kreuzberg 4.0.0.pre.rc.11 → 4.0.0.pre.rc.13

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 (369) hide show
  1. checksums.yaml +4 -4
  2. data/.gitignore +14 -14
  3. data/.rspec +3 -3
  4. data/.rubocop.yaml +1 -1
  5. data/.rubocop.yml +538 -538
  6. data/Gemfile +8 -8
  7. data/Gemfile.lock +2 -105
  8. data/README.md +454 -454
  9. data/Rakefile +25 -25
  10. data/Steepfile +47 -47
  11. data/examples/async_patterns.rb +341 -341
  12. data/ext/kreuzberg_rb/extconf.rb +45 -45
  13. data/ext/kreuzberg_rb/native/.cargo/config.toml +2 -2
  14. data/ext/kreuzberg_rb/native/Cargo.lock +6941 -6941
  15. data/ext/kreuzberg_rb/native/Cargo.toml +54 -54
  16. data/ext/kreuzberg_rb/native/README.md +425 -425
  17. data/ext/kreuzberg_rb/native/build.rs +15 -15
  18. data/ext/kreuzberg_rb/native/include/ieeefp.h +11 -11
  19. data/ext/kreuzberg_rb/native/include/msvc_compat/strings.h +14 -14
  20. data/ext/kreuzberg_rb/native/include/strings.h +20 -20
  21. data/ext/kreuzberg_rb/native/include/unistd.h +47 -47
  22. data/ext/kreuzberg_rb/native/src/lib.rs +3158 -3158
  23. data/extconf.rb +28 -28
  24. data/kreuzberg.gemspec +214 -214
  25. data/lib/kreuzberg/api_proxy.rb +142 -142
  26. data/lib/kreuzberg/cache_api.rb +81 -81
  27. data/lib/kreuzberg/cli.rb +55 -55
  28. data/lib/kreuzberg/cli_proxy.rb +127 -127
  29. data/lib/kreuzberg/config.rb +724 -724
  30. data/lib/kreuzberg/error_context.rb +80 -80
  31. data/lib/kreuzberg/errors.rb +118 -118
  32. data/lib/kreuzberg/extraction_api.rb +340 -340
  33. data/lib/kreuzberg/mcp_proxy.rb +186 -186
  34. data/lib/kreuzberg/ocr_backend_protocol.rb +113 -113
  35. data/lib/kreuzberg/post_processor_protocol.rb +86 -86
  36. data/lib/kreuzberg/result.rb +279 -279
  37. data/lib/kreuzberg/setup_lib_path.rb +80 -80
  38. data/lib/kreuzberg/validator_protocol.rb +89 -89
  39. data/lib/kreuzberg/version.rb +5 -5
  40. data/lib/kreuzberg.rb +109 -109
  41. data/lib/{libpdfium.dylib → pdfium.dll} +0 -0
  42. data/sig/kreuzberg/internal.rbs +184 -184
  43. data/sig/kreuzberg.rbs +546 -546
  44. data/spec/binding/cache_spec.rb +227 -227
  45. data/spec/binding/cli_proxy_spec.rb +85 -85
  46. data/spec/binding/cli_spec.rb +55 -55
  47. data/spec/binding/config_spec.rb +345 -345
  48. data/spec/binding/config_validation_spec.rb +283 -283
  49. data/spec/binding/error_handling_spec.rb +213 -213
  50. data/spec/binding/errors_spec.rb +66 -66
  51. data/spec/binding/plugins/ocr_backend_spec.rb +307 -307
  52. data/spec/binding/plugins/postprocessor_spec.rb +269 -269
  53. data/spec/binding/plugins/validator_spec.rb +274 -274
  54. data/spec/fixtures/config.toml +39 -39
  55. data/spec/fixtures/config.yaml +41 -41
  56. data/spec/fixtures/invalid_config.toml +4 -4
  57. data/spec/smoke/package_spec.rb +178 -178
  58. data/spec/spec_helper.rb +42 -42
  59. data/vendor/Cargo.toml +2 -1
  60. data/vendor/kreuzberg/Cargo.toml +2 -2
  61. data/vendor/kreuzberg/README.md +230 -230
  62. data/vendor/kreuzberg/benches/otel_overhead.rs +48 -48
  63. data/vendor/kreuzberg/build.rs +843 -843
  64. data/vendor/kreuzberg/src/api/error.rs +81 -81
  65. data/vendor/kreuzberg/src/api/handlers.rs +199 -199
  66. data/vendor/kreuzberg/src/api/mod.rs +79 -79
  67. data/vendor/kreuzberg/src/api/server.rs +353 -353
  68. data/vendor/kreuzberg/src/api/types.rs +170 -170
  69. data/vendor/kreuzberg/src/cache/mod.rs +1167 -1167
  70. data/vendor/kreuzberg/src/chunking/mod.rs +1877 -1877
  71. data/vendor/kreuzberg/src/chunking/processor.rs +220 -220
  72. data/vendor/kreuzberg/src/core/batch_mode.rs +95 -95
  73. data/vendor/kreuzberg/src/core/config.rs +1080 -1080
  74. data/vendor/kreuzberg/src/core/extractor.rs +1156 -1156
  75. data/vendor/kreuzberg/src/core/io.rs +329 -329
  76. data/vendor/kreuzberg/src/core/mime.rs +605 -605
  77. data/vendor/kreuzberg/src/core/mod.rs +47 -47
  78. data/vendor/kreuzberg/src/core/pipeline.rs +1184 -1184
  79. data/vendor/kreuzberg/src/embeddings.rs +500 -500
  80. data/vendor/kreuzberg/src/error.rs +431 -431
  81. data/vendor/kreuzberg/src/extraction/archive.rs +954 -954
  82. data/vendor/kreuzberg/src/extraction/docx.rs +398 -398
  83. data/vendor/kreuzberg/src/extraction/email.rs +854 -854
  84. data/vendor/kreuzberg/src/extraction/excel.rs +688 -688
  85. data/vendor/kreuzberg/src/extraction/html.rs +601 -601
  86. data/vendor/kreuzberg/src/extraction/image.rs +491 -491
  87. data/vendor/kreuzberg/src/extraction/libreoffice.rs +574 -562
  88. data/vendor/kreuzberg/src/extraction/markdown.rs +213 -213
  89. data/vendor/kreuzberg/src/extraction/mod.rs +81 -81
  90. data/vendor/kreuzberg/src/extraction/office_metadata/app_properties.rs +398 -398
  91. data/vendor/kreuzberg/src/extraction/office_metadata/core_properties.rs +247 -247
  92. data/vendor/kreuzberg/src/extraction/office_metadata/custom_properties.rs +240 -240
  93. data/vendor/kreuzberg/src/extraction/office_metadata/mod.rs +130 -130
  94. data/vendor/kreuzberg/src/extraction/office_metadata/odt_properties.rs +284 -284
  95. data/vendor/kreuzberg/src/extraction/pptx.rs +3100 -3100
  96. data/vendor/kreuzberg/src/extraction/structured.rs +490 -490
  97. data/vendor/kreuzberg/src/extraction/table.rs +328 -328
  98. data/vendor/kreuzberg/src/extraction/text.rs +269 -269
  99. data/vendor/kreuzberg/src/extraction/xml.rs +333 -333
  100. data/vendor/kreuzberg/src/extractors/archive.rs +447 -447
  101. data/vendor/kreuzberg/src/extractors/bibtex.rs +470 -470
