kreuzberg 4.0.0.rc2 → 4.0.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (446) hide show
  1. checksums.yaml +4 -4
  2. data/.gitignore +14 -14
  3. data/.rspec +3 -3
  4. data/.rubocop.yaml +1 -1
  5. data/.rubocop.yml +543 -538
  6. data/Gemfile +8 -8
  7. data/Gemfile.lock +194 -6
  8. data/README.md +396 -426
  9. data/Rakefile +34 -25
  10. data/Steepfile +51 -47
  11. data/examples/async_patterns.rb +283 -341
  12. data/ext/kreuzberg_rb/extconf.rb +65 -45
  13. data/ext/kreuzberg_rb/native/.cargo/config.toml +23 -0
  14. data/ext/kreuzberg_rb/native/Cargo.lock +7619 -6535
  15. data/ext/kreuzberg_rb/native/Cargo.toml +75 -44
  16. data/ext/kreuzberg_rb/native/README.md +425 -425
  17. data/ext/kreuzberg_rb/native/build.rs +15 -15
  18. data/ext/kreuzberg_rb/native/include/ieeefp.h +11 -11
  19. data/ext/kreuzberg_rb/native/include/msvc_compat/strings.h +14 -14
  20. data/ext/kreuzberg_rb/native/include/strings.h +20 -20
  21. data/ext/kreuzberg_rb/native/include/unistd.h +47 -47
  22. data/ext/kreuzberg_rb/native/src/lib.rs +3802 -2998
  23. data/extconf.rb +60 -28
  24. data/kreuzberg.gemspec +199 -148
  25. data/lib/kreuzberg/api_proxy.rb +126 -142
  26. data/lib/kreuzberg/cache_api.rb +67 -46
  27. data/lib/kreuzberg/cli.rb +47 -55
  28. data/lib/kreuzberg/cli_proxy.rb +117 -127
  29. data/lib/kreuzberg/config.rb +936 -691
  30. data/lib/kreuzberg/error_context.rb +136 -32
  31. data/lib/kreuzberg/errors.rb +116 -118
  32. data/lib/kreuzberg/extraction_api.rb +313 -85
  33. data/lib/kreuzberg/mcp_proxy.rb +177 -186
  34. data/lib/kreuzberg/ocr_backend_protocol.rb +40 -113
  35. data/lib/kreuzberg/post_processor_protocol.rb +15 -86
  36. data/lib/kreuzberg/result.rb +334 -216
  37. data/lib/kreuzberg/setup_lib_path.rb +99 -80
  38. data/lib/kreuzberg/types.rb +170 -0
  39. data/lib/kreuzberg/validator_protocol.rb +16 -89
  40. data/lib/kreuzberg/version.rb +5 -5
  41. data/lib/kreuzberg.rb +96 -103
  42. data/lib/libpdfium.so +0 -0
  43. data/sig/kreuzberg/internal.rbs +184 -184
  44. data/sig/kreuzberg.rbs +561 -520
  45. data/spec/binding/async_operations_spec.rb +473 -0
  46. data/spec/binding/batch_operations_spec.rb +595 -0
  47. data/spec/binding/batch_spec.rb +359 -0
  48. data/spec/binding/cache_spec.rb +227 -227
  49. data/spec/binding/cli_proxy_spec.rb +85 -85
  50. data/spec/binding/cli_spec.rb +55 -55
  51. data/spec/binding/config_result_spec.rb +377 -0
  52. data/spec/binding/config_spec.rb +419 -345
  53. data/spec/binding/config_validation_spec.rb +377 -283
  54. data/spec/binding/embeddings_spec.rb +816 -0
  55. data/spec/binding/error_handling_spec.rb +399 -213
  56. data/spec/binding/error_recovery_spec.rb +488 -0
  57. data/spec/binding/errors_spec.rb +66 -66
  58. data/spec/binding/font_config_spec.rb +220 -0
  59. data/spec/binding/images_spec.rb +738 -0
  60. data/spec/binding/keywords_extraction_spec.rb +600 -0
  61. data/spec/binding/metadata_types_spec.rb +1228 -0
  62. data/spec/binding/pages_extraction_spec.rb +471 -0
  63. data/spec/binding/plugins/ocr_backend_spec.rb +307 -307
  64. data/spec/binding/plugins/postprocessor_spec.rb +269 -269
  65. data/spec/binding/plugins/validator_spec.rb +273 -274
  66. data/spec/binding/tables_spec.rb +641 -0
  67. data/spec/fixtures/config.toml +38 -39
  68. data/spec/fixtures/config.yaml +41 -41
  69. data/spec/fixtures/invalid_config.toml +3 -4
  70. data/spec/smoke/package_spec.rb +177 -178
  71. data/spec/spec_helper.rb +40 -42
  72. data/spec/unit/config/chunking_config_spec.rb +213 -0
  73. data/spec/unit/config/embedding_config_spec.rb +343 -0
  74. data/spec/unit/config/extraction_config_spec.rb +438 -0
  75. data/spec/unit/config/font_config_spec.rb +285 -0
  76. data/spec/unit/config/hierarchy_config_spec.rb +314 -0
  77. data/spec/unit/config/image_extraction_config_spec.rb +209 -0
  78. data/spec/unit/config/image_preprocessing_config_spec.rb +249 -0
  79. data/spec/unit/config/keyword_config_spec.rb +229 -0
  80. data/spec/unit/config/language_detection_config_spec.rb +258 -0
  81. data/spec/unit/config/ocr_config_spec.rb +171 -0
  82. data/spec/unit/config/page_config_spec.rb +221 -0
  83. data/spec/unit/config/pdf_config_spec.rb +267 -0
  84. data/spec/unit/config/postprocessor_config_spec.rb +290 -0
  85. data/spec/unit/config/tesseract_config_spec.rb +181 -0
  86. data/spec/unit/config/token_reduction_config_spec.rb +251 -0
  87. data/test/metadata_types_test.rb +959 -0
  88. data/vendor/Cargo.toml +61 -0
  89. data/vendor/kreuzberg/Cargo.toml +259 -204
  90. data/vendor/kreuzberg/README.md +263 -175
  91. data/vendor/kreuzberg/build.rs +782 -474
  92. data/vendor/kreuzberg/examples/bench_fixes.rs +71 -0
  93. data/vendor/kreuzberg/examples/test_pdfium_fork.rs +62 -0
  94. data/vendor/kreuzberg/src/api/error.rs +81 -81
  95. data/vendor/kreuzberg/src/api/handlers.rs +320 -199
  96. data/vendor/kreuzberg/src/api/mod.rs +94 -79
  97. data/vendor/kreuzberg/src/api/server.rs +518 -353
  98. data/vendor/kreuzberg/src/api/types.rs +206 -170
  99. data/vendor/kreuzberg/src/cache/mod.rs +1167 -1167
  100. data/vendor/kreuzberg/src/chunking/mod.rs +2303 -677
  101. data/vendor/kreuzberg/src/chunking/processor.rs +219 -0
  102. data/vendor/kreuzberg/src/core/batch_mode.rs +95 -95
  103. data/vendor/kreuzberg/src/core/batch_optimizations.rs +385 -0
  104. data/vendor/kreuzberg/src/core/config.rs +1914 -1032
  105. data/vendor/kreuzberg/src/core/config_validation.rs +949 -0
  106. data/vendor/kreuzberg/src/core/extractor.rs +1200 -1024
  107. data/vendor/kreuzberg/src/core/formats.rs +235 -0
  108. data/vendor/kreuzberg/src/core/io.rs +329 -329
  109. data/vendor/kreuzberg/src/core/mime.rs +605 -605
  110. data/vendor/kreuzberg/src/core/mod.rs +61 -45
  111. data/vendor/kreuzberg/src/core/pipeline.rs +1223 -984
  112. data/vendor/kreuzberg/src/core/server_config.rs +1220 -0
  113. data/vendor/kreuzberg/src/embeddings.rs +471 -432
  114. data/vendor/kreuzberg/src/error.rs +431 -431
  115. data/vendor/kreuzberg/src/extraction/archive.rs +959 -954
