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
@@ -1,484 +0,0 @@
1
- //! Security utilities for document extractors.
2
- //!
3
- //! This module provides validation and protection mechanisms against common attacks:
4
- //! - ZIP bomb detection (decompression bombs)
5
- //! - XML entity expansion limits
6
- //! - Nesting depth limits
7
- //! - Input size limits
8
- //! - Entity length validation
9
-
10
- #[cfg(feature = "archives")]
11
- use std::io::{Read, Seek};
12
-
13
- /// Configuration for security limits across extractors.
14
- ///
15
- /// All limits are intentionally conservative to prevent DoS attacks
16
- /// while still supporting legitimate documents.
17
- #[derive(Clone, Debug)]
18
- pub struct SecurityLimits {
19
- /// Maximum uncompressed size for archives (500 MB)
20
- pub max_archive_size: usize,
21
-
22
- /// Maximum compression ratio before flagging as potential bomb (100:1)
23
- pub max_compression_ratio: usize,
24
-
25
- /// Maximum number of files in archive (10,000)
26
- pub max_files_in_archive: usize,
27
-
28
- /// Maximum nesting depth for structures (100)
29
- pub max_nesting_depth: usize,
30
-
31
- /// Maximum entity/string length (32)
32
- pub max_entity_length: usize,
33
-
34
- /// Maximum string growth per document (100 MB)
35
- pub max_content_size: usize,
36
-
37
- /// Maximum iterations per operation
38
- pub max_iterations: usize,
39
-
40
- /// Maximum XML depth (100 levels)
41
- pub max_xml_depth: usize,
42
-
43
- /// Maximum cells per table (100,000)
44
- pub max_table_cells: usize,
45
- }
46
-
47
- impl Default for SecurityLimits {
48
- fn default() -> Self {
49
- Self {
50
- max_archive_size: 500 * 1024 * 1024,
51
- max_compression_ratio: 100,
52
- max_files_in_archive: 10_000,
53
- max_nesting_depth: 100,
54
- max_entity_length: 32,
55
- max_content_size: 100 * 1024 * 1024,
56
- max_iterations: 10_000_000,
57
- max_xml_depth: 100,
58
- max_table_cells: 100_000,
59
- }
60
- }
61
- }
62
-
63
- /// Security validation errors.
64
- #[derive(Debug, Clone)]
65
- pub enum SecurityError {
66
- /// Potential ZIP bomb detected
67
- ZipBombDetected {
68
- compressed_size: u64,
69
- uncompressed_size: u64,
70
- ratio: f64,
71
- },
72
-
73
- /// Archive exceeds maximum size
74
- ArchiveTooLarge { size: u64, max: usize },
75
-
76
- /// Archive contains too many files
77
- TooManyFiles { count: usize, max: usize },
78
-
79
- /// Nesting too deep
80
- NestingTooDeep { depth: usize, max: usize },
81
-
82
- /// Content exceeds maximum size
83
- ContentTooLarge { size: usize, max: usize },
84
-
85
- /// Entity/string too long
86
- EntityTooLong { length: usize, max: usize },
87
-
88
- /// Too many iterations
89
- TooManyIterations { count: usize, max: usize },
90
-
91
- /// XML depth exceeded
92
- XmlDepthExceeded { depth: usize, max: usize },
93
-
94
- /// Too many table cells
95
- TooManyCells { cells: usize, max: usize },
96
- }
97
-
98
- impl std::fmt::Display for SecurityError {
99
- fn fmt(&self, f: &mut std::fmt::Formatter) -> std::fmt::Result {
100
- match self {
101
- SecurityError::ZipBombDetected {
102
- compressed_size,
103
- uncompressed_size,
104
- ratio,
105
- } => {
106
- write!(
107
- f,
108
- "Potential ZIP bomb detected: compressed {}B -> uncompressed {}B (ratio: {:.1}:1)",
109
- compressed_size, uncompressed_size, ratio
110
- )
111
- }
112
- SecurityError::ArchiveTooLarge { size, max } => {
113
