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
@@ -1,190 +0,0 @@
1
- Apache License
2
- Version 2.0, January 2004
3
- http://www.apache.org/licenses/
4
-
5
- TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6
-
7
- 1. Definitions.
8
-
9
- "License" shall mean the terms and conditions for use, reproduction,
10
- and distribution as defined by Sections 1 through 9 of this document.
11
-
12
- "Licensor" shall mean the copyright owner or entity authorized by
13
- the copyright owner that is granting the License.
14
-
15
- "Legal Entity" shall mean the union of the acting entity and all
16
- other entities that control, are controlled by, or are under common
17
- control with that entity. For the purposes of this definition,
18
- "control" means (i) the power, direct or indirect, to cause the
19
- direction or management of such entity, whether by contract or
20
- otherwise, or (ii) ownership of fifty percent (50%) or more of the
21
- outstanding shares, or (iii) beneficial ownership of such entity.
22
-
23
- "You" (or "Your") shall mean an individual or Legal Entity
24
- exercising permissions granted by this License.
25
-
26
- "Source" form shall mean the preferred form for making modifications,
27
- including but not limited to software source code, documentation
28
- source, and configuration files.
29
-
30
- "Object" form shall mean any form resulting from mechanical
31
- transformation or translation of a Source form, including but
32
- not limited to compiled object code, generated documentation,
33
- and conversions to other media types.
34
-
35
- "Work" shall mean the work of authorship, whether in Source or
36
- Object form, made available under the License, as indicated by a
37
- copyright notice that is included in or attached to the work
38
- (an example is provided in the Appendix below).
39
-
40
- "Derivative Works" shall mean any work, whether in Source or Object
41
- form, that is based on (or derived from) the Work and for which the
42
- editorial revisions, annotations, elaborations, or other modifications
43
- represent, as a whole, an original work of authorship. For the purposes
44
- of this License, Derivative Works shall not include works that remain
45
- separable from, or merely link (or bind by name) to the interfaces of,
46
- the Work and Derivative Works thereof.
47
-
48
- "Contribution" shall mean any work of authorship, including
49
- the original version of the Work and any modifications or additions
50
- to that Work or Derivative Works thereof, that is intentionally
51
- submitted to Licensor for inclusion in the Work by the copyright owner
52
- or by an individual or Legal Entity authorized to submit on behalf of
53
- the copyright owner. For the purposes of this definition, "submitted"
54
- means any form of electronic, verbal, or written communication sent
55
- to the Licensor or its representatives, including but not limited to
56
- communication on electronic mailing lists, source code control systems,
57
- and issue tracking systems that are managed by, or on behalf of, the
58
- Licensor for the purpose of discussing and improving the Work, but
59
- excluding communication that is conspicuously marked or otherwise
60
- designated in writing by the copyright owner as "Not a Contribution."
61
-
62
- "Contributor" shall mean Licensor and any individual or Legal Entity
63
- on behalf of whom a Contribution has been received by Licensor and
64
- subsequently incorporated within the Work.
65
-
66
- 2. Grant of Copyright License. Subject to the terms and conditions of
67
- this License, each Contributor hereby grants to You a perpetual,
68
- worldwide, non-exclusive, no-charge, royalty-free, irrevocable
69
- copyright license to reproduce, prepare Derivative Works of,
70
- publicly display, publicly perform, sublicense, and distribute the
71
- Work and such Derivative Works in Source or Object form.
72
-
73
- 3. Grant of Patent License. Subject to the terms and conditions of
74
- this License, each Contributor hereby grants to You a perpetual,
75
- worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76
- (except as stated in this section) patent license to make, have made,
77
- use, offer to sell, sell, import, and otherwise transfer the Work,
78
- where such license applies only to those patent claims licensable
79
- by such Contributor that are necessarily infringed by their
80
- Contribution(s) alone or by combination of their Contribution(s)
81
- with the Work to which such Contribution(s) was submitted. If You
82
- institute patent litigation against any entity (including a
83
- cross-claim or counterclaim in a lawsuit) alleging that the Work
84
- or a Contribution incorporated within the Work constitutes direct
85
- or contributory patent infringement, then any patent licenses
86
- granted to You under this License for that Work shall terminate
87
- as of the date such litigation is filed.
