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
@@ -1,439 +1,415 @@
1
- //! Configuration loading integration tests.
2
- //!
3
- //! Tests the config loading APIs:
4
- //! - from_file() with TOML/YAML/JSON
5
- //! - discover() for searching parent directories
6
- //! - Error handling for invalid configs
7
-
8
- use kreuzberg::KreuzbergError;
9
- use kreuzberg::core::config::ExtractionConfig;
10
- use std::fs;
11
- use tempfile::TempDir;
12
-
13
- /// Test loading config from TOML file.
14
- #[test]
15
- fn test_from_file_toml_succeeds() {
16
- let temp_dir = TempDir::new().unwrap();
17
- let config_path = temp_dir.path().join("config.toml");
18
-
19
- let toml_content = r#"
20
- [ocr]
21
- enabled = true
22
- backend = "tesseract"
23
-
24
- [chunking]
25
- max_chars = 1000
26
- max_overlap = 100
27
- "#;
28
-
29
- fs::write(&config_path, toml_content).unwrap();
30
-
31
- let config = ExtractionConfig::from_file(&config_path);
32
- assert!(config.is_ok(), "Should load TOML config successfully");
33
-
34
- let config = config.unwrap();
35
- assert!(config.ocr.is_some(), "Should have OCR config");
36
- assert!(config.chunking.is_some(), "Should have chunking config");
37
-
38
- let chunking = config.chunking.unwrap();
39
- assert_eq!(chunking.max_chars, 1000);
40
- assert_eq!(chunking.max_overlap, 100);
41
- }
42
-
43
- /// Test loading config from YAML file.
44
- #[test]
45
- fn test_from_file_yaml_succeeds() {
46
- let temp_dir = TempDir::new().unwrap();
47
- let config_path = temp_dir.path().join("config.yaml");
48
-
49
- let yaml_content = r#"
50
- ocr:
51
- enabled: true
52
- backend: tesseract
53
- chunking:
54
- max_chars: 1000
55
- max_overlap: 100
56
- "#;
57
-
58
- fs::write(&config_path, yaml_content).unwrap();
59
-
60
- let config = ExtractionConfig::from_file(&config_path);
61
- assert!(config.is_ok(), "Should load YAML config successfully");
62
-
63
- let config = config.unwrap();
64
- assert!(config.ocr.is_some(), "Should have OCR config");
65
- assert!(config.chunking.is_some(), "Should have chunking config");
66
-
67
- let chunking = config.chunking.unwrap();
68
- assert_eq!(chunking.max_chars, 1000);
69
- assert_eq!(chunking.max_overlap, 100);
70
- }
71
-
72
- /// Test loading config from JSON file.
73
- #[test]
74
- fn test_from_file_json_succeeds() {
75
- let temp_dir = TempDir::new().unwrap();
76
- let config_path = temp_dir.path().join("config.json");
77
-
78
- let json_content = r#"
79
- {
80
- "ocr": {
81
- "enabled": true,
82
- "backend": "tesseract"
83
- },
84
- "chunking": {
85
- "max_chars": 1000,
86
- "max_overlap": 100
87
- }
88
- }
89
- "#;
90
-
91
- fs::write(&config_path, json_content).unwrap();
92
-
93
- let config = ExtractionConfig::from_file(&config_path);
94
- assert!(config.is_ok(), "Should load JSON config successfully");
95
-
96
- let config = config.unwrap();
97
- assert!(config.ocr.is_some(), "Should have OCR config");
98
- assert!(config.chunking.is_some(), "Should have chunking config");
99
-
100
- let chunking = config.chunking.unwrap();
101
- assert_eq!(chunking.max_chars, 1000);
102
- assert_eq!(chunking.max_overlap, 100);
103
- }
104
-
105
- /// Test loading config from .yml extension.
