@delali/narsil-react-native 0.3.1-next.155 → 0.3.1-next.157

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 +1,174 @@
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[2129] = {
8
+ 1570, 1574, 1740, 1570, 1574, 1746, 1570, 1580, 1570, 1582, 1585, 1570, 1582, 1585, 1705, 1576, 1585, 1570, 1583,
9
+ 1607, 1740, 1570, 1611, 1576, 1570, 1657, 1726, 1570, 1740, 1576, 1575, 1577, 1575, 1582, 1576, 1586, 1578, 1575,
10
+ 1582, 1578, 1578, 1576, 1605, 1575, 1583, 1726, 1585, 1575, 1585, 1583, 1575, 1585, 1583, 1711, 1585, 1583, 1575,
11
+ 1585, 1705, 1576, 1609, 1575, 1588, 1575, 1590, 1578, 1593, 1608, 1576, 1604, 1575, 1590, 1578, 1593, 1608, 1576,
12
+ 1604, 1575, 1578, 1575, 1590, 1591, 1585, 1584, 1575, 1590, 1705, 1576, 1575, 1590, 1705, 1740, 1575, 1590, 1705,
13
+ 1746, 1575, 1591, 1585, 1575, 1601, 1575, 1594, 1740, 1576, 1575, 1601, 1585, 1575, 1583, 1575, 1604, 1711, 1575,
14
+ 1608, 1585, 1575, 1608, 1611, 1670, 1576, 1575, 1608, 1611, 1670, 1576, 1574, 1740, 1575, 1608, 1611, 1670, 1740,
15
+ 1575, 1608, 1611, 1670, 1746, 1575, 1609, 1575, 1611, 1575, 1611, 1584, 1585, 1575, 1611, 1729, 1740, 1722, 1575,
16
+ 1657, 1726, 1576, 1611, 1576, 1575, 1662, 1612, 1576, 1575, 1662, 1612, 1746, 1575, 1670, 1726, 1576, 1575, 1670,
17
+ 1726, 1740, 1575, 1670, 1726, 1746, 1575, 1705, 1579, 1585, 1575, 1705, 1657, 1726, 1576, 1575, 1705, 1657, 1726,
18
+ 1740, 1575, 1705, 1657, 1726, 1746, 1575, 1705, 1740, 1604, 1575, 1575, 1705, 1740, 1604, 1740, 1575, 1705, 1740,
19
+ 1604, 1746, 1575, 1711, 1585, 1670, 1729, 1575, 1729, 1606, 1575, 1740, 1591, 1746, 1575, 1740, 1705, 1576, 1578,
20
+ 1578, 1576, 1586, 1613, 1578, 1578, 1578, 1585, 1578, 1585, 1578, 1740, 1578, 1578, 1585, 1740, 1610, 1578, 1593,
21
+ 1584, 1575, 1583, 1578, 1606, 1578, 1608, 1578, 1608, 1576, 1605, 1578, 1608, 1729, 1740, 1578, 1608, 1729, 1740,
22
+ 1722, 1578, 1612, 1729, 1576, 1578, 1705, 1578, 1726, 1576, 1578, 1726, 1608, 1681, 1575, 1578, 1726, 1608, 1681,
23
+ 1740, 1578, 1726, 1608, 1681, 1746, 1578, 1726, 1740, 1578, 1726, 1746, 1578, 1740, 1610, 1579, 1576, 1579, 1576,
24
+ 1574, 1740, 1722, 1579, 1576, 1578, 1585, 1578, 1740, 1578, 1579, 1576, 1585, 1740, 1579, 1576, 1585, 1746, 1579,
25
+ 1576, 1593, 1579, 1579, 1576, 1604, 1575, 1579, 1576, 1604, 1578, 1585, 1578, 1740, 1578, 1579, 1576, 1729, 1585,
26
+ 1579, 1583, 1576, 1574, 1746, 1579, 1585, 1570, 1722, 1579, 1585, 1575, 1722, 1579, 1585, 1588, 1579, 1593, 1584,
27
+ 1579, 1594, 1740, 1585, 1579, 1604, 1612, 1584, 1579, 1604, 1612, 1584, 1608, 1579, 1576, 1604, 1575, 1579, 1604,
28
+ 1705, 1729, 1579, 1610, 1579, 1612, 1576, 1579, 1612, 1576, 1585, 1729, 1576, 1579, 1612, 1576, 1585, 1729, 1740,
29
+ 1579, 1612, 1576, 1585, 1729, 1746, 1579, 1612, 1576, 1611, 1576, 1579, 1612, 1584, 1579, 1612, 1584, 1705, 1585,
30
+ 1608, 1579, 1612, 1584, 1705, 1585, 1611, 1576, 1579, 1612, 1584, 1740, 1579, 1681, 1575, 1579, 1681, 1608, 1722,
31
+ 1579, 1681, 1740, 1579, 1681, 1746, 1579, 1726, 1585, 1579, 1726, 1585, 1575, 1579, 1726, 1585, 1575, 1729, 1608,
32
+ 1575, 1579, 1726, 1585, 1662, 1608, 1585, 1579, 1726, 1740, 1579, 1729, 1578, 1579, 1729, 1578, 1585, 1579, 1729,
33
+ 1578, 1585, 1740, 1579, 1729, 1578, 1585, 1740, 1610, 1579, 1740, 1670, 1580, 1582, 1576, 1582, 1576, 1585, 1729,
34
+ 1576, 1582, 1576, 1585, 1729, 1740, 1582, 1576, 1585, 1729, 1746, 1582, 1576, 1607, 1608, 1592, 1582, 1576, 1611,
35
+ 1576, 1582, 1576, 1611, 1578, 1576, 1582, 1576, 1611, 1578, 1740, 1582, 1576, 1611, 1578, 1746, 1582, 1576, 1611,
36
+ 1612, 1576, 1582, 1578, 1582, 1578, 1606, 1582, 1580, 1705, 1729, 1582, 1589, 1582, 1591, 1591, 1585, 1584, 1582,
37
+ 1604, 1584, 1740, 1582, 1608, 1582, 1608, 1575, 1609, 1582, 1608, 1611, 1729, 1740, 1582, 1608, 1705, 1729, 1582,
38
+ 1612, 1576, 1577, 1582, 1711, 1729, 1582, 1711, 1729, 1608, 1722, 1582, 1711, 1729, 1740, 1722, 1582, 1740, 1591,
39
+ 1576, 1582, 1740, 1591, 1576, 1705, 1729, 1583, 1585, 1583, 1585, 1582, 1576, 1578, 1583, 1585, 1582, 1729, 1583,
40
+ 1585, 1582, 1746, 1583, 1585, 1586, 1602, 1740, 1602, 1578, 1583, 1585, 1590, 1578, 1583, 1588, 1583, 1601, 1593,
41
+ 1729, 1583, 1604, 1670, 1591, 1662, 1583, 1604, 1670, 1591, 1662, 1740, 1583, 1604, 1670, 1591, 1662, 1740, 1576,
42
+ 1722, 1583, 1608, 1583, 1608, 1585, 1583, 1608, 1585, 1575, 1609, 1583, 1608, 1590, 1585, 1575, 1583, 1608, 1590,
43
+ 1585, 1608, 1722, 1583, 1608, 1590, 1585, 1740, 1583, 1608, 1590, 1585, 1746, 1583, 1608, 1611, 1608, 1722, 1583,
44
+ 1705, 1726, 1576, 1574, 1740, 1722, 1583, 1705, 1726, 1576, 1578, 1576, 1583, 1705, 1726, 1576, 1578, 1740, 1583,
45
+ 1705, 1726, 1576, 1578, 1746, 1583, 1705, 1726, 1576, 1608, 1583, 1705, 1726, 1576, 1611, 1576, 1583, 1705, 1726,
46
+ 1576, 1740, 1576, 1583, 1740, 1583, 1740, 1576, 1583, 1740, 1578, 1576, 1583, 1740, 1578, 1740, 1583, 1740, 1578,
47
+ 1746, 1583, 1740, 1585, 1583, 1740, 1612, 1576, 1583, 1740, 1705, 1726, 1608, 1583, 1740, 1705, 1726, 1612, 1576,
48
+ 1583, 1740, 1705, 1726, 1740, 1583, 1740, 1705, 1726, 1740, 1722, 1583, 1746, 1585, 1585, 1575, 1590, 1578, 1608,
49
+ 1722, 1585, 1575, 1590, 1578, 1729, 1585, 1575, 1590, 1578, 1746, 1585, 1585, 1740, 1593, 1729, 1585, 1585, 1740,
50
+ 1593, 1746, 1585, 1705, 1610, 1585, 1705, 1726, 1585, 1705, 1726, 1576, 1585, 1705, 1726, 1578, 1576, 1585, 1705,
51
+ 1726, 1578, 1576, 1729, 1608, 1722, 1585, 1705, 1726, 1578, 1740, 1585, 1705, 1726, 1578, 1746, 1585, 1705, 1726,
52
+ 1740, 1585, 1705, 1726, 1746, 1585, 1729, 1576, 1585, 1729, 1740, 1585, 1729, 1746, 1586, 1586, 1576, 1589, 1604,
53
+ 1586, 1576, 1590, 1585, 1586, 1576, 1604, 1586, 1576, 1604, 1575, 1578, 1586, 1576, 1604, 1740, 1729, 1586, 1589,
54
+ 1608, 1722, 1586, 1589, 1729, 1586, 1589, 1746, 1586, 1602, 1576, 1574, 1602, 1586, 1602, 1740, 1578, 1740, 1722,
55
+ 1586, 1602, 1740, 1602, 1578, 1586, 1705, 1606, 1586, 1705, 1608, 1740, 1729, 1586, 1740, 1576, 1583, 1613, 1589,
56
+ 1576, 1601, 1589, 1587, 1740, 1585, 1589, 1601, 1585, 1589, 1608, 1585, 1578, 1589, 1608, 1585, 1578, 1587, 1576,
57
+ 1604, 1589, 1608, 1585, 1578, 1608, 1722, 1589, 1608, 1585, 1578, 1740, 1722, 1590, 1590, 1576, 1578, 1590, 1576,
58
+ 1578, 1726, 1590, 1576, 1583, 1613, 1590, 1576, 1585, 1575, 1590, 1576, 1585, 1746, 1590, 1576, 1604, 1590, 1576,
59
+ 1604, 1608, 1722, 1590, 1578, 1590, 1585, 1608, 1585, 1590, 1585, 1608, 1585, 1578, 1590, 1585, 1608, 1585, 1740,
60
+ 1590, 1604, 1591, 1604, 1729, 1590, 1608, 1670, 1590, 1608, 1670, 1576, 1590, 1608, 1670, 1578, 1576, 1590, 1608,
61
