kreuzberg 4.0.0.pre.rc.8 → 4.0.0.pre.rc.13

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 (370) hide show
  1. checksums.yaml +4 -4
  2. data/.gitignore +14 -14
  3. data/.rspec +3 -3
  4. data/.rubocop.yaml +1 -1
  5. data/.rubocop.yml +538 -538
  6. data/Gemfile +8 -8
  7. data/Gemfile.lock +4 -104
  8. data/README.md +454 -432
  9. data/Rakefile +25 -25
  10. data/Steepfile +47 -47
  11. data/examples/async_patterns.rb +341 -341
  12. data/ext/kreuzberg_rb/extconf.rb +45 -45
  13. data/ext/kreuzberg_rb/native/.cargo/config.toml +2 -2
  14. data/ext/kreuzberg_rb/native/Cargo.lock +6941 -6721
  15. data/ext/kreuzberg_rb/native/Cargo.toml +54 -54
  16. data/ext/kreuzberg_rb/native/README.md +425 -425
  17. data/ext/kreuzberg_rb/native/build.rs +15 -15
  18. data/ext/kreuzberg_rb/native/include/ieeefp.h +11 -11
  19. data/ext/kreuzberg_rb/native/include/msvc_compat/strings.h +14 -14
  20. data/ext/kreuzberg_rb/native/include/strings.h +20 -20
  21. data/ext/kreuzberg_rb/native/include/unistd.h +47 -47
  22. data/ext/kreuzberg_rb/native/src/lib.rs +3158 -3135
  23. data/extconf.rb +28 -28
  24. data/kreuzberg.gemspec +214 -182
  25. data/lib/kreuzberg/api_proxy.rb +142 -142
  26. data/lib/kreuzberg/cache_api.rb +81 -46
  27. data/lib/kreuzberg/cli.rb +55 -55
  28. data/lib/kreuzberg/cli_proxy.rb +127 -127
  29. data/lib/kreuzberg/config.rb +724 -724
  30. data/lib/kreuzberg/error_context.rb +80 -32
  31. data/lib/kreuzberg/errors.rb +118 -118
  32. data/lib/kreuzberg/extraction_api.rb +340 -85
  33. data/lib/kreuzberg/mcp_proxy.rb +186 -186
  34. data/lib/kreuzberg/ocr_backend_protocol.rb +113 -113
  35. data/lib/kreuzberg/post_processor_protocol.rb +86 -86
  36. data/lib/kreuzberg/result.rb +279 -279
  37. data/lib/kreuzberg/setup_lib_path.rb +80 -80
  38. data/lib/kreuzberg/validator_protocol.rb +89 -89
  39. data/lib/kreuzberg/version.rb +5 -5
  40. data/lib/kreuzberg.rb +109 -103
  41. data/lib/pdfium.dll +0 -0
  42. data/sig/kreuzberg/internal.rbs +184 -184
  43. data/sig/kreuzberg.rbs +546 -537
  44. data/spec/binding/cache_spec.rb +227 -227
  45. data/spec/binding/cli_proxy_spec.rb +85 -85
  46. data/spec/binding/cli_spec.rb +55 -55
  47. data/spec/binding/config_spec.rb +345 -345
  48. data/spec/binding/config_validation_spec.rb +283 -283
  49. data/spec/binding/error_handling_spec.rb +213 -213
  50. data/spec/binding/errors_spec.rb +66 -66
  51. data/spec/binding/plugins/ocr_backend_spec.rb +307 -307
  52. data/spec/binding/plugins/postprocessor_spec.rb +269 -269
  53. data/spec/binding/plugins/validator_spec.rb +274 -274
  54. data/spec/fixtures/config.toml +39 -39
  55. data/spec/fixtures/config.yaml +41 -41
  56. data/spec/fixtures/invalid_config.toml +4 -4
  57. data/spec/smoke/package_spec.rb +178 -178
  58. data/spec/spec_helper.rb +42 -42
  59. data/vendor/Cargo.toml +45 -0
  60. data/vendor/kreuzberg/Cargo.toml +61 -38
  61. data/vendor/kreuzberg/README.md +230 -221
  62. data/vendor/kreuzberg/benches/otel_overhead.rs +48 -48
  63. data/vendor/kreuzberg/build.rs +843 -891
  64. data/vendor/kreuzberg/src/api/error.rs +81 -81
  65. data/vendor/kreuzberg/src/api/handlers.rs +199 -199
  66. data/vendor/kreuzberg/src/api/mod.rs +79 -79
  67. data/vendor/kreuzberg/src/api/server.rs +353 -353
  68. data/vendor/kreuzberg/src/api/types.rs +170 -170
  69. data/vendor/kreuzberg/src/cache/mod.rs +1167 -1167
  70. data/vendor/kreuzberg/src/chunking/mod.rs +1877 -1877
  71. data/vendor/kreuzberg/src/chunking/processor.rs +220 -220
  72. data/vendor/kreuzberg/src/core/batch_mode.rs +95 -95
  73. data/vendor/kreuzberg/src/core/config.rs +1080 -1080
  74. data/vendor/kreuzberg/src/core/extractor.rs +1156 -1156
  75. data/vendor/kreuzberg/src/core/io.rs +329 -329
  76. data/vendor/kreuzberg/src/core/mime.rs +605 -605
  77. data/vendor/kreuzberg/src/core/mod.rs +47 -47
  78. data/vendor/kreuzberg/src/core/pipeline.rs +1184 -1171
  79. data/vendor/kreuzberg/src/embeddings.rs +500 -432
  80. data/vendor/kreuzberg/src/error.rs +431 -431
  81. data/vendor/kreuzberg/src/extraction/archive.rs +954 -954
  82. data/vendor/kreuzberg/src/extraction/docx.rs +398 -398
  83. data/vendor/kreuzberg/src/extraction/email.rs +854 -854
  84. data/vendor/kreuzberg/src/extraction/excel.rs +688 -688
  85. data/vendor/kreuzberg/src/extraction/html.rs +601 -569
  86. data/vendor/kreuzberg/src/extraction/image.rs +491 -491
  87. data/vendor/kreuzberg/src/extraction/libreoffice.rs +574 -562
  88. data/vendor/kreuzberg/src/extraction/markdown.rs +213 -213
  89. data/vendor/kreuzberg/src/extraction/mod.rs +81 -81
  90. data/vendor/kreuzberg/src/extraction/office_metadata/app_properties.rs +398 -398
  91. data/vendor/kreuzberg/src/extraction/office_metadata/core_properties.rs +247 -247
  92. data/vendor/kreuzberg/src/extraction/office_metadata/custom_properties.rs +240 -240
  93. data/vendor/kreuzberg/src/extraction/office_metadata/mod.rs +130 -130
  94. data/vendor/kreuzberg/src/extraction/office_metadata/odt_properties.rs +284 -284
  95. data/vendor/kreuzberg/src/extraction/pptx.rs +3100 -3100
  96. data/vendor/kreuzberg/src/extraction/structured.rs +490 -490
  97. data/vendor/kreuzberg/src/extraction/table.rs +328 -328
  98. data/vendor/kreuzberg/src/extraction/text.rs +269 -269
  99. data/vendor/kreuzberg/src/extraction/xml.rs +333 -333
  100. data/vendor/kreuzberg/src/extractors/archive.rs +447 -447
  101. data/vendor/kreuzberg/src/extractors/bibtex.rs +470 -470
  102. data/vendor/kreuzberg/src/extractors/docbook.rs +504 -504
  103. data/vendor/kreuzberg/src/extractors/docx.rs +400 -400
  104. data/vendor/kreuzberg/src/extractors/email.rs +157 -157
