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
@@ -1,267 +0,0 @@
1
- # frozen_string_literal: true
2
-
3
- RSpec.describe Kreuzberg::Config::PDF do
4
- describe '#initialize' do
5
- it 'creates config with default values' do
6
- config = described_class.new
7
-
8
- expect(config.extract_images).to be false
9
- expect(config.passwords).to be_nil
10
- expect(config.extract_metadata).to be true
11
- expect(config.font_config).to be_nil
12
- expect(config.hierarchy).to be_nil
13
- end
14
-
15
- it 'creates config with custom values' do
16
- config = described_class.new(
17
- extract_images: true,
18
- passwords: %w[secret backup],
19
- extract_metadata: false
20
- )
21
-
22
- expect(config.extract_images).to be true
23
- expect(config.passwords).to eq %w[secret backup]
24
- expect(config.extract_metadata).to be false
25
- end
26
-
27
- it 'accepts passwords as single string' do
28
- config = described_class.new(passwords: 'secret')
29
-
30
- expect(config.passwords).to eq ['secret']
31
- expect(config.passwords).to be_a Array
32
- end
33
-
34
- it 'accepts passwords as array of strings' do
35
- config = described_class.new(passwords: %w[pwd1 pwd2 pwd3])
36
-
37
- expect(config.passwords).to eq %w[pwd1 pwd2 pwd3]
38
- end
39
-
40
- it 'converts passwords to strings' do
41
- config = described_class.new(passwords: [123, :symbol])
42
-
43
- expect(config.passwords).to eq %w[123 symbol]
44
- expect(config.passwords.all?(String)).to be true
45
- end
46
-
47
- it 'accepts font_config as instance' do
48
- font_config = Kreuzberg::Config::FontConfig.new(enabled: true)
49
- config = described_class.new(font_config: font_config)
50
-
51
- expect(config.font_config).to be_a Kreuzberg::Config::FontConfig
52
- end
53
-
54
- it 'converts font_config hash to instance' do
55
- config = described_class.new(font_config: { enabled: false })
56
-
57
- expect(config.font_config).to be_a Kreuzberg::Config::FontConfig
58
- expect(config.font_config.enabled).to be false
59
- end
60
-
61
- it 'accepts hierarchy as instance' do
62
- hierarchy = Kreuzberg::Config::Hierarchy.new(enabled: true)
63
- config = described_class.new(hierarchy: hierarchy)
64
-
65
- expect(config.hierarchy).to be_a Kreuzberg::Config::Hierarchy
66
- end
67
-
68
- it 'converts hierarchy hash to instance' do
69
- config = described_class.new(hierarchy: { enabled: true, k_clusters: 8 })
70
-
71
- expect(config.hierarchy).to be_a Kreuzberg::Config::Hierarchy
72
- expect(config.hierarchy.enabled).to be true
73
- end
74
- end
75
-
76
- describe '#to_h' do
77
- it 'serializes to hash with default values' do
78
- config = described_class.new
79
- hash = config.to_h
80
-
81
- expect(hash).to be_a Hash
82
- expect(hash[:extract_images]).to be false
83
- expect(hash[:extract_metadata]).to be true
84
- end
85
-
86
- it 'includes passwords in hash when present' do
87
- config = described_class.new(passwords: %w[secret backup])
88
- hash = config.to_h
89
-
90
- expect(hash[:passwords]).to eq %w[secret backup]
91
- end
92
-
93
- it 'includes font_config in hash when present' do
94
- config = described_class.new(font_config: { enabled: true })
95
- hash = config.to_h
96
-
97
- expect(hash[:font_config]).to be_a Hash
98
- end
99
-
100
- it 'includes hierarchy in hash when present' do
101
- config = described_class.new(hierarchy: { enabled: true })
102
- hash = config.to_h
103
-
104
- expect(hash[:hierarchy]).to be_a Hash
105
- end
106
-
107
- it 'compacts nil values from hash' do
108
- config = described_class.new(extract_images: true)
109
- hash = config.to_h
110
-
111
- expect(hash.key?(:passwords)).to be false
112
- expect(hash.key?(:font_config)).to be false
113
- end
114
- end
115
-
116
- describe 'validation' do
117
- it 'rejects invalid font_config type' do
118
- expect do
119
- described_class.new(font_config: 'invalid')
120
- end.to raise_error ArgumentError, /Expected.*FontConfig.*Hash.*nil/
121
- end
122
-
123
- it 'rejects invalid hierarchy type' do
124
- expect do
125
- described_class.new(hierarchy: 'invalid')
126
- end.to raise_error ArgumentError, /Expected.*Hierarchy.*Hash.*nil/
127
- end
128
-
129
- it 'accepts valid boolean extract_images' do
130
- expect do
131
- described_class.new(extract_images: true)
132
- end.not_to raise_error
133
- end
134
- end
135
-
136
- describe 'keyword arguments' do
137
- it 'accepts all keyword arguments' do
138
- config = described_class.new(