  102. data/vendor/kreuzberg/src/extractors/docbook.rs +504 -504
  103. data/vendor/kreuzberg/src/extractors/docx.rs +400 -400
  104. data/vendor/kreuzberg/src/extractors/email.rs +157 -157
  105. data/vendor/kreuzberg/src/extractors/epub.rs +708 -708
  106. data/vendor/kreuzberg/src/extractors/excel.rs +345 -345
  107. data/vendor/kreuzberg/src/extractors/fictionbook.rs +492 -492
  108. data/vendor/kreuzberg/src/extractors/html.rs +407 -407
  109. data/vendor/kreuzberg/src/extractors/image.rs +219 -219
  110. data/vendor/kreuzberg/src/extractors/jats.rs +1054 -1054
  111. data/vendor/kreuzberg/src/extractors/jupyter.rs +368 -368
  112. data/vendor/kreuzberg/src/extractors/latex.rs +653 -653
  113. data/vendor/kreuzberg/src/extractors/markdown.rs +701 -701
  114. data/vendor/kreuzberg/src/extractors/mod.rs +429 -429
  115. data/vendor/kreuzberg/src/extractors/odt.rs +628 -628
  116. data/vendor/kreuzberg/src/extractors/opml.rs +635 -635
  117. data/vendor/kreuzberg/src/extractors/orgmode.rs +529 -529
  118. data/vendor/kreuzberg/src/extractors/pdf.rs +749 -722
  119. data/vendor/kreuzberg/src/extractors/pptx.rs +267 -267
  120. data/vendor/kreuzberg/src/extractors/rst.rs +577 -577
  121. data/vendor/kreuzberg/src/extractors/rtf.rs +809 -809
  122. data/vendor/kreuzberg/src/extractors/security.rs +484 -484
  123. data/vendor/kreuzberg/src/extractors/security_tests.rs +367 -367
  124. data/vendor/kreuzberg/src/extractors/structured.rs +142 -142
  125. data/vendor/kreuzberg/src/extractors/text.rs +265 -265
  126. data/vendor/kreuzberg/src/extractors/typst.rs +651 -651
  127. data/vendor/kreuzberg/src/extractors/xml.rs +147 -147
  128. data/vendor/kreuzberg/src/image/dpi.rs +164 -164
  129. data/vendor/kreuzberg/src/image/mod.rs +6 -6
  130. data/vendor/kreuzberg/src/image/preprocessing.rs +417 -417
  131. data/vendor/kreuzberg/src/image/resize.rs +89 -89
  132. data/vendor/kreuzberg/src/keywords/config.rs +154 -154
  133. data/vendor/kreuzberg/src/keywords/mod.rs +237 -237
  134. data/vendor/kreuzberg/src/keywords/processor.rs +275 -275
  135. data/vendor/kreuzberg/src/keywords/rake.rs +293 -293
  136. data/vendor/kreuzberg/src/keywords/types.rs +68 -68
  137. data/vendor/kreuzberg/src/keywords/yake.rs +163 -163
  138. data/vendor/kreuzberg/src/language_detection/mod.rs +985 -985
  139. data/vendor/kreuzberg/src/language_detection/processor.rs +219 -219
  140. data/vendor/kreuzberg/src/lib.rs +113 -113
  141. data/vendor/kreuzberg/src/mcp/mod.rs +35 -35
  142. data/vendor/kreuzberg/src/mcp/server.rs +2076 -2076
  143. data/vendor/kreuzberg/src/ocr/cache.rs +469 -469
  144. data/vendor/kreuzberg/src/ocr/error.rs +37 -37
  145. data/vendor/kreuzberg/src/ocr/hocr.rs +216 -216
  146. data/vendor/kreuzberg/src/ocr/mod.rs +58 -58
  147. data/vendor/kreuzberg/src/ocr/processor.rs +863 -863
  148. data/vendor/kreuzberg/src/ocr/table/mod.rs +4 -4
  149. data/vendor/kreuzberg/src/ocr/table/tsv_parser.rs +144 -144
  150. data/vendor/kreuzberg/src/ocr/tesseract_backend.rs +452 -452
  151. data/vendor/kreuzberg/src/ocr/types.rs +393 -393
  152. data/vendor/kreuzberg/src/ocr/utils.rs +47 -47
  153. data/vendor/kreuzberg/src/ocr/validation.rs +206 -206
  154. data/vendor/kreuzberg/src/panic_context.rs +154 -154
  155. data/vendor/kreuzberg/src/pdf/bindings.rs +44 -44
  156. data/vendor/kreuzberg/src/pdf/bundled.rs +346 -346
  157. data/vendor/kreuzberg/src/pdf/error.rs +130 -130
  158. data/vendor/kreuzberg/src/pdf/images.rs +139 -139
  159. data/vendor/kreuzberg/src/pdf/metadata.rs +489 -489
  160. data/vendor/kreuzberg/src/pdf/mod.rs +68 -68
  161. data/vendor/kreuzberg/src/pdf/rendering.rs +368 -368
  162. data/vendor/kreuzberg/src/pdf/table.rs +420 -420
  163. data/vendor/kreuzberg/src/pdf/text.rs +240 -240
  164. data/vendor/kreuzberg/src/plugins/extractor.rs +1044 -1044
  165. data/vendor/kreuzberg/src/plugins/mod.rs +212 -212
  166. data/vendor/kreuzberg/src/plugins/ocr.rs +639 -639
  167. data/vendor/kreuzberg/src/plugins/processor.rs +650 -650
  168. data/vendor/kreuzberg/src/plugins/registry.rs +1339 -1339
  169. data/vendor/kreuzberg/src/plugins/traits.rs +258 -258
  170. data/vendor/kreuzberg/src/plugins/validator.rs +967 -967
  171. data/vendor/kreuzberg/src/stopwords/mod.rs +1470 -1470
  172. data/vendor/kreuzberg/src/text/mod.rs +25 -25
  173. data/vendor/kreuzberg/src/text/quality.rs +697 -697
  174. data/vendor/kreuzberg/src/text/quality_processor.rs +219 -219
  175. data/vendor/kreuzberg/src/text/string_utils.rs +217 -217
  176. data/vendor/kreuzberg/src/text/token_reduction/cjk_utils.rs +164 -164
  177. data/vendor/kreuzberg/src/text/token_reduction/config.rs +100 -100
  178. data/vendor/kreuzberg/src/text/token_reduction/core.rs +796 -796
  179. data/vendor/kreuzberg/src/text/token_reduction/filters.rs +902 -902
  180. data/vendor/kreuzberg/src/text/token_reduction/mod.rs +160 -160
  181. data/vendor/kreuzberg/src/text/token_reduction/semantic.rs +619 -619
  182. data/vendor/kreuzberg/src/text/token_reduction/simd_text.rs +147 -147
  183. data/vendor/kreuzberg/src/types.rs +1055 -1055
  184. data/vendor/kreuzberg/src/utils/mod.rs +17 -17
  185. data/vendor/kreuzberg/src/utils/quality.rs +959 -959
  186. data/vendor/kreuzberg/src/utils/string_utils.rs +381 -381
  187. data/vendor/kreuzberg/stopwords/af_stopwords.json +53 -53
  188. data/vendor/kreuzberg/stopwords/ar_stopwords.json +482 -482
  189. data/vendor/kreuzberg/stopwords/bg_stopwords.json +261 -261
