -562
  273. data/vendor/kreuzberg/stopwords/ro_stopwords.json +436 -436
  274. data/vendor/kreuzberg/stopwords/ru_stopwords.json +561 -561
  275. data/vendor/kreuzberg/stopwords/si_stopwords.json +193 -193
  276. data/vendor/kreuzberg/stopwords/sk_stopwords.json +420 -420
  277. data/vendor/kreuzberg/stopwords/sl_stopwords.json +448 -448
  278. data/vendor/kreuzberg/stopwords/so_stopwords.json +32 -32
  279. data/vendor/kreuzberg/stopwords/st_stopwords.json +33 -33
  280. data/vendor/kreuzberg/stopwords/sv_stopwords.json +420 -420
  281. data/vendor/kreuzberg/stopwords/sw_stopwords.json +76 -76
  282. data/vendor/kreuzberg/stopwords/ta_stopwords.json +129 -129
  283. data/vendor/kreuzberg/stopwords/te_stopwords.json +54 -54
  284. data/vendor/kreuzberg/stopwords/th_stopwords.json +118 -118
  285. data/vendor/kreuzberg/stopwords/tl_stopwords.json +149 -149
  286. data/vendor/kreuzberg/stopwords/tr_stopwords.json +506 -506
  287. data/vendor/kreuzberg/stopwords/uk_stopwords.json +75 -75
  288. data/vendor/kreuzberg/stopwords/ur_stopwords.json +519 -519
  289. data/vendor/kreuzberg/stopwords/vi_stopwords.json +647 -647
  290. data/vendor/kreuzberg/stopwords/yo_stopwords.json +62 -62
  291. data/vendor/kreuzberg/stopwords/zh_stopwords.json +796 -796
  292. data/vendor/kreuzberg/stopwords/zu_stopwords.json +31 -31
  293. data/vendor/kreuzberg/tests/api_embed.rs +360 -0
  294. data/vendor/kreuzberg/tests/api_extract_multipart.rs +52 -52
  295. data/vendor/kreuzberg/tests/api_large_pdf_extraction.rs +471 -0
  296. data/vendor/kreuzberg/tests/api_large_pdf_extraction_diagnostics.rs +289 -0
  297. data/vendor/kreuzberg/tests/api_tests.rs +1472 -966
  298. data/vendor/kreuzberg/tests/archive_integration.rs +545 -543
  299. data/vendor/kreuzberg/tests/batch_orchestration.rs +587 -556
  300. data/vendor/kreuzberg/tests/batch_pooling_benchmark.rs +154 -0
  301. data/vendor/kreuzberg/tests/batch_processing.rs +328 -316
  302. data/vendor/kreuzberg/tests/bibtex_parity_test.rs +421 -421
  303. data/vendor/kreuzberg/tests/concurrency_stress.rs +541 -525
  304. data/vendor/kreuzberg/tests/config_features.rs +612 -598
  305. data/vendor/kreuzberg/tests/config_integration_test.rs +753 -0
  306. data/vendor/kreuzberg/tests/config_loading_tests.rs +416 -415
  307. data/vendor/kreuzberg/tests/core_integration.rs +519 -510
  308. data/vendor/kreuzberg/tests/csv_integration.rs +414 -414
  309. data/vendor/kreuzberg/tests/data/hierarchy_ground_truth.json +294 -0
  310. data/vendor/kreuzberg/tests/docbook_extractor_tests.rs +500 -498
  311. data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +122 -122
  312. data/vendor/kreuzberg/tests/docx_vs_pandoc_comparison.rs +370 -370
  313. data/vendor/kreuzberg/tests/email_integration.rs +327 -325
  314. data/vendor/kreuzberg/tests/epub_native_extractor_tests.rs +275 -275
  315. data/vendor/kreuzberg/tests/error_handling.rs +402 -393
  316. data/vendor/kreuzberg/tests/fictionbook_extractor_tests.rs +228 -228
  317. data/vendor/kreuzberg/tests/format_integration.rs +165 -159
  318. data/vendor/kreuzberg/tests/helpers/mod.rs +202 -142
  319. data/vendor/kreuzberg/tests/html_table_test.rs +551 -551
  320. data/vendor/kreuzberg/tests/image_integration.rs +255 -253
  321. data/vendor/kreuzberg/tests/instrumentation_test.rs +139 -139
  322. data/vendor/kreuzberg/tests/jats_extractor_tests.rs +639 -639
  323. data/vendor/kreuzberg/tests/jupyter_extractor_tests.rs +704 -704
  324. data/vendor/kreuzberg/tests/keywords_integration.rs +479 -479
  325. data/vendor/kreuzberg/tests/keywords_quality.rs +509 -509
  326. data/vendor/kreuzberg/tests/latex_extractor_tests.rs +496 -496
  327. data/vendor/kreuzberg/tests/markdown_extractor_tests.rs +490 -490
  328. data/vendor/kreuzberg/tests/mime_detection.rs +429 -428
