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
@@ -1,186 +1,186 @@
1
- # frozen_string_literal: true
2
-
3
- require 'open3'
4
- require 'pathname'
5
- require 'json'
6
-
7
- module Kreuzberg
8
- # MCP (Model Context Protocol) server proxy
9
- #
10
- # Starts and manages the Kreuzberg MCP server for Claude Desktop integration.
11
- #
12
- # @example Start MCP server
13
- # server = Kreuzberg::MCPProxy.new
14
- # server.start
15
- #
16
- module MCPProxy
17
- Error = Class.new(Kreuzberg::Errors::Error)
18
- MissingBinaryError = Class.new(Error)
19
- ServerError = Class.new(Error)
20
-
21
- # MCP server instance
22
- class Server
23
- attr_reader :pid, :transport
24
-
25
- # Initialize MCP server
26
- #
27
- # @param transport [String] Transport method ("stdio" or "sse")
28
- #
29
- def initialize(transport: 'stdio')
30
- @transport = transport
31
- @pid = nil
32
- @stdin = nil
33
- @stdout = nil
34
- @stderr = nil
35
- end
36
-
37
- # Start the MCP server
38
- #
39
- # @return [Integer, nil] Process ID (for SSE) or nil (for stdio)
40
- #
41
- def start
42
- binary = MCPProxy.find_mcp_binary
43
-
44
- case @transport
45
- when 'stdio'
46
- start_stdio(binary)
47
- when 'sse'
48
- start_sse(binary)
49
- else
50
- raise ServerError, "Unknown transport: #{@transport}"
51
- end
52
- end
53
-
54
- # Stop the server
55
- #
56
- # @return [void]
57
- #
58
- def stop
59
- return unless @pid
60
-
61
- Process.kill('TERM', @pid)
62
- Process.wait(@pid)
63
- rescue Errno::ESRCH, Errno::ECHILD
64
- # Process already dead
65
- ensure
66
- @pid = nil
67
- close_pipes
68
- end
69
-
70
- # Send a message to the server (stdio only)
71
- #
72
- # @param message [Hash] JSON-RPC message
73
- # @return [void]
74
- #
75
- def send_message(message)
76
- raise ServerError, 'Can only send messages in stdio mode' unless @transport == 'stdio'
77
- raise ServerError, 'Server not started' unless @stdin
78
-
79
- @stdin.puts(JSON.generate(message))
80
- @stdin.flush
81
- end
82
-
83
- # Read a message from the server (stdio only)
84
- #
85
- # @return [Hash] JSON-RPC message
86
- #
87
- def read_message
88
- raise ServerError, 'Can only read messages in stdio mode' unless @transport == 'stdio'
89
- raise ServerError, 'Server not started' unless @stdout
90
-
91
- line = @stdout.gets
92
- JSON.parse(line) if line
93
- end
94
-
95
- # Check if server is running
96
- #
97
- # @return [Boolean]
98
- #
99
- def running?
