twitter_cldr 3.2.1 → 3.3.0

Sign up to get free protection for your applications and to get access to all the features.
Files changed (1172) hide show
  1. checksums.yaml +4 -4
  2. data/Gemfile +9 -4
  3. data/History.txt +11 -0
  4. data/README.md +40 -3
  5. data/Rakefile +26 -21
  6. data/lib/twitter_cldr/collation/collator.rb +3 -3
  7. data/lib/twitter_cldr/collation/sort_key_builder.rb +10 -10
  8. data/lib/twitter_cldr/data_readers/calendar_data_reader.rb +8 -8
  9. data/lib/twitter_cldr/data_readers/date_time_data_reader.rb +2 -2
  10. data/lib/twitter_cldr/data_readers/number_data_reader.rb +10 -10
  11. data/lib/twitter_cldr/data_readers/timespan_data_reader.rb +27 -27
  12. data/lib/twitter_cldr/formatters/list_formatter.rb +1 -1
  13. data/lib/twitter_cldr/formatters/numbers/currency_formatter.rb +3 -3
  14. data/lib/twitter_cldr/formatters/numbers/helpers/integer.rb +7 -5
  15. data/lib/twitter_cldr/formatters/numbers/rbnf/formatters.rb +1 -1
  16. data/lib/twitter_cldr/formatters/numbers/rbnf/rule.rb +1 -1
  17. data/lib/twitter_cldr/formatters/numbers/rbnf/rule_set.rb +3 -2
  18. data/lib/twitter_cldr/formatters/numbers/rbnf.rb +2 -2
  19. data/lib/twitter_cldr/formatters/plurals/rules.rb +1 -1
  20. data/lib/twitter_cldr/localized/localized_date.rb +2 -2
  21. data/lib/twitter_cldr/localized/localized_datetime.rb +8 -8
  22. data/lib/twitter_cldr/localized/localized_number.rb +7 -7
  23. data/lib/twitter_cldr/localized/localized_string.rb +33 -1
  24. data/lib/twitter_cldr/localized/localized_symbol.rb +9 -1
  25. data/lib/twitter_cldr/localized/localized_time.rb +2 -2
  26. data/lib/twitter_cldr/localized/localized_timespan.rb +10 -10
  27. data/lib/twitter_cldr/parsers/number_parser.rb +1 -1
  28. data/lib/twitter_cldr/parsers/parser.rb +5 -1
  29. data/lib/twitter_cldr/parsers/unicode_regex/character_class.rb +41 -2
  30. data/lib/twitter_cldr/parsers/unicode_regex/character_range.rb +8 -0
  31. data/lib/twitter_cldr/parsers/unicode_regex/character_set.rb +66 -23
  32. data/lib/twitter_cldr/parsers/unicode_regex/literal.rb +4 -0
  33. data/lib/twitter_cldr/parsers/unicode_regex/unicode_string.rb +6 -3
  34. data/lib/twitter_cldr/parsers/unicode_regex_parser.rb +65 -32
  35. data/lib/twitter_cldr/parsers.rb +1 -2
  36. data/lib/twitter_cldr/resources/custom_locales_resources_importer.rb +4 -4
  37. data/lib/twitter_cldr/resources/download.rb +13 -6
  38. data/lib/twitter_cldr/resources/language_codes_importer.rb +7 -7
  39. data/lib/twitter_cldr/resources/loader.rb +4 -1
  40. data/lib/twitter_cldr/resources/locales_resources_importer.rb +30 -12
  41. data/lib/twitter_cldr/resources/postal_codes_importer.rb +32 -22
  42. data/lib/twitter_cldr/resources/properties/age_property_importer.rb +27 -0
  43. data/lib/twitter_cldr/resources/properties/arabic_shaping_property_importer.rb +42 -0
  44. data/lib/twitter_cldr/resources/properties/bidi_brackets_property_importer.rb +41 -0
  45. data/lib/twitter_cldr/resources/properties/blocks_property_importer.rb +27 -0
  46. data/lib/twitter_cldr/resources/properties/derived_core_properties_importer.rb +36 -0
  47. data/lib/twitter_cldr/resources/properties/east_asian_width_property_importer.rb +27 -0
  48. data/lib/twitter_cldr/resources/properties/grapheme_break_property_importer.rb +27 -0
  49. data/lib/twitter_cldr/resources/properties/hangul_syllable_type_property_importer.rb +27 -0
  50. data/lib/twitter_cldr/resources/properties/indic_positional_category_property_importer.rb +27 -0
  51. data/lib/twitter_cldr/resources/properties/indic_syllabic_category_property_importer.rb +27 -0
  52. data/lib/twitter_cldr/resources/properties/jamo_property_importer.rb +27 -0
  53. data/lib/twitter_cldr/resources/properties/line_break_property_importer.rb +27 -0
  54. data/lib/twitter_cldr/resources/properties/prop_list_importer.rb +36 -0
  55. data/lib/twitter_cldr/resources/properties/properties_importer.rb +59 -0
  56. data/lib/twitter_cldr/resources/properties/property_importer.rb +83 -0
  57. data/lib/twitter_cldr/resources/properties/script_extensions_property_importer.rb +40 -0
  58. data/lib/twitter_cldr/resources/properties/script_property_importer.rb +27 -0
  59. data/lib/twitter_cldr/resources/properties/sentence_break_property_importer.rb +27 -0
  60. data/lib/twitter_cldr/resources/properties/unicode_data_properties_importer.rb +60 -0
  61. data/lib/twitter_cldr/resources/properties/word_break_property_importer.rb +27 -0
  62. data/lib/twitter_cldr/resources/properties.rb +36 -0
  63. data/lib/twitter_cldr/resources/readme_renderer.rb +2 -2
  64. data/lib/twitter_cldr/resources/segment_tests_importer.rb +66 -0
  65. data/lib/twitter_cldr/resources/tailoring_importer.rb +7 -7
  66. data/lib/twitter_cldr/resources/uli/segment_exceptions_importer.rb +1 -1
  67. data/lib/twitter_cldr/resources/unicode_data_importer.rb +19 -60
  68. data/lib/twitter_cldr/resources/unicode_property_aliases_importer.rb +97 -0
  69. data/lib/twitter_cldr/resources.rb +21 -22
  70. data/lib/twitter_cldr/segmentation/break_iterator.rb +54 -0
  71. data/lib/twitter_cldr/segmentation/cursor.rb +34 -0
  72. data/lib/twitter_cldr/segmentation/parser.rb +71 -0
  73. data/lib/twitter_cldr/segmentation/rule.rb +79 -0
  74. data/lib/twitter_cldr/segmentation/rule_set.rb +116 -0
  75. data/lib/twitter_cldr/segmentation/rule_set_builder.rb +142 -0
  76. data/lib/twitter_cldr/segmentation.rb +17 -0
  77. data/lib/twitter_cldr/shared/bidi.rb +4 -4
  78. data/lib/twitter_cldr/shared/calendar.rb +11 -11
  79. data/lib/twitter_cldr/shared/caser.rb +84 -0
  80. data/lib/twitter_cldr/shared/code_point.rb +101 -139
  81. data/lib/twitter_cldr/shared/currencies.rb +5 -5
  82. data/lib/twitter_cldr/shared/language_codes.rb +2 -2
  83. data/lib/twitter_cldr/shared/languages.rb +1 -1
  84. data/lib/twitter_cldr/shared/likely_subtags.rb +104 -0
  85. data/lib/twitter_cldr/shared/locale.rb +252 -0
  86. data/lib/twitter_cldr/shared/postal_codes.rb +21 -9
  87. data/lib/twitter_cldr/shared/properties/arabic_shaping.rb +40 -0
  88. data/lib/twitter_cldr/shared/properties/bidi_brackets.rb +28 -0
  89. data/lib/twitter_cldr/shared/properties.rb +13 -0
  90. data/lib/twitter_cldr/shared/properties_database.rb +180 -0
  91. data/lib/twitter_cldr/shared/property_name_aliases.rb +48 -0
  92. data/lib/twitter_cldr/shared/property_normalizer.rb +108 -0
  93. data/lib/twitter_cldr/shared/property_set.rb +113 -0
  94. data/lib/twitter_cldr/shared/property_value_aliases.rb +99 -0
  95. data/lib/twitter_cldr/shared/unicode_regex.rb +29 -3
  96. data/lib/twitter_cldr/shared.rb +9 -1
  97. data/lib/twitter_cldr/tokenizers/numbers/number_tokenizer.rb +1 -1
  98. data/lib/twitter_cldr/tokenizers/token.rb +1 -1
  99. data/lib/twitter_cldr/tokenizers/tokenizer.rb +15 -13
  100. data/lib/twitter_cldr/tokenizers/unicode_regex/unicode_regex_tokenizer.rb +4 -4
  101. data/lib/twitter_cldr/utils/file_system_trie.rb +145 -0
  102. data/lib/twitter_cldr/utils/range_set.rb +131 -31
  103. data/lib/twitter_cldr/utils/regexp_sampler.rb +0 -1
  104. data/lib/twitter_cldr/utils/script_detector.rb +75 -0
  105. data/lib/twitter_cldr/utils/yaml.rb +3 -3
  106. data/lib/twitter_cldr/utils.rb +8 -5
  107. data/lib/twitter_cldr/version.rb +1 -1
  108. data/lib/twitter_cldr/versions.rb +30 -0
  109. data/lib/twitter_cldr.rb +8 -10
  110. data/resources/locales/af/calendars.yml +8 -8
  111. data/resources/locales/af/lists.yml +8 -4
  112. data/resources/locales/af/numbers.yml +54 -30
  113. data/resources/locales/ar/lists.yml +8 -4
  114. data/resources/locales/ar/numbers.yml +48 -24
  115. data/resources/locales/be/calendars.yml +4 -4
  116. data/resources/locales/be/lists.yml +2 -1
  117. data/resources/locales/be/numbers.yml +24 -12
  118. data/resources/locales/bg/calendars.yml +8 -8
  119. data/resources/locales/bg/lists.yml +8 -4
  120. data/resources/locales/bg/numbers.yml +48 -24
  121. data/resources/locales/bn/lists.yml +8 -4
  122. data/resources/locales/bn/numbers.yml +48 -24
  123. data/resources/locales/ca/calendars.yml +8 -8
  124. data/resources/locales/ca/lists.yml +8 -4
  125. data/resources/locales/ca/numbers.yml +48 -24
  126. data/resources/locales/cs/calendars.yml +32 -32
  127. data/resources/locales/cs/lists.yml +8 -4
  128. data/resources/locales/cs/numbers.yml +48 -24
  129. data/resources/locales/cy/calendars.yml +8 -8
  130. data/resources/locales/cy/lists.yml +6 -3
  131. data/resources/locales/cy/numbers.yml +48 -24
  132. data/resources/locales/da/calendars.yml +10 -10
  133. data/resources/locales/da/lists.yml +8 -4
  134. data/resources/locales/da/numbers.yml +48 -24
  135. data/resources/locales/de/calendars.yml +8 -8
  136. data/resources/locales/de/lists.yml +8 -4
  137. data/resources/locales/de/numbers.yml +48 -24
