kreuzberg 4.0.0.rc1 → 4.0.0.rc2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (342) hide show
  1. checksums.yaml +4 -4
  2. data/.gitignore +14 -8
  3. data/.rspec +3 -3
  4. data/.rubocop.yaml +1 -534
  5. data/.rubocop.yml +538 -0
  6. data/Gemfile +8 -9
  7. data/Gemfile.lock +9 -109
  8. data/README.md +426 -421
  9. data/Rakefile +25 -25
  10. data/Steepfile +47 -47
  11. data/examples/async_patterns.rb +341 -340
  12. data/ext/kreuzberg_rb/extconf.rb +45 -35
  13. data/ext/kreuzberg_rb/native/Cargo.lock +6535 -0
  14. data/ext/kreuzberg_rb/native/Cargo.toml +44 -36
  15. data/ext/kreuzberg_rb/native/README.md +425 -425
  16. data/ext/kreuzberg_rb/native/build.rs +15 -17
  17. data/ext/kreuzberg_rb/native/include/ieeefp.h +11 -11
  18. data/ext/kreuzberg_rb/native/include/msvc_compat/strings.h +14 -14
  19. data/ext/kreuzberg_rb/native/include/strings.h +20 -20
  20. data/ext/kreuzberg_rb/native/include/unistd.h +47 -47
  21. data/ext/kreuzberg_rb/native/src/lib.rs +2998 -2939
  22. data/extconf.rb +28 -28
  23. data/kreuzberg.gemspec +148 -105
  24. data/lib/kreuzberg/api_proxy.rb +142 -142
  25. data/lib/kreuzberg/cache_api.rb +46 -45
  26. data/lib/kreuzberg/cli.rb +55 -55
  27. data/lib/kreuzberg/cli_proxy.rb +127 -127
  28. data/lib/kreuzberg/config.rb +691 -684
  29. data/lib/kreuzberg/error_context.rb +32 -0
  30. data/lib/kreuzberg/errors.rb +118 -50
  31. data/lib/kreuzberg/extraction_api.rb +85 -84
  32. data/lib/kreuzberg/mcp_proxy.rb +186 -186
  33. data/lib/kreuzberg/ocr_backend_protocol.rb +113 -113
  34. data/lib/kreuzberg/post_processor_protocol.rb +86 -86
  35. data/lib/kreuzberg/result.rb +216 -216
  36. data/lib/kreuzberg/setup_lib_path.rb +80 -79
  37. data/lib/kreuzberg/validator_protocol.rb +89 -89
  38. data/lib/kreuzberg/version.rb +5 -5
  39. data/lib/kreuzberg.rb +103 -82
  40. data/sig/kreuzberg/internal.rbs +184 -184
  41. data/sig/kreuzberg.rbs +520 -468
  42. data/spec/binding/cache_spec.rb +227 -227
  43. data/spec/binding/cli_proxy_spec.rb +85 -87
  44. data/spec/binding/cli_spec.rb +55 -54
  45. data/spec/binding/config_spec.rb +345 -345
  46. data/spec/binding/config_validation_spec.rb +283 -283
  47. data/spec/binding/error_handling_spec.rb +213 -213
  48. data/spec/binding/errors_spec.rb +66 -66
  49. data/spec/binding/plugins/ocr_backend_spec.rb +307 -307
  50. data/spec/binding/plugins/postprocessor_spec.rb +269 -269
  51. data/spec/binding/plugins/validator_spec.rb +274 -274
  52. data/spec/fixtures/config.toml +39 -39
  53. data/spec/fixtures/config.yaml +41 -42
  54. data/spec/fixtures/invalid_config.toml +4 -4
  55. data/spec/smoke/package_spec.rb +178 -178
  56. data/spec/spec_helper.rb +42 -42
  57. data/vendor/kreuzberg/Cargo.toml +204 -134
  58. data/vendor/kreuzberg/README.md +175 -175
  59. data/vendor/kreuzberg/benches/otel_overhead.rs +48 -0
  60. data/vendor/kreuzberg/build.rs +474 -460
  61. data/vendor/kreuzberg/src/api/error.rs +81 -81
  62. data/vendor/kreuzberg/src/api/handlers.rs +199 -199
  63. data/vendor/kreuzberg/src/api/mod.rs +79 -79
  64. data/vendor/kreuzberg/src/api/server.rs +353 -353
  65. data/vendor/kreuzberg/src/api/types.rs +170 -170
  66. data/vendor/kreuzberg/src/cache/mod.rs +1167 -1143
  67. data/vendor/kreuzberg/src/chunking/mod.rs +677 -677
  68. data/vendor/kreuzberg/src/core/batch_mode.rs +95 -35
  69. data/vendor/kreuzberg/src/core/config.rs +1032 -1032
  70. data/vendor/kreuzberg/src/core/extractor.rs +1024 -903
  71. data/vendor/kreuzberg/src/core/io.rs +329 -327
  72. data/vendor/kreuzberg/src/core/mime.rs +605 -615
  73. data/vendor/kreuzberg/src/core/mod.rs +45 -42
  74. data/vendor/kreuzberg/src/core/pipeline.rs +984 -906
  75. data/vendor/kreuzberg/src/embeddings.rs +432 -323
  76. data/vendor/kreuzberg/src/error.rs +431 -431
  77. data/vendor/kreuzberg/src/extraction/archive.rs +954 -954
  78. data/vendor/kreuzberg/src/extraction/docx.rs +40 -40
  79. data/vendor/kreuzberg/src/extraction/email.rs +854 -854
  80. data/vendor/kreuzberg/src/extraction/excel.rs +688 -688
  81. data/vendor/kreuzberg/src/extraction/html.rs +553 -553
  82. data/vendor/kreuzberg/src/extraction/image.rs +368 -368
  83. data/vendor/kreuzberg/src/extraction/libreoffice.rs +563 -564
  84. data/vendor/kreuzberg/src/extraction/markdown.rs +213 -0
  85. data/vendor/kreuzberg/src/extraction/mod.rs +81 -77
  86. data/vendor/kreuzberg/src/extraction/office_metadata/app_properties.rs +398 -398
  87. data/vendor/kreuzberg/src/extraction/office_metadata/core_properties.rs +247 -247
  88. data/vendor/kreuzberg/src/extraction/office_metadata/custom_properties.rs +240 -240
  89. data/vendor/kreuzberg/src/extraction/office_metadata/mod.rs +130 -128
  90. data/vendor/kreuzberg/src/extraction/office_metadata/odt_properties.rs +287 -0
  91. data/vendor/kreuzberg/src/extraction/pptx.rs +3000 -3000
  92. data/vendor/kreuzberg/src/extraction/structured.rs +490 -490
  93. data/vendor/kreuzberg/src/extraction/table.rs +328 -328
  94. data/vendor/kreuzberg/src/extraction/text.rs +269 -269
  95. data/vendor/kreuzberg/src/extraction/xml.rs +333 -333
  96. data/vendor/kreuzberg/src/extractors/archive.rs +446 -425
  97. data/vendor/kreuzberg/src/extractors/bibtex.rs +469 -0
  98. data/vendor/kreuzberg/src/extractors/docbook.rs +502 -0
  99. data/vendor/kreuzberg/src/extractors/docx.rs +367 -479
  100. data/vendor/kreuzberg/src/extractors/email.rs +143 -129
  101. data/vendor/kreuzberg/src/extractors/epub.rs +707 -0
  102. data/vendor/kreuzberg/src/extractors/excel.rs +343 -344
  103. data/vendor/kreuzberg/src/extractors/fictionbook.rs +491 -0
  104. data/vendor/kreuzberg/src/extractors/fictionbook.rs.backup2 +738 -0
  105. data/vendor/kreuzberg/src/extractors/html.rs +393 -410
  106. data/vendor/kreuzberg/src/extractors/image.rs +198 -195
  107. data/vendor/kreuzberg/src/extractors/jats.rs +1051 -0
  108. data/vendor/kreuzberg/src/extractors/jupyter.rs +367 -0
  109. data/vendor/kreuzberg/src/extractors/latex.rs +652 -0
  110. data/vendor/kreuzberg/src/extractors/markdown.rs +700 -0
  111. data/vendor/kreuzberg/src/extractors/mod.rs +365 -268
  112. data/vendor/kreuzberg/src/extractors/odt.rs +628 -0
  113. data/vendor/kreuzberg/src/extractors/opml.rs +634 -0
  114. data/vendor/kreuzberg/src/extractors/orgmode.rs +528 -0
  115. data/vendor/kreuzberg/src/extractors/pdf.rs +493 -496
  116. data/vendor/kreuzberg/src/extractors/pptx.rs +248 -234