- write!(f, "Archive too large: {} bytes (max: {} bytes)", size, max)
114
- }
115
- SecurityError::TooManyFiles { count, max } => {
116
- write!(f, "Archive has too many files: {} (max: {})", count, max)
117
- }
118
- SecurityError::NestingTooDeep { depth, max } => {
119
- write!(f, "Nesting too deep: {} levels (max: {})", depth, max)
120
- }
121
- SecurityError::ContentTooLarge { size, max } => {
122
- write!(f, "Content too large: {} bytes (max: {} bytes)", size, max)
123
- }
124
- SecurityError::EntityTooLong { length, max } => {
125
- write!(f, "Entity too long: {} chars (max: {})", length, max)
126
- }
127
- SecurityError::TooManyIterations { count, max } => {
128
- write!(f, "Too many iterations: {} (max: {})", count, max)
129
- }
130
- SecurityError::XmlDepthExceeded { depth, max } => {
131
- write!(f, "XML depth exceeded: {} (max: {})", depth, max)
132
- }
133
- SecurityError::TooManyCells { cells, max } => {
134
- write!(f, "Too many table cells: {} (max: {})", cells, max)
135
- }
136
- }
137
- }
138
- }
139
-
140
- impl std::error::Error for SecurityError {}
141
-
142
- /// Helper struct for validating ZIP archives for security issues.
143
- #[cfg(feature = "archives")]
144
- pub struct ZipBombValidator {
145
- limits: SecurityLimits,
146
- }
147
-
148
- #[cfg(feature = "archives")]
149
- impl ZipBombValidator {
150
- /// Create a new ZIP bomb validator.
151
- pub fn new(limits: SecurityLimits) -> Self {
152
- Self { limits }
153
- }
154
-
155
- /// Validate a ZIP archive for security issues.
156
- ///
157
- /// # Arguments
158
- /// * `archive` - Mutable ZIP archive to validate
159
- ///
160
- /// # Returns
161
- /// * `Ok(())` if archive is safe
162
- /// * `Err(SecurityError)` if security limit violated
163
- pub fn validate<R: Read + Seek>(&self, archive: &mut zip::ZipArchive<R>) -> Result<(), SecurityError> {
164
- let file_count = archive.len();
165
-
166
- if file_count > self.limits.max_files_in_archive {
167
- return Err(SecurityError::TooManyFiles {
168
- count: file_count,
169
- max: self.limits.max_files_in_archive,
170
- });
171
- }
172
-
173
- let mut total_uncompressed: u64 = 0;
174
- let mut total_compressed: u64 = 0;
175
-
176
- for i in 0..file_count {
177
- if let Ok(file) = archive.by_index(i) {
178
- let compressed_size = file.compressed_size();
179
- let uncompressed_size = file.size();
180
-
181
- total_uncompressed += uncompressed_size;
182
- total_compressed += compressed_size;
183
-
184
- if compressed_size > 0 && uncompressed_size > 0 {
185
- let ratio = uncompressed_size as f64 / compressed_size as f64;
186
- if ratio > self.limits.max_compression_ratio as f64 {
187
- return Err(SecurityError::ZipBombDetected {
188
- compressed_size,
189
- uncompressed_size,
190
- ratio,
191
- });
192
- }
193
- }
194
- }
195
- }
196
-
197
- if total_uncompressed > self.limits.max_archive_size as u64 {
198
- return Err(SecurityError::ArchiveTooLarge {
199
- size: total_uncompressed,
200
- max: self.limits.max_archive_size,
201
- });
202
- }
203
-
204
- if total_compressed > 0 {
205
- let ratio = total_uncompressed as f64 / total_compressed as f64;
206
- if ratio > self.limits.max_compression_ratio as f64 {
207
- return Err(SecurityError::ZipBombDetected {
208
- compressed_size: total_compressed,
209
- uncompressed_size: total_uncompressed,
210
- ratio,
211
- });
212
- }
213
- }
214
-
215
- Ok(())
216
- }
217
- }
218
-
219
- /// Helper struct for tracking and validating string growth.
