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 +1,111 @@
1
+ [
2
+ "a",
3
+ "ach",
4
+ "ag",
5
+ "agus",
6
+ "an",
7
+ "aon",
8
+ "ar",
9
+ "arna",
10
+ "as",
11
+ "b'",
12
+ "ba",
13
+ "beirt",
14
+ "bhúr",
15
+ "caoga",
16
+ "ceathair",
17
+ "ceathrar",
18
+ "chomh",
19
+ "chtó",
20
+ "chuig",
21
+ "chun",
22
+ "cois",
23
+ "céad",
24
+ "cúig",
25
+ "cúigear",
26
+ "d'",
27
+ "daichead",
28
+ "dar",
29
+ "de",
30
+ "deich",
31
+ "deichniúr",
32
+ "den",
33
+ "dhá",
34
+ "do",
35
+ "don",
36
+ "dtí",
37
+ "dá",
38
+ "dár",
39
+ "dó",
40
+ "faoi",
41
+ "faoin",
42
+ "faoina",
43
+ "faoinár",
44
+ "fara",
45
+ "fiche",
46
+ "gach",
47
+ "gan",
48
+ "go",
49
+ "gur",
50
+ "haon",
51
+ "hocht",
52
+ "i",
53
+ "iad",
54
+ "idir",
55
+ "in",
56
+ "ina",
57
+ "ins",
58
+ "inár",
59
+ "is",
60
+ "le",
61
+ "leis",
62
+ "lena",
63
+ "lenár",
64
+ "m'",
65
+ "mar",
66
+ "mo",
67
+ "mé",
68
+ "na",
69
+ "nach",
70
+ "naoi",
71
+ "naonúr",
72
+ "ná",
73
+ "ní",
74
+ "níor",
75
+ "nó",
76
+ "nócha",
77
+ "ocht",
78
+ "ochtar",
79
+ "os",
80
+ "roimh",
81
+ "sa",
82
+ "seacht",
83
+ "seachtar",
84
+ "seachtó",
85
+ "seasca",
86
+ "seisear",
87
+ "siad",
88
+ "sibh",
89
+ "sinn",
90
+ "sna",
91
+ "sé",
92
+ "sí",
93
+ "tar",
94
+ "thar",
95
+ "thú",
96
+ "triúr",
97
+ "trí",
98
+ "trína",
99
+ "trínár",
100
+ "tríocha",
101
+ "tú",
102
+ "um",
103
+ "ár",
104
+ "é",
105
+ "éis",
106
+ "í",
107
+ "ó",
108
+ "ón",
109
+ "óna",
110
+ "ónár"
111
+ ]
@@ -0,0 +1,162 @@
1
+ [
2
+ "a",
3
+ "alí",
4
+ "ao",
5
+ "aos",
6
+ "aquel",
7
+ "aquela",
8
+ "aquelas",
9
+ "aqueles",
10
+ "aquilo",
11
+ "aquí",
12
+ "as",
13
+ "así",
14
+ "aínda",
15
+ "ben",
16
+ "cando",
17
+ "che",
18
+ "co",
19
+ "coa",
20
+ "coas",
21
+ "comigo",
22
+ "con",
23
+ "connosco",
24
+ "contigo",
25
+ "convosco",
26
+ "cos",
27
+ "cun",
28
+ "cunha",
29
+ "cunhas",
30
+ "cuns",
31
+ "da",
32
+ "dalgunha",
33
+ "dalgunhas",
34
+ "dalgún",
35
+ "dalgúns",
36
+ "das",
37
+ "de",
38
+ "del",
39
+ "dela",
40
+ "delas",
41
+ "deles",
42
+ "desde",
43
+ "deste",
44
+ "do",
45
+ "dos",
46
+ "dun",
47
+ "dunha",
48
+ "dunhas",
49
+ "duns",
50
+ "e",
51
+ "el",
52
+ "ela",
53
+ "elas",
54
+ "eles",
55
+ "en",
56
+ "era",
57
+ "eran",
58
+ "esa",
59
+ "esas",
60
+ "ese",
61
+ "eses",
62
+ "esta",
63
+ "estaba",
64
+ "estar",
65
+ "este",
66
+ "estes",
67
+ "estiven",
68
+ "estou",
69
+ "está",
70
+ "están",
71
+ "eu",
72
+ "facer",
