kreuzberg 4.0.0.rc1 → 4.0.0.rc2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (342) hide show
  1. checksums.yaml +4 -4
  2. data/.gitignore +14 -8
  3. data/.rspec +3 -3
  4. data/.rubocop.yaml +1 -534
  5. data/.rubocop.yml +538 -0
  6. data/Gemfile +8 -9
  7. data/Gemfile.lock +9 -109
  8. data/README.md +426 -421
  9. data/Rakefile +25 -25
  10. data/Steepfile +47 -47
  11. data/examples/async_patterns.rb +341 -340
  12. data/ext/kreuzberg_rb/extconf.rb +45 -35
  13. data/ext/kreuzberg_rb/native/Cargo.lock +6535 -0
  14. data/ext/kreuzberg_rb/native/Cargo.toml +44 -36
  15. data/ext/kreuzberg_rb/native/README.md +425 -425
  16. data/ext/kreuzberg_rb/native/build.rs +15 -17
  17. data/ext/kreuzberg_rb/native/include/ieeefp.h +11 -11
  18. data/ext/kreuzberg_rb/native/include/msvc_compat/strings.h +14 -14
  19. data/ext/kreuzberg_rb/native/include/strings.h +20 -20
  20. data/ext/kreuzberg_rb/native/include/unistd.h +47 -47
  21. data/ext/kreuzberg_rb/native/src/lib.rs +2998 -2939
  22. data/extconf.rb +28 -28
  23. data/kreuzberg.gemspec +148 -105
  24. data/lib/kreuzberg/api_proxy.rb +142 -142
  25. data/lib/kreuzberg/cache_api.rb +46 -45
  26. data/lib/kreuzberg/cli.rb +55 -55
  27. data/lib/kreuzberg/cli_proxy.rb +127 -127
  28. data/lib/kreuzberg/config.rb +691 -684
  29. data/lib/kreuzberg/error_context.rb +32 -0
  30. data/lib/kreuzberg/errors.rb +118 -50
  31. data/lib/kreuzberg/extraction_api.rb +85 -84
  32. data/lib/kreuzberg/mcp_proxy.rb +186 -186
  33. data/lib/kreuzberg/ocr_backend_protocol.rb +113 -113
  34. data/lib/kreuzberg/post_processor_protocol.rb +86 -86
  35. data/lib/kreuzberg/result.rb +216 -216
  36. data/lib/kreuzberg/setup_lib_path.rb +80 -79
  37. data/lib/kreuzberg/validator_protocol.rb +89 -89
  38. data/lib/kreuzberg/version.rb +5 -5
  39. data/lib/kreuzberg.rb +103 -82
  40. data/sig/kreuzberg/internal.rbs +184 -184
  41. data/sig/kreuzberg.rbs +520 -468
  42. data/spec/binding/cache_spec.rb +227 -227
  43. data/spec/binding/cli_proxy_spec.rb +85 -87
  44. data/spec/binding/cli_spec.rb +55 -54
  45. data/spec/binding/config_spec.rb +345 -345
  46. data/spec/binding/config_validation_spec.rb +283 -283
  47. data/spec/binding/error_handling_spec.rb +213 -213
  48. data/spec/binding/errors_spec.rb +66 -66
  49. data/spec/binding/plugins/ocr_backend_spec.rb +307 -307
  50. data/spec/binding/plugins/postprocessor_spec.rb +269 -269
  51. data/spec/binding/plugins/validator_spec.rb +274 -274
  52. data/spec/fixtures/config.toml +39 -39
  53. data/spec/fixtures/config.yaml +41 -42
  54. data/spec/fixtures/invalid_config.toml +4 -4
  55. data/spec/smoke/package_spec.rb +178 -178
  56. data/spec/spec_helper.rb +42 -42
  57. data/vendor/kreuzberg/Cargo.toml +204 -134
  58. data/vendor/kreuzberg/README.md +175 -175
  59. data/vendor/kreuzberg/benches/otel_overhead.rs +48 -0
  60. data/vendor/kreuzberg/build.rs +474 -460
  61. data/vendor/kreuzberg/src/api/error.rs +81 -81
  62. data/vendor/kreuzberg/src/api/handlers.rs +199 -199
  63. data/vendor/kreuzberg/src/api/mod.rs +79 -79
  64. data/vendor/kreuzberg/src/api/server.rs +353 -353
  65. data/vendor/kreuzberg/src/api/types.rs +170 -170
  66. data/vendor/kreuzberg/src/cache/mod.rs +1167 -1143
  67. data/vendor/kreuzberg/src/chunking/mod.rs +677 -677
  68. data/vendor/kreuzberg/src/core/batch_mode.rs +95 -35
  69. data/vendor/kreuzberg/src/core/config.rs +1032 -1032
  70. data/vendor/kreuzberg/src/core/extractor.rs +1024 -903
  71. data/vendor/kreuzberg/src/core/io.rs +329 -327
  72. data/vendor/kreuzberg/src/core/mime.rs +605 -615
  73. data/vendor/kreuzberg/src/core/mod.rs +45 -42
  74. data/vendor/kreuzberg/src/core/pipeline.rs +984 -906
  75. data/vendor/kreuzberg/src/embeddings.rs +432 -323
  76. data/vendor/kreuzberg/src/error.rs +431 -431
  77. data/vendor/kreuzberg/src/extraction/archive.rs +954 -954
  78. data/vendor/kreuzberg/src/extraction/docx.rs +40 -40
  79. data/vendor/kreuzberg/src/extraction/email.rs +854 -854
  80. data/vendor/kreuzberg/src/extraction/excel.rs +688 -688
  81. data/vendor/kreuzberg/src/extraction/html.rs +553 -553
