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
@@ -1,53 +0,0 @@
1
- /// Prevents premature destruction of local objects.
2
- ///
3
- /// Ruby's garbage collector is conservative; it scans the C level machine stack as well.
4
- /// Possible in-use Ruby objects must remain visible on stack, to be properly marked as such.
5
- /// However, Rust's compiler optimizations might remove the references to these objects from
6
- /// the stack when they are not being used directly.
7
- ///
8
- /// Consider the following example:
9
- ///
10
- /// ```ignore
11
- /// use rb_sys::{rb_str_new_cstr, rb_str_cat_cstr, RSTRING_PTR, rb_gc_guard};
12
- ///
13
- /// unsafe {
14
- /// let s = rb_str_new_cstr(" world\0".as_ptr() as _);
15
- /// let sptr = RSTRING_PTR(s);
16
- /// let t = rb_str_new_cstr("hello,\0".as_ptr() as _); // Possible GC invocation
17
- /// let u = rb_str_cat_cstr(t, sptr);
18
- /// rb_gc_guard!(s); // ensure `s` (and thus `sptr`) do not get GC-ed
19
- /// }
20
- /// ```
21
- ///
22
- /// In this example, without the `rb_gc_guard!`, the last use of `s` is before the last use
23
- /// of `sptr`. Compilers could think `s` and `t` are allowed to overlap. That would
24
- /// eliminate `s` from the stack, while `sptr` is still in use. If our GC runs at that
25
- /// very moment, `s` gets swept out, which also destroys `sptr`.
26
- ///
27
- /// In order to prevent this scenario, `rb_gc_guard!` must be placed after the last use
28
- /// of `sptr`. Placing `rb_gc_guard!` before dereferencing `sptr` would be of no use.
29
- ///
30
- /// Using the `rb_gc_guard!` macro has the following advantages:
31
- ///
32
- /// - the intent of the macro use is clear.
33
- ///
34
- /// - `rb_gc_guard!` only affects its call site, without negatively affecting other systems.
35
- ///
36
- /// # Example
37
- /// ```no_run
38
- /// use rb_sys::{rb_utf8_str_new_cstr, rb_gc_guard};
39
- ///
40
- /// let my_string = unsafe { rb_utf8_str_new_cstr("hello world\0".as_ptr() as _) };
41
- /// let _ = rb_gc_guard!(my_string);
42
- /// ```
43
- #[macro_export]
44
- macro_rules! rb_gc_guard {
45
- ($v:expr) => {{
46
- unsafe {
47
- let val: $crate::VALUE = $v;
48
- let rb_gc_guarded_ptr = std::ptr::read_volatile(&&val);
49
- std::arch::asm!("/* {0} */", in(reg) rb_gc_guarded_ptr);
50
- *rb_gc_guarded_ptr
51
- }
52
- }};
53
- }
@@ -1,38 +0,0 @@
1
- //! Helper to define the `ruby_abi_version` function needed for extensions.
2
- //!
3
- //! Since Ruby 3.2, gems are required to define a `ruby_abi_version` function.
4
- //! For C extensions, this is done transparently by including `ruby.h`, but for
5
- //! Rust we have to define it ourselves. This is enabled automatically by when
6
- //! compiling a gem.
7
-
8
- #[doc(hidden)]
9
- #[cfg(not(has_ruby_abi_version))]
10
- pub const __RB_SYS_RUBY_ABI_VERSION: std::os::raw::c_ulonglong = 0;
11
-
12
- #[doc(hidden)]
13
- #[cfg(has_ruby_abi_version)]
14
- pub const __RB_SYS_RUBY_ABI_VERSION: std::os::raw::c_ulonglong = crate::RUBY_ABI_VERSION as _;
15
-
16
- #[doc(hidden)]
17
- #[no_mangle]
18
- #[allow(unused)]
19
- pub extern "C" fn ruby_abi_version() -> std::os::raw::c_ulonglong {
20
- __RB_SYS_RUBY_ABI_VERSION
21
- }
22
-
23
- #[doc(hidden)]
24
- #[no_mangle]
25
- #[allow(unused)]
26
- #[cfg(ruby_engine = "truffleruby")]
27
- pub extern "C" fn rb_tr_abi_version() -> *const std::os::raw::c_char {
28
- crate::TRUFFLERUBY_ABI_VERSION.as_ptr() as *const _
29
- }
30
-
31
- #[deprecated(
32
- since = "0.9.102",
33
- note = "You no longer need to invoke this macro, the `ruby_abi_version` function is defined automatically."
