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 +1,369 @@
1
+ use super::error::{PdfError, Result};
2
+ use image::DynamicImage;
3
+ use pdfium_render::prelude::*;
4
+ use serde::{Deserialize, Serialize};
5
+
6
+ const PDF_POINTS_PER_INCH: f64 = 72.0;
7
+
8
+ #[derive(Debug, Clone, Serialize, Deserialize)]
9
+ pub struct PageRenderOptions {
10
+ pub target_dpi: i32,
11
+ pub max_image_dimension: i32,
12
+ pub auto_adjust_dpi: bool,
13
+ pub min_dpi: i32,
14
+ pub max_dpi: i32,
15
+ }
16
+
17
+ impl Default for PageRenderOptions {
18
+ fn default() -> Self {
19
+ Self {
20
+ target_dpi: 300,
21
+ max_image_dimension: 65536,
22
+ auto_adjust_dpi: true,
23
+ min_dpi: 72,
24
+ max_dpi: 600,
25
+ }
26
+ }
27
+ }
28
+
29
+ pub struct PdfRenderer {
30
+ pdfium: Pdfium,
31
+ }
32
+
33
+ impl PdfRenderer {
34
+ pub fn new() -> Result<Self> {
35
+ let binding = Pdfium::bind_to_library(Pdfium::pdfium_platform_library_name_at_path("./"))
36
+ .or_else(|_| Pdfium::bind_to_system_library())
37
+ .map_err(|e| PdfError::RenderingFailed(format!("Failed to initialize Pdfium: {}", e)))?;
38
+
39
+ let pdfium = Pdfium::new(binding);
40
+ Ok(Self { pdfium })
41
+ }
42
+
43
+ pub fn render_page_to_image(
44
+ &self,
45
+ pdf_bytes: &[u8],
46
+ page_index: usize,
47
+ options: &PageRenderOptions,
48
+ ) -> Result<DynamicImage> {
49
+ self.render_page_to_image_with_password(pdf_bytes, page_index, options, None)
50
+ }
51
+
52
+ pub fn render_page_to_image_with_password(
53
+ &self,
54
+ pdf_bytes: &[u8],
55
+ page_index: usize,
56
+ options: &PageRenderOptions,
57
+ password: Option<&str>,
58
+ ) -> Result<DynamicImage> {
59
+ let document = self.pdfium.load_pdf_from_byte_slice(pdf_bytes, password).map_err(|e| {
60
+ let err_msg = e.to_string();
61
+ if (err_msg.contains("password") || err_msg.contains("Password")) && password.is_some() {
62
+ PdfError::InvalidPassword
63
+ } else if err_msg.contains("password") || err_msg.contains("Password") {
64
+ PdfError::PasswordRequired
65
+ } else {
66
+ PdfError::InvalidPdf(err_msg)
67
+ }
68
+ })?;
69
+
70
+ let page = document
71
+ .pages()
72
+ .get(page_index as u16)
73
+ .map_err(|_| PdfError::PageNotFound(page_index))?;
74
+
75
+ let width_points = page.width().value;
76
+ let height_points = page.height().value;
77
+
78
+ let dpi = if options.auto_adjust_dpi {
79
+ calculate_optimal_dpi(
80
+ width_points as f64,
81
+ height_points as f64,
82
+ options.target_dpi,
83
+ options.max_image_dimension,
84
+ options.min_dpi,
85
+ options.max_dpi,
86
+ )
87
+ } else {
88
+ options.target_dpi
89
+ };
90
+
91
+ let scale = dpi as f64 / PDF_POINTS_PER_INCH;
92
+
93
+ let config = PdfRenderConfig::new()
94
+ .set_target_width(((width_points * scale as f32) as i32).max(1))
95
+ .set_target_height(((height_points * scale as f32) as i32).max(1))
96
+ .rotate_if_landscape(PdfPageRenderRotation::None, false);
97
+
98
+ let bitmap = page
99
+ .render_with_config(&config)
100
