kreuzberg 4.0.0.rc1 → 4.0.0.rc2

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 (342) hide show
  1. checksums.yaml +4 -4
  2. data/.gitignore +14 -8
  3. data/.rspec +3 -3
  4. data/.rubocop.yaml +1 -534
  5. data/.rubocop.yml +538 -0
  6. data/Gemfile +8 -9
  7. data/Gemfile.lock +9 -109
  8. data/README.md +426 -421
  9. data/Rakefile +25 -25
  10. data/Steepfile +47 -47
  11. data/examples/async_patterns.rb +341 -340
  12. data/ext/kreuzberg_rb/extconf.rb +45 -35
  13. data/ext/kreuzberg_rb/native/Cargo.lock +6535 -0
  14. data/ext/kreuzberg_rb/native/Cargo.toml +44 -36
  15. data/ext/kreuzberg_rb/native/README.md +425 -425
  16. data/ext/kreuzberg_rb/native/build.rs +15 -17
  17. data/ext/kreuzberg_rb/native/include/ieeefp.h +11 -11
  18. data/ext/kreuzberg_rb/native/include/msvc_compat/strings.h +14 -14
  19. data/ext/kreuzberg_rb/native/include/strings.h +20 -20
  20. data/ext/kreuzberg_rb/native/include/unistd.h +47 -47
  21. data/ext/kreuzberg_rb/native/src/lib.rs +2998 -2939
  22. data/extconf.rb +28 -28
  23. data/kreuzberg.gemspec +148 -105
  24. data/lib/kreuzberg/api_proxy.rb +142 -142
  25. data/lib/kreuzberg/cache_api.rb +46 -45
  26. data/lib/kreuzberg/cli.rb +55 -55
  27. data/lib/kreuzberg/cli_proxy.rb +127 -127
  28. data/lib/kreuzberg/config.rb +691 -684
  29. data/lib/kreuzberg/error_context.rb +32 -0
  30. data/lib/kreuzberg/errors.rb +118 -50
  31. data/lib/kreuzberg/extraction_api.rb +85 -84
  32. data/lib/kreuzberg/mcp_proxy.rb +186 -186
  33. data/lib/kreuzberg/ocr_backend_protocol.rb +113 -113
  34. data/lib/kreuzberg/post_processor_protocol.rb +86 -86
  35. data/lib/kreuzberg/result.rb +216 -216
  36. data/lib/kreuzberg/setup_lib_path.rb +80 -79
  37. data/lib/kreuzberg/validator_protocol.rb +89 -89
  38. data/lib/kreuzberg/version.rb +5 -5
  39. data/lib/kreuzberg.rb +103 -82
  40. data/sig/kreuzberg/internal.rbs +184 -184
  41. data/sig/kreuzberg.rbs +520 -468
  42. data/spec/binding/cache_spec.rb +227 -227
  43. data/spec/binding/cli_proxy_spec.rb +85 -87
  44. data/spec/binding/cli_spec.rb +55 -54
  45. data/spec/binding/config_spec.rb +345 -345
  46. data/spec/binding/config_validation_spec.rb +283 -283
  47. data/spec/binding/error_handling_spec.rb +213 -213
  48. data/spec/binding/errors_spec.rb +66 -66
  49. data/spec/binding/plugins/ocr_backend_spec.rb +307 -307
  50. data/spec/binding/plugins/postprocessor_spec.rb +269 -269
  51. data/spec/binding/plugins/validator_spec.rb +274 -274
  52. data/spec/fixtures/config.toml +39 -39
  53. data/spec/fixtures/config.yaml +41 -42
  54. data/spec/fixtures/invalid_config.toml +4 -4
  55. data/spec/smoke/package_spec.rb +178 -178
  56. data/spec/spec_helper.rb +42 -42
  57. data/vendor/kreuzberg/Cargo.toml +204 -134
  58. data/vendor/kreuzberg/README.md +175 -175
  59. data/vendor/kreuzberg/benches/otel_overhead.rs +48 -0
  60. data/vendor/kreuzberg/build.rs +474 -460
  61. data/vendor/kreuzberg/src/api/error.rs +81 -81
  62. data/vendor/kreuzberg/src/api/handlers.rs +199 -199
  63. data/vendor/kreuzberg/src/api/mod.rs +79 -79
  64. data/vendor/kreuzberg/src/api/server.rs +353 -353
  65. data/vendor/kreuzberg/src/api/types.rs +170 -170
  66. data/vendor/kreuzberg/src/cache/mod.rs +1167 -1143
  67. data/vendor/kreuzberg/src/chunking/mod.rs +677 -677
  68. data/vendor/kreuzberg/src/core/batch_mode.rs +95 -35
  69. data/vendor/kreuzberg/src/core/config.rs +1032 -1032
  70. data/vendor/kreuzberg/src/core/extractor.rs +1024 -903
  71. data/vendor/kreuzberg/src/core/io.rs +329 -327
  72. data/vendor/kreuzberg/src/core/mime.rs +605 -615
  73. data/vendor/kreuzberg/src/core/mod.rs +45 -42
  74. data/vendor/kreuzberg/src/core/pipeline.rs +984 -906
  75. data/vendor/kreuzberg/src/embeddings.rs +432 -323
  76. data/vendor/kreuzberg/src/error.rs +431 -431
  77. data/vendor/kreuzberg/src/extraction/archive.rs +954 -954
  78. data/vendor/kreuzberg/src/extraction/docx.rs +40 -40
  79. data/vendor/kreuzberg/src/extraction/email.rs +854 -854
  80. data/vendor/kreuzberg/src/extraction/excel.rs +688 -688
  81. data/vendor/kreuzberg/src/extraction/html.rs +553 -553
  82. data/vendor/kreuzberg/src/extraction/image.rs +368 -368
  83. data/vendor/kreuzberg/src/extraction/libreoffice.rs +563 -564
  84. data/vendor/kreuzberg/src/extraction/markdown.rs +213 -0
  85. data/vendor/kreuzberg/src/extraction/mod.rs +81 -77
  86. data/vendor/kreuzberg/src/extraction/office_metadata/app_properties.rs +398 -398
  87. data/vendor/kreuzberg/src/extraction/office_metadata/core_properties.rs +247 -247
  88. data/vendor/kreuzberg/src/extraction/office_metadata/custom_properties.rs +240 -240
  89. data/vendor/kreuzberg/src/extraction/office_metadata/mod.rs +130 -128
  90. data/vendor/kreuzberg/src/extraction/office_metadata/odt_properties.rs +287 -0
  91. data/vendor/kreuzberg/src/extraction/pptx.rs +3000 -3000
  92. data/vendor/kreuzberg/src/extraction/structured.rs +490 -490
  93. data/vendor/kreuzberg/src/extraction/table.rs +328 -328
  94. data/vendor/kreuzberg/src/extraction/text.rs +269 -269
  95. data/vendor/kreuzberg/src/extraction/xml.rs +333 -333
  96. data/vendor/kreuzberg/src/extractors/archive.rs +446 -425
  97. data/vendor/kreuzberg/src/extractors/bibtex.rs +469 -0
  98. data/vendor/kreuzberg/src/extractors/docbook.rs +502 -0
  99. data/vendor/kreuzberg/src/extractors/docx.rs +367 -479
  100. data/vendor/kreuzberg/src/extractors/email.rs +143 -129
  101. data/vendor/kreuzberg/src/extractors/epub.rs +707 -0
