kreuzberg 4.0.0.rc2 → 4.0.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (446) hide show
  1. checksums.yaml +4 -4
  2. data/.gitignore +14 -14
  3. data/.rspec +3 -3
  4. data/.rubocop.yaml +1 -1
  5. data/.rubocop.yml +543 -538
  6. data/Gemfile +8 -8
  7. data/Gemfile.lock +194 -6
  8. data/README.md +391 -426
  9. data/Rakefile +34 -25
  10. data/Steepfile +51 -47
  11. data/examples/async_patterns.rb +283 -341
  12. data/ext/kreuzberg_rb/extconf.rb +65 -45
  13. data/ext/kreuzberg_rb/native/.cargo/config.toml +23 -0
  14. data/ext/kreuzberg_rb/native/Cargo.lock +7619 -6535
  15. data/ext/kreuzberg_rb/native/Cargo.toml +75 -44
  16. data/ext/kreuzberg_rb/native/README.md +425 -425
  17. data/ext/kreuzberg_rb/native/build.rs +15 -15
  18. data/ext/kreuzberg_rb/native/include/ieeefp.h +11 -11
  19. data/ext/kreuzberg_rb/native/include/msvc_compat/strings.h +14 -14
  20. data/ext/kreuzberg_rb/native/include/strings.h +20 -20
  21. data/ext/kreuzberg_rb/native/include/unistd.h +47 -47
  22. data/ext/kreuzberg_rb/native/src/lib.rs +3802 -2998
  23. data/extconf.rb +60 -28
  24. data/kreuzberg.gemspec +199 -148
  25. data/lib/kreuzberg/api_proxy.rb +126 -142
  26. data/lib/kreuzberg/cache_api.rb +67 -46
  27. data/lib/kreuzberg/cli.rb +47 -55
  28. data/lib/kreuzberg/cli_proxy.rb +117 -127
  29. data/lib/kreuzberg/config.rb +936 -691
  30. data/lib/kreuzberg/error_context.rb +136 -32
  31. data/lib/kreuzberg/errors.rb +116 -118
  32. data/lib/kreuzberg/extraction_api.rb +313 -85
  33. data/lib/kreuzberg/mcp_proxy.rb +177 -186
  34. data/lib/kreuzberg/ocr_backend_protocol.rb +40 -113
  35. data/lib/kreuzberg/post_processor_protocol.rb +15 -86
  36. data/lib/kreuzberg/result.rb +334 -216
  37. data/lib/kreuzberg/setup_lib_path.rb +99 -80
  38. data/lib/kreuzberg/types.rb +170 -0
  39. data/lib/kreuzberg/validator_protocol.rb +16 -89
  40. data/lib/kreuzberg/version.rb +5 -5
  41. data/lib/kreuzberg.rb +96 -103
  42. data/lib/libpdfium.so +0 -0
  43. data/sig/kreuzberg/internal.rbs +184 -184
  44. data/sig/kreuzberg.rbs +561 -520
  45. data/spec/binding/async_operations_spec.rb +473 -0
  46. data/spec/binding/batch_operations_spec.rb +595 -0
  47. data/spec/binding/batch_spec.rb +359 -0
  48. data/spec/binding/cache_spec.rb +227 -227
  49. data/spec/binding/cli_proxy_spec.rb +85 -85
  50. data/spec/binding/cli_spec.rb +55 -55
  51. data/spec/binding/config_result_spec.rb +377 -0
  52. data/spec/binding/config_spec.rb +419 -345
  53. data/spec/binding/config_validation_spec.rb +377 -283
  54. data/spec/binding/embeddings_spec.rb +816 -0
  55. data/spec/binding/error_handling_spec.rb +399 -213
  56. data/spec/binding/error_recovery_spec.rb +488 -0
  57. data/spec/binding/errors_spec.rb +66 -66
  58. data/spec/binding/font_config_spec.rb +220 -0
  59. data/spec/binding/images_spec.rb +738 -0
  60. data/spec/binding/keywords_extraction_spec.rb +600 -0
  61. data/spec/binding/metadata_types_spec.rb +1228 -0
  62. data/spec/binding/pages_extraction_spec.rb +471 -0
  63. data/spec/binding/plugins/ocr_backend_spec.rb +307 -307
  64. data/spec/binding/plugins/postprocessor_spec.rb +269 -269
  65. data/spec/binding/plugins/validator_spec.rb +273 -274
  66. data/spec/binding/tables_spec.rb +641 -0
  67. data/spec/fixtures/config.toml +38 -39
  68. data/spec/fixtures/config.yaml +41 -41
  69. data/spec/fixtures/invalid_config.toml +3 -4
  70. data/spec/smoke/package_spec.rb +177 -178
  71. data/spec/spec_helper.rb +40 -42
  72. data/spec/unit/config/chunking_config_spec.rb +213 -0
  73. data/spec/unit/config/embedding_config_spec.rb +343 -0
  74. data/spec/unit/config/extraction_config_spec.rb +438 -0
  75. data/spec/unit/config/font_config_spec.rb +285 -0
  76. data/spec/unit/config/hierarchy_config_spec.rb +314 -0
  77. data/spec/unit/config/image_extraction_config_spec.rb +209 -0
  78. data/spec/unit/config/image_preprocessing_config_spec.rb +249 -0
  79. data/spec/unit/config/keyword_config_spec.rb +229 -0
  80. data/spec/unit/config/language_detection_config_spec.rb +258 -0
  81. data/spec/unit/config/ocr_config_spec.rb +171 -0
  82. data/spec/unit/config/page_config_spec.rb +221 -0
  83. data/spec/unit/config/pdf_config_spec.rb +267 -0
  84. data/spec/unit/config/postprocessor_config_spec.rb +290 -0
  85. data/spec/unit/config/tesseract_config_spec.rb +181 -0
  86. data/spec/unit/config/token_reduction_config_spec.rb +251 -0
  87. data/test/metadata_types_test.rb +959 -0
  88. data/vendor/Cargo.toml +61 -0
  89. data/vendor/kreuzberg/Cargo.toml +259 -204
  90. data/vendor/kreuzberg/README.md +263 -175
  91. data/vendor/kreuzberg/build.rs +782 -474
  92. data/vendor/kreuzberg/examples/bench_fixes.rs +71 -0
  93. data/vendor/kreuzberg/examples/test_pdfium_fork.rs +62 -0
  94. data/vendor/kreuzberg/src/api/error.rs +81 -81
  95. data/vendor/kreuzberg/src/api/handlers.rs +320 -199
  96. data/vendor/kreuzberg/src/api/mod.rs +94 -79
  97. data/vendor/kreuzberg/src/api/server.rs +518 -353
  98. data/vendor/kreuzberg/src/api/types.rs +206 -170
  99. data/vendor/kreuzberg/src/cache/mod.rs +1167 -1167
  100. data/vendor/kreuzberg/src/chunking/mod.rs +2303 -677
  101. data/vendor/kreuzberg/src/chunking/processor.rs +219 -0
  102. data/vendor/kreuzberg/src/core/batch_mode.rs +95 -95
  103. data/vendor/kreuzberg/src/core/batch_optimizations.rs +385 -0
  104. data/vendor/kreuzberg/src/core/config.rs +1914 -1032
  105. data/vendor/kreuzberg/src/core/config_validation.rs +949 -0
  106. data/vendor/kreuzberg/src/core/extractor.rs +1200 -1024
  107. data/vendor/kreuzberg/src/core/formats.rs +235 -0
  108. data/vendor/kreuzberg/src/core/io.rs +329 -329
  109. data/vendor/kreuzberg/src/core/mime.rs +605 -605
  110. data/vendor/kreuzberg/src/core/mod.rs +61 -45
  111. data/vendor/kreuzberg/src/core/pipeline.rs +1223 -984
