kreuzberg 4.0.0.pre.rc.29 → 4.0.0.rc1

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 (321) hide show
  1. checksums.yaml +4 -4
  2. data/.gitignore +0 -6
  3. data/.rubocop.yaml +534 -1
  4. data/Gemfile +2 -1
  5. data/Gemfile.lock +28 -116
  6. data/README.md +269 -629
  7. data/Rakefile +0 -9
  8. data/Steepfile +4 -8
  9. data/examples/async_patterns.rb +58 -1
  10. data/ext/kreuzberg_rb/extconf.rb +5 -35
  11. data/ext/kreuzberg_rb/native/Cargo.toml +16 -55
  12. data/ext/kreuzberg_rb/native/build.rs +14 -12
  13. data/ext/kreuzberg_rb/native/include/ieeefp.h +1 -1
  14. data/ext/kreuzberg_rb/native/include/msvc_compat/strings.h +1 -1
  15. data/ext/kreuzberg_rb/native/include/strings.h +2 -2
  16. data/ext/kreuzberg_rb/native/include/unistd.h +1 -1
  17. data/ext/kreuzberg_rb/native/src/lib.rs +34 -897
  18. data/extconf.rb +6 -38
  19. data/kreuzberg.gemspec +20 -114
  20. data/lib/kreuzberg/api_proxy.rb +18 -2
  21. data/lib/kreuzberg/cache_api.rb +0 -22
  22. data/lib/kreuzberg/cli.rb +10 -2
  23. data/lib/kreuzberg/cli_proxy.rb +10 -0
  24. data/lib/kreuzberg/config.rb +22 -274
  25. data/lib/kreuzberg/errors.rb +7 -73
  26. data/lib/kreuzberg/extraction_api.rb +8 -237
  27. data/lib/kreuzberg/mcp_proxy.rb +11 -2
  28. data/lib/kreuzberg/ocr_backend_protocol.rb +73 -0
  29. data/lib/kreuzberg/post_processor_protocol.rb +71 -0
  30. data/lib/kreuzberg/result.rb +33 -151
  31. data/lib/kreuzberg/setup_lib_path.rb +2 -22
  32. data/lib/kreuzberg/validator_protocol.rb +73 -0
  33. data/lib/kreuzberg/version.rb +1 -1
  34. data/lib/kreuzberg.rb +13 -27
  35. data/pkg/kreuzberg-4.0.0.rc1.gem +0 -0
  36. data/sig/kreuzberg.rbs +12 -105
  37. data/spec/binding/cache_spec.rb +22 -22
  38. data/spec/binding/cli_proxy_spec.rb +4 -2
  39. data/spec/binding/cli_spec.rb +11 -12
  40. data/spec/binding/config_spec.rb +0 -74
  41. data/spec/binding/config_validation_spec.rb +6 -100
  42. data/spec/binding/error_handling_spec.rb +97 -283
  43. data/spec/binding/plugins/ocr_backend_spec.rb +8 -8
  44. data/spec/binding/plugins/postprocessor_spec.rb +11 -11
  45. data/spec/binding/plugins/validator_spec.rb +13 -12
  46. data/spec/examples.txt +104 -0
  47. data/spec/fixtures/config.toml +1 -0
  48. data/spec/fixtures/config.yaml +1 -0
  49. data/spec/fixtures/invalid_config.toml +1 -0
  50. data/spec/smoke/package_spec.rb +3 -2
  51. data/spec/spec_helper.rb +3 -1
  52. data/vendor/kreuzberg/Cargo.toml +67 -192
  53. data/vendor/kreuzberg/README.md +9 -97
  54. data/vendor/kreuzberg/build.rs +194 -516
  55. data/vendor/kreuzberg/src/api/handlers.rs +9 -130
  56. data/vendor/kreuzberg/src/api/mod.rs +3 -18
  57. data/vendor/kreuzberg/src/api/server.rs +71 -236
  58. data/vendor/kreuzberg/src/api/types.rs +7 -43
  59. data/vendor/kreuzberg/src/bin/profile_extract.rs +455 -0
  60. data/vendor/kreuzberg/src/cache/mod.rs +3 -27
  61. data/vendor/kreuzberg/src/chunking/mod.rs +79 -1705
  62. data/vendor/kreuzberg/src/core/batch_mode.rs +0 -60
  63. data/vendor/kreuzberg/src/core/config.rs +23 -905
  64. data/vendor/kreuzberg/src/core/extractor.rs +106 -403
  65. data/vendor/kreuzberg/src/core/io.rs +2 -4
  66. data/vendor/kreuzberg/src/core/mime.rs +12 -2
  67. data/vendor/kreuzberg/src/core/mod.rs +3 -22
  68. data/vendor/kreuzberg/src/core/pipeline.rs +78 -395
  69. data/vendor/kreuzberg/src/embeddings.rs +21 -169
  70. data/vendor/kreuzberg/src/error.rs +2 -2
  71. data/vendor/kreuzberg/src/extraction/archive.rs +31 -36
  72. data/vendor/kreuzberg/src/extraction/docx.rs +1 -365
  73. data/vendor/kreuzberg/src/extraction/email.rs +11 -12
  74. data/vendor/kreuzberg/src/extraction/excel.rs +129 -138
  75. data/vendor/kreuzberg/src/extraction/html.rs +170 -1447
  76. data/vendor/kreuzberg/src/extraction/image.rs +14 -138
  77. data/vendor/kreuzberg/src/extraction/libreoffice.rs +3 -13