34
- )]
35
- #[macro_export]
36
- macro_rules! ruby_abi_version {
37
- () => {};
38
- }
@@ -1,31 +0,0 @@
1
- #![allow(rustdoc::broken_intra_doc_links)]
2
- #![allow(non_upper_case_globals)]
3
- #![allow(non_snake_case)]
4
-
5
- //! Definitions for Ruby's special constants.
6
- //!
7
- //! Makes it easier to reference important Ruby constants, without having to dig
8
- //! around in bindgen's output.
9
-
10
- use std::ffi::c_long;
11
-
12
- use crate::{VALUE, ruby_special_consts};
13
-
14
- pub const Qfalse: ruby_special_consts = ruby_special_consts::RUBY_Qfalse;
15
- pub const Qtrue: ruby_special_consts = ruby_special_consts::RUBY_Qtrue;
16
- pub const Qnil: ruby_special_consts = ruby_special_consts::RUBY_Qnil;
17
- pub const Qundef: ruby_special_consts = ruby_special_consts::RUBY_Qundef;
18
- pub const IMMEDIATE_MASK: ruby_special_consts = ruby_special_consts::RUBY_IMMEDIATE_MASK;
19
- pub const FIXNUM_FLAG: ruby_special_consts = ruby_special_consts::RUBY_FIXNUM_FLAG;
20
- pub const FIXNUM_MIN: c_long = c_long::MIN / 2;
21
- pub const FIXNUM_MAX: c_long = c_long::MAX / 2;
22
- pub const FLONUM_MASK: ruby_special_consts = ruby_special_consts::RUBY_FLONUM_MASK;
23
- pub const FLONUM_FLAG: ruby_special_consts = ruby_special_consts::RUBY_FLONUM_FLAG;
24
- pub const SYMBOL_FLAG: ruby_special_consts = ruby_special_consts::RUBY_SYMBOL_FLAG;
25
-
26
- #[allow(clippy::from_over_into)]
27
- impl Into<VALUE> for ruby_special_consts {
28
- fn into(self) -> VALUE {
29
- self as VALUE
30
- }
31
- }
@@ -1,179 +0,0 @@
1
- #include "ruby.h"
2
- #include "ruby/ruby.h"
3
- #include "ruby/intern.h"
4
- #include "ruby/version.h"
5
-
6
- // Check that we have Ruby API version macros
7
- #if !defined(RUBY_API_VERSION_MAJOR)
8
- #error "RUBY_API_VERSION_MAJOR is not defined, Ruby headers might not be configured correctly"
9
- #endif
10
-
11
- #if !defined(RUBY_API_VERSION_MINOR)
12
- #error "RUBY_API_VERSION_MINOR is not defined, Ruby headers might not be configured correctly"
13
- #endif
14
-
15
- // Define a macro to check for Ruby 3.3+
16
- #if RUBY_API_VERSION_MAJOR > 3 || (RUBY_API_VERSION_MAJOR == 3 && RUBY_API_VERSION_MINOR >= 3)
17
- #define RUBY_VERSION_AT_LEAST_3_3 1
18
- #else
19
- #define RUBY_VERSION_AT_LEAST_3_3 0
20
- #endif
21
-
22
- long impl_rstring_len(VALUE obj)
23
- {
24
- return RSTRING_LEN(obj);
25
- }
26
-
27
- char *
28
- impl_rstring_ptr(VALUE obj)
29
- {
30
- return RSTRING_PTR(obj);
31
- }
32
-
33
- long impl_rarray_len(VALUE obj)
34
- {
35
- return RARRAY_LEN(obj);
36
- }
37
-
38
- const VALUE *
39
- impl_rarray_const_ptr(VALUE obj)
40
- {
41
- return RARRAY_CONST_PTR(obj);
42
- }
43
-
44
- VALUE
45
- impl_rbasic_class(VALUE obj)
46
- {
47
- return RBASIC_CLASS(obj);
48
- }
49
-
50
- int impl_frozen_p(VALUE obj)
51
- {
52
- return RB_OBJ_FROZEN(obj);
53
- }
54
-
55
- int impl_special_const_p(VALUE obj)
56
- {
57
- return SPECIAL_CONST_P(obj);
58
- }
59
-
60
- int impl_bignum_positive_p(VALUE obj)
61
- {
62
- return RBIGNUM_POSITIVE_P(obj);
63
- }
64
-
65
- int impl_bignum_negative_p(VALUE obj)
66
- {
67
- return RBIGNUM_NEGATIVE_P(obj);