  190. data/vendor/kreuzberg/stopwords/bn_stopwords.json +400 -400
  191. data/vendor/kreuzberg/stopwords/br_stopwords.json +1205 -1205
  192. data/vendor/kreuzberg/stopwords/ca_stopwords.json +280 -280
  193. data/vendor/kreuzberg/stopwords/cs_stopwords.json +425 -425
  194. data/vendor/kreuzberg/stopwords/da_stopwords.json +172 -172
  195. data/vendor/kreuzberg/stopwords/de_stopwords.json +622 -622
  196. data/vendor/kreuzberg/stopwords/el_stopwords.json +849 -849
  197. data/vendor/kreuzberg/stopwords/en_stopwords.json +1300 -1300
  198. data/vendor/kreuzberg/stopwords/eo_stopwords.json +175 -175
  199. data/vendor/kreuzberg/stopwords/es_stopwords.json +734 -734
  200. data/vendor/kreuzberg/stopwords/et_stopwords.json +37 -37
  201. data/vendor/kreuzberg/stopwords/eu_stopwords.json +100 -100
  202. data/vendor/kreuzberg/stopwords/fa_stopwords.json +801 -801
  203. data/vendor/kreuzberg/stopwords/fi_stopwords.json +849 -849
  204. data/vendor/kreuzberg/stopwords/fr_stopwords.json +693 -693
  205. data/vendor/kreuzberg/stopwords/ga_stopwords.json +111 -111
  206. data/vendor/kreuzberg/stopwords/gl_stopwords.json +162 -162
  207. data/vendor/kreuzberg/stopwords/gu_stopwords.json +226 -226
  208. data/vendor/kreuzberg/stopwords/ha_stopwords.json +41 -41
  209. data/vendor/kreuzberg/stopwords/he_stopwords.json +196 -196
  210. data/vendor/kreuzberg/stopwords/hi_stopwords.json +227 -227
  211. data/vendor/kreuzberg/stopwords/hr_stopwords.json +181 -181
  212. data/vendor/kreuzberg/stopwords/hu_stopwords.json +791 -791
  213. data/vendor/kreuzberg/stopwords/hy_stopwords.json +47 -47
  214. data/vendor/kreuzberg/stopwords/id_stopwords.json +760 -760
  215. data/vendor/kreuzberg/stopwords/it_stopwords.json +634 -634
  216. data/vendor/kreuzberg/stopwords/ja_stopwords.json +136 -136
  217. data/vendor/kreuzberg/stopwords/kn_stopwords.json +84 -84
  218. data/vendor/kreuzberg/stopwords/ko_stopwords.json +681 -681
  219. data/vendor/kreuzberg/stopwords/ku_stopwords.json +64 -64
  220. data/vendor/kreuzberg/stopwords/la_stopwords.json +51 -51
  221. data/vendor/kreuzberg/stopwords/lt_stopwords.json +476 -476
  222. data/vendor/kreuzberg/stopwords/lv_stopwords.json +163 -163
  223. data/vendor/kreuzberg/stopwords/ml_stopwords.json +1 -1
  224. data/vendor/kreuzberg/stopwords/mr_stopwords.json +101 -101
  225. data/vendor/kreuzberg/stopwords/ms_stopwords.json +477 -477
  226. data/vendor/kreuzberg/stopwords/ne_stopwords.json +490 -490
  227. data/vendor/kreuzberg/stopwords/nl_stopwords.json +415 -415
  228. data/vendor/kreuzberg/stopwords/no_stopwords.json +223 -223
  229. data/vendor/kreuzberg/stopwords/pl_stopwords.json +331 -331
  230. data/vendor/kreuzberg/stopwords/pt_stopwords.json +562 -562
  231. data/vendor/kreuzberg/stopwords/ro_stopwords.json +436 -436
  232. data/vendor/kreuzberg/stopwords/ru_stopwords.json +561 -561
  233. data/vendor/kreuzberg/stopwords/si_stopwords.json +193 -193
  234. data/vendor/kreuzberg/stopwords/sk_stopwords.json +420 -420
  235. data/vendor/kreuzberg/stopwords/sl_stopwords.json +448 -448
  236. data/vendor/kreuzberg/stopwords/so_stopwords.json +32 -32
  237. data/vendor/kreuzberg/stopwords/st_stopwords.json +33 -33
  238. data/vendor/kreuzberg/stopwords/sv_stopwords.json +420 -420
  239. data/vendor/kreuzberg/stopwords/sw_stopwords.json +76 -76
  240. data/vendor/kreuzberg/stopwords/ta_stopwords.json +129 -129
  241. data/vendor/kreuzberg/stopwords/te_stopwords.json +54 -54
  242. data/vendor/kreuzberg/stopwords/th_stopwords.json +118 -118
  243. data/vendor/kreuzberg/stopwords/tl_stopwords.json +149 -149
  244. data/vendor/kreuzberg/stopwords/tr_stopwords.json +506 -506
  245. data/vendor/kreuzberg/stopwords/uk_stopwords.json +75 -75
  246. data/vendor/kreuzberg/stopwords/ur_stopwords.json +519 -519
  247. data/vendor/kreuzberg/stopwords/vi_stopwords.json +647 -647
  248. data/vendor/kreuzberg/stopwords/yo_stopwords.json +62 -62
  249. data/vendor/kreuzberg/stopwords/zh_stopwords.json +796 -796
  250. data/vendor/kreuzberg/stopwords/zu_stopwords.json +31 -31
  251. data/vendor/kreuzberg/tests/api_extract_multipart.rs +52 -52
  252. data/vendor/kreuzberg/tests/api_tests.rs +966 -966
  253. data/vendor/kreuzberg/tests/archive_integration.rs +545 -545
  254. data/vendor/kreuzberg/tests/batch_orchestration.rs +556 -556
  255. data/vendor/kreuzberg/tests/batch_processing.rs +318 -318
  256. data/vendor/kreuzberg/tests/bibtex_parity_test.rs +421 -421
  257. data/vendor/kreuzberg/tests/concurrency_stress.rs +533 -533
  258. data/vendor/kreuzberg/tests/config_features.rs +612 -612
  259. data/vendor/kreuzberg/tests/config_loading_tests.rs +416 -416
  260. data/vendor/kreuzberg/tests/core_integration.rs +510 -510
  261. data/vendor/kreuzberg/tests/csv_integration.rs +414 -414
  262. data/vendor/kreuzberg/tests/docbook_extractor_tests.rs +500 -500
  263. data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +122 -122
  264. data/vendor/kreuzberg/tests/docx_vs_pandoc_comparison.rs +370 -370
  265. data/vendor/kreuzberg/tests/email_integration.rs +327 -327
  266. data/vendor/kreuzberg/tests/epub_native_extractor_tests.rs +275 -275
  267. data/vendor/kreuzberg/tests/error_handling.rs +402 -402
  268. data/vendor/kreuzberg/tests/fictionbook_extractor_tests.rs +228 -228
  269. data/vendor/kreuzberg/tests/format_integration.rs +164 -164
  270. data/vendor/kreuzberg/tests/helpers/mod.rs +142 -142
  271. data/vendor/kreuzberg/tests/html_table_test.rs +551 -551
