kreuzberg 4.0.0.rc2 → 4.0.1

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 +391 -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 +1,285 @@
1
+ # frozen_string_literal: true
2
+
3
+ RSpec.describe Kreuzberg::Config::FontConfig 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 true
9
+ expect(config.custom_font_dirs).to be_nil
10
+ end
11
+
12
+ it 'creates config with enabled false' do
13
+ config = described_class.new(enabled: false)
14
+
15
+ expect(config.enabled).to be false
16
+ end
17
+
18
+ it 'creates config with custom_font_dirs' do
19
+ dirs = ['/usr/share/fonts', '/home/user/.fonts']
20
+ config = described_class.new(custom_font_dirs: dirs)
21
+
22
+ expect(config.custom_font_dirs).to eq dirs
23
+ end
24
+
25
+ it 'accepts single font directory as string' do
26
+ config = described_class.new(custom_font_dirs: '/usr/share/fonts')
27
+
28
+ expect(config.custom_font_dirs).to eq '/usr/share/fonts'
29
+ end
30
+
31
+ it 'accepts multiple directories as array' do
32
+ dirs = ['/fonts1', '/fonts2', '/fonts3']
33
+ config = described_class.new(custom_font_dirs: dirs)
34
+
35
+ expect(config.custom_font_dirs).to eq dirs
36
+ end
37
+
38
+ it 'converts enabled to boolean' do
39
+ config = described_class.new(enabled: 1)
40
+
41
+ expect(config.enabled).to be true
42
+ end
43
+ end
44
+
45
+ describe '#to_h' do
46
+ it 'serializes to hash with default values' do
47
+ config = described_class.new
48
+ hash = config.to_h
49
+
50
+ expect(hash).to be_a Hash
51
+ expect(hash[:enabled]).to be true
52
+ end
53
+
54
+ it 'includes custom_font_dirs when present' do
55
+ dirs = ['/fonts']
56
+ config = described_class.new(custom_font_dirs: dirs)
57
+ hash = config.to_h
58
+
59
+ expect(hash[:custom_font_dirs]).to eq dirs
60
+ end
61
+
62
+ it 'compacts nil values from hash' do
63
+ config = described_class.new(enabled: true)
64
+ hash = config.to_h
65
+
66
+ expect(hash.key?(:custom_font_dirs)).to be false
67
+ end
68
+
69
+ it 'includes both keys when both are present' do
70
+ config = described_class.new(
71
+ enabled: true,
72
+ custom_font_dirs: ['/fonts']
73
+ )
74
+ hash = config.to_h
75
+
76
+ expect(hash.keys).to contain_exactly(:enabled, :custom_font_dirs)
77
+ end
78
+ end
79
+
80
+ describe 'validation' do
81
+ it 'accepts enabled true' do
82
+ expect do
83
+ described_class.new(enabled: true)
84
+ end.not_to raise_error
85
+ end
86
+
87
+ it 'accepts enabled false' do
88
+ expect do
89
+ described_class.new(enabled: false)
90
+ end.not_to raise_error
91
+ end
92
+
93
+ it 'accepts custom_font_dirs as string' do
94
+ expect do
95
+ described_class.new(custom_font_dirs: '/fonts')
96
+ end.not_to raise_error
97
+ end
98
+
99
+ it 'accepts custom_font_dirs as array' do
100
+ expect do
101
+ described_class.new(custom_font_dirs: ['/fonts1', '/fonts2'])
102
+ end.not_to raise_error
103
+ end
104
+ end
105
+
106
+ describe 'keyword arguments' do
107
+ it 'accepts all keyword arguments' do
108
+ dirs = ['/fonts']
109
+ config = described_class.new(
110
+ enabled: false,
111
+ custom_font_dirs: dirs
112
+ )
113
+
114
+ expect(config.enabled).to be false
115
+ expect(config.custom_font_dirs).to eq dirs
116
+ end
117
+ end
118
+
119
+ describe 'equality' do
120
+ it 'compares configs by value' do
121
+ config1 = described_class.new(
122
+ enabled: true,
123
+ custom_font_dirs: ['/fonts']
124
+ )
125
+ config2 = described_class.new(
126
+ enabled: true,
127
+ custom_font_dirs: ['/fonts']