106
- #[test]
107
- fn test_from_file_yml_extension_succeeds() {
108
- let temp_dir = TempDir::new().unwrap();
109
- let config_path = temp_dir.path().join("config.yml");
110
-
111
- let yml_content = r#"
112
- ocr:
113
- enabled: true
114
- "#;
115
-
116
- fs::write(&config_path, yml_content).unwrap();
117
-
118
- let config = ExtractionConfig::from_file(&config_path);
119
- assert!(config.is_ok(), "Should load .yml config successfully");
120
- }
121
-
122
- /// Test from_file with nonexistent path fails.
123
- #[test]
124
- fn test_from_file_nonexistent_path_fails() {
125
- let result = ExtractionConfig::from_file("/nonexistent/path/config.toml");
126
- assert!(result.is_err(), "Should fail for nonexistent path: {:?}", result);
127
- // Error can be Io or other types depending on the implementation
128
- }
129
-
130
- /// Test from_file with malformed TOML fails.
131
- #[test]
132
- fn test_from_file_malformed_toml_fails() {
133
- let temp_dir = TempDir::new().unwrap();
134
- let config_path = temp_dir.path().join("config.toml");
135
-
136
- let malformed_toml = r#"
137
- [ocr
138
- enabled = true
139
- "#;
140
-
141
- fs::write(&config_path, malformed_toml).unwrap();
142
-
143
- let result = ExtractionConfig::from_file(&config_path);
144
- assert!(result.is_err(), "Should fail for malformed TOML: {:?}", result);
145
- // Error handling varies - just ensure it failed
146
- }
147
-
148
- /// Test from_file with malformed JSON fails.
149
- #[test]
150
- fn test_from_file_malformed_json_fails() {
151
- let temp_dir = TempDir::new().unwrap();
152
- let config_path = temp_dir.path().join("config.json");
153
-
154
- let malformed_json = r#"
155
- {
156
- "ocr": {
157
- "enabled": true
158
- }
159
- "chunking": {}
160
- }
161
- "#;
162
-
163
- fs::write(&config_path, malformed_json).unwrap();
164
-
165
- let result = ExtractionConfig::from_file(&config_path);
166
- assert!(result.is_err(), "Should fail for malformed JSON: {:?}", result);
167
- // Error handling varies - just ensure it failed
168
- }
169
-
170
- /// Test from_file with malformed YAML fails.
171
- #[test]
172
- fn test_from_file_malformed_yaml_fails() {
173
- let temp_dir = TempDir::new().unwrap();
174
- let config_path = temp_dir.path().join("config.yaml");
175
-
176
- let malformed_yaml = r#"
177
- ocr:
178
- enabled: true
179
- - invalid_list
180
- "#;
181
-
182
- fs::write(&config_path, malformed_yaml).unwrap();
183
-
184
- let result = ExtractionConfig::from_file(&config_path);
185
- assert!(result.is_err(), "Should fail for malformed YAML: {:?}", result);
186
- // Error handling varies - just ensure it failed
187
- }
188
-
189
- /// Test from_file with empty file uses defaults.
190
- #[test]
191
- fn test_from_file_empty_file_uses_defaults() {
192
- let temp_dir = TempDir::new().unwrap();
193
- let config_path = temp_dir.path().join("config.toml");
194
-
195
- fs::write(&config_path, "").unwrap();
196
-
197
- let config = ExtractionConfig::from_file(&config_path);
198
- assert!(config.is_ok(), "Should load empty file successfully");
199
-
200
- let config = config.unwrap();
201
- // Should have default values
202
- assert!(config.ocr.is_none(), "Default config should have no OCR");
203
- assert!(config.chunking.is_none(), "Default config should have no chunking");
204
- }
205
-
206
- /// Test from_file with unsupported extension fails.
207
- #[test]
208
- fn test_from_file_unsupported_extension_fails() {
209
- let temp_dir = TempDir::new().unwrap();
210
- let config_path = temp_dir.path().join("config.txt");
211
-
212
- fs::write(&config_path, "ocr:\n enabled: true").unwrap();
213
-
214
- let result = ExtractionConfig::from_file(&config_path);
215
- assert!(result.is_err(), "Should fail for unsupported extension: {:?}", result);
216
-
217
- match result {
218
- Err(KreuzbergError::Validation { message, .. }) => {
219
- assert!(
220
- message.contains("format") || message.contains("extension") || message.contains("Unsupported"),
221
- "Error should mention format/extension: {}",
222
- message
223
- );
224
- }
225
- _ => {
226
- // Some other error is also acceptable
227
- }
228
- }
229
- }
230
-
231
- /// Test discover() finds config in current directory.