  105. data/vendor/kreuzberg/src/extractors/epub.rs +708 -708
  106. data/vendor/kreuzberg/src/extractors/excel.rs +345 -345
  107. data/vendor/kreuzberg/src/extractors/fictionbook.rs +492 -492
  108. data/vendor/kreuzberg/src/extractors/html.rs +407 -407
  109. data/vendor/kreuzberg/src/extractors/image.rs +219 -219
  110. data/vendor/kreuzberg/src/extractors/jats.rs +1054 -1054
  111. data/vendor/kreuzberg/src/extractors/jupyter.rs +368 -368
  112. data/vendor/kreuzberg/src/extractors/latex.rs +653 -653
  113. data/vendor/kreuzberg/src/extractors/markdown.rs +701 -701
  114. data/vendor/kreuzberg/src/extractors/mod.rs +429 -429
  115. data/vendor/kreuzberg/src/extractors/odt.rs +628 -628
  116. data/vendor/kreuzberg/src/extractors/opml.rs +635 -635
  117. data/vendor/kreuzberg/src/extractors/orgmode.rs +529 -529
  118. data/vendor/kreuzberg/src/extractors/pdf.rs +749 -673
  119. data/vendor/kreuzberg/src/extractors/pptx.rs +267 -267
  120. data/vendor/kreuzberg/src/extractors/rst.rs +577 -577
  121. data/vendor/kreuzberg/src/extractors/rtf.rs +809 -809
  122. data/vendor/kreuzberg/src/extractors/security.rs +484 -484
  123. data/vendor/kreuzberg/src/extractors/security_tests.rs +367 -367
  124. data/vendor/kreuzberg/src/extractors/structured.rs +142 -142
  125. data/vendor/kreuzberg/src/extractors/text.rs +265 -265
  126. data/vendor/kreuzberg/src/extractors/typst.rs +651 -651
  127. data/vendor/kreuzberg/src/extractors/xml.rs +147 -147
  128. data/vendor/kreuzberg/src/image/dpi.rs +164 -164
  129. data/vendor/kreuzberg/src/image/mod.rs +6 -6
  130. data/vendor/kreuzberg/src/image/preprocessing.rs +417 -417
  131. data/vendor/kreuzberg/src/image/resize.rs +89 -89
  132. data/vendor/kreuzberg/src/keywords/config.rs +154 -154
  133. data/vendor/kreuzberg/src/keywords/mod.rs +237 -237
  134. data/vendor/kreuzberg/src/keywords/processor.rs +275 -275
  135. data/vendor/kreuzberg/src/keywords/rake.rs +293 -293
  136. data/vendor/kreuzberg/src/keywords/types.rs +68 -68
  137. data/vendor/kreuzberg/src/keywords/yake.rs +163 -163
  138. data/vendor/kreuzberg/src/language_detection/mod.rs +985 -985
  139. data/vendor/kreuzberg/src/language_detection/processor.rs +219 -219
  140. data/vendor/kreuzberg/src/lib.rs +113 -113
  141. data/vendor/kreuzberg/src/mcp/mod.rs +35 -35
  142. data/vendor/kreuzberg/src/mcp/server.rs +2076 -2076
  143. data/vendor/kreuzberg/src/ocr/cache.rs +469 -469
  144. data/vendor/kreuzberg/src/ocr/error.rs +37 -37
  145. data/vendor/kreuzberg/src/ocr/hocr.rs +216 -216
  146. data/vendor/kreuzberg/src/ocr/mod.rs +58 -58
  147. data/vendor/kreuzberg/src/ocr/processor.rs +863 -863
  148. data/vendor/kreuzberg/src/ocr/table/mod.rs +4 -4
  149. data/vendor/kreuzberg/src/ocr/table/tsv_parser.rs +144 -144
  150. data/vendor/kreuzberg/src/ocr/tesseract_backend.rs +452 -452
  151. data/vendor/kreuzberg/src/ocr/types.rs +393 -393
  152. data/vendor/kreuzberg/src/ocr/utils.rs +47 -47
  153. data/vendor/kreuzberg/src/ocr/validation.rs +206 -206
  154. data/vendor/kreuzberg/src/panic_context.rs +154 -154
  155. data/vendor/kreuzberg/src/pdf/bindings.rs +44 -0
  156. data/vendor/kreuzberg/src/pdf/bundled.rs +346 -328
  157. data/vendor/kreuzberg/src/pdf/error.rs +130 -130
  158. data/vendor/kreuzberg/src/pdf/images.rs +139 -139
  159. data/vendor/kreuzberg/src/pdf/metadata.rs +489 -489
  160. data/vendor/kreuzberg/src/pdf/mod.rs +68 -66
  161. data/vendor/kreuzberg/src/pdf/rendering.rs +368 -368
  162. data/vendor/kreuzberg/src/pdf/table.rs +420 -417
  163. data/vendor/kreuzberg/src/pdf/text.rs +240 -240
  164. data/vendor/kreuzberg/src/plugins/extractor.rs +1044 -1044
  165. data/vendor/kreuzberg/src/plugins/mod.rs +212 -212
  166. data/vendor/kreuzberg/src/plugins/ocr.rs +639 -639
  167. data/vendor/kreuzberg/src/plugins/processor.rs +650 -650
  168. data/vendor/kreuzberg/src/plugins/registry.rs +1339 -1339
  169. data/vendor/kreuzberg/src/plugins/traits.rs +258 -258
  170. data/vendor/kreuzberg/src/plugins/validator.rs +967 -967
  171. data/vendor/kreuzberg/src/stopwords/mod.rs +1470 -1470
  172. data/vendor/kreuzberg/src/text/mod.rs +25 -25
  173. data/vendor/kreuzberg/src/text/quality.rs +697 -697
  174. data/vendor/kreuzberg/src/text/quality_processor.rs +219 -219
  175. data/vendor/kreuzberg/src/text/string_utils.rs +217 -217
  176. data/vendor/kreuzberg/src/text/token_reduction/cjk_utils.rs +164 -164
  177. data/vendor/kreuzberg/src/text/token_reduction/config.rs +100 -100
  178. data/vendor/kreuzberg/src/text/token_reduction/core.rs +796 -796
  179. data/vendor/kreuzberg/src/text/token_reduction/filters.rs +902 -902
  180. data/vendor/kreuzberg/src/text/token_reduction/mod.rs +160 -160
  181. data/vendor/kreuzberg/src/text/token_reduction/semantic.rs +619 -619
  182. data/vendor/kreuzberg/src/text/token_reduction/simd_text.rs +147 -147
  183. data/vendor/kreuzberg/src/types.rs +1055 -1055
  184. data/vendor/kreuzberg/src/utils/mod.rs +17 -17
  185. data/vendor/kreuzberg/src/utils/quality.rs +959 -959
  186. data/vendor/kreuzberg/src/utils/string_utils.rs +381 -381
  187. data/vendor/kreuzberg/stopwords/af_stopwords.json +53 -53
  188. data/vendor/kreuzberg/stopwords/ar_stopwords.json +482 -482
  189. data/vendor/kreuzberg/stopwords/bg_stopwords.json +261 -261
  190. data/vendor/kreuzberg/stopwords/bn_stopwords.json +400 -400
  191. data/vendor/kreuzberg/stopwords/br_stopwords.json +1205 -1205
  192. data/vendor/kreuzberg/stopwords/ca_stopwords.json +280 -280
  193. data/vendor/kreuzberg/stopwords/cs_stopwords.json +425 -425
  194. data/vendor/kreuzberg/stopwords/da_stopwords.json +172 -172
