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
@@ -1,181 +0,0 @@
1
- # frozen_string_literal: true
2
-
3
- RSpec.describe Kreuzberg::Config::Tesseract do
4
- describe '#initialize' do
5
- it 'creates config with no arguments' do
6
- config = described_class.new
7
-
8
- expect(config).to be_a described_class
9
- expect(config.options).to eq({})
10
- end
11
-
12
- it 'creates config with custom options' do
13
- config = described_class.new(dpi: 300, psm: 3)
14
-
15
- expect(config.options[:dpi]).to eq 300
16
- expect(config.options[:psm]).to eq 3
17
- end
18
-
19
- it 'converts string keys to symbols' do
20
- config = described_class.new('oem' => 1, 'lang' => 'eng')
21
-
22
- expect(config.options[:oem]).to eq 1
23
- expect(config.options[:lang]).to eq 'eng'
24
- end
25
-
26
- it 'accepts preprocessing as hash' do
27
- config = described_class.new(preprocessing: { target_dpi: 300 })
28
-
29
- expect(config.options[:preprocessing]).to be_a Kreuzberg::Config::ImagePreprocessing
30
- end
31
-
32
- it 'accepts preprocessing as instance' do
33
- preprocessing = Kreuzberg::Config::ImagePreprocessing.new(target_dpi: 600)
34
- config = described_class.new(preprocessing: preprocessing)
35
-
36
- expect(config.options[:preprocessing]).to be_a Kreuzberg::Config::ImagePreprocessing
37
- expect(config.options[:preprocessing].target_dpi).to eq 600
38
- end
39
- end
40
-
41
- describe '#to_h' do
42
- it 'returns options as hash' do
43
- config = described_class.new(dpi: 300, psm: 3)
44
- hash = config.to_h
45
-
46
- expect(hash).to be_a Hash
47
- expect(hash[:dpi]).to eq 300
48
- expect(hash[:psm]).to eq 3
49
- end
50
-
51
- it 'includes nested preprocessing in hash' do
52
- config = described_class.new(
53
- preprocessing: { target_dpi: 300, denoise: true }
54
- )
55
- hash = config.to_h
56
-
57
- expect(hash[:preprocessing]).to be_a Kreuzberg::Config::ImagePreprocessing
58
- # Access the config object's attributes
59
- expect(hash[:preprocessing].target_dpi).to eq 300
60
- expect(hash[:preprocessing].denoise).to be true
61
- end
62
-
63
- it 'returns duplicate hash not original' do
64
- config = described_class.new(value: 'test')
65
- hash1 = config.to_h
66
- hash2 = config.to_h
67
-
68
- expect(hash1).to eq hash2
69
- expect(hash1).not_to be hash2
70
- end
71
- end
72
-
73
- describe 'validation' do
74
- it 'rejects invalid preprocessing type' do
75
- expect do
76
- described_class.new(preprocessing: 'invalid')
77
- end.to raise_error ArgumentError, /preprocessing must be.*ImagePreprocessing.*Hash/
78
- end
79
-
80
- it 'accepts valid preprocessing hash' do
81
- expect do
82
- described_class.new(preprocessing: { target_dpi: 300 })
83
- end.not_to raise_error
84
- end
85
-
86
- it 'accepts valid preprocessing instance' do
87
- preprocessing = Kreuzberg::Config::ImagePreprocessing.new
88
- expect do
89
- described_class.new(preprocessing: preprocessing)
90
- end.not_to raise_error
91
- end
92
- end
93
-
94
- describe 'keyword arguments' do
95
- it 'accepts arbitrary keyword arguments' do
96
- config = described_class.new(
97
- dpi: 300,
98
- psm: 3,
99
- oem: 1,
100
- custom_option: 'value'
101
- )
102
-
103
- expect(config.options[:dpi]).to eq 300
104
- expect(config.options[:psm]).to eq 3
105
- expect(config.options[:oem]).to eq 1
106
- expect(config.options[:custom_option]).to eq 'value'
107
- end
108
-
109
- it 'stores all options with symbol keys' do
110
- config = described_class.new(foo: 'bar', baz: 42)
111
-
112
- expect(config.options.keys).to all be_a Symbol
113
- expect(config.options[:foo]).to eq 'bar'
114
- expect(config.options[:baz]).to eq 42
115
- end
116
- end
117
-
118
- describe 'equality' do
119
- it 'compares configs by options value' do
120
- config1 = described_class.new(dpi: 300, psm: 3)
121
- config2 = described_class.new(dpi: 300, psm: 3)
122
-
123
- expect(config1.options).to eq config2.options
124
- end
125
-
126
- it 'detects differences in options' do
127
- config1 = described_class.new(dpi: 300)
128
- config2 = described_class.new(dpi: 600)
129
-
130
- expect(config1.options).not_to eq config2.options
131
- end
132
- end
133
-
134
- describe 'nested config integration' do
135
- it 'can be nested in OCR config' do
136
- tesseract = described_class.new(dpi: 300, psm: 3)
137
- ocr = Kreuzberg::Config::OCR.new(tesseract_config: tesseract)
138
-
139
- expect(ocr.tesseract_config).to be_a described_class
140
- expect(ocr.tesseract_config.options[:dpi]).to eq 300