128
+ )
129
+
130
+ expect(config1.enabled).to eq config2.enabled
131
+ expect(config1.custom_font_dirs).to eq config2.custom_font_dirs
132
+ end
133
+
134
+ it 'detects differences in enabled' do
135
+ config1 = described_class.new(enabled: true)
136
+ config2 = described_class.new(enabled: false)
137
+
138
+ expect(config1.enabled).not_to eq config2.enabled
139
+ end
140
+
141
+ it 'detects differences in custom_font_dirs' do
142
+ config1 = described_class.new(custom_font_dirs: ['/fonts1'])
143
+ config2 = described_class.new(custom_font_dirs: ['/fonts2'])
144
+
145
+ expect(config1.custom_font_dirs).not_to eq config2.custom_font_dirs
146
+ end
147
+ end
148
+
149
+ describe 'nested config integration' do
150
+ it 'can be nested in PDF config' do
151
+ font_config = described_class.new(enabled: true, custom_font_dirs: ['/fonts'])
152
+ pdf = Kreuzberg::Config::PDF.new(font_config: font_config)
153
+
154
+ expect(pdf.font_config).to be_a described_class
155
+ expect(pdf.font_config.enabled).to be true
156
+ expect(pdf.font_config.custom_font_dirs).to eq ['/fonts']
157
+ end
158
+
159
+ it 'accepts hash in PDF config' do
160
+ pdf = Kreuzberg::Config::PDF.new(
161
+ font_config: { enabled: true, custom_font_dirs: ['/fonts'] }
162
+ )
163
+
164
+ expect(pdf.font_config).to be_a described_class
165
+ expect(pdf.font_config.enabled).to be true
166
+ expect(pdf.font_config.custom_font_dirs).to eq ['/fonts']
167
+ end
168
+
169
+ it 'can be nested in Extraction config via PDF' do
170
+ extraction = Kreuzberg::Config::Extraction.new(
171
+ pdf_options: { font_config: { enabled: true } }
172
+ )
173
+
174
+ expect(extraction.pdf_options.font_config).to be_a described_class
175
+ expect(extraction.pdf_options.font_config.enabled).to be true
176
+ end
177
+ end
178
+
179
+ describe 'symbol vs string key handling' do
180
+ it 'converts symbol enabled to boolean' do
181
+ config = described_class.new(enabled: true)
182
+
183
+ expect(config.enabled).to be true
184
+ end
185
+
186
+ it 'preserves custom_font_dirs as array' do
187
+ dirs = ['/fonts1', '/fonts2']
188
+ config = described_class.new(custom_font_dirs: dirs)
189
+
190
+ expect(config.custom_font_dirs).to eq dirs
191
+ end
192
+ end
193
+
194
+ describe 'boolean conversion' do
195
+ it 'converts truthy enabled to true' do
196
+ config = described_class.new(enabled: 1)
197
+
198
+ expect(config.enabled).to be true
199
+ end
200
+
201
+ it 'converts false enabled to false' do
202
+ config = described_class.new(enabled: false)
203
+
204
+ expect(config.enabled).to be false
205
+ end
206
+
207
+ it 'converts string yes to true' do
208
+ config = described_class.new(enabled: 'yes')
209
+
210
+ expect(config.enabled).to be true
211
+ end
212
+
213
+ it 'converts nil to false' do
214
+ config = described_class.new(enabled: nil)
215
+
216
+ expect(config.enabled).to be false
217
+ end
218
+ end
219
+
220
+ describe 'font directory handling' do
221
+ it 'stores single directory path as string' do
222
+ config = described_class.new(custom_font_dirs: '/usr/share/fonts')
223
+
224
+ expect(config.custom_font_dirs).to eq '/usr/share/fonts'
225
+ end
226
+
227
+ it 'stores multiple directories as array' do
228
+ dirs = ['/fonts1', '/fonts2', '/fonts3']
229
+ config = described_class.new(custom_font_dirs: dirs)
230
+
231
+ expect(config.custom_font_dirs).to eq dirs
232
+ expect(config.custom_font_dirs).to be_a Array
233
+ end
234
+
235
+ it 'preserves exact directory paths' do