  195. data/vendor/kreuzberg/stopwords/de_stopwords.json +622 -622
  196. data/vendor/kreuzberg/stopwords/el_stopwords.json +849 -849
  197. data/vendor/kreuzberg/stopwords/en_stopwords.json +1300 -1300
  198. data/vendor/kreuzberg/stopwords/eo_stopwords.json +175 -175
  199. data/vendor/kreuzberg/stopwords/es_stopwords.json +734 -734
  200. data/vendor/kreuzberg/stopwords/et_stopwords.json +37 -37
  201. data/vendor/kreuzberg/stopwords/eu_stopwords.json +100 -100
  202. data/vendor/kreuzberg/stopwords/fa_stopwords.json +801 -801
  203. data/vendor/kreuzberg/stopwords/fi_stopwords.json +849 -849
  204. data/vendor/kreuzberg/stopwords/fr_stopwords.json +693 -693
  205. data/vendor/kreuzberg/stopwords/ga_stopwords.json +111 -111
  206. data/vendor/kreuzberg/stopwords/gl_stopwords.json +162 -162
  207. data/vendor/kreuzberg/stopwords/gu_stopwords.json +226 -226
  208. data/vendor/kreuzberg/stopwords/ha_stopwords.json +41 -41
  209. data/vendor/kreuzberg/stopwords/he_stopwords.json +196 -196
  210. data/vendor/kreuzberg/stopwords/hi_stopwords.json +227 -227
  211. data/vendor/kreuzberg/stopwords/hr_stopwords.json +181 -181
  212. data/vendor/kreuzberg/stopwords/hu_stopwords.json +791 -791
  213. data/vendor/kreuzberg/stopwords/hy_stopwords.json +47 -47
  214. data/vendor/kreuzberg/stopwords/id_stopwords.json +760 -760
  215. data/vendor/kreuzberg/stopwords/it_stopwords.json +634 -634
  216. data/vendor/kreuzberg/stopwords/ja_stopwords.json +136 -136
  217. data/vendor/kreuzberg/stopwords/kn_stopwords.json +84 -84
  218. data/vendor/kreuzberg/stopwords/ko_stopwords.json +681 -681
  219. data/vendor/kreuzberg/stopwords/ku_stopwords.json +64 -64
  220. data/vendor/kreuzberg/stopwords/la_stopwords.json +51 -51
  221. data/vendor/kreuzberg/stopwords/lt_stopwords.json +476 -476
  222. data/vendor/kreuzberg/stopwords/lv_stopwords.json +163 -163
  223. data/vendor/kreuzberg/stopwords/ml_stopwords.json +1 -1
  224. data/vendor/kreuzberg/stopwords/mr_stopwords.json +101 -101
  225. data/vendor/kreuzberg/stopwords/ms_stopwords.json +477 -477
  226. data/vendor/kreuzberg/stopwords/ne_stopwords.json +490 -490
  227. data/vendor/kreuzberg/stopwords/nl_stopwords.json +415 -415
  228. data/vendor/kreuzberg/stopwords/no_stopwords.json +223 -223
  229. data/vendor/kreuzberg/stopwords/pl_stopwords.json +331 -331
  230. data/vendor/kreuzberg/stopwords/pt_stopwords.json +562 -562
  231. data/vendor/kreuzberg/stopwords/ro_stopwords.json +436 -436
  232. data/vendor/kreuzberg/stopwords/ru_stopwords.json +561 -561
  233. data/vendor/kreuzberg/stopwords/si_stopwords.json +193 -193
  234. data/vendor/kreuzberg/stopwords/sk_stopwords.json +420 -420
  235. data/vendor/kreuzberg/stopwords/sl_stopwords.json +448 -448
  236. data/vendor/kreuzberg/stopwords/so_stopwords.json +32 -32
  237. data/vendor/kreuzberg/stopwords/st_stopwords.json +33 -33
  238. data/vendor/kreuzberg/stopwords/sv_stopwords.json +420 -420
  239. data/vendor/kreuzberg/stopwords/sw_stopwords.json +76 -76
  240. data/vendor/kreuzberg/stopwords/ta_stopwords.json +129 -129
  241. data/vendor/kreuzberg/stopwords/te_stopwords.json +54 -54
  242. data/vendor/kreuzberg/stopwords/th_stopwords.json +118 -118
  243. data/vendor/kreuzberg/stopwords/tl_stopwords.json +149 -149
  244. data/vendor/kreuzberg/stopwords/tr_stopwords.json +506 -506
  245. data/vendor/kreuzberg/stopwords/uk_stopwords.json +75 -75
  246. data/vendor/kreuzberg/stopwords/ur_stopwords.json +519 -519
  247. data/vendor/kreuzberg/stopwords/vi_stopwords.json +647 -647
  248. data/vendor/kreuzberg/stopwords/yo_stopwords.json +62 -62
  249. data/vendor/kreuzberg/stopwords/zh_stopwords.json +796 -796
  250. data/vendor/kreuzberg/stopwords/zu_stopwords.json +31 -31
  251. data/vendor/kreuzberg/tests/api_extract_multipart.rs +52 -52
  252. data/vendor/kreuzberg/tests/api_tests.rs +966 -966
  253. data/vendor/kreuzberg/tests/archive_integration.rs +545 -545
  254. data/vendor/kreuzberg/tests/batch_orchestration.rs +556 -556
  255. data/vendor/kreuzberg/tests/batch_processing.rs +318 -318
  256. data/vendor/kreuzberg/tests/bibtex_parity_test.rs +421 -421
  257. data/vendor/kreuzberg/tests/concurrency_stress.rs +533 -533
  258. data/vendor/kreuzberg/tests/config_features.rs +612 -612
  259. data/vendor/kreuzberg/tests/config_loading_tests.rs +416 -416
  260. data/vendor/kreuzberg/tests/core_integration.rs +510 -510
  261. data/vendor/kreuzberg/tests/csv_integration.rs +414 -414
  262. data/vendor/kreuzberg/tests/docbook_extractor_tests.rs +500 -500
  263. data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +122 -122
  264. data/vendor/kreuzberg/tests/docx_vs_pandoc_comparison.rs +370 -370
  265. data/vendor/kreuzberg/tests/email_integration.rs +327 -327
  266. data/vendor/kreuzberg/tests/epub_native_extractor_tests.rs +275 -275
  267. data/vendor/kreuzberg/tests/error_handling.rs +402 -402
  268. data/vendor/kreuzberg/tests/fictionbook_extractor_tests.rs +228 -228
  269. data/vendor/kreuzberg/tests/format_integration.rs +164 -161
  270. data/vendor/kreuzberg/tests/helpers/mod.rs +142 -142
  271. data/vendor/kreuzberg/tests/html_table_test.rs +551 -551
  272. data/vendor/kreuzberg/tests/image_integration.rs +255 -255
  273. data/vendor/kreuzberg/tests/instrumentation_test.rs +139 -139
  274. data/vendor/kreuzberg/tests/jats_extractor_tests.rs +639 -639
  275. data/vendor/kreuzberg/tests/jupyter_extractor_tests.rs +704 -704
  276. data/vendor/kreuzberg/tests/keywords_integration.rs +479 -479
  277. data/vendor/kreuzberg/tests/keywords_quality.rs +509 -509
  278. data/vendor/kreuzberg/tests/latex_extractor_tests.rs +496 -496