  117. data/vendor/kreuzberg/src/extractors/rst.rs +576 -0
  118. data/vendor/kreuzberg/src/extractors/rtf.rs +810 -0
  119. data/vendor/kreuzberg/src/extractors/security.rs +484 -0
  120. data/vendor/kreuzberg/src/extractors/security_tests.rs +367 -0
  121. data/vendor/kreuzberg/src/extractors/structured.rs +140 -126
  122. data/vendor/kreuzberg/src/extractors/text.rs +260 -242
  123. data/vendor/kreuzberg/src/extractors/typst.rs +650 -0
  124. data/vendor/kreuzberg/src/extractors/xml.rs +135 -128
  125. data/vendor/kreuzberg/src/image/dpi.rs +164 -164
  126. data/vendor/kreuzberg/src/image/mod.rs +6 -6
  127. data/vendor/kreuzberg/src/image/preprocessing.rs +417 -417
  128. data/vendor/kreuzberg/src/image/resize.rs +89 -89
  129. data/vendor/kreuzberg/src/keywords/config.rs +154 -154
  130. data/vendor/kreuzberg/src/keywords/mod.rs +237 -237
  131. data/vendor/kreuzberg/src/keywords/processor.rs +267 -267
  132. data/vendor/kreuzberg/src/keywords/rake.rs +293 -294
  133. data/vendor/kreuzberg/src/keywords/types.rs +68 -68
  134. data/vendor/kreuzberg/src/keywords/yake.rs +163 -163
  135. data/vendor/kreuzberg/src/language_detection/mod.rs +942 -942
  136. data/vendor/kreuzberg/src/lib.rs +105 -102
  137. data/vendor/kreuzberg/src/mcp/mod.rs +32 -32
  138. data/vendor/kreuzberg/src/mcp/server.rs +1968 -1966
  139. data/vendor/kreuzberg/src/ocr/cache.rs +469 -469
  140. data/vendor/kreuzberg/src/ocr/error.rs +37 -37
  141. data/vendor/kreuzberg/src/ocr/hocr.rs +216 -216
  142. data/vendor/kreuzberg/src/ocr/mod.rs +58 -58
  143. data/vendor/kreuzberg/src/ocr/processor.rs +863 -847
  144. data/vendor/kreuzberg/src/ocr/table/mod.rs +4 -4
  145. data/vendor/kreuzberg/src/ocr/table/tsv_parser.rs +144 -144
  146. data/vendor/kreuzberg/src/ocr/tesseract_backend.rs +450 -450
  147. data/vendor/kreuzberg/src/ocr/types.rs +393 -393
  148. data/vendor/kreuzberg/src/ocr/utils.rs +47 -47
  149. data/vendor/kreuzberg/src/ocr/validation.rs +206 -206
  150. data/vendor/kreuzberg/src/panic_context.rs +154 -0
  151. data/vendor/kreuzberg/src/pdf/error.rs +122 -122
  152. data/vendor/kreuzberg/src/pdf/images.rs +139 -139
  153. data/vendor/kreuzberg/src/pdf/metadata.rs +346 -346
  154. data/vendor/kreuzberg/src/pdf/mod.rs +50 -50
  155. data/vendor/kreuzberg/src/pdf/rendering.rs +369 -369
  156. data/vendor/kreuzberg/src/pdf/table.rs +393 -420
  157. data/vendor/kreuzberg/src/pdf/text.rs +158 -161
  158. data/vendor/kreuzberg/src/plugins/extractor.rs +1013 -1010
  159. data/vendor/kreuzberg/src/plugins/mod.rs +209 -209
  160. data/vendor/kreuzberg/src/plugins/ocr.rs +620 -629
  161. data/vendor/kreuzberg/src/plugins/processor.rs +642 -641
  162. data/vendor/kreuzberg/src/plugins/registry.rs +1337 -1324
  163. data/vendor/kreuzberg/src/plugins/traits.rs +258 -258
  164. data/vendor/kreuzberg/src/plugins/validator.rs +956 -955
  165. data/vendor/kreuzberg/src/stopwords/mod.rs +1470 -1470
  166. data/vendor/kreuzberg/src/text/mod.rs +19 -19
  167. data/vendor/kreuzberg/src/text/quality.rs +697 -697
  168. data/vendor/kreuzberg/src/text/string_utils.rs +217 -217
  169. data/vendor/kreuzberg/src/text/token_reduction/cjk_utils.rs +164 -164
  170. data/vendor/kreuzberg/src/text/token_reduction/config.rs +100 -100
  171. data/vendor/kreuzberg/src/text/token_reduction/core.rs +796 -796
  172. data/vendor/kreuzberg/src/text/token_reduction/filters.rs +902 -902
  173. data/vendor/kreuzberg/src/text/token_reduction/mod.rs +160 -160
  174. data/vendor/kreuzberg/src/text/token_reduction/semantic.rs +619 -619
  175. data/vendor/kreuzberg/src/text/token_reduction/simd_text.rs +147 -147
  176. data/vendor/kreuzberg/src/types.rs +903 -873
  177. data/vendor/kreuzberg/src/utils/mod.rs +17 -17
  178. data/vendor/kreuzberg/src/utils/quality.rs +959 -959
  179. data/vendor/kreuzberg/src/utils/string_utils.rs +381 -381
  180. data/vendor/kreuzberg/stopwords/af_stopwords.json +53 -53
  181. data/vendor/kreuzberg/stopwords/ar_stopwords.json +482 -482
  182. data/vendor/kreuzberg/stopwords/bg_stopwords.json +261 -261
  183. data/vendor/kreuzberg/stopwords/bn_stopwords.json +400 -400
  184. data/vendor/kreuzberg/stopwords/br_stopwords.json +1205 -1205
  185. data/vendor/kreuzberg/stopwords/ca_stopwords.json +280 -280
  186. data/vendor/kreuzberg/stopwords/cs_stopwords.json +425 -425
  187. data/vendor/kreuzberg/stopwords/da_stopwords.json +172 -172
  188. data/vendor/kreuzberg/stopwords/de_stopwords.json +622 -622
  189. data/vendor/kreuzberg/stopwords/el_stopwords.json +849 -849
  190. data/vendor/kreuzberg/stopwords/en_stopwords.json +1300 -1300
  191. data/vendor/kreuzberg/stopwords/eo_stopwords.json +175 -175
  192. data/vendor/kreuzberg/stopwords/es_stopwords.json +734 -734
  193. data/vendor/kreuzberg/stopwords/et_stopwords.json +37 -37
  194. data/vendor/kreuzberg/stopwords/eu_stopwords.json +100 -100
  195. data/vendor/kreuzberg/stopwords/fa_stopwords.json +801 -801
  196. data/vendor/kreuzberg/stopwords/fi_stopwords.json +849 -849
  197. data/vendor/kreuzberg/stopwords/fr_stopwords.json +693 -693
  198. data/vendor/kreuzberg/stopwords/ga_stopwords.json +111 -111
  199. data/vendor/kreuzberg/stopwords/gl_stopwords.json +162 -162
  200. data/vendor/kreuzberg/stopwords/gu_stopwords.json +226 -226
  201. data/vendor/kreuzberg/stopwords/ha_stopwords.json +41 -41
  202. data/vendor/kreuzberg/stopwords/he_stopwords.json +196 -196
  203. data/vendor/kreuzberg/stopwords/hi_stopwords.json +227 -227
  204. data/vendor/kreuzberg/stopwords/hr_stopwords.json +181 -181
  205. data/vendor/kreuzberg/stopwords/hu_stopwords.json +791 -791
  206. data/vendor/kreuzberg/stopwords/hy_stopwords.json +47 -47
  207. data/vendor/kreuzberg/stopwords/id_stopwords.json +760 -760
  208. data/vendor/kreuzberg/stopwords/it_stopwords.json +634 -634
  209. data/vendor/kreuzberg/stopwords/ja_stopwords.json +136 -136
  210. data/vendor/kreuzberg/stopwords/kn_stopwords.json +84 -84
  211. data/vendor/kreuzberg/stopwords/ko_stopwords.json +681 -681
  212. data/vendor/kreuzberg/stopwords/ku_stopwords.json +64 -64
  213. data/vendor/kreuzberg/stopwords/la_stopwords.json +51 -51
  214. data/vendor/kreuzberg/stopwords/lt_stopwords.json +476 -476
  215. data/vendor/kreuzberg/stopwords/lv_stopwords.json +163 -163
  216. data/vendor/kreuzberg/stopwords/ml_stopwords.json +1 -1
  217. data/vendor/kreuzberg/stopwords/mr_stopwords.json +101 -101