  102. data/vendor/kreuzberg/src/extractors/excel.rs +343 -344
  103. data/vendor/kreuzberg/src/extractors/fictionbook.rs +491 -0
  104. data/vendor/kreuzberg/src/extractors/fictionbook.rs.backup2 +738 -0
  105. data/vendor/kreuzberg/src/extractors/html.rs +393 -410
  106. data/vendor/kreuzberg/src/extractors/image.rs +198 -195
  107. data/vendor/kreuzberg/src/extractors/jats.rs +1051 -0
  108. data/vendor/kreuzberg/src/extractors/jupyter.rs +367 -0
  109. data/vendor/kreuzberg/src/extractors/latex.rs +652 -0
  110. data/vendor/kreuzberg/src/extractors/markdown.rs +700 -0
  111. data/vendor/kreuzberg/src/extractors/mod.rs +365 -268
  112. data/vendor/kreuzberg/src/extractors/odt.rs +628 -0
  113. data/vendor/kreuzberg/src/extractors/opml.rs +634 -0
  114. data/vendor/kreuzberg/src/extractors/orgmode.rs +528 -0
  115. data/vendor/kreuzberg/src/extractors/pdf.rs +493 -496
  116. data/vendor/kreuzberg/src/extractors/pptx.rs +248 -234
  117. data/vendor/kreuzberg/src/extractors/rst.rs +576 -0
  118. data/vendor/kreuzberg/src/extractors/rtf.rs +810 -0
  119. data/vendor/kreuzberg/src/extractors/security.rs +484 -0
  120. data/vendor/kreuzberg/src/extractors/security_tests.rs +367 -0
  121. data/vendor/kreuzberg/src/extractors/structured.rs +140 -126
  122. data/vendor/kreuzberg/src/extractors/text.rs +260 -242
  123. data/vendor/kreuzberg/src/extractors/typst.rs +650 -0
  124. data/vendor/kreuzberg/src/extractors/xml.rs +135 -128
  125. data/vendor/kreuzberg/src/image/dpi.rs +164 -164
  126. data/vendor/kreuzberg/src/image/mod.rs +6 -6
  127. data/vendor/kreuzberg/src/image/preprocessing.rs +417 -417
  128. data/vendor/kreuzberg/src/image/resize.rs +89 -89
  129. data/vendor/kreuzberg/src/keywords/config.rs +154 -154
  130. data/vendor/kreuzberg/src/keywords/mod.rs +237 -237
  131. data/vendor/kreuzberg/src/keywords/processor.rs +267 -267
  132. data/vendor/kreuzberg/src/keywords/rake.rs +293 -294
  133. data/vendor/kreuzberg/src/keywords/types.rs +68 -68
  134. data/vendor/kreuzberg/src/keywords/yake.rs +163 -163
  135. data/vendor/kreuzberg/src/language_detection/mod.rs +942 -942
  136. data/vendor/kreuzberg/src/lib.rs +105 -102
  137. data/vendor/kreuzberg/src/mcp/mod.rs +32 -32
  138. data/vendor/kreuzberg/src/mcp/server.rs +1968 -1966
  139. data/vendor/kreuzberg/src/ocr/cache.rs +469 -469
  140. data/vendor/kreuzberg/src/ocr/error.rs +37 -37
  141. data/vendor/kreuzberg/src/ocr/hocr.rs +216 -216
  142. data/vendor/kreuzberg/src/ocr/mod.rs +58 -58
  143. data/vendor/kreuzberg/src/ocr/processor.rs +863 -847
  144. data/vendor/kreuzberg/src/ocr/table/mod.rs +4 -4
  145. data/vendor/kreuzberg/src/ocr/table/tsv_parser.rs +144 -144
  146. data/vendor/kreuzberg/src/ocr/tesseract_backend.rs +450 -450
  147. data/vendor/kreuzberg/src/ocr/types.rs +393 -393
  148. data/vendor/kreuzberg/src/ocr/utils.rs +47 -47
  149. data/vendor/kreuzberg/src/ocr/validation.rs +206 -206
  150. data/vendor/kreuzberg/src/panic_context.rs +154 -0
  151. data/vendor/kreuzberg/src/pdf/error.rs +122 -122
  152. data/vendor/kreuzberg/src/pdf/images.rs +139 -139
  153. data/vendor/kreuzberg/src/pdf/metadata.rs +346 -346
  154. data/vendor/kreuzberg/src/pdf/mod.rs +50 -50
  155. data/vendor/kreuzberg/src/pdf/rendering.rs +369 -369
  156. data/vendor/kreuzberg/src/pdf/table.rs +393 -420
  157. data/vendor/kreuzberg/src/pdf/text.rs +158 -161
  158. data/vendor/kreuzberg/src/plugins/extractor.rs +1013 -1010
  159. data/vendor/kreuzberg/src/plugins/mod.rs +209 -209
  160. data/vendor/kreuzberg/src/plugins/ocr.rs +620 -629
  161. data/vendor/kreuzberg/src/plugins/processor.rs +642 -641
  162. data/vendor/kreuzberg/src/plugins/registry.rs +1337 -1324
  163. data/vendor/kreuzberg/src/plugins/traits.rs +258 -258
  164. data/vendor/kreuzberg/src/plugins/validator.rs +956 -955
  165. data/vendor/kreuzberg/src/stopwords/mod.rs +1470 -1470
  166. data/vendor/kreuzberg/src/text/mod.rs +19 -19
  167. data/vendor/kreuzberg/src/text/quality.rs +697 -697
  168. data/vendor/kreuzberg/src/text/string_utils.rs +217 -217
  169. data/vendor/kreuzberg/src/text/token_reduction/cjk_utils.rs +164 -164
  170. data/vendor/kreuzberg/src/text/token_reduction/config.rs +100 -100
  171. data/vendor/kreuzberg/src/text/token_reduction/core.rs +796 -796
  172. data/vendor/kreuzberg/src/text/token_reduction/filters.rs +902 -902
  173. data/vendor/kreuzberg/src/text/token_reduction/mod.rs +160 -160
  174. data/vendor/kreuzberg/src/text/token_reduction/semantic.rs +619 -619
  175. data/vendor/kreuzberg/src/text/token_reduction/simd_text.rs +147 -147
  176. data/vendor/kreuzberg/src/types.rs +903 -873
  177. data/vendor/kreuzberg/src/utils/mod.rs +17 -17
  178. data/vendor/kreuzberg/src/utils/quality.rs +959 -959
  179. data/vendor/kreuzberg/src/utils/string_utils.rs +381 -381
  180. data/vendor/kreuzberg/stopwords/af_stopwords.json +53 -53
  181. data/vendor/kreuzberg/stopwords/ar_stopwords.json +482 -482
  182. data/vendor/kreuzberg/stopwords/bg_stopwords.json +261 -261
  183. data/vendor/kreuzberg/stopwords/bn_stopwords.json +400 -400
  184. data/vendor/kreuzberg/stopwords/br_stopwords.json +1205 -1205
  185. data/vendor/kreuzberg/stopwords/ca_stopwords.json +280 -280
  186. data/vendor/kreuzberg/stopwords/cs_stopwords.json +425 -425
  187. data/vendor/kreuzberg/stopwords/da_stopwords.json +172 -172
  188. data/vendor/kreuzberg/stopwords/de_stopwords.json +622 -622