88
-
89
- 4. Redistribution. You may reproduce and distribute copies of the
90
- Work or Derivative Works thereof in any medium, with or without
91
- modifications, and in Source or Object form, provided that You
92
- meet the following conditions:
93
-
94
- (a) You must give any other recipients of the Work or
95
- Derivative Works a copy of this License; and
96
-
97
- (b) You must cause any modified files to carry prominent notices
98
- stating that You changed the files; and
99
-
100
- (c) You must retain, in the Source form of any Derivative Works
101
- that You distribute, all copyright, patent, trademark, and
102
- attribution notices from the Source form of the Work,
103
- excluding those notices that do not pertain to any part of
104
- the Derivative Works; and
105
-
106
- (d) If the Work includes a "NOTICE" text file as part of its
107
- distribution, then any Derivative Works that You distribute must
108
- include a readable copy of the attribution notices contained
109
- within such NOTICE file, excluding those notices that do not
110
- pertain to any part of the Derivative Works, in at least one
111
- of the following places: within a NOTICE text file distributed
112
- as part of the Derivative Works; within the Source form or
113
- documentation, if provided along with the Derivative Works; or,
114
- within a display generated by the Derivative Works, if and
115
- wherever such third-party notices normally appear. The contents
116
- of the NOTICE file are for informational purposes only and
117
- do not modify the License. You may add Your own attribution
118
- notices within Derivative Works that You distribute, alongside
119
- or as an addendum to the NOTICE text from the Work, provided
120
- that such additional attribution notices cannot be construed
121
- as modifying the License.
122
-
123
- You may add Your own copyright statement to Your modifications and
124
- may provide additional or different license terms and conditions
125
- for use, reproduction, or distribution of Your modifications, or
126
- for any such Derivative Works as a whole, provided Your use,
127
- reproduction, and distribution of the Work otherwise complies with
128
- the conditions stated in this License.
129
-
130
- 5. Submission of Contributions. Unless You explicitly state otherwise,
131
- any Contribution intentionally submitted for inclusion in the Work
132
- by You to the Licensor shall be under the terms and conditions of
133
- this License, without any additional terms or conditions.
134
- Notwithstanding the above, nothing herein shall supersede or modify
135
- the terms of any separate license agreement you may have executed
136
- with Licensor regarding such Contributions.
137
-
138
- 6. Trademarks. This License does not grant permission to use the trade
139
- names, trademarks, service marks, or product names of the Licensor,
140
- except as required for reasonable and customary use in describing the
141
- origin of the Work and reproducing the content of the NOTICE file.
142
-
143
- 7. Disclaimer of Warranty. Unless required by applicable law or
144
- agreed to in writing, Licensor provides the Work (and each
145
- Contributor provides its Contributions) on an "AS IS" BASIS,
146
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147
- implied, including, without limitation, any warranties or conditions
148
- of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149
- PARTICULAR PURPOSE. You are solely responsible for determining the
150
- appropriateness of using or redistributing the Work and assume any
151
- risks associated with Your exercise of permissions under this License.
152
-
153
- 8. Limitation of Liability. In no event and under no legal theory,
154
- whether in tort (including negligence), contract, or otherwise,
155
- unless required by applicable law (such as deliberate and grossly
156
- negligent acts) or agreed to in writing, shall any Contributor be
157
- liable to You for damages, including any direct, indirect, special,
158
- incidental, or consequential damages of any character arising as a
159
- result of this License or out of the use or inability to use the
160
- Work (including but not limited to damages for loss of goodwill,
161
- work stoppage, computer failure or malfunction, or any and all
162
- other commercial damages or losses), even if such Contributor
163
- has been advised of the possibility of such damages.
164
-
165
- 9. Accepting Warranty or Additional Liability. While redistributing
166
- the Work or Derivative Works thereof, You may choose to offer,
167
- and charge a fee for, acceptance of support, warranty, indemnity,
168
- or other liability obligations and/or rights consistent with this
169
- License. However, in accepting such obligations, You may act only
170
- on Your own behalf and on Your sole responsibility, not on behalf
171
- of any other Contributor, and only if You agree to indemnify,
172
- defend, and hold each Contributor harmless for any liability
173
- incurred by, or claims asserted against, such Contributor by reason
174
- of your accepting any such warranty or additional liability.
175
-
176
- END OF TERMS AND CONDITIONS
177
-
178
- Copyright 2021-2022 Ian Ker-Seymer
179
-
180
- Licensed under the Apache License, Version 2.0 (the "License");
181
- you may not use this file except in compliance with the License.
