kreuzberg 4.0.0.rc1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (265) hide show
  1. checksums.yaml +7 -0
  2. data/.gitignore +8 -0
  3. data/.rspec +3 -0
  4. data/.rubocop.yaml +534 -0
  5. data/Gemfile +9 -0
  6. data/Gemfile.lock +157 -0
  7. data/README.md +421 -0
  8. data/Rakefile +25 -0
  9. data/Steepfile +47 -0
  10. data/examples/async_patterns.rb +340 -0
  11. data/ext/kreuzberg_rb/extconf.rb +35 -0
  12. data/ext/kreuzberg_rb/native/Cargo.toml +36 -0
  13. data/ext/kreuzberg_rb/native/README.md +425 -0
  14. data/ext/kreuzberg_rb/native/build.rs +17 -0
  15. data/ext/kreuzberg_rb/native/include/ieeefp.h +11 -0
  16. data/ext/kreuzberg_rb/native/include/msvc_compat/strings.h +14 -0
  17. data/ext/kreuzberg_rb/native/include/strings.h +20 -0
  18. data/ext/kreuzberg_rb/native/include/unistd.h +47 -0
  19. data/ext/kreuzberg_rb/native/src/lib.rs +2939 -0
  20. data/extconf.rb +28 -0
  21. data/kreuzberg.gemspec +105 -0
  22. data/lib/kreuzberg/api_proxy.rb +142 -0
  23. data/lib/kreuzberg/cache_api.rb +45 -0
  24. data/lib/kreuzberg/cli.rb +55 -0
  25. data/lib/kreuzberg/cli_proxy.rb +127 -0
  26. data/lib/kreuzberg/config.rb +684 -0
  27. data/lib/kreuzberg/errors.rb +50 -0
  28. data/lib/kreuzberg/extraction_api.rb +84 -0
  29. data/lib/kreuzberg/mcp_proxy.rb +186 -0
  30. data/lib/kreuzberg/ocr_backend_protocol.rb +113 -0
  31. data/lib/kreuzberg/post_processor_protocol.rb +86 -0
  32. data/lib/kreuzberg/result.rb +216 -0
  33. data/lib/kreuzberg/setup_lib_path.rb +79 -0
  34. data/lib/kreuzberg/validator_protocol.rb +89 -0
  35. data/lib/kreuzberg/version.rb +5 -0
  36. data/lib/kreuzberg.rb +82 -0
  37. data/pkg/kreuzberg-4.0.0.rc1.gem +0 -0
  38. data/sig/kreuzberg/internal.rbs +184 -0
  39. data/sig/kreuzberg.rbs +468 -0
  40. data/spec/binding/cache_spec.rb +227 -0
  41. data/spec/binding/cli_proxy_spec.rb +87 -0
  42. data/spec/binding/cli_spec.rb +54 -0
  43. data/spec/binding/config_spec.rb +345 -0
  44. data/spec/binding/config_validation_spec.rb +283 -0
  45. data/spec/binding/error_handling_spec.rb +213 -0
  46. data/spec/binding/errors_spec.rb +66 -0
  47. data/spec/binding/plugins/ocr_backend_spec.rb +307 -0
  48. data/spec/binding/plugins/postprocessor_spec.rb +269 -0
  49. data/spec/binding/plugins/validator_spec.rb +274 -0
  50. data/spec/examples.txt +104 -0
  51. data/spec/fixtures/config.toml +39 -0
  52. data/spec/fixtures/config.yaml +42 -0
  53. data/spec/fixtures/invalid_config.toml +4 -0
  54. data/spec/smoke/package_spec.rb +178 -0
  55. data/spec/spec_helper.rb +42 -0
  56. data/vendor/kreuzberg/Cargo.toml +134 -0
  57. data/vendor/kreuzberg/README.md +175 -0
  58. data/vendor/kreuzberg/build.rs +460 -0
  59. data/vendor/kreuzberg/src/api/error.rs +81 -0
  60. data/vendor/kreuzberg/src/api/handlers.rs +199 -0
  61. data/vendor/kreuzberg/src/api/mod.rs +79 -0
  62. data/vendor/kreuzberg/src/api/server.rs +353 -0
  63. data/vendor/kreuzberg/src/api/types.rs +170 -0
  64. data/vendor/kreuzberg/src/bin/profile_extract.rs +455 -0
  65. data/vendor/kreuzberg/src/cache/mod.rs +1143 -0