  112. data/vendor/kreuzberg/src/core/server_config.rs +1220 -0
  113. data/vendor/kreuzberg/src/embeddings.rs +471 -432
  114. data/vendor/kreuzberg/src/error.rs +431 -431
  115. data/vendor/kreuzberg/src/extraction/archive.rs +959 -954
  116. data/vendor/kreuzberg/src/extraction/capacity.rs +263 -0
  117. data/vendor/kreuzberg/src/extraction/docx.rs +404 -40
  118. data/vendor/kreuzberg/src/extraction/email.rs +855 -854
  119. data/vendor/kreuzberg/src/extraction/excel.rs +697 -688
  120. data/vendor/kreuzberg/src/extraction/html.rs +1830 -553
  121. data/vendor/kreuzberg/src/extraction/image.rs +492 -368
  122. data/vendor/kreuzberg/src/extraction/libreoffice.rs +574 -563
  123. data/vendor/kreuzberg/src/extraction/markdown.rs +216 -213
  124. data/vendor/kreuzberg/src/extraction/mod.rs +93 -81
  125. data/vendor/kreuzberg/src/extraction/office_metadata/app_properties.rs +398 -398
  126. data/vendor/kreuzberg/src/extraction/office_metadata/core_properties.rs +247 -247
  127. data/vendor/kreuzberg/src/extraction/office_metadata/custom_properties.rs +240 -240
  128. data/vendor/kreuzberg/src/extraction/office_metadata/mod.rs +130 -130
  129. data/vendor/kreuzberg/src/extraction/office_metadata/odt_properties.rs +284 -287
  130. data/vendor/kreuzberg/src/extraction/pptx.rs +3102 -3000
  131. data/vendor/kreuzberg/src/extraction/structured.rs +491 -490
  132. data/vendor/kreuzberg/src/extraction/table.rs +329 -328
  133. data/vendor/kreuzberg/src/extraction/text.rs +277 -269
  134. data/vendor/kreuzberg/src/extraction/xml.rs +333 -333
  135. data/vendor/kreuzberg/src/extractors/archive.rs +447 -446
  136. data/vendor/kreuzberg/src/extractors/bibtex.rs +470 -469
  137. data/vendor/kreuzberg/src/extractors/docbook.rs +504 -502
  138. data/vendor/kreuzberg/src/extractors/docx.rs +400 -367
  139. data/vendor/kreuzberg/src/extractors/email.rs +157 -143
  140. data/vendor/kreuzberg/src/extractors/epub.rs +696 -707
  141. data/vendor/kreuzberg/src/extractors/excel.rs +385 -343
  142. data/vendor/kreuzberg/src/extractors/fictionbook.rs +492 -491
  143. data/vendor/kreuzberg/src/extractors/html.rs +419 -393
  144. data/vendor/kreuzberg/src/extractors/image.rs +219 -198
  145. data/vendor/kreuzberg/src/extractors/jats.rs +1054 -1051
  146. data/vendor/kreuzberg/src/extractors/jupyter.rs +368 -367
  147. data/vendor/kreuzberg/src/extractors/latex.rs +653 -652
  148. data/vendor/kreuzberg/src/extractors/markdown.rs +701 -700
  149. data/vendor/kreuzberg/src/extractors/mod.rs +429 -365
  150. data/vendor/kreuzberg/src/extractors/odt.rs +628 -628
  151. data/vendor/kreuzberg/src/extractors/opml.rs +635 -634
  152. data/vendor/kreuzberg/src/extractors/orgmode.rs +529 -528
  153. data/vendor/kreuzberg/src/extractors/pdf.rs +761 -493
  154. data/vendor/kreuzberg/src/extractors/pptx.rs +279 -248
  155. data/vendor/kreuzberg/src/extractors/rst.rs +577 -576
  156. data/vendor/kreuzberg/src/extractors/rtf.rs +809 -810
  157. data/vendor/kreuzberg/src/extractors/security.rs +484 -484
  158. data/vendor/kreuzberg/src/extractors/security_tests.rs +367 -367
  159. data/vendor/kreuzberg/src/extractors/structured.rs +142 -140
  160. data/vendor/kreuzberg/src/extractors/text.rs +265 -260
  161. data/vendor/kreuzberg/src/extractors/typst.rs +651 -650
  162. data/vendor/kreuzberg/src/extractors/xml.rs +147 -135
  163. data/vendor/kreuzberg/src/image/dpi.rs +164 -164
  164. data/vendor/kreuzberg/src/image/mod.rs +6 -6
  165. data/vendor/kreuzberg/src/image/preprocessing.rs +417 -417
  166. data/vendor/kreuzberg/src/image/resize.rs +89 -89
  167. data/vendor/kreuzberg/src/keywords/config.rs +154 -154
  168. data/vendor/kreuzberg/src/keywords/mod.rs +237 -237
  169. data/vendor/kreuzberg/src/keywords/processor.rs +275 -267
  170. data/vendor/kreuzberg/src/keywords/rake.rs +293 -293
  171. data/vendor/kreuzberg/src/keywords/types.rs +68 -68
  172. data/vendor/kreuzberg/src/keywords/yake.rs +163 -163
  173. data/vendor/kreuzberg/src/language_detection/mod.rs +985 -942
  174. data/vendor/kreuzberg/src/language_detection/processor.rs +218 -0
  175. data/vendor/kreuzberg/src/lib.rs +114 -105
  176. data/vendor/kreuzberg/src/mcp/mod.rs +35 -32
  177. data/vendor/kreuzberg/src/mcp/server.rs +2090 -1968
  178. data/vendor/kreuzberg/src/ocr/cache.rs +469 -469
  179. data/vendor/kreuzberg/src/ocr/error.rs +37 -37
  180. data/vendor/kreuzberg/src/ocr/hocr.rs +216 -216
  181. data/vendor/kreuzberg/src/ocr/language_registry.rs +520 -0
  182. data/vendor/kreuzberg/src/ocr/mod.rs +60 -58
  183. data/vendor/kreuzberg/src/ocr/processor.rs +858 -863
  184. data/vendor/kreuzberg/src/ocr/table/mod.rs +4 -4
  185. data/vendor/kreuzberg/src/ocr/table/tsv_parser.rs +144 -144
  186. data/vendor/kreuzberg/src/ocr/tesseract_backend.rs +456 -450
  187. data/vendor/kreuzberg/src/ocr/types.rs +393 -393
  188. data/vendor/kreuzberg/src/ocr/utils.rs +47 -47
  189. data/vendor/kreuzberg/src/ocr/validation.rs +206 -206
  190. data/vendor/kreuzberg/src/panic_context.rs +154 -154
  191. data/vendor/kreuzberg/src/pdf/bindings.rs +306 -0
  192. data/vendor/kreuzberg/src/pdf/bundled.rs +408 -0
  193. data/vendor/kreuzberg/src/pdf/error.rs +214 -122
  194. data/vendor/kreuzberg/src/pdf/fonts.rs +358 -0
  195. data/vendor/kreuzberg/src/pdf/hierarchy.rs +903 -0
  196. data/vendor/kreuzberg/src/pdf/images.rs +139 -139
  197. data/vendor/kreuzberg/src/pdf/metadata.rs +509 -346
  198. data/vendor/kreuzberg/src/pdf/mod.rs +81 -50
  199. data/vendor/kreuzberg/src/pdf/rendering.rs +369 -369
  200. data/vendor/kreuzberg/src/pdf/table.rs +417 -393
  201. data/vendor/kreuzberg/src/pdf/text.rs +553 -158
  202. data/vendor/kreuzberg/src/plugins/extractor.rs +1042 -1013
  203. data/vendor/kreuzberg/src/plugins/mod.rs +212 -209