141
- end
142
-
143
- it 'accepts preprocessing nested in tesseract' do
144
- preprocessing_data = { target_dpi: 600, denoise: true }
145
- tesseract = described_class.new(preprocessing: preprocessing_data)
146
-
147
- expect(tesseract.options[:preprocessing]).to be_a Kreuzberg::Config::ImagePreprocessing
148
- expect(tesseract.options[:preprocessing].denoise).to be true
149
- end
150
- end
151
-
152
- describe 'symbol vs string key handling' do
153
- it 'normalizes all keys to symbols' do
154
- config = described_class.new(
155
- 'string_key' => 'value1',
156
- symbol_key: 'value2'
157
- )
158
-
159
- expect(config.options.keys).to all be_a Symbol
160
- expect(config.options[:string_key]).to eq 'value1'
161
- expect(config.options[:symbol_key]).to eq 'value2'
162
- end
163
-
164
- it 'preserves string values while converting keys to symbols' do
165
- config = described_class.new('test_key' => 'test_value')
166
-
167
- expect(config.options[:test_key]).to eq 'test_value'
168
- expect(config.options[:test_key]).to be_a String
169
- end
170
- end
171
-
172
- describe 'immutability concerns' do
173
- it 'stores options but does not freeze them by default' do
174
- config = described_class.new(value: 'test')
175
-
176
- # The config itself can be modified by re-assigning instance variables
177
- # This is a design choice that allows for mutability
178
- expect(config.options).to respond_to(:merge)
179
- end
180
- end
181
- end
@@ -1,251 +0,0 @@
1
- # frozen_string_literal: true
2
-
3
- RSpec.describe Kreuzberg::Config::TokenReduction do
4
- describe '#initialize' do
5
- it 'creates config with default values' do
6
- config = described_class.new
7
-
8
- expect(config.mode).to eq 'off'
9
- expect(config.preserve_important_words).to be true
10
- end
11
-
12
- it 'creates config with custom mode' do
13
- config = described_class.new(mode: 'light')
14
-
15
- expect(config.mode).to eq 'light'
16
- expect(config.preserve_important_words).to be true
17
- end
18
-
19
- it 'creates config with custom preserve setting' do
20
- config = described_class.new(
21
- mode: 'aggressive',
22
- preserve_important_words: false
23
- )
24
-
25
- expect(config.mode).to eq 'aggressive'
26
- expect(config.preserve_important_words).to be false
27
- end
28
-
29
- it 'converts mode symbol to string' do
30
- config = described_class.new(mode: :moderate)
31
-
32
- expect(config.mode).to eq 'moderate'
33
- expect(config.mode).to be_a String
34
- end
35
-
36
- it 'converts preserve_important_words to boolean' do
37
- config = described_class.new(preserve_important_words: 1)
38
-
39
- expect(config.preserve_important_words).to be true
40
- end
41
- end
42
-
43
- describe '#to_h' do
44
- it 'serializes to hash with all values' do
45
- config = described_class.new(
46
- mode: 'light',
47
- preserve_important_words: false
48
- )
49
- hash = config.to_h
50
-
51
- expect(hash).to be_a Hash
52
- expect(hash[:mode]).to eq 'light'
53
- expect(hash[:preserve_important_words]).to be false
54
- end
55
-
56
- it 'always includes all keys in hash' do
57
- config = described_class.new
58
- hash = config.to_h
59
-
60
- expect(hash.keys).to contain_exactly(:mode, :preserve_important_words)
61
- end
62
- end
63
-
64
- describe 'validation' do
65
- it 'accepts off mode' do
66
- expect do
67
- described_class.new(mode: 'off')
68
- end.not_to raise_error
69
- end
70
-
71
- it 'accepts light mode' do
72
- expect do
73
- described_class.new(mode: 'light')
74
- end.not_to raise_error
75
- end
76
-
77
- it 'accepts moderate mode' do
78
- expect do
79
- described_class.new(mode: 'moderate')
80
- end.not_to raise_error
81
- end
82
-
83
- it 'accepts aggressive mode' do
84
- expect do
85
- described_class.new(mode: 'aggressive')
86
- end.not_to raise_error
87
- end
88
-
89
- it 'accepts maximum mode' do
90
- expect do
91
- described_class.new(mode: 'maximum')
92
- end.not_to raise_error
93
- end
94
-
95
- it 'rejects invalid mode' do
96
- expect do
97
- described_class.new(mode: 'invalid_mode')
98
- end.to raise_error ArgumentError, /Invalid token reduction mode/
99
- end
100
-
101
- it 'lists valid modes in error message' do
102
- expect do
103
- described_class.new(mode: 'unknown')
104
- end.to raise_error ArgumentError, /off.*light.*moderate.*aggressive.*maximum/
105
- end
106
- end
107
-
108
- describe 'keyword arguments' do
109
- it 'accepts all keyword arguments' do
110
- config = described_class.new(