  116. data/vendor/kreuzberg/src/extraction/capacity.rs +263 -0
  117. data/vendor/kreuzberg/src/extraction/docx.rs +404 -40
  118. data/vendor/kreuzberg/src/extraction/email.rs +855 -854
  119. data/vendor/kreuzberg/src/extraction/excel.rs +697 -688
  120. data/vendor/kreuzberg/src/extraction/html.rs +1830 -553
  121. data/vendor/kreuzberg/src/extraction/image.rs +492 -368
  122. data/vendor/kreuzberg/src/extraction/libreoffice.rs +574 -563
  123. data/vendor/kreuzberg/src/extraction/markdown.rs +216 -213
  124. data/vendor/kreuzberg/src/extraction/mod.rs +93 -81
  125. data/vendor/kreuzberg/src/extraction/office_metadata/app_properties.rs +398 -398
  126. data/vendor/kreuzberg/src/extraction/office_metadata/core_properties.rs +247 -247
  127. data/vendor/kreuzberg/src/extraction/office_metadata/custom_properties.rs +240 -240
  128. data/vendor/kreuzberg/src/extraction/office_metadata/mod.rs +130 -130
  129. data/vendor/kreuzberg/src/extraction/office_metadata/odt_properties.rs +284 -287
  130. data/vendor/kreuzberg/src/extraction/pptx.rs +3102 -3000
  131. data/vendor/kreuzberg/src/extraction/structured.rs +491 -490
  132. data/vendor/kreuzberg/src/extraction/table.rs +329 -328
  133. data/vendor/kreuzberg/src/extraction/text.rs +277 -269
  134. data/vendor/kreuzberg/src/extraction/xml.rs +333 -333
  135. data/vendor/kreuzberg/src/extractors/archive.rs +447 -446
  136. data/vendor/kreuzberg/src/extractors/bibtex.rs +470 -469
  137. data/vendor/kreuzberg/src/extractors/docbook.rs +504 -502
  138. data/vendor/kreuzberg/src/extractors/docx.rs +400 -367
  139. data/vendor/kreuzberg/src/extractors/email.rs +157 -143
  140. data/vendor/kreuzberg/src/extractors/epub.rs +696 -707
  141. data/vendor/kreuzberg/src/extractors/excel.rs +385 -343
  142. data/vendor/kreuzberg/src/extractors/fictionbook.rs +492 -491
  143. data/vendor/kreuzberg/src/extractors/html.rs +419 -393
  144. data/vendor/kreuzberg/src/extractors/image.rs +219 -198
  145. data/vendor/kreuzberg/src/extractors/jats.rs +1054 -1051
  146. data/vendor/kreuzberg/src/extractors/jupyter.rs +368 -367
  147. data/vendor/kreuzberg/src/extractors/latex.rs +653 -652
  148. data/vendor/kreuzberg/src/extractors/markdown.rs +701 -700
  149. data/vendor/kreuzberg/src/extractors/mod.rs +429 -365
  150. data/vendor/kreuzberg/src/extractors/odt.rs +628 -628
  151. data/vendor/kreuzberg/src/extractors/opml.rs +635 -634
  152. data/vendor/kreuzberg/src/extractors/orgmode.rs +529 -528
  153. data/vendor/kreuzberg/src/extractors/pdf.rs +761 -493
  154. data/vendor/kreuzberg/src/extractors/pptx.rs +279 -248
  155. data/vendor/kreuzberg/src/extractors/rst.rs +577 -576
  156. data/vendor/kreuzberg/src/extractors/rtf.rs +809 -810
  157. data/vendor/kreuzberg/src/extractors/security.rs +484 -484
  158. data/vendor/kreuzberg/src/extractors/security_tests.rs +367 -367
  159. data/vendor/kreuzberg/src/extractors/structured.rs +142 -140
  160. data/vendor/kreuzberg/src/extractors/text.rs +265 -260
  161. data/vendor/kreuzberg/src/extractors/typst.rs +651 -650
  162. data/vendor/kreuzberg/src/extractors/xml.rs +147 -135
  163. data/vendor/kreuzberg/src/image/dpi.rs +164 -164
  164. data/vendor/kreuzberg/src/image/mod.rs +6 -6
  165. data/vendor/kreuzberg/src/image/preprocessing.rs +417 -417
  166. data/vendor/kreuzberg/src/image/resize.rs +89 -89
  167. data/vendor/kreuzberg/src/keywords/config.rs +154 -154
  168. data/vendor/kreuzberg/src/keywords/mod.rs +237 -237
  169. data/vendor/kreuzberg/src/keywords/processor.rs +275 -267
  170. data/vendor/kreuzberg/src/keywords/rake.rs +293 -293
  171. data/vendor/kreuzberg/src/keywords/types.rs +68 -68
  172. data/vendor/kreuzberg/src/keywords/yake.rs +163 -163
  173. data/vendor/kreuzberg/src/language_detection/mod.rs +985 -942
  174. data/vendor/kreuzberg/src/language_detection/processor.rs +218 -0
  175. data/vendor/kreuzberg/src/lib.rs +114 -105
  176. data/vendor/kreuzberg/src/mcp/mod.rs +35 -32
  177. data/vendor/kreuzberg/src/mcp/server.rs +2090 -1968
  178. data/vendor/kreuzberg/src/ocr/cache.rs +469 -469
  179. data/vendor/kreuzberg/src/ocr/error.rs +37 -37
  180. data/vendor/kreuzberg/src/ocr/hocr.rs +216 -216
  181. data/vendor/kreuzberg/src/ocr/language_registry.rs +520 -0
  182. data/vendor/kreuzberg/src/ocr/mod.rs +60 -58
  183. data/vendor/kreuzberg/src/ocr/processor.rs +858 -863
  184. data/vendor/kreuzberg/src/ocr/table/mod.rs +4 -4
  185. data/vendor/kreuzberg/src/ocr/table/tsv_parser.rs +144 -144
  186. data/vendor/kreuzberg/src/ocr/tesseract_backend.rs +456 -450
  187. data/vendor/kreuzberg/src/ocr/types.rs +393 -393
  188. data/vendor/kreuzberg/src/ocr/utils.rs +47 -47
  189. data/vendor/kreuzberg/src/ocr/validation.rs +206 -206
  190. data/vendor/kreuzberg/src/panic_context.rs +154 -154
  191. data/vendor/kreuzberg/src/pdf/bindings.rs +306 -0
  192. data/vendor/kreuzberg/src/pdf/bundled.rs +408 -0
  193. data/vendor/kreuzberg/src/pdf/error.rs +214 -122
  194. data/vendor/kreuzberg/src/pdf/fonts.rs +358 -0
  195. data/vendor/kreuzberg/src/pdf/hierarchy.rs +903 -0
  196. data/vendor/kreuzberg/src/pdf/images.rs +139 -139
  197. data/vendor/kreuzberg/src/pdf/metadata.rs +509 -346
  198. data/vendor/kreuzberg/src/pdf/mod.rs +81 -50
  199. data/vendor/kreuzberg/src/pdf/rendering.rs +369 -369
  200. data/vendor/kreuzberg/src/pdf/table.rs +417 -393
  201. data/vendor/kreuzberg/src/pdf/text.rs +553 -158
  202. data/vendor/kreuzberg/src/plugins/extractor.rs +1042 -1013
  203. data/vendor/kreuzberg/src/plugins/mod.rs +212 -209
  204. data/vendor/kreuzberg/src/plugins/ocr.rs +637 -620
  205. data/vendor/kreuzberg/src/plugins/processor.rs +650 -642
  206. data/vendor/kreuzberg/src/plugins/registry.rs +1339 -1337
  207. data/vendor/kreuzberg/src/plugins/traits.rs +258 -258
  208. data/vendor/kreuzberg/src/plugins/validator.rs +967 -956
  209. data/vendor/kreuzberg/src/stopwords/mod.rs +1470 -1470
  210. data/vendor/kreuzberg/src/text/mod.rs +27 -19
  211. data/vendor/kreuzberg/src/text/quality.rs +710 -697