+ 1670, 1578, 1740, 1590, 1608, 1670, 1578, 1746, 1590, 1608, 1670, 1608, 1590, 1608, 1670, 1612, 1576, 1590, 1608,
62
+ 1670, 1740, 1590, 1608, 1670, 1740, 1722, 1590, 1705, 1576, 1590, 1705, 1578, 1576, 1590, 1705, 1578, 1740, 1590,
63
+ 1705, 1578, 1746, 1590, 1705, 1612, 1576, 1590, 1705, 1740, 1590, 1705, 1746, 1590, 1740, 1584, 1726, 1576, 1590,
64
+ 1740, 1584, 1726, 1740, 1590, 1740, 1584, 1726, 1746, 1590, 1740, 1705, 1612, 1672, 1590, 1746, 1591, 1585, 1601,
65
+ 1591, 1585, 1740, 1602, 1591, 1585, 1740, 1602, 1608, 1722, 1591, 1585, 1740, 1602, 1729, 1591, 1585, 1740, 1602,
66
+ 1746, 1591, 1608, 1585, 1591, 1608, 1585, 1662, 1585, 1592, 1576, 1729, 1585, 1593, 1593, 1584, 1583, 1593, 1592,
67
+ 1740, 1606, 1593, 1604, 1575, 1602, 1608, 1722, 1593, 1604, 1575, 1602, 1729, 1593, 1604, 1575, 1602, 1746, 1593,
68
+ 1604, 1575, 1608, 1613, 1593, 1608, 1608, 1607, 1740, 1594, 1576, 1740, 1584, 1594, 1582, 1589, 1594, 1584, 1594,
69
+ 1585, 1608, 1593, 1594, 1585, 1608, 1593, 1576, 1578, 1594, 1746, 1601, 1585, 1583, 1601, 1740, 1602, 1602, 1580,
70
+ 1604, 1602, 1580, 1740, 1604, 1729, 1602, 1591, 1606, 1604, 1574, 1746, 1604, 1575, 1604, 1575, 1586, 1607, 1740,
71
+ 1604, 1608, 1604, 1608, 1580, 1576, 1604, 1608, 1580, 1740, 1604, 1608, 1580, 1746, 1604, 1608, 1587, 1576, 1578,
72
+ 1604, 1608, 1587, 1729, 1604, 1608, 1711, 1604, 1608, 1711, 1608, 1722, 1604, 1681, 1705, 1662, 1610, 1604, 1711,
73
+ 1578, 1576, 1604, 1711, 1578, 1740, 1604, 1711, 1578, 1746, 1604, 1711, 1612, 1576, 1604, 1711, 1740, 1604, 1711,
74
+ 1740, 1722, 1604, 1711, 1746, 1604, 1740, 1604, 1740, 1576, 1604, 1740, 1612, 1576, 1604, 1740, 1722, 1604, 1746,
75
+ 1607, 1607, 1578, 1593, 1604, 1602, 1607, 1582, 1578, 1604, 1601, 1607, 1587, 1578, 1585, 1605, 1607, 1587, 1578,
76
+ 1585, 1607, 1729, 1607, 1587, 1591, 1608, 1588, 1607, 1587, 1740, 1584, 1607, 1591, 1574, 1604, 1729, 1607, 1591,
77
+ 1574, 1604, 1746, 1607, 1591, 1576, 1574, 1604, 1607, 1591, 1578, 1593, 1608, 1604, 1607, 1591, 1604, 1602, 1607,
78
+ 1593, 1604, 1608, 1605, 1607, 1595, 1578, 1608, 1604, 1607, 1604, 1575, 1607, 1608, 1705, 1610, 1607, 1608, 1705,
79
+ 1612, 1576, 1578, 1607, 1608, 1705, 1612, 1729, 1607, 1612, 1576, 1590, 1578, 1607, 1681, 1575, 1607, 1681, 1611,
80
+ 1576, 1607, 1681, 1746, 1607, 1705, 1608, 1604, 1607, 1711, 1585, 1607, 1729, 1585, 1579, 1576, 1609, 1607, 1740,
81
+ 1585, 1575, 1607, 1740, 1585, 1740, 1607, 1740, 1585, 1746, 1607, 1740, 1722, 1608, 1608, 1575, 1585, 1608, 1575,
82
+ 1604, 1746, 1608, 1613, 1611, 1574, 1740, 1611, 1574, 1746, 1611, 1576, 1611, 1576, 1662, 1591, 1612, 1584, 1611,
83
+ 1576, 1711, 1587, 1740, 1585, 1611, 1591, 1580, 1578, 1611, 1602, 1591, 1729, 1611, 1608, 1611, 1608, 1582, 1608,
84
+ 1575, 1609, 1611, 1705, 1576, 1604, 1612, 1576, 1611, 1705, 1578, 1729, 1611, 1729, 1611, 1729, 1740, 1722, 1611,
85
+ 1740, 1576, 1611, 1746, 1657, 1726, 1740, 1705, 1662, 1576, 1574, 1746, 1662, 1576, 1588, 1662, 1576, 1611, 1576,
86
+ 1662, 1576, 1611, 1670, 1662, 1585, 1662, 1585, 1575, 1611, 1576, 1662, 1591, 1612, 1584, 1662, 1604, 1662, 1608,
87
+ 1585, 1575, 1662, 1608, 1670, 1726, 1576, 1662, 1608, 1670, 1726, 1578, 1576, 1662, 1608, 1670, 1726, 1578, 1740,
88
+ 1662, 1608, 1670, 1726, 1578, 1746, 1662, 1608, 1670, 1726, 1608, 1662, 1608, 1670, 1726, 1608, 1722, 1662, 1608,
89
+ 1670, 1726, 1612, 1576, 1662, 1608, 1670, 1726, 1740, 1722, 1662, 1670, 1726, 1604, 1575, 1662, 1726, 1585, 1662,
90
+ 1729, 1604, 1575, 1662, 1729, 1604, 1740, 1662, 1729, 1604, 1746, 1590, 1740, 1662, 1729, 1604, 1746, 1590, 1746,
91
+ 1662, 1729, 1604, 1746, 1590, 1746, 1729, 1740, 1662, 1740, 1593, 1670, 1576, 1585, 1670, 1576, 1729, 1576, 1670,
92
+ 1576, 1729, 1612, 1576, 1670, 1576, 1729, 1746, 1670, 1604, 1575, 1670, 1604, 1608, 1670, 1604, 1740, 1722, 1670,
93
+ 1604, 1746, 1670, 1705, 1576, 1670, 1705, 1740, 1670, 1705, 1740, 1722, 1670, 1705, 1746, 1670, 1726, 1608, 1657,
94
+ 1576, 1670, 1726, 1608, 1657, 1608, 1722, 1670, 1726, 1608, 1657, 1740, 1670, 1726, 1608, 1657, 1746, 1670, 1726,
95
+ 1729, 1670, 1740, 1587, 1740, 1722, 1672, 1726, 1608, 1611, 1672, 1575, 1672, 1726, 1608, 1611, 1672, 1604, 1740,
96
+ 1576, 1672, 1726, 1608, 1611, 1672, 1608, 1672, 1726, 1608, 1611, 1672, 1611, 1576, 1672, 1726, 1608, 1611, 1672,
97
+ 1740, 1672, 1726, 1608, 1611, 1672, 1740, 1722, 1705, 1705, 1574, 1740, 1705, 1574, 1746, 1705, 1576, 1705, 1576,
98
+ 1601, 1740, 1705, 1576, 1605, 1705, 1578, 1705, 1580, 1726, 1740, 1705, 1585, 1575, 1705, 1585, 1578, 1576, 1705,
99
+ 1585, 1578, 1576, 1729, 1608, 1722, 1705, 1585, 1578, 1740, 1705, 1585, 1578, 1746, 1705, 1585, 1578, 1746, 1729,
100
+ 1608, 1705, 1585, 1585, 1729, 1576, 1705, 1585, 1585, 1729, 1740, 1705, 1585, 1585, 1729, 1746, 1705, 1585, 1608,
101
+ 1705, 1585, 1611, 1576, 1705, 1585, 1740, 1722, 1705, 1585, 1746, 1705, 1591, 1740, 1705, 1604, 1705, 1606, 1705,
102
+ 1608, 1574, 1740, 1705, 1608, 1578, 1585, 1705, 1608, 1585, 1575, 1705, 1608, 1585, 1608, 1722, 1705, 1608, 1585,
103
+ 1613, 1705, 1608, 1585, 1746, 1705, 1608, 1591, 1610, 1705, 1608, 1609, 1705, 1608, 1611, 1591, 1576, 1705, 1608,
104
+ 1611, 1591, 1740, 1705, 1608, 1611, 1591, 1746, 1705, 1726, 1608, 1604, 1575, 1705, 1726, 1608, 1604, 1608, 1705,
105
+ 1726, 1608, 1604, 1612, 1576, 1705, 1726, 1608, 1604, 1740, 1705, 1726, 1608, 1604, 1740, 1722, 1705, 1726, 1608,
106
+ 1604, 1746, 1705, 1729, 1705, 1729, 1576, 1705, 1729, 1578, 1576, 1705, 1729, 1578, 1740, 1705, 1729, 1578, 1746,
107
+ 1705, 1729, 1608, 1705, 1729, 1608, 1722, 1705, 1729, 1612, 1576, 1705, 1729, 1740, 1705, 1729, 1740, 1722, 1705,
108
+ 1729, 1746, 1705, 1740, 1705, 1740, 1576, 1705, 1740, 1591, 1576, 1705, 1740, 1591, 1585, 1601, 1705, 1740, 1591,
109
+ 1746, 1705, 1740, 1604, 1574, 1746, 1705, 1740, 1608, 1611, 1705, 1729, 1705, 1740, 1608, 1722, 1705, 1740, 1746,
110
+ 1705, 1746, 1705, 1746, 1579, 1593, 1584, 1705, 1746, 1585, 1585, 1740, 1593, 1746, 1711, 1574, 1740, 1711, 1574,
111
+ 1746, 1711, 1576, 1711, 1585, 1583, 1711, 1585, 1608, 1613, 1711, 1585, 1608, 1662, 1711, 1585, 1608, 1729, 1608,
112
+ 1722, 1711, 1612, 1578, 1740, 1711, 1740, 1711, 1740, 1576, 1711, 1746, 1729, 1585, 1729, 1606, 1729, 1608, 1729,
113
+ 1608, 1574, 1740, 1729, 1608, 1574, 1746, 1729, 1608, 1575, 1729, 1608, 1576, 1585, 1575, 1729, 1608, 1576, 1585,
114
+ 1740, 1729, 1608, 1576, 1585, 1746, 1729, 1608, 1578, 1576, 1729, 1608, 1578, 1740, 1729, 1608, 1578, 1746, 1729,
115
+ 1608, 1585, 1729, 1576, 1729, 1608, 1585, 1729, 1740, 1729, 1608, 1585, 1729, 1746, 1729, 1608, 1590, 1705, 1578,
