kreuzberg 4.0.0.rc2 → 4.0.1

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 (446) 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 +543 -538
  6. data/Gemfile +8 -8
  7. data/Gemfile.lock +194 -6
  8. data/README.md +391 -426
  9. data/Rakefile +34 -25
  10. data/Steepfile +51 -47
  11. data/examples/async_patterns.rb +283 -341
  12. data/ext/kreuzberg_rb/extconf.rb +65 -45
  13. data/ext/kreuzberg_rb/native/.cargo/config.toml +23 -0
  14. data/ext/kreuzberg_rb/native/Cargo.lock +7619 -6535
  15. data/ext/kreuzberg_rb/native/Cargo.toml +75 -44
  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 +3802 -2998
  23. data/extconf.rb +60 -28
  24. data/kreuzberg.gemspec +199 -148
  25. data/lib/kreuzberg/api_proxy.rb +126 -142
  26. data/lib/kreuzberg/cache_api.rb +67 -46
  27. data/lib/kreuzberg/cli.rb +47 -55
  28. data/lib/kreuzberg/cli_proxy.rb +117 -127
  29. data/lib/kreuzberg/config.rb +936 -691
  30. data/lib/kreuzberg/error_context.rb +136 -32
  31. data/lib/kreuzberg/errors.rb +116 -118
  32. data/lib/kreuzberg/extraction_api.rb +313 -85
  33. data/lib/kreuzberg/mcp_proxy.rb +177 -186
  34. data/lib/kreuzberg/ocr_backend_protocol.rb +40 -113
  35. data/lib/kreuzberg/post_processor_protocol.rb +15 -86
  36. data/lib/kreuzberg/result.rb +334 -216
  37. data/lib/kreuzberg/setup_lib_path.rb +99 -80
  38. data/lib/kreuzberg/types.rb +170 -0
  39. data/lib/kreuzberg/validator_protocol.rb +16 -89
  40. data/lib/kreuzberg/version.rb +5 -5
  41. data/lib/kreuzberg.rb +96 -103
  42. data/lib/libpdfium.so +0 -0
  43. data/sig/kreuzberg/internal.rbs +184 -184
  44. data/sig/kreuzberg.rbs +561 -520
  45. data/spec/binding/async_operations_spec.rb +473 -0
  46. data/spec/binding/batch_operations_spec.rb +595 -0
  47. data/spec/binding/batch_spec.rb +359 -0
  48. data/spec/binding/cache_spec.rb +227 -227
  49. data/spec/binding/cli_proxy_spec.rb +85 -85
  50. data/spec/binding/cli_spec.rb +55 -55
  51. data/spec/binding/config_result_spec.rb +377 -0
  52. data/spec/binding/config_spec.rb +419 -345
  53. data/spec/binding/config_validation_spec.rb +377 -283
  54. data/spec/binding/embeddings_spec.rb +816 -0
  55. data/spec/binding/error_handling_spec.rb +399 -213
  56. data/spec/binding/error_recovery_spec.rb +488 -0
  57. data/spec/binding/errors_spec.rb +66 -66
  58. data/spec/binding/font_config_spec.rb +220 -0
  59. data/spec/binding/images_spec.rb +738 -0
  60. data/spec/binding/keywords_extraction_spec.rb +600 -0
  61. data/spec/binding/metadata_types_spec.rb +1228 -0
  62. data/spec/binding/pages_extraction_spec.rb +471 -0
  63. data/spec/binding/plugins/ocr_backend_spec.rb +307 -307
  64. data/spec/binding/plugins/postprocessor_spec.rb +269 -269
  65. data/spec/binding/plugins/validator_spec.rb +273 -274
  66. data/spec/binding/tables_spec.rb +641 -0
  67. data/spec/fixtures/config.toml +38 -39
  68. data/spec/fixtures/config.yaml +41 -41
  69. data/spec/fixtures/invalid_config.toml +3 -4
  70. data/spec/smoke/package_spec.rb +177 -178
  71. data/spec/spec_helper.rb +40 -42
  72. data/spec/unit/config/chunking_config_spec.rb +213 -0
  73. data/spec/unit/config/embedding_config_spec.rb +343 -0
  74. data/spec/unit/config/extraction_config_spec.rb +438 -0
  75. data/spec/unit/config/font_config_spec.rb +285 -0
  76. data/spec/unit/config/hierarchy_config_spec.rb +314 -0
  77. data/spec/unit/config/image_extraction_config_spec.rb +209 -0
  78. data/spec/unit/config/image_preprocessing_config_spec.rb +249 -0
  79. data/spec/unit/config/keyword_config_spec.rb +229 -0
  80. data/spec/unit/config/language_detection_config_spec.rb +258 -0
  81. data/spec/unit/config/ocr_config_spec.rb +171 -0
  82. data/spec/unit/config/page_config_spec.rb +221 -0
  83. data/spec/unit/config/pdf_config_spec.rb +267 -0
  84. data/spec/unit/config/postprocessor_config_spec.rb +290 -0
  85. data/spec/unit/config/tesseract_config_spec.rb +181 -0
  86. data/spec/unit/config/token_reduction_config_spec.rb +251 -0
  87. data/test/metadata_types_test.rb +959 -0
  88. data/vendor/Cargo.toml +61 -0
  89. data/vendor/kreuzberg/Cargo.toml +259 -204
  90. data/vendor/kreuzberg/README.md +263 -175
  91. data/vendor/kreuzberg/build.rs +782 -474
  92. data/vendor/kreuzberg/examples/bench_fixes.rs +71 -0
  93. data/vendor/kreuzberg/examples/test_pdfium_fork.rs +62 -0
  94. data/vendor/kreuzberg/src/api/error.rs +81 -81
  95. data/vendor/kreuzberg/src/api/handlers.rs +320 -199
  96. data/vendor/kreuzberg/src/api/mod.rs +94 -79
  97. data/vendor/kreuzberg/src/api/server.rs +518 -353
  98. data/vendor/kreuzberg/src/api/types.rs +206 -170
  99. data/vendor/kreuzberg/src/cache/mod.rs +1167 -1167
  100. data/vendor/kreuzberg/src/chunking/mod.rs +2303 -677
  101. data/vendor/kreuzberg/src/chunking/processor.rs +219 -0
  102. data/vendor/kreuzberg/src/core/batch_mode.rs +95 -95
  103. data/vendor/kreuzberg/src/core/batch_optimizations.rs +385 -0
  104. data/vendor/kreuzberg/src/core/config.rs +1914 -1032
  105. data/vendor/kreuzberg/src/core/config_validation.rs +949 -0
  106. data/vendor/kreuzberg/src/core/extractor.rs +1200 -1024
  107. data/vendor/kreuzberg/src/core/formats.rs +235 -0
  108. data/vendor/kreuzberg/src/core/io.rs +329 -329
  109. data/vendor/kreuzberg/src/core/mime.rs +605 -605
  110. data/vendor/kreuzberg/src/core/mod.rs +61 -45
  111. data/vendor/kreuzberg/src/core/pipeline.rs +1223 -984
  112. data/vendor/kreuzberg/src/core/server_config.rs +1220 -0
  113. data/vendor/kreuzberg/src/embeddings.rs +471 -432
  114. data/vendor/kreuzberg/src/error.rs +431 -431
  115. data/vendor/kreuzberg/src/extraction/archive.rs +959 -954
  116. data/vendor/kreuzberg/src/extraction/capacity.rs +263 -0
  117. data/vendor/kreuzberg/src/extraction/docx.rs +404 -40
  118. data/vendor/kreuzberg/src/extraction/email.rs +855 -854
  119. data/vendor/kreuzberg/src/extraction/excel.rs +697 -688
  120. data/vendor/kreuzberg/src/extraction/html.rs +1830 -553
  121. data/vendor/kreuzberg/src/extraction/image.rs +492 -368
  122. data/vendor/kreuzberg/src/extraction/libreoffice.rs +574 -563
  123. data/vendor/kreuzberg/src/extraction/markdown.rs +216 -213
  124. data/vendor/kreuzberg/src/extraction/mod.rs +93 -81
