twitter_cldr 1.6.2 → 1.7.0

Sign up to get free protection for your applications and to get access to all the features.
Files changed (733) hide show
  1. data/Gemfile +3 -1
  2. data/History.txt +8 -0
  3. data/README.md +64 -14
  4. data/Rakefile +57 -7
  5. data/js/lib/compiler.rb +3 -1
  6. data/js/lib/mustache/bundle.coffee +5 -5
  7. data/js/lib/mustache/numbers/numbers.coffee +179 -0
  8. data/js/lib/mustache/shared/currencies.coffee +27 -0
  9. data/js/lib/renderers/numbers/numbers_renderer.rb +31 -0
  10. data/js/lib/renderers/plurals/rules/plural_rules_compiler.rb +5 -1
  11. data/js/lib/renderers/shared/currencies_renderer.rb +23 -0
  12. data/js/lib/twitter_cldr_js.rb +2 -0
  13. data/js/spec/js/calendars/timespan_spec.js +2 -2
  14. data/js/spec/js/numbers/currency_spec.js +34 -0
  15. data/js/spec/js/numbers/decimal_spec.js +24 -0
  16. data/js/spec/js/numbers/helpers/fraction_spec.js +23 -0
  17. data/js/spec/js/numbers/helpers/integer_spec.js +100 -0
  18. data/js/spec/js/numbers/number_spec.js +70 -0
  19. data/js/spec/js/numbers/percent_spec.js +22 -0
  20. data/js/spec/rb/renderers/plurals/plural_rules_compiler_spec.rb +4 -0
  21. data/lib/twitter_cldr/collation/collator.rb +14 -20
  22. data/lib/twitter_cldr/collation/trie_builder.rb +3 -3
  23. data/lib/twitter_cldr/formatters/numbers/decimal_formatter.rb +0 -6
  24. data/lib/twitter_cldr/formatters/numbers/helpers/base.rb +1 -1
  25. data/lib/twitter_cldr/formatters/numbers/number_formatter.rb +6 -2
  26. data/lib/twitter_cldr/normalization/base.rb +7 -1
  27. data/lib/twitter_cldr/normalization/nfd.rb +2 -6
  28. data/lib/twitter_cldr/normalization/nfkc.rb +4 -10
  29. data/lib/twitter_cldr/normalization/nfkd.rb +12 -37
  30. data/lib/twitter_cldr/resources.rb +10 -3
  31. data/lib/twitter_cldr/resources/canonical_compositions_updater.rb +51 -0
  32. data/lib/twitter_cldr/resources/composition_exclusions_importer.rb +62 -0
  33. data/lib/twitter_cldr/resources/custom_locales_resources_importer.rb +80 -0
  34. data/lib/twitter_cldr/resources/download.rb +41 -0
  35. data/lib/twitter_cldr/resources/loader.rb +1 -1
  36. data/lib/twitter_cldr/resources/locales_resources_importer.rb +105 -0
  37. data/lib/twitter_cldr/resources/phone_codes_importer.rb +48 -0
  38. data/lib/twitter_cldr/resources/postal_codes_importer.rb +44 -0
  39. data/lib/twitter_cldr/resources/tailoring_importer.rb +18 -16
  40. data/lib/twitter_cldr/resources/unicode_data_importer.rb +90 -0
  41. data/lib/twitter_cldr/shared.rb +3 -1
  42. data/lib/twitter_cldr/shared/code_point.rb +47 -36
  43. data/lib/twitter_cldr/shared/currencies.rb +12 -15
  44. data/lib/twitter_cldr/shared/phone_codes.rb +30 -0
  45. data/lib/twitter_cldr/shared/postal_codes.rb +35 -0
  46. data/lib/twitter_cldr/tokenizers/calendars/timespan_tokenizer.rb +11 -3
  47. data/lib/twitter_cldr/tokenizers/numbers/number_tokenizer.rb +8 -1
  48. data/lib/twitter_cldr/utils/code_points.rb +2 -2
  49. data/lib/twitter_cldr/version.rb +1 -1
  50. data/resources/collation/tailoring/af.yml +3 -3
  51. data/resources/collation/tailoring/ar.yml +3 -3
  52. data/resources/collation/tailoring/ca.yml +3 -3
  53. data/resources/collation/tailoring/cs.yml +3 -3
  54. data/resources/collation/tailoring/da.yml +4 -4
  55. data/resources/collation/tailoring/de.yml +3 -3
  56. data/resources/collation/tailoring/el.yml +3 -3
  57. data/resources/collation/tailoring/en.yml +3 -3
  58. data/resources/collation/tailoring/es.yml +3 -3
  59. data/resources/collation/tailoring/eu.yml +3 -3
  60. data/resources/collation/tailoring/fa.yml +3 -3
  61. data/resources/collation/tailoring/fi.yml +3 -3
  62. data/resources/collation/tailoring/fil.yml +3 -3
  63. data/resources/collation/tailoring/fr.yml +3 -3
  64. data/resources/collation/tailoring/he.yml +3 -3
  65. data/resources/collation/tailoring/hi.yml +3 -3
  66. data/resources/collation/tailoring/hu.yml +3 -3
  67. data/resources/collation/tailoring/id.yml +3 -3
  68. data/resources/collation/tailoring/it.yml +3 -3
  69. data/resources/collation/tailoring/ja.yml +3 -3
  70. data/resources/collation/tailoring/ko.yml +3 -3
  71. data/resources/collation/tailoring/ms.yml +3 -3
  72. data/resources/collation/tailoring/nb.yml +3 -3
  73. data/resources/collation/tailoring/nl.yml +3 -3
  74. data/resources/collation/tailoring/pl.yml +3 -3
  75. data/resources/collation/tailoring/pt.yml +3 -3
  76. data/resources/collation/tailoring/ru.yml +3 -3
  77. data/resources/collation/tailoring/sv.yml +3 -3
  78. data/resources/collation/tailoring/th.yml +3 -3
  79. data/resources/collation/tailoring/tr.yml +3 -3
  80. data/resources/collation/tailoring/uk.yml +3 -3
  81. data/resources/collation/tailoring/ur.yml +3 -3
  82. data/resources/collation/tailoring/zh-Hant.yml +3 -3
  83. data/resources/collation/tailoring/zh.yml +3 -3
  84. data/resources/custom/locales/af/units.yml +19 -19
  85. data/resources/custom/locales/ar/units.yml +35 -35
  86. data/resources/custom/locales/ca/units.yml +19 -19
  87. data/resources/custom/locales/cs/units.yml +23 -23
  88. data/resources/custom/locales/da/units.yml +19 -19
  89. data/resources/custom/locales/de/units.yml +19 -19
  90. data/resources/custom/locales/el/units.yml +19 -19
  91. data/resources/custom/locales/en/units.yml +10 -10
  92. data/resources/custom/locales/es/units.yml +19 -19
  93. data/resources/custom/locales/eu/units.yml +19 -19
  94. data/resources/custom/locales/fa/units.yml +15 -15
  95. data/resources/custom/locales/fi/units.yml +19 -19
  96. data/resources/custom/locales/fil/units.yml +19 -19
  97. data/resources/custom/locales/fr/units.yml +19 -19
  98. data/resources/custom/locales/he/units.yml +19 -19
  99. data/resources/custom/locales/hi/units.yml +19 -19
  100. data/resources/custom/locales/hu/units.yml +15 -15
  101. data/resources/custom/locales/id/units.yml +15 -15
  102. data/resources/custom/locales/it/units.yml +19 -19
  103. data/resources/custom/locales/ja/units.yml +15 -15
  104. data/resources/custom/locales/ko/units.yml +15 -15
  105. data/resources/custom/locales/ms/units.yml +15 -15
  106. data/resources/custom/locales/nb/units.yml +19 -19
  107. data/resources/custom/locales/nl/units.yml +19 -19
  108. data/resources/custom/locales/pl/units.yml +27 -23
  109. data/resources/custom/locales/pt/units.yml +19 -19
  110. data/resources/custom/locales/ru/units.yml +27 -27
  111. data/resources/custom/locales/sv/units.yml +19 -19
  112. data/resources/custom/locales/th/units.yml +15 -15
  113. data/resources/custom/locales/tr/units.yml +15 -15
  114. data/resources/custom/locales/uk/units.yml +27 -27
  115. data/resources/custom/locales/ur/units.yml +19 -19
  116. data/resources/custom/locales/zh-Hant/units.yml +15 -15
  117. data/resources/custom/locales/zh/units.yml +15 -15
  118. data/resources/locales/af/calendars.yml +114 -113
  119. data/resources/locales/af/languages.yml +174 -173
  120. data/resources/locales/af/numbers.yml +43 -42
  121. data/resources/locales/af/plurals.yml +3 -2
  122. data/resources/locales/af/units.yml +136 -135
  123. data/resources/locales/ar/calendars.yml +121 -120
  124. data/resources/locales/ar/languages.yml +501 -500
  125. data/resources/locales/ar/numbers.yml +36 -35
  126. data/resources/locales/ar/plurals.yml +9 -1
  127. data/resources/locales/ar/units.yml +220 -219
  128. data/resources/locales/ca/calendars.yml +157 -156
  129. data/resources/locales/ca/languages.yml +511 -510
  130. data/resources/locales/ca/numbers.yml +44 -43
  131. data/resources/locales/ca/plurals.yml +3 -2
  132. data/resources/locales/ca/units.yml +136 -135
  133. data/resources/locales/cs/calendars.yml +153 -152
  134. data/resources/locales/cs/languages.yml +472 -471
  135. data/resources/locales/cs/numbers.yml +45 -44
  136. data/resources/locales/cs/plurals.yml +3 -2
  137. data/resources/locales/cs/units.yml +164 -163
  138. data/resources/locales/da/calendars.yml +117 -116
  139. data/resources/locales/da/languages.yml +515 -514
  140. data/resources/locales/da/numbers.yml +44 -43
  141. data/resources/locales/da/plurals.yml +3 -1
  142. data/resources/locales/da/units.yml +122 -121
  143. data/resources/locales/de/calendars.yml +136 -135
  144. data/resources/locales/de/languages.yml +514 -513
  145. data/resources/locales/de/numbers.yml +44 -43
  146. data/resources/locales/de/plurals.yml +3 -1
  147. data/resources/locales/de/units.yml +136 -135
  148. data/resources/locales/el/calendars.yml +138 -137
  149. data/resources/locales/el/languages.yml +520 -519
  150. data/resources/locales/el/numbers.yml +43 -42
  151. data/resources/locales/el/plurals.yml +3 -2
  152. data/resources/locales/el/units.yml +143 -142
  153. data/resources/locales/en/calendars.yml +117 -116