236
+ dir = '/home/user/.local/share/fonts'
237
+ config = described_class.new(custom_font_dirs: dir)
238
+
239
+ expect(config.custom_font_dirs).to eq dir
240
+ end
241
+
242
+ it 'preserves array of directory paths' do
243
+ dirs = ['/usr/share/fonts', '/home/user/.fonts', '~/.local/share/fonts']
244
+ config = described_class.new(custom_font_dirs: dirs)
245
+
246
+ expect(config.custom_font_dirs).to eq dirs
247
+ end
248
+ end
249
+
250
+ describe 'mutability' do
251
+ it 'allows modification of enabled' do
252
+ config = described_class.new(enabled: true)
253
+ config.enabled = false
254
+
255
+ expect(config.enabled).to be false
256
+ end
257
+
258
+ it 'allows modification of custom_font_dirs' do
259
+ config = described_class.new(custom_font_dirs: ['/fonts1'])
260
+ config.custom_font_dirs = ['/fonts2']
261
+
262
+ expect(config.custom_font_dirs).to eq ['/fonts2']
263
+ end
264
+ end
265
+
266
+ describe 'default behavior' do
267
+ it 'defaults to enabled' do
268
+ config = described_class.new
269
+
270
+ expect(config.enabled).to be true
271
+ end
272
+
273
+ it 'defaults to no custom font directories' do
274
+ config = described_class.new
275
+
276
+ expect(config.custom_font_dirs).to be_nil
277
+ end
278
+
279
+ it 'allows disabling font support' do
280
+ config = described_class.new(enabled: false)
281
+
282
+ expect(config.enabled).to be false
283
+ end
284
+ end
285
+ end
@@ -0,0 +1,314 @@
1
+ # frozen_string_literal: true
2
+
3
+ RSpec.describe Kreuzberg::Config::Hierarchy 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 true
9
+ expect(config.k_clusters).to eq 6
10
+ expect(config.include_bbox).to be true
11
+ expect(config.ocr_coverage_threshold).to be_nil
12
+ end
13
+
14
+ it 'creates config with custom values' do
15
+ config = described_class.new(
16
+ enabled: false,
17
+ k_clusters: 10,
18
+ include_bbox: false,
19
+ ocr_coverage_threshold: 0.95
20
+ )
21
+
22
+ expect(config.enabled).to be false
23
+ expect(config.k_clusters).to eq 10
24
+ expect(config.include_bbox).to be false
25
+ expect(config.ocr_coverage_threshold).to eq 0.95
26
+ end
27
+
28
+ it 'converts k_clusters to integer' do
29
+ config = described_class.new(k_clusters: '8')
30
+
31
+ expect(config.k_clusters).to eq 8
32
+ expect(config.k_clusters).to be_a Integer
33
+ end
34
+
35
+ it 'converts enabled to boolean' do
36
+ config = described_class.new(enabled: 1)
37
+
38
+ expect(config.enabled).to be true
39
+ end
40
+
41
+ it 'converts include_bbox to boolean' do
42
+ config = described_class.new(include_bbox: false)
43
+
44
+ expect(config.include_bbox).to be false
45
+ end
46
+
47
+ it 'converts ocr_coverage_threshold to float' do
48
+ config = described_class.new(ocr_coverage_threshold: '0.85')
49
+
50
+ expect(config.ocr_coverage_threshold).to eq 0.85
51
+ expect(config.ocr_coverage_threshold).to be_a Float
52
+ end
53
+ end
54
+
55
+ describe '#to_h' do
56
+ it 'serializes to hash with all values' do
57
+ config = described_class.new(
58
+ enabled: true,
59
+ k_clusters: 8,
60
+ include_bbox: true
61
+ )
62
+ hash = config.to_h
63
+
64
+ expect(hash).to be_a Hash
65
+ expect(hash[:enabled]).to be true
66
+ expect(hash[:k_clusters]).to eq 8
67
+ expect(hash[:include_bbox]).to be true
68
+ end
69
+
70
+ it 'includes ocr_coverage_threshold when present' do
71
+ config = described_class.new(ocr_coverage_threshold: 0.9)
72
+ hash = config.to_h
73
+
74
+ expect(hash[:ocr_coverage_threshold]).to eq 0.9