  78. data/vendor/kreuzberg/src/extraction/mod.rs +5 -21
  79. data/vendor/kreuzberg/src/extraction/office_metadata/mod.rs +0 -2
  80. data/vendor/kreuzberg/src/extraction/pandoc/batch.rs +275 -0
  81. data/vendor/kreuzberg/src/extraction/pandoc/mime_types.rs +178 -0
  82. data/vendor/kreuzberg/src/extraction/pandoc/mod.rs +491 -0
  83. data/vendor/kreuzberg/src/extraction/pandoc/server.rs +496 -0
  84. data/vendor/kreuzberg/src/extraction/pandoc/subprocess.rs +1188 -0
  85. data/vendor/kreuzberg/src/extraction/pandoc/version.rs +162 -0
  86. data/vendor/kreuzberg/src/extraction/pptx.rs +94 -196
  87. data/vendor/kreuzberg/src/extraction/structured.rs +4 -5
  88. data/vendor/kreuzberg/src/extraction/table.rs +1 -2
  89. data/vendor/kreuzberg/src/extraction/text.rs +10 -18
  90. data/vendor/kreuzberg/src/extractors/archive.rs +0 -22
  91. data/vendor/kreuzberg/src/extractors/docx.rs +148 -69
  92. data/vendor/kreuzberg/src/extractors/email.rs +9 -37
  93. data/vendor/kreuzberg/src/extractors/excel.rs +40 -81
  94. data/vendor/kreuzberg/src/extractors/html.rs +173 -182
  95. data/vendor/kreuzberg/src/extractors/image.rs +8 -32
  96. data/vendor/kreuzberg/src/extractors/mod.rs +10 -171
  97. data/vendor/kreuzberg/src/extractors/pandoc.rs +201 -0
  98. data/vendor/kreuzberg/src/extractors/pdf.rs +64 -329
  99. data/vendor/kreuzberg/src/extractors/pptx.rs +34 -79
  100. data/vendor/kreuzberg/src/extractors/structured.rs +0 -16
  101. data/vendor/kreuzberg/src/extractors/text.rs +7 -30
  102. data/vendor/kreuzberg/src/extractors/xml.rs +8 -27
  103. data/vendor/kreuzberg/src/keywords/processor.rs +1 -9
  104. data/vendor/kreuzberg/src/keywords/rake.rs +1 -0
  105. data/vendor/kreuzberg/src/language_detection/mod.rs +51 -94
  106. data/vendor/kreuzberg/src/lib.rs +5 -17
  107. data/vendor/kreuzberg/src/mcp/mod.rs +1 -4
  108. data/vendor/kreuzberg/src/mcp/server.rs +21 -145
  109. data/vendor/kreuzberg/src/ocr/mod.rs +0 -2
  110. data/vendor/kreuzberg/src/ocr/processor.rs +8 -19
  111. data/vendor/kreuzberg/src/ocr/tesseract_backend.rs +0 -2
  112. data/vendor/kreuzberg/src/pdf/error.rs +1 -93
  113. data/vendor/kreuzberg/src/pdf/metadata.rs +100 -263
  114. data/vendor/kreuzberg/src/pdf/mod.rs +2 -33
  115. data/vendor/kreuzberg/src/pdf/rendering.rs +12 -12
  116. data/vendor/kreuzberg/src/pdf/table.rs +64 -61
  117. data/vendor/kreuzberg/src/pdf/text.rs +24 -416
  118. data/vendor/kreuzberg/src/plugins/extractor.rs +8 -40
  119. data/vendor/kreuzberg/src/plugins/mod.rs +0 -3
  120. data/vendor/kreuzberg/src/plugins/ocr.rs +14 -22
  121. data/vendor/kreuzberg/src/plugins/processor.rs +1 -10
  122. data/vendor/kreuzberg/src/plugins/registry.rs +0 -15
  123. data/vendor/kreuzberg/src/plugins/validator.rs +8 -20
  124. data/vendor/kreuzberg/src/stopwords/mod.rs +2 -2
  125. data/vendor/kreuzberg/src/text/mod.rs +0 -8
  126. data/vendor/kreuzberg/src/text/quality.rs +15 -28
  127. data/vendor/kreuzberg/src/text/string_utils.rs +10 -22
  128. data/vendor/kreuzberg/src/text/token_reduction/core.rs +50 -86
  129. data/vendor/kreuzberg/src/text/token_reduction/filters.rs +16 -37
  130. data/vendor/kreuzberg/src/text/token_reduction/simd_text.rs +1 -2
  131. data/vendor/kreuzberg/src/types.rs +67 -907
  132. data/vendor/kreuzberg/src/utils/mod.rs +0 -14
  133. data/vendor/kreuzberg/src/utils/quality.rs +3 -12
  134. data/vendor/kreuzberg/tests/api_tests.rs +0 -506
  135. data/vendor/kreuzberg/tests/archive_integration.rs +0 -2
  136. data/vendor/kreuzberg/tests/batch_orchestration.rs +12 -57
  137. data/vendor/kreuzberg/tests/batch_processing.rs +8 -32
  138. data/vendor/kreuzberg/tests/chunking_offset_demo.rs +92 -0
  139. data/vendor/kreuzberg/tests/concurrency_stress.rs +8 -40
  140. data/vendor/kreuzberg/tests/config_features.rs +1 -33
  141. data/vendor/kreuzberg/tests/config_loading_tests.rs +39 -16
  142. data/vendor/kreuzberg/tests/core_integration.rs +9 -35
