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
@@ -1,285 +0,0 @@
1
- # frozen_string_literal: true
2
-
3
- RSpec.describe Kreuzberg::Config::FontConfig 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.custom_font_dirs).to be_nil
10
- end
11
-
12
- it 'creates config with enabled false' do
13
- config = described_class.new(enabled: false)
14
-
15
- expect(config.enabled).to be false
16
- end
17
-
18
- it 'creates config with custom_font_dirs' do
19
- dirs = ['/usr/share/fonts', '/home/user/.fonts']
20
- config = described_class.new(custom_font_dirs: dirs)
21
-
22
- expect(config.custom_font_dirs).to eq dirs
23
- end
24
-
25
- it 'accepts single font directory as string' do
26
- config = described_class.new(custom_font_dirs: '/usr/share/fonts')
27
-
28
- expect(config.custom_font_dirs).to eq '/usr/share/fonts'
29
- end
30
-
31
- it 'accepts multiple directories as array' do
32
- dirs = ['/fonts1', '/fonts2', '/fonts3']
33
- config = described_class.new(custom_font_dirs: dirs)
34
-
35
- expect(config.custom_font_dirs).to eq dirs
36
- end
37
-
38
- it 'converts enabled to boolean' do
39
- config = described_class.new(enabled: 1)
40
-
41
- expect(config.enabled).to be true
42
- end
43
- end
44
-
45
- describe '#to_h' do
46
- it 'serializes to hash with default values' do
47
- config = described_class.new
48
- hash = config.to_h
49
-
50
- expect(hash).to be_a Hash
51
- expect(hash[:enabled]).to be true
52
- end
53
-
54
- it 'includes custom_font_dirs when present' do
55
- dirs = ['/fonts']
56
- config = described_class.new(custom_font_dirs: dirs)
57
- hash = config.to_h
58
-
59
- expect(hash[:custom_font_dirs]).to eq dirs
60
- end
61
-
62
- it 'compacts nil values from hash' do
63
- config = described_class.new(enabled: true)
64
- hash = config.to_h
65
-
66
- expect(hash.key?(:custom_font_dirs)).to be false
67
- end
68
-
69
- it 'includes both keys when both are present' do
70
- config = described_class.new(
71
- enabled: true,
72
- custom_font_dirs: ['/fonts']
73
- )
74
- hash = config.to_h
75
-
76
- expect(hash.keys).to contain_exactly(:enabled, :custom_font_dirs)
77
- end
78
- end
79
-
80
- describe 'validation' do
81
- it 'accepts enabled true' do
82
- expect do
83
- described_class.new(enabled: true)
84
- end.not_to raise_error
85
- end
86
-
87
- it 'accepts enabled false' do
88
- expect do
89
- described_class.new(enabled: false)
90
- end.not_to raise_error
91
- end
92
-
93
- it 'accepts custom_font_dirs as string' do
94
- expect do
95
- described_class.new(custom_font_dirs: '/fonts')
96
- end.not_to raise_error
97
- end
98
-
99
- it 'accepts custom_font_dirs as array' do
100
- expect do
101
- described_class.new(custom_font_dirs: ['/fonts1', '/fonts2'])
102
- end.not_to raise_error
103
- end
104
- end
105
-
106
- describe 'keyword arguments' do
107
- it 'accepts all keyword arguments' do
108
- dirs = ['/fonts']
109
- config = described_class.new(
110
- enabled: false,
111
- custom_font_dirs: dirs
112
- )
113
-
114
- expect(config.enabled).to be false
115
- expect(config.custom_font_dirs).to eq dirs
116
- end
117
- end
118
-
119
- describe 'equality' do
120
- it 'compares configs by value' do
121
- config1 = described_class.new(
122
- enabled: true,
123
- custom_font_dirs: ['/fonts']
124
- )
125
- config2 = described_class.new(
126
- enabled: true,
127
- custom_font_dirs: ['/fonts']
128
- )
129
-
130
- expect(config1.enabled).to eq config2.enabled