75
+ end
76
+
77
+ it 'compacts nil values from hash' do
78
+ config = described_class.new(enabled: true)
79
+ hash = config.to_h
80
+
81
+ expect(hash.key?(:ocr_coverage_threshold)).to be false
82
+ end
83
+ end
84
+
85
+ describe '.from_h' do
86
+ it 'creates from hash' do
87
+ hash = { enabled: true, k_clusters: 8 }
88
+ config = described_class.from_h(hash)
89
+
90
+ expect(config).to be_a described_class
91
+ expect(config.enabled).to be true
92
+ expect(config.k_clusters).to eq 8
93
+ end
94
+
95
+ it 'returns nil for nil input' do
96
+ config = described_class.from_h(nil)
97
+
98
+ expect(config).to be_nil
99
+ end
100
+
101
+ it 'returns instance as-is' do
102
+ original = described_class.new(k_clusters: 10)
103
+ config = described_class.from_h(original)
104
+
105
+ expect(config).to be original
106
+ end
107
+
108
+ it 'converts symbol keys in hash' do
109
+ hash = { 'enabled' => true, 'k_clusters' => 8 }
110
+ config = described_class.from_h(hash)
111
+
112
+ expect(config.enabled).to be true
113
+ expect(config.k_clusters).to eq 8
114
+ end
115
+ end
116
+
117
+ describe 'validation' do
118
+ it 'accepts valid k_clusters' do
119
+ expect do
120
+ described_class.new(k_clusters: 5)
121
+ end.not_to raise_error
122
+ end
123
+
124
+ it 'accepts valid ocr_coverage_threshold' do
125
+ expect do
126
+ described_class.new(ocr_coverage_threshold: 0.8)
127
+ end.not_to raise_error
128
+ end
129
+
130
+ it 'accepts enabled true' do
131
+ expect do
132
+ described_class.new(enabled: true)
133
+ end.not_to raise_error
134
+ end
135
+ end
136
+
137
+ describe 'keyword arguments' do
138
+ it 'accepts all keyword arguments' do
139
+ config = described_class.new(
140
+ enabled: false,
141
+ k_clusters: 12,
142
+ include_bbox: false,
143
+ ocr_coverage_threshold: 0.75
144
+ )
145
+
146
+ expect(config.enabled).to be false
147
+ expect(config.k_clusters).to eq 12
148
+ expect(config.include_bbox).to be false
149
+ expect(config.ocr_coverage_threshold).to eq 0.75
150
+ end
151
+ end
152
+
153
+ describe 'equality' do
154
+ it 'compares configs by value' do
155
+ config1 = described_class.new(
156
+ enabled: true,
157
+ k_clusters: 8
158
+ )
159
+ config2 = described_class.new(
160
+ enabled: true,
161
+ k_clusters: 8
162
+ )
163
+
164
+ expect(config1.enabled).to eq config2.enabled
165
+ expect(config1.k_clusters).to eq config2.k_clusters
166
+ end
167
+
168
+ it 'detects differences in enabled' do
169
+ config1 = described_class.new(enabled: true)
170
+ config2 = described_class.new(enabled: false)
171
+
172
+ expect(config1.enabled).not_to eq config2.enabled
173
+ end
174
+
175
+ it 'detects differences in k_clusters' do
176
+ config1 = described_class.new(k_clusters: 6)
177
+ config2 = described_class.new(k_clusters: 10)
178
+
179
+ expect(config1.k_clusters).not_to eq config2.k_clusters
180
+ end
181
+
182
+ it 'detects differences in ocr_coverage_threshold' do
183
+ config1 = described_class.new(ocr_coverage_threshold: 0.8)
184
+ config2 = described_class.new(ocr_coverage_threshold: 0.9)
185
+
186
+ expect(config1.ocr_coverage_threshold).not_to eq config2.ocr_coverage_threshold
187
+ end
188
+ end
189
+
190
+ describe 'nested config integration' do
191
+ it 'can be nested in PDF config' do
192
+ hierarchy = described_class.new(k_clusters: 8, enabled: true)
193
+ pdf = Kreuzberg::Config::PDF.new(hierarchy: hierarchy)
194
+
195
+ expect(pdf.hierarchy).to be_a described_class
196