73
+ "foi",
74
+ "foron",
75
+ "fun",
76
+ "había",
77
+ "hai",
78
+ "iso",
79
+ "isto",
80
+ "la",
81
+ "las",
82
+ "lle",
83
+ "lles",
84
+ "lo",
85
+ "los",
86
+ "mais",
87
+ "me",
88
+ "meu",
89
+ "meus",
90
+ "min",
91
+ "miña",
92
+ "miñas",
93
+ "moi",
94
+ "na",
95
+ "nas",
96
+ "neste",
97
+ "nin",
98
+ "no",
99
+ "non",
100
+ "nos",
101
+ "nosa",
102
+ "nosas",
103
+ "noso",
104
+ "nosos",
105
+ "nun",
106
+ "nunha",
107
+ "nunhas",
108
+ "nuns",
109
+ "nós",
110
+ "o",
111
+ "os",
112
+ "ou",
113
+ "para",
114
+ "pero",
115
+ "pode",
116
+ "pois",
117
+ "pola",
118
+ "polas",
119
+ "polo",
120
+ "polos",
121
+ "por",
122
+ "que",
123
+ "se",
124
+ "senón",
125
+ "ser",
126
+ "seu",
127
+ "seus",
128
+ "sexa",
129
+ "sido",
130
+ "sobre",
131
+ "súa",
132
+ "súas",
133
+ "tamén",
134
+ "tan",
135
+ "te",
136
+ "ten",
137
+ "ter",
138
+ "teu",
139
+ "teus",
140
+ "teñen",
141
+ "teño",
142
+ "ti",
143
+ "tido",
144
+ "tiven",
145
+ "tiña",
146
+ "túa",
147
+ "túas",
148
+ "un",
149
+ "unha",
150
+ "unhas",
151
+ "uns",
152
+ "vos",
153
+ "vosa",
154
+ "vosas",
155
+ "voso",
156
+ "vosos",
157
+ "vós",
158
+ "á",
159
+ "é",
160
+ "ó",
161
+ "ós"
162
+ ]
@@ -0,0 +1,226 @@
1
+ [
2
+ "અંગે",
3
+ "અંદર",
4
+ "અથવા",
5
+ "અને",
6
+ "અમને",
7
+ "અમારું",
8
+ "અમે",
9
+ "અહીં",
10
+ "આ",
11
+ "આગળ",
12
+ "આથી",
13
+ "આનું",
14
+ "આને",
15
+ "આપણને",
16
+ "આપણું",
17
+ "આપણે",
18
+ "આપી",
19
+ "આર",
20
+ "આવી",
21
+ "આવે",
22
+ "ઉપર",
23
+ "ઉભા",
24
+ "ઊંચે",
25
+ "ઊભું",
26
+ "એ",
27
+ "એક",
28
+ "એન",
29
+ "એના",
30
+ "એનાં",
31
+ "એની",
32
+ "એનું",
33
+ "એને",
34
+ "એનો",
35
+ "એમ",
36
+ "એવા",
37
+ "એવાં",
38
+ "એવી",
39
+ "એવું",
40
+ "એવો",
41
+ "ઓછું",
42
+ "કંઈક",
43
+ "કઈ",
44
+ "કયું",
45
+ "કયો",
46
+ "કરતાં",
47
+ "કરવું",
48
+ "કરી",
49
+ "કરીએ",
50
+ "કરું",
51
+ "કરે",
52
+ "કરેલું",
53
+ "કર્યા",
54
+ "કર્યાં",
55
+ "કર્યું",
56
+ "કર્યો",
57
+ "કાંઈ",
58
+ "કે",
59
+ "કેટલું",
60
+ "કેમ",
61
+ "કેવી",
62
+ "કેવું",
63
+ "કોઈ",
64
+ "કોઈક",
65
+ "કોણ",
66
+ "કોણે",
67
+ "કોને",
68
+ "ક્યાં",
69
+ "ક્યારે",
70
+ "ખૂબ",
71
+ "ગઈ",
72
+ "ગયા",
73
+ "ગયાં",
74
+ "ગયું",
75
+ "ગયો",
76
+ "ઘણું",
77
+ "છ",
78
+ "છતાં",
79
+ "છીએ",
80
+ "છું",
81
+ "છે",
82
+ "છેક",
83
+ "છો",
84
+ "જ",
85
+ "જાય",
86
+ "જી",
87
+ "જે",
88
+ "જેટલું",
89
+ "જેને",
90
+ "જેમ",
91
+ "જેવી",
92
+ "જેવું",
93
+ "જેવો",
94
+ "જો",
95
+ "જોઈએ",
96
+ "જ્યાં",
97
+ "જ્યારે",
98
+ "ઝાઝું",