+ .map_err(|e| PdfError::RenderingFailed(format!("Failed to render page: {}", e)))?;
101
+
102
+ let image = bitmap.as_image().into_rgb8();
103
+
104
+ Ok(DynamicImage::ImageRgb8(image))
105
+ }
106
+
107
+ pub fn render_all_pages(&self, pdf_bytes: &[u8], options: &PageRenderOptions) -> Result<Vec<DynamicImage>> {
108
+ self.render_all_pages_with_password(pdf_bytes, options, None)
109
+ }
110
+
111
+ pub fn render_all_pages_with_password(
112
+ &self,
113
+ pdf_bytes: &[u8],
114
+ options: &PageRenderOptions,
115
+ password: Option<&str>,
116
+ ) -> Result<Vec<DynamicImage>> {
117
+ let document = self.pdfium.load_pdf_from_byte_slice(pdf_bytes, password).map_err(|e| {
118
+ let err_msg = e.to_string();
119
+ if (err_msg.contains("password") || err_msg.contains("Password")) && password.is_some() {
120
+ PdfError::InvalidPassword
121
+ } else if err_msg.contains("password") || err_msg.contains("Password") {
122
+ PdfError::PasswordRequired
123
+ } else {
124
+ PdfError::InvalidPdf(err_msg)
125
+ }
126
+ })?;
127
+
128
+ let page_count = document.pages().len() as usize;
129
+ let mut images = Vec::with_capacity(page_count);
130
+
131
+ for page_index in 0..page_count {
132
+ let image = self.render_page_to_image_with_password(pdf_bytes, page_index, options, password)?;
133
+ images.push(image);
134
+ }
135
+
136
+ Ok(images)
137
+ }
138
+ }
139
+
140
+ pub fn render_page_to_image(pdf_bytes: &[u8], page_index: usize, options: &PageRenderOptions) -> Result<DynamicImage> {
141
+ let renderer = PdfRenderer::new()?;
142
+ renderer.render_page_to_image(pdf_bytes, page_index, options)
143
+ }
144
+
145
+ #[allow(clippy::too_many_arguments)]
146
+ fn calculate_optimal_dpi(
147
+ page_width: f64,
148
+ page_height: f64,
149
+ target_dpi: i32,
150
+ max_dimension: i32,
151
+ min_dpi: i32,
152
+ max_dpi: i32,
153
+ ) -> i32 {
154
+ let width_inches = page_width / PDF_POINTS_PER_INCH;
155
+ let height_inches = page_height / PDF_POINTS_PER_INCH;
156
+
157
+ let width_at_target = (width_inches * target_dpi as f64) as i32;
158
+ let height_at_target = (height_inches * target_dpi as f64) as i32;
159
+
160
+ if width_at_target <= max_dimension && height_at_target <= max_dimension {
161
+ return target_dpi.clamp(min_dpi, max_dpi);
162
+ }
163
+
164
+ let width_limited_dpi = (max_dimension as f64 / width_inches) as i32;
165
+ let height_limited_dpi = (max_dimension as f64 / height_inches) as i32;
166
+
167
+ width_limited_dpi.min(height_limited_dpi).clamp(min_dpi, max_dpi)
168
+ }
169
+
170
+ #[cfg(test)]
171
+ mod tests {
172
+ use super::*;
173
+
174
+ #[test]
175
+ fn test_renderer_creation() {
176
+ let result = PdfRenderer::new();
177
+ assert!(result.is_ok());
178
+ }
179
+
180
+ #[test]
181
+ fn test_render_invalid_pdf() {
182
+ let renderer = PdfRenderer::new().unwrap();
183
+ let options = PageRenderOptions::default();
184
+ let result = renderer.render_page_to_image(b"not a pdf", 0, &options);
185
+ assert!(result.is_err());