131
- expect(config1.custom_font_dirs).to eq config2.custom_font_dirs
132
- end
133
-
134
- it 'detects differences in enabled' do
135
- config1 = described_class.new(enabled: true)
136
- config2 = described_class.new(enabled: false)
137
-
138
- expect(config1.enabled).not_to eq config2.enabled
139
- end
140
-
141
- it 'detects differences in custom_font_dirs' do
142
- config1 = described_class.new(custom_font_dirs: ['/fonts1'])
143
- config2 = described_class.new(custom_font_dirs: ['/fonts2'])
144
-
145
- expect(config1.custom_font_dirs).not_to eq config2.custom_font_dirs
146
- end
147
- end
148
-
149
- describe 'nested config integration' do
150
- it 'can be nested in PDF config' do
151
- font_config = described_class.new(enabled: true, custom_font_dirs: ['/fonts'])
152
- pdf = Kreuzberg::Config::PDF.new(font_config: font_config)
153
-
154
- expect(pdf.font_config).to be_a described_class
155
- expect(pdf.font_config.enabled).to be true
156
- expect(pdf.font_config.custom_font_dirs).to eq ['/fonts']
157
- end
158
-
159
- it 'accepts hash in PDF config' do
160
- pdf = Kreuzberg::Config::PDF.new(
161
- font_config: { enabled: true, custom_font_dirs: ['/fonts'] }
162
- )
163
-
164
- expect(pdf.font_config).to be_a described_class
165
- expect(pdf.font_config.enabled).to be true
166
- expect(pdf.font_config.custom_font_dirs).to eq ['/fonts']
167
- end
168
-
169
- it 'can be nested in Extraction config via PDF' do
170
- extraction = Kreuzberg::Config::Extraction.new(
171
- pdf_options: { font_config: { enabled: true } }
172
- )
173
-
174
- expect(extraction.pdf_options.font_config).to be_a described_class
175
- expect(extraction.pdf_options.font_config.enabled).to be true
176
- end
177
- end
178
-
179
- describe 'symbol vs string key handling' do
180
- it 'converts symbol enabled to boolean' do
181
- config = described_class.new(enabled: true)
182
-
183
- expect(config.enabled).to be true
184
- end
185
-
186
- it 'preserves custom_font_dirs as array' do
187
- dirs = ['/fonts1', '/fonts2']
188
- config = described_class.new(custom_font_dirs: dirs)
189
-
190
- expect(config.custom_font_dirs).to eq dirs
191
- end
192
- end
193
-
194
- describe 'boolean conversion' do
195
- it 'converts truthy enabled to true' do
196
- config = described_class.new(enabled: 1)
197
-
198
- expect(config.enabled).to be true
199
- end
200
-
201
- it 'converts false enabled to false' do
202
- config = described_class.new(enabled: false)
203
-
204
- expect(config.enabled).to be false
205
- end
206
-
207
- it 'converts string yes to true' do
208
- config = described_class.new(enabled: 'yes')
209
-
210
- expect(config.enabled).to be true
211
- end
212
-
213
- it 'converts nil to false' do
214
- config = described_class.new(enabled: nil)
215
-
216
- expect(config.enabled).to be false
217
- end
218
- end
219
-
220
- describe 'font directory handling' do
221
- it 'stores single directory path as string' do
222
- config = described_class.new(custom_font_dirs: '/usr/share/fonts')
223
-
224
- expect(config.custom_font_dirs).to eq '/usr/share/fonts'
225
- end
226
-
227
- it 'stores multiple directories as array' do
228
- dirs = ['/fonts1', '/fonts2', '/fonts3']
229
- config = described_class.new(custom_font_dirs: dirs)
230
-
231
- expect(config.custom_font_dirs).to eq dirs
232
- expect(config.custom_font_dirs).to be_a Array
233
- end
234
-
235
