@delali/narsil-react-native 0.3.1-next.154 → 0.3.1-next.156

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 (253) hide show
  1. package/NOTICE +144 -0
  2. package/NarsilReactNative.podspec +2 -2
  3. package/android/CMakeLists.txt +1 -1
  4. package/cpp/HybridNarsilCoreAnalysis.cpp +277 -0
  5. package/cpp/HybridNarsilCoreImpl.hpp +43 -0
  6. package/cpp/HybridNarsilCoreKeyword.cpp +253 -0
  7. package/cpp/HybridNarsilCoreMath.cpp +47 -0
  8. package/cpp/core/include/narsil_analysis.h +86 -0
  9. package/cpp/core/include/narsil_core.h +1 -1
  10. package/cpp/core/include/narsil_keyword.h +110 -0
  11. package/cpp/core/include/narsil_math.h +36 -0
  12. package/cpp/core/src/analysis/analyse.c +281 -0
  13. package/cpp/core/src/analysis/analyser.h +49 -0
  14. package/cpp/core/src/analysis/languages.c +79 -0
  15. package/cpp/core/src/analysis/languages.h +42 -0
  16. package/cpp/core/src/analysis/normalise.c +242 -0
  17. package/cpp/core/src/analysis/normalise.h +28 -0
  18. package/cpp/core/src/analysis/split.c +183 -0
  19. package/cpp/core/src/analysis/split.h +27 -0
  20. package/cpp/core/src/analysis/stop_words.c +82 -0
  21. package/cpp/core/src/analysis/stop_words.h +19 -0
  22. package/cpp/core/src/analysis/term_cache.c +88 -0
  23. package/cpp/core/src/analysis/term_cache.h +36 -0
  24. package/cpp/core/src/analysis/text.c +161 -0
  25. package/cpp/core/src/analysis/text.h +45 -0
  26. package/cpp/core/src/analysis/transform.c +103 -0
  27. package/cpp/core/src/analysis/unicode.c +252 -0
  28. package/cpp/core/src/analysis/unicode.h +54 -0
  29. package/cpp/core/src/internal.h +4 -0
  30. package/cpp/core/src/keyword/pass.h +117 -0
  31. package/cpp/core/src/keyword/prune.c +324 -0
  32. package/cpp/core/src/keyword/request.c +179 -0
  33. package/cpp/core/src/keyword/rows.c +83 -0
  34. package/cpp/core/src/keyword/rows.h +18 -0
  35. package/cpp/core/src/keyword/score.c +257 -0
  36. package/cpp/core/src/keyword/score.h +17 -0
  37. package/cpp/core/src/keyword/scratch.c +226 -0
  38. package/cpp/core/src/keyword/scratch.h +55 -0
  39. package/cpp/core/src/keyword/select.c +155 -0
  40. package/cpp/core/src/keyword/select.h +17 -0
  41. package/cpp/core/src/languages/bulgarian_stemmer.c +114 -0
  42. package/cpp/core/src/languages/data/albanian.c +54 -0
  43. package/cpp/core/src/languages/data/amharic.c +93 -0
  44. package/cpp/core/src/languages/data/arabic.c +146 -0
  45. package/cpp/core/src/languages/data/armenian.c +46 -0
  46. package/cpp/core/src/languages/data/azerbaijani.c +68 -0
  47. package/cpp/core/src/languages/data/bambara.c +48 -0
  48. package/cpp/core/src/languages/data/basque.c +62 -0
  49. package/cpp/core/src/languages/data/belarusian.c +56 -0
  50. package/cpp/core/src/languages/data/bengali.c +63 -0
  51. package/cpp/core/src/languages/data/bosnian.c +73 -0
  52. package/cpp/core/src/languages/data/breton.c +52 -0
  53. package/cpp/core/src/languages/data/bulgarian.c +144 -0
  54. package/cpp/core/src/languages/data/burmese.c +48 -0
  55. package/cpp/core/src/languages/data/catalan.c +84 -0
  56. package/cpp/core/src/languages/data/chinese.c +70 -0
  57. package/cpp/core/src/languages/data/croatian.c +72 -0
  58. package/cpp/core/src/languages/data/czech.c +72 -0
  59. package/cpp/core/src/languages/data/dagbani.c +88 -0
  60. package/cpp/core/src/languages/data/danish.c +56 -0
  61. package/cpp/core/src/languages/data/declarations.h +114 -0
  62. package/cpp/core/src/languages/data/dutch.c +58 -0
  63. package/cpp/core/src/languages/data/english.c +172 -0
  64. package/cpp/core/src/languages/data/esperanto.c +71 -0
  65. package/cpp/core/src/languages/data/estonian.c +417 -0
  66. package/cpp/core/src/languages/data/ewe.c +89 -0
  67. package/cpp/core/src/languages/data/faroese.c +54 -0
  68. package/cpp/core/src/languages/data/fijian.c +44 -0
  69. package/cpp/core/src/languages/data/finnish.c +100 -0
  70. package/cpp/core/src/languages/data/french.c +74 -0
  71. package/cpp/core/src/languages/data/ga.c +83 -0
  72. package/cpp/core/src/languages/data/galician.c +70 -0
  73. package/cpp/core/src/languages/data/georgian.c +57 -0
  74. package/cpp/core/src/languages/data/german.c +96 -0
  75. package/cpp/core/src/languages/data/greek.c +202 -0
  76. package/cpp/core/src/languages/data/guarani.c +110 -0
  77. package/cpp/core/src/languages/data/gujarati.c +90 -0
  78. package/cpp/core/src/languages/data/haitian-creole.c +54 -0
  79. package/cpp/core/src/languages/data/hausa.c +85 -0
  80. package/cpp/core/src/languages/data/hawaiian.c +50 -0
  81. package/cpp/core/src/languages/data/hebrew.c +85 -0
  82. package/cpp/core/src/languages/data/hindi.c +91 -0
  83. package/cpp/core/src/languages/data/hungarian.c +98 -0
  84. package/cpp/core/src/languages/data/icelandic.c +73 -0
  85. package/cpp/core/src/languages/data/igbo.c +90 -0
  86. package/cpp/core/src/languages/data/indonesian.c +296 -0
  87. package/cpp/core/src/languages/data/irish.c +60 -0
  88. package/cpp/core/src/languages/data/italian.c +107 -0
  89. package/cpp/core/src/languages/data/japanese.c +52 -0
  90. package/cpp/core/src/languages/data/kannada.c +60 -0
  91. package/cpp/core/src/languages/data/kazakh.c +57 -0
  92. package/cpp/core/src/languages/data/khmer.c +71 -0
  93. package/cpp/core/src/languages/data/kinyarwanda.c +54 -0
  94. package/cpp/core/src/languages/data/kirundi.c +53 -0
  95. package/cpp/core/src/languages/data/korean.c +74 -0
  96. package/cpp/core/src/languages/data/kurmanji.c +43 -0
  97. package/cpp/core/src/languages/data/kyrgyz.c +65 -0
  98. package/cpp/core/src/languages/data/lao.c +46 -0
  99. package/cpp/core/src/languages/data/latin.c +46 -0
  100. package/cpp/core/src/languages/data/latvian.c +75 -0
  101. package/cpp/core/src/languages/data/lingala.c +88 -0
  102. package/cpp/core/src/languages/data/lithuanian.c +65 -0
  103. package/cpp/core/src/languages/data/luxembourgish.c +80 -0
  104. package/cpp/core/src/languages/data/macedonian.c +286 -0
  105. package/cpp/core/src/languages/data/malagasy.c +51 -0
  106. package/cpp/core/src/languages/data/malay.c +184 -0
  107. package/cpp/core/src/languages/data/malayalam.c +64 -0
  108. package/cpp/core/src/languages/data/maltese.c +102 -0
  109. package/cpp/core/src/languages/data/maori.c +52 -0
  110. package/cpp/core/src/languages/data/marathi.c +62 -0
  111. package/cpp/core/src/languages/data/nepali.c +72 -0
  112. package/cpp/core/src/languages/data/norwegian.c +74 -0
  113. package/cpp/core/src/languages/data/oromo.c +51 -0
  114. package/cpp/core/src/languages/data/persian.c +150 -0
  115. package/cpp/core/src/languages/data/polish.c +111 -0
  116. package/cpp/core/src/languages/data/portuguese.c +91 -0
  117. package/cpp/core/src/languages/data/punjabi.c +80 -0
  118. package/cpp/core/src/languages/data/registry.c +116 -0
  119. package/cpp/core/src/languages/data/romanian.c +93 -0
  120. package/cpp/core/src/languages/data/russian.c +76 -0
  121. package/cpp/core/src/languages/data/samoan.c +47 -0
  122. package/cpp/core/src/languages/data/sanskrit.c +53 -0
  123. package/cpp/core/src/languages/data/scottish-gaelic.c +119 -0
  124. package/cpp/core/src/languages/data/serbian.c +84 -0
  125. package/cpp/core/src/languages/data/shona.c +55 -0
  126. package/cpp/core/src/languages/data/sinhala.c +78 -0
  127. package/cpp/core/src/languages/data/slovak.c +135 -0
  128. package/cpp/core/src/languages/data/slovenian.c +139 -0
  129. package/cpp/core/src/languages/data/sorani.c +55 -0
  130. package/cpp/core/src/languages/data/spanish.c +84 -0
  131. package/cpp/core/src/languages/data/swahili.c +59 -0
  132. package/cpp/core/src/languages/data/swedish.c +60 -0
  133. package/cpp/core/src/languages/data/tagalog.c +75 -0
  134. package/cpp/core/src/languages/data/tamil.c +69 -0
  135. package/cpp/core/src/languages/data/tatar.c +548 -0
  136. package/cpp/core/src/languages/data/telugu.c +54 -0
  137. package/cpp/core/src/languages/data/thai.c +46 -0
  138. package/cpp/core/src/languages/data/tibetan.c +55 -0
  139. package/cpp/core/src/languages/data/tigrinya.c +73 -0
  140. package/cpp/core/src/languages/data/tongan.c +47 -0
  141. package/cpp/core/src/languages/data/turkish.c +100 -0