186
+ assert!(matches!(result.unwrap_err(), PdfError::InvalidPdf(_)));
187
+ }
188
+
189
+ #[test]
190
+ fn test_render_page_not_found() {
191
+ let renderer = PdfRenderer::new().unwrap();
192
+ let options = PageRenderOptions::default();
193
+ let minimal_pdf = b"%PDF-1.4\n%\xE2\xE3\xCF\xD3\n";
194
+ let result = renderer.render_page_to_image(minimal_pdf, 999, &options);
195
+
196
+ if let Err(err) = result {
197
+ assert!(matches!(
198
+ err,
199
+ PdfError::PageNotFound(_) | PdfError::InvalidPdf(_) | PdfError::PasswordRequired
200
+ ));
201
+ }
202
+ }
203
+
204
+ #[test]
205
+ fn test_calculate_optimal_dpi_within_limits() {
206
+ let dpi = calculate_optimal_dpi(612.0, 792.0, 300, 65536, 72, 600);
207
+ assert!((72..=600).contains(&dpi));
208
+ }
209
+
210
+ #[test]
211
+ fn test_calculate_optimal_dpi_oversized_page() {
212
+ let dpi = calculate_optimal_dpi(10000.0, 10000.0, 300, 4096, 72, 600);
213
+ assert!(dpi >= 72);
214
+ assert!(dpi < 300);
215
+ }
216
+
217
+ #[test]
218
+ fn test_calculate_optimal_dpi_min_clamp() {
219
+ let dpi = calculate_optimal_dpi(100.0, 100.0, 10, 65536, 72, 600);
220
+ assert_eq!(dpi, 72);
221
+ }
222
+
223
+ #[test]
224
+ fn test_calculate_optimal_dpi_max_clamp() {
225
+ let dpi = calculate_optimal_dpi(100.0, 100.0, 1000, 65536, 72, 600);
226
+ assert_eq!(dpi, 600);
227
+ }
228
+
229
+ #[test]
230
+ fn test_page_render_options_default() {
231
+ let options = PageRenderOptions::default();
232
+ assert_eq!(options.target_dpi, 300);
233
+ assert_eq!(options.max_image_dimension, 65536);
234
+ assert!(options.auto_adjust_dpi);
235
+ assert_eq!(options.min_dpi, 72);
236
+ assert_eq!(options.max_dpi, 600);
237
+ }
238
+
239
+ #[test]
240
+ fn test_renderer_size() {
241
+ assert!(size_of::<PdfRenderer>() > 0);
242
+ }
243
+
244
+ #[test]
245
+ fn test_render_all_pages_empty_pdf() {
246
+ let renderer = PdfRenderer::new().unwrap();
247
+ let options = PageRenderOptions::default();
248
+ let result = renderer.render_all_pages(b"not a pdf", &options);
249
+ assert!(result.is_err());
250
+ }
251
+
252
+ #[test]
253
+ fn test_render_page_with_password_none() {
254
+ let renderer = PdfRenderer::new().unwrap();
255
+ let options = PageRenderOptions::default();
256
+ let result = renderer.render_page_to_image_with_password(b"not a pdf", 0, &options, None);
257
+ assert!(result.is_err());
258
+ }
259
+
260
+ #[test]
261
+ fn test_render_all_pages_with_password_none() {
262
+ let renderer = PdfRenderer::new().unwrap();
263
+ let options = PageRenderOptions::default();
264
+ let result = renderer.render_all_pages_with_password(b"not a pdf", &options, None);
265
+ assert!(result.is_err());
266
+ }
267
+
268
+ #[test]
269
+ fn test_render_page_to_image_function() {
270
+ let options = PageRenderOptions::default();
271
+ let result = render_page_to_image(b"not a pdf", 0, &options);
272
+ assert!(result.is_err());
273
+ }
274
+
275
+ #[test]
276
+ fn test_calculate_optimal_dpi_tall_page() {