100
- return false unless @pid
101
-
102
- Process.kill(0, @pid)
103
- true
104
- rescue Errno::ESRCH, Errno::EPERM
105
- false
106
- end
107
-
108
- private
109
-
110
- def start_stdio(binary)
111
- @stdin, @stdout, @stderr, wait_thr = Open3.popen3(binary.to_s, 'mcp', '--transport', 'stdio')
112
- @pid = wait_thr.pid
113
- nil
114
- end
115
-
116
- def start_sse(binary)
117
- @pid = spawn(
118
- binary.to_s,
119
- 'mcp',
120
- '--transport', 'sse',
121
- out: $stdout,
122
- err: $stderr
123
- )
124
- Process.detach(@pid)
125
- sleep 1 # Give server time to start
126
- @pid
127
- end
128
-
129
- def close_pipes
130
- @stdin&.close
131
- @stdout&.close
132
- @stderr&.close
133
- @stdin = @stdout = @stderr = nil
134
- end
135
- end
136
-
137
- module_function
138
-
139
- # Run MCP server with a block
140
- #
141
- # @param transport [String] Transport method
142
- # @yield [Server] Yields server instance
143
- # @return [Object] Block result
144
- #
145
- # @example
146
- # Kreuzberg::MCPProxy.run(transport: 'stdio') do |server|
147
- # server.send_message({ method: 'tools/list' })
148
- # response = server.read_message
149
- # end
150
- #
151
- def run(transport: 'stdio')
152
- server = Server.new(transport: transport)
153
- server.start
154
- yield server
155
- ensure
156
- server&.stop
157
- end
158
-
159
- # Find the MCP binary
160
- #
161
- # @return [Pathname] Path to binary
162
- # @raise [MissingBinaryError] If not found
163
- #
164
- def find_mcp_binary
165
- # MCP is served by kreuzberg CLI
166
- binary_name = Gem.win_platform? ? 'kreuzberg.exe' : 'kreuzberg'
167
- found = CLIProxy.search_paths(binary_name).find(&:file?)
168
- return found if found
169
-
170
- raise MissingBinaryError, missing_binary_message
171
- end
172
-
173
- # Error message for missing binary
174
- #
175
- # @return [String]
176
- #
177
- def missing_binary_message
178
- <<~MSG.strip
179
- kreuzberg binary not found for MCP server. Build it with:
180
- `cargo build --release --package kreuzberg-cli`
181
-
182
- Or ensure kreuzberg is installed with MCP support.
183
- MSG
184
- end
185
- end
186
- end
1
+ # frozen_string_literal: true
2
+
3
+ require 'open3'
4
+ require 'pathname'
5
+ require 'json'
6
+
7
+ module Kreuzberg
8
+ # MCP (Model Context Protocol) server proxy
9
+ #
10
+ # Starts and manages the Kreuzberg MCP server for Claude Desktop integration.
11
+ #
12
+ # @example Start MCP server
13
+ # server = Kreuzberg::MCPProxy.new
14
+ # server.start
15
+ #
16
+ module MCPProxy
17
+ Error = Class.new(Kreuzberg::Errors::Error)
18
+ MissingBinaryError = Class.new(Error)
19
+ ServerError = Class.new(Error)
20
+
21
+ # MCP server instance
22
+ class Server
23
+ attr_reader :pid, :transport
24
+
25
+ # Initialize MCP server
26
+ #
27
+ # @param transport [String] Transport method ("stdio" or "sse")
28
+ #
29
+ def initialize(transport: 'stdio')
30
+ @transport = transport
31
+ @pid = nil
32
+ @stdin = nil
33
+ @stdout = nil
34
+ @stderr = nil
35
+ end
36
+
37
+ # Start the MCP server
38
+ #
39
+ # @return [Integer, nil] Process ID (for SSE) or nil (for stdio)
40
+ #
41
+ def start
42
+ binary = MCPProxy.find_mcp_binary
43
+
44
+ case @transport
45
+ when 'stdio'
46
+ start_stdio(binary)
47
+ when 'sse'
48
+ start_sse(binary)
49
+ else
50
+ raise ServerError, "Unknown transport: #{@transport}"
51
+ end
52
+ end
53
+
54
+ # Stop the server
55
+ #
56
+ # @return [void]
57
+ #
58
+ def stop
59
+ return unless @pid
60
+
61
+ Process.kill('TERM', @pid)
62
+ Process.wait(@pid)
63
+ rescue Errno::ESRCH, Errno::ECHILD
64
+ # Process already dead
65
+ ensure
66
+ @pid = nil
67
+ close_pipes
68
+ end
69
+
70
+ # Send a message to the server (stdio only)
71
+ #
72
+ # @param message [Hash] JSON-RPC message
73
+ # @return [void]
74
+ #
75
+ def send_message(message)
76
+ raise ServerError, 'Can only send messages in stdio mode' unless @transport == 'stdio'
77
+ raise ServerError, 'Server not started' unless @stdin
78
+
79
+ @stdin.puts(JSON.generate(message))
80
+ @stdin.flush
81
+ end
82
+
83
+ # Read a message from the server (stdio only)
84
+ #
85
+ # @return [Hash] JSON-RPC message
86
+ #
87
+ def read_message
88
+ raise ServerError, 'Can only read messages in stdio mode' unless @transport == 'stdio'
89
+ raise ServerError, 'Server not started' unless @stdout
90
+
91
+ line = @stdout.gets
92
+ JSON.parse(line) if line
93
+ end
94
+
95
+ # Check if server is running
96
+ #
97
+ # @return [Boolean]
98
+ #
99
+ def running?