  143. data/vendor/kreuzberg/tests/csv_integration.rs +81 -71
  144. data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +25 -23
  145. data/vendor/kreuzberg/tests/email_integration.rs +1 -3
  146. data/vendor/kreuzberg/tests/error_handling.rs +34 -43
  147. data/vendor/kreuzberg/tests/format_integration.rs +1 -7
  148. data/vendor/kreuzberg/tests/helpers/mod.rs +0 -60
  149. data/vendor/kreuzberg/tests/image_integration.rs +0 -2
  150. data/vendor/kreuzberg/tests/mime_detection.rs +16 -17
  151. data/vendor/kreuzberg/tests/ocr_configuration.rs +0 -4
  152. data/vendor/kreuzberg/tests/ocr_errors.rs +0 -22
  153. data/vendor/kreuzberg/tests/ocr_quality.rs +0 -2
  154. data/vendor/kreuzberg/tests/pandoc_integration.rs +503 -0
  155. data/vendor/kreuzberg/tests/pdf_integration.rs +0 -2
  156. data/vendor/kreuzberg/tests/pipeline_integration.rs +2 -36
  157. data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +0 -5
  158. data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +1 -17
  159. data/vendor/kreuzberg/tests/plugin_system.rs +0 -6
  160. data/vendor/kreuzberg/tests/registry_integration_tests.rs +22 -2
  161. data/vendor/kreuzberg/tests/security_validation.rs +1 -13
  162. data/vendor/kreuzberg/tests/test_fastembed.rs +23 -45
  163. metadata +25 -171
  164. data/.rubocop.yml +0 -543
  165. data/ext/kreuzberg_rb/native/.cargo/config.toml +0 -23
  166. data/ext/kreuzberg_rb/native/Cargo.lock +0 -7619
  167. data/lib/kreuzberg/error_context.rb +0 -136
  168. data/lib/kreuzberg/types.rb +0 -170
  169. data/lib/libpdfium.so +0 -0
  170. data/spec/binding/async_operations_spec.rb +0 -473
  171. data/spec/binding/batch_operations_spec.rb +0 -595
  172. data/spec/binding/batch_spec.rb +0 -359
  173. data/spec/binding/config_result_spec.rb +0 -377
  174. data/spec/binding/embeddings_spec.rb +0 -816
  175. data/spec/binding/error_recovery_spec.rb +0 -488
  176. data/spec/binding/font_config_spec.rb +0 -220
  177. data/spec/binding/images_spec.rb +0 -738
  178. data/spec/binding/keywords_extraction_spec.rb +0 -600
  179. data/spec/binding/metadata_types_spec.rb +0 -1228
  180. data/spec/binding/pages_extraction_spec.rb +0 -471
  181. data/spec/binding/tables_spec.rb +0 -641
  182. data/spec/unit/config/chunking_config_spec.rb +0 -213
  183. data/spec/unit/config/embedding_config_spec.rb +0 -343
  184. data/spec/unit/config/extraction_config_spec.rb +0 -438
  185. data/spec/unit/config/font_config_spec.rb +0 -285
  186. data/spec/unit/config/hierarchy_config_spec.rb +0 -314
  187. data/spec/unit/config/image_extraction_config_spec.rb +0 -209
  188. data/spec/unit/config/image_preprocessing_config_spec.rb +0 -249
  189. data/spec/unit/config/keyword_config_spec.rb +0 -229
  190. data/spec/unit/config/language_detection_config_spec.rb +0 -258
  191. data/spec/unit/config/ocr_config_spec.rb +0 -171
  192. data/spec/unit/config/page_config_spec.rb +0 -221
  193. data/spec/unit/config/pdf_config_spec.rb +0 -267
  194. data/spec/unit/config/postprocessor_config_spec.rb +0 -290
  195. data/spec/unit/config/tesseract_config_spec.rb +0 -181
  196. data/spec/unit/config/token_reduction_config_spec.rb +0 -251
  197. data/test/metadata_types_test.rb +0 -959
  198. data/vendor/Cargo.toml +0 -61
  199. data/vendor/kreuzberg/examples/bench_fixes.rs +0 -71
  200. data/vendor/kreuzberg/examples/test_pdfium_fork.rs +0 -62
  201. data/vendor/kreuzberg/src/chunking/processor.rs +0 -219
  202. data/vendor/kreuzberg/src/core/batch_optimizations.rs +0 -385
  203. data/vendor/kreuzberg/src/core/config_validation.rs +0 -949
  204. data/vendor/kreuzberg/src/core/formats.rs +0 -235
  205. data/vendor/kreuzberg/src/core/server_config.rs +0 -1220
  206. data/vendor/kreuzberg/src/extraction/capacity.rs +0 -263
  207. data/vendor/kreuzberg/src/extraction/markdown.rs +0 -216