  154. data/resources/locales/en/languages.yml +559 -558
  155. data/resources/locales/en/numbers.yml +32 -31
  156. data/resources/locales/en/plurals.yml +3 -1
  157. data/resources/locales/en/units.yml +108 -107
  158. data/resources/locales/es/calendars.yml +118 -117
  159. data/resources/locales/es/languages.yml +511 -510
  160. data/resources/locales/es/numbers.yml +42 -41
  161. data/resources/locales/es/plurals.yml +3 -1
  162. data/resources/locales/es/units.yml +136 -135
  163. data/resources/locales/eu/calendars.yml +124 -123
  164. data/resources/locales/eu/languages.yml +162 -161
  165. data/resources/locales/eu/numbers.yml +44 -43
  166. data/resources/locales/eu/plurals.yml +3 -2
  167. data/resources/locales/eu/units.yml +129 -128
  168. data/resources/locales/fa/calendars.yml +137 -136
  169. data/resources/locales/fa/languages.yml +489 -488
  170. data/resources/locales/fa/numbers.yml +31 -30
  171. data/resources/locales/fa/plurals.yml +3 -1
  172. data/resources/locales/fa/units.yml +122 -121
  173. data/resources/locales/fi/calendars.yml +153 -152
  174. data/resources/locales/fi/languages.yml +520 -519
  175. data/resources/locales/fi/numbers.yml +44 -43
  176. data/resources/locales/fi/plurals.yml +3 -1
  177. data/resources/locales/fi/units.yml +136 -135
  178. data/resources/locales/fil/calendars.yml +123 -122
  179. data/resources/locales/fil/languages.yml +169 -168
  180. data/resources/locales/fil/numbers.yml +32 -31
  181. data/resources/locales/fil/plurals.yml +3 -1
  182. data/resources/locales/fil/units.yml +122 -121
  183. data/resources/locales/fr/calendars.yml +144 -143
  184. data/resources/locales/fr/languages.yml +512 -511
  185. data/resources/locales/fr/numbers.yml +44 -43
  186. data/resources/locales/fr/plurals.yml +3 -1
  187. data/resources/locales/fr/units.yml +136 -135
  188. data/resources/locales/he/calendars.yml +120 -119
  189. data/resources/locales/he/languages.yml +282 -281
  190. data/resources/locales/he/numbers.yml +32 -31
  191. data/resources/locales/he/plurals.yml +3 -1
  192. data/resources/locales/he/units.yml +122 -121
  193. data/resources/locales/hi/calendars.yml +112 -111
  194. data/resources/locales/hi/languages.yml +511 -510
  195. data/resources/locales/hi/numbers.yml +32 -31
  196. data/resources/locales/hi/plurals.yml +3 -1
  197. data/resources/locales/hi/units.yml +122 -121
  198. data/resources/locales/hu/calendars.yml +142 -141
  199. data/resources/locales/hu/languages.yml +520 -519
  200. data/resources/locales/hu/numbers.yml +43 -42
  201. data/resources/locales/hu/plurals.yml +3 -1
  202. data/resources/locales/hu/units.yml +108 -107
  203. data/resources/locales/id/calendars.yml +117 -116
  204. data/resources/locales/id/languages.yml +514 -513
  205. data/resources/locales/id/numbers.yml +43 -42
  206. data/resources/locales/id/plurals.yml +3 -1
  207. data/resources/locales/id/units.yml +108 -107
  208. data/resources/locales/it/calendars.yml +123 -122
  209. data/resources/locales/it/languages.yml +504 -503
  210. data/resources/locales/it/numbers.yml +44 -43
  211. data/resources/locales/it/plurals.yml +3 -1
  212. data/resources/locales/it/units.yml +122 -121
  213. data/resources/locales/ja/calendars.yml +109 -108
  214. data/resources/locales/ja/languages.yml +516 -515
  215. data/resources/locales/ja/numbers.yml +35 -34
  216. data/resources/locales/ja/plurals.yml +3 -1
  217. data/resources/locales/ja/units.yml +108 -107
  218. data/resources/locales/ko/calendars.yml +112 -111
  219. data/resources/locales/ko/languages.yml +509 -508
  220. data/resources/locales/ko/numbers.yml +32 -31
  221. data/resources/locales/ko/plurals.yml +3 -1
  222. data/resources/locales/ko/units.yml +108 -107
  223. data/resources/locales/ms/calendars.yml +134 -133
  224. data/resources/locales/ms/languages.yml +158 -157
  225. data/resources/locales/ms/numbers.yml +31 -30
  226. data/resources/locales/ms/plurals.yml +3 -1
  227. data/resources/locales/ms/units.yml +136 -135
  228. data/resources/locales/nb/calendars.yml +143 -142
  229. data/resources/locales/nb/languages.yml +530 -529
  230. data/resources/locales/nb/numbers.yml +44 -43
  231. data/resources/locales/nb/plurals.yml +3 -2
  232. data/resources/locales/nb/units.yml +130 -129
  233. data/resources/locales/nl/calendars.yml +124 -123
  234. data/resources/locales/nl/languages.yml +516 -515
  235. data/resources/locales/nl/numbers.yml +44 -43
  236. data/resources/locales/nl/plurals.yml +3 -1
  237. data/resources/locales/nl/units.yml +122 -121
  238. data/resources/locales/pl/calendars.yml +148 -147
  239. data/resources/locales/pl/languages.yml +505 -504
  240. data/resources/locales/pl/numbers.yml +46 -45
  241. data/resources/locales/pl/plurals.yml +5 -1
  242. data/resources/locales/pl/units.yml +205 -204
  243. data/resources/locales/pt/calendars.yml +131 -130
  244. data/resources/locales/pt/languages.yml +517 -516
  245. data/resources/locales/pt/numbers.yml +44 -43
  246. data/resources/locales/pt/plurals.yml +3 -1
  247. data/resources/locales/pt/units.yml +136 -135
  248. data/resources/locales/ru/calendars.yml +143 -142
  249. data/resources/locales/ru/languages.yml +511 -510
  250. data/resources/locales/ru/numbers.yml +43 -42
  251. data/resources/locales/ru/plurals.yml +5 -1
  252. data/resources/locales/ru/units.yml +192 -191
  253. data/resources/locales/sv/calendars.yml +151 -150
  254. data/resources/locales/sv/languages.yml +531 -530
  255. data/resources/locales/sv/numbers.yml +44 -43
  256. data/resources/locales/sv/plurals.yml +3 -1
  257. data/resources/locales/sv/units.yml +136 -135
  258. data/resources/locales/th/calendars.yml +125 -124
  259. data/resources/locales/th/languages.yml +510 -509
  260. data/resources/locales/th/numbers.yml +41 -40
  261. data/resources/locales/th/plurals.yml +3 -1
  262. data/resources/locales/th/units.yml +108 -107
  263. data/resources/locales/tr/calendars.yml +139 -138
  264. data/resources/locales/tr/languages.yml +511 -510
  265. data/resources/locales/tr/numbers.yml +43 -42
  266. data/resources/locales/tr/plurals.yml +3 -1
  267. data/resources/locales/tr/units.yml +108 -107
  268. data/resources/locales/uk/calendars.yml +131 -130
  269. data/resources/locales/uk/languages.yml +520 -519
  270. data/resources/locales/uk/numbers.yml +46 -45
  271. data/resources/locales/uk/plurals.yml +5 -2
  272. data/resources/locales/uk/units.yml +192 -191
  273. data/resources/locales/ur/calendars.yml +111 -110
  274. data/resources/locales/ur/languages.yml +164 -163
  275. data/resources/locales/ur/numbers.yml +32 -31
  276. data/resources/locales/ur/plurals.yml +3 -1
  277. data/resources/locales/ur/units.yml +136 -135
  278. data/resources/locales/zh-Hant/calendars.yml +116 -115
  279. data/resources/locales/zh-Hant/languages.yml +510 -509
  280. data/resources/locales/zh-Hant/numbers.yml +35 -34
  281. data/resources/locales/zh-Hant/plurals.yml +3 -2
  282. data/resources/locales/zh-Hant/units.yml +108 -107
  283. data/resources/locales/zh/calendars.yml +138 -137
  284. data/resources/locales/zh/languages.yml +506 -505
  285. data/resources/locales/zh/numbers.yml +35 -34
  286. data/resources/locales/zh/plurals.yml +3 -1
  287. data/resources/locales/zh/units.yml +80 -79
  288. data/resources/shared/currencies.yml +448 -451
  289. data/resources/shared/phone_codes.yml +241 -0
  290. data/resources/shared/postal_codes.yml +160 -0
  291. data/resources/unicode_data/blocks.yml +221 -221
  292. data/resources/unicode_data/blocks/aegean_numbers.yml +913 -0
  293. data/resources/unicode_data/blocks/alchemical_symbols.yml +1857 -0
  294. data/resources/unicode_data/blocks/alphabetic_presentation_forms.yml +929 -0
  295. data/resources/unicode_data/blocks/ancient_greek_musical_notation.yml +1121 -0
  296. data/resources/unicode_data/blocks/ancient_greek_numbers.yml +1201 -0
  297. data/resources/unicode_data/blocks/ancient_symbols.yml +193 -0
  298. data/resources/unicode_data/blocks/arabic.yml +4049 -0
  299. data/resources/unicode_data/blocks/arabic_extended_a.yml +625 -0
  300. data/resources/unicode_data/blocks/arabic_mathematical_alphabetic_symbols.yml +2289 -0
  301. data/resources/unicode_data/{arabic_presentation_forms_a.yml → blocks/arabic_presentation_forms_a.yml} +7369 -7368
  302. data/resources/unicode_data/{arabic_presentation_forms_b.yml → blocks/arabic_presentation_forms_b.yml} +1414 -1414
  303. data/resources/unicode_data/blocks/arabic_supplement.yml +769 -0
  304. data/resources/unicode_data/blocks/armenian.yml +1393 -0
  305. data/resources/unicode_data/blocks/arrows.yml +1793 -0
  306. data/resources/unicode_data/blocks/avestan.yml +977 -0
  307. data/resources/unicode_data/blocks/balinese.yml +1937 -0
