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
data/.rubocop.yml DELETED
@@ -1,543 +0,0 @@
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
- Enabled: true
40
- Max: 350
41
- CountComments: false
42
- CountAsOne: []
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
- - 'lib/kreuzberg/config.rb'
56
-
57
- Naming/FileName:
58
- Enabled: true
59
- Exclude:
60
- - 'Gemfile'
61
- - 'Rakefile'
62
-
63
- RSpec/SpecFilePathFormat:
64
- Enabled: false
65
- RSpec/SpecFilePathSuffix:
66
- Enabled: false
67
-
68
- RSpec/PendingWithoutReason:
69
- Enabled: false
70
-
71
- RSpec/LeakyConstantDeclaration:
72
- Enabled: false
73
-
74
- RSpec/UnspecifiedException:
75
- Enabled: false
76
-
77
- Lint/ConstantDefinitionInBlock:
78
- Enabled: false
79
- Exclude:
80
- - 'spec/**/*'
81
-
82
- RSpec/InstanceVariable:
83
- Enabled: false
84
-
85
- Gemspec/DevelopmentDependencies:
86
- Enabled: false
87
-
88
- Metrics/ParameterLists:
89
- Max: 14
90
- Exclude:
91
- - 'lib/kreuzberg/config.rb'
92
-
93
- Metrics/CyclomaticComplexity:
94
- Max: 7
95
- Exclude:
96
- - 'lib/kreuzberg/config.rb'
97
-
98
- Metrics/PerceivedComplexity:
99
- Max: 12
100
- Exclude:
101
- - 'lib/kreuzberg/config.rb'
102
-
103
- Metrics/ClassLength:
104
- Exclude:
105
- - 'lib/kreuzberg/config.rb'
106
-
107
- RSpec/RepeatedExampleGroupBody:
108
- Enabled: false
109
-
110
- RSpec/DescribeClass:
111
- Enabled: false
112
-
113
- RSpec/PredicateMatcher:
114
- Enabled: false
115
-
116
- Gemspec/AddRuntimeDependency:
117
- Enabled: true
118
-
119
- Gemspec/AttributeAssignment:
120
- Enabled: true
121
-
122
- Gemspec/DeprecatedAttributeAssignment:
123
- Enabled: true
124
-
125
- Gemspec/RequireMFA:
126
- Enabled: false
127
-
128
- Layout/EmptyLinesAfterModuleInclusion:
129
- Enabled: true
130
-
131
- Layout/LineContinuationLeadingSpace:
132
- Enabled: true
133
-
134
- Layout/LineContinuationSpacing:
135
- Enabled: true
136
-
137
- Layout/LineEndStringConcatenationIndentation:
138
- Enabled: true
139
-
140
- Layout/SpaceBeforeBrackets:
141
- Enabled: true
142
-
143
- Lint/AmbiguousAssignment:
144
- Enabled: true
145
-
146
- Lint/AmbiguousOperatorPrecedence:
147
- Enabled: true
148
-
149
- Lint/AmbiguousRange:
150
- Enabled: true
151
-
152
- Lint/ArrayLiteralInRegexp:
153
- Enabled: true
154
-
155
- Lint/ConstantOverwrittenInRescue:
156
- Enabled: true
157
-
158
- Lint/ConstantReassignment:
159
- Enabled: true
160
-
161
- Lint/CopDirectiveSyntax:
162
- Enabled: true
163
-
164
- Lint/DeprecatedConstants:
165
- Enabled: true
166
-
167
- Lint/DuplicateBranch:
168
- Enabled: true
169
-
170
- Lint/DuplicateMagicComment:
171
- Enabled: true
172
-
173
- Lint/DuplicateMatchPattern:
174
- Enabled: true
175
-
176
- Lint/DuplicateRegexpCharacterClassElement:
177
- Enabled: true
178
-
179
- Lint/DuplicateSetElement:
180
- Enabled: true
181
-
182
- Lint/EmptyBlock:
183
- Enabled: true
184
-
185
- Lint/EmptyClass:
186
- Enabled: true
187
-
188
- Lint/EmptyInPattern:
189
- Enabled: true
190
-
191
- Lint/HashNewWithKeywordArgumentsAsDefault:
192
- Enabled: true
193
-
194
- Lint/IncompatibleIoSelectWithFiberScheduler:
195
- Enabled: true
196
-
197
- Lint/ItWithoutArgumentsInBlock:
198
- Enabled: true
199
-
200
- Lint/LambdaWithoutLiteralBlock:
201
- Enabled: true
202
-
203
- Lint/LiteralAssignmentInCondition:
204
- Enabled: true
205
-
206
- Lint/MixedCaseRange:
207
- Enabled: true
208
-
209
- Lint/NoReturnInBeginEndBlocks:
210
- Enabled: true
211
-
212
- Lint/NonAtomicFileOperation:
213
- Enabled: true
214
-
215