100
+ return false unless @pid
101
+
102
+ Process.kill(0, @pid)
103
+ true
104
+ rescue Errno::ESRCH, Errno::EPERM
105
+ false
106
+ end
107
+
108
+ private
109
+
110
+ def start_stdio(binary)
111
+ @stdin, @stdout, @stderr, wait_thr = Open3.popen3(binary.to_s, 'mcp', '--transport', 'stdio')
112
+ @pid = wait_thr.pid
113
+ nil
114
+ end
115
+
116
+ def start_sse(binary)
117
+ @pid = spawn(
118
+ binary.to_s,
119
+ 'mcp',
120
+ '--transport', 'sse',
121
+ out: $stdout,
122
+ err: $stderr
123
+ )
124
+ Process.detach(@pid)
125
+ sleep 1 # Give server time to start
126
+ @pid
127
+ end
128
+
129
+ def close_pipes
130
+ @stdin&.close
131
+ @stdout&.close
132
+ @stderr&.close
133
+ @stdin = @stdout = @stderr = nil
134
+ end
135
+ end
136
+
137
+ module_function
138
+
139
+ # Run MCP server with a block
140
+ #
141
+ # @param transport [String] Transport method
142
+ # @yield [Server] Yields server instance
143
+ # @return [Object] Block result
144
+ #
145
+ # @example
146
+ # Kreuzberg::MCPProxy.run(transport: 'stdio') do |server|
147
+ # server.send_message({ method: 'tools/list' })
148
+ # response = server.read_message
149
+ # end
150
+ #
151
+ def run(transport: 'stdio')
152
+ server = Server.new(transport: transport)
153
+ server.start
154
+ yield server
155
+ ensure
156
+ server&.stop
157
+ end
158
+
159
+ # Find the MCP binary
160
+ #
161
+ # @return [Pathname] Path to binary
162
+ # @raise [MissingBinaryError] If not found
163
+ #
164
+ def find_mcp_binary
165
+ # MCP is served by kreuzberg CLI
166
+ binary_name = Gem.win_platform? ? 'kreuzberg.exe' : 'kreuzberg'
167
+ found = CLIProxy.search_paths(binary_name).find(&:file?)
168
+ return found if found
169
+
170
+ raise MissingBinaryError, missing_binary_message
171
+ end
172
+
173
+ # Error message for missing binary
174
+ #
175
+ # @return [String]
176
+ #
177
+ def missing_binary_message
178
+ <<~MSG.strip
179
+ kreuzberg binary not found for MCP server. Build it with:
180
+ `cargo build --release --package kreuzberg-cli`
181
+
182
+ Or ensure kreuzberg is installed with MCP support.
183
+ MSG
184
+ end
185
+ end
186
+ end
@@ -1,113 +1,113 @@
1
- # frozen_string_literal: true
2
-
3
- module Kreuzberg
4
- # OCR backend protocol interface.
5
- #
6
- # This module defines the protocol that all Ruby OCR backends must implement
7
- # to be registered with the Rust core via the FFI bridge.
8
- #
9
- # OCR backends implement optical character recognition for images and scanned documents.
10
- # They are called when OCR is enabled in the extraction configuration.