- it 'preserves exact directory paths' do
236
- dir = '/home/user/.local/share/fonts'
237
- config = described_class.new(custom_font_dirs: dir)
238
-
239
- expect(config.custom_font_dirs).to eq dir
240
- end
241
-
242
- it 'preserves array of directory paths' do
243
- dirs = ['/usr/share/fonts', '/home/user/.fonts', '~/.local/share/fonts']
244
- config = described_class.new(custom_font_dirs: dirs)
245
-
246
- expect(config.custom_font_dirs).to eq dirs
247
- end
248
- end
249
-
250
- describe 'mutability' do
251
- it 'allows modification of enabled' do
252
- config = described_class.new(enabled: true)
253
- config.enabled = false
254
-
255
- expect(config.enabled).to be false
256
- end
257
-
258
- it 'allows modification of custom_font_dirs' do
259
- config = described_class.new(custom_font_dirs: ['/fonts1'])
260
- config.custom_font_dirs = ['/fonts2']
261
-
262
- expect(config.custom_font_dirs).to eq ['/fonts2']
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 custom font directories' do
274
- config = described_class.new
275
-
276
- expect(config.custom_font_dirs).to be_nil
277
- end
278
-
279
- it 'allows disabling font support' do
280
- config = described_class.new(enabled: false)
281
-
282
- expect(config.enabled).to be false
283
- end
284
- end
285
- end
@@ -1,314 +0,0 @@
1
- # frozen_string_literal: true
2
-
3
- RSpec.describe Kreuzberg::Config::Hierarchy 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.k_clusters).to eq 6
10
- expect(config.include_bbox).to be true
11
- expect(config.ocr_coverage_threshold).to be_nil
12
- end
13
-
14
- it 'creates config with custom values' do
15
- config = described_class.new(
16
- enabled: false,
17
- k_clusters: 10,
18
- include_bbox: false,
19
- ocr_coverage_threshold: 0.95
20
- )
21
-
22
- expect(config.enabled).to be false
23
- expect(config.k_clusters).to eq 10
24
- expect(config.include_bbox).to be false
25
- expect(config.ocr_coverage_threshold).to eq 0.95
26
- end
27
-
28
- it 'converts k_clusters to integer' do
29
- config = described_class.new(k_clusters: '8')
30
-
31
- expect(config.k_clusters).to eq 8
32
- expect(config.k_clusters).to be_a Integer
33
- end
34
-
35
- it 'converts enabled to boolean' do
36
- config = described_class.new(enabled: 1)
37
-
38
- expect(config.enabled).to be true
39
- end
40
-
41
- it 'converts include_bbox to boolean' do
42
- config = described_class.new(include_bbox: false)
43
-
44
- expect(config.include_bbox).to be false
45
- end
46
-
47
- it 'converts ocr_coverage_threshold to float' do
48
- config = described_class.new(ocr_coverage_threshold: '0.85')
49
-
50
- expect(config.ocr_coverage_threshold).to eq 0.85
51
- expect(config.ocr_coverage_threshold).to be_a Float
52
- end
53
- end
54
-
55
- describe '#to_h' do
56
- it 'serializes to hash with all values' do
57
- config = described_class.new(
58
- enabled: true,
59
- k_clusters: 8,
60
- include_bbox: true
61
- )
62
- hash = config.to_h
63
-
64
- expect(hash).to be_a Hash
65
- expect(hash[:enabled]).to be true
66
- expect(hash[:k_clusters]).to eq 8
67
- expect(hash[:include_bbox]).to be true
68
- end
69
-
70
- it 'includes ocr_coverage_threshold when present' do
71
- config = described_class.new(ocr_coverage_threshold: 0.9)
72
- hash = config.to_h
73
-
74
- expect(hash[:ocr_coverage_threshold]).to eq 0.9
75
- end
76
-
77
- it 'compacts nil values from hash' do
78
- config = described_class.new(enabled: true)