182
- You may obtain a copy of the License at
183
-
184
- http://www.apache.org/licenses/LICENSE-2.0
185
-
186
- Unless required by applicable law or agreed to in writing, software
187
- distributed under the License is distributed on an "AS IS" BASIS,
188
- WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
189
- See the License for the specific language governing permissions and
190
- limitations under the License.
@@ -1,21 +0,0 @@
1
- #!/bin/bash
2
-
3
- set -euo pipefail
4
- IFS=$'\n\t'
5
-
6
- if ! git diff-index --quiet HEAD --; then
7
- echo "There are git changes, cannot release"
8
- exit 1
9
- fi
10
-
11
- read -rp "What version would you like to release? (current $(grep version Cargo.toml)): " version
12
- read -rp "Are you sure you want to bump to v$version? <y/N> " prompt
13
-
14
- if [[ $prompt =~ [yY](es)* ]]; then
15
- sed -i '' "s/^version = .*/version = \"$version\"/g" Cargo.toml
16
- cargo build
17
- git add Cargo.lock Cargo.toml ../../Cargo.lock
18
- git commit -am "Bump to v$version"
19
- git tag "v$version"
20
- git push --atomic origin main "v$version"
21
- fi
@@ -1,108 +0,0 @@
1
- use rb_sys_build::{RbConfig, utils::is_mswin_or_mingw};
2
-
3
- use crate::version::Version;
4
-
5
- pub(crate) fn is_global_allocator_enabled(rb_config: &RbConfig) -> bool {
6
- let Some((major, minor)) = rb_config.major_minor() else {
7
- return false;
8
- };
9
- let current_version = Version::new(major, minor);
10
- let two_four = Version::new(2, 4);
11
- let is_enabled = is_env_variable_defined("CARGO_FEATURE_GLOBAL_ALLOCATOR");
12
-
13
- if current_version >= two_four {
14
- is_enabled
15
- } else {
16
- if is_enabled {
17
- eprintln!("WARN: The global allocator feature is only supported on Ruby 2.4+.");
18
- }
19
- false
20
- }
21
- }
22
-
23
- pub(crate) fn is_gem_enabled() -> bool {
24
- cfg!(rb_sys_gem)
25
- }
26
-
27
- pub(crate) fn is_no_link_ruby_enabled() -> bool {
28
- is_env_variable_defined("CARGO_FEATURE_NO_LINK_RUBY")
29
- }
30
-
31
- pub(crate) fn is_debug_build_enabled() -> bool {
32
- if is_linting() {
33
- return false;
34
- }
35
-
36
- println!("cargo:rerun-if-env-changed=RB_SYS_DEBUG_BUILD");
37
-
38
- is_env_variable_defined("RB_SYS_DEBUG_BUILD")
39
- }
40
-
41
- pub(crate) fn is_ruby_static_enabled(rbconfig: &RbConfig) -> bool {
42
- println!("cargo:rerun-if-env-changed=RUBY_STATIC");
43
-
44
- match std::env::var("RUBY_STATIC") {
45
- Ok(val) => val == "true" || val == "1",
46
- _ => {
47
- is_env_variable_defined("CARGO_FEATURE_RUBY_STATIC")
48
- || rbconfig.get("ENABLE_SHARED").map(|v| v == "no").unwrap_or(false)
49
- }
50
- }
51
- }
52
-
53
- pub(crate) fn is_link_ruby_enabled() -> bool {
54
- if is_linting() {
55
- return false;
56
- }
57
-
58
- if is_no_link_ruby_enabled() {
59
- false
60
- } else if is_mswin_or_mingw() {
61
- true
62
- } else if is_gem_enabled() {
63
- if is_env_variable_defined("CARGO_FEATURE_LINK_RUBY") {
64
- let msg = "
65
- The `gem` and `link-ruby` features are mutually exclusive on this
66
- platform, since the libruby symbols will be available at runtime.
67
-
68
- If you for some reason want to dangerously link libruby for your gem
69
- (*not recommended*), you can remove the `gem` feature and add this
70
- to your `Cargo.toml`:
71
-
72
- [dependencies.rb-sys]
73
- features = [\"link-ruby\"] # Living dangerously!