  66. data/vendor/kreuzberg/src/chunking/mod.rs +677 -0
  67. data/vendor/kreuzberg/src/core/batch_mode.rs +35 -0
  68. data/vendor/kreuzberg/src/core/config.rs +1032 -0
  69. data/vendor/kreuzberg/src/core/extractor.rs +903 -0
  70. data/vendor/kreuzberg/src/core/io.rs +327 -0
  71. data/vendor/kreuzberg/src/core/mime.rs +615 -0
  72. data/vendor/kreuzberg/src/core/mod.rs +42 -0
  73. data/vendor/kreuzberg/src/core/pipeline.rs +906 -0
  74. data/vendor/kreuzberg/src/embeddings.rs +323 -0
  75. data/vendor/kreuzberg/src/error.rs +431 -0
  76. data/vendor/kreuzberg/src/extraction/archive.rs +954 -0
  77. data/vendor/kreuzberg/src/extraction/docx.rs +40 -0
  78. data/vendor/kreuzberg/src/extraction/email.rs +854 -0
  79. data/vendor/kreuzberg/src/extraction/excel.rs +688 -0
  80. data/vendor/kreuzberg/src/extraction/html.rs +553 -0
  81. data/vendor/kreuzberg/src/extraction/image.rs +368 -0
  82. data/vendor/kreuzberg/src/extraction/libreoffice.rs +564 -0
  83. data/vendor/kreuzberg/src/extraction/mod.rs +77 -0
  84. data/vendor/kreuzberg/src/extraction/office_metadata/app_properties.rs +398 -0
  85. data/vendor/kreuzberg/src/extraction/office_metadata/core_properties.rs +247 -0
  86. data/vendor/kreuzberg/src/extraction/office_metadata/custom_properties.rs +240 -0
  87. data/vendor/kreuzberg/src/extraction/office_metadata/mod.rs +128 -0
  88. data/vendor/kreuzberg/src/extraction/pandoc/batch.rs +275 -0
  89. data/vendor/kreuzberg/src/extraction/pandoc/mime_types.rs +178 -0
  90. data/vendor/kreuzberg/src/extraction/pandoc/mod.rs +491 -0
  91. data/vendor/kreuzberg/src/extraction/pandoc/server.rs +496 -0
  92. data/vendor/kreuzberg/src/extraction/pandoc/subprocess.rs +1188 -0
  93. data/vendor/kreuzberg/src/extraction/pandoc/version.rs +162 -0
  94. data/vendor/kreuzberg/src/extraction/pptx.rs +3000 -0
  95. data/vendor/kreuzberg/src/extraction/structured.rs +490 -0
  96. data/vendor/kreuzberg/src/extraction/table.rs +328 -0
  97. data/vendor/kreuzberg/src/extraction/text.rs +269 -0
  98. data/vendor/kreuzberg/src/extraction/xml.rs +333 -0
  99. data/vendor/kreuzberg/src/extractors/archive.rs +425 -0
  100. data/vendor/kreuzberg/src/extractors/docx.rs +479 -0
  101. data/vendor/kreuzberg/src/extractors/email.rs +129 -0
  102. data/vendor/kreuzberg/src/extractors/excel.rs +344 -0
  103. data/vendor/kreuzberg/src/extractors/html.rs +410 -0
  104. data/vendor/kreuzberg/src/extractors/image.rs +195 -0
  105. data/vendor/kreuzberg/src/extractors/mod.rs +268 -0
  106. data/vendor/kreuzberg/src/extractors/pandoc.rs +201 -0
  107. data/vendor/kreuzberg/src/extractors/pdf.rs +496 -0
  108. data/vendor/kreuzberg/src/extractors/pptx.rs +234 -0
  109. data/vendor/kreuzberg/src/extractors/structured.rs +126 -0
  110. data/vendor/kreuzberg/src/extractors/text.rs +242 -0
  111. data/vendor/kreuzberg/src/extractors/xml.rs +128 -0
  112. data/vendor/kreuzberg/src/image/dpi.rs +164 -0
  113. data/vendor/kreuzberg/src/image/mod.rs +6 -0
  114. data/vendor/kreuzberg/src/image/preprocessing.rs +417 -0
  115. data/vendor/kreuzberg/src/image/resize.rs +89 -0