  218. data/vendor/kreuzberg/stopwords/ms_stopwords.json +477 -477
  219. data/vendor/kreuzberg/stopwords/ne_stopwords.json +490 -490
  220. data/vendor/kreuzberg/stopwords/nl_stopwords.json +415 -415
  221. data/vendor/kreuzberg/stopwords/no_stopwords.json +223 -223
  222. data/vendor/kreuzberg/stopwords/pl_stopwords.json +331 -331
  223. data/vendor/kreuzberg/stopwords/pt_stopwords.json +562 -562
  224. data/vendor/kreuzberg/stopwords/ro_stopwords.json +436 -436
  225. data/vendor/kreuzberg/stopwords/ru_stopwords.json +561 -561
  226. data/vendor/kreuzberg/stopwords/si_stopwords.json +193 -193
  227. data/vendor/kreuzberg/stopwords/sk_stopwords.json +420 -420
  228. data/vendor/kreuzberg/stopwords/sl_stopwords.json +448 -448
  229. data/vendor/kreuzberg/stopwords/so_stopwords.json +32 -32
  230. data/vendor/kreuzberg/stopwords/st_stopwords.json +33 -33
  231. data/vendor/kreuzberg/stopwords/sv_stopwords.json +420 -420
  232. data/vendor/kreuzberg/stopwords/sw_stopwords.json +76 -76
  233. data/vendor/kreuzberg/stopwords/ta_stopwords.json +129 -129
  234. data/vendor/kreuzberg/stopwords/te_stopwords.json +54 -54
  235. data/vendor/kreuzberg/stopwords/th_stopwords.json +118 -118
  236. data/vendor/kreuzberg/stopwords/tl_stopwords.json +149 -149
  237. data/vendor/kreuzberg/stopwords/tr_stopwords.json +506 -506
  238. data/vendor/kreuzberg/stopwords/uk_stopwords.json +75 -75
  239. data/vendor/kreuzberg/stopwords/ur_stopwords.json +519 -519
  240. data/vendor/kreuzberg/stopwords/vi_stopwords.json +647 -647
  241. data/vendor/kreuzberg/stopwords/yo_stopwords.json +62 -62
  242. data/vendor/kreuzberg/stopwords/zh_stopwords.json +796 -796
  243. data/vendor/kreuzberg/stopwords/zu_stopwords.json +31 -31
  244. data/vendor/kreuzberg/tests/api_extract_multipart.rs +52 -0
  245. data/vendor/kreuzberg/tests/api_tests.rs +966 -966
  246. data/vendor/kreuzberg/tests/archive_integration.rs +543 -543
  247. data/vendor/kreuzberg/tests/batch_orchestration.rs +556 -542
  248. data/vendor/kreuzberg/tests/batch_processing.rs +316 -304
  249. data/vendor/kreuzberg/tests/bibtex_parity_test.rs +421 -0
  250. data/vendor/kreuzberg/tests/concurrency_stress.rs +525 -509
  251. data/vendor/kreuzberg/tests/config_features.rs +598 -580
  252. data/vendor/kreuzberg/tests/config_loading_tests.rs +415 -439
  253. data/vendor/kreuzberg/tests/core_integration.rs +510 -493
  254. data/vendor/kreuzberg/tests/csv_integration.rs +414 -424
  255. data/vendor/kreuzberg/tests/docbook_extractor_tests.rs +498 -0
  256. data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +122 -124
  257. data/vendor/kreuzberg/tests/docx_vs_pandoc_comparison.rs +370 -0
  258. data/vendor/kreuzberg/tests/email_integration.rs +325 -325
  259. data/vendor/kreuzberg/tests/epub_native_extractor_tests.rs +275 -0
  260. data/vendor/kreuzberg/tests/error_handling.rs +393 -393
  261. data/vendor/kreuzberg/tests/fictionbook_extractor_tests.rs +228 -0
  262. data/vendor/kreuzberg/tests/format_integration.rs +159 -159
  263. data/vendor/kreuzberg/tests/helpers/mod.rs +142 -142
  264. data/vendor/kreuzberg/tests/html_table_test.rs +551 -0
  265. data/vendor/kreuzberg/tests/image_integration.rs +253 -253
  266. data/vendor/kreuzberg/tests/instrumentation_test.rs +139 -0
  267. data/vendor/kreuzberg/tests/jats_extractor_tests.rs +639 -0
  268. data/vendor/kreuzberg/tests/jupyter_extractor_tests.rs +704 -0
  269. data/vendor/kreuzberg/tests/keywords_integration.rs +479 -479
  270. data/vendor/kreuzberg/tests/keywords_quality.rs +509 -509
  271. data/vendor/kreuzberg/tests/latex_extractor_tests.rs +496 -0
  272. data/vendor/kreuzberg/tests/markdown_extractor_tests.rs +490 -0
  273. data/vendor/kreuzberg/tests/mime_detection.rs +428 -428
  274. data/vendor/kreuzberg/tests/ocr_configuration.rs +510 -510
  275. data/vendor/kreuzberg/tests/ocr_errors.rs +676 -676
  276. data/vendor/kreuzberg/tests/ocr_quality.rs +627 -627
  277. data/vendor/kreuzberg/tests/ocr_stress.rs +469 -469
  278. data/vendor/kreuzberg/tests/odt_extractor_tests.rs +695 -0
  279. data/vendor/kreuzberg/tests/opml_extractor_tests.rs +616 -0
  280. data/vendor/kreuzberg/tests/orgmode_extractor_tests.rs +822 -0
  281. data/vendor/kreuzberg/tests/pdf_integration.rs +43 -43
  282. data/vendor/kreuzberg/tests/pipeline_integration.rs +1411 -1412
  283. data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +771 -771
  284. data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +560 -561
  285. data/vendor/kreuzberg/tests/plugin_system.rs +921 -921
  286. data/vendor/kreuzberg/tests/plugin_validator_test.rs +783 -783
  287. data/vendor/kreuzberg/tests/registry_integration_tests.rs +586 -607
  288. data/vendor/kreuzberg/tests/rst_extractor_tests.rs +692 -0
  289. data/vendor/kreuzberg/tests/rtf_extractor_tests.rs +776 -0
  290. data/vendor/kreuzberg/tests/security_validation.rs +415 -404
  291. data/vendor/kreuzberg/tests/stopwords_integration_test.rs +888 -888
  292. data/vendor/kreuzberg/tests/test_fastembed.rs +609 -609
  293. data/vendor/kreuzberg/tests/typst_behavioral_tests.rs +1259 -0
  294. data/vendor/kreuzberg/tests/typst_extractor_tests.rs +647 -0
  295. data/vendor/kreuzberg/tests/xlsx_metadata_extraction_test.rs +87 -87
  296. data/vendor/rb-sys/.cargo-ok +1 -0
  297. data/vendor/rb-sys/.cargo_vcs_info.json +6 -0
  298. data/vendor/rb-sys/Cargo.lock +393 -0
  299. data/vendor/rb-sys/Cargo.toml +70 -0
  300. data/vendor/rb-sys/Cargo.toml.orig +57 -0
  301. data/vendor/rb-sys/LICENSE-APACHE +190 -0
  302. data/vendor/rb-sys/LICENSE-MIT +21 -0
  303. data/vendor/rb-sys/bin/release.sh +21 -0
  304. data/vendor/rb-sys/build/features.rs +108 -0
  305. data/vendor/rb-sys/build/main.rs +246 -0
  306. data/vendor/rb-sys/build/stable_api_config.rs +153 -0
  307. data/vendor/rb-sys/build/version.rs +48 -0
  308. data/vendor/rb-sys/readme.md +36 -0
  309. data/vendor/rb-sys/src/bindings.rs +21 -0
  310. data/vendor/rb-sys/src/hidden.rs +11 -0
  311. data/vendor/rb-sys/src/lib.rs +34 -0
  312. data/vendor/rb-sys/src/macros.rs +371 -0
  313. data/vendor/rb-sys/src/memory.rs +53 -0
  314. data/vendor/rb-sys/src/ruby_abi_version.rs +38 -0
  315. data/vendor/rb-sys/src/special_consts.rs +31 -0
  316. data/vendor/rb-sys/src/stable_api/compiled.c +179 -0
  317. data/vendor/rb-sys/src/stable_api/compiled.rs +257 -0
  318. data/vendor/rb-sys/src/stable_api/ruby_2_6.rs +316 -0
  319. data/vendor/rb-sys/src/stable_api/ruby_2_7.rs +316 -0