  204. data/vendor/kreuzberg/src/plugins/ocr.rs +637 -620
  205. data/vendor/kreuzberg/src/plugins/processor.rs +650 -642
  206. data/vendor/kreuzberg/src/plugins/registry.rs +1339 -1337
  207. data/vendor/kreuzberg/src/plugins/traits.rs +258 -258
  208. data/vendor/kreuzberg/src/plugins/validator.rs +967 -956
  209. data/vendor/kreuzberg/src/stopwords/mod.rs +1470 -1470
  210. data/vendor/kreuzberg/src/text/mod.rs +27 -19
  211. data/vendor/kreuzberg/src/text/quality.rs +710 -697
  212. data/vendor/kreuzberg/src/text/quality_processor.rs +231 -0
  213. data/vendor/kreuzberg/src/text/string_utils.rs +229 -217
  214. data/vendor/kreuzberg/src/text/token_reduction/cjk_utils.rs +164 -164
  215. data/vendor/kreuzberg/src/text/token_reduction/config.rs +100 -100
  216. data/vendor/kreuzberg/src/text/token_reduction/core.rs +832 -796
  217. data/vendor/kreuzberg/src/text/token_reduction/filters.rs +923 -902
  218. data/vendor/kreuzberg/src/text/token_reduction/mod.rs +160 -160
  219. data/vendor/kreuzberg/src/text/token_reduction/semantic.rs +619 -619
  220. data/vendor/kreuzberg/src/text/token_reduction/simd_text.rs +148 -147
  221. data/vendor/kreuzberg/src/text/utf8_validation.rs +193 -0
  222. data/vendor/kreuzberg/src/types.rs +1713 -903
  223. data/vendor/kreuzberg/src/utils/mod.rs +31 -17
  224. data/vendor/kreuzberg/src/utils/pool.rs +503 -0
  225. data/vendor/kreuzberg/src/utils/pool_sizing.rs +364 -0
  226. data/vendor/kreuzberg/src/utils/quality.rs +968 -959
  227. data/vendor/kreuzberg/src/utils/string_pool.rs +761 -0
  228. data/vendor/kreuzberg/src/utils/string_utils.rs +381 -381
  229. data/vendor/kreuzberg/stopwords/af_stopwords.json +53 -53
  230. data/vendor/kreuzberg/stopwords/ar_stopwords.json +482 -482
  231. data/vendor/kreuzberg/stopwords/bg_stopwords.json +261 -261
  232. data/vendor/kreuzberg/stopwords/bn_stopwords.json +400 -400
  233. data/vendor/kreuzberg/stopwords/br_stopwords.json +1205 -1205
  234. data/vendor/kreuzberg/stopwords/ca_stopwords.json +280 -280
  235. data/vendor/kreuzberg/stopwords/cs_stopwords.json +425 -425
  236. data/vendor/kreuzberg/stopwords/da_stopwords.json +172 -172
  237. data/vendor/kreuzberg/stopwords/de_stopwords.json +622 -622
  238. data/vendor/kreuzberg/stopwords/el_stopwords.json +849 -849
  239. data/vendor/kreuzberg/stopwords/en_stopwords.json +1300 -1300
  240. data/vendor/kreuzberg/stopwords/eo_stopwords.json +175 -175
  241. data/vendor/kreuzberg/stopwords/es_stopwords.json +734 -734
  242. data/vendor/kreuzberg/stopwords/et_stopwords.json +37 -37
  243. data/vendor/kreuzberg/stopwords/eu_stopwords.json +100 -100
  244. data/vendor/kreuzberg/stopwords/fa_stopwords.json +801 -801
  245. data/vendor/kreuzberg/stopwords/fi_stopwords.json +849 -849
  246. data/vendor/kreuzberg/stopwords/fr_stopwords.json +693 -693
  247. data/vendor/kreuzberg/stopwords/ga_stopwords.json +111 -111
  248. data/vendor/kreuzberg/stopwords/gl_stopwords.json +162 -162
  249. data/vendor/kreuzberg/stopwords/gu_stopwords.json +226 -226
  250. data/vendor/kreuzberg/stopwords/ha_stopwords.json +41 -41
  251. data/vendor/kreuzberg/stopwords/he_stopwords.json +196 -196
  252. data/vendor/kreuzberg/stopwords/hi_stopwords.json +227 -227
  253. data/vendor/kreuzberg/stopwords/hr_stopwords.json +181 -181
  254. data/vendor/kreuzberg/stopwords/hu_stopwords.json +791 -791
  255. data/vendor/kreuzberg/stopwords/hy_stopwords.json +47 -47
  256. data/vendor/kreuzberg/stopwords/id_stopwords.json +760 -760
  257. data/vendor/kreuzberg/stopwords/it_stopwords.json +634 -634
  258. data/vendor/kreuzberg/stopwords/ja_stopwords.json +136 -136
  259. data/vendor/kreuzberg/stopwords/kn_stopwords.json +84 -84
  260. data/vendor/kreuzberg/stopwords/ko_stopwords.json +681 -681
  261. data/vendor/kreuzberg/stopwords/ku_stopwords.json +64 -64
  262. data/vendor/kreuzberg/stopwords/la_stopwords.json +51 -51
  263. data/vendor/kreuzberg/stopwords/lt_stopwords.json +476 -476
  264. data/vendor/kreuzberg/stopwords/lv_stopwords.json +163 -163
  265. data/vendor/kreuzberg/stopwords/ml_stopwords.json +1 -1
  266. data/vendor/kreuzberg/stopwords/mr_stopwords.json +101 -101
  267. data/vendor/kreuzberg/stopwords/ms_stopwords.json +477 -477
  268. data/vendor/kreuzberg/stopwords/ne_stopwords.json +490 -490
  269. data/vendor/kreuzberg/stopwords/nl_stopwords.json +415 -415
  270. data/vendor/kreuzberg/stopwords/no_stopwords.json +223 -223
  271. data/vendor/kreuzberg/stopwords/pl_stopwords.json +331 -331
  272. data/vendor/kreuzberg/stopwords/pt_stopwords.json +562 -562
  273. data/vendor/kreuzberg/stopwords/ro_stopwords.json +436 -436
  274. data/vendor/kreuzberg/stopwords/ru_stopwords.json +561 -561
  275. data/vendor/kreuzberg/stopwords/si_stopwords.json +193 -193
  276. data/vendor/kreuzberg/stopwords/sk_stopwords.json +420 -420
  277. data/vendor/kreuzberg/stopwords/sl_stopwords.json +448 -448
  278. data/vendor/kreuzberg/stopwords/so_stopwords.json +32 -32
  279. data/vendor/kreuzberg/stopwords/st_stopwords.json +33 -33
  280. data/vendor/kreuzberg/stopwords/sv_stopwords.json +420 -420
  281. data/vendor/kreuzberg/stopwords/sw_stopwords.json +76 -76
  282. data/vendor/kreuzberg/stopwords/ta_stopwords.json +129 -129
  283. data/vendor/kreuzberg/stopwords/te_stopwords.json +54 -54
  284. data/vendor/kreuzberg/stopwords/th_stopwords.json +118 -118
  285. data/vendor/kreuzberg/stopwords/tl_stopwords.json +149 -149
  286. data/vendor/kreuzberg/stopwords/tr_stopwords.json +506 -506
  287. data/vendor/kreuzberg/stopwords/uk_stopwords.json +75 -75
  288. data/vendor/kreuzberg/stopwords/ur_stopwords.json +519 -519
  289. data/vendor/kreuzberg/stopwords/vi_stopwords.json +647 -647
  290. data/vendor/kreuzberg/stopwords/yo_stopwords.json +62 -62
  291. data/vendor/kreuzberg/stopwords/zh_stopwords.json +796 -796