  208. data/vendor/kreuzberg/src/extraction/office_metadata/odt_properties.rs +0 -284
  209. data/vendor/kreuzberg/src/extractors/bibtex.rs +0 -470
  210. data/vendor/kreuzberg/src/extractors/docbook.rs +0 -504
  211. data/vendor/kreuzberg/src/extractors/epub.rs +0 -696
  212. data/vendor/kreuzberg/src/extractors/fictionbook.rs +0 -492
  213. data/vendor/kreuzberg/src/extractors/jats.rs +0 -1054
  214. data/vendor/kreuzberg/src/extractors/jupyter.rs +0 -368
  215. data/vendor/kreuzberg/src/extractors/latex.rs +0 -653
  216. data/vendor/kreuzberg/src/extractors/markdown.rs +0 -701
  217. data/vendor/kreuzberg/src/extractors/odt.rs +0 -628
  218. data/vendor/kreuzberg/src/extractors/opml.rs +0 -635
  219. data/vendor/kreuzberg/src/extractors/orgmode.rs +0 -529
  220. data/vendor/kreuzberg/src/extractors/rst.rs +0 -577
  221. data/vendor/kreuzberg/src/extractors/rtf.rs +0 -809
  222. data/vendor/kreuzberg/src/extractors/security.rs +0 -484
  223. data/vendor/kreuzberg/src/extractors/security_tests.rs +0 -367
  224. data/vendor/kreuzberg/src/extractors/typst.rs +0 -651
  225. data/vendor/kreuzberg/src/language_detection/processor.rs +0 -218
  226. data/vendor/kreuzberg/src/ocr/language_registry.rs +0 -520
  227. data/vendor/kreuzberg/src/panic_context.rs +0 -154
  228. data/vendor/kreuzberg/src/pdf/bindings.rs +0 -306
  229. data/vendor/kreuzberg/src/pdf/bundled.rs +0 -408
  230. data/vendor/kreuzberg/src/pdf/fonts.rs +0 -358
  231. data/vendor/kreuzberg/src/pdf/hierarchy.rs +0 -903
  232. data/vendor/kreuzberg/src/text/quality_processor.rs +0 -231
  233. data/vendor/kreuzberg/src/text/utf8_validation.rs +0 -193
  234. data/vendor/kreuzberg/src/utils/pool.rs +0 -503
  235. data/vendor/kreuzberg/src/utils/pool_sizing.rs +0 -364
  236. data/vendor/kreuzberg/src/utils/string_pool.rs +0 -761
  237. data/vendor/kreuzberg/tests/api_embed.rs +0 -360
  238. data/vendor/kreuzberg/tests/api_extract_multipart.rs +0 -52
  239. data/vendor/kreuzberg/tests/api_large_pdf_extraction.rs +0 -471
  240. data/vendor/kreuzberg/tests/api_large_pdf_extraction_diagnostics.rs +0 -289
  241. data/vendor/kreuzberg/tests/batch_pooling_benchmark.rs +0 -154
  242. data/vendor/kreuzberg/tests/bibtex_parity_test.rs +0 -421
  243. data/vendor/kreuzberg/tests/config_integration_test.rs +0 -753
  244. data/vendor/kreuzberg/tests/data/hierarchy_ground_truth.json +0 -294
  245. data/vendor/kreuzberg/tests/docbook_extractor_tests.rs +0 -500
  246. data/vendor/kreuzberg/tests/docx_vs_pandoc_comparison.rs +0 -370
  247. data/vendor/kreuzberg/tests/epub_native_extractor_tests.rs +0 -275
  248. data/vendor/kreuzberg/tests/fictionbook_extractor_tests.rs +0 -228
  249. data/vendor/kreuzberg/tests/html_table_test.rs +0 -551
  250. data/vendor/kreuzberg/tests/instrumentation_test.rs +0 -139
  251. data/vendor/kreuzberg/tests/jats_extractor_tests.rs +0 -639
  252. data/vendor/kreuzberg/tests/jupyter_extractor_tests.rs +0 -704
  253. data/vendor/kreuzberg/tests/latex_extractor_tests.rs +0 -496
  254. data/vendor/kreuzberg/tests/markdown_extractor_tests.rs +0 -490
  255. data/vendor/kreuzberg/tests/ocr_language_registry.rs +0 -191
  256. data/vendor/kreuzberg/tests/odt_extractor_tests.rs +0 -674
  257. data/vendor/kreuzberg/tests/opml_extractor_tests.rs +0 -616
  258. data/vendor/kreuzberg/tests/orgmode_extractor_tests.rs +0 -822
  259. data/vendor/kreuzberg/tests/page_markers.rs +0 -297
  260. data/vendor/kreuzberg/tests/pdf_hierarchy_detection.rs +0 -301
  261. data/vendor/kreuzberg/tests/pdf_hierarchy_quality.rs +0 -589
  262. data/vendor/kreuzberg/tests/pdf_ocr_triggering.rs +0 -301
  263. data/vendor/kreuzberg/tests/pdf_text_merging.rs +0 -475
  264. data/vendor/kreuzberg/tests/pdfium_linking.rs +0 -340
  265. data/vendor/kreuzberg/tests/rst_extractor_tests.rs +0 -694
  266. data/vendor/kreuzberg/tests/rtf_extractor_tests.rs +0 -775
  267. data/vendor/kreuzberg/tests/typst_behavioral_tests.rs +0 -1260