  125. data/vendor/kreuzberg/src/extraction/office_metadata/app_properties.rs +398 -398
  126. data/vendor/kreuzberg/src/extraction/office_metadata/core_properties.rs +247 -247
  127. data/vendor/kreuzberg/src/extraction/office_metadata/custom_properties.rs +240 -240
  128. data/vendor/kreuzberg/src/extraction/office_metadata/mod.rs +130 -130
  129. data/vendor/kreuzberg/src/extraction/office_metadata/odt_properties.rs +284 -287
  130. data/vendor/kreuzberg/src/extraction/pptx.rs +3102 -3000
  131. data/vendor/kreuzberg/src/extraction/structured.rs +491 -490
  132. data/vendor/kreuzberg/src/extraction/table.rs +329 -328
  133. data/vendor/kreuzberg/src/extraction/text.rs +277 -269
  134. data/vendor/kreuzberg/src/extraction/xml.rs +333 -333
  135. data/vendor/kreuzberg/src/extractors/archive.rs +447 -446
  136. data/vendor/kreuzberg/src/extractors/bibtex.rs +470 -469
  137. data/vendor/kreuzberg/src/extractors/docbook.rs +504 -502
  138. data/vendor/kreuzberg/src/extractors/docx.rs +400 -367
  139. data/vendor/kreuzberg/src/extractors/email.rs +157 -143
  140. data/vendor/kreuzberg/src/extractors/epub.rs +696 -707
  141. data/vendor/kreuzberg/src/extractors/excel.rs +385 -343
  142. data/vendor/kreuzberg/src/extractors/fictionbook.rs +492 -491
  143. data/vendor/kreuzberg/src/extractors/html.rs +419 -393
  144. data/vendor/kreuzberg/src/extractors/image.rs +219 -198
  145. data/vendor/kreuzberg/src/extractors/jats.rs +1054 -1051
  146. data/vendor/kreuzberg/src/extractors/jupyter.rs +368 -367
  147. data/vendor/kreuzberg/src/extractors/latex.rs +653 -652
  148. data/vendor/kreuzberg/src/extractors/markdown.rs +701 -700
  149. data/vendor/kreuzberg/src/extractors/mod.rs +429 -365
  150. data/vendor/kreuzberg/src/extractors/odt.rs +628 -628
  151. data/vendor/kreuzberg/src/extractors/opml.rs +635 -634
  152. data/vendor/kreuzberg/src/extractors/orgmode.rs +529 -528
  153. data/vendor/kreuzberg/src/extractors/pdf.rs +761 -493
  154. data/vendor/kreuzberg/src/extractors/pptx.rs +279 -248
  155. data/vendor/kreuzberg/src/extractors/rst.rs +577 -576
  156. data/vendor/kreuzberg/src/extractors/rtf.rs +809 -810
  157. data/vendor/kreuzberg/src/extractors/security.rs +484 -484
  158. data/vendor/kreuzberg/src/extractors/security_tests.rs +367 -367
  159. data/vendor/kreuzberg/src/extractors/structured.rs +142 -140
  160. data/vendor/kreuzberg/src/extractors/text.rs +265 -260
  161. data/vendor/kreuzberg/src/extractors/typst.rs +651 -650
  162. data/vendor/kreuzberg/src/extractors/xml.rs +147 -135
  163. data/vendor/kreuzberg/src/image/dpi.rs +164 -164
  164. data/vendor/kreuzberg/src/image/mod.rs +6 -6
  165. data/vendor/kreuzberg/src/image/preprocessing.rs +417 -417
  166. data/vendor/kreuzberg/src/image/resize.rs +89 -89
  167. data/vendor/kreuzberg/src/keywords/config.rs +154 -154
  168. data/vendor/kreuzberg/src/keywords/mod.rs +237 -237
  169. data/vendor/kreuzberg/src/keywords/processor.rs +275 -267
  170. data/vendor/kreuzberg/src/keywords/rake.rs +293 -293
  171. data/vendor/kreuzberg/src/keywords/types.rs +68 -68
  172. data/vendor/kreuzberg/src/keywords/yake.rs +163 -163
  173. data/vendor/kreuzberg/src/language_detection/mod.rs +985 -942
  174. data/vendor/kreuzberg/src/language_detection/processor.rs +218 -0
  175. data/vendor/kreuzberg/src/lib.rs +114 -105
  176. data/vendor/kreuzberg/src/mcp/mod.rs +35 -32
  177. data/vendor/kreuzberg/src/mcp/server.rs +2090 -1968
  178. data/vendor/kreuzberg/src/ocr/cache.rs +469 -469
  179. data/vendor/kreuzberg/src/ocr/error.rs +37 -37
  180. data/vendor/kreuzberg/src/ocr/hocr.rs +216 -216
  181. data/vendor/kreuzberg/src/ocr/language_registry.rs +520 -0
  182. data/vendor/kreuzberg/src/ocr/mod.rs +60 -58
  183. data/vendor/kreuzberg/src/ocr/processor.rs +858 -863
  184. data/vendor/kreuzberg/src/ocr/table/mod.rs +4 -4
  185. data/vendor/kreuzberg/src/ocr/table/tsv_parser.rs +144 -144
  186. data/vendor/kreuzberg/src/ocr/tesseract_backend.rs +456 -450
  187. data/vendor/kreuzberg/src/ocr/types.rs +393 -393
  188. data/vendor/kreuzberg/src/ocr/utils.rs +47 -47
  189. data/vendor/kreuzberg/src/ocr/validation.rs +206 -206
  190. data/vendor/kreuzberg/src/panic_context.rs +154 -154
  191. data/vendor/kreuzberg/src/pdf/bindings.rs +306 -0
  192. data/vendor/kreuzberg/src/pdf/bundled.rs +408 -0
  193. data/vendor/kreuzberg/src/pdf/error.rs +214 -122
  194. data/vendor/kreuzberg/src/pdf/fonts.rs +358 -0
  195. data/vendor/kreuzberg/src/pdf/hierarchy.rs +903 -0
  196. data/vendor/kreuzberg/src/pdf/images.rs +139 -139
  197. data/vendor/kreuzberg/src/pdf/metadata.rs +509 -346
  198. data/vendor/kreuzberg/src/pdf/mod.rs +81 -50
  199. data/vendor/kreuzberg/src/pdf/rendering.rs +369 -369
  200. data/vendor/kreuzberg/src/pdf/table.rs +417 -393
  201. data/vendor/kreuzberg/src/pdf/text.rs +553 -158
  202. data/vendor/kreuzberg/src/plugins/extractor.rs +1042 -1013
  203. data/vendor/kreuzberg/src/plugins/mod.rs +212 -209
  204. data/vendor/kreuzberg/src/plugins/ocr.rs +637 -620
  205. data/vendor/kreuzberg/src/plugins/processor.rs +650 -642
  206. data/vendor/kreuzberg/src/plugins/registry.rs +1339 -1337
  207. data/vendor/kreuzberg/src/plugins/traits.rs +258 -258
  208. data/vendor/kreuzberg/src/plugins/validator.rs +967 -956
  209. data/vendor/kreuzberg/src/stopwords/mod.rs +1470 -1470
  210. data/vendor/kreuzberg/src/text/mod.rs +27 -19
  211. data/vendor/kreuzberg/src/text/quality.rs +710 -697
  212. data/vendor/kreuzberg/src/text/quality_processor.rs +231 -0
  213. data/vendor/kreuzberg/src/text/string_utils.rs +229 -217
  214. data/vendor/kreuzberg/src/text/token_reduction/cjk_utils.rs +164 -164
  215. data/vendor/kreuzberg/src/text/token_reduction/config.rs +100 -100
  216. data/vendor/kreuzberg/src/text/token_reduction/core.rs +832 -796
  217. data/vendor/kreuzberg/src/text/token_reduction/filters.rs +923 -902
  218. data/vendor/kreuzberg/src/text/token_reduction/mod.rs +160 -160
  219. data/vendor/kreuzberg/src/text/token_reduction/semantic.rs +619 -619
  220. data/vendor/kreuzberg/src/text/token_reduction/simd_text.rs +148 -147
  221. data/vendor/kreuzberg/src/text/utf8_validation.rs +193 -0