  292. data/vendor/kreuzberg/stopwords/zu_stopwords.json +31 -31
  293. data/vendor/kreuzberg/tests/api_embed.rs +360 -0
  294. data/vendor/kreuzberg/tests/api_extract_multipart.rs +52 -52
  295. data/vendor/kreuzberg/tests/api_large_pdf_extraction.rs +471 -0
  296. data/vendor/kreuzberg/tests/api_large_pdf_extraction_diagnostics.rs +289 -0
  297. data/vendor/kreuzberg/tests/api_tests.rs +1472 -966
  298. data/vendor/kreuzberg/tests/archive_integration.rs +545 -543
  299. data/vendor/kreuzberg/tests/batch_orchestration.rs +587 -556
  300. data/vendor/kreuzberg/tests/batch_pooling_benchmark.rs +154 -0
  301. data/vendor/kreuzberg/tests/batch_processing.rs +328 -316
  302. data/vendor/kreuzberg/tests/bibtex_parity_test.rs +421 -421
  303. data/vendor/kreuzberg/tests/concurrency_stress.rs +541 -525
  304. data/vendor/kreuzberg/tests/config_features.rs +612 -598
  305. data/vendor/kreuzberg/tests/config_integration_test.rs +753 -0
  306. data/vendor/kreuzberg/tests/config_loading_tests.rs +416 -415
  307. data/vendor/kreuzberg/tests/core_integration.rs +519 -510
  308. data/vendor/kreuzberg/tests/csv_integration.rs +414 -414
  309. data/vendor/kreuzberg/tests/data/hierarchy_ground_truth.json +294 -0
  310. data/vendor/kreuzberg/tests/docbook_extractor_tests.rs +500 -498
  311. data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +122 -122
  312. data/vendor/kreuzberg/tests/docx_vs_pandoc_comparison.rs +370 -370
  313. data/vendor/kreuzberg/tests/email_integration.rs +327 -325
  314. data/vendor/kreuzberg/tests/epub_native_extractor_tests.rs +275 -275
  315. data/vendor/kreuzberg/tests/error_handling.rs +402 -393
  316. data/vendor/kreuzberg/tests/fictionbook_extractor_tests.rs +228 -228
  317. data/vendor/kreuzberg/tests/format_integration.rs +165 -159
  318. data/vendor/kreuzberg/tests/helpers/mod.rs +202 -142
  319. data/vendor/kreuzberg/tests/html_table_test.rs +551 -551
  320. data/vendor/kreuzberg/tests/image_integration.rs +255 -253
  321. data/vendor/kreuzberg/tests/instrumentation_test.rs +139 -139
  322. data/vendor/kreuzberg/tests/jats_extractor_tests.rs +639 -639
  323. data/vendor/kreuzberg/tests/jupyter_extractor_tests.rs +704 -704
  324. data/vendor/kreuzberg/tests/keywords_integration.rs +479 -479
  325. data/vendor/kreuzberg/tests/keywords_quality.rs +509 -509
  326. data/vendor/kreuzberg/tests/latex_extractor_tests.rs +496 -496
  327. data/vendor/kreuzberg/tests/markdown_extractor_tests.rs +490 -490
  328. data/vendor/kreuzberg/tests/mime_detection.rs +429 -428
  329. data/vendor/kreuzberg/tests/ocr_configuration.rs +514 -510
  330. data/vendor/kreuzberg/tests/ocr_errors.rs +698 -676
  331. data/vendor/kreuzberg/tests/ocr_language_registry.rs +191 -0
  332. data/vendor/kreuzberg/tests/ocr_quality.rs +629 -627
  333. data/vendor/kreuzberg/tests/ocr_stress.rs +469 -469
  334. data/vendor/kreuzberg/tests/odt_extractor_tests.rs +674 -695
  335. data/vendor/kreuzberg/tests/opml_extractor_tests.rs +616 -616
  336. data/vendor/kreuzberg/tests/orgmode_extractor_tests.rs +822 -822
  337. data/vendor/kreuzberg/tests/page_markers.rs +297 -0
  338. data/vendor/kreuzberg/tests/pdf_hierarchy_detection.rs +301 -0
  339. data/vendor/kreuzberg/tests/pdf_hierarchy_quality.rs +589 -0
  340. data/vendor/kreuzberg/tests/pdf_integration.rs +45 -43
  341. data/vendor/kreuzberg/tests/pdf_ocr_triggering.rs +301 -0
  342. data/vendor/kreuzberg/tests/pdf_text_merging.rs +475 -0
  343. data/vendor/kreuzberg/tests/pdfium_linking.rs +340 -0
  344. data/vendor/kreuzberg/tests/pipeline_integration.rs +1446 -1411
  345. data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +776 -771
  346. data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +577 -560
  347. data/vendor/kreuzberg/tests/plugin_system.rs +927 -921
  348. data/vendor/kreuzberg/tests/plugin_validator_test.rs +783 -783
  349. data/vendor/kreuzberg/tests/registry_integration_tests.rs +587 -586
  350. data/vendor/kreuzberg/tests/rst_extractor_tests.rs +694 -692
  351. data/vendor/kreuzberg/tests/rtf_extractor_tests.rs +775 -776
  352. data/vendor/kreuzberg/tests/security_validation.rs +416 -415
  353. data/vendor/kreuzberg/tests/stopwords_integration_test.rs +888 -888
  354. data/vendor/kreuzberg/tests/test_fastembed.rs +631 -609
  355. data/vendor/kreuzberg/tests/typst_behavioral_tests.rs +1260 -1259
  356. data/vendor/kreuzberg/tests/typst_extractor_tests.rs +648 -647
  357. data/vendor/kreuzberg/tests/xlsx_metadata_extraction_test.rs +87 -87
  358. data/vendor/kreuzberg-ffi/Cargo.toml +67 -0
  359. data/vendor/kreuzberg-ffi/README.md +851 -0
  360. data/vendor/kreuzberg-ffi/benches/result_view_benchmark.rs +227 -0
  361. data/vendor/kreuzberg-ffi/build.rs +168 -0
  362. data/vendor/kreuzberg-ffi/cbindgen.toml +37 -0
  363. data/vendor/kreuzberg-ffi/kreuzberg-ffi.pc.in +12 -0
  364. data/vendor/kreuzberg-ffi/kreuzberg.h +3012 -0
  365. data/vendor/kreuzberg-ffi/src/batch_streaming.rs +588 -0
  366. data/vendor/kreuzberg-ffi/src/config.rs +1341 -0
  367. data/vendor/kreuzberg-ffi/src/error.rs +901 -0
  368. data/vendor/kreuzberg-ffi/src/extraction.rs +555 -0
  369. data/vendor/kreuzberg-ffi/src/helpers.rs +879 -0
  370. data/vendor/kreuzberg-ffi/src/lib.rs +977 -0
  371. data/vendor/kreuzberg-ffi/src/memory.rs +493 -0
  372. data/vendor/kreuzberg-ffi/src/mime.rs +329 -0
  373. data/vendor/kreuzberg-ffi/src/panic_shield.rs +265 -0
  374. data/vendor/kreuzberg-ffi/src/plugins/document_extractor.rs +442 -0
  375. data/vendor/kreuzberg-ffi/src/plugins/mod.rs +14 -0
  376. data/vendor/kreuzberg-ffi/src/plugins/ocr_backend.rs +628 -0
  377. data/vendor/kreuzberg-ffi/src/plugins/post_processor.rs +438 -0
  378. data/vendor/kreuzberg-ffi/src/plugins/validator.rs +329 -0
  379. data/vendor/kreuzberg-ffi/src/result.rs +510 -0
