@delali/narsil-react-native 0.3.1-next.155 → 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 +1,69 @@
1
+ #include "../../analysis/languages.h"
2
+ #include "declarations.h"
3
+ #include "../snowball/tamil_stemmer.h"
4
+
5
+ #include <stddef.h>
6
+ #include <stdint.h>
7
+
8
+ static const uint16_t stop_word_units[503] = {
9
+ 2949, 2969, 3021, 2965, 3009, 2949, 2969, 3021, 2965, 3015, 2949, 2975, 3009, 2980, 3021, 2980, 2949, 2980, 2985,
10
+ 3006, 2994, 3021, 2949, 2980, 2985, 3021, 2949, 2980, 2993, 3021, 2965, 3009, 2949, 2980, 3007, 2965, 2949, 2980,
11
+ 3007, 2994, 3021, 2949, 2980, 3009, 2949, 2980, 3015, 2949, 2980, 3016, 2949, 2984, 3021, 2980, 2949, 2985, 3021,
12
+ 2993, 3009, 2949, 2994, 3021, 2994, 2980, 3009, 2949, 2997, 2985, 3021, 2949, 2997, 2992, 2980, 3009, 2949, 2997,
13
+ 2992, 3021, 2949, 2997, 2992, 3021, 2965, 2995, 3021, 2949, 2997, 2995, 3021, 2949, 2997, 3016, 2950, 2965, 3007,
14
+ 2991, 2950, 2965, 3007, 2991, 3019, 2992, 3021, 2950, 2965, 3009, 2990, 3021, 2951, 2969, 3021, 2965, 3009, 2951,
15
+ 2969, 3021, 2965, 3015, 2951, 2975, 2990, 3021, 2951, 2980, 2985, 3006, 2994, 3021, 2951, 2980, 2985, 3016, 2951,
16
+ 2980, 2985, 3021, 2951, 2980, 2993, 3021, 2965, 3009, 2951, 2980, 3007, 2994, 3021, 2951, 2980, 3009, 2951, 2980,
17
+ 3016, 2951, 2984, 3021, 2980, 2951, 2985, 3021, 2985, 3009, 2990, 3021, 2951, 2986, 3021, 2986, 3019, 2980, 3009,
18
+ 2951, 2992, 3009, 2951, 2992, 3009, 2965, 3021, 2965, 3009, 2990, 3021, 2951, 2992, 3009, 2984, 3021, 2980, 2951,
19
+ 2992, 3009, 2984, 3021, 2980, 3009, 2951, 2997, 2992, 3021, 2951, 2997, 3016, 2953, 2985, 3021, 2953, 2995, 3021,
20
+ 2995, 2953, 2995, 3021, 2995, 2980, 3009, 2953, 2995, 3021, 2995, 2985, 2958, 2984, 3021, 2980, 2958, 2985, 2958,
21
+ 2985, 2997, 3015, 2958, 2985, 3009, 2990, 3021, 2958, 2985, 3021, 2958, 2985, 3021, 2985, 2958, 2985, 3021, 2985,
22
+ 3009, 2990, 3021, 2958, 2985, 3021, 2986, 2980, 3009, 2958, 2985, 3021, 2986, 2980, 3016, 2958, 2985, 3021, 2993,
23
+ 2958, 2985, 3021, 2993, 3009, 2958, 2985, 3021, 2993, 3009, 2990, 3021, 2958, 2994, 3021, 2994, 3006, 2990, 3021,
24
+ 2959, 2985, 3021, 2962, 2992, 3009, 2962, 2992, 3015, 2963, 2992, 3021, 2965, 3018, 2979, 3021, 2975, 2965, 3018,
25
+ 2979, 3021, 2975, 3009, 2965, 3018, 2995, 3021, 2995, 2970, 2993, 3021, 2993, 3009, 2970, 3007, 2993, 3009, 2970,
26
+ 3007, 2994, 2980, 2985, 2980, 3009, 2980, 2985, 3021, 2980, 2997, 3007, 2992, 2980, 3006, 2985, 3021, 2984, 3006,