  116. data/vendor/kreuzberg/src/keywords/config.rs +154 -0
  117. data/vendor/kreuzberg/src/keywords/mod.rs +237 -0
  118. data/vendor/kreuzberg/src/keywords/processor.rs +267 -0
  119. data/vendor/kreuzberg/src/keywords/rake.rs +294 -0
  120. data/vendor/kreuzberg/src/keywords/types.rs +68 -0
  121. data/vendor/kreuzberg/src/keywords/yake.rs +163 -0
  122. data/vendor/kreuzberg/src/language_detection/mod.rs +942 -0
  123. data/vendor/kreuzberg/src/lib.rs +102 -0
  124. data/vendor/kreuzberg/src/mcp/mod.rs +32 -0
  125. data/vendor/kreuzberg/src/mcp/server.rs +1966 -0
  126. data/vendor/kreuzberg/src/ocr/cache.rs +469 -0
  127. data/vendor/kreuzberg/src/ocr/error.rs +37 -0
  128. data/vendor/kreuzberg/src/ocr/hocr.rs +216 -0
  129. data/vendor/kreuzberg/src/ocr/mod.rs +58 -0
  130. data/vendor/kreuzberg/src/ocr/processor.rs +847 -0
  131. data/vendor/kreuzberg/src/ocr/table/mod.rs +4 -0
  132. data/vendor/kreuzberg/src/ocr/table/tsv_parser.rs +144 -0
  133. data/vendor/kreuzberg/src/ocr/tesseract_backend.rs +450 -0
  134. data/vendor/kreuzberg/src/ocr/types.rs +393 -0
  135. data/vendor/kreuzberg/src/ocr/utils.rs +47 -0
  136. data/vendor/kreuzberg/src/ocr/validation.rs +206 -0
  137. data/vendor/kreuzberg/src/pdf/error.rs +122 -0
  138. data/vendor/kreuzberg/src/pdf/images.rs +139 -0
  139. data/vendor/kreuzberg/src/pdf/metadata.rs +346 -0
  140. data/vendor/kreuzberg/src/pdf/mod.rs +50 -0
  141. data/vendor/kreuzberg/src/pdf/rendering.rs +369 -0
  142. data/vendor/kreuzberg/src/pdf/table.rs +420 -0
  143. data/vendor/kreuzberg/src/pdf/text.rs +161 -0
  144. data/vendor/kreuzberg/src/plugins/extractor.rs +1010 -0
  145. data/vendor/kreuzberg/src/plugins/mod.rs +209 -0
  146. data/vendor/kreuzberg/src/plugins/ocr.rs +629 -0
  147. data/vendor/kreuzberg/src/plugins/processor.rs +641 -0
  148. data/vendor/kreuzberg/src/plugins/registry.rs +1324 -0
  149. data/vendor/kreuzberg/src/plugins/traits.rs +258 -0
  150. data/vendor/kreuzberg/src/plugins/validator.rs +955 -0
  151. data/vendor/kreuzberg/src/stopwords/mod.rs +1470 -0
  152. data/vendor/kreuzberg/src/text/mod.rs +19 -0
  153. data/vendor/kreuzberg/src/text/quality.rs +697 -0
  154. data/vendor/kreuzberg/src/text/string_utils.rs +217 -0
  155. data/vendor/kreuzberg/src/text/token_reduction/cjk_utils.rs +164 -0
  156. data/vendor/kreuzberg/src/text/token_reduction/config.rs +100 -0
  157. data/vendor/kreuzberg/src/text/token_reduction/core.rs +796 -0
  158. data/vendor/kreuzberg/src/text/token_reduction/filters.rs +902 -0
  159. data/vendor/kreuzberg/src/text/token_reduction/mod.rs +160 -0
  160. data/vendor/kreuzberg/src/text/token_reduction/semantic.rs +619 -0
  161. data/vendor/kreuzberg/src/text/token_reduction/simd_text.rs +147 -0
  162. data/vendor/kreuzberg/src/types.rs +873 -0
  163. data/vendor/kreuzberg/src/utils/mod.rs +17 -0
  164. data/vendor/kreuzberg/src/utils/quality.rs +959 -0
  165. data/vendor/kreuzberg/src/utils/string_utils.rs +381 -0
  166. data/vendor/kreuzberg/stopwords/af_stopwords.json +53 -0
  167. data/vendor/kreuzberg/stopwords/ar_stopwords.json +482 -0