  279. data/vendor/kreuzberg/tests/markdown_extractor_tests.rs +490 -490
  280. data/vendor/kreuzberg/tests/mime_detection.rs +429 -429
  281. data/vendor/kreuzberg/tests/ocr_configuration.rs +514 -514
  282. data/vendor/kreuzberg/tests/ocr_errors.rs +698 -698
  283. data/vendor/kreuzberg/tests/ocr_quality.rs +629 -629
  284. data/vendor/kreuzberg/tests/ocr_stress.rs +469 -469
  285. data/vendor/kreuzberg/tests/odt_extractor_tests.rs +674 -674
  286. data/vendor/kreuzberg/tests/opml_extractor_tests.rs +616 -616
  287. data/vendor/kreuzberg/tests/orgmode_extractor_tests.rs +822 -822
  288. data/vendor/kreuzberg/tests/pdf_integration.rs +45 -45
  289. data/vendor/kreuzberg/tests/pdfium_linking.rs +374 -374
  290. data/vendor/kreuzberg/tests/pipeline_integration.rs +1436 -1436
  291. data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +776 -776
  292. data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +560 -560
  293. data/vendor/kreuzberg/tests/plugin_system.rs +927 -927
  294. data/vendor/kreuzberg/tests/plugin_validator_test.rs +783 -783
  295. data/vendor/kreuzberg/tests/registry_integration_tests.rs +587 -587
  296. data/vendor/kreuzberg/tests/rst_extractor_tests.rs +694 -694
  297. data/vendor/kreuzberg/tests/rtf_extractor_tests.rs +775 -775
  298. data/vendor/kreuzberg/tests/security_validation.rs +416 -416
  299. data/vendor/kreuzberg/tests/stopwords_integration_test.rs +888 -888
  300. data/vendor/kreuzberg/tests/test_fastembed.rs +631 -631
  301. data/vendor/kreuzberg/tests/typst_behavioral_tests.rs +1260 -1260
  302. data/vendor/kreuzberg/tests/typst_extractor_tests.rs +648 -648
  303. data/vendor/kreuzberg/tests/xlsx_metadata_extraction_test.rs +87 -87
  304. data/vendor/kreuzberg-ffi/Cargo.toml +63 -0
  305. data/vendor/kreuzberg-ffi/README.md +851 -0
  306. data/vendor/kreuzberg-ffi/build.rs +176 -0
  307. data/vendor/kreuzberg-ffi/cbindgen.toml +27 -0
  308. data/vendor/kreuzberg-ffi/kreuzberg-ffi-install.pc +12 -0
  309. data/vendor/kreuzberg-ffi/kreuzberg-ffi.pc.in +12 -0
  310. data/vendor/kreuzberg-ffi/kreuzberg.h +1087 -0
  311. data/vendor/kreuzberg-ffi/src/lib.rs +3616 -0
  312. data/vendor/kreuzberg-ffi/src/panic_shield.rs +247 -0
  313. data/vendor/kreuzberg-ffi/tests.disabled/README.md +48 -0
  314. data/vendor/kreuzberg-ffi/tests.disabled/config_loading_tests.rs +299 -0
  315. data/vendor/kreuzberg-ffi/tests.disabled/config_tests.rs +346 -0
  316. data/vendor/kreuzberg-ffi/tests.disabled/extractor_tests.rs +232 -0
  317. data/vendor/kreuzberg-ffi/tests.disabled/plugin_registration_tests.rs +470 -0
  318. data/vendor/kreuzberg-tesseract/.commitlintrc.json +13 -0
  319. data/vendor/kreuzberg-tesseract/.crate-ignore +2 -0
  320. data/vendor/kreuzberg-tesseract/Cargo.lock +2933 -0
  321. data/vendor/kreuzberg-tesseract/Cargo.toml +48 -0
  322. data/vendor/kreuzberg-tesseract/LICENSE +22 -0
  323. data/vendor/kreuzberg-tesseract/README.md +399 -0
  324. data/vendor/kreuzberg-tesseract/build.rs +1354 -0
  325. data/vendor/kreuzberg-tesseract/patches/README.md +71 -0
  326. data/vendor/kreuzberg-tesseract/patches/tesseract.diff +199 -0
  327. data/vendor/kreuzberg-tesseract/src/api.rs +1371 -0
  328. data/vendor/kreuzberg-tesseract/src/choice_iterator.rs +77 -0
  329. data/vendor/kreuzberg-tesseract/src/enums.rs +297 -0
  330. data/vendor/kreuzberg-tesseract/src/error.rs +81 -0
  331. data/vendor/kreuzberg-tesseract/src/lib.rs +145 -0
  332. data/vendor/kreuzberg-tesseract/src/monitor.rs +57 -0
  333. data/vendor/kreuzberg-tesseract/src/mutable_iterator.rs +197 -0
  334. data/vendor/kreuzberg-tesseract/src/page_iterator.rs +253 -0
  335. data/vendor/kreuzberg-tesseract/src/result_iterator.rs +286 -0
  336. data/vendor/kreuzberg-tesseract/src/result_renderer.rs +183 -0
  337. data/vendor/kreuzberg-tesseract/tests/integration_test.rs +211 -0
  338. data/vendor/rb-sys/.cargo_vcs_info.json +5 -5
  339. data/vendor/rb-sys/Cargo.lock +393 -393
  340. data/vendor/rb-sys/Cargo.toml +70 -70
  341. data/vendor/rb-sys/Cargo.toml.orig +57 -57
  342. data/vendor/rb-sys/LICENSE-APACHE +190 -190
  343. data/vendor/rb-sys/LICENSE-MIT +21 -21
  344. data/vendor/rb-sys/build/features.rs +111 -111
  345. data/vendor/rb-sys/build/main.rs +286 -286
  346. data/vendor/rb-sys/build/stable_api_config.rs +155 -155
  347. data/vendor/rb-sys/build/version.rs +50 -50
  348. data/vendor/rb-sys/readme.md +36 -36
  349. data/vendor/rb-sys/src/bindings.rs +21 -21
  350. data/vendor/rb-sys/src/hidden.rs +11 -11
  351. data/vendor/rb-sys/src/lib.rs +35 -35
  352. data/vendor/rb-sys/src/macros.rs +371 -371
  353. data/vendor/rb-sys/src/memory.rs +53 -53
  354. data/vendor/rb-sys/src/ruby_abi_version.rs +38 -38
  355. data/vendor/rb-sys/src/special_consts.rs +31 -31
  356. data/vendor/rb-sys/src/stable_api/compiled.c +179 -179
  357. data/vendor/rb-sys/src/stable_api/compiled.rs +257 -257
  358. data/vendor/rb-sys/src/stable_api/ruby_2_7.rs +324 -324
  359. data/vendor/rb-sys/src/stable_api/ruby_3_0.rs +332 -332
  360. data/vendor/rb-sys/src/stable_api/ruby_3_1.rs +325 -325
  361. data/vendor/rb-sys/src/stable_api/ruby_3_2.rs +323 -323
  362. data/vendor/rb-sys/src/stable_api/ruby_3_3.rs +339 -339
  363. data/vendor/rb-sys/src/stable_api/ruby_3_4.rs +339 -339
  364. data/vendor/rb-sys/src/stable_api.rs +260 -260
  365. data/vendor/rb-sys/src/symbol.rs +31 -31
  366. data/vendor/rb-sys/src/tracking_allocator.rs +330 -330
  367. data/vendor/rb-sys/src/utils.rs +89 -89
  368. data/vendor/rb-sys/src/value_type.rs +7 -7
  369. metadata +44 -81
  370. data/vendor/rb-sys/bin/release.sh +0 -21
@@ -1,328 +1,346 @@
1
- //! Runtime extraction of bundled PDFium library.