  380. data/vendor/kreuzberg-ffi/src/result_pool.rs +639 -0
  381. data/vendor/kreuzberg-ffi/src/result_view.rs +773 -0
  382. data/vendor/kreuzberg-ffi/src/string_intern.rs +568 -0
  383. data/vendor/kreuzberg-ffi/src/types.rs +363 -0
  384. data/vendor/kreuzberg-ffi/src/util.rs +210 -0
  385. data/vendor/kreuzberg-ffi/src/validation.rs +848 -0
  386. data/vendor/kreuzberg-ffi/tests.disabled/README.md +48 -0
  387. data/vendor/kreuzberg-ffi/tests.disabled/config_loading_tests.rs +299 -0
  388. data/vendor/kreuzberg-ffi/tests.disabled/config_tests.rs +346 -0
  389. data/vendor/kreuzberg-ffi/tests.disabled/extractor_tests.rs +232 -0
  390. data/vendor/kreuzberg-ffi/tests.disabled/plugin_registration_tests.rs +470 -0
  391. data/vendor/kreuzberg-tesseract/.commitlintrc.json +13 -0
  392. data/vendor/kreuzberg-tesseract/.crate-ignore +2 -0
  393. data/vendor/kreuzberg-tesseract/Cargo.lock +2933 -0
  394. data/vendor/kreuzberg-tesseract/Cargo.toml +57 -0
  395. data/vendor/{rb-sys/LICENSE-MIT → kreuzberg-tesseract/LICENSE} +22 -21
  396. data/vendor/kreuzberg-tesseract/README.md +399 -0
  397. data/vendor/kreuzberg-tesseract/build.rs +1127 -0
  398. data/vendor/kreuzberg-tesseract/patches/README.md +71 -0
  399. data/vendor/kreuzberg-tesseract/patches/tesseract.diff +199 -0
  400. data/vendor/kreuzberg-tesseract/src/api.rs +1371 -0
  401. data/vendor/kreuzberg-tesseract/src/choice_iterator.rs +77 -0
  402. data/vendor/kreuzberg-tesseract/src/enums.rs +297 -0
  403. data/vendor/kreuzberg-tesseract/src/error.rs +81 -0
  404. data/vendor/kreuzberg-tesseract/src/lib.rs +145 -0
  405. data/vendor/kreuzberg-tesseract/src/monitor.rs +57 -0
  406. data/vendor/kreuzberg-tesseract/src/mutable_iterator.rs +197 -0
  407. data/vendor/kreuzberg-tesseract/src/page_iterator.rs +253 -0
  408. data/vendor/kreuzberg-tesseract/src/result_iterator.rs +286 -0
  409. data/vendor/kreuzberg-tesseract/src/result_renderer.rs +183 -0
  410. data/vendor/kreuzberg-tesseract/tests/integration_test.rs +211 -0
  411. metadata +196 -45
  412. data/vendor/kreuzberg/benches/otel_overhead.rs +0 -48
  413. data/vendor/kreuzberg/src/extractors/fictionbook.rs.backup2 +0 -738
  414. data/vendor/rb-sys/.cargo-ok +0 -1
  415. data/vendor/rb-sys/.cargo_vcs_info.json +0 -6
  416. data/vendor/rb-sys/Cargo.lock +0 -393
  417. data/vendor/rb-sys/Cargo.toml +0 -70
  418. data/vendor/rb-sys/Cargo.toml.orig +0 -57
  419. data/vendor/rb-sys/LICENSE-APACHE +0 -190
  420. data/vendor/rb-sys/bin/release.sh +0 -21
  421. data/vendor/rb-sys/build/features.rs +0 -108
  422. data/vendor/rb-sys/build/main.rs +0 -246
  423. data/vendor/rb-sys/build/stable_api_config.rs +0 -153
  424. data/vendor/rb-sys/build/version.rs +0 -48
  425. data/vendor/rb-sys/readme.md +0 -36
  426. data/vendor/rb-sys/src/bindings.rs +0 -21
  427. data/vendor/rb-sys/src/hidden.rs +0 -11
  428. data/vendor/rb-sys/src/lib.rs +0 -34
  429. data/vendor/rb-sys/src/macros.rs +0 -371
  430. data/vendor/rb-sys/src/memory.rs +0 -53
  431. data/vendor/rb-sys/src/ruby_abi_version.rs +0 -38
  432. data/vendor/rb-sys/src/special_consts.rs +0 -31
  433. data/vendor/rb-sys/src/stable_api/compiled.c +0 -179
  434. data/vendor/rb-sys/src/stable_api/compiled.rs +0 -257
  435. data/vendor/rb-sys/src/stable_api/ruby_2_6.rs +0 -316
  436. data/vendor/rb-sys/src/stable_api/ruby_2_7.rs +0 -316
  437. data/vendor/rb-sys/src/stable_api/ruby_3_0.rs +0 -324
  438. data/vendor/rb-sys/src/stable_api/ruby_3_1.rs +0 -317
  439. data/vendor/rb-sys/src/stable_api/ruby_3_2.rs +0 -315
  440. data/vendor/rb-sys/src/stable_api/ruby_3_3.rs +0 -326
  441. data/vendor/rb-sys/src/stable_api/ruby_3_4.rs +0 -327
  442. data/vendor/rb-sys/src/stable_api.rs +0 -261
  443. data/vendor/rb-sys/src/symbol.rs +0 -31
  444. data/vendor/rb-sys/src/tracking_allocator.rs +0 -332
  445. data/vendor/rb-sys/src/utils.rs +0 -89
  446. data/vendor/rb-sys/src/value_type.rs +0 -7
@@ -1,315 +0,0 @@
1
- use super::StableApiDefinition;
2
- use crate::{
3
- VALUE, debug_ruby_assert_type,
4
- internal::{RArray, RString, RTypedData},
5
- ruby_value_type::RUBY_T_DATA,
6
- value_type,
7
- };
8
- use std::{
9
- ffi::c_void,
10
- os::raw::{c_char, c_long},
11
- ptr::NonNull,
12
- time::Duration,
13
- };
14
-
15
- #[cfg(not(ruby_eq_3_2))]
16
- compile_error!("This file should only be included in Ruby 3.2 builds");
17
-
18
- pub struct Definition;
19
-
20
- impl StableApiDefinition for Definition {
21
- const VERSION_MAJOR: u32 = 3;
22
- const VERSION_MINOR: u32 = 2;
23
-
24
- #[inline]
25
- unsafe fn rstring_len(&self, obj: VALUE) -> c_long {
26
- assert!(self.type_p(obj, crate::ruby_value_type::RUBY_T_STRING));
27
-
28
- let rstring: &RString = &*(obj as *const RString);
29
- let flags = rstring.basic.flags;
30
- let is_heap = (flags & crate::ruby_rstring_flags::RSTRING_NOEMBED as VALUE) != 0;
31
-
32
- if !is_heap {
33
- rstring.as_.embed.len as _
34
- } else {
35
- rstring.as_.heap.len
36
- }
37
- }
38
-
39
- #[inline]
40
- unsafe fn rstring_ptr(&self, obj: VALUE) -> *const c_char {
41
- assert!(self.type_p(obj, crate::ruby_value_type::RUBY_T_STRING));
42
-
43
- let rstring: &RString = &*(obj as *const RString);
44
- let flags = rstring.basic.flags;
45
- let is_heap = (flags & crate::ruby_rstring_flags::RSTRING_NOEMBED as VALUE) != 0;
46
- let ptr = if !is_heap {
47
- std::ptr::addr_of!(rstring.as_.embed.ary) as *const _
48
- } else {
49
- rstring.as_.heap.ptr
50
- };
51
-
52
- assert!(!ptr.is_null());
53
-
54
- ptr
55
- }
56
-
57
- #[inline]
58
- unsafe fn rarray_len(&self, obj: VALUE) -> c_long {
59
- assert!(self.type_p(obj, value_type::RUBY_T_ARRAY));
60
-
61
- let rarray: &RArray = &*(obj as *const RArray);
62
- let flags = rarray.basic.flags;
63
- let is_embedded = (flags & crate::ruby_rarray_flags::RARRAY_EMBED_FLAG as VALUE) != 0;