  329. data/vendor/kreuzberg/tests/ocr_configuration.rs +514 -510
  330. data/vendor/kreuzberg/tests/ocr_errors.rs +698 -676
  331. data/vendor/kreuzberg/tests/ocr_language_registry.rs +191 -0
  332. data/vendor/kreuzberg/tests/ocr_quality.rs +629 -627
  333. data/vendor/kreuzberg/tests/ocr_stress.rs +469 -469
  334. data/vendor/kreuzberg/tests/odt_extractor_tests.rs +674 -695
  335. data/vendor/kreuzberg/tests/opml_extractor_tests.rs +616 -616
  336. data/vendor/kreuzberg/tests/orgmode_extractor_tests.rs +822 -822
  337. data/vendor/kreuzberg/tests/page_markers.rs +297 -0
  338. data/vendor/kreuzberg/tests/pdf_hierarchy_detection.rs +301 -0
  339. data/vendor/kreuzberg/tests/pdf_hierarchy_quality.rs +589 -0
  340. data/vendor/kreuzberg/tests/pdf_integration.rs +45 -43
  341. data/vendor/kreuzberg/tests/pdf_ocr_triggering.rs +301 -0
  342. data/vendor/kreuzberg/tests/pdf_text_merging.rs +475 -0
  343. data/vendor/kreuzberg/tests/pdfium_linking.rs +340 -0
  344. data/vendor/kreuzberg/tests/pipeline_integration.rs +1446 -1411
  345. data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +776 -771
  346. data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +577 -560
  347. data/vendor/kreuzberg/tests/plugin_system.rs +927 -921
  348. data/vendor/kreuzberg/tests/plugin_validator_test.rs +783 -783
  349. data/vendor/kreuzberg/tests/registry_integration_tests.rs +587 -586
  350. data/vendor/kreuzberg/tests/rst_extractor_tests.rs +694 -692
  351. data/vendor/kreuzberg/tests/rtf_extractor_tests.rs +775 -776
  352. data/vendor/kreuzberg/tests/security_validation.rs +416 -415
  353. data/vendor/kreuzberg/tests/stopwords_integration_test.rs +888 -888
  354. data/vendor/kreuzberg/tests/test_fastembed.rs +631 -609
  355. data/vendor/kreuzberg/tests/typst_behavioral_tests.rs +1260 -1259
  356. data/vendor/kreuzberg/tests/typst_extractor_tests.rs +648 -647
  357. data/vendor/kreuzberg/tests/xlsx_metadata_extraction_test.rs +87 -87
  358. data/vendor/kreuzberg-ffi/Cargo.toml +67 -0
  359. data/vendor/kreuzberg-ffi/README.md +851 -0
  360. data/vendor/kreuzberg-ffi/benches/result_view_benchmark.rs +227 -0
  361. data/vendor/kreuzberg-ffi/build.rs +168 -0
  362. data/vendor/kreuzberg-ffi/cbindgen.toml +37 -0
  363. data/vendor/kreuzberg-ffi/kreuzberg-ffi.pc.in +12 -0
  364. data/vendor/kreuzberg-ffi/kreuzberg.h +3012 -0
  365. data/vendor/kreuzberg-ffi/src/batch_streaming.rs +588 -0
  366. data/vendor/kreuzberg-ffi/src/config.rs +1341 -0
  367. data/vendor/kreuzberg-ffi/src/error.rs +901 -0
  368. data/vendor/kreuzberg-ffi/src/extraction.rs +555 -0
  369. data/vendor/kreuzberg-ffi/src/helpers.rs +879 -0
  370. data/vendor/kreuzberg-ffi/src/lib.rs +977 -0
  371. data/vendor/kreuzberg-ffi/src/memory.rs +493 -0
  372. data/vendor/kreuzberg-ffi/src/mime.rs +329 -0
  373. data/vendor/kreuzberg-ffi/src/panic_shield.rs +265 -0
  374. data/vendor/kreuzberg-ffi/src/plugins/document_extractor.rs +442 -0
  375. data/vendor/kreuzberg-ffi/src/plugins/mod.rs +14 -0
  376. data/vendor/kreuzberg-ffi/src/plugins/ocr_backend.rs +628 -0
  377. data/vendor/kreuzberg-ffi/src/plugins/post_processor.rs +438 -0
  378. data/vendor/kreuzberg-ffi/src/plugins/validator.rs +329 -0
  379. data/vendor/kreuzberg-ffi/src/result.rs +510 -0
  380. data/vendor/kreuzberg-ffi/src/result_pool.rs +639 -0
  381. data/vendor/kreuzberg-ffi/src/result_view.rs +773 -0
  382. data/vendor/kreuzberg-ffi/src/string_intern.rs +568 -0
  383. data/vendor/kreuzberg-ffi/src/types.rs +363 -0
  384. data/vendor/kreuzberg-ffi/src/util.rs +210 -0
  385. data/vendor/kreuzberg-ffi/src/validation.rs +848 -0
  386. data/vendor/kreuzberg-ffi/tests.disabled/README.md +48 -0
  387. data/vendor/kreuzberg-ffi/tests.disabled/config_loading_tests.rs +299 -0
  388. data/vendor/kreuzberg-ffi/tests.disabled/config_tests.rs +346 -0
