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
@@ -1,213 +0,0 @@
1
- # frozen_string_literal: true
2
-
3
- RSpec.describe Kreuzberg::Config::Chunking do
4
- describe '#initialize' do
5
- it 'creates config with default values' do
6
- config = described_class.new
7
-
8
- expect(config.max_chars).to eq 1000
9
- expect(config.max_overlap).to eq 200
10
- expect(config.preset).to be_nil
11
- expect(config.embedding).to be_nil
12
- expect(config.enabled).to be true
13
- end
14
-
15
- it 'creates config with custom values' do
16
- config = described_class.new(
17
- max_chars: 500,
18
- max_overlap: 100,
19
- preset: 'fast'
20
- )
21
-
22
- expect(config.max_chars).to eq 500
23
- expect(config.max_overlap).to eq 100
24
- expect(config.preset).to eq 'fast'
25
- end
26
-
27
- it 'accepts chunk_size alias for max_chars' do
28
- config = described_class.new(chunk_size: 750)
29
-
30
- expect(config.max_chars).to eq 750
31
- end
32
-
33
- it 'accepts chunk_overlap alias for max_overlap' do
34
- config = described_class.new(chunk_overlap: 150)
35
-
36
- expect(config.max_overlap).to eq 150
37
- end
38
-
39
- it 'uses max_chars when both chunk_size and max_chars provided' do
40
- config = described_class.new(chunk_size: 500, max_chars: 1000)
41
-
42
- expect(config.max_chars).to eq 500
43
- end
44
-
45
- it 'accepts embedding as instance' do
46
- embedding = Kreuzberg::Config::Embedding.new(model: { type: :preset, name: 'fast' })
47
- config = described_class.new(embedding: embedding)
48
-
49
- expect(config.embedding).to be_a Kreuzberg::Config::Embedding
50
- end
51
-
52
- it 'converts embedding hash to instance' do
53
- config = described_class.new(embedding: { model: { type: :preset, name: 'balanced' } })
54
-
55
- expect(config.embedding).to be_a Kreuzberg::Config::Embedding
56
- end
57
- end
58
-
59
- describe '#to_h' do
60
- it 'serializes to hash with default values' do
61
- config = described_class.new
62
- hash = config.to_h
63
-
64
- expect(hash).to be_a Hash
65
- expect(hash[:max_chars]).to eq 1000
66
- expect(hash[:max_overlap]).to eq 200
67
- expect(hash[:enabled]).to be true
68
- end
69
-
70
- it 'includes embedding in hash when present' do
71
- config = described_class.new(embedding: { model: { type: :preset, name: 'fast' } })
72
- hash = config.to_h
73
-
74
- expect(hash[:embedding]).to be_a Hash
75
- end
76
-
77
- it 'compacts nil values from hash' do
78
- config = described_class.new
79
- hash = config.to_h
80
-
81
- expect(hash.key?(:preset)).to be false
82
- expect(hash.key?(:embedding)).to be false
83
- end
84
- end
85
-
86
- describe 'validation' do
87
- it 'rejects negative max_chars' do
88
- expect do
89
- described_class.new(max_chars: -100)
90
- end.to raise_error ArgumentError, /max_chars must be a positive integer/
91
- end
92
-
93
- it 'rejects negative max_overlap' do
94
- expect do
95
- described_class.new(max_overlap: -50)
96
- end.to raise_error ArgumentError, /max_overlap must be a positive integer/
97
- end
98
-
99
- it 'accepts zero values' do
100
- expect do
101
- described_class.new(max_chars: 0, max_overlap: 0)
102
- end.not_to raise_error
103
- end
104
-
105
- it 'accepts positive values' do
106
- expect do
107
- described_class.new(max_chars: 2000, max_overlap: 500)
108
- end.not_to raise_error
109
- end
110
- end
111
-
112
- describe 'keyword arguments' do
113
- it 'accepts all keyword arguments' do
114
- config = described_class.new(
115
- max_chars: 750,
116
- max_overlap: 150,
117
- preset: 'balanced',
118
- enabled: true
119
- )
120
-
121
- expect(config.max_chars).to eq 750
122
- expect(config.max_overlap).to eq 150
123
- expect(config.preset).to eq 'balanced'
124
- expect(config.enabled).to be true
125
- end
126
-
127
- it 'converts preset to string' do
128
- config = described_class.new(preset: :fast)
129
-
130
- expect(config.preset).to eq 'fast'
131
- expect(config.preset).to be_a String
132
- end
133
- end
134
-
135
- describe 'equality' do
136
- it 'compares configs by value' do
137
- config1 = described_class.new(max_chars: 500, max_overlap: 100)
138
- config2 = described_class.new(max_chars: 500, max_overlap: 100)