74
- "
75
- .split('\n')
76
- .map(|line| line.trim())
77
- .collect::<Vec<_>>()
78
- .join("\n");
79
-
80
- eprintln!("ERROR: {}", msg);
81
- std::process::exit(1);
82
- } else {
83
- false
84
- }
85
- } else {
86
- is_env_variable_defined("CARGO_FEATURE_LINK_RUBY")
87
- }
88
- }
89
-
90
- pub(crate) fn is_env_variable_defined(name: &str) -> bool {
91
- std::env::var(name).is_ok()
92
- }
93
-
94
- fn is_linting() -> bool {
95
- println!("cargo:rerun-if-env-changed=RUSTC_WRAPPER");
96
-
97
- let clippy = match std::env::var_os("CARGO_CFG_FEATURE") {
98
- Some(val) => val.to_str().unwrap_or("").contains("clippy"),
99
- _ => false,
100
- };
101
-
102
- let rust_analyzer = match std::env::var_os("RUSTC_WRAPPER") {
103
- Some(val) => val.to_str().unwrap_or("").contains("rust-analyzer"),
104
- _ => false,
105
- };
106
-
107
- clippy || rust_analyzer
108
- }
@@ -1,246 +0,0 @@
1
- mod features;
2
- #[cfg(feature = "stable-api")]
3
- mod stable_api_config;
4
- mod version;
5
-
6
- use features::*;
7
- use rb_sys_build::{RbConfig, RubyEngine, bindings};
8
- use std::io::Write;
9
- use std::{
10
- env,
11
- fs::{self, File},
12
- path::PathBuf,
13
- };
14
- use version::Version;
15
-
16
- const SUPPORTED_RUBY_VERSIONS: [Version; 10] = [
17
- Version::new(2, 3),
18
- Version::new(2, 4),
19
- Version::new(2, 5),
20
- Version::new(2, 6),
21
- Version::new(2, 7),
22
- Version::new(3, 0),
23
- Version::new(3, 1),
24
- Version::new(3, 2),
25
- Version::new(3, 3),
26
- Version::new(3, 4),
27
- ];
28
-
29
- fn main() {
30
- warn_deprecated_feature_flags();
31
-
32
- let mut rbconfig = RbConfig::current();
33
- let out_dir = PathBuf::from(env::var("OUT_DIR").unwrap());
34
- let cfg_capture_path = out_dir.join(format!("cfg-capture-{}", rbconfig.ruby_version_slug()));
35
- let mut cfg_capture_file = File::create(cfg_capture_path).expect("create cfg capture file");
36
-
37
- println!("cargo:rerun-if-env-changed=RUBY_ROOT");
38
- println!("cargo:rerun-if-env-changed=RUBY_VERSION");
39
- println!("cargo:rerun-if-env-changed=RUBY");
40
-
41
- for file in fs::read_dir("build").unwrap() {
42
- println!("cargo:rerun-if-changed={}", file.unwrap().path().display());
43
- }
44
-
45
- let bindings_path = bindings::generate(&rbconfig, is_ruby_static_enabled(&rbconfig), &mut cfg_capture_file)
46
- .expect("generate bindings");
47
- println!("Bindings generated at: {}", bindings_path.display());
48
- println!("cargo:rustc-env=RB_SYS_BINDINGS_PATH={}", bindings_path.display());
49
- export_cargo_cfg(&mut rbconfig, &mut cfg_capture_file);
50
-
51
- #[cfg(feature = "stable-api")]
52
- if let Err(e) = stable_api_config::setup(&rbconfig) {
53
- eprintln!("Failed to setup stable API: {}", e);
54
- std::process::exit(1);
55
- }
56
-
57
- if is_link_ruby_enabled() {
58
- link_libruby(&mut rbconfig);
59
- } else {
60
- add_libruby_to_blocklist(&mut rbconfig);
61
- enable_dynamic_lookup(&mut rbconfig);
62
- }
63
-
64
- expose_cargo_features(&mut cfg_capture_file);
65
- add_unsupported_link_args_to_blocklist(&mut rbconfig);
66
- rbconfig.print_cargo_args();
67
-
68
- if is_debug_build_enabled() {
69
- debug_and_exit(&mut rbconfig);
70
- }
71
- }
72
-
73
- macro_rules! cfg_capture {
74
- ($file:expr, $fmt:expr, $($arg:tt)*) => {
75
- println!($fmt, $($arg)*);
76
- writeln!($file, $fmt, $($arg)*).unwrap();