  189. data/vendor/kreuzberg/stopwords/el_stopwords.json +849 -849
  190. data/vendor/kreuzberg/stopwords/en_stopwords.json +1300 -1300
  191. data/vendor/kreuzberg/stopwords/eo_stopwords.json +175 -175
  192. data/vendor/kreuzberg/stopwords/es_stopwords.json +734 -734
  193. data/vendor/kreuzberg/stopwords/et_stopwords.json +37 -37
  194. data/vendor/kreuzberg/stopwords/eu_stopwords.json +100 -100
  195. data/vendor/kreuzberg/stopwords/fa_stopwords.json +801 -801
  196. data/vendor/kreuzberg/stopwords/fi_stopwords.json +849 -849
  197. data/vendor/kreuzberg/stopwords/fr_stopwords.json +693 -693
  198. data/vendor/kreuzberg/stopwords/ga_stopwords.json +111 -111
  199. data/vendor/kreuzberg/stopwords/gl_stopwords.json +162 -162
  200. data/vendor/kreuzberg/stopwords/gu_stopwords.json +226 -226
  201. data/vendor/kreuzberg/stopwords/ha_stopwords.json +41 -41
  202. data/vendor/kreuzberg/stopwords/he_stopwords.json +196 -196
  203. data/vendor/kreuzberg/stopwords/hi_stopwords.json +227 -227
  204. data/vendor/kreuzberg/stopwords/hr_stopwords.json +181 -181
  205. data/vendor/kreuzberg/stopwords/hu_stopwords.json +791 -791
  206. data/vendor/kreuzberg/stopwords/hy_stopwords.json +47 -47
  207. data/vendor/kreuzberg/stopwords/id_stopwords.json +760 -760
  208. data/vendor/kreuzberg/stopwords/it_stopwords.json +634 -634
  209. data/vendor/kreuzberg/stopwords/ja_stopwords.json +136 -136
  210. data/vendor/kreuzberg/stopwords/kn_stopwords.json +84 -84
  211. data/vendor/kreuzberg/stopwords/ko_stopwords.json +681 -681
  212. data/vendor/kreuzberg/stopwords/ku_stopwords.json +64 -64
  213. data/vendor/kreuzberg/stopwords/la_stopwords.json +51 -51
  214. data/vendor/kreuzberg/stopwords/lt_stopwords.json +476 -476
  215. data/vendor/kreuzberg/stopwords/lv_stopwords.json +163 -163
  216. data/vendor/kreuzberg/stopwords/ml_stopwords.json +1 -1
  217. data/vendor/kreuzberg/stopwords/mr_stopwords.json +101 -101
  218. data/vendor/kreuzberg/stopwords/ms_stopwords.json +477 -477
  219. data/vendor/kreuzberg/stopwords/ne_stopwords.json +490 -490
  220. data/vendor/kreuzberg/stopwords/nl_stopwords.json +415 -415
  221. data/vendor/kreuzberg/stopwords/no_stopwords.json +223 -223
  222. data/vendor/kreuzberg/stopwords/pl_stopwords.json +331 -331
  223. data/vendor/kreuzberg/stopwords/pt_stopwords.json +562 -562
  224. data/vendor/kreuzberg/stopwords/ro_stopwords.json +436 -436
  225. data/vendor/kreuzberg/stopwords/ru_stopwords.json +561 -561
  226. data/vendor/kreuzberg/stopwords/si_stopwords.json +193 -193
  227. data/vendor/kreuzberg/stopwords/sk_stopwords.json +420 -420
  228. data/vendor/kreuzberg/stopwords/sl_stopwords.json +448 -448
  229. data/vendor/kreuzberg/stopwords/so_stopwords.json +32 -32
  230. data/vendor/kreuzberg/stopwords/st_stopwords.json +33 -33
  231. data/vendor/kreuzberg/stopwords/sv_stopwords.json +420 -420
  232. data/vendor/kreuzberg/stopwords/sw_stopwords.json +76 -76
  233. data/vendor/kreuzberg/stopwords/ta_stopwords.json +129 -129
  234. data/vendor/kreuzberg/stopwords/te_stopwords.json +54 -54
  235. data/vendor/kreuzberg/stopwords/th_stopwords.json +118 -118
  236. data/vendor/kreuzberg/stopwords/tl_stopwords.json +149 -149
  237. data/vendor/kreuzberg/stopwords/tr_stopwords.json +506 -506
  238. data/vendor/kreuzberg/stopwords/uk_stopwords.json +75 -75
  239. data/vendor/kreuzberg/stopwords/ur_stopwords.json +519 -519
  240. data/vendor/kreuzberg/stopwords/vi_stopwords.json +647 -647
  241. data/vendor/kreuzberg/stopwords/yo_stopwords.json +62 -62
  242. data/vendor/kreuzberg/stopwords/zh_stopwords.json +796 -796
  243. data/vendor/kreuzberg/stopwords/zu_stopwords.json +31 -31
  244. data/vendor/kreuzberg/tests/api_extract_multipart.rs +52 -0
  245. data/vendor/kreuzberg/tests/api_tests.rs +966 -966
  246. data/vendor/kreuzberg/tests/archive_integration.rs +543 -543
  247. data/vendor/kreuzberg/tests/batch_orchestration.rs +556 -542
  248. data/vendor/kreuzberg/tests/batch_processing.rs +316 -304
  249. data/vendor/kreuzberg/tests/bibtex_parity_test.rs +421 -0
  250. data/vendor/kreuzberg/tests/concurrency_stress.rs +525 -509
  251. data/vendor/kreuzberg/tests/config_features.rs +598 -580
  252. data/vendor/kreuzberg/tests/config_loading_tests.rs +415 -439
  253. data/vendor/kreuzberg/tests/core_integration.rs +510 -493
  254. data/vendor/kreuzberg/tests/csv_integration.rs +414 -424
  255. data/vendor/kreuzberg/tests/docbook_extractor_tests.rs +498 -0
  256. data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +122 -124
  257. data/vendor/kreuzberg/tests/docx_vs_pandoc_comparison.rs +370 -0
  258. data/vendor/kreuzberg/tests/email_integration.rs +325 -325
  259. data/vendor/kreuzberg/tests/epub_native_extractor_tests.rs +275 -0
  260. data/vendor/kreuzberg/tests/error_handling.rs +393 -393
  261. data/vendor/kreuzberg/tests/fictionbook_extractor_tests.rs +228 -0
  262. data/vendor/kreuzberg/tests/format_integration.rs +159 -159
  263. data/vendor/kreuzberg/tests/helpers/mod.rs +142 -142
  264. data/vendor/kreuzberg/tests/html_table_test.rs +551 -0
  265. data/vendor/kreuzberg/tests/image_integration.rs +253 -253
  266. data/vendor/kreuzberg/tests/instrumentation_test.rs +139 -0
  267. data/vendor/kreuzberg/tests/jats_extractor_tests.rs +639 -0
  268. data/vendor/kreuzberg/tests/jupyter_extractor_tests.rs +704 -0
  269. data/vendor/kreuzberg/tests/keywords_integration.rs +479 -479
  270. data/vendor/kreuzberg/tests/keywords_quality.rs +509 -509