  82. data/vendor/kreuzberg/src/extraction/image.rs +368 -368
  83. data/vendor/kreuzberg/src/extraction/libreoffice.rs +563 -564
  84. data/vendor/kreuzberg/src/extraction/markdown.rs +213 -0
  85. data/vendor/kreuzberg/src/extraction/mod.rs +81 -77
  86. data/vendor/kreuzberg/src/extraction/office_metadata/app_properties.rs +398 -398
  87. data/vendor/kreuzberg/src/extraction/office_metadata/core_properties.rs +247 -247
  88. data/vendor/kreuzberg/src/extraction/office_metadata/custom_properties.rs +240 -240
  89. data/vendor/kreuzberg/src/extraction/office_metadata/mod.rs +130 -128
  90. data/vendor/kreuzberg/src/extraction/office_metadata/odt_properties.rs +287 -0
  91. data/vendor/kreuzberg/src/extraction/pptx.rs +3000 -3000
  92. data/vendor/kreuzberg/src/extraction/structured.rs +490 -490
  93. data/vendor/kreuzberg/src/extraction/table.rs +328 -328
  94. data/vendor/kreuzberg/src/extraction/text.rs +269 -269
  95. data/vendor/kreuzberg/src/extraction/xml.rs +333 -333
  96. data/vendor/kreuzberg/src/extractors/archive.rs +446 -425
  97. data/vendor/kreuzberg/src/extractors/bibtex.rs +469 -0
  98. data/vendor/kreuzberg/src/extractors/docbook.rs +502 -0
  99. data/vendor/kreuzberg/src/extractors/docx.rs +367 -479
  100. data/vendor/kreuzberg/src/extractors/email.rs +143 -129
  101. data/vendor/kreuzberg/src/extractors/epub.rs +707 -0
  102. data/vendor/kreuzberg/src/extractors/excel.rs +343 -344
  103. data/vendor/kreuzberg/src/extractors/fictionbook.rs +491 -0
  104. data/vendor/kreuzberg/src/extractors/fictionbook.rs.backup2 +738 -0
  105. data/vendor/kreuzberg/src/extractors/html.rs +393 -410
  106. data/vendor/kreuzberg/src/extractors/image.rs +198 -195
  107. data/vendor/kreuzberg/src/extractors/jats.rs +1051 -0
  108. data/vendor/kreuzberg/src/extractors/jupyter.rs +367 -0
  109. data/vendor/kreuzberg/src/extractors/latex.rs +652 -0
  110. data/vendor/kreuzberg/src/extractors/markdown.rs +700 -0
  111. data/vendor/kreuzberg/src/extractors/mod.rs +365 -268
  112. data/vendor/kreuzberg/src/extractors/odt.rs +628 -0
  113. data/vendor/kreuzberg/src/extractors/opml.rs +634 -0
  114. data/vendor/kreuzberg/src/extractors/orgmode.rs +528 -0
  115. data/vendor/kreuzberg/src/extractors/pdf.rs +493 -496
  116. data/vendor/kreuzberg/src/extractors/pptx.rs +248 -234
  117. data/vendor/kreuzberg/src/extractors/rst.rs +576 -0
  118. data/vendor/kreuzberg/src/extractors/rtf.rs +810 -0
  119. data/vendor/kreuzberg/src/extractors/security.rs +484 -0
  120. data/vendor/kreuzberg/src/extractors/security_tests.rs +367 -0
  121. data/vendor/kreuzberg/src/extractors/structured.rs +140 -126
  122. data/vendor/kreuzberg/src/extractors/text.rs +260 -242
  123. data/vendor/kreuzberg/src/extractors/typst.rs +650 -0
  124. data/vendor/kreuzberg/src/extractors/xml.rs +135 -128
  125. data/vendor/kreuzberg/src/image/dpi.rs +164 -164
  126. data/vendor/kreuzberg/src/image/mod.rs +6 -6
  127. data/vendor/kreuzberg/src/image/preprocessing.rs +417 -417
  128. data/vendor/kreuzberg/src/image/resize.rs +89 -89
  129. data/vendor/kreuzberg/src/keywords/config.rs +154 -154
  130. data/vendor/kreuzberg/src/keywords/mod.rs +237 -237
  131. data/vendor/kreuzberg/src/keywords/processor.rs +267 -267
  132. data/vendor/kreuzberg/src/keywords/rake.rs +293 -294
  133. data/vendor/kreuzberg/src/keywords/types.rs +68 -68
  134. data/vendor/kreuzberg/src/keywords/yake.rs +163 -163
  135. data/vendor/kreuzberg/src/language_detection/mod.rs +942 -942
  136. data/vendor/kreuzberg/src/lib.rs +105 -102
  137. data/vendor/kreuzberg/src/mcp/mod.rs +32 -32
  138. data/vendor/kreuzberg/src/mcp/server.rs +1968 -1966
  139. data/vendor/kreuzberg/src/ocr/cache.rs +469 -469
  140. data/vendor/kreuzberg/src/ocr/error.rs +37 -37
  141. data/vendor/kreuzberg/src/ocr/hocr.rs +216 -216
  142. data/vendor/kreuzberg/src/ocr/mod.rs +58 -58
  143. data/vendor/kreuzberg/src/ocr/processor.rs +863 -847
  144. data/vendor/kreuzberg/src/ocr/table/mod.rs +4 -4
  145. data/vendor/kreuzberg/src/ocr/table/tsv_parser.rs +144 -144
  146. data/vendor/kreuzberg/src/ocr/tesseract_backend.rs +450 -450
  147. data/vendor/kreuzberg/src/ocr/types.rs +393 -393