  138. data/resources/locales/de-CH/calendars.yml +8 -8
  139. data/resources/locales/de-CH/lists.yml +8 -4
  140. data/resources/locales/de-CH/numbers.yml +48 -24
  141. data/resources/locales/el/calendars.yml +8 -8
  142. data/resources/locales/el/lists.yml +8 -4
  143. data/resources/locales/el/numbers.yml +48 -24
  144. data/resources/locales/en/calendars.yml +4 -4
  145. data/resources/locales/en/lists.yml +8 -4
  146. data/resources/locales/en/numbers.yml +48 -24
  147. data/resources/locales/en-150/calendars.yml +4 -4
  148. data/resources/locales/en-150/lists.yml +8 -4
  149. data/resources/locales/en-150/numbers.yml +48 -24
  150. data/resources/locales/en-AU/calendars.yml +4 -4
  151. data/resources/locales/en-AU/lists.yml +8 -4
  152. data/resources/locales/en-AU/numbers.yml +48 -24
  153. data/resources/locales/en-CA/calendars.yml +4 -4
  154. data/resources/locales/en-CA/lists.yml +8 -4
  155. data/resources/locales/en-CA/numbers.yml +48 -24
  156. data/resources/locales/en-GB/calendars.yml +4 -4
  157. data/resources/locales/en-GB/lists.yml +8 -4
  158. data/resources/locales/en-GB/numbers.yml +48 -24
  159. data/resources/locales/en-IE/calendars.yml +4 -4
  160. data/resources/locales/en-IE/lists.yml +8 -4
  161. data/resources/locales/en-IE/numbers.yml +48 -24
  162. data/resources/locales/en-SG/calendars.yml +4 -4
  163. data/resources/locales/en-SG/lists.yml +8 -4
  164. data/resources/locales/en-SG/numbers.yml +48 -24
  165. data/resources/locales/en-ZA/calendars.yml +4 -4
  166. data/resources/locales/en-ZA/lists.yml +8 -4
  167. data/resources/locales/en-ZA/numbers.yml +48 -24
  168. data/resources/locales/es/lists.yml +8 -4
  169. data/resources/locales/es/numbers.yml +48 -24
  170. data/resources/locales/es-419/calendars.yml +8 -8
  171. data/resources/locales/es-419/lists.yml +8 -4
  172. data/resources/locales/es-419/numbers.yml +50 -26
  173. data/resources/locales/es-CO/lists.yml +8 -4
  174. data/resources/locales/es-CO/numbers.yml +48 -24
  175. data/resources/locales/es-MX/lists.yml +8 -4
  176. data/resources/locales/es-MX/numbers.yml +48 -24
  177. data/resources/locales/es-US/lists.yml +8 -4
  178. data/resources/locales/es-US/numbers.yml +48 -24
  179. data/resources/locales/eu/calendars.yml +8 -8
  180. data/resources/locales/eu/lists.yml +8 -4
  181. data/resources/locales/eu/numbers.yml +48 -24
  182. data/resources/locales/fa/lists.yml +8 -4
  183. data/resources/locales/fa/numbers.yml +48 -24
  184. data/resources/locales/fi/calendars.yml +8 -8
  185. data/resources/locales/fi/lists.yml +8 -4
  186. data/resources/locales/fi/numbers.yml +48 -24
  187. data/resources/locales/fil/calendars.yml +8 -8
  188. data/resources/locales/fil/lists.yml +8 -4
  189. data/resources/locales/fil/numbers.yml +48 -24
  190. data/resources/locales/fr/calendars.yml +8 -8
  191. data/resources/locales/fr/lists.yml +8 -4
  192. data/resources/locales/fr/numbers.yml +48 -24
  193. data/resources/locales/fr-BE/calendars.yml +8 -8
  194. data/resources/locales/fr-BE/lists.yml +8 -4
  195. data/resources/locales/fr-BE/numbers.yml +48 -24
  196. data/resources/locales/fr-CA/calendars.yml +8 -8
  197. data/resources/locales/fr-CA/lists.yml +8 -4
  198. data/resources/locales/fr-CA/numbers.yml +48 -24
  199. data/resources/locales/fr-CH/calendars.yml +8 -8
  200. data/resources/locales/fr-CH/lists.yml +8 -4
  201. data/resources/locales/fr-CH/numbers.yml +48 -24
  202. data/resources/locales/ga/calendars.yml +8 -8
  203. data/resources/locales/ga/lists.yml +8 -4
  204. data/resources/locales/ga/numbers.yml +48 -24
  205. data/resources/locales/gl/calendars.yml +8 -8
  206. data/resources/locales/gl/lists.yml +8 -4
  207. data/resources/locales/gl/numbers.yml +48 -24
  208. data/resources/locales/he/calendars.yml +28 -28
  209. data/resources/locales/he/lists.yml +8 -4
  210. data/resources/locales/he/numbers.yml +48 -24
  211. data/resources/locales/hi/calendars.yml +8 -8
  212. data/resources/locales/hi/lists.yml +8 -4
  213. data/resources/locales/hi/numbers.yml +48 -24
  214. data/resources/locales/hr/lists.yml +8 -4
  215. data/resources/locales/hr/numbers.yml +48 -24
  216. data/resources/locales/hu/lists.yml +8 -4
  217. data/resources/locales/hu/numbers.yml +48 -24
  218. data/resources/locales/id/calendars.yml +8 -8
  219. data/resources/locales/id/lists.yml +8 -4
  220. data/resources/locales/id/numbers.yml +49 -25
  221. data/resources/locales/is/calendars.yml +8 -8
  222. data/resources/locales/is/lists.yml +8 -4
  223. data/resources/locales/is/numbers.yml +48 -24
  224. data/resources/locales/it/calendars.yml +8 -8
  225. data/resources/locales/it/lists.yml +8 -4
  226. data/resources/locales/it/numbers.yml +54 -30
  227. data/resources/locales/it-CH/calendars.yml +8 -8
  228. data/resources/locales/it-CH/lists.yml +8 -4
  229. data/resources/locales/it-CH/numbers.yml +54 -30
  230. data/resources/locales/ja/calendars.yml +32 -32
  231. data/resources/locales/ja/lists.yml +8 -4
  232. data/resources/locales/ja/numbers.yml +48 -24
  233. data/resources/locales/ko/calendars.yml +8 -8
  234. data/resources/locales/ko/lists.yml +8 -4
  235. data/resources/locales/ko/numbers.yml +48 -24
  236. data/resources/locales/lv/lists.yml +8 -4
  237. data/resources/locales/lv/numbers.yml +48 -24
  238. data/resources/locales/ms/calendars.yml +8 -8
  239. data/resources/locales/ms/lists.yml +8 -4
  240. data/resources/locales/ms/numbers.yml +48 -24
  241. data/resources/locales/nb/calendars.yml +9 -9
  242. data/resources/locales/nb/lists.yml +8 -4
  243. data/resources/locales/nb/numbers.yml +48 -24
  244. data/resources/locales/nl/calendars.yml +8 -8
  245. data/resources/locales/nl/lists.yml +8 -4
  246. data/resources/locales/nl/numbers.yml +48 -24
  247. data/resources/locales/pl/calendars.yml +8 -8
  248. data/resources/locales/pl/lists.yml +8 -4
  249. data/resources/locales/pl/numbers.yml +48 -24
  250. data/resources/locales/pt/calendars.yml +8 -8
  251. data/resources/locales/pt/lists.yml +8 -4
  252. data/resources/locales/pt/numbers.yml +48 -24
  253. data/resources/locales/ro/calendars.yml +8 -8
  254. data/resources/locales/ro/lists.yml +8 -4
  255. data/resources/locales/ro/numbers.yml +48 -24
  256. data/resources/locales/ru/calendars.yml +8 -8
  257. data/resources/locales/ru/lists.yml +8 -4
  258. data/resources/locales/ru/numbers.yml +48 -24
  259. data/resources/locales/sk/calendars.yml +8 -8
  260. data/resources/locales/sk/lists.yml +8 -4
  261. data/resources/locales/sk/numbers.yml +48 -24
  262. data/resources/locales/sq/calendars.yml +8 -8
  263. data/resources/locales/sq/lists.yml +8 -4
  264. data/resources/locales/sq/numbers.yml +48 -24
  265. data/resources/locales/sr/lists.yml +8 -4
  266. data/resources/locales/sr/numbers.yml +48 -24
  267. data/resources/locales/sv/calendars.yml +10 -10
  268. data/resources/locales/sv/lists.yml +8 -4
  269. data/resources/locales/sv/numbers.yml +48 -24
  270. data/resources/locales/ta/calendars.yml +8 -8
  271. data/resources/locales/ta/lists.yml +8 -4
  272. data/resources/locales/ta/numbers.yml +48 -24
  273. data/resources/locales/th/calendars.yml +8 -8
  274. data/resources/locales/th/lists.yml +8 -4
  275. data/resources/locales/th/numbers.yml +48 -24
  276. data/resources/locales/tr/lists.yml +8 -4
  277. data/resources/locales/tr/numbers.yml +50 -26
  278. data/resources/locales/uk/calendars.yml +8 -8
  279. data/resources/locales/uk/lists.yml +8 -4
  280. data/resources/locales/uk/numbers.yml +48 -24
  281. data/resources/locales/ur/calendars.yml +8 -8
  282. data/resources/locales/ur/lists.yml +8 -4
  283. data/resources/locales/ur/numbers.yml +48 -24
  284. data/resources/locales/vi/calendars.yml +32 -32
  285. data/resources/locales/vi/lists.yml +8 -4
  286. data/resources/locales/vi/numbers.yml +48 -24
  287. data/resources/locales/zh/calendars.yml +32 -32
  288. data/resources/locales/zh/lists.yml +8 -4
  289. data/resources/locales/zh/numbers.yml +48 -24
  290. data/resources/locales/zh-Hant/calendars.yml +32 -32
  291. data/resources/locales/zh-Hant/lists.yml +8 -4
  292. data/resources/locales/zh-Hant/numbers.yml +48 -24
  293. data/resources/shared/aliases.yml +1351 -0
  294. data/resources/shared/likely_subtags.yml +1149 -0
  295. data/resources/shared/postal_codes.yml +486 -289
  296. data/resources/shared/segments/segments_root.yml +57 -57
  297. data/resources/shared/segments/tests/sentence_break_test.yml +527 -0
  298. data/resources/shared/segments/tests/word_break_test.yml +1379 -0
  299. data/resources/shared/territories_containment.yml +25 -17
  300. data/resources/shared/variables.yml +1194 -0
  301. data/resources/unicode_data/blocks/ahom.yml +913 -0
  302. data/resources/unicode_data/blocks/anatolian_hieroglyphs.yml +9329 -0
  303. data/resources/unicode_data/blocks/arabic.yml +16 -0