77
- };
78
- }
79
-
80
- macro_rules! cfg_capture_opt {
81
- ($file:expr, $fmt:expr, $opt:expr) => {
82
- if let Some(val) = $opt {
83
- cfg_capture!($file, $fmt, val);
84
- }
85
- };
86
- }
87
-
88
- fn add_unsupported_link_args_to_blocklist(rbconfig: &mut RbConfig) {
89
- rbconfig.blocklist_link_arg("-Wl,--compress-debug-sections=zlib");
90
- rbconfig.blocklist_link_arg("-s");
91
- }
92
-
93
- fn add_libruby_to_blocklist(rbconfig: &mut RbConfig) {
94
- rbconfig.blocklist_lib(&rbconfig.libruby_so_name());
95
- rbconfig.blocklist_lib(&rbconfig.libruby_static_name());
96
- }
97
-
98
- fn debug_and_exit(rbconfig: &mut RbConfig) {
99
- eprintln!("========== RbConfig\n");
100
- dbg!(rbconfig);
101
-
102
- eprintln!("========== Environment Variables\n");
103
- let env: std::collections::HashMap<_, _> = std::env::vars().collect();
104
- dbg!(env);
105
-
106
- eprintln!("==========\n");
107
- eprintln!("The \"RB_SYS_DEBUG_BUILD\" env var was set, aborting.");
108
- std::process::exit(1);
109
- }
110
-
111
- fn link_libruby(rbconfig: &mut RbConfig) {
112
- if is_link_ruby_enabled() {
113
- rbconfig.link_ruby(is_ruby_static_enabled(rbconfig));
114
- }
115
- }
116
-
117
- fn export_cargo_cfg(rbconfig: &mut RbConfig, cap: &mut File) {
118
- rustc_cfg(rbconfig, "ruby_major", "MAJOR");
119
- rustc_cfg(rbconfig, "ruby_minor", "MINOR");
120
- rustc_cfg(rbconfig, "ruby_teeny", "TEENY");
121
- rustc_cfg(rbconfig, "ruby_patchlevel", "PATCHLEVEL");
122
- rustc_cfg(rbconfig, "ruby_api_version", "RUBY_API_VERSION");
123
-
124
- println!("cargo:rustc-check-cfg=cfg(use_global_allocator)");
125
- if is_global_allocator_enabled(rbconfig) {
126
- println!("cargo:rustc-cfg=use_global_allocator");
127
- }
128
-
129
- println!("cargo:rustc-check-cfg=cfg(has_ruby_abi_version)");
130
- if rbconfig.has_ruby_dln_check_abi() {
131
- println!("cargo:rustc-cfg=has_ruby_abi_version");
132
- }
133
-
134
- println!("cargo:rustc-check-cfg=cfg(ruby_engine, values(\"mri\", \"truffleruby\"))");
135
- match rbconfig.ruby_engine() {
136
- RubyEngine::Mri => {
137
- println!("cargo:rustc-cfg=ruby_engine=\"mri\"");
138
- }
139
- RubyEngine::TruffleRuby => {
140
- println!("cargo:rustc-cfg=ruby_engine=\"truffleruby\"");
141
- }
142
- _ => panic!("unsupported ruby engine"),
143
- }
144
-
145
- let version = Version::current(rbconfig);
146
-
147
- for v in SUPPORTED_RUBY_VERSIONS.iter() {
148
- let v = v.to_owned();
149
-
150
- println!("cargo:rustc-check-cfg=cfg(ruby_lt_{}_{})", v.major(), v.minor());
151
- if version < v {
152
- println!(r#"cargo:rustc-cfg=ruby_lt_{}_{}"#, v.major(), v.minor());
153
- cfg_capture!(cap, r#"cargo:version_lt_{}_{}=true"#, v.major(), v.minor());
154
- } else {
155
- cfg_capture!(cap, r#"cargo:version_lt_{}_{}=false"#, v.major(), v.minor());
156
- }
157
-
158
- println!("cargo:rustc-check-cfg=cfg(ruby_lte_{}_{})", v.major(), v.minor());
159
- if version <= v {
160
- println!(r#"cargo:rustc-cfg=ruby_lte_{}_{}"#, v.major(), v.minor());
161
- cfg_capture!(cap, r#"cargo:version_lte_{}_{}=true"#, v.major(), v.minor());
162
- } else {
163
- cfg_capture!(cap, r#"cargo:version_lte_{}_{}=false"#, v.major(), v.minor());
164
- }
165
-
166
- println!("cargo:rustc-check-cfg=cfg(ruby_eq_{}_{})", v.major(), v.minor());
167
- if version == v {
168
