kreuzberg 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 (265) hide show
  1. checksums.yaml +7 -0
  2. data/.gitignore +8 -0
  3. data/.rspec +3 -0
  4. data/.rubocop.yaml +534 -0
  5. data/Gemfile +9 -0
  6. data/Gemfile.lock +157 -0
  7. data/README.md +421 -0
  8. data/Rakefile +25 -0
  9. data/Steepfile +47 -0
  10. data/examples/async_patterns.rb +340 -0
  11. data/ext/kreuzberg_rb/extconf.rb +35 -0
  12. data/ext/kreuzberg_rb/native/Cargo.toml +36 -0
  13. data/ext/kreuzberg_rb/native/README.md +425 -0
  14. data/ext/kreuzberg_rb/native/build.rs +17 -0
  15. data/ext/kreuzberg_rb/native/include/ieeefp.h +11 -0
  16. data/ext/kreuzberg_rb/native/include/msvc_compat/strings.h +14 -0
  17. data/ext/kreuzberg_rb/native/include/strings.h +20 -0
  18. data/ext/kreuzberg_rb/native/include/unistd.h +47 -0
  19. data/ext/kreuzberg_rb/native/src/lib.rs +2939 -0
  20. data/extconf.rb +28 -0
  21. data/kreuzberg.gemspec +105 -0
  22. data/lib/kreuzberg/api_proxy.rb +142 -0
  23. data/lib/kreuzberg/cache_api.rb +45 -0
  24. data/lib/kreuzberg/cli.rb +55 -0
  25. data/lib/kreuzberg/cli_proxy.rb +127 -0
  26. data/lib/kreuzberg/config.rb +684 -0
  27. data/lib/kreuzberg/errors.rb +50 -0
  28. data/lib/kreuzberg/extraction_api.rb +84 -0
  29. data/lib/kreuzberg/mcp_proxy.rb +186 -0
  30. data/lib/kreuzberg/ocr_backend_protocol.rb +113 -0
  31. data/lib/kreuzberg/post_processor_protocol.rb +86 -0
  32. data/lib/kreuzberg/result.rb +216 -0
  33. data/lib/kreuzberg/setup_lib_path.rb +79 -0
  34. data/lib/kreuzberg/validator_protocol.rb +89 -0
  35. data/lib/kreuzberg/version.rb +5 -0
  36. data/lib/kreuzberg.rb +82 -0
  37. data/pkg/kreuzberg-4.0.0.rc1.gem +0 -0
  38. data/sig/kreuzberg/internal.rbs +184 -0
  39. data/sig/kreuzberg.rbs +468 -0
  40. data/spec/binding/cache_spec.rb +227 -0
  41. data/spec/binding/cli_proxy_spec.rb +87 -0
  42. data/spec/binding/cli_spec.rb +54 -0
  43. data/spec/binding/config_spec.rb +345 -0
  44. data/spec/binding/config_validation_spec.rb +283 -0
  45. data/spec/binding/error_handling_spec.rb +213 -0
  46. data/spec/binding/errors_spec.rb +66 -0
  47. data/spec/binding/plugins/ocr_backend_spec.rb +307 -0
  48. data/spec/binding/plugins/postprocessor_spec.rb +269 -0
  49. data/spec/binding/plugins/validator_spec.rb +274 -0
  50. data/spec/examples.txt +104 -0
  51. data/spec/fixtures/config.toml +39 -0
  52. data/spec/fixtures/config.yaml +42 -0
  53. data/spec/fixtures/invalid_config.toml +4 -0
  54. data/spec/smoke/package_spec.rb +178 -0
  55. data/spec/spec_helper.rb +42 -0
  56. data/vendor/kreuzberg/Cargo.toml +134 -0
  57. data/vendor/kreuzberg/README.md +175 -0
  58. data/vendor/kreuzberg/build.rs +460 -0
  59. data/vendor/kreuzberg/src/api/error.rs +81 -0
  60. data/vendor/kreuzberg/src/api/handlers.rs +199 -0
  61. data/vendor/kreuzberg/src/api/mod.rs +79 -0
  62. data/vendor/kreuzberg/src/api/server.rs +353 -0
  63. data/vendor/kreuzberg/src/api/types.rs +170 -0
  64. data/vendor/kreuzberg/src/bin/profile_extract.rs +455 -0
  65. data/vendor/kreuzberg/src/cache/mod.rs +1143 -0
  66. data/vendor/kreuzberg/src/chunking/mod.rs +677 -0
  67. data/vendor/kreuzberg/src/core/batch_mode.rs +35 -0
  68. data/vendor/kreuzberg/src/core/config.rs +1032 -0