  308. data/resources/unicode_data/blocks/bamum.yml +1409 -0
  309. data/resources/unicode_data/blocks/bamum_supplement.yml +9105 -0
  310. data/resources/unicode_data/blocks/basic_latin.yml +2049 -0
  311. data/resources/unicode_data/blocks/batak.yml +897 -0
  312. data/resources/unicode_data/blocks/bengali.yml +1473 -0
  313. data/resources/unicode_data/blocks/block_elements.yml +513 -0
  314. data/resources/unicode_data/blocks/bopomofo.yml +657 -0
  315. data/resources/unicode_data/blocks/bopomofo_extended.yml +433 -0
  316. data/resources/unicode_data/{box_drawing.yml → blocks/box_drawing.yml} +1537 -1537
  317. data/resources/unicode_data/blocks/brahmi.yml +1729 -0
  318. data/resources/unicode_data/blocks/braille_patterns.yml +4097 -0
  319. data/resources/unicode_data/blocks/buginese.yml +481 -0
  320. data/resources/unicode_data/blocks/buhid.yml +321 -0
  321. data/resources/unicode_data/blocks/byzantine_musical_symbols.yml +3937 -0
  322. data/resources/unicode_data/blocks/carian.yml +785 -0
  323. data/resources/unicode_data/blocks/chakma.yml +1073 -0
  324. data/resources/unicode_data/blocks/cham.yml +1329 -0
  325. data/resources/unicode_data/blocks/cherokee.yml +1361 -0
  326. data/resources/unicode_data/{cjk_compatibility.yml → blocks/cjk_compatibility.yml} +2706 -2706
  327. data/resources/unicode_data/{cjk_compatibility_forms.yml → blocks/cjk_compatibility_forms.yml} +363 -363
  328. data/resources/unicode_data/blocks/cjk_compatibility_ideographs.yml +7553 -0
  329. data/resources/unicode_data/blocks/cjk_compatibility_ideographs_supplement.yml +8673 -0
  330. data/resources/unicode_data/blocks/cjk_radicals_supplement.yml +1841 -0
  331. data/resources/unicode_data/blocks/cjk_strokes.yml +577 -0
  332. data/resources/unicode_data/blocks/cjk_symbols_and_punctuation.yml +1025 -0
  333. data/resources/unicode_data/blocks/cjk_unified_ideographs.yml +33 -0
  334. data/resources/unicode_data/blocks/cjk_unified_ideographs_extension_a.yml +33 -0
  335. data/resources/unicode_data/blocks/cjk_unified_ideographs_extension_b.yml +33 -0
  336. data/resources/unicode_data/blocks/cjk_unified_ideographs_extension_c.yml +33 -0
  337. data/resources/unicode_data/blocks/cjk_unified_ideographs_extension_d.yml +33 -0
  338. data/resources/unicode_data/blocks/combining_diacritical_marks.yml +1793 -0
  339. data/resources/unicode_data/{combining_diacritical_marks_for_symbols.yml → blocks/combining_diacritical_marks_for_symbols.yml} +409 -409
  340. data/resources/unicode_data/blocks/combining_diacritical_marks_supplement.yml +689 -0
  341. data/resources/unicode_data/blocks/combining_half_marks.yml +113 -0
  342. data/resources/unicode_data/blocks/common_indic_number_forms.yml +161 -0
  343. data/resources/unicode_data/blocks/control_pictures.yml +625 -0
  344. data/resources/unicode_data/blocks/coptic.yml +1969 -0
  345. data/resources/unicode_data/blocks/counting_rod_numerals.yml +289 -0
  346. data/resources/unicode_data/blocks/cuneiform.yml +14065 -0
  347. data/resources/unicode_data/blocks/cuneiform_numbers_and_punctuation.yml +1649 -0
  348. data/resources/unicode_data/blocks/currency_symbols.yml +417 -0
  349. data/resources/unicode_data/blocks/cypriot_syllabary.yml +881 -0
  350. data/resources/unicode_data/{cyrillic.yml → blocks/cyrillic.yml} +2765 -2765
  351. data/resources/unicode_data/blocks/cyrillic_extended_a.yml +513 -0
  352. data/resources/unicode_data/blocks/cyrillic_extended_b.yml +1425 -0
  353. data/resources/unicode_data/blocks/cyrillic_supplement.yml +641 -0
  354. data/resources/unicode_data/blocks/deseret.yml +1281 -0
  355. data/resources/unicode_data/blocks/devanagari.yml +2033 -0
  356. data/resources/unicode_data/blocks/devanagari_extended.yml +449 -0
  357. data/resources/unicode_data/blocks/dingbats.yml +3057 -0
  358. data/resources/unicode_data/blocks/domino_tiles.yml +1601 -0
  359. data/resources/unicode_data/blocks/egyptian_hieroglyphs.yml +17137 -0
  360. data/resources/unicode_data/blocks/emoticons.yml +1217 -0
  361. data/resources/unicode_data/blocks/enclosed_alphanumeric_supplement.yml +2737 -0
  362. data/resources/unicode_data/blocks/enclosed_alphanumerics.yml +2561 -0
  363. data/resources/unicode_data/{enclosed_cjk_letters_and_months.yml → blocks/enclosed_cjk_letters_and_months.yml} +3067 -3067
  364. data/resources/unicode_data/{enclosed_ideographic_supplement.yml → blocks/enclosed_ideographic_supplement.yml} +685 -685
  365. data/resources/unicode_data/blocks/ethiopic.yml +5729 -0
  366. data/resources/unicode_data/blocks/ethiopic_extended.yml +1265 -0
  367. data/resources/unicode_data/blocks/ethiopic_extended_a.yml +513 -0
  368. data/resources/unicode_data/blocks/ethiopic_supplement.yml +417 -0
  369. data/resources/unicode_data/blocks/general_punctuation.yml +1713 -0
  370. data/resources/unicode_data/blocks/geometric_shapes.yml +1537 -0
  371. data/resources/unicode_data/blocks/georgian.yml +1409 -0
  372. data/resources/unicode_data/blocks/georgian_supplement.yml +641 -0
  373. data/resources/unicode_data/blocks/glagolitic.yml +1505 -0
  374. data/resources/unicode_data/blocks/gothic.yml +433 -0
  375. data/resources/unicode_data/{greek_and_coptic.yml → blocks/greek_and_coptic.yml} +1360 -1360
  376. data/resources/unicode_data/{greek_extended.yml → blocks/greek_extended.yml} +2330 -2330
  377. data/resources/unicode_data/blocks/gujarati.yml +1345 -0
  378. data/resources/unicode_data/blocks/gurmukhi.yml +1265 -0
  379. data/resources/unicode_data/{halfwidth_and_fullwidth_forms.yml → blocks/halfwidth_and_fullwidth_forms.yml} +2517 -2517
  380. data/resources/unicode_data/{hangul_compatibility_jamo.yml → blocks/hangul_compatibility_jamo.yml} +993 -993
  381. data/resources/unicode_data/blocks/hangul_jamo.yml +4097 -0
  382. data/resources/unicode_data/blocks/hangul_jamo_extended_a.yml +465 -0
  383. data/resources/unicode_data/blocks/hangul_jamo_extended_b.yml +1153 -0
  384. data/resources/unicode_data/blocks/hangul_syllables.yml +33 -0
  385. data/resources/unicode_data/blocks/hanunoo.yml +369 -0
  386. data/resources/unicode_data/blocks/hebrew.yml +1393 -0
  387. data/resources/unicode_data/blocks/high_private_use_surrogates.yml +33 -0
  388. data/resources/unicode_data/blocks/high_surrogates.yml +33 -0
  389. data/resources/unicode_data/blocks/hiragana.yml +1489 -0
  390. data/resources/unicode_data/blocks/ideographic_description_characters.yml +193 -0
  391. data/resources/unicode_data/blocks/imperial_aramaic.yml +497 -0
  392. data/resources/unicode_data/blocks/inscriptional_pahlavi.yml +433 -0
  393. data/resources/unicode_data/blocks/inscriptional_parthian.yml +481 -0
  394. data/resources/unicode_data/{ipa_extensions.yml → blocks/ipa_extensions.yml} +1050 -1050
  395. data/resources/unicode_data/blocks/javanese.yml +1457 -0
  396. data/resources/unicode_data/blocks/kaithi.yml +1057 -0
  397. data/resources/unicode_data/blocks/kana_supplement.yml +33 -0
  398. data/resources/unicode_data/{kanbun.yml → blocks/kanbun.yml} +167 -167
  399. data/resources/unicode_data/blocks/kangxi_radicals.yml +3425 -0
  400. data/resources/unicode_data/blocks/kannada.yml +1377 -0
  401. data/resources/unicode_data/blocks/katakana.yml +1537 -0
  402. data/resources/unicode_data/blocks/katakana_phonetic_extensions.yml +257 -0
  403. data/resources/unicode_data/blocks/kayah_li.yml +769 -0
  404. data/resources/unicode_data/blocks/kharoshthi.yml +1041 -0
  405. data/resources/unicode_data/blocks/khmer.yml +1825 -0
  406. data/resources/unicode_data/blocks/khmer_symbols.yml +513 -0
  407. data/resources/unicode_data/blocks/lao.yml +1073 -0
  408. data/resources/unicode_data/{latin_1_supplement.yml → blocks/latin_1_supplement.yml} +1319 -1319
  409. data/resources/unicode_data/{latin_extended_a.yml → blocks/latin_extended_a.yml} +1210 -1210
  410. data/resources/unicode_data/{latin_extended_additional.yml → blocks/latin_extended_additional.yml} +2460 -2460
  411. data/resources/unicode_data/{latin_extended_b.yml → blocks/latin_extended_b.yml} +2096 -2096
  412. data/resources/unicode_data/blocks/latin_extended_c.yml +513 -0
  413. data/resources/unicode_data/blocks/latin_extended_d.yml +2145 -0
  414. data/resources/unicode_data/blocks/lepcha.yml +1185 -0
  415. data/resources/unicode_data/blocks/letterlike_symbols.yml +1281 -0
  416. data/resources/unicode_data/blocks/limbu.yml +1057 -0
  417. data/resources/unicode_data/blocks/linear_b_ideograms.yml +1969 -0
  418. data/resources/unicode_data/blocks/linear_b_syllabary.yml +1409 -0
  419. data/resources/unicode_data/blocks/lisu.yml +769 -0
  420. data/resources/unicode_data/blocks/low_surrogates.yml +33 -0
  421. data/resources/unicode_data/blocks/lycian.yml +465 -0
  422. data/resources/unicode_data/blocks/lydian.yml +433 -0