139
- extract_images: true,
140
- passwords: %w[pwd1 pwd2],
141
- extract_metadata: false,
142
- font_config: { enabled: true },
143
- hierarchy: { k_clusters: 10 }
144
- )
145
-
146
- expect(config.extract_images).to be true
147
- expect(config.passwords).to eq %w[pwd1 pwd2]
148
- expect(config.extract_metadata).to be false
149
- expect(config.font_config).to be_a Kreuzberg::Config::FontConfig
150
- expect(config.hierarchy).to be_a Kreuzberg::Config::Hierarchy
151
- end
152
- end
153
-
154
- describe 'equality' do
155
- it 'compares configs by value' do
156
- config1 = described_class.new(
157
- extract_images: true,
158
- extract_metadata: false
159
- )
160
- config2 = described_class.new(
161
- extract_images: true,
162
- extract_metadata: false
163
- )
164
-
165
- expect(config1.extract_images).to eq config2.extract_images
166
- expect(config1.extract_metadata).to eq config2.extract_metadata
167
- end
168
-
169
- it 'detects differences in extract_images' do
170
- config1 = described_class.new(extract_images: true)
171
- config2 = described_class.new(extract_images: false)
172
-
173
- expect(config1.extract_images).not_to eq config2.extract_images
174
- end
175
-
176
- it 'detects differences in passwords' do
177
- config1 = described_class.new(passwords: %w[pwd1])
178
- config2 = described_class.new(passwords: %w[pwd2])
179
-
180
- expect(config1.passwords).not_to eq config2.passwords
181
- end
182
- end
183
-
184
- describe 'nested config integration' do
185
- it 'can be nested in Extraction config' do
186
- pdf = described_class.new(extract_images: true)
187
- extraction = Kreuzberg::Config::Extraction.new(pdf_options: pdf)
188
-
189
- expect(extraction.pdf_options).to be_a described_class
190
- expect(extraction.pdf_options.extract_images).to be true
191
- end
192
-
193
- it 'accepts hash in Extraction config' do
194
- extraction = Kreuzberg::Config::Extraction.new(
195
- pdf_options: { extract_images: true, passwords: ['secret'] }
196
- )
197
-
198
- expect(extraction.pdf_options).to be_a described_class
199
- expect(extraction.pdf_options.extract_images).to be true
200
- expect(extraction.pdf_options.passwords).to eq ['secret']
201
- end
202
- end
203
-
204
- describe 'font_config assignment' do
205
- it 'allows setting font_config after initialization' do
206
- config = described_class.new
207
- font_config = Kreuzberg::Config::FontConfig.new(enabled: true)
208
- config.font_config = font_config
209
-
210
- expect(config.font_config).to be_a Kreuzberg::Config::FontConfig
211
- expect(config.font_config.enabled).to be true
212
- end
213
-
214
- it 'converts hash to font_config instance on assignment' do
215
- config = described_class.new
216
- config.font_config = { enabled: false }
217
-
218
- expect(config.font_config).to be_a Kreuzberg::Config::FontConfig
219
- expect(config.font_config.enabled).to be false
220
- end
221
- end
222
-
223
- describe 'hierarchy assignment' do
224
- it 'allows setting hierarchy after initialization' do
225
- config = described_class.new
226
- hierarchy = Kreuzberg::Config::Hierarchy.new(enabled: true)
227
- config.hierarchy = hierarchy
228
-
229
- expect(config.hierarchy).to be_a Kreuzberg::Config::Hierarchy
230
- expect(config.hierarchy.enabled).to be true
231
- end
232
-
233
- it 'converts hash to hierarchy instance on assignment' do
234
- config = described_class.new
235
- config.hierarchy = { enabled: true, k_clusters: 6 }
236
-
237
- expect(config.hierarchy).to be_a Kreuzberg::Config::Hierarchy
238
- expect(config.hierarchy.enabled).to be true
239
- end
240
- end
241
-
242
- describe 'boolean conversion' do
243
- it 'converts truthy extract_images to true' do
244
- config = described_class.new(extract_images: 1)
245
-
246
- expect(config.extract_images).to be true
247
- end
248
-
249
- it 'converts false extract_images to false' do
250
- config = described_class.new(extract_images: false)
251
-
252
- expect(config.extract_images).to be false
253
- end
254
-
255
- it 'converts truthy extract_metadata to true' do
256
- config = described_class.new(extract_metadata: 'yes')
257
-
258
- expect(config.extract_metadata).to be true
259
- end
260
-
261
- it 'converts false extract_metadata to false' do
262
- config = described_class.new(extract_metadata: false)
263
-
264
- expect(config.extract_metadata).to be false
265
- end
266
- end
267
- end
@@ -1,290 +0,0 @@
1
- # frozen_string_literal: true