  222. data/vendor/kreuzberg/src/types.rs +1713 -903
  223. data/vendor/kreuzberg/src/utils/mod.rs +31 -17
  224. data/vendor/kreuzberg/src/utils/pool.rs +503 -0
  225. data/vendor/kreuzberg/src/utils/pool_sizing.rs +364 -0
  226. data/vendor/kreuzberg/src/utils/quality.rs +968 -959
  227. data/vendor/kreuzberg/src/utils/string_pool.rs +761 -0
  228. data/vendor/kreuzberg/src/utils/string_utils.rs +381 -381
  229. data/vendor/kreuzberg/stopwords/af_stopwords.json +53 -53
  230. data/vendor/kreuzberg/stopwords/ar_stopwords.json +482 -482
  231. data/vendor/kreuzberg/stopwords/bg_stopwords.json +261 -261
  232. data/vendor/kreuzberg/stopwords/bn_stopwords.json +400 -400
  233. data/vendor/kreuzberg/stopwords/br_stopwords.json +1205 -1205
  234. data/vendor/kreuzberg/stopwords/ca_stopwords.json +280 -280
  235. data/vendor/kreuzberg/stopwords/cs_stopwords.json +425 -425
  236. data/vendor/kreuzberg/stopwords/da_stopwords.json +172 -172
  237. data/vendor/kreuzberg/stopwords/de_stopwords.json +622 -622
  238. data/vendor/kreuzberg/stopwords/el_stopwords.json +849 -849
  239. data/vendor/kreuzberg/stopwords/en_stopwords.json +1300 -1300
  240. data/vendor/kreuzberg/stopwords/eo_stopwords.json +175 -175
  241. data/vendor/kreuzberg/stopwords/es_stopwords.json +734 -734
  242. data/vendor/kreuzberg/stopwords/et_stopwords.json +37 -37
  243. data/vendor/kreuzberg/stopwords/eu_stopwords.json +100 -100
  244. data/vendor/kreuzberg/stopwords/fa_stopwords.json +801 -801
  245. data/vendor/kreuzberg/stopwords/fi_stopwords.json +849 -849
  246. data/vendor/kreuzberg/stopwords/fr_stopwords.json +693 -693
  247. data/vendor/kreuzberg/stopwords/ga_stopwords.json +111 -111
  248. data/vendor/kreuzberg/stopwords/gl_stopwords.json +162 -162
  249. data/vendor/kreuzberg/stopwords/gu_stopwords.json +226 -226
  250. data/vendor/kreuzberg/stopwords/ha_stopwords.json +41 -41
  251. data/vendor/kreuzberg/stopwords/he_stopwords.json +196 -196
  252. data/vendor/kreuzberg/stopwords/hi_stopwords.json +227 -227
  253. data/vendor/kreuzberg/stopwords/hr_stopwords.json +181 -181
  254. data/vendor/kreuzberg/stopwords/hu_stopwords.json +791 -791
  255. data/vendor/kreuzberg/stopwords/hy_stopwords.json +47 -47
  256. data/vendor/kreuzberg/stopwords/id_stopwords.json +760 -760
  257. data/vendor/kreuzberg/stopwords/it_stopwords.json +634 -634
  258. data/vendor/kreuzberg/stopwords/ja_stopwords.json +136 -136
  259. data/vendor/kreuzberg/stopwords/kn_stopwords.json +84 -84
  260. data/vendor/kreuzberg/stopwords/ko_stopwords.json +681 -681
  261. data/vendor/kreuzberg/stopwords/ku_stopwords.json +64 -64
  262. data/vendor/kreuzberg/stopwords/la_stopwords.json +51 -51
  263. data/vendor/kreuzberg/stopwords/lt_stopwords.json +476 -476
  264. data/vendor/kreuzberg/stopwords/lv_stopwords.json +163 -163
  265. data/vendor/kreuzberg/stopwords/ml_stopwords.json +1 -1
  266. data/vendor/kreuzberg/stopwords/mr_stopwords.json +101 -101
  267. data/vendor/kreuzberg/stopwords/ms_stopwords.json +477 -477
  268. data/vendor/kreuzberg/stopwords/ne_stopwords.json +490 -490
  269. data/vendor/kreuzberg/stopwords/nl_stopwords.json +415 -415
  270. data/vendor/kreuzberg/stopwords/no_stopwords.json +223 -223
  271. data/vendor/kreuzberg/stopwords/pl_stopwords.json +331 -331
  272. data/vendor/kreuzberg/stopwords/pt_stopwords.json +562 -562
  273. data/vendor/kreuzberg/stopwords/ro_stopwords.json +436 -436
  274. data/vendor/kreuzberg/stopwords/ru_stopwords.json +561 -561
  275. data/vendor/kreuzberg/stopwords/si_stopwords.json +193 -193
  276. data/vendor/kreuzberg/stopwords/sk_stopwords.json +420 -420
  277. data/vendor/kreuzberg/stopwords/sl_stopwords.json +448 -448
  278. data/vendor/kreuzberg/stopwords/so_stopwords.json +32 -32
  279. data/vendor/kreuzberg/stopwords/st_stopwords.json +33 -33
  280. data/vendor/kreuzberg/stopwords/sv_stopwords.json +420 -420
  281. data/vendor/kreuzberg/stopwords/sw_stopwords.json +76 -76
  282. data/vendor/kreuzberg/stopwords/ta_stopwords.json +129 -129
  283. data/vendor/kreuzberg/stopwords/te_stopwords.json +54 -54
  284. data/vendor/kreuzberg/stopwords/th_stopwords.json +118 -118
  285. data/vendor/kreuzberg/stopwords/tl_stopwords.json +149 -149
  286. data/vendor/kreuzberg/stopwords/tr_stopwords.json +506 -506
  287. data/vendor/kreuzberg/stopwords/uk_stopwords.json +75 -75
  288. data/vendor/kreuzberg/stopwords/ur_stopwords.json +519 -519
  289. data/vendor/kreuzberg/stopwords/vi_stopwords.json +647 -647
  290. data/vendor/kreuzberg/stopwords/yo_stopwords.json +62 -62
  291. data/vendor/kreuzberg/stopwords/zh_stopwords.json +796 -796
  292. data/vendor/kreuzberg/stopwords/zu_stopwords.json +31 -31
  293. data/vendor/kreuzberg/tests/api_embed.rs +360 -0
  294. data/vendor/kreuzberg/tests/api_extract_multipart.rs +52 -52
  295. data/vendor/kreuzberg/tests/api_large_pdf_extraction.rs +471 -0
  296. data/vendor/kreuzberg/tests/api_large_pdf_extraction_diagnostics.rs +289 -0
  297. data/vendor/kreuzberg/tests/api_tests.rs +1472 -966
  298. data/vendor/kreuzberg/tests/archive_integration.rs +545 -543
  299. data/vendor/kreuzberg/tests/batch_orchestration.rs +587 -556
  300. data/vendor/kreuzberg/tests/batch_pooling_benchmark.rs +154 -0
  301. data/vendor/kreuzberg/tests/batch_processing.rs +328 -316
  302. data/vendor/kreuzberg/tests/bibtex_parity_test.rs +421 -421
  303. data/vendor/kreuzberg/tests/concurrency_stress.rs +541 -525
  304. data/vendor/kreuzberg/tests/config_features.rs +612 -598
  305. data/vendor/kreuzberg/tests/config_integration_test.rs +753 -0
  306. data/vendor/kreuzberg/tests/config_loading_tests.rs +416 -415
  307. data/vendor/kreuzberg/tests/core_integration.rs +519 -510
  308. data/vendor/kreuzberg/tests/csv_integration.rs +414 -414
  309. data/vendor/kreuzberg/tests/data/hierarchy_ground_truth.json +294 -0
  310. data/vendor/kreuzberg/tests/docbook_extractor_tests.rs +500 -498
  311. data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +122 -122
  312. data/vendor/kreuzberg/tests/docx_vs_pandoc_comparison.rs +370 -370
  313. data/vendor/kreuzberg/tests/email_integration.rs +327 -325
  314. data/vendor/kreuzberg/tests/epub_native_extractor_tests.rs +275 -275