68
- }
69
-
70
- enum ruby_value_type
71
- impl_builtin_type(VALUE obj)
72
- {
73
- return RB_BUILTIN_TYPE(obj);
74
- }
75
-
76
- int impl_nil_p(VALUE obj)
77
- {
78
- return NIL_P(obj);
79
- }
80
-
81
- int impl_fixnum_p(VALUE obj)
82
- {
83
- return FIXNUM_P(obj);
84
- }
85
-
86
- int impl_static_sym_p(VALUE obj)
87
- {
88
- return STATIC_SYM_P(obj);
89
- }
90
-
91
- int impl_flonum_p(VALUE obj)
92
- {
93
- return FLONUM_P(obj);
94
- }
95
-
96
- int impl_immediate_p(VALUE obj)
97
- {
98
- return IMMEDIATE_P(obj);
99
- }
100
-
101
- int impl_rb_test(VALUE obj)
102
- {
103
- return RB_TEST(obj);
104
- }
105
-
106
- int impl_type_p(VALUE obj, enum ruby_value_type type)
107
- {
108
- return RB_TYPE_P(obj, type);
109
- }
110
-
111
- int impl_dynamic_sym_p(VALUE obj)
112
- {
113
- return RB_DYNAMIC_SYM_P(obj);
114
- }
115
-
116
- int impl_symbol_p(VALUE obj)
117
- {
118
- return RB_SYMBOL_P(obj);
119
- }
120
-
121
- int impl_float_type_p(VALUE obj)
122
- {
123
- return RB_FLOAT_TYPE_P(obj);
124
- }
125
-
126
- enum ruby_value_type
127
- impl_rb_type(VALUE obj)
128
- {
129
- return rb_type(obj);
130
- }
131
-
132
- int impl_integer_type_p(VALUE obj)
133
- {
134
- return RB_INTEGER_TYPE_P(obj);
135
- }
136
-
137
- int impl_rstring_interned_p(VALUE obj)
138
- {
139
- Check_Type(obj, T_STRING);
140
-
141
- return !(FL_TEST(obj, RSTRING_FSTR) == 0);
142
- }
143
-
144
- void impl_thread_sleep(struct timeval time)
145
- {
146
- rb_thread_wait_for(time);
147
- }
148
-
149
- // RTypedData implementations
150
- int impl_rtypeddata_p(VALUE obj)
151
- {
152
- return RTYPEDDATA_P(obj);
153
- }
154
-
155
- int impl_rtypeddata_embedded_p(VALUE obj)
156
- {
157
- #if RUBY_VERSION_AT_LEAST_3_3
158
- return RTYPEDDATA_EMBEDDED_P(obj);
159
- #else
160
- // On Ruby versions before 3.3, embedded typed data is not supported
161
- return 0;
162
- #endif
163
- }
164
-
165
- const struct rb_data_type_struct *
166
- impl_rtypeddata_type(VALUE obj)
167
- {
168
- return RTYPEDDATA_TYPE(obj);
169
- }
170
-
171
- void *
172
- impl_rtypeddata_get_data(VALUE obj)
173
- {
174
- #if RUBY_VERSION_AT_LEAST_3_3
175
- return RTYPEDDATA_GET_DATA(obj);
176
- #else
177
- return RTYPEDDATA(obj)->data;
178
- #endif
179
- }
@@ -1,257 +0,0 @@
1
- use super::StableApiDefinition;
2
- use crate::{RUBY_API_VERSION_MAJOR, RUBY_API_VERSION_MINOR, VALUE, ruby_value_type, timeval};
3
- use std::{
4
- ffi::c_void,
5
- os::raw::{c_char, c_long},
6
- ptr::NonNull,
7
- time::Duration,
8
- };
9
-
10
- #[allow(dead_code)]
11
- extern "C" {
12
- #[link_name = "impl_rstring_len"]
13
- fn impl_rstring_len(str: VALUE) -> c_long;
14
-
15
- #[link_name = "impl_rstring_ptr"]
16
- fn impl_rstring_ptr(str: VALUE) -> *const c_char;
17
-
18
- #[link_name = "impl_rarray_len"]
19
- fn impl_rarray_len(ary: VALUE) -> c_long;
20
-
21
- #[link_name = "impl_rarray_const_ptr"]
22
- fn impl_rarray_const_ptr(ary: VALUE) -> *const VALUE;
23
-
24
- #[link_name = "impl_rbasic_class"]
25
- fn impl_rbasic_class(obj: VALUE) -> VALUE;
26
-
27
- #[link_name = "impl_frozen_p"]
28
- fn impl_frozen_p(obj: VALUE) -> bool;
29
-
30