79
- hash = config.to_h
80
-
81
- expect(hash.key?(:ocr_coverage_threshold)).to be false
82
- end
83
- end
84
-
85
- describe '.from_h' do
86
- it 'creates from hash' do
87
- hash = { enabled: true, k_clusters: 8 }
88
- config = described_class.from_h(hash)
89
-
90
- expect(config).to be_a described_class
91
- expect(config.enabled).to be true
92
- expect(config.k_clusters).to eq 8
93
- end
94
-
95
- it 'returns nil for nil input' do
96
- config = described_class.from_h(nil)
97
-
98
- expect(config).to be_nil
99
- end
100
-
101
- it 'returns instance as-is' do
102
- original = described_class.new(k_clusters: 10)
103
- config = described_class.from_h(original)
104
-
105
- expect(config).to be original
106
- end
107
-
108
- it 'converts symbol keys in hash' do
109
- hash = { 'enabled' => true, 'k_clusters' => 8 }
110
- config = described_class.from_h(hash)
111
-
112
- expect(config.enabled).to be true
113
- expect(config.k_clusters).to eq 8
114
- end
115
- end
116
-
117
- describe 'validation' do
118
- it 'accepts valid k_clusters' do
119
- expect do
120
- described_class.new(k_clusters: 5)
121
- end.not_to raise_error
122
- end
123
-
124
- it 'accepts valid ocr_coverage_threshold' do
125
- expect do
126
- described_class.new(ocr_coverage_threshold: 0.8)
127
- end.not_to raise_error
128
- end
129
-
130
- it 'accepts enabled true' do
131
- expect do
132
- described_class.new(enabled: true)
133
- end.not_to raise_error
134
- end
135
- end
136
-
137
- describe 'keyword arguments' do
138
- it 'accepts all keyword arguments' do
139
- config = described_class.new(
140
- enabled: false,
141
- k_clusters: 12,
142
- include_bbox: false,
143
- ocr_coverage_threshold: 0.75
144
- )
145
-
146
- expect(config.enabled).to be false
147
- expect(config.k_clusters).to eq 12
148
- expect(config.include_bbox).to be false
149
- expect(config.ocr_coverage_threshold).to eq 0.75
150
- end
151
- end
152
-
153
- describe 'equality' do
154
- it 'compares configs by value' do
155
- config1 = described_class.new(
156
- enabled: true,
157
- k_clusters: 8
158
- )
159
- config2 = described_class.new(
160
- enabled: true,
161
- k_clusters: 8
162
- )
163
-
164
- expect(config1.enabled).to eq config2.enabled
165
- expect(config1.k_clusters).to eq config2.k_clusters
166
- end
167
-
168
- it 'detects differences in enabled' do
169
- config1 = described_class.new(enabled: true)
170
- config2 = described_class.new(enabled: false)
171
-
172
- expect(config1.enabled).not_to eq config2.enabled
173
- end
174
-
175
- it 'detects differences in k_clusters' do
176
- config1 = described_class.new(k_clusters: 6)
177
- config2 = described_class.new(k_clusters: 10)
178
-
179
- expect(config1.k_clusters).not_to eq config2.k_clusters
180
- end
181
-
182
- it 'detects differences in ocr_coverage_threshold' do
183
- config1 = described_class.new(ocr_coverage_threshold: 0.8)
184
- config2 = described_class.new(ocr_coverage_threshold: 0.9)
185
-
186
- expect(config1.ocr_coverage_threshold).not_to eq config2.ocr_coverage_threshold
187
- end
188
- end
189
-
190
- describe 'nested config integration' do
191
- it 'can be nested in PDF config' do
192
- hierarchy = described_class.new(k_clusters: 8, enabled: true)
193
- pdf = Kreuzberg::Config::PDF.new(hierarchy: hierarchy)
194
-
195
- expect(pdf.hierarchy).to be_a described_class
196
- expect(pdf.hierarchy.k_clusters).to eq 8
197