+ expect(pdf.hierarchy.k_clusters).to eq 8
197
+ expect(pdf.hierarchy.enabled).to be true
198
+ end
199
+
200
+ it 'accepts hash in PDF config' do
201
+ pdf = Kreuzberg::Config::PDF.new(
202
+ hierarchy: { enabled: true, k_clusters: 10 }
203
+ )
204
+
205
+ expect(pdf.hierarchy).to be_a described_class
206
+ expect(pdf.hierarchy.enabled).to be true
207
+ expect(pdf.hierarchy.k_clusters).to eq 10
208
+ end
209
+
210
+ it 'can be nested in Extraction config via PDF' do
211
+ extraction = Kreuzberg::Config::Extraction.new(
212
+ pdf_options: { hierarchy: { k_clusters: 8 } }
213
+ )
214
+
215
+ expect(extraction.pdf_options.hierarchy).to be_a described_class
216
+ expect(extraction.pdf_options.hierarchy.k_clusters).to eq 8
217
+ end
218
+ end
219
+
220
+ describe 'symbol vs string key handling' do
221
+ it 'converts symbol enabled to boolean' do
222
+ config = described_class.new(enabled: true)
223
+
224
+ expect(config.enabled).to be true
225
+ end
226
+
227
+ it 'converts k_clusters string to integer' do
228
+ config = described_class.new(k_clusters: '12')
229
+
230
+ expect(config.k_clusters).to eq 12
231
+ expect(config.k_clusters).to be_a Integer
232
+ end
233
+ end
234
+
235
+ describe 'boolean conversion' do
236
+ it 'converts truthy enabled to true' do
237
+ config = described_class.new(enabled: 1)
238
+
239
+ expect(config.enabled).to be true
240
+ end
241
+
242
+ it 'converts false enabled to false' do
243
+ config = described_class.new(enabled: false)
244
+
245
+ expect(config.enabled).to be false
246
+ end
247
+
248
+ it 'converts truthy include_bbox to true' do
249
+ config = described_class.new(include_bbox: 'yes')
250
+
251
+ expect(config.include_bbox).to be true
252
+ end
253
+
254
+ it 'converts false include_bbox to false' do
255
+ config = described_class.new(include_bbox: false)
256
+
257
+ expect(config.include_bbox).to be false
258
+ end
259
+ end
260
+
261
+ describe 'k_clusters parameter' do
262
+ it 'accepts small k_clusters' do
263
+ config = described_class.new(k_clusters: 3)
264
+
265
+ expect(config.k_clusters).to eq 3
266
+ end
267
+
268
+ it 'accepts large k_clusters' do
269
+ config = described_class.new(k_clusters: 20)
270
+
271
+ expect(config.k_clusters).to eq 20
272
+ end
273
+
274
+ it 'defaults to 6 clusters' do
275
+ config = described_class.new
276
+
277
+ expect(config.k_clusters).to eq 6
278
+ end
279
+
280
+ it 'converts string k_clusters to integer' do
281
+ config = described_class.new(k_clusters: '15')
282
+
283
+ expect(config.k_clusters).to eq 15
284
+ expect(config.k_clusters).to be_a Integer
285
+ end
286
+ end
287
+
288
+ describe 'ocr_coverage_threshold' do
289
+ it 'accepts high threshold values' do
290
+ config = described_class.new(ocr_coverage_threshold: 0.95)
291
+
292
+ expect(config.ocr_coverage_threshold).to eq 0.95
293
+ end
294
+
295
+ it 'accepts low threshold values' do
296
+ config = described_class.new(ocr_coverage_threshold: 0.1)
297
+
298
+ expect(config.ocr_coverage_threshold).to eq 0.1
299
+ end
300
+
301
+ it 'accepts nil for threshold' do
302
+ config = described_class.new(ocr_coverage_threshold: nil)
303
+
304
+ expect(config.ocr_coverage_threshold).to be_nil
305
+ end
306
+
307
+ it 'converts string threshold to float' do
308
+ config = described_class.new(ocr_coverage_threshold: '0.85')
309
+
310
+ expect(config.ocr_coverage_threshold).to eq 0.85
311
+ expect(config.ocr_coverage_threshold).to be_a Float
312
+ end
313
+ end
314
+ end