  315. data/vendor/kreuzberg/tests/error_handling.rs +402 -393
  316. data/vendor/kreuzberg/tests/fictionbook_extractor_tests.rs +228 -228
  317. data/vendor/kreuzberg/tests/format_integration.rs +165 -159
  318. data/vendor/kreuzberg/tests/helpers/mod.rs +202 -142
  319. data/vendor/kreuzberg/tests/html_table_test.rs +551 -551
  320. data/vendor/kreuzberg/tests/image_integration.rs +255 -253
  321. data/vendor/kreuzberg/tests/instrumentation_test.rs +139 -139
  322. data/vendor/kreuzberg/tests/jats_extractor_tests.rs +639 -639
  323. data/vendor/kreuzberg/tests/jupyter_extractor_tests.rs +704 -704
  324. data/vendor/kreuzberg/tests/keywords_integration.rs +479 -479
  325. data/vendor/kreuzberg/tests/keywords_quality.rs +509 -509
  326. data/vendor/kreuzberg/tests/latex_extractor_tests.rs +496 -496
  327. data/vendor/kreuzberg/tests/markdown_extractor_tests.rs +490 -490
  328. data/vendor/kreuzberg/tests/mime_detection.rs +429 -428
  329. data/vendor/kreuzberg/tests/ocr_configuration.rs +514 -510
  330. data/vendor/kreuzberg/tests/ocr_errors.rs +698 -676
  331. data/vendor/kreuzberg/tests/ocr_language_registry.rs +191 -0
  332. data/vendor/kreuzberg/tests/ocr_quality.rs +629 -627
  333. data/vendor/kreuzberg/tests/ocr_stress.rs +469 -469
  334. data/vendor/kreuzberg/tests/odt_extractor_tests.rs +674 -695
  335. data/vendor/kreuzberg/tests/opml_extractor_tests.rs +616 -616
  336. data/vendor/kreuzberg/tests/orgmode_extractor_tests.rs +822 -822
  337. data/vendor/kreuzberg/tests/page_markers.rs +297 -0
  338. data/vendor/kreuzberg/tests/pdf_hierarchy_detection.rs +301 -0
  339. data/vendor/kreuzberg/tests/pdf_hierarchy_quality.rs +589 -0
  340. data/vendor/kreuzberg/tests/pdf_integration.rs +45 -43
  341. data/vendor/kreuzberg/tests/pdf_ocr_triggering.rs +301 -0
  342. data/vendor/kreuzberg/tests/pdf_text_merging.rs +475 -0
  343. data/vendor/kreuzberg/tests/pdfium_linking.rs +340 -0
  344. data/vendor/kreuzberg/tests/pipeline_integration.rs +1446 -1411
  345. data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +776 -771
  346. data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +577 -560
  347. data/vendor/kreuzberg/tests/plugin_system.rs +927 -921
  348. data/vendor/kreuzberg/tests/plugin_validator_test.rs +783 -783
  349. data/vendor/kreuzberg/tests/registry_integration_tests.rs +587 -586
  350. data/vendor/kreuzberg/tests/rst_extractor_tests.rs +694 -692
  351. data/vendor/kreuzberg/tests/rtf_extractor_tests.rs +775 -776
  352. data/vendor/kreuzberg/tests/security_validation.rs +416 -415
  353. data/vendor/kreuzberg/tests/stopwords_integration_test.rs +888 -888
  354. data/vendor/kreuzberg/tests/test_fastembed.rs +631 -609
  355. data/vendor/kreuzberg/tests/typst_behavioral_tests.rs +1260 -1259
  356. data/vendor/kreuzberg/tests/typst_extractor_tests.rs +648 -647
  357. data/vendor/kreuzberg/tests/xlsx_metadata_extraction_test.rs +87 -87
  358. data/vendor/kreuzberg-ffi/Cargo.toml +67 -0
  359. data/vendor/kreuzberg-ffi/README.md +851 -0
  360. data/vendor/kreuzberg-ffi/benches/result_view_benchmark.rs +227 -0
  361. data/vendor/kreuzberg-ffi/build.rs +168 -0
  362. data/vendor/kreuzberg-ffi/cbindgen.toml +37 -0
  363. data/vendor/kreuzberg-ffi/kreuzberg-ffi.pc.in +12 -0
  364. data/vendor/kreuzberg-ffi/kreuzberg.h +3012 -0
  365. data/vendor/kreuzberg-ffi/src/batch_streaming.rs +588 -0
  366. data/vendor/kreuzberg-ffi/src/config.rs +1341 -0
  367. data/vendor/kreuzberg-ffi/src/error.rs +901 -0
  368. data/vendor/kreuzberg-ffi/src/extraction.rs +555 -0
  369. data/vendor/kreuzberg-ffi/src/helpers.rs +879 -0
  370. data/vendor/kreuzberg-ffi/src/lib.rs +977 -0
  371. data/vendor/kreuzberg-ffi/src/memory.rs +493 -0
  372. data/vendor/kreuzberg-ffi/src/mime.rs +329 -0
  373. data/vendor/kreuzberg-ffi/src/panic_shield.rs +265 -0
  374. data/vendor/kreuzberg-ffi/src/plugins/document_extractor.rs +442 -0
  375. data/vendor/kreuzberg-ffi/src/plugins/mod.rs +14 -0
  376. data/vendor/kreuzberg-ffi/src/plugins/ocr_backend.rs +628 -0
  377. data/vendor/kreuzberg-ffi/src/plugins/post_processor.rs +438 -0
  378. data/vendor/kreuzberg-ffi/src/plugins/validator.rs +329 -0
  379. data/vendor/kreuzberg-ffi/src/result.rs +510 -0
  380. data/vendor/kreuzberg-ffi/src/result_pool.rs +639 -0
  381. data/vendor/kreuzberg-ffi/src/result_view.rs +773 -0
  382. data/vendor/kreuzberg-ffi/src/string_intern.rs +568 -0
  383. data/vendor/kreuzberg-ffi/src/types.rs +363 -0
  384. data/vendor/kreuzberg-ffi/src/util.rs +210 -0
  385. data/vendor/kreuzberg-ffi/src/validation.rs +848 -0
  386. data/vendor/kreuzberg-ffi/tests.disabled/README.md +48 -0
  387. data/vendor/kreuzberg-ffi/tests.disabled/config_loading_tests.rs +299 -0
  388. data/vendor/kreuzberg-ffi/tests.disabled/config_tests.rs +346 -0
  389. data/vendor/kreuzberg-ffi/tests.disabled/extractor_tests.rs +232 -0
  390. data/vendor/kreuzberg-ffi/tests.disabled/plugin_registration_tests.rs +470 -0
  391. data/vendor/kreuzberg-tesseract/.commitlintrc.json +13 -0
  392. data/vendor/kreuzberg-tesseract/.crate-ignore +2 -0
  393. data/vendor/kreuzberg-tesseract/Cargo.lock +2933 -0
  394. data/vendor/kreuzberg-tesseract/Cargo.toml +57 -0
  395. data/vendor/{rb-sys/LICENSE-MIT → kreuzberg-tesseract/LICENSE} +22 -21
  396. data/vendor/kreuzberg-tesseract/README.md +399 -0
  397. data/vendor/kreuzberg-tesseract/build.rs +1127 -0
  398. data/vendor/kreuzberg-tesseract/patches/README.md +71 -0
  399. data/vendor/kreuzberg-tesseract/patches/tesseract.diff +199 -0
  400. data/vendor/kreuzberg-tesseract/src/api.rs +1371 -0
  401. data/vendor/kreuzberg-tesseract/src/choice_iterator.rs +77 -0
  402. data/vendor/kreuzberg-tesseract/src/enums.rs +297 -0
  403. data/vendor/kreuzberg-tesseract/src/error.rs +81 -0
  404. data/vendor/kreuzberg-tesseract/src/lib.rs +145 -0
  405. data/vendor/kreuzberg-tesseract/src/monitor.rs +57 -0
  406. data/vendor/kreuzberg-tesseract/src/mutable_iterator.rs +197 -0
  407. data/vendor/kreuzberg-tesseract/src/page_iterator.rs +253 -0
  408. data/vendor/kreuzberg-tesseract/src/result_iterator.rs +286 -0
  409. data/vendor/kreuzberg-tesseract/src/result_renderer.rs +183 -0