2
-
3
- RSpec.describe Kreuzberg::Config::PostProcessor do
4
- describe '#initialize' do
5
- it 'creates config with default values' do
6
- config = described_class.new
7
-
8
- expect(config.enabled).to be true
9
- expect(config.enabled_processors).to be_nil
10
- expect(config.disabled_processors).to be_nil
11
- end
12
-
13
- it 'creates config with enabled true' do
14
- config = described_class.new(enabled: true)
15
-
16
- expect(config.enabled).to be true
17
- end
18
-
19
- it 'creates config with enabled false' do
20
- config = described_class.new(enabled: false)
21
-
22
- expect(config.enabled).to be false
23
- end
24
-
25
- it 'creates config with enabled_processors list' do
26
- config = described_class.new(
27
- enabled: true,
28
- enabled_processors: %w[quality formatting]
29
- )
30
-
31
- expect(config.enabled_processors).to eq %w[quality formatting]
32
- end
33
-
34
- it 'creates config with disabled_processors list' do
35
- config = described_class.new(
36
- enabled: true,
37
- disabled_processors: %w[token_reduction]
38
- )
39
-
40
- expect(config.disabled_processors).to eq %w[token_reduction]
41
- end
42
-
43
- it 'converts enabled_processors to strings' do
44
- config = described_class.new(enabled_processors: %i[quality formatting])
45
-
46
- expect(config.enabled_processors).to eq %w[quality formatting]
47
- expect(config.enabled_processors.all?(String)).to be true
48
- end
49
-
50
- it 'converts disabled_processors to strings' do
51
- config = described_class.new(disabled_processors: [:quality])
52
-
53
- expect(config.disabled_processors).to eq %w[quality]
54
- expect(config.disabled_processors.all?(String)).to be true
55
- end
56
-
57
- it 'converts enabled to boolean' do
58
- config = described_class.new(enabled: 1)
59
-
60
- expect(config.enabled).to be true
61
- end
62
- end
63
-
64
- describe '#to_h' do
65
- it 'serializes to hash with default values' do
66
- config = described_class.new
67
- hash = config.to_h
68
-
69
- expect(hash).to be_a Hash
70
- expect(hash[:enabled]).to be true
71
- end
72
-
73
- it 'includes enabled_processors in hash when present' do
74
- config = described_class.new(enabled_processors: %w[quality])
75
- hash = config.to_h
76
-
77
- expect(hash[:enabled_processors]).to eq %w[quality]
78
- end
79
-
80
- it 'includes disabled_processors in hash when present' do
81
- config = described_class.new(disabled_processors: %w[token_reduction])
82
- hash = config.to_h
83
-
84
- expect(hash[:disabled_processors]).to eq %w[token_reduction]
85
- end
86
-
87
- it 'compacts nil values from hash' do
88
- config = described_class.new(enabled: true)
89
- hash = config.to_h
90
-
91
- expect(hash.key?(:enabled_processors)).to be false
92
- expect(hash.key?(:disabled_processors)).to be false
93
- end
94
- end
95
-
96
- describe 'validation' do
97
- it 'accepts enabled true' do
98
- expect do
99
- described_class.new(enabled: true)
100
- end.not_to raise_error
101
- end
102
-
103
- it 'accepts enabled false' do
104
- expect do
105
- described_class.new(enabled: false)
106
- end.not_to raise_error
107
- end
108
-
109
- it 'accepts enabled_processors list' do
110
- expect do
111
- described_class.new(enabled_processors: %w[quality formatting])
112
- end.not_to raise_error
113
- end
114
-
115
- it 'accepts disabled_processors list' do
116
- expect do
117
- described_class.new(disabled_processors: %w[token_reduction])
118
- end.not_to raise_error
119
- end
120
-
121
- it 'accepts both enabled and disabled processors' do
122
- expect do
123
- described_class.new(
124
- enabled_processors: %w[quality],
125
- disabled_processors: %w[formatting]
126
- )
127
- end.not_to raise_error
128
- end
129
- end
130
-
131
- describe 'keyword arguments' do
132
- it 'accepts all keyword arguments' do
133
- config = described_class.new(
134
- enabled: true,
135
- enabled_processors: %w[quality],
136
- disabled_processors: %w[token_reduction]
137
- )
138
-
139
- expect(config.enabled).to be true
140
- expect(config.enabled_processors).to eq %w[quality]
141
- expect(config.disabled_processors).to eq %w[token_reduction]
142
- end
143
- end
144
-
145
- describe 'equality' do
146
- it 'compares configs by value' do
147
- config1 = described_class.new(
148
- enabled: true,
149
- enabled_processors: %w[quality]
150
- )
151
- config2 = described_class.new(
152
- enabled: true,
153
- enabled_processors: %w[quality]