  271. data/vendor/kreuzberg/tests/latex_extractor_tests.rs +496 -0
  272. data/vendor/kreuzberg/tests/markdown_extractor_tests.rs +490 -0
  273. data/vendor/kreuzberg/tests/mime_detection.rs +428 -428
  274. data/vendor/kreuzberg/tests/ocr_configuration.rs +510 -510
  275. data/vendor/kreuzberg/tests/ocr_errors.rs +676 -676
  276. data/vendor/kreuzberg/tests/ocr_quality.rs +627 -627
  277. data/vendor/kreuzberg/tests/ocr_stress.rs +469 -469
  278. data/vendor/kreuzberg/tests/odt_extractor_tests.rs +695 -0
  279. data/vendor/kreuzberg/tests/opml_extractor_tests.rs +616 -0
  280. data/vendor/kreuzberg/tests/orgmode_extractor_tests.rs +822 -0
  281. data/vendor/kreuzberg/tests/pdf_integration.rs +43 -43
  282. data/vendor/kreuzberg/tests/pipeline_integration.rs +1411 -1412
  283. data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +771 -771
  284. data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +560 -561
  285. data/vendor/kreuzberg/tests/plugin_system.rs +921 -921
  286. data/vendor/kreuzberg/tests/plugin_validator_test.rs +783 -783
  287. data/vendor/kreuzberg/tests/registry_integration_tests.rs +586 -607
  288. data/vendor/kreuzberg/tests/rst_extractor_tests.rs +692 -0
  289. data/vendor/kreuzberg/tests/rtf_extractor_tests.rs +776 -0
  290. data/vendor/kreuzberg/tests/security_validation.rs +415 -404
  291. data/vendor/kreuzberg/tests/stopwords_integration_test.rs +888 -888
  292. data/vendor/kreuzberg/tests/test_fastembed.rs +609 -609
  293. data/vendor/kreuzberg/tests/typst_behavioral_tests.rs +1259 -0
  294. data/vendor/kreuzberg/tests/typst_extractor_tests.rs +647 -0
  295. data/vendor/kreuzberg/tests/xlsx_metadata_extraction_test.rs +87 -87
  296. data/vendor/rb-sys/.cargo-ok +1 -0
  297. data/vendor/rb-sys/.cargo_vcs_info.json +6 -0
  298. data/vendor/rb-sys/Cargo.lock +393 -0
  299. data/vendor/rb-sys/Cargo.toml +70 -0
  300. data/vendor/rb-sys/Cargo.toml.orig +57 -0
  301. data/vendor/rb-sys/LICENSE-APACHE +190 -0
  302. data/vendor/rb-sys/LICENSE-MIT +21 -0
  303. data/vendor/rb-sys/bin/release.sh +21 -0
  304. data/vendor/rb-sys/build/features.rs +108 -0
  305. data/vendor/rb-sys/build/main.rs +246 -0
  306. data/vendor/rb-sys/build/stable_api_config.rs +153 -0
  307. data/vendor/rb-sys/build/version.rs +48 -0
  308. data/vendor/rb-sys/readme.md +36 -0
  309. data/vendor/rb-sys/src/bindings.rs +21 -0
  310. data/vendor/rb-sys/src/hidden.rs +11 -0
  311. data/vendor/rb-sys/src/lib.rs +34 -0
  312. data/vendor/rb-sys/src/macros.rs +371 -0
  313. data/vendor/rb-sys/src/memory.rs +53 -0
  314. data/vendor/rb-sys/src/ruby_abi_version.rs +38 -0
  315. data/vendor/rb-sys/src/special_consts.rs +31 -0
  316. data/vendor/rb-sys/src/stable_api/compiled.c +179 -0
  317. data/vendor/rb-sys/src/stable_api/compiled.rs +257 -0
  318. data/vendor/rb-sys/src/stable_api/ruby_2_6.rs +316 -0
  319. data/vendor/rb-sys/src/stable_api/ruby_2_7.rs +316 -0
  320. data/vendor/rb-sys/src/stable_api/ruby_3_0.rs +324 -0
  321. data/vendor/rb-sys/src/stable_api/ruby_3_1.rs +317 -0
  322. data/vendor/rb-sys/src/stable_api/ruby_3_2.rs +315 -0
  323. data/vendor/rb-sys/src/stable_api/ruby_3_3.rs +326 -0
  324. data/vendor/rb-sys/src/stable_api/ruby_3_4.rs +327 -0
  325. data/vendor/rb-sys/src/stable_api.rs +261 -0
  326. data/vendor/rb-sys/src/symbol.rs +31 -0
  327. data/vendor/rb-sys/src/tracking_allocator.rs +332 -0
  328. data/vendor/rb-sys/src/utils.rs +89 -0
  329. data/vendor/rb-sys/src/value_type.rs +7 -0
  330. metadata +90 -95
  331. data/pkg/kreuzberg-4.0.0.rc1.gem +0 -0
  332. data/spec/examples.txt +0 -104
  333. data/vendor/kreuzberg/src/bin/profile_extract.rs +0 -455
  334. data/vendor/kreuzberg/src/extraction/pandoc/batch.rs +0 -275
  335. data/vendor/kreuzberg/src/extraction/pandoc/mime_types.rs +0 -178
  336. data/vendor/kreuzberg/src/extraction/pandoc/mod.rs +0 -491
  337. data/vendor/kreuzberg/src/extraction/pandoc/server.rs +0 -496
  338. data/vendor/kreuzberg/src/extraction/pandoc/subprocess.rs +0 -1188
  339. data/vendor/kreuzberg/src/extraction/pandoc/version.rs +0 -162
  340. data/vendor/kreuzberg/src/extractors/pandoc.rs +0 -201
  341. data/vendor/kreuzberg/tests/chunking_offset_demo.rs +0 -92
  342. data/vendor/kreuzberg/tests/pandoc_integration.rs +0 -503
@@ -1,345 +1,345 @@
1
- # frozen_string_literal: true
2
-
3
- RSpec.describe Kreuzberg::Config do
4
- describe Kreuzberg::Config::OCR do
5
- it 'creates with default values' do
6
- ocr = described_class.new
7
-
8
- expect(ocr.backend).to eq('tesseract')
9
- expect(ocr.language).to eq('eng')
10
- expect(ocr.tesseract_config).to be_nil
11
- end
12
-
13
- it 'creates with custom values' do
14
- ocr = described_class.new(
15
- backend: 'easyocr',
16
- language: 'deu'
17
- )
18
-
19
- expect(ocr.backend).to eq('easyocr')
20
- expect(ocr.language).to eq('deu')
21
- end
22
-
23
- it 'converts to hash' do
24
- ocr = described_class.new(backend: 'tesseract', language: 'fra')
25
- hash = ocr.to_h
26
-
27
- expect(hash).to be_a(Hash)
28
- expect(hash[:backend]).to eq('tesseract')
29
- expect(hash[:language]).to eq('fra')
30
- end
31
- end
32
-
33
- describe Kreuzberg::Config::Chunking do
34
- it 'creates with default values' do
35
- chunking = described_class.new
36
-
37
- expect(chunking.max_chars).to eq(1000)
38
- expect(chunking.max_overlap).to eq(200)
39
- expect(chunking.preset).to be_nil
40
- expect(chunking.embedding).to be_nil
41
- end
42
-
43
- it 'creates with custom values' do
44