  304. data/resources/unicode_data/blocks/arabic_presentation_forms_a.yml +2 -2
  305. data/resources/unicode_data/blocks/bassa_vah.yml +577 -0
  306. data/resources/unicode_data/blocks/buginese.yml +2 -2
  307. data/resources/unicode_data/blocks/caucasian_albanian.yml +849 -0
  308. data/resources/unicode_data/blocks/cherokee_supplement.yml +1281 -0
  309. data/resources/unicode_data/blocks/cjk_unified_ideographs_extension_e.yml +33 -0
  310. data/resources/unicode_data/blocks/combining_diacritical_marks_extended.yml +241 -0
  311. data/resources/unicode_data/blocks/coptic_epact_numbers.yml +449 -0
  312. data/resources/unicode_data/blocks/cuneiform_numbers_and_punctuation.yml +2 -2
  313. data/resources/unicode_data/blocks/duployan.yml +2289 -0
  314. data/resources/unicode_data/blocks/early_dynastic_cuneiform.yml +3137 -0
  315. data/resources/unicode_data/blocks/elbasan.yml +641 -0
  316. data/resources/unicode_data/blocks/general_punctuation.yml +64 -0
  317. data/resources/unicode_data/blocks/geometric_shapes_extended.yml +1361 -0
  318. data/resources/unicode_data/blocks/grantha.yml +1361 -0
  319. data/resources/unicode_data/blocks/gujarati.yml +0 -16
  320. data/resources/unicode_data/blocks/hatran.yml +417 -0
  321. data/resources/unicode_data/blocks/kannada.yml +0 -16
  322. data/resources/unicode_data/blocks/khojki.yml +977 -0
  323. data/resources/unicode_data/blocks/khudawadi.yml +1105 -0
  324. data/resources/unicode_data/blocks/latin_extended_e.yml +865 -0
  325. data/resources/unicode_data/blocks/linear_a.yml +5457 -0
  326. data/resources/unicode_data/blocks/mahajani.yml +625 -0
  327. data/resources/unicode_data/blocks/manichaean.yml +817 -0
  328. data/resources/unicode_data/blocks/mende_kikakui.yml +3409 -0
  329. data/resources/unicode_data/blocks/miscellaneous_technical.yml +4 -4
  330. data/resources/unicode_data/blocks/modi.yml +1265 -0
  331. data/resources/unicode_data/blocks/mongolian.yml +2 -2
  332. data/resources/unicode_data/blocks/mro.yml +689 -0
  333. data/resources/unicode_data/blocks/multani.yml +609 -0
  334. data/resources/unicode_data/blocks/myanmar_extended_b.yml +497 -0
  335. data/resources/unicode_data/blocks/nabataean.yml +641 -0
  336. data/resources/unicode_data/blocks/old_hungarian.yml +1729 -0
  337. data/resources/unicode_data/blocks/old_north_arabian.yml +513 -0
  338. data/resources/unicode_data/blocks/old_permic.yml +689 -0
  339. data/resources/unicode_data/blocks/ornamental_dingbats.yml +769 -0
  340. data/resources/unicode_data/blocks/pahawh_hmong.yml +2033 -0
  341. data/resources/unicode_data/blocks/palmyrene.yml +513 -0
  342. data/resources/unicode_data/blocks/pau_cin_hau.yml +913 -0
  343. data/resources/unicode_data/blocks/psalter_pahlavi.yml +465 -0
  344. data/resources/unicode_data/blocks/shorthand_format_controls.yml +65 -0
  345. data/resources/unicode_data/blocks/siddham.yml +1473 -0
  346. data/resources/unicode_data/blocks/sinhala_archaic_numbers.yml +321 -0
  347. data/resources/unicode_data/blocks/supplemental_arrows_c.yml +2369 -0
  348. data/resources/unicode_data/blocks/supplemental_symbols_and_pictographs.yml +241 -0
  349. data/resources/unicode_data/blocks/sutton_signwriting.yml +10753 -0
  350. data/resources/unicode_data/blocks/tirhuta.yml +1313 -0
  351. data/resources/unicode_data/blocks/warang_citi.yml +1345 -0
  352. data/resources/unicode_data/properties/ASCII_Hex_Digit/value.dump +5 -0
  353. data/resources/unicode_data/properties/Age/1.1/value.dump +0 -0
  354. data/resources/unicode_data/properties/Age/2.0/value.dump +0 -0
  355. data/resources/unicode_data/properties/Age/2.1/value.dump +4 -0
  356. data/resources/unicode_data/properties/Age/3.0/value.dump +0 -0
  357. data/resources/unicode_data/properties/Age/3.1/value.dump +0 -0
  358. data/resources/unicode_data/properties/Age/3.2/value.dump +0 -0
  359. data/resources/unicode_data/properties/Age/4.0/value.dump +0 -0
  360. data/resources/unicode_data/properties/Age/4.1/value.dump +0 -0
  361. data/resources/unicode_data/properties/Age/5.0/value.dump +0 -0
  362. data/resources/unicode_data/properties/Age/5.1/value.dump +0 -0
  363. data/resources/unicode_data/properties/Age/5.2/value.dump +0 -0
  364. data/resources/unicode_data/properties/Age/6.0/value.dump +0 -0
  365. data/resources/unicode_data/properties/Age/6.1/value.dump +0 -0
  366. data/resources/unicode_data/properties/Age/6.2/value.dump +3 -0
  367. data/resources/unicode_data/properties/Age/6.3/value.dump +4 -0
  368. data/resources/unicode_data/properties/Alphabetic/value.dump +0 -0
  369. data/resources/unicode_data/properties/Bidi_Class/AL/value.dump +0 -0
  370. data/resources/unicode_data/properties/Bidi_Class/AN/value.dump +0 -0
  371. data/resources/unicode_data/properties/Bidi_Class/B/value.dump +8 -0
  372. data/resources/unicode_data/properties/Bidi_Class/BN/value.dump +0 -0
  373. data/resources/unicode_data/properties/Bidi_Class/CS/value.dump +15 -0
  374. data/resources/unicode_data/properties/Bidi_Class/EN/value.dump +0 -0
  375. data/resources/unicode_data/properties/Bidi_Class/ES/value.dump +11 -0
  376. data/resources/unicode_data/properties/Bidi_Class/ET/value.dump +27 -0
  377. data/resources/unicode_data/properties/Bidi_Class/FSI/value.dump +3 -0
  378. data/resources/unicode_data/properties/Bidi_Class/L/value.dump +0 -0
  379. data/resources/unicode_data/properties/Bidi_Class/LRE/value.dump +3 -0
  380. data/resources/unicode_data/properties/Bidi_Class/LRI/value.dump +3 -0
  381. data/resources/unicode_data/properties/Bidi_Class/LRO/value.dump +3 -0
  382. data/resources/unicode_data/properties/Bidi_Class/NSM/value.dump +0 -0
  383. data/resources/unicode_data/properties/Bidi_Class/ON/value.dump +0 -0
  384. data/resources/unicode_data/properties/Bidi_Class/PDF/value.dump +3 -0
  385. data/resources/unicode_data/properties/Bidi_Class/PDI/value.dump +3 -0
  386. data/resources/unicode_data/properties/Bidi_Class/R/value.dump +0 -0
  387. data/resources/unicode_data/properties/Bidi_Class/RLE/value.dump +3 -0
  388. data/resources/unicode_data/properties/Bidi_Class/RLI/value.dump +3 -0
  389. data/resources/unicode_data/properties/Bidi_Class/RLO/value.dump +3 -0
  390. data/resources/unicode_data/properties/Bidi_Class/S/value.dump +5 -0
  391. data/resources/unicode_data/properties/Bidi_Class/WS/value.dump +0 -0
  392. data/resources/unicode_data/properties/Bidi_Control/value.dump +4 -0
  393. data/resources/unicode_data/properties/Bidi_Mirrored/N/value.dump +0 -0
  394. data/resources/unicode_data/properties/Bidi_Mirrored/Y/value.dump +115 -0
  395. data/resources/unicode_data/properties/Block/Aegean Numbers/value.dump +0 -0
  396. data/resources/unicode_data/properties/Block/Alchemical Symbols/value.dump +0 -0
  397. data/resources/unicode_data/properties/Block/Alphabetic Presentation Forms/value.dump +0 -0
  398. data/resources/unicode_data/properties/Block/Ancient Greek Musical Notation/value.dump +0 -0
  399. data/resources/unicode_data/properties/Block/Ancient Greek Numbers/value.dump +3 -0
  400. data/resources/unicode_data/properties/Block/Ancient Symbols/value.dump +3 -0
  401. data/resources/unicode_data/properties/Block/Arabic/value.dump +0 -0
  402. data/resources/unicode_data/properties/Block/Arabic Extended-A/value.dump +3 -0
  403. data/resources/unicode_data/properties/Block/Arabic Mathematical Alphabetic Symbols/value.dump +0 -0
  404. data/resources/unicode_data/properties/Block/Arabic Presentation Forms-A/value.dump +3 -0
  405. data/resources/unicode_data/properties/Block/Arabic Presentation Forms-B/value.dump +3 -0
  406. data/resources/unicode_data/properties/Block/Arabic Supplement/value.dump +3 -0
  407. data/resources/unicode_data/properties/Block/Armenian/value.dump +3 -0
  408. data/resources/unicode_data/properties/Block/Arrows/value.dump +3 -0
  409. data/resources/unicode_data/properties/Block/Avestan/value.dump +0 -0
  410. data/resources/unicode_data/properties/Block/Balinese/value.dump +0 -0
  411. data/resources/unicode_data/properties/Block/Bamum/value.dump +3 -0
  412. data/resources/unicode_data/properties/Block/Bamum Supplement/value.dump +0 -0
  413. data/resources/unicode_data/properties/Block/Basic Latin/value.dump +0 -0
  414. data/resources/unicode_data/properties/Block/Batak/value.dump +3 -0
  415. data/resources/unicode_data/properties/Block/Bengali/value.dump +3 -0
  416. data/resources/unicode_data/properties/Block/Block Elements/value.dump +3 -0
  417. data/resources/unicode_data/properties/Block/Bopomofo/value.dump +0 -0
  418. data/resources/unicode_data/properties/Block/Bopomofo Extended/value.dump +3 -0
  419. data/resources/unicode_data/properties/Block/Box Drawing/value.dump +0 -0
  420. data/resources/unicode_data/properties/Block/Brahmi/value.dump +0 -0