232
- #[test]
233
- fn test_discover_finds_config_in_current_dir() {
234
- let temp_dir = TempDir::new().unwrap();
235
- let config_path = temp_dir.path().join("kreuzberg.toml");
236
-
237
- let toml_content = r#"
238
- [ocr]
239
- enabled = true
240
- "#;
241
-
242
- fs::write(&config_path, toml_content).unwrap();
243
-
244
- // Change to temp directory
245
- let original_dir = std::env::current_dir().unwrap();
246
- std::env::set_current_dir(temp_dir.path()).unwrap();
247
-
248
- let result = ExtractionConfig::discover();
249
-
250
- // Restore original directory
251
- std::env::set_current_dir(original_dir).unwrap();
252
-
253
- assert!(result.is_ok(), "Discover should succeed");
254
- let config = result.unwrap();
255
- assert!(config.is_some(), "Should find config in current directory");
256
- assert!(config.unwrap().ocr.is_some(), "Should have OCR config");
257
- }
258
-
259
- /// Test discover() finds config in parent directory.
260
- #[test]
261
- fn test_discover_finds_config_in_parent_dir() {
262
- let temp_dir = TempDir::new().unwrap();
263
- let config_path = temp_dir.path().join("kreuzberg.toml");
264
-
265
- let toml_content = r#"
266
- [ocr]
267
- enabled = true
268
- "#;
269
-
270
- fs::write(&config_path, toml_content).unwrap();
271
-
272
- // Create subdirectory
273
- let sub_dir = temp_dir.path().join("subdir");
274
- fs::create_dir(&sub_dir).unwrap();
275
-
276
- // Change to subdirectory
277
- let original_dir = std::env::current_dir().unwrap();
278
- std::env::set_current_dir(&sub_dir).unwrap();
279
-
280
- let result = ExtractionConfig::discover();
281
-
282
- // Restore original directory
283
- std::env::set_current_dir(original_dir).unwrap();
284
-
285
- assert!(result.is_ok(), "Discover should succeed");
286
- let config = result.unwrap();
287
- assert!(config.is_some(), "Should find config in parent directory");
288
- assert!(config.unwrap().ocr.is_some(), "Should have OCR config");
289
- }
290
-
291
- /// Test discover() returns None when no config found.
292
- #[test]
293
- fn test_discover_returns_none_when_not_found() {
294
- let temp_dir = TempDir::new().unwrap();
295
- let sub_dir = temp_dir.path().join("subdir");
296
- fs::create_dir(&sub_dir).unwrap();
297
-
298
- // Change to subdirectory (no config files)
299
- let original_dir = std::env::current_dir().unwrap();
300
- std::env::set_current_dir(&sub_dir).unwrap();
301
-
302
- let result = ExtractionConfig::discover();
303
-
304
- // Restore original directory
305
- std::env::set_current_dir(original_dir).unwrap();
306
-
307
- assert!(result.is_ok(), "Discover should succeed even when no config found");
308
- let _config = result.unwrap();
309
- // May return None or may find a config in parent directories (e.g., repository root)
310
- // Just verify it doesn't error - the specific behavior depends on the directory structure
311
- }
312
-
313
- /// Test discover() prefers certain file names.