  148. data/vendor/kreuzberg/src/ocr/utils.rs +47 -47
  149. data/vendor/kreuzberg/src/ocr/validation.rs +206 -206
  150. data/vendor/kreuzberg/src/panic_context.rs +154 -0
  151. data/vendor/kreuzberg/src/pdf/error.rs +122 -122
  152. data/vendor/kreuzberg/src/pdf/images.rs +139 -139
  153. data/vendor/kreuzberg/src/pdf/metadata.rs +346 -346
  154. data/vendor/kreuzberg/src/pdf/mod.rs +50 -50
  155. data/vendor/kreuzberg/src/pdf/rendering.rs +369 -369
  156. data/vendor/kreuzberg/src/pdf/table.rs +393 -420
  157. data/vendor/kreuzberg/src/pdf/text.rs +158 -161
  158. data/vendor/kreuzberg/src/plugins/extractor.rs +1013 -1010
  159. data/vendor/kreuzberg/src/plugins/mod.rs +209 -209
  160. data/vendor/kreuzberg/src/plugins/ocr.rs +620 -629
  161. data/vendor/kreuzberg/src/plugins/processor.rs +642 -641
  162. data/vendor/kreuzberg/src/plugins/registry.rs +1337 -1324
  163. data/vendor/kreuzberg/src/plugins/traits.rs +258 -258
  164. data/vendor/kreuzberg/src/plugins/validator.rs +956 -955
  165. data/vendor/kreuzberg/src/stopwords/mod.rs +1470 -1470
  166. data/vendor/kreuzberg/src/text/mod.rs +19 -19
  167. data/vendor/kreuzberg/src/text/quality.rs +697 -697
  168. data/vendor/kreuzberg/src/text/string_utils.rs +217 -217
  169. data/vendor/kreuzberg/src/text/token_reduction/cjk_utils.rs +164 -164
  170. data/vendor/kreuzberg/src/text/token_reduction/config.rs +100 -100
  171. data/vendor/kreuzberg/src/text/token_reduction/core.rs +796 -796
  172. data/vendor/kreuzberg/src/text/token_reduction/filters.rs +902 -902
  173. data/vendor/kreuzberg/src/text/token_reduction/mod.rs +160 -160
  174. data/vendor/kreuzberg/src/text/token_reduction/semantic.rs +619 -619
  175. data/vendor/kreuzberg/src/text/token_reduction/simd_text.rs +147 -147
  176. data/vendor/kreuzberg/src/types.rs +903 -873
  177. data/vendor/kreuzberg/src/utils/mod.rs +17 -17
  178. data/vendor/kreuzberg/src/utils/quality.rs +959 -959
  179. data/vendor/kreuzberg/src/utils/string_utils.rs +381 -381
  180. data/vendor/kreuzberg/stopwords/af_stopwords.json +53 -53
  181. data/vendor/kreuzberg/stopwords/ar_stopwords.json +482 -482
  182. data/vendor/kreuzberg/stopwords/bg_stopwords.json +261 -261
  183. data/vendor/kreuzberg/stopwords/bn_stopwords.json +400 -400
  184. data/vendor/kreuzberg/stopwords/br_stopwords.json +1205 -1205
  185. data/vendor/kreuzberg/stopwords/ca_stopwords.json +280 -280
  186. data/vendor/kreuzberg/stopwords/cs_stopwords.json +425 -425
  187. data/vendor/kreuzberg/stopwords/da_stopwords.json +172 -172
  188. data/vendor/kreuzberg/stopwords/de_stopwords.json +622 -622
  189. data/vendor/kreuzberg/stopwords/el_stopwords.json +849 -849
  190. data/vendor/kreuzberg/stopwords/en_stopwords.json +1300 -1300
  191. data/vendor/kreuzberg/stopwords/eo_stopwords.json +175 -175
  192. data/vendor/kreuzberg/stopwords/es_stopwords.json +734 -734
  193. data/vendor/kreuzberg/stopwords/et_stopwords.json +37 -37
  194. data/vendor/kreuzberg/stopwords/eu_stopwords.json +100 -100
  195. data/vendor/kreuzberg/stopwords/fa_stopwords.json +801 -801
  196. data/vendor/kreuzberg/stopwords/fi_stopwords.json +849 -849
  197. data/vendor/kreuzberg/stopwords/fr_stopwords.json +693 -693
  198. data/vendor/kreuzberg/stopwords/ga_stopwords.json +111 -111
  199. data/vendor/kreuzberg/stopwords/gl_stopwords.json +162 -162
  200. data/vendor/kreuzberg/stopwords/gu_stopwords.json +226 -226
  201. data/vendor/kreuzberg/stopwords/ha_stopwords.json +41 -41
  202. data/vendor/kreuzberg/stopwords/he_stopwords.json +196 -196
  203. data/vendor/kreuzberg/stopwords/hi_stopwords.json +227 -227
  204. data/vendor/kreuzberg/stopwords/hr_stopwords.json +181 -181
  205. data/vendor/kreuzberg/stopwords/hu_stopwords.json +791 -791
  206. data/vendor/kreuzberg/stopwords/hy_stopwords.json +47 -47
  207. data/vendor/kreuzberg/stopwords/id_stopwords.json +760 -760
  208. data/vendor/kreuzberg/stopwords/it_stopwords.json +634 -634
  209. data/vendor/kreuzberg/stopwords/ja_stopwords.json +136 -136
  210. data/vendor/kreuzberg/stopwords/kn_stopwords.json +84 -84
  211. data/vendor/kreuzberg/stopwords/ko_stopwords.json +681 -681