11
- #
12
- # @example Implementing a custom OCR backend
13
- # class CustomOcrBackend
14
- # include Kreuzberg::OcrBackendProtocol
15
- #
16
- # def name
17
- # "custom-ocr"
18
- # end
19
- #
20
- # def process_image(image_bytes, config)
21
- # # Perform OCR on image_bytes
22
- # # This is a placeholder - integrate with a real OCR engine
23
- # text = my_ocr_engine.recognize(image_bytes, language: config["language"])
24
- # text
25
- # end
26
- # end
27
- #
28
- # backend = CustomOcrBackend.new
29
- # Kreuzberg.register_ocr_backend(backend.name, backend)
30
- #
31
- # # Use in extraction
32
- # result = Kreuzberg.extract_file_sync(
33
- # "scanned.pdf",
34
- # config: { ocr: { backend: "custom-ocr", language: "eng" } }
35
- # )
36
- #
37
- # @example Implementing an OCR backend with initialization
38
- # class ModelBasedOcr
39
- # include Kreuzberg::OcrBackendProtocol
40
- #
41
- # def initialize
42
- # @model = nil
43
- # end
44
- #
45
- # def name
46
- # "model-ocr"
47
- # end
48
- #
49
- # def process_image(image_bytes, config)
50
- # # Load model on first use (lazy initialization)
51
- # @model ||= load_model
52
- #
53
- # # Run OCR
54
- # @model.recognize(image_bytes, config)
55
- # end
56
- #
57
- # private
58
- #
59
- # def load_model
60
- # # Load ML model for OCR
61
- # MyOcrModel.load("path/to/model")
62
- # end
63
- # end
64
- #
65
- # Kreuzberg.register_ocr_backend("model-ocr", ModelBasedOcr.new)
66
- #
67
- module OcrBackendProtocol
68
- # Return the unique name of this OCR backend.
69
- #
70
- # This name is used in ExtractionConfig to select the backend:
71
- #
72
- # config = { ocr: { backend: "custom-ocr", language: "eng" } }
73
- #
74
- # The name should be a lowercase string with hyphens (e.g., "custom-ocr", "tesseract").
75
- #
76
- # @return [String] Unique backend identifier
77
- #
78
- # @example
79
- # def name
80
- # "custom-ocr"
81
- # end
82
- def name
83
- raise NotImplementedError, "#{self.class} must implement #name"
84
- end
85
-
86
- # Process image bytes and extract text via OCR.
87
- #
88
- # This method receives raw image data (PNG, JPEG, TIFF, etc.) and an OCR configuration
89
- # hash. It must return the extracted text as a string.
90
- #
91
- # The config hash contains OCR settings such as:
92
- # - "language" [String] - Language code (e.g., "eng", "deu", "fra")
93
- # - "backend" [String] - Backend name (same as #name)
94
- # - Additional backend-specific settings
95
- #
96
- # @param image_bytes [String] Binary image data (PNG, JPEG, TIFF, etc.)
97
- # @param config [Hash] OCR configuration with the following keys:
98
- # - "language" [String] - Language code for OCR (e.g., "eng", "deu")
99
- # - "backend" [String] - Backend name
100
- #
101
- # @return [String] Extracted text content
102
- #
103
- # @example
104
- # def process_image(image_bytes, config)
105
- # language = config["language"] || "eng"
106
- # text = my_ocr_engine.recognize(image_bytes, language: language)
107
- # text
108
- # end
109
- def process_image(image_bytes, config)
110
- raise NotImplementedError, "#{self.class} must implement #process_image(image_bytes, config)"
111
- end
112
- end
113
- end
1
+ # frozen_string_literal: true
2
+
3
+ module Kreuzberg
4
+ # OCR backend protocol interface.
5
+ #
6
+ # This module defines the protocol that all Ruby OCR backends must implement
7
+ # to be registered with the Rust core via the FFI bridge.
8
+ #
9
+ # OCR backends implement optical character recognition for images and scanned documents.