  142. package/cpp/core/src/languages/data/twi.c +88 -0
  143. package/cpp/core/src/languages/data/ukrainian.c +99 -0
  144. package/cpp/core/src/languages/data/urdu.c +174 -0
  145. package/cpp/core/src/languages/data/vietnamese.c +88 -0
  146. package/cpp/core/src/languages/data/welsh.c +143 -0
  147. package/cpp/core/src/languages/data/wolof.c +51 -0
  148. package/cpp/core/src/languages/data/xhosa.c +56 -0
  149. package/cpp/core/src/languages/data/yoruba.c +93 -0
  150. package/cpp/core/src/languages/data/zulu.c +58 -0
  151. package/cpp/core/src/languages/marks.c +64 -0
  152. package/cpp/core/src/languages/rules.c +63 -0
  153. package/cpp/core/src/languages/rules.h +68 -0
  154. package/cpp/core/src/languages/sanskrit_stemmer.c +50 -0
  155. package/cpp/core/src/languages/scripts.c +143 -0
  156. package/cpp/core/src/languages/slovenian_stemmer.c +46 -0
  157. package/cpp/core/src/languages/snowball/api.c +52 -0
  158. package/cpp/core/src/languages/snowball/api.h +43 -0
  159. package/cpp/core/src/languages/snowball/arabic_stemmer.c +1506 -0
  160. package/cpp/core/src/languages/snowball/arabic_stemmer.h +24 -0
  161. package/cpp/core/src/languages/snowball/armenian_stemmer.c +523 -0
  162. package/cpp/core/src/languages/snowball/armenian_stemmer.h +24 -0
  163. package/cpp/core/src/languages/snowball/basque_stemmer.c +1089 -0
  164. package/cpp/core/src/languages/snowball/basque_stemmer.h +24 -0
  165. package/cpp/core/src/languages/snowball/catalan_stemmer.c +1380 -0
  166. package/cpp/core/src/languages/snowball/catalan_stemmer.h +24 -0
  167. package/cpp/core/src/languages/snowball/czech_stemmer.c +582 -0
  168. package/cpp/core/src/languages/snowball/czech_stemmer.h +24 -0
  169. package/cpp/core/src/languages/snowball/danish_stemmer.c +352 -0
  170. package/cpp/core/src/languages/snowball/danish_stemmer.h +24 -0
  171. package/cpp/core/src/languages/snowball/dutch_stemmer.c +1657 -0
  172. package/cpp/core/src/languages/snowball/dutch_stemmer.h +24 -0
  173. package/cpp/core/src/languages/snowball/english_stemmer.c +1019 -0
  174. package/cpp/core/src/languages/snowball/english_stemmer.h +24 -0
  175. package/cpp/core/src/languages/snowball/esperanto_stemmer.c +716 -0
  176. package/cpp/core/src/languages/snowball/esperanto_stemmer.h +24 -0
  177. package/cpp/core/src/languages/snowball/estonian_stemmer.c +1361 -0
  178. package/cpp/core/src/languages/snowball/estonian_stemmer.h +24 -0
  179. package/cpp/core/src/languages/snowball/finnish_stemmer.c +800 -0
  180. package/cpp/core/src/languages/snowball/finnish_stemmer.h +24 -0
  181. package/cpp/core/src/languages/snowball/french_stemmer.c +1217 -0
  182. package/cpp/core/src/languages/snowball/french_stemmer.h +24 -0
  183. package/cpp/core/src/languages/snowball/german_stemmer.c +567 -0
  184. package/cpp/core/src/languages/snowball/german_stemmer.h +24 -0
  185. package/cpp/core/src/languages/snowball/greek_stemmer.c +3450 -0
  186. package/cpp/core/src/languages/snowball/greek_stemmer.h +24 -0
  187. package/cpp/core/src/languages/snowball/hindi_stemmer.c +325 -0
  188. package/cpp/core/src/languages/snowball/hindi_stemmer.h +24 -0
  189. package/cpp/core/src/languages/snowball/hungarian_stemmer.c +742 -0
  190. package/cpp/core/src/languages/snowball/hungarian_stemmer.h +24 -0
  191. package/cpp/core/src/languages/snowball/indonesian_stemmer.c +443 -0
  192. package/cpp/core/src/languages/snowball/indonesian_stemmer.h +24 -0
  193. package/cpp/core/src/languages/snowball/irish_stemmer.c +428 -0
  194. package/cpp/core/src/languages/snowball/irish_stemmer.h +24 -0
  195. package/cpp/core/src/languages/snowball/italian_stemmer.c +983 -0
  196. package/cpp/core/src/languages/snowball/italian_stemmer.h +24 -0
  197. package/cpp/core/src/languages/snowball/lithuanian_stemmer.c +794 -0
  198. package/cpp/core/src/languages/snowball/lithuanian_stemmer.h +24 -0
  199. package/cpp/core/src/languages/snowball/nepali_stemmer.c +361 -0
  200. package/cpp/core/src/languages/snowball/nepali_stemmer.h +24 -0
  201. package/cpp/core/src/languages/snowball/norwegian_stemmer.c +332 -0
  202. package/cpp/core/src/languages/snowball/norwegian_stemmer.h +24 -0
  203. package/cpp/core/src/languages/snowball/persian_stemmer.c +538 -0
  204. package/cpp/core/src/languages/snowball/persian_stemmer.h +24 -0
  205. package/cpp/core/src/languages/snowball/polish_stemmer.c +501 -0
  206. package/cpp/core/src/languages/snowball/polish_stemmer.h +24 -0
  207. package/cpp/core/src/languages/snowball/portuguese_stemmer.c +866 -0
  208. package/cpp/core/src/languages/snowball/portuguese_stemmer.h +24 -0
  209. package/cpp/core/src/languages/snowball/romanian_stemmer.c +940 -0
  210. package/cpp/core/src/languages/snowball/romanian_stemmer.h +24 -0
  211. package/cpp/core/src/languages/snowball/russian_stemmer.c +598 -0
  212. package/cpp/core/src/languages/snowball/russian_stemmer.h +24 -0
  213. package/cpp/core/src/languages/snowball/serbian_stemmer.c +6765 -0
  214. package/cpp/core/src/languages/snowball/serbian_stemmer.h +24 -0
  215. package/cpp/core/src/languages/snowball/snowball_runtime.h +122 -0
  216. package/cpp/core/src/languages/snowball/spanish_stemmer.c +955 -0
  217. package/cpp/core/src/languages/snowball/spanish_stemmer.h +24 -0
  218. package/cpp/core/src/languages/snowball/swedish_stemmer.c +364 -0
  219. package/cpp/core/src/languages/snowball/swedish_stemmer.h +24 -0
  220. package/cpp/core/src/languages/snowball/tamil_stemmer.c +1305 -0
  221. package/cpp/core/src/languages/snowball/tamil_stemmer.h +24 -0
  222. package/cpp/core/src/languages/snowball/turkish_stemmer.c +1700 -0
  223. package/cpp/core/src/languages/snowball/turkish_stemmer.h +24 -0
  224. package/cpp/core/src/languages/snowball/utilities.c +716 -0
  225. package/cpp/core/src/languages/substitutions.c +131 -0
  226. package/cpp/core/src/languages/swahili_stemmer.c +85 -0
  227. package/cpp/core/src/languages/ukrainian_stemmer.c +168 -0
  228. package/cpp/core/src/locks.c +2 -15
  229. package/cpp/core/src/math/apply.c +44 -0
  230. package/cpp/core/src/math/fdlibm.h +16 -0
  231. package/cpp/core/src/math/inverse.c +242 -0
  232. package/cpp/core/src/math/log.c +90 -0
  233. package/cpp/core/src/math/reduce.c +325 -0
  234. package/cpp/core/src/math/trig.c +188 -0
  235. package/cpp/core/src/math/words.h +45 -0
  236. package/cpp/core/src/thread_yield.h +18 -0
  237. package/cpp/core/src/unicode/decompositions.c +310 -0
  238. package/cpp/core/src/unicode/lowercase.c +172 -0
  239. package/cpp/core/src/unicode/properties.c +214 -0
  240. package/cpp/core/src/workspace.c +5 -1
  241. package/lib/engine/analysis.d.ts +3 -0
  242. package/lib/engine/analysis.js +76 -0
  243. package/lib/engine/core.js +5 -0
  244. package/lib/engine/keyword.d.ts +3 -0
  245. package/lib/engine/keyword.js +25 -0
  246. package/lib/specs/core.nitro.d.ts +1 -0
  247. package/nitrogen/generated/shared/c++/HybridNarsilCoreSpec.cpp +1 -0
  248. package/nitrogen/generated/shared/c++/HybridNarsilCoreSpec.hpp +1 -0
  249. package/package.json +4 -3
  250. package/src/engine/analysis.ts +87 -0
  251. package/src/engine/core.ts +6 -0
  252. package/src/engine/keyword.ts +26 -0
  253. package/src/specs/core.nitro.ts +1 -0
@@ -0,0 +1,202 @@
1
+ #include "../../analysis/languages.h"
2
+ #include "declarations.h"
3
+ #include "../rules.h"
4
+ #include "../snowball/greek_stemmer.h"
5
+
6
+ #include <stddef.h>
7
+ #include <stdint.h>
8
+
9
+ static const uint16_t stop_word_units[3061] = {
10
+ 945, 953, 945, 954, 959, 956, 945, 945, 954, 959, 956, 951, 945, 954, 961, 953, 946, 969, 963, 945, 955, 951, 952,
11
+ 949, 953, 945, 945, 955, 951, 952, 953, 957, 945, 945, 955, 955, 945, 945, 955, 955, 945, 967, 959, 965, 945, 955,
12
+ 955, 949, 963, 945, 955, 955, 951, 945, 955, 955, 951, 957, 945, 955, 955, 951, 963, 945, 955, 955, 953, 969, 963,
13
+ 945, 955, 955, 953, 969, 964, 953, 954, 945, 945, 955, 955, 959, 945, 955, 955, 959, 953, 945, 955, 955, 959, 953,
14
+ 969, 963, 945, 955, 955, 959, 953, 969, 964, 953, 954, 945, 945, 955, 955, 959, 957, 945, 955, 955, 959, 963, 945,
15
+ 955, 955, 959, 964, 949, 945, 955, 955, 959, 965, 945, 955, 955, 959, 965, 963, 945, 955, 955, 969, 957, 945, 956,
16