  320. data/vendor/rb-sys/src/stable_api/ruby_3_0.rs +324 -0
  321. data/vendor/rb-sys/src/stable_api/ruby_3_1.rs +317 -0
  322. data/vendor/rb-sys/src/stable_api/ruby_3_2.rs +315 -0
  323. data/vendor/rb-sys/src/stable_api/ruby_3_3.rs +326 -0
  324. data/vendor/rb-sys/src/stable_api/ruby_3_4.rs +327 -0
  325. data/vendor/rb-sys/src/stable_api.rs +261 -0
  326. data/vendor/rb-sys/src/symbol.rs +31 -0
  327. data/vendor/rb-sys/src/tracking_allocator.rs +332 -0
  328. data/vendor/rb-sys/src/utils.rs +89 -0
  329. data/vendor/rb-sys/src/value_type.rs +7 -0
  330. metadata +90 -95
  331. data/pkg/kreuzberg-4.0.0.rc1.gem +0 -0
  332. data/spec/examples.txt +0 -104
  333. data/vendor/kreuzberg/src/bin/profile_extract.rs +0 -455
  334. data/vendor/kreuzberg/src/extraction/pandoc/batch.rs +0 -275
  335. data/vendor/kreuzberg/src/extraction/pandoc/mime_types.rs +0 -178
  336. data/vendor/kreuzberg/src/extraction/pandoc/mod.rs +0 -491
  337. data/vendor/kreuzberg/src/extraction/pandoc/server.rs +0 -496
  338. data/vendor/kreuzberg/src/extraction/pandoc/subprocess.rs +0 -1188
  339. data/vendor/kreuzberg/src/extraction/pandoc/version.rs +0 -162
  340. data/vendor/kreuzberg/src/extractors/pandoc.rs +0 -201
  341. data/vendor/kreuzberg/tests/chunking_offset_demo.rs +0 -92
  342. data/vendor/kreuzberg/tests/pandoc_integration.rs +0 -503
@@ -1,469 +1,469 @@
1
- use super::error::OcrError;
2
- use super::utils::compute_hash;
3
- use crate::types::OcrExtractionResult;
4
- use std::fs;
5
- use std::path::PathBuf;
6
-
7
- pub struct OcrCache {
8
- cache_dir: PathBuf,
9
- }
10
-
11
- impl OcrCache {
12
- pub fn new(cache_dir: Option<PathBuf>) -> Result<Self, OcrError> {
13
- let cache_dir = cache_dir.unwrap_or_else(|| {
14
- let mut path = std::env::current_dir().unwrap_or_else(|_| PathBuf::from("."));
15
- path.push(".kreuzberg");
16
- path.push("ocr");
17
- path
18
- });
19
-
20
- fs::create_dir_all(&cache_dir)
21
- .map_err(|e| OcrError::CacheError(format!("Failed to create cache directory: {}", e)))?;
22
-
23
- Ok(Self { cache_dir })
24
- }
25
-
26
- fn get_cache_path(&self, cache_key: &str) -> PathBuf {
27
- self.cache_dir.join(format!("{}.msgpack", cache_key))
28
- }
29
-
30
- pub fn get_cached_result(
31
- &self,
32
- image_hash: &str,
33
- backend: &str,
34
- config: &str,
35
- ) -> Result<Option<OcrExtractionResult>, OcrError> {
36
- let cache_key = self.generate_cache_key(image_hash, backend, config);
37
- let cache_path = self.get_cache_path(&cache_key);
38
-
39
- if !cache_path.exists() {
40
- return Ok(None);
41
- }
42
-
43
- let cached_bytes =
44
- fs::read(&cache_path).map_err(|e| OcrError::CacheError(format!("Failed to read cache file: {}", e)))?;
45
-
46
- let result: OcrExtractionResult = rmp_serde::from_slice(&cached_bytes)
47
- .map_err(|e| OcrError::CacheError(format!("Failed to deserialize cache: {}", e)))?;
48
-
49
- Ok(Some(result))
50
- }
51
-
52
- pub fn set_cached_result(
53
- &self,
54
- image_hash: &str,
55
- backend: &str,
56
- config: &str,
57
- result: &OcrExtractionResult,
58
- ) -> Result<(), OcrError> {
59
- let cache_key = self.generate_cache_key(image_hash, backend, config);
60
- let cache_path = self.get_cache_path(&cache_key);
61
-
62
- let serialized = rmp_serde::to_vec(result)
63
- .map_err(|e| OcrError::CacheError(format!("Failed to serialize result: {}", e)))?;
64
-
65
- let pid = std::process::id();
66
- let thread_id = std::thread::current().id();
67
- let timestamp = std::time::SystemTime::now()
68
- .duration_since(std::time::UNIX_EPOCH)
69
- .unwrap_or_default()
70
- .as_nanos();
71
- let temp_name = format!("{}.tmp.{}.{:?}.{}", cache_key, pid, thread_id, timestamp);
72
- let temp_path = self.cache_dir.join(temp_name);
73
-
74
- fs::write(&temp_path, &serialized)
75
- .map_err(|e| OcrError::CacheError(format!("Failed to write temp cache file: {}", e)))?;
76
-
77
- fs::rename(&temp_path, &cache_path).map_err(|e| {
78
- let _ = fs::remove_file(&temp_path);
79
- OcrError::CacheError(format!("Failed to rename cache file: {}", e))
80
- })?;
81
-
82
- Ok(())
83
- }
84
-
85
- fn generate_cache_key(&self, image_hash: &str, backend: &str, config: &str) -> String {
86
- let cache_string = format!(
87
- "image_hash={}&ocr_backend={}&ocr_config={}",
88
- image_hash, backend, config
89
- );
90
-
91
- compute_hash(&cache_string)
92
- }
93
-
94
- pub fn clear(&self) -> Result<(), OcrError> {
95
- if !self.cache_dir.exists() {
96
- return Ok(());
97
- }
98
-
99
- let entries = fs::read_dir(&self.cache_dir)
100
- .map_err(|e| OcrError::CacheError(format!("Failed to read cache directory: {}", e)))?;
101
-
102
- for entry in entries.flatten() {
103
- if let Some(ext) = entry.path().extension()
104
- && ext == "msgpack"
105
- {
106
- let _ = fs::remove_file(entry.path());
107
- }
108
- }
109
-
110
- Ok(())
111
- }
112
-
113
- pub fn get_stats(&self) -> Result<OcrCacheStats, OcrError> {
114
- if !self.cache_dir.exists() {
115
- return Ok(OcrCacheStats::default());
116
- }
117
-
118
- let entries = fs::read_dir(&self.cache_dir)
119
- .map_err(|e| OcrError::CacheError(format!("Failed to read cache directory: {}", e)))?;
120
-
121
- let mut total_files = 0;
122
- let mut total_size_bytes = 0u64;
123
-
124
- for entry in entries.flatten() {
125
- if let Some(ext) = entry.path().extension()
126
- && ext == "msgpack"
127
- {
128
- total_files += 1;
129
- if let Ok(metadata) = entry.metadata() {
130
- total_size_bytes += metadata.len();
131
- }
132
- }
133
- }
134
-
135
- Ok(OcrCacheStats {
136
- total_files,
137
- total_size_mb: total_size_bytes as f64 / 1024.0 / 1024.0,
138
- })
139
- }
140
- }
141
-
142
- #[derive(Debug, Clone, Default)]
143
- pub struct OcrCacheStats {
144
- pub total_files: usize,
145
- pub total_size_mb: f64,
146
- }
147
-
148
- #[cfg(test)]
149
- mod tests {
150
- use super::*;
151
- use std::collections::HashMap;
152
-
153
- #[test]
154
- fn test_cache_get_set() {
155
- let temp_dir = tempfile::tempdir().unwrap();
156
- let cache = OcrCache::new(Some(temp_dir.path().to_path_buf())).unwrap();
157
-
158
- let result = OcrExtractionResult {
159
- content: "Test OCR result".to_string(),
160
- mime_type: "text/plain".to_string(),
161
- metadata: HashMap::new(),
162
- tables: Vec::new(),
163
- };
164
-
165
- cache.set_cached_result("abc123", "tesseract", "eng", &result).unwrap();
166
-
167
- let cached = cache.get_cached_result("abc123", "tesseract", "eng").unwrap();