  212. data/vendor/kreuzberg/stopwords/ku_stopwords.json +64 -64
  213. data/vendor/kreuzberg/stopwords/la_stopwords.json +51 -51
  214. data/vendor/kreuzberg/stopwords/lt_stopwords.json +476 -476
  215. data/vendor/kreuzberg/stopwords/lv_stopwords.json +163 -163
  216. data/vendor/kreuzberg/stopwords/ml_stopwords.json +1 -1
  217. data/vendor/kreuzberg/stopwords/mr_stopwords.json +101 -101
  218. data/vendor/kreuzberg/stopwords/ms_stopwords.json +477 -477
  219. data/vendor/kreuzberg/stopwords/ne_stopwords.json +490 -490
  220. data/vendor/kreuzberg/stopwords/nl_stopwords.json +415 -415
  221. data/vendor/kreuzberg/stopwords/no_stopwords.json +223 -223
  222. data/vendor/kreuzberg/stopwords/pl_stopwords.json +331 -331
  223. data/vendor/kreuzberg/stopwords/pt_stopwords.json +562 -562
  224. data/vendor/kreuzberg/stopwords/ro_stopwords.json +436 -436
  225. data/vendor/kreuzberg/stopwords/ru_stopwords.json +561 -561
  226. data/vendor/kreuzberg/stopwords/si_stopwords.json +193 -193
  227. data/vendor/kreuzberg/stopwords/sk_stopwords.json +420 -420
  228. data/vendor/kreuzberg/stopwords/sl_stopwords.json +448 -448
  229. data/vendor/kreuzberg/stopwords/so_stopwords.json +32 -32
  230. data/vendor/kreuzberg/stopwords/st_stopwords.json +33 -33
  231. data/vendor/kreuzberg/stopwords/sv_stopwords.json +420 -420
  232. data/vendor/kreuzberg/stopwords/sw_stopwords.json +76 -76
  233. data/vendor/kreuzberg/stopwords/ta_stopwords.json +129 -129
  234. data/vendor/kreuzberg/stopwords/te_stopwords.json +54 -54
  235. data/vendor/kreuzberg/stopwords/th_stopwords.json +118 -118
  236. data/vendor/kreuzberg/stopwords/tl_stopwords.json +149 -149
  237. data/vendor/kreuzberg/stopwords/tr_stopwords.json +506 -506
  238. data/vendor/kreuzberg/stopwords/uk_stopwords.json +75 -75
  239. data/vendor/kreuzberg/stopwords/ur_stopwords.json +519 -519
  240. data/vendor/kreuzberg/stopwords/vi_stopwords.json +647 -647
  241. data/vendor/kreuzberg/stopwords/yo_stopwords.json +62 -62
  242. data/vendor/kreuzberg/stopwords/zh_stopwords.json +796 -796
  243. data/vendor/kreuzberg/stopwords/zu_stopwords.json +31 -31
  244. data/vendor/kreuzberg/tests/api_extract_multipart.rs +52 -0
  245. data/vendor/kreuzberg/tests/api_tests.rs +966 -966
  246. data/vendor/kreuzberg/tests/archive_integration.rs +543 -543
  247. data/vendor/kreuzberg/tests/batch_orchestration.rs +556 -542
  248. data/vendor/kreuzberg/tests/batch_processing.rs +316 -304
  249. data/vendor/kreuzberg/tests/bibtex_parity_test.rs +421 -0
  250. data/vendor/kreuzberg/tests/concurrency_stress.rs +525 -509
  251. data/vendor/kreuzberg/tests/config_features.rs +598 -580
  252. data/vendor/kreuzberg/tests/config_loading_tests.rs +415 -439
  253. data/vendor/kreuzberg/tests/core_integration.rs +510 -493
  254. data/vendor/kreuzberg/tests/csv_integration.rs +414 -424
  255. data/vendor/kreuzberg/tests/docbook_extractor_tests.rs +498 -0
  256. data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +122 -124
  257. data/vendor/kreuzberg/tests/docx_vs_pandoc_comparison.rs +370 -0
  258. data/vendor/kreuzberg/tests/email_integration.rs +325 -325
  259. data/vendor/kreuzberg/tests/epub_native_extractor_tests.rs +275 -0
  260. data/vendor/kreuzberg/tests/error_handling.rs +393 -393
  261. data/vendor/kreuzberg/tests/fictionbook_extractor_tests.rs +228 -0
  262. data/vendor/kreuzberg/tests/format_integration.rs +159 -159
  263. data/vendor/kreuzberg/tests/helpers/mod.rs +142 -142
  264. data/vendor/kreuzberg/tests/html_table_test.rs +551 -0
  265. data/vendor/kreuzberg/tests/image_integration.rs +253 -253
  266. data/vendor/kreuzberg/tests/instrumentation_test.rs +139 -0
  267. data/vendor/kreuzberg/tests/jats_extractor_tests.rs +639 -0
  268. data/vendor/kreuzberg/tests/jupyter_extractor_tests.rs +704 -0
  269. data/vendor/kreuzberg/tests/keywords_integration.rs +479 -479
  270. data/vendor/kreuzberg/tests/keywords_quality.rs +509 -509
  271. data/vendor/kreuzberg/tests/latex_extractor_tests.rs +496 -0
  272. data/vendor/kreuzberg/tests/markdown_extractor_tests.rs +490 -0
  273. data/vendor/kreuzberg/tests/mime_detection.rs +428 -428