+ 945, 945, 956, 949, 963, 945, 945, 956, 949, 963, 969, 963, 945, 957, 945, 957, 945, 945, 957, 945, 956, 949, 963,
17
+ 945, 945, 957, 945, 956, 949, 964, 945, 958, 965, 945, 957, 949, 965, 945, 957, 964, 953, 945, 957, 964, 953, 960,
18
+ 949, 961, 945, 945, 957, 964, 953, 963, 945, 957, 969, 945, 957, 969, 964, 949, 961, 969, 945, 958, 945, 966, 957,
19
+ 945, 945, 960, 945, 960, 949, 957, 945, 957, 964, 953, 945, 960, 959, 945, 960, 959, 968, 949, 945, 961, 945, 945,
20
+ 961, 945, 947, 949, 945, 961, 947, 945, 945, 961, 947, 959, 964, 949, 961, 959, 945, 961, 953, 963, 964, 949, 961,
21
+ 945, 945, 961, 954, 949, 964, 945, 945, 961, 967, 953, 954, 945, 945, 963, 945, 965, 961, 953, 959, 945, 965, 964,
22
+ 945, 945, 965, 964, 949, 963, 945, 965, 964, 951, 945, 965, 964, 951, 957, 945, 965, 964, 951, 963, 945, 965, 964,
23
+ 959, 945, 965, 964, 959, 953, 945, 965, 964, 959, 957, 945, 965, 964, 959, 963, 945, 965, 964, 959, 965, 945, 965,
24
+ 964, 959, 965, 963, 945, 965, 964, 969, 957, 945, 966, 959, 964, 959, 965, 945, 966, 959, 965, 946, 949, 946, 945,
25
+ 953, 945, 946, 949, 946, 945, 953, 959, 964, 945, 964, 945, 947, 945, 947, 945, 961, 947, 949, 947, 953, 947, 953,
26
+ 945, 947, 961, 951, 947, 959, 961, 945, 947, 965, 961, 969, 948, 945, 953, 948, 945, 953, 963, 948, 949, 948, 949,
27
+ 957, 948, 951, 948, 951, 955, 945, 948, 951, 948, 953, 948, 953, 945, 949, 945, 957, 949, 945, 965, 964, 959, 949,
28
+ 945, 965, 964, 959, 957, 949, 945, 965, 964, 959, 965, 949, 945, 965, 964, 959, 965, 963, 949, 945, 965, 964, 969,
29
+ 957, 949, 947, 954, 945, 953, 961, 945, 949, 947, 954, 945, 953, 961, 969, 963, 949, 947, 969, 949, 948, 969, 949,
30
+ 953, 952, 949, 949, 953, 956, 945, 953, 949, 953, 956, 945, 963, 964, 949, 949, 953, 957, 945, 953, 949, 953, 963,
31
+ 949, 953, 963, 945, 953, 949, 953, 963, 945, 963, 964, 949, 949, 953, 963, 964, 949, 949, 953, 964, 949, 949, 953,
32
+ 967, 945, 949, 953, 967, 945, 956, 949, 949, 953, 967, 945, 957, 949, 953, 967, 945, 964, 949, 949, 953, 967, 949,
33
+ 949, 953, 967, 949, 963, 949, 954, 949, 954, 945, 963, 964, 945, 949, 954, 945, 963, 964, 949, 963, 949, 954, 945,
34
+ 963, 964, 951, 949, 954, 945, 963, 964, 951, 957, 949, 954, 945, 963, 964, 951, 963, 949, 954, 945, 963, 964, 959,
35
+ 949, 954, 945, 963, 964, 959, 953, 949, 954, 945, 963, 964, 959, 957, 949, 954, 945, 963, 964, 959, 963, 949, 954,
36
+ 945, 963, 964, 959, 965, 949, 954, 945, 963, 964, 959, 965, 963, 949, 954, 945, 963, 964, 969, 957, 949, 954, 949,
37
+ 953, 949, 954, 949, 953, 957, 945, 949, 954, 949, 953, 957, 949, 963, 949, 954, 949, 953, 957, 951, 949, 954, 949,
38
+ 953, 957, 951, 957, 949, 954, 949, 953, 957, 951, 963, 949, 954, 949, 953, 957, 959, 949, 954, 949, 953, 957, 959,
39
+ 953, 949, 954, 949, 953, 957, 959, 957, 949, 954, 949, 953, 957, 959, 963, 949, 954, 949, 953, 957, 959, 965, 949,
40
+ 954, 949, 953, 957, 959, 965, 963, 949, 954, 949, 953, 957, 969, 957, 949, 954, 964, 959, 963, 949, 956, 945, 963,
41
+ 949, 956, 949, 953, 963, 949, 956, 949, 957, 945, 949, 956, 960, 961, 959, 963, 949, 957, 949, 957, 945, 949, 957,
42
+ 945, 957, 949, 957, 945, 963, 949, 957, 959, 963, 949, 957, 964, 949, 955, 969, 963, 949, 957, 964, 959, 963, 949,
43
+ 957, 964, 969, 956, 949, 964, 945, 958, 965, 949, 957, 969, 949, 958, 949, 958, 945, 966, 957, 945, 949, 958, 951,
44
+ 963, 949, 958, 953, 963, 959, 965, 949, 958, 969, 949, 960, 949, 960, 945, 957, 969, 949, 960, 949, 953, 948, 951,
45
+ 949, 960, 949, 953, 964, 945, 949, 960, 953, 949, 960, 953, 963, 951, 963, 949, 960, 959, 956, 949, 957, 969, 963,
46
+ 949, 963, 945, 963, 949, 963, 949, 953, 963, 949, 963, 949, 957, 945, 949, 963, 964, 969, 949, 963, 965, 949, 964,
47
+ 949, 961, 945, 949, 964, 949, 961, 945, 953, 949, 964, 949, 961, 945, 963, 949, 964, 949, 961, 949, 963, 949, 964,
48
+ 949, 961, 951, 949, 964, 949, 961, 951, 963, 949, 964, 949, 961, 959, 949, 964, 949, 961, 959, 953, 949, 964, 949,
49
+ 961, 959, 957, 949, 964, 949, 961, 959, 963, 949, 964, 949, 961, 959, 965, 949, 964, 949, 961, 959, 965, 963, 949,
50
+ 964, 949, 961, 969, 957, 949, 964, 959, 965, 964, 945, 949, 964, 959, 965, 964, 949, 963, 949, 964, 959, 965, 964,
51
+ 951, 949, 964, 959, 965, 964, 951, 957, 949, 964, 959, 965, 964, 951, 963, 949, 964, 959, 965, 964, 959, 949, 964,
52
+ 959, 965, 964, 959, 953, 949, 964, 959, 965, 964, 959, 957, 949, 964, 959, 965, 964, 959, 963, 949, 964, 959, 965,
53
+ 964, 959, 965, 949, 964, 959, 965, 964, 959, 965, 963, 949, 964, 959, 965, 964, 969, 957, 949, 964, 963, 953, 949,
54
+ 965, 947, 949, 949, 965, 952, 965, 963, 949, 965, 964, 965, 967, 969, 963, 949, 966, 949, 958, 951, 963, 949, 967,
55
+ 949, 953, 949, 967, 949, 953, 963, 949, 967, 949, 964, 949, 949, 967, 952, 949, 963, 949, 967, 959, 956, 949, 949,
56
+ 967, 959, 965, 956, 949, 949, 967, 959, 965, 957, 949, 967, 964, 949, 963, 949, 967, 969, 949, 969, 963, 951, 951,
57
+ 956, 945, 963, 964, 945, 957, 951, 956, 945, 963, 964, 949, 951, 956, 959, 965, 957, 951, 963, 945, 963, 964, 945,
58
+ 957, 951, 963, 945, 963, 964, 949, 951, 963, 959, 965, 957, 951, 964, 945, 957, 951, 964, 945, 957, 949, 951, 964,
59
+ 959, 953, 951, 964, 964, 959, 957, 952, 945, 953, 953, 953, 953, 953, 953, 953, 963, 945, 956, 949, 953, 963, 953,
60
+ 945, 953, 963, 969, 963, 954, 954, 945, 952, 954, 945, 952, 949, 954, 945, 952, 949, 956, 953, 945, 954, 945, 952,
61
+ 949, 956, 953, 945, 963, 954, 945, 952, 949, 957, 945, 954, 945, 952, 949, 957, 945, 963, 954, 945, 952, 949, 957,
62
+ 959, 963, 954, 945, 952, 949, 964, 953, 954, 945, 952, 959, 955, 959, 965, 954, 945, 952, 969, 963, 954, 945, 953,
63
+ 954, 945, 953, 964, 959, 953, 954, 945, 954, 945, 954, 945, 954, 969, 963, 954, 945, 955, 945, 954, 945, 955, 969,
64
+ 963, 954, 945, 956, 953, 945, 954, 945, 956, 953, 945, 957, 954, 945, 956, 953, 945, 963, 954, 945, 956, 960, 959,
65
+ 963, 945, 954, 945, 956, 960, 959, 963, 949, 963, 954, 945, 956, 960, 959, 963, 951, 954, 945, 956, 960, 959, 963,
66
+ 951, 957, 954, 945, 956, 960, 959, 963, 951, 963, 954, 945, 956, 960, 959, 963, 959, 954, 945, 956, 960, 959, 963,
67
+ 959, 953, 954, 945, 956, 960, 959, 963, 959, 957, 954, 945, 956, 960, 959, 963, 959, 963, 954, 945, 956, 960, 959,
68
+ 963, 959, 965, 954, 945, 956, 960, 959, 963, 959, 965, 963, 954, 945, 956, 960, 959, 963, 969, 957, 954, 945, 957,
69
+ 949, 953, 963, 954, 945, 957, 949, 957, 954, 945, 957, 949, 957, 945, 954, 945, 957, 949, 957, 945, 957, 954, 945,
70
+ 957, 949, 957, 945, 963, 954, 945, 957, 949, 957, 959, 963, 954, 945, 960, 959, 953, 945, 954, 945, 960, 959, 953,
71
+ 945, 957, 954, 945, 960, 959, 953, 945, 963, 954, 945, 960, 959, 953, 949, 963, 954, 945, 960, 959, 953, 959, 954,
72
+ 945, 960, 959, 953, 959, 953, 954, 945, 960, 959, 953, 959, 957, 954, 945, 960, 959, 953, 959, 963, 954, 945, 960,
73
+ 959, 953, 959, 965, 954, 945, 960, 959, 953, 959, 965, 963, 954, 945, 960, 959, 953, 969, 957, 954, 945, 960, 959,
74
+ 964, 949, 954, 945, 960, 959, 965, 954, 945, 960, 969, 963, 954, 945, 964, 954, 945, 964, 945, 954, 945, 964, 953,
75
+ 954, 945, 964, 953, 964, 953, 954, 945, 964, 959, 960, 953, 957, 954, 945, 964, 969, 954, 953, 954, 953, 959, 955,
76
+ 945, 963, 954, 955, 960, 954, 959, 957, 964, 945, 954, 964, 955, 954, 965, 961, 953, 969, 963, 955, 953, 947, 945,
77
+ 954, 953, 955, 953, 947, 959, 955, 953, 947, 969, 964, 949, 961, 959, 955, 959, 947, 969, 955, 959, 953, 960, 945,
78
+ 955, 959, 953, 960, 959, 957, 956, 945, 956, 945, 950, 953, 956, 945, 954, 945, 961, 953, 956, 945, 954, 961, 965,
79
+ 945, 956, 945, 955, 953, 963, 964, 945, 956, 945, 955, 955, 959, 957, 956, 945, 963, 956, 949, 956, 949, 952, 956,
80
+ 949, 952, 945, 965, 961, 953, 959, 956, 949, 953, 959, 957, 956, 949, 955, 949, 953, 956, 949, 955, 955, 949, 964,
81
+ 945, 953, 956, 949, 956, 953, 945, 963, 956, 949, 957, 956, 949, 961, 953, 954, 945, 956, 949, 961, 953, 954, 949,
82
+ 963, 956, 949, 961, 953, 954, 959, 953, 956, 949, 961, 953, 954, 959, 965, 963, 956, 949, 961, 953, 954, 969, 957,
83
+ 956, 949, 963, 945, 956, 949, 964, 956, 949, 964, 945, 956, 949, 964, 945, 958, 965, 956, 949, 967, 961, 953, 956,
84
+ 951, 956, 951, 957, 956, 951, 960, 969, 963, 956, 951, 964, 949, 956, 953, 945, 956, 953, 945, 957, 956, 953, 945,
85