  268. data/vendor/kreuzberg/tests/typst_extractor_tests.rs +0 -648
  269. data/vendor/kreuzberg-ffi/Cargo.toml +0 -67
  270. data/vendor/kreuzberg-ffi/README.md +0 -851
  271. data/vendor/kreuzberg-ffi/benches/result_view_benchmark.rs +0 -227
  272. data/vendor/kreuzberg-ffi/build.rs +0 -168
  273. data/vendor/kreuzberg-ffi/cbindgen.toml +0 -37
  274. data/vendor/kreuzberg-ffi/kreuzberg-ffi.pc.in +0 -12
  275. data/vendor/kreuzberg-ffi/kreuzberg.h +0 -3012
  276. data/vendor/kreuzberg-ffi/src/batch_streaming.rs +0 -588
  277. data/vendor/kreuzberg-ffi/src/config.rs +0 -1341
  278. data/vendor/kreuzberg-ffi/src/error.rs +0 -901
  279. data/vendor/kreuzberg-ffi/src/extraction.rs +0 -555
  280. data/vendor/kreuzberg-ffi/src/helpers.rs +0 -879
  281. data/vendor/kreuzberg-ffi/src/lib.rs +0 -977
  282. data/vendor/kreuzberg-ffi/src/memory.rs +0 -493
  283. data/vendor/kreuzberg-ffi/src/mime.rs +0 -329
  284. data/vendor/kreuzberg-ffi/src/panic_shield.rs +0 -265
  285. data/vendor/kreuzberg-ffi/src/plugins/document_extractor.rs +0 -442
  286. data/vendor/kreuzberg-ffi/src/plugins/mod.rs +0 -14
  287. data/vendor/kreuzberg-ffi/src/plugins/ocr_backend.rs +0 -628
  288. data/vendor/kreuzberg-ffi/src/plugins/post_processor.rs +0 -438
  289. data/vendor/kreuzberg-ffi/src/plugins/validator.rs +0 -329
  290. data/vendor/kreuzberg-ffi/src/result.rs +0 -510
  291. data/vendor/kreuzberg-ffi/src/result_pool.rs +0 -639
  292. data/vendor/kreuzberg-ffi/src/result_view.rs +0 -773
  293. data/vendor/kreuzberg-ffi/src/string_intern.rs +0 -568
  294. data/vendor/kreuzberg-ffi/src/types.rs +0 -363
  295. data/vendor/kreuzberg-ffi/src/util.rs +0 -210
  296. data/vendor/kreuzberg-ffi/src/validation.rs +0 -848
  297. data/vendor/kreuzberg-ffi/tests.disabled/README.md +0 -48
  298. data/vendor/kreuzberg-ffi/tests.disabled/config_loading_tests.rs +0 -299
  299. data/vendor/kreuzberg-ffi/tests.disabled/config_tests.rs +0 -346
  300. data/vendor/kreuzberg-ffi/tests.disabled/extractor_tests.rs +0 -232
  301. data/vendor/kreuzberg-ffi/tests.disabled/plugin_registration_tests.rs +0 -470
  302. data/vendor/kreuzberg-tesseract/.commitlintrc.json +0 -13
  303. data/vendor/kreuzberg-tesseract/.crate-ignore +0 -2
  304. data/vendor/kreuzberg-tesseract/Cargo.lock +0 -2933
  305. data/vendor/kreuzberg-tesseract/Cargo.toml +0 -57
  306. data/vendor/kreuzberg-tesseract/LICENSE +0 -22
  307. data/vendor/kreuzberg-tesseract/README.md +0 -399
  308. data/vendor/kreuzberg-tesseract/build.rs +0 -1127
  309. data/vendor/kreuzberg-tesseract/patches/README.md +0 -71
  310. data/vendor/kreuzberg-tesseract/patches/tesseract.diff +0 -199
  311. data/vendor/kreuzberg-tesseract/src/api.rs +0 -1371
  312. data/vendor/kreuzberg-tesseract/src/choice_iterator.rs +0 -77
  313. data/vendor/kreuzberg-tesseract/src/enums.rs +0 -297
  314. data/vendor/kreuzberg-tesseract/src/error.rs +0 -81
  315. data/vendor/kreuzberg-tesseract/src/lib.rs +0 -145
  316. data/vendor/kreuzberg-tesseract/src/monitor.rs +0 -57
  317. data/vendor/kreuzberg-tesseract/src/mutable_iterator.rs +0 -197
  318. data/vendor/kreuzberg-tesseract/src/page_iterator.rs +0 -253
  319. data/vendor/kreuzberg-tesseract/src/result_iterator.rs +0 -286
  320. data/vendor/kreuzberg-tesseract/src/result_renderer.rs +0 -183
  321. data/vendor/kreuzberg-tesseract/tests/integration_test.rs +0 -211
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA256:
3
- metadata.gz: f243ab522441e38c6e3a68083ce4d75a271e123a16444bdb78f98112f6d62f6a
4
- data.tar.gz: 890da0d377ca08b10fd2c511ac553fafed46bbb7ba08ac87408f5653a56fcb24
3
+ metadata.gz: bfb7dc6c3685285b053af795140387ad8292c698cbba4cfda3411390dfe3cd48
4
+ data.tar.gz: 7688722b9a8d99564044a8bca31c6fadf107208aabaa336d450069b636a02726
5
5
  SHA512:
6
- metadata.gz: 364bf3ad47e380b9cbf3a4e625b07552f0b82a6b8b23bc0778ec9a970b0c8d5d9920d5edd87175c7e6a4aae65a82f4253bef9991601152e2e015e12fc6a59d7c