  168. data/vendor/kreuzberg/stopwords/bg_stopwords.json +261 -0
  169. data/vendor/kreuzberg/stopwords/bn_stopwords.json +400 -0
  170. data/vendor/kreuzberg/stopwords/br_stopwords.json +1205 -0
  171. data/vendor/kreuzberg/stopwords/ca_stopwords.json +280 -0
  172. data/vendor/kreuzberg/stopwords/cs_stopwords.json +425 -0
  173. data/vendor/kreuzberg/stopwords/da_stopwords.json +172 -0
  174. data/vendor/kreuzberg/stopwords/de_stopwords.json +622 -0
  175. data/vendor/kreuzberg/stopwords/el_stopwords.json +849 -0
  176. data/vendor/kreuzberg/stopwords/en_stopwords.json +1300 -0
  177. data/vendor/kreuzberg/stopwords/eo_stopwords.json +175 -0
  178. data/vendor/kreuzberg/stopwords/es_stopwords.json +734 -0
  179. data/vendor/kreuzberg/stopwords/et_stopwords.json +37 -0
  180. data/vendor/kreuzberg/stopwords/eu_stopwords.json +100 -0
  181. data/vendor/kreuzberg/stopwords/fa_stopwords.json +801 -0
  182. data/vendor/kreuzberg/stopwords/fi_stopwords.json +849 -0
  183. data/vendor/kreuzberg/stopwords/fr_stopwords.json +693 -0
  184. data/vendor/kreuzberg/stopwords/ga_stopwords.json +111 -0
  185. data/vendor/kreuzberg/stopwords/gl_stopwords.json +162 -0
  186. data/vendor/kreuzberg/stopwords/gu_stopwords.json +226 -0
  187. data/vendor/kreuzberg/stopwords/ha_stopwords.json +41 -0
  188. data/vendor/kreuzberg/stopwords/he_stopwords.json +196 -0
  189. data/vendor/kreuzberg/stopwords/hi_stopwords.json +227 -0
  190. data/vendor/kreuzberg/stopwords/hr_stopwords.json +181 -0
  191. data/vendor/kreuzberg/stopwords/hu_stopwords.json +791 -0
  192. data/vendor/kreuzberg/stopwords/hy_stopwords.json +47 -0
  193. data/vendor/kreuzberg/stopwords/id_stopwords.json +760 -0
  194. data/vendor/kreuzberg/stopwords/it_stopwords.json +634 -0
  195. data/vendor/kreuzberg/stopwords/ja_stopwords.json +136 -0
  196. data/vendor/kreuzberg/stopwords/kn_stopwords.json +84 -0
  197. data/vendor/kreuzberg/stopwords/ko_stopwords.json +681 -0
  198. data/vendor/kreuzberg/stopwords/ku_stopwords.json +64 -0
  199. data/vendor/kreuzberg/stopwords/la_stopwords.json +51 -0
  200. data/vendor/kreuzberg/stopwords/lt_stopwords.json +476 -0
  201. data/vendor/kreuzberg/stopwords/lv_stopwords.json +163 -0
  202. data/vendor/kreuzberg/stopwords/ml_stopwords.json +1 -0
  203. data/vendor/kreuzberg/stopwords/mr_stopwords.json +101 -0
  204. data/vendor/kreuzberg/stopwords/ms_stopwords.json +477 -0
  205. data/vendor/kreuzberg/stopwords/ne_stopwords.json +490 -0
  206. data/vendor/kreuzberg/stopwords/nl_stopwords.json +415 -0
  207. data/vendor/kreuzberg/stopwords/no_stopwords.json +223 -0
  208. data/vendor/kreuzberg/stopwords/pl_stopwords.json +331 -0
  209. data/vendor/kreuzberg/stopwords/pt_stopwords.json +562 -0
  210. data/vendor/kreuzberg/stopwords/ro_stopwords.json +436 -0
  211. data/vendor/kreuzberg/stopwords/ru_stopwords.json +561 -0
  212. data/vendor/kreuzberg/stopwords/si_stopwords.json +193 -0
  213. data/vendor/kreuzberg/stopwords/sk_stopwords.json +420 -0
  214. data/vendor/kreuzberg/stopwords/sl_stopwords.json +448 -0
  215. data/vendor/kreuzberg/stopwords/so_stopwords.json +32 -0