116
+ 1576, 1729, 1608, 1590, 1705, 1578, 1740, 1729, 1608, 1590, 1705, 1578, 1746, 1729, 1608, 1611, 1576, 1729, 1608,
117
+ 1611, 1740, 1729, 1608, 1611, 1746, 1729, 1608, 1670, 1705, 1576, 1729, 1608, 1670, 1705, 1740, 1729, 1608, 1670,
118
+ 1705, 1746, 1729, 1608, 1711, 1574, 1740, 1729, 1608, 1711, 1574, 1746, 1729, 1608, 1711, 1740, 1576, 1729, 1608,
119
+ 1722, 1729, 1740, 1729, 1740, 1722, 1729, 1746, 1740, 1740, 1602, 1740, 1612, 1740, 1740, 1729, 1740, 1729, 1576,
120
+ 1722,
121
+ };
122
+
123
+ static const uint32_t stop_word_offsets[517] = {
124
+ 0, 3, 6, 8, 11, 17, 21, 24, 27, 30, 32, 37, 43, 47, 50, 56, 61, 63, 70, 79, 84, 88, 92, 96, 101, 105, 110, 113, 116,
125
+ 121, 128, 133, 138, 140, 142, 146, 151, 157, 161, 165, 169, 173, 177, 181, 186, 191, 196, 201, 206, 211, 216, 219,
126
+ 223, 226, 227, 228, 232, 234, 236, 241, 245, 250, 252, 254, 258, 262, 267, 271, 273, 276, 281, 286, 291, 294, 297,
127
+ 300, 302, 307, 314, 318, 322, 326, 330, 338, 342, 347, 351, 355, 358, 361, 365, 369, 378, 382, 384, 387, 393, 399,
128
+ 405, 410, 413, 419, 426, 430, 433, 437, 440, 443, 446, 450, 457, 463, 466, 469, 473, 478, 484, 487, 488, 490, 495,
129
+ 500, 505, 510, 514, 519, 524, 529, 534, 536, 539, 543, 545, 550, 554, 556, 560, 565, 569, 573, 576, 581, 586, 590,
130
+ 596, 598, 603, 607, 611, 618, 622, 624, 628, 633, 639, 647, 649, 652, 657, 662, 668, 673, 678, 683, 690, 696, 702,
131
+ 708, 713, 719, 725, 727, 730, 734, 738, 742, 745, 749, 754, 760, 765, 771, 773, 774, 780, 785, 790, 795, 800, 803,
132
+ 806, 810, 815, 823, 828, 833, 837, 841, 844, 847, 850, 851, 855, 859, 862, 867, 872, 876, 879, 882, 887, 893, 898,
133
+ 901, 906, 911, 914, 918, 921, 925, 932, 938, 944, 945, 948, 952, 956, 960, 964, 967, 972, 974, 978, 983, 988, 993,
134
+ 996, 1000, 1005, 1010, 1015, 1019, 1024, 1028, 1033, 1036, 1040, 1044, 1048, 1052, 1055, 1058, 1063, 1068, 1073, 1078,
135
+ 1080, 1083, 1087, 1093, 1098, 1103, 1106, 1111, 1115, 1116, 1119, 1123, 1129, 1134, 1139, 1144, 1149, 1153, 1156,
136
+ 1158, 1162, 1168, 1170, 1173, 1175, 1176, 1179, 1184, 1187, 1190, 1192, 1197, 1199, 1203, 1207, 1211, 1216, 1220,
137
+ 1223, 1228, 1233, 1237, 1241, 1245, 1249, 1252, 1256, 1259, 1261, 1264, 1268, 1271, 1273, 1274, 1279, 1284, 1289,
138
+ 1295, 1300, 1304, 1309, 1314, 1319, 1325, 1329, 1334, 1339, 1342, 1346, 1352, 1357, 1362, 1365, 1369, 1372, 1376,
139
+ 1379, 1385, 1389, 1393, 1397, 1400, 1401, 1404, 1408, 1410, 1413, 1416, 1418, 1424, 1430, 1434, 1438, 1440, 1446,
140
+ 1452, 1456, 1458, 1462, 1465, 1467, 1471, 1475, 1478, 1482, 1486, 1488, 1493, 1497, 1499, 1503, 1508, 1514, 1520,
141
+ 1526, 1531, 1537, 1543, 1549, 1554, 1557, 1561, 1565, 1571, 1577, 1585, 1588, 1591, 1595, 1600, 1604, 1607, 1610,
142
+ 1614, 1617, 1620, 1623, 1627, 1630, 1635, 1641, 1646, 1651, 1654, 1659, 1665, 1673, 1679, 1686, 1692, 1699, 1700,
143
+ 1703, 1706, 1708, 1712, 1715, 1717, 1721, 1724, 1728, 1735, 1739, 1743, 1749, 1754, 1759, 1764, 1767, 1771, 1775,
144
+ 1778, 1781, 1783, 1785, 1789, 1793, 1797, 1802, 1806, 1810, 1814, 1817, 1822, 1827, 1832, 1837, 1842, 1848, 1853,
145
+ 1859, 1864, 1866, 1869, 1873, 1877, 1881, 1884, 1888, 1892, 1895, 1899, 1902, 1904, 1907, 1911, 1916, 1920, 1925,
146
+ 1931, 1935, 1938, 1940, 1945, 1952, 1955, 1958, 1960, 1963, 1967, 1971, 1977, 1981, 1983, 1986, 1988, 1990, 1992,
147
+ 1994, 1998, 2002, 2005, 2010, 2015, 2020, 2024, 2028, 2032, 2037, 2042, 2047, 2053, 2059, 2065, 2069, 2073, 2077,
148
+ 2082, 2087, 2092, 2097, 2102, 2107, 2110, 2112, 2115, 2117, 2118, 2123, 2125, 2129,
149
+ };
150
+
151
+ static const uint32_t keep_ranges[12] = {
152
+ 48, 57, 65, 90, 97, 122, 1569, 1641, 1646, 1747, 1776, 1785,
153
+ };
154
+
155
+ const narsil_language narsil_language_urdu = {
156
+ .name = "urdu",
157
+ .revision = "1",
158
+ .stop_word_units = stop_word_units,
159
+ .stop_word_offsets = stop_word_offsets,
160
+ .stop_word_count = 516,
161
+ .ascii_keep = {0x03FF000000000000ULL, 0x07FFFFFE07FFFFFEULL},
162
+ .keep_ranges = keep_ranges,
163
+ .keep_range_count = 6,
164
+ .splits_code_points = 0,
165
+ .strips_possessive = 0,
166
+ .normalises_diacritics = 0,
167
+ .min_token_length = 1,
168
+ .ngram_size = 0,
169
+ .normalise = NULL,
170
+ .stem_by_rules = NULL,
171
+ .create_snowball = NULL,
172
+ .snowball_stem = NULL,
173
+ .close_snowball = NULL,
174
+ };
@@ -0,0 +1,88 @@
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[856] = {
8
+ 97, 105, 97, 108, 244, 97, 109, 101, 110, 97, 110, 104, 98, 105, 7871, 116, 98, 224, 98, 224, 105, 98, 225, 99, 98,
9
+ 232, 110, 98, 233, 110, 103, 98, 244, 110, 103, 98, 7841, 110, 98, 7843, 110, 98, 7845, 121, 98, 7857, 110, 103, 98,
10
+ 7875, 110, 98, 7879, 116, 98, 7883, 98, 7895, 110, 103, 98, 7897, 98, 7899, 98, 7903, 105, 98, 7913, 99, 99, 97, 111,
11
+ 99, 104, 97, 99, 104, 105, 7871, 99, 99, 104, 111, 99, 104, 111, 97, 99, 104, 117, 121, 7879, 110, 99, 104, 237, 110,
12
+ 104, 99, 104, 250, 99, 104, 259, 110, 103, 99, 104, 432, 97, 99, 104, 7853, 99, 99, 104, 7855, 99, 99, 104, 7881, 99,
13
+ 104, 7881, 110, 99, 104, 7899, 99, 104, 7907, 116, 99, 104, 7911, 110, 99, 104, 7913, 99, 111, 110, 99, 117, 7889,
14
+ 110, 99, 117, 7897, 99, 99, 224, 110, 103, 99, 225, 99, 99, 225, 105, 99, 226, 121, 99, 242, 110, 99, 243, 99, 244,
15
+ 99, 249, 110, 103, 99, 259, 110, 99, 361, 110, 103, 99, 417, 99, 417, 110, 99, 7843, 99, 7847, 110, 99, 7853, 117, 99,
16
+ 7911, 97, 99, 7913, 100, 111, 100, 117, 121, 100, 224, 111, 100, 236, 100, 432, 7899, 105, 100, 7841, 100, 7851, 117,
17
+ 100, 7919, 101, 109, 103, 105, 7919, 97, 103, 236, 104, 97, 121, 104, 111, 7863, 99, 104, 417, 110, 104, 7885, 104,
18
+ 7887, 105, 107, 104, 105, 107, 104, 225, 99, 107, 104, 244, 110, 103, 108, 117, 244, 110, 108, 224, 108, 224, 109,
19
+ 108, 234, 110, 108, 250, 99, 108, 7841, 105, 108, 7847, 110, 108, 7899, 110, 109, 117, 7889, 110, 109, 224, 109, 236,
20
+ 110, 104, 109, 7895, 105, 109, 7897, 116, 109, 7899, 105, 109, 7907, 110, 103, 97, 121, 110, 103, 104, 101, 110, 110,
21
+ 103, 104, 7881, 109, 110, 103, 111, 224, 105, 110, 103, 111, 7843, 105, 110, 103, 224, 121, 110, 103, 244, 105, 110,
22
+ 103, 432, 417, 105, 110, 103, 432, 7901, 105, 110, 103, 7885, 110, 110, 103, 7885, 116, 110, 104, 110, 104, 97, 117,
23
+ 110, 104, 105, 7873, 117, 110, 104, 224, 110, 104, 233, 110, 104, 432, 110, 104, 432, 110, 103, 110, 104, 7845, 116,
24
+ 110, 104, 7853, 110, 110, 104, 7881, 110, 104, 7919, 110, 103, 110, 224, 111, 110, 224, 121, 110, 234, 110, 110, 243,