  410. data/vendor/kreuzberg-tesseract/tests/integration_test.rs +211 -0
  411. metadata +196 -45
  412. data/vendor/kreuzberg/benches/otel_overhead.rs +0 -48
  413. data/vendor/kreuzberg/src/extractors/fictionbook.rs.backup2 +0 -738
  414. data/vendor/rb-sys/.cargo-ok +0 -1
  415. data/vendor/rb-sys/.cargo_vcs_info.json +0 -6
  416. data/vendor/rb-sys/Cargo.lock +0 -393
  417. data/vendor/rb-sys/Cargo.toml +0 -70
  418. data/vendor/rb-sys/Cargo.toml.orig +0 -57
  419. data/vendor/rb-sys/LICENSE-APACHE +0 -190
  420. data/vendor/rb-sys/bin/release.sh +0 -21
  421. data/vendor/rb-sys/build/features.rs +0 -108
  422. data/vendor/rb-sys/build/main.rs +0 -246
  423. data/vendor/rb-sys/build/stable_api_config.rs +0 -153
  424. data/vendor/rb-sys/build/version.rs +0 -48
  425. data/vendor/rb-sys/readme.md +0 -36
  426. data/vendor/rb-sys/src/bindings.rs +0 -21
  427. data/vendor/rb-sys/src/hidden.rs +0 -11
  428. data/vendor/rb-sys/src/lib.rs +0 -34
  429. data/vendor/rb-sys/src/macros.rs +0 -371
  430. data/vendor/rb-sys/src/memory.rs +0 -53
  431. data/vendor/rb-sys/src/ruby_abi_version.rs +0 -38
  432. data/vendor/rb-sys/src/special_consts.rs +0 -31
  433. data/vendor/rb-sys/src/stable_api/compiled.c +0 -179
  434. data/vendor/rb-sys/src/stable_api/compiled.rs +0 -257
  435. data/vendor/rb-sys/src/stable_api/ruby_2_6.rs +0 -316
  436. data/vendor/rb-sys/src/stable_api/ruby_2_7.rs +0 -316
  437. data/vendor/rb-sys/src/stable_api/ruby_3_0.rs +0 -324
  438. data/vendor/rb-sys/src/stable_api/ruby_3_1.rs +0 -317
  439. data/vendor/rb-sys/src/stable_api/ruby_3_2.rs +0 -315
  440. data/vendor/rb-sys/src/stable_api/ruby_3_3.rs +0 -326
  441. data/vendor/rb-sys/src/stable_api/ruby_3_4.rs +0 -327
  442. data/vendor/rb-sys/src/stable_api.rs +0 -261
  443. data/vendor/rb-sys/src/symbol.rs +0 -31
  444. data/vendor/rb-sys/src/tracking_allocator.rs +0 -332
  445. data/vendor/rb-sys/src/utils.rs +0 -89
  446. data/vendor/rb-sys/src/value_type.rs +0 -7
@@ -1,801 +1,801 @@
1
- [
2
- "!",
3
- ",",
4
- ".",
5
- ":",
6
- ";",
7
- "،",
8
- "؛",
9
- "؟",
10
- "آباد",
11
- "آره",
12
- "آری",
13
- "آمد",
14
- "آمده",
15
- "آن",
16
- "آنان",
17
- "آنجا",
18
- "آنطور",
19
- "آنقدر",
20
- "آنكه",
21
- "آنها",
22
- "آنچه",
23
- "آنکه",
24
- "آورد",
25
- "آورده",
26
- "آيد",
27
- "آی",
28
- "آیا",
29
- "آیند",
30
- "اتفاقا",
31
- "اثرِ",
32
- "احتراما",
33
- "احتمالا",
34
- "اخیر",
35
- "اری",
36
- "از",
37
- "ازجمله",
38
- "اساسا",
39
- "است",
40
- "استفاد",
41
- "استفاده",
42
- "اش",
43
- "اشکارا",
44
- "اصلا",
45
- "اصولا",
46
- "اعلام",
47
- "اغلب",
48
- "اكنون",
49
- "الان",
50
- "البته",
51
- "البتّه",
52
- "ام",
53
- "اما",
54
- "امروز",
55
- "امروزه",
56
- "امسال",
57
- "امشب",
58
- "امور",
59
- "ان",
60
- "انجام",
61
- "اند",
62
- "انشاالله",
63
- "انصافا",
64
- "انطور",
65
- "انقدر",
66
- "انها",
67
- "انچنان",
68
- "انکه",
69
- "انگار",
70
- "او",
71
- "اول",
72
- "اولا",
73
- "اي",
74
- "ايشان",
75
- "ايم",
76
- "اين",
77
- "اينكه",
78
- "اکثرا",
79
- "اکنون",
80
- "اگر",
81
- "ای",
82
- "ایا",
83
- "اید",
84
- "ایشان",
85
- "ایم",
86
- "این",
87
- "اینجا",
88
- "ایند",
89
- "اینطور",
90
- "اینقدر",
91
- "اینها",
92
- "اینچنین",
93
- "اینک",
94
- "اینکه",
95
- "اینگونه",
96
- "با",
97
- "بار",
98
- "بارة",
99
- "باره",
100
- "بارها",
101
- "باز",
102
- "بازهم",
103
- "باش",
104
- "باشد",
105
- "باشم",
106
- "باشند",
107
- "باشيم",
108
- "باشی",
109
- "باشید",
110
- "باشیم",
111
- "بالا",
112
- "بالاخره",
113
- "بالایِ",
114
- "بالطبع",
115
- "بايد",
116
- "باید",
117
- "بتوان",
118
- "بتواند",
119
- "بتوانی",
120
- "بتوانیم",
121
- "بخش",
122
- "بخشی",
123
- "بخواه",
124
- "بخواهد",
125
- "بخواهم",
126
- "بخواهند",
127
- "بخواهی",
128
- "بخواهید",
129
- "بخواهیم",
130
- "بد",
131
- "بدون",
132
- "بر",
133
- "برابر",
134
- "برابرِ",
135
- "براحتی",
136
- "براساس",
137
- "براستی",
138
- "براي",
139
- "برای",
140
- "برایِ",
141
- "برخوردار",
142
- "برخي",
143
- "برخی",
144
- "برداري",
145
- "برعکس",
146
- "بروز",
147
- "بزرگ",
148
- "بزودی",
149
- "بسا",
150
- "بسيار",
151
- "بسياري",
152
- "بسیار",
153
- "بسیاری",
154
- "بطور",
155
- "بعد",
156
- "بعدا",
157
- "بعدها",
158
- "بعری",
159
- "بعضا",
160
- "بعضي",
161
- "بلافاصله",
162
- "بلكه",
163
- "بله",
164
- "بلکه",
165
- "بلی",
166
- "بنابراين",
167
- "بنابراین",
168
- "بندي",
169
- "به",
170
- "بهتر",
171
- "بهترين",
172
- "بود",
173
- "بودم",
174
- "بودن",
175
- "بودند",
176
- "بوده",
177
- "بودی",
178
- "بودید",
179
- "بودیم",
180
- "بویژه",
181
- "بي",
182
- "بيست",
183
- "بيش",
184
- "بيشتر",
185
- "بيشتري",
186
- "بين",
187
- "بکن",
188
- "بکند",
189
- "بکنم",
190
- "بکنند",
191
- "بکنی",
192
- "بکنید",
193
- "بکنیم",
194
- "بگو",
195
- "بگوید",
196
- "بگویم",
197
- "بگویند",
198
- "بگویی",
199
- "بگویید",
200
- "بگوییم",
201
- "بگیر",
202
- "بگیرد",
203
- "بگیرم",
204
- "بگیرند",
205
- "بگیری",
206
- "بگیرید",
207
- "بگیریم",
208
- "بی",
209
- "بیا",
210
- "بیاب",
211
- "بیابد",
212
- "بیابم",
213
- "بیابند",
214
- "بیابی",
215
- "بیابید",
216
- "بیابیم",
217
- "بیاور",
218
- "بیاورد",
219
- "بیاورم",
220
- "بیاورند",
221
- "بیاوری",
222
- "بیاورید",
223
- "بیاوریم",
224
- "بیاید",
225
- "بیایم",
226
- "بیایند",
227
- "بیایی",
228
- "بیایید",
229
- "بیاییم",
230
- "بیرون",
231
- "بیرونِ",
232
- "بیش",
233
- "بیشتر",
234
- "بیشتری",
235
- "بین",
236
- "ت",
237
- "تا",
238
- "تازه",
239
- "تاكنون",
240
- "تان",
241
- "تاکنون",
242
- "تحت",
243
- "تر",
244
- "تر براساس",
245
- "ترين",
246
- "تقریبا",
247
- "تلویحا",
248
- "تمام",
249
- "تماما",
250
- "تمامي",
251
- "تنها",
252
- "تو",
253
- "تواند",
254
- "توانست",
255
- "توانستم",
256
- "توانستن",
257
- "توانستند",
258
- "توانسته",
259
- "توانستی",
260
- "توانستیم",
261
- "توانم",
262
- "توانند",
263
- "توانی",
264
- "توانید",
265
- "توانیم",
266
- "توسط",
267
- "تولِ",
268
- "تویِ",
269
- "ثانیا",
270
- "جا",
271
- "جاي",
272
- "جايي",
273
- "جای",
274
- "جدا",
275
- "جديد",
276
- "جدید",
277
- "جريان",
278
- "جریان",
279
- "جز",
280
- "جلوگيري",
281
- "جلویِ",
282
- "جمعا",
283
- "جناح",
284
- "جهت",
285
- "حاضر",
286
- "حال",
287
- "حالا",
288
- "حتما",
289
- "حتي",
290
- "حتی",
291
- "حداکثر",
292
- "حدودا",
293
- "حدودِ",
294
- "حق",
295
- "خارجِ",
296
- "خب",
297
- "خدمات",
298