+ 963, 956, 959, 955, 953, 963, 956, 959, 955, 959, 957, 959, 964, 953, 956, 959, 957, 945, 967, 945, 956, 959, 957,
86
+ 949, 963, 956, 959, 957, 951, 956, 959, 957, 951, 957, 956, 959, 957, 951, 963, 956, 959, 957, 959, 956, 959, 957,
87
+ 959, 953, 956, 959, 957, 959, 956, 953, 945, 963, 956, 959, 957, 959, 963, 956, 959, 957, 959, 965, 956, 959, 957,
88
+ 959, 965, 963, 956, 959, 957, 969, 957, 956, 959, 965, 956, 960, 959, 961, 949, 953, 956, 960, 959, 961, 959, 965,
89
+ 957, 956, 960, 961, 945, 946, 959, 956, 960, 961, 959, 963, 957, 945, 957, 945, 953, 957, 969, 961, 953, 963, 958,
90
+ 945, 957, 945, 958, 945, 966, 957, 953, 954, 945, 959, 959, 953, 959, 955, 945, 959, 955, 949, 963, 959, 955, 951,
91
+ 959, 955, 951, 957, 959, 955, 951, 963, 959, 955, 959, 959, 955, 959, 947, 965, 961, 945, 959, 955, 959, 953, 959,
92
+ 955, 959, 957, 959, 955, 959, 957, 949, 957, 959, 955, 959, 963, 959, 955, 959, 964, 949, 955, 945, 959, 955, 959,
93
+ 965, 959, 955, 959, 965, 963, 959, 955, 969, 957, 959, 955, 969, 963, 959, 956, 969, 963, 959, 960, 959, 953, 945,
94
+ 959, 960, 959, 953, 945, 957, 959, 960, 959, 953, 945, 963, 959, 960, 959, 953, 949, 963, 959, 960, 959, 953, 959,
95
+ 959, 960, 959, 953, 959, 953, 959, 960, 959, 953, 959, 957, 959, 960, 959, 953, 959, 963, 959, 960, 959, 953, 959,
96
+ 965, 959, 960, 959, 953, 959, 965, 963, 959, 960, 959, 953, 969, 957, 959, 960, 959, 964, 949, 959, 960, 959, 965,
97
+ 959, 960, 969, 963, 959, 961, 953, 963, 956, 949, 957, 945, 959, 961, 953, 963, 956, 949, 957, 949, 963, 959, 961,
98
+ 953, 963, 956, 949, 957, 969, 957, 959, 961, 953, 963, 956, 949, 957, 969, 963, 959, 963, 945, 959, 963, 949, 963,
99
+ 959, 963, 951, 959, 963, 951, 957, 959, 963, 951, 963, 959, 963, 959, 959, 963, 959, 953, 959, 963, 959, 957, 959,
100
+ 963, 959, 963, 959, 963, 959, 965, 959, 963, 959, 965, 963, 959, 963, 969, 957, 959, 964, 945, 957, 959, 964, 953,
101
+ 959, 964, 959, 965, 959, 965, 959, 965, 964, 949, 959, 967, 953, 960, 945, 955, 953, 960, 945, 957, 964, 945, 960,
102
+ 945, 957, 964, 959, 964, 949, 960, 945, 957, 964, 959, 965, 960, 945, 957, 964, 969, 963, 960, 945, 961, 960, 945,
103
+ 961, 945, 960, 949, 961, 945, 960, 949, 961, 953, 960, 949, 961, 953, 960, 959, 965, 960, 949, 961, 953, 963, 963,
104
+ 959, 964, 949, 961, 959, 960, 949, 961, 963, 953, 960, 949, 961, 965, 963, 953, 960, 953, 945, 960, 953, 952, 945,
105
+ 957, 959, 957, 960, 953, 959, 960, 953, 963, 969, 960, 955, 945, 953, 960, 955, 949, 959, 957, 960, 955, 951, 957,
106
+ 960, 959, 953, 945, 960, 959, 953, 945, 957, 960, 959, 953, 945, 963, 960, 959, 953, 949, 963, 960, 959, 953, 959,
107
+ 960, 959, 953, 959, 953, 960, 959, 953, 959, 957, 960, 959, 953, 959, 963, 960, 959, 953, 959, 965, 960, 959, 953,
108
+ 959, 965, 963, 960, 959, 953, 969, 957, 960, 959, 955, 965, 960, 959, 963, 949, 963, 960, 959, 963, 951, 960, 959,
109
+ 963, 951, 957, 960, 959, 963, 951, 963, 960, 959, 963, 959, 953, 960, 959, 963, 959, 963, 960, 959, 963, 959, 965,
110
+ 963, 960, 959, 964, 949, 960, 959, 965, 960, 959, 965, 952, 949, 960, 959, 965, 952, 949, 957, 945, 960, 961, 949,
111
+ 960, 949, 953, 960, 961, 953, 957, 960, 961, 959, 960, 961, 959, 954, 949, 953, 956, 949, 957, 959, 965, 960, 961,
112
+ 959, 954, 949, 953, 964, 945, 953, 960, 961, 959, 960, 949, 961, 963, 953, 960, 961, 959, 963, 960, 961, 959, 964,
113
+ 959, 965, 960, 961, 959, 967, 952, 949, 963, 960, 961, 959, 967, 964, 949, 963, 960, 961, 969, 964, 965, 964, 949,
114
+ 961, 945, 960, 969, 963, 963, 945, 957, 963, 945, 963, 963, 949, 963, 949, 953, 963, 963, 951, 956, 949, 961, 945,
115
+ 963, 953, 947, 945, 963, 959, 963, 963, 959, 965, 963, 964, 945, 963, 964, 951, 963, 964, 951, 957, 963, 964, 951,
116
+ 963, 963, 964, 953, 963, 963, 964, 959, 963, 964, 959, 957, 963, 964, 959, 965, 963, 964, 959, 965, 963, 963, 964,
117
+ 969, 957, 963, 965, 963, 965, 947, 967, 961, 959, 957, 969, 963, 963, 965, 957, 963, 965, 957, 945, 956, 945, 963,
118
+ 965, 957, 949, 960, 969, 963, 963, 965, 957, 951, 952, 969, 963, 963, 965, 967, 957, 945, 963, 965, 967, 957, 945,
119
+ 963, 963, 965, 967, 957, 949, 963, 963, 965, 967, 957, 951, 963, 965, 967, 957, 951, 957, 963, 965, 967, 957, 951,
120
+ 963, 963, 965, 967, 957, 959, 963, 965, 967, 957, 959, 953, 963, 965, 967, 957, 959, 957, 963, 965, 967, 957, 959,
121
+ 963, 963, 965, 967, 957, 959, 965, 963, 965, 967, 957, 959, 965, 963, 963, 965, 967, 957, 969, 957, 963, 965, 967,
122
+ 957, 969, 963, 963, 969, 963, 964, 945, 964, 945, 964, 945, 965, 964, 945, 964, 945, 965, 964, 949, 963, 964, 945,
123
+ 965, 964, 951, 964, 945, 965, 964, 951, 957, 964, 945, 965, 964, 951, 963, 964, 945, 965, 964, 959, 963, 964, 945,
124
+ 965, 964, 959, 965, 964, 945, 965, 964, 969, 957, 964, 945, 967, 945, 964, 945, 967, 945, 964, 949, 964, 949, 964,
125
+ 949, 955, 953, 954, 945, 964, 949, 955, 953, 954, 969, 963, 964, 949, 963, 964, 949, 964, 959, 953, 945, 964, 949,
126
+ 964, 959, 953, 945, 957, 964, 949, 964, 959, 953, 945, 963, 964, 949, 964, 959, 953, 949, 963, 964, 949, 964, 959,
127
+ 953, 959, 964, 949, 964, 959, 953, 959, 953, 964, 949, 964, 959, 953, 959, 957, 964, 949, 964, 959, 953, 959, 963,
128
+ 964, 949, 964, 959, 953, 959, 965, 964, 949, 964, 959, 953, 959, 965, 963, 964, 949, 964, 959, 953, 969, 957, 964,
129
+ 951, 964, 951, 957, 964, 951, 962, 964, 951, 963, 964, 953, 964, 953, 957, 945, 964, 953, 960, 959, 964, 945, 964,
130
+ 953, 960, 959, 964, 949, 964, 953, 962, 964, 953, 963, 964, 959, 964, 959, 953, 964, 959, 957, 964, 959, 963, 964,
131
+ 959, 963, 945, 964, 959, 963, 949, 963, 964, 959, 963, 951, 964, 959, 963, 951, 957, 964, 959, 963, 951, 963, 964,
132
+ 959, 963, 959, 964, 959, 963, 959, 953, 964, 959, 963, 959, 957, 964, 959, 963, 959, 963, 964, 959, 963, 959, 965,
133
+ 964, 959, 963, 959, 965, 963, 964, 959, 963, 969, 957, 964, 959, 964, 949, 964, 959, 965, 964, 959, 965, 955, 945,
134
+ 967, 953, 963, 964, 959, 964, 959, 965, 955, 945, 967, 953, 963, 964, 959, 957, 964, 959, 965, 962, 964, 959, 965,
135
+ 963, 964, 959, 965, 964, 945, 964, 959, 965, 964, 949, 963, 964, 959, 965, 964, 951, 964, 959, 965, 964, 951, 957,
136
+ 964, 959, 965, 964, 951, 963, 964, 959, 965, 964, 959, 964, 959, 965, 964, 959, 953, 964, 959, 965, 964, 959, 953,
137
+ 963, 964, 959, 965, 964, 959, 957, 964, 959, 965, 964, 959, 963, 964, 959, 965, 964, 959, 965, 964, 959, 965, 964,
138
+ 959, 965, 963, 964, 959, 965, 964, 969, 957, 964, 965, 967, 959, 957, 964, 969, 957, 964, 969, 961, 945, 965, 960,
139
+ 965, 960, 949, 961, 965, 960, 959, 965, 960, 959, 968, 951, 965, 960, 959, 968, 953, 957, 965, 963, 964, 949, 961,
140
+ 945, 966, 949, 964, 959, 963, 967, 945, 956, 951, 955, 945, 967, 952, 949, 963, 967, 964, 949, 963, 967, 969, 961,
141
+ 953, 963, 967, 969, 961, 953, 963, 964, 945, 968, 951, 955, 945, 969, 969, 961, 945, 953, 945, 969, 963, 969, 963,
142
+ 945, 957, 969, 963, 959, 964, 959, 965, 969, 963, 960, 959, 965, 969, 963, 964, 949, 969, 963, 964, 959, 963, 959,
143
+ 969, 967,
144
+ };
145
+
146
+ static const uint32_t stop_word_offsets[594] = {
147
+ 0, 2, 7, 12, 19, 26, 33, 37, 44, 49, 53, 58, 63, 69, 78, 82, 87, 94, 104, 109, 114, 120, 125, 131, 136, 139, 144, 150,
148
+ 152, 155, 162, 171, 175, 179, 187, 192, 195, 202, 208, 210, 218, 221, 226, 229, 234, 238, 246, 254, 260, 266, 268,
149
+ 273, 277, 282, 286, 291, 296, 300, 305, 310, 315, 320, 326, 331, 337, 341, 347, 357, 359, 362, 364, 366, 369, 376,
150
+ 380, 383, 387, 389, 392, 394, 400, 402, 405, 408, 413, 419, 425, 432, 438, 445, 453, 456, 459, 463, 468, 475, 480,
151
+ 483, 488, 495, 500, 504, 508, 514, 519, 525, 529, 534, 536, 542, 549, 555, 562, 569, 575, 582, 589, 596, 603, 611,
152
+ 618, 622, 628, 635, 641, 648, 655, 661, 668, 675, 682, 689, 697, 704, 709, 713, 718, 723, 729, 731, 734, 738, 742,
153
+ 746, 753, 758, 768, 771, 773, 779, 783, 789, 792, 794, 799, 805, 811, 814, 820, 828, 832, 837, 842, 846, 849, 854,
154
+ 860, 866, 872, 877, 883, 888, 894, 900, 906, 912, 919, 925, 931, 938, 944, 951, 958, 964, 971, 978, 985, 992, 1000,
155
+ 1007, 1011, 1015, 1020, 1027, 1033, 1037, 1042, 1047, 1052, 1057, 1063, 1068, 1073, 1076, 1079, 1080, 1087, 1093,
156
+ 1098, 1105, 1111, 1116, 1120, 1125, 1129, 1134, 1136, 1137, 1139, 1142, 1147, 1151, 1155, 1156, 1159, 1163, 1170,