111
- mode: 'maximum',
112
- preserve_important_words: false
113
- )
114
-
115
- expect(config.mode).to eq 'maximum'
116
- expect(config.preserve_important_words).to be false
117
- end
118
- end
119
-
120
- describe 'equality' do
121
- it 'compares configs by value' do
122
- config1 = described_class.new(mode: 'light', preserve_important_words: true)
123
- config2 = described_class.new(mode: 'light', preserve_important_words: true)
124
-
125
- expect(config1.mode).to eq config2.mode
126
- expect(config1.preserve_important_words).to eq config2.preserve_important_words
127
- end
128
-
129
- it 'detects differences in mode' do
130
- config1 = described_class.new(mode: 'light')
131
- config2 = described_class.new(mode: 'aggressive')
132
-
133
- expect(config1.mode).not_to eq config2.mode
134
- end
135
-
136
- it 'detects differences in preserve_important_words' do
137
- config1 = described_class.new(preserve_important_words: true)
138
- config2 = described_class.new(preserve_important_words: false)
139
-
140
- expect(config1.preserve_important_words).not_to eq config2.preserve_important_words
141
- end
142
- end
143
-
144
- describe 'nested config integration' do
145
- it 'can be nested in Extraction config' do
146
- token_reduction = described_class.new(mode: 'light')
147
- extraction = Kreuzberg::Config::Extraction.new(token_reduction: token_reduction)
148
-
149
- expect(extraction.token_reduction).to be_a described_class
150
- expect(extraction.token_reduction.mode).to eq 'light'
151
- end
152
-
153
- it 'accepts hash in Extraction config' do
154
- extraction = Kreuzberg::Config::Extraction.new(
155
- token_reduction: { mode: 'moderate', preserve_important_words: true }
156
- )
157
-
158
- expect(extraction.token_reduction).to be_a described_class
159
- expect(extraction.token_reduction.mode).to eq 'moderate'
160
- expect(extraction.token_reduction.preserve_important_words).to be true
161
- end
162
- end
163
-
164
- describe 'symbol vs string key handling' do
165
- it 'converts symbol mode to string' do
166
- config = described_class.new(mode: :aggressive)
167
-
168
- expect(config.mode).to eq 'aggressive'
169
- expect(config.mode).to be_a String
170
- end
171
-
172
- it 'accepts string mode' do
173
- config = described_class.new(mode: 'light')
174
-
175
- expect(config.mode).to eq 'light'
176
- expect(config.mode).to be_a String
177
- end
178
- end
179
-
180
- describe 'boolean conversion' do
181
- it 'converts truthy preserve_important_words to true' do
182
- config = described_class.new(preserve_important_words: 1)
183
-
184
- expect(config.preserve_important_words).to be true
185
- end
186
-
187
- it 'converts false preserve_important_words to false' do
188
- config = described_class.new(preserve_important_words: false)
189
-
190
- expect(config.preserve_important_words).to be false
191
- end
192
-
193
- it 'converts string yes to true' do
194
- config = described_class.new(preserve_important_words: 'yes')
195
-
196
- expect(config.preserve_important_words).to be true
197
- end
198
- end
199
-
200
- describe 'reduction modes' do
201
- it 'off mode disables reduction' do
202
- config = described_class.new(mode: 'off')
203
-
204
- expect(config.mode).to eq 'off'
205
- end
206
-
207
- it 'light mode provides light reduction' do
208
- config = described_class.new(mode: 'light')
209
-
210
- expect(config.mode).to eq 'light'
211
- end
212
-
213
- it 'moderate mode provides balanced reduction' do
214
- config = described_class.new(mode: 'moderate')
215
-
216
- expect(config.mode).to eq 'moderate'
217
- end
218
-
219
- it 'aggressive mode reduces more tokens' do
220
- config = described_class.new(mode: 'aggressive')
221
-
222
- expect(config.mode).to eq 'aggressive'
223
- end
224
-
225
- it 'maximum mode is most aggressive' do
226
- config = described_class.new(mode: 'maximum')
227
-
228
- expect(config.mode).to eq 'maximum'
229
- end
230
- end
231
-
232
- describe 'default behavior' do
233
- it 'defaults to off mode for safety' do
234
- config = described_class.new
235
-
236
- expect(config.mode).to eq 'off'
237
- end
238
-
239
- it 'defaults to preserving important words' do
240
- config = described_class.new
241
-
242
- expect(config.preserve_important_words).to be true
243
- end
244
-
245
- it 'can enable reduction with light mode' do
246
- config = described_class.new(mode: 'light')
247
-
248
- expect(config.mode).to eq 'light'
249
- end
250
- end
251
- end