  216. data/vendor/kreuzberg/stopwords/st_stopwords.json +33 -0
  217. data/vendor/kreuzberg/stopwords/sv_stopwords.json +420 -0
  218. data/vendor/kreuzberg/stopwords/sw_stopwords.json +76 -0
  219. data/vendor/kreuzberg/stopwords/ta_stopwords.json +129 -0
  220. data/vendor/kreuzberg/stopwords/te_stopwords.json +54 -0
  221. data/vendor/kreuzberg/stopwords/th_stopwords.json +118 -0
  222. data/vendor/kreuzberg/stopwords/tl_stopwords.json +149 -0
  223. data/vendor/kreuzberg/stopwords/tr_stopwords.json +506 -0
  224. data/vendor/kreuzberg/stopwords/uk_stopwords.json +75 -0
  225. data/vendor/kreuzberg/stopwords/ur_stopwords.json +519 -0
  226. data/vendor/kreuzberg/stopwords/vi_stopwords.json +647 -0
  227. data/vendor/kreuzberg/stopwords/yo_stopwords.json +62 -0
  228. data/vendor/kreuzberg/stopwords/zh_stopwords.json +796 -0
  229. data/vendor/kreuzberg/stopwords/zu_stopwords.json +31 -0
  230. data/vendor/kreuzberg/tests/api_tests.rs +966 -0
  231. data/vendor/kreuzberg/tests/archive_integration.rs +543 -0
  232. data/vendor/kreuzberg/tests/batch_orchestration.rs +542 -0
  233. data/vendor/kreuzberg/tests/batch_processing.rs +304 -0
  234. data/vendor/kreuzberg/tests/chunking_offset_demo.rs +92 -0
  235. data/vendor/kreuzberg/tests/concurrency_stress.rs +509 -0
  236. data/vendor/kreuzberg/tests/config_features.rs +580 -0
  237. data/vendor/kreuzberg/tests/config_loading_tests.rs +439 -0
  238. data/vendor/kreuzberg/tests/core_integration.rs +493 -0
  239. data/vendor/kreuzberg/tests/csv_integration.rs +424 -0
  240. data/vendor/kreuzberg/tests/docx_metadata_extraction_test.rs +124 -0
  241. data/vendor/kreuzberg/tests/email_integration.rs +325 -0
  242. data/vendor/kreuzberg/tests/error_handling.rs +393 -0
  243. data/vendor/kreuzberg/tests/format_integration.rs +159 -0
  244. data/vendor/kreuzberg/tests/helpers/mod.rs +142 -0
  245. data/vendor/kreuzberg/tests/image_integration.rs +253 -0
  246. data/vendor/kreuzberg/tests/keywords_integration.rs +479 -0
  247. data/vendor/kreuzberg/tests/keywords_quality.rs +509 -0
  248. data/vendor/kreuzberg/tests/mime_detection.rs +428 -0
  249. data/vendor/kreuzberg/tests/ocr_configuration.rs +510 -0
  250. data/vendor/kreuzberg/tests/ocr_errors.rs +676 -0
  251. data/vendor/kreuzberg/tests/ocr_quality.rs +627 -0
  252. data/vendor/kreuzberg/tests/ocr_stress.rs +469 -0
  253. data/vendor/kreuzberg/tests/pandoc_integration.rs +503 -0
  254. data/vendor/kreuzberg/tests/pdf_integration.rs +43 -0
  255. data/vendor/kreuzberg/tests/pipeline_integration.rs +1412 -0
  256. data/vendor/kreuzberg/tests/plugin_ocr_backend_test.rs +771 -0
  257. data/vendor/kreuzberg/tests/plugin_postprocessor_test.rs +561 -0
  258. data/vendor/kreuzberg/tests/plugin_system.rs +921 -0
  259. data/vendor/kreuzberg/tests/plugin_validator_test.rs +783 -0
  260. data/vendor/kreuzberg/tests/registry_integration_tests.rs +607 -0
  261. data/vendor/kreuzberg/tests/security_validation.rs +404 -0
  262. data/vendor/kreuzberg/tests/stopwords_integration_test.rs +888 -0
  263. data/vendor/kreuzberg/tests/test_fastembed.rs +609 -0