7
- data.tar.gz: 58bb34b94650ae86d9ca99a3365cf23b25e6a99311028f22520df994794e705e22601b5e2c94b7f636dc94ce15d3af9e46ddb20408de67f916575229e76ca7e5
6
+ metadata.gz: 3c5b66fc2c0457f670c39e53f038a5fa040760ac3f36b8731c35210d2ca98b1cf65ae41411bd6788411f18090ffd269878cf814d4b93b4201098f5e5950782e0
7
+ data.tar.gz: 1a02c5c0ffb830454e20e03e937aa4d80e73d9e6a6ae4913ed9d35d6cdb84ffbb2141711fa3b2ce5fcd821b109613f5ec01cbfdcface5615071727b26c772347
data/.gitignore CHANGED
@@ -6,9 +6,3 @@ lib/*.dll
6
6
  lib/*.dylib
7
7
  lib/*.so
8
8
  lib/*.dll
9
-
10
- # Vendor directory for local development (symlink to ../../crates/kreuzberg)
11
- # In CI, this is replaced by the actual vendored crate files
12
- # Exception: vendor/rb-sys is patched and committed
13
- !vendor/rb-sys/
14
- vendor/
data/.rubocop.yaml CHANGED
@@ -1 +1,534 @@
1
- inherit_from: .rubocop.yml
1
+
2
+ plugins:
3
+ - rubocop-performance
4
+ - rubocop-rspec
5
+
6
+ AllCops:
7
+ TargetRubyVersion: 3.2
8
+ NewCops: enable
9
+ SuggestExtensions: false
10
+ Exclude:
11
+ - 'vendor/**/*'
12
+ - 'tmp/**/*'
13
+ - 'lib/**/*.bundle'
14
+ - 'ext/**/*'
15
+
16
+ Style/StringLiterals:
17
+ Enabled: true
18
+ EnforcedStyle: single_quotes
19
+
20
+ Style/StringLiteralsInInterpolation:
21
+ Enabled: true
22
+ EnforcedStyle: single_quotes
23
+
24
+ Style/FrozenStringLiteralComment:
25
+ Enabled: true
26
+ EnforcedStyle: always
27
+
28
+ Style/Documentation:
29
+ Enabled: false
30
+
31
+ Layout/LineLength:
32
+ Max: 120
33
+ AllowedPatterns:
34
+ - '\A\s*#'
35
+ Exclude:
36
+ - 'spec/**/*'
37
+
38
+ Metrics/BlockLength:
39
+ Max: 350
40
+ Exclude:
41
+ - '*.gemspec'
42
+ - 'examples/**/*'
43
+
44
+ Metrics/MethodLength:
45
+ Max: 18
46
+ Exclude:
47
+ - 'spec/**/*'
48
+ - 'examples/**/*'
49
+
50
+ Metrics/AbcSize:
51
+ Max: 20
52
+ Exclude:
53
+ - 'spec/**/*'
54
+ - 'examples/**/*'
55
+
56
+ Naming/FileName:
57
+ Enabled: true
58
+ Exclude:
59
+ - 'Gemfile'
60
+ - 'Rakefile'
61
+
62
+ RSpec/SpecFilePathFormat:
63
+ Enabled: false
64
+ RSpec/SpecFilePathSuffix:
65
+ Enabled: false
66
+
67
+ RSpec/PendingWithoutReason:
68
+ Enabled: false
69
+
70
+ RSpec/LeakyConstantDeclaration:
71
+ Enabled: false
72
+
73
+ RSpec/UnspecifiedException:
74
+ Enabled: false
75
+
76
+ Lint/ConstantDefinitionInBlock:
77
+ Exclude:
78
+ - 'spec/**/*'
79
+
80
+ RSpec/InstanceVariable:
81
+ Enabled: false
82
+
83
+ Gemspec/DevelopmentDependencies:
84
+ Enabled: false
85
+
86
+ Metrics/ParameterLists:
87
+ Max: 7
88
+ Exclude:
89
+ - 'lib/kreuzberg/config.rb'
90
+
91
+ Metrics/CyclomaticComplexity:
92
+ Max: 7
93
+ Exclude:
94
+ - 'lib/kreuzberg/config.rb'
95
+
96
+ RSpec/RepeatedExampleGroupBody:
97
+ Enabled: false
98
+
99
+ RSpec/DescribeClass:
100
+ Enabled: false
101
+
102
+ RSpec/PredicateMatcher:
103
+ Enabled: false
104
+
105
+ # New cops from RuboCop 1.65+
106
+ Gemspec/AddRuntimeDependency:
107
+ Enabled: true
108
+
109
+ Gemspec/AttributeAssignment:
110
+ Enabled: true
111
+
112
+ Gemspec/DeprecatedAttributeAssignment:
113
+ Enabled: true
114
+
115
+ Gemspec/RequireMFA:
116
+ Enabled: false
117
+
118
+ Layout/EmptyLinesAfterModuleInclusion:
119
+ Enabled: true
120
+
121
+ Layout/LineContinuationLeadingSpace:
122
+ Enabled: true
123
+
124
+ Layout/LineContinuationSpacing:
125
+ Enabled: true
126
+
127
+ Layout/LineEndStringConcatenationIndentation:
128
+ Enabled: true
129
+
130
+ Layout/SpaceBeforeBrackets:
131
+ Enabled: true
132
+
133
+ Lint/AmbiguousAssignment:
134
+ Enabled: true
135
+
136
+ Lint/AmbiguousOperatorPrecedence:
137
+ Enabled: true
138
+
139
+ Lint/AmbiguousRange:
140
+ Enabled: true
141
+
142
+ Lint/ArrayLiteralInRegexp:
143
+ Enabled: true
144
+
145
+ Lint/ConstantOverwrittenInRescue:
146
+ Enabled: true
147
+
148
+ Lint/ConstantReassignment:
149
+ Enabled: true
150
+
151
+ Lint/CopDirectiveSyntax:
152
+ Enabled: true
153
+
154