  421. data/resources/unicode_data/properties/Block/Braille Patterns/value.dump +0 -0
  422. data/resources/unicode_data/properties/Block/Buginese/value.dump +0 -0
  423. data/resources/unicode_data/properties/Block/Buhid/value.dump +3 -0
  424. data/resources/unicode_data/properties/Block/Byzantine Musical Symbols/value.dump +0 -0
  425. data/resources/unicode_data/properties/Block/CJK Compatibility/value.dump +0 -0
  426. data/resources/unicode_data/properties/Block/CJK Compatibility Forms/value.dump +3 -0
  427. data/resources/unicode_data/properties/Block/CJK Compatibility Ideographs/value.dump +0 -0
  428. data/resources/unicode_data/properties/Block/CJK Compatibility Ideographs Supplement/value.dump +0 -0
  429. data/resources/unicode_data/properties/Block/CJK Radicals Supplement/value.dump +3 -0
  430. data/resources/unicode_data/properties/Block/CJK Strokes/value.dump +3 -0
  431. Punctuation/value.dump +0 -0
  432. data/resources/unicode_data/properties/Block/CJK Unified Ideographs/value.dump +0 -0
  433. data/resources/unicode_data/properties/Block/CJK Unified Ideographs Extension A/value.dump +0 -0
  434. data/resources/unicode_data/properties/Block/CJK Unified Ideographs Extension B/value.dump +0 -0
  435. data/resources/unicode_data/properties/Block/CJK Unified Ideographs Extension C/value.dump +0 -0
  436. data/resources/unicode_data/properties/Block/CJK Unified Ideographs Extension D/value.dump +3 -0
  437. data/resources/unicode_data/properties/Block/Carian/value.dump +3 -0
  438. data/resources/unicode_data/properties/Block/Chakma/value.dump +0 -0
  439. data/resources/unicode_data/properties/Block/Cham/value.dump +0 -0
  440. data/resources/unicode_data/properties/Block/Cherokee/value.dump +3 -0
  441. data/resources/unicode_data/properties/Block/Combining Diacritical Marks/value.dump +0 -0
  442. data/resources/unicode_data/properties/Block/Combining Diacritical Marks Supplement/value.dump +3 -0
  443. data/resources/unicode_data/properties/Block/Combining Diacritical Marks for Symbols/value.dump +3 -0
  444. data/resources/unicode_data/properties/Block/Combining Half Marks/value.dump +3 -0
  445. data/resources/unicode_data/properties/Block/Common Indic Number Forms/value.dump +3 -0
  446. data/resources/unicode_data/properties/Block/Control Pictures/value.dump +0 -0
  447. data/resources/unicode_data/properties/Block/Coptic/value.dump +3 -0
  448. data/resources/unicode_data/properties/Block/Counting Rod Numerals/value.dump +3 -0
  449. data/resources/unicode_data/properties/Block/Cuneiform/value.dump +0 -0
  450. Punctuation/value.dump +0 -0
  451. data/resources/unicode_data/properties/Block/Currency Symbols/value.dump +3 -0
  452. data/resources/unicode_data/properties/Block/Cypriot Syllabary/value.dump +0 -0
  453. data/resources/unicode_data/properties/Block/Cyrillic/value.dump +0 -0
  454. data/resources/unicode_data/properties/Block/Cyrillic Extended-A/value.dump +3 -0
  455. data/resources/unicode_data/properties/Block/Cyrillic Extended-B/value.dump +3 -0
  456. data/resources/unicode_data/properties/Block/Cyrillic Supplement/value.dump +0 -0
  457. data/resources/unicode_data/properties/Block/Deseret/value.dump +0 -0
  458. data/resources/unicode_data/properties/Block/Devanagari/value.dump +0 -0
  459. data/resources/unicode_data/properties/Block/Devanagari Extended/value.dump +3 -0
  460. data/resources/unicode_data/properties/Block/Dingbats/value.dump +0 -0
  461. data/resources/unicode_data/properties/Block/Domino Tiles/value.dump +3 -0
  462. data/resources/unicode_data/properties/Block/Egyptian Hieroglyphs/value.dump +0 -0
  463. data/resources/unicode_data/properties/Block/Emoticons/value.dump +0 -0
  464. data/resources/unicode_data/properties/Block/Enclosed Alphanumeric Supplement/value.dump +0 -0
  465. data/resources/unicode_data/properties/Block/Enclosed Alphanumerics/value.dump +3 -0
  466. Months/value.dump +0 -0
  467. data/resources/unicode_data/properties/Block/Enclosed Ideographic Supplement/value.dump +0 -0
  468. data/resources/unicode_data/properties/Block/Ethiopic/value.dump +0 -0
  469. data/resources/unicode_data/properties/Block/Ethiopic Extended/value.dump +3 -0
  470. data/resources/unicode_data/properties/Block/Ethiopic Extended-A/value.dump +0 -0
  471. data/resources/unicode_data/properties/Block/Ethiopic Supplement/value.dump +3 -0
  472. data/resources/unicode_data/properties/Block/General Punctuation/value.dump +0 -0
  473. data/resources/unicode_data/properties/Block/Geometric Shapes/value.dump +3 -0
  474. data/resources/unicode_data/properties/Block/Georgian/value.dump +3 -0
  475. data/resources/unicode_data/properties/Block/Georgian Supplement/value.dump +0 -0
  476. data/resources/unicode_data/properties/Block/Glagolitic/value.dump +0 -0
  477. data/resources/unicode_data/properties/Block/Gothic/value.dump +3 -0
  478. data/resources/unicode_data/properties/Block/Greek Extended/value.dump +0 -0
  479. data/resources/unicode_data/properties/Block/Greek and Coptic/value.dump +3 -0
  480. data/resources/unicode_data/properties/Block/Gujarati/value.dump +4 -0
  481. data/resources/unicode_data/properties/Block/Gurmukhi/value.dump +0 -0
  482. Fullwidth Forms/value.dump +0 -0
  483. data/resources/unicode_data/properties/Block/Hangul Compatibility Jamo/value.dump +3 -0
  484. data/resources/unicode_data/properties/Block/Hangul Jamo/value.dump +0 -0
  485. data/resources/unicode_data/properties/Block/Hangul Jamo Extended-A/value.dump +3 -0
  486. data/resources/unicode_data/properties/Block/Hangul Jamo Extended-B/value.dump +3 -0
  487. data/resources/unicode_data/properties/Block/Hangul Syllables/value.dump +0 -0
  488. data/resources/unicode_data/properties/Block/Hanunoo/value.dump +3 -0
  489. data/resources/unicode_data/properties/Block/Hebrew/value.dump +3 -0
  490. data/resources/unicode_data/properties/Block/High Private Use Surrogates/value.dump +3 -0
  491. data/resources/unicode_data/properties/Block/High Surrogates/value.dump +0 -0
  492. data/resources/unicode_data/properties/Block/Hiragana/value.dump +3 -0
  493. data/resources/unicode_data/properties/Block/IPA Extensions/value.dump +3 -0
  494. data/resources/unicode_data/properties/Block/Ideographic Description Characters/value.dump +3 -0
  495. data/resources/unicode_data/properties/Block/Imperial Aramaic/value.dump +3 -0
  496. data/resources/unicode_data/properties/Block/Inscriptional Pahlavi/value.dump +3 -0
  497. data/resources/unicode_data/properties/Block/Inscriptional Parthian/value.dump +3 -0
  498. data/resources/unicode_data/properties/Block/Javanese/value.dump +3 -0
  499. data/resources/unicode_data/properties/Block/Kaithi/value.dump +3 -0
  500. data/resources/unicode_data/properties/Block/Kana Supplement/value.dump +0 -0
  501. data/resources/unicode_data/properties/Block/Kanbun/value.dump +3 -0
  502. data/resources/unicode_data/properties/Block/Kangxi Radicals/value.dump +0 -0
  503. data/resources/unicode_data/properties/Block/Kannada/value.dump +3 -0
  504. data/resources/unicode_data/properties/Block/Katakana/value.dump +3 -0
  505. data/resources/unicode_data/properties/Block/Katakana Phonetic Extensions/value.dump +3 -0
  506. data/resources/unicode_data/properties/Block/Kayah Li/value.dump +0 -0
  507. data/resources/unicode_data/properties/Block/Kharoshthi/value.dump +0 -0
  508. data/resources/unicode_data/properties/Block/Khmer/value.dump +3 -0
  509. data/resources/unicode_data/properties/Block/Khmer Symbols/value.dump +3 -0
  510. data/resources/unicode_data/properties/Block/Lao/value.dump +3 -0
  511. data/resources/unicode_data/properties/Block/Latin Extended Additional/value.dump +0 -0
  512. data/resources/unicode_data/properties/Block/Latin Extended-A/value.dump +0 -0
  513. data/resources/unicode_data/properties/Block/Latin Extended-B/value.dump +3 -0
  514. data/resources/unicode_data/properties/Block/Latin Extended-C/value.dump +3 -0
  515. data/resources/unicode_data/properties/Block/Latin Extended-D/value.dump +3 -0
  516. data/resources/unicode_data/properties/Block/Latin-1 Supplement/value.dump +3 -0
  517. data/resources/unicode_data/properties/Block/Lepcha/value.dump +0 -0
  518. data/resources/unicode_data/properties/Block/Letterlike Symbols/value.dump +0 -0
  519. data/resources/unicode_data/properties/Block/Limbu/value.dump +0 -0
  520. data/resources/unicode_data/properties/Block/Linear B Ideograms/value.dump +0 -0
  521. data/resources/unicode_data/properties/Block/Linear B Syllabary/value.dump +0 -0
  522. data/resources/unicode_data/properties/Block/Lisu/value.dump +3 -0
  523. data/resources/unicode_data/properties/Block/Low Surrogates/value.dump +0 -0
  524. data/resources/unicode_data/properties/Block/Lycian/value.dump +3 -0
  525. data/resources/unicode_data/properties/Block/Lydian/value.dump +3 -0