- "خصوصا",
299
- "خلاصه",
300
- "خواست",
301
- "خواستم",
302
- "خواستن",
303
- "خواستند",
304
- "خواسته",
305
- "خواستی",
306
- "خواستید",
307
- "خواستیم",
308
- "خواهد",
309
- "خواهم",
310
- "خواهند",
311
- "خواهيم",
312
- "خواهی",
313
- "خواهید",
314
- "خواهیم",
315
- "خوب",
316
- "خود",
317
- "خودت",
318
- "خودتان",
319
- "خودش",
320
- "خودشان",
321
- "خودم",
322
- "خودمان",
323
- "خوشبختانه",
324
- "خويش",
325
- "خویش",
326
- "خویشتن",
327
- "خیاه",
328
- "خیر",
329
- "خیلی",
330
- "داد",
331
- "دادم",
332
- "دادن",
333
- "دادند",
334
- "داده",
335
- "دادی",
336
- "دادید",
337
- "دادیم",
338
- "دار",
339
- "دارد",
340
- "دارم",
341
- "دارند",
342
- "داريم",
343
- "داری",
344
- "دارید",
345
- "داریم",
346
- "داشت",
347
- "داشتم",
348
- "داشتن",
349
- "داشتند",
350
- "داشته",
351
- "داشتی",
352
- "داشتید",
353
- "داشتیم",
354
- "دانست",
355
- "دانند",
356
- "دایم",
357
- "دایما",
358
- "در",
359
- "درباره",
360
- "درمجموع",
361
- "درون",
362
- "دریغ",
363
- "دقیقا",
364
- "دنبالِ",
365
- "ده",
366
- "دهد",
367
- "دهم",
368
- "دهند",
369
- "دهی",
370
- "دهید",
371
- "دهیم",
372
- "دو",
373
- "دوباره",
374
- "دوم",
375
- "ديده",
376
- "ديروز",
377
- "ديگر",
378
- "ديگران",
379
- "ديگري",
380
- "دیر",
381
- "دیروز",
382
- "دیگر",
383
- "دیگران",
384
- "دیگری",
385
- "را",
386
- "راحت",
387
- "راسا",
388
- "راستی",
389
- "راه",
390
- "رسما",
391
- "رسید",
392
- "رفت",
393
- "رفته",
394
- "رو",
395
- "روب",
396
- "روز",
397
- "روزانه",
398
- "روزهاي",
399
- "روي",
400
- "روی",
401
- "رویِ",
402
- "ريزي",
403
- "زمان",
404
- "زمانی",
405
- "زمینه",
406
- "زود",
407
- "زياد",
408
- "زير",
409
- "زيرا",
410
- "زیر",
411
- "زیرِ",
412
- "سابق",
413
- "ساخته",
414
- "سازي",
415
- "سالانه",
416
- "سالیانه",
417
- "سایر",
418
- "سراسر",
419
- "سرانجام",
420
- "سریعا",
421
- "سریِ",
422
- "سعي",
423
- "سمتِ",
424
- "سوم",
425
- "سوي",
426
- "سوی",
427
- "سویِ",
428
- "سپس",
429
- "شان",
430
- "شايد",
431
- "شاید",
432
- "شخصا",
433
- "شد",
434
- "شدم",
435
- "شدن",
436
- "شدند",
437
- "شده",
438
- "شدی",
439
- "شدید",
440
- "شدیدا",
441
- "شدیم",
442
- "شش",
443
- "شش نداشته",
444
- "شما",
445
- "شناسي",
446
- "شود",
447
- "شوم",
448
- "شوند",
449
- "شونده",
450
- "شوی",
451
- "شوید",
452
- "شویم",
453
- "صرفا",
454
- "صورت",
455
- "ضدِّ",
456
- "ضدِّ",
457
- "ضمن",
458
- "طبعا",
459
- "طبقِ",
460
- "طبیعتا",
461
- "طرف",
462
- "طريق",
463
- "طریق",
464
- "طور",
465
- "طي",
466
- "طی",
467
- "ظاهرا",
468
- "عدم",
469
- "عقبِ",
470
- "علّتِ",
471
- "علیه",
472
- "عمدا",
473
- "عمدتا",
474
- "عمل",
475
- "عملا",
476
- "عنوان",
477
- "عنوانِ",
478
- "غالبا",
479
- "غير",
480
- "غیر",
481
- "فردا",
482
- "فعلا",
483
- "فقط",
484
- "فكر",
485
- "فوق",
486
- "قابل",
487
- "قبل",
488
- "قبلا",
489
- "قدری",
490
- "قصدِ",
491
- "قطعا",
492
- "كرد",
493
- "كردم",
494
- "كردن",
495
- "كردند",
496
- "كرده",
497
- "كسي",
498
- "كل",
499
- "كمتر",
500
- "كند",
501
- "كنم",
502
- "كنند",
503
- "كنيد",
504
- "كنيم",
505
- "كه",
506
- "لااقل",
507
- "لطفا",
508
- "لطفاً",
509
- "ما",
510
- "مان",
511
- "مانند",
512
- "مانندِ",
513
- "مبادا",
514
- "متاسفانه",
515
- "متعاقبا",
516
- "مثل",
517
- "مثلا",
518
- "مثلِ",
519
- "مجانی",
520
- "مجددا",
521
- "مجموعا",
522
- "مختلف",
523
- "مدام",
524
- "مدت",
525
- "مدّتی",
526
- "مردم",
527
- "مرسی",
528
- "مستقیما",
529
- "مسلما",
530
- "مطمینا",
531
- "معمولا",
532
- "مقابل",
533
- "ممکن",
534
- "من",
535
- "موارد",
536
- "مورد",
537
- "موقتا",
538
- "مي",
539
- "ميليارد",
540
- "ميليون",
541
- "مگر",
542
- "می",
543
- "می شود",
544
- "میان",
545
- "می‌رسد",
546
- "می‌رود",
547
- "می‌شود",
548
- "می‌کنیم",
549
- "ناشي",
550
- "نام",
551
- "ناگاه",
552
- "ناگهان",
553
- "ناگهانی",
554
- "نبايد",
555
- "نباید",
556
- "نبود",
557
- "نخست",
558
- "نخستين",
559
- "نخواهد",
560
- "نخواهم",
561
- "نخواهند",
562
- "نخواهی",
563
- "نخواهید",
564
- "نخواهیم",
565
- "ندارد",
566
- "ندارم",
567
- "ندارند",
568
- "نداری",
569
- "ندارید",
570
- "نداریم",
571
- "نداشت",
572
- "نداشتم",
573
- "نداشتند",
574
- "نداشته",
575
- "نداشتی",
576
- "نداشتید",
577
- "نداشتیم",
578
- "نزديك",
579
- "نزدِ",
580
- "نزدیکِ",
581
- "نسبتا",
582
- "نشان",
583
- "نشده",
584
- "نظير",
585
- "نظیر",
586
- "نكرده",
587
- "نمايد",
588
- "نمي",
589
- "نمی",
590
- "نمی‌شود",
591
- "نه",
592
- "نهایتا",
593
- "نوع",
594
- "نوعي",
595
- "نوعی",
596
- "نيز",
597
- "نيست",
598
- "نگاه",
599
- "نیز",
600
- "نیست",
601
- "ها",
602
- "هاي",
603
- "هايي",
604
- "های",
605
- "هایی",
606
- "هبچ",
607
- "هر",
608
- "هرچه",
609
- "هرگز",
610
- "هزار",
611
- "هست",
612
- "هستم",
613
- "هستند",
614
- "هستيم",
615
- "هستی",
616
- "هستید",
617
- "هستیم",
618
- "هفت",
619
- "هم",
620
- "همان",
621
- "همه",
622
- "همواره",
623
- "همين",
624
- "همچنان",
625
- "همچنين",
626
- "همچنین",
627
- "همچون",
628
- "همیشه",
629
- "همین",
630
- "هنوز",
631
- "هنگام",
632
- "هنگامِ",
633
- "هنگامی",
634
- "هيچ",
635
- "هیچ",
636
- "هیچگاه",
637
- "و",
638
- "واقعا",
639
- "واقعی",
640
- "وجود",
641
- "وسطِ",
642
- "وضع",
643
- "وقتي",
644
- "وقتی",
645
- "وقتیکه",
646
- "ولی",
647
- "وي",
648
- "وگو",
649
- "وی",
650
- "ویژه",
651
- "يا",
652
- "يابد",
653
- "يك",
654
- "يكديگر",
655
- "يكي",
656
- "ّه",
657
- "٪",
658
- "پارسال",
659
- "پاعینِ",
660
- "پس",
661
- "پنج",
662
- "پيش",
663
- "پیدا",
664
- "پیش",
665
- "پیشاپیش",
666
- "پیشتر",
667
- "پیشِ",
668
- "چرا",
669
- "چطور",
670
- "چقدر",
671
- "چنان",
672
- "چنانچه",
673
- "چنانکه",
674
- "چند",
675
- "چندین",
676
- "چنين",
677
- "چنین",
678
- "چه",
679
- "چهار",
680
- "چو",
681
- "چون",
682
- "چيزي",
683
- "چگونه",
684
- "چیز",
685
- "چیزی",
686
- "چیست",
687
- "کاش",
688
- "کامل",
689
- "کاملا",
690
- "کتبا",
691
- "کجا",
692
- "کجاست",
693
- "کدام",
694
- "کرد",
695
- "کردم",
696
- "کردن",
697
- "کردند",
698
- "کرده",
699
- "کردی",
700
- "کردید",
701
- "کردیم",
702
- "کس",
703
- "کسانی",
704
- "کسی",
705
- "کل",
706
- "کلا",
707
- "کم",
708
- "کماکان",
709
- "کمتر",
710
- "کمتری",
711
- "کمی",
712
- "کن",
713
- "کنار",
714
- "کنارِ",
715
- "کند",
716
- "کنم",
717
- "کنند",
718
- "کننده",
719
- "کنون",
720
- "کنونی",
721
- "کنی",
722
- "کنید",
723
- "کنیم",
724
- "که",
725
- "کو",
726
- "کَی",
727
- "کی",
728
- "گاه",
729
- "گاهی",
730
- "گذاري",