  212. data/vendor/kreuzberg/src/text/quality_processor.rs +231 -0
  213. data/vendor/kreuzberg/src/text/string_utils.rs +229 -217
  214. data/vendor/kreuzberg/src/text/token_reduction/cjk_utils.rs +164 -164
  215. data/vendor/kreuzberg/src/text/token_reduction/config.rs +100 -100
  216. data/vendor/kreuzberg/src/text/token_reduction/core.rs +832 -796
  217. data/vendor/kreuzberg/src/text/token_reduction/filters.rs +923 -902
  218. data/vendor/kreuzberg/src/text/token_reduction/mod.rs +160 -160
  219. data/vendor/kreuzberg/src/text/token_reduction/semantic.rs +619 -619
  220. data/vendor/kreuzberg/src/text/token_reduction/simd_text.rs +148 -147
  221. data/vendor/kreuzberg/src/text/utf8_validation.rs +193 -0
  222. data/vendor/kreuzberg/src/types.rs +1713 -903
  223. data/vendor/kreuzberg/src/utils/mod.rs +31 -17
  224. data/vendor/kreuzberg/src/utils/pool.rs +503 -0
  225. data/vendor/kreuzberg/src/utils/pool_sizing.rs +364 -0
  226. data/vendor/kreuzberg/src/utils/quality.rs +968 -959
  227. data/vendor/kreuzberg/src/utils/string_pool.rs +761 -0
  228. data/vendor/kreuzberg/src/utils/string_utils.rs +381 -381
  229. data/vendor/kreuzberg/stopwords/af_stopwords.json +53 -53
  230. data/vendor/kreuzberg/stopwords/ar_stopwords.json +482 -482
  231. data/vendor/kreuzberg/stopwords/bg_stopwords.json +261 -261
  232. data/vendor/kreuzberg/stopwords/bn_stopwords.json +400 -400
  233. data/vendor/kreuzberg/stopwords/br_stopwords.json +1205 -1205
  234. data/vendor/kreuzberg/stopwords/ca_stopwords.json +280 -280
  235. data/vendor/kreuzberg/stopwords/cs_stopwords.json +425 -425
  236. data/vendor/kreuzberg/stopwords/da_stopwords.json +172 -172
  237. data/vendor/kreuzberg/stopwords/de_stopwords.json +622 -622
  238. data/vendor/kreuzberg/stopwords/el_stopwords.json +849 -849
  239. data/vendor/kreuzberg/stopwords/en_stopwords.json +1300 -1300
  240. data/vendor/kreuzberg/stopwords/eo_stopwords.json +175 -175
  241. data/vendor/kreuzberg/stopwords/es_stopwords.json +734 -734
  242. data/vendor/kreuzberg/stopwords/et_stopwords.json +37 -37
  243. data/vendor/kreuzberg/stopwords/eu_stopwords.json +100 -100
  244. data/vendor/kreuzberg/stopwords/fa_stopwords.json +801 -801
  245. data/vendor/kreuzberg/stopwords/fi_stopwords.json +849 -849
  246. data/vendor/kreuzberg/stopwords/fr_stopwords.json +693 -693
  247. data/vendor/kreuzberg/stopwords/ga_stopwords.json +111 -111
  248. data/vendor/kreuzberg/stopwords/gl_stopwords.json +162 -162
  249. data/vendor/kreuzberg/stopwords/gu_stopwords.json +226 -226
  250. data/vendor/kreuzberg/stopwords/ha_stopwords.json +41 -41
  251. data/vendor/kreuzberg/stopwords/he_stopwords.json +196 -196
  252. data/vendor/kreuzberg/stopwords/hi_stopwords.json +227 -227
  253. data/vendor/kreuzberg/stopwords/hr_stopwords.json +181 -181
  254. data/vendor/kreuzberg/stopwords/hu_stopwords.json +791 -791
  255. data/vendor/kreuzberg/stopwords/hy_stopwords.json +47 -47
  256. data/vendor/kreuzberg/stopwords/id_stopwords.json +760 -760
  257. data/vendor/kreuzberg/stopwords/it_stopwords.json +634 -634
  258. data/vendor/kreuzberg/stopwords/ja_stopwords.json +136 -136
  259. data/vendor/kreuzberg/stopwords/kn_stopwords.json +84 -84
  260. data/vendor/kreuzberg/stopwords/ko_stopwords.json +681 -681
  261. data/vendor/kreuzberg/stopwords/ku_stopwords.json +64 -64
  262. data/vendor/kreuzberg/stopwords/la_stopwords.json +51 -51
  263. data/vendor/kreuzberg/stopwords/lt_stopwords.json +476 -476
  264. data/vendor/kreuzberg/stopwords/lv_stopwords.json +163 -163
  265. data/vendor/kreuzberg/stopwords/ml_stopwords.json +1 -1
  266. data/vendor/kreuzberg/stopwords/mr_stopwords.json +101 -101
  267. data/vendor/kreuzberg/stopwords/ms_stopwords.json +477 -477
  268. data/vendor/kreuzberg/stopwords/ne_stopwords.json +490 -490
  269. data/vendor/kreuzberg/stopwords/nl_stopwords.json +415 -415
  270. data/vendor/kreuzberg/stopwords/no_stopwords.json +223 -223
  271. data/vendor/kreuzberg/stopwords/pl_stopwords.json +331 -331
  272. data/vendor/kreuzberg/stopwords/pt_stopwords.json +562 -562
  273. data/vendor/kreuzberg/stopwords/ro_stopwords.json +436 -436
  274. data/vendor/kreuzberg/stopwords/ru_stopwords.json +561 -561
  275. data/vendor/kreuzberg/stopwords/si_stopwords.json +193 -193
  276. data/vendor/kreuzberg/stopwords/sk_stopwords.json +420 -420
  277. data/vendor/kreuzberg/stopwords/sl_stopwords.json +448 -448
  278. data/vendor/kreuzberg/stopwords/so_stopwords.json +32 -32
  279. data/vendor/kreuzberg/stopwords/st_stopwords.json +33 -33
  280. data/vendor/kreuzberg/stopwords/sv_stopwords.json +420 -420
  281. data/vendor/kreuzberg/stopwords/sw_stopwords.json +76 -76
  282. data/vendor/kreuzberg/stopwords/ta_stopwords.json +129 -129
  283. data/vendor/kreuzberg/stopwords/te_stopwords.json +54 -54
  284. data/vendor/kreuzberg/stopwords/th_stopwords.json +118 -118
  285. data/vendor/kreuzberg/stopwords/tl_stopwords.json +149 -149
  286. data/vendor/kreuzberg/stopwords/tr_stopwords.json +506 -506
  287. data/vendor/kreuzberg/stopwords/uk_stopwords.json +75 -75
  288. data/vendor/kreuzberg/stopwords/ur_stopwords.json +519 -519
  289. data/vendor/kreuzberg/stopwords/vi_stopwords.json +647 -647
  290. data/vendor/kreuzberg/stopwords/yo_stopwords.json +62 -62
  291. data/vendor/kreuzberg/stopwords/zh_stopwords.json +796 -796
  292. data/vendor/kreuzberg/stopwords/zu_stopwords.json +31 -31
  293. data/vendor/kreuzberg/tests/api_embed.rs +360 -0
  294. data/vendor/kreuzberg/tests/api_extract_multipart.rs +52 -52
  295. data/vendor/kreuzberg/tests/api_large_pdf_extraction.rs +471 -0
  296. data/vendor/kreuzberg/tests/api_large_pdf_extraction_diagnostics.rs +289 -0
  297. data/vendor/kreuzberg/tests/api_tests.rs +1472 -966
  298. data/vendor/kreuzberg/tests/archive_integration.rs +545 -543
  299. data/vendor/kreuzberg/tests/batch_orchestration.rs +587 -556
  300. data/vendor/kreuzberg/tests/batch_pooling_benchmark.rs +154 -0
  301. data/vendor/kreuzberg/tests/batch_processing.rs +328 -316
  302. data/vendor/kreuzberg/tests/bibtex_parity_test.rs +421 -421