25
+ 110, 243, 99, 110, 243, 105, 110, 259, 109, 110, 417, 105, 110, 7845, 121, 110, 7871, 117, 110, 7873, 110, 110, 7885,
26
+ 110, 7899, 110, 7919, 97, 111, 225, 105, 112, 104, 111, 112, 104, 232, 112, 104, 243, 99, 112, 104, 243, 116, 112,
27
+ 104, 7843, 105, 112, 104, 7855, 116, 112, 104, 7887, 110, 103, 112, 104, 7889, 99, 112, 104, 7909, 116, 112, 104,
28
+ 7913, 116, 113, 117, 97, 113, 117, 121, 7871, 116, 113, 117, 121, 7875, 110, 113, 117, 225, 113, 117, 7843, 114, 97,
29
+ 114, 105, 234, 110, 103, 114, 105, 7879, 116, 114, 224, 121, 114, 225, 111, 114, 233, 110, 114, 237, 99, 104, 114,
30
+ 259, 110, 103, 114, 7845, 116, 114, 7857, 110, 103, 114, 7891, 105, 114, 7913, 97, 115, 97, 111, 115, 97, 117, 115,
31
+ 111, 115, 117, 253, 116, 115, 236, 115, 7841, 99, 104, 115, 7845, 116, 115, 7855, 112, 115, 7869, 115, 7889, 115,
32
+ 7921, 116, 97, 110, 104, 116, 104, 97, 110, 104, 116, 104, 101, 111, 116, 104, 111, 7841, 116, 116, 104, 111, 7855,
33
+ 116, 116, 104, 117, 7847, 110, 116, 104, 224, 116, 104, 225, 110, 103, 116, 104, 236, 116, 104, 237, 109, 116, 104,
34
+ 244, 105, 116, 104, 432, 7901, 110, 103, 116, 104, 7845, 121, 116, 104, 7849, 121, 116, 104, 7853, 109, 116, 104,
35
+ 7871, 116, 104, 7871, 99, 104, 116, 104, 7887, 109, 116, 104, 7889, 99, 116, 104, 7889, 116, 116, 104, 7897, 99, 116,
36
+ 104, 7917, 97, 116, 111, 224, 116, 111, 7865, 116, 116, 114, 111, 110, 103, 116, 114, 234, 110, 116, 114, 432, 7899,
37
+ 99, 116, 114, 7875, 110, 116, 114, 7879, 116, 116, 114, 7887, 110, 103, 116, 117, 121, 116, 234, 110, 104, 116, 244,
38
+ 105, 116, 7841, 105, 116, 7845, 109, 116, 7845, 110, 116, 7855, 112, 116, 7885, 116, 116, 7897, 116, 116, 7899, 116,
39
+ 7899, 105, 116, 7915, 116, 7915, 110, 103, 118, 101, 111, 118, 105, 7879, 99, 118, 224, 118, 224, 111, 118, 226, 110,
40
+ 103, 118, 232, 111, 118, 236, 118, 7851, 110, 118, 7853, 121, 118, 7873, 118, 7899, 105, 118, 7903, 118, 7909, 116,
41
+ 118, 7915, 97, 120, 111, 233, 116, 120, 111, 7859, 110, 120, 111, 7865, 116, 120, 117, 7875, 120, 117, 7889, 110, 103,
42
+ 120, 7879, 112, 224, 224, 111, 225, 225, 105, 225, 110, 103, 244, 110, 103, 250, 105, 253, 273, 97, 110, 103, 273,
43
+ 105, 273, 105, 7873, 117, 273, 226, 121, 273, 227, 273, 243, 273, 432, 7907, 99, 273, 7871, 110, 273, 7873, 117, 273,
44
+ 7875, 417, 417, 105, 432, 7841, 7845, 121, 7855, 116, 7891, 7893, 110, 103, 7899, 7901, 7903, 7911, 97, 7915, 7917,
45
+ };
46
+
47
+ static const uint32_t stop_word_offsets[266] = {
48
+ 0, 2, 5, 9, 12, 16, 18, 21, 24, 27, 31, 35, 38, 41, 44, 48, 51, 54, 56, 60, 62, 64, 67, 70, 73, 76, 81, 84, 88, 94,
49
+ 99, 102, 107, 111, 115, 119, 122, 126, 129, 133, 137, 140, 143, 147, 151, 155, 158, 161, 164, 167, 169, 171, 175, 178,
50
+ 182, 184, 187, 189, 192, 195, 198, 200, 202, 205, 208, 210, 214, 216, 219, 221, 223, 227, 229, 232, 236, 239, 241,
51
+ 244, 247, 251, 256, 260, 262, 265, 268, 271, 274, 277, 280, 284, 286, 290, 293, 296, 299, 301, 305, 310, 315, 320,
52
+ 325, 329, 333, 338, 343, 347, 351, 353, 357, 362, 365, 368, 371, 376, 380, 384, 387, 392, 395, 398, 401, 403, 406,
53
+ 409, 412, 415, 418, 421, 424, 426, 428, 431, 434, 437, 440, 444, 448, 452, 456, 461, 465, 469, 473, 476, 481, 486,
54
+ 489, 492, 494, 499, 503, 506, 509, 512, 516, 520, 523, 527, 530, 533, 536, 539, 541, 545, 547, 551, 554, 557, 559,
55
+ 561, 563, 567, 572, 576, 581, 586, 591, 594, 599, 602, 606, 610, 616, 620, 624, 628, 631, 636, 640, 644, 648, 652,
56
+ 656, 659, 663, 668, 672, 677, 681, 685, 690, 693, 697, 700, 703, 706, 709, 712, 715, 718, 720, 723, 725, 729, 732,
57
+ 736, 738, 741, 745, 748, 750, 753, 756, 758, 761, 763, 766, 769, 773, 777, 781, 784, 789, 792, 793, 795, 796, 798,
58
+ 801, 804, 806, 807, 811, 813, 817, 820, 822, 824, 828, 831, 834, 836, 837, 839, 840, 841, 843, 845, 846, 849, 850,
59
+ 851, 852, 854, 855, 856,
60
+ };
61
+
62
+ static const uint32_t keep_ranges[74] = {
63
+ 48, 57, 65, 90, 97, 122, 170, 170, 186, 186, 192, 214, 216, 246, 248, 696, 736, 740, 7424, 7461, 7468, 7516, 7522,
64
+ 7525, 7531, 7543, 7545, 7614, 7680, 7935, 8305, 8305, 8319, 8319, 8336, 8348, 8490, 8491, 8498, 8498, 8526, 8526,
65
+ 8544, 8584, 11360, 11391, 42786, 42887, 42891, 42972, 42993, 43007, 43824, 43866, 43868, 43876, 43878, 43881, 64256,
66
+ 64262, 65313, 65338, 65345, 65370, 67456, 67461, 67463, 67504, 67506, 67514, 122624, 122654, 122661, 122666,
67
+ };
68
+
69
+ const narsil_language narsil_language_vietnamese = {
70
+ .name = "vietnamese",
71
+ .revision = "1",
72
+ .stop_word_units = stop_word_units,
73
+ .stop_word_offsets = stop_word_offsets,
74
+ .stop_word_count = 265,
75
+ .ascii_keep = {0x03FF000000000000ULL, 0x07FFFFFE07FFFFFEULL},
76
+ .keep_ranges = keep_ranges,
77
+ .keep_range_count = 37,
78
+ .splits_code_points = 1,
79
+ .strips_possessive = 0,
80
+ .normalises_diacritics = 0,
81
+ .min_token_length = 1,
82
+ .ngram_size = 0,
83
+ .normalise = NULL,
84
+ .stem_by_rules = NULL,
85
+ .create_snowball = NULL,
86
+ .snowball_stem = NULL,
87
+ .close_snowball = NULL,
88
+ };
@@ -0,0 +1,143 @@
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[1998] = {
8
+ 97, 97, 99, 97, 99, 104, 111, 115, 97, 99, 104, 111, 115, 105, 97, 100, 100, 97, 115, 97, 103, 97, 103, 111, 115, 97,
9
+ 105, 97, 105, 108, 97, 108, 108, 97, 108, 108, 97, 110, 97, 108, 108, 117, 97, 109, 97, 109, 98, 101, 108, 108, 97,
10
+ 109, 103, 121, 108, 99, 104, 97, 109, 108, 97, 109, 108, 119, 103, 97, 109, 114, 121, 119, 97, 109, 114, 121, 119,
11
+ 105, 97, 101, 116, 104, 97, 110, 103, 101, 110, 97, 114, 97, 114, 97, 108, 108, 97, 114, 100, 97, 108, 97, 114, 102,
12
+ 101, 114, 97, 114, 110, 97, 102, 97, 114, 111, 115, 97, 116, 97, 116, 105, 97, 119, 114, 98, 97, 99, 104, 98, 97, 105,
13
+ 98, 97, 110, 116, 98, 97, 114, 111, 100, 98, 97, 119, 98, 98, 101, 108, 108, 97, 99, 104, 98, 101, 110, 98, 101, 116,
14
+ 104, 98, 108, 97, 101, 110, 98, 108, 101, 98, 108, 105, 116, 104, 98, 111, 98, 98, 111, 98, 108, 98, 111, 98, 109, 97,
15
+ 110, 98, 111, 100, 98, 111, 115, 105, 98, 98, 114, 111, 110, 98, 114, 121, 100, 98, 119, 121, 115, 105, 103, 98, 121,
16
+ 100, 98, 121, 100, 100, 98, 121, 100, 100, 97, 102, 98, 121, 100, 100, 97, 105, 98, 121, 100, 100, 101, 110, 98, 121,
17
+ 100, 100, 119, 110, 98, 121, 110, 110, 97, 103, 98, 121, 116, 104, 99, 97, 100, 119, 99, 97, 101, 108, 99, 97, 110,
18
+ 116, 99, 101, 102, 110, 111, 103, 105, 99, 101, 105, 99, 101, 105, 115, 105, 111, 99, 104, 97, 101, 108, 99, 104, 100,
19
