kreuzberg 4.0.0.pre.rc.6

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 (330) hide show
  1. checksums.yaml +7 -0
  2. data/.gitignore +14 -0
  3. data/.rspec +3 -0
  4. data/.rubocop.yaml +1 -0
  5. data/.rubocop.yml +538 -0
  6. data/Gemfile +8 -0
  7. data/Gemfile.lock +157 -0
  8. data/README.md +426 -0
  9. data/Rakefile +25 -0
  10. data/Steepfile +47 -0
  11. data/examples/async_patterns.rb +341 -0
  12. data/ext/kreuzberg_rb/extconf.rb +45 -0
  13. data/ext/kreuzberg_rb/native/Cargo.lock +6535 -0
  14. data/ext/kreuzberg_rb/native/Cargo.toml +44 -0
  15. data/ext/kreuzberg_rb/native/README.md +425 -0
  16. data/ext/kreuzberg_rb/native/build.rs +15 -0
  17. data/ext/kreuzberg_rb/native/include/ieeefp.h +11 -0
  18. data/ext/kreuzberg_rb/native/include/msvc_compat/strings.h +14 -0
  19. data/ext/kreuzberg_rb/native/include/strings.h +20 -0
  20. data/ext/kreuzberg_rb/native/include/unistd.h +47 -0
  21. data/ext/kreuzberg_rb/native/src/lib.rs +2998 -0
  22. data/extconf.rb +28 -0
  23. data/kreuzberg.gemspec +148 -0
  24. data/lib/kreuzberg/api_proxy.rb +142 -0
  25. data/lib/kreuzberg/cache_api.rb +46 -0
  26. data/lib/kreuzberg/cli.rb +55 -0
  27. data/lib/kreuzberg/cli_proxy.rb +127 -0
  28. data/lib/kreuzberg/config.rb +691 -0
  29. data/lib/kreuzberg/error_context.rb +32 -0
  30. data/lib/kreuzberg/errors.rb +118 -0
  31. data/lib/kreuzberg/extraction_api.rb +85 -0
  32. data/lib/kreuzberg/mcp_proxy.rb +186 -0
  33. data/lib/kreuzberg/ocr_backend_protocol.rb +113 -0
  34. data/lib/kreuzberg/post_processor_protocol.rb +86 -0
  35. data/lib/kreuzberg/result.rb +216 -0
  36. data/lib/kreuzberg/setup_lib_path.rb +80 -0
  37. data/lib/kreuzberg/validator_protocol.rb +89 -0
  38. data/lib/kreuzberg/version.rb +5 -0
  39. data/lib/kreuzberg.rb +103 -0
  40. data/sig/kreuzberg/internal.rbs +184 -0
  41. data/sig/kreuzberg.rbs +520 -0
  42. data/spec/binding/cache_spec.rb +227 -0
  43. data/spec/binding/cli_proxy_spec.rb +85 -0
  44. data/spec/binding/cli_spec.rb +55 -0
  45. data/spec/binding/config_spec.rb +345 -0
  46. data/spec/binding/config_validation_spec.rb +283 -0
  47. data/spec/binding/error_handling_spec.rb +213 -0
  48. data/spec/binding/errors_spec.rb +66 -0
  49. data/spec/binding/plugins/ocr_backend_spec.rb +307 -0
  50. data/spec/binding/plugins/postprocessor_spec.rb +269 -0
  51. data/spec/binding/plugins/validator_spec.rb +274 -0
  52. data/spec/fixtures/config.toml +39 -0
  53. data/spec/fixtures/config.yaml +41 -0
  54. data/spec/fixtures/invalid_config.toml +4 -0
  55. data/spec/smoke/package_spec.rb +178 -0
  56. data/spec/spec_helper.rb +42 -0
  57. data/vendor/kreuzberg/Cargo.toml +204 -0
  58. data/vendor/kreuzberg/README.md +175 -0
  59. data/vendor/kreuzberg/benches/otel_overhead.rs +48 -0
  60. data/vendor/kreuzberg/build.rs +474 -0
  61. data/vendor/kreuzberg/src/api/error.rs +81 -0
  62. data/vendor/kreuzberg/src/api/handlers.rs +199 -0
  63. data/vendor/kreuzberg/src/api/mod.rs +79 -0
  64. data/vendor/kreuzberg/src/api/server.rs +353 -0
  65. data/vendor/kreuzberg/src/api/types.rs +170 -0
  66. data/vendor/kreuzberg/src/cache/mod.rs +1167 -0
  67. data/vendor/kreuzberg/src/chunking/mod.rs +677 -0
  68. data/vendor/kreuzberg/src/core/batch_mode.rs +95 -0
  69. data/vendor/kreuzberg/src/core/config.rs +1032 -0
  70. data/vendor/kreuzberg/src/core/extractor.rs +1024 -0
  71. data/vendor/kreuzberg/src/core/io.rs +329 -0
  72. data/vendor/kreuzberg/src/core/mime.rs +605 -0
  73. data/vendor/kreuzberg/src/core/mod.rs +45 -0