  423. data/resources/unicode_data/blocks/mahjong_tiles.yml +705 -0
  424. data/resources/unicode_data/blocks/malayalam.yml +1569 -0
  425. data/resources/unicode_data/blocks/mandaic.yml +465 -0
  426. data/resources/unicode_data/{mathematical_alphanumeric_symbols.yml → blocks/mathematical_alphanumeric_symbols.yml} +11953 -11953
  427. data/resources/unicode_data/blocks/mathematical_operators.yml +4097 -0
  428. data/resources/unicode_data/blocks/meetei_mayek.yml +897 -0
  429. data/resources/unicode_data/blocks/meetei_mayek_extensions.yml +369 -0
  430. data/resources/unicode_data/blocks/meroitic_cursive.yml +417 -0
  431. data/resources/unicode_data/blocks/meroitic_hieroglyphs.yml +513 -0
  432. data/resources/unicode_data/blocks/miao.yml +2129 -0
  433. data/resources/unicode_data/blocks/miscellaneous_mathematical_symbols_a.yml +769 -0
  434. data/resources/unicode_data/blocks/miscellaneous_mathematical_symbols_b.yml +2049 -0
  435. data/resources/unicode_data/blocks/miscellaneous_symbols.yml +4097 -0
  436. data/resources/unicode_data/blocks/miscellaneous_symbols_and_arrows.yml +1393 -0
  437. data/resources/unicode_data/blocks/miscellaneous_symbols_and_pictographs.yml +8529 -0
  438. data/resources/unicode_data/blocks/miscellaneous_technical.yml +3905 -0
  439. data/resources/unicode_data/blocks/modifier_tone_letters.yml +513 -0
  440. data/resources/unicode_data/blocks/mongolian.yml +2497 -0
  441. data/resources/unicode_data/blocks/musical_symbols.yml +3521 -0
  442. data/resources/unicode_data/blocks/myanmar.yml +2561 -0
  443. data/resources/unicode_data/blocks/myanmar_extended_a.yml +449 -0
  444. data/resources/unicode_data/blocks/new_tai_lue.yml +1329 -0
  445. data/resources/unicode_data/blocks/nko.yml +945 -0
  446. data/resources/unicode_data/blocks/number_forms.yml +929 -0
  447. data/resources/unicode_data/blocks/ogham.yml +465 -0
  448. data/resources/unicode_data/blocks/ol_chiki.yml +769 -0
  449. data/resources/unicode_data/blocks/old_italic.yml +561 -0
  450. data/resources/unicode_data/blocks/old_persian.yml +801 -0
  451. data/resources/unicode_data/blocks/old_south_arabian.yml +513 -0
  452. data/resources/unicode_data/blocks/old_turkic.yml +1169 -0
  453. data/resources/unicode_data/blocks/optical_character_recognition.yml +177 -0
  454. data/resources/unicode_data/blocks/oriya.yml +1441 -0
  455. data/resources/unicode_data/blocks/osmanya.yml +641 -0
  456. data/resources/unicode_data/blocks/phags_pa.yml +897 -0
  457. data/resources/unicode_data/blocks/phaistos_disc.yml +737 -0
  458. data/resources/unicode_data/blocks/phoenician.yml +465 -0
  459. data/resources/unicode_data/blocks/phonetic_extensions.yml +2049 -0
  460. data/resources/unicode_data/blocks/phonetic_extensions_supplement.yml +1025 -0
  461. data/resources/unicode_data/blocks/playing_cards.yml +945 -0
  462. data/resources/unicode_data/blocks/private_use_area.yml +33 -0
  463. data/resources/unicode_data/blocks/rejang.yml +593 -0
  464. data/resources/unicode_data/blocks/rumi_numeral_symbols.yml +497 -0
  465. data/resources/unicode_data/blocks/runic.yml +1297 -0
  466. data/resources/unicode_data/blocks/samaritan.yml +977 -0
  467. data/resources/unicode_data/blocks/saurashtra.yml +1297 -0
  468. data/resources/unicode_data/blocks/sharada.yml +1329 -0
  469. data/resources/unicode_data/blocks/shavian.yml +769 -0
  470. data/resources/unicode_data/blocks/sinhala.yml +1281 -0
  471. data/resources/unicode_data/blocks/small_form_variants.yml +417 -0
  472. data/resources/unicode_data/blocks/sora_sompeng.yml +561 -0
  473. data/resources/unicode_data/blocks/spacing_modifier_letters.yml +1281 -0
  474. data/resources/unicode_data/blocks/specials.yml +81 -0
  475. data/resources/unicode_data/blocks/sundanese.yml +1025 -0
  476. data/resources/unicode_data/blocks/sundanese_supplement.yml +129 -0
  477. data/resources/unicode_data/blocks/superscripts_and_subscripts.yml +673 -0
  478. data/resources/unicode_data/blocks/supplemental_arrows_a.yml +257 -0
  479. data/resources/unicode_data/blocks/supplemental_arrows_b.yml +2049 -0
  480. data/resources/unicode_data/blocks/supplemental_mathematical_operators.yml +4097 -0
  481. data/resources/unicode_data/blocks/supplemental_punctuation.yml +961 -0
  482. data/resources/unicode_data/blocks/supplementary_private_use_area_a.yml +33 -0
  483. data/resources/unicode_data/blocks/supplementary_private_use_area_b.yml +33 -0
  484. data/resources/unicode_data/blocks/syloti_nagri.yml +705 -0
  485. data/resources/unicode_data/blocks/syriac.yml +1233 -0
  486. data/resources/unicode_data/blocks/tagalog.yml +321 -0
  487. data/resources/unicode_data/blocks/tagbanwa.yml +289 -0
  488. data/resources/unicode_data/blocks/tags.yml +1553 -0
  489. data/resources/unicode_data/blocks/tai_le.yml +561 -0
  490. data/resources/unicode_data/blocks/tai_tham.yml +2033 -0
  491. data/resources/unicode_data/blocks/tai_viet.yml +1153 -0
  492. data/resources/unicode_data/blocks/tai_xuan_jing_symbols.yml +1393 -0
  493. data/resources/unicode_data/blocks/takri.yml +1057 -0
  494. data/resources/unicode_data/blocks/tamil.yml +1153 -0
  495. data/resources/unicode_data/blocks/telugu.yml +1489 -0
  496. data/resources/unicode_data/blocks/thaana.yml +801 -0
  497. data/resources/unicode_data/blocks/thai.yml +1393 -0
  498. data/resources/unicode_data/blocks/tibetan.yml +3377 -0
  499. data/resources/unicode_data/blocks/tifinagh.yml +945 -0
  500. data/resources/unicode_data/blocks/transport_and_map_symbols.yml +1121 -0
  501. data/resources/unicode_data/blocks/ugaritic.yml +497 -0
  502. data/resources/unicode_data/blocks/unified_canadian_aboriginal_syllabics.yml +10241 -0
  503. data/resources/unicode_data/blocks/unified_canadian_aboriginal_syllabics_extended.yml +1121 -0
  504. data/resources/unicode_data/blocks/vai.yml +4801 -0
  505. data/resources/unicode_data/blocks/variation_selectors.yml +257 -0
  506. data/resources/unicode_data/blocks/variation_selectors_supplement.yml +3841 -0
  507. data/resources/unicode_data/blocks/vedic_extensions.yml +625 -0
  508. data/resources/unicode_data/{vertical_forms.yml → blocks/vertical_forms.yml} +121 -121
  509. data/resources/unicode_data/blocks/yi_radicals.yml +881 -0
  510. data/resources/unicode_data/blocks/yi_syllables.yml +18641 -0
  511. data/resources/unicode_data/blocks/yijing_hexagram_symbols.yml +1025 -0
  512. data/resources/unicode_data/canonical_compositions.yml +4925 -0
  513. data/resources/unicode_data/composition_exclusions.yml +78 -74
  514. data/resources/unicode_data/hangul_blocks.yml +9 -9
  515. data/spec/collation/collation_spec.rb +6 -6
  516. data/spec/collation/collator_spec.rb +18 -19
  517. data/spec/collation/trie_builder_spec.rb +6 -9
  518. data/spec/core_ext/array_spec.rb +1 -1
  519. data/spec/core_ext/string_spec.rb +1 -1
  520. data/spec/formatters/numbers/currency_formatter_spec.rb +5 -0
  521. data/spec/formatters/numbers/decimal_formatter_spec.rb +4 -0
  522. data/spec/formatters/numbers/number_formatter_spec.rb +4 -4
  523. data/spec/formatters/numbers/percent_formatter_spec.rb +8 -0
  524. data/spec/normalization/base_spec.rb +2 -2
  525. data/spec/normalization/normalization_spec.rb +7 -3
  526. data/spec/readme_spec.rb +9 -9
  527. data/spec/resources/loader_spec.rb +4 -4
  528. data/spec/shared/code_point_spec.rb +102 -62
  529. data/spec/shared/currencies_spec.rb +17 -19
  530. data/spec/shared/phone_codes_spec.rb +49 -0
  531. data/spec/shared/postal_codes_spec.rb +68 -0
  532. data/spec/utils/code_points_spec.rb +6 -6
  533. metadata +264 -224
  534. data/resources/unicode_data/aegean_numbers.yml +0 -913
  535. data/resources/unicode_data/alchemical_symbols.yml +0 -1857
  536. data/resources/unicode_data/alphabetic_presentation_forms.yml +0 -929
  537. data/resources/unicode_data/ancient_greek_musical_notation.yml +0 -1121
  538. data/resources/unicode_data/ancient_greek_numbers.yml +0 -1201
  539. data/resources/unicode_data/ancient_symbols.yml +0 -193
  540. data/resources/unicode_data/arabic.yml +0 -4049
  541. data/resources/unicode_data/arabic_extended_a.yml +0 -625
  542. data/resources/unicode_data/arabic_mathematical_alphabetic_symbols.yml +0 -2289
  543. data/resources/unicode_data/arabic_supplement.yml +0 -769
  544. data/resources/unicode_data/armenian.yml +0 -1393
  545. data/resources/unicode_data/arrows.yml +0 -1793
  546. data/resources/unicode_data/avestan.yml +0 -977
  547. data/resources/unicode_data/balinese.yml +0 -1937
  548. data/resources/unicode_data/bamum.yml +0 -1409
  549. data/resources/unicode_data/bamum_supplement.yml +0 -9105
  550. data/resources/unicode_data/basic_latin.yml +0 -2049
  551. data/resources/unicode_data/batak.yml +0 -897