  272. data/vendor/kreuzberg/tests/image_integration.rs +255 -255
  273. data/vendor/kreuzberg/tests/instrumentation_test.rs +139 -139
  274. data/vendor/kreuzberg/tests/jats_extractor_tests.rs +639 -639
  275. data/vendor/kreuzberg/tests/jupyter_extractor_tests.rs +704 -704
  276. data/vendor/kreuzberg/tests/keywords_integration.rs +479 -479
  277. data/vendor/kreuzberg/tests/keywords_quality.rs +509 -509
  278. data/vendor/kreuzberg/tests/latex_extractor_tests.rs +496 -496
  279. data/vendor/kreuzberg/tests/markdown_extractor_tests.rs +490 -490
  280. data/vendor/kreuzberg/tests/mime_detection.rs +429 -429
  281. data/vendor/kreuzberg/tests/ocr_configuration.rs +514 -514
  282. data/vendor/kreuzberg/tests/ocr_errors.rs +698 -698
  283. data/vendor/kreuzberg/tests/ocr_quality.rs +629 -629
  284. data/vendor/kreuzberg/tests/ocr_stress.rs +469 -469
  285. data/vendor/kreuzberg/tests/odt_extractor_tests.rs +674 -674
  286. data/vendor/kreuzberg/tests/opml_extractor_tests.rs +616 -616
  287. data/vendor/kreuzberg/tests/orgmode_extractor_tests.rs +822 -822
  288. data/vendor/kreuzberg/tests/pdf_integration.rs +45 -45
  289. data/vendor/kreuzberg/tests/pdfium_linking.rs +374 -374
  290. data/vendor/kreuzberg/tests/pipeline_integration.rs +1436 -1436
  291. data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +776 -776
  292. data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +560 -560
  293. data/vendor/kreuzberg/tests/plugin_system.rs +927 -927
  294. data/vendor/kreuzberg/tests/plugin_validator_test.rs +783 -783
  295. data/vendor/kreuzberg/tests/registry_integration_tests.rs +587 -587
  296. data/vendor/kreuzberg/tests/rst_extractor_tests.rs +694 -694
  297. data/vendor/kreuzberg/tests/rtf_extractor_tests.rs +775 -775
  298. data/vendor/kreuzberg/tests/security_validation.rs +416 -416
  299. data/vendor/kreuzberg/tests/stopwords_integration_test.rs +888 -888
  300. data/vendor/kreuzberg/tests/test_fastembed.rs +631 -631
  301. data/vendor/kreuzberg/tests/typst_behavioral_tests.rs +1260 -1260
  302. data/vendor/kreuzberg/tests/typst_extractor_tests.rs +648 -648
  303. data/vendor/kreuzberg/tests/xlsx_metadata_extraction_test.rs +87 -87
  304. data/vendor/kreuzberg-ffi/Cargo.toml +3 -3
  305. data/vendor/kreuzberg-ffi/README.md +851 -851
  306. data/vendor/kreuzberg-ffi/build.rs +176 -176
  307. data/vendor/kreuzberg-ffi/cbindgen.toml +27 -27
  308. data/vendor/kreuzberg-ffi/kreuzberg-ffi-install.pc +12 -12
  309. data/vendor/kreuzberg-ffi/kreuzberg-ffi.pc.in +12 -12
  310. data/vendor/kreuzberg-ffi/kreuzberg.h +1087 -1087
  311. data/vendor/kreuzberg-ffi/src/lib.rs +3616 -3616
  312. data/vendor/kreuzberg-ffi/src/panic_shield.rs +247 -247
  313. data/vendor/kreuzberg-ffi/tests.disabled/README.md +48 -48
  314. data/vendor/kreuzberg-ffi/tests.disabled/config_loading_tests.rs +299 -299
  315. data/vendor/kreuzberg-ffi/tests.disabled/config_tests.rs +346 -346
  316. data/vendor/kreuzberg-ffi/tests.disabled/extractor_tests.rs +232 -232
  317. data/vendor/kreuzberg-ffi/tests.disabled/plugin_registration_tests.rs +470 -470
  318. data/vendor/kreuzberg-tesseract/.commitlintrc.json +13 -13
  319. data/vendor/kreuzberg-tesseract/.crate-ignore +2 -2
  320. data/vendor/kreuzberg-tesseract/Cargo.lock +2933 -2933
  321. data/vendor/kreuzberg-tesseract/Cargo.toml +2 -2
  322. data/vendor/kreuzberg-tesseract/LICENSE +22 -22
  323. data/vendor/kreuzberg-tesseract/README.md +399 -399
  324. data/vendor/kreuzberg-tesseract/build.rs +1354 -1354
  325. data/vendor/kreuzberg-tesseract/patches/README.md +71 -71
  326. data/vendor/kreuzberg-tesseract/patches/tesseract.diff +199 -199
  327. data/vendor/kreuzberg-tesseract/src/api.rs +1371 -1371
  328. data/vendor/kreuzberg-tesseract/src/choice_iterator.rs +77 -77
  329. data/vendor/kreuzberg-tesseract/src/enums.rs +297 -297
  330. data/vendor/kreuzberg-tesseract/src/error.rs +81 -81
  331. data/vendor/kreuzberg-tesseract/src/lib.rs +145 -145
  332. data/vendor/kreuzberg-tesseract/src/monitor.rs +57 -57
  333. data/vendor/kreuzberg-tesseract/src/mutable_iterator.rs +197 -197
  334. data/vendor/kreuzberg-tesseract/src/page_iterator.rs +253 -253
  335. data/vendor/kreuzberg-tesseract/src/result_iterator.rs +286 -286
  336. data/vendor/kreuzberg-tesseract/src/result_renderer.rs +183 -183
  337. data/vendor/kreuzberg-tesseract/tests/integration_test.rs +211 -211
  338. data/vendor/rb-sys/.cargo_vcs_info.json +5 -5
  339. data/vendor/rb-sys/Cargo.lock +393 -393
  340. data/vendor/rb-sys/Cargo.toml +70 -70
  341. data/vendor/rb-sys/Cargo.toml.orig +57 -57
  342. data/vendor/rb-sys/LICENSE-APACHE +190 -190
  343. data/vendor/rb-sys/LICENSE-MIT +21 -21
  344. data/vendor/rb-sys/build/features.rs +111 -111
  345. data/vendor/rb-sys/build/main.rs +286 -286
  346. data/vendor/rb-sys/build/stable_api_config.rs +155 -155
  347. data/vendor/rb-sys/build/version.rs +50 -50
  348. data/vendor/rb-sys/readme.md +36 -36
  349. data/vendor/rb-sys/src/bindings.rs +21 -21
  350. data/vendor/rb-sys/src/hidden.rs +11 -11
  351. data/vendor/rb-sys/src/lib.rs +35 -35
  352. data/vendor/rb-sys/src/macros.rs +371 -371
  353. data/vendor/rb-sys/src/memory.rs +53 -53
  354. data/vendor/rb-sys/src/ruby_abi_version.rs +38 -38
  355. data/vendor/rb-sys/src/special_consts.rs +31 -31
  356. data/vendor/rb-sys/src/stable_api/compiled.c +179 -179
  357. data/vendor/rb-sys/src/stable_api/compiled.rs +257 -257