  74. data/vendor/kreuzberg/src/core/pipeline.rs +984 -0
  75. data/vendor/kreuzberg/src/embeddings.rs +432 -0
  76. data/vendor/kreuzberg/src/error.rs +431 -0
  77. data/vendor/kreuzberg/src/extraction/archive.rs +954 -0
  78. data/vendor/kreuzberg/src/extraction/docx.rs +40 -0
  79. data/vendor/kreuzberg/src/extraction/email.rs +854 -0
  80. data/vendor/kreuzberg/src/extraction/excel.rs +688 -0
  81. data/vendor/kreuzberg/src/extraction/html.rs +553 -0
  82. data/vendor/kreuzberg/src/extraction/image.rs +368 -0
  83. data/vendor/kreuzberg/src/extraction/libreoffice.rs +563 -0
  84. data/vendor/kreuzberg/src/extraction/markdown.rs +213 -0
  85. data/vendor/kreuzberg/src/extraction/mod.rs +81 -0
  86. data/vendor/kreuzberg/src/extraction/office_metadata/app_properties.rs +398 -0
  87. data/vendor/kreuzberg/src/extraction/office_metadata/core_properties.rs +247 -0
  88. data/vendor/kreuzberg/src/extraction/office_metadata/custom_properties.rs +240 -0
  89. data/vendor/kreuzberg/src/extraction/office_metadata/mod.rs +130 -0
  90. data/vendor/kreuzberg/src/extraction/office_metadata/odt_properties.rs +287 -0
  91. data/vendor/kreuzberg/src/extraction/pptx.rs +3000 -0
  92. data/vendor/kreuzberg/src/extraction/structured.rs +490 -0
  93. data/vendor/kreuzberg/src/extraction/table.rs +328 -0
  94. data/vendor/kreuzberg/src/extraction/text.rs +269 -0
  95. data/vendor/kreuzberg/src/extraction/xml.rs +333 -0
  96. data/vendor/kreuzberg/src/extractors/archive.rs +446 -0
  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 -0
  100. data/vendor/kreuzberg/src/extractors/email.rs +143 -0
  101. data/vendor/kreuzberg/src/extractors/epub.rs +707 -0
  102. data/vendor/kreuzberg/src/extractors/excel.rs +343 -0
  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 -0
  106. data/vendor/kreuzberg/src/extractors/image.rs +198 -0
  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 -0
  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 -0
  116. data/vendor/kreuzberg/src/extractors/pptx.rs +248 -0
  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 -0
  122. data/vendor/kreuzberg/src/extractors/text.rs +260 -0
  123. data/vendor/kreuzberg/src/extractors/typst.rs +650 -0
  124. data/vendor/kreuzberg/src/extractors/xml.rs +135 -0
  125. data/vendor/kreuzberg/src/image/dpi.rs +164 -0
  126. data/vendor/kreuzberg/src/image/mod.rs +6 -0
  127. data/vendor/kreuzberg/src/image/preprocessing.rs +417 -0
  128. data/vendor/kreuzberg/src/image/resize.rs +89 -0
  129. data/vendor/kreuzberg/src/keywords/config.rs +154 -0
  130. data/vendor/kreuzberg/src/keywords/mod.rs +237 -0
  131. data/vendor/kreuzberg/src/keywords/processor.rs +267 -0
  132. data/vendor/kreuzberg/src/keywords/rake.rs +293 -0
  133. data/vendor/kreuzberg/src/keywords/types.rs +68 -0
  134. data/vendor/kreuzberg/src/keywords/yake.rs +163 -0
  135. data/vendor/kreuzberg/src/language_detection/mod.rs +942 -0
  136. data/vendor/kreuzberg/src/lib.rs +105 -0
  137. data/vendor/kreuzberg/src/mcp/mod.rs +32 -0
  138. data/vendor/kreuzberg/src/mcp/server.rs +1968 -0
  139. data/vendor/kreuzberg/src/ocr/cache.rs +469 -0
  140. data/vendor/kreuzberg/src/ocr/error.rs +37 -0
  141. data/vendor/kreuzberg/src/ocr/hocr.rs +216 -0
  142. data/vendor/kreuzberg/src/ocr/mod.rs +58 -0
  143. data/vendor/kreuzberg/src/ocr/processor.rs +863 -0
  144. data/vendor/kreuzberg/src/ocr/table/mod.rs +4 -0
  145. data/vendor/kreuzberg/src/ocr/table/tsv_parser.rs +144 -0
  146. data/vendor/kreuzberg/src/ocr/tesseract_backend.rs +450 -0