157
+ 1178, 1184, 1191, 1198, 1204, 1211, 1216, 1219, 1225, 1229, 1234, 1238, 1243, 1248, 1254, 1260, 1267, 1275, 1282,
158
+ 1290, 1298, 1305, 1313, 1321, 1329, 1337, 1346, 1354, 1360, 1365, 1371, 1378, 1385, 1392, 1398, 1405, 1412, 1419,
159
+ 1425, 1432, 1439, 1446, 1453, 1461, 1468, 1474, 1479, 1484, 1487, 1491, 1495, 1501, 1508, 1512, 1514, 1520, 1523,
160
+ 1528, 1531, 1537, 1543, 1547, 1555, 1559, 1564, 1570, 1572, 1576, 1582, 1588, 1595, 1601, 1604, 1606, 1609, 1617,
161
+ 1622, 1627, 1635, 1641, 1644, 1650, 1657, 1664, 1672, 1679, 1683, 1686, 1690, 1696, 1701, 1703, 1706, 1711, 1715,
162
+ 1718, 1722, 1726, 1731, 1739, 1745, 1750, 1754, 1759, 1764, 1768, 1773, 1781, 1786, 1791, 1797, 1802, 1805, 1811,
163
+ 1818, 1824, 1829, 1831, 1834, 1839, 1843, 1850, 1851, 1853, 1856, 1860, 1863, 1867, 1871, 1874, 1881, 1885, 1889,
164
+ 1895, 1899, 1906, 1910, 1915, 1919, 1923, 1927, 1932, 1938, 1944, 1950, 1955, 1961, 1967, 1973, 1979, 1986, 1992,
165
+ 1997, 2001, 2005, 2013, 2022, 2031, 2040, 2043, 2047, 2050, 2054, 2058, 2061, 2065, 2069, 2073, 2077, 2082, 2086,
166
+ 2090, 2093, 2097, 2099, 2103, 2106, 2110, 2115, 2122, 2128, 2134, 2137, 2141, 2145, 2149, 2156, 2167, 2172, 2178,
167
+ 2181, 2188, 2191, 2195, 2199, 2204, 2208, 2212, 2217, 2222, 2227, 2231, 2236, 2241, 2246, 2251, 2257, 2262, 2266,
168
+ 2271, 2275, 2280, 2285, 2290, 2295, 2301, 2305, 2308, 2313, 2320, 2326, 2330, 2333, 2344, 2353, 2361, 2365, 2371,
169
+ 2378, 2385, 2394, 2397, 2400, 2403, 2405, 2409, 2415, 2419, 2422, 2425, 2428, 2431, 2435, 2439, 2443, 2446, 2450,
170
+ 2454, 2459, 2463, 2465, 2474, 2477, 2483, 2490, 2497, 2502, 2508, 2514, 2519, 2525, 2531, 2536, 2542, 2548, 2554,
171
+ 2560, 2567, 2573, 2579, 2584, 2586, 2591, 2597, 2602, 2608, 2614, 2620, 2626, 2632, 2636, 2642, 2644, 2650, 2657,
172
+ 2660, 2666, 2673, 2680, 2687, 2693, 2700, 2707, 2714, 2721, 2729, 2736, 2738, 2741, 2744, 2747, 2749, 2753, 2759,
173
+ 2765, 2768, 2771, 2773, 2776, 2779, 2782, 2786, 2791, 2795, 2800, 2805, 2809, 2814, 2819, 2824, 2829, 2835, 2840,
174
+ 2844, 2847, 2857, 2868, 2872, 2876, 2881, 2887, 2892, 2898, 2904, 2909, 2915, 2922, 2928, 2934, 2940, 2947, 2953,
175
+ 2958, 2961, 2965, 2967, 2971, 2974, 2979, 2985, 2991, 2996, 3002, 3006, 3010, 3015, 3022, 3026, 3027, 3032, 3034,
176
+ 3038, 3044, 3049, 3053, 3059, 3061,
177
+ };
178
+
179
+ static const uint32_t keep_ranges[14] = {
180
+ 48, 57, 65, 90, 97, 122, 181, 181, 837, 837, 880, 1023, 7936, 8191,
181
+ };
182
+
183
+ const narsil_language narsil_language_greek = {
184
+ .name = "greek",
185
+ .revision = "4f02e255d00e5848",
186
+ .stop_word_units = stop_word_units,
187
+ .stop_word_offsets = stop_word_offsets,
188
+ .stop_word_count = 593,
189
+ .ascii_keep = {0x03FF000000000000ULL, 0x07FFFFFE07FFFFFEULL},
190
+ .keep_ranges = keep_ranges,
191
+ .keep_range_count = 7,
192
+ .splits_code_points = 0,
193
+ .strips_possessive = 0,
194
+ .normalises_diacritics = 0,
195
+ .min_token_length = 1,
196
+ .ngram_size = 0,
197
+ .normalise = narsil_greek_normalise,
198
+ .stem_by_rules = NULL,
199
+ .create_snowball = greek_create_env,
200
+ .snowball_stem = greek_stem,
201
+ .close_snowball = greek_close_env,
202
+ };
@@ -0,0 +1,110 @@
1
+ #include "../../analysis/languages.h"
2
+ #include "declarations.h"
3
+ #include "../rules.h"
4
+
5
+ #include <stddef.h>
6
+ #include <stdint.h>
7
+
8
+ static const uint16_t stop_word_units[607] = {
9
+ 97, 106, 97, 97, 107, 117, 101, 97, 109, 98, 117, 101, 97, 109, 98, 117, 233, 118, 97, 97, 109, 111, 97, 110, 105, 97,
10
+ 112, 121, 116, 233, 112, 101, 97, 114, 97, 107, 97, 39, 101, 97, 114, 97, 107, 97, 42892, 101, 97, 118, 97, 118, 101,
11
+ 97, 118, 101, 97, 118, 101, 105, 99, 104, 101, 99, 104, 117, 103, 117, 105, 99, 104, 117, 112, 101, 99, 104, 233, 118,
12
+ 101, 103, 111, 116, 121, 111, 103, 117, 105, 103, 117, 105, 118, 101, 103, 117, 253, 112, 101, 104, 97, 104, 97, 39,
13
+ 101, 104, 97, 39, 101, 107, 117, 233, 114, 97, 104, 97, 39, 233, 118, 97, 104, 97, 103, 771, 117, 97, 104, 97, 42892,
14
+ 101, 104, 97, 42892, 101, 107, 117, 233, 114, 97, 104, 97, 42892, 233, 118, 97, 104, 101, 110, 100, 105, 118, 101,
15
+ 104, 101, 115, 101, 104, 101, 116, 97, 104, 101, 7869, 104, 105, 107, 117, 225, 105, 104, 225, 107, 97, 116, 117, 104,
16
+ 237, 110, 97, 106, 97, 114, 101, 106, 97, 118, 101, 106, 101, 112, 101, 107, 97, 116, 117, 107, 111, 107, 111, 39,
17
+ 225, 103, 771, 97, 107, 111, 39, 225, 112, 101, 107, 111, 39, 227, 107, 111, 39, 227, 103, 97, 107, 111, 39, 227, 118,
18
+ 97, 107, 111, 42892, 225, 103, 771, 97, 107, 111, 42892, 225, 112, 101, 107, 111, 42892, 227, 107, 111, 42892, 227,
19
+ 103, 97, 107, 111, 42892, 227, 118, 97, 107, 117, 107, 117, 114, 105, 107, 117, 233, 114, 97, 107, 243, 118, 97, 109,
20
+ 97, 121, 109, 97, 109, 97, 121, 109, 225, 118, 97, 109, 98, 97, 39, 101, 109, 98, 97, 39, 233, 105, 99, 104, 97, 109,
21
+ 98, 97, 39, 233, 105, 99, 104, 97, 112, 97, 109, 98, 97, 39, 233, 114, 101, 109, 98, 97, 42892, 101, 109, 98, 97,
22
+ 42892, 233, 105, 99, 104, 97, 109, 98, 97, 42892, 233, 105, 99, 104, 97, 112, 97, 109, 98, 97, 42892, 233, 114, 101,
23
+ 109, 98, 111, 118, 121, 109, 98, 111, 121, 109, 98, 111, 121, 118, 101, 109, 98, 121, 116, 233, 112, 101, 109, 101,
24
+ 109, 111, 245, 109, 225, 118, 97, 109, 225, 118, 97, 112, 97, 110, 97, 104, 225, 110, 105, 114, 105, 110, 100, 97,
25
+ 106, 101, 110, 100, 101, 110, 100, 105, 118, 101, 110, 100, 233, 118, 101, 110, 101, 110, 103, 117, 233, 114, 97, 110,
26
+ 105, 107, 111, 110, 107, 111, 111, 112, 97, 111, 112, 97, 105, 116, 101, 111, 114, 101, 111, 241, 111, 110, 100, 105,
27
+ 118, 101, 112, 101, 112, 101, 103, 117, 97, 112, 101, 110, 100, 101, 112, 101, 116, 101, 297, 112, 101, 118, 101, 112,
28
+ 101, 7869, 112, 105, 107, 111, 112, 233, 105, 99, 104, 97, 112, 233, 118, 97, 114, 97, 109, 111, 114, 101, 104, 101,
29
+ 114, 101, 104, 101, 103, 117, 97, 114, 101, 116, 97, 114, 101, 118, 101, 114, 105, 114, 101, 114, 117, 112, 105, 114,
30
+ 117, 112, 105, 118, 101, 116, 233, 114, 227, 117, 109, 105, 117, 109, 237, 118, 97, 117, 112, 101, 117, 112, 233, 105,
31
+ 117, 112, 233, 105, 99, 104, 97, 117, 112, 233, 112, 101, 117, 112, 233, 114, 245, 117, 112, 233, 118, 97, 117, 112,
32
+ 233, 118, 97, 114, 101, 118, 97, 39, 101, 107, 117, 101, 118, 97, 39, 101, 114, 227, 118, 97, 42892, 101, 107, 117,
33
+ 101, 118, 97, 42892, 101, 114, 227, 118, 111, 105, 225, 114, 105, 237, 110, 97, 241, 97, 110, 100, 101, 241, 97, 110,
34
+ 101,
35
+ };
36
+
37
+ static const uint32_t stop_word_offsets[122] = {
38
+ 0, 3, 7, 12, 19, 22, 25, 32, 39, 46, 51, 54, 58, 61, 67, 72, 77, 82, 85, 90, 95, 97, 101, 110, 116, 122, 126, 135,
39
+ 141, 148, 152, 156, 159, 165, 171, 175, 179, 183, 187, 191, 193, 200, 206, 210, 216, 222, 229, 235, 239, 245, 251,
40
+ 253, 257, 262, 266, 271, 278, 283, 292, 303, 310, 315, 324, 335, 342, 347, 351, 357, 364, 366, 369, 373, 379, 387,
41
+ 392, 395, 400, 405, 407, 413, 417, 420, 423, 429, 432, 440, 442, 447, 452, 457, 461, 464, 468, 474, 478, 482, 486,
42
+ 493, 497, 501, 505, 509, 515, 519, 522, 527, 530, 534, 541, 546, 551, 556, 563, 570, 576, 583, 589, 592, 595, 598,
43
+ 603, 607,
44
+ };
45
+
46
+ static const uint32_t keep_ranges[734] = {
47
+ 39, 39, 48, 57, 65, 90, 97, 122, 170, 170, 186, 186, 192, 214, 216, 246, 248, 696, 736, 740, 768, 879, 921, 921, 953,
48
+ 953, 1155, 1161, 1425, 1469, 1471, 1471, 1473, 1474, 1476, 1477, 1479, 1479, 1552, 1562, 1611, 1631, 1648, 1648, 1750,
49
+ 1756, 1759, 1764, 1767, 1768, 1770, 1773, 1809, 1809, 1840, 1866, 1958, 1968, 2027, 2035, 2045, 2045, 2070, 2073,
50
+ 2075, 2083, 2085, 2087, 2089, 2093, 2137, 2139, 2199, 2207, 2250, 2273, 2275, 2307, 2362, 2364, 2366, 2383, 2385,
51
+ 2391, 2402, 2403, 2433, 2435, 2492, 2492, 2494, 2500, 2503, 2504, 2507, 2509, 2519, 2519, 2530, 2531, 2558, 2558,
52
+ 2561, 2563, 2620, 2620, 2622, 2626, 2631, 2632, 2635, 2637, 2641, 2641, 2672, 2673, 2677, 2677, 2689, 2691, 2748,
53
+ 2748, 2750, 2757, 2759, 2761, 2763, 2765, 2786, 2787, 2810, 2815, 2817, 2819, 2876, 2876, 2878, 2884, 2887, 2888,
54
+ 2891, 2893, 2901, 2903, 2914, 2915, 2946, 2946, 3006, 3010, 3014, 3016, 3018, 3021, 3031, 3031, 3072, 3076, 3132,
55