  264. data/vendor/kreuzberg/tests/xlsx_metadata_extraction_test.rs +87 -0
  265. metadata +471 -0
@@ -0,0 +1,261 @@
1
+ [
2
+ "а",
3
+ "автентичен",
4
+ "аз",
5
+ "ако",
6
+ "ала",
7
+ "бе",
8
+ "без",
9
+ "беше",
10
+ "би",
11
+ "бивш",
12
+ "бивша",
13
+ "бившо",
14
+ "бил",
15
+ "била",
16
+ "били",
17
+ "било",
18
+ "благодаря",
19
+ "близо",
20
+ "бъдат",
21
+ "бъде",
22
+ "бяха",
23
+ "в",
24
+ "вас",
25
+ "ваш",
26
+ "ваша",
27
+ "вероятно",
28
+ "вече",
29
+ "взема",
30
+ "ви",
31
+ "вие",
32
+ "винаги",
33
+ "внимава",
34
+ "време",
35
+ "все",
36
+ "всеки",
37
+ "всички",
38
+ "всичко",
39
+ "всяка",
40
+ "във",
41
+ "въпреки",
42
+ "върху",
43
+ "г",
44
+ "ги",
45
+ "главен",
46
+ "главна",
47
+ "главно",
48
+ "глас",
49
+ "го",
50
+ "година",
51
+ "години",
52
+ "годишен",
53
+ "д",
54
+ "да",
55
+ "дали",
56
+ "два",
57
+ "двама",
58
+ "двамата",
59
+ "две",
60
+ "двете",
61
+ "ден",
62
+ "днес",
63
+ "дни",
64
+ "до",
65
+ "добра",
66
+ "добре",
67
+ "добро",
68
+ "добър",
69
+ "докато",
70
+ "докога",
71
+ "дори",
72
+ "досега",
73
+ "доста",
74
+ "друг",
75
+ "друга",
76
+ "други",
77
+ "е",
78
+ "евтин",
79
+ "едва",
80
+ "един",
81
+ "една",
82
+ "еднаква",
83
+ "еднакви",
84
+ "еднакъв",
85
+ "едно",
86
+ "екип",
87
+ "ето",
88
+ "живот",
89
+ "за",
90
+ "забавям",
91
+ "зад",
92
+ "заедно",
93
+ "заради",
94
+ "засега",
95
+ "заспал",
96
+ "затова",
97
+ "защо",
98
+ "защото",
99
+ "и",
100
+ "из",
101
+ "или",
102
+ "им",
103
+ "има",
104
+ "имат",
105
+ "иска",
106
+ "й",
107
+ "каза",
108
+ "как",
109
+ "каква",
110
+ "какво",
111
+ "както",
112
+ "какъв",
113
+ "като",
114
+ "кога",
115
+ "когато",
116
+ "което",
117
+ "които",
118
+ "кой",
119
+ "който",
120
+ "колко",
121
+ "която",
122
+ "къде",
123
+ "където",
124
+ "към",
125
+ "лесен",
126
+ "лесно",
127
+ "ли",
128
+ "лош",
129
+ "м",
130
+ "май",
131
+ "малко",
132
+ "ме",
133
+ "между",
134
+ "мек",
135
+ "мен",
136
+ "месец",
137
+ "ми",
138
+ "много",
139
+ "мнозина",
140
+ "мога",
141
+ "могат",
142
+ "може",
143
+ "мокър",
144
+ "моля",
145
+ "момента",
146
+ "му",
147
+ "н",
148
+ "на",
149
+ "над",
150
+ "назад",
151
+ "най",
152
+ "направи",
153
+ "напред",
154
+ "например",
155
+ "нас",
156
+ "не",
157
+ "него",
158
+ "нещо",
159
+ "нея",
160
+ "ни",
161
+ "ние",
162
+ "никой",
163
+ "нито",
164
+ "нищо",
165
+ "но",
166
+ "нов",
167
+ "нова",
168
+ "нови",
169
+ "новина",
170
+ "някои",
171
+ "някой",
172
+ "няколко",
173
+ "няма",
174
+ "обаче",
175
+ "около",
176
+ "освен",
177
+ "особено",
178
+ "от",
179
+ "отгоре",
180
+ "отново",
181
+ "още",
182
+ "пак",
183
+ "по",
184
+ "повече",
185
+ "повечето",
186
+ "под",
187
+ "поне",
188
+ "поради",
189
+ "после",
190
+ "почти",
191
+ "прави",
192
+ "пред",
193
+ "преди",
194
+ "през",
195
+ "при",
196
+ "пък",
197
+ "първата",
198
+ "първи",
199
+ "първо",
200
+ "пъти",
201
+ "равен",
202
+ "равна",
203
+ "с",
204
+ "са",
205
+ "сам",
206
+ "само",
207
+ "се",
208
+ "сега",
209
+ "си",
210
+ "син",
211
+ "скоро",
212
+ "след",
213
+ "следващ",
214
+ "сме",
215
+ "смях",
216
+ "според",
217
+ "сред",