99
+ "તને",
100
+ "તમને",
101
+ "તમારું",
102
+ "તમે",
103
+ "તા",
104
+ "તારાથી",
105
+ "તારામાં",
106
+ "તારું",
107
+ "તું",
108
+ "તે",
109
+ "તેં",
110
+ "તેઓ",
111
+ "તેણે",
112
+ "તેથી",
113
+ "તેના",
114
+ "તેની",
115
+ "તેનું",
116
+ "તેને",
117
+ "તેમ",
118
+ "તેમનું",
119
+ "તેમને",
120
+ "તેવી",
121
+ "તેવું",
122
+ "તો",
123
+ "ત્યાં",
124
+ "ત્યારે",
125
+ "થઇ",
126
+ "થઈ",
127
+ "થઈએ",
128
+ "થતા",
129
+ "થતાં",
130
+ "થતી",
131
+ "થતું",
132
+ "થતો",
133
+ "થયા",
134
+ "થયાં",
135
+ "થયું",
136
+ "થયેલું",
137
+ "થયો",
138
+ "થવું",
139
+ "થાઉં",
140
+ "થાઓ",
141
+ "થાય",
142
+ "થી",
143
+ "થોડું",
144
+ "દરેક",
145
+ "ન",
146
+ "નં",
147
+ "નં.",
148
+ "નથી",
149
+ "નહિ",
150
+ "નહી",
151
+ "નહીં",
152
+ "ના",
153
+ "ની",
154
+ "નીચે",
155
+ "નું",
156
+ "ને",
157
+ "નો",
158
+ "પછી",
159
+ "પણ",
160
+ "પર",
161
+ "પરંતુ",
162
+ "પહેલાં",
163
+ "પાછળ",
164
+ "પાસે",
165
+ "પોતાનું",
166
+ "પ્રત્યેક",
167
+ "ફક્ત",
168
+ "ફરી",
169
+ "ફરીથી",
170
+ "બંને",
171
+ "બધા",
172
+ "બધું",
173
+ "બની",
174
+ "બહાર",
175
+ "બહુ",
176
+ "બાદ",
177
+ "બે",
178
+ "મને",
179
+ "મા",
180
+ "માં",
181
+ "માટે",
182
+ "માત્ર",
183
+ "મારું",
184
+ "મી",
185
+ "મૂકવું",
186
+ "મૂકી",
187
+ "મૂક્યા",
188
+ "મૂક્યાં",
189
+ "મૂક્યું",
190
+ "મેં",
191
+ "રહી",
192
+ "રહે",
193
+ "રહેવું",
194
+ "રહ્યા",
195
+ "રહ્યાં",
196
+ "રહ્યો",
197
+ "રીતે",
198
+ "રૂ.",
199
+ "રૂા",
200
+ "લેતા",
201
+ "લેતું",
202
+ "લેવા",
203
+ "વગેરે",
204
+ "વધુ",
205
+ "શકે",
206
+ "શા",
207
+ "શું",
208
+ "સરખું",
209
+ "સામે",
210
+ "સુધી",
211
+ "હતા",
212
+ "હતાં",
213
+ "હતી",
214
+ "હતું",
215
+ "હવે",
216
+ "હશે",
217
+ "હશો",
218
+ "હા",
219
+ "હું",
220
+ "હો",
221
+ "હોઈ",
222
+ "હોઈશ",
223
+ "હોઈશું",
224
+ "હોય",
225
+ "હોવા"
226
+ ]
@@ -0,0 +1,41 @@
1
+ [
2
+ "a",
3
+ "amma",
4
+ "ba",
5
+ "ban",
6
+ "ce",
7
+ "cikin",
8
+ "da",
9
+ "don",
10
+ "ga",
11
+ "in",
12
+ "ina",
13
+ "ita",
14
+ "ji",
15
+ "ka",
16
+ "ko",
17
+ "kuma",
18
+ "lokacin",
19
+ "ma",
20
+ "mai",
21
+ "na",
22
+ "ne",
23
+ "ni",
24
+ "sai",
25
+ "shi",
26
+ "su",
27
+ "suka",
28
+ "sun",
29
+ "ta",
30
+ "tafi",
31
+ "take",
32
+ "tana",
33
+ "wani",
34
+ "wannan",
35
+ "wata",
36
+ "ya",
37
+ "yake",
38
+ "yana",
39
+ "yi",
40
+ "za"
41
+ ]
@@ -0,0 +1,196 @@
1
+ [
2
+ "אבל",
3
+ "או",
4
+ "אולי",
5
+ "אותה",
6
+ "אותו",
7
+ "אותי",
8
+ "אותך",
9
+ "אותם",
10
+ "אותן",
11
+ "אותנו",
12
+ "אז",
13
+ "אחר",
14
+ "אחרות",