  147. data/vendor/kreuzberg/src/ocr/types.rs +393 -0
  148. data/vendor/kreuzberg/src/ocr/utils.rs +47 -0
  149. data/vendor/kreuzberg/src/ocr/validation.rs +206 -0
  150. data/vendor/kreuzberg/src/panic_context.rs +154 -0
  151. data/vendor/kreuzberg/src/pdf/error.rs +122 -0
  152. data/vendor/kreuzberg/src/pdf/images.rs +139 -0
  153. data/vendor/kreuzberg/src/pdf/metadata.rs +346 -0
  154. data/vendor/kreuzberg/src/pdf/mod.rs +50 -0
  155. data/vendor/kreuzberg/src/pdf/rendering.rs +369 -0
  156. data/vendor/kreuzberg/src/pdf/table.rs +393 -0
  157. data/vendor/kreuzberg/src/pdf/text.rs +158 -0
  158. data/vendor/kreuzberg/src/plugins/extractor.rs +1013 -0
  159. data/vendor/kreuzberg/src/plugins/mod.rs +209 -0
  160. data/vendor/kreuzberg/src/plugins/ocr.rs +620 -0
  161. data/vendor/kreuzberg/src/plugins/processor.rs +642 -0
  162. data/vendor/kreuzberg/src/plugins/registry.rs +1337 -0
  163. data/vendor/kreuzberg/src/plugins/traits.rs +258 -0
  164. data/vendor/kreuzberg/src/plugins/validator.rs +956 -0
  165. data/vendor/kreuzberg/src/stopwords/mod.rs +1470 -0
  166. data/vendor/kreuzberg/src/text/mod.rs +19 -0
  167. data/vendor/kreuzberg/src/text/quality.rs +697 -0
  168. data/vendor/kreuzberg/src/text/string_utils.rs +217 -0
  169. data/vendor/kreuzberg/src/text/token_reduction/cjk_utils.rs +164 -0
  170. data/vendor/kreuzberg/src/text/token_reduction/config.rs +100 -0
  171. data/vendor/kreuzberg/src/text/token_reduction/core.rs +796 -0
  172. data/vendor/kreuzberg/src/text/token_reduction/filters.rs +902 -0
  173. data/vendor/kreuzberg/src/text/token_reduction/mod.rs +160 -0
  174. data/vendor/kreuzberg/src/text/token_reduction/semantic.rs +619 -0
  175. data/vendor/kreuzberg/src/text/token_reduction/simd_text.rs +147 -0
  176. data/vendor/kreuzberg/src/types.rs +903 -0
  177. data/vendor/kreuzberg/src/utils/mod.rs +17 -0
  178. data/vendor/kreuzberg/src/utils/quality.rs +959 -0
  179. data/vendor/kreuzberg/src/utils/string_utils.rs +381 -0
  180. data/vendor/kreuzberg/stopwords/af_stopwords.json +53 -0
  181. data/vendor/kreuzberg/stopwords/ar_stopwords.json +482 -0
  182. data/vendor/kreuzberg/stopwords/bg_stopwords.json +261 -0
  183. data/vendor/kreuzberg/stopwords/bn_stopwords.json +400 -0
  184. data/vendor/kreuzberg/stopwords/br_stopwords.json +1205 -0
  185. data/vendor/kreuzberg/stopwords/ca_stopwords.json +280 -0
  186. data/vendor/kreuzberg/stopwords/cs_stopwords.json +425 -0
  187. data/vendor/kreuzberg/stopwords/da_stopwords.json +172 -0
  188. data/vendor/kreuzberg/stopwords/de_stopwords.json +622 -0
  189. data/vendor/kreuzberg/stopwords/el_stopwords.json +849 -0
  190. data/vendor/kreuzberg/stopwords/en_stopwords.json +1300 -0
  191. data/vendor/kreuzberg/stopwords/eo_stopwords.json +175 -0
  192. data/vendor/kreuzberg/stopwords/es_stopwords.json +734 -0
  193. data/vendor/kreuzberg/stopwords/et_stopwords.json +37 -0
  194. data/vendor/kreuzberg/stopwords/eu_stopwords.json +100 -0
  195. data/vendor/kreuzberg/stopwords/fa_stopwords.json +801 -0
  196. data/vendor/kreuzberg/stopwords/fi_stopwords.json +849 -0
  197. data/vendor/kreuzberg/stopwords/fr_stopwords.json +693 -0
  198. data/vendor/kreuzberg/stopwords/ga_stopwords.json +111 -0
  199. data/vendor/kreuzberg/stopwords/gl_stopwords.json +162 -0
  200. data/vendor/kreuzberg/stopwords/gu_stopwords.json +226 -0
  201. data/vendor/kreuzberg/stopwords/ha_stopwords.json +41 -0
  202. data/vendor/kreuzberg/stopwords/he_stopwords.json +196 -0