731
- "گذاشته",
732
- "گذشته",
733
- "گردد",
734
- "گرفت",
735
- "گرفتم",
736
- "گرفتن",
737
- "گرفتند",
738
- "گرفته",
739
- "گرفتی",
740
- "گرفتید",
741
- "گرفتیم",
742
- "گروهي",
743
- "گفت",
744
- "گفتم",
745
- "گفتن",
746
- "گفتند",
747
- "گفته",
748
- "گفتی",
749
- "گفتید",
750
- "گفتیم",
751
- "گه",
752
- "گهگاه",
753
- "گو",
754
- "گويد",
755
- "گويند",
756
- "گویا",
757
- "گوید",
758
- "گویم",
759
- "گویند",
760
- "گویی",
761
- "گویید",
762
- "گوییم",
763
- "گيرد",
764
- "گيري",
765
- "گیرد",
766
- "گیرم",
767
- "گیرند",
768
- "گیری",
769
- "گیرید",
770
- "گیریم",
771
- "ی",
772
- "یا",
773
- "یابد",
774
- "یابم",
775
- "یابند",
776
- "یابی",
777
- "یابید",
778
- "یابیم",
779
- "یافت",
780
- "یافتم",
781
- "یافتن",
782
- "یافته",
783
- "یافتی",
784
- "یافتید",
785
- "یافتیم",
786
- "یعنی",
787
- "یقینا",
788
- "یه",
789
- "یک",
790
- "یکی",
791
- "۰",
792
- "۱",
793
- "۲",
794
- "۳",
795
- "۴",
796
- "۵",
797
- "۶",
798
- "۷",
799
- "۸",
800
- "۹"
801
- ]
1
+ [
2
+ "!",
3
+ ",",
4
+ ".",
5
+ ":",
6
+ ";",
7
+ "،",
8
+ "؛",
9
+ "؟",
10
+ "آباد",
11
+ "آره",
12
+ "آری",
13
+ "آمد",
14
+ "آمده",
15
+ "آن",
16
+ "آنان",
17
+ "آنجا",
18
+ "آنطور",
19
+ "آنقدر",
20
+ "آنكه",
21
+ "آنها",
22
+ "آنچه",
23
+ "آنکه",
24
+ "آورد",
25
+ "آورده",
26
+ "آيد",
27
+ "آی",
28
+ "آیا",
29
+ "آیند",
30
+ "اتفاقا",
31
+ "اثرِ",
32
+ "احتراما",
33
+ "احتمالا",
34
+ "اخیر",
35
+ "اری",
36
+ "از",
37
+ "ازجمله",
38
+ "اساسا",
39
+ "است",
40
+ "استفاد",
41
+ "استفاده",
42
+ "اش",
43
+ "اشکارا",
44
+ "اصلا",
45
+ "اصولا",
46
+ "اعلام",
47
+ "اغلب",
48
+ "اكنون",
49
+ "الان",
50
+ "البته",
51
+ "البتّه",
52
+ "ام",
53
+ "اما",
54
+ "امروز",
55
+ "امروزه",
56
+ "امسال",
57
+ "امشب",
58
+ "امور",
59
+ "ان",
60
+ "انجام",
61
+ "اند",
62
+ "انشاالله",
63
+ "انصافا",
64
+ "انطور",
65
+ "انقدر",
66
+ "انها",
67
+ "انچنان",
68
+ "انکه",
69
+ "انگار",
70
+ "او",
71
+ "اول",
72
+ "اولا",
73
+ "اي",
74
+ "ايشان",
75
+ "ايم",
76
+ "اين",
77
+ "اينكه",
78
+ "اکثرا",
79
+ "اکنون",
80
+ "اگر",
81
+ "ای",
82
+ "ایا",
83
+ "اید",
84
+ "ایشان",
85
+ "ایم",
86
+ "این",
87
+ "اینجا",
88
+ "ایند",
89
+ "اینطور",
90
+ "اینقدر",
91
+ "اینها",
92
+ "اینچنین",
93
+ "اینک",
94
+ "اینکه",
95
+ "اینگونه",
96
+ "با",
97
+ "بار",
98
+ "بارة",
99
+ "باره",
100
+ "بارها",
101
+ "باز",
102
+ "بازهم",
103
+ "باش",
104
+ "باشد",
105
+ "باشم",
106
+ "باشند",
107
+ "باشيم",
108
+ "باشی",
109
+ "باشید",
110
+ "باشیم",
111
+ "بالا",
112
+ "بالاخره",
113
+ "بالایِ",
114
+ "بالطبع",
115
+ "بايد",
116
+ "باید",
117
+ "بتوان",
118
+ "بتواند",
119
+ "بتوانی",
120
+ "بتوانیم",
121
+ "بخش",
122
+ "بخشی",
123
+ "بخواه",
124
+ "بخواهد",
125
+ "بخواهم",
126
+ "بخواهند",
127
+ "بخواهی",
128
+ "بخواهید",
129
+ "بخواهیم",
130
+ "بد",
131
+ "بدون",
132
+ "بر",
133
+ "برابر",
134
+ "برابرِ",
135
+ "براحتی",
136
+ "براساس",
137
+ "براستی",
138
+ "براي",
139
+ "برای",
140
+ "برایِ",
141
+ "برخوردار",
142
+ "برخي",
143
+ "برخی",
144
+ "برداري",
145
+ "برعکس",
146
+ "بروز",
147
+ "بزرگ",
148
+ "بزودی",
149
+ "بسا",
150
+ "بسيار",
151
+ "بسياري",
152
+ "بسیار",
153
+ "بسیاری",
154
+ "بطور",
155
+ "بعد",
156
+ "بعدا",
157
+ "بعدها",
158
+ "بعری",
159
+ "بعضا",
160
+ "بعضي",
161
+ "بلافاصله",
162
+ "بلكه",
163
+ "بله",
164
+ "بلکه",
165
+ "بلی",
166
+ "بنابراين",
167
+ "بنابراین",
168
+ "بندي",
169
+ "به",
170
+ "بهتر",
171
+ "بهترين",
172
+ "بود",
173
+ "بودم",
174
+ "بودن",
175
+ "بودند",
176
+ "بوده",
177
+ "بودی",
178
+ "بودید",
179
+ "بودیم",
180
+ "بویژه",
181
+ "بي",
182
+ "بيست",
183
+ "بيش",
184
+ "بيشتر",
185
+ "بيشتري",
186
+ "بين",
187
+ "بکن",
188
+ "بکند",
189
+ "بکنم",
190
+ "بکنند",
191
+ "بکنی",
192
+ "بکنید",
193
+ "بکنیم",
194
+ "بگو",
195
+ "بگوید",
196
+ "بگویم",
197
+ "بگویند",
198
+ "بگویی",
199
+ "بگویید",
200
+ "بگوییم",
201
+ "بگیر",
202
+ "بگیرد",
203
+ "بگیرم",
204
+ "بگیرند",
205
+ "بگیری",
206
+ "بگیرید",
207
+ "بگیریم",
208
+ "بی",
209
+ "بیا",
210
+ "بیاب",
211
+ "بیابد",
212
+ "بیابم",
213
+ "بیابند",
214
+ "بیابی",
215
+ "بیابید",
216
+ "بیابیم",
217
+ "بیاور",
218
+ "بیاورد",
219
+ "بیاورم",
220
+ "بیاورند",
221
+ "بیاوری",
222
+ "بیاورید",
223
+ "بیاوریم",
224
+ "بیاید",
225
+ "بیایم",
226
+ "بیایند",
227
+ "بیایی",
228
+ "بیایید",
229
+ "بیاییم",
230
+ "بیرون",
231
+ "بیرونِ",
232
+ "بیش",
233
+ "بیشتر",
234
+ "بیشتری",
235
+ "بین",
236
+ "ت",
237
+ "تا",
238
+ "تازه",
239
+ "تاكنون",
240
+ "تان",
241
+ "تاکنون",
242
+ "تحت",
243
+ "تر",
244
+ "تر براساس",
245
+ "ترين",
246
+ "تقریبا",
247
+ "تلویحا",
248
+ "تمام",
249
+ "تماما",
250
+ "تمامي",
251
+ "تنها",
252
+ "تو",
253
+ "تواند",
254
+ "توانست",
255
+ "توانستم",
256
+ "توانستن",
257
+ "توانستند",
258
+ "توانسته",
259
+ "توانستی",
260
+ "توانستیم",
261
+ "توانم",
262
+ "توانند",
263
+ "توانی",
264
+ "توانید",
265
+ "توانیم",
266
+ "توسط",
267
+ "تولِ",
268
+ "تویِ",
269
+ "ثانیا",
270
+ "جا",
271
+ "جاي",
272
+ "جايي",
273
+ "جای",
274
+ "جدا",
275
+ "جديد",
276
+ "جدید",
277
+ "جريان",
278
+ "جریان",
279
+ "جز",
280
+ "جلوگيري",
281
+ "جلویِ",
282
+ "جمعا",
283
+ "جناح",
284
+ "جهت",
285
+ "حاضر",
286
+ "حال",
287
+ "حالا",
288
+ "حتما",
289
+ "حتي",
290
+ "حتی",
291
+ "حداکثر",
292
+ "حدودا",
293
+ "حدودِ",
294
+ "حق",
295
+ "خارجِ",
296
+ "خب",
297
+ "خدمات",
298
+ "خصوصا",
299
+ "خلاصه",
300
+ "خواست",
301
+ "خواستم",
302
+ "خواستن",
303
+ "خواستند",
304
+ "خواسته",
305
+ "خواستی",
306
+ "خواستید",
307
+ "خواستیم",
308
+ "خواهد",
309
+ "خواهم",
310
+ "خواهند",
311
+ "خواهيم",
312
+ "خواهی",
313
+ "خواهید",
314
+ "خواهیم",
315
+ "خوب",
316
+ "خود",
317
+ "خودت",
318
+ "خودتان",
319
+ "خودش",
320
+ "خودشان",
321
+ "خودم",
322
+ "خودمان",
323
+ "خوشبختانه",
324
+ "خويش",
325
+ "خویش",
326
+ "خویشتن",
327
+ "خیاه",
328
+ "خیر",
329
+ "خیلی",
330
+ "داد",
331
+ "دادم",
332
+ "دادن",
333
+ "دادند",
334
+ "داده",
335
+ "دادی",
336
+ "دادید",
337
+ "دادیم",
338
+ "دار",
339
+ "دارد",
340
+ "دارم",
341
+ "دارند",
342
+ "داريم",
343
+ "داری",
344
+ "دارید",
345
+ "داریم",
346
+ "داشت",
347
+ "داشتم",
348
+ "داشتن",
349
+ "داشتند",
350
+ "داشته",
351
+ "داشتی",
352
+ "داشتید",
353
+ "داشتیم",
354
+ "دانست",
355
+ "دانند",
356
+ "دایم",
357
+ "دایما",
358
+ "در",
359
+ "درباره",
360
+ "درمجموع",
361
+ "درون",
362
+ "دریغ",
363
+ "دقیقا",
364