139
-
140
- expect(config1.max_chars).to eq config2.max_chars
141
- expect(config1.max_overlap).to eq config2.max_overlap
142
- end
143
-
144
- it 'detects differences' do
145
- config1 = described_class.new(max_chars: 500)
146
- config2 = described_class.new(max_chars: 1000)
147
-
148
- expect(config1.max_chars).not_to eq config2.max_chars
149
- end
150
- end
151
-
152
- describe 'nested config integration' do
153
- it 'can be nested in Extraction config' do
154
- chunking = described_class.new(max_chars: 750, preset: 'fast')
155
- extraction = Kreuzberg::Config::Extraction.new(chunking: chunking)
156
-
157
- expect(extraction.chunking).to be_a described_class
158
- expect(extraction.chunking.max_chars).to eq 750
159
- end
160
-
161
- it 'accepts hash in Extraction config' do
162
- extraction = Kreuzberg::Config::Extraction.new(
163
- chunking: { max_chars: 500, preset: 'balanced' }
164
- )
165
-
166
- expect(extraction.chunking).to be_a described_class
167
- expect(extraction.chunking.max_chars).to eq 500
168
- end
169
- end
170
-
171
- describe 'symbol vs string key handling' do
172
- it 'converts symbol preset to string' do
173
- config = described_class.new(preset: :fast)
174
-
175
- expect(config.preset).to eq 'fast'
176
- expect(config.preset).to be_a String
177
- end
178
-
179
- it 'converts integer strings to integers' do
180
- config = described_class.new(max_chars: '1500', max_overlap: '300')
181
-
182
- expect(config.max_chars).to eq 1500
183
- expect(config.max_overlap).to eq 300
184
- expect(config.max_chars).to be_a Integer
185
- end
186
- end
187
-
188
- describe 'enabled field' do
189
- it 'defaults to true' do
190
- config = described_class.new
191
-
192
- expect(config.enabled).to be true
193
- end
194
-
195
- it 'accepts false' do
196
- config = described_class.new(enabled: false)
197
-
198
- expect(config.enabled).to be false
199
- end
200
-
201
- it 'converts truthy values to true' do
202
- config = described_class.new(enabled: 'yes')
203
-
204
- expect(config.enabled).to be true
205
- end
206
-
207
- it 'can be nil' do
208
- config = described_class.new(enabled: nil)
209
-
210
- expect(config.enabled).to be_nil
211
- end
212
- end
213
- end
@@ -1,343 +0,0 @@
1
- # frozen_string_literal: true
2
-
3
- RSpec.describe Kreuzberg::Config::Embedding do
4
- describe '#initialize' do
5
- it 'creates config with default values' do
6
- config = described_class.new
7
-
8
- expect(config.model).to be_a Hash
9
- expect(config.model[:type]).to eq :preset
10
- expect(config.model[:name]).to eq 'balanced'
11
- expect(config.normalize).to be true
12
- expect(config.batch_size).to eq 32
13
- expect(config.show_download_progress).to be false
14
- expect(config.cache_dir).to be_nil
15
- end
16
-
17
- it 'creates config with custom model hash' do
18
- model = { type: :preset, name: 'fast' }
19
- config = described_class.new(model: model)
20
-
21
- expect(config.model[:type]).to eq :preset
22
- expect(config.model[:name]).to eq 'fast'
23
- end
24
-
25
- it 'creates config with custom values' do
26
- config = described_class.new(
27
- normalize: false,
28
- batch_size: 64,
29
- show_download_progress: true,
30
- cache_dir: '/cache'
31
- )
32
-
33
- expect(config.normalize).to be false
34
- expect(config.batch_size).to eq 64
35
- expect(config.show_download_progress).to be true
36
- expect(config.cache_dir).to eq '/cache'
37
- end
38
-
39
- it 'converts model with to_h method' do
40
- model_like = double(to_h: { type: :custom, name: 'model' })
41
- config = described_class.new(model: model_like)
42
-
43
- expect(config.model).to be_a Hash
44
- expect(config.model[:type]).to eq :custom
45
- end
46
-
47
- it 'converts batch_size to integer' do
48
- config = described_class.new(batch_size: '128')
49
-
50
- expect(config.batch_size).to eq 128
51
- expect(config.batch_size).to be_a Integer
52
- end
53
-
54
- it 'converts normalize to boolean' do
55
- config = described_class.new(normalize: 1)
56
-
57
- expect(config.normalize).to be true
58
- end
59
-
60
- it 'converts show_download_progress to boolean' do
61
- config = described_class.new(show_download_progress: 'yes')