  389. data/vendor/kreuzberg-ffi/tests.disabled/extractor_tests.rs +232 -0
  390. data/vendor/kreuzberg-ffi/tests.disabled/plugin_registration_tests.rs +470 -0
  391. data/vendor/kreuzberg-tesseract/.commitlintrc.json +13 -0
  392. data/vendor/kreuzberg-tesseract/.crate-ignore +2 -0
  393. data/vendor/kreuzberg-tesseract/Cargo.lock +2933 -0
  394. data/vendor/kreuzberg-tesseract/Cargo.toml +57 -0
  395. data/vendor/{rb-sys/LICENSE-MIT → kreuzberg-tesseract/LICENSE} +22 -21
  396. data/vendor/kreuzberg-tesseract/README.md +399 -0
  397. data/vendor/kreuzberg-tesseract/build.rs +1127 -0
  398. data/vendor/kreuzberg-tesseract/patches/README.md +71 -0
  399. data/vendor/kreuzberg-tesseract/patches/tesseract.diff +199 -0
  400. data/vendor/kreuzberg-tesseract/src/api.rs +1371 -0
  401. data/vendor/kreuzberg-tesseract/src/choice_iterator.rs +77 -0
  402. data/vendor/kreuzberg-tesseract/src/enums.rs +297 -0
  403. data/vendor/kreuzberg-tesseract/src/error.rs +81 -0
  404. data/vendor/kreuzberg-tesseract/src/lib.rs +145 -0
  405. data/vendor/kreuzberg-tesseract/src/monitor.rs +57 -0
  406. data/vendor/kreuzberg-tesseract/src/mutable_iterator.rs +197 -0
  407. data/vendor/kreuzberg-tesseract/src/page_iterator.rs +253 -0
  408. data/vendor/kreuzberg-tesseract/src/result_iterator.rs +286 -0
  409. data/vendor/kreuzberg-tesseract/src/result_renderer.rs +183 -0
  410. data/vendor/kreuzberg-tesseract/tests/integration_test.rs +211 -0
  411. metadata +196 -45
  412. data/vendor/kreuzberg/benches/otel_overhead.rs +0 -48
  413. data/vendor/kreuzberg/src/extractors/fictionbook.rs.backup2 +0 -738
  414. data/vendor/rb-sys/.cargo-ok +0 -1
  415. data/vendor/rb-sys/.cargo_vcs_info.json +0 -6
  416. data/vendor/rb-sys/Cargo.lock +0 -393
  417. data/vendor/rb-sys/Cargo.toml +0 -70
  418. data/vendor/rb-sys/Cargo.toml.orig +0 -57
  419. data/vendor/rb-sys/LICENSE-APACHE +0 -190
  420. data/vendor/rb-sys/bin/release.sh +0 -21
  421. data/vendor/rb-sys/build/features.rs +0 -108
  422. data/vendor/rb-sys/build/main.rs +0 -246
  423. data/vendor/rb-sys/build/stable_api_config.rs +0 -153
  424. data/vendor/rb-sys/build/version.rs +0 -48
  425. data/vendor/rb-sys/readme.md +0 -36
  426. data/vendor/rb-sys/src/bindings.rs +0 -21
  427. data/vendor/rb-sys/src/hidden.rs +0 -11
  428. data/vendor/rb-sys/src/lib.rs +0 -34
  429. data/vendor/rb-sys/src/macros.rs +0 -371
  430. data/vendor/rb-sys/src/memory.rs +0 -53
  431. data/vendor/rb-sys/src/ruby_abi_version.rs +0 -38
  432. data/vendor/rb-sys/src/special_consts.rs +0 -31
  433. data/vendor/rb-sys/src/stable_api/compiled.c +0 -179
  434. data/vendor/rb-sys/src/stable_api/compiled.rs +0 -257
  435. data/vendor/rb-sys/src/stable_api/ruby_2_6.rs +0 -316
  436. data/vendor/rb-sys/src/stable_api/ruby_2_7.rs +0 -316
  437. data/vendor/rb-sys/src/stable_api/ruby_3_0.rs +0 -324
  438. data/vendor/rb-sys/src/stable_api/ruby_3_1.rs +0 -317
  439. data/vendor/rb-sys/src/stable_api/ruby_3_2.rs +0 -315
  440. data/vendor/rb-sys/src/stable_api/ruby_3_3.rs +0 -326
  441. data/vendor/rb-sys/src/stable_api/ruby_3_4.rs +0 -327
  442. data/vendor/rb-sys/src/stable_api.rs +0 -261
  443. data/vendor/rb-sys/src/symbol.rs +0 -31
  444. data/vendor/rb-sys/src/tracking_allocator.rs +0 -332
  445. data/vendor/rb-sys/src/utils.rs +0 -89
  446. data/vendor/rb-sys/src/value_type.rs +0 -7
@@ -0,0 +1,258 @@
1
+ # frozen_string_literal: true
2
+
3
+ RSpec.describe Kreuzberg::Config::LanguageDetection do
4
+ describe '#initialize' do
5
+ it 'creates config with default values' do
6
+ config = described_class.new
7
+
8
+ expect(config.enabled).to be false
9
+ expect(config.min_confidence).to eq 0.5
10
+ expect(config.detect_multiple).to be false
11
+ end
12
+
13
+ it 'creates config with custom values' do
14
+ config = described_class.new(
15
+ enabled: true,
16
+ min_confidence: 0.9,