  358. data/vendor/rb-sys/src/stable_api/ruby_2_7.rs +324 -324
  359. data/vendor/rb-sys/src/stable_api/ruby_3_0.rs +332 -332
  360. data/vendor/rb-sys/src/stable_api/ruby_3_1.rs +325 -325
  361. data/vendor/rb-sys/src/stable_api/ruby_3_2.rs +323 -323
  362. data/vendor/rb-sys/src/stable_api/ruby_3_3.rs +339 -339
  363. data/vendor/rb-sys/src/stable_api/ruby_3_4.rs +339 -339
  364. data/vendor/rb-sys/src/stable_api.rs +260 -260
  365. data/vendor/rb-sys/src/symbol.rs +31 -31
  366. data/vendor/rb-sys/src/tracking_allocator.rs +330 -330
  367. data/vendor/rb-sys/src/utils.rs +89 -89
  368. data/vendor/rb-sys/src/value_type.rs +7 -7
  369. metadata +7 -80
@@ -1,693 +1,693 @@
1
- [
2
- "a",
3
- "abord",
4
- "absolument",
5
- "afin",
6
- "ah",
7
- "ai",
8
- "aie",
9
- "aient",
10
- "aies",
11
- "ailleurs",
12
- "ainsi",
13
- "ait",
14
- "allaient",
15
- "allo",
16
- "allons",
17
- "allô",
18
- "alors",
19
- "anterieur",
20
- "anterieure",
21
- "anterieures",
22
- "apres",
23
- "après",
24
- "as",
25
- "assez",
26
- "attendu",
27
- "au",
28
- "aucun",
29
- "aucune",
30
- "aucuns",
31
- "aujourd",
32
- "aujourd'hui",
33
- "aupres",
34
- "auquel",
35
- "aura",
36
- "aurai",
37
- "auraient",
38
- "aurais",
39
- "aurait",
40
- "auras",
41
- "aurez",
42
- "auriez",
43
- "aurions",
44
- "aurons",
45
- "auront",
46
- "aussi",
47
- "autant",
48
- "autre",
49
- "autrefois",
50
- "autrement",
51
- "autres",
52
- "autrui",
53
- "aux",
54
- "auxquelles",
55
- "auxquels",
56
- "avaient",
57
- "avais",
58
- "avait",
59
- "avant",
60
- "avec",
61
- "avez",
62
- "aviez",
63
- "avions",
64
- "avoir",
65
- "avons",
66
- "ayant",
67
- "ayez",
68
- "ayons",
69
- "b",
70
- "bah",
71
- "bas",
72
- "basee",
73
- "bat",
74
- "beau",
75
- "beaucoup",
76
- "bien",
77
- "bigre",
78
- "bon",
79
- "boum",
80
- "bravo",
81
- "brrr",
82
- "c",
83
- "car",
84
- "ce",
85
- "ceci",
86
- "cela",
87
- "celle",
88
- "celle-ci",
89
- "celle-là",
90
- "celles",
91
- "celles-ci",
92
- "celles-là",
93
- "celui",
94
- "celui-ci",
95
- "celui-là",
96
- "celà",
97
- "cent",
98
- "cependant",
99
- "certain",
100
- "certaine",
101
- "certaines",
102
- "certains",
103
- "certes",
104
- "ces",
105
- "cet",
106
- "cette",
107
- "ceux",
108
- "ceux-ci",
109
- "ceux-là",
110
- "chacun",
111
- "chacune",
112
- "chaque",
113
- "cher",
114
- "chers",
115
- "chez",
116
- "chiche",
117
- "chut",
118
- "chère",
119
- "chères",
120
- "ci",
121
- "cinq",
122
- "cinquantaine",
123
- "cinquante",
124
- "cinquantième",
125
- "cinquième",
126
- "clac",
127
- "clic",
128
- "combien",
129
- "comme",
130
- "comment",
131
- "comparable",
132
- "comparables",
133
- "compris",
134
- "concernant",
135
- "contre",
136
- "couic",
137
- "crac",
138
- "d",
139
- "da",
140
- "dans",
141
- "de",
142
- "debout",
143
- "dedans",
144
- "dehors",
145
- "deja",
146
- "delà",
147
- "depuis",
148
- "dernier",
149
- "derniere",
150
- "derriere",
151
- "derrière",
152
- "des",
153
- "desormais",
154
- "desquelles",
155
- "desquels",
156
- "dessous",
157
- "dessus",
158
- "deux",
159
- "deuxième",
160
- "deuxièmement",
161
- "devant",
162
- "devers",
163
- "devra",
164
- "devrait",
165
- "different",
166
- "differentes",
167
- "differents",
168
- "différent",
169
- "différente",
170
- "différentes",
171
- "différents",
172
- "dire",
173
- "directe",
174
- "directement",
175
- "dit",
176
- "dite",
177
- "dits",
178
- "divers",
179
- "diverse",
180
- "diverses",
181
- "dix",
182
- "dix-huit",
183
- "dix-neuf",
184
- "dix-sept",
185
- "dixième",
186
- "doit",
187
- "doivent",
188
- "donc",
189
- "dont",
190
- "dos",
191
- "douze",
192
- "douzième",
193
- "dring",
194
- "droite",
195
- "du",
196
- "duquel",
197
- "durant",
198
- "dès",
199
- "début",
200
- "désormais",
201
- "e",
202
- "effet",
203
- "egale",
204
- "egalement",
205
- "egales",
206
- "eh",
207
- "elle",
208
- "elle-même",
209
- "elles",
210
- "elles-mêmes",
211
- "en",
212
- "encore",
213
- "enfin",
214
- "entre",
215
- "envers",
216
- "environ",
217
- "es",
218
- "essai",
219
- "est",
220
- "et",
221
- "etant",
222
- "etc",
223
- "etre",
224
- "eu",
225
- "eue",
226
- "eues",
227
- "euh",
228
- "eurent",
229
- "eus",
230
- "eusse",
231
- "eussent",
232
- "eusses",
233
- "eussiez",
234
- "eussions",
235
- "eut",
236
- "eux",
237
- "eux-mêmes",
238
- "exactement",
239
- "excepté",
240
- "extenso",
241
- "exterieur",
242
- "eûmes",
243
- "eût",
244
- "eûtes",
245
- "f",
246
- "fais",
247
- "faisaient",
248
- "faisant",
249
- "fait",
250
- "faites",
251
- "façon",
252
- "feront",
253
- "fi",
254
- "flac",
255
- "floc",
256
- "fois",
257
- "font",
258
- "force",
259
- "furent",
260
- "fus",
261
- "fusse",
262
- "fussent",
263
- "fusses",
264
- "fussiez",
265
- "fussions",
266
- "fut",
267
- "fûmes",
268
- "fût",
269
- "fûtes",
270
- "g",
271
- "gens",
272
- "h",
273
- "ha",
274
- "haut",
275
- "hein",
276
- "hem",
277
- "hep",
278
- "hi",
279
- "ho",
280
- "holà",
281
- "hop",
282
- "hormis",
283
- "hors",
284
- "hou",
285
- "houp",
286
- "hue",
287
- "hui",
288
- "huit",
289
- "huitième",
290
- "hum",
291
- "hurrah",
292
- "hé",
293
- "hélas",
294
- "i",
295
- "ici",
296
- "il",
297
- "ils",
298
- "importe",
299
- "j",
300
- "je",
301
- "jusqu",
302
- "jusque",
303
- "juste",
304
- "k",
305
- "l",
306
- "la",
307
- "laisser",
308
- "laquelle",
309
- "las",
310
- "le",
311
- "lequel",
312
- "les",
313
- "lesquelles",
314
- "lesquels",
315
- "leur",
316
- "leurs",
317
- "longtemps",
318
- "lors",
319
- "lorsque",
