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
@@ -1,360 +0,0 @@
1
- //! Integration tests for the /embed API endpoint.
2
-
3
- #![cfg(all(feature = "api", feature = "embeddings"))]
4
-
5
- use axum::{
6
- body::Body,
7
- http::{Request, StatusCode},
8
- };
9
- use serde_json::json;
10
- use tower::ServiceExt;
11
-
12
- use kreuzberg::{
13
- ExtractionConfig,
14
- api::{EmbedResponse, create_router},
15
- };
16
-
17
- /// Test embed endpoint with valid texts.
18
- #[tokio::test]
19
- async fn test_embed_valid_texts() {
20
- let app = create_router(ExtractionConfig::default());
21
-
22
- let request_body = json!({
23
- "texts": ["Hello world", "Second text"]
24
- });
25
-
26
- let response = app
27
- .oneshot(
28
- Request::builder()
29
- .method("POST")
30
- .uri("/embed")
31
- .header("content-type", "application/json")
32
- .body(Body::from(serde_json::to_string(&request_body).unwrap()))
33
- .unwrap(),
34
- )
35
- .await
36
- .unwrap();
37
-
38
- assert_eq!(response.status(), StatusCode::OK);
39
-
40
- let body = axum::body::to_bytes(response.into_body(), usize::MAX).await.unwrap();
41
- let embed_response: EmbedResponse = serde_json::from_slice(&body).unwrap();
42
-
43
- assert_eq!(embed_response.count, 2);
44
- assert_eq!(embed_response.embeddings.len(), 2);
45
- assert!(embed_response.dimensions > 0);
46
- assert!(!embed_response.model.is_empty());
47
-
48
- // Verify embeddings have correct dimensions
49
- for embedding in &embed_response.embeddings {
50
- assert_eq!(embedding.len(), embed_response.dimensions);
51
- }
52
- }
53
-
54
- /// Test embed endpoint with empty texts array returns 400.
55
- #[tokio::test]
56
- async fn test_embed_empty_texts() {
57
- let app = create_router(ExtractionConfig::default());
58
-
59
- let request_body = json!({
60
- "texts": []
61
- });
62
-
63
- let response = app
64
- .oneshot(
65
- Request::builder()
66
- .method("POST")
67
- .uri("/embed")
68
- .header("content-type", "application/json")
69
- .body(Body::from(serde_json::to_string(&request_body).unwrap()))
70
- .unwrap(),
71
- )
72
- .await
73
- .unwrap();
74
-
75
- assert_eq!(response.status(), StatusCode::BAD_REQUEST);
76
- }
77
-
78
- /// Test embed endpoint with custom embedding configuration.
79
- #[tokio::test]
80
- async fn test_embed_with_custom_config() {
81
- let app = create_router(ExtractionConfig::default());
82
-
83
- let request_body = json!({
84
- "texts": ["Test embedding with custom config"],
85
- "config": {
86
- "model": {
87
- "preset": {
88
- "name": "fast"
89
- }
90
- },
91
- "batch_size": 32
92
- }
93
- });
94
-
95
- let response = app
96
- .oneshot(
97
- Request::builder()
98
- .method("POST")
99
- .uri("/embed")
100
- .header("content-type", "application/json")
101
- .body(Body::from(serde_json::to_string(&request_body).unwrap()))
102
- .unwrap(),
103
- )
104
- .await
105
- .unwrap();
106
-
107
- assert_eq!(response.status(), StatusCode::OK);
108
-
109
- let body = axum::body::to_bytes(response.into_body(), usize::MAX).await.unwrap();
110
- let embed_response: EmbedResponse = serde_json::from_slice(&body).unwrap();
111
-
112
- assert_eq!(embed_response.count, 1);
113
- assert_eq!(embed_response.embeddings.len(), 1);
114
- assert_eq!(embed_response.model, "fast");
115
- }
116
-
117
- /// Test embed endpoint with single text.
118
- #[tokio::test]
119
- async fn test_embed_single_text() {
120
- let app = create_router(ExtractionConfig::default());
121
-
122
- let request_body = json!({
123
- "texts": ["Single text for embedding"]
124
- });
125
-
126
- let response = app
127
- .oneshot(
128
- Request::builder()
129
- .method("POST")
130
- .uri("/embed")
131
- .header("content-type", "application/json")
132
- .body(Body::from(serde_json::to_string(&request_body).unwrap()))
133
- .unwrap(),
134
- )
135
- .await
136
- .unwrap();
137
-
138
- assert_eq!(response.status(), StatusCode::OK);
139
-
140
- let body = axum::body::to_bytes(response.into_body(), usize::MAX).await.unwrap();
141
- let embed_response: EmbedResponse = serde_json::from_slice(&body).unwrap();
142
-
143
- assert_eq!(embed_response.count, 1);
144
- assert_eq!(embed_response.embeddings.len(), 1);
145
- }
146
-
147
- /// Test embed endpoint with multiple texts (batch).