+ "دنبالِ",
365
+ "ده",
366
+ "دهد",
367
+ "دهم",
368
+ "دهند",
369
+ "دهی",
370
+ "دهید",
371
+ "دهیم",
372
+ "دو",
373
+ "دوباره",
374
+ "دوم",
375
+ "ديده",
376
+ "ديروز",
377
+ "ديگر",
378
+ "ديگران",
379
+ "ديگري",
380
+ "دیر",
381
+ "دیروز",
382
+ "دیگر",
383
+ "دیگران",
384
+ "دیگری",
385
+ "را",
386
+ "راحت",
387
+ "راسا",
388
+ "راستی",
389
+ "راه",
390
+ "رسما",
391
+ "رسید",
392
+ "رفت",
393
+ "رفته",
394
+ "رو",
395
+ "روب",
396
+ "روز",
397
+ "روزانه",
398
+ "روزهاي",
399
+ "روي",
400
+ "روی",
401
+ "رویِ",
402
+ "ريزي",
403
+ "زمان",
404
+ "زمانی",
405
+ "زمینه",
406
+ "زود",
407
+ "زياد",
408
+ "زير",
409
+ "زيرا",
410
+ "زیر",
411
+ "زیرِ",
412
+ "سابق",
413
+ "ساخته",
414
+ "سازي",
415
+ "سالانه",
416
+ "سالیانه",
417
+ "سایر",
418
+ "سراسر",
419
+ "سرانجام",
420
+ "سریعا",
421
+ "سریِ",
422
+ "سعي",
423
+ "سمتِ",
424
+ "سوم",
425
+ "سوي",
426
+ "سوی",
427
+ "سویِ",
428
+ "سپس",
429
+ "شان",
430
+ "شايد",
431
+ "شاید",
432
+ "شخصا",
433
+ "شد",
434
+ "شدم",
435
+ "شدن",
436
+ "شدند",
437
+ "شده",
438
+ "شدی",
439
+ "شدید",
440
+ "شدیدا",
441
+ "شدیم",
442
+ "شش",
443
+ "شش نداشته",
444
+ "شما",
445
+ "شناسي",
446
+ "شود",
447
+ "شوم",
448
+ "شوند",
449
+ "شونده",
450
+ "شوی",
451
+ "شوید",
452
+ "شویم",
453
+ "صرفا",
454
+ "صورت",
455
+ "ضدِّ",
456
+ "ضدِّ",
457
+ "ضمن",
458
+ "طبعا",
459
+ "طبقِ",
460
+ "طبیعتا",
461
+ "طرف",
462
+ "طريق",
463
+ "طریق",
464
+ "طور",
465
+ "طي",
466
+ "طی",
467
+ "ظاهرا",
468
+ "عدم",
469
+ "عقبِ",
470
+ "علّتِ",
471
+ "علیه",
472
+ "عمدا",
473
+ "عمدتا",
474
+ "عمل",
475
+ "عملا",
476
+ "عنوان",
477
+ "عنوانِ",
478
+ "غالبا",
479
+ "غير",
480
+ "غیر",
481
+ "فردا",
482
+ "فعلا",
483
+ "فقط",
484
+ "فكر",
485
+ "فوق",
486
+ "قابل",
487
+ "قبل",
488
+ "قبلا",
489
+ "قدری",
490
+ "قصدِ",
491
+ "قطعا",
492
+ "كرد",
493
+ "كردم",
494
+ "كردن",
495
+ "كردند",
496
+ "كرده",
497
+ "كسي",
498
+ "كل",
499
+ "كمتر",
500
+ "كند",
501
+ "كنم",
502
+ "كنند",
503
+ "كنيد",
504
+ "كنيم",
505
+ "كه",
506
+ "لااقل",
507
+ "لطفا",
508
+ "لطفاً",
509
+ "ما",
510
+ "مان",
511
+ "مانند",
512
+ "مانندِ",
513
+ "مبادا",
514
+ "متاسفانه",
515
+ "متعاقبا",
516
+ "مثل",
517
+ "مثلا",
518
+ "مثلِ",
519
+ "مجانی",
520
+ "مجددا",
521
+ "مجموعا",
522
+ "مختلف",
523
+ "مدام",
524
+ "مدت",
525
+ "مدّتی",
526
+ "مردم",
527
+ "مرسی",
528
+ "مستقیما",
529
+ "مسلما",
530
+ "مطمینا",
531
+ "معمولا",
532
+ "مقابل",
533
+ "ممکن",
534
+ "من",
535
+ "موارد",
536
+ "مورد",
537
+ "موقتا",
538
+ "مي",
539
+ "ميليارد",
540
+ "ميليون",
541
+ "مگر",
542
+ "می",
543
+ "می شود",
544
+ "میان",
545
+ "می‌رسد",
546
+ "می‌رود",
547
+ "می‌شود",
548
+ "می‌کنیم",
549
+ "ناشي",
550
+ "نام",
551
+ "ناگاه",
552
+ "ناگهان",
553
+ "ناگهانی",
554
+ "نبايد",
555
+ "نباید",
556
+ "نبود",
557
+ "نخست",
558
+ "نخستين",
559
+ "نخواهد",
560
+ "نخواهم",
561
+ "نخواهند",
562
+ "نخواهی",
563
+ "نخواهید",
564
+ "نخواهیم",
565
+ "ندارد",
566
+ "ندارم",
567
+ "ندارند",
568
+ "نداری",
569
+ "ندارید",
570
+ "نداریم",
571
+ "نداشت",
572
+ "نداشتم",
573
+ "نداشتند",
574
+ "نداشته",
575
+ "نداشتی",
576
+ "نداشتید",
577
+ "نداشتیم",
578
+ "نزديك",
579
+ "نزدِ",
580
+ "نزدیکِ",
581
+ "نسبتا",
582
+ "نشان",
583
+ "نشده",
584
+ "نظير",
585
+ "نظیر",
586
+ "نكرده",
587
+ "نمايد",
588
+ "نمي",
589
+ "نمی",
590
+ "نمی‌شود",
591
+ "نه",
592
+ "نهایتا",
593
+ "نوع",
594
+ "نوعي",
595
+ "نوعی",
596
+ "نيز",
597
+ "نيست",
598
+ "نگاه",
599
+ "نیز",
600
+ "نیست",
601
+ "ها",
602
+ "هاي",
603
+ "هايي",
604
+ "های",
605
+ "هایی",
606
+ "هبچ",
607
+ "هر",
608
+ "هرچه",
609
+ "هرگز",
610
+ "هزار",
611
+ "هست",
612
+ "هستم",
613
+ "هستند",
614
+ "هستيم",
615
+ "هستی",
616
+ "هستید",
617
+ "هستیم",
618
+ "هفت",
619
+ "هم",
620
+ "همان",
621
+ "همه",
622
+ "همواره",
623
+ "همين",
624
+ "همچنان",
625
+ "همچنين",
626
+ "همچنین",
627
+ "همچون",
628
+ "همیشه",
629
+ "همین",
630
+ "هنوز",
631
+ "هنگام",
632
+ "هنگامِ",
633
+ "هنگامی",
634
+ "هيچ",
635
+ "هیچ",
636
+ "هیچگاه",
637
+ "و",
638
+ "واقعا",
639
+ "واقعی",
640
+ "وجود",
641
+ "وسطِ",
642
+ "وضع",
643
+ "وقتي",
644
+ "وقتی",
645
+ "وقتیکه",
646
+ "ولی",
647
+ "وي",
648
+ "وگو",
649
+ "وی",
650
+ "ویژه",
651
+ "يا",
652
+ "يابد",
653
+ "يك",
654
+ "يكديگر",
655
+ "يكي",
656
+ "ّه",
657
+ "٪",
658
+ "پارسال",
659
+ "پاعینِ",
660
+ "پس",
661
+ "پنج",
662
+ "پيش",
663
+ "پیدا",
664
+ "پیش",
665
+ "پیشاپیش",
666
+ "پیشتر",
667
+ "پیشِ",
668
+ "چرا",
669
+ "چطور",
670
+ "چقدر",
671
+ "چنان",
672
+ "چنانچه",
673
+ "چنانکه",
674
+ "چند",
675
+ "چندین",
676
+ "چنين",
677
+ "چنین",
678
+ "چه",
679
+ "چهار",
680
+ "چو",
681
+ "چون",
682
+ "چيزي",
683
+ "چگونه",
684
+ "چیز",
685
+ "چیزی",
686
+ "چیست",
687
+ "کاش",
688
+ "کامل",
689
+ "کاملا",
690
+ "کتبا",
691
+ "کجا",
692
+ "کجاست",
693
+ "کدام",
694
+ "کرد",
695
+ "کردم",
696
+ "کردن",
697
+ "کردند",
698
+ "کرده",
699
+ "کردی",
700
+ "کردید",
701
+ "کردیم",
702
+ "کس",
703
+ "کسانی",
704
+ "کسی",
705
+ "کل",
706
+ "کلا",
707
+ "کم",
708
+ "کماکان",
709
+ "کمتر",
710
+ "کمتری",
711
+ "کمی",
712
+ "کن",
713
+ "کنار",
714
+ "کنارِ",
715
+ "کند",
716
+ "کنم",
717
+ "کنند",
718
+ "کننده",
719
+ "کنون",
720
+ "کنونی",
721
+ "کنی",
722
+ "کنید",
723
+ "کنیم",
724
+ "که",
725
+ "کو",
726
+ "کَی",
727
+ "کی",
728
+ "گاه",
729
+ "گاهی",
730
+ "گذاري",
731
+ "گذاشته",
732
+ "گذشته",
733
+ "گردد",
734
+ "گرفت",
735
+ "گرفتم",
736
+ "گرفتن",
737
+ "گرفتند",
738
+ "گرفته",
739
+ "گرفتی",
740
+ "گرفتید",
741
+ "گرفتیم",
742
+ "گروهي",
743
+ "گفت",
744
+ "گفتم",
745
+ "گفتن",
746
+ "گفتند",
747
+ "گفته",
748
+ "گفتی",
749
+ "گفتید",
750
+ "گفتیم",
751
+ "گه",
752
+ "گهگاه",
753
+ "گو",
754
+ "گويد",
755
+ "گويند",
756
+ "گویا",
757
+ "گوید",
758
+ "گویم",
759
+ "گویند",
760
+ "گویی",
761
+ "گویید",
762
+ "گوییم",
763
+ "گيرد",
764
+ "گيري",
765
+ "گیرد",
766
+ "گیرم",
767
+ "گیرند",
768
+ "گیری",
769
+ "گیرید",
770
+ "گیریم",
771
+ "ی",
772
+ "یا",
773
+ "یابد",
774
+ "یابم",
775
+ "یابند",
776
+ "یابی",
777
+ "یابید",
778
+ "یابیم",
779
+ "یافت",
780
+ "یافتم",
781
+ "یافتن",
782
+ "یافته",
783
+ "یافتی",
784
+ "یافتید",
785
+ "یافتیم",
786
+ "یعنی",
787
+ "یقینا",
788
+ "یه",
789
+ "یک",
790
+ "یکی",
791
+ "۰",
792
+ "۱",
793
+ "۲",
794
+ "۳",
795
+ "۴",
796
+ "۵",
797
+ "۶",
798
+ "۷",
799
+ "۸",
800
+ "۹"
801
+ ]