17
+ detect_multiple: true
18
+ )
19
+
20
+ expect(config.enabled).to be true
21
+ expect(config.min_confidence).to eq 0.9
22
+ expect(config.detect_multiple).to be true
23
+ end
24
+
25
+ it 'converts enabled to boolean' do
26
+ config = described_class.new(enabled: 1)
27
+
28
+ expect(config.enabled).to be true
29
+ expect(config.enabled).to be_a TrueClass
30
+ end
31
+
32
+ it 'converts min_confidence to float' do
33
+ config = described_class.new(min_confidence: '0.75')
34
+
35
+ expect(config.min_confidence).to eq 0.75
36
+ expect(config.min_confidence).to be_a Float
37
+ end
38
+
39
+ it 'converts detect_multiple to boolean' do
40
+ config = described_class.new(detect_multiple: 'yes')
41
+
42
+ expect(config.detect_multiple).to be true
43
+ end
44
+ end
45
+
46
+ describe '#to_h' do
47
+ it 'serializes to hash with all values' do
48
+ config = described_class.new(
49
+ enabled: true,
50
+ min_confidence: 0.8,
51
+ detect_multiple: true
52
+ )
53
+ hash = config.to_h
54
+
55
+ expect(hash).to be_a Hash
56
+ expect(hash[:enabled]).to be true
57
+ expect(hash[:min_confidence]).to eq 0.8
58
+ expect(hash[:detect_multiple]).to be true
59
+ end
60
+
61
+ it 'always includes all keys in hash' do
62
+ config = described_class.new
63
+ hash = config.to_h
64
+
65
+ expect(hash.keys).to contain_exactly(
66
+ :enabled,
67
+ :min_confidence,
68
+ :detect_multiple
69
+ )
70
+ end
71
+ end
72
+
73
+ describe 'validation' do
74
+ it 'accepts confidence value of 0.5' do
75
+ expect do
76
+ described_class.new(min_confidence: 0.5)
77
+ end.not_to raise_error
78
+ end
79
+
80
+ it 'accepts confidence value of 0.0' do
81
+ expect do
82
+ described_class.new(min_confidence: 0.0)
83
+ end.not_to raise_error
84
+ end
85
+
86
+ it 'accepts confidence value of 1.0' do
87
+ expect do
88
+ described_class.new(min_confidence: 1.0)
89
+ end.not_to raise_error
90
+ end
91
+
92
+ it 'accepts boolean enabled' do
93
+ expect do
94
+ described_class.new(enabled: true)
95
+ end.not_to raise_error
96
+ end
97
+ end
98
+
99
+ describe 'keyword arguments' do
100
+ it 'accepts all keyword arguments' do
101
+ config = described_class.new(
102
+ enabled: true,
103
+ min_confidence: 0.85,
104
+ detect_multiple: true
105
+ )
106
+
107
+ expect(config.enabled).to be true
108
+ expect(config.min_confidence).to eq 0.85
109
+ expect(config.detect_multiple).to be true
110
+ end
111
+ end
112
+
113
+ describe 'equality' do
114
+ it 'compares configs by value' do
115
+ config1 = described_class.new(
116
+ enabled: true,
117
+ min_confidence: 0.8
118
+ )
119
+ config2 = described_class.new(
120
+ enabled: true,
121
+ min_confidence: 0.8
122
+ )
123
+
124
+ expect(config1.enabled).to eq config2.enabled
125
+ expect(config1.min_confidence).to eq config2.min_confidence
126
+ end
127
+
128
+ it 'detects differences in enabled' do
129
+ config1 = described_class.new(enabled: true)
130
+ config2 = described_class.new(enabled: false)
131
+
132
+ expect(config1.enabled).not_to eq config2.enabled
133
+ end
134
+
135
+ it 'detects differences in min_confidence' do
136
+ config1 = described_class.new(min_confidence: 0.5)
137
+ config2 = described_class.new(min_confidence: 0.9)
138
+
139
+ expect(config1.min_confidence).not_to eq config2.min_confidence
140
+ end
141
+
142
+ it 'detects differences in detect_multiple' do
143
+ config1 = described_class.new(detect_multiple: true)
144
+ config2 = described_class.new(detect_multiple: false)
145
+
146
+ expect(config1.detect_multiple).not_to eq config2.detect_multiple
147
+ end
148
+ end
149
+
150
+ describe 'nested config integration' do
151
+ it 'can be nested in Extraction config' do
152
+ lang_detect = described_class.new(enabled: true, min_confidence: 0.9)
153
+ extraction = Kreuzberg::Config::Extraction.new(language_detection: lang_detect)
154
+
155