64
-
65
- if is_embedded {
66
- let mut f = rarray.basic.flags;
67
- f &= crate::ruby_rarray_flags::RARRAY_EMBED_LEN_MASK as VALUE;
68
- f >>= crate::ruby_rarray_consts::RARRAY_EMBED_LEN_SHIFT as VALUE;
69
- f as c_long
70
- } else {
71
- rarray.as_.heap.len
72
- }
73
- }
74
-
75
- #[inline]
76
- unsafe fn rarray_const_ptr(&self, obj: VALUE) -> *const VALUE {
77
- assert!(self.type_p(obj, value_type::RUBY_T_ARRAY));
78
-
79
- let rarray: &RArray = &*(obj as *const RArray);
80
- let flags = rarray.basic.flags;
81
- let is_embedded = (flags & crate::ruby_rarray_flags::RARRAY_EMBED_FLAG as VALUE) != 0;
82
- let ptr = if is_embedded {
83
- std::ptr::addr_of!(rarray.as_.ary) as *const _
84
- } else {
85
- rarray.as_.heap.ptr
86
- };
87
-
88
- assert!(!ptr.is_null());
89
-
90
- ptr
91
- }
92
-
93
- #[inline]
94
- unsafe fn rbasic_class(&self, obj: VALUE) -> Option<NonNull<VALUE>> {
95
- let rbasic = obj as *const crate::RBasic;
96
-
97
- NonNull::<VALUE>::new((*rbasic).klass as _)
98
- }
99
-
100
- #[inline]
101
- unsafe fn frozen_p(&self, obj: VALUE) -> bool {
102
- if self.special_const_p(obj) {
103
- true
104
- } else {
105
- let rbasic = obj as *const crate::RBasic;
106
- ((*rbasic).flags & crate::ruby_fl_type::RUBY_FL_FREEZE as VALUE) != 0
107
- }
108
- }
109
-
110
- #[inline]
111
- unsafe fn bignum_positive_p(&self, obj: VALUE) -> bool {
112
- let rbasic = obj as *const crate::RBasic;
113
-
114
- ((*rbasic).flags & crate::ruby_fl_type::RUBY_FL_USER1 as VALUE) != 0
115
- }
116
-
117
- #[inline]
118
- fn special_const_p(&self, value: VALUE) -> bool {
119
- let is_immediate = (value) & (crate::special_consts::IMMEDIATE_MASK as VALUE) != 0;
120
- let test = (value & !(crate::Qnil as VALUE)) != 0;
121
-
122
- is_immediate || !test
123
- }
124
-
125
- #[inline]
126
- unsafe fn builtin_type(&self, obj: VALUE) -> crate::ruby_value_type {
127
- let rbasic = obj as *const crate::RBasic;
128
- let ret: u32 = ((*rbasic).flags & crate::ruby_value_type::RUBY_T_MASK as VALUE) as _;
129
-
130
- std::mem::transmute::<_, crate::ruby_value_type>(ret)
131
- }
132
-
133
- #[inline]
134
- fn nil_p(&self, obj: VALUE) -> bool {
135
- obj == (crate::Qnil as VALUE)
136
- }
137
-
138
- #[inline]
139
- fn fixnum_p(&self, obj: VALUE) -> bool {
140
- (obj & crate::FIXNUM_FLAG as VALUE) != 0
141
- }
142
-
143
- #[inline]
144
- fn static_sym_p(&self, obj: VALUE) -> bool {
145
- let mask = !(VALUE::MAX << crate::ruby_special_consts::RUBY_SPECIAL_SHIFT as VALUE);
146
- (obj & mask) == crate::ruby_special_consts::RUBY_SYMBOL_FLAG as VALUE
147
- }
148
-
149
- #[inline]
150
- fn flonum_p(&self, obj: VALUE) -> bool {
151
- #[cfg(ruby_use_flonum = "true")]
152
- let ret = (obj & crate::FLONUM_MASK as VALUE) == crate::FLONUM_FLAG as VALUE;
153
-
154
- #[cfg(not(ruby_use_flonum = "true"))]
155
- let ret = false;
156
-
157
- ret
158
- }
159
-
160
- #[inline]
161
- fn immediate_p(&self, obj: VALUE) -> bool {
162
- (obj & crate::special_consts::IMMEDIATE_MASK as VALUE) != 0
163
- }
164
-
165
- #[inline]
166
- fn rb_test(&self, obj: VALUE) -> bool {
167
- (obj & !(crate::Qnil as VALUE)) != 0
168
- }
169
-
170
- #[inline]
171
- unsafe fn type_p(&self, obj: VALUE, t: crate::ruby_value_type) -> bool {
172
- use crate::ruby_special_consts::*;
173
- use crate::ruby_value_type::*;
174
-
175
- if t == RUBY_T_TRUE {
176
- obj == RUBY_Qtrue as _
177
- } else if t == RUBY_T_FALSE {
178
- obj == RUBY_Qfalse as _
179
- } else if t == RUBY_T_NIL {
180
- obj == RUBY_Qnil as _
181
- } else if t == RUBY_T_UNDEF {
182
- obj == RUBY_Qundef as _
183
- } else if t == RUBY_T_FIXNUM {
184
- self.fixnum_p(obj)
185
- } else if t == RUBY_T_SYMBOL {
186
- self.symbol_p(obj)
187
- } else if t == RUBY_T_FLOAT {
188
- self.float_type_p(obj)
189
- } else if self.special_const_p(obj) {
190
- false
191
- } else if t == self.builtin_type(obj) {
192
- true
193
- } else {
194
- t == self.rb_type(obj)
195
- }
196
- }
197
-
198
- #[inline]
199
- unsafe fn symbol_p(&self, obj: VALUE) -> bool {
200
- self.static_sym_p(obj) || self.dynamic_sym_p(obj)
201
- }
202
-
203
- #[inline]
204
- unsafe fn float_type_p(&self, obj: VALUE) -> bool {
205
- if self.flonum_p(obj) {
206
- true
207
- } else if self.special_const_p(obj) {
208
- false
209
- } else {
210
- self.builtin_type(obj) == value_type::RUBY_T_FLOAT
211
- }
212
- }
213
-
214
- #[inline]
215
- unsafe fn rb_type(&self, obj: VALUE) -> crate::ruby_value_type {
216
- use crate::ruby_special_consts::*;
217
- use crate::ruby_value_type::*;
218
-
219
- if !self.special_const_p(obj) {
220
- self.builtin_type(obj)
221
- } else if obj == RUBY_Qfalse as _ {
222
- RUBY_T_FALSE
223
- } else if obj == RUBY_Qnil as _ {
224
- RUBY_T_NIL
225
- } else if obj == RUBY_Qtrue as _ {
226
- RUBY_T_TRUE
227
- } else if obj == RUBY_Qundef as _ {
228
- RUBY_T_UNDEF
229
- } else if self.fixnum_p(obj) {
230
- RUBY_T_FIXNUM
231
- } else if self.static_sym_p(obj) {
232
- RUBY_T_SYMBOL
233
- } else {
234
- debug_assert!(self.flonum_p(obj));
235
- RUBY_T_FLOAT
236
- }
237
- }
238
-
239
- #[inline]
240
- unsafe fn dynamic_sym_p(&self, obj: VALUE) -> bool {
241
- if self.special_const_p(obj) {
242
- false
243
- } else {
244
- self.builtin_type(obj) == value_type::RUBY_T_SYMBOL
245
- }
246
- }
247
-
248
- #[inline]
249
- unsafe fn integer_type_p(&self, obj: VALUE) -> bool {
250
- if self.fixnum_p(obj) {
251
- true
252
- } else if self.special_const_p(obj) {
253
- false
254
- } else {
255
- self.builtin_type(obj) == value_type::RUBY_T_BIGNUM
256
- }
257
- }
258
-
259
- #[inline]
260
- unsafe fn rstring_interned_p(&self, obj: VALUE) -> bool {
261
- assert!(self.type_p(obj, value_type::RUBY_T_STRING));
262
-
263
- let rstring: &RString = &*(obj as *const RString);
264
- let flags = rstring.basic.flags;
265
-
266