320
- "lui",
321
- "lui-meme",
322
- "lui-même",
323
- "là",
324
- "lès",
325
- "m",
326
- "ma",
327
- "maint",
328
- "maintenant",
329
- "mais",
330
- "malgre",
331
- "malgré",
332
- "maximale",
333
- "me",
334
- "meme",
335
- "memes",
336
- "merci",
337
- "mes",
338
- "mien",
339
- "mienne",
340
- "miennes",
341
- "miens",
342
- "mille",
343
- "mince",
344
- "mine",
345
- "minimale",
346
- "moi",
347
- "moi-meme",
348
- "moi-même",
349
- "moindres",
350
- "moins",
351
- "mon",
352
- "mot",
353
- "moyennant",
354
- "multiple",
355
- "multiples",
356
- "même",
357
- "mêmes",
358
- "n",
359
- "na",
360
- "naturel",
361
- "naturelle",
362
- "naturelles",
363
- "ne",
364
- "neanmoins",
365
- "necessaire",
366
- "necessairement",
367
- "neuf",
368
- "neuvième",
369
- "ni",
370
- "nombreuses",
371
- "nombreux",
372
- "nommés",
373
- "non",
374
- "nos",
375
- "notamment",
376
- "notre",
377
- "nous",
378
- "nous-mêmes",
379
- "nouveau",
380
- "nouveaux",
381
- "nul",
382
- "néanmoins",
383
- "nôtre",
384
- "nôtres",
385
- "o",
386
- "oh",
387
- "ohé",
388
- "ollé",
389
- "olé",
390
- "on",
391
- "ont",
392
- "onze",
393
- "onzième",
394
- "ore",
395
- "ou",
396
- "ouf",
397
- "ouias",
398
- "oust",
399
- "ouste",
400
- "outre",
401
- "ouvert",
402
- "ouverte",
403
- "ouverts",
404
- "o|",
405
- "où",
406
- "p",
407
- "paf",
408
- "pan",
409
- "par",
410
- "parce",
411
- "parfois",
412
- "parle",
413
- "parlent",
414
- "parler",
415
- "parmi",
416
- "parole",
417
- "parseme",
418
- "partant",
419
- "particulier",
420
- "particulière",
421
- "particulièrement",
422
- "pas",
423
- "passé",
424
- "pendant",
425
- "pense",
426
- "permet",
427
- "personne",
428
- "personnes",
429
- "peu",
430
- "peut",
431
- "peuvent",
432
- "peux",
433
- "pff",
434
- "pfft",
435
- "pfut",
436
- "pif",
437
- "pire",
438
- "pièce",
439
- "plein",
440
- "plouf",
441
- "plupart",
442
- "plus",
443
- "plusieurs",
444
- "plutôt",
445
- "possessif",
446
- "possessifs",
447
- "possible",
448
- "possibles",
449
- "pouah",
450
- "pour",
451
- "pourquoi",
452
- "pourrais",
453
- "pourrait",
454
- "pouvait",
455
- "prealable",
456
- "precisement",
457
- "premier",
458
- "première",
459
- "premièrement",
460
- "pres",
461
- "probable",
462
- "probante",
463
- "procedant",
464
- "proche",
465
- "près",
466
- "psitt",
467
- "pu",
468
- "puis",
469
- "puisque",
470
- "pur",
471
- "pure",
472
- "q",
473
- "qu",
474
- "quand",
475
- "quant",
476
- "quant-à-soi",
477
- "quanta",
478
- "quarante",
479
- "quatorze",
480
- "quatre",
481
- "quatre-vingt",
482
- "quatrième",
483
- "quatrièmement",
484
- "que",
485
- "quel",
486
- "quelconque",
487
- "quelle",
488
- "quelles",
489
- "quelqu'un",
490
- "quelque",
491
- "quelques",
492
- "quels",
493
- "qui",
494
- "quiconque",
495
- "quinze",
496
- "quoi",
497
- "quoique",
498
- "r",
499
- "rare",
500
- "rarement",
501
- "rares",
502
- "relative",
503
- "relativement",
504
- "remarquable",
505
- "rend",
506
- "rendre",
507
- "restant",
508
- "reste",
509
- "restent",
510
- "restrictif",
511
- "retour",
512
- "revoici",
513
- "revoilà",
514
- "rien",
515
- "s",
516
- "sa",
517
- "sacrebleu",
518
- "sait",
519
- "sans",
520
- "sapristi",
521
- "sauf",
522
- "se",
523
- "sein",
524
- "seize",
525
- "selon",
526
- "semblable",
527
- "semblaient",
528
- "semble",
529
- "semblent",
530
- "sent",
531
- "sept",
532
- "septième",
533
- "sera",
534
- "serai",
535
- "seraient",
536
- "serais",
537
- "serait",
538
- "seras",
539
- "serez",
540
- "seriez",
541
- "serions",
542
- "serons",
543
- "seront",
544
- "ses",
545
- "seul",
546
- "seule",
547
- "seulement",
548
- "si",
549
- "sien",
550
- "sienne",
551
- "siennes",
552
- "siens",
553
- "sinon",
554
- "six",
555
- "sixième",
556
- "soi",
557
- "soi-même",
558
- "soient",
559
- "sois",
560
- "soit",
561
- "soixante",
562
- "sommes",
563
- "son",
564
- "sont",
565
- "sous",
566
- "souvent",
567
- "soyez",
568
- "soyons",
569
- "specifique",
570
- "specifiques",
571
- "speculatif",
572
- "stop",
573
- "strictement",
574
- "subtiles",
575
- "suffisant",
576
- "suffisante",
577
- "suffit",
578
- "suis",
579
- "suit",
580
- "suivant",
581
- "suivante",
582
- "suivantes",
583
- "suivants",
584
- "suivre",
585
- "sujet",
586
- "superpose",
587
- "sur",
588
- "surtout",
589
- "t",
590
- "ta",
591
- "tac",
592
- "tandis",
593
- "tant",
594
- "tardive",
595
- "te",
596
- "tel",
597
- "telle",
598
- "tellement",
599
- "telles",
600
- "tels",
601
- "tenant",
602
- "tend",
603
- "tenir",
604
- "tente",
605
- "tes",
606
- "tic",
607
- "tien",
608
- "tienne",
609
- "tiennes",
610
- "tiens",
611
- "toc",
612
- "toi",
613
- "toi-même",
614
- "ton",
615
- "touchant",
616
- "toujours",
617
- "tous",
618
- "tout",
619
- "toute",
620
- "toutefois",
621
- "toutes",
622
- "treize",
623
- "trente",
624
- "tres",
625
- "trois",
626
- "troisième",
627
- "troisièmement",
628
- "trop",
629
- "très",
630
- "tsoin",
631
- "tsouin",
632
- "tu",
633
- "té",
634
- "u",
635
- "un",
636
- "une",
637
- "unes",
638
- "uniformement",
639
- "unique",
640
- "uniques",
641
- "uns",
642
- "v",
643
- "va",
644
- "vais",
645
- "valeur",
646
- "vas",
647
- "vers",
648
- "via",
649
- "vif",
650
- "vifs",
651
- "vingt",
652
- "vivat",
653
- "vive",
654
- "vives",
655
- "vlan",
656
- "voici",
657
- "voie",
658
- "voient",
659
- "voilà",
660
- "voire",
661
- "vont",
662
- "vos",
663
- "votre",
664
- "vous",
665
- "vous-mêmes",
666
- "vu",
667
- "vé",
668
- "vôtre",