+ expect(extraction.language_detection).to be_a described_class
156
+ expect(extraction.language_detection.enabled).to be true
157
+ expect(extraction.language_detection.min_confidence).to eq 0.9
158
+ end
159
+
160
+ it 'accepts hash in Extraction config' do
161
+ extraction = Kreuzberg::Config::Extraction.new(
162
+ language_detection: { enabled: true, min_confidence: 0.75 }
163
+ )
164
+
165
+ expect(extraction.language_detection).to be_a described_class
166
+ expect(extraction.language_detection.enabled).to be true
167
+ expect(extraction.language_detection.min_confidence).to eq 0.75
168
+ end
169
+ end
170
+
171
+ describe 'symbol vs string key handling' do
172
+ it 'accepts symbol and string enabled values' do
173
+ config = described_class.new(enabled: true)
174
+
175
+ expect(config.enabled).to be true
176
+ end
177
+
178
+ it 'converts min_confidence string to float' do
179
+ config = described_class.new(min_confidence: '0.95')
180
+
181
+ expect(config.min_confidence).to eq 0.95
182
+ expect(config.min_confidence).to be_a Float
183
+ end
184
+ end
185
+
186
+ describe 'boolean conversion' do
187
+ it 'converts truthy enabled to true' do
188
+ config = described_class.new(enabled: 1)
189
+
190
+ expect(config.enabled).to be true
191
+ end
192
+
193
+ it 'converts false enabled to false' do
194
+ config = described_class.new(enabled: false)
195
+
196
+ expect(config.enabled).to be false
197
+ end
198
+
199
+ it 'converts truthy detect_multiple to true' do
200
+ config = described_class.new(detect_multiple: 'yes')
201
+
202
+ expect(config.detect_multiple).to be true
203
+ end
204
+
205
+ it 'converts false detect_multiple to false' do
206
+ config = described_class.new(detect_multiple: false)
207
+
208
+ expect(config.detect_multiple).to be false
209
+ end
210
+ end
211
+
212
+ describe 'confidence range' do
213
+ it 'accepts minimum confidence value' do
214
+ config = described_class.new(min_confidence: 0.0)
215
+
216
+ expect(config.min_confidence).to eq 0.0
217
+ end
218
+
219
+ it 'accepts maximum confidence value' do
220
+ config = described_class.new(min_confidence: 1.0)
221
+
222
+ expect(config.min_confidence).to eq 1.0
223
+ end
224
+
225
+ it 'accepts mid-range confidence value' do
226
+ config = described_class.new(min_confidence: 0.6)
227
+
228
+ expect(config.min_confidence).to eq 0.6
229
+ end
230
+
231
+ it 'preserves high precision confidence values' do
232
+ config = described_class.new(min_confidence: 0.123456)
233
+
234
+ expect(config.min_confidence).to be_within(0.00001).of(0.123456)
235
+ end
236
+ end
237
+
238
+ describe 'multiple language detection' do
239
+ it 'allows enabling multiple language detection' do
240
+ config = described_class.new(detect_multiple: true)
241
+
242
+ expect(config.detect_multiple).to be true
243
+ end
244
+
245
+ it 'defaults to single language detection' do
246
+ config = described_class.new
247
+
248
+ expect(config.detect_multiple).to be false
249
+ end
250
+
251
+ it 'can be disabled when enabled is true' do
252
+ config = described_class.new(enabled: true, detect_multiple: false)
253
+
254
+ expect(config.enabled).to be true
255
+ expect(config.detect_multiple).to be false
256
+ end
257
+ end
258
+ end
@@ -0,0 +1,171 @@
1
+ # frozen_string_literal: true
2
+
3
+ RSpec.describe Kreuzberg::Config::OCR do
4
+ describe '#initialize' do
5
+ it 'creates config with default values' do
6
+ config = described_class.new
7
+
8
+ expect(config.backend).to eq 'tesseract'
9
+ expect(config.language).to eq 'eng'
10
+ expect(config.tesseract_config).to be_nil
11
+ end
12
+
13
+ it 'creates config with custom string values' do
14
+ config = described_class.new(
15
+ backend: 'easyocr',
16
+ language: 'fra'
17
+ )
18
+
19
+ expect(config.backend).to eq 'easyocr'
20
+ expect(config.language).to eq 'fra'