314
- #[test]
315
- fn test_discover_file_name_preference() {
316
- let temp_dir = TempDir::new().unwrap();
317
-
318
- // Create multiple config files
319
- fs::write(temp_dir.path().join("kreuzberg.toml"), "[ocr]\nenabled = true").unwrap();
320
- fs::write(temp_dir.path().join(".kreuzberg.toml"), "[ocr]\nenabled = false").unwrap();
321
-
322
- let original_dir = std::env::current_dir().unwrap();
323
- if std::env::set_current_dir(temp_dir.path()).is_err() {
324
- // Skip this test if we can't change directory
325
- return;
326
- }
327
-
328
- let result = ExtractionConfig::discover();
329
-
330
- // Always restore directory even if test fails
331
- let _ = std::env::set_current_dir(original_dir);
332
-
333
- assert!(result.is_ok(), "Discover should succeed");
334
- let config = result.unwrap();
335
- assert!(config.is_some(), "Should find a config file");
336
- }
337
-
338
- /// Test discover() with nested directories.
339
- #[test]
340
- fn test_discover_with_nested_directories() {
341
- let temp_dir = TempDir::new().unwrap();
342
- let config_path = temp_dir.path().join("kreuzberg.toml");
343
-
344
- let toml_content = r#"
345
- [ocr]
346
- enabled = true
347
- "#;
348
-
349
- fs::write(&config_path, toml_content).unwrap();
350
-
351
- // Create nested subdirectories
352
- let level1 = temp_dir.path().join("level1");
353
- let level2 = level1.join("level2");
354
- let level3 = level2.join("level3");
355
- fs::create_dir_all(&level3).unwrap();
356
-
357
- // Change to deepest directory
358
- let original_dir = std::env::current_dir().unwrap();
359
- if std::env::set_current_dir(&level3).is_err() {
360
- // Skip this test if we can't change directory
361
- return;
362
- }
363
-
364
- let result = ExtractionConfig::discover();
365
-
366
- // Always restore directory even if test fails
367
- let _ = std::env::set_current_dir(&original_dir);
368
-
369
- assert!(result.is_ok(), "Discover should succeed");
370
- let config = result.unwrap();
371
- assert!(config.is_some(), "Should find config in ancestor directory");
372
- assert!(config.unwrap().ocr.is_some(), "Should have OCR config");
373
- }
374
-
375
- /// Test config loading with all supported features.
376
- #[test]
377
- fn test_from_file_comprehensive_config() {
378
- let temp_dir = TempDir::new().unwrap();
379
- let config_path = temp_dir.path().join("config.toml");
380
-
381
- let toml_content = r#"
382
- [ocr]
383
- enabled = true
384
- backend = "tesseract"
385
-
386
- [chunking]
387
- max_chars = 2000
388
- max_overlap = 200
389
-
390
- [language_detection]
391
- enabled = true
392
-
393
- [images]
394
- enabled = true
395
-
396
- [pdf_options]
397
- extract_images = true
398
- "#;
399
-
400
- fs::write(&config_path, toml_content).unwrap();
401
-
402
- let config = ExtractionConfig::from_file(&config_path);
403
- assert!(config.is_ok(), "Should load comprehensive config successfully");
404
-
405
- let config = config.unwrap();
406
- assert!(config.ocr.is_some(), "Should have OCR config");
407
- assert!(config.chunking.is_some(), "Should have chunking config");
408
- assert!(
409
- config.language_detection.is_some(),
410
- "Should have language detection config"
411
- );
412
- assert!(config.images.is_some(), "Should have image extraction config");
413
- assert!(config.pdf_options.is_some(), "Should have PDF config");
414
- }
415
-
416
- /// Test config validation with invalid values.
417
- #[test]
418
- fn test_from_file_with_invalid_values() {
419
- let temp_dir = TempDir::new().unwrap();
420
- let config_path = temp_dir.path().join("config.toml");
421
-
422
- // Negative values should be rejected during deserialization or validation
423
- let toml_content = r#"
424
- [chunking]
425
- max_chars = -1000
426
- max_overlap = -100
427
- "#;
428
-
429
- fs::write(&config_path, toml_content).unwrap();
430
-
431
- let result = ExtractionConfig::from_file(&config_path);
432
- // Should either fail parsing or have clamped values
433
- if let Ok(config) = result {
434
- // If it succeeds, values should be reasonable
435
- if let Some(chunking) = config.chunking {
436
- assert!(chunking.max_chars > 0, "max_chars should be positive");
437
- }
438
- }
439
- }
1
+ //! Configuration loading integration tests.