- #[link_name = "impl_special_const_p"]
31
- fn impl_special_const_p(value: VALUE) -> bool;
32
-
33
- #[link_name = "impl_bignum_positive_p"]
34
- fn impl_bignum_positive_p(obj: VALUE) -> bool;
35
-
36
- #[link_name = "impl_bignum_negative_p"]
37
- fn impl_bignum_negative_p(obj: VALUE) -> bool;
38
-
39
- #[link_name = "impl_builtin_type"]
40
- fn impl_builtin_type(obj: VALUE) -> ruby_value_type;
41
-
42
- #[link_name = "impl_nil_p"]
43
- fn impl_nil_p(obj: VALUE) -> bool;
44
-
45
- #[link_name = "impl_fixnum_p"]
46
- fn impl_fixnum_p(obj: VALUE) -> bool;
47
-
48
- #[link_name = "impl_static_sym_p"]
49
- fn impl_static_sym_p(obj: VALUE) -> bool;
50
-
51
- #[link_name = "impl_flonum_p"]
52
- fn impl_flonum_p(obj: VALUE) -> bool;
53
-
54
- #[link_name = "impl_immediate_p"]
55
- fn impl_immediate_p(obj: VALUE) -> bool;
56
-
57
- #[link_name = "impl_rb_test"]
58
- fn impl_rb_test(obj: VALUE) -> bool;
59
-
60
- #[link_name = "impl_type_p"]
61
- fn impl_type_p(obj: VALUE, ty: ruby_value_type) -> bool;
62
-
63
- #[link_name = "impl_dynamic_sym_p"]
64
- fn impl_dynamic_sym_p(obj: VALUE) -> bool;
65
-
66
- #[link_name = "impl_symbol_p"]
67
- fn impl_symbol_p(obj: VALUE) -> bool;
68
-
69
- #[link_name = "impl_float_type_p"]
70
- fn impl_float_type_p(obj: VALUE) -> bool;
71
-
72
- #[link_name = "impl_rb_type"]
73
- fn impl_rb_type(obj: VALUE) -> ruby_value_type;
74
-
75
- #[link_name = "impl_integer_type_p"]
76
- fn impl_integer_type_p(obj: VALUE) -> bool;
77
-
78
- #[link_name = "impl_rstring_interned_p"]
79
- fn impl_rstring_interned_p(obj: VALUE) -> bool;
80
-
81
- #[link_name = "impl_thread_sleep"]
82
- fn impl_thread_sleep(interval: timeval);
83
-
84
- // RTypedData functions
85
- #[link_name = "impl_rtypeddata_p"]
86
- fn impl_rtypeddata_p(obj: VALUE) -> bool;
87
-
88
- #[link_name = "impl_rtypeddata_embedded_p"]
89
- fn impl_rtypeddata_embedded_p(obj: VALUE) -> bool;
90
-
91
- #[link_name = "impl_rtypeddata_type"]
92
- fn impl_rtypeddata_type(obj: VALUE) -> *const crate::rb_data_type_t;
93
-
94
- #[link_name = "impl_rtypeddata_get_data"]
95
- fn impl_rtypeddata_get_data(obj: VALUE) -> *mut c_void;
96
- }
97
-
98
- pub struct Definition;
99
-
100
- impl StableApiDefinition for Definition {
101
- const VERSION_MAJOR: u32 = RUBY_API_VERSION_MAJOR;
102
- const VERSION_MINOR: u32 = RUBY_API_VERSION_MINOR;
103
-
104
- #[inline]
105
- unsafe fn rstring_len(&self, obj: VALUE) -> std::os::raw::c_long {
106
- impl_rstring_len(obj)
107
- }
108
-
109
- #[inline]
110
- unsafe fn rstring_ptr(&self, obj: VALUE) -> *const std::os::raw::c_char {
111
- impl_rstring_ptr(obj)
112
- }
113
-
114
- #[inline]
115
- unsafe fn rarray_len(&self, obj: VALUE) -> std::os::raw::c_long {
116
- impl_rarray_len(obj)
117
- }
118
-
119
- #[inline]
120
- unsafe fn rarray_const_ptr(&self, obj: VALUE) -> *const VALUE {
121
- impl_rarray_const_ptr(obj)
122
- }
123
-
124
- #[inline]
125
- unsafe fn rbasic_class(&self, obj: VALUE) -> Option<NonNull<VALUE>> {
126
- NonNull::<VALUE>::new(impl_rbasic_class(obj) as _)
127
- }
128
-
129
- unsafe fn frozen_p(&self, obj: VALUE) -> bool {
130
- impl_frozen_p(obj)