220
- pub struct StringGrowthValidator {
221
- max_size: usize,
222
- current_size: usize,
223
- }
224
-
225
- impl StringGrowthValidator {
226
- /// Create a new string growth validator.
227
- pub fn new(max_size: usize) -> Self {
228
- Self {
229
- max_size,
230
- current_size: 0,
231
- }
232
- }
233
-
234
- /// Validate and update size after appending.
235
- ///
236
- /// # Returns
237
- /// * `Ok(())` if size is within limits
238
- /// * `Err(SecurityError)` if size exceeds limit
239
- pub fn check_append(&mut self, len: usize) -> Result<(), SecurityError> {
240
- self.current_size = self.current_size.saturating_add(len);
241
- if self.current_size > self.max_size {
242
- Err(SecurityError::ContentTooLarge {
243
- size: self.current_size,
244
- max: self.max_size,
245
- })
246
- } else {
247
- Ok(())
248
- }
249
- }
250
-
251
- /// Get current size.
252
- pub fn current_size(&self) -> usize {
253
- self.current_size
254
- }
255
- }
256
-
257
- /// Helper struct for validating iteration counts.
258
- pub struct IterationValidator {
259
- max_iterations: usize,
260
- current_count: usize,
261
- }
262
-
263
- impl IterationValidator {
264
- /// Create a new iteration validator.
265
- pub fn new(max_iterations: usize) -> Self {
266
- Self {
267
- max_iterations,
268
- current_count: 0,
269
- }
270
- }
271
-
272
- /// Validate and increment iteration count.
273
- ///
274
- /// # Returns
275
- /// * `Ok(())` if count is within limits
276
- /// * `Err(SecurityError)` if count exceeds limit
277
- pub fn check_iteration(&mut self) -> Result<(), SecurityError> {
278
- self.current_count += 1;
279
- if self.current_count > self.max_iterations {
280
- Err(SecurityError::TooManyIterations {
281
- count: self.current_count,
282
- max: self.max_iterations,
283
- })
284
- } else {
285
- Ok(())
286
- }
287
- }
288
-
289
- /// Get current iteration count.
290
- pub fn current_count(&self) -> usize {
291
- self.current_count
292
- }
293
- }
294
-
295
- /// Helper struct for validating nesting depth.
296
- pub struct DepthValidator {
297
- max_depth: usize,
298
- current_depth: usize,
299
- }
300
-
301
- impl DepthValidator {
302
- /// Create a new depth validator.
303
- pub fn new(max_depth: usize) -> Self {
304
- Self {
305
- max_depth,
306
- current_depth: 0,
307
- }
308
- }
309
-
310
- /// Push a level (increase depth).
311
- ///
312
- /// # Returns
313
- /// * `Ok(())` if depth is within limits
314
- /// * `Err(SecurityError)` if depth exceeds limit
315
- pub fn push(&mut self) -> Result<(), SecurityError> {
316
- self.current_depth += 1;
317
- if self.current_depth > self.max_depth {
318
- Err(SecurityError::NestingTooDeep {
319
- depth: self.current_depth,
320
- max: self.max_depth,
321
- })
322
- } else {
323
- Ok(())
324
- }
325
- }
326
-
327
- /// Pop a level (decrease depth).
328
- pub fn pop(&mut self) {
329
- if self.current_depth > 0 {
330
- self.current_depth -= 1;
331
- }
332
- }
333
-
334
- /// Get current depth.
335
- pub fn current_depth(&self) -> usize {
336
- self.current_depth
337
- }
338
- }
339
-
340
- /// Helper struct for validating entity/string length.
341
- pub struct EntityValidator {
342
- max_length: usize,
343
- }
344
-
345
- impl EntityValidator {
346
- /// Create a new entity validator.
347
- pub fn new(max_length: usize) -> Self {
348
- Self { max_length }
349
- }
350
-
351
- /// Validate entity length.
352
- ///
353
- /// # Returns
354
- /// * `Ok(())` if length is within limits
355
- /// * `Err(SecurityError)` if length exceeds limit
356
- pub fn validate(&self, content: &str) -> Result<(), SecurityError> {
357
- if content.len() > self.max_length {
358
- Err(SecurityError::EntityTooLong {
359
- length: content.len(),
360
- max: self.max_length,
361
- })
362
- } else {
363
- Ok(())
364
- }
365
- }
366
- }
367
-
368
- /// Helper struct for validating table cell counts.