168
-
169
- assert!(cached.is_some());
170
- assert_eq!(cached.unwrap().content, "Test OCR result");
171
- }
172
-
173
- #[test]
174
- fn test_cache_miss() {
175
- let temp_dir = tempfile::tempdir().unwrap();
176
- let cache = OcrCache::new(Some(temp_dir.path().to_path_buf())).unwrap();
177
-
178
- let cached = cache.get_cached_result("nonexistent", "tesseract", "eng").unwrap();
179
-
180
- assert!(cached.is_none());
181
- }
182
-
183
- #[test]
184
- fn test_cache_clear() {
185
- let temp_dir = tempfile::tempdir().unwrap();
186
- let cache = OcrCache::new(Some(temp_dir.path().to_path_buf())).unwrap();
187
-
188
- let result = OcrExtractionResult {
189
- content: "Test".to_string(),
190
- mime_type: "text/plain".to_string(),
191
- metadata: HashMap::new(),
192
- tables: Vec::new(),
193
- };
194
-
195
- cache.set_cached_result("test", "tesseract", "eng", &result).unwrap();
196
-
197
- cache.clear().unwrap();
198
-
199
- let cached = cache.get_cached_result("test", "tesseract", "eng").unwrap();
200
- assert!(cached.is_none());
201
- }
202
-
203
- #[test]
204
- fn test_cache_stats() {
205
- let temp_dir = tempfile::tempdir().unwrap();
206
- let cache = OcrCache::new(Some(temp_dir.path().to_path_buf())).unwrap();
207
-
208
- let stats = cache.get_stats().unwrap();
209
- assert_eq!(stats.total_files, 0);
210
-
211
- let result = OcrExtractionResult {
212
- content: "Test".to_string(),
213
- mime_type: "text/plain".to_string(),
214
- metadata: HashMap::new(),
215
- tables: Vec::new(),
216
- };
217
-
218
- cache.set_cached_result("test", "tesseract", "eng", &result).unwrap();
219
-
220
- let stats = cache.get_stats().unwrap();
221
- assert_eq!(stats.total_files, 1);
222
- assert!(stats.total_size_mb > 0.0);
223
- }
224
-
225
- #[test]
226
- fn test_cache_key_generation_deterministic() {
227
- let temp_dir = tempfile::tempdir().unwrap();
228
- let cache = OcrCache::new(Some(temp_dir.path().to_path_buf())).unwrap();
229
-
230
- let key1 = cache.generate_cache_key("abc123", "tesseract", "eng");
231
- let key2 = cache.generate_cache_key("abc123", "tesseract", "eng");
232
-
233
- assert_eq!(key1, key2);
234
- assert_eq!(key1.len(), 16);
235
- }
236
-
237
- #[test]
238
- fn test_cache_key_generation_different_inputs() {
239
- let temp_dir = tempfile::tempdir().unwrap();
240
- let cache = OcrCache::new(Some(temp_dir.path().to_path_buf())).unwrap();
241
-
242
- let key1 = cache.generate_cache_key("abc123", "tesseract", "eng");
243
- let key2 = cache.generate_cache_key("def456", "tesseract", "eng");
244
- let key3 = cache.generate_cache_key("abc123", "easyocr", "eng");
245
- let key4 = cache.generate_cache_key("abc123", "tesseract", "fra");
246
-
247
- assert_ne!(key1, key2);
248
- assert_ne!(key1, key3);
249
- assert_ne!(key1, key4);
250
- }
251
-
252
- #[test]
253
- fn test_cache_multiple_entries() {
254
- let temp_dir = tempfile::tempdir().unwrap();
255
- let cache = OcrCache::new(Some(temp_dir.path().to_path_buf())).unwrap();
256
-
257
- let result1 = OcrExtractionResult {
258
- content: "First".to_string(),
259
- mime_type: "text/plain".to_string(),
260
- metadata: HashMap::new(),
261
- tables: Vec::new(),
262
- };
263
-
264
- let result2 = OcrExtractionResult {
265
- content: "Second".to_string(),
266
- mime_type: "text/plain".to_string(),
267
- metadata: HashMap::new(),
268
- tables: Vec::new(),
269
- };
270
-
271
- cache.set_cached_result("hash1", "tesseract", "eng", &result1).unwrap();
272
- cache.set_cached_result("hash2", "tesseract", "eng", &result2).unwrap();
273
-
274
- let stats = cache.get_stats().unwrap();
275
- assert_eq!(stats.total_files, 2);
276
-
277
- let retrieved1 = cache.get_cached_result("hash1", "tesseract", "eng").unwrap();
278
- let retrieved2 = cache.get_cached_result("hash2", "tesseract", "eng").unwrap();
279
-
280
- assert_eq!(retrieved1.unwrap().content, "First");
281
- assert_eq!(retrieved2.unwrap().content, "Second");
282
- }
283
-
284
- #[test]
285
- fn test_cache_overwrite() {
286
- let temp_dir = tempfile::tempdir().unwrap();
287
- let cache = OcrCache::new(Some(temp_dir.path().to_path_buf())).unwrap();
288
-
289
- let result1 = OcrExtractionResult {
290
- content: "Original".to_string(),
291
- mime_type: "text/plain".to_string(),
292
- metadata: HashMap::new(),
293
- tables: Vec::new(),
294
- };
295
-
296
- let result2 = OcrExtractionResult {
297
- content: "Updated".to_string(),
298
- mime_type: "text/plain".to_string(),
299
- metadata: HashMap::new(),
300
- tables: Vec::new(),
301
- };
302
-
303
- cache.set_cached_result("test", "tesseract", "eng", &result1).unwrap();
304
- cache.set_cached_result("test", "tesseract", "eng", &result2).unwrap();
305
-
306
- let retrieved = cache.get_cached_result("test", "tesseract", "eng").unwrap();
307
- assert_eq!(retrieved.unwrap().content, "Updated");
308
-
309
- let stats = cache.get_stats().unwrap();
310
- assert_eq!(stats.total_files, 1);
311
- }
312
-
313
- #[test]
314
- fn test_cache_with_tables() {
315
- let temp_dir = tempfile::tempdir().unwrap();
316
- let cache = OcrCache::new(Some(temp_dir.path().to_path_buf())).unwrap();
317
-
318
- use crate::types::OcrTable;
319
-
320
- let table = OcrTable {
321
- cells: vec![vec!["A".to_string(), "B".to_string()]],
322
- markdown: "| A | B |".to_string(),
323
- page_number: 0,
324
- };
325
-
326
- let result = OcrExtractionResult {
327
- content: "Content with table".to_string(),
328
- mime_type: "text/markdown".to_string(),
329
- metadata: HashMap::new(),
330
- tables: vec![table],
331
- };
332
-
333
- cache.set_cached_result("test", "tesseract", "eng", &result).unwrap();
334
-
335
- let retrieved = cache.get_cached_result("test", "tesseract", "eng").unwrap().unwrap();
336
- assert_eq!(retrieved.tables.len(), 1);
337
- assert_eq!(retrieved.tables[0].cells[0][0], "A");
338
- }
339
-
340
- #[test]
341
- fn test_cache_with_metadata() {
342
- let temp_dir = tempfile::tempdir().unwrap();
343
- let cache = OcrCache::new(Some(temp_dir.path().to_path_buf())).unwrap();
344
-
345
- let mut metadata = HashMap::new();
346
- metadata.insert("language".to_string(), serde_json::Value::String("eng".to_string()));
347
- metadata.insert("confidence".to_string(), serde_json::Value::String("95.5".to_string()));
348
-
349
- let result = OcrExtractionResult {
350
- content: "Content".to_string(),
351
- mime_type: "text/plain".to_string(),
352
- metadata,
353
- tables: Vec::new(),
354
- };
355
-
356