  552. data/resources/unicode_data/bengali.yml +0 -1473
  553. data/resources/unicode_data/block_elements.yml +0 -513
  554. data/resources/unicode_data/bopomofo.yml +0 -657
  555. data/resources/unicode_data/bopomofo_extended.yml +0 -433
  556. data/resources/unicode_data/brahmi.yml +0 -1729
  557. data/resources/unicode_data/braille_patterns.yml +0 -4097
  558. data/resources/unicode_data/buginese.yml +0 -481
  559. data/resources/unicode_data/buhid.yml +0 -321
  560. data/resources/unicode_data/byzantine_musical_symbols.yml +0 -3937
  561. data/resources/unicode_data/carian.yml +0 -785
  562. data/resources/unicode_data/chakma.yml +0 -1073
  563. data/resources/unicode_data/cham.yml +0 -1329
  564. data/resources/unicode_data/cherokee.yml +0 -1361
  565. data/resources/unicode_data/cjk_compatibility_ideographs.yml +0 -7553
  566. data/resources/unicode_data/cjk_compatibility_ideographs_supplement.yml +0 -8673
  567. data/resources/unicode_data/cjk_radicals_supplement.yml +0 -1841
  568. data/resources/unicode_data/cjk_strokes.yml +0 -577
  569. data/resources/unicode_data/cjk_symbols_and_punctuation.yml +0 -1025
  570. data/resources/unicode_data/cjk_unified_ideographs.yml +0 -33
  571. data/resources/unicode_data/cjk_unified_ideographs_extension_a.yml +0 -33
  572. data/resources/unicode_data/cjk_unified_ideographs_extension_b.yml +0 -33
  573. data/resources/unicode_data/cjk_unified_ideographs_extension_c.yml +0 -33
  574. data/resources/unicode_data/cjk_unified_ideographs_extension_d.yml +0 -33
  575. data/resources/unicode_data/combining_diacritical_marks.yml +0 -1793
  576. data/resources/unicode_data/combining_diacritical_marks_supplement.yml +0 -689
  577. data/resources/unicode_data/combining_half_marks.yml +0 -113
  578. data/resources/unicode_data/common_indic_number_forms.yml +0 -161
  579. data/resources/unicode_data/control_pictures.yml +0 -625
  580. data/resources/unicode_data/coptic.yml +0 -1969
  581. data/resources/unicode_data/counting_rod_numerals.yml +0 -289
  582. data/resources/unicode_data/cuneiform.yml +0 -14065
  583. data/resources/unicode_data/cuneiform_numbers_and_punctuation.yml +0 -1649
  584. data/resources/unicode_data/currency_symbols.yml +0 -417
  585. data/resources/unicode_data/cypriot_syllabary.yml +0 -881
  586. data/resources/unicode_data/cyrillic_extended_a.yml +0 -513
  587. data/resources/unicode_data/cyrillic_extended_b.yml +0 -1425
  588. data/resources/unicode_data/cyrillic_supplement.yml +0 -641
  589. data/resources/unicode_data/decomposition_map.yml +0 -4565
  590. data/resources/unicode_data/deseret.yml +0 -1281
  591. data/resources/unicode_data/devanagari.yml +0 -2033
  592. data/resources/unicode_data/devanagari_extended.yml +0 -449
  593. data/resources/unicode_data/dingbats.yml +0 -3057
  594. data/resources/unicode_data/domino_tiles.yml +0 -1601
  595. data/resources/unicode_data/egyptian_hieroglyphs.yml +0 -17137
  596. data/resources/unicode_data/emoticons.yml +0 -1217
  597. data/resources/unicode_data/enclosed_alphanumeric_supplement.yml +0 -2737
  598. data/resources/unicode_data/enclosed_alphanumerics.yml +0 -2561
  599. data/resources/unicode_data/ethiopic.yml +0 -5729
  600. data/resources/unicode_data/ethiopic_extended.yml +0 -1265
  601. data/resources/unicode_data/ethiopic_extended_a.yml +0 -513
  602. data/resources/unicode_data/ethiopic_supplement.yml +0 -417
  603. data/resources/unicode_data/general_punctuation.yml +0 -1713
  604. data/resources/unicode_data/geometric_shapes.yml +0 -1537
  605. data/resources/unicode_data/georgian.yml +0 -1409
  606. data/resources/unicode_data/georgian_supplement.yml +0 -641
  607. data/resources/unicode_data/glagolitic.yml +0 -1505
  608. data/resources/unicode_data/gothic.yml +0 -433
  609. data/resources/unicode_data/gujarati.yml +0 -1345
  610. data/resources/unicode_data/gurmukhi.yml +0 -1265
  611. data/resources/unicode_data/hangul_jamo.yml +0 -4097
  612. data/resources/unicode_data/hangul_jamo_extended_a.yml +0 -465
  613. data/resources/unicode_data/hangul_jamo_extended_b.yml +0 -1153
  614. data/resources/unicode_data/hangul_syllables.yml +0 -33
  615. data/resources/unicode_data/hanunoo.yml +0 -369
  616. data/resources/unicode_data/hebrew.yml +0 -1393
  617. data/resources/unicode_data/high_private_use_surrogates.yml +0 -33
  618. data/resources/unicode_data/high_surrogates.yml +0 -33
  619. data/resources/unicode_data/hiragana.yml +0 -1489
  620. data/resources/unicode_data/ideographic_description_characters.yml +0 -193
  621. data/resources/unicode_data/imperial_aramaic.yml +0 -497
  622. data/resources/unicode_data/inscriptional_pahlavi.yml +0 -433
  623. data/resources/unicode_data/inscriptional_parthian.yml +0 -481
  624. data/resources/unicode_data/javanese.yml +0 -1457
  625. data/resources/unicode_data/kaithi.yml +0 -1057
  626. data/resources/unicode_data/kana_supplement.yml +0 -33
  627. data/resources/unicode_data/kangxi_radicals.yml +0 -3425
  628. data/resources/unicode_data/kannada.yml +0 -1377
  629. data/resources/unicode_data/katakana.yml +0 -1537
  630. data/resources/unicode_data/katakana_phonetic_extensions.yml +0 -257
  631. data/resources/unicode_data/kayah_li.yml +0 -769
  632. data/resources/unicode_data/kharoshthi.yml +0 -1041
  633. data/resources/unicode_data/khmer.yml +0 -1825
  634. data/resources/unicode_data/khmer_symbols.yml +0 -513
  635. data/resources/unicode_data/lao.yml +0 -1073
  636. data/resources/unicode_data/latin_extended_c.yml +0 -513
  637. data/resources/unicode_data/latin_extended_d.yml +0 -2145
  638. data/resources/unicode_data/lepcha.yml +0 -1185
  639. data/resources/unicode_data/letterlike_symbols.yml +0 -1281
  640. data/resources/unicode_data/limbu.yml +0 -1057
  641. data/resources/unicode_data/linear_b_ideograms.yml +0 -1969
  642. data/resources/unicode_data/linear_b_syllabary.yml +0 -1409
  643. data/resources/unicode_data/lisu.yml +0 -769
  644. data/resources/unicode_data/low_surrogates.yml +0 -33
  645. data/resources/unicode_data/lycian.yml +0 -465
  646. data/resources/unicode_data/lydian.yml +0 -433
  647. data/resources/unicode_data/mahjong_tiles.yml +0 -705
  648. data/resources/unicode_data/malayalam.yml +0 -1569
  649. data/resources/unicode_data/mandaic.yml +0 -465
  650. data/resources/unicode_data/mathematical_operators.yml +0 -4097
  651. data/resources/unicode_data/meetei_mayek.yml +0 -897
  652. data/resources/unicode_data/meetei_mayek_extensions.yml +0 -369
  653. data/resources/unicode_data/meroitic_cursive.yml +0 -417
  654. data/resources/unicode_data/meroitic_hieroglyphs.yml +0 -513
  655. data/resources/unicode_data/miao.yml +0 -2129
  656. data/resources/unicode_data/miscellaneous_mathematical_symbols_a.yml +0 -769
  657. data/resources/unicode_data/miscellaneous_mathematical_symbols_b.yml +0 -2049
  658. data/resources/unicode_data/miscellaneous_symbols.yml +0 -4097
  659. data/resources/unicode_data/miscellaneous_symbols_and_arrows.yml +0 -1393
  660. data/resources/unicode_data/miscellaneous_symbols_and_pictographs.yml +0 -8529
  661. data/resources/unicode_data/miscellaneous_technical.yml +0 -3905
  662. data/resources/unicode_data/modifier_tone_letters.yml +0 -513
  663. data/resources/unicode_data/mongolian.yml +0 -2497
  664. data/resources/unicode_data/musical_symbols.yml +0 -3521
  665. data/resources/unicode_data/myanmar.yml +0 -2561
  666. data/resources/unicode_data/myanmar_extended_a.yml +0 -449
  667. data/resources/unicode_data/new_tai_lue.yml +0 -1329
  668. data/resources/unicode_data/nko.yml +0 -945
  669. data/resources/unicode_data/number_forms.yml +0 -929
  670. data/resources/unicode_data/ogham.yml +0 -465
  671. data/resources/unicode_data/ol_chiki.yml +0 -769
  672. data/resources/unicode_data/old_italic.yml +0 -561
  673. data/resources/unicode_data/old_persian.yml +0 -801
  674. data/resources/unicode_data/old_south_arabian.yml +0 -513
  675. data/resources/unicode_data/old_turkic.yml +0 -1169
  676. data/resources/unicode_data/optical_character_recognition.yml +0 -177
  677. data/resources/unicode_data/oriya.yml +0 -1441
  678. data/resources/unicode_data/osmanya.yml +0 -641
  679. data/resources/unicode_data/phags_pa.yml +0 -897
  680. data/resources/unicode_data/phaistos_disc.yml +0 -737
  681. data/resources/unicode_data/phoenician.yml +0 -465
  682. data/resources/unicode_data/phonetic_extensions.yml +0 -2049
  683. data/resources/unicode_data/phonetic_extensions_supplement.yml +0 -1025
  684. data/resources/unicode_data/playing_cards.yml +0 -945
  685. data/resources/unicode_data/private_use_area.yml +0 -33
  686. data/resources/unicode_data/rejang.yml +0 -593
  687. data/resources/unicode_data/rumi_numeral_symbols.yml +0 -497
  688. data/resources/unicode_data/runic.yml +0 -1297