+ Lint/DeprecatedConstants:
155
+ Enabled: true
156
+
157
+ Lint/DuplicateBranch:
158
+ Enabled: true
159
+
160
+ Lint/DuplicateMagicComment:
161
+ Enabled: true
162
+
163
+ Lint/DuplicateMatchPattern:
164
+ Enabled: true
165
+
166
+ Lint/DuplicateRegexpCharacterClassElement:
167
+ Enabled: true
168
+
169
+ Lint/DuplicateSetElement:
170
+ Enabled: true
171
+
172
+ Lint/EmptyBlock:
173
+ Enabled: true
174
+
175
+ Lint/EmptyClass:
176
+ Enabled: true
177
+
178
+ Lint/EmptyInPattern:
179
+ Enabled: true
180
+
181
+ Lint/HashNewWithKeywordArgumentsAsDefault:
182
+ Enabled: true
183
+
184
+ Lint/IncompatibleIoSelectWithFiberScheduler:
185
+ Enabled: true
186
+
187
+ Lint/ItWithoutArgumentsInBlock:
188
+ Enabled: true
189
+
190
+ Lint/LambdaWithoutLiteralBlock:
191
+ Enabled: true
192
+
193
+ Lint/LiteralAssignmentInCondition:
194
+ Enabled: true
195
+
196
+ Lint/MixedCaseRange:
197
+ Enabled: true
198
+
199
+ Lint/NoReturnInBeginEndBlocks:
200
+ Enabled: true
201
+
202
+ Lint/NonAtomicFileOperation:
203
+ Enabled: true
204
+
205
+ Lint/NumberedParameterAssignment:
206
+ Enabled: true
207
+
208
+ Lint/NumericOperationWithConstantResult:
209
+ Enabled: true
210
+
211
+ Lint/OrAssignmentToConstant:
212
+ Enabled: true
213
+
214
+ Lint/RedundantDirGlobSort:
215
+ Enabled: true
216
+
217
+ Lint/RedundantRegexpQuantifiers:
218
+ Enabled: true
219
+
220
+ Lint/RedundantTypeConversion:
221
+ Enabled: true
222
+
223
+ Lint/RefinementImportMethods:
224
+ Enabled: true
225
+
226
+ Lint/RequireRangeParentheses:
227
+ Enabled: true
228
+
229
+ Lint/RequireRelativeSelfPath:
230
+ Enabled: true
231
+
232
+ Lint/SharedMutableDefault:
233
+ Enabled: true
234
+
235
+ Lint/SuppressedExceptionInNumberConversion:
236
+ Enabled: true
237
+
238
+ Lint/SymbolConversion:
239
+ Enabled: true
240
+
241
+ Lint/ToEnumArguments:
242
+ Enabled: true
243
+
244
+ Lint/TripleQuotes:
245
+ Enabled: true
246
+
247
+ Lint/UnescapedBracketInRegexp:
248
+ Enabled: true
249
+
250
+ Lint/UnexpectedBlockArity:
251
+ Enabled: true
252
+
253
+ Lint/UnmodifiedReduceAccumulator:
254
+ Enabled: true
255
+
256
+ Lint/UselessConstantScoping:
257
+ Enabled: true
258
+
259
+ Lint/UselessDefaultValueArgument:
260
+ Enabled: true
261
+
262
+ Lint/UselessDefined:
263
+ Enabled: true
264
+
265
+ Lint/UselessNumericOperation:
266
+ Enabled: true
267
+
268
+ Lint/UselessOr:
269
+ Enabled: true
270
+
271
+ Lint/UselessRescue:
272
+ Enabled: true
273
+
274
+ Lint/UselessRuby2Keywords:
275
+ Enabled: true
276
+
277
+ Metrics/CollectionLiteralLength:
278
+ Enabled: true
279
+
280
+ Naming/BlockForwarding:
281
+ Enabled: true
282
+
283
+ Naming/PredicateMethod:
284
+ Enabled: true
285
+
286
+ Security/CompoundHash:
287
+ Enabled: true
288
+
289
+ Security/IoMethods:
290
+ Enabled: true
291
+
292
+ Style/AmbiguousEndlessMethodDefinition:
293
+ Enabled: true
294
+
295
+ Style/ArgumentsForwarding:
296
+ Enabled: true
297
+
298
+ Style/ArrayIntersect:
299
+ Enabled: true
300
+
301
+ Style/ArrayIntersectWithSingleElement:
302
+ Enabled: true
303
+
304
+ Style/BitwisePredicate:
305
+ Enabled: true
306
+
307
+ Style/CollectionCompact:
308
+ Enabled: true
309
+
310
+ Style/CollectionQuerying:
311
+ Enabled: true
312
+
313
+ Style/CombinableDefined:
314
+ Enabled: true
315
+
316
+ Style/ComparableBetween:
317
+ Enabled: true
318
+
319
+ Style/ComparableClamp:
320
+ Enabled: true
321
+
322
+ Style/ConcatArrayLiterals:
323
+ Enabled: true
324
+
325
+ Style/DataInheritance:
326
+ Enabled: true
327
+
328
+ Style/DigChain:
329
+ Enabled: true
330
+
331
+ Style/DirEmpty:
332
+ Enabled: true
333
+
334
+ Style/DocumentDynamicEvalDefinition:
335
+ Enabled: true
336
+
337
+ Style/EmptyHeredoc:
338
+ Enabled: true
339
+
340
+ Style/EmptyStringInsideInterpolation:
341
+ Enabled: true
342
+
343
+ Style/EndlessMethod:
344
+ Enabled: true
345
+
346
+ Style/EnvHome:
347
+ Enabled: true
348
+
349
+ Style/ExactRegexpMatch:
350
+ Enabled: true
351
+
352
+ Style/FetchEnvVar:
353
+ Enabled: true
354
+
355
+ Style/FileEmpty:
356
+ Enabled: true
357
+
358
+ Style/FileNull:
359
+ Enabled: true
360
+
361
+ Style/FileRead:
362
+ Enabled: true
363
+
364
+ Style/FileTouch:
365
+ Enabled: true
366
+
367
+ Style/FileWrite:
368
+ Enabled: true
369
+
370
+ Style/HashConversion:
371
+ Enabled: true
372
+
373
+ Style/HashExcept:
374
+ Enabled: true
375
+
376
+ Style/HashFetchChain:
377
+ Enabled: true
378
+
379
+ Style/HashSlice:
380
+ Enabled: true
381
+
382
+ Style/IfWithBooleanLiteralBranches:
383
+ Enabled: true
384
+
385
+ Style/InPatternThen:
386
+ Enabled: true
387
+
388
+ Style/ItAssignment:
389
+ Enabled: true
390
+
391
+ Style/ItBlockParameter:
392
+ Enabled: true
393
+
394
+ Style/KeywordArgumentsMerging:
395
+ Enabled: true
396
+
397
+ Style/MagicCommentFormat:
398
+ Enabled: true
399
+
400
+ Style/MapCompactWithConditionalBlock:
401
+ Enabled: true
402
+
403
+ Style/MapIntoArray:
404
+ Enabled: true
405
+
406
+ Style/MapToHash:
407
+ Enabled: true
408
+
409
+ Style/MapToSet:
410
+ Enabled: true
411
+
412
+ Style/MinMaxComparison:
413
+ Enabled: true
414
+
415
+ Style/MultilineInPatternThen:
416
+ Enabled: true
417
+
418
+ Style/NegatedIfElseCondition:
419
+ Enabled: true
420
+
421
+ Style/NestedFileDirname:
422
+ Enabled: true
423
+
424
+ Style/NilLambda:
425
+ Enabled: true
426
+
427
+ Style/NumberedParameters:
428
+ Enabled: true
429
+
430
+ Style/NumberedParametersLimit:
431
+ Enabled: true
432
+
433
+ Style/ObjectThen:
434
+ Enabled: true
435
+
436
+ Style/OpenStructUse:
437
+ Enabled: true
438
+
439
+ Style/OperatorMethodCall:
440
+ Enabled: true
441
+
442
+ Style/QuotedSymbols:
443
+ Enabled: true
444
+
445
+ Style/RedundantArgument:
446
+ Enabled: true
447
+
448
+ Style/RedundantArrayConstructor:
449
+ Enabled: true
450
+
451
+ Style/RedundantArrayFlatten:
452
+ Enabled: true
453
+
454
+ Style/RedundantConstantBase:
455
+ Enabled: true
456
+
457
+ Style/RedundantCurrentDirectoryInPath:
458
+ Enabled: true
459
+
460
+ Style/RedundantDoubleSplatHashBraces:
461
+ Enabled: true
462
+
463
+ Style/RedundantEach:
464
+ Enabled: true
465
+
466
+ Style/RedundantFilterChain:
467
+ Enabled: true
468
+
469
+ Style/RedundantFormat:
470
+ Enabled: true
471
+
472
+ Style/RedundantHeredocDelimiterQuotes:
473
+ Enabled: true
474
+
475
+ Style/RedundantInitialize:
476
+ Enabled: true
477
+
478
+ Style/RedundantInterpolationUnfreeze:
479
+ Enabled: true
480
+
481
+ Style/RedundantLineContinuation:
482
+ Enabled: true
483
+
484
+ Style/RedundantRegexpArgument:
485
+ Enabled: true
486
+
487
+ Style/RedundantRegexpConstructor:
488
+ Enabled: true
489
+
490
+ Style/RedundantSelfAssignmentBranch:
491
+ Enabled: true
492
+
493
+ Style/RedundantStringEscape:
494
+ Enabled: true
495
+
496
+ Style/ReturnNilInPredicateMethodDefinition:
497
+ Enabled: true
498
+
499
+ Style/SafeNavigationChainLength:
500
+ Enabled: true
501
+
502
+ Style/SelectByRegexp:
503
+ Enabled: true
504
+
505
+ Style/SendWithLiteralMethodName:
506
+ Enabled: true
507
+
508
+ Style/SingleLineDoEndBlock:
509
+ Enabled: true
510
+
511
+ Style/StringChars:
512
+ Enabled: true
513
+
514
+ Style/SuperArguments:
515
+ Enabled: true
516
+
517
+ Style/SuperWithArgsParentheses:
518
+ Enabled: true
519
+
520
+ Style/SwapValues:
521
+ Enabled: true
522
+
523
+ Style/YAMLFileRead:
524
+ Enabled: true
525
+
526
+ # Adjust RSpec metrics for test blocks
527
+ RSpec/ExampleLength:
528
+ Max: 35
529
+
530
+ RSpec/MultipleExpectations:
531
+ Max: 15
532
+
533
+ RSpec/NestedGroups:
534
+ Max: 6
data/Gemfile CHANGED
@@ -5,4 +5,5 @@ source 'https://rubygems.org'
5
5
  gemspec
6
6
 
7
7
  gem 'pry', '~> 0.14', group: :development
8
- gem 'pry-byebug', '~> 3.10', group: :development, platforms: %i[ruby mri]
8
+
9
+ gem 'pry-byebug', '~> 3.10', group: :development unless Gem.win_platform?