  203. data/vendor/kreuzberg/stopwords/hi_stopwords.json +227 -0
  204. data/vendor/kreuzberg/stopwords/hr_stopwords.json +181 -0
  205. data/vendor/kreuzberg/stopwords/hu_stopwords.json +791 -0
  206. data/vendor/kreuzberg/stopwords/hy_stopwords.json +47 -0
  207. data/vendor/kreuzberg/stopwords/id_stopwords.json +760 -0
  208. data/vendor/kreuzberg/stopwords/it_stopwords.json +634 -0
  209. data/vendor/kreuzberg/stopwords/ja_stopwords.json +136 -0
  210. data/vendor/kreuzberg/stopwords/kn_stopwords.json +84 -0
  211. data/vendor/kreuzberg/stopwords/ko_stopwords.json +681 -0
  212. data/vendor/kreuzberg/stopwords/ku_stopwords.json +64 -0
  213. data/vendor/kreuzberg/stopwords/la_stopwords.json +51 -0
  214. data/vendor/kreuzberg/stopwords/lt_stopwords.json +476 -0
  215. data/vendor/kreuzberg/stopwords/lv_stopwords.json +163 -0
  216. data/vendor/kreuzberg/stopwords/ml_stopwords.json +1 -0
  217. data/vendor/kreuzberg/stopwords/mr_stopwords.json +101 -0
  218. data/vendor/kreuzberg/stopwords/ms_stopwords.json +477 -0
  219. data/vendor/kreuzberg/stopwords/ne_stopwords.json +490 -0
  220. data/vendor/kreuzberg/stopwords/nl_stopwords.json +415 -0
  221. data/vendor/kreuzberg/stopwords/no_stopwords.json +223 -0
  222. data/vendor/kreuzberg/stopwords/pl_stopwords.json +331 -0
  223. data/vendor/kreuzberg/stopwords/pt_stopwords.json +562 -0
  224. data/vendor/kreuzberg/stopwords/ro_stopwords.json +436 -0
  225. data/vendor/kreuzberg/stopwords/ru_stopwords.json +561 -0
  226. data/vendor/kreuzberg/stopwords/si_stopwords.json +193 -0
  227. data/vendor/kreuzberg/stopwords/sk_stopwords.json +420 -0
  228. data/vendor/kreuzberg/stopwords/sl_stopwords.json +448 -0
  229. data/vendor/kreuzberg/stopwords/so_stopwords.json +32 -0
  230. data/vendor/kreuzberg/stopwords/st_stopwords.json +33 -0
  231. data/vendor/kreuzberg/stopwords/sv_stopwords.json +420 -0
  232. data/vendor/kreuzberg/stopwords/sw_stopwords.json +76 -0
  233. data/vendor/kreuzberg/stopwords/ta_stopwords.json +129 -0
  234. data/vendor/kreuzberg/stopwords/te_stopwords.json +54 -0
  235. data/vendor/kreuzberg/stopwords/th_stopwords.json +118 -0
  236. data/vendor/kreuzberg/stopwords/tl_stopwords.json +149 -0
  237. data/vendor/kreuzberg/stopwords/tr_stopwords.json +506 -0
  238. data/vendor/kreuzberg/stopwords/uk_stopwords.json +75 -0
  239. data/vendor/kreuzberg/stopwords/ur_stopwords.json +519 -0
  240. data/vendor/kreuzberg/stopwords/vi_stopwords.json +647 -0
  241. data/vendor/kreuzberg/stopwords/yo_stopwords.json +62 -0
  242. data/vendor/kreuzberg/stopwords/zh_stopwords.json +796 -0
  243. data/vendor/kreuzberg/stopwords/zu_stopwords.json +31 -0
  244. data/vendor/kreuzberg/tests/api_extract_multipart.rs +52 -0
  245. data/vendor/kreuzberg/tests/api_tests.rs +966 -0
  246. data/vendor/kreuzberg/tests/archive_integration.rs +543 -0
  247. data/vendor/kreuzberg/tests/batch_orchestration.rs +556 -0
  248. data/vendor/kreuzberg/tests/batch_processing.rs +316 -0
  249. data/vendor/kreuzberg/tests/bibtex_parity_test.rs +421 -0
  250. data/vendor/kreuzberg/tests/concurrency_stress.rs +525 -0
  251. data/vendor/kreuzberg/tests/config_features.rs +598 -0
  252. data/vendor/kreuzberg/tests/config_loading_tests.rs +415 -0
  253. data/vendor/kreuzberg/tests/core_integration.rs +510 -0
  254. data/vendor/kreuzberg/tests/csv_integration.rs +414 -0
  255. data/vendor/kreuzberg/tests/docbook_extractor_tests.rs +498 -0
  256. data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +122 -0
  257. data/vendor/kreuzberg/tests/docx_vs_pandoc_comparison.rs +370 -0