- cache.set_cached_result("test", "tesseract", "eng", &result).unwrap();
357
-
358
- let retrieved = cache.get_cached_result("test", "tesseract", "eng").unwrap().unwrap();
359
- assert_eq!(
360
- retrieved.metadata.get("language").unwrap(),
361
- &serde_json::Value::String("eng".to_string())
362
- );
363
- assert_eq!(
364
- retrieved.metadata.get("confidence").unwrap(),
365
- &serde_json::Value::String("95.5".to_string())
366
- );
367
- }
368
-
369
- #[test]
370
- fn test_cache_clear_selective() {
371
- let temp_dir = tempfile::tempdir().unwrap();
372
- let cache = OcrCache::new(Some(temp_dir.path().to_path_buf())).unwrap();
373
-
374
- let result = OcrExtractionResult {
375
- content: "Test".to_string(),
376
- mime_type: "text/plain".to_string(),
377
- metadata: HashMap::new(),
378
- tables: Vec::new(),
379
- };
380
-
381
- cache.set_cached_result("test1", "tesseract", "eng", &result).unwrap();
382
- cache.set_cached_result("test2", "tesseract", "eng", &result).unwrap();
383
-
384
- fs::write(temp_dir.path().join("other.txt"), "not a msgpack file").unwrap();
385
-
386
- cache.clear().unwrap();
387
-
388
- assert!(cache.get_cached_result("test1", "tesseract", "eng").unwrap().is_none());
389
- assert!(cache.get_cached_result("test2", "tesseract", "eng").unwrap().is_none());
390
-
391
- assert!(temp_dir.path().join("other.txt").exists());
392
- }
393
-
394
- #[test]
395
- fn test_cache_stats_nonexistent_dir() {
396
- let temp_dir = tempfile::tempdir().unwrap();
397
- let cache_path = temp_dir.path().join("nonexistent");
398
- let cache = OcrCache { cache_dir: cache_path };
399
-
400
- let stats = cache.get_stats().unwrap();
401
- assert_eq!(stats.total_files, 0);
402
- assert_eq!(stats.total_size_mb, 0.0);
403
- }
404
-
405
- #[test]
406
- fn test_cache_clear_nonexistent_dir() {
407
- let temp_dir = tempfile::tempdir().unwrap();
408
- let cache_path = temp_dir.path().join("nonexistent");
409
- let cache = OcrCache { cache_dir: cache_path };
410
-
411
- assert!(cache.clear().is_ok());
412
- }
413
-
414
- #[test]
415
- fn test_cache_get_path() {
416
- let temp_dir = tempfile::tempdir().unwrap();
417
- let cache = OcrCache::new(Some(temp_dir.path().to_path_buf())).unwrap();
418
-
419
- let path = cache.get_cache_path("abc123");
420
-
421
- assert!(path.to_string_lossy().contains("abc123.msgpack"));
422
- assert_eq!(path.parent().unwrap(), temp_dir.path());
423
- }
424
-
425
- #[test]
426
- fn test_cache_stats_default() {
427
- let stats = OcrCacheStats::default();
428
- assert_eq!(stats.total_files, 0);
429
- assert_eq!(stats.total_size_mb, 0.0);
430
- }
431
-
432
- #[test]
433
- fn test_cache_empty_content() {
434
- let temp_dir = tempfile::tempdir().unwrap();
435
- let cache = OcrCache::new(Some(temp_dir.path().to_path_buf())).unwrap();
436
-
437
- let result = OcrExtractionResult {
438
- content: String::new(),
439
- mime_type: "text/plain".to_string(),
440
- metadata: HashMap::new(),
441
- tables: Vec::new(),
442
- };
443
-
444
- cache.set_cached_result("empty", "tesseract", "eng", &result).unwrap();
445
-
446
- let retrieved = cache.get_cached_result("empty", "tesseract", "eng").unwrap();
447
- assert_eq!(retrieved.unwrap().content, "");
448
- }
449
-
450
- #[test]
451
- fn test_cache_large_content() {
452
- let temp_dir = tempfile::tempdir().unwrap();
453
- let cache = OcrCache::new(Some(temp_dir.path().to_path_buf())).unwrap();
454
-
455
- let large_content = "x".repeat(10_000);
456
-
457
- let result = OcrExtractionResult {
458
- content: large_content.clone(),
459
- mime_type: "text/plain".to_string(),
460
- metadata: HashMap::new(),
461
- tables: Vec::new(),
462
- };
463
-
464
- cache.set_cached_result("large", "tesseract", "eng", &result).unwrap();
465
-
466
- let retrieved = cache.get_cached_result("large", "tesseract", "eng").unwrap();
467
- assert_eq!(retrieved.unwrap().content.len(), 10_000);
468
- }
469
- }
1
+ use super::error::OcrError;
2
+ use super::utils::compute_hash;
3
+ use crate::types::OcrExtractionResult;
4
+ use std::fs;
5
+ use std::path::PathBuf;
6
+
7
+ pub struct OcrCache {
8
+ cache_dir: PathBuf,
9
+ }
10
+
11
+ impl OcrCache {
12
+ pub fn new(cache_dir: Option<PathBuf>) -> Result<Self, OcrError> {
13
+ let cache_dir = cache_dir.unwrap_or_else(|| {
14
+ let mut path = std::env::current_dir().unwrap_or_else(|_| PathBuf::from("."));
15
+ path.push(".kreuzberg");
16
+ path.push("ocr");
17
+ path
18
+ });
19
+
20
+ fs::create_dir_all(&cache_dir)
21
+ .map_err(|e| OcrError::CacheError(format!("Failed to create cache directory: {}", e)))?;
22
+
23
+ Ok(Self { cache_dir })
24
+ }
25
+
26
+ fn get_cache_path(&self, cache_key: &str) -> PathBuf {
27
+ self.cache_dir.join(format!("{}.msgpack", cache_key))
28
+ }
29
+
30
+ pub fn get_cached_result(
31
+ &self,
32
+ image_hash: &str,
33
+ backend: &str,
34
+ config: &str,
35
+ ) -> Result<Option<OcrExtractionResult>, OcrError> {
36
+ let cache_key = self.generate_cache_key(image_hash, backend, config);
37
+ let cache_path = self.get_cache_path(&cache_key);
38
+
39
+ if !cache_path.exists() {
40
+ return Ok(None);
41
+ }
42
+
43
+ let cached_bytes =
44
+ fs::read(&cache_path).map_err(|e| OcrError::CacheError(format!("Failed to read cache file: {}", e)))?;
45
+
46
+ let result: OcrExtractionResult = rmp_serde::from_slice(&cached_bytes)
47
+ .map_err(|e| OcrError::CacheError(format!("Failed to deserialize cache: {}", e)))?;
48
+
49
+ Ok(Some(result))
50
+ }
51
+
52
+ pub fn set_cached_result(
53
+ &self,
54
+ image_hash: &str,
55
+ backend: &str,
56
+ config: &str,
57
+ result: &OcrExtractionResult,
58
+ ) -> Result<(), OcrError> {
59
+ let cache_key = self.generate_cache_key(image_hash, backend, config);
60
+ let cache_path = self.get_cache_path(&cache_key);
61
+
62
+ let serialized = rmp_serde::to_vec(result)
63
+ .map_err(|e| OcrError::CacheError(format!("Failed to serialize result: {}", e)))?;
64
+
65
+ let pid = std::process::id();
66
+ let thread_id = std::thread::current().id();
67
+ let timestamp = std::time::SystemTime::now()
68
+ .duration_since(std::time::UNIX_EPOCH)
69
+ .unwrap_or_default()
70
+ .as_nanos();
71
+ let temp_name = format!("{}.tmp.{}.{:?}.{}", cache_key, pid, thread_id, timestamp);
72
+ let temp_path = self.cache_dir.join(temp_name);
73
+
74
+ fs::write(&temp_path, &serialized)
75
+ .map_err(|e| OcrError::CacheError(format!("Failed to write temp cache file: {}", e)))?;
76
+
77