  689. data/resources/unicode_data/samaritan.yml +0 -977
  690. data/resources/unicode_data/saurashtra.yml +0 -1297
  691. data/resources/unicode_data/sharada.yml +0 -1329
  692. data/resources/unicode_data/shavian.yml +0 -769
  693. data/resources/unicode_data/sinhala.yml +0 -1281
  694. data/resources/unicode_data/small_form_variants.yml +0 -417
  695. data/resources/unicode_data/sora_sompeng.yml +0 -561
  696. data/resources/unicode_data/spacing_modifier_letters.yml +0 -1281
  697. data/resources/unicode_data/specials.yml +0 -81
  698. data/resources/unicode_data/sundanese.yml +0 -1025
  699. data/resources/unicode_data/sundanese_supplement.yml +0 -129
  700. data/resources/unicode_data/superscripts_and_subscripts.yml +0 -673
  701. data/resources/unicode_data/supplemental_arrows_a.yml +0 -257
  702. data/resources/unicode_data/supplemental_arrows_b.yml +0 -2049
  703. data/resources/unicode_data/supplemental_mathematical_operators.yml +0 -4097
  704. data/resources/unicode_data/supplemental_punctuation.yml +0 -961
  705. data/resources/unicode_data/supplementary_private_use_area_a.yml +0 -33
  706. data/resources/unicode_data/supplementary_private_use_area_b.yml +0 -33
  707. data/resources/unicode_data/syloti_nagri.yml +0 -705
  708. data/resources/unicode_data/syriac.yml +0 -1233
  709. data/resources/unicode_data/tagalog.yml +0 -321
  710. data/resources/unicode_data/tagbanwa.yml +0 -289
  711. data/resources/unicode_data/tags.yml +0 -1553
  712. data/resources/unicode_data/tai_le.yml +0 -561
  713. data/resources/unicode_data/tai_tham.yml +0 -2033
  714. data/resources/unicode_data/tai_viet.yml +0 -1153
  715. data/resources/unicode_data/tai_xuan_jing_symbols.yml +0 -1393
  716. data/resources/unicode_data/takri.yml +0 -1057
  717. data/resources/unicode_data/tamil.yml +0 -1153
  718. data/resources/unicode_data/telugu.yml +0 -1489
  719. data/resources/unicode_data/thaana.yml +0 -801
  720. data/resources/unicode_data/thai.yml +0 -1393
  721. data/resources/unicode_data/tibetan.yml +0 -3377
  722. data/resources/unicode_data/tifinagh.yml +0 -945
  723. data/resources/unicode_data/transport_and_map_symbols.yml +0 -1121
  724. data/resources/unicode_data/ugaritic.yml +0 -497
  725. data/resources/unicode_data/unified_canadian_aboriginal_syllabics.yml +0 -10241
  726. data/resources/unicode_data/unified_canadian_aboriginal_syllabics_extended.yml +0 -1121
  727. data/resources/unicode_data/vai.yml +0 -4801
  728. data/resources/unicode_data/variation_selectors.yml +0 -257
  729. data/resources/unicode_data/variation_selectors_supplement.yml +0 -3841
  730. data/resources/unicode_data/vedic_extensions.yml +0 -625
  731. data/resources/unicode_data/yi_radicals.yml +0 -881
  732. data/resources/unicode_data/yi_syllables.yml +0 -18641
  733. data/resources/unicode_data/yijing_hexagram_symbols.yml +0 -1025
data/resources/locales/en/languages.yml CHANGED
@@ -1,558 +1,559 @@
1
- en:
2
- languages:
3
- aa: Afar
4
- ab: Abkhazian
5
- ace: Achinese
6
- ach: Acoli
7
- ada: Adangme
8
- ady: Adyghe
9
- ae: Avestan
10
- af: Afrikaans
11
- afa: "Afro-Asiatic Language"
12
- afh: Afrihili
13
- agq: Aghem
14
- ain: Ainu
15
- ak: Akan
16
- akk: Akkadian
17
- ale: Aleut
18
- alg: "Algonquian Language"
19
- alt: "Southern Altai"
20
- am: Amharic
21
- an: Aragonese
22
- ang: "Old English"
23
- anp: Angika
24
- apa: "Apache Language"
25
- ar: Arabic
26
- ar-001: "Modern Standard Arabic"
27
- arc: Aramaic
28
- arn: Araucanian
29
- arp: Arapaho
30
- art: "Artificial Language"
31
- arw: Arawak
32
- as: Assamese
33
- asa: Asu
34
- ast: Asturian
35
- ath: "Athapascan Language"
36
- aus: "Australian Language"
37
- av: Avaric
38
- awa: Awadhi
39
- ay: Aymara
40
- az: Azeri
41
- ba: Bashkir
42
- bad: Banda
43
- bai: "Bamileke Language"
44
- bal: Baluchi
45
- ban: Balinese
46
- bas: Basaa
47
- bat: "Baltic Language"
48
- be: Belarusian
49
- bej: Beja
50
- bem: Bemba
51
- ber: Berber
52
- bez: Bena
53
- bg: Bulgarian
54
- bh: Bihari
55
- bho: Bhojpuri
56
- bi: Bislama
57
- bik: Bikol
58
- bin: Bini
59
- bla: Siksika
60
- bm: Bambara
61
- bn: Bengali
62
- bnt: Bantu
63
- bo: Tibetan
64
- br: Breton
65
- bra: Braj
66
- brx: Bodo
67
- bs: Bosnian
68
- btk: Batak
69
- bua: Buriat
70
- bug: Buginese
71
- byn: Blin
72
- ca: Catalan
73
- cad: Caddo
74
- cai: "Central American Indian Language"
75
- car: Carib
76
- cau: "Caucasian Language"
77
- cay: Cayuga
78
- cch: Atsam
79
- ce: Chechen
80
- ceb: Cebuano
81
- cel: "Celtic Language"
82
- cgg: Chiga
83
- ch: Chamorro
84
- chb: Chibcha
85
- chg: Chagatai
86
- chk: Chuukese
87
- chm: Mari
88
- chn: "Chinook Jargon"
89
- cho: Choctaw
90
- chp: Chipewyan
91
- chr: Cherokee
92
- chy: Cheyenne
93
- ckb: "Sorani Kurdish"
94
- cmc: "Chamic Language"
95
- co: Corsican
96
- cop: Coptic
97
- cpe: "English-based Creole or Pidgin"
98
- cpf: "French-based Creole or Pidgin"
99
- cpp: "Portuguese-based Creole or Pidgin"
100
- cr: Cree
101
- crh: "Crimean Turkish"
102
- crp: "Creole or Pidgin"
103
- cs: Czech
104
- csb: Kashubian
105
- cu: "Church Slavic"
106
- cus: "Cushitic Language"
107
- cv: Chuvash
108
- cy: Welsh
109
- da: Danish
110
- dak: Dakota
111
- dar: Dargwa
112
- dav: Taita
113
- day: Dayak
114
- de: German
115
- de-AT: "Austrian German"
116
- de-CH: "Swiss High German"
117
- del: Delaware
118
- den: Slave
119
- dgr: Dogrib
120
- din: Dinka
121
- dje: Zarma
122
- doi: Dogri
123
- dra: "Dravidian Language"
124
- dsb: "Lower Sorbian"
125
- dua: Duala
126
- dum: "Middle Dutch"
127
- dv: Divehi
128
- dyo: Jola-Fonyi
129
- dyu: Dyula
130
- dz: Dzongkha
131
- ebu: Embu
132
- ee: Ewe
133
- efi: Efik
134
- egy: "Ancient Egyptian"
135
- eka: Ekajuk
136
- el: Greek
137
- elx: Elamite
138
- en: English
139
- en-AU: "Australian English"
140
- en-CA: "Canadian English"
141
- en-GB: "British English"
142
- en-US: "U.S. English"
143
- enm: "Middle English"
144
- eo: Esperanto
145
- es: Spanish
146
- es-419: "Latin American Spanish"
147
- es-ES: "Iberian Spanish"
148
- et: Estonian
149
- eu: Basque
150
- ewo: Ewondo
151
- fa: Persian
152
- fan: Fang
153
- fat: Fanti
154
- ff: Fulah
155
- fi: Finnish
156
- fil: Filipino
157
- fiu: "Finno-Ugrian Language"
158
- fj: Fijian
159
- fo: Faroese
160
- fon: Fon
161
- fr: French
162
- fr-CA: "Canadian French"
163
- fr-CH: "Swiss French"
164
- frm: "Middle French"
165
- fro: "Old French"
166
- frr: "Northern Frisian"
167
- frs: "Eastern Frisian"
168
- fur: Friulian
169
- fy: "Western Frisian"
170
- ga: Irish
171
- gaa: Ga
172
- gay: Gayo
173
- gba: Gbaya
174
- gd: "Scottish Gaelic"
175
- gem: "Germanic Language"
176
- gez: Geez
177
- gil: Gilbertese
178
- gl: Galician
179
- gmh: "Middle High German"
180
- gn: Guarani
181
- goh: "Old High German"
182
- gon: Gondi
183
- gor: Gorontalo
184
- got: Gothic
185
- grb: Grebo
186
- grc: "Ancient Greek"
187
- gsw: "Swiss German"
188
- gu: Gujarati
189
- guz: Gusii
190
- gv: Manx
191
- gwi: Gwichʼin
192
- ha: Hausa
193
- hai: Haida
194
- haw: Hawaiian
195
- he: Hebrew
196
- hi: Hindi
197
- hil: Hiligaynon
198
- him: Himachali
199
- hit: Hittite
200
- hmn: Hmong
201
- ho: "Hiri Motu"
202
- hr: Croatian
203
- hsb: "Upper Sorbian"
204
- ht: Haitian
205
- hu: Hungarian
206
- hup: Hupa
207
- hy: Armenian
208
- hz: Herero
209
- ia: Interlingua
210
- iba: Iban
211
- id: Indonesian
212
- ie: Interlingue
213
- ig: Igbo
214
- ii: "Sichuan Yi"
215
- ijo: Ijo
216
- ik: Inupiaq
217
- ilo: Iloko
218
- inc: "Indic Language"
219
- ine: "Indo-European Language"
220
- inh: Ingush
221
- io: Ido
222
- ira: "Iranian Language"
223
- iro: "Iroquoian Language"
224
- is: Icelandic
225
- it: Italian
226
- iu: Inuktitut
227
- ja: Japanese
228
- jbo: Lojban
229
- jmc: Machame
230
- jpr: Judeo-Persian
231
- jrb: Judeo-Arabic
232
- jv: Javanese
233
- ka: Georgian
234
- kaa: Kara-Kalpak
235
- kab: Kabyle
236
- kac: Kachin
237
- kaj: Jju
238
- kam: Kamba
239
- kar: Karen
240
- kaw: Kawi
241
- kbd: Kabardian
242
- kcg: Tyap
243
- kde: Makonde
244
- kea: Kabuverdianu
245
- kfo: Koro
246
- kg: Kongo
247
- kha: Khasi
248
- khi: "Khoisan Language"
249
- kho: Khotanese
250
- khq: "Koyra Chiini"
251
- ki: Kikuyu
252
- kj: Kuanyama
253
- kk: Kazakh
254
- kl: Kalaallisut
255
- kln: Kalenjin
256
- km: Khmer
257
- kmb: Kimbundu
258
- kn: Kannada
259
- ko: Korean
260
- kok: Konkani
261
- kos: Kosraean
262
- kpe: Kpelle
263
- kr: Kanuri
264
- krc: Karachay-Balkar
265
- krl: Karelian
266
- kro: Kru
267
- kru: Kurukh
268
- ks: Kashmiri
269
- ksb: Shambala
270
- ksf: Bafia
271
- ksh: Colognian
272
- ku: Kurdish
273
- kum: Kumyk
274
- kut: Kutenai
275
- kv: Komi
276
- kw: Cornish
277
- ky: Kirghiz
278
- la: Latin
279
- lad: Ladino
280
- lag: Langi
281
- lah: Lahnda
282
- lam: Lamba
283
- lb: Luxembourgish
284
- lez: Lezghian
285
- lg: Ganda