62
-
63
- expect(config.show_download_progress).to be true
64
- end
65
-
66
- it 'converts cache_dir to string' do
67
- config = described_class.new(cache_dir: :default_cache)
68
-
69
- expect(config.cache_dir).to be_a String
70
- end
71
- end
72
-
73
- describe '#to_h' do
74
- it 'serializes to hash with all values' do
75
- config = described_class.new(
76
- model: { type: :preset, name: 'fast' },
77
- batch_size: 64
78
- )
79
- hash = config.to_h
80
-
81
- expect(hash).to be_a Hash
82
- expect(hash[:model]).to be_a Hash
83
- expect(hash[:normalize]).to be true
84
- expect(hash[:batch_size]).to eq 64
85
- end
86
-
87
- it 'includes cache_dir when present' do
88
- config = described_class.new(cache_dir: '/cache')
89
- hash = config.to_h
90
-
91
- expect(hash[:cache_dir]).to eq '/cache'
92
- end
93
-
94
- it 'compacts nil values from hash' do
95
- config = described_class.new
96
- hash = config.to_h
97
-
98
- expect(hash.key?(:cache_dir)).to be false
99
- end
100
-
101
- it 'always includes model in hash' do
102
- config = described_class.new
103
- hash = config.to_h
104
-
105
- expect(hash.key?(:model)).to be true
106
- expect(hash[:model]).to be_a Hash
107
- end
108
- end
109
-
110
- describe 'validation' do
111
- it 'rejects invalid model type (not hash)' do
112
- expect do
113
- described_class.new(model: 'invalid_string')
114
- end.to raise_error ArgumentError, /model must be a Hash/
115
- end
116
-
117
- it 'accepts model as hash' do
118
- expect do
119
- described_class.new(model: { type: :preset, name: 'fast' })
120
- end.not_to raise_error
121
- end
122
-
123
- it 'accepts model with to_h method' do
124
- model_like = double(to_h: { type: :preset, name: 'fast' })
125
- expect do
126
- described_class.new(model: model_like)
127
- end.not_to raise_error
128
- end
129
-
130
- it 'accepts valid batch_size' do
131
- expect do
132
- described_class.new(batch_size: 32)
133
- end.not_to raise_error
134
- end
135
-
136
- it 'accepts valid cache_dir' do
137
- expect do
138
- described_class.new(cache_dir: '/tmp/cache')
139
- end.not_to raise_error
140
- end
141
- end
142
-
143
- describe 'keyword arguments' do
144
- it 'accepts all keyword arguments' do
145
- config = described_class.new(
146
- model: { type: :preset, name: 'balanced' },
147
- normalize: true,
148
- batch_size: 48,
149
- show_download_progress: true,
150
- cache_dir: '/cache'
151
- )
152
-
153
- expect(config.model[:name]).to eq 'balanced'
154
- expect(config.normalize).to be true
155
- expect(config.batch_size).to eq 48
156
- expect(config.show_download_progress).to be true
157
- expect(config.cache_dir).to eq '/cache'
158
- end
159
- end
160
-
161
- describe 'equality' do
162
- it 'compares configs by value' do
163
- config1 = described_class.new(
164
- model: { type: :preset, name: 'fast' },
165
- batch_size: 64
166
- )
167
- config2 = described_class.new(
168
- model: { type: :preset, name: 'fast' },
169
- batch_size: 64
170
- )
171
-
172
- expect(config1.model).to eq config2.model
173
- expect(config1.batch_size).to eq config2.batch_size
174
- end
175
-
176
- it 'detects differences in model' do
177
- config1 = described_class.new(model: { type: :preset, name: 'fast' })
178
- config2 = described_class.new(model: { type: :preset, name: 'balanced' })
179
-
180
- expect(config1.model).not_to eq config2.model
181
- end
182
-
183
- it 'detects differences in batch_size' do
184
- config1 = described_class.new(batch_size: 32)
185
- config2 = described_class.new(batch_size: 64)
186
-
187
- expect(config1.batch_size).not_to eq config2.batch_size
188
- end
189
-
190
- it 'detects differences in normalize' do
191
- config1 = described_class.new(normalize: true)
192
- config2 = described_class.new(normalize: false)
193
-
194
- expect(config1.normalize).not_to eq config2.normalize
195
- end
196
- end
197
-
198
- describe 'nested config integration' do
199
- it 'can be nested in Chunking config' do
200
- embedding = described_class.new(
201
- model: { type: :preset, name: 'fast' },
202
- batch_size: 64
203
- )
204
- chunking = Kreuzberg::Config::Chunking.new(embedding: embedding)