- chunking = described_class.new(
45
- max_chars: 500,
46
- max_overlap: 100,
47
- preset: 'fast'
48
- )
49
-
50
- expect(chunking.max_chars).to eq(500)
51
- expect(chunking.max_overlap).to eq(100)
52
- expect(chunking.preset).to eq('fast')
53
- end
54
-
55
- it 'converts to hash' do
56
- chunking = described_class.new(max_chars: 750)
57
- hash = chunking.to_h
58
-
59
- expect(hash).to be_a(Hash)
60
- expect(hash[:max_chars]).to eq(750)
61
- end
62
- end
63
-
64
- describe Kreuzberg::Config::LanguageDetection do
65
- it 'creates with default values' do
66
- lang = described_class.new
67
-
68
- expect(lang.enabled).to be false
69
- expect(lang.min_confidence).to eq(0.5)
70
- end
71
-
72
- it 'creates with custom values' do
73
- lang = described_class.new(enabled: true, min_confidence: 0.9)
74
-
75
- expect(lang.enabled).to be true
76
- expect(lang.min_confidence).to eq(0.9)
77
- end
78
-
79
- it 'converts to hash' do
80
- lang = described_class.new(enabled: true, min_confidence: 0.75)
81
- hash = lang.to_h
82
-
83
- expect(hash).to be_a(Hash)
84
- expect(hash[:enabled]).to be true
85
- expect(hash[:min_confidence]).to eq(0.75)
86
- end
87
- end
88
-
89
- describe Kreuzberg::Config::PDF do
90
- it 'creates with default values' do
91
- pdf = described_class.new
92
-
93
- expect(pdf.extract_images).to be false
94
- expect(pdf.passwords).to be_nil
95
- expect(pdf.extract_metadata).to be true
96
- end
97
-
98
- it 'creates with custom values' do
99
- pdf = described_class.new(
100
- extract_images: true,
101
- passwords: %w[secret backup]
102
- )
103
-
104
- expect(pdf.extract_images).to be true
105
- expect(pdf.passwords).to eq(%w[secret backup])
106
- end
107
-
108
- it 'converts to hash' do
109
- pdf = described_class.new(extract_images: true, passwords: ['test'])
110
- hash = pdf.to_h
111
-
112
- expect(hash).to be_a(Hash)
113
- expect(hash[:extract_images]).to be true
114
- expect(hash[:passwords]).to eq(['test'])
115
- end
116
- end
117
-
118
- describe Kreuzberg::Config::Extraction do
119
- describe '.from_file' do
120
- it 'loads configuration from TOML file' do
121
- config_path = File.join(__dir__, '..', 'fixtures', 'config.toml')
122
- config = described_class.from_file(config_path)
123
-
124
- expect(config.use_cache).to be false
125
- expect(config.enable_quality_processing).to be true
126
- expect(config.force_ocr).to be true
127
- end
128
-
129
- it 'loads OCR config from TOML file' do
130
- config_path = File.join(__dir__, '..', 'fixtures', 'config.toml')
131
- config = described_class.from_file(config_path)
132
-
133
- expect(config.ocr).to be_a(Kreuzberg::Config::OCR)
134
- expect(config.ocr.backend).to eq('tesseract')
135
- expect(config.ocr.language).to eq('deu')
136
- end
137
-
138
- it 'loads chunking config from TOML file' do
139
- config_path = File.join(__dir__, '..', 'fixtures', 'config.toml')
140
- config = described_class.from_file(config_path)
141
-
142
- expect(config.chunking).to be_a(Kreuzberg::Config::Chunking)
143
- expect(config.chunking.max_chars).to eq(500)
144
- expect(config.chunking.max_overlap).to eq(100)
145
- expect(config.chunking.preset).to eq('fast')
146
- end
147
-
148
- it 'loads language detection config from TOML file' do
149
- config_path = File.join(__dir__, '..', 'fixtures', 'config.toml')
150
- config = described_class.from_file(config_path)
151
-
152
- expect(config.language_detection).to be_a(Kreuzberg::Config::LanguageDetection)
153
- expect(config.language_detection.enabled).to be true
154
- expect(config.language_detection.min_confidence).to eq(0.9)
155
- end
156
-
157
- it 'loads PDF options from TOML file' do
158
- config_path = File.join(__dir__, '..', 'fixtures', 'config.toml')
159
- config = described_class.from_file(config_path)
160
-
161
- expect(config.pdf_options).to be_a(Kreuzberg::Config::PDF)
162
- expect(config.pdf_options.extract_images).to be true
163
- expect(config.pdf_options.passwords).to eq(%w[secret backup])
164
- expect(config.pdf_options.extract_metadata).to be true
165
- end
166
-
167
- it 'loads configuration from YAML file' do
168
- config_path = File.join(__dir__, '..', 'fixtures', 'config.yaml')
169
- config = described_class.from_file(config_path)
170
-
171
- expect(config.use_cache).to be false
172
- expect(config.enable_quality_processing).to be true
173
- expect(config.force_ocr).to be true
174
- end
175
-
176
- it 'loads OCR config from YAML file' do
177
- config_path = File.join(__dir__, '..', 'fixtures', 'config.yaml')
178
- config = described_class.from_file(config_path)
179
-
180
- expect(config.ocr).to be_a(Kreuzberg::Config::OCR)
181
- expect(config.ocr.backend).to eq('tesseract')
182
- expect(config.ocr.language).to eq('fra')
183
- end
184
-
185
- it 'loads chunking config from YAML file' do
186
- config_path = File.join(__dir__, '..', 'fixtures', 'config.yaml')
187
- config = described_class.from_file(config_path)
188
-
189
- expect(config.chunking).to be_a(Kreuzberg::Config::Chunking)
190
- expect(config.chunking.max_chars).to eq(750)
191
- expect(config.chunking.max_overlap).to eq(150)
192
- expect(config.chunking.preset).to eq('balanced')
193
- end
194
-
195
- it 'works with absolute paths' do
196
- config_path = File.expand_path('../fixtures/config.toml', __dir__)
197
- config = described_class.from_file(config_path)
198
-
199
- expect(config.use_cache).to be false
200
- end
201
-
202
- it 'works with relative paths' do
203
- config_path = File.join(__dir__, '..', 'fixtures', 'config.yaml')