  274. data/vendor/kreuzberg/tests/ocr_configuration.rs +510 -510
  275. data/vendor/kreuzberg/tests/ocr_errors.rs +676 -676
  276. data/vendor/kreuzberg/tests/ocr_quality.rs +627 -627
  277. data/vendor/kreuzberg/tests/ocr_stress.rs +469 -469
  278. data/vendor/kreuzberg/tests/odt_extractor_tests.rs +695 -0
  279. data/vendor/kreuzberg/tests/opml_extractor_tests.rs +616 -0
  280. data/vendor/kreuzberg/tests/orgmode_extractor_tests.rs +822 -0
  281. data/vendor/kreuzberg/tests/pdf_integration.rs +43 -43
  282. data/vendor/kreuzberg/tests/pipeline_integration.rs +1411 -1412
  283. data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +771 -771
  284. data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +560 -561
  285. data/vendor/kreuzberg/tests/plugin_system.rs +921 -921
  286. data/vendor/kreuzberg/tests/plugin_validator_test.rs +783 -783
  287. data/vendor/kreuzberg/tests/registry_integration_tests.rs +586 -607
  288. data/vendor/kreuzberg/tests/rst_extractor_tests.rs +692 -0
  289. data/vendor/kreuzberg/tests/rtf_extractor_tests.rs +776 -0
  290. data/vendor/kreuzberg/tests/security_validation.rs +415 -404
  291. data/vendor/kreuzberg/tests/stopwords_integration_test.rs +888 -888
  292. data/vendor/kreuzberg/tests/test_fastembed.rs +609 -609
  293. data/vendor/kreuzberg/tests/typst_behavioral_tests.rs +1259 -0
  294. data/vendor/kreuzberg/tests/typst_extractor_tests.rs +647 -0
  295. data/vendor/kreuzberg/tests/xlsx_metadata_extraction_test.rs +87 -87
  296. data/vendor/rb-sys/.cargo-ok +1 -0
  297. data/vendor/rb-sys/.cargo_vcs_info.json +6 -0
  298. data/vendor/rb-sys/Cargo.lock +393 -0
  299. data/vendor/rb-sys/Cargo.toml +70 -0
  300. data/vendor/rb-sys/Cargo.toml.orig +57 -0
  301. data/vendor/rb-sys/LICENSE-APACHE +190 -0
  302. data/vendor/rb-sys/LICENSE-MIT +21 -0
  303. data/vendor/rb-sys/bin/release.sh +21 -0
  304. data/vendor/rb-sys/build/features.rs +108 -0
  305. data/vendor/rb-sys/build/main.rs +246 -0
  306. data/vendor/rb-sys/build/stable_api_config.rs +153 -0
  307. data/vendor/rb-sys/build/version.rs +48 -0
  308. data/vendor/rb-sys/readme.md +36 -0
  309. data/vendor/rb-sys/src/bindings.rs +21 -0
  310. data/vendor/rb-sys/src/hidden.rs +11 -0
  311. data/vendor/rb-sys/src/lib.rs +34 -0
  312. data/vendor/rb-sys/src/macros.rs +371 -0
  313. data/vendor/rb-sys/src/memory.rs +53 -0
  314. data/vendor/rb-sys/src/ruby_abi_version.rs +38 -0
  315. data/vendor/rb-sys/src/special_consts.rs +31 -0
  316. data/vendor/rb-sys/src/stable_api/compiled.c +179 -0
  317. data/vendor/rb-sys/src/stable_api/compiled.rs +257 -0
  318. data/vendor/rb-sys/src/stable_api/ruby_2_6.rs +316 -0
  319. data/vendor/rb-sys/src/stable_api/ruby_2_7.rs +316 -0
  320. data/vendor/rb-sys/src/stable_api/ruby_3_0.rs +324 -0
  321. data/vendor/rb-sys/src/stable_api/ruby_3_1.rs +317 -0
  322. data/vendor/rb-sys/src/stable_api/ruby_3_2.rs +315 -0
  323. data/vendor/rb-sys/src/stable_api/ruby_3_3.rs +326 -0
  324. data/vendor/rb-sys/src/stable_api/ruby_3_4.rs +327 -0
  325. data/vendor/rb-sys/src/stable_api.rs +261 -0
  326. data/vendor/rb-sys/src/symbol.rs +31 -0
  327. data/vendor/rb-sys/src/tracking_allocator.rs +332 -0
  328. data/vendor/rb-sys/src/utils.rs +89 -0
  329. data/vendor/rb-sys/src/value_type.rs +7 -0
  330. metadata +90 -95
  331. data/pkg/kreuzberg-4.0.0.rc1.gem +0 -0
  332. data/spec/examples.txt +0 -104
  333. data/vendor/kreuzberg/src/bin/profile_extract.rs +0 -455
  334. data/vendor/kreuzberg/src/extraction/pandoc/batch.rs +0 -275
  335. data/vendor/kreuzberg/src/extraction/pandoc/mime_types.rs +0 -178
  336. data/vendor/kreuzberg/src/extraction/pandoc/mod.rs +0 -491
  337. data/vendor/kreuzberg/src/extraction/pandoc/server.rs +0 -496
  338. data/vendor/kreuzberg/src/extraction/pandoc/subprocess.rs +0 -1188
  339. data/vendor/kreuzberg/src/extraction/pandoc/version.rs +0 -162
  340. data/vendor/kreuzberg/src/extractors/pandoc.rs +0 -201
  341. data/vendor/kreuzberg/tests/chunking_offset_demo.rs +0 -92
  342. data/vendor/kreuzberg/tests/pandoc_integration.rs +0 -503
@@ -0,0 +1,332 @@
1
+ //! Support for reporting Rust memory usage to the Ruby GC.