- println!(r#"cargo:rustc-cfg=ruby_eq_{}_{}"#, v.major(), v.minor());
169
- cfg_capture!(cap, r#"cargo:version_eq_{}_{}=true"#, v.major(), v.minor());
170
- } else {
171
- cfg_capture!(cap, r#"cargo:version_eq_{}_{}=false"#, v.major(), v.minor());
172
- }
173
-
174
- println!("cargo:rustc-check-cfg=cfg(ruby_gte_{}_{})", v.major(), v.minor());
175
- if version >= v {
176
- println!(r#"cargo:rustc-cfg=ruby_gte_{}_{}"#, v.major(), v.minor());
177
- cfg_capture!(cap, r#"cargo:version_gte_{}_{}=true"#, v.major(), v.minor());
178
- } else {
179
- cfg_capture!(cap, r#"cargo:version_gte_{}_{}=false"#, v.major(), v.minor());
180
- }
181
-
182
- println!("cargo:rustc-check-cfg=cfg(ruby_gt_{}_{})", v.major(), v.minor());
183
- if version > v {
184
- println!(r#"cargo:rustc-cfg=ruby_gt_{}_{}"#, v.major(), v.minor());
185
- cfg_capture!(cap, r#"cargo:version_gt_{}_{}=true"#, v.major(), v.minor());
186
- } else {
187
- cfg_capture!(cap, r#"cargo:version_gt_{}_{}=false"#, v.major(), v.minor());
188
- }
189
- }
190
-
191
- cfg_capture_opt!(cap, "cargo:root={}", rbconfig.get("prefix"));
192
- cfg_capture_opt!(cap, "cargo:include={}", rbconfig.get("includedir"));
193
- cfg_capture_opt!(cap, "cargo:archinclude={}", rbconfig.get("archincludedir"));
194
- cfg_capture_opt!(cap, "cargo:libdir={}", rbconfig.get("libdir"));
195
- cfg_capture_opt!(cap, "cargo:version={}", rbconfig.get("ruby_version"));
196
- cfg_capture_opt!(cap, "cargo:major={}", rbconfig.get("MAJOR"));
197
- cfg_capture_opt!(cap, "cargo:minor={}", rbconfig.get("MINOR"));
198
- cfg_capture_opt!(cap, "cargo:teeny={}", rbconfig.get("TEENY"));
199
- cfg_capture_opt!(cap, "cargo:patchlevel={}", rbconfig.get("PATCHLEVEL"));
200
- cfg_capture!(cap, "cargo:engine={}", rbconfig.ruby_engine());
201
-
202
- for key in rbconfig.all_keys() {
203
- cfg_capture!(cap, "cargo:rbconfig_{}={}", key, rbconfig.get(key).expect("key"));
204
- }
205
-
206
- if is_ruby_static_enabled(rbconfig) {
207
- cfg_capture!(cap, "cargo:lib={}", rbconfig.libruby_static_name());
208
- cfg_capture!(cap, "cargo:ruby_static={}", "true");
209
- } else {
210
- cfg_capture!(cap, "cargo:lib={}", rbconfig.libruby_so_name());
211
- }
212
- }
213
-
214
- fn rustc_cfg(rbconfig: &RbConfig, name: &str, key: &str) {
215
- println!("cargo:rustc-check-cfg=cfg({})", name);
216
- if let Some(k) = rbconfig.get(key) {
217
- println!("cargo:rustc-cfg={}=\"{}\"", name, k);
218
- }
219
- }
220
-
221
- fn enable_dynamic_lookup(rbconfig: &mut RbConfig) {
222
- // See https://github.com/oxidize-rb/rb-sys/issues/88
223
- if cfg!(target_os = "macos") {
224
- rbconfig.push_dldflags("-Wl,-undefined,dynamic_lookup");
225
- } else if matches!(rbconfig.ruby_engine(), RubyEngine::TruffleRuby) {
226
- rbconfig.push_dldflags("-Wl,-z,lazy");
227
- }
228
- }
229
-
230
- fn expose_cargo_features(cap: &mut File) {
231
- for (key, val) in std::env::vars() {
232
- if !key.starts_with("CARGO_FEATURE_") {
233
- continue;
234
- }
235
-
236
- cfg_capture!(cap, "cargo:{}={}", key.to_lowercase(), val);
237
- }
238
- }
239
-
240
- fn warn_deprecated_feature_flags() {
241
- if cfg!(feature = "ruby-macros") {
242
- println!(
243
- "cargo:warning=The \"ruby-macros\" feature flag is deprecated and will be removed in a future release. Please use \"stable-api\" instead."
244
- );
245
- }
246
- }