+ 105, 99, 104, 101, 105, 99, 104, 105, 99, 104, 119, 97, 114, 97, 101, 99, 104, 119, 101, 99, 104, 119, 101, 99, 104,
20
+ 99, 104, 119, 105, 99, 111, 100, 105, 99, 111, 108, 108, 105, 99, 114, 101, 100, 117, 99, 119, 101, 115, 116, 105,
21
+ 121, 110, 97, 117, 99, 121, 100, 99, 121, 102, 97, 109, 115, 101, 114, 99, 121, 102, 97, 110, 99, 121, 102, 101, 114,
22
+ 99, 121, 109, 114, 121, 100, 99, 121, 110, 99, 121, 110, 116, 99, 121, 110, 116, 97, 102, 100, 97, 100, 97, 108, 100,
23
+ 97, 110, 100, 97, 110, 103, 111, 115, 100, 97, 117, 100, 97, 119, 100, 100, 97, 100, 100, 97, 117, 100, 100, 101, 99,
24
+ 104, 114, 97, 117, 100, 100, 101, 102, 110, 121, 100, 100, 105, 111, 100, 100, 105, 102, 114, 105, 102, 111, 108, 100,
25
+ 100, 105, 103, 111, 110, 100, 100, 105, 109, 100, 100, 105, 119, 101, 100, 100, 97, 114, 100, 100, 111, 100, 100, 100,
26
+ 119, 101, 117, 100, 100, 100, 119, 121, 100, 100, 121, 100, 100, 100, 100, 121, 108, 97, 105, 100, 100, 121, 108, 101,
27
+ 100, 100, 121, 108, 101, 110, 100, 101, 98, 121, 103, 100, 101, 99, 104, 114, 97, 117, 100, 101, 102, 110, 121, 100,
28
+ 100, 100, 101, 102, 110, 121, 100, 100, 105, 111, 100, 101, 103, 100, 101, 114, 98, 121, 110, 100, 101, 117, 100, 100,
29
+ 101, 103, 100, 101, 117, 103, 97, 105, 110, 100, 101, 119, 105, 115, 100, 105, 100, 105, 102, 114, 105, 102, 111, 108,
30
+ 100, 105, 103, 111, 110, 100, 105, 103, 119, 121, 100, 100, 100, 105, 103, 119, 121, 100, 100, 105, 97, 100, 100, 105,
31
+ 108, 121, 110, 100, 105, 109, 100, 105, 112, 121, 110, 100, 105, 115, 103, 119, 121, 108, 100, 105, 119, 101, 100,
32
+ 100, 100, 105, 119, 101, 100, 100, 97, 114, 100, 105, 119, 101, 116, 104, 97, 102, 100, 105, 119, 114, 110, 111, 100,
33
+ 100, 111, 100, 111, 100, 100, 111, 101, 115, 100, 114, 97, 119, 115, 100, 114, 111, 115, 100, 114, 119, 121, 100, 119,
34
+ 101, 117, 100, 100, 119, 105, 100, 119, 121, 100, 121, 100, 121, 100, 100, 100, 121, 108, 97, 105, 100, 121, 108, 101,
35
+ 100, 121, 108, 101, 110, 100, 121, 109, 97, 100, 121, 110, 97, 101, 102, 101, 102, 97, 108, 108, 97, 105, 101, 102,
36
+ 111, 101, 105, 101, 105, 99, 104, 101, 105, 110, 101, 105, 115, 105, 97, 117, 101, 105, 115, 105, 111, 101, 115, 101,
37
+ 105, 115, 111, 101, 115, 101, 110, 119, 101, 100, 105, 103, 101, 114, 101, 114, 97, 105, 108, 108, 101, 114, 98, 121,
38
+ 110, 101, 114, 105, 111, 101, 100, 101, 114, 115, 101, 116, 111, 101, 117, 102, 97, 99, 104, 102, 97, 105, 110, 116,
39
+ 102, 97, 110, 102, 97, 116, 104, 102, 97, 119, 114, 102, 101, 102, 101, 108, 102, 101, 108, 108, 121, 102, 101, 115,
40
+ 117, 108, 102, 101, 119, 110, 102, 102, 119, 114, 100, 100, 102, 105, 102, 111, 102, 111, 100, 102, 111, 100, 100,
41
+ 102, 119, 121, 102, 119, 121, 97, 102, 102, 121, 102, 121, 100, 100, 102, 121, 100, 100, 97, 102, 102, 121, 100, 100,
42
+ 97, 105, 102, 121, 100, 100, 101, 110, 102, 121, 110, 100, 102, 121, 110, 121, 102, 121, 116, 104, 103, 97, 100, 97,
43
+ 101, 108, 103, 97, 100, 119, 103, 97, 101, 108, 103, 97, 102, 111, 100, 100, 103, 97, 108, 108, 103, 97, 108, 108, 97,
44
+ 105, 103, 97, 108, 108, 117, 103, 97, 108, 119, 103, 97, 110, 103, 101, 105, 115, 105, 111, 103, 101, 110, 103, 101,
45
+ 110, 110, 121, 99, 104, 103, 101, 114, 108, 108, 97, 119, 103, 105, 108, 121, 100, 100, 103, 111, 98, 101, 105, 116,
46
+ 104, 105, 111, 103, 111, 114, 97, 117, 103, 111, 115, 111, 100, 103, 119, 97, 101, 108, 111, 100, 103, 119, 97, 103,
47
+ 103, 119, 97, 104, 97, 110, 111, 108, 103, 119, 101, 108, 100, 103, 119, 101, 108, 119, 99, 104, 103, 119, 105, 114,
48
+ 105, 111, 110, 101, 100, 100, 111, 108, 103, 119, 109, 112, 97, 115, 103, 119, 110, 97, 101, 116, 104, 103, 119, 110,
49
+ 97, 102, 103, 119, 110, 97, 119, 110, 103, 119, 110, 101, 117, 100, 103, 119, 121, 98, 111, 100, 103, 121, 100, 103,
50
+ 121, 100, 97, 103, 121, 100, 97, 103, 103, 121, 102, 97, 110, 103, 121, 102, 101, 114, 103, 121, 109, 114, 121, 100,
51
+ 103, 121, 110, 116, 103, 121, 110, 116, 97, 102, 103, 121, 119, 105, 114, 104, 97, 110, 102, 111, 100, 111, 108, 104,
52
+ 97, 110, 110, 101, 114, 104, 101, 98, 104, 101, 100, 100, 105, 119, 104, 101, 102, 121, 100, 104, 105, 104, 105, 114,
53
+ 104, 111, 108, 108, 104, 111, 110, 104, 117, 110, 104, 117, 110, 97, 105, 110, 104, 119, 110, 104, 119, 121, 110, 116,
54
+ 104, 121, 100, 104, 121, 110, 104, 121, 110, 110, 121, 104, 121, 116, 114, 97, 99, 104, 105, 105, 97, 119, 110, 105,
55
+ 100, 100, 105, 105, 100, 100, 111, 105, 100, 100, 121, 110, 105, 100, 100, 121, 110, 116, 105, 115, 105, 115, 111,
56
+ 100, 108, 97, 119, 101, 114, 108, 97, 119, 110, 108, 97, 119, 114, 108, 108, 97, 105, 108, 108, 97, 119, 101, 114,
57
+ 108, 108, 97, 119, 110, 108, 108, 101, 108, 108, 101, 105, 97, 102, 108, 111, 116, 109, 97, 101, 109, 97, 101, 110,
58
+ 109, 97, 101, 110, 116, 109, 97, 101, 115, 109, 97, 105, 109, 97, 105, 110, 116, 109, 97, 116, 104, 109, 97, 119, 114,
59
+ 109, 101, 100, 100, 97, 105, 109, 101, 103, 105, 115, 109, 101, 116, 104, 117, 109, 101, 119, 110, 109, 105, 109, 111,
60
+ 100, 109, 111, 100, 100, 109, 111, 114, 109, 117, 110, 117, 100, 109, 119, 121, 109, 119, 121, 97, 102, 109, 119, 121,
61
+ 110, 109, 121, 110, 100, 110, 110, 97, 110, 97, 100, 110, 97, 100, 100, 111, 110, 97, 103, 110, 97, 105, 108, 108,
62
+ 110, 97, 119, 110, 97, 119, 114, 110, 101, 98, 110, 101, 115, 97, 102, 110, 101, 117, 110, 104, 119, 110, 105, 110,
63
+ 105, 100, 110, 105, 102, 101, 114, 110, 105, 115, 110, 111, 100, 105, 110, 111, 115, 110, 117, 110, 108, 108, 101,
64
+ 111, 111, 99, 104, 114, 111, 100, 100, 105, 111, 101, 100, 100, 111, 101, 115, 111, 103, 121, 115, 116, 97, 108, 111,
65
+ 104, 101, 114, 119, 121, 100, 100, 111, 108, 97, 102, 111, 110, 100, 111, 110, 105, 111, 115, 112, 97, 112, 97, 109,
66
+ 112, 97, 110, 112, 97, 114, 104, 97, 117, 112, 97, 119, 98, 112, 101, 100, 97, 105, 114, 112, 101, 100, 119, 97, 114,
67
+ 112, 101, 110, 111, 100, 111, 108, 112, 101, 116, 104, 112, 101, 116, 104, 97, 117, 112, 108, 101, 110, 116, 121, 110,
68
+ 112, 108, 105, 116, 104, 112, 108, 238, 115, 112, 111, 98, 112, 111, 98, 109, 97, 110, 112, 111, 112, 101, 116, 104,
69
+ 112, 114, 105, 102, 112, 114, 121, 100, 112, 117, 109, 112, 117, 109, 112, 112, 121, 109, 116, 104, 101, 103, 114,
70
+ 114, 97, 105, 114, 97, 110, 114, 104, 97, 103, 114, 104, 97, 105, 114, 104, 97, 105, 100, 114, 104, 97, 105, 110, 114,
71
+ 104, 97, 110, 114, 104, 101, 105, 110, 105, 114, 104, 101, 105, 110, 121, 114, 104, 111, 105, 114, 104, 119, 110, 103,
72