669
- "vôtres",
670
- "w",
671
- "x",
672
- "y",
673
- "z",
674
- "zut",
675
- "à",
676
- "â",
677
- "ça",
678
- "ès",
679
- "étaient",
680
- "étais",
681
- "était",
682
- "étant",
683
- "état",
684
- "étiez",
685
- "étions",
686
- "été",
687
- "étée",
688
- "étées",
689
- "étés",
690
- "êtes",
691
- "être",
692
- "ô"
693
- ]
1
+ [
2
+ "a",
3
+ "abord",
4
+ "absolument",
5
+ "afin",
6
+ "ah",
7
+ "ai",
8
+ "aie",
9
+ "aient",
10
+ "aies",
11
+ "ailleurs",
12
+ "ainsi",
13
+ "ait",
14
+ "allaient",
15
+ "allo",
16
+ "allons",
17
+ "allô",
18
+ "alors",
19
+ "anterieur",
20
+ "anterieure",
21
+ "anterieures",
22
+ "apres",
23
+ "après",
24
+ "as",
25
+ "assez",
26
+ "attendu",
27
+ "au",
28
+ "aucun",
29
+ "aucune",
30
+ "aucuns",
31
+ "aujourd",
32
+ "aujourd'hui",
33
+ "aupres",
34
+ "auquel",
35
+ "aura",
36
+ "aurai",
37
+ "auraient",
38
+ "aurais",
39
+ "aurait",
40
+ "auras",
41
+ "aurez",
42
+ "auriez",
43
+ "aurions",
44
+ "aurons",
45
+ "auront",
46
+ "aussi",
47
+ "autant",
48
+ "autre",
49
+ "autrefois",
50
+ "autrement",
51
+ "autres",
52
+ "autrui",
53
+ "aux",
54
+ "auxquelles",
55
+ "auxquels",
56
+ "avaient",
57
+ "avais",
58
+ "avait",
59
+ "avant",
60
+ "avec",
61
+ "avez",
62
+ "aviez",
63
+ "avions",
64
+ "avoir",
65
+ "avons",
66
+ "ayant",
67
+ "ayez",
68
+ "ayons",
69
+ "b",
70
+ "bah",
71
+ "bas",
72
+ "basee",
73
+ "bat",
74
+ "beau",
75
+ "beaucoup",
76
+ "bien",
77
+ "bigre",
78
+ "bon",
79
+ "boum",
80
+ "bravo",
81
+ "brrr",
82
+ "c",
83
+ "car",
84
+ "ce",
85
+ "ceci",
86
+ "cela",
87
+ "celle",
88
+ "celle-ci",
89
+ "celle-là",
90
+ "celles",
91
+ "celles-ci",
92
+ "celles-là",
93
+ "celui",
94
+ "celui-ci",
95
+ "celui-là",
96
+ "celà",
97
+ "cent",
98
+ "cependant",
99
+ "certain",
100
+ "certaine",
101
+ "certaines",
102
+ "certains",
103
+ "certes",
104
+ "ces",
105
+ "cet",
106
+ "cette",
107
+ "ceux",
108
+ "ceux-ci",
109
+ "ceux-là",
110
+ "chacun",
111
+ "chacune",
112
+ "chaque",
113
+ "cher",
114
+ "chers",
115
+ "chez",
116
+ "chiche",
117
+ "chut",
118
+ "chère",
119
+ "chères",
120
+ "ci",
121
+ "cinq",
122
+ "cinquantaine",
123
+ "cinquante",
124
+ "cinquantième",
125
+ "cinquième",
126
+ "clac",
127
+ "clic",
128
+ "combien",
129
+ "comme",
130
+ "comment",
131
+ "comparable",
132
+ "comparables",
133
+ "compris",
134
+ "concernant",
135
+ "contre",
136
+ "couic",
137
+ "crac",
138
+ "d",
139
+ "da",
140
+ "dans",
141
+ "de",
142
+ "debout",
143
+ "dedans",
144
+ "dehors",
145
+ "deja",
146
+ "delà",
147
+ "depuis",
148
+ "dernier",
149
+ "derniere",
150
+ "derriere",
151
+ "derrière",
152
+ "des",
153
+ "desormais",
154
+ "desquelles",
155
+ "desquels",
156
+ "dessous",
157
+ "dessus",
158
+ "deux",
159
+ "deuxième",
160
+ "deuxièmement",
161
+ "devant",
162
+ "devers",
163
+ "devra",
164
+ "devrait",
165
+ "different",
166
+ "differentes",
167
+ "differents",
168
+ "différent",
169
+ "différente",
170
+ "différentes",
171
+ "différents",
172
+ "dire",
173
+ "directe",
174
+ "directement",
175
+ "dit",
176
+ "dite",
177
+ "dits",
178
+ "divers",
179
+ "diverse",
180
+ "diverses",
181
+ "dix",
182
+ "dix-huit",
183
+ "dix-neuf",
184
+ "dix-sept",
185
+ "dixième",
186
+ "doit",
187
+ "doivent",
188
+ "donc",
189
+ "dont",
190
+ "dos",
191
+ "douze",
192
+ "douzième",
193
+ "dring",
194
+ "droite",
195
+ "du",
196
+ "duquel",
197
+ "durant",
198
+ "dès",
199
+ "début",
200
+ "désormais",
201
+ "e",
202
+ "effet",
203
+ "egale",
204
+ "egalement",
205
+ "egales",
206
+ "eh",
207
+ "elle",
208
+ "elle-même",
209
+ "elles",
210
+ "elles-mêmes",
211
+ "en",
212
+ "encore",
213
+ "enfin",
214
+ "entre",
215
+ "envers",
216
+ "environ",
217
+ "es",
218
+ "essai",
219
+ "est",
220
+ "et",
221
+ "etant",
222
+ "etc",
223
+ "etre",
224
+ "eu",
225
+ "eue",
226
+ "eues",
227
+ "euh",
228
+ "eurent",
229
+ "eus",
230
+ "eusse",
231
+ "eussent",
232
+ "eusses",
233
+ "eussiez",
234
+ "eussions",
235
+ "eut",
236
+ "eux",
237
+ "eux-mêmes",
238
+ "exactement",
239
+ "excepté",
240
+ "extenso",
241
+ "exterieur",
242
+ "eûmes",
243
+ "eût",
244
+ "eûtes",
245
+ "f",
246
+ "fais",
247
+ "faisaient",
248
+ "faisant",
249
+ "fait",
250
+ "faites",
251
+ "façon",
252
+ "feront",
253
+ "fi",
254
+ "flac",
255
+ "floc",
256
+ "fois",
257
+ "font",
258
+ "force",
259
+ "furent",
260
+ "fus",
261
+ "fusse",
262
+ "fussent",
263
+ "fusses",
264
+ "fussiez",
265
+ "fussions",
266
+ "fut",
267
+ "fûmes",
268
+ "fût",
269
+ "fûtes",
270
+ "g",
271
+ "gens",
272
+ "h",
273
+ "ha",
274
+ "haut",
275
+ "hein",
276
+ "hem",
277
+ "hep",
278
+ "hi",
279
+ "ho",
280
+ "holà",
281
+ "hop",
282
+ "hormis",
283
+ "hors",
284
+ "hou",
285
+ "houp",
286
+ "hue",
287
+ "hui",
288
+ "huit",
289
+ "huitième",
290
+ "hum",
291
+ "hurrah",
292
+ "hé",
293
+ "hélas",
294
+ "i",
295
+ "ici",
296
+ "il",
297
+ "ils",
298
+ "importe",
299
+ "j",
300
+ "je",
301
+ "jusqu",
302
+ "jusque",
303
+ "juste",
304
+ "k",
305
+ "l",
306
+ "la",
307
+ "laisser",
308
+ "laquelle",
309
+ "las",
310
+ "le",
311
+ "lequel",
312
+ "les",
313
+ "lesquelles",
314
+ "lesquels",
315
+ "leur",
316
+ "leurs",
317
+ "longtemps",
318
+ "lors",
319
+ "lorsque",
320
+ "lui",
321
+ "lui-meme",
322
+ "lui-même",
323
+ "là",
324
+ "lès",
325
+ "m",
326
+ "ma",
327
+ "maint",
328
+ "maintenant",
329
+ "mais",
330
+ "malgre",
331
+ "malgré",
332
+ "maximale",
333
+ "me",
334
+ "meme",
335
+ "memes",
336
+ "merci",
337
+ "mes",
338
+ "mien",
339
+ "mienne",
340
+ "miennes",
341
+ "miens",