  69. data/vendor/kreuzberg/src/core/extractor.rs +903 -0
  70. data/vendor/kreuzberg/src/core/io.rs +327 -0
  71. data/vendor/kreuzberg/src/core/mime.rs +615 -0
  72. data/vendor/kreuzberg/src/core/mod.rs +42 -0
  73. data/vendor/kreuzberg/src/core/pipeline.rs +906 -0
  74. data/vendor/kreuzberg/src/embeddings.rs +323 -0
  75. data/vendor/kreuzberg/src/error.rs +431 -0
  76. data/vendor/kreuzberg/src/extraction/archive.rs +954 -0
  77. data/vendor/kreuzberg/src/extraction/docx.rs +40 -0
  78. data/vendor/kreuzberg/src/extraction/email.rs +854 -0
  79. data/vendor/kreuzberg/src/extraction/excel.rs +688 -0
  80. data/vendor/kreuzberg/src/extraction/html.rs +553 -0
  81. data/vendor/kreuzberg/src/extraction/image.rs +368 -0
  82. data/vendor/kreuzberg/src/extraction/libreoffice.rs +564 -0
  83. data/vendor/kreuzberg/src/extraction/mod.rs +77 -0
  84. data/vendor/kreuzberg/src/extraction/office_metadata/app_properties.rs +398 -0
  85. data/vendor/kreuzberg/src/extraction/office_metadata/core_properties.rs +247 -0
  86. data/vendor/kreuzberg/src/extraction/office_metadata/custom_properties.rs +240 -0
  87. data/vendor/kreuzberg/src/extraction/office_metadata/mod.rs +128 -0
  88. data/vendor/kreuzberg/src/extraction/pandoc/batch.rs +275 -0
  89. data/vendor/kreuzberg/src/extraction/pandoc/mime_types.rs +178 -0
  90. data/vendor/kreuzberg/src/extraction/pandoc/mod.rs +491 -0
  91. data/vendor/kreuzberg/src/extraction/pandoc/server.rs +496 -0
  92. data/vendor/kreuzberg/src/extraction/pandoc/subprocess.rs +1188 -0
  93. data/vendor/kreuzberg/src/extraction/pandoc/version.rs +162 -0
  94. data/vendor/kreuzberg/src/extraction/pptx.rs +3000 -0
  95. data/vendor/kreuzberg/src/extraction/structured.rs +490 -0
  96. data/vendor/kreuzberg/src/extraction/table.rs +328 -0
  97. data/vendor/kreuzberg/src/extraction/text.rs +269 -0
  98. data/vendor/kreuzberg/src/extraction/xml.rs +333 -0
  99. data/vendor/kreuzberg/src/extractors/archive.rs +425 -0
  100. data/vendor/kreuzberg/src/extractors/docx.rs +479 -0
  101. data/vendor/kreuzberg/src/extractors/email.rs +129 -0
  102. data/vendor/kreuzberg/src/extractors/excel.rs +344 -0
  103. data/vendor/kreuzberg/src/extractors/html.rs +410 -0
  104. data/vendor/kreuzberg/src/extractors/image.rs +195 -0
  105. data/vendor/kreuzberg/src/extractors/mod.rs +268 -0
  106. data/vendor/kreuzberg/src/extractors/pandoc.rs +201 -0
  107. data/vendor/kreuzberg/src/extractors/pdf.rs +496 -0
  108. data/vendor/kreuzberg/src/extractors/pptx.rs +234 -0
  109. data/vendor/kreuzberg/src/extractors/structured.rs +126 -0
  110. data/vendor/kreuzberg/src/extractors/text.rs +242 -0
  111. data/vendor/kreuzberg/src/extractors/xml.rs +128 -0
  112. data/vendor/kreuzberg/src/image/dpi.rs +164 -0
  113. data/vendor/kreuzberg/src/image/mod.rs +6 -0
  114. data/vendor/kreuzberg/src/image/preprocessing.rs +417 -0
  115. data/vendor/kreuzberg/src/image/resize.rs +89 -0
  116. data/vendor/kreuzberg/src/keywords/config.rs +154 -0
  117. data/vendor/kreuzberg/src/keywords/mod.rs +237 -0
  118. data/vendor/kreuzberg/src/keywords/processor.rs +267 -0
  119. data/vendor/kreuzberg/src/keywords/rake.rs +294 -0
  120. data/vendor/kreuzberg/src/keywords/types.rs +68 -0