  258. data/vendor/kreuzberg/tests/email_integration.rs +325 -0
  259. data/vendor/kreuzberg/tests/epub_native_extractor_tests.rs +275 -0
  260. data/vendor/kreuzberg/tests/error_handling.rs +393 -0
  261. data/vendor/kreuzberg/tests/fictionbook_extractor_tests.rs +228 -0
  262. data/vendor/kreuzberg/tests/format_integration.rs +159 -0
  263. data/vendor/kreuzberg/tests/helpers/mod.rs +142 -0
  264. data/vendor/kreuzberg/tests/html_table_test.rs +551 -0
  265. data/vendor/kreuzberg/tests/image_integration.rs +253 -0
  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 -0
  270. data/vendor/kreuzberg/tests/keywords_quality.rs +509 -0
  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 -0
  274. data/vendor/kreuzberg/tests/ocr_configuration.rs +510 -0
  275. data/vendor/kreuzberg/tests/ocr_errors.rs +676 -0
  276. data/vendor/kreuzberg/tests/ocr_quality.rs +627 -0
  277. data/vendor/kreuzberg/tests/ocr_stress.rs +469 -0
  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 -0
  282. data/vendor/kreuzberg/tests/pipeline_integration.rs +1411 -0
  283. data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +771 -0
  284. data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +560 -0
  285. data/vendor/kreuzberg/tests/plugin_system.rs +921 -0
  286. data/vendor/kreuzberg/tests/plugin_validator_test.rs +783 -0
  287. data/vendor/kreuzberg/tests/registry_integration_tests.rs +586 -0
  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 -0
  291. data/vendor/kreuzberg/tests/stopwords_integration_test.rs +888 -0
  292. data/vendor/kreuzberg/tests/test_fastembed.rs +609 -0
  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 -0
  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 +536 -0
@@ -0,0 +1,368 @@
1
+ //! Image extraction functionality.
2
+ //!
3
+ //! This module provides functions for extracting metadata and EXIF data from images.
4
+
5
+ use crate::error::{KreuzbergError, Result};
6
+ use exif::{In, Reader, Tag};
7
+ use image::ImageReader;
8
+ use std::collections::HashMap;
9
+ use std::io::Cursor;
10
+
11
+ /// Image metadata extracted from an image file.
12
+ #[derive(Debug, Clone)]
13
+ pub struct ImageMetadata {
14
+ /// Image width in pixels
15
+ pub width: u32,
16
+ /// Image height in pixels
17
+ pub height: u32,
18
+ /// Image format (e.g., "PNG", "JPEG")
19
+ pub format: String,
20
+ /// EXIF data if available
21
+ pub exif_data: HashMap<String, String>,
22
+ }
23
+
24
+ /// Extract metadata from image bytes.
25
+ ///
26
+ /// Extracts dimensions, format, and EXIF data from the image.
27
+ pub fn extract_image_metadata(bytes: &[u8]) -> Result<ImageMetadata> {
28
+ let reader = ImageReader::new(Cursor::new(bytes))
29
+ .with_guessed_format()
30
+ .map_err(|e| KreuzbergError::parsing(format!("Failed to read image format: {}", e)))?;
31
+
32
+ let format = reader
33
+ .format()
34
+ .ok_or_else(|| KreuzbergError::parsing("Could not determine image format".to_string()))?;
35
+
36
+ let image = reader
37
+ .decode()
38
+ .map_err(|e| KreuzbergError::parsing(format!("Failed to decode image: {}", e)))?;
39
+
40
+ let width = image.width();
41
+ let height = image.height();
42
+ let format_str = format!("{:?}", format).to_uppercase();
43
+
44
+ let exif_data = extract_exif_data(bytes);
45
+
46
+ Ok(ImageMetadata {
47
+ width,
48
+ height,
49
+ format: format_str,
50
+ exif_data,
51
+ })
52
+ }
53
+
54
+ /// Extract EXIF data from image bytes.
55
+ ///
56
+ /// Returns a HashMap of EXIF tags and their values.