154
- )
155
-
156
- expect(config1.enabled).to eq config2.enabled
157
- expect(config1.enabled_processors).to eq config2.enabled_processors
158
- end
159
-
160
- it 'detects differences in enabled' do
161
- config1 = described_class.new(enabled: true)
162
- config2 = described_class.new(enabled: false)
163
-
164
- expect(config1.enabled).not_to eq config2.enabled
165
- end
166
-
167
- it 'detects differences in enabled_processors' do
168
- config1 = described_class.new(enabled_processors: %w[quality])
169
- config2 = described_class.new(enabled_processors: %w[formatting])
170
-
171
- expect(config1.enabled_processors).not_to eq config2.enabled_processors
172
- end
173
- end
174
-
175
- describe 'nested config integration' do
176
- it 'can be nested in Extraction config' do
177
- postprocessor = described_class.new(
178
- enabled: true,
179
- enabled_processors: %w[quality]
180
- )
181
- extraction = Kreuzberg::Config::Extraction.new(postprocessor: postprocessor)
182
-
183
- expect(extraction.postprocessor).to be_a described_class
184
- expect(extraction.postprocessor.enabled).to be true
185
- expect(extraction.postprocessor.enabled_processors).to eq %w[quality]
186
- end
187
-
188
- it 'accepts hash in Extraction config' do
189
- extraction = Kreuzberg::Config::Extraction.new(
190
- postprocessor: {
191
- enabled: true,
192
- enabled_processors: %w[quality formatting]
193
- }
194
- )
195
-
196
- expect(extraction.postprocessor).to be_a described_class
197
- expect(extraction.postprocessor.enabled).to be true
198
- expect(extraction.postprocessor.enabled_processors).to eq %w[quality formatting]
199
- end
200
- end
201
-
202
- describe 'symbol vs string key handling' do
203
- it 'converts symbol enabled_processors to strings' do
204
- config = described_class.new(enabled_processors: %i[quality formatting])
205
-
206
- expect(config.enabled_processors).to eq %w[quality formatting]
207
- expect(config.enabled_processors.all?(String)).to be true
208
- end
209
-
210
- it 'converts symbol disabled_processors to strings' do
211
- config = described_class.new(disabled_processors: [:token_reduction])
212
-
213
- expect(config.disabled_processors).to eq %w[token_reduction]
214
- expect(config.disabled_processors.all?(String)).to be true
215
- end
216
- end
217
-
218
- describe 'processor lists' do
219
- it 'stores empty enabled_processors list' do
220
- config = described_class.new(enabled_processors: [])
221
-
222
- expect(config.enabled_processors).to eq []
223
- end
224
-
225
- it 'stores single enabled_processor' do
226
- config = described_class.new(enabled_processors: %w[quality])
227
-
228
- expect(config.enabled_processors).to eq %w[quality]
229
- end
230
-
231
- it 'stores multiple enabled_processors' do
232
- processors = %w[quality formatting cleanup]
233
- config = described_class.new(enabled_processors: processors)
234
-
235
- expect(config.enabled_processors).to eq processors
236
- end
237
-
238
- it 'stores multiple disabled_processors' do
239
- processors = %w[token_reduction duplicate_removal]
240
- config = described_class.new(disabled_processors: processors)
241
-
242
- expect(config.disabled_processors).to eq processors
243
- end
244
- end
245
-
246
- describe 'boolean conversion' do
247
- it 'converts truthy enabled to true' do
248
- config = described_class.new(enabled: 1)
249
-
250
- expect(config.enabled).to be true
251
- end
252
-
253
- it 'converts false enabled to false' do
254
- config = described_class.new(enabled: false)
255
-
256
- expect(config.enabled).to be false
257
- end
258
-
259
- it 'converts string true to true' do
260
- config = described_class.new(enabled: 'yes')
261
-
262
- expect(config.enabled).to be true
263
- end
264
- end
265
-
266
- describe 'default behavior' do
267
- it 'defaults to enabled' do
268
- config = described_class.new
269
-
270
- expect(config.enabled).to be true
271
- end
272
-
273
- it 'defaults to no specific processors' do
274
- config = described_class.new
275
-
276
- expect(config.enabled_processors).to be_nil
277
- expect(config.disabled_processors).to be_nil
278
- end
279
-
280
- it 'allows disabling while specifying processors' do
281
- config = described_class.new(
282
- enabled: false,
283
- enabled_processors: %w[quality]
284
- )
285
-
286
- expect(config.enabled).to be false
287
- expect(config.enabled_processors).to eq %w[quality]
288
- end
289
- end
290
- end