21
+ end
22
+
23
+ it 'converts symbol keys to strings' do
24
+ config = described_class.new(backend: :tesseract, language: :deu)
25
+
26
+ expect(config.backend).to eq 'tesseract'
27
+ expect(config.language).to eq 'deu'
28
+ end
29
+
30
+ it 'accepts tesseract_config as instance' do
31
+ tesseract = Kreuzberg::Config::Tesseract.new(options: 'value')
32
+ config = described_class.new(tesseract_config: tesseract)
33
+
34
+ expect(config.tesseract_config).to be_a Kreuzberg::Config::Tesseract
35
+ end
36
+
37
+ it 'converts tesseract_config hash to instance' do
38
+ config = described_class.new(tesseract_config: { option: 'value' })
39
+
40
+ expect(config.tesseract_config).to be_a Kreuzberg::Config::Tesseract
41
+ end
42
+ end
43
+
44
+ describe '#to_h' do
45
+ it 'serializes to hash with default values' do
46
+ config = described_class.new
47
+ hash = config.to_h
48
+
49
+ expect(hash).to be_a Hash
50
+ expect(hash[:backend]).to eq 'tesseract'
51
+ expect(hash[:language]).to eq 'eng'
52
+ expect(hash[:tesseract_config]).to be_nil
53
+ end
54
+
55
+ it 'includes tesseract_config in hash when present' do
56
+ config = described_class.new(
57
+ backend: 'tesseract',
58
+ tesseract_config: { dpi: 300 }
59
+ )
60
+ hash = config.to_h
61
+
62
+ expect(hash[:tesseract_config]).to be_a Hash
63
+ end
64
+
65
+ it 'compacts nil values from hash' do
66
+ config = described_class.new(backend: 'tesseract')
67
+ hash = config.to_h
68
+
69
+ expect(hash.key?(:tesseract_config)).to be false
70
+ end
71
+ end
72
+
73
+ describe 'validation' do
74
+ it 'accepts valid backends' do
75
+ expect do
76
+ described_class.new(backend: 'tesseract')
77
+ end.not_to raise_error
78
+ end
79
+
80
+ it 'accepts symbol language' do
81
+ expect do
82
+ described_class.new(language: :fra)
83
+ end.not_to raise_error
84
+ end
85
+
86
+ it 'raises error for invalid tesseract_config type' do
87
+ expect do
88
+ described_class.new(tesseract_config: 'invalid')
89
+ end.to raise_error ArgumentError, /Expected.*Tesseract.*Hash.*nil/
90
+ end
91
+ end
92
+
93
+ describe 'keyword arguments' do
94
+ it 'accepts keyword arguments only' do
95
+ config = described_class.new(backend: 'tesseract', language: 'eng')
96
+
97
+ expect(config.backend).to eq 'tesseract'
98
+ expect(config.language).to eq 'eng'
99
+ end
100
+
101
+ it 'ignores unknown keywords gracefully' do
102
+ # This test documents current behavior
103
+ # The initialize method doesn't explicitly reject unknown keys
104
+ config = described_class.new(backend: 'tesseract')
105
+ expect(config).to be_a described_class
106
+ end
107
+ end
108
+
109
+ describe 'equality' do
110
+ it 'compares configs by value' do
111
+ config1 = described_class.new(backend: 'tesseract', language: 'eng')
112
+ config2 = described_class.new(backend: 'tesseract', language: 'eng')
113
+
114
+ expect(config1.backend).to eq config2.backend
115
+ expect(config1.language).to eq config2.language
116
+ end
117
+
118
+ it 'detects differences in backend' do
119
+ config1 = described_class.new(backend: 'tesseract')
120
+ config2 = described_class.new(backend: 'easyocr')
121
+
122
+ expect(config1.backend).not_to eq config2.backend
123
+ end
124
+
125
+ it 'detects differences in language' do
126
+ config1 = described_class.new(language: 'eng')
127
+ config2 = described_class.new(language: 'fra')
128
+
129
+ expect(config1.language).not_to eq config2.language
130
+ end
131
+ end
132
+
133
+ describe 'nested config integration' do
134
+ it 'integrates with Extraction config' do
135
+ ocr_config = described_class.new(backend: 'tesseract', language: 'deu')
136
+ extraction = Kreuzberg::Config::Extraction.new(ocr: ocr_config)
137
+
138
+ expect(extraction.ocr).to be_a described_class
139
+ expect(extraction.ocr.backend).to eq 'tesseract'
140
+ expect(extraction.ocr.language).to eq 'deu'