204
- config = described_class.from_file(config_path)
205
-
206
- expect(config.use_cache).to be false
207
- end
208
-
209
- it 'raises error for non-existent file' do
210
- expect do
211
- described_class.from_file('/path/to/nonexistent/config.toml')
212
- end.to raise_error(Kreuzberg::Errors::ValidationError, /Failed to read config file/)
213
- end
214
-
215
- it 'raises error for invalid TOML file' do
216
- config_path = File.join(__dir__, '..', 'fixtures', 'invalid_config.toml')
217
- expect do
218
- described_class.from_file(config_path)
219
- end.to raise_error(Kreuzberg::Errors::ValidationError, /Invalid TOML/)
220
- end
221
-
222
- it 'detects file format from extension' do
223
- toml_path = File.join(__dir__, '..', 'fixtures', 'config.toml')
224
- yaml_path = File.join(__dir__, '..', 'fixtures', 'config.yaml')
225
-
226
- toml_config = described_class.from_file(toml_path)
227
- yaml_config = described_class.from_file(yaml_path)
228
-
229
- expect(toml_config.ocr.language).to eq('deu')
230
- expect(yaml_config.ocr.language).to eq('fra')
231
- end
232
- end
233
-
234
- it 'creates with default values' do
235
- config = described_class.new
236
-
237
- expect(config.use_cache).to be true
238
- expect(config.enable_quality_processing).to be false
239
- expect(config.force_ocr).to be false
240
- expect(config.ocr).to be_nil
241
- expect(config.chunking).to be_nil
242
- expect(config.language_detection).to be_nil
243
- expect(config.pdf_options).to be_nil
244
- end
245
-
246
- it 'creates with custom values' do
247
- ocr = Kreuzberg::Config::OCR.new(backend: 'easyocr')
248
- chunking = Kreuzberg::Config::Chunking.new(max_chars: 500)
249
- lang = Kreuzberg::Config::LanguageDetection.new(enabled: true)
250
- pdf = Kreuzberg::Config::PDF.new(extract_images: true)
251
-
252
- config = described_class.new(
253
- use_cache: false,
254
- enable_quality_processing: true,
255
- force_ocr: true,
256
- ocr: ocr,
257
- chunking: chunking,
258
- language_detection: lang,
259
- pdf_options: pdf
260
- )
261
-
262
- expect(config.use_cache).to be false
263
- expect(config.enable_quality_processing).to be true
264
- expect(config.force_ocr).to be true
265
- expect(config.ocr).to eq(ocr)
266
- expect(config.chunking).to eq(chunking)
267
- expect(config.language_detection).to eq(lang)
268
- expect(config.pdf_options).to eq(pdf)
269
- end
270
-
271
- it 'accepts hash for nested configs' do
272
- config = described_class.new(
273
- ocr: { backend: 'tesseract', language: 'eng' },
274
- chunking: { max_chars: 500 }
275
- )
276
-
277
- expect(config.ocr).to be_a(Kreuzberg::Config::OCR)
278
- expect(config.ocr.backend).to eq('tesseract')
279
- expect(config.chunking).to be_a(Kreuzberg::Config::Chunking)
280
- expect(config.chunking.max_chars).to eq(500)
281
- end
282
-
283
- it 'converts to hash' do
284
- config = described_class.new(
285
- use_cache: false,
286
- ocr: { backend: 'tesseract' }
287
- )
288
- hash = config.to_h
289
-
290
- expect(hash).to be_a(Hash)
291
- expect(hash[:use_cache]).to be false
292
- expect(hash[:ocr]).to be_a(Hash)
293
- expect(hash[:ocr][:backend]).to eq('tesseract')
294
- end
295
-
296
- it 'raises error for invalid config type' do
297
- expect do
298
- described_class.new(ocr: 'invalid')
299
- end.to raise_error(ArgumentError, /Expected.*OCR/)
300
- end
301
- end
302
-
303
- describe 'ExtractionConfig alias' do
304
- it 'exists at module level' do
305
- expect(Kreuzberg.const_defined?(:ExtractionConfig)).to be true
306
- end
307
-
308
- it 'is the same class as Config::Extraction' do
309
- expect(Kreuzberg::ExtractionConfig).to eq(Kreuzberg::Config::Extraction)
310
- end
311
-
312
- it 'can be instantiated using the alias' do
313
- config = Kreuzberg::ExtractionConfig.new(use_cache: false)
314
-
315
- expect(config).to be_a(Kreuzberg::Config::Extraction)
316
- expect(config.use_cache).to be false
317
- end
318
-
319
- it 'supports all methods through the alias' do
320
- config = Kreuzberg::ExtractionConfig.new(
321
- use_cache: false,
322
- force_ocr: true,
323
- ocr: { backend: 'tesseract', language: 'eng' }
324
- )
325
-
326
- expect(config.use_cache).to be false
327
- expect(config.force_ocr).to be true
328
- expect(config.ocr).to be_a(Kreuzberg::Config::OCR)
329
- expect(config.ocr.backend).to eq('tesseract')
330
-
331
- hash = config.to_h
332
- expect(hash[:use_cache]).to be false
333
- expect(hash[:force_ocr]).to be true
334
- end
335
-
336
- it 'supports from_file through the alias' do
337
- config_path = File.join(__dir__, '..', 'fixtures', 'config.toml')
338
- config = Kreuzberg::ExtractionConfig.from_file(config_path)
339
-
340
- expect(config).to be_a(Kreuzberg::Config::Extraction)
341
- expect(config.use_cache).to be false
342
- expect(config.enable_quality_processing).to be true
343
- end
344
- end
345
- end
1
+ # frozen_string_literal: true
2
+
3
+ RSpec.describe Kreuzberg::Config do
4
+ describe Kreuzberg::Config::OCR do
5
+ it 'creates with default values' do
6
+ ocr = described_class.new
7
+
8
+ expect(ocr.backend).to eq('tesseract')
9
+ expect(ocr.language).to eq('eng')
10
+ expect(ocr.tesseract_config).to be_nil
11
+ end
12
+
13
+ it 'creates with custom values' do
14
+ ocr = described_class.new(
15
+ backend: 'easyocr',
16
+ language: 'deu'
17
+ )
18
+
19
+ expect(ocr.backend).to eq('easyocr')
20
+ expect(ocr.language).to eq('deu')
21
+ end
22
+
23
+ it 'converts to hash' do
24