205
-
206
- expect(chunking.embedding).to be_a described_class
207
- expect(chunking.embedding.batch_size).to eq 64
208
- end
209
-
210
- it 'accepts hash in Chunking config' do
211
- chunking = Kreuzberg::Config::Chunking.new(
212
- embedding: { model: { type: :preset, name: 'balanced' } }
213
- )
214
-
215
- expect(chunking.embedding).to be_a described_class
216
- expect(chunking.embedding.model[:name]).to eq 'balanced'
217
- end
218
-
219
- it 'can be nested in Extraction config via Chunking' do
220
- extraction = Kreuzberg::Config::Extraction.new(
221
- chunking: { embedding: { batch_size: 48 } }
222
- )
223
-
224
- expect(extraction.chunking.embedding).to be_a described_class
225
- expect(extraction.chunking.embedding.batch_size).to eq 48
226
- end
227
- end
228
-
229
- describe 'symbol vs string key handling' do
230
- it 'normalizes model keys to symbols' do
231
- config = described_class.new(model: { 'type' => :preset, 'name' => 'fast' })
232
-
233
- expect(config.model).to be_a Hash
234
- expect(config.model[:type]).to eq :preset
235
- end
236
-
237
- it 'preserves symbol values in model' do
238
- config = described_class.new(model: { type: :preset })
239
-
240
- expect(config.model[:type]).to eq :preset
241
- end
242
- end
243
-
244
- describe 'boolean conversion' do
245
- it 'converts truthy normalize to true' do
246
- config = described_class.new(normalize: 1)
247
-
248
- expect(config.normalize).to be true
249
- end
250
-
251
- it 'converts false normalize to false' do
252
- config = described_class.new(normalize: false)
253
-
254
- expect(config.normalize).to be false
255
- end
256
-
257
- it 'converts truthy show_download_progress to true' do
258
- config = described_class.new(show_download_progress: 'yes')
259
-
260
- expect(config.show_download_progress).to be true
261
- end
262
-
263
- it 'converts false show_download_progress to false' do
264
- config = described_class.new(show_download_progress: false)
265
-
266
- expect(config.show_download_progress).to be false
267
- end
268
- end
269
-
270
- describe 'model configuration' do
271
- it 'accepts preset model type' do
272
- config = described_class.new(model: { type: :preset, name: 'fast' })
273
-
274
- expect(config.model[:type]).to eq :preset
275
- end
276
-
277
- it 'accepts custom model type' do
278
- config = described_class.new(model: { type: :custom, path: '/model' })
279
-
280
- expect(config.model[:type]).to eq :custom
281
- end
282
-
283
- it 'preserves model configuration details' do
284
- model = { type: :preset, name: 'balanced', dimensions: 384 }
285
- config = described_class.new(model: model)
286
-
287
- expect(config.model[:dimensions]).to eq 384
288
- end
289
- end
290
-
291
- describe 'batch size handling' do
292
- it 'defaults to 32' do
293
- config = described_class.new
294
-
295
- expect(config.batch_size).to eq 32
296
- end
297
-
298
- it 'accepts small batch sizes' do
299
- config = described_class.new(batch_size: 1)
300
-
301
- expect(config.batch_size).to eq 1
302
- end
303
-
304
- it 'accepts large batch sizes' do
305
- config = described_class.new(batch_size: 512)
306
-
307
- expect(config.batch_size).to eq 512
308
- end
309
-
310
- it 'converts string batch_size to integer' do
311
- config = described_class.new(batch_size: '256')
312
-
313
- expect(config.batch_size).to eq 256
314
- expect(config.batch_size).to be_a Integer
315
- end
316
- end
317
-
318
- describe 'cache directory' do
319
- it 'defaults to nil' do
320
- config = described_class.new
321
-
322
- expect(config.cache_dir).to be_nil
323
- end
324
-
325
- it 'accepts absolute paths' do
326
- config = described_class.new(cache_dir: '/var/cache/embeddings')
327
-
328
- expect(config.cache_dir).to eq '/var/cache/embeddings'
329
- end
330
-
331
- it 'accepts relative paths' do
332
- config = described_class.new(cache_dir: './cache')
333
-
334
- expect(config.cache_dir).to eq './cache'
335
- end
336
-
337
- it 'converts path to string' do
338
- config = described_class.new(cache_dir: :default_cache)
339
-
340
- expect(config.cache_dir).to be_a String
341
- end
342
- end
343
- end