  121. data/vendor/kreuzberg/src/keywords/yake.rs +163 -0
  122. data/vendor/kreuzberg/src/language_detection/mod.rs +942 -0
  123. data/vendor/kreuzberg/src/lib.rs +102 -0
  124. data/vendor/kreuzberg/src/mcp/mod.rs +32 -0
  125. data/vendor/kreuzberg/src/mcp/server.rs +1966 -0
  126. data/vendor/kreuzberg/src/ocr/cache.rs +469 -0
  127. data/vendor/kreuzberg/src/ocr/error.rs +37 -0
  128. data/vendor/kreuzberg/src/ocr/hocr.rs +216 -0
  129. data/vendor/kreuzberg/src/ocr/mod.rs +58 -0
  130. data/vendor/kreuzberg/src/ocr/processor.rs +847 -0
  131. data/vendor/kreuzberg/src/ocr/table/mod.rs +4 -0
  132. data/vendor/kreuzberg/src/ocr/table/tsv_parser.rs +144 -0
  133. data/vendor/kreuzberg/src/ocr/tesseract_backend.rs +450 -0
  134. data/vendor/kreuzberg/src/ocr/types.rs +393 -0
  135. data/vendor/kreuzberg/src/ocr/utils.rs +47 -0
  136. data/vendor/kreuzberg/src/ocr/validation.rs +206 -0
  137. data/vendor/kreuzberg/src/pdf/error.rs +122 -0
  138. data/vendor/kreuzberg/src/pdf/images.rs +139 -0
  139. data/vendor/kreuzberg/src/pdf/metadata.rs +346 -0
  140. data/vendor/kreuzberg/src/pdf/mod.rs +50 -0
  141. data/vendor/kreuzberg/src/pdf/rendering.rs +369 -0
  142. data/vendor/kreuzberg/src/pdf/table.rs +420 -0
  143. data/vendor/kreuzberg/src/pdf/text.rs +161 -0
  144. data/vendor/kreuzberg/src/plugins/extractor.rs +1010 -0
  145. data/vendor/kreuzberg/src/plugins/mod.rs +209 -0
  146. data/vendor/kreuzberg/src/plugins/ocr.rs +629 -0
  147. data/vendor/kreuzberg/src/plugins/processor.rs +641 -0
  148. data/vendor/kreuzberg/src/plugins/registry.rs +1324 -0
  149. data/vendor/kreuzberg/src/plugins/traits.rs +258 -0
  150. data/vendor/kreuzberg/src/plugins/validator.rs +955 -0
  151. data/vendor/kreuzberg/src/stopwords/mod.rs +1470 -0
  152. data/vendor/kreuzberg/src/text/mod.rs +19 -0
  153. data/vendor/kreuzberg/src/text/quality.rs +697 -0
  154. data/vendor/kreuzberg/src/text/string_utils.rs +217 -0
  155. data/vendor/kreuzberg/src/text/token_reduction/cjk_utils.rs +164 -0
  156. data/vendor/kreuzberg/src/text/token_reduction/config.rs +100 -0
  157. data/vendor/kreuzberg/src/text/token_reduction/core.rs +796 -0
  158. data/vendor/kreuzberg/src/text/token_reduction/filters.rs +902 -0
  159. data/vendor/kreuzberg/src/text/token_reduction/mod.rs +160 -0
  160. data/vendor/kreuzberg/src/text/token_reduction/semantic.rs +619 -0
  161. data/vendor/kreuzberg/src/text/token_reduction/simd_text.rs +147 -0
  162. data/vendor/kreuzberg/src/types.rs +873 -0
  163. data/vendor/kreuzberg/src/utils/mod.rs +17 -0
  164. data/vendor/kreuzberg/src/utils/quality.rs +959 -0
  165. data/vendor/kreuzberg/src/utils/string_utils.rs +381 -0
  166. data/vendor/kreuzberg/stopwords/af_stopwords.json +53 -0
  167. data/vendor/kreuzberg/stopwords/ar_stopwords.json +482 -0
  168. data/vendor/kreuzberg/stopwords/bg_stopwords.json +261 -0
  169. data/vendor/kreuzberg/stopwords/bn_stopwords.json +400 -0
  170. data/vendor/kreuzberg/stopwords/br_stopwords.json +1205 -0
  171. data/vendor/kreuzberg/stopwords/ca_stopwords.json +280 -0
  172. data/vendor/kreuzberg/stopwords/cs_stopwords.json +425 -0
  173. data/vendor/kreuzberg/stopwords/da_stopwords.json +172 -0