  526. data/resources/unicode_data/properties/Block/Mahjong Tiles/value.dump +0 -0
  527. data/resources/unicode_data/properties/Block/Malayalam/value.dump +0 -0
  528. data/resources/unicode_data/properties/Block/Mandaic/value.dump +3 -0
  529. data/resources/unicode_data/properties/Block/Mathematical Alphanumeric Symbols/value.dump +0 -0
  530. data/resources/unicode_data/properties/Block/Mathematical Operators/value.dump +0 -0
  531. data/resources/unicode_data/properties/Block/Meetei Mayek/value.dump +3 -0
  532. data/resources/unicode_data/properties/Block/Meetei Mayek Extensions/value.dump +3 -0
  533. data/resources/unicode_data/properties/Block/Meroitic Cursive/value.dump +3 -0
  534. data/resources/unicode_data/properties/Block/Meroitic Hieroglyphs/value.dump +3 -0
  535. data/resources/unicode_data/properties/Block/Miao/value.dump +0 -0
  536. data/resources/unicode_data/properties/Block/Miscellaneous Mathematical Symbols-A/value.dump +3 -0
  537. data/resources/unicode_data/properties/Block/Miscellaneous Mathematical Symbols-B/value.dump +3 -0
  538. data/resources/unicode_data/properties/Block/Miscellaneous Symbols/value.dump +0 -0
  539. data/resources/unicode_data/properties/Block/Miscellaneous Symbols And Pictographs/value.dump +0 -0
  540. Arrows/value.dump +0 -0
  541. data/resources/unicode_data/properties/Block/Miscellaneous Technical/value.dump +0 -0
  542. data/resources/unicode_data/properties/Block/Modifier Tone Letters/value.dump +0 -0
  543. data/resources/unicode_data/properties/Block/Mongolian/value.dump +0 -0
  544. data/resources/unicode_data/properties/Block/Musical Symbols/value.dump +0 -0
  545. data/resources/unicode_data/properties/Block/Myanmar/value.dump +0 -0
  546. data/resources/unicode_data/properties/Block/Myanmar Extended-A/value.dump +3 -0
  547. data/resources/unicode_data/properties/Block/NKo/value.dump +3 -0
  548. data/resources/unicode_data/properties/Block/New Tai Lue/value.dump +3 -0
  549. data/resources/unicode_data/properties/Block/Number Forms/value.dump +3 -0
  550. data/resources/unicode_data/properties/Block/Ogham/value.dump +3 -0
  551. data/resources/unicode_data/properties/Block/Ol Chiki/value.dump +3 -0
  552. data/resources/unicode_data/properties/Block/Old Italic/value.dump +0 -0
  553. data/resources/unicode_data/properties/Block/Old Persian/value.dump +3 -0
  554. data/resources/unicode_data/properties/Block/Old South Arabian/value.dump +5 -0
  555. data/resources/unicode_data/properties/Block/Old Turkic/value.dump +0 -0
  556. data/resources/unicode_data/properties/Block/Optical Character Recognition/value.dump +3 -0
  557. data/resources/unicode_data/properties/Block/Oriya/value.dump +0 -0
  558. data/resources/unicode_data/properties/Block/Osmanya/value.dump +3 -0
  559. data/resources/unicode_data/properties/Block/Phags-pa/value.dump +3 -0
  560. data/resources/unicode_data/properties/Block/Phaistos Disc/value.dump +3 -0
  561. data/resources/unicode_data/properties/Block/Phoenician/value.dump +0 -0
  562. data/resources/unicode_data/properties/Block/Phonetic Extensions/value.dump +0 -0
  563. data/resources/unicode_data/properties/Block/Phonetic Extensions Supplement/value.dump +3 -0
  564. data/resources/unicode_data/properties/Block/Playing Cards/value.dump +3 -0
  565. data/resources/unicode_data/properties/Block/Private Use Area/value.dump +0 -0
  566. data/resources/unicode_data/properties/Block/Rejang/value.dump +3 -0
  567. data/resources/unicode_data/properties/Block/Rumi Numeral Symbols/value.dump +3 -0
  568. data/resources/unicode_data/properties/Block/Runic/value.dump +3 -0
  569. data/resources/unicode_data/properties/Block/Samaritan/value.dump +0 -0
  570. data/resources/unicode_data/properties/Block/Saurashtra/value.dump +3 -0
  571. data/resources/unicode_data/properties/Block/Sharada/value.dump +3 -0
  572. data/resources/unicode_data/properties/Block/Shavian/value.dump +3 -0
  573. data/resources/unicode_data/properties/Block/Sinhala/value.dump +3 -0
  574. data/resources/unicode_data/properties/Block/Small Form Variants/value.dump +3 -0
  575. data/resources/unicode_data/properties/Block/Sora Sompeng/value.dump +3 -0
  576. data/resources/unicode_data/properties/Block/Spacing Modifier Letters/value.dump +3 -0
  577. data/resources/unicode_data/properties/Block/Specials/value.dump +3 -0
  578. data/resources/unicode_data/properties/Block/Sundanese/value.dump +3 -0
  579. data/resources/unicode_data/properties/Block/Sundanese Supplement/value.dump +3 -0
  580. data/resources/unicode_data/properties/Block/Superscripts and Subscripts/value.dump +3 -0
  581. data/resources/unicode_data/properties/Block/Supplemental Arrows-A/value.dump +3 -0
  582. data/resources/unicode_data/properties/Block/Supplemental Arrows-B/value.dump +0 -0
  583. data/resources/unicode_data/properties/Block/Supplemental Mathematical Operators/value.dump +0 -0
  584. data/resources/unicode_data/properties/Block/Supplemental Punctuation/value.dump +0 -0
  585. data/resources/unicode_data/properties/Block/Supplementary Private Use Area-A/value.dump +0 -0
  586. data/resources/unicode_data/properties/Block/Supplementary Private Use Area-B/value.dump +0 -0
  587. data/resources/unicode_data/properties/Block/Syloti Nagri/value.dump +0 -0
  588. data/resources/unicode_data/properties/Block/Syriac/value.dump +0 -0
  589. data/resources/unicode_data/properties/Block/Tagalog/value.dump +0 -0
  590. data/resources/unicode_data/properties/Block/Tagbanwa/value.dump +3 -0
  591. data/resources/unicode_data/properties/Block/Tags/value.dump +0 -0
  592. data/resources/unicode_data/properties/Block/Tai Le/value.dump +3 -0
  593. data/resources/unicode_data/properties/Block/Tai Tham/value.dump +3 -0
  594. data/resources/unicode_data/properties/Block/Tai Viet/value.dump +3 -0
  595. data/resources/unicode_data/properties/Block/Tai Xuan Jing Symbols/value.dump +0 -0
  596. data/resources/unicode_data/properties/Block/Takri/value.dump +3 -0
  597. data/resources/unicode_data/properties/Block/Tamil/value.dump +3 -0
  598. data/resources/unicode_data/properties/Block/Telugu/value.dump +0 -0
  599. data/resources/unicode_data/properties/Block/Thaana/value.dump +3 -0
  600. data/resources/unicode_data/properties/Block/Thai/value.dump +0 -0
  601. data/resources/unicode_data/properties/Block/Tibetan/value.dump +0 -0
  602. data/resources/unicode_data/properties/Block/Tifinagh/value.dump +3 -0
  603. data/resources/unicode_data/properties/Block/Transport And Map Symbols/value.dump +3 -0
  604. data/resources/unicode_data/properties/Block/Ugaritic/value.dump +3 -0
  605. data/resources/unicode_data/properties/Block/Unified Canadian Aboriginal Syllabics/value.dump +0 -0
  606. data/resources/unicode_data/properties/Block/Unified Canadian Aboriginal Syllabics Extended/value.dump +3 -0
  607. data/resources/unicode_data/properties/Block/Vai/value.dump +0 -0
  608. data/resources/unicode_data/properties/Block/Variation Selectors/value.dump +0 -0
  609. data/resources/unicode_data/properties/Block/Variation Selectors Supplement/value.dump +0 -0
  610. data/resources/unicode_data/properties/Block/Vedic Extensions/value.dump +3 -0
  611. data/resources/unicode_data/properties/Block/Vertical Forms/value.dump +3 -0
  612. data/resources/unicode_data/properties/Block/Yi Radicals/value.dump +3 -0
  613. data/resources/unicode_data/properties/Block/Yi Syllables/value.dump +0 -0
  614. data/resources/unicode_data/properties/Block/Yijing Hexagram Symbols/value.dump +3 -0
  615. data/resources/unicode_data/properties/Canonical_Combining_Class/0/value.dump +0 -0
  616. data/resources/unicode_data/properties/Canonical_Combining_Class/1/value.dump +13 -0
  617. data/resources/unicode_data/properties/Canonical_Combining_Class/10/value.dump +3 -0
  618. data/resources/unicode_data/properties/Canonical_Combining_Class/103/value.dump +3 -0
  619. data/resources/unicode_data/properties/Canonical_Combining_Class/107/value.dump +3 -0
  620. data/resources/unicode_data/properties/Canonical_Combining_Class/11/value.dump +3 -0
  621. data/resources/unicode_data/properties/Canonical_Combining_Class/118/value.dump +3 -0
  622. data/resources/unicode_data/properties/Canonical_Combining_Class/12/value.dump +3 -0
  623. data/resources/unicode_data/properties/Canonical_Combining_Class/122/value.dump +3 -0
  624. data/resources/unicode_data/properties/Canonical_Combining_Class/129/value.dump +3 -0
  625. data/resources/unicode_data/properties/Canonical_Combining_Class/13/value.dump +3 -0
  626. data/resources/unicode_data/properties/Canonical_Combining_Class/130/value.dump +5 -0
  627. data/resources/unicode_data/properties/Canonical_Combining_Class/132/value.dump +3 -0
  628. data/resources/unicode_data/properties/Canonical_Combining_Class/14/value.dump +3 -0