15
+ "אחרי",
16
+ "אחריכן",
17
+ "אחרים",
18
+ "אחרת",
19
+ "אי",
20
+ "איזה",
21
+ "איך",
22
+ "אין",
23
+ "איפה",
24
+ "איתה",
25
+ "איתו",
26
+ "איתי",
27
+ "איתך",
28
+ "איתכם",
29
+ "איתכן",
30
+ "איתם",
31
+ "איתן",
32
+ "איתנו",
33
+ "אך",
34
+ "אל",
35
+ "אלה",
36
+ "אלו",
37
+ "אם",
38
+ "אנחנו",
39
+ "אני",
40
+ "אס",
41
+ "אף",
42
+ "אצל",
43
+ "אשר",
44
+ "את",
45
+ "אתה",
46
+ "אתכם",
47
+ "אתכן",
48
+ "אתם",
49
+ "אתן",
50
+ "באיזומידה",
51
+ "באמצע",
52
+ "באמצעות",
53
+ "בגלל",
54
+ "בין",
55
+ "בלי",
56
+ "במידה",
57
+ "במקוםשבו",
58
+ "ברם",
59
+ "בשביל",
60
+ "בשעהש",
61
+ "בתוך",
62
+ "גם",
63
+ "דרך",
64
+ "הוא",
65
+ "היא",
66
+ "היה",
67
+ "היכן",
68
+ "היתה",
69
+ "היתי",
70
+ "הם",
71
+ "הן",
72
+ "הנה",
73
+ "הסיבהשבגללה",
74
+ "הרי",
75
+ "ואילו",
76
+ "ואת",
77
+ "זאת",
78
+ "זה",
79
+ "זות",
80
+ "יהיה",
81
+ "יוכל",
82
+ "יוכלו",
83
+ "יותרמדי",
84
+ "יכול",
85
+ "יכולה",
86
+ "יכולות",
87
+ "יכולים",
88
+ "יכל",
89
+ "יכלה",
90
+ "יכלו",
91
+ "יש",
92
+ "כאן",
93
+ "כאשר",
94
+ "כולם",
95
+ "כולן",
96
+ "כזה",
97
+ "כי",
98
+ "כיצד",
99
+ "כך",
100
+ "ככה",
101
+ "כל",
102
+ "כלל",
103
+ "כמו",
104
+ "כן",
105
+ "כפי",
106
+ "כש",
107
+ "לא",
108
+ "לאו",
109
+ "לאיזותכלית",
110
+ "לאן",
111
+ "לבין",
112
+ "לה",
113
+ "להיות",
114
+ "להם",
115
+ "להן",
116
+ "לו",
117
+ "לי",
118
+ "לכם",
119
+ "לכן",
120
+ "למה",
121
+ "למטה",
122
+ "למעלה",
123
+ "למקוםשבו",
124
+ "למרות",
125
+ "לנו",
126
+ "לעבר",
127
+ "לעיכן",
128
+ "לפיכך",
129
+ "לפני",
130
+ "מאד",
131
+ "מאחורי",
132
+ "מאיזוסיבה",
133
+ "מאין",
134
+ "מאיפה",
135
+ "מבלי",
136
+ "מבעד",
137
+ "מדוע",
138
+ "מה",
139
+ "מהיכן",
140
+ "מול",
141
+ "מחוץ",
142
+ "מי",
143
+ "מכאן",
144
+ "מכיוון",
145
+ "מלבד",
146
+ "מן",
147
+ "מנין",
148
+ "מסוגל",
149
+ "מעט",
150
+ "מעטים",
151
+ "מעל",
152
+ "מצד",
153
+ "מקוםבו",
154
+ "מתחת",
155
+ "מתי",
156
+ "נגד",
157
+ "נגר",
158
+ "נו",
159
+ "עד",
160
+ "עז",
161
+ "על",
162
+ "עלי",
163
+ "עליה",
164
+ "עליהם",
165
+ "עליהן",
166
+ "עליו",
167
+ "עליך",
168
+ "עליכם",
169
+ "עלינו",
170
+ "עם",
171
+ "עצמה",
172
+ "עצמהם",
173
+ "עצמהן",
174
+ "עצמו",
175
+ "עצמי",
176
+ "עצמם",
177
+ "עצמן",
178
+ "עצמנו",
179
+ "פה",
180
+ "רק",
181
+ "שוב",
182
+ "של",
183
+ "שלה",
184
+ "שלהם",
185
+ "שלהן",
186
+ "שלו",
187
+ "שלי",
188
+ "שלך",
189
+ "שלכה",
190
+ "שלכם",
191
+ "שלכן",
192
+ "שלנו",
193
+ "שם",
194
+ "תהיה",
195
+ "תחת"
196
+ ]