148
- #[tokio::test]
149
- async fn test_embed_batch() {
150
- let app = create_router(ExtractionConfig::default());
151
-
152
- let texts: Vec<String> = (0..10).map(|i| format!("Test text number {}", i)).collect();
153
-
154
- let request_body = json!({
155
- "texts": texts
156
- });
157
-
158
- let response = app
159
- .oneshot(
160
- Request::builder()
161
- .method("POST")
162
- .uri("/embed")
163
- .header("content-type", "application/json")
164
- .body(Body::from(serde_json::to_string(&request_body).unwrap()))
165
- .unwrap(),
166
- )
167
- .await
168
- .unwrap();
169
-
170
- assert_eq!(response.status(), StatusCode::OK);
171
-
172
- let body = axum::body::to_bytes(response.into_body(), usize::MAX).await.unwrap();
173
- let embed_response: EmbedResponse = serde_json::from_slice(&body).unwrap();
174
-
175
- assert_eq!(embed_response.count, 10);
176
- assert_eq!(embed_response.embeddings.len(), 10);
177
-
178
- // Verify all embeddings have the same dimensions
179
- let first_dim = embed_response.embeddings[0].len();
180
- for embedding in &embed_response.embeddings {
181
- assert_eq!(embedding.len(), first_dim);
182
- }
183
- }
184
-
185
- /// Test embed endpoint with long text.
186
- #[tokio::test]
187
- async fn test_embed_long_text() {
188
- let app = create_router(ExtractionConfig::default());
189
-
190
- let long_text = "Lorem ipsum dolor sit amet, consectetur adipiscing elit. ".repeat(100);
191
-
192
- let request_body = json!({
193
- "texts": [long_text]
194
- });
195
-
196
- let response = app
197
- .oneshot(
198
- Request::builder()
199
- .method("POST")
200
- .uri("/embed")
201
- .header("content-type", "application/json")
202
- .body(Body::from(serde_json::to_string(&request_body).unwrap()))
203
- .unwrap(),
204
- )
205
- .await
206
- .unwrap();
207
-
208
- assert_eq!(response.status(), StatusCode::OK);
209
-
210
- let body = axum::body::to_bytes(response.into_body(), usize::MAX).await.unwrap();
211
- let embed_response: EmbedResponse = serde_json::from_slice(&body).unwrap();
212
-
213
- assert_eq!(embed_response.count, 1);
214
- assert_eq!(embed_response.embeddings.len(), 1);
215
- }
216
-
217
- /// Test embed endpoint with malformed JSON returns 400.
218
- #[tokio::test]
219
- async fn test_embed_malformed_json() {
220
- let app = create_router(ExtractionConfig::default());
221
-
222
- let response = app
223
- .oneshot(
224
- Request::builder()
225
- .method("POST")
226
- .uri("/embed")
227
- .header("content-type", "application/json")
228
- .body(Body::from("{invalid json}"))
229
- .unwrap(),
230
- )
231
- .await
232
- .unwrap();
233
-
234
- assert_eq!(response.status(), StatusCode::BAD_REQUEST);
235
- }
236
-
237
- /// Test embed endpoint preserves embedding vector values across calls.
238
- #[tokio::test]
239
- async fn test_embed_deterministic() {
240
- let app = create_router(ExtractionConfig::default());
241
-
242
- let request_body = json!({
243
- "texts": ["Deterministic test"]
244
- });
245
-
246
- // First call
247
- let response1 = app
248
- .clone()
249
- .oneshot(
250
- Request::builder()
251
- .method("POST")
252
- .uri("/embed")
253
- .header("content-type", "application/json")
254
- .body(Body::from(serde_json::to_string(&request_body).unwrap()))
255
- .unwrap(),
256
- )
257
- .await
258
- .unwrap();
259
-
260
- assert_eq!(response1.status(), StatusCode::OK);
261
-
262
- let body1 = axum::body::to_bytes(response1.into_body(), usize::MAX).await.unwrap();
263
- let embed_response1: EmbedResponse = serde_json::from_slice(&body1).unwrap();
264
-
265
- // Second call with same text
266
- let response2 = app
267
- .oneshot(
268
- Request::builder()
269
- .method("POST")
270
- .uri("/embed")
271
- .header("content-type", "application/json")
272
- .body(Body::from(serde_json::to_string(&request_body).unwrap()))
273
- .unwrap(),
274
- )
275
- .await
276
- .unwrap();
277
-
278
- assert_eq!(response2.status(), StatusCode::OK);
279
-
280
- let body2 = axum::body::to_bytes(response2.into_body(), usize::MAX).await.unwrap();
281
- let embed_response2: EmbedResponse = serde_json::from_slice(&body2).unwrap();
282
-
283
- // Compare embeddings - they should be identical
284
- assert_eq!(embed_response1.embeddings.len(), embed_response2.embeddings.len());
285
- assert_eq!(embed_response1.embeddings[0], embed_response2.embeddings[0]);
286
- }
287
-
288
- /// Test embed endpoint with different embedding presets.