286
- li: Limburgish
287
- ln: Lingala
288
- lo: Lao
289
- lol: Mongo
290
- loz: Lozi
291
- lt: Lithuanian
292
- lu: Luba-Katanga
293
- lua: Luba-Lulua
294
- lui: Luiseno
295
- lun: Lunda
296
- luo: Luo
297
- lus: Lushai
298
- luy: Luyia
299
- lv: Latvian
300
- mad: Madurese
301
- mag: Magahi
302
- mai: Maithili
303
- mak: Makasar
304
- man: Mandingo
305
- map: "Austronesian Language"
306
- mas: Masai
307
- mdf: Moksha
308
- mdr: Mandar
309
- men: Mende
310
- mer: Meru
311
- mfe: Morisyen
312
- mg: Malagasy
313
- mga: "Middle Irish"
314
- mgh: Makhuwa-Meetto
315
- mh: Marshallese
316
- mi: Maori
317
- mic: Micmac
318
- min: Minangkabau
319
- mis: "Miscellaneous Language"
320
- mk: Macedonian
321
- mkh: "Mon-Khmer Language"
322
- ml: Malayalam
323
- mn: Mongolian
324
- mnc: Manchu
325
- mni: Manipuri
326
- mno: "Manobo Language"
327
- mo: Moldavian
328
- moh: Mohawk
329
- mos: Mossi
330
- mr: Marathi
331
- ms: Malay
332
- mt: Maltese
333
- mua: Mundang
334
- mul: "Multiple Languages"
335
- mun: "Munda Language"
336
- mus: Creek
337
- mwl: Mirandese
338
- mwr: Marwari
339
- my: Burmese
340
- myn: "Mayan Language"
341
- myv: Erzya
342
- na: Nauru
343
- nah: Nahuatl
344
- nai: "North American Indian Language"
345
- nap: Neapolitan
346
- naq: Nama
347
- nb: "Norwegian Bokmål"
348
- nd: "North Ndebele"
349
- nds: "Low German"
350
- ne: Nepali
351
- new: Newari
352
- ng: Ndonga
353
- nia: Nias
354
- nic: "Niger-Kordofanian Language"
355
- niu: Niuean
356
- nl: Dutch
357
- nl-BE: Flemish
358
- nmg: Kwasio
359
- nn: "Norwegian Nynorsk"
360
- "no": Norwegian
361
- nog: Nogai
362
- non: "Old Norse"
363
- nqo: N’Ko
364
- nr: "South Ndebele"
365
- nso: "Northern Sotho"
366
- nub: "Nubian Language"
367
- nus: Nuer
368
- nv: Navajo
369
- nwc: "Classical Newari"
370
- ny: Nyanja
371
- nym: Nyamwezi
372
- nyn: Nyankole
373
- nyo: Nyoro
374
- nzi: Nzima
375
- oc: Occitan
376
- oj: Ojibwa
377
- om: Oromo
378
- or: Oriya
379
- os: Ossetic
380
- osa: Osage
381
- ota: "Ottoman Turkish"
382
- oto: "Otomian Language"
383
- pa: Punjabi
384
- paa: "Papuan Language"
385
- pag: Pangasinan
386
- pal: Pahlavi
387
- pam: Pampanga
388
- pap: Papiamento
389
- pau: Palauan
390
- peo: "Old Persian"
391
- phi: "Philippine Language"
392
- phn: Phoenician
393
- pi: Pali
394
- pl: Polish
395
- pon: Pohnpeian
396
- pra: "Prakrit Language"
397
- pro: "Old Provençal"
398
- ps: Pushto
399
- pt: Portuguese
400
- pt-BR: "Brazilian Portuguese"
401
- pt-PT: "Iberian Portuguese"
402
- qu: Quechua
403
- raj: Rajasthani
404
- rap: Rapanui
405
- rar: Rarotongan
406
- rm: Romansh
407
- rn: Rundi
408
- ro: Romanian
409
- roa: "Romance Language"
410
- rof: Rombo
411
- rom: Romany
412
- root: Root
413
- ru: Russian
414
- rup: Aromanian
415
- rw: Kinyarwanda
416
- rwk: Rwa
417
- sa: Sanskrit
418
- sad: Sandawe
419
- sah: Sakha
420
- sai: "South American Indian Language"
421
- sal: "Salishan Language"
422
- sam: "Samaritan Aramaic"
423
- saq: Samburu
424
- sas: Sasak
425
- sat: Santali
426
- sbp: Sangu
427
- sc: Sardinian
428
- scn: Sicilian
429
- sco: Scots
430
- sd: Sindhi
431
- se: "Northern Sami"
432
- see: Seneca
433
- seh: Sena
434
- sel: Selkup
435
- sem: "Semitic Language"
436
- ses: "Koyraboro Senni"
437
- sg: Sango
438
- sga: "Old Irish"
439
- sgn: "Sign Language"
440
- sh: Serbo-Croatian
441
- shi: Tachelhit
442
- shn: Shan
443
- si: Sinhala
444
- sid: Sidamo
445
- sio: "Siouan Language"
446
- sit: "Sino-Tibetan Language"
447
- sk: Slovak
448
- sl: Slovenian
449
- sla: "Slavic Language"
450
- sm: Samoan
451
- sma: "Southern Sami"
452
- smi: "Sami Language"
453
- smj: "Lule Sami"
454
- smn: "Inari Sami"
455
- sms: "Skolt Sami"
456
- sn: Shona
457
- snk: Soninke
458
- so: Somali
459
- sog: Sogdien
460
- son: Songhai
461
- sq: Albanian
462
- sr: Serbian
463
- srn: "Sranan Tongo"
464
- srr: Serer
465
- ss: Swati
466
- ssa: "Nilo-Saharan Language"
467
- ssy: Saho
468
- st: "Southern Sotho"
469
- su: Sundanese
470
- suk: Sukuma
471
- sus: Susu
472
- sux: Sumerian
473
- sv: Swedish
474
- sw: Swahili
475
- swb: Comorian
476
- swc: "Congo Swahili"
477
- syc: "Classical Syriac"
478
- syr: Syriac
479
- ta: Tamil
480
- tai: "Tai Language"
481
- te: Telugu
482
- tem: Timne
483
- teo: Teso
484
- ter: Tereno
485
- tet: Tetum
486
- tg: Tajik
487
- th: Thai
488
- ti: Tigrinya
489
- tig: Tigre
490
- tiv: Tiv
491
- tk: Turkmen
492
- tkl: Tokelau
493
- tl: Tagalog
494
- tlh: Klingon
495
- tli: Tlingit
496
- tmh: Tamashek
497
- tn: Tswana
498
- to: Tongan
499
- tog: "Nyasa Tonga"
500
- tpi: "Tok Pisin"
501
- tr: Turkish
502
- trv: Taroko
503
- ts: Tsonga
504
- tsi: Tsimshian
505
- tt: Tatar
506
- tum: Tumbuka
507
- tup: "Tupi Language"
508
- tut: "Altaic Language"
509
- tvl: Tuvalu
510
- tw: Twi
511
- twq: Tasawaq
512
- ty: Tahitian
513
- tyv: Tuvinian
514
- tzm: "Central Morocco Tamazight"
515
- udm: Udmurt
516
- ug: Uyghur
517
- uga: Ugaritic
518
- uk: Ukrainian
519
- umb: Umbundu
520
- und: "Unknown Language"
521
- ur: Urdu
522
- uz: Uzbek
523
- vai: Vai
524
- ve: Venda
525
- vi: Vietnamese
526
- vo: Volapük
527
- vot: Votic
528
- vun: Vunjo
529
- wa: Walloon
530
- wae: Walser
531
- wak: "Wakashan Language"
532
- wal: Walamo
533
- war: Waray
534
- was: Washo
535
- wen: "Sorbian Language"
536
- wo: Wolof
537
- xal: Kalmyk
538
- xh: Xhosa
539
- xog: Soga
540
- yao: Yao
541
- yap: Yapese
542
- yav: Yangben
543
- yi: Yiddish
544
- yo: Yoruba
545
- ypk: "Yupik Language"
546
- yue: Cantonese
547
- za: Zhuang
548
- zap: Zapotec
549
- zbl: Blissymbols
550
- zen: Zenaga
551
- zh: Chinese
552
- zh-Hans: "Simplified Chinese"
553
- zh-Hant: "Traditional Chinese"
554
- znd: Zande
555
- zu: Zulu
556
- zun: Zuni
557
- zxx: "No linguistic content"
558
- zza: Zaza
1
+ ---
2
+ :en:
3
+ :languages:
4
+ :aa: Afar
5
+ :ab: Abkhazian
6
+ :ace: Achinese
7
+ :ach: Acoli
8
+ :ada: Adangme
9
+ :ady: Adyghe
10
+ :ae: Avestan
11
+ :af: Afrikaans
12
+ :afa: Afro-Asiatic Language
13
+ :afh: Afrihili
14
+ :agq: Aghem
15
+ :ain: Ainu
16
+ :ak: Akan
17
+ :akk: Akkadian
18
+ :ale: Aleut
19
+ :alg: Algonquian Language
20
+ :alt: Southern Altai
21
+ :am: Amharic
22
+ :an: Aragonese
23
+ :ang: Old English
24
+ :anp: Angika
25
+ :apa: Apache Language
26
+ :ar: Arabic
27
+ :ar-001: Modern Standard Arabic
28
+ :arc: Aramaic
29
+ :arn: Araucanian
30
+ :arp: Arapaho
31
+ :art: Artificial Language
32
+ :arw: Arawak
33
+ :as: Assamese
34
+ :asa: Asu
35
+ :ast: Asturian
36
+ :ath: Athapascan Language
37
+ :aus: Australian Language
38
+ :av: Avaric
39
+ :awa: Awadhi
40
+ :ay: Aymara
41
+ :az: Azeri
42
+ :ba: Bashkir
43
+ :bad: Banda
44
+ :bai: Bamileke Language
45
+ :bal: Baluchi
46
+ :ban: Balinese
47
+ :bas: Basaa
48
+ :bat: Baltic Language
49
+ :be: Belarusian
50
+ :bej: Beja
51
+ :bem: Bemba
52
+ :ber: Berber
53
+ :bez: Bena
54
+ :bg: Bulgarian
55
+ :bh: Bihari
56
+ :bho: Bhojpuri
57
+ :bi: Bislama
58
+ :bik: Bikol
59
+ :bin: Bini
60
+ :bla: Siksika
61
+ :bm: Bambara
62
+ :bn: Bengali
63
+ :bnt: Bantu
64
+ :bo: Tibetan
65
+ :br: Breton
66
+ :bra: Braj
67
+ :brx: Bodo
68
+ :bs: Bosnian
69
+ :btk: Batak
70
+ :bua: Buriat
71
+ :bug: Buginese
72
+ :byn: Blin
73
+ :ca: Catalan
74
+ :cad: Caddo
75
+ :cai: Central American Indian Language
76
+ :car: Carib
77
+ :cau: Caucasian Language
78
+ :cay: Cayuga
79
+ :cch: Atsam
80
+ :ce: Chechen
81
+ :ceb: Cebuano
82
+ :cel: Celtic Language
83
+ :cgg: Chiga
84
+ :ch: Chamorro
85
+ :chb: Chibcha
86
+ :chg: Chagatai
87
+ :chk: Chuukese
88
+ :chm: Mari
89
+ :chn: Chinook Jargon
90
+ :cho: Choctaw
91
+ :chp: Chipewyan
92
+ :chr: Cherokee
93
+ :chy: Cheyenne
94
+ :ckb: Sorani Kurdish
95
+ :cmc: Chamic Language
96
+ :co: Corsican
97
+ :cop: Coptic
98
+ :cpe: English-based Creole or Pidgin
99
+ :cpf: French-based Creole or Pidgin
100
+ :cpp: Portuguese-based Creole or Pidgin
101
+ :cr: Cree
102
+ :crh: Crimean Turkish
103
+ :crp: Creole or Pidgin
104
+ :cs: Czech
105
+ :csb: Kashubian
106
+ :cu: Church Slavic
107
+ :cus: Cushitic Language
108
+ :cv: Chuvash
109
+ :cy: Welsh
110
+ :da: Danish
111
+ :dak: Dakota
112
+ :dar: Dargwa
113
+ :dav: Taita
114
+ :day: Dayak
115
+ :de: German
116
+ :de-AT: Austrian German
117
+ :de-CH: Swiss High German
118
+ :del: Delaware
119
+ :den: Slave
120
+ :dgr: Dogrib
121
+ :din: Dinka
122
+ :dje: Zarma
123
+ :doi: Dogri
124
+ :dra: Dravidian Language
125
+ :dsb: Lower Sorbian
126
+ :dua: Duala
127
+ :dum: Middle Dutch
128
+ :dv: Divehi
129
+ :dyo: Jola-Fonyi
130
+ :dyu: Dyula
131
+ :dz: Dzongkha
132
+ :ebu: Embu
133
+ :ee: Ewe
134
+ :efi: Efik
135
+ :egy: Ancient Egyptian
136
+ :eka: Ekajuk
137
+ :el: Greek
138
+ :elx: Elamite
139
+ :en: English
140
+ :en-AU: Australian English
141
+ :en-CA: Canadian English
142
+ :en-GB: British English
143
+ :en-US: U.S. English
144
+ :enm: Middle English
145
+ :eo: Esperanto
146
+ :es: Spanish
147