+ ocr = described_class.new(backend: 'tesseract', language: 'fra')
25
+ hash = ocr.to_h
26
+
27
+ expect(hash).to be_a(Hash)
28
+ expect(hash[:backend]).to eq('tesseract')
29
+ expect(hash[:language]).to eq('fra')
30
+ end
31
+ end
32
+
33
+ describe Kreuzberg::Config::Chunking do
34
+ it 'creates with default values' do
35
+ chunking = described_class.new
36
+
37
+ expect(chunking.max_chars).to eq(1000)
38
+ expect(chunking.max_overlap).to eq(200)
39
+ expect(chunking.preset).to be_nil
40
+ expect(chunking.embedding).to be_nil
41
+ end
42
+
43
+ it 'creates with custom values' do
44
+ chunking = described_class.new(
45
+ max_chars: 500,
46
+ max_overlap: 100,
47
+ preset: 'fast'
48
+ )
49
+
50
+ expect(chunking.max_chars).to eq(500)
51
+ expect(chunking.max_overlap).to eq(100)
52
+ expect(chunking.preset).to eq('fast')
53
+ end
54
+
55
+ it 'converts to hash' do
56
+ chunking = described_class.new(max_chars: 750)
57
+ hash = chunking.to_h
58
+
59
+ expect(hash).to be_a(Hash)
60
+ expect(hash[:max_chars]).to eq(750)
61
+ end
62
+ end
63
+
64
+ describe Kreuzberg::Config::LanguageDetection do
65
+ it 'creates with default values' do
66
+ lang = described_class.new
67
+
68
+ expect(lang.enabled).to be false
69
+ expect(lang.min_confidence).to eq(0.5)
70
+ end
71
+
72
+ it 'creates with custom values' do
73
+ lang = described_class.new(enabled: true, min_confidence: 0.9)
74
+
75
+ expect(lang.enabled).to be true
76
+ expect(lang.min_confidence).to eq(0.9)
77
+ end
78
+
79
+ it 'converts to hash' do
80
+ lang = described_class.new(enabled: true, min_confidence: 0.75)
81
+ hash = lang.to_h
82
+
83
+ expect(hash).to be_a(Hash)
84
+ expect(hash[:enabled]).to be true
85
+ expect(hash[:min_confidence]).to eq(0.75)
86
+ end
87
+ end
88
+
89
+ describe Kreuzberg::Config::PDF do
90
+ it 'creates with default values' do
91
+ pdf = described_class.new
92
+
93
+ expect(pdf.extract_images).to be false
94
+ expect(pdf.passwords).to be_nil
95
+ expect(pdf.extract_metadata).to be true
96
+ end
97
+
98
+ it 'creates with custom values' do
99
+ pdf = described_class.new(
100
+ extract_images: true,
101
+ passwords: %w[secret backup]
102
+ )
103
+
104
+ expect(pdf.extract_images).to be true
105
+ expect(pdf.passwords).to eq(%w[secret backup])
106
+ end
107
+
108
+ it 'converts to hash' do
109
+ pdf = described_class.new(extract_images: true, passwords: ['test'])
110
+ hash = pdf.to_h
111
+
112
+ expect(hash).to be_a(Hash)
113
+ expect(hash[:extract_images]).to be true
114
+ expect(hash[:passwords]).to eq(['test'])
115
+ end
116
+ end
117
+
118
+ describe Kreuzberg::Config::Extraction do
119
+ describe '.from_file' do
120
+ it 'loads configuration from TOML file' do
121
+ config_path = File.join(__dir__, '..', 'fixtures', 'config.toml')
122
+ config = described_class.from_file(config_path)
123
+
124
+ expect(config.use_cache).to be false
125
+ expect(config.enable_quality_processing).to be true
126
+ expect(config.force_ocr).to be true
127
+ end
128
+
129
+ it 'loads OCR config from TOML file' do
130
+ config_path = File.join(__dir__, '..', 'fixtures', 'config.toml')
131
+ config = described_class.from_file(config_path)
132
+
133
+ expect(config.ocr).to be_a(Kreuzberg::Config::OCR)
134
+ expect(config.ocr.backend).to eq('tesseract')
135
+ expect(config.ocr.language).to eq('deu')
136
+ end
137
+
138
+ it 'loads chunking config from TOML file' do
139
+ config_path = File.join(__dir__, '..', 'fixtures', 'config.toml')
140
+ config = described_class.from_file(config_path)
141
+
142
+ expect(config.chunking).to be_a(Kreuzberg::Config::Chunking)
143
+ expect(config.chunking.max_chars).to eq(500)
144
+ expect(config.chunking.max_overlap).to eq(100)
145
+ expect(config.chunking.preset).to eq('fast')
146
+ end
147
+
148
+ it 'loads language detection config from TOML file' do
149
+ config_path = File.join(__dir__, '..', 'fixtures', 'config.toml')
150
+ config = described_class.from_file(config_path)
151
+
152
+ expect(config.language_detection).to be_a(Kreuzberg::Config::LanguageDetection)
153
+ expect(config.language_detection.enabled).to be true
154
+ expect(config.language_detection.min_confidence).to eq(0.9)
155
+ end
156
+
157
+ it 'loads PDF options from TOML file' do
158
+ config_path = File.join(__dir__, '..', 'fixtures', 'config.toml')
159
+ config = described_class.from_file(config_path)
160
+
161
+ expect(config.pdf_options).to be_a(Kreuzberg::Config::PDF)
162
+ expect(config.pdf_options.extract_images).to be true
163
+ expect(config.pdf_options.passwords).to eq(%w[secret backup])
164
+ expect(config.pdf_options.extract_metadata).to be true
165
+ end
166
+
167
+ it 'loads configuration from YAML file' do
168
+ config_path = File.join(__dir__, '..', 'fixtures', 'config.yaml')
169
+ config = described_class.from_file(config_path)
170
+
171
+ expect(config.use_cache).to be false
172
+ expect(config.enable_quality_processing).to be true
173
+ expect(config.force_ocr).to be true
174
+ end
175
+
176
+ it 'loads OCR config from YAML file' do
177
+ config_path = File.join(__dir__, '..', 'fixtures', 'config.yaml')
178
+ config = described_class.from_file(config_path)
179
+
180
+ expect(config.ocr).to be_a(Kreuzberg::Config::OCR)
181
+ expect(config.ocr.backend).to eq('tesseract')
182
+ expect(config.ocr.language).to eq('fra')
183
+ end
184
+
185
+ it 'loads chunking config from YAML file' do
186
+ config_path = File.join(__dir__, '..', 'fixtures', 'config.yaml')
187