+ 3132, 3134, 3140, 3142, 3144, 3146, 3149, 3157, 3158, 3170, 3171, 3201, 3203, 3260, 3260, 3262, 3268, 3270, 3272,
56
+ 3274, 3277, 3285, 3286, 3298, 3299, 3315, 3315, 3328, 3331, 3387, 3388, 3390, 3396, 3398, 3400, 3402, 3405, 3415,
57
+ 3415, 3426, 3427, 3457, 3459, 3530, 3530, 3535, 3540, 3542, 3542, 3544, 3551, 3570, 3571, 3633, 3633, 3636, 3642,
58
+ 3655, 3662, 3761, 3761, 3764, 3772, 3784, 3790, 3864, 3865, 3893, 3893, 3895, 3895, 3897, 3897, 3902, 3903, 3953,
59
+ 3972, 3974, 3975, 3981, 3991, 3993, 4028, 4038, 4038, 4139, 4158, 4182, 4185, 4190, 4192, 4194, 4196, 4199, 4205,
60
+ 4209, 4212, 4226, 4237, 4239, 4239, 4250, 4253, 4957, 4959, 5906, 5909, 5938, 5940, 5970, 5971, 6002, 6003, 6068,
61
+ 6099, 6109, 6109, 6155, 6157, 6159, 6159, 6277, 6278, 6313, 6313, 6432, 6443, 6448, 6459, 6679, 6683, 6741, 6750,
62
+ 6752, 6780, 6783, 6783, 6832, 6877, 6880, 6891, 6912, 6916, 6964, 6980, 7019, 7027, 7040, 7042, 7073, 7085, 7142,
63
+ 7155, 7204, 7223, 7376, 7378, 7380, 7400, 7405, 7405, 7412, 7412, 7415, 7417, 7424, 7461, 7468, 7516, 7522, 7525,
64
+ 7531, 7543, 7545, 7614, 7616, 7935, 8126, 8126, 8305, 8305, 8319, 8319, 8336, 8348, 8400, 8432, 8490, 8491, 8498,
65
+ 8498, 8526, 8526, 8544, 8584, 11360, 11391, 11503, 11505, 11647, 11647, 11744, 11775, 12330, 12335, 12441, 12442,
66
+ 42607, 42610, 42612, 42621, 42654, 42655, 42736, 42737, 42786, 42887, 42891, 42972, 42993, 43007, 43010, 43010, 43014,
67
+ 43014, 43019, 43019, 43043, 43047, 43052, 43052, 43136, 43137, 43188, 43205, 43232, 43249, 43263, 43263, 43302, 43309,
68
+ 43335, 43347, 43392, 43395, 43443, 43456, 43493, 43493, 43561, 43574, 43587, 43587, 43596, 43597, 43643, 43645, 43696,
69
+ 43696, 43698, 43700, 43703, 43704, 43710, 43711, 43713, 43713, 43755, 43759, 43765, 43766, 43824, 43866, 43868, 43876,
70
+ 43878, 43881, 44003, 44010, 44012, 44013, 64256, 64262, 64286, 64286, 65024, 65039, 65056, 65071, 65313, 65338, 65345,
71
+ 65370, 66045, 66045, 66272, 66272, 66422, 66426, 67456, 67461, 67463, 67504, 67506, 67514, 68097, 68099, 68101, 68102,
72
+ 68108, 68111, 68152, 68154, 68159, 68159, 68325, 68326, 68900, 68903, 68969, 68973, 69291, 69292, 69370, 69375, 69446,
73
+ 69456, 69506, 69509, 69632, 69634, 69688, 69702, 69744, 69744, 69747, 69748, 69759, 69762, 69808, 69818, 69826, 69826,
74
+ 69888, 69890, 69927, 69940, 69957, 69958, 70003, 70003, 70016, 70018, 70067, 70080, 70089, 70092, 70094, 70095, 70188,
75
+ 70199, 70206, 70206, 70209, 70209, 70367, 70378, 70400, 70403, 70459, 70460, 70462, 70468, 70471, 70472, 70475, 70477,
76
+ 70487, 70487, 70498, 70499, 70502, 70508, 70512, 70516, 70584, 70592, 70594, 70594, 70597, 70597, 70599, 70602, 70604,
77
+ 70608, 70610, 70610, 70625, 70626, 70709, 70726, 70750, 70750, 70832, 70851, 71087, 71093, 71096, 71104, 71132, 71133,
78
+ 71216, 71232, 71339, 71351, 71453, 71467, 71724, 71738, 71984, 71989, 71991, 71992, 71995, 71998, 72000, 72000, 72002,
79
+ 72003, 72145, 72151, 72154, 72160, 72164, 72164, 72193, 72202, 72243, 72249, 72251, 72254, 72263, 72263, 72273, 72283,
80
+ 72330, 72345, 72544, 72551, 72751, 72758, 72760, 72767, 72850, 72871, 72873, 72886, 73009, 73014, 73018, 73018, 73020,
81
+ 73021, 73023, 73029, 73031, 73031, 73098, 73102, 73104, 73105, 73107, 73111, 73459, 73462, 73472, 73473, 73475, 73475,
82
+ 73524, 73530, 73534, 73538, 73562, 73562, 78912, 78912, 78919, 78933, 90398, 90415, 92912, 92916, 92976, 92982, 94031,
83
+ 94031, 94033, 94087, 94095, 94098, 94180, 94180, 94192, 94193, 113821, 113822, 118528, 118573, 118576, 118598, 119141,
84
+ 119145, 119149, 119154, 119163, 119170, 119173, 119179, 119210, 119213, 119362, 119364, 121344, 121398, 121403,
85
+ 121452, 121461, 121461, 121476, 121476, 121499, 121503, 121505, 121519, 122624, 122654, 122661, 122666, 122880,
86
+ 122886, 122888, 122904, 122907, 122913, 122915, 122916, 122918, 122922, 123023, 123023, 123184, 123190, 123566,
87
+ 123566, 123628, 123631, 124140, 124143, 124398, 124399, 124643, 124643, 124646, 124646, 124654, 124655, 124661,
88
+ 124661, 125136, 125142, 125252, 125258, 917760, 917999,
89
+ };
90
+
91
+ const narsil_language narsil_language_guarani = {
92
+ .name = "guarani",
93
+ .revision = "1",
94
+ .stop_word_units = stop_word_units,
95
+ .stop_word_offsets = stop_word_offsets,
96
+ .stop_word_count = 121,
97
+ .ascii_keep = {0x03FF008000000000ULL, 0x07FFFFFE07FFFFFEULL},
98
+ .keep_ranges = keep_ranges,
99
+ .keep_range_count = 367,
100
+ .splits_code_points = 1,
101
+ .strips_possessive = 0,
102
+ .normalises_diacritics = 0,
103
+ .min_token_length = 1,
104
+ .ngram_size = 0,
105
+ .normalise = narsil_guarani_normalise,
106
+ .stem_by_rules = NULL,
107
+ .create_snowball = NULL,
108
+ .snowball_stem = NULL,
109
+ .close_snowball = NULL,
110
+ };
@@ -0,0 +1,90 @@
1
+ #include "../../analysis/languages.h"
2
+ #include "declarations.h"
3
+
4
+ #include <stddef.h>
5
+ #include <stdint.h>
6
+
7
+ static const uint16_t stop_word_units[819] = {
8
+ 2693, 2690, 2711, 2759, 2693, 2690, 2726, 2736, 2693, 2725, 2741, 2750, 2693, 2728, 2759, 2693, 2734, 2728, 2759,
9
+ 2693, 2734, 2750, 2736, 2753, 2690, 2693, 2734, 2759, 2693, 2745, 2752, 2690, 2694, 2694, 2711, 2739, 2694, 2725,
10
+ 2752, 2694, 2728, 2753, 2690, 2694, 2728, 2759, 2694, 2730, 2723, 2728, 2759, 2694, 2730, 2723, 2753, 2690, 2694,
11
+ 2730, 2723, 2759, 2694, 2730, 2752, 2694, 2736, 2694, 2741, 2752, 2694, 2741, 2759, 2697, 2730, 2736, 2697, 2733,
12
+ 2750, 2698, 2690, 2714, 2759, 2698, 2733, 2753, 2690, 2703, 2703, 2709, 2703, 2728, 2703, 2728, 2750, 2703, 2728,
13
+ 2750, 2690, 2703, 2728, 2752, 2703, 2728, 2753, 2690, 2703, 2728, 2759, 2703, 2728, 2763, 2703, 2734, 2703, 2741,
14
+ 2750, 2703, 2741, 2750, 2690, 2703, 2741, 2752, 2703, 2741, 2753, 2690, 2703, 2741, 2763, 2707, 2715, 2753, 2690,
15
+ 2709, 2690, 2696, 2709, 2709, 2696, 2709, 2735, 2753, 2690, 2709, 2735, 2763, 2709, 2736, 2724, 2750, 2690, 2709,
16
+ 2736, 2741, 2753, 2690, 2709, 2736, 2752, 2709, 2736, 2752, 2703, 2709, 2736, 2753, 2690, 2709, 2736, 2759, 2709,
17
+ 2736, 2759, 2738, 2753, 2690, 2709, 2736, 2765, 2735, 2750, 2709, 2736, 2765, 2735, 2750, 2690, 2709, 2736, 2765,
18
+ 2735, 2753, 2690, 2709, 2736, 2765, 2735, 2763, 2709, 2750, 2690, 2696, 2709, 2759, 2709, 2759, 2719, 2738, 2753,
19
+ 2690, 2709, 2759, 2734, 2709, 2759, 2741, 2752, 2709, 2759, 2741, 2753, 2690, 2709, 2763, 2696, 2709, 2763, 2696,
20
+ 2709, 2709, 2763, 2723, 2709, 2763, 2723, 2759, 2709, 2763, 2728, 2759, 2709, 2765, 2735, 2750, 2690, 2709, 2765,
21
+ 2735, 2750, 2736, 2759, 2710, 2754, 2732, 2711, 2696, 2711, 2735, 2750, 2711, 2735, 2750, 2690, 2711, 2735, 2753,
22
+ 2690, 2711, 2735, 2763, 2712, 2723, 2753, 2690, 2715, 2715, 2724, 2750, 2690, 2715, 2752, 2703, 2715, 2753, 2690,
23
+ 2715, 2759, 2715, 2759, 2709, 2715, 2763, 2716, 2716, 2750, 2735, 2716, 2752, 2716, 2759, 2716, 2759, 2719, 2738,
24
+ 2753, 2690, 2716, 2759, 2728, 2759, 2716, 2759, 2734, 2716, 2759, 2741, 2752, 2716, 2759, 2741, 2753, 2690, 2716,
25
+ 2759, 2741, 2763, 2716, 2763, 2716, 2763, 2696, 2703, 2716, 2765, 2735, 2750, 2690, 2716, 2765, 2735, 2750, 2736,
26
+ 2759, 2717, 2750, 2717, 2753, 2690, 2724, 2728, 2759, 2724, 2734, 2728, 2759, 2724, 2734, 2750, 2736, 2753, 2690,
27
+ 2724, 2734, 2759, 2724, 2750, 2724, 2750, 2736, 2750, 2725, 2752, 2724, 2750, 2736, 2750, 2734, 2750, 2690, 2724,
28
+ 2750, 2736, 2753, 2690, 2724, 2753, 2690, 2724, 2759, 2724, 2759, 2690, 2724, 2759, 2707, 2724, 2759, 2723, 2759,
29
+ 2724, 2759, 2725, 2752, 2724, 2759, 2728, 2750, 2724, 2759, 2728, 2752, 2724, 2759, 2728, 2753, 2690, 2724, 2759,
30
+ 2728, 2759, 2724, 2759, 2734, 2724, 2759, 2734, 2728, 2753, 2690, 2724, 2759, 2734, 2728, 2759, 2724, 2759, 2741,
31
+ 2752, 2724, 2759, 2741, 2753, 2690, 2724, 2763, 2724, 2765, 2735, 2750, 2690, 2724, 2765, 2735, 2750, 2736, 2759,
32
+ 2725, 2695, 2725, 2696, 2725, 2696, 2703, 2725, 2724, 2750, 2725, 2724, 2750, 2690, 2725, 2724, 2752, 2725, 2724,
33
+ 2753, 2690, 2725, 2724, 2763, 2725, 2735, 2750, 2725, 2735, 2750, 2690, 2725, 2735, 2753, 2690, 2725, 2735, 2759,
34
+ 2738, 2753, 2690, 2725, 2735, 2763, 2725, 2741, 2753, 2690, 2725, 2750, 2697, 2690, 2725, 2750, 2707, 2725, 2750,
35
+ 2735, 2725, 2752, 2725, 2763, 2721, 2753, 2690, 2726, 2736, 2759, 2709, 2728, 2728, 2690, 2728, 2725, 2752, 2728,
36