2
+ //!
3
+ //! Tests the config loading APIs:
4
+ //! - from_file() with TOML/YAML/JSON
5
+ //! - discover() for searching parent directories
6
+ //! - Error handling for invalid configs
7
+
8
+ use kreuzberg::KreuzbergError;
9
+ use kreuzberg::core::config::ExtractionConfig;
10
+ use std::fs;
11
+ use tempfile::TempDir;
12
+
13
+ /// Test loading config from TOML file.
14
+ #[test]
15
+ fn test_from_file_toml_succeeds() {
16
+ let temp_dir = TempDir::new().unwrap();
17
+ let config_path = temp_dir.path().join("config.toml");
18
+
19
+ let toml_content = r#"
20
+ [ocr]
21
+ enabled = true
22
+ backend = "tesseract"
23
+
24
+ [chunking]
25
+ max_chars = 1000
26
+ max_overlap = 100
27
+ "#;
28
+
29
+ fs::write(&config_path, toml_content).unwrap();
30
+
31
+ let config = ExtractionConfig::from_file(&config_path);
32
+ assert!(config.is_ok(), "Should load TOML config successfully");
33
+
34
+ let config = config.unwrap();
35
+ assert!(config.ocr.is_some(), "Should have OCR config");
36
+ assert!(config.chunking.is_some(), "Should have chunking config");
37
+
38
+ let chunking = config.chunking.unwrap();
39
+ assert_eq!(chunking.max_chars, 1000);
40
+ assert_eq!(chunking.max_overlap, 100);
41
+ }
42
+
43
+ /// Test loading config from YAML file.
44
+ #[test]
45
+ fn test_from_file_yaml_succeeds() {
46
+ let temp_dir = TempDir::new().unwrap();
47
+ let config_path = temp_dir.path().join("config.yaml");
48
+
49
+ let yaml_content = r#"
50
+ ocr:
51
+ enabled: true
52
+ backend: tesseract
53
+ chunking:
54
+ max_chars: 1000
55
+ max_overlap: 100
56
+ "#;
57
+
58
+ fs::write(&config_path, yaml_content).unwrap();
59
+
60
+ let config = ExtractionConfig::from_file(&config_path);
61
+ assert!(config.is_ok(), "Should load YAML config successfully");
62
+
63
+ let config = config.unwrap();
64
+ assert!(config.ocr.is_some(), "Should have OCR config");
65
+ assert!(config.chunking.is_some(), "Should have chunking config");
66
+
67
+ let chunking = config.chunking.unwrap();
68
+ assert_eq!(chunking.max_chars, 1000);
69
+ assert_eq!(chunking.max_overlap, 100);
70
+ }
71
+
72
+ /// Test loading config from JSON file.
73
+ #[test]
74
+ fn test_from_file_json_succeeds() {
75
+ let temp_dir = TempDir::new().unwrap();
76
+ let config_path = temp_dir.path().join("config.json");
77
+
78
+ let json_content = r#"
79
+ {
80
+ "ocr": {
81
+ "enabled": true,
82
+ "backend": "tesseract"
83
+ },
84
+ "chunking": {
85
+ "max_chars": 1000,
86
+ "max_overlap": 100
87
+ }
88
+ }
89
+ "#;
90
+
91
+ fs::write(&config_path, json_content).unwrap();
92
+
93
+ let config = ExtractionConfig::from_file(&config_path);
94
+ assert!(config.is_ok(), "Should load JSON config successfully");
95
+
96
+ let config = config.unwrap();
97
+ assert!(config.ocr.is_some(), "Should have OCR config");
98
+ assert!(config.chunking.is_some(), "Should have chunking config");
99
+
100
+ let chunking = config.chunking.unwrap();
101
+ assert_eq!(chunking.max_chars, 1000);
102
+ assert_eq!(chunking.max_overlap, 100);
103
+ }
104
+
105
+ /// Test loading config from .yml extension.