  629. data/resources/unicode_data/properties/Canonical_Combining_Class/15/value.dump +3 -0
  630. data/resources/unicode_data/properties/Canonical_Combining_Class/16/value.dump +3 -0
  631. data/resources/unicode_data/properties/Canonical_Combining_Class/17/value.dump +3 -0
  632. data/resources/unicode_data/properties/Canonical_Combining_Class/18/value.dump +4 -0
  633. data/resources/unicode_data/properties/Canonical_Combining_Class/19/value.dump +3 -0
  634. data/resources/unicode_data/properties/Canonical_Combining_Class/20/value.dump +3 -0
  635. data/resources/unicode_data/properties/Canonical_Combining_Class/202/value.dump +5 -0
  636. data/resources/unicode_data/properties/Canonical_Combining_Class/21/value.dump +3 -0
  637. data/resources/unicode_data/properties/Canonical_Combining_Class/214/value.dump +3 -0
  638. data/resources/unicode_data/properties/Canonical_Combining_Class/216/value.dump +6 -0
  639. data/resources/unicode_data/properties/Canonical_Combining_Class/218/value.dump +3 -0
  640. data/resources/unicode_data/properties/Canonical_Combining_Class/22/value.dump +3 -0
  641. data/resources/unicode_data/properties/Canonical_Combining_Class/220/value.dump +70 -0
  642. data/resources/unicode_data/properties/Canonical_Combining_Class/222/value.dump +6 -0
  643. data/resources/unicode_data/properties/Canonical_Combining_Class/224/value.dump +3 -0
  644. data/resources/unicode_data/properties/Canonical_Combining_Class/226/value.dump +3 -0
  645. data/resources/unicode_data/properties/Canonical_Combining_Class/228/value.dump +5 -0
  646. data/resources/unicode_data/properties/Canonical_Combining_Class/23/value.dump +3 -0
  647. data/resources/unicode_data/properties/Canonical_Combining_Class/230/value.dump +0 -0
  648. data/resources/unicode_data/properties/Canonical_Combining_Class/232/value.dump +6 -0
  649. data/resources/unicode_data/properties/Canonical_Combining_Class/233/value.dump +6 -0
  650. data/resources/unicode_data/properties/Canonical_Combining_Class/234/value.dump +5 -0
  651. data/resources/unicode_data/properties/Canonical_Combining_Class/24/value.dump +3 -0
  652. data/resources/unicode_data/properties/Canonical_Combining_Class/240/value.dump +3 -0
  653. data/resources/unicode_data/properties/Canonical_Combining_Class/25/value.dump +3 -0
  654. data/resources/unicode_data/properties/Canonical_Combining_Class/26/value.dump +3 -0
  655. data/resources/unicode_data/properties/Canonical_Combining_Class/27/value.dump +4 -0
  656. data/resources/unicode_data/properties/Canonical_Combining_Class/28/value.dump +4 -0
  657. data/resources/unicode_data/properties/Canonical_Combining_Class/29/value.dump +4 -0
  658. data/resources/unicode_data/properties/Canonical_Combining_Class/30/value.dump +4 -0
  659. data/resources/unicode_data/properties/Canonical_Combining_Class/31/value.dump +4 -0
  660. data/resources/unicode_data/properties/Canonical_Combining_Class/32/value.dump +4 -0
  661. data/resources/unicode_data/properties/Canonical_Combining_Class/33/value.dump +3 -0
  662. data/resources/unicode_data/properties/Canonical_Combining_Class/34/value.dump +3 -0
  663. data/resources/unicode_data/properties/Canonical_Combining_Class/35/value.dump +3 -0
  664. data/resources/unicode_data/properties/Canonical_Combining_Class/36/value.dump +3 -0
  665. data/resources/unicode_data/properties/Canonical_Combining_Class/7/value.dump +19 -0
  666. data/resources/unicode_data/properties/Canonical_Combining_Class/8/value.dump +3 -0
  667. data/resources/unicode_data/properties/Canonical_Combining_Class/84/value.dump +3 -0
  668. data/resources/unicode_data/properties/Canonical_Combining_Class/9/value.dump +41 -0
  669. data/resources/unicode_data/properties/Canonical_Combining_Class/91/value.dump +3 -0
  670. data/resources/unicode_data/properties/Case_Ignorable/value.dump +0 -0
  671. data/resources/unicode_data/properties/Cased/value.dump +0 -0
  672. data/resources/unicode_data/properties/Changes_When_Casefolded/value.dump +0 -0
  673. data/resources/unicode_data/properties/Changes_When_Casemapped/value.dump +0 -0
  674. data/resources/unicode_data/properties/Changes_When_Lowercased/value.dump +0 -0
  675. data/resources/unicode_data/properties/Changes_When_Titlecased/value.dump +589 -0
  676. data/resources/unicode_data/properties/Changes_When_Uppercased/value.dump +588 -0
  677. data/resources/unicode_data/properties/Dash/value.dump +0 -0
  678. data/resources/unicode_data/properties/Default_Ignorable_Code_Point/value.dump +0 -0
  679. data/resources/unicode_data/properties/Deprecated/value.dump +0 -0
  680. data/resources/unicode_data/properties/Diacritic/value.dump +135 -0
  681. data/resources/unicode_data/properties/East_Asian_Width/A/value.dump +0 -0
  682. data/resources/unicode_data/properties/East_Asian_Width/F/value.dump +0 -0
  683. data/resources/unicode_data/properties/East_Asian_Width/H/value.dump +9 -0
  684. data/resources/unicode_data/properties/East_Asian_Width/N/value.dump +0 -0
  685. data/resources/unicode_data/properties/East_Asian_Width/Na/value.dump +9 -0
  686. data/resources/unicode_data/properties/East_Asian_Width/W/value.dump +0 -0
  687. data/resources/unicode_data/properties/Extender/value.dump +26 -0
  688. data/resources/unicode_data/properties/General_Category/C/c/value.dump +0 -0
  689. data/resources/unicode_data/properties/General_Category/C/f/value.dump +0 -0
  690. data/resources/unicode_data/properties/General_Category/C/o/value.dump +0 -0
  691. data/resources/unicode_data/properties/General_Category/C/s/value.dump +0 -0
  692. data/resources/unicode_data/properties/General_Category/L/l/value.dump +0 -0
  693. data/resources/unicode_data/properties/General_Category/L/m/value.dump +54 -0
  694. data/resources/unicode_data/properties/General_Category/L/o/value.dump +0 -0
  695. data/resources/unicode_data/properties/General_Category/L/t/value.dump +12 -0
  696. data/resources/unicode_data/properties/General_Category/L/u/value.dump +0 -0
  697. data/resources/unicode_data/properties/General_Category/M/c/value.dump +0 -0
  698. data/resources/unicode_data/properties/General_Category/M/e/value.dump +6 -0
  699. data/resources/unicode_data/properties/General_Category/M/n/value.dump +0 -0
  700. data/resources/unicode_data/properties/General_Category/N/d/value.dump +0 -0
  701. data/resources/unicode_data/properties/General_Category/N/l/value.dump +0 -0
  702. data/resources/unicode_data/properties/General_Category/N/o/value.dump +0 -0
  703. data/resources/unicode_data/properties/General_Category/P/c/value.dump +8 -0
  704. data/resources/unicode_data/properties/General_Category/P/d/value.dump +0 -0
  705. data/resources/unicode_data/properties/General_Category/P/e/value.dump +72 -0
  706. data/resources/unicode_data/properties/General_Category/P/f/value.dump +14 -0
  707. data/resources/unicode_data/properties/General_Category/P/i/value.dump +13 -0
  708. data/resources/unicode_data/properties/General_Category/P/o/value.dump +0 -0
  709. data/resources/unicode_data/properties/General_Category/P/s/value.dump +76 -0
  710. data/resources/unicode_data/properties/General_Category/S/c/value.dump +21 -0
  711. data/resources/unicode_data/properties/General_Category/S/k/value.dump +0 -0
  712. data/resources/unicode_data/properties/General_Category/S/m/value.dump +0 -0
  713. data/resources/unicode_data/properties/General_Category/S/o/value.dump +0 -0
  714. data/resources/unicode_data/properties/General_Category/Z/l/value.dump +3 -0
  715. data/resources/unicode_data/properties/General_Category/Z/p/value.dump +3 -0
  716. data/resources/unicode_data/properties/General_Category/Z/s/value.dump +0 -0
  717. data/resources/unicode_data/properties/Grapheme_Base/value.dump +0 -0
  718. data/resources/unicode_data/properties/Grapheme_Cluster_Break/CR/value.dump +3 -0
  719. data/resources/unicode_data/properties/Grapheme_Cluster_Break/Control/value.dump +0 -0
  720. data/resources/unicode_data/properties/Grapheme_Cluster_Break/Extend/value.dump +0 -0
  721. data/resources/unicode_data/properties/Grapheme_Cluster_Break/L/value.dump +0 -0
  722. data/resources/unicode_data/properties/Grapheme_Cluster_Break/LF/value.dump +3 -0
  723. data/resources/unicode_data/properties/Grapheme_Cluster_Break/LV/value.dump +0 -0
  724. data/resources/unicode_data/properties/Grapheme_Cluster_Break/LVT/value.dump +401 -0
  725. data/resources/unicode_data/properties/Grapheme_Cluster_Break/Regional_Indicator/value.dump +3 -0
  726. data/resources/unicode_data/properties/Grapheme_Cluster_Break/SpacingMark/value.dump +0 -0
  727. data/resources/unicode_data/properties/Grapheme_Cluster_Break/T/value.dump +4 -0
  728. data/resources/unicode_data/properties/Grapheme_Cluster_Break/V/value.dump +4 -0