27
+ 2985, 3021, 2984, 3006, 2990, 3021, 2984, 3008, 2986, 2993, 3021, 2993, 3007, 2986, 2993, 3021, 2993, 3007, 2991,
28
+ 2986, 2994, 2986, 2994, 3021, 2997, 3015, 2993, 3009, 2986, 3007, 2985, 3021, 2986, 3007, 2985, 3021, 2985, 2992,
29
+ 3021, 2986, 3007, 2993, 2986, 3007, 2993, 2965, 3009, 2986, 3015, 2992, 3021, 2986, 3019, 2980, 3009, 2986, 3019,
30
+ 2985, 3021, 2993, 2986, 3019, 2994, 2986, 3019, 2994, 3021, 2990, 2975, 3021, 2975, 3009, 2990, 3015, 2990, 2975,
31
+ 3021, 2975, 3009, 2990, 3021, 2990, 2993, 3021, 2993, 2990, 2993, 3021, 2993, 3009, 2990, 3021, 2990, 3007, 2965,
32
+ 2990, 3007, 2965, 2997, 3009, 2990, 3021, 2990, 3008, 2980, 3009, 2990, 3009, 2980, 2994, 3021, 2990, 3009, 2993,
33
+ 3016, 2990, 3015, 2994, 3009, 2990, 3021, 2990, 3015, 2994, 3021, 2991, 3006, 2992, 3021, 2997, 2984, 3021, 2980,
34
+ 2997, 2984, 3021, 2980, 3009, 2997, 2992, 3009, 2990, 3021, 2997, 2992, 3016, 2997, 3007, 2975, 2997, 3015, 2979,
35
+ 3021, 2975, 3009, 2990, 3021, 2997, 3015, 2993, 3009,
36
+ };
37
+
38
+ static const uint32_t stop_word_offsets[109] = {
39
+ 0, 5, 10, 16, 22, 26, 32, 36, 41, 44, 47, 50, 54, 59, 65, 69, 74, 78, 85, 89, 92, 96, 103, 108, 113, 118, 122, 128,
40
+ 132, 136, 142, 147, 150, 153, 157, 164, 171, 174, 183, 189, 196, 200, 203, 206, 210, 216, 221, 225, 227, 231, 236,
41
+ 239, 243, 250, 256, 262, 266, 271, 278, 285, 288, 291, 294, 297, 302, 308, 313, 318, 322, 325, 329, 332, 336, 340,
42
+ 344, 348, 350, 355, 361, 363, 370, 374, 381, 384, 389, 393, 397, 402, 405, 409, 416, 423, 427, 434, 437, 444, 448,
43
+ 453, 457, 463, 467, 471, 475, 480, 485, 488, 491, 499, 503,
44
+ };
45
+
46
+ static const uint32_t keep_ranges[8] = {
47
+ 48, 57, 65, 90, 97, 122, 2944, 3071,
48
+ };
49
+
50
+ const narsil_language narsil_language_tamil = {
51
+ .name = "tamil",
52
+ .revision = "f859bf3d19447fbc",
53
+ .stop_word_units = stop_word_units,
54
+ .stop_word_offsets = stop_word_offsets,
55
+ .stop_word_count = 108,
56
+ .ascii_keep = {0x03FF000000000000ULL, 0x07FFFFFE07FFFFFEULL},
57
+ .keep_ranges = keep_ranges,
58
+ .keep_range_count = 4,
59
+ .splits_code_points = 0,
60
+ .strips_possessive = 0,
61
+ .normalises_diacritics = 0,
62
+ .min_token_length = 1,
63
+ .ngram_size = 0,
64
+ .normalise = NULL,
65
+ .stem_by_rules = NULL,
66
+ .create_snowball = tamil_create_env,
67
+ .snowball_stem = tamil_stem,
68
+ .close_snowball = tamil_close_env,
69
+ };