+ 2745, 2751, 2728, 2745, 2752, 2728, 2745, 2752, 2690, 2728, 2750, 2728, 2752, 2728, 2752, 2714, 2759, 2728, 2753,
37
+ 2690, 2728, 2759, 2728, 2763, 2730, 2715, 2752, 2730, 2723, 2730, 2736, 2730, 2736, 2690, 2724, 2753, 2730, 2745,
38
+ 2759, 2738, 2750, 2690, 2730, 2750, 2715, 2739, 2730, 2750, 2744, 2759, 2730, 2763, 2724, 2750, 2728, 2753, 2690,
39
+ 2730, 2765, 2736, 2724, 2765, 2735, 2759, 2709, 2731, 2709, 2765, 2724, 2731, 2736, 2752, 2731, 2736, 2752, 2725,
40
+ 2752, 2732, 2690, 2728, 2759, 2732, 2727, 2750, 2732, 2727, 2753, 2690, 2732, 2728, 2752, 2732, 2745, 2750, 2736,
41
+ 2732, 2745, 2753, 2732, 2750, 2726, 2732, 2759, 2734, 2728, 2759, 2734, 2750, 2734, 2750, 2690, 2734, 2750, 2719,
42
+ 2759, 2734, 2750, 2724, 2765, 2736, 2734, 2750, 2736, 2753, 2690, 2734, 2752, 2734, 2754, 2709, 2741, 2753, 2690,
43
+ 2734, 2754, 2709, 2752, 2734, 2754, 2709, 2765, 2735, 2750, 2734, 2754, 2709, 2765, 2735, 2750, 2690, 2734, 2754,
44
+ 2709, 2765, 2735, 2753, 2690, 2734, 2759, 2690, 2736, 2745, 2752, 2736, 2745, 2759, 2736, 2745, 2759, 2741, 2753,
45
+ 2690, 2736, 2745, 2765, 2735, 2750, 2736, 2745, 2765, 2735, 2750, 2690, 2736, 2745, 2765, 2735, 2763, 2736, 2752,
46
+ 2724, 2759, 2736, 2754, 2750, 2738, 2759, 2724, 2750, 2738, 2759, 2724, 2753, 2690, 2738, 2759, 2741, 2750, 2741,
47
+ 2711, 2759, 2736, 2759, 2741, 2727, 2753, 2742, 2709, 2759, 2742, 2750, 2742, 2753, 2690, 2744, 2736, 2710, 2753,
48
+ 2690, 2744, 2750, 2734, 2759, 2744, 2753, 2727, 2752, 2745, 2724, 2750, 2745, 2724, 2750, 2690, 2745, 2724, 2752,
49
+ 2745, 2724, 2753, 2690, 2745, 2741, 2759, 2745, 2742, 2759, 2745, 2742, 2763, 2745, 2750, 2745, 2753, 2690, 2745,
50
+ 2763, 2745, 2763, 2696, 2745, 2763, 2696, 2742, 2745, 2763, 2696, 2742, 2753, 2690, 2745, 2763, 2735, 2745, 2763,
51
+ 2741, 2750,
52
+ };
53
+
54
+ static const uint32_t stop_word_offsets[223] = {
55
+ 0, 4, 8, 12, 15, 19, 25, 28, 32, 33, 36, 39, 43, 46, 51, 56, 60, 63, 65, 68, 71, 74, 77, 81, 85, 86, 88, 90, 93, 97,
56
+ 100, 104, 107, 110, 112, 115, 119, 122, 126, 129, 133, 137, 139, 143, 146, 151, 156, 159, 163, 167, 170, 176, 181,
57
+ 187, 193, 198, 202, 204, 210, 213, 217, 222, 225, 229, 232, 236, 240, 245, 251, 254, 256, 259, 263, 267, 270, 274,
58
+ 275, 279, 282, 285, 287, 290, 292, 293, 296, 298, 300, 306, 310, 313, 317, 322, 326, 328, 332, 337, 343, 348, 351,
59
+ 355, 361, 364, 366, 372, 379, 384, 387, 389, 392, 395, 399, 403, 407, 411, 416, 420, 423, 429, 434, 438, 443, 445,
60
+ 450, 456, 458, 460, 463, 466, 470, 473, 477, 480, 483, 487, 491, 497, 500, 504, 508, 511, 514, 516, 521, 525, 526,
61
+ 528, 531, 534, 537, 541, 543, 545, 549, 552, 554, 556, 559, 561, 563, 568, 574, 578, 582, 589, 597, 601, 604, 609,
62
+ 613, 616, 620, 623, 627, 630, 633, 635, 638, 640, 643, 647, 652, 657, 659, 665, 669, 675, 682, 689, 692, 695, 698,
63
+ 704, 709, 715, 720, 724, 727, 731, 736, 740, 745, 748, 751, 753, 756, 761, 765, 769, 772, 776, 779, 783, 786, 789,
64
+ 792, 794, 797, 799, 802, 806, 812, 815, 819,
65
+ };
66
+
67
+ static const uint32_t keep_ranges[8] = {
68
+ 48, 57, 65, 90, 97, 122, 2688, 2815,
69
+ };
70
+
71
+ const narsil_language narsil_language_gujarati = {
72
+ .name = "gujarati",
73
+ .revision = "1",
74
+ .stop_word_units = stop_word_units,
75
+ .stop_word_offsets = stop_word_offsets,
76
+ .stop_word_count = 222,
77
+ .ascii_keep = {0x03FF000000000000ULL, 0x07FFFFFE07FFFFFEULL},
78
+ .keep_ranges = keep_ranges,
79
+ .keep_range_count = 4,
80
+ .splits_code_points = 0,
81
+ .strips_possessive = 0,
82
+ .normalises_diacritics = 0,
83
+ .min_token_length = 1,
84
+ .ngram_size = 0,
85
+ .normalise = NULL,
86
+ .stem_by_rules = NULL,
87
+ .create_snowball = NULL,
88
+ .snowball_stem = NULL,
89
+ .close_snowball = NULL,
90
+ };
@@ -0,0 +1,54 @@
1
+ #include "../../analysis/languages.h"
2
+ #include "declarations.h"
3
+
4
+ #include <stddef.h>
5
+ #include <stdint.h>
6
+
7
+ static const uint16_t stop_word_units[323] = {
8
+ 97, 97, 107, 97, 110, 97, 110, 107, 242, 97, 110, 116, 97, 112, 97, 112, 114, 101, 97, 116, 242, 97, 118, 97, 110, 97,
9
+ 118, 97, 110, 108, 232, 98, 121, 101, 110, 98, 121, 101, 110, 107, 101, 98, 242, 99, 104, 97, 107, 100, 101, 100, 101,
10
+ 106, 97, 100, 101, 112, 105, 101, 101, 104, 101, 110, 101, 112, 105, 102, 242, 102, 242, 107, 103, 101, 110, 103, 101,
11
+ 110, 121, 101, 110, 107, 105, 107, 105, 108, 232, 115, 107, 105, 115, 97, 107, 111, 110, 98, 121, 101, 110, 107, 111,
12
+ 110, 110, 107, 111, 110, 110, 101, 110, 107, 111, 110, 115, 97, 107, 111, 116, 101, 107, 111, 117, 107, 111, 117, 107,
13
+ 111, 117, 109, 97, 110, 107, 111, 117, 110, 121, 101, 108, 108, 97, 108, 97, 97, 108, 101, 108, 105, 108, 121, 101,
14
+ 108, 232, 108, 242, 109, 109, 101, 110, 109, 119, 101, 110, 109, 232, 115, 105, 110, 97, 110, 110, 97, 112, 110, 111,
15
+ 110, 110, 111, 117, 111, 111, 104, 111, 115, 105, 110, 111, 110, 111, 115, 119, 97, 111, 117, 111, 117, 109, 101, 110,
16
+ 109, 112, 97, 112, 97, 109, 105, 112, 97, 110, 100, 97, 110, 112, 97, 115, 107, 101, 112, 105, 116, 111, 112, 111,
17
+ 117, 112, 114, 97, 108, 112, 114, 101, 115, 107, 101, 112, 119, 105, 115, 107, 101, 115, 97, 115, 97, 110, 115, 101,
18
+ 115, 101, 108, 109, 97, 110, 115, 105, 115, 111, 117, 115, 119, 97, 115, 242, 116, 116, 97, 116, 97, 110, 116, 97,
19
+ 110, 107, 111, 117, 116, 97, 112, 116, 101, 116, 111, 117, 116, 111, 117, 106, 111, 117, 116, 111, 117, 116, 116, 111,
20
+ 117, 116, 111, 116, 97, 110, 116, 119, 242, 112, 116, 232, 108, 119, 119, 105, 119, 232, 121, 121, 111, 121, 111, 110,
21
+ 121, 111, 110, 110, 232, 115, 107, 101,
22
+ };
23
+
24
+ static const uint32_t stop_word_offsets[95] = {
25
+ 0, 1, 3, 5, 9, 12, 14, 18, 21, 25, 31, 35, 41, 43, 47, 49, 53, 57, 58, 60, 62, 65, 67, 70, 73, 79, 81, 86, 90, 97,
26
+ 101, 107, 112, 116, 122, 128, 134, 135, 137, 140, 142, 144, 147, 149, 151, 152, 155, 159, 163, 166, 169, 172, 175,
27
+ 176, 178, 184, 188, 190, 196, 198, 202, 208, 213, 217, 220, 224, 230, 236, 238, 241, 243, 249, 251, 254, 257, 260,
28
+ 262, 265, 271, 274, 276, 279, 285, 289, 297, 301, 304, 305, 307, 309, 310, 312, 315, 319, 323,
29
+ };
30
+
31
+ static const uint32_t keep_ranges[14] = {
32
+ 48, 57, 65, 90, 97, 122, 200, 200, 210, 210, 232, 232, 242, 242,
33
+ };
34
+
35
+ const narsil_language narsil_language_haitian_creole = {
36
+ .name = "haitian-creole",
37
+ .revision = "1",
38
+ .stop_word_units = stop_word_units,
39
+ .stop_word_offsets = stop_word_offsets,
40
+ .stop_word_count = 94,
41
+ .ascii_keep = {0x03FF000000000000ULL, 0x07FFFFFE07FFFFFEULL},
42
+ .keep_ranges = keep_ranges,
43
+ .keep_range_count = 7,
44
+ .splits_code_points = 0,
45
+ .strips_possessive = 0,
46
+ .normalises_diacritics = 0,
47
+ .min_token_length = 1,
48
+ .ngram_size = 0,
49
+ .normalise = NULL,
50
+ .stem_by_rules = NULL,
51
+ .create_snowball = NULL,
52
+ .snowball_stem = NULL,
53
+ .close_snowball = NULL,
54
+ };
@@ -0,0 +1,85 @@
1
+ #include "../../analysis/languages.h"
2
+ #include "declarations.h"
3
+
4
+ #include <stddef.h>
5
+ #include <stdint.h>
6
+
7
+ static const uint16_t stop_word_units[975] = {
8
+ 97, 97, 98, 105, 110, 97, 98, 105, 110, 100, 97, 97, 99, 101, 97, 107, 97, 97, 107, 97, 108, 108, 97, 97, 107, 97,
9
+ 110, 97, 107, 101, 97, 107, 119, 97, 105, 97, 108, 104, 97, 108, 105, 97, 108, 108, 97, 104, 97, 109, 109, 97, 97,
10
+ 110, 97, 110, 97, 97, 115, 104, 101, 98, 97, 98, 97, 97, 98, 97, 105, 98, 97, 108, 108, 101, 98, 97, 110, 98, 97, 110,
11
+ 101, 98, 97, 114, 98, 97, 115, 97, 98, 97, 115, 117, 98, 97, 121, 97, 110, 98, 105, 110, 98, 105, 115, 97, 98, 105,
12
+ 115, 97, 110, 105, 98, 105, 121, 117, 98, 117, 103, 117, 99, 101, 99, 101, 119, 97, 99, 101, 119, 97, 114, 99, 105,
13
+ 107, 97, 99, 105, 107, 105, 110, 100, 97, 100, 97, 103, 97, 100, 97, 105, 100, 97, 107, 101, 100, 97, 109, 97, 100,
14
+ 97, 109, 97, 110, 100, 97, 110, 100, 97, 116, 97, 100, 97, 121, 97, 100, 105, 110, 103, 97, 100, 111, 108, 101, 100,
15
+ 111, 109, 105, 110, 100, 111, 110, 100, 117, 98, 98, 97, 110, 100, 117, 98, 117, 100, 117, 107, 100, 117, 107, 97,
16
+ 100, 117, 107, 107, 97, 110, 100, 117, 107, 107, 97, 110, 105, 110, 102, 97, 102, 97, 116, 97, 110, 103, 97, 103, 97,
17
+ 98, 97, 103, 97, 98, 97, 116, 97, 103, 97, 98, 97, 116, 97, 114, 103, 97, 109, 101, 103, 97, 114, 101, 103, 111, 109,