+ config = described_class.from_file(config_path)
188
+
189
+ expect(config.chunking).to be_a(Kreuzberg::Config::Chunking)
190
+ expect(config.chunking.max_chars).to eq(750)
191
+ expect(config.chunking.max_overlap).to eq(150)
192
+ expect(config.chunking.preset).to eq('balanced')
193
+ end
194
+
195
+ it 'works with absolute paths' do
196
+ config_path = File.expand_path('../fixtures/config.toml', __dir__)
197
+ config = described_class.from_file(config_path)
198
+
199
+ expect(config.use_cache).to be false
200
+ end
201
+
202
+ it 'works with relative paths' do
203
+ config_path = File.join(__dir__, '..', 'fixtures', 'config.yaml')
204
+ config = described_class.from_file(config_path)
205
+
206
+ expect(config.use_cache).to be false
207
+ end
208
+
209
+ it 'raises error for non-existent file' do
210
+ expect do
211
+ described_class.from_file('/path/to/nonexistent/config.toml')
212
+ end.to raise_error(Kreuzberg::Errors::ValidationError, /Failed to read config file/)
213
+ end
214
+
215
+ it 'raises error for invalid TOML file' do
216
+ config_path = File.join(__dir__, '..', 'fixtures', 'invalid_config.toml')
217
+ expect do
218
+ described_class.from_file(config_path)
219
+ end.to raise_error(Kreuzberg::Errors::ValidationError, /Invalid TOML/)
220
+ end
221
+
222
+ it 'detects file format from extension' do
223
+ toml_path = File.join(__dir__, '..', 'fixtures', 'config.toml')
224
+ yaml_path = File.join(__dir__, '..', 'fixtures', 'config.yaml')
225
+
226
+ toml_config = described_class.from_file(toml_path)
227
+ yaml_config = described_class.from_file(yaml_path)
228
+
229
+ expect(toml_config.ocr.language).to eq('deu')
230
+ expect(yaml_config.ocr.language).to eq('fra')
231
+ end
232
+ end
233
+
234
+ it 'creates with default values' do
235
+ config = described_class.new
236
+
237
+ expect(config.use_cache).to be true
238
+ expect(config.enable_quality_processing).to be false
239
+ expect(config.force_ocr).to be false
240
+ expect(config.ocr).to be_nil
241
+ expect(config.chunking).to be_nil
242
+ expect(config.language_detection).to be_nil
243
+ expect(config.pdf_options).to be_nil
244
+ end
245
+
246
+ it 'creates with custom values' do
247
+ ocr = Kreuzberg::Config::OCR.new(backend: 'easyocr')
248
+ chunking = Kreuzberg::Config::Chunking.new(max_chars: 500)
249
+ lang = Kreuzberg::Config::LanguageDetection.new(enabled: true)
250
+ pdf = Kreuzberg::Config::PDF.new(extract_images: true)
251
+
252
+ config = described_class.new(
253
+ use_cache: false,
254
+ enable_quality_processing: true,
255
+ force_ocr: true,
256
+ ocr: ocr,
257
+ chunking: chunking,
258
+ language_detection: lang,
259
+ pdf_options: pdf
260
+ )
261
+
262
+ expect(config.use_cache).to be false
263
+ expect(config.enable_quality_processing).to be true
264
+ expect(config.force_ocr).to be true
265
+ expect(config.ocr).to eq(ocr)
266
+ expect(config.chunking).to eq(chunking)
267
+ expect(config.language_detection).to eq(lang)
268
+ expect(config.pdf_options).to eq(pdf)
269
+ end
270
+
271
+ it 'accepts hash for nested configs' do
272
+ config = described_class.new(
273
+ ocr: { backend: 'tesseract', language: 'eng' },
274
+ chunking: { max_chars: 500 }
275
+ )
276
+
277
+ expect(config.ocr).to be_a(Kreuzberg::Config::OCR)
278
+ expect(config.ocr.backend).to eq('tesseract')
279
+ expect(config.chunking).to be_a(Kreuzberg::Config::Chunking)
280
+ expect(config.chunking.max_chars).to eq(500)
281
+ end
282
+
283
+ it 'converts to hash' do
284
+ config = described_class.new(
285
+ use_cache: false,
286
+ ocr: { backend: 'tesseract' }
287
+ )
288
+ hash = config.to_h
289
+
290
+ expect(hash).to be_a(Hash)
291
+ expect(hash[:use_cache]).to be false
292
+ expect(hash[:ocr]).to be_a(Hash)
293
+ expect(hash[:ocr][:backend]).to eq('tesseract')
294
+ end
295
+
296
+ it 'raises error for invalid config type' do
297
+ expect do
298
+ described_class.new(ocr: 'invalid')
299
+ end.to raise_error(ArgumentError, /Expected.*OCR/)
300
+ end
301
+ end
302
+
303
+ describe 'ExtractionConfig alias' do
304
+ it 'exists at module level' do
305
+ expect(Kreuzberg.const_defined?(:ExtractionConfig)).to be true
306
+ end
307
+
308
+ it 'is the same class as Config::Extraction' do
309
+ expect(Kreuzberg::ExtractionConfig).to eq(Kreuzberg::Config::Extraction)
310
+ end
311
+
312
+ it 'can be instantiated using the alias' do
313
+ config = Kreuzberg::ExtractionConfig.new(use_cache: false)
314
+
315
+ expect(config).to be_a(Kreuzberg::Config::Extraction)
316
+ expect(config.use_cache).to be false
317
+ end
318
+
319
+ it 'supports all methods through the alias' do
320
+ config = Kreuzberg::ExtractionConfig.new(
321
+ use_cache: false,
322
+ force_ocr: true,
323
+ ocr: { backend: 'tesseract', language: 'eng' }
324
+ )
325
+
326
+ expect(config.use_cache).to be false
327
+ expect(config.force_ocr).to be true
328
+ expect(config.ocr).to be_a(Kreuzberg::Config::OCR)
329
+ expect(config.ocr.backend).to eq('tesseract')
330
+
331
+ hash = config.to_h
332
+ expect(hash[:use_cache]).to be false
333
+ expect(hash[:force_ocr]).to be true
334
+ end
335
+
336
+ it 'supports from_file through the alias' do
337
+ config_path = File.join(__dir__, '..', 'fixtures', 'config.toml')
338
+ config = Kreuzberg::ExtractionConfig.from_file(config_path)
339
+
340
+ expect(config).to be_a(Kreuzberg::Config::Extraction)
341
+ expect(config.use_cache).to be false
342
+ expect(config.enable_quality_processing).to be true
343
+ end
344
+ end
345
+ end