2
- //!
3
- //! When the `pdf-bundled` feature is enabled, the PDFium library is embedded in the binary
4
- //! using `include_bytes!` during compilation. This module handles runtime extraction to a
5
- //! temporary directory and provides the path for dynamic loading.
6
- //!
7
- //! # How It Works
8
- //!
9
- //! 1. During build (build.rs): PDFium is copied to OUT_DIR and the build script sets
10
- //! `KREUZBERG_PDFIUM_BUNDLED_PATH` environment variable
11
- //! 2. At compile time: `include_bytes!` embeds the library binary in the executable
12
- //! 3. At runtime: `extract_bundled_pdfium()` extracts to `$TMPDIR/kreuzberg-pdfium/`
13
- //! 4. Library is reused if already present (based on modification time)
14
- //!
15
- //! # Example
16
- //!
17
- //! ```rust,ignore
18
- //! # #[cfg(feature = "pdf-bundled")]
19
- //! # {
20
- //! use kreuzberg::pdf::bundled::extract_bundled_pdfium;
21
- //!
22
- //! # fn example() -> kreuzberg::Result<()> {
23
- //! let lib_path = extract_bundled_pdfium()?;
24
- //! println!("Extracted to: {}", lib_path.display());
25
- //! # Ok(())
26
- //! # }
27
- //! # }
28
- //! ```
29
-
30
- use std::fs;
31
- use std::io;
32
- use std::path::{Path, PathBuf};
33
-
34
- #[cfg(unix)]
35
- use std::os::unix::fs::PermissionsExt;
36
-
37
- /// Runtime library name and extraction directory for the bundled PDFium library.
38
- ///
39
- /// Returns tuple of (library_name, extraction_directory)
40
- fn bundled_library_info() -> (&'static str, &'static str) {
41
- if cfg!(target_os = "windows") {
42
- ("pdfium.dll", "kreuzberg-pdfium")
43
- } else if cfg!(target_os = "macos") {
44
- ("libpdfium.dylib", "kreuzberg-pdfium")
45
- } else if cfg!(target_os = "linux") {
46
- ("libpdfium.so", "kreuzberg-pdfium")
47
- } else {
48
- // Fallback for other Unix-like systems
49
- ("libpdfium.so", "kreuzberg-pdfium")
50
- }
51
- }
52
-
53
- /// Get the temporary directory for bundled PDFium extraction.
54
- ///
55
- /// Uses `std::env::temp_dir()` on all platforms.
56
- fn get_extraction_dir() -> io::Result<PathBuf> {
57
- let (_, subdir) = bundled_library_info();
58
- Ok(std::env::temp_dir().join(subdir))
59
- }
60
-
61
- /// Check if extracted library exists and is valid.
62
- ///
63
- /// Verifies:
64
- /// - File exists at expected path
65
- /// - File size matches embedded size (basic validation)
66
- ///
67
- /// Returns `true` if library can be safely reused, `false` if extraction is needed.
68
- fn is_extracted_library_valid(lib_path: &Path, embedded_size: usize) -> bool {
69
- if !lib_path.exists() {
70
- return false;
71
- }
72
-
73
- // Verify file size matches to catch partial/corrupted extractions
74
- match fs::metadata(lib_path) {
75
- Ok(metadata) => {
76
- let file_size = metadata.len() as usize;
77
- // Allow 1% size difference for platform-specific variations
78
- let size_tolerance = (embedded_size as f64 * 0.01) as usize;
79
- let min_size = embedded_size.saturating_sub(size_tolerance);
80
- let max_size = embedded_size.saturating_add(size_tolerance);
81
- file_size >= min_size && file_size <= max_size
82
- }
83
- Err(_) => false,
84
- }
85
- }
86
-
87
- /// Extract bundled PDFium library to temporary directory.