106
+ #[test]
107
+ fn test_from_file_yml_extension_succeeds() {
108
+ let temp_dir = TempDir::new().unwrap();
109
+ let config_path = temp_dir.path().join("config.yml");
110
+
111
+ let yml_content = r#"
112
+ ocr:
113
+ enabled: true
114
+ "#;
115
+
116
+ fs::write(&config_path, yml_content).unwrap();
117
+
118
+ let config = ExtractionConfig::from_file(&config_path);
119
+ assert!(config.is_ok(), "Should load .yml config successfully");
120
+ }
121
+
122
+ /// Test from_file with nonexistent path fails.
123
+ #[test]
124
+ fn test_from_file_nonexistent_path_fails() {
125
+ let result = ExtractionConfig::from_file("/nonexistent/path/config.toml");
126
+ assert!(result.is_err(), "Should fail for nonexistent path: {:?}", result);
127
+ }
128
+
129
+ /// Test from_file with malformed TOML fails.
130
+ #[test]
131
+ fn test_from_file_malformed_toml_fails() {
132
+ let temp_dir = TempDir::new().unwrap();
133
+ let config_path = temp_dir.path().join("config.toml");
134
+
135
+ let malformed_toml = r#"
136
+ [ocr
137
+ enabled = true
138
+ "#;
139
+
140
+ fs::write(&config_path, malformed_toml).unwrap();
141
+
142
+ let result = ExtractionConfig::from_file(&config_path);
143
+ assert!(result.is_err(), "Should fail for malformed TOML: {:?}", result);
144
+ }
145
+
146
+ /// Test from_file with malformed JSON fails.
147
+ #[test]
148
+ fn test_from_file_malformed_json_fails() {
149
+ let temp_dir = TempDir::new().unwrap();
150
+ let config_path = temp_dir.path().join("config.json");
151
+
152
+ let malformed_json = r#"
153
+ {
154
+ "ocr": {
155
+ "enabled": true
156
+ }
157
+ "chunking": {}
158
+ }
159
+ "#;
160
+
161
+ fs::write(&config_path, malformed_json).unwrap();
162
+
163
+ let result = ExtractionConfig::from_file(&config_path);
164
+ assert!(result.is_err(), "Should fail for malformed JSON: {:?}", result);
165
+ }
166
+
167
+ /// Test from_file with malformed YAML fails.
168
+ #[test]
169
+ fn test_from_file_malformed_yaml_fails() {
170
+ let temp_dir = TempDir::new().unwrap();
171
+ let config_path = temp_dir.path().join("config.yaml");
172
+
173
+ let malformed_yaml = r#"
174
+ ocr:
175
+ enabled: true
176
+ - invalid_list
177
+ "#;
178
+
179
+ fs::write(&config_path, malformed_yaml).unwrap();
180
+
181
+ let result = ExtractionConfig::from_file(&config_path);
182
+ assert!(result.is_err(), "Should fail for malformed YAML: {:?}", result);
183
+ }
184
+
185
+ /// Test from_file with empty file uses defaults.
186
+ #[test]
187
+ fn test_from_file_empty_file_uses_defaults() {
188
+ let temp_dir = TempDir::new().unwrap();
189
+ let config_path = temp_dir.path().join("config.toml");
190
+
191
+ fs::write(&config_path, "").unwrap();
192
+
193
+ let config = ExtractionConfig::from_file(&config_path);
194
+ assert!(config.is_ok(), "Should load empty file successfully");
195
+
196
+ let config = config.unwrap();
197
+ assert!(config.ocr.is_none(), "Default config should have no OCR");
198
+ assert!(config.chunking.is_none(), "Default config should have no chunking");
199
+ }
200
+
201
+ /// Test from_file with unsupported extension fails.