57
+ /// If EXIF data is not available or cannot be parsed, returns an empty HashMap.
58
+ fn extract_exif_data(bytes: &[u8]) -> HashMap<String, String> {
59
+ let mut exif_map = HashMap::new();
60
+
61
+ let exif_reader = match Reader::new().read_from_container(&mut Cursor::new(bytes)) {
62
+ Ok(reader) => reader,
63
+ Err(_) => return exif_map,
64
+ };
65
+
66
+ let common_tags = [
67
+ (Tag::Make, "Make"),
68
+ (Tag::Model, "Model"),
69
+ (Tag::DateTime, "DateTime"),
70
+ (Tag::DateTimeOriginal, "DateTimeOriginal"),
71
+ (Tag::DateTimeDigitized, "DateTimeDigitized"),
72
+ (Tag::Software, "Software"),
73
+ (Tag::Orientation, "Orientation"),
74
+ (Tag::XResolution, "XResolution"),
75
+ (Tag::YResolution, "YResolution"),
76
+ (Tag::ResolutionUnit, "ResolutionUnit"),
77
+ (Tag::ExposureTime, "ExposureTime"),
78
+ (Tag::FNumber, "FNumber"),
79
+ (Tag::PhotographicSensitivity, "ISO"),
80
+ (Tag::FocalLength, "FocalLength"),
81
+ (Tag::Flash, "Flash"),
82
+ (Tag::WhiteBalance, "WhiteBalance"),
83
+ (Tag::GPSLatitude, "GPSLatitude"),
84
+ (Tag::GPSLongitude, "GPSLongitude"),
85
+ (Tag::GPSAltitude, "GPSAltitude"),
86
+ ];
87
+
88
+ for (tag, field_name) in common_tags {
89
+ if let Some(field) = exif_reader.get_field(tag, In::PRIMARY) {
90
+ exif_map.insert(field_name.to_string(), field.display_value().to_string());
91
+ }
92
+ }
93
+
94
+ exif_map
95
+ }
96
+
97
+ #[cfg(test)]
98
+ mod tests {
99
+ use super::*;
100
+ use image::{ImageBuffer, ImageFormat, Rgb, RgbImage};
101
+ use std::io::Cursor;
102
+
103
+ fn create_test_image(width: u32, height: u32, format: ImageFormat) -> Vec<u8> {
104
+ let img: RgbImage = ImageBuffer::from_fn(width, height, |x, y| {
105
+ let r = ((x as f32 / width as f32) * 255.0) as u8;
106
+ let g = ((y as f32 / height as f32) * 255.0) as u8;
107
+ let b = 128;
108
+ Rgb([r, g, b])
109
+ });
110
+
111
+ let mut bytes: Vec<u8> = Vec::new();
112
+ let mut cursor = Cursor::new(&mut bytes);
113
+ img.write_to(&mut cursor, format).unwrap();
114
+ bytes
115
+ }
116
+
117
+ #[test]
118
+ fn test_extract_png_image_returns_correct_metadata() {
119
+ let bytes = create_test_image(100, 80, ImageFormat::Png);
120
+ let result = extract_image_metadata(&bytes);
121
+
122
+ assert!(result.is_ok());
123
+ let metadata = result.unwrap();
124
+ assert_eq!(metadata.width, 100);
125
+ assert_eq!(metadata.height, 80);
126
+ assert_eq!(metadata.format, "PNG");
127
+ }
128
+
129
+ #[test]
130
+ fn test_extract_jpeg_image_returns_correct_metadata() {
131
+ let bytes = create_test_image(200, 150, ImageFormat::Jpeg);
132
+ let result = extract_image_metadata(&bytes);
133
+
134
+ assert!(result.is_ok());
135
+ let metadata = result.unwrap();
136
+ assert_eq!(metadata.width, 200);
137
+ assert_eq!(metadata.height, 150);
138
+ assert_eq!(metadata.format, "JPEG");
139
+ }
140
+
141
+ #[test]
142
+ fn test_extract_webp_image_returns_correct_metadata() {
143
+ let bytes = create_test_image(120, 90, ImageFormat::WebP);
144
+ let result = extract_image_metadata(&bytes);
145
+
146
+ assert!(result.is_ok());
147
+ let metadata = result.unwrap();
148
+ assert_eq!(metadata.width, 120);
149
+ assert_eq!(metadata.height, 90);
150
+ assert_eq!(metadata.format, "WEBP");
151
+ }
152
+
153
+ #[test]
154
+ fn test_extract_bmp_image_returns_correct_metadata() {
155
+ let bytes = create_test_image(50, 50, ImageFormat::Bmp);
156
+ let result = extract_image_metadata(&bytes);
157
+
158
+ assert!(result.is_ok());
159
+ let metadata = result.unwrap();
160
+ assert_eq!(metadata.width, 50);
161