88
- ///
89
- /// # Behavior
90
- ///
91
- /// - Embeds PDFium library using `include_bytes!`
92
- /// - Extracts to `$TMPDIR/kreuzberg-pdfium/`
93
- /// - Reuses extracted library if size matches
94
- /// - Sets permissions to 0755 on Unix
95
- /// - Returns path to extracted library
96
- ///
97
- /// # Errors
98
- ///
99
- /// Returns `std::io::Error` if:
100
- /// - Cannot create extraction directory
101
- /// - Cannot write library file
102
- /// - Cannot set file permissions (Unix only)
103
- ///
104
- /// # Platform-Specific Library Names
105
- ///
106
- /// - Linux: `libpdfium.so`
107
- /// - macOS: `libpdfium.dylib`
108
- /// - Windows: `pdfium.dll`
109
- pub fn extract_bundled_pdfium() -> io::Result<PathBuf> {
110
- let (lib_name, _) = bundled_library_info();
111
- let extract_dir = get_extraction_dir()?;
112
-
113
- // Create extraction directory if it doesn't exist
114
- fs::create_dir_all(&extract_dir).map_err(|e| {
115
- io::Error::new(
116
- e.kind(),
117
- format!(
118
- "Failed to create bundled pdfium extraction directory '{}': {}",
119
- extract_dir.display(),
120
- e
121
- ),
122
- )
123
- })?;
124
-
125
- let lib_path = extract_dir.join(lib_name);
126
-
127
- // Include bundled PDFium library
128
- let bundled_lib = include_bytes!(env!("KREUZBERG_PDFIUM_BUNDLED_PATH"));
129
-
130
- // Check if library already exists and is valid
131
- if is_extracted_library_valid(&lib_path, bundled_lib.len()) {
132
- return Ok(lib_path);
133
- }
134
-
135
- // Write library to disk
136
- fs::write(&lib_path, bundled_lib).map_err(|e| {
137
- io::Error::new(
138
- e.kind(),
139
- format!(
140
- "Failed to extract bundled pdfium library to '{}': {}",
141
- lib_path.display(),
142
- e
143
- ),
144
- )
145
- })?;
146
-
147
- // Set executable permissions on Unix
148
- #[cfg(unix)]
149
- {
150
- let perms = fs::Permissions::from_mode(0o755);
151
- fs::set_permissions(&lib_path, perms).map_err(|e| {
152
- io::Error::new(
153
- e.kind(),
154
- format!(
155
- "Failed to set permissions on bundled pdfium library '{}': {}",
156
- lib_path.display(),
157
- e
158
- ),
159
- )
160
- })?;
161
- }
162
-
163
- Ok(lib_path)
164
- }
165
-
166
- #[cfg(test)]
167
- mod tests {
168
- use super::*;
169
-
170
- #[test]
171
- fn test_bundled_library_info_windows() {
172
- if cfg!(target_os = "windows") {
173
- let (name, dir) = bundled_library_info();
174
- assert_eq!(name, "pdfium.dll");
175
- assert_eq!(dir, "kreuzberg-pdfium");
176
- }
177
- }
178
-
179
- #[test]
180
- fn test_bundled_library_info_macos() {
181
- if cfg!(target_os = "macos") {
182
- let (name, dir) = bundled_library_info();
183
- assert_eq!(name, "libpdfium.dylib");
184
- assert_eq!(dir, "kreuzberg-pdfium");
185
- }
186
- }
187
-
188
- #[test]
189
- fn test_bundled_library_info_linux() {
190
- if cfg!(target_os = "linux") {
191
- let (name, dir) = bundled_library_info();
192
- assert_eq!(name, "libpdfium.so");
193
- assert_eq!(dir, "kreuzberg-pdfium");
194
- }
195
- }
196
-
197
- #[test]
198
- fn test_get_extraction_dir() {
199
- let result = get_extraction_dir();
200
- assert!(result.is_ok());
201
- let dir = result.unwrap();
202
- assert!(dir.to_str().is_some());
203
- assert!(dir.ends_with("kreuzberg-pdfium"));
204
- }
205
-
206
- #[test]
207
- fn test_is_extracted_library_valid_missing() {
208
- let nonexistent = PathBuf::from("/tmp/nonexistent-pdfium-test");
209
- assert!(!is_extracted_library_valid(&nonexistent, 1000));
210
- }
211
-
212
- #[test]
213
- fn test_is_extracted_library_valid_size_match() {
214
- // Create a temporary test file
215
- let temp_dir = std::env::temp_dir();
216
- let test_file = temp_dir.join("test-pdfium-size.dll");
217
- let test_size = 5_000_000;
218
- let test_data = vec![0u8; test_size];
219
-
220
- if let Ok(_) = fs::write(&test_file, &test_data) {
221
- let is_valid = is_extracted_library_valid(&test_file, test_size);
222
- assert!(is_valid);
223
- let _ = fs::remove_file(&test_file);
224
- }
225
- }
226
-
227
- #[test]
228
- fn test_is_extracted_library_valid_size_tolerance() {
229
- // Create a temporary test file
230
- let temp_dir = std::env::temp_dir();
231
- let test_file = temp_dir.join("test-pdfium-tolerance.dll");
232
- let original_size = 10_000_000;
233
- let tolerance = (original_size as f64 * 0.01) as usize;
234
-
235
- // Create file that's 0.5% smaller (within tolerance)
236
- let actual_size = original_size - tolerance / 2;
237
- let test_data = vec![0u8; actual_size];
238
-
239
- if let Ok(_) = fs::write(&test_file, &test_data) {
240
- let is_valid = is_extracted_library_valid(&test_file, original_size);
241
- assert!(is_valid);
242
- let _ = fs::remove_file(&test_file);
243
- }
244
- }
245
-
246
- #[test]
247
- fn test_is_extracted_library_valid_size_mismatch() {
248
- // Create a temporary test file
249
- let temp_dir = std::env::temp_dir();
250
- let test_file = temp_dir.join("test-pdfium-mismatch.dll");
251
- let original_size = 10_000_000;
252
-
253
- // Create file that's 10% smaller (outside tolerance)
254
- let actual_size = (original_size as f64 * 0.85) as usize;
255
- let test_data = vec![0u8; actual_size];
256
-
257
- if let Ok(_) = fs::write(&test_file, &test_data) {
258
- let is_valid = is_extracted_library_valid(&test_file, original_size);
259
- assert!(!is_valid);
260
- let _ = fs::remove_file(&test_file);
261
- }
262
- }
263
-
264
- #[test]
265
- #[cfg(feature = "pdf-bundled")]
266
- fn test_extract_bundled_pdfium() {
267
- let result = extract_bundled_pdfium();
268
- assert!(result.is_ok());
269
-
270
- let lib_path = result.unwrap();
271
- assert!(
272
- lib_path.exists(),
273
- "Extracted library should exist at: {}",
274
- lib_path.display()
275
- );
276
- assert!(lib_path.file_name().is_some(), "Library path should have filename");
277
-
278
- // Verify correct library name for platform
279
- let (expected_name, _) = bundled_library_info();
280
- assert_eq!(lib_path.file_name().unwrap(), expected_name);
281
- }
282
-
283
- #[test]
284
- #[cfg(feature = "pdf-bundled")]
285
- fn test_extract_bundled_pdfium_reuses_existing() {
286
- // First extraction
287
- let result1 = extract_bundled_pdfium();
288
- assert!(result1.is_ok());
289
- let path1 = result1.unwrap();
290
-
291
- // Get file size and basic metadata of first extraction
292
- let metadata1 = fs::metadata(&path1).expect("Should be able to read metadata");
293
- let size1 = metadata1.len();
294
-
295
- // Second extraction should reuse the file
296
- let result2 = extract_bundled_pdfium();
297
- assert!(result2.is_ok());
298
- let path2 = result2.unwrap();
299
-
300
- // Paths should be identical
301
- assert_eq!(path1, path2, "Extraction should return same path on second call");
302
-
303
- // File size should be identical (reused, not rewritten)
304
- let metadata2 = fs::metadata(&path2).expect("Should be able to read metadata");
305
- let size2 = metadata2.len();
306
- assert_eq!(size1, size2, "Reused library should have same file size");
307
- }
308
-
309
- #[test]
310
- #[cfg(unix)]
311
- #[cfg(feature = "pdf-bundled")]
312
- fn test_extract_bundled_pdfium_permissions() {
313
- let result = extract_bundled_pdfium();
314
- assert!(result.is_ok());
315
-
316
- let lib_path = result.unwrap();
317
- let metadata = fs::metadata(&lib_path).expect("Should be able to read metadata");
318
- let perms = metadata.permissions();
319
- let mode = perms.mode();
320
-
321
- // Verify executable bit is set (at least 0o700 or 0o755)
322
- assert!(
323
- mode & 0o111 != 0,
324
- "Library should have executable bit set, got mode: {:#o}",
325
- mode
326
- );
327
- }
328
- }
1
+ //! Runtime extraction of bundled PDFium library.