  303. data/vendor/kreuzberg/tests/concurrency_stress.rs +541 -525
  304. data/vendor/kreuzberg/tests/config_features.rs +612 -598
  305. data/vendor/kreuzberg/tests/config_integration_test.rs +753 -0
  306. data/vendor/kreuzberg/tests/config_loading_tests.rs +416 -415
  307. data/vendor/kreuzberg/tests/core_integration.rs +519 -510
  308. data/vendor/kreuzberg/tests/csv_integration.rs +414 -414
  309. data/vendor/kreuzberg/tests/data/hierarchy_ground_truth.json +294 -0
  310. data/vendor/kreuzberg/tests/docbook_extractor_tests.rs +500 -498
  311. data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +122 -122
  312. data/vendor/kreuzberg/tests/docx_vs_pandoc_comparison.rs +370 -370
  313. data/vendor/kreuzberg/tests/email_integration.rs +327 -325
  314. data/vendor/kreuzberg/tests/epub_native_extractor_tests.rs +275 -275
  315. data/vendor/kreuzberg/tests/error_handling.rs +402 -393
  316. data/vendor/kreuzberg/tests/fictionbook_extractor_tests.rs +228 -228
  317. data/vendor/kreuzberg/tests/format_integration.rs +165 -159
  318. data/vendor/kreuzberg/tests/helpers/mod.rs +202 -142
  319. data/vendor/kreuzberg/tests/html_table_test.rs +551 -551
  320. data/vendor/kreuzberg/tests/image_integration.rs +255 -253
  321. data/vendor/kreuzberg/tests/instrumentation_test.rs +139 -139
  322. data/vendor/kreuzberg/tests/jats_extractor_tests.rs +639 -639
  323. data/vendor/kreuzberg/tests/jupyter_extractor_tests.rs +704 -704
  324. data/vendor/kreuzberg/tests/keywords_integration.rs +479 -479
  325. data/vendor/kreuzberg/tests/keywords_quality.rs +509 -509
  326. data/vendor/kreuzberg/tests/latex_extractor_tests.rs +496 -496
  327. data/vendor/kreuzberg/tests/markdown_extractor_tests.rs +490 -490
  328. data/vendor/kreuzberg/tests/mime_detection.rs +429 -428
  329. data/vendor/kreuzberg/tests/ocr_configuration.rs +514 -510
  330. data/vendor/kreuzberg/tests/ocr_errors.rs +698 -676
  331. data/vendor/kreuzberg/tests/ocr_language_registry.rs +191 -0
  332. data/vendor/kreuzberg/tests/ocr_quality.rs +629 -627
  333. data/vendor/kreuzberg/tests/ocr_stress.rs +469 -469
  334. data/vendor/kreuzberg/tests/odt_extractor_tests.rs +674 -695
  335. data/vendor/kreuzberg/tests/opml_extractor_tests.rs +616 -616
  336. data/vendor/kreuzberg/tests/orgmode_extractor_tests.rs +822 -822
  337. data/vendor/kreuzberg/tests/page_markers.rs +297 -0
  338. data/vendor/kreuzberg/tests/pdf_hierarchy_detection.rs +301 -0
  339. data/vendor/kreuzberg/tests/pdf_hierarchy_quality.rs +589 -0
  340. data/vendor/kreuzberg/tests/pdf_integration.rs +45 -43
  341. data/vendor/kreuzberg/tests/pdf_ocr_triggering.rs +301 -0
  342. data/vendor/kreuzberg/tests/pdf_text_merging.rs +475 -0
  343. data/vendor/kreuzberg/tests/pdfium_linking.rs +340 -0
  344. data/vendor/kreuzberg/tests/pipeline_integration.rs +1446 -1411
  345. data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +776 -771
  346. data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +577 -560
  347. data/vendor/kreuzberg/tests/plugin_system.rs +927 -921
  348. data/vendor/kreuzberg/tests/plugin_validator_test.rs +783 -783
  349. data/vendor/kreuzberg/tests/registry_integration_tests.rs +587 -586
  350. data/vendor/kreuzberg/tests/rst_extractor_tests.rs +694 -692
  351. data/vendor/kreuzberg/tests/rtf_extractor_tests.rs +775 -776
  352. data/vendor/kreuzberg/tests/security_validation.rs +416 -415
  353. data/vendor/kreuzberg/tests/stopwords_integration_test.rs +888 -888
  354. data/vendor/kreuzberg/tests/test_fastembed.rs +631 -609
  355. data/vendor/kreuzberg/tests/typst_behavioral_tests.rs +1260 -1259
  356. data/vendor/kreuzberg/tests/typst_extractor_tests.rs +648 -647
  357. data/vendor/kreuzberg/tests/xlsx_metadata_extraction_test.rs +87 -87
  358. data/vendor/kreuzberg-ffi/Cargo.toml +67 -0
  359. data/vendor/kreuzberg-ffi/README.md +851 -0
  360. data/vendor/kreuzberg-ffi/benches/result_view_benchmark.rs +227 -0
  361. data/vendor/kreuzberg-ffi/build.rs +168 -0
  362. data/vendor/kreuzberg-ffi/cbindgen.toml +37 -0
  363. data/vendor/kreuzberg-ffi/kreuzberg-ffi.pc.in +12 -0
  364. data/vendor/kreuzberg-ffi/kreuzberg.h +3012 -0
  365. data/vendor/kreuzberg-ffi/src/batch_streaming.rs +588 -0
  366. data/vendor/kreuzberg-ffi/src/config.rs +1341 -0
  367. data/vendor/kreuzberg-ffi/src/error.rs +901 -0
  368. data/vendor/kreuzberg-ffi/src/extraction.rs +555 -0
  369. data/vendor/kreuzberg-ffi/src/helpers.rs +879 -0
  370. data/vendor/kreuzberg-ffi/src/lib.rs +977 -0
  371. data/vendor/kreuzberg-ffi/src/memory.rs +493 -0
  372. data/vendor/kreuzberg-ffi/src/mime.rs +329 -0
  373. data/vendor/kreuzberg-ffi/src/panic_shield.rs +265 -0
  374. data/vendor/kreuzberg-ffi/src/plugins/document_extractor.rs +442 -0
  375. data/vendor/kreuzberg-ffi/src/plugins/mod.rs +14 -0
  376. data/vendor/kreuzberg-ffi/src/plugins/ocr_backend.rs +628 -0
  377. data/vendor/kreuzberg-ffi/src/plugins/post_processor.rs +438 -0
  378. data/vendor/kreuzberg-ffi/src/plugins/validator.rs +329 -0
  379. data/vendor/kreuzberg-ffi/src/result.rs +510 -0
  380. data/vendor/kreuzberg-ffi/src/result_pool.rs +639 -0
  381. data/vendor/kreuzberg-ffi/src/result_view.rs +773 -0
  382. data/vendor/kreuzberg-ffi/src/string_intern.rs +568 -0
  383. data/vendor/kreuzberg-ffi/src/types.rs +363 -0
  384. data/vendor/kreuzberg-ffi/src/util.rs +210 -0
  385. data/vendor/kreuzberg-ffi/src/validation.rs +848 -0
  386. data/vendor/kreuzberg-ffi/tests.disabled/README.md +48 -0
  387. data/vendor/kreuzberg-ffi/tests.disabled/config_loading_tests.rs +299 -0
  388. data/vendor/kreuzberg-ffi/tests.disabled/config_tests.rs +346 -0
  389. data/vendor/kreuzberg-ffi/tests.disabled/extractor_tests.rs +232 -0
  390. data/vendor/kreuzberg-ffi/tests.disabled/plugin_registration_tests.rs +470 -0
  391. data/vendor/kreuzberg-tesseract/.commitlintrc.json +13 -0
  392. data/vendor/kreuzberg-tesseract/.crate-ignore +2 -0
  393. data/vendor/kreuzberg-tesseract/Cargo.lock +2933 -0
  394. data/vendor/kreuzberg-tesseract/Cargo.toml +57 -0