- (flags & crate::ruby_rstring_flags::RSTRING_FSTR as VALUE) != 0
267
- }
268
-
269
- #[inline]
270
- fn thread_sleep(&self, duration: Duration) {
271
- let seconds = duration.as_secs() as _;
272
- let microseconds = duration.subsec_micros() as _;
273
-
274
- let time = crate::timeval {
275
- tv_sec: seconds,
276
- tv_usec: microseconds,
277
- };
278
-
279
- unsafe { crate::rb_thread_wait_for(time) }
280
- }
281
-
282
- #[inline]
283
- unsafe fn rtypeddata_p(&self, obj: VALUE) -> bool {
284
- debug_ruby_assert_type!(obj, RUBY_T_DATA, "rtypeddata_p called on non-T_DATA object");
285
-
286
- // Access the RTypedData struct
287
- let rdata = obj as *const RTypedData;
288
- let typed_flag = (*rdata).typed_flag;
289
- // Valid typed_flag value for Ruby 3.2 and earlier is only 1
290
- typed_flag == 1
291
- }
292
-
293
- #[inline]
294
- unsafe fn rtypeddata_embedded_p(&self, _obj: VALUE) -> bool {
295
- // Ruby 3.2 and lower don't support embedded data
296
- false
297
- }
298
-
299
- #[inline]
300
- unsafe fn rtypeddata_type(&self, obj: VALUE) -> *const crate::rb_data_type_t {
301
- debug_ruby_assert_type!(obj, RUBY_T_DATA, "rtypeddata_type called on non-T_DATA object");
302
-
303
- let rdata = obj as *const RTypedData;
304
- (*rdata).type_
305
- }
306
-
307
- #[inline]
308
- unsafe fn rtypeddata_get_data(&self, obj: VALUE) -> *mut c_void {
309
- debug_ruby_assert_type!(obj, RUBY_T_DATA, "rtypeddata_get_data called on non-T_DATA object");
310
-
311
- // For Ruby 3.2 and lower, simply return the data field
312
- let rdata = obj as *const RTypedData;
313
- (*rdata).data
314
- }
315
- }
@@ -1,326 +0,0 @@
1
- use super::StableApiDefinition;
2
- use crate::{
3
- VALUE, debug_ruby_assert_type,
4
- internal::{RArray, RString},
5
- ruby_value_type::RUBY_T_DATA,
6
- value_type,
7
- };
8
- use std::{
9
- os::raw::{c_char, c_long},
10
- ptr::NonNull,
11
- time::Duration,
12
- };
13
-
14
- #[cfg(not(ruby_eq_3_3))]
15
- compile_error!("This file should only be included in Ruby 3.3 builds");
16
-
17
- pub struct Definition;
18
-
19
- impl StableApiDefinition for Definition {
20
- const VERSION_MAJOR: u32 = 3;
21
- const VERSION_MINOR: u32 = 3;
22
-
23
- #[inline]
24
- unsafe fn rstring_len(&self, obj: VALUE) -> c_long {
25
- assert!(self.type_p(obj, crate::ruby_value_type::RUBY_T_STRING));
26
-
27
- let rstring: &RString = &*(obj as *const RString);
28
- rstring.len
29
- }
30
-
31
- #[inline]
32
- unsafe fn rstring_ptr(&self, obj: VALUE) -> *const c_char {
33
- assert!(self.type_p(obj, crate::ruby_value_type::RUBY_T_STRING));
34
-
35
- let rstring: &RString = &*(obj as *const RString);
36
- let flags = rstring.basic.flags;
37
- let is_heap = (flags & crate::ruby_rstring_flags::RSTRING_NOEMBED as VALUE) != 0;
38
- let ptr = if !is_heap {
39
- std::ptr::addr_of!(rstring.as_.embed.ary) as *const _
40
- } else {
41
- rstring.as_.heap.ptr
42
- };
43
-
44
- assert!(!ptr.is_null());
45
-
46
- ptr
47
- }
48
-
49
- #[inline]
50
- unsafe fn rarray_len(&self, obj: VALUE) -> c_long {
51
- assert!(self.type_p(obj, value_type::RUBY_T_ARRAY));
52
-
53
- let rarray: &RArray = &*(obj as *const RArray);
54
- let flags = rarray.basic.flags;
55
- let is_embedded = (flags & crate::ruby_rarray_flags::RARRAY_EMBED_FLAG as VALUE) != 0;
56
-
57
- if is_embedded {
58
- let mut f = rarray.basic.flags;
59
- f &= crate::ruby_rarray_flags::RARRAY_EMBED_LEN_MASK as VALUE;
60
- f >>= crate::ruby_rarray_consts::RARRAY_EMBED_LEN_SHIFT as VALUE;
61
- f as c_long
62
- } else {
63
- rarray.as_.heap.len
64
- }
65
- }
66
-
67
- #[inline]
68
- unsafe fn rarray_const_ptr(&self, obj: VALUE) -> *const VALUE {
69
- assert!(self.type_p(obj, value_type::RUBY_T_ARRAY));
70
-
71
- let rarray: &RArray = &*(obj as *const RArray);
72
- let flags = rarray.basic.flags;
73
- let is_embedded = (flags & crate::ruby_rarray_flags::RARRAY_EMBED_FLAG as VALUE) != 0;
74
- let ptr = if is_embedded {
75
- std::ptr::addr_of!(rarray.as_.ary) as *const _
76
- } else {
77
- rarray.as_.heap.ptr
78
- };
79
-
80
- assert!(!ptr.is_null());
81
-
82
- ptr
83
- }
84
-
85
- #[inline]
86
- unsafe fn rbasic_class(&self, obj: VALUE) -> Option<NonNull<VALUE>> {
87
- let rbasic = obj as *const crate::RBasic;
88
-
89
- NonNull::<VALUE>::new((*rbasic).klass as _)
90
- }
91
-
92
- #[inline]
93
- unsafe fn frozen_p(&self, obj: VALUE) -> bool {
94
- if self.special_const_p(obj) {
95
- true
96
- } else {
97
- let rbasic = obj as *const crate::RBasic;
98
- ((*rbasic).flags & crate::ruby_fl_type::RUBY_FL_FREEZE as VALUE) != 0
99
- }
100
- }
101
-
102
- #[inline]
103
- unsafe fn bignum_positive_p(&self, obj: VALUE) -> bool {
104
- let rbasic = obj as *const crate::RBasic;
105
-
106
- ((*rbasic).flags & crate::ruby_fl_type::RUBY_FL_USER1 as VALUE) != 0
107
- }
108
-
109
- #[inline]
110
- fn special_const_p(&self, value: VALUE) -> bool {
111
- let is_immediate = (value) & (crate::special_consts::IMMEDIATE_MASK as VALUE) != 0;
112
- let test = (value & !(crate::Qnil as VALUE)) != 0;
113
-
114
- is_immediate || !test
115
- }
116
-
117
- #[inline]
118
- unsafe fn builtin_type(&self, obj: VALUE) -> crate::ruby_value_type {
119
- let rbasic = obj as *const crate::RBasic;
120
- let ret: u32 = ((*rbasic).flags & crate::ruby_value_type::RUBY_T_MASK as VALUE) as _;
121
-
122
- std::mem::transmute::<_, crate::ruby_value_type>(ret)
123
- }
124
-
125
- #[inline]
126
- fn nil_p(&self, obj: VALUE) -> bool {
127
- obj == (crate::Qnil as VALUE)
128
- }
129
-
130
- #[inline]
131
- fn fixnum_p(&self, obj: VALUE) -> bool {
132
- (obj & crate::FIXNUM_FLAG as VALUE) != 0
133
- }
134
-
135
- #[inline]
136
- fn static_sym_p(&self, obj: VALUE) -> bool {
137
- let mask = !(VALUE::MAX << crate::ruby_special_consts::RUBY_SPECIAL_SHIFT as VALUE);
138
- (obj & mask) == crate::ruby_special_consts::RUBY_SYMBOL_FLAG as VALUE
139
- }
140
-
141