+ 114, 104, 121, 119, 114, 104, 121, 119, 98, 101, 116, 104, 114, 104, 121, 119, 98, 114, 121, 100, 114, 104, 121, 119,
73
+ 102, 97, 105, 110, 116, 114, 104, 121, 119, 108, 101, 114, 104, 121, 119, 115, 117, 116, 114, 105, 111, 101, 100, 114,
74
+ 111, 101, 100, 100, 114, 111, 101, 100, 100, 119, 110, 114, 111, 105, 114, 119, 121, 114, 119, 121, 102, 114, 121,
75
+ 100, 119, 114, 121, 100, 121, 99, 104, 114, 121, 100, 121, 109, 114, 121, 119, 102, 97, 105, 110, 116, 114, 121, 119,
76
+ 115, 117, 116, 115, 97, 105, 116, 104, 115, 97, 119, 108, 115, 101, 102, 115, 105, 99, 114, 104, 97, 117, 115, 105,
77
+ 119, 114, 115, 105, 373, 114, 115, 117, 116, 115, 121, 115, 121, 100, 100, 115, 121, 109, 117, 100, 116, 97, 105, 114,
78
+ 116, 97, 110, 116, 101, 98, 121, 103, 116, 105, 116, 105, 112, 121, 110, 116, 111, 112, 116, 114, 97, 116, 114, 105,
79
+ 116, 114, 111, 116, 114, 111, 115, 116, 114, 119, 121, 116, 117, 116, 117, 97, 116, 117, 97, 103, 117, 99, 104, 101,
80
+ 108, 117, 99, 104, 111, 100, 117, 103, 97, 105, 110, 117, 110, 117, 110, 105, 103, 117, 110, 105, 103, 111, 108, 121,
81
+ 110, 117, 110, 105, 111, 110, 117, 110, 108, 108, 101, 117, 110, 114, 104, 121, 119, 117, 110, 119, 97, 105, 116, 104,
82
+ 117, 119, 99, 104, 117, 119, 99, 104, 98, 101, 110, 119, 97, 104, 97, 110, 111, 108, 119, 97, 104, 226, 110, 119, 97,
83
+ 105, 116, 104, 119, 101, 100, 105, 119, 101, 100, 121, 110, 119, 101, 105, 116, 104, 105, 97, 117, 119, 101, 105, 116,
84
+ 104, 105, 111, 119, 101, 108, 119, 101, 108, 108, 119, 105, 114, 119, 105, 114, 105, 111, 110, 101, 100, 100, 111,
85
+ 108, 119, 110, 97, 101, 116, 104, 119, 110, 97, 102, 119, 110, 101, 115, 119, 110, 101, 117, 100, 119, 114, 116, 104,
86
+ 119, 121, 98, 111, 100, 119, 121, 102, 119, 121, 116, 104, 121, 121, 99, 104, 119, 97, 110, 101, 103, 111, 108, 121,
87
+ 99, 104, 121, 100, 105, 103, 121, 100, 119, 121, 102, 121, 100, 121, 121, 100, 121, 99, 104, 121, 100, 121, 109, 121,
88
+ 109, 121, 109, 97, 121, 109, 100, 100, 97, 110, 103, 111, 115, 121, 109, 100, 100, 101, 110, 103, 121, 115, 121, 109,
89
+ 108, 97, 101, 110, 121, 109, 121, 115, 103, 121, 110, 121, 110, 97, 121, 110, 103, 121, 110, 103, 108, 375, 110, 121,
90
+ 110, 111, 121, 114, 121, 115, 116, 111, 100, 121, 119, 226, 244, 108,
91
+ };
92
+
93
+ static const uint32_t stop_word_offsets[435] = {
94
+ 0, 1, 3, 8, 14, 19, 21, 25, 27, 30, 33, 38, 42, 44, 50, 57, 60, 65, 70, 80, 85, 87, 92, 97, 102, 107, 111, 113, 116,
95
+ 119, 123, 126, 130, 135, 139, 146, 149, 153, 158, 161, 166, 169, 173, 179, 182, 187, 191, 195, 201, 204, 208, 214,
96
+ 220, 226, 232, 238, 242, 246, 250, 254, 261, 264, 270, 275, 279, 283, 286, 293, 297, 303, 307, 311, 316, 321, 331,
97
+ 334, 342, 347, 352, 358, 361, 365, 371, 373, 376, 379, 385, 388, 391, 394, 398, 406, 416, 425, 431, 435, 444, 448,
98
+ 454, 458, 463, 469, 474, 480, 485, 492, 499, 508, 511, 517, 524, 531, 536, 538, 546, 551, 558, 568, 573, 576, 581,
99
+ 588, 594, 602, 610, 617, 619, 622, 626, 631, 635, 639, 644, 647, 650, 652, 656, 661, 665, 670, 674, 678, 680, 687,
100
+ 690, 692, 696, 699, 705, 712, 718, 725, 727, 733, 738, 744, 747, 750, 752, 756, 761, 764, 768, 772, 774, 777, 782,
101
+ 787, 791, 797, 799, 801, 804, 808, 811, 816, 818, 822, 828, 834, 840, 844, 848, 852, 858, 862, 866, 872, 876, 882,
102
+ 887, 891, 894, 900, 903, 910, 917, 923, 932, 937, 942, 949, 953, 961, 966, 973, 985, 991, 998, 1003, 1009, 1015, 1021,
103
+ 1024, 1028, 1033, 1038, 1043, 1049, 1053, 1059, 1064, 1072, 1078, 1081, 1087, 1092, 1094, 1097, 1101, 1104, 1107,
104
+ 1113, 1116, 1121, 1124, 1127, 1132, 1139, 1140, 1144, 1148, 1152, 1157, 1163, 1165, 1169, 1174, 1178, 1182, 1186,
105
+ 1192, 1197, 1200, 1206, 1209, 1212, 1216, 1221, 1225, 1228, 1233, 1237, 1241, 1247, 1252, 1257, 1261, 1263, 1266,
106
+ 1270, 1273, 1278, 1281, 1286, 1290, 1294, 1295, 1297, 1300, 1305, 1308, 1313, 1316, 1320, 1323, 1328, 1331, 1334,
107
+ 1336, 1339, 1344, 1347, 1351, 1354, 1360, 1361, 1365, 1369, 1373, 1376, 1383, 1391, 1395, 1398, 1401, 1403, 1405,
108
+ 1408, 1411, 1417, 1421, 1427, 1433, 1440, 1444, 1450, 1457, 1462, 1466, 1469, 1475, 1481, 1485, 1489, 1492, 1496,
109
+ 1503, 1504, 1507, 1510, 1514, 1518, 1523, 1528, 1532, 1538, 1544, 1548, 1553, 1557, 1565, 1573, 1582, 1588, 1595,
110
+ 1600, 1605, 1612, 1615, 1618, 1622, 1626, 1632, 1637, 1645, 1651, 1656, 1660, 1663, 1670, 1674, 1678, 1681, 1683,
111
+ 1687, 1692, 1696, 1699, 1704, 1706, 1711, 1714, 1717, 1720, 1723, 1727, 1731, 1733, 1736, 1740, 1745, 1750, 1755,
112
+ 1757, 1761, 1769, 1774, 1779, 1785, 1792, 1796, 1803, 1810, 1815, 1820, 1824, 1829, 1837, 1844, 1847, 1851, 1854,
113
+ 1865, 1871, 1875, 1879, 1884, 1888, 1893, 1896, 1900, 1901, 1911, 1918, 1923, 1926, 1931, 1935, 1937, 1940, 1949,
114
+ 1958, 1964, 1969, 1971, 1974, 1977, 1983, 1986, 1988, 1993, 1995, 1996, 1998,
115
+ };
116
+
117
+ static const uint32_t keep_ranges[74] = {
118
+ 48, 57, 65, 90, 97, 122, 170, 170, 186, 186, 192, 214, 216, 246, 248, 696, 736, 740, 7424, 7461, 7468, 7516, 7522,
119
+ 7525, 7531, 7543, 7545, 7614, 7680, 7935, 8305, 8305, 8319, 8319, 8336, 8348, 8490, 8491, 8498, 8498, 8526, 8526,
120
+ 8544, 8584, 11360, 11391, 42786, 42887, 42891, 42972, 42993, 43007, 43824, 43866, 43868, 43876, 43878, 43881, 64256,
121
+ 64262, 65313, 65338, 65345, 65370, 67456, 67461, 67463, 67504, 67506, 67514, 122624, 122654, 122661, 122666,
122
+ };
123
+
124
+ const narsil_language narsil_language_welsh = {
125
+ .name = "welsh",
126
+ .revision = "1",
127
+ .stop_word_units = stop_word_units,
128
+ .stop_word_offsets = stop_word_offsets,
129
+ .stop_word_count = 434,
130
+ .ascii_keep = {0x03FF000000000000ULL, 0x07FFFFFE07FFFFFEULL},
131
+ .keep_ranges = keep_ranges,
132
+ .keep_range_count = 37,
133
+ .splits_code_points = 1,
134
+ .strips_possessive = 0,
135
+ .normalises_diacritics = 0,
136
+ .min_token_length = 1,
137
+ .ngram_size = 0,
138
+ .normalise = NULL,
139
+ .stem_by_rules = NULL,
140
+ .create_snowball = NULL,
141
+ .snowball_stem = NULL,
142
+ .close_snowball = NULL,
143
+ };
@@ -0,0 +1,51 @@
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[204] = {
8
+ 97, 107, 97, 109, 98, 97, 98, 97, 110, 98, 101, 110, 101, 101, 110, 98, 101, 110, 110, 98, 105, 98, 105, 105, 98, 111,
9
+ 111, 98, 117, 98, 117, 99, 97, 99, 105, 100, 97, 102, 97, 100, 105, 110, 97, 100, 117, 102, 97, 102, 105, 102, 117,
10
+ 103, 105, 105, 116, 105, 116, 97, 109, 106, 105, 107, 105, 107, 111, 110, 107, 117, 108, 97, 108, 105, 108, 111, 111,
11
+ 108, 108, 117, 108, 233, 112, 112, 109, 97, 109, 97, 110, 109, 105, 109, 111, 111, 109, 109, 117, 110, 97, 110, 97,