+ fs::rename(&temp_path, &cache_path).map_err(|e| {
78
+ let _ = fs::remove_file(&temp_path);
79
+ OcrError::CacheError(format!("Failed to rename cache file: {}", e))
80
+ })?;
81
+
82
+ Ok(())
83
+ }
84
+
85
+ fn generate_cache_key(&self, image_hash: &str, backend: &str, config: &str) -> String {
86
+ let cache_string = format!(
87
+ "image_hash={}&ocr_backend={}&ocr_config={}",
88
+ image_hash, backend, config
89
+ );
90
+
91
+ compute_hash(&cache_string)
92
+ }
93
+
94
+ pub fn clear(&self) -> Result<(), OcrError> {
95
+ if !self.cache_dir.exists() {
96
+ return Ok(());
97
+ }
98
+
99
+ let entries = fs::read_dir(&self.cache_dir)
100
+ .map_err(|e| OcrError::CacheError(format!("Failed to read cache directory: {}", e)))?;
101
+
102
+ for entry in entries.flatten() {
103
+ if let Some(ext) = entry.path().extension()
104
+ && ext == "msgpack"
105
+ {
106
+ let _ = fs::remove_file(entry.path());
107
+ }
108
+ }
109
+
110
+ Ok(())
111
+ }
112
+
113
+ pub fn get_stats(&self) -> Result<OcrCacheStats, OcrError> {
114
+ if !self.cache_dir.exists() {
115
+ return Ok(OcrCacheStats::default());
116
+ }
117
+
118
+ let entries = fs::read_dir(&self.cache_dir)
119
+ .map_err(|e| OcrError::CacheError(format!("Failed to read cache directory: {}", e)))?;
120
+
121
+ let mut total_files = 0;
122
+ let mut total_size_bytes = 0u64;
123
+
124
+ for entry in entries.flatten() {
125
+ if let Some(ext) = entry.path().extension()
126
+ && ext == "msgpack"
127
+ {
128
+ total_files += 1;
129
+ if let Ok(metadata) = entry.metadata() {
130
+ total_size_bytes += metadata.len();
131
+ }
132
+ }
133
+ }
134
+
135
+ Ok(OcrCacheStats {
136
+ total_files,
137
+ total_size_mb: total_size_bytes as f64 / 1024.0 / 1024.0,
138
+ })
139
+ }
140
+ }
141
+
142
+ #[derive(Debug, Clone, Default)]
143
+ pub struct OcrCacheStats {
144
+ pub total_files: usize,
145
+ pub total_size_mb: f64,
146
+ }
147
+
148
+ #[cfg(test)]
149
+ mod tests {
150
+ use super::*;
151
+ use std::collections::HashMap;
152
+
153
+ #[test]
154
+ fn test_cache_get_set() {
155
+ let temp_dir = tempfile::tempdir().unwrap();
156
+ let cache = OcrCache::new(Some(temp_dir.path().to_path_buf())).unwrap();
157
+
158
+ let result = OcrExtractionResult {
159
+ content: "Test OCR result".to_string(),
160
+ mime_type: "text/plain".to_string(),
161
+ metadata: HashMap::new(),
162
+ tables: Vec::new(),
163
+ };
164
+
165
+ cache.set_cached_result("abc123", "tesseract", "eng", &result).unwrap();
166
+
167
+ let cached = cache.get_cached_result("abc123", "tesseract", "eng").unwrap();
168
+
169
+ assert!(cached.is_some());
170
+ assert_eq!(cached.unwrap().content, "Test OCR result");
171
+ }
172
+
173
+ #[test]
174
+ fn test_cache_miss() {
175
+ let temp_dir = tempfile::tempdir().unwrap();
176
+ let cache = OcrCache::new(Some(temp_dir.path().to_path_buf())).unwrap();
177
+
178
+ let cached = cache.get_cached_result("nonexistent", "tesseract", "eng").unwrap();
179
+
180
+ assert!(cached.is_none());
181
+ }
182
+
183
+ #[test]
184
+ fn test_cache_clear() {
185
+ let temp_dir = tempfile::tempdir().unwrap();
186
+ let cache = OcrCache::new(Some(temp_dir.path().to_path_buf())).unwrap();
187
+
188
+ let result = OcrExtractionResult {
189
+ content: "Test".to_string(),
190
+ mime_type: "text/plain".to_string(),
191
+ metadata: HashMap::new(),
192
+ tables: Vec::new(),
193
+ };
194
+
195
+ cache.set_cached_result("test", "tesseract", "eng", &result).unwrap();
196
+
197
+ cache.clear().unwrap();
198
+
199
+ let cached = cache.get_cached_result("test", "tesseract", "eng").unwrap();
200
+ assert!(cached.is_none());
201
+ }
202
+
203
+ #[test]
204
+ fn test_cache_stats() {
205
+ let temp_dir = tempfile::tempdir().unwrap();
206
+ let cache = OcrCache::new(Some(temp_dir.path().to_path_buf())).unwrap();
207
+
208
+ let stats = cache.get_stats().unwrap();
209
+ assert_eq!(stats.total_files, 0);
210
+
211
+ let result = OcrExtractionResult {
212
+ content: "Test".to_string(),
213
+ mime_type: "text/plain".to_string(),
214
+ metadata: HashMap::new(),
215
+ tables: Vec::new(),
216
+ };
217
+
218
+ cache.set_cached_result("test", "tesseract", "eng", &result).unwrap();
219
+
220
+ let stats = cache.get_stats().unwrap();
221
+ assert_eq!(stats.total_files, 1);
222
+ assert!(stats.total_size_mb > 0.0);
223
+ }
224
+
225
+ #[test]
226
+ fn test_cache_key_generation_deterministic() {
227
+ let temp_dir = tempfile::tempdir().unwrap();
228
+ let cache = OcrCache::new(Some(temp_dir.path().to_path_buf())).unwrap();
229
+
230
+ let key1 = cache.generate_cache_key("abc123", "tesseract", "eng");
231
+ let key2 = cache.generate_cache_key("abc123", "tesseract", "eng");
232
+
233
+ assert_eq!(key1, key2);
234
+ assert_eq!(key1.len(), 16);
235
+ }
236
+
237
+ #[test]
238
+ fn test_cache_key_generation_different_inputs() {
239
+ let temp_dir = tempfile::tempdir().unwrap();
240
+ let cache = OcrCache::new(Some(temp_dir.path().to_path_buf())).unwrap();
241
+
242
+ let key1 = cache.generate_cache_key("abc123", "tesseract", "eng");
243
+ let key2 = cache.generate_cache_key("def456", "tesseract", "eng");
244
+ let key3 = cache.generate_cache_key("abc123", "easyocr", "eng");
245
+ let key4 = cache.generate_cache_key("abc123", "tesseract", "fra");
246
+
247
+ assert_ne!(key1, key2);
248
+ assert_ne!(key1, key3);
249
+ assert_ne!(key1, key4);
250
+ }
251
+
252
+ #[test]
253
+ fn test_cache_multiple_entries() {
254
+ let temp_dir = tempfile::tempdir().unwrap();
255
+ let cache = OcrCache::new(Some(temp_dir.path().to_path_buf())).unwrap();
256
+
257
+ let result1 = OcrExtractionResult {
258
+ content: "First".to_string(),
259
+ mime_type: "text/plain".to_string(),
260
+ metadata: HashMap::new(),
261
+ tables: Vec::new(),
262
+ };
263
+
264
+ let result2 = OcrExtractionResult {
265
+ content: "Second".to_string(),
266
+ mime_type: "text/plain".to_string(),
267
+ metadata: HashMap::new(),
268
+ tables: Vec::new(),
269
+ };
270
+
271
+ cache.set_cached_result("hash1", "tesseract", "eng", &result1).unwrap();
272
+ cache.set_cached_result("hash2", "tesseract", "eng", &result2).unwrap();
273
+
274
+ let stats = cache.get_stats().unwrap();
275
+ assert_eq!(stats.total_files, 2);
276
+
277
+ let retrieved1 = cache.get_cached_result("hash1", "tesseract", "eng").unwrap();
278
+ let retrieved2 = cache.get_cached_result("hash2", "tesseract", "eng").unwrap();
279
+
280
+ assert_eq!(retrieved1.unwrap().content, "First");
281
+ assert_eq!(retrieved2.unwrap().content, "Second");