218
+ "срещу",
219
+ "сте",
220
+ "съм",
221
+ "със",
222
+ "също",
223
+ "т",
224
+ "т.н.",
225
+ "тази",
226
+ "така",
227
+ "такива",
228
+ "такъв",
229
+ "там",
230
+ "твой",
231
+ "те",
232
+ "тези",
233
+ "ти",
234
+ "то",
235
+ "това",
236
+ "тогава",
237
+ "този",
238
+ "той",
239
+ "толкова",
240
+ "точно",
241
+ "три",
242
+ "трябва",
243
+ "тук",
244
+ "тъй",
245
+ "тя",
246
+ "тях",
247
+ "у",
248
+ "утре",
249
+ "харесва",
250
+ "хиляди",
251
+ "ч",
252
+ "часа",
253
+ "че",
254
+ "често",
255
+ "чрез",
256
+ "ще",
257
+ "щом",
258
+ "юмрук",
259
+ "я",
260
+ "як"
261
+ ]
@@ -0,0 +1,400 @@
1
+ [
2
+ "অতএব",
3
+ "অথচ",
4
+ "অথবা",
5
+ "অনুযায়ী",
6
+ "অনেক",
7
+ "অনেকে",
8
+ "অনেকেই",
9
+ "অন্তত",
10
+ "অন্য",
11
+ "অবধি",
12
+ "অবশ্য",
13
+ "অর্থাত",
14
+ "আই",
15
+ "আগামী",
16
+ "আগে",
17
+ "আগেই",
18
+ "আছে",
19
+ "আজ",
20
+ "আদ্যভাগে",
21
+ "আপনার",
22
+ "আপনি",
23
+ "আবার",
24
+ "আমরা",
25
+ "আমাকে",
26
+ "আমাদের",
27
+ "আমার",
28
+ "আমি",
29
+ "আর",
30
+ "আরও",
31
+ "ই",
32
+ "ইত্যাদি",
33
+ "ইহা",
34
+ "উচিত",
35
+ "উত্তর",
36
+ "উনি",
37
+ "উপর",
38
+ "উপরে",
39
+ "এ",
40
+ "এঁদের",
41
+ "এঁরা",
42
+ "এই",
43
+ "একই",
44
+ "একটি",
45
+ "একবার",
46
+ "একে",
47
+ "এক্",
48
+ "এখন",
49
+ "এখনও",
50
+ "এখানে",
51
+ "এখানেই",
52
+ "এটা",
53
+ "এটাই",
54
+ "এটি",
55
+ "এত",
56
+ "এতটাই",
57
+ "এতে",
58
+ "এদের",
59
+ "এব",
60
+ "এবং",
61
+ "এবার",
62
+ "এমন",
63
+ "এমনকী",
64
+ "এমনি",
65
+ "এর",
66
+ "এরা",
67
+ "এল",
68
+ "এস",
69
+ "এসে",
70
+ "ঐ",
71
+ "ও",
72
+ "ওঁদের",
73
+ "ওঁর",
74
+ "ওঁরা",
75
+ "ওই",
76
+ "ওকে",
77
+ "ওখানে",
78
+ "ওদের",
79
+ "ওর",
80
+ "ওরা",
81
+ "কখনও",
82
+ "কত",
83
+ "কবে",
84
+ "কমনে",
85
+ "কয়েক",
86
+ "কয়েকটি",
87
+ "করছে",
88
+ "করছেন",
89
+ "করতে",
90
+ "করবে",
91
+ "করবেন",
92
+ "করলে",
93
+ "করলেন",
94
+ "করা",
95
+ "করাই",
96
+ "করায়",
97
+ "করার",
98
+ "করি",
99
+ "করিতে",
100
+ "করিয়া",
101
+ "করিয়ে",
102
+ "করে",
103
+ "করেই",
104
+ "করেছিলেন",
105
+ "করেছে",
106
+ "করেছেন",
107
+ "করেন",
108
+ "কাউকে",
109
+ "কাছ",
110
+ "কাছে",
111
+ "কাজ",
112
+ "কাজে",
113
+ "কারও",
114
+ "কারণ",
115
+ "কি",
116
+ "কিংবা",
117
+ "কিছু",
118
+ "কিছুই",
119
+ "কিন্তু",
120
+ "কী",
121
+ "কে",
122
+ "কেউ",
123
+ "কেউই",
124
+ "কেখা",
125
+ "কেন",
126
+ "কোটি",
127
+ "কোন",
128
+ "কোনও",
129
+ "কোনো",
130
+ "ক্ষেত্রে",
131
+ "কয়েক",
132
+ "খুব",
133
+ "গিয়ে",
134
+ "গিয়েছে",
135
+ "গিয়ে",
136
+ "গুলি",
137
+ "গেছে",
138
+ "গেল",
139
+ "গেলে",
140
+ "গোটা",
141
+ "চলে",
142
+ "চান",
143
+ "চায়",
144
+ "চার",
145
+ "চালু",
146
+ "চেয়ে",
147
+ "চেষ্টা",
148
+ "ছাড়া",
149
+ "ছাড়াও",
150
+ "ছিল",
151
+ "ছিলেন",
152
+ "জন",
153
+ "জনকে",
154
+ "জনের",
155
+ "জন্য",
156
+ "জন্যওজে",
157
+ "জানতে",
158
+ "জানা",
159
+ "জানানো",
160
+ "জানায়",
161
+ "জানিয়ে",
162
+ "জানিয়েছে",
163
+ "জে",
164
+ "জ্নজন",
165
+ "টি",
166
+ "ঠিক",
167
+ "তখন",
168
+ "তত",
169
+ "তথা",
170
+ "তবু",
171
+ "তবে",
172
+ "তা",
173
+ "তাঁকে",
174
+ "তাঁদের",
175
+ "তাঁর",
176
+ "তাঁরা",
177
+ "তাঁাহারা",
178
+ "তাই",
179
+ "তাও",
180
+ "তাকে",
181
+ "তাতে",
182
+ "তাদের",
183
+ "তার",
184
+ "তারপর",
185
+ "তারা",
186