369
- pub struct TableValidator {
370
- max_cells: usize,
371
- current_cells: usize,
372
- }
373
-
374
- impl TableValidator {
375
- /// Create a new table validator.
376
- pub fn new(max_cells: usize) -> Self {
377
- Self {
378
- max_cells,
379
- current_cells: 0,
380
- }
381
- }
382
-
383
- /// Add cells to table and validate.
384
- ///
385
- /// # Returns
386
- /// * `Ok(())` if cell count is within limits
387
- /// * `Err(SecurityError)` if cell count exceeds limit
388
- pub fn add_cells(&mut self, count: usize) -> Result<(), SecurityError> {
389
- self.current_cells = self.current_cells.saturating_add(count);
390
- if self.current_cells > self.max_cells {
391
- Err(SecurityError::TooManyCells {
392
- cells: self.current_cells,
393
- max: self.max_cells,
394
- })
395
- } else {
396
- Ok(())
397
- }
398
- }
399
-
400
- /// Get current cell count.
401
- pub fn current_cells(&self) -> usize {
402
- self.current_cells
403
- }
404
- }
405
-
406
- #[cfg(test)]
407
- mod tests {
408
- use super::*;
409
-
410
- #[test]
411
- fn test_depth_validator() {
412
- let mut validator = DepthValidator::new(3);
413
-
414
- assert!(validator.push().is_ok());
415
- assert_eq!(validator.current_depth(), 1);
416
-
417
- assert!(validator.push().is_ok());
418
- assert_eq!(validator.current_depth(), 2);
419
-
420
- assert!(validator.push().is_ok());
421
- assert_eq!(validator.current_depth(), 3);
422
-
423
- assert!(validator.push().is_err());
424
- assert_eq!(validator.current_depth(), 4);
425
-
426
- validator.pop();
427
- assert_eq!(validator.current_depth(), 3);
428
- }
429
-
430
- #[test]
431
- fn test_entity_validator() {
432
- let validator = EntityValidator::new(10);
433
-
434
- assert!(validator.validate("short").is_ok());
435
-
436
- assert!(validator.validate("0123456789").is_ok());
437
-
438
- assert!(validator.validate("01234567890").is_err());
439
- }
440
-
441
- #[test]
442
- fn test_string_growth_validator() {
443
- let mut validator = StringGrowthValidator::new(100);
444
-
445
- assert!(validator.check_append(50).is_ok());
446
- assert_eq!(validator.current_size(), 50);
447
-
448
- assert!(validator.check_append(50).is_ok());
449
- assert_eq!(validator.current_size(), 100);
450
-
451
- assert!(validator.check_append(1).is_err());
452
- }
453
-
454
- #[test]
455
- fn test_iteration_validator() {
456
- let mut validator = IterationValidator::new(3);
457
-
458
- assert!(validator.check_iteration().is_ok());
459
- assert!(validator.check_iteration().is_ok());
460
- assert!(validator.check_iteration().is_ok());
461
- assert!(validator.check_iteration().is_err());
462
- }
463
-
464
- #[test]
465
- fn test_table_validator() {
466
- let mut validator = TableValidator::new(10);
467
-
468
- assert!(validator.add_cells(5).is_ok());
469
- assert_eq!(validator.current_cells(), 5);
470
-
471
- assert!(validator.add_cells(5).is_ok());
472
- assert_eq!(validator.current_cells(), 10);
473
-
474
- assert!(validator.add_cells(1).is_err());
475
- }
476
-
477
- #[test]
478
- fn test_default_limits() {
479
- let limits = SecurityLimits::default();
480
- assert_eq!(limits.max_archive_size, 500 * 1024 * 1024);
481
- assert_eq!(limits.max_nesting_depth, 100);
482
- assert_eq!(limits.max_entity_length, 32);
483
- }
484
- }