2
+ //!
3
+ //! When the `bundled-pdfium` feature is enabled, the PDFium library is embedded in the binary
4
+ //! using `include_bytes!` during compilation. This module handles runtime extraction to a
5
+ //! temporary directory and provides the path for dynamic loading.
6
+ //!
7
+ //! # How It Works
8
+ //!
9
+ //! 1. During build (build.rs): PDFium is copied to OUT_DIR and the build script sets
10
+ //! `KREUZBERG_PDFIUM_BUNDLED_PATH` environment variable
11
+ //! 2. At compile time: `include_bytes!` embeds the library binary in the executable
12
+ //! 3. At runtime: `extract_bundled_pdfium()` extracts to `$TMPDIR/kreuzberg-pdfium/`
13
+ //! 4. Library is reused if already present (based on modification time)
14
+ //!
15
+ //! # Example
16
+ //!
17
+ //! ```rust,ignore
18
+ //! # #[cfg(feature = "bundled-pdfium")]
19
+ //! # {
20
+ //! use kreuzberg::pdf::bundled::extract_bundled_pdfium;
21
+ //!
22
+ //! # fn example() -> kreuzberg::Result<()> {
23
+ //! let lib_path = extract_bundled_pdfium()?;
24
+ //! println!("Extracted to: {}", lib_path.display());
25
+ //! # Ok(())
26
+ //! # }
27
+ //! # }
28
+ //! ```
29
+
30
+ use std::fs;
31
+ use std::io;
32
+ use std::path::{Path, PathBuf};
33
+
34
+ #[cfg(unix)]
35
+ use std::os::unix::fs::PermissionsExt;
36
+
37
+ /// Runtime library name and extraction directory for the bundled PDFium library.
38
+ ///
39
+ /// Returns tuple of (library_name, extraction_directory)
40
+ fn bundled_library_info() -> (&'static str, &'static str) {
41
+ if cfg!(target_os = "windows") {
42
+ ("pdfium.dll", "kreuzberg-pdfium")
43
+ } else if cfg!(target_os = "macos") {
44
+ ("libpdfium.dylib", "kreuzberg-pdfium")
45
+ } else if cfg!(target_os = "linux") {
46
+ ("libpdfium.so", "kreuzberg-pdfium")
47
+ } else {
48
+ // Fallback for other Unix-like systems
49
+ ("libpdfium.so", "kreuzberg-pdfium")
50
+ }
51
+ }
52
+
53
+ /// Get the temporary directory for bundled PDFium extraction.
54
+ ///
55
+ /// Uses `std::env::temp_dir()` on all platforms.
56
+ fn get_extraction_dir() -> io::Result<PathBuf> {
57
+ let (_, subdir) = bundled_library_info();
58
+ Ok(std::env::temp_dir().join(subdir))
59
+ }
60
+
61
+ /// Check if extracted library exists and is valid.
62
+ ///
63
+ /// Verifies:
64
+ /// - File exists at expected path
65
+ /// - File size matches embedded size (basic validation)
66
+ ///
67
+ /// Returns `true` if library can be safely reused, `false` if extraction is needed.
68
+ fn is_extracted_library_valid(lib_path: &Path, embedded_size: usize) -> bool {
69
+ if !lib_path.exists() {
70
+ return false;
71
+ }
72
+
73
+ // Verify file size matches to catch partial/corrupted extractions
74
+ match fs::metadata(lib_path) {
75
+ Ok(metadata) => {
76
+ let file_size = metadata.len() as usize;
77
+ // Allow 1% size difference for platform-specific variations
78
+ let size_tolerance = (embedded_size as f64 * 0.01) as usize;
79
+ let min_size = embedded_size.saturating_sub(size_tolerance);
80
+ let max_size = embedded_size.saturating_add(size_tolerance);
81
+ file_size >= min_size && file_size <= max_size
82
+ }
83
+ Err(_) => false,
84
+ }
85
+ }
86
+
87
+ /// Extract bundled PDFium library to temporary directory.
88
+ ///
89
+ /// # Behavior
90
+ ///
91
+ /// - Embeds PDFium library using `include_bytes!`
92
+ /// - Extracts to `$TMPDIR/kreuzberg-pdfium/` (non-WASM only)
93
+ /// - Reuses extracted library if size matches
94
+ /// - Sets permissions to 0755 on Unix
95
+ /// - Returns path to extracted library
96
+ ///
97
+ /// # WASM Handling
98
+ ///
99
+ /// On WASM targets (wasm32-*), this function returns an error with a helpful
100
+ /// message directing users to use WASM-specific initialization. WASM PDFium
101
+ /// is initialized through the runtime, not via file extraction.
102
+ ///
103
+ /// # Errors
104
+ ///
105
+ /// Returns `std::io::Error` if:
106
+ /// - Cannot create extraction directory
107
+ /// - Cannot write library file
108
+ /// - Cannot set file permissions (Unix only)
109
+ /// - Target is WASM (filesystem access not available)
110
+ ///
111
+ /// # Platform-Specific Library Names
112
+ ///
113
+ /// - Linux: `libpdfium.so`
114
+ /// - macOS: `libpdfium.dylib`
115
+ /// - Windows: `pdfium.dll`
116
+ pub fn extract_bundled_pdfium() -> io::Result<PathBuf> {
117
+ // WASM targets cannot use file extraction
118
+ #[cfg(target_arch = "wasm32")]
119
+ {
120
+ return Err(io::Error::new(
121
+ io::ErrorKind::Unsupported,
122
+ "File extraction is not available in WASM. \
123
+ PDFium for WASM must be initialized via the WebAssembly runtime. \
124
+ Use a WASM-compatible environment with proper module initialization.",
125
+ ));
126
+ }
127
+
128
+ let (lib_name, _) = bundled_library_info();
129
+ let extract_dir = get_extraction_dir()?;
130
+
131
+ // Create extraction directory if it doesn't exist
132
+ fs::create_dir_all(&extract_dir).map_err(|e| {
133
+ io::Error::new(
134
+ e.kind(),
135
+ format!(
136
+ "Failed to create bundled pdfium extraction directory '{}': {}",
137
+ extract_dir.display(),
138
+ e
139
+ ),
140
+ )
141
+ })?;
142
+
143
+ let lib_path = extract_dir.join(lib_name);
144
+
145
+ // Include bundled PDFium library
146
+ let bundled_lib = include_bytes!(env!("KREUZBERG_PDFIUM_BUNDLED_PATH"));
147
+
148
+ // Check if library already exists and is valid
149
+ if is_extracted_library_valid(&lib_path, bundled_lib.len()) {
150
+ return Ok(lib_path);
151
+ }
152
+
153
+ // Write library to disk
154
+ fs::write(&lib_path, bundled_lib).map_err(|e| {
155
+ io::Error::new(
156
+ e.kind(),
157
+ format!(
158
+ "Failed to extract bundled pdfium library to '{}': {}",
159
+ lib_path.display(),
160
+ e
161
+ ),
162
+ )
163
+ })?;
164
+
165
+ // Set executable permissions on Unix
166
+ #[cfg(unix)]
167
+ {
168