+ "তারৈ",
187
+ "তাহলে",
188
+ "তাহা",
189
+ "তাহাতে",
190
+ "তাহার",
191
+ "তিনঐ",
192
+ "তিনি",
193
+ "তিনিও",
194
+ "তুমি",
195
+ "তুলে",
196
+ "তেমন",
197
+ "তো",
198
+ "তোমার",
199
+ "থাকবে",
200
+ "থাকবেন",
201
+ "থাকা",
202
+ "থাকায়",
203
+ "থাকে",
204
+ "থাকেন",
205
+ "থেকে",
206
+ "থেকেই",
207
+ "থেকেও",
208
+ "দিকে",
209
+ "দিতে",
210
+ "দিন",
211
+ "দিয়ে",
212
+ "দিয়েছে",
213
+ "দিয়েছেন",
214
+ "দিলেন",
215
+ "দু",
216
+ "দুই",
217
+ "দুটি",
218
+ "দুটো",
219
+ "দেওয়া",
220
+ "দেওয়ার",
221
+ "দেওয়া",
222
+ "দেখতে",
223
+ "দেখা",
224
+ "দেখে",
225
+ "দেন",
226
+ "দেয়",
227
+ "দ্বারা",
228
+ "ধরা",
229
+ "ধরে",
230
+ "ধামার",
231
+ "নতুন",
232
+ "নয়",
233
+ "না",
234
+ "নাই",
235
+ "নাকি",
236
+ "নাগাদ",
237
+ "নানা",
238
+ "নিজে",
239
+ "নিজেই",
240
+ "নিজেদের",
241
+ "নিজের",
242
+ "নিতে",
243
+ "নিয়ে",
244
+ "নিয়ে",
245
+ "নেই",
246
+ "নেওয়া",
247
+ "নেওয়ার",
248
+ "নেওয়া",
249
+ "নয়",
250
+ "পক্ষে",
251
+ "পর",
252
+ "পরে",
253
+ "পরেই",
254
+ "পরেও",
255
+ "পর্যন্ত",
256
+ "পাওয়া",
257
+ "পাচ",
258
+ "পারি",
259
+ "পারে",
260
+ "পারেন",
261
+ "পি",
262
+ "পেয়ে",
263
+ "পেয়্র্",
264
+ "প্রতি",
265
+ "প্রথম",
266
+ "প্রভৃতি",
267
+ "প্রযন্ত",
268
+ "প্রাথমিক",
269
+ "প্রায়",
270
+ "প্রায়",
271
+ "ফলে",
272
+ "ফিরে",
273
+ "ফের",
274
+ "বক্তব্য",
275
+ "বদলে",
276
+ "বন",
277
+ "বরং",
278
+ "বলতে",
279
+ "বলল",
280
+ "বললেন",
281
+ "বলা",
282
+ "বলে",
283
+ "বলেছেন",
284
+ "বলেন",
285
+ "বসে",
286
+ "বহু",
287
+ "বা",
288
+ "বাদে",
289
+ "বার",
290
+ "বি",
291
+ "বিনা",
292
+ "বিভিন্ন",
293
+ "বিশেষ",
294
+ "বিষয়টি",
295
+ "বেশ",
296
+ "বেশি",
297
+ "ব্যবহার",
298
+ "ব্যাপারে",
299
+ "ভাবে",
300
+ "ভাবেই",
301
+ "মতো",
302
+ "মতোই",
303
+ "মধ্যভাগে",
304
+ "মধ্যে",
305
+ "মধ্যেই",
306
+ "মধ্যেও",
307
+ "মনে",
308
+ "মাত্র",
309
+ "মাধ্যমে",
310
+ "মোট",
311
+ "মোটেই",
312
+ "যখন",
313
+ "যত",
314
+ "যতটা",
315
+ "যথেষ্ট",
316
+ "যদি",
317
+ "যদিও",
318
+ "যা",
319
+ "যাঁর",
320
+ "যাঁরা",
321
+ "যাওয়া",
322
+ "যাওয়ার",
323
+ "যাওয়া",
324
+ "যাকে",
325
+ "যাচ্ছে",
326
+ "যাতে",
327
+ "যাদের",
328
+ "যান",
329
+ "যাবে",
330
+ "যায়",
331
+ "যার",
332
+ "যারা",
333
+ "যিনি",
334
+ "যে",
335
+ "যেখানে",
336
+ "যেতে",
337
+ "যেন",
338
+ "যেমন",
339
+ "র",
340
+ "রকম",
341
+ "রয়েছে",
342
+ "রাখা",
343
+ "রেখে",
344
+ "লক্ষ",
345
+ "শুধু",
346
+ "শুরু",
347
+ "সঙ্গে",
348
+ "সঙ্গেও",
349
+ "সব",
350
+ "সবার",
351
+ "সমস্ত",
352
+ "সম্প্রতি",
353
+ "সহ",
354
+ "সহিত",
355
+ "সাধারণ",
356
+ "সামনে",
357
+ "সি",
358
+ "সুতরাং",
359
+ "সে",
360
+ "সেই",
361
+ "সেখান",
362
+ "সেখানে",
363
+ "সেটা",
364
+ "সেটাই",
365
+ "সেটাও",
366
+ "সেটি",
367
+ "স্পষ্ট",
368
+ "স্বয়ং",
369
+ "হইতে",
370
+ "হইবে",
371
+ "হইয়া",
372
+ "হওয়া",
373
+ "হওয়ায়",
374
+ "হওয়ার",
375
+ "হচ্ছে",
376
+ "হত",
377
+ "হতে",
378
+ "হতেই",
379
+ "হন",
380
+ "হবে",
381
+ "হবেন",
382
+ "হয়",
383
+ "হয়তো",
384
+ "হয়নি",
385
+ "হয়ে",
386
+ "হয়েই",
387
+ "হয়েছিল",
388
+ "হয়েছে",
389
+ "হয়েছেন",
390
+ "হল",
391
+ "হলে",
392
+ "হলেই",
393
+ "হলেও",
394
+ "হলো",
395
+ "হাজার",
396
+ "হিসাবে",
397
+ "হৈলে",
398
+ "হোক",
399
+ "হয়"
400
+ ]