  395. data/vendor/{rb-sys/LICENSE-MIT → kreuzberg-tesseract/LICENSE} +22 -21
  396. data/vendor/kreuzberg-tesseract/README.md +399 -0
  397. data/vendor/kreuzberg-tesseract/build.rs +1127 -0
  398. data/vendor/kreuzberg-tesseract/patches/README.md +71 -0
  399. data/vendor/kreuzberg-tesseract/patches/tesseract.diff +199 -0
  400. data/vendor/kreuzberg-tesseract/src/api.rs +1371 -0
  401. data/vendor/kreuzberg-tesseract/src/choice_iterator.rs +77 -0
  402. data/vendor/kreuzberg-tesseract/src/enums.rs +297 -0
  403. data/vendor/kreuzberg-tesseract/src/error.rs +81 -0
  404. data/vendor/kreuzberg-tesseract/src/lib.rs +145 -0
  405. data/vendor/kreuzberg-tesseract/src/monitor.rs +57 -0
  406. data/vendor/kreuzberg-tesseract/src/mutable_iterator.rs +197 -0
  407. data/vendor/kreuzberg-tesseract/src/page_iterator.rs +253 -0
  408. data/vendor/kreuzberg-tesseract/src/result_iterator.rs +286 -0
  409. data/vendor/kreuzberg-tesseract/src/result_renderer.rs +183 -0
  410. data/vendor/kreuzberg-tesseract/tests/integration_test.rs +211 -0
  411. metadata +196 -45
  412. data/vendor/kreuzberg/benches/otel_overhead.rs +0 -48
  413. data/vendor/kreuzberg/src/extractors/fictionbook.rs.backup2 +0 -738
  414. data/vendor/rb-sys/.cargo-ok +0 -1
  415. data/vendor/rb-sys/.cargo_vcs_info.json +0 -6
  416. data/vendor/rb-sys/Cargo.lock +0 -393
  417. data/vendor/rb-sys/Cargo.toml +0 -70
  418. data/vendor/rb-sys/Cargo.toml.orig +0 -57
  419. data/vendor/rb-sys/LICENSE-APACHE +0 -190
  420. data/vendor/rb-sys/bin/release.sh +0 -21
  421. data/vendor/rb-sys/build/features.rs +0 -108
  422. data/vendor/rb-sys/build/main.rs +0 -246
  423. data/vendor/rb-sys/build/stable_api_config.rs +0 -153
  424. data/vendor/rb-sys/build/version.rs +0 -48
  425. data/vendor/rb-sys/readme.md +0 -36
  426. data/vendor/rb-sys/src/bindings.rs +0 -21
  427. data/vendor/rb-sys/src/hidden.rs +0 -11
  428. data/vendor/rb-sys/src/lib.rs +0 -34
  429. data/vendor/rb-sys/src/macros.rs +0 -371
  430. data/vendor/rb-sys/src/memory.rs +0 -53
  431. data/vendor/rb-sys/src/ruby_abi_version.rs +0 -38
  432. data/vendor/rb-sys/src/special_consts.rs +0 -31
  433. data/vendor/rb-sys/src/stable_api/compiled.c +0 -179
  434. data/vendor/rb-sys/src/stable_api/compiled.rs +0 -257
  435. data/vendor/rb-sys/src/stable_api/ruby_2_6.rs +0 -316
  436. data/vendor/rb-sys/src/stable_api/ruby_2_7.rs +0 -316
  437. data/vendor/rb-sys/src/stable_api/ruby_3_0.rs +0 -324
  438. data/vendor/rb-sys/src/stable_api/ruby_3_1.rs +0 -317
  439. data/vendor/rb-sys/src/stable_api/ruby_3_2.rs +0 -315
  440. data/vendor/rb-sys/src/stable_api/ruby_3_3.rs +0 -326
  441. data/vendor/rb-sys/src/stable_api/ruby_3_4.rs +0 -327
  442. data/vendor/rb-sys/src/stable_api.rs +0 -261
  443. data/vendor/rb-sys/src/symbol.rs +0 -31
  444. data/vendor/rb-sys/src/tracking_allocator.rs +0 -332
  445. data/vendor/rb-sys/src/utils.rs +0 -89
  446. data/vendor/rb-sys/src/value_type.rs +0 -7
data/.rubocop.yml CHANGED
@@ -1,538 +1,543 @@
1
-
2
- plugins:
3
- - rubocop-performance
4
- - rubocop-rspec
5
-
6
- AllCops:
7
- TargetRubyVersion: 3.2
8
- NewCops: enable
9
- SuggestExtensions: false
10
- Exclude:
11
- - 'vendor/**/*'
12
- - 'tmp/**/*'
13
- - 'lib/**/*.bundle'
14
- - 'ext/**/*'
15
-
16
- Style/StringLiterals:
17
- Enabled: true
18
- EnforcedStyle: single_quotes
19
-
20
- Style/StringLiteralsInInterpolation:
21
- Enabled: true
22
- EnforcedStyle: single_quotes
23
-
24
- Style/FrozenStringLiteralComment:
25
- Enabled: true
26
- EnforcedStyle: always
27
-
28
- Style/Documentation:
29
- Enabled: false
30
-
31
- Layout/LineLength:
32
- Max: 120
33
- AllowedPatterns:
34
- - '\A\s*#'
35
- Exclude:
36
- - 'spec/**/*'
37
-
38
- Metrics/BlockLength:
39
- Enabled: true
40
- Max: 350
41
- CountComments: false
42
- CountAsOne: []
43
-
44
- Metrics/MethodLength:
45
- Max: 18
46
- Exclude:
47
- - 'spec/**/*'
48
- - 'examples/**/*'
49
-
50
- Metrics/AbcSize:
51
- Max: 20
52
- Exclude:
53
- - 'spec/**/*'
54
- - 'examples/**/*'
55
-
56
- Naming/FileName:
57
- Enabled: true
58
- Exclude:
59
- - 'Gemfile'
60
- - 'Rakefile'
61
-
62
- RSpec/SpecFilePathFormat:
63
- Enabled: false
64
- RSpec/SpecFilePathSuffix:
65
- Enabled: false
66
-
67
- RSpec/PendingWithoutReason:
68
- Enabled: false
69
-
70
- RSpec/LeakyConstantDeclaration:
71
- Enabled: false
72
-
73
- RSpec/UnspecifiedException:
74
- Enabled: false
75
-
76
- Lint/ConstantDefinitionInBlock:
77
- Enabled: false
78
- Exclude:
79
- - 'spec/**/*'
80
-
81
- RSpec/InstanceVariable:
82
- Enabled: false
83
-
84
- Gemspec/DevelopmentDependencies:
85
- Enabled: false
86
-
87
- Metrics/ParameterLists:
88
- Max: 14
89
- Exclude:
90
- - 'lib/kreuzberg/config.rb'
91
-
92
- Metrics/CyclomaticComplexity:
93
- Max: 7
94
- Exclude:
95
- - 'lib/kreuzberg/config.rb'
96
-
97
- Metrics/PerceivedComplexity:
98
- Max: 12
99
- Exclude:
100
- - 'lib/kreuzberg/config.rb'
101
-
102
- RSpec/RepeatedExampleGroupBody:
103
- Enabled: false
104
-
105
- RSpec/DescribeClass:
106
- Enabled: false
107
-
108
- RSpec/PredicateMatcher:
109
- Enabled: false
110
-
111
- Gemspec/AddRuntimeDependency:
112
- Enabled: true
113
-
114
- Gemspec/AttributeAssignment:
115
- Enabled: true
116
-
117
- Gemspec/DeprecatedAttributeAssignment:
118
- Enabled: true
119
-
120
- Gemspec/RequireMFA:
121
- Enabled: false
122
-
123
- Layout/EmptyLinesAfterModuleInclusion:
124
- Enabled: true
125
-
126
- Layout/LineContinuationLeadingSpace:
127
- Enabled: true
128
-
129
- Layout/LineContinuationSpacing:
130
- Enabled: true
131
-
132
- Layout/LineEndStringConcatenationIndentation:
133
- Enabled: true
134
-
135
- Layout/SpaceBeforeBrackets:
136
- Enabled: true
137
-
138
- Lint/AmbiguousAssignment:
139
- Enabled: true
140
-
141
- Lint/AmbiguousOperatorPrecedence:
142
- Enabled: true
143
-
144
- Lint/AmbiguousRange:
145
- Enabled: true
146
-
147
- Lint/ArrayLiteralInRegexp:
148
- Enabled: true
149
-
150
- Lint/ConstantOverwrittenInRescue:
151
- Enabled: true
152
-
153
- Lint/ConstantReassignment:
154
- Enabled: true
155
-
156
- Lint/CopDirectiveSyntax:
157
- Enabled: true
158
-
159
- Lint/DeprecatedConstants:
160
- Enabled: true
161
-
162
- Lint/DuplicateBranch:
163
- Enabled: true
164
-
165
- Lint/DuplicateMagicComment:
166
- Enabled: true
167
-
168
- Lint/DuplicateMatchPattern:
169
- Enabled: true
170
-
171
- Lint/DuplicateRegexpCharacterClassElement:
172
- Enabled: true
173
-
174
- Lint/DuplicateSetElement:
175
- Enabled: true
176
-
177
- Lint/EmptyBlock:
178
- Enabled: true
179
-
180
- Lint/EmptyClass:
181
- Enabled: true
182
-
183
- Lint/EmptyInPattern:
184
- Enabled: true
185
-
186
- Lint/HashNewWithKeywordArgumentsAsDefault:
187
- Enabled: true
188
-
189
- Lint/IncompatibleIoSelectWithFiberScheduler:
190
- Enabled: true
191
-
192
- Lint/ItWithoutArgumentsInBlock:
193
- Enabled: true
194
-
195
- Lint/LambdaWithoutLiteralBlock:
196
- Enabled: true
197
-
198
- Lint/LiteralAssignmentInCondition:
199
- Enabled: true
200
-
201
- Lint/MixedCaseRange:
202
- Enabled: true
203
-
204
- Lint/NoReturnInBeginEndBlocks:
205
- Enabled: true
206
-
207
- Lint/NonAtomicFileOperation:
208
- Enabled: true
209
-
210
- Lint/NumberedParameterAssignment:
211
- Enabled: true
212
-
213
- Lint/NumericOperationWithConstantResult:
214
- Enabled: true
215
-
216
- Lint/OrAssignmentToConstant:
217
- Enabled: true
218
-
219
- Lint/RedundantDirGlobSort:
220
- Enabled: true
221
-
222
- Lint/RedundantRegexpQuantifiers:
223
- Enabled: true
224
-
225
- Lint/RedundantTypeConversion:
226
- Enabled: true
227
-
228
- Lint/RefinementImportMethods:
229
- Enabled: true
230
-
231
- Lint/RequireRangeParentheses:
232
- Enabled: true
233
-
234
- Lint/RequireRelativeSelfPath:
235
- Enabled: true
236
-
237
- Lint/SharedMutableDefault:
238
- Enabled: true
239
-
240
- Lint/SuppressedExceptionInNumberConversion:
241
- Enabled: true
242
-
243
- Lint/SymbolConversion:
244
- Enabled: true
245
-
246
- Lint/ToEnumArguments:
247
- Enabled: true
248
-
249
- Lint/TripleQuotes:
250
- Enabled: true
251
-
252
- Lint/UnescapedBracketInRegexp:
253
- Enabled: true
254
-
255
- Lint/UnexpectedBlockArity:
256
- Enabled: true
257
-
258
- Lint/UnmodifiedReduceAccumulator:
259
- Enabled: true
260
-
261
- Lint/UselessConstantScoping:
262
- Enabled: true
263
-
264
- Lint/UselessDefaultValueArgument:
265
- Enabled: true
266
-
267
- Lint/UselessDefined:
268
- Enabled: true
269
-
270
- Lint/UselessNumericOperation:
271
- Enabled: true
272
-
273
- Lint/UselessOr:
274
- Enabled: true
275
-
276
- Lint/UselessRescue:
277
- Enabled: true
278
-
279
- Lint/UselessRuby2Keywords:
280
- Enabled: true
281
-
282
- Metrics/CollectionLiteralLength:
283
- Enabled: true
284
-
285
- Naming/BlockForwarding:
286
- Enabled: true
287
-
288
- Naming/PredicateMethod:
289
- Enabled: true
290
-
291
- Security/CompoundHash:
292
- Enabled: true
293
-
294
- Security/IoMethods:
295
- Enabled: true
296
-
297
- Style/AmbiguousEndlessMethodDefinition:
298
- Enabled: true
299
-
300
- Style/ArgumentsForwarding:
301
- Enabled: true
302
-
303
- Style/ArrayIntersect:
304
- Enabled: true
305
-
306
- Style/ArrayIntersectWithSingleElement:
307
- Enabled: true
308
-
309
- Style/BitwisePredicate:
310
- Enabled: true
311
-
312
- Style/CollectionCompact:
313
- Enabled: true
314
-
315
- Style/CollectionQuerying:
316
- Enabled: true
317
-
318
- Style/CombinableDefined:
319
- Enabled: true
320
-
321
- Style/ComparableBetween:
322
- Enabled: true
323
-
324
- Style/ComparableClamp:
325
- Enabled: true
326
-
327
- Style/ConcatArrayLiterals:
328
- Enabled: true
329
-
330
- Style/DataInheritance:
331
- Enabled: true
332
-
333
- Style/DigChain:
334
- Enabled: true
335
-
336
- Style/DirEmpty:
337
- Enabled: true
338
-
339
- Style/DocumentDynamicEvalDefinition:
340
- Enabled: true
341
-
342
- Style/EmptyHeredoc:
343
- Enabled: true
344
-
345
- Style/EmptyStringInsideInterpolation:
346
- Enabled: true
347
-
348
- Style/EndlessMethod:
349
- Enabled: true
350
-
351
- Style/EnvHome:
352
- Enabled: true
353
-
354
- Style/ExactRegexpMatch:
355
- Enabled: true
356
-
357
- Style/FetchEnvVar:
358
- Enabled: true
359
-
360
- Style/FileEmpty:
361
- Enabled: true
362
-
363
- Style/FileNull:
364
- Enabled: true
365
-
366
- Style/FileRead:
367
- Enabled: true
368
-
369
- Style/FileTouch:
370
- Enabled: true
371
-
372
- Style/FileWrite:
373
- Enabled: true
374
-
375
- Style/HashConversion:
376
- Enabled: true
377
-
378
- Style/HashExcept:
379
- Enabled: true
380
-
381
- Style/HashFetchChain:
382
- Enabled: true
383
-
384
- Style/HashSlice:
385
- Enabled: true
386
-
387
- Style/IfWithBooleanLiteralBranches:
388
- Enabled: true
389
-
390
- Style/InPatternThen:
391
- Enabled: true
392
-
393
- Style/ItAssignment:
394
- Enabled: true
395
-
396
- Style/ItBlockParameter:
397
- Enabled: true
398
-
399
- Style/KeywordArgumentsMerging:
400
- Enabled: true
401
-
402
- Style/MagicCommentFormat:
403
- Enabled: true
404
-
405
- Style/MapCompactWithConditionalBlock:
406
- Enabled: true
407
-
408
- Style/MapIntoArray:
409
- Enabled: true
410
-
411
- Style/MapToHash:
412
- Enabled: true
413
-
414
- Style/MapToSet:
415
- Enabled: true
416
-
417
- Style/MinMaxComparison:
418
- Enabled: true
419
-
420
- Style/MultilineInPatternThen:
421
- Enabled: true
422
-
423
- Style/NegatedIfElseCondition:
424
- Enabled: true
425
-
426
- Style/NestedFileDirname:
427
- Enabled: true
428
-
429
- Style/NilLambda:
430
- Enabled: true
431
-
432
- Style/NumberedParameters:
433
- Enabled: true
434
-
435
- Style/NumberedParametersLimit:
436
- Enabled: true
437
-
438
- Style/ObjectThen:
439
- Enabled: true
440
-
441
- Style/OpenStructUse:
442
- Enabled: true
443
-
444
- Style/OperatorMethodCall:
445
- Enabled: true
446
-
447
- Style/QuotedSymbols:
448
- Enabled: true
449
-
450
- Style/RedundantArgument:
451
- Enabled: true
452
-
453
- Style/RedundantArrayConstructor:
454
- Enabled: true
455
-
456
- Style/RedundantArrayFlatten:
457
- Enabled: true
458
-
459
- Style/RedundantConstantBase:
460
- Enabled: true
461
-
462
- Style/RedundantCurrentDirectoryInPath:
463
- Enabled: true
464
-
465
- Style/RedundantDoubleSplatHashBraces:
466
- Enabled: true