202
+ #[test]
203
+ fn test_from_file_unsupported_extension_fails() {
204
+ let temp_dir = TempDir::new().unwrap();
205
+ let config_path = temp_dir.path().join("config.txt");
206
+
207
+ fs::write(&config_path, "ocr:\n enabled: true").unwrap();
208
+
209
+ let result = ExtractionConfig::from_file(&config_path);
210
+ assert!(result.is_err(), "Should fail for unsupported extension: {:?}", result);
211
+
212
+ if let Err(KreuzbergError::Validation { message, .. }) = result {
213
+ assert!(
214
+ message.contains("format") || message.contains("extension") || message.contains("Unsupported"),
215
+ "Error should mention format/extension: {}",
216
+ message
217
+ );
218
+ }
219
+ }
220
+
221
+ /// Test discover() finds config in current directory.
222
+ #[test]
223
+ #[serial_test::serial]
224
+ fn test_discover_finds_config_in_current_dir() {
225
+ let temp_dir = TempDir::new().unwrap();
226
+ let config_path = temp_dir.path().join("kreuzberg.toml");
227
+
228
+ let toml_content = r#"
229
+ [ocr]
230
+ enabled = true
231
+ "#;
232
+
233
+ fs::write(&config_path, toml_content).unwrap();
234
+
235
+ let original_dir = std::env::current_dir().unwrap();
236
+ std::env::set_current_dir(temp_dir.path()).unwrap();
237
+
238
+ let result = ExtractionConfig::discover();
239
+
240
+ std::env::set_current_dir(original_dir).unwrap();
241
+
242
+ assert!(result.is_ok(), "Discover should succeed");
243
+ let config = result.unwrap();
244
+ assert!(config.is_some(), "Should find config in current directory");
245
+ assert!(config.unwrap().ocr.is_some(), "Should have OCR config");
246
+ }
247
+
248
+ /// Test discover() finds config in parent directory.
249
+ #[test]
250
+ #[serial_test::serial]
251
+ fn test_discover_finds_config_in_parent_dir() {
252
+ let temp_dir = TempDir::new().unwrap();
253
+ let config_path = temp_dir.path().join("kreuzberg.toml");
254
+
255
+ let toml_content = r#"
256
+ [ocr]
257
+ enabled = true
258
+ "#;
259
+
260
+ fs::write(&config_path, toml_content).unwrap();
261
+
262
+ let sub_dir = temp_dir.path().join("subdir");
263
+ fs::create_dir(&sub_dir).unwrap();
264
+
265
+ let original_dir = std::env::current_dir().unwrap();
266
+ std::env::set_current_dir(&sub_dir).unwrap();
267
+
268
+ let result = ExtractionConfig::discover();
269
+
270
+ std::env::set_current_dir(original_dir).unwrap();
271
+
272
+ assert!(result.is_ok(), "Discover should succeed");
273
+ let config = result.unwrap();
274
+ assert!(config.is_some(), "Should find config in parent directory");
275
+ assert!(config.unwrap().ocr.is_some(), "Should have OCR config");
276
+ }
277
+
278
+ /// Test discover() returns None when no config found.
279
+ #[test]
280
+ #[serial_test::serial]
281
+ fn test_discover_returns_none_when_not_found() {
282
+ let temp_dir = TempDir::new().unwrap();
283
+ let sub_dir = temp_dir.path().join("subdir");
284
+ fs::create_dir(&sub_dir).unwrap();
285
+
286
+ let original_dir = std::env::current_dir().unwrap();
287
+ std::env::set_current_dir(&sub_dir).unwrap();
288
+
289
+ let result = ExtractionConfig::discover();
290
+
291
+ std::env::set_current_dir(original_dir).unwrap();
292
+
293
+ assert!(result.is_ok(), "Discover should succeed even when no config found");
294
+ let _config = result.unwrap();
295
+ }
296
+
297
+ /// Test discover() prefers certain file names.