+ assert_eq!(metadata.height, 50);
162
+ assert_eq!(metadata.format, "BMP");
163
+ }
164
+
165
+ #[test]
166
+ fn test_extract_tiff_image_returns_correct_metadata() {
167
+ let bytes = create_test_image(180, 120, ImageFormat::Tiff);
168
+ let result = extract_image_metadata(&bytes);
169
+
170
+ assert!(result.is_ok());
171
+ let metadata = result.unwrap();
172
+ assert_eq!(metadata.width, 180);
173
+ assert_eq!(metadata.height, 120);
174
+ assert_eq!(metadata.format, "TIFF");
175
+ }
176
+
177
+ #[test]
178
+ fn test_extract_gif_image_returns_correct_metadata() {
179
+ let bytes = create_test_image(64, 64, ImageFormat::Gif);
180
+ let result = extract_image_metadata(&bytes);
181
+
182
+ assert!(result.is_ok());
183
+ let metadata = result.unwrap();
184
+ assert_eq!(metadata.width, 64);
185
+ assert_eq!(metadata.height, 64);
186
+ assert_eq!(metadata.format, "GIF");
187
+ }
188
+
189
+ #[test]
190
+ fn test_extract_image_extreme_aspect_ratio() {
191
+ let bytes = create_test_image(1000, 10, ImageFormat::Png);
192
+ let result = extract_image_metadata(&bytes);
193
+
194
+ assert!(result.is_ok());
195
+ let metadata = result.unwrap();
196
+ assert_eq!(metadata.width, 1000);
197
+ assert_eq!(metadata.height, 10);
198
+ assert!(metadata.width / metadata.height >= 100);
199
+ }
200
+
201
+ #[test]
202
+ fn test_extract_image_dimensions_correctly() {
203
+ let bytes = create_test_image(640, 480, ImageFormat::Png);
204
+ let result = extract_image_metadata(&bytes);
205
+
206
+ assert!(result.is_ok());
207
+ let metadata = result.unwrap();
208
+ assert_eq!(metadata.width, 640);
209
+ assert_eq!(metadata.height, 480);
210
+ }
211
+
212
+ #[test]
213
+ fn test_extract_image_format_correctly() {
214
+ let png_bytes = create_test_image(100, 100, ImageFormat::Png);
215
+ let jpeg_bytes = create_test_image(100, 100, ImageFormat::Jpeg);
216
+
217
+ let png_metadata = extract_image_metadata(&png_bytes).unwrap();
218
+ let jpeg_metadata = extract_image_metadata(&jpeg_bytes).unwrap();
219
+
220
+ assert_eq!(png_metadata.format, "PNG");
221
+ assert_eq!(jpeg_metadata.format, "JPEG");
222
+ }
223
+
224
+ #[test]
225
+ fn test_extract_image_without_exif_returns_empty_map() {
226
+ let bytes = create_test_image(100, 100, ImageFormat::Png);
227
+ let result = extract_image_metadata(&bytes);
228
+
229
+ assert!(result.is_ok());
230
+ let metadata = result.unwrap();
231
+ assert!(metadata.exif_data.is_empty());
232
+ }
233
+
234
+ #[test]
235
+ fn test_extract_exif_data_from_jpeg_with_exif() {
236
+ let bytes = create_test_image(100, 100, ImageFormat::Jpeg);
237
+ let result = extract_image_metadata(&bytes);
238
+
239
+ assert!(result.is_ok());
240
+ let metadata = result.unwrap();
241
+ assert_eq!(metadata.exif_data.len(), 0);
242
+ }
243
+
244
+ #[test]
245
+ fn test_extract_image_metadata_invalid_returns_error() {
246
+ let invalid_bytes = vec![0, 1, 2, 3, 4, 5];
247
+ let result = extract_image_metadata(&invalid_bytes);
248
+ assert!(result.is_err());
249
+ }
250
+
251
+ #[test]
252
+ fn test_extract_image_corrupted_data_returns_error() {
253
+ let mut bytes = create_test_image(100, 100, ImageFormat::Png);
254
+ if bytes.len() > 50 {
255
+ for byte in bytes.iter_mut().take(50).skip(20) {
256
+ *byte = 0xFF;
257
+ }
258
+ }
259
+
260
+ let result = extract_image_metadata(&bytes);
261
+ assert!(result.is_ok() || result.is_err());
262
+ }
263
+
264
+ #[test]
265
+ fn test_extract_image_empty_bytes_returns_error() {
266
+ let empty_bytes: Vec<u8> = Vec::new();
267
+ let result = extract_image_metadata(&empty_bytes);