  729. data/resources/unicode_data/properties/Grapheme_Extend/value.dump +0 -0
  730. data/resources/unicode_data/properties/Grapheme_Link/value.dump +41 -0
  731. data/resources/unicode_data/properties/Hangul_Syllable_Type/L/value.dump +0 -0
  732. data/resources/unicode_data/properties/Hangul_Syllable_Type/LV/value.dump +0 -0
  733. data/resources/unicode_data/properties/Hangul_Syllable_Type/LVT/value.dump +401 -0
  734. data/resources/unicode_data/properties/Hangul_Syllable_Type/T/value.dump +4 -0
  735. data/resources/unicode_data/properties/Hangul_Syllable_Type/V/value.dump +4 -0
  736. data/resources/unicode_data/properties/Hex_Digit/value.dump +8 -0
  737. data/resources/unicode_data/properties/Hyphen/value.dump +12 -0
  738. data/resources/unicode_data/properties/IDS_Binary_Operator/value.dump +4 -0
  739. data/resources/unicode_data/properties/IDS_Trinary_Operator/value.dump +3 -0
  740. data/resources/unicode_data/properties/ID_Continue/value.dump +0 -0
  741. data/resources/unicode_data/properties/ID_Start/value.dump +0 -0
  742. data/resources/unicode_data/properties/Ideographic/value.dump +0 -0
  743. data/resources/unicode_data/properties/Indic_Positional_Category/Bottom/value.dump +78 -0
  744. data/resources/unicode_data/properties/Indic_Positional_Category/Bottom_And_Right/value.dump +4 -0
  745. data/resources/unicode_data/properties/Indic_Positional_Category/Invisible/value.dump +10 -0
  746. data/resources/unicode_data/properties/Indic_Positional_Category/Left/value.dump +36 -0
  747. data/resources/unicode_data/properties/Indic_Positional_Category/Left_And_Right/value.dump +10 -0
  748. data/resources/unicode_data/properties/Indic_Positional_Category/Overstruck/value.dump +8 -0
  749. data/resources/unicode_data/properties/Indic_Positional_Category/Right/value.dump +86 -0
  750. data/resources/unicode_data/properties/Indic_Positional_Category/Top/value.dump +91 -0
  751. data/resources/unicode_data/properties/Indic_Positional_Category/Top_And_Bottom/value.dump +8 -0
  752. data/resources/unicode_data/properties/Indic_Positional_Category/Top_And_Bottom_And_Right/value.dump +3 -0
  753. data/resources/unicode_data/properties/Indic_Positional_Category/Top_And_Left/value.dump +6 -0
  754. data/resources/unicode_data/properties/Indic_Positional_Category/Top_And_Left_And_Right/value.dump +4 -0
  755. data/resources/unicode_data/properties/Indic_Positional_Category/Top_And_Right/value.dump +12 -0
  756. data/resources/unicode_data/properties/Indic_Positional_Category/Visual_Order_Left/value.dump +8 -0
  757. data/resources/unicode_data/properties/Indic_Syllabic_Category/Avagraha/value.dump +15 -0
  758. data/resources/unicode_data/properties/Indic_Syllabic_Category/Bindu/value.dump +0 -0
  759. data/resources/unicode_data/properties/Indic_Syllabic_Category/Consonant/value.dump +0 -0
  760. data/resources/unicode_data/properties/Indic_Syllabic_Category/Consonant_Dead/value.dump +4 -0
  761. data/resources/unicode_data/properties/Indic_Syllabic_Category/Consonant_Final/value.dump +13 -0
  762. data/resources/unicode_data/properties/Indic_Syllabic_Category/Consonant_Head_Letter/value.dump +3 -0
  763. data/resources/unicode_data/properties/Indic_Syllabic_Category/Consonant_Medial/value.dump +12 -0
  764. data/resources/unicode_data/properties/Indic_Syllabic_Category/Consonant_Placeholder/value.dump +0 -0
  765. data/resources/unicode_data/properties/Indic_Syllabic_Category/Consonant_Repha/value.dump +8 -0
  766. data/resources/unicode_data/properties/Indic_Syllabic_Category/Consonant_Subjoined/value.dump +11 -0
  767. data/resources/unicode_data/properties/Indic_Syllabic_Category/Modifying_Letter/value.dump +3 -0
  768. data/resources/unicode_data/properties/Indic_Syllabic_Category/Nukta/value.dump +18 -0
  769. data/resources/unicode_data/properties/Indic_Syllabic_Category/Register_Shifter/value.dump +3 -0
  770. data/resources/unicode_data/properties/Indic_Syllabic_Category/Tone_Letter/value.dump +5 -0
  771. data/resources/unicode_data/properties/Indic_Syllabic_Category/Tone_Mark/value.dump +17 -0
  772. data/resources/unicode_data/properties/Indic_Syllabic_Category/Virama/value.dump +41 -0
  773. data/resources/unicode_data/properties/Indic_Syllabic_Category/Visarga/value.dump +32 -0
  774. data/resources/unicode_data/properties/Indic_Syllabic_Category/Vowel/value.dump +6 -0
  775. data/resources/unicode_data/properties/Indic_Syllabic_Category/Vowel_Dependent/value.dump +112 -0
  776. data/resources/unicode_data/properties/Indic_Syllabic_Category/Vowel_Independent/value.dump +0 -0
  777. data/resources/unicode_data/properties/Jamo_Short_Name/A/value.dump +3 -0
  778. data/resources/unicode_data/properties/Jamo_Short_Name/AE/value.dump +3 -0
  779. data/resources/unicode_data/properties/Jamo_Short_Name/B/value.dump +4 -0
  780. data/resources/unicode_data/properties/Jamo_Short_Name/BB/value.dump +3 -0
  781. data/resources/unicode_data/properties/Jamo_Short_Name/BS/value.dump +3 -0
  782. data/resources/unicode_data/properties/Jamo_Short_Name/C/value.dump +4 -0
  783. data/resources/unicode_data/properties/Jamo_Short_Name/D/value.dump +4 -0
  784. data/resources/unicode_data/properties/Jamo_Short_Name/DD/value.dump +3 -0
  785. data/resources/unicode_data/properties/Jamo_Short_Name/E/value.dump +3 -0
  786. data/resources/unicode_data/properties/Jamo_Short_Name/EO/value.dump +3 -0
  787. data/resources/unicode_data/properties/Jamo_Short_Name/EU/value.dump +3 -0
  788. data/resources/unicode_data/properties/Jamo_Short_Name/G/value.dump +0 -0
  789. data/resources/unicode_data/properties/Jamo_Short_Name/GG/value.dump +4 -0
  790. data/resources/unicode_data/properties/Jamo_Short_Name/GS/value.dump +3 -0
  791. data/resources/unicode_data/properties/Jamo_Short_Name/H/value.dump +4 -0
  792. data/resources/unicode_data/properties/Jamo_Short_Name/I/value.dump +3 -0
  793. data/resources/unicode_data/properties/Jamo_Short_Name/J/value.dump +4 -0
  794. data/resources/unicode_data/properties/Jamo_Short_Name/JJ/value.dump +3 -0
  795. data/resources/unicode_data/properties/Jamo_Short_Name/K/value.dump +4 -0
  796. data/resources/unicode_data/properties/Jamo_Short_Name/L/value.dump +3 -0
  797. data/resources/unicode_data/properties/Jamo_Short_Name/LB/value.dump +3 -0
  798. data/resources/unicode_data/properties/Jamo_Short_Name/LG/value.dump +3 -0
  799. data/resources/unicode_data/properties/Jamo_Short_Name/LH/value.dump +3 -0
  800. data/resources/unicode_data/properties/Jamo_Short_Name/LM/value.dump +3 -0
  801. data/resources/unicode_data/properties/Jamo_Short_Name/LP/value.dump +3 -0
  802. data/resources/unicode_data/properties/Jamo_Short_Name/LS/value.dump +3 -0
  803. data/resources/unicode_data/properties/Jamo_Short_Name/LT/value.dump +3 -0
  804. data/resources/unicode_data/properties/Jamo_Short_Name/M/value.dump +4 -0
  805. data/resources/unicode_data/properties/Jamo_Short_Name/N/value.dump +4 -0
  806. data/resources/unicode_data/properties/Jamo_Short_Name/NG/value.dump +3 -0
  807. data/resources/unicode_data/properties/Jamo_Short_Name/NH/value.dump +3 -0
  808. data/resources/unicode_data/properties/Jamo_Short_Name/NJ/value.dump +3 -0
  809. data/resources/unicode_data/properties/Jamo_Short_Name/O/value.dump +3 -0
  810. data/resources/unicode_data/properties/Jamo_Short_Name/OE/value.dump +3 -0
  811. data/resources/unicode_data/properties/Jamo_Short_Name/P/value.dump +4 -0
  812. data/resources/unicode_data/properties/Jamo_Short_Name/R/value.dump +3 -0
  813. data/resources/unicode_data/properties/Jamo_Short_Name/S/value.dump +4 -0
  814. data/resources/unicode_data/properties/Jamo_Short_Name/SS/value.dump +6 -0
  815. data/resources/unicode_data/properties/Jamo_Short_Name/T/value.dump +4 -0
  816. data/resources/unicode_data/properties/Jamo_Short_Name/U/value.dump +3 -0
  817. data/resources/unicode_data/properties/Jamo_Short_Name/WA/value.dump +3 -0
  818. data/resources/unicode_data/properties/Jamo_Short_Name/WAE/value.dump +3 -0
  819. data/resources/unicode_data/properties/Jamo_Short_Name/WE/value.dump +3 -0
  820. data/resources/unicode_data/properties/Jamo_Short_Name/WEO/value.dump +3 -0
  821. data/resources/unicode_data/properties/Jamo_Short_Name/WI/value.dump +3 -0
  822. data/resources/unicode_data/properties/Jamo_Short_Name/YA/value.dump +3 -0
  823. data/resources/unicode_data/properties/Jamo_Short_Name/YAE/value.dump +3 -0
  824. data/resources/unicode_data/properties/Jamo_Short_Name/YE/value.dump +3 -0
  825. data/resources/unicode_data/properties/Jamo_Short_Name/YEO/value.dump +3 -0
  826. data/resources/unicode_data/properties/Jamo_Short_Name/YI/value.dump +3 -0
  827. data/resources/unicode_data/properties/Jamo_Short_Name/YO/value.dump +3 -0
  828. data/resources/unicode_data/properties/Jamo_Short_Name/YU/value.dump +3 -0