  174. data/vendor/kreuzberg/stopwords/de_stopwords.json +622 -0
  175. data/vendor/kreuzberg/stopwords/el_stopwords.json +849 -0
  176. data/vendor/kreuzberg/stopwords/en_stopwords.json +1300 -0
  177. data/vendor/kreuzberg/stopwords/eo_stopwords.json +175 -0
  178. data/vendor/kreuzberg/stopwords/es_stopwords.json +734 -0
  179. data/vendor/kreuzberg/stopwords/et_stopwords.json +37 -0
  180. data/vendor/kreuzberg/stopwords/eu_stopwords.json +100 -0
  181. data/vendor/kreuzberg/stopwords/fa_stopwords.json +801 -0
  182. data/vendor/kreuzberg/stopwords/fi_stopwords.json +849 -0
  183. data/vendor/kreuzberg/stopwords/fr_stopwords.json +693 -0
  184. data/vendor/kreuzberg/stopwords/ga_stopwords.json +111 -0
  185. data/vendor/kreuzberg/stopwords/gl_stopwords.json +162 -0
  186. data/vendor/kreuzberg/stopwords/gu_stopwords.json +226 -0
  187. data/vendor/kreuzberg/stopwords/ha_stopwords.json +41 -0
  188. data/vendor/kreuzberg/stopwords/he_stopwords.json +196 -0
  189. data/vendor/kreuzberg/stopwords/hi_stopwords.json +227 -0
  190. data/vendor/kreuzberg/stopwords/hr_stopwords.json +181 -0
  191. data/vendor/kreuzberg/stopwords/hu_stopwords.json +791 -0
  192. data/vendor/kreuzberg/stopwords/hy_stopwords.json +47 -0
  193. data/vendor/kreuzberg/stopwords/id_stopwords.json +760 -0
  194. data/vendor/kreuzberg/stopwords/it_stopwords.json +634 -0
  195. data/vendor/kreuzberg/stopwords/ja_stopwords.json +136 -0
  196. data/vendor/kreuzberg/stopwords/kn_stopwords.json +84 -0
  197. data/vendor/kreuzberg/stopwords/ko_stopwords.json +681 -0
  198. data/vendor/kreuzberg/stopwords/ku_stopwords.json +64 -0
  199. data/vendor/kreuzberg/stopwords/la_stopwords.json +51 -0
  200. data/vendor/kreuzberg/stopwords/lt_stopwords.json +476 -0
  201. data/vendor/kreuzberg/stopwords/lv_stopwords.json +163 -0
  202. data/vendor/kreuzberg/stopwords/ml_stopwords.json +1 -0
  203. data/vendor/kreuzberg/stopwords/mr_stopwords.json +101 -0
  204. data/vendor/kreuzberg/stopwords/ms_stopwords.json +477 -0
  205. data/vendor/kreuzberg/stopwords/ne_stopwords.json +490 -0
  206. data/vendor/kreuzberg/stopwords/nl_stopwords.json +415 -0
  207. data/vendor/kreuzberg/stopwords/no_stopwords.json +223 -0
  208. data/vendor/kreuzberg/stopwords/pl_stopwords.json +331 -0
  209. data/vendor/kreuzberg/stopwords/pt_stopwords.json +562 -0
  210. data/vendor/kreuzberg/stopwords/ro_stopwords.json +436 -0
  211. data/vendor/kreuzberg/stopwords/ru_stopwords.json +561 -0
  212. data/vendor/kreuzberg/stopwords/si_stopwords.json +193 -0
  213. data/vendor/kreuzberg/stopwords/sk_stopwords.json +420 -0
  214. data/vendor/kreuzberg/stopwords/sl_stopwords.json +448 -0
  215. data/vendor/kreuzberg/stopwords/so_stopwords.json +32 -0
  216. data/vendor/kreuzberg/stopwords/st_stopwords.json +33 -0
  217. data/vendor/kreuzberg/stopwords/sv_stopwords.json +420 -0
  218. data/vendor/kreuzberg/stopwords/sw_stopwords.json +76 -0
  219. data/vendor/kreuzberg/stopwords/ta_stopwords.json +129 -0
  220. data/vendor/kreuzberg/stopwords/te_stopwords.json +54 -0
  221. data/vendor/kreuzberg/stopwords/th_stopwords.json +118 -0
  222. data/vendor/kreuzberg/stopwords/tl_stopwords.json +149 -0
  223. data/vendor/kreuzberg/stopwords/tr_stopwords.json +506 -0