141
+ end
142
+
143
+ it 'accepts hash in Extraction config and converts to instance' do
144
+ extraction = Kreuzberg::Config::Extraction.new(
145
+ ocr: { backend: 'easyocr', language: 'fra' }
146
+ )
147
+
148
+ expect(extraction.ocr).to be_a described_class
149
+ expect(extraction.ocr.backend).to eq 'easyocr'
150
+ end
151
+ end
152
+
153
+ describe 'symbol vs string key handling' do
154
+ it 'converts symbol keys to correct attributes' do
155
+ config = described_class.new(backend: :tesseract, language: :fra)
156
+
157
+ expect(config.backend).to eq 'tesseract'
158
+ expect(config.language).to eq 'fra'
159
+ end
160
+
161
+ it 'handles mixed symbol and string values' do
162
+ config = described_class.new(
163
+ backend: 'tesseract',
164
+ language: :eng
165
+ )
166
+
167
+ expect(config.backend).to eq 'tesseract'
168
+ expect(config.language).to eq 'eng'
169
+ end
170
+ end
171
+ end
@@ -0,0 +1,221 @@
1
+ # frozen_string_literal: true
2
+
3
+ RSpec.describe Kreuzberg::Config::PageConfig do
4
+ describe '#initialize' do
5
+ it 'creates config with default values' do
6
+ config = described_class.new
7
+
8
+ expect(config.extract_pages).to be false
9
+ expect(config.insert_page_markers).to be false
10
+ expect(config.marker_format).to eq "\n\n<!-- PAGE {page_num} -->\n\n"
11
+ end
12
+
13
+ it 'creates config with custom values' do
14
+ config = described_class.new(
15
+ extract_pages: true,
16
+ insert_page_markers: true,
17
+ marker_format: '--- PAGE {page_num} ---'
18
+ )
19
+
20
+ expect(config.extract_pages).to be true
21
+ expect(config.insert_page_markers).to be true
22
+ expect(config.marker_format).to eq '--- PAGE {page_num} ---'
23
+ end
24
+
25
+ it 'converts boolean values' do
26
+ config = described_class.new(
27
+ extract_pages: true,
28
+ insert_page_markers: false
29
+ )
30
+
31
+ expect(config.extract_pages).to be true
32
+ expect(config.insert_page_markers).to be false
33
+ end
34
+
35
+ it 'converts marker_format to string' do
36
+ config = described_class.new(marker_format: :default)
37
+
38
+ expect(config.marker_format).to be_a String
39
+ end
40
+ end
41
+
42
+ describe '#to_h' do
43
+ it 'serializes to hash with all values' do
44
+ config = described_class.new(extract_pages: true)
45
+ hash = config.to_h
46
+
47
+ expect(hash).to be_a Hash
48
+ expect(hash[:extract_pages]).to be true
49
+ expect(hash[:insert_page_markers]).to be false
50
+ expect(hash[:marker_format]).to eq "\n\n<!-- PAGE {page_num} -->\n\n"
51
+ end
52
+
53
+ it 'always includes all keys in hash' do
54
+ config = described_class.new
55
+ hash = config.to_h
56
+
57
+ expect(hash.keys).to contain_exactly(
58
+ :extract_pages,
59
+ :insert_page_markers,
60
+ :marker_format
61
+ )
62
+ end
63
+ end
64
+
65
+ describe 'validation' do
66
+ it 'accepts boolean extract_pages' do
67
+ expect do
68
+ described_class.new(extract_pages: true)
69
+ end.not_to raise_error
70
+ end
71
+
72
+ it 'accepts boolean insert_page_markers' do
73
+ expect do
74
+ described_class.new(insert_page_markers: true)
75
+ end.not_to raise_error
76
+ end
77
+
78
+ it 'accepts custom marker formats' do
79
+ expect do
80
+ described_class.new(marker_format: '===== PAGE {page_num} =====')
81
+ end.not_to raise_error
82
+ end
83
+ end
84
+
85
+ describe 'keyword arguments' do
86
+ it 'accepts all keyword arguments' do
87
+ config = described_class.new(
88
+ extract_pages: true,
89
+ insert_page_markers: true,
90
+ marker_format: 'Page: {page_num}'
91
+ )
92
+
93
+ expect(config.extract_pages).to be true
94
+ expect(config.insert_page_markers).to be true
95
+ expect(config.marker_format).to eq 'Page: {page_num}'
96
+ end
97
+ end
98
+
99
+ describe 'equality' do
100
+ it 'compares configs by value' do
101
+ config1 = described_class.new(
102
+ extract_pages: true,
103