282
+ }
283
+
284
+ #[test]
285
+ fn test_cache_overwrite() {
286
+ let temp_dir = tempfile::tempdir().unwrap();
287
+ let cache = OcrCache::new(Some(temp_dir.path().to_path_buf())).unwrap();
288
+
289
+ let result1 = OcrExtractionResult {
290
+ content: "Original".to_string(),
291
+ mime_type: "text/plain".to_string(),
292
+ metadata: HashMap::new(),
293
+ tables: Vec::new(),
294
+ };
295
+
296
+ let result2 = OcrExtractionResult {
297
+ content: "Updated".to_string(),
298
+ mime_type: "text/plain".to_string(),
299
+ metadata: HashMap::new(),
300
+ tables: Vec::new(),
301
+ };
302
+
303
+ cache.set_cached_result("test", "tesseract", "eng", &result1).unwrap();
304
+ cache.set_cached_result("test", "tesseract", "eng", &result2).unwrap();
305
+
306
+ let retrieved = cache.get_cached_result("test", "tesseract", "eng").unwrap();
307
+ assert_eq!(retrieved.unwrap().content, "Updated");
308
+
309
+ let stats = cache.get_stats().unwrap();
310
+ assert_eq!(stats.total_files, 1);
311
+ }
312
+
313
+ #[test]
314
+ fn test_cache_with_tables() {
315
+ let temp_dir = tempfile::tempdir().unwrap();
316
+ let cache = OcrCache::new(Some(temp_dir.path().to_path_buf())).unwrap();
317
+
318
+ use crate::types::OcrTable;
319
+
320
+ let table = OcrTable {
321
+ cells: vec![vec!["A".to_string(), "B".to_string()]],
322
+ markdown: "| A | B |".to_string(),
323
+ page_number: 0,
324
+ };
325
+
326
+ let result = OcrExtractionResult {
327
+ content: "Content with table".to_string(),
328
+ mime_type: "text/markdown".to_string(),
329
+ metadata: HashMap::new(),
330
+ tables: vec![table],
331
+ };
332
+
333
+ cache.set_cached_result("test", "tesseract", "eng", &result).unwrap();
334
+
335
+ let retrieved = cache.get_cached_result("test", "tesseract", "eng").unwrap().unwrap();
336
+ assert_eq!(retrieved.tables.len(), 1);
337
+ assert_eq!(retrieved.tables[0].cells[0][0], "A");
338
+ }
339
+
340
+ #[test]
341
+ fn test_cache_with_metadata() {
342
+ let temp_dir = tempfile::tempdir().unwrap();
343
+ let cache = OcrCache::new(Some(temp_dir.path().to_path_buf())).unwrap();
344
+
345
+ let mut metadata = HashMap::new();
346
+ metadata.insert("language".to_string(), serde_json::Value::String("eng".to_string()));
347
+ metadata.insert("confidence".to_string(), serde_json::Value::String("95.5".to_string()));
348
+
349
+ let result = OcrExtractionResult {
350
+ content: "Content".to_string(),
351
+ mime_type: "text/plain".to_string(),
352
+ metadata,
353
+ tables: Vec::new(),
354
+ };
355
+
356
+ cache.set_cached_result("test", "tesseract", "eng", &result).unwrap();
357
+
358
+ let retrieved = cache.get_cached_result("test", "tesseract", "eng").unwrap().unwrap();
359
+ assert_eq!(
360
+ retrieved.metadata.get("language").unwrap(),
361
+ &serde_json::Value::String("eng".to_string())
362
+ );
363
+ assert_eq!(
364
+ retrieved.metadata.get("confidence").unwrap(),
365
+ &serde_json::Value::String("95.5".to_string())
366
+ );
367
+ }
368
+
369
+ #[test]
370
+ fn test_cache_clear_selective() {
371
+ let temp_dir = tempfile::tempdir().unwrap();
372
+ let cache = OcrCache::new(Some(temp_dir.path().to_path_buf())).unwrap();
373
+
374
+ let result = OcrExtractionResult {
375
+ content: "Test".to_string(),
376
+ mime_type: "text/plain".to_string(),
377
+ metadata: HashMap::new(),
378
+ tables: Vec::new(),
379
+ };
380
+
381
+ cache.set_cached_result("test1", "tesseract", "eng", &result).unwrap();
382
+ cache.set_cached_result("test2", "tesseract", "eng", &result).unwrap();
383
+
384
+ fs::write(temp_dir.path().join("other.txt"), "not a msgpack file").unwrap();
385
+
386
+ cache.clear().unwrap();
387
+
388
+ assert!(cache.get_cached_result("test1", "tesseract", "eng").unwrap().is_none());
389
+ assert!(cache.get_cached_result("test2", "tesseract", "eng").unwrap().is_none());
390
+
391
+ assert!(temp_dir.path().join("other.txt").exists());
392
+ }
393
+
394
+ #[test]
395
+ fn test_cache_stats_nonexistent_dir() {
396
+ let temp_dir = tempfile::tempdir().unwrap();
397
+ let cache_path = temp_dir.path().join("nonexistent");
398
+ let cache = OcrCache { cache_dir: cache_path };
399
+
400
+ let stats = cache.get_stats().unwrap();
401
+ assert_eq!(stats.total_files, 0);
402
+ assert_eq!(stats.total_size_mb, 0.0);
403
+ }
404
+
405
+ #[test]
406
+ fn test_cache_clear_nonexistent_dir() {
407
+ let temp_dir = tempfile::tempdir().unwrap();
408
+ let cache_path = temp_dir.path().join("nonexistent");
409
+ let cache = OcrCache { cache_dir: cache_path };
410
+
411
+ assert!(cache.clear().is_ok());
412
+ }
413
+
414
+ #[test]
415
+ fn test_cache_get_path() {
416
+ let temp_dir = tempfile::tempdir().unwrap();
417
+ let cache = OcrCache::new(Some(temp_dir.path().to_path_buf())).unwrap();
418
+
419
+ let path = cache.get_cache_path("abc123");
420
+
421
+ assert!(path.to_string_lossy().contains("abc123.msgpack"));
422
+ assert_eq!(path.parent().unwrap(), temp_dir.path());
423
+ }
424
+
425
+ #[test]
426
+ fn test_cache_stats_default() {
427
+ let stats = OcrCacheStats::default();
428
+ assert_eq!(stats.total_files, 0);
429
+ assert_eq!(stats.total_size_mb, 0.0);
430
+ }
431
+
432
+ #[test]
433
+ fn test_cache_empty_content() {
434
+ let temp_dir = tempfile::tempdir().unwrap();
435
+ let cache = OcrCache::new(Some(temp_dir.path().to_path_buf())).unwrap();
436
+
437
+ let result = OcrExtractionResult {
438
+ content: String::new(),
439
+ mime_type: "text/plain".to_string(),
440
+ metadata: HashMap::new(),
441
+ tables: Vec::new(),
442
+ };
443
+
444
+ cache.set_cached_result("empty", "tesseract", "eng", &result).unwrap();
445
+
446
+ let retrieved = cache.get_cached_result("empty", "tesseract", "eng").unwrap();
447
+ assert_eq!(retrieved.unwrap().content, "");
448
+ }
449
+
450
+ #[test]
451
+ fn test_cache_large_content() {
452
+ let temp_dir = tempfile::tempdir().unwrap();
453
+ let cache = OcrCache::new(Some(temp_dir.path().to_path_buf())).unwrap();
454
+
455
+ let large_content = "x".repeat(10_000);
456
+
457
+ let result = OcrExtractionResult {
458
+ content: large_content.clone(),
459
+ mime_type: "text/plain".to_string(),
460
+ metadata: HashMap::new(),
461
+ tables: Vec::new(),
462
+ };
463
+
464
+ cache.set_cached_result("large", "tesseract", "eng", &result).unwrap();
465
+
466
+ let retrieved = cache.get_cached_result("large", "tesseract", "eng").unwrap();
467
+ assert_eq!(retrieved.unwrap().content.len(), 10_000);
468
+ }
469
+ }