2
+
3
+ use std::{
4
+ fmt::Formatter,
5
+ sync::{
6
+ Arc,
7
+ atomic::{AtomicIsize, Ordering},
8
+ },
9
+ };
10
+
11
+ #[cfg(ruby_engine = "mri")]
12
+ mod mri {
13
+ use crate::{rb_gc_adjust_memory_usage, utils::is_ruby_vm_started};
14
+ use std::alloc::{GlobalAlloc, Layout, System};
15
+
16
+ /// A simple wrapper over [`System`] which reports memory usage to
17
+ /// the Ruby GC. This gives the GC a more accurate picture of the process'
18
+ /// memory usage so it can make better decisions about when to run.
19
+ #[derive(Debug)]
20
+ pub struct TrackingAllocator;
21
+
22
+ impl TrackingAllocator {
23
+ /// Create a new [`TrackingAllocator`].
24
+ #[allow(clippy::new_without_default)]
25
+ pub const fn new() -> Self {
26
+ Self
27
+ }
28
+
29
+ /// Create a new [`TrackingAllocator`] with default values.
30
+ pub const fn default() -> Self {
31
+ Self::new()
32
+ }
33
+
34
+ /// Adjust the memory usage reported to the Ruby GC by `delta`. Useful for
35
+ /// tracking allocations invisible to the Rust allocator, such as `mmap` or
36
+ /// direct `malloc` calls.
37
+ ///
38
+ /// # Example
39
+ /// ```
40
+ /// use rb_sys::TrackingAllocator;
41
+ ///
42
+ /// // Allocate 1024 bytes of memory using `mmap` or `malloc`...
43
+ /// TrackingAllocator::adjust_memory_usage(1024);
44
+ ///
45
+ /// // ...and then after the memory is freed, adjust the memory usage again.
46
+ /// TrackingAllocator::adjust_memory_usage(-1024);
47
+ /// ```
48
+ #[inline]
49
+ pub fn adjust_memory_usage(delta: isize) -> isize {
50
+ if delta == 0 {
51
+ return 0;
52
+ }
53
+
54
+ #[cfg(target_pointer_width = "32")]
55
+ let delta = delta as i32;
56
+
57
+ #[cfg(target_pointer_width = "64")]
58
+ let delta = delta as i64;
59
+
60
+ unsafe {
61
+ if is_ruby_vm_started() {
62
+ // On Windows, ssize_t is i32 even on 64-bit, so cast i64 to i32
63
+ #[cfg(all(target_pointer_width = "64", target_os = "windows"))]
64
+ rb_gc_adjust_memory_usage(delta as i32);
65
+
66
+ #[cfg(not(all(target_pointer_width = "64", target_os = "windows")))]
67
+ rb_gc_adjust_memory_usage(delta);
68
+
69
+ delta as isize
70
+ } else {
71
+ 0
72
+ }
73
+ }
74
+ }
75
+ }
76
+
77
+ unsafe impl GlobalAlloc for TrackingAllocator {
78
+ #[inline]
79
+ unsafe fn alloc(&self, layout: Layout) -> *mut u8 {
80
+ let ret = System.alloc(layout);
81
+ let delta = layout.size() as isize;
82
+
83
+ if !ret.is_null() && delta != 0 {
84
+ Self::adjust_memory_usage(delta);
85
+ }
86
+
87
+ ret
88
+ }
89
+
90
+ #[inline]
91
+ unsafe fn alloc_zeroed(&self, layout: Layout) -> *mut u8 {
92
+ let ret = System.alloc_zeroed(layout);
93
+ let delta = layout.size() as isize;
94
+
95
+ if !ret.is_null() && delta != 0 {
96
+ Self::adjust_memory_usage(delta);
97
+ }
98
+
99
+ ret
100
+ }
101
+
102
+ #[inline]
103
+ unsafe fn dealloc(&self, ptr: *mut u8, layout: Layout) {
104
+ System.dealloc(ptr, layout);
105
+ let delta = -(layout.size() as isize);
106
+
107
+ if delta != 0 {
108
+ Self::adjust_memory_usage(delta);
109
+ }
110
+ }
111
+
112
+ #[inline]
113
+ unsafe fn realloc(&self, ptr: *mut u8, layout: Layout, new_size: usize) -> *mut u8 {
114
+ let ret = System.realloc(ptr, layout, new_size);
115
+ let delta = new_size as isize - layout.size() as isize;
116
+
117
+ if !ret.is_null() && delta != 0 {
118
+ Self::adjust_memory_usage(delta);
119
+ }
120
+
121
+ ret
122
+ }
123
+ }
124
+ }
125
+
126
+ #[cfg(not(ruby_engine = "mri"))]
127
+ mod non_mri {
128
+ use std::alloc::{GlobalAlloc, Layout, System};
129
+
130
+ /// A simple wrapper over [`System`] as a fallback for non-MRI Ruby engines.