268
+ assert!(result.is_err());
269
+ }
270
+
271
+ #[test]
272
+ fn test_extract_image_unsupported_format_returns_error() {
273
+ let unsupported_bytes = vec![0x00, 0x00, 0x00, 0x0C, 0x6A, 0x50, 0x20, 0x20, 0x0D, 0x0A, 0x87, 0x0A];
274
+ let result = extract_image_metadata(&unsupported_bytes);
275
+ assert!(result.is_err());
276
+ }
277
+
278
+ #[test]
279
+ fn test_extract_very_small_image_1x1_pixel() {
280
+ let bytes = create_test_image(1, 1, ImageFormat::Png);
281
+ let result = extract_image_metadata(&bytes);
282
+
283
+ assert!(result.is_ok());
284
+ let metadata = result.unwrap();
285
+ assert_eq!(metadata.width, 1);
286
+ assert_eq!(metadata.height, 1);
287
+ assert_eq!(metadata.format, "PNG");
288
+ }
289
+
290
+ #[test]
291
+ fn test_extract_large_image_dimensions() {
292
+ let bytes = create_test_image(2048, 1536, ImageFormat::Png);
293
+ let result = extract_image_metadata(&bytes);
294
+
295
+ assert!(result.is_ok());
296
+ let metadata = result.unwrap();
297
+ assert_eq!(metadata.width, 2048);
298
+ assert_eq!(metadata.height, 1536);
299
+ }
300
+
301
+ #[test]
302
+ fn test_extract_image_with_no_metadata_has_empty_exif() {
303
+ let bytes = create_test_image(100, 100, ImageFormat::Png);
304
+ let result = extract_image_metadata(&bytes);
305
+
306
+ assert!(result.is_ok());
307
+ let metadata = result.unwrap();
308
+ assert!(metadata.exif_data.is_empty());
309
+ }
310
+
311
+ #[test]
312
+ fn test_extract_exif_data_returns_empty_map_for_non_jpeg() {
313
+ let png_bytes = create_test_image(100, 100, ImageFormat::Png);
314
+ let exif_data = extract_exif_data(&png_bytes);
315
+ assert!(exif_data.is_empty());
316
+ }
317
+
318
+ #[test]
319
+ fn test_extract_rectangular_image_portrait_orientation() {
320
+ let bytes = create_test_image(400, 800, ImageFormat::Jpeg);
321
+ let result = extract_image_metadata(&bytes);
322
+
323
+ assert!(result.is_ok());
324
+ let metadata = result.unwrap();
325
+ assert_eq!(metadata.width, 400);
326
+ assert_eq!(metadata.height, 800);
327
+ assert!(metadata.height > metadata.width);
328
+ }
329
+
330
+ #[test]
331
+ fn test_extract_rectangular_image_landscape_orientation() {
332
+ let bytes = create_test_image(800, 400, ImageFormat::Png);
333
+ let result = extract_image_metadata(&bytes);
334
+
335
+ assert!(result.is_ok());
336
+ let metadata = result.unwrap();
337
+ assert_eq!(metadata.width, 800);
338
+ assert_eq!(metadata.height, 400);
339
+ assert!(metadata.width > metadata.height);
340
+ }
341
+
342
+ #[test]
343
+ fn test_extract_square_image_equal_dimensions() {
344
+ let bytes = create_test_image(512, 512, ImageFormat::Png);
345
+ let result = extract_image_metadata(&bytes);
346
+
347
+ assert!(result.is_ok());
348
+ let metadata = result.unwrap();
349
+ assert_eq!(metadata.width, 512);
350
+ assert_eq!(metadata.height, 512);
351
+ assert_eq!(metadata.width, metadata.height);
352
+ }
353
+
354
+ #[test]
355
+ fn test_extract_metadata_preserves_format_case() {
356
+ let png_bytes = create_test_image(100, 100, ImageFormat::Png);
357
+ let jpeg_bytes = create_test_image(100, 100, ImageFormat::Jpeg);
358
+ let webp_bytes = create_test_image(100, 100, ImageFormat::WebP);
359
+
360
+ let png_meta = extract_image_metadata(&png_bytes).unwrap();
361
+ let jpeg_meta = extract_image_metadata(&jpeg_bytes).unwrap();
362
+ let webp_meta = extract_image_metadata(&webp_bytes).unwrap();
363
+
364
+ assert_eq!(png_meta.format, "PNG");
365
+ assert_eq!(jpeg_meta.format, "JPEG");
366
+ assert_eq!(webp_meta.format, "WEBP");
367
+ }
368
+ }