289
- #[tokio::test]
290
- async fn test_embed_different_presets() {
291
- let app = create_router(ExtractionConfig::default());
292
-
293
- // Test with "fast" preset
294
- let request_fast = json!({
295
- "texts": ["Test text"],
296
- "config": {
297
- "model": {
298
- "preset": {
299
- "name": "fast"
300
- }
301
- }
302
- }
303
- });
304
-
305
- let response_fast = app
306
- .clone()
307
- .oneshot(
308
- Request::builder()
309
- .method("POST")
310
- .uri("/embed")
311
- .header("content-type", "application/json")
312
- .body(Body::from(serde_json::to_string(&request_fast).unwrap()))
313
- .unwrap(),
314
- )
315
- .await
316
- .unwrap();
317
-
318
- assert_eq!(response_fast.status(), StatusCode::OK);
319
-
320
- let body_fast = axum::body::to_bytes(response_fast.into_body(), usize::MAX)
321
- .await
322
- .unwrap();
323
- let embed_fast: EmbedResponse = serde_json::from_slice(&body_fast).unwrap();
324
-
325
- // Test with "balanced" preset
326
- let request_balanced = json!({
327
- "texts": ["Test text"],
328
- "config": {
329
- "model": {
330
- "preset": {
331
- "name": "balanced"
332
- }
333
- }
334
- }
335
- });
336
-
337
- let response_balanced = app
338
- .oneshot(
339
- Request::builder()
340
- .method("POST")
341
- .uri("/embed")
342
- .header("content-type", "application/json")
343
- .body(Body::from(serde_json::to_string(&request_balanced).unwrap()))
344
- .unwrap(),
345
- )
346
- .await
347
- .unwrap();
348
-
349
- assert_eq!(response_balanced.status(), StatusCode::OK);
350
-
351
- let body_balanced = axum::body::to_bytes(response_balanced.into_body(), usize::MAX)
352
- .await
353
- .unwrap();
354
- let embed_balanced: EmbedResponse = serde_json::from_slice(&body_balanced).unwrap();
355
-
356
- // Different presets should have different dimensions
357
- assert_ne!(embed_fast.dimensions, embed_balanced.dimensions);
358
- assert_eq!(embed_fast.model, "fast");
359
- assert_eq!(embed_balanced.model, "balanced");
360
- }
@@ -1,52 +0,0 @@
1
- #![cfg(feature = "api")]
2
- //! Integration test for the `/extract` API handler using multipart uploads.
3
-
4
- use axum::{
5
- body::{Body, to_bytes},
6
- http::{Request, StatusCode},
7
- };
8
- use kreuzberg::{
9
- ExtractionConfig,
10
- api::{ApiSizeLimits, create_router_with_limits},
11
- };
12
- use serde_json::Value;
13
- use tower::ServiceExt;
14
-
15
- #[tokio::test]
16
- async fn test_extract_accepts_single_file_multipart() {
17
- let router = create_router_with_limits(ExtractionConfig::default(), ApiSizeLimits::from_mb(5, 5));
18
-
19
- let boundary = "X-BOUNDARY";
20
- let body = format!(
21
- "--{boundary}\r\n\
22
- Content-Disposition: form-data; name=\"files\"; filename=\"test.txt\"\r\n\
23
- Content-Type: text/plain\r\n\
24
- \r\n\
25
- Hello world\r\n\
26
- --{boundary}--\r\n"
27
- );
28
- let body_bytes = body.into_bytes();
29
-
30
- let request = Request::builder()
31
- .method("POST")
32
- .uri("/extract")
33
- .header("content-type", format!("multipart/form-data; boundary={boundary}"))
34
- .header("content-length", body_bytes.len())
35
- .body(Body::from(body_bytes))
36
- .expect("Failed to build request");
37
-
38
- let response = router.oneshot(request).await.expect("Request failed");
39
- assert_eq!(response.status(), StatusCode::OK);
40
-
41
- let bytes = to_bytes(response.into_body(), 1_000_000)
42
- .await
43
- .expect("Failed to read body");
44
- let value: Value = serde_json::from_slice(&bytes).expect("Response JSON parse failed");
45
- let content = value
46
- .get(0)
47
- .and_then(|v| v.get("content"))
48
- .and_then(Value::as_str)
49
- .expect("Response should include extracted content");
50
-
51
- assert_eq!(content.trim_end_matches('\n'), "Hello world");
52
- }