467
-
468
- Style/RedundantEach:
469
- Enabled: true
470
-
471
- Style/RedundantFilterChain:
472
- Enabled: true
473
-
474
- Style/RedundantFormat:
475
- Enabled: true
476
-
477
- Style/RedundantHeredocDelimiterQuotes:
478
- Enabled: true
479
-
480
- Style/RedundantInitialize:
481
- Enabled: true
482
-
483
- Style/RedundantInterpolationUnfreeze:
484
- Enabled: true
485
-
486
- Style/RedundantLineContinuation:
487
- Enabled: true
488
-
489
- Style/RedundantRegexpArgument:
490
- Enabled: true
491
-
492
- Style/RedundantRegexpConstructor:
493
- Enabled: true
494
-
495
- Style/RedundantSelfAssignmentBranch:
496
- Enabled: true
497
-
498
- Style/RedundantStringEscape:
499
- Enabled: true
500
-
501
- Style/ReturnNilInPredicateMethodDefinition:
502
- Enabled: true
503
-
504
- Style/SafeNavigationChainLength:
505
- Enabled: true
506
-
507
- Style/SelectByRegexp:
508
- Enabled: true
509
-
510
- Style/SendWithLiteralMethodName:
511
- Enabled: true
512
-
513
- Style/SingleLineDoEndBlock:
514
- Enabled: true
515
-
516
- Style/StringChars:
517
- Enabled: true
518
-
519
- Style/SuperArguments:
520
- Enabled: true
521
-
522
- Style/SuperWithArgsParentheses:
523
- Enabled: true
524
-
525
- Style/SwapValues:
526
- Enabled: true
527
-
528
- Style/YAMLFileRead:
529
- Enabled: true
530
-
531
- RSpec/ExampleLength:
532
- Max: 35
533
-
534
- RSpec/MultipleExpectations:
535
- Max: 15
536
-
537
- RSpec/NestedGroups:
538
- Max: 6
1
+
2
+ plugins:
3
+ - rubocop-performance
4
+ - rubocop-rspec
5
+
6
+ AllCops:
7
+ TargetRubyVersion: 3.2
8
+ NewCops: enable
9
+ SuggestExtensions: false
10
+ Exclude:
11
+ - 'vendor/**/*'
12
+ - 'tmp/**/*'
13
+ - 'lib/**/*.bundle'
14
+ - 'ext/**/*'
15
+
16
+ Style/StringLiterals:
17
+ Enabled: true
18
+ EnforcedStyle: single_quotes
19
+
20
+ Style/StringLiteralsInInterpolation:
21
+ Enabled: true
22
+ EnforcedStyle: single_quotes
23
+
24
+ Style/FrozenStringLiteralComment:
25
+ Enabled: true
26
+ EnforcedStyle: always
27
+
28
+ Style/Documentation:
29
+ Enabled: false
30
+
31
+ Layout/LineLength:
32
+ Max: 120
33
+ AllowedPatterns:
34
+ - '\A\s*#'
35
+ Exclude:
36
+ - 'spec/**/*'
37
+
38
+ Metrics/BlockLength:
39
+ Enabled: true
40
+ Max: 350
41
+ CountComments: false
42
+ CountAsOne: []
43
+
44
+ Metrics/MethodLength:
45
+ Max: 18
46
+ Exclude:
47
+ - 'spec/**/*'
48
+ - 'examples/**/*'
49
+
50
+ Metrics/AbcSize:
51
+ Max: 20
52
+ Exclude:
53
+ - 'spec/**/*'
54
+ - 'examples/**/*'
55
+ - 'lib/kreuzberg/config.rb'
56
+
57
+ Naming/FileName:
58
+ Enabled: true
59
+ Exclude:
60
+ - 'Gemfile'
61
+ - 'Rakefile'
62
+
63
+ RSpec/SpecFilePathFormat:
64
+ Enabled: false
65
+ RSpec/SpecFilePathSuffix:
66
+ Enabled: false
67
+
68
+ RSpec/PendingWithoutReason:
69
+ Enabled: false
70
+
71
+ RSpec/LeakyConstantDeclaration:
72
+ Enabled: false
73
+
74
+ RSpec/UnspecifiedException:
75
+ Enabled: false
76
+
77
+ Lint/ConstantDefinitionInBlock:
78
+ Enabled: false
79
+ Exclude:
80
+ - 'spec/**/*'
81
+
82
+ RSpec/InstanceVariable:
83
+ Enabled: false
84
+
85
+ Gemspec/DevelopmentDependencies:
86
+ Enabled: false
87
+
88
+ Metrics/ParameterLists:
89
+ Max: 14
90
+ Exclude:
91
+ - 'lib/kreuzberg/config.rb'
92
+
93
+ Metrics/CyclomaticComplexity:
94
+ Max: 7
95
+ Exclude:
96
+ - 'lib/kreuzberg/config.rb'
97
+
98
+ Metrics/PerceivedComplexity:
99
+ Max: 12
100
+ Exclude:
101
+ - 'lib/kreuzberg/config.rb'
102
+
103
+ Metrics/ClassLength:
104
+ Exclude:
105
+ - 'lib/kreuzberg/config.rb'
106
+
107
+ RSpec/RepeatedExampleGroupBody:
108
+ Enabled: false
109
+
110
+ RSpec/DescribeClass:
111
+ Enabled: false
112
+
113
+ RSpec/PredicateMatcher:
114
+ Enabled: false
115
+
116
+ Gemspec/AddRuntimeDependency:
117
+ Enabled: true
118
+
119
+ Gemspec/AttributeAssignment:
120
+ Enabled: true
121
+
122
+ Gemspec/DeprecatedAttributeAssignment:
123
+ Enabled: true
124
+
125
+ Gemspec/RequireMFA:
126
+ Enabled: false
127
+
128
+ Layout/EmptyLinesAfterModuleInclusion:
129
+ Enabled: true
130
+
131
+ Layout/LineContinuationLeadingSpace:
132
+ Enabled: true
133
+
134
+ Layout/LineContinuationSpacing:
135
+ Enabled: true
136
+
137
+ Layout/LineEndStringConcatenationIndentation:
138
+ Enabled: true
139
+
140
+ Layout/SpaceBeforeBrackets:
141
+ Enabled: true
142
+
143
+ Lint/AmbiguousAssignment:
144
+ Enabled: true
145
+
146
+ Lint/AmbiguousOperatorPrecedence:
147
+ Enabled: true
148
+
149
+ Lint/AmbiguousRange:
150
+ Enabled: true
151
+
152
+ Lint/ArrayLiteralInRegexp:
153
+ Enabled: true
154
+
155
+ Lint/ConstantOverwrittenInRescue:
156
+ Enabled: true
157
+
158
+ Lint/ConstantReassignment:
159
+ Enabled: true
160
+
161
+ Lint/CopDirectiveSyntax:
162
+ Enabled: true
163
+
164
+ Lint/DeprecatedConstants:
165
+ Enabled: true
166
+
167
+ Lint/DuplicateBranch:
168
+ Enabled: true
169
+
170
+ Lint/DuplicateMagicComment:
171
+ Enabled: true
172
+
173
+ Lint/DuplicateMatchPattern:
174
+ Enabled: true
175
+
176
+ Lint/DuplicateRegexpCharacterClassElement:
177
+ Enabled: true
178
+
179
+ Lint/DuplicateSetElement:
180
+ Enabled: true
181
+
182
+ Lint/EmptyBlock:
183
+ Enabled: true
184
+
185
+ Lint/EmptyClass:
186
+ Enabled: true
187
+
188
+ Lint/EmptyInPattern:
189
+ Enabled: true
190
+
191
+ Lint/HashNewWithKeywordArgumentsAsDefault:
192
+ Enabled: true
193
+
194
+ Lint/IncompatibleIoSelectWithFiberScheduler:
195
+ Enabled: true
196
+
197
+ Lint/ItWithoutArgumentsInBlock:
198
+ Enabled: true
199
+
200
+ Lint/LambdaWithoutLiteralBlock:
201
+ Enabled: true
202
+
203
+ Lint/LiteralAssignmentInCondition:
204
+ Enabled: true
205
+
206
+ Lint/MixedCaseRange:
207
+ Enabled: true
208
+
209
+ Lint/NoReturnInBeginEndBlocks:
210
+ Enabled: true
211
+
212
+ Lint/NonAtomicFileOperation:
213
+ Enabled: true
214
+
215
+ Lint/NumberedParameterAssignment:
216
+ Enabled: true
217
+
218
+ Lint/NumericOperationWithConstantResult:
219
+ Enabled: true
220
+
221
+ Lint/OrAssignmentToConstant:
222
+ Enabled: true
223
+
224
+ Lint/RedundantDirGlobSort:
225
+ Enabled: true
226
+
227
+ Lint/RedundantRegexpQuantifiers:
228
+ Enabled: true
229
+
230
+ Lint/RedundantTypeConversion:
231