- #[inline]
142
- fn flonum_p(&self, obj: VALUE) -> bool {
143
- #[cfg(ruby_use_flonum = "true")]
144
- let ret = (obj & crate::FLONUM_MASK as VALUE) == crate::FLONUM_FLAG as VALUE;
145
-
146
- #[cfg(not(ruby_use_flonum = "true"))]
147
- let ret = false;
148
-
149
- ret
150
- }
151
-
152
- #[inline]
153
- fn immediate_p(&self, obj: VALUE) -> bool {
154
- (obj & crate::special_consts::IMMEDIATE_MASK as VALUE) != 0
155
- }
156
-
157
- #[inline]
158
- fn rb_test(&self, obj: VALUE) -> bool {
159
- (obj & !(crate::Qnil as VALUE)) != 0
160
- }
161
-
162
- #[inline]
163
- unsafe fn type_p(&self, obj: VALUE, t: crate::ruby_value_type) -> bool {
164
- use crate::ruby_special_consts::*;
165
- use crate::ruby_value_type::*;
166
-
167
- if t == RUBY_T_TRUE {
168
- obj == RUBY_Qtrue as _
169
- } else if t == RUBY_T_FALSE {
170
- obj == RUBY_Qfalse as _
171
- } else if t == RUBY_T_NIL {
172
- obj == RUBY_Qnil as _
173
- } else if t == RUBY_T_UNDEF {
174
- obj == RUBY_Qundef as _
175
- } else if t == RUBY_T_FIXNUM {
176
- self.fixnum_p(obj)
177
- } else if t == RUBY_T_SYMBOL {
178
- self.symbol_p(obj)
179
- } else if t == RUBY_T_FLOAT {
180
- self.float_type_p(obj)
181
- } else if self.special_const_p(obj) {
182
- false
183
- } else if t == self.builtin_type(obj) {
184
- true
185
- } else {
186
- t == self.rb_type(obj)
187
- }
188
- }
189
-
190
- #[inline]
191
- unsafe fn symbol_p(&self, obj: VALUE) -> bool {
192
- self.static_sym_p(obj) || self.dynamic_sym_p(obj)
193
- }
194
-
195
- #[inline]
196
- unsafe fn float_type_p(&self, obj: VALUE) -> bool {
197
- if self.flonum_p(obj) {
198
- true
199
- } else if self.special_const_p(obj) {
200
- false
201
- } else {
202
- self.builtin_type(obj) == value_type::RUBY_T_FLOAT
203
- }
204
- }
205
-
206
- #[inline]
207
- unsafe fn rb_type(&self, obj: VALUE) -> crate::ruby_value_type {
208
- use crate::ruby_special_consts::*;
209
- use crate::ruby_value_type::*;
210
-
211
- if !self.special_const_p(obj) {
212
- self.builtin_type(obj)
213
- } else if obj == RUBY_Qfalse as _ {
214
- RUBY_T_FALSE
215
- } else if obj == RUBY_Qnil as _ {
216
- RUBY_T_NIL
217
- } else if obj == RUBY_Qtrue as _ {
218
- RUBY_T_TRUE
219
- } else if obj == RUBY_Qundef as _ {
220
- RUBY_T_UNDEF
221
- } else if self.fixnum_p(obj) {
222
- RUBY_T_FIXNUM
223
- } else if self.static_sym_p(obj) {
224
- RUBY_T_SYMBOL
225
- } else {
226
- debug_assert!(self.flonum_p(obj));
227
- RUBY_T_FLOAT
228
- }
229
- }
230
-
231
- #[inline]
232
- unsafe fn dynamic_sym_p(&self, obj: VALUE) -> bool {
233
- if self.special_const_p(obj) {
234
- false
235
- } else {
236
- self.builtin_type(obj) == value_type::RUBY_T_SYMBOL
237
- }
238
- }
239
-
240
- #[inline]
241
- unsafe fn integer_type_p(&self, obj: VALUE) -> bool {
242
- if self.fixnum_p(obj) {
243
- true
244
- } else if self.special_const_p(obj) {
245
- false
246
- } else {
247
- self.builtin_type(obj) == value_type::RUBY_T_BIGNUM
248
- }
249
- }
250
-
251
- #[inline]
252
- unsafe fn rstring_interned_p(&self, obj: VALUE) -> bool {
253
- assert!(self.type_p(obj, value_type::RUBY_T_STRING));
254
-
255
- let rstring: &RString = &*(obj as *const RString);
256
- let flags = rstring.basic.flags;
257
-
258
- (flags & crate::ruby_rstring_flags::RSTRING_FSTR as VALUE) != 0
259
- }
260
-
261
- #[inline]
262
- fn thread_sleep(&self, duration: Duration) {
263
- let seconds = duration.as_secs() as _;
264
- let microseconds = duration.subsec_micros() as _;
265
-
266
- let time = crate::timeval {
267
- tv_sec: seconds,
268
- tv_usec: microseconds,
269
- };
270
-
271
- unsafe { crate::rb_thread_wait_for(time) }
272
- }
273
-
274
- #[inline]
275
- unsafe fn rtypeddata_p(&self, obj: VALUE) -> bool {
276
- debug_ruby_assert_type!(obj, RUBY_T_DATA, "rtypeddata_p called on non-T_DATA object");
277
-
278
- // Access the RTypedData struct
279
- let rdata = obj as *const crate::internal::RTypedData;
280
- let typed_flag = (*rdata).typed_flag;
281
- // Valid typed_flag values are 1, 2, or 3
282
- typed_flag != 0 && typed_flag <= 3
283
- }
284
-
285
- #[inline]
286
- unsafe fn rtypeddata_embedded_p(&self, obj: VALUE) -> bool {
287
- debug_ruby_assert_type!(obj, RUBY_T_DATA, "rtypeddata_embedded_p called on non-T_DATA object");
288
-
289
- let rdata = obj as *const crate::internal::RTypedData;
290
- let typed_flag = (*rdata).typed_flag;
291
- #[cfg(target_pointer_width = "64")]
292
- const FLAG: u64 = crate::TYPED_DATA_EMBEDDED as u64;
293
- #[cfg(target_pointer_width = "32")]
294
- const FLAG: u32 = crate::TYPED_DATA_EMBEDDED as u32;
295
-
296
- (typed_flag & FLAG) != 0
297
- }
298
-
299
- #[inline]
300
- unsafe fn rtypeddata_type(&self, obj: VALUE) -> *const crate::rb_data_type_t {
301
- debug_ruby_assert_type!(obj, RUBY_T_DATA, "rtypeddata_type called on non-T_DATA object");
302
-
303
- let rdata = obj as *const crate::internal::RTypedData;
304
- (*rdata).type_
305
- }
306
-
307
- #[inline]
308
- unsafe fn rtypeddata_get_data(&self, obj: VALUE) -> *mut std::ffi::c_void {
309
- debug_ruby_assert_type!(obj, RUBY_T_DATA, "rtypeddata_get_data called on non-T_DATA object");
310
-
311
- if self.rtypeddata_embedded_p(obj) {
312
- // For embedded data, calculate pointer based on struct layout
313
- // The formula matches Ruby's implementation:
314
- // embedded_typed_data_size = sizeof(RTypedData) - sizeof(void *)
315
- const EMBEDDED_TYPED_DATA_SIZE: usize =
316
- std::mem::size_of::<crate::internal::RTypedData>() - std::mem::size_of::<*mut std::ffi::c_void>();
317
-
318
- // Return address after the header as the data pointer
319
- (obj as *mut u8).add(EMBEDDED_TYPED_DATA_SIZE) as *mut std::ffi::c_void
320
- } else {
321
- // For non-embedded data, return the data field directly
322
- let rdata = obj as *const crate::internal::RTypedData;
323
- (*rdata).data
324
- }
325
- }
326
- }