10
+ # They are called when OCR is enabled in the extraction configuration.
11
+ #
12
+ # @example Implementing a custom OCR backend
13
+ # class CustomOcrBackend
14
+ # include Kreuzberg::OcrBackendProtocol
15
+ #
16
+ # def name
17
+ # "custom-ocr"
18
+ # end
19
+ #
20
+ # def process_image(image_bytes, config)
21
+ # # Perform OCR on image_bytes
22
+ # # This is a placeholder - integrate with a real OCR engine
23
+ # text = my_ocr_engine.recognize(image_bytes, language: config["language"])
24
+ # text
25
+ # end
26
+ # end
27
+ #
28
+ # backend = CustomOcrBackend.new
29
+ # Kreuzberg.register_ocr_backend(backend.name, backend)
30
+ #
31
+ # # Use in extraction
32
+ # result = Kreuzberg.extract_file_sync(
33
+ # "scanned.pdf",
34
+ # config: { ocr: { backend: "custom-ocr", language: "eng" } }
35
+ # )
36
+ #
37
+ # @example Implementing an OCR backend with initialization
38
+ # class ModelBasedOcr
39
+ # include Kreuzberg::OcrBackendProtocol
40
+ #
41
+ # def initialize
42
+ # @model = nil
43
+ # end
44
+ #
45
+ # def name
46
+ # "model-ocr"
47
+ # end
48
+ #
49
+ # def process_image(image_bytes, config)
50
+ # # Load model on first use (lazy initialization)
51
+ # @model ||= load_model
52
+ #
53
+ # # Run OCR
54
+ # @model.recognize(image_bytes, config)
55
+ # end
56
+ #
57
+ # private
58
+ #
59
+ # def load_model
60
+ # # Load ML model for OCR
61
+ # MyOcrModel.load("path/to/model")
62
+ # end
63
+ # end
64
+ #
65
+ # Kreuzberg.register_ocr_backend("model-ocr", ModelBasedOcr.new)
66
+ #
67
+ module OcrBackendProtocol
68
+ # Return the unique name of this OCR backend.
69
+ #
70
+ # This name is used in ExtractionConfig to select the backend:
71
+ #
72
+ # config = { ocr: { backend: "custom-ocr", language: "eng" } }
73
+ #
74
+ # The name should be a lowercase string with hyphens (e.g., "custom-ocr", "tesseract").
75
+ #
76
+ # @return [String] Unique backend identifier
77
+ #
78
+ # @example
79
+ # def name
80
+ # "custom-ocr"
81
+ # end
82
+ def name
83
+ raise NotImplementedError, "#{self.class} must implement #name"
84
+ end
85
+
86
+ # Process image bytes and extract text via OCR.
87
+ #
88
+ # This method receives raw image data (PNG, JPEG, TIFF, etc.) and an OCR configuration
89
+ # hash. It must return the extracted text as a string.
90
+ #
91
+ # The config hash contains OCR settings such as:
92
+ # - "language" [String] - Language code (e.g., "eng", "deu", "fra")
93
+ # - "backend" [String] - Backend name (same as #name)
94
+ # - Additional backend-specific settings
95
+ #
96
+ # @param image_bytes [String] Binary image data (PNG, JPEG, TIFF, etc.)
97
+ # @param config [Hash] OCR configuration with the following keys:
98
+ # - "language" [String] - Language code for OCR (e.g., "eng", "deu")
99
+ # - "backend" [String] - Backend name
100
+ #
101
+ # @return [String] Extracted text content
102
+ #
103
+ # @example
104
+ # def process_image(image_bytes, config)
105
+ # language = config["language"] || "eng"
106
+ # text = my_ocr_engine.recognize(image_bytes, language: language)
107
+ # text
108
+ # end
109
+ def process_image(image_bytes, config)
110
+ raise NotImplementedError, "#{self.class} must implement #process_image(image_bytes, config)"
111
+ end
112
+ end
113
+ end