+ :es-419: Latin American Spanish
148
+ :es-ES: Iberian Spanish
149
+ :et: Estonian
150
+ :eu: Basque
151
+ :ewo: Ewondo
152
+ :fa: Persian
153
+ :fan: Fang
154
+ :fat: Fanti
155
+ :ff: Fulah
156
+ :fi: Finnish
157
+ :fil: Filipino
158
+ :fiu: Finno-Ugrian Language
159
+ :fj: Fijian
160
+ :fo: Faroese
161
+ :fon: Fon
162
+ :fr: French
163
+ :fr-CA: Canadian French
164
+ :fr-CH: Swiss French
165
+ :frm: Middle French
166
+ :fro: Old French
167
+ :frr: Northern Frisian
168
+ :frs: Eastern Frisian
169
+ :fur: Friulian
170
+ :fy: Western Frisian
171
+ :ga: Irish
172
+ :gaa: Ga
173
+ :gay: Gayo
174
+ :gba: Gbaya
175
+ :gd: Scottish Gaelic
176
+ :gem: Germanic Language
177
+ :gez: Geez
178
+ :gil: Gilbertese
179
+ :gl: Galician
180
+ :gmh: Middle High German
181
+ :gn: Guarani
182
+ :goh: Old High German
183
+ :gon: Gondi
184
+ :gor: Gorontalo
185
+ :got: Gothic
186
+ :grb: Grebo
187
+ :grc: Ancient Greek
188
+ :gsw: Swiss German
189
+ :gu: Gujarati
190
+ :guz: Gusii
191
+ :gv: Manx
192
+ :gwi: Gwichʼin
193
+ :ha: Hausa
194
+ :hai: Haida
195
+ :haw: Hawaiian
196
+ :he: Hebrew
197
+ :hi: Hindi
198
+ :hil: Hiligaynon
199
+ :him: Himachali
200
+ :hit: Hittite
201
+ :hmn: Hmong
202
+ :ho: Hiri Motu
203
+ :hr: Croatian
204
+ :hsb: Upper Sorbian
205
+ :ht: Haitian
206
+ :hu: Hungarian
207
+ :hup: Hupa
208
+ :hy: Armenian
209
+ :hz: Herero
210
+ :ia: Interlingua
211
+ :iba: Iban
212
+ :id: Indonesian
213
+ :ie: Interlingue
214
+ :ig: Igbo
215
+ :ii: Sichuan Yi
216
+ :ijo: Ijo
217
+ :ik: Inupiaq
218
+ :ilo: Iloko
219
+ :inc: Indic Language
220
+ :ine: Indo-European Language
221
+ :inh: Ingush
222
+ :io: Ido
223
+ :ira: Iranian Language
224
+ :iro: Iroquoian Language
225
+ :is: Icelandic
226
+ :it: Italian
227
+ :iu: Inuktitut
228
+ :ja: Japanese
229
+ :jbo: Lojban
230
+ :jmc: Machame
231
+ :jpr: Judeo-Persian
232
+ :jrb: Judeo-Arabic
233
+ :jv: Javanese
234
+ :ka: Georgian
235
+ :kaa: Kara-Kalpak
236
+ :kab: Kabyle
237
+ :kac: Kachin
238
+ :kaj: Jju
239
+ :kam: Kamba
240
+ :kar: Karen
241
+ :kaw: Kawi
242
+ :kbd: Kabardian
243
+ :kcg: Tyap
244
+ :kde: Makonde
245
+ :kea: Kabuverdianu
246
+ :kfo: Koro
247
+ :kg: Kongo
248
+ :kha: Khasi
249
+ :khi: Khoisan Language
250
+ :kho: Khotanese
251
+ :khq: Koyra Chiini
252
+ :ki: Kikuyu
253
+ :kj: Kuanyama
254
+ :kk: Kazakh
255
+ :kl: Kalaallisut
256
+ :kln: Kalenjin
257
+ :km: Khmer
258
+ :kmb: Kimbundu
259
+ :kn: Kannada
260
+ :ko: Korean
261
+ :kok: Konkani
262
+ :kos: Kosraean
263
+ :kpe: Kpelle
264
+ :kr: Kanuri
265
+ :krc: Karachay-Balkar
266
+ :krl: Karelian
267
+ :kro: Kru
268
+ :kru: Kurukh
269
+ :ks: Kashmiri
270
+ :ksb: Shambala
271
+ :ksf: Bafia
272
+ :ksh: Colognian
273
+ :ku: Kurdish
274
+ :kum: Kumyk
275
+ :kut: Kutenai
276
+ :kv: Komi
277
+ :kw: Cornish
278
+ :ky: Kirghiz
279
+ :la: Latin
280
+ :lad: Ladino
281
+ :lag: Langi
282
+ :lah: Lahnda
283
+ :lam: Lamba
284
+ :lb: Luxembourgish
285
+ :lez: Lezghian
286
+ :lg: Ganda
287
+ :li: Limburgish
288
+ :ln: Lingala
289
+ :lo: Lao
290
+ :lol: Mongo
291
+ :loz: Lozi
292
+ :lt: Lithuanian
293
+ :lu: Luba-Katanga
294
+ :lua: Luba-Lulua
295
+ :lui: Luiseno
296
+ :lun: Lunda
297
+ :luo: Luo
298
+ :lus: Lushai
299
+ :luy: Luyia
300
+ :lv: Latvian
301
+ :mad: Madurese
302
+ :mag: Magahi
303
+ :mai: Maithili
304
+ :mak: Makasar
305
+ :man: Mandingo
306
+ :map: Austronesian Language
307
+ :mas: Masai
308
+ :mdf: Moksha
309
+ :mdr: Mandar
310
+ :men: Mende
311
+ :mer: Meru
312
+ :mfe: Morisyen
313
+ :mg: Malagasy
314
+ :mga: Middle Irish
315
+ :mgh: Makhuwa-Meetto
316
+ :mh: Marshallese
317
+ :mi: Maori
318
+ :mic: Micmac
319
+ :min: Minangkabau
320
+ :mis: Miscellaneous Language
321
+ :mk: Macedonian
322
+ :mkh: Mon-Khmer Language
323
+ :ml: Malayalam
324
+ :mn: Mongolian
325
+ :mnc: Manchu
326
+ :mni: Manipuri
327
+ :mno: Manobo Language
328
+ :mo: Moldavian
329
+ :moh: Mohawk
330
+ :mos: Mossi
331
+ :mr: Marathi
332
+ :ms: Malay
333
+ :mt: Maltese
334
+ :mua: Mundang
335
+ :mul: Multiple Languages
336
+ :mun: Munda Language
337
+ :mus: Creek
338
+ :mwl: Mirandese
339
+ :mwr: Marwari
340
+ :my: Burmese
341
+ :myn: Mayan Language
342
+ :myv: Erzya
343
+ :na: Nauru
344
+ :nah: Nahuatl
345
+ :nai: North American Indian Language
346
+ :nap: Neapolitan
347
+ :naq: Nama
348
+ :nb: Norwegian Bokmål
349
+ :nd: North Ndebele
350
+ :nds: Low German
351
+ :ne: Nepali
352
+ :new: Newari
353
+ :ng: Ndonga
354
+ :nia: Nias
355
+ :nic: Niger-Kordofanian Language
356
+ :niu: Niuean
357
+ :nl: Dutch
358
+ :nl-BE: Flemish
359
+ :nmg: Kwasio
360
+ :nn: Norwegian Nynorsk
361
+ :no: Norwegian
362
+ :nog: Nogai
363
+ :non: Old Norse
364
+ :nqo: N’Ko
365
+ :nr: South Ndebele
366
+ :nso: Northern Sotho
367
+ :nub: Nubian Language
368
+ :nus: Nuer
369
+ :nv: Navajo
370
+ :nwc: Classical Newari
371
+ :ny: Nyanja
372
+ :nym: Nyamwezi
373
+ :nyn: Nyankole
374
+ :nyo: Nyoro
375
+ :nzi: Nzima
376
+ :oc: Occitan
377
+ :oj: Ojibwa
378
+ :om: Oromo
379
+ :or: Oriya
380
+ :os: Ossetic
381
+ :osa: Osage
382
+ :ota: Ottoman Turkish
383
+ :oto: Otomian Language
384
+ :pa: Punjabi
385
+ :paa: Papuan Language
386
+ :pag: Pangasinan
387
+ :pal: Pahlavi
388
+ :pam: Pampanga
389
+ :pap: Papiamento
390
+ :pau: Palauan
391
+ :peo: Old Persian
392
+ :phi: Philippine Language
393
+ :phn: Phoenician
394
+ :pi: Pali
395
+ :pl: Polish
396
+ :pon: Pohnpeian
397
+ :pra: Prakrit Language
398
+ :pro: Old Provençal
399
+ :ps: Pushto
400
+ :pt: Portuguese
401
+ :pt-BR: Brazilian Portuguese
402
+ :pt-PT: Iberian Portuguese
403
+ :qu: Quechua
404
+ :raj: Rajasthani
405
+ :rap: Rapanui
406
+ :rar: Rarotongan
407
+ :rm: Romansh
408
+ :rn: Rundi
409
+ :ro: Romanian
410
+ :roa: Romance Language
411
+ :rof: Rombo
412
+ :rom: Romany
413
+ :root: Root
414
+ :ru: Russian
415
+ :rup: Aromanian
416
+ :rw: Kinyarwanda
417
+ :rwk: Rwa
418
+ :sa: Sanskrit
419
+ :sad: Sandawe
420
+ :sah: Sakha
421
+ :sai: South American Indian Language
422
+ :sal: Salishan Language
423
+ :sam: Samaritan Aramaic
424
+ :saq: Samburu
425
+ :sas: Sasak
426
+ :sat: Santali
427
+ :sbp: Sangu
428
+ :sc: Sardinian
429
+ :scn: Sicilian
430
+ :sco: Scots
431
+ :sd: Sindhi
432
+ :se: Northern Sami
433
+ :see: Seneca
434
+ :seh: Sena
435
+ :sel: Selkup
436
+ :sem: Semitic Language
437
+ :ses: Koyraboro Senni
438
+ :sg: Sango
439
+ :sga: Old Irish
440
+ :sgn: Sign Language
441
+ :sh: Serbo-Croatian
442
+ :shi: Tachelhit
443
+ :shn: Shan
444
+ :si: Sinhala
445
+ :sid: Sidamo
446
+ :sio: Siouan Language
447
+ :sit: Sino-Tibetan Language
448
+ :sk: Slovak
449
+ :sl: Slovenian
450
+ :sla: Slavic Language
451
+ :sm: Samoan
452
+ :sma: Southern Sami
453
+ :smi: Sami Language
454
+ :smj: Lule Sami
455
+ :smn: Inari Sami
456
+ :sms: Skolt Sami
457
+ :sn: Shona
458
+ :snk: Soninke
459
+ :so: Somali
460
+ :sog: Sogdien
461
+ :son: Songhai
462
+ :sq: Albanian
463
+ :sr: Serbian
464
+ :srn: Sranan Tongo
465
+ :srr: Serer
466
+ :ss: Swati
467
+ :ssa: Nilo-Saharan Language
468
+ :ssy: Saho
469
+ :st: Southern Sotho
470
+ :su: Sundanese
471
+ :suk: Sukuma
472
+ :sus: Susu
473
+ :sux: Sumerian
474
+ :sv: Swedish
475
+ :sw: Swahili
476
+ :swb: Comorian
477
+ :swc: Congo Swahili
478
+ :syc: Classical Syriac
479
+ :syr: Syriac
480
+ :ta: Tamil
481
+ :tai: Tai Language
482
+ :te: Telugu
483
+ :tem: Timne
484
+ :teo: Teso
485
+ :ter: Tereno
486
+ :tet: Tetum
487
+ :tg: Tajik
488
+ :th: Thai
489
+ :ti: Tigrinya
490
+ :tig: Tigre
491
+ :tiv: Tiv
492
+ :tk: Turkmen
493
+ :tkl: Tokelau
494
+ :tl: Tagalog
495
+ :tlh: Klingon
496
+ :tli: Tlingit
497
+ :tmh: Tamashek
498
+ :tn: Tswana
499
+ :to: Tongan
500
+ :tog: Nyasa Tonga
501
+ :tpi: Tok Pisin
502
+ :tr: Turkish
503
+ :trv: Taroko
504
+ :ts: Tsonga
505
+ :tsi: Tsimshian
506
+ :tt: Tatar
507
+ :tum: Tumbuka
508
+ :tup: Tupi Language
509
+ :tut: Altaic Language
510
+ :tvl: Tuvalu
511
+ :tw: Twi
512
+ :twq: Tasawaq
513
+ :ty: Tahitian
514
+ :tyv: Tuvinian
515
+ :tzm: Central Morocco Tamazight
516
+ :udm: Udmurt
517
+ :ug: Uyghur
518
+ :uga: Ugaritic
519
+ :uk: Ukrainian
520
+ :umb: Umbundu
521
+ :und: Unknown Language
522
+ :ur: Urdu
523
+ :uz: Uzbek
524
+ :vai: Vai
525
+ :ve: Venda
526
+ :vi: Vietnamese
527
+ :vo: Volapük
528
+ :vot: Votic
529
+ :vun: Vunjo
530
+ :wa: Walloon
531
+ :wae: Walser
532
+ :wak: Wakashan Language
533
+ :wal: Walamo
534
+ :war: Waray
535
+ :was: Washo
536
+ :wen: Sorbian Language
537
+ :wo: Wolof
538
+ :xal: Kalmyk
539
+ :xh: Xhosa
540
+ :xog: Soga
541
+ :yao: Yao
542
+ :yap: Yapese
543
+ :yav: Yangben
544
+ :yi: Yiddish
545
+ :yo: Yoruba
546
+ :ypk: Yupik Language
547
+ :yue: Cantonese
548
+ :za: Zhuang
549
+ :zap: Zapotec
550
+ :zbl: Blissymbols
551
+ :zen: Zenaga
552
+ :zh: Chinese
553
+ :zh-Hans: Simplified Chinese
554
+ :zh-Hant: Traditional Chinese
555
+ :znd: Zande
556
+ :zu: Zulu
557
+ :zun: Zuni
558
+ :zxx: No linguistic content
559
+ :zza: Zaza