12
+ 97, 110, 97, 241, 117, 110, 100, 97, 120, 110, 100, 97, 120, 116, 101, 110, 101, 110, 103, 97, 110, 103, 101, 101,
13
+ 110, 110, 105, 110, 117, 110, 114, 101, 107, 107, 115, 97, 115, 97, 109, 97, 115, 101, 101, 110, 115, 105, 115, 117,
14
+ 115, 117, 110, 117, 116, 101, 119, 97, 97, 121, 101, 119, 97, 108, 108, 97, 119, 105, 121, 101, 101, 110, 121, 101,
15
+ 110, 101, 101, 110, 121, 105, 121, 105, 105, 121, 111, 111, 121, 117, 121, 111, 119, 121, 233, 112, 112, 241, 105,
16
+ 241, 111, 111, 109, 241, 117, 241, 233, 112, 112,
17
+ };
18
+
19
+ static const uint32_t stop_word_offsets[68] = {
20
+ 0, 2, 4, 6, 9, 15, 19, 21, 24, 29, 31, 33, 35, 39, 43, 45, 47, 49, 51, 53, 55, 59, 61, 63, 66, 68, 70, 72, 76, 78, 82,
21
+ 84, 87, 89, 93, 95, 97, 100, 104, 108, 114, 116, 119, 124, 126, 129, 133, 135, 139, 143, 145, 147, 151, 153, 158, 163,
22
+ 165, 169, 175, 177, 180, 185, 188, 192, 194, 198, 200, 204,
23
+ };
24
+
25
+ static const uint32_t keep_ranges[74] = {
26
+ 48, 57, 65, 90, 97, 122, 170, 170, 186, 186, 192, 214, 216, 246, 248, 696, 736, 740, 7424, 7461, 7468, 7516, 7522,
27
+ 7525, 7531, 7543, 7545, 7614, 7680, 7935, 8305, 8305, 8319, 8319, 8336, 8348, 8490, 8491, 8498, 8498, 8526, 8526,
28
+ 8544, 8584, 11360, 11391, 42786, 42887, 42891, 42972, 42993, 43007, 43824, 43866, 43868, 43876, 43878, 43881, 64256,
29
+ 64262, 65313, 65338, 65345, 65370, 67456, 67461, 67463, 67504, 67506, 67514, 122624, 122654, 122661, 122666,
30
+ };
31
+
32
+ const narsil_language narsil_language_wolof = {
33
+ .name = "wolof",
34
+ .revision = "1",
35
+ .stop_word_units = stop_word_units,
36
+ .stop_word_offsets = stop_word_offsets,
37
+ .stop_word_count = 67,
38
+ .ascii_keep = {0x03FF000000000000ULL, 0x07FFFFFE07FFFFFEULL},
39
+ .keep_ranges = keep_ranges,
40
+ .keep_range_count = 37,
41
+ .splits_code_points = 1,
42
+ .strips_possessive = 0,
43
+ .normalises_diacritics = 0,
44
+ .min_token_length = 1,
45
+ .ngram_size = 0,
46
+ .normalise = NULL,
47
+ .stem_by_rules = NULL,
48
+ .create_snowball = NULL,
49
+ .snowball_stem = NULL,
50
+ .close_snowball = NULL,
51
+ };
@@ -0,0 +1,56 @@
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[384] = {
8
+ 97, 98, 97, 97, 98, 97, 110, 121, 101, 97, 98, 111, 97, 112, 104, 111, 98, 97, 107, 104, 101, 98, 111, 110, 97, 98,
9
+ 111, 110, 107, 101, 101, 108, 105, 101, 108, 111, 101, 109, 118, 97, 101, 110, 121, 101, 101, 115, 105, 101, 115, 111,
10
+ 101, 122, 105, 101, 122, 105, 110, 121, 101, 101, 122, 111, 107, 97, 107, 104, 117, 108, 117, 107, 97, 109, 118, 97,
11
+ 107, 97, 110, 99, 105, 110, 99, 105, 107, 97, 110, 121, 101, 107, 101, 107, 111, 100, 119, 97, 107, 111, 110, 107,
12
+ 101, 107, 117, 98, 97, 107, 117, 110, 121, 101, 107, 119, 97, 121, 101, 108, 97, 108, 97, 107, 104, 101, 108, 101,
13
+ 108, 101, 121, 111, 108, 111, 108, 111, 110, 107, 101, 108, 111, 119, 111, 109, 97, 108, 117, 110, 103, 97, 109, 110,
14
+ 97, 110, 97, 110, 97, 110, 103, 111, 110, 97, 110, 103, 97, 112, 104, 97, 107, 97, 116, 104, 105, 110, 103, 97, 112,
15
+ 104, 97, 110, 100, 108, 101, 110, 103, 101, 110, 120, 97, 110, 103, 111, 107, 117, 110, 103, 111, 107, 117, 98, 97,
16
+ 110, 105, 110, 97, 110, 106, 101, 111, 107, 97, 110, 121, 101, 111, 107, 111, 111, 107, 117, 111, 108, 111, 111, 108,
17
+ 117, 111, 109, 110, 121, 101, 112, 104, 97, 107, 97, 116, 104, 105, 112, 104, 97, 109, 98, 105, 112, 104, 97, 109, 98,
18
+ 105, 108, 105, 112, 104, 97, 110, 116, 115, 105, 112, 104, 101, 122, 117, 108, 117, 115, 97, 107, 104, 101, 115, 111,
19
+ 110, 107, 101, 116, 104, 105, 110, 97, 117, 107, 117, 98, 97, 117, 107, 117, 122, 101, 119, 97, 98, 111, 119, 97, 107,
20
+ 104, 101, 119, 97, 107, 104, 111, 119, 97, 109, 119, 101, 110, 97, 119, 101, 110, 117, 119, 101, 116, 104, 117, 120,
21
+ 97, 121, 97, 98, 111, 121, 97, 107, 104, 101, 121, 97, 107, 104, 111, 121, 97, 109, 121, 101, 110, 97, 121, 101, 110,
22
+ 117, 121, 101, 116, 104, 117, 121, 111, 110, 107, 101, 122, 97, 98, 111, 122, 97, 107, 104, 101, 122, 97, 107, 104,
23
+ 111, 122, 97, 109, 122, 101, 110, 117, 122, 101, 116, 104, 117, 122, 111, 110, 107, 101,
24
+ };
25
+
26
+ static const uint32_t stop_word_offsets[84] = {
27
+ 0, 3, 9, 12, 16, 21, 25, 30, 33, 36, 40, 44, 47, 50, 53, 59, 62, 69, 74, 82, 87, 89, 94, 99, 103, 108, 113, 115, 120,
28
+ 122, 126, 128, 133, 137, 144, 147, 149, 156, 167, 177, 183, 188, 195, 199, 202, 208, 211, 214, 217, 220, 225, 233,
29
+ 239, 247, 254, 261, 266, 271, 276, 281, 286, 290, 295, 300, 303, 307, 311, 316, 318, 322, 327, 332, 335, 339, 343,
30
+ 348, 353, 357, 362, 367, 370, 374, 379, 384,
31
+ };
32
+
33
+ static const uint32_t keep_ranges[8] = {
34
+ 45, 45, 48, 57, 65, 90, 97, 122,
35
+ };
36
+
37
+ const narsil_language narsil_language_xhosa = {
38
+ .name = "xhosa",
39
+ .revision = "1",
40
+ .stop_word_units = stop_word_units,
41
+ .stop_word_offsets = stop_word_offsets,
42
+ .stop_word_count = 83,
43
+ .ascii_keep = {0x03FF200000000000ULL, 0x07FFFFFE07FFFFFEULL},
44
+ .keep_ranges = keep_ranges,
45
+ .keep_range_count = 4,
46
+ .splits_code_points = 0,
47
+ .strips_possessive = 0,
48
+ .normalises_diacritics = 0,
49
+ .min_token_length = 1,
50
+ .ngram_size = 0,
51
+ .normalise = NULL,
52
+ .stem_by_rules = NULL,
53
+ .create_snowball = NULL,
54
+ .snowball_stem = NULL,
55
+ .close_snowball = NULL,
56
+ };
@@ -0,0 +1,93 @@
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[302] = {
8
+ 97, 97, 110, 98, 225, 98, 237, 98, 7865, 768, 114, 7865, 768, 98, 7865, 769, 7865, 768, 100, 237, 7865, 768, 102, 250,
9
+ 110, 102, 7865, 769, 103, 98, 111, 103, 98, 111, 103, 7865, 769, 103, 7865, 769, 105, 110, 250, 105, 114, 250, 106,
10
+ 249, 106, 7865, 106, 7865, 769, 107, 97, 110, 107, 236, 107, 237, 107, 242, 107, 7885, 769, 108, 225, 98, 7865, 769,
11
+ 108, 225, 116, 105, 108, 225, 224, 225, 114, 237, 110, 108, 232, 108, 243, 107, 232, 108, 243, 114, 237, 108, 7865,
12
+ 769, 121, 236, 110, 108, 7885, 109, 105, 109, 111, 109, 225, 97, 109, 7885, 768, 110, 105, 110, 225, 224, 110, 236,
13
+ 107, 97, 110, 110, 237, 110, 237, 103, 98, 224, 110, 237, 110, 250, 110, 237, 112, 97, 110, 237, 116, 111, 114, 237,
14
+ 110, 237, 116, 111, 114, 237, 112, 233, 110, 237, 119, 225, 106, 250, 110, 505, 107, 97, 110, 111, 111, 104, 117, 110,
15
+ 112, 97, 100, 224, 112, 224, 225, 112, 224, 225, 112, 233, 112, 250, 112, 7885, 768, 112, 7865, 768, 108, 250, 114,
16
+ 7865, 768, 115, 236, 115, 237, 115, 237, 98, 7865, 768, 115, 237, 110, 250, 116, 97, 98, 105, 116, 105, 116, 224, 98,