- Lint/NumberedParameterAssignment:
216
- Enabled: true
217
-
218
- Lint/NumericOperationWithConstantResult:
219
- Enabled: true
220
-
221
- Lint/OrAssignmentToConstant:
222
- Enabled: true
223
-
224
- Lint/RedundantDirGlobSort:
225
- Enabled: true
226
-
227
- Lint/RedundantRegexpQuantifiers:
228
- Enabled: true
229
-
230
- Lint/RedundantTypeConversion:
231
- Enabled: true
232
-
233
- Lint/RefinementImportMethods:
234
- Enabled: true
235
-
236
- Lint/RequireRangeParentheses:
237
- Enabled: true
238
-
239
- Lint/RequireRelativeSelfPath:
240
- Enabled: true
241
-
242
- Lint/SharedMutableDefault:
243
- Enabled: true
244
-
245
- Lint/SuppressedExceptionInNumberConversion:
246
- Enabled: true
247
-
248
- Lint/SymbolConversion:
249
- Enabled: true
250
-
251
- Lint/ToEnumArguments:
252
- Enabled: true
253
-
254
- Lint/TripleQuotes:
255
- Enabled: true
256
-
257
- Lint/UnescapedBracketInRegexp:
258
- Enabled: true
259
-
260
- Lint/UnexpectedBlockArity:
261
- Enabled: true
262
-
263
- Lint/UnmodifiedReduceAccumulator:
264
- Enabled: true
265
-
266
- Lint/UselessConstantScoping:
267
- Enabled: true
268
-
269
- Lint/UselessDefaultValueArgument:
270
- Enabled: true
271
-
272
- Lint/UselessDefined:
273
- Enabled: true
274
-
275
- Lint/UselessNumericOperation:
276
- Enabled: true
277
-
278
- Lint/UselessOr:
279
- Enabled: true
280
-
281
- Lint/UselessRescue:
282
- Enabled: true
283
-
284
- Lint/UselessRuby2Keywords:
285
- Enabled: true
286
-
287
- Metrics/CollectionLiteralLength:
288
- Enabled: true
289
-
290
- Naming/BlockForwarding:
291
- Enabled: true
292
-
293
- Naming/PredicateMethod:
294
- Enabled: true
295
-
296
- Security/CompoundHash:
297
- Enabled: true
298
-
299
- Security/IoMethods:
300
- Enabled: true
301
-
302
- Style/AmbiguousEndlessMethodDefinition:
303
- Enabled: true
304
-
305
- Style/ArgumentsForwarding:
306
- Enabled: true
307
-
308
- Style/ArrayIntersect:
309
- Enabled: true
310
-
311
- Style/ArrayIntersectWithSingleElement:
312
- Enabled: true
313
-
314
- Style/BitwisePredicate:
315
- Enabled: true
316
-
317
- Style/CollectionCompact:
318
- Enabled: true
319
-
320
- Style/CollectionQuerying:
321
- Enabled: true
322
-
323
- Style/CombinableDefined:
324
- Enabled: true
325
-
326
- Style/ComparableBetween:
327
- Enabled: true
328
-
329
- Style/ComparableClamp:
330
- Enabled: true
331
-
332
- Style/ConcatArrayLiterals:
333
- Enabled: true
334
-
335
- Style/DataInheritance:
336
- Enabled: true
337
-
338
- Style/DigChain:
339
- Enabled: true
340
-
341
- Style/DirEmpty:
342
- Enabled: true
343
-
344
- Style/DocumentDynamicEvalDefinition:
345
- Enabled: true
346
-
347
- Style/EmptyHeredoc:
348
- Enabled: true
349
-
350
- Style/EmptyStringInsideInterpolation:
351
- Enabled: true
352
-
353
- Style/EndlessMethod:
354
- Enabled: true
355
-
356
- Style/EnvHome:
357
- Enabled: true
358
-
359
- Style/ExactRegexpMatch:
360
- Enabled: true
361
-
362
- Style/FetchEnvVar:
363
- Enabled: true
364
-
365
- Style/FileEmpty:
366
- Enabled: true
367
-
368
- Style/FileNull:
369
- Enabled: true
370
-
371
- Style/FileRead:
372
- Enabled: true
373
-
374
- Style/FileTouch:
375
- Enabled: true
376
-
377
- Style/FileWrite:
378
- Enabled: true
379
-
380
- Style/HashConversion:
381
- Enabled: true
382
-
383
- Style/HashExcept:
384
- Enabled: true
385
-
386
- Style/HashFetchChain:
387
- Enabled: true
388
-
389
- Style/HashSlice:
390
- Enabled: true
391
-
392
- Style/IfWithBooleanLiteralBranches:
393
- Enabled: true
394
-
395
- Style/InPatternThen:
396
- Enabled: true
397
-
398