+ insert_page_markers: true,
104
+ marker_format: '--- PAGE {page_num} ---'
105
+ )
106
+ config2 = described_class.new(
107
+ extract_pages: true,
108
+ insert_page_markers: true,
109
+ marker_format: '--- PAGE {page_num} ---'
110
+ )
111
+
112
+ expect(config1.extract_pages).to eq config2.extract_pages
113
+ expect(config1.insert_page_markers).to eq config2.insert_page_markers
114
+ expect(config1.marker_format).to eq config2.marker_format
115
+ end
116
+
117
+ it 'detects differences in extract_pages' do
118
+ config1 = described_class.new(extract_pages: true)
119
+ config2 = described_class.new(extract_pages: false)
120
+
121
+ expect(config1.extract_pages).not_to eq config2.extract_pages
122
+ end
123
+
124
+ it 'detects differences in marker_format' do
125
+ config1 = described_class.new(marker_format: 'Format A')
126
+ config2 = described_class.new(marker_format: 'Format B')
127
+
128
+ expect(config1.marker_format).not_to eq config2.marker_format
129
+ end
130
+ end
131
+
132
+ describe 'nested config integration' do
133
+ it 'can be nested in Extraction config' do
134
+ pages = described_class.new(extract_pages: true)
135
+ extraction = Kreuzberg::Config::Extraction.new(pages: pages)
136
+
137
+ expect(extraction.pages).to be_a described_class
138
+ expect(extraction.pages.extract_pages).to be true
139
+ end
140
+
141
+ it 'accepts hash in Extraction config' do
142
+ extraction = Kreuzberg::Config::Extraction.new(
143
+ pages: { extract_pages: true, insert_page_markers: true }
144
+ )
145
+
146
+ expect(extraction.pages).to be_a described_class
147
+ expect(extraction.pages.extract_pages).to be true
148
+ expect(extraction.pages.insert_page_markers).to be true
149
+ end
150
+ end
151
+
152
+ describe 'marker format' do
153
+ it 'preserves custom marker format' do
154
+ format = '=== PAGE {page_num} ==='
155
+ config = described_class.new(marker_format: format)
156
+
157
+ expect(config.marker_format).to eq format
158
+ end
159
+
160
+ it 'preserves default marker format' do
161
+ config = described_class.new
162
+
163
+ expect(config.marker_format).to include '{page_num}'
164
+ end
165
+
166
+ it 'allows empty marker format' do
167
+ config = described_class.new(marker_format: '')
168
+
169
+ expect(config.marker_format).to eq ''
170
+ end
171
+
172
+ it 'handles multiline marker formats' do
173
+ format = "\n--- PAGE {page_num} ---\n"
174
+ config = described_class.new(marker_format: format)
175
+
176
+ expect(config.marker_format).to eq format
177
+ end
178
+ end
179
+
180
+ describe 'symbol vs string key handling' do
181
+ it 'converts symbol values to strings' do
182
+ config = described_class.new(marker_format: :default_format)
183
+
184
+ expect(config.marker_format).to be_a String
185
+ end
186
+
187
+ it 'preserves string marker format' do
188
+ format = 'Custom Format'
189
+ config = described_class.new(marker_format: format)
190
+
191
+ expect(config.marker_format).to eq format
192
+ expect(config.marker_format).to be_a String
193
+ end
194
+ end
195
+
196
+ describe 'boolean conversion' do
197
+ it 'converts truthy extract_pages to true' do
198
+ config = described_class.new(extract_pages: 1)
199
+
200
+ expect(config.extract_pages).to be true
201
+ end
202
+
203
+ it 'converts false extract_pages to false' do
204
+ config = described_class.new(extract_pages: false)
205
+
206
+ expect(config.extract_pages).to be false
207
+ end
208
+
209
+ it 'converts truthy insert_page_markers to true' do
210
+ config = described_class.new(insert_page_markers: 'yes')
211
+
212
+ expect(config.insert_page_markers).to be true
213
+ end
214
+
215
+ it 'converts false insert_page_markers to false' do
216
+ config = described_class.new(insert_page_markers: false)
217
+
218
+ expect(config.insert_page_markers).to be false
219
+ end
220
+ end
221
+ end