131
- }
132
-
133
- #[inline]
134
- fn special_const_p(&self, value: VALUE) -> bool {
135
- unsafe { impl_special_const_p(value) }
136
- }
137
-
138
- #[inline]
139
- unsafe fn bignum_positive_p(&self, obj: VALUE) -> bool {
140
- impl_bignum_positive_p(obj)
141
- }
142
-
143
- #[inline]
144
- unsafe fn bignum_negative_p(&self, obj: VALUE) -> bool {
145
- impl_bignum_negative_p(obj)
146
- }
147
-
148
- #[inline]
149
- unsafe fn builtin_type(&self, obj: VALUE) -> ruby_value_type {
150
- impl_builtin_type(obj)
151
- }
152
-
153
- #[inline]
154
- fn nil_p(&self, obj: VALUE) -> bool {
155
- unsafe { impl_nil_p(obj) }
156
- }
157
-
158
- #[inline]
159
- fn fixnum_p(&self, obj: VALUE) -> bool {
160
- unsafe { impl_fixnum_p(obj) }
161
- }
162
-
163
- #[inline]
164
- fn static_sym_p(&self, obj: VALUE) -> bool {
165
- unsafe { impl_static_sym_p(obj) }
166
- }
167
-
168
- #[inline]
169
- fn flonum_p(&self, obj: VALUE) -> bool {
170
- unsafe { impl_flonum_p(obj) }
171
- }
172
-
173
- #[inline]
174
- fn immediate_p(&self, obj: VALUE) -> bool {
175
- unsafe { impl_immediate_p(obj) }
176
- }
177
-
178
- #[inline]
179
- fn rb_test(&self, obj: VALUE) -> bool {
180
- unsafe { impl_rb_test(obj) }
181
- }
182
-
183
- #[inline]
184
- unsafe fn type_p(&self, obj: VALUE, ty: ruby_value_type) -> bool {
185
- impl_type_p(obj, ty)
186
- }
187
-
188
- #[inline]
189
- unsafe fn dynamic_sym_p(&self, obj: VALUE) -> bool {
190
- impl_dynamic_sym_p(obj)
191
- }
192
-
193
- #[inline]
194
- unsafe fn symbol_p(&self, obj: VALUE) -> bool {
195
- impl_symbol_p(obj)
196
- }
197
-
198
- #[inline]
199
- unsafe fn float_type_p(&self, obj: VALUE) -> bool {
200
- impl_float_type_p(obj)
201
- }
202
-
203
- #[inline]
204
- unsafe fn rb_type(&self, obj: VALUE) -> crate::ruby_value_type {
205
- impl_rb_type(obj)
206
- }
207
-
208
- #[inline]
209
- unsafe fn integer_type_p(&self, obj: VALUE) -> bool {
210
- impl_integer_type_p(obj)
211
- }
212
-
213
- #[inline]
214
- unsafe fn rstring_interned_p(&self, obj: VALUE) -> bool {
215
- impl_rstring_interned_p(obj)
216
- }
217
-
218
- #[inline]
219
- fn thread_sleep(&self, duration: Duration) {
220
- let seconds = duration.as_secs() as _;
221
- let microseconds = duration.subsec_micros() as _;
222
-
223
- let time = crate::timeval {
224
- tv_sec: seconds,
225
- tv_usec: microseconds,
226
- };
227
-
228
- unsafe { impl_thread_sleep(time) }
229
- }
230
-
231
- #[inline]
232
- unsafe fn rtypeddata_p(&self, obj: VALUE) -> bool {
233
- impl_rtypeddata_p(obj)
234
- }
235
-
236
- #[inline]
237
- #[cfg(ruby_gte_3_3)]
238
- unsafe fn rtypeddata_embedded_p(&self, obj: VALUE) -> bool {
239
- impl_rtypeddata_embedded_p(obj)
240
- }
241
-
242
- #[inline]
243
- #[cfg(ruby_lt_3_3)]
244
- unsafe fn rtypeddata_embedded_p(&self, _obj: VALUE) -> bool {
245
- false
246
- }
247
-
248
- #[inline]
249
- unsafe fn rtypeddata_type(&self, obj: VALUE) -> *const crate::rb_data_type_t {
250
- impl_rtypeddata_type(obj)
251
- }
252
-
253
- #[inline]
254
- unsafe fn rtypeddata_get_data(&self, obj: VALUE) -> *mut c_void {
255
- impl_rtypeddata_get_data(obj)
256
- }
257
- }