- expect(pdf.hierarchy.enabled).to be true
198
- end
199
-
200
- it 'accepts hash in PDF config' do
201
- pdf = Kreuzberg::Config::PDF.new(
202
- hierarchy: { enabled: true, k_clusters: 10 }
203
- )
204
-
205
- expect(pdf.hierarchy).to be_a described_class
206
- expect(pdf.hierarchy.enabled).to be true
207
- expect(pdf.hierarchy.k_clusters).to eq 10
208
- end
209
-
210
- it 'can be nested in Extraction config via PDF' do
211
- extraction = Kreuzberg::Config::Extraction.new(
212
- pdf_options: { hierarchy: { k_clusters: 8 } }
213
- )
214
-
215
- expect(extraction.pdf_options.hierarchy).to be_a described_class
216
- expect(extraction.pdf_options.hierarchy.k_clusters).to eq 8
217
- end
218
- end
219
-
220
- describe 'symbol vs string key handling' do
221
- it 'converts symbol enabled to boolean' do
222
- config = described_class.new(enabled: true)
223
-
224
- expect(config.enabled).to be true
225
- end
226
-
227
- it 'converts k_clusters string to integer' do
228
- config = described_class.new(k_clusters: '12')
229
-
230
- expect(config.k_clusters).to eq 12
231
- expect(config.k_clusters).to be_a Integer
232
- end
233
- end
234
-
235
- describe 'boolean conversion' do
236
- it 'converts truthy enabled to true' do
237
- config = described_class.new(enabled: 1)
238
-
239
- expect(config.enabled).to be true
240
- end
241
-
242
- it 'converts false enabled to false' do
243
- config = described_class.new(enabled: false)
244
-
245
- expect(config.enabled).to be false
246
- end
247
-
248
- it 'converts truthy include_bbox to true' do
249
- config = described_class.new(include_bbox: 'yes')
250
-
251
- expect(config.include_bbox).to be true
252
- end
253
-
254
- it 'converts false include_bbox to false' do
255
- config = described_class.new(include_bbox: false)
256
-
257
- expect(config.include_bbox).to be false
258
- end
259
- end
260
-
261
- describe 'k_clusters parameter' do
262
- it 'accepts small k_clusters' do
263
- config = described_class.new(k_clusters: 3)
264
-
265
- expect(config.k_clusters).to eq 3
266
- end
267
-
268
- it 'accepts large k_clusters' do
269
- config = described_class.new(k_clusters: 20)
270
-
271
- expect(config.k_clusters).to eq 20
272
- end
273
-
274
- it 'defaults to 6 clusters' do
275
- config = described_class.new
276
-
277
- expect(config.k_clusters).to eq 6
278
- end
279
-
280
- it 'converts string k_clusters to integer' do
281
- config = described_class.new(k_clusters: '15')
282
-
283
- expect(config.k_clusters).to eq 15
284
- expect(config.k_clusters).to be_a Integer
285
- end
286
- end
287
-
288
- describe 'ocr_coverage_threshold' do
289
- it 'accepts high threshold values' do
290
- config = described_class.new(ocr_coverage_threshold: 0.95)
291
-
292
- expect(config.ocr_coverage_threshold).to eq 0.95
293
- end
294
-
295
- it 'accepts low threshold values' do
296
- config = described_class.new(ocr_coverage_threshold: 0.1)
297
-
298
- expect(config.ocr_coverage_threshold).to eq 0.1
299
- end
300
-
301
- it 'accepts nil for threshold' do
302
- config = described_class.new(ocr_coverage_threshold: nil)
303
-
304
- expect(config.ocr_coverage_threshold).to be_nil
305
- end
306
-
307
- it 'converts string threshold to float' do
308
- config = described_class.new(ocr_coverage_threshold: '0.85')
309
-
310
- expect(config.ocr_coverage_threshold).to eq 0.85
311
- expect(config.ocr_coverage_threshold).to be_a Float
312
- end
313
- end
314
- end