- Style/ItAssignment:
399
- Enabled: true
400
-
401
- Style/ItBlockParameter:
402
- Enabled: true
403
-
404
- Style/KeywordArgumentsMerging:
405
- Enabled: true
406
-
407
- Style/MagicCommentFormat:
408
- Enabled: true
409
-
410
- Style/MapCompactWithConditionalBlock:
411
- Enabled: true
412
-
413
- Style/MapIntoArray:
414
- Enabled: true
415
-
416
- Style/MapToHash:
417
- Enabled: true
418
-
419
- Style/MapToSet:
420
- Enabled: true
421
-
422
- Style/MinMaxComparison:
423
- Enabled: true
424
-
425
- Style/MultilineInPatternThen:
426
- Enabled: true
427
-
428
- Style/NegatedIfElseCondition:
429
- Enabled: true
430
-
431
- Style/NestedFileDirname:
432
- Enabled: true
433
-
434
- Style/NilLambda:
435
- Enabled: true
436
-
437
- Style/NumberedParameters:
438
- Enabled: true
439
-
440
- Style/NumberedParametersLimit:
441
- Enabled: true
442
-
443
- Style/ObjectThen:
444
- Enabled: true
445
-
446
- Style/OpenStructUse:
447
- Enabled: true
448
-
449
- Style/OperatorMethodCall:
450
- Enabled: true
451
-
452
- Style/QuotedSymbols:
453
- Enabled: true
454
-
455
- Style/RedundantArgument:
456
- Enabled: true
457
-
458
- Style/RedundantArrayConstructor:
459
- Enabled: true
460
-
461
- Style/RedundantArrayFlatten:
462
- Enabled: true
463
-
464
- Style/RedundantConstantBase:
465
- Enabled: true
466
-
467
- Style/RedundantCurrentDirectoryInPath:
468
- Enabled: true
469
-
470
- Style/RedundantDoubleSplatHashBraces:
471
- Enabled: true
472
-
473
- Style/RedundantEach:
474
- Enabled: true
475
-
476
- Style/RedundantFilterChain:
477
- Enabled: true
478
-
479
- Style/RedundantFormat:
480
- Enabled: true
481
-
482
- Style/RedundantHeredocDelimiterQuotes:
483
- Enabled: true
484
-
485
- Style/RedundantInitialize:
486
- Enabled: true
487
-
488
- Style/RedundantInterpolationUnfreeze:
489
- Enabled: true
490
-
491
- Style/RedundantLineContinuation:
492
- Enabled: true
493
-
494
- Style/RedundantRegexpArgument:
495
- Enabled: true
496
-
497
- Style/RedundantRegexpConstructor:
498
- Enabled: true
499
-
500
- Style/RedundantSelfAssignmentBranch:
501
- Enabled: true
502
-
503
- Style/RedundantStringEscape:
504
- Enabled: true
505
-
506
- Style/ReturnNilInPredicateMethodDefinition:
507
- Enabled: true
508
-
509
- Style/SafeNavigationChainLength:
510
- Enabled: true
511
-
512
- Style/SelectByRegexp:
513
- Enabled: true
514
-
515
- Style/SendWithLiteralMethodName:
516
- Enabled: true
517
-
518
- Style/SingleLineDoEndBlock:
519
- Enabled: true
520
-
521
- Style/StringChars:
522
- Enabled: true
523
-
524
- Style/SuperArguments:
525
- Enabled: true
526
-
527
- Style/SuperWithArgsParentheses:
528
- Enabled: true
529
-
530
- Style/SwapValues:
531
- Enabled: true
532
-
533
- Style/YAMLFileRead:
534
- Enabled: true
535
-
536
- RSpec/ExampleLength:
537
- Max: 50
538
-
539
- RSpec/MultipleExpectations:
540
- Max: 25
541
-
542
- RSpec/NestedGroups:
543
- Max: 6
@@ -1,23 +0,0 @@
1
- [build]
2
- rustflags = ["-A", "unpredictable-function-pointer-comparisons", "-A", "fn_ptr_eq"]
3
-
4
- # Windows GNU target configuration
5
- [target.x86_64-pc-windows-gnu]
6
- rustflags = [
7
- "-A",
8
- "unpredictable-function-pointer-comparisons",
9
- "-A",
10
- "fn_ptr_eq",
11
- "-C",
12
- "link-arg=-lbcrypt",
13
- "-C",
14
- "link-arg=-lcrypt32",
15
- "-C",
16
- "link-arg=-lws2_32",
17
- "-C",
18
- "link-arg=-luserenv",
19
- ]
20
-
21
- # Windows MSVC target configuration (fallback)
22
- [target.x86_64-pc-windows-msvc]
23
- rustflags = ["-A", "unpredictable-function-pointer-comparisons", "-A", "fn_ptr_eq"]