298
+ #[test]
299
+ #[serial_test::serial]
300
+ fn test_discover_file_name_preference() {
301
+ let temp_dir = TempDir::new().unwrap();
302
+
303
+ fs::write(temp_dir.path().join("kreuzberg.toml"), "[ocr]\nenabled = true").unwrap();
304
+ fs::write(temp_dir.path().join(".kreuzberg.toml"), "[ocr]\nenabled = false").unwrap();
305
+
306
+ let original_dir = std::env::current_dir().unwrap();
307
+ if std::env::set_current_dir(temp_dir.path()).is_err() {
308
+ return;
309
+ }
310
+
311
+ let result = ExtractionConfig::discover();
312
+
313
+ let _ = std::env::set_current_dir(original_dir);
314
+
315
+ assert!(result.is_ok(), "Discover should succeed");
316
+ let config = result.unwrap();
317
+ assert!(config.is_some(), "Should find a config file");
318
+ }
319
+
320
+ /// Test discover() with nested directories.
321
+ #[test]
322
+ #[serial_test::serial]
323
+ fn test_discover_with_nested_directories() {
324
+ let temp_dir = TempDir::new().unwrap();
325
+ let config_path = temp_dir.path().join("kreuzberg.toml");
326
+
327
+ let toml_content = r#"
328
+ [ocr]
329
+ enabled = true
330
+ "#;
331
+
332
+ fs::write(&config_path, toml_content).unwrap();
333
+
334
+ let level1 = temp_dir.path().join("level1");
335
+ let level2 = level1.join("level2");
336
+ let level3 = level2.join("level3");
337
+ fs::create_dir_all(&level3).unwrap();
338
+
339
+ let original_dir = std::env::current_dir().unwrap();
340
+ if std::env::set_current_dir(&level3).is_err() {
341
+ return;
342
+ }
343
+
344
+ let result = ExtractionConfig::discover();
345
+
346
+ let _ = std::env::set_current_dir(&original_dir);
347
+
348
+ assert!(result.is_ok(), "Discover should succeed");
349
+ let config = result.unwrap();
350
+ assert!(config.is_some(), "Should find config in ancestor directory");
351
+ assert!(config.unwrap().ocr.is_some(), "Should have OCR config");
352
+ }
353
+
354
+ /// Test config loading with all supported features.
355
+ #[test]
356
+ fn test_from_file_comprehensive_config() {
357
+ let temp_dir = TempDir::new().unwrap();
358
+ let config_path = temp_dir.path().join("config.toml");
359
+
360
+ let toml_content = r#"
361
+ [ocr]
362
+ enabled = true
363
+ backend = "tesseract"
364
+
365
+ [chunking]
366
+ max_chars = 2000
367
+ max_overlap = 200
368
+
369
+ [language_detection]
370
+ enabled = true
371
+
372
+ [images]
373
+ enabled = true
374
+
375
+ [pdf_options]
376
+ extract_images = true
377
+ "#;
378
+
379
+ fs::write(&config_path, toml_content).unwrap();
380
+
381
+ let config = ExtractionConfig::from_file(&config_path);
382
+ assert!(config.is_ok(), "Should load comprehensive config successfully");
383
+
384
+ let config = config.unwrap();
385
+ assert!(config.ocr.is_some(), "Should have OCR config");
386
+ assert!(config.chunking.is_some(), "Should have chunking config");
387
+ assert!(
388
+ config.language_detection.is_some(),
389
+ "Should have language detection config"
390
+ );
391
+ assert!(config.images.is_some(), "Should have image extraction config");
392
+ assert!(config.pdf_options.is_some(), "Should have PDF config");
393
+ }
394
+
395
+ /// Test config validation with invalid values.
396
+ #[test]
397
+ fn test_from_file_with_invalid_values() {
398
+ let temp_dir = TempDir::new().unwrap();
399
+ let config_path = temp_dir.path().join("config.toml");
400
+
401
+ let toml_content = r#"
402
+ [chunking]
403
+ max_chars = -1000
404
+ max_overlap = -100
405
+ "#;
406
+
407
+ fs::write(&config_path, toml_content).unwrap();
408
+
409
+ let result = ExtractionConfig::from_file(&config_path);
410
+ if let Ok(config) = result
411
+ && let Some(chunking) = config.chunking
412
+ {
413
+ assert!(chunking.max_chars > 0, "max_chars should be positive");
414
+ }
415
+ }