+ let perms = fs::Permissions::from_mode(0o755);
169
+ fs::set_permissions(&lib_path, perms).map_err(|e| {
170
+ io::Error::new(
171
+ e.kind(),
172
+ format!(
173
+ "Failed to set permissions on bundled pdfium library '{}': {}",
174
+ lib_path.display(),
175
+ e
176
+ ),
177
+ )
178
+ })?;
179
+ }
180
+
181
+ Ok(lib_path)
182
+ }
183
+
184
+ #[cfg(test)]
185
+ mod tests {
186
+ use super::*;
187
+
188
+ #[test]
189
+ fn test_bundled_library_info_windows() {
190
+ if cfg!(target_os = "windows") {
191
+ let (name, dir) = bundled_library_info();
192
+ assert_eq!(name, "pdfium.dll");
193
+ assert_eq!(dir, "kreuzberg-pdfium");
194
+ }
195
+ }
196
+
197
+ #[test]
198
+ fn test_bundled_library_info_macos() {
199
+ if cfg!(target_os = "macos") {
200
+ let (name, dir) = bundled_library_info();
201
+ assert_eq!(name, "libpdfium.dylib");
202
+ assert_eq!(dir, "kreuzberg-pdfium");
203
+ }
204
+ }
205
+
206
+ #[test]
207
+ fn test_bundled_library_info_linux() {
208
+ if cfg!(target_os = "linux") {
209
+ let (name, dir) = bundled_library_info();
210
+ assert_eq!(name, "libpdfium.so");
211
+ assert_eq!(dir, "kreuzberg-pdfium");
212
+ }
213
+ }
214
+
215
+ #[test]
216
+ fn test_get_extraction_dir() {
217
+ let result = get_extraction_dir();
218
+ assert!(result.is_ok());
219
+ let dir = result.unwrap();
220
+ assert!(dir.to_str().is_some());
221
+ assert!(dir.ends_with("kreuzberg-pdfium"));
222
+ }
223
+
224
+ #[test]
225
+ fn test_is_extracted_library_valid_missing() {
226
+ let nonexistent = PathBuf::from("/tmp/nonexistent-pdfium-test");
227
+ assert!(!is_extracted_library_valid(&nonexistent, 1000));
228
+ }
229
+
230
+ #[test]
231
+ fn test_is_extracted_library_valid_size_match() {
232
+ // Create a temporary test file
233
+ let temp_dir = std::env::temp_dir();
234
+ let test_file = temp_dir.join("test-pdfium-size.dll");
235
+ let test_size = 5_000_000;
236
+ let test_data = vec![0u8; test_size];
237
+
238
+ if let Ok(_) = fs::write(&test_file, &test_data) {
239
+ let is_valid = is_extracted_library_valid(&test_file, test_size);
240
+ assert!(is_valid);
241
+ let _ = fs::remove_file(&test_file);
242
+ }
243
+ }
244
+
245
+ #[test]
246
+ fn test_is_extracted_library_valid_size_tolerance() {
247
+ // Create a temporary test file
248
+ let temp_dir = std::env::temp_dir();
249
+ let test_file = temp_dir.join("test-pdfium-tolerance.dll");
250
+ let original_size = 10_000_000;
251
+ let tolerance = (original_size as f64 * 0.01) as usize;
252
+
253
+ // Create file that's 0.5% smaller (within tolerance)
254
+ let actual_size = original_size - tolerance / 2;
255
+ let test_data = vec![0u8; actual_size];
256
+
257
+ if let Ok(_) = fs::write(&test_file, &test_data) {
258
+ let is_valid = is_extracted_library_valid(&test_file, original_size);
259
+ assert!(is_valid);
260
+ let _ = fs::remove_file(&test_file);
261
+ }
262
+ }
263
+
264
+ #[test]
265
+ fn test_is_extracted_library_valid_size_mismatch() {
266
+ // Create a temporary test file
267
+ let temp_dir = std::env::temp_dir();
268
+ let test_file = temp_dir.join("test-pdfium-mismatch.dll");
269
+ let original_size = 10_000_000;
270
+
271
+ // Create file that's 10% smaller (outside tolerance)
272
+ let actual_size = (original_size as f64 * 0.85) as usize;
273
+ let test_data = vec![0u8; actual_size];
274
+
275
+ if let Ok(_) = fs::write(&test_file, &test_data) {
276
+ let is_valid = is_extracted_library_valid(&test_file, original_size);
277
+ assert!(!is_valid);
278
+ let _ = fs::remove_file(&test_file);
279
+ }
280
+ }
281
+
282
+ #[test]
283
+ #[cfg(feature = "bundled-pdfium")]
284
+ fn test_extract_bundled_pdfium() {
285
+ let result = extract_bundled_pdfium();
286
+ assert!(result.is_ok());
287
+
288
+ let lib_path = result.unwrap();
289
+ assert!(
290
+ lib_path.exists(),
291
+ "Extracted library should exist at: {}",
292
+ lib_path.display()
293
+ );
294
+ assert!(lib_path.file_name().is_some(), "Library path should have filename");
295
+
296
+ // Verify correct library name for platform
297
+ let (expected_name, _) = bundled_library_info();
298
+ assert_eq!(lib_path.file_name().unwrap(), expected_name);
299
+ }
300
+
301
+ #[test]
302
+ #[cfg(feature = "bundled-pdfium")]
303
+ fn test_extract_bundled_pdfium_reuses_existing() {
304
+ // First extraction
305
+ let result1 = extract_bundled_pdfium();
306
+ assert!(result1.is_ok());
307
+ let path1 = result1.unwrap();
308
+
309
+ // Get file size and basic metadata of first extraction
310
+ let metadata1 = fs::metadata(&path1).expect("Should be able to read metadata");
311
+ let size1 = metadata1.len();
312
+
313
+ // Second extraction should reuse the file
314
+ let result2 = extract_bundled_pdfium();
315
+ assert!(result2.is_ok());
316
+ let path2 = result2.unwrap();
317
+
318
+ // Paths should be identical
319
+ assert_eq!(path1, path2, "Extraction should return same path on second call");
320
+
321
+ // File size should be identical (reused, not rewritten)
322
+ let metadata2 = fs::metadata(&path2).expect("Should be able to read metadata");
323
+ let size2 = metadata2.len();
324
+ assert_eq!(size1, size2, "Reused library should have same file size");
325
+ }
326
+
327
+ #[test]
328
+ #[cfg(unix)]
329
+ #[cfg(feature = "bundled-pdfium")]
330
+ fn test_extract_bundled_pdfium_permissions() {
331
+ let result = extract_bundled_pdfium();
332
+ assert!(result.is_ok());
333
+
334
+ let lib_path = result.unwrap();
335
+ let metadata = fs::metadata(&lib_path).expect("Should be able to read metadata");
336
+ let perms = metadata.permissions();
337
+ let mode = perms.mode();
338
+
339
+ // Verify executable bit is set (at least 0o700 or 0o755)
340
+ assert!(
341
+ mode & 0o111 != 0,
342
+ "Library should have executable bit set, got mode: {:#o}",
343
+ mode
344
+ );
345
+ }
346
+ }