131
+ pub struct TrackingAllocator;
132
+
133
+ impl TrackingAllocator {
134
+ #[allow(clippy::new_without_default)]
135
+ pub const fn new() -> Self {
136
+ Self
137
+ }
138
+
139
+ pub const fn default() -> Self {
140
+ Self::new()
141
+ }
142
+
143
+ pub fn adjust_memory_usage(_delta: isize) -> isize {
144
+ 0
145
+ }
146
+ }
147
+
148
+ unsafe impl GlobalAlloc for TrackingAllocator {
149
+ #[inline]
150
+ unsafe fn alloc(&self, layout: Layout) -> *mut u8 {
151
+ System.alloc(layout)
152
+ }
153
+
154
+ #[inline]
155
+ unsafe fn alloc_zeroed(&self, layout: Layout) -> *mut u8 {
156
+ System.alloc_zeroed(layout)
157
+ }
158
+
159
+ #[inline]
160
+ unsafe fn dealloc(&self, ptr: *mut u8, layout: Layout) {
161
+ System.dealloc(ptr, layout)
162
+ }
163
+
164
+ #[inline]
165
+ unsafe fn realloc(&self, ptr: *mut u8, layout: Layout, new_size: usize) -> *mut u8 {
166
+ System.realloc(ptr, layout, new_size)
167
+ }
168
+ }
169
+ }
170
+
171
+ #[cfg(ruby_engine = "mri")]
172
+ pub use mri::*;
173
+
174
+ #[cfg(not(ruby_engine = "mri"))]
175
+ pub use non_mri::*;
176
+
177
+ /// Set the global allocator to [`TrackingAllocator`].
178
+ ///
179
+ /// # Example
180
+ /// ```
181
+ /// // File: ext/my_gem/src/lib.rs
182
+ /// use rb_sys::set_global_tracking_allocator;
183
+ ///
184
+ /// set_global_tracking_allocator!();
185
+ /// ```
186
+ #[macro_export]
187
+ macro_rules! set_global_tracking_allocator {
188
+ () => {
189
+ #[global_allocator]
190
+ static RUBY_GLOBAL_TRACKING_ALLOCATOR: $crate::tracking_allocator::TrackingAllocator =
191
+ $crate::tracking_allocator::TrackingAllocator;
192
+ };
193
+ }
194
+
195
+ #[derive(Debug)]
196
+ #[repr(transparent)]
197
+ struct MemsizeDelta(Arc<AtomicIsize>);
198
+
199
+ impl MemsizeDelta {
200
+ fn new(delta: isize) -> Self {
201
+ let delta = TrackingAllocator::adjust_memory_usage(delta);
202
+ Self(Arc::new(AtomicIsize::new(delta)))
203
+ }
204
+
205
+ fn add(&self, delta: usize) {
206
+ if delta == 0 {
207
+ return;
208
+ }
209
+
210
+ let delta = TrackingAllocator::adjust_memory_usage(delta as _);
211
+ self.0.fetch_add(delta as _, Ordering::SeqCst);
212
+ }
213
+
214
+ fn sub(&self, delta: usize) {
215
+ if delta == 0 {
216
+ return;
217
+ }
218
+
219
+ let delta = TrackingAllocator::adjust_memory_usage(-(delta as isize));
220
+ self.0.fetch_add(delta, Ordering::SeqCst);
221
+ }
222
+
223
+ fn get(&self) -> isize {
224
+ self.0.load(Ordering::SeqCst)
225
+ }
226
+ }
227
+
228
+ impl Clone for MemsizeDelta {
229
+ fn clone(&self) -> Self {
230
+ Self(Arc::clone(&self.0))
231
+ }
232
+ }
233
+
234
+ impl Drop for MemsizeDelta {
235
+ fn drop(&mut self) {
236
+ let memsize = self.0.swap(0, Ordering::SeqCst);
237
+ TrackingAllocator::adjust_memory_usage(0 - memsize);
238
+ }
239
+ }
240
+
241
+ /// A guard which adjusts the memory usage reported to the Ruby GC by `delta`.
242
+ /// This allows you to track resources which are invisible to the Rust
243
+ /// allocator, such as items that are known to internally use `mmap` or direct
244
+ /// `malloc` in their implementation.
245
+ ///
246
+ /// Internally, it uses an [`Arc<AtomicIsize>`] to track the memory usage delta,
247
+ /// and is safe to clone when `T` is [`Clone`].
248
+ ///
249
+ /// # Example
250
+ /// ```
251
+ /// use rb_sys::tracking_allocator::ManuallyTracked;
252
+ ///
253
+ /// type SomethingThatUsedMmap = ();
254
+ ///
255
+ /// // Will tell the Ruby GC that 1024 bytes were allocated.
256
+ /// let item = ManuallyTracked::new(SomethingThatUsedMmap, 1024);
257
+ ///
258
+ /// // Will tell the Ruby GC that 1024 bytes were freed.
259
+ /// std::mem::drop(item);
260
+ /// ```
261
+ pub struct ManuallyTracked<T> {
262
+ item: T,
263
+ memsize_delta: MemsizeDelta,
264
+ }
265
+
266
+ impl<T> ManuallyTracked<T> {
267
+ /// Create a new `ManuallyTracked<T>`, and immediately report that `memsize`
268
+ /// bytes were allocated.
269
+ pub fn wrap(item: T, memsize: usize) -> Self {
270
+ Self {
271
+ item,
272
+ memsize_delta: MemsizeDelta::new(memsize as _),
273
+ }
274
+ }
275
+
276
+ /// Increase the memory usage reported to the Ruby GC by `memsize` bytes.
277
+ pub fn increase_memory_usage(&self, memsize: usize) {
278
+ self.memsize_delta.add(memsize);
279
+ }
280
+
281
+ /// Decrease the memory usage reported to the Ruby GC by `memsize` bytes.
282
+ pub fn decrease_memory_usage(&self, memsize: usize) {
283
+ self.memsize_delta.sub(memsize);
284
+ }
285
+
286
+ /// Get the current memory usage delta.
287
+ pub fn memsize_delta(&self) -> isize {
288
+ self.memsize_delta.get()
289
+ }
290
+
291
+ /// Get a shared reference to the inner `T`.
292
+ pub fn get(&self) -> &T {
293
+ &self.item
294
+ }
295
+
296
+ /// Get a mutable reference to the inner `T`.