  224. data/vendor/kreuzberg/stopwords/uk_stopwords.json +75 -0
  225. data/vendor/kreuzberg/stopwords/ur_stopwords.json +519 -0
  226. data/vendor/kreuzberg/stopwords/vi_stopwords.json +647 -0
  227. data/vendor/kreuzberg/stopwords/yo_stopwords.json +62 -0
  228. data/vendor/kreuzberg/stopwords/zh_stopwords.json +796 -0
  229. data/vendor/kreuzberg/stopwords/zu_stopwords.json +31 -0
  230. data/vendor/kreuzberg/tests/api_tests.rs +966 -0
  231. data/vendor/kreuzberg/tests/archive_integration.rs +543 -0
  232. data/vendor/kreuzberg/tests/batch_orchestration.rs +542 -0
  233. data/vendor/kreuzberg/tests/batch_processing.rs +304 -0
  234. data/vendor/kreuzberg/tests/chunking_offset_demo.rs +92 -0
  235. data/vendor/kreuzberg/tests/concurrency_stress.rs +509 -0
  236. data/vendor/kreuzberg/tests/config_features.rs +580 -0
  237. data/vendor/kreuzberg/tests/config_loading_tests.rs +439 -0
  238. data/vendor/kreuzberg/tests/core_integration.rs +493 -0
  239. data/vendor/kreuzberg/tests/csv_integration.rs +424 -0
  240. data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +124 -0
  241. data/vendor/kreuzberg/tests/email_integration.rs +325 -0
  242. data/vendor/kreuzberg/tests/error_handling.rs +393 -0
  243. data/vendor/kreuzberg/tests/format_integration.rs +159 -0
  244. data/vendor/kreuzberg/tests/helpers/mod.rs +142 -0
  245. data/vendor/kreuzberg/tests/image_integration.rs +253 -0
  246. data/vendor/kreuzberg/tests/keywords_integration.rs +479 -0
  247. data/vendor/kreuzberg/tests/keywords_quality.rs +509 -0
  248. data/vendor/kreuzberg/tests/mime_detection.rs +428 -0
  249. data/vendor/kreuzberg/tests/ocr_configuration.rs +510 -0
  250. data/vendor/kreuzberg/tests/ocr_errors.rs +676 -0
  251. data/vendor/kreuzberg/tests/ocr_quality.rs +627 -0
  252. data/vendor/kreuzberg/tests/ocr_stress.rs +469 -0
  253. data/vendor/kreuzberg/tests/pandoc_integration.rs +503 -0
  254. data/vendor/kreuzberg/tests/pdf_integration.rs +43 -0
  255. data/vendor/kreuzberg/tests/pipeline_integration.rs +1412 -0
  256. data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +771 -0
  257. data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +561 -0
  258. data/vendor/kreuzberg/tests/plugin_system.rs +921 -0
  259. data/vendor/kreuzberg/tests/plugin_validator_test.rs +783 -0
  260. data/vendor/kreuzberg/tests/registry_integration_tests.rs +607 -0
  261. data/vendor/kreuzberg/tests/security_validation.rs +404 -0
  262. data/vendor/kreuzberg/tests/stopwords_integration_test.rs +888 -0
  263. data/vendor/kreuzberg/tests/test_fastembed.rs +609 -0
  264. data/vendor/kreuzberg/tests/xlsx_metadata_extraction_test.rs +87 -0
  265. metadata +471 -0
@@ -0,0 +1,47 @@
1
+ [
2
+ "այդ",
3
+ "այլ",
4
+ "այն",
5
+ "այս",
6
+ "դու",
7
+ "դուք",
8
+ "եմ",
9
+ "են",
10
+ "ենք",
11
+ "ես",
12
+ "եք",
13
+ "է",
14
+ "էի",
15
+ "էին",
16
+ "էինք",
17
+ "էիր",
18
+ "էիք",
19
+ "էր",
20
+ "ըստ",
21
+ "թ",
22
+ "ի",
23
+ "ին",
24
+ "իսկ",
25
+ "իր",
26
+ "կամ",
27
+ "համար",
28
+ "հետ",
29
+ "հետո",
30
+ "մենք",
31
+ "մեջ",
32
+ "մի",
33
+ "ն",
34
+ "նա",
35
+ "նաև",
36
+ "նրա",
37
+ "նրանք",
38
+ "որ",
39
+ "որը",
40
+ "որոնք",
41
+ "որպես",
42
+ "ու",
43
+ "ում",
44
+ "պիտի",
45
+ "վրա",
46
+ "և"
47
+ ]