17
+ 237, 116, 237, 119, 224, 119, 225, 119, 7885, 110, 119, 7885, 768, 110, 121, 237, 119, 7885, 769, 110, 121, 236, 237,
18
+ 224, 116, 105, 224, 119, 97, 224, 119, 7885, 110, 232, 109, 105, 233, 236, 119, 7885, 237, 242, 117, 110, 243, 324,
19
+ 324, 108, 225, 7779, 7779, 101, 7779, 233, 7779, 249, 103, 98, 7885, 769, 110, 7865, 7865, 109, 7885, 769, 7865, 110,
20
+ 105, 7865, 121, 105, 110, 7885, 106, 7885, 769, 7885, 768, 112, 7885, 768, 108, 7885, 112, 7885, 768, 7885, 768, 117,
21
+ 110,
22
+ };
23
+
24
+ static const uint32_t stop_word_offsets[89] = {
25
+ 0, 1, 3, 5, 7, 13, 18, 22, 25, 28, 34, 40, 43, 46, 48, 50, 53, 56, 58, 60, 62, 65, 70, 74, 81, 83, 87, 91, 97, 99,
26
+ 101, 103, 106, 109, 111, 114, 119, 121, 126, 130, 134, 140, 148, 154, 159, 160, 164, 168, 174, 176, 181, 186, 189,
27
+ 191, 193, 198, 202, 206, 208, 212, 214, 216, 218, 221, 227, 231, 234, 237, 240, 244, 247, 248, 251, 252, 255, 256,
28
+ 257, 260, 261, 263, 265, 272, 273, 277, 280, 284, 288, 298, 302,
29
+ };
30
+
31
+ static const uint32_t keep_ranges[700] = {
32
+ 48, 57, 65, 90, 97, 122, 192, 193, 200, 201, 204, 205, 210, 211, 217, 218, 224, 225, 232, 233, 236, 237, 242, 243,
33
+ 249, 250, 323, 324, 383, 383, 504, 505, 768, 879, 921, 921, 953, 953, 1155, 1161, 1425, 1469, 1471, 1471, 1473, 1474,
34
+ 1476, 1477, 1479, 1479, 1552, 1562, 1611, 1631, 1648, 1648, 1750, 1756, 1759, 1764, 1767, 1768, 1770, 1773, 1809,
35
+ 1809, 1840, 1866, 1958, 1968, 2027, 2035, 2045, 2045, 2070, 2073, 2075, 2083, 2085, 2087, 2089, 2093, 2137, 2139,
36
+ 2199, 2207, 2250, 2273, 2275, 2307, 2362, 2364, 2366, 2383, 2385, 2391, 2402, 2403, 2433, 2435, 2492, 2492, 2494,
37
+ 2500, 2503, 2504, 2507, 2509, 2519, 2519, 2530, 2531, 2558, 2558, 2561, 2563, 2620, 2620, 2622, 2626, 2631, 2632,
38
+ 2635, 2637, 2641, 2641, 2672, 2673, 2677, 2677, 2689, 2691, 2748, 2748, 2750, 2757, 2759, 2761, 2763, 2765, 2786,
39
+ 2787, 2810, 2815, 2817, 2819, 2876, 2876, 2878, 2884, 2887, 2888, 2891, 2893, 2901, 2903, 2914, 2915, 2946, 2946,
40
+ 3006, 3010, 3014, 3016, 3018, 3021, 3031, 3031, 3072, 3076, 3132, 3132, 3134, 3140, 3142, 3144, 3146, 3149, 3157,
41
+ 3158, 3170, 3171, 3201, 3203, 3260, 3260, 3262, 3268, 3270, 3272, 3274, 3277, 3285, 3286, 3298, 3299, 3315, 3315,
42
+ 3328, 3331, 3387, 3388, 3390, 3396, 3398, 3400, 3402, 3405, 3415, 3415, 3426, 3427, 3457, 3459, 3530, 3530, 3535,
43
+ 3540, 3542, 3542, 3544, 3551, 3570, 3571, 3633, 3633, 3636, 3642, 3655, 3662, 3761, 3761, 3764, 3772, 3784, 3790,
44
+ 3864, 3865, 3893, 3893, 3895, 3895, 3897, 3897, 3902, 3903, 3953, 3972, 3974, 3975, 3981, 3991, 3993, 4028, 4038,
45
+ 4038, 4139, 4158, 4182, 4185, 4190, 4192, 4194, 4196, 4199, 4205, 4209, 4212, 4226, 4237, 4239, 4239, 4250, 4253,
46
+ 4957, 4959, 5906, 5909, 5938, 5940, 5970, 5971, 6002, 6003, 6068, 6099, 6109, 6109, 6155, 6157, 6159, 6159, 6277,
47
+ 6278, 6313, 6313, 6432, 6443, 6448, 6459, 6679, 6683, 6741, 6750, 6752, 6780, 6783, 6783, 6832, 6877, 6880, 6891,
48
+ 6912, 6916, 6964, 6980, 7019, 7027, 7040, 7042, 7073, 7085, 7142, 7155, 7204, 7223, 7376, 7378, 7380, 7400, 7405,
49
+ 7405, 7412, 7412, 7415, 7417, 7616, 7679, 7778, 7779, 7864, 7865, 7884, 7885, 8126, 8126, 8400, 8432, 8490, 8490,
50
+ 11503, 11505, 11647, 11647, 11744, 11775, 12330, 12335, 12441, 12442, 42607, 42610, 42612, 42621, 42654, 42655, 42736,
51
+ 42737, 43010, 43010, 43014, 43014, 43019, 43019, 43043, 43047, 43052, 43052, 43136, 43137, 43188, 43205, 43232, 43249,
52
+ 43263, 43263, 43302, 43309, 43335, 43347, 43392, 43395, 43443, 43456, 43493, 43493, 43561, 43574, 43587, 43587, 43596,
53
+ 43597, 43643, 43645, 43696, 43696, 43698, 43700, 43703, 43704, 43710, 43711, 43713, 43713, 43755, 43759, 43765, 43766,
54
+ 44003, 44010, 44012, 44013, 64286, 64286, 65024, 65039, 65056, 65071, 66045, 66045, 66272, 66272, 66422, 66426, 68097,
55
+ 68099, 68101, 68102, 68108, 68111, 68152, 68154, 68159, 68159, 68325, 68326, 68900, 68903, 68969, 68973, 69291, 69292,
56
+ 69370, 69375, 69446, 69456, 69506, 69509, 69632, 69634, 69688, 69702, 69744, 69744, 69747, 69748, 69759, 69762, 69808,
57
+ 69818, 69826, 69826, 69888, 69890, 69927, 69940, 69957, 69958, 70003, 70003, 70016, 70018, 70067, 70080, 70089, 70092,
58
+ 70094, 70095, 70188, 70199, 70206, 70206, 70209, 70209, 70367, 70378, 70400, 70403, 70459, 70460, 70462, 70468, 70471,
59
+ 70472, 70475, 70477, 70487, 70487, 70498, 70499, 70502, 70508, 70512, 70516, 70584, 70592, 70594, 70594, 70597, 70597,
60
+ 70599, 70602, 70604, 70608, 70610, 70610, 70625, 70626, 70709, 70726, 70750, 70750, 70832, 70851, 71087, 71093, 71096,
61
+ 71104, 71132, 71133, 71216, 71232, 71339, 71351, 71453, 71467, 71724, 71738, 71984, 71989, 71991, 71992, 71995, 71998,
62
+ 72000, 72000, 72002, 72003, 72145, 72151, 72154, 72160, 72164, 72164, 72193, 72202, 72243, 72249, 72251, 72254, 72263,
63
+ 72263, 72273, 72283, 72330, 72345, 72544, 72551, 72751, 72758, 72760, 72767, 72850, 72871, 72873, 72886, 73009, 73014,
64
+ 73018, 73018, 73020, 73021, 73023, 73029, 73031, 73031, 73098, 73102, 73104, 73105, 73107, 73111, 73459, 73462, 73472,
65
+ 73473, 73475, 73475, 73524, 73530, 73534, 73538, 73562, 73562, 78912, 78912, 78919, 78933, 90398, 90415, 92912, 92916,
66
+ 92976, 92982, 94031, 94031, 94033, 94087, 94095, 94098, 94180, 94180, 94192, 94193, 113821, 113822, 118528, 118573,
67
+ 118576, 118598, 119141, 119145, 119149, 119154, 119163, 119170, 119173, 119179, 119210, 119213, 119362, 119364,
68
+ 121344, 121398, 121403, 121452, 121461, 121461, 121476, 121476, 121499, 121503, 121505, 121519, 122880, 122886,
69
+ 122888, 122904, 122907, 122913, 122915, 122916, 122918, 122922, 123023, 123023, 123184, 123190, 123566, 123566,
70
+ 123628, 123631, 124140, 124143, 124398, 124399, 124643, 124643, 124646, 124646, 124654, 124655, 124661, 124661,
71
+ 125136, 125142, 125252, 125258, 917760, 917999,
72
+ };
73
+
74
+ const narsil_language narsil_language_yoruba = {
75
+ .name = "yoruba",
76
+ .revision = "1",
77
+ .stop_word_units = stop_word_units,
78
+ .stop_word_offsets = stop_word_offsets,
79
+ .stop_word_count = 88,
80
+ .ascii_keep = {0x03FF000000000000ULL, 0x07FFFFFE07FFFFFEULL},
81
+ .keep_ranges = keep_ranges,
82
+ .keep_range_count = 350,
83
+ .splits_code_points = 1,
84
+ .strips_possessive = 0,
85
+ .normalises_diacritics = 0,
86
+ .min_token_length = 1,
87
+ .ngram_size = 0,
88
+ .normalise = NULL,
89
+ .stem_by_rules = NULL,
90
+ .create_snowball = NULL,
91
+ .snowball_stem = NULL,
92
+ .close_snowball = NULL,
93
+ };