18
+ 97, 103, 117, 100, 97, 104, 97, 105, 102, 97, 114, 104, 97, 107, 97, 104, 97, 107, 97, 110, 104, 97, 107, 105, 107,
19
+ 97, 104, 97, 114, 104, 97, 116, 116, 97, 104, 117, 100, 117, 105, 100, 97, 110, 105, 110, 105, 110, 97, 105, 110, 100,
20
+ 97, 105, 110, 106, 105, 105, 116, 97, 105, 121, 97, 106, 117, 110, 97, 107, 97, 107, 97, 102, 105, 110, 107, 97, 105,
21
+ 107, 97, 107, 101, 107, 97, 109, 97, 114, 107, 97, 110, 107, 97, 110, 97, 107, 97, 110, 107, 97, 107, 97, 110, 109,
22
+ 117, 107, 97, 110, 115, 97, 107, 97, 110, 115, 117, 107, 97, 110, 116, 97, 107, 97, 115, 97, 107, 97, 115, 97, 110,
23
+ 99, 101, 107, 97, 115, 97, 110, 99, 101, 119, 97, 114, 107, 97, 119, 97, 105, 107, 101, 107, 101, 110, 97, 110, 107,
24
+ 105, 107, 105, 109, 97, 110, 105, 110, 107, 105, 110, 107, 111, 107, 111, 100, 97, 107, 111, 100, 97, 121, 97, 107,
25
+ 101, 107, 111, 105, 110, 97, 107, 111, 109, 97, 105, 107, 111, 119, 97, 107, 111, 119, 97, 99, 101, 107, 111, 119, 97,
26
+ 110, 101, 107, 111, 119, 97, 110, 110, 101, 107, 117, 107, 117, 107, 101, 107, 117, 109, 97, 107, 117, 110, 107, 117,
27
+ 110, 97, 107, 117, 115, 97, 107, 117, 115, 97, 110, 107, 117, 119, 97, 107, 119, 97, 114, 97, 105, 108, 97, 108, 108,
28
+ 97, 105, 108, 97, 108, 108, 101, 108, 111, 107, 97, 99, 105, 110, 109, 97, 109, 97, 99, 101, 109, 97, 102, 105, 109,
29
+ 97, 105, 109, 97, 105, 109, 97, 107, 111, 110, 109, 97, 107, 97, 109, 97, 110, 97, 109, 97, 114, 97, 115, 97, 109, 97,
30
+ 115, 97, 109, 97, 115, 117, 109, 97, 116, 97, 109, 97, 116, 117, 107, 97, 114, 109, 101, 109, 105, 110, 109, 105, 110,
31
+ 105, 109, 105, 115, 97, 108, 105, 109, 105, 115, 97, 108, 105, 110, 109, 117, 109, 117, 100, 100, 105, 110, 109, 117,
32
+ 107, 97, 109, 117, 107, 101, 109, 117, 107, 117, 109, 117, 110, 109, 117, 110, 97, 109, 117, 115, 97, 109, 109, 97,
33
+ 110, 110, 97, 110, 97, 107, 101, 110, 97, 109, 117, 110, 97, 110, 110, 97, 115, 97, 110, 97, 115, 117, 110, 97, 119,
34
+ 97, 110, 101, 110, 105, 115, 97, 115, 97, 98, 111, 100, 97, 115, 97, 105, 115, 97, 109, 115, 97, 117, 114, 97, 115,
35
+ 97, 117, 114, 97, 110, 115, 97, 117, 114, 97, 110, 115, 117, 115, 104, 105, 115, 104, 105, 109, 97, 115, 111, 115, 97,
36
+ 105, 115, 117, 115, 117, 107, 97, 115, 117, 107, 97, 110, 115, 117, 107, 101, 115, 117, 109, 97, 115, 117, 110, 115,
37
+ 117, 110, 97, 115, 117, 110, 101, 116, 97, 116, 97, 99, 101, 116, 97, 102, 105, 116, 97, 107, 101, 116, 97, 109, 107,
38
+ 97, 114, 116, 97, 110, 97, 116, 111, 116, 117, 110, 116, 117, 110, 100, 97, 116, 117, 110, 105, 119, 97, 119, 97, 100,
39
+ 97, 110, 99, 97, 110, 119, 97, 100, 97, 110, 100, 97, 119, 97, 100, 97, 110, 110, 97, 110, 119, 97, 100, 97, 110, 115,
40
+ 117, 119, 97, 100, 100, 97, 119, 97, 105, 119, 97, 110, 100, 97, 119, 97, 110, 101, 119, 97, 110, 105, 119, 97, 110,
41
+ 110, 97, 110, 119, 97, 115, 117, 119, 97, 116, 97, 121, 97, 121, 97, 99, 101, 121, 97, 100, 100, 97, 121, 97, 107, 97,
42
+ 110, 121, 97, 107, 101, 121, 97, 110, 121, 97, 110, 97, 121, 97, 110, 122, 117, 121, 97, 110, 122, 117, 110, 121, 97,
43
+ 117, 121, 97, 119, 97, 121, 97, 119, 97, 110, 121, 97, 119, 97, 110, 99, 105, 110, 121, 97, 121, 105, 121, 97, 121,
44
+ 105, 110, 121, 97, 121, 105, 110, 100, 97, 121, 105, 121, 105, 110, 121, 105, 119, 97, 121, 105, 119, 117, 121, 105,
45
+ 119, 117, 119, 97, 121, 105, 119, 117, 119, 97, 114, 122, 97, 122, 97, 105, 122, 97, 107, 97, 122, 97, 109, 117, 122,
46
+ 97, 110, 122, 97, 114, 97, 114, 122, 97, 115, 117, 122, 97, 116, 97, 122, 97, 116, 111, 110, 122, 117, 119, 97,
47
+ };
48
+
49
+ static const uint32_t stop_word_offsets[229] = {
50
+ 0, 1, 5, 11, 14, 17, 23, 27, 30, 35, 41, 46, 50, 52, 55, 59, 61, 64, 67, 72, 75, 79, 82, 86, 90, 95, 98, 102, 108,
51
+ 112, 116, 118, 122, 127, 131, 136, 138, 142, 145, 149, 153, 158, 161, 165, 169, 174, 178, 183, 186, 192, 196, 199,
52
+ 203, 209, 217, 219, 224, 226, 230, 236, 243, 247, 251, 255, 259, 265, 269, 274, 280, 283, 288, 292, 296, 298, 301,
53
+ 305, 309, 312, 315, 319, 321, 326, 329, 333, 338, 341, 345, 350, 355, 360, 365, 370, 374, 381, 391, 396, 398, 403,
54
+ 405, 412, 415, 417, 421, 429, 434, 439, 443, 449, 455, 462, 464, 468, 472, 475, 479, 483, 488, 492, 498, 504, 509,
55
+ 516, 518, 522, 526, 529, 537, 541, 545, 551, 555, 559, 563, 570, 572, 575, 579, 585, 592, 594, 600, 604, 608, 612,
56
+ 615, 619, 627, 629, 633, 637, 640, 644, 648, 652, 654, 656, 658, 664, 667, 670, 675, 681, 689, 692, 697, 702, 704,
57
+ 708, 713, 717, 721, 724, 728, 732, 734, 738, 742, 746, 752, 756, 758, 761, 766, 770, 772, 780, 787, 795, 802, 807,
58
+ 810, 815, 819, 823, 829, 833, 837, 839, 843, 848, 853, 857, 860, 864, 869, 875, 878, 882, 887, 895, 899, 904, 911,
59
+ 913, 916, 920, 924, 930, 937, 939, 942, 946, 950, 953, 958, 962, 966, 971, 975,
60
+ };
61
+
62
+ static const uint32_t keep_ranges[22] = {
63
+ 39, 39, 48, 57, 65, 90, 97, 122, 385, 385, 394, 394, 408, 409, 435, 436, 595, 595, 599, 599, 700, 700,
64
+ };
65
+
66
+ const narsil_language narsil_language_hausa = {
67
+ .name = "hausa",
68
+ .revision = "1",
69
+ .stop_word_units = stop_word_units,
70
+ .stop_word_offsets = stop_word_offsets,
71
+ .stop_word_count = 228,
72
+ .ascii_keep = {0x03FF008000000000ULL, 0x07FFFFFE07FFFFFEULL},
73
+ .keep_ranges = keep_ranges,
74
+ .keep_range_count = 11,
75
+ .splits_code_points = 0,
76
+ .strips_possessive = 0,
77
+ .normalises_diacritics = 0,
78
+ .min_token_length = 1,
79
+ .ngram_size = 0,
80
+ .normalise = NULL,
81
+ .stem_by_rules = NULL,
82
+ .create_snowball = NULL,
83
+ .snowball_stem = NULL,
84
+ .close_snowball = NULL,
85
+ };
@@ -0,0 +1,50 @@
1
+ #include "../../analysis/languages.h"
2
+ #include "declarations.h"
3
+
4
+ #include <stddef.h>
5
+ #include <stdint.h>
6
+
7
+ static const uint16_t stop_word_units[180] = {
8
+ 39, 97, 39, 111, 104, 101, 39, 97, 39, 111, 108, 101, 39, 111, 39, 111, 101, 39, 111, 108, 117, 97, 39, 111, 117, 107,
9
+ 111, 117, 97, 97, 39, 101, 97, 107, 117, 97, 107, 257, 97, 110, 97, 97, 117, 101, 104, 101, 104, 111, 39, 105, 105,
10
+ 105, 97, 105, 104, 111, 105, 110, 257, 105, 257, 107, 97, 107, 97, 39, 117, 107, 101, 107, 101, 107, 97, 104, 105,
11
+ 107, 111, 107, 111, 39, 117, 107, 111, 110, 97, 107, 111, 117, 107, 257, 107, 257, 107, 111, 117, 107, 257, 110, 97,
12
+ 107, 257, 117, 107, 257, 117, 97, 107, 275, 105, 97, 107, 275, 108, 257, 107, 275, 110, 257, 108, 111, 97, 108, 257,
13
+ 107, 111, 117, 108, 257, 117, 97, 109, 97, 109, 97, 105, 109, 97, 117, 109, 101, 109, 257, 107, 111, 117, 109, 257,
14
+ 117, 97, 110, 97, 110, 97, 39, 101, 110, 101, 105, 110, 111, 110, 257, 110, 333, 111, 112, 97, 104, 97, 112, 363, 117,
15
+ 97, 119, 97, 108, 101, 119, 97, 117,
16
+ };
17
+
18
+ static const uint32_t stop_word_offsets[58] = {
19
+ 0, 6, 12, 14, 17, 22, 28, 29, 32, 35, 38, 41, 43, 44, 46, 50, 51, 53, 56, 59, 61, 63, 67, 69, 75, 77, 81, 85, 88, 90,
20
+ 95, 99, 102, 106, 110, 114, 118, 121, 126, 130, 132, 135, 138, 140, 145, 149, 151, 155, 158, 160, 162, 164, 165, 169,
21
+ 171, 173, 177, 180,
22
+ };
23
+
24
+ static const uint32_t keep_ranges[76] = {
25
+ 39, 39, 48, 57, 65, 90, 97, 122, 170, 170, 186, 186, 192, 214, 216, 246, 248, 696, 736, 740, 7424, 7461, 7468, 7516,
26
+ 7522, 7525, 7531, 7543, 7545, 7614, 7680, 7935, 8305, 8305, 8319, 8319, 8336, 8348, 8490, 8491, 8498, 8498, 8526,
27
+ 8526, 8544, 8584, 11360, 11391, 42786, 42887, 42891, 42972, 42993, 43007, 43824, 43866, 43868, 43876, 43878, 43881,
28
+ 64256, 64262, 65313, 65338, 65345, 65370, 67456, 67461, 67463, 67504, 67506, 67514, 122624, 122654, 122661, 122666,
29
+ };
30
+
31
+ const narsil_language narsil_language_hawaiian = {
32
+ .name = "hawaiian",
33
+ .revision = "1",
34
+ .stop_word_units = stop_word_units,
35
+ .stop_word_offsets = stop_word_offsets,
36
+ .stop_word_count = 57,
37
+ .ascii_keep = {0x03FF008000000000ULL, 0x07FFFFFE07FFFFFEULL},
38
+ .keep_ranges = keep_ranges,
39
+ .keep_range_count = 38,
40
+ .splits_code_points = 1,
41
+ .strips_possessive = 0,
42
+ .normalises_diacritics = 0,
43
+ .min_token_length = 1,
44
+ .ngram_size = 0,
45
+ .normalise = NULL,
46
+ .stem_by_rules = NULL,
47
+ .create_snowball = NULL,
48
+ .snowball_stem = NULL,
49
+ .close_snowball = NULL,
50
+ };