342
+ "mille",
343
+ "mince",
344
+ "mine",
345
+ "minimale",
346
+ "moi",
347
+ "moi-meme",
348
+ "moi-même",
349
+ "moindres",
350
+ "moins",
351
+ "mon",
352
+ "mot",
353
+ "moyennant",
354
+ "multiple",
355
+ "multiples",
356
+ "même",
357
+ "mêmes",
358
+ "n",
359
+ "na",
360
+ "naturel",
361
+ "naturelle",
362
+ "naturelles",
363
+ "ne",
364
+ "neanmoins",
365
+ "necessaire",
366
+ "necessairement",
367
+ "neuf",
368
+ "neuvième",
369
+ "ni",
370
+ "nombreuses",
371
+ "nombreux",
372
+ "nommés",
373
+ "non",
374
+ "nos",
375
+ "notamment",
376
+ "notre",
377
+ "nous",
378
+ "nous-mêmes",
379
+ "nouveau",
380
+ "nouveaux",
381
+ "nul",
382
+ "néanmoins",
383
+ "nôtre",
384
+ "nôtres",
385
+ "o",
386
+ "oh",
387
+ "ohé",
388
+ "ollé",
389
+ "olé",
390
+ "on",
391
+ "ont",
392
+ "onze",
393
+ "onzième",
394
+ "ore",
395
+ "ou",
396
+ "ouf",
397
+ "ouias",
398
+ "oust",
399
+ "ouste",
400
+ "outre",
401
+ "ouvert",
402
+ "ouverte",
403
+ "ouverts",
404
+ "o|",
405
+ "où",
406
+ "p",
407
+ "paf",
408
+ "pan",
409
+ "par",
410
+ "parce",
411
+ "parfois",
412
+ "parle",
413
+ "parlent",
414
+ "parler",
415
+ "parmi",
416
+ "parole",
417
+ "parseme",
418
+ "partant",
419
+ "particulier",
420
+ "particulière",
421
+ "particulièrement",
422
+ "pas",
423
+ "passé",
424
+ "pendant",
425
+ "pense",
426
+ "permet",
427
+ "personne",
428
+ "personnes",
429
+ "peu",
430
+ "peut",
431
+ "peuvent",
432
+ "peux",
433
+ "pff",
434
+ "pfft",
435
+ "pfut",
436
+ "pif",
437
+ "pire",
438
+ "pièce",
439
+ "plein",
440
+ "plouf",
441
+ "plupart",
442
+ "plus",
443
+ "plusieurs",
444
+ "plutôt",
445
+ "possessif",
446
+ "possessifs",
447
+ "possible",
448
+ "possibles",
449
+ "pouah",
450
+ "pour",
451
+ "pourquoi",
452
+ "pourrais",
453
+ "pourrait",
454
+ "pouvait",
455
+ "prealable",
456
+ "precisement",
457
+ "premier",
458
+ "première",
459
+ "premièrement",
460
+ "pres",
461
+ "probable",
462
+ "probante",
463
+ "procedant",
464
+ "proche",
465
+ "près",
466
+ "psitt",
467
+ "pu",
468
+ "puis",
469
+ "puisque",
470
+ "pur",
471
+ "pure",
472
+ "q",
473
+ "qu",
474
+ "quand",
475
+ "quant",
476
+ "quant-à-soi",
477
+ "quanta",
478
+ "quarante",
479
+ "quatorze",
480
+ "quatre",
481
+ "quatre-vingt",
482
+ "quatrième",
483
+ "quatrièmement",
484
+ "que",
485
+ "quel",
486
+ "quelconque",
487
+ "quelle",
488
+ "quelles",
489
+ "quelqu'un",
490
+ "quelque",
491
+ "quelques",
492
+ "quels",
493
+ "qui",
494
+ "quiconque",
495
+ "quinze",
496
+ "quoi",
497
+ "quoique",
498
+ "r",
499
+ "rare",
500
+ "rarement",
501
+ "rares",
502
+ "relative",
503
+ "relativement",
504
+ "remarquable",
505
+ "rend",
506
+ "rendre",
507
+ "restant",
508
+ "reste",
509
+ "restent",
510
+ "restrictif",
511
+ "retour",
512
+ "revoici",
513
+ "revoilà",
514
+ "rien",
515
+ "s",
516
+ "sa",
517
+ "sacrebleu",
518
+ "sait",
519
+ "sans",
520
+ "sapristi",
521
+ "sauf",
522
+ "se",
523
+ "sein",
524
+ "seize",
525
+ "selon",
526
+ "semblable",
527
+ "semblaient",
528
+ "semble",
529
+ "semblent",
530
+ "sent",
531
+ "sept",
532
+ "septième",
533
+ "sera",
534
+ "serai",
535
+ "seraient",
536
+ "serais",
537
+ "serait",
538
+ "seras",
539
+ "serez",
540
+ "seriez",
541
+ "serions",
542
+ "serons",
543
+ "seront",
544
+ "ses",
545
+ "seul",
546
+ "seule",
547
+ "seulement",
548
+ "si",
549
+ "sien",
550
+ "sienne",
551
+ "siennes",
552
+ "siens",
553
+ "sinon",
554
+ "six",
555
+ "sixième",
556
+ "soi",
557
+ "soi-même",
558
+ "soient",
559
+ "sois",
560
+ "soit",
561
+ "soixante",
562
+ "sommes",
563
+ "son",
564
+ "sont",
565
+ "sous",
566
+ "souvent",
567
+ "soyez",
568
+ "soyons",
569
+ "specifique",
570
+ "specifiques",
571
+ "speculatif",
572
+ "stop",
573
+ "strictement",
574
+ "subtiles",
575
+ "suffisant",
576
+ "suffisante",
577
+ "suffit",
578
+ "suis",
579
+ "suit",
580
+ "suivant",
581
+ "suivante",
582
+ "suivantes",
583
+ "suivants",
584
+ "suivre",
585
+ "sujet",
586
+ "superpose",
587
+ "sur",
588
+ "surtout",
589
+ "t",
590
+ "ta",
591
+ "tac",
592
+ "tandis",
593
+ "tant",
594
+ "tardive",
595
+ "te",
596
+ "tel",
597
+ "telle",
598
+ "tellement",
599
+ "telles",
600
+ "tels",
601
+ "tenant",
602
+ "tend",
603
+ "tenir",
604
+ "tente",
605
+ "tes",
606
+ "tic",
607
+ "tien",
608
+ "tienne",
609
+ "tiennes",
610
+ "tiens",
611
+ "toc",
612
+ "toi",
613
+ "toi-même",
614
+ "ton",
615
+ "touchant",
616
+ "toujours",
617
+ "tous",
618
+ "tout",
619
+ "toute",
620
+ "toutefois",
621
+ "toutes",
622
+ "treize",
623
+ "trente",
624
+ "tres",
625
+ "trois",
626
+ "troisième",
627
+ "troisièmement",
628
+ "trop",
629
+ "très",
630
+ "tsoin",
631
+ "tsouin",
632
+ "tu",
633
+ "té",
634
+ "u",
635
+ "un",
636
+ "une",
637
+ "unes",
638
+ "uniformement",
639
+ "unique",
640
+ "uniques",
641
+ "uns",
642
+ "v",
643
+ "va",
644
+ "vais",
645
+ "valeur",
646
+ "vas",
647
+ "vers",
648
+ "via",
649
+ "vif",
650
+ "vifs",
651
+ "vingt",
652
+ "vivat",
653
+ "vive",
654
+ "vives",
655
+ "vlan",
656
+ "voici",
657
+ "voie",
658
+ "voient",
659
+ "voilà",
660
+ "voire",
661
+ "vont",
662
+ "vos",
663
+ "votre",
664
+ "vous",
665
+ "vous-mêmes",
666
+ "vu",
667
+ "vé",
668
+ "vôtre",
669
+ "vôtres",
670
+ "w",
671
+ "x",
672
+ "y",
673
+ "z",
674
+ "zut",
675
+ "à",
676
+ "â",
677
+ "ça",
678
+ "ès",
679
+ "étaient",
680
+ "étais",
681
+ "était",
682
+ "étant",
683
+ "état",
684
+ "étiez",
685
+ "étions",
686
+ "été",
687
+ "étée",
688
+ "étées",
689
+ "étés",
690
+ "êtes",
691
+ "être",
692
+ "ô"
693
+ ]