297
+ pub fn get_mut(&mut self) -> &mut T {
298
+ &mut self.item
299
+ }
300
+ }
301
+
302
+ impl ManuallyTracked<()> {
303
+ /// Create a new `ManuallyTracked<()>`, and immediately report that
304
+ /// `memsize` bytes were allocated.
305
+ pub fn new(memsize: usize) -> Self {
306
+ Self::wrap((), memsize)
307
+ }
308
+ }
309
+
310
+ impl Default for ManuallyTracked<()> {
311
+ fn default() -> Self {
312
+ Self::wrap((), 0)
313
+ }
314
+ }
315
+
316
+ impl<T: Clone> Clone for ManuallyTracked<T> {
317
+ fn clone(&self) -> Self {
318
+ Self {
319
+ item: self.item.clone(),
320
+ memsize_delta: self.memsize_delta.clone(),
321
+ }
322
+ }
323
+ }
324
+
325
+ impl<T: std::fmt::Debug> std::fmt::Debug for ManuallyTracked<T> {
326
+ fn fmt(&self, f: &mut Formatter<'_>) -> std::fmt::Result {
327
+ f.debug_struct("ManuallyTracked")
328
+ .field("item", &self.item)
329
+ .field("memsize_delta", &self.memsize_delta)
330
+ .finish()
331
+ }
332
+ }
@@ -0,0 +1,89 @@
1
+ //! Internal utility functions.
2
+
3
+ /// Check if the Ruby VM is globally available.
4
+ ///
5
+ /// Unfortunately there is no public API for this check, but there's a hidden
6
+ /// `ruby_current_vm_ptr` symbol in libruby 2.5 - 3.2 which we can use to
7
+ /// determine if the VM has been initialized, or shut down.
8
+ ///
9
+ /// # Notes
10
+ ///
11
+ /// Ruby 2.4 and below don't have a global VM pointer, so we can't check if it's
12
+ /// null. Ruby 2.4 is EOL, and support will be dropped soon anyway.
13
+ //
14
+ /// In Ruby 3.3, the global VM pointer is no longer exported, so there's no
15
+ /// simple way to check the global VM pointer, so instead we check if known
16
+ /// static value is non-zero.
17
+ ///
18
+ /// On Ruby < 3.3, we also need to check if the global VM pointer is null to
19
+ /// ensure the VM hasn't stopped, which makes the function name a bit of a
20
+ /// misnomer... but in actuality this function can only guarantee that the
21
+ /// VM is started, not that it's still running.
22
+ #[allow(dead_code)]
23
+ pub(crate) unsafe fn is_ruby_vm_started() -> bool {
24
+ #[cfg(ruby_engine = "mri")]
25
+ let ret = {
26
+ #[cfg(all(ruby_gt_2_4, ruby_lte_3_2))]
27
+ let ret = !crate::hidden::ruby_current_vm_ptr.is_null();
28
+
29
+ #[cfg(any(ruby_lte_2_4, ruby_gt_3_2))]
30
+ let ret = crate::rb_cBasicObject != 0;
31
+
32
+ ret
33
+ };
34
+
35
+ #[cfg(ruby_engine = "truffleruby")]
36
+ let ret = crate::rb_cBasicObject != 0;
37
+
38
+ ret
39
+ }
40
+
41
+ /// Macro for conditionally asserting type checks in Ruby, only active when RUBY_DEBUG is enabled.
42
+ /// This matches Ruby's behavior of only checking types in debug mode.
43
+ #[macro_export]
44
+ macro_rules! debug_ruby_assert_type {
45
+ ($obj:expr, $type:expr, $message:expr) => {
46
+ #[cfg(ruby_ruby_debug = "true")]
47
+ {
48
+ #[allow(clippy::macro_metavars_in_unsafe)]
49
+ unsafe {
50
+ assert!(
51
+ !$crate::SPECIAL_CONST_P($obj) && $crate::RB_BUILTIN_TYPE($obj) == $type,
52
+ $message
53
+ );
54
+ }
55
+ }
56
+ #[cfg(not(ruby_ruby_debug = "true"))]
57
+ {
58
+ let _ = ($obj, $type, $message); // Prevent unused variable warnings
59
+ }
60
+ };
61
+ }
62
+
63
+ #[cfg(test)]
64
+ mod tests {
65
+ use super::*;
66
+ use rusty_fork::rusty_fork_test;
67
+
68
+ rusty_fork_test! {
69
+ #[test]
70
+ fn test_is_ruby_vm_started() {
71
+ assert!(!unsafe { is_ruby_vm_started() });
72
+
73
+ #[cfg(windows)]
74
+ {
75
+ let mut argc = 0;
76
+ let mut argv: [*mut std::os::raw::c_char; 0] = [];
77
+ let mut argv = argv.as_mut_ptr();
78
+ unsafe { rb_sys::rb_w32_sysinit(&mut argc, &mut argv) };
79
+ }
80
+
81
+ match unsafe { crate::ruby_setup() } {
82
+ 0 => {}
83
+ code => panic!("Failed to setup Ruby (error code: {})", code),
84
+ };
85
+
86
+ assert!(unsafe { is_ruby_vm_started() });
87
+ }
88
+ }
89
+ }
@@ -0,0 +1,7 @@
1
+ #![allow(rustdoc::broken_intra_doc_links)]
2
+ //! Definitions for Ruby's special constants.
3
+ //!
4
+ //! Makes it easier to reference important Ruby constants, without havign to dig
5
+ //! around in bindgen's output.
6
+
7
+ pub use crate::ruby_value_type::*;