277
+ let dpi = calculate_optimal_dpi(612.0, 10000.0, 300, 4096, 72, 600);
278
+ assert!((72..=600).contains(&dpi));
279
+ }
280
+
281
+ #[test]
282
+ fn test_calculate_optimal_dpi_wide_page() {
283
+ let dpi = calculate_optimal_dpi(10000.0, 612.0, 300, 4096, 72, 600);
284
+ assert!((72..=600).contains(&dpi));
285
+ }
286
+
287
+ #[test]
288
+ fn test_calculate_optimal_dpi_square_page() {
289
+ let dpi = calculate_optimal_dpi(1000.0, 1000.0, 300, 65536, 72, 600);
290
+ assert!((72..=600).contains(&dpi));
291
+ }
292
+
293
+ #[test]
294
+ fn test_calculate_optimal_dpi_tiny_page() {
295
+ let dpi = calculate_optimal_dpi(72.0, 72.0, 300, 65536, 72, 600);
296
+ assert_eq!(dpi, 300);
297
+ }
298
+
299
+ #[test]
300
+ fn test_calculate_optimal_dpi_target_equals_max() {
301
+ let dpi = calculate_optimal_dpi(612.0, 792.0, 600, 65536, 72, 600);
302
+ assert_eq!(dpi, 600);
303
+ }
304
+
305
+ #[test]
306
+ fn test_calculate_optimal_dpi_target_equals_min() {
307
+ let dpi = calculate_optimal_dpi(612.0, 792.0, 72, 65536, 72, 600);
308
+ assert_eq!(dpi, 72);
309
+ }
310
+
311
+ #[test]
312
+ fn test_calculate_optimal_dpi_exactly_at_limit() {
313
+ let page_size = 65536.0 / 300.0 * PDF_POINTS_PER_INCH;
314
+ let dpi = calculate_optimal_dpi(page_size, page_size, 300, 65536, 72, 600);
315
+ assert!((72..=600).contains(&dpi));
316
+ }
317
+
318
+ #[test]
319
+ fn test_page_render_options_custom() {
320
+ let options = PageRenderOptions {
321
+ target_dpi: 150,
322
+ max_image_dimension: 8192,
323
+ auto_adjust_dpi: false,
324
+ min_dpi: 50,
325
+ max_dpi: 400,
326
+ };
327
+
328
+ assert_eq!(options.target_dpi, 150);
329
+ assert_eq!(options.max_image_dimension, 8192);
330
+ assert!(!options.auto_adjust_dpi);
331
+ assert_eq!(options.min_dpi, 50);
332
+ assert_eq!(options.max_dpi, 400);
333
+ }
334
+
335
+ #[test]
336
+ fn test_page_render_options_clone() {
337
+ let options1 = PageRenderOptions::default();
338
+ let options2 = options1.clone();
339
+
340
+ assert_eq!(options1.target_dpi, options2.target_dpi);
341
+ assert_eq!(options1.max_image_dimension, options2.max_image_dimension);
342
+ assert_eq!(options1.auto_adjust_dpi, options2.auto_adjust_dpi);
343
+ }
344
+
345
+ #[test]
346
+ fn test_pdf_points_per_inch_constant() {
347
+ assert_eq!(PDF_POINTS_PER_INCH, 72.0);
348
+ }
349
+
350
+ #[test]
351
+ fn test_render_empty_bytes() {
352
+ let renderer = PdfRenderer::new().unwrap();
353
+ let options = PageRenderOptions::default();
354
+ let result = renderer.render_page_to_image(&[], 0, &options);
355
+ assert!(result.is_err());
356
+ }
357
+
358
+ #[test]
359
+ fn test_calculate_optimal_dpi_zero_target() {
360
+ let dpi = calculate_optimal_dpi(612.0, 792.0, 0, 65536, 72, 600);
361
+ assert_eq!(dpi, 72);
362
+ }
363
+
364
+ #[test]
365
+ fn test_calculate_optimal_dpi_negative_target() {
366
+ let dpi = calculate_optimal_dpi(612.0, 792.0, -100, 65536, 72, 600);
367
+ assert_eq!(dpi, 72);
368
+ }
369
+ }