+ Enabled: true
232
+
233
+ Lint/RefinementImportMethods:
234
+ Enabled: true
235
+
236
+ Lint/RequireRangeParentheses:
237
+ Enabled: true
238
+
239
+ Lint/RequireRelativeSelfPath:
240
+ Enabled: true
241
+
242
+ Lint/SharedMutableDefault:
243
+ Enabled: true
244
+
245
+ Lint/SuppressedExceptionInNumberConversion:
246
+ Enabled: true
247
+
248
+ Lint/SymbolConversion:
249
+ Enabled: true
250
+
251
+ Lint/ToEnumArguments:
252
+ Enabled: true
253
+
254
+ Lint/TripleQuotes:
255
+ Enabled: true
256
+
257
+ Lint/UnescapedBracketInRegexp:
258
+ Enabled: true
259
+
260
+ Lint/UnexpectedBlockArity:
261
+ Enabled: true
262
+
263
+ Lint/UnmodifiedReduceAccumulator:
264
+ Enabled: true
265
+
266
+ Lint/UselessConstantScoping:
267
+ Enabled: true
268
+
269
+ Lint/UselessDefaultValueArgument:
270
+ Enabled: true
271
+
272
+ Lint/UselessDefined:
273
+ Enabled: true
274
+
275
+ Lint/UselessNumericOperation:
276
+ Enabled: true
277
+
278
+ Lint/UselessOr:
279
+ Enabled: true
280
+
281
+ Lint/UselessRescue:
282
+ Enabled: true
283
+
284
+ Lint/UselessRuby2Keywords:
285
+ Enabled: true
286
+
287
+ Metrics/CollectionLiteralLength:
288
+ Enabled: true
289
+
290
+ Naming/BlockForwarding:
291
+ Enabled: true
292
+
293
+ Naming/PredicateMethod:
294
+ Enabled: true
295
+
296
+ Security/CompoundHash:
297
+ Enabled: true
298
+
299
+ Security/IoMethods:
300
+ Enabled: true
301
+
302
+ Style/AmbiguousEndlessMethodDefinition:
303
+ Enabled: true
304
+
305
+ Style/ArgumentsForwarding:
306
+ Enabled: true
307
+
308
+ Style/ArrayIntersect:
309
+ Enabled: true
310
+
311
+ Style/ArrayIntersectWithSingleElement:
312
+ Enabled: true
313
+
314
+ Style/BitwisePredicate:
315
+ Enabled: true
316
+
317
+ Style/CollectionCompact:
318
+ Enabled: true
319
+
320
+ Style/CollectionQuerying:
321
+ Enabled: true
322
+
323
+ Style/CombinableDefined:
324
+ Enabled: true
325
+
326
+ Style/ComparableBetween:
327
+ Enabled: true
328
+
329
+ Style/ComparableClamp:
330
+ Enabled: true
331
+
332
+ Style/ConcatArrayLiterals:
333
+ Enabled: true
334
+
335
+ Style/DataInheritance:
336
+ Enabled: true
337
+
338
+ Style/DigChain:
339
+ Enabled: true
340
+
341
+ Style/DirEmpty:
342
+ Enabled: true
343
+
344
+ Style/DocumentDynamicEvalDefinition:
345
+ Enabled: true
346
+
347
+ Style/EmptyHeredoc:
348
+ Enabled: true
349
+
350
+ Style/EmptyStringInsideInterpolation:
351
+ Enabled: true
352
+
353
+ Style/EndlessMethod:
354
+ Enabled: true
355
+
356
+ Style/EnvHome:
357
+ Enabled: true
358
+
359
+ Style/ExactRegexpMatch:
360
+ Enabled: true
361
+
362
+ Style/FetchEnvVar:
363
+ Enabled: true
364
+
365
+ Style/FileEmpty:
366
+ Enabled: true
367
+
368
+ Style/FileNull:
369
+ Enabled: true
370
+
371
+ Style/FileRead:
372
+ Enabled: true
373
+
374
+ Style/FileTouch:
375
+ Enabled: true
376
+
377
+ Style/FileWrite:
378
+ Enabled: true
379
+
380
+ Style/HashConversion:
381
+ Enabled: true
382
+
383
+ Style/HashExcept:
384
+ Enabled: true
385
+
386
+ Style/HashFetchChain:
387
+ Enabled: true
388
+
389
+ Style/HashSlice:
390
+ Enabled: true
391
+
392
+ Style/IfWithBooleanLiteralBranches:
393
+ Enabled: true
394
+
395
+ Style/InPatternThen:
396
+ Enabled: true
397
+
398
+ Style/ItAssignment:
399
+ Enabled: true
400
+
401
+ Style/ItBlockParameter:
402
+ Enabled: true
403
+
404
+ Style/KeywordArgumentsMerging:
405
+ Enabled: true
406
+
407
+ Style/MagicCommentFormat:
408
+ Enabled: true
409
+
410
+ Style/MapCompactWithConditionalBlock:
411
+ Enabled: true
412
+
413
+ Style/MapIntoArray:
414
+ Enabled: true
415
+
416
+ Style/MapToHash:
417
+ Enabled: true
418
+
419
+ Style/MapToSet:
420
+ Enabled: true
421
+
422
+ Style/MinMaxComparison:
423
+ Enabled: true
424
+
425
+ Style/MultilineInPatternThen:
426
+ Enabled: true
427
+
428
+ Style/NegatedIfElseCondition:
429
+ Enabled: true
430
+
431
+ Style/NestedFileDirname:
432
+ Enabled: true
433
+
434
+ Style/NilLambda:
435
+ Enabled: true
436
+
437
+ Style/NumberedParameters:
438
+ Enabled: true
439
+
440
+ Style/NumberedParametersLimit:
441
+ Enabled: true
442
+
443
+ Style/ObjectThen:
444
+ Enabled: true
445
+
446
+ Style/OpenStructUse:
447
+ Enabled: true
448
+
449
+ Style/OperatorMethodCall:
450
+ Enabled: true
451
+
452
+ Style/QuotedSymbols:
453
+ Enabled: true
454
+
455
+ Style/RedundantArgument:
456
+ Enabled: true
457
+
458
+ Style/RedundantArrayConstructor:
459
+ Enabled: true
460
+
461
+ Style/RedundantArrayFlatten:
462
+ Enabled: true
463
+
464
+ Style/RedundantConstantBase:
465
+ Enabled: true
466
+
467
+ Style/RedundantCurrentDirectoryInPath:
468
+ Enabled: true
469
+
470
+ Style/RedundantDoubleSplatHashBraces:
471
+ Enabled: true
472
+
473
+ Style/RedundantEach:
474
+ Enabled: true
475
+
476
+ Style/RedundantFilterChain:
477
+ Enabled: true
478
+
479
+ Style/RedundantFormat:
480
+ Enabled: true
481
+
482
+ Style/RedundantHeredocDelimiterQuotes:
483
+ Enabled: true
484
+
485
+ Style/RedundantInitialize:
486
+ Enabled: true
487
+
488
+ Style/RedundantInterpolationUnfreeze:
489
+ Enabled: true
490
+
491
+ Style/RedundantLineContinuation:
492
+ Enabled: true
493
+
494
+ Style/RedundantRegexpArgument:
495
+ Enabled: true
496
+
497
+ Style/RedundantRegexpConstructor:
498
+ Enabled: true
499
+
500
+ Style/RedundantSelfAssignmentBranch:
501
+ Enabled: true
502
+
503
+ Style/RedundantStringEscape:
504
+ Enabled: true
505
+
506
+ Style/ReturnNilInPredicateMethodDefinition:
507
+ Enabled: true
508
+
509
+ Style/SafeNavigationChainLength:
510
+ Enabled: true
511
+
512
+ Style/SelectByRegexp:
513
+ Enabled: true
514
+
515
+ Style/SendWithLiteralMethodName:
516
+ Enabled: true
517
+
518
+ Style/SingleLineDoEndBlock:
519
+ Enabled: true
520
+
521
+ Style/StringChars:
522
+ Enabled: true
523
+
524
+ Style/SuperArguments:
525
+ Enabled: true
526
+
527
+ Style/SuperWithArgsParentheses:
528
+ Enabled: true
529
+
530
+ Style/SwapValues:
531
+ Enabled: true
532
+
533
+ Style/YAMLFileRead:
534
+ Enabled: true
535
+
536
+ RSpec/ExampleLength:
537
+ Max: 50
538
+
539
+ RSpec/MultipleExpectations:
540
+ Max: 25
541
+
542
+ RSpec/NestedGroups:
543
+ Max: 6