  829. data/resources/unicode_data/properties/Jamo_Short_Name/value.dump +3 -0
  830. data/resources/unicode_data/properties/Join_Control/value.dump +3 -0
  831. data/resources/unicode_data/properties/Line_Break/AI/value.dump +0 -0
  832. data/resources/unicode_data/properties/Line_Break/AL/value.dump +0 -0
  833. data/resources/unicode_data/properties/Line_Break/B2/value.dump +4 -0
  834. data/resources/unicode_data/properties/Line_Break/BA/value.dump +0 -0
  835. data/resources/unicode_data/properties/Line_Break/BB/value.dump +15 -0
  836. data/resources/unicode_data/properties/Line_Break/BK/value.dump +4 -0
  837. data/resources/unicode_data/properties/Line_Break/CB/value.dump +3 -0
  838. data/resources/unicode_data/properties/Line_Break/CJ/value.dump +27 -0
  839. data/resources/unicode_data/properties/Line_Break/CL/value.dump +81 -0
  840. data/resources/unicode_data/properties/Line_Break/CM/value.dump +0 -0
  841. data/resources/unicode_data/properties/Line_Break/CP/value.dump +4 -0
  842. data/resources/unicode_data/properties/Line_Break/CR/value.dump +3 -0
  843. data/resources/unicode_data/properties/Line_Break/EX/value.dump +24 -0
  844. data/resources/unicode_data/properties/Line_Break/GL/value.dump +13 -0
  845. data/resources/unicode_data/properties/Line_Break/H2/value.dump +0 -0
  846. data/resources/unicode_data/properties/Line_Break/H3/value.dump +401 -0
  847. data/resources/unicode_data/properties/Line_Break/HL/value.dump +12 -0
  848. data/resources/unicode_data/properties/Line_Break/HY/value.dump +3 -0
  849. data/resources/unicode_data/properties/Line_Break/ID/value.dump +0 -0
  850. data/resources/unicode_data/properties/Line_Break/IN/value.dump +4 -0
  851. data/resources/unicode_data/properties/Line_Break/IS/value.dump +12 -0
  852. data/resources/unicode_data/properties/Line_Break/JL/value.dump +0 -0
  853. data/resources/unicode_data/properties/Line_Break/JT/value.dump +4 -0
  854. data/resources/unicode_data/properties/Line_Break/JV/value.dump +4 -0
  855. data/resources/unicode_data/properties/Line_Break/LF/value.dump +3 -0
  856. data/resources/unicode_data/properties/Line_Break/NL/value.dump +3 -0
  857. data/resources/unicode_data/properties/Line_Break/NS/value.dump +17 -0
  858. data/resources/unicode_data/properties/Line_Break/NU/value.dump +0 -0
  859. data/resources/unicode_data/properties/Line_Break/OP/value.dump +83 -0
  860. data/resources/unicode_data/properties/Line_Break/PO/value.dump +20 -0
  861. data/resources/unicode_data/properties/Line_Break/PR/value.dump +24 -0
  862. data/resources/unicode_data/properties/Line_Break/QU/value.dump +0 -0
  863. data/resources/unicode_data/properties/Line_Break/RI/value.dump +3 -0
  864. data/resources/unicode_data/properties/Line_Break/SA/value.dump +0 -0
  865. data/resources/unicode_data/properties/Line_Break/SG/value.dump +0 -0
  866. data/resources/unicode_data/properties/Line_Break/SP/value.dump +3 -0
  867. data/resources/unicode_data/properties/Line_Break/SY/value.dump +3 -0
  868. data/resources/unicode_data/properties/Line_Break/WJ/value.dump +4 -0
  869. data/resources/unicode_data/properties/Line_Break/XX/value.dump +0 -0
  870. data/resources/unicode_data/properties/Line_Break/ZW/value.dump +3 -0
  871. data/resources/unicode_data/properties/Logical_Order_Exception/value.dump +8 -0
  872. data/resources/unicode_data/properties/Lowercase/value.dump +0 -0
  873. data/resources/unicode_data/properties/Math/value.dump +0 -0
  874. data/resources/unicode_data/properties/Noncharacter_Code_Point/value.dump +22 -0
  875. data/resources/unicode_data/properties/Numeric_Type/0/value.dump +0 -0
  876. data/resources/unicode_data/properties/Numeric_Type/1/value.dump +69 -0
  877. data/resources/unicode_data/properties/Numeric_Type/2/value.dump +68 -0
  878. data/resources/unicode_data/properties/Numeric_Type/3/value.dump +68 -0
  879. data/resources/unicode_data/properties/Numeric_Type/4/value.dump +68 -0
  880. data/resources/unicode_data/properties/Numeric_Type/5/value.dump +65 -0
  881. data/resources/unicode_data/properties/Numeric_Type/6/value.dump +65 -0
  882. data/resources/unicode_data/properties/Numeric_Type/7/value.dump +65 -0
  883. data/resources/unicode_data/properties/Numeric_Type/8/value.dump +65 -0
  884. data/resources/unicode_data/properties/Numeric_Type/9/value.dump +67 -0
  885. data/resources/unicode_data/properties/Numeric_Type/value.dump +0 -0
  886. data/resources/unicode_data/properties/Other_Alphabetic/value.dump +0 -0
  887. data/resources/unicode_data/properties/Other_Default_Ignorable_Code_Point/value.dump +0 -0
  888. data/resources/unicode_data/properties/Other_Grapheme_Extend/value.dump +19 -0
  889. data/resources/unicode_data/properties/Other_ID_Continue/value.dump +6 -0
  890. data/resources/unicode_data/properties/Other_ID_Start/value.dump +5 -0
  891. data/resources/unicode_data/properties/Other_Lowercase/value.dump +20 -0
  892. data/resources/unicode_data/properties/Other_Math/value.dump +0 -0
  893. data/resources/unicode_data/properties/Other_Uppercase/value.dump +4 -0
  894. data/resources/unicode_data/properties/Pattern_Syntax/value.dump +0 -0
  895. data/resources/unicode_data/properties/Pattern_White_Space/value.dump +8 -0
  896. data/resources/unicode_data/properties/Quotation_Mark/value.dump +14 -0
  897. data/resources/unicode_data/properties/Radical/value.dump +0 -0
  898. data/resources/unicode_data/properties/STerm/value.dump +0 -0
  899. data/resources/unicode_data/properties/Script/Arabic/value.dump +0 -0
  900. data/resources/unicode_data/properties/Script/Armenian/value.dump +8 -0
  901. data/resources/unicode_data/properties/Script/Avestan/value.dump +0 -0
  902. data/resources/unicode_data/properties/Script/Balinese/value.dump +0 -0
  903. data/resources/unicode_data/properties/Script/Bamum/value.dump +0 -0
  904. data/resources/unicode_data/properties/Script/Batak/value.dump +4 -0
  905. data/resources/unicode_data/properties/Script/Bengali/value.dump +16 -0
  906. data/resources/unicode_data/properties/Script/Bopomofo/value.dump +5 -0
  907. data/resources/unicode_data/properties/Script/Brahmi/value.dump +0 -0
  908. data/resources/unicode_data/properties/Script/Braille/value.dump +0 -0
  909. data/resources/unicode_data/properties/Script/Buginese/value.dump +0 -0
  910. data/resources/unicode_data/properties/Script/Buhid/value.dump +3 -0
  911. data/resources/unicode_data/properties/Script/Canadian_Aboriginal/value.dump +0 -0
  912. data/resources/unicode_data/properties/Script/Carian/value.dump +3 -0
  913. data/resources/unicode_data/properties/Script/Chakma/value.dump +0 -0
  914. data/resources/unicode_data/properties/Script/Cham/value.dump +0 -0
  915. data/resources/unicode_data/properties/Script/Cherokee/value.dump +3 -0
  916. data/resources/unicode_data/properties/Script/Common/value.dump +0 -0
  917. data/resources/unicode_data/properties/Script/Coptic/value.dump +5 -0
  918. data/resources/unicode_data/properties/Script/Cuneiform/value.dump +0 -0
  919. data/resources/unicode_data/properties/Script/Cypriot/value.dump +0 -0
  920. data/resources/unicode_data/properties/Script/Cyrillic/value.dump +0 -0
  921. data/resources/unicode_data/properties/Script/Deseret/value.dump +0 -0
  922. data/resources/unicode_data/properties/Script/Devanagari/value.dump +0 -0
  923. data/resources/unicode_data/properties/Script/Egyptian_Hieroglyphs/value.dump +0 -0
  924. data/resources/unicode_data/properties/Script/Ethiopic/value.dump +0 -0
  925. data/resources/unicode_data/properties/Script/Georgian/value.dump +0 -0
  926. data/resources/unicode_data/properties/Script/Glagolitic/value.dump +0 -0
  927. data/resources/unicode_data/properties/Script/Gothic/value.dump +3 -0
  928. data/resources/unicode_data/properties/Script/Greek/value.dump +0 -0
  929. data/resources/unicode_data/properties/Script/Gujarati/value.dump +40 -0
  930. data/resources/unicode_data/properties/Script/Gurmukhi/value.dump +50 -0
  931. data/resources/unicode_data/properties/Script/Han/value.dump +0 -0
  932. data/resources/unicode_data/properties/Script/Hangul/value.dump +0 -0
  933. data/resources/unicode_data/properties/Script/Hanunoo/value.dump +3 -0
  934. data/resources/unicode_data/properties/Script/Hebrew/value.dump +11 -0
  935. data/resources/unicode_data/properties/Script/Hiragana/value.dump +0 -0
  936. data/resources/unicode_data/properties/Script/Imperial_Aramaic/value.dump +4 -0
  937. data/resources/unicode_data/properties/Script/Inherited/value.dump +0 -0
  938. data/resources/unicode_data/properties/Script/Inscriptional_Pahlavi/value.dump +4 -0
  939. data/resources/unicode_data/properties/Script/Inscriptional_Parthian/value.dump +4 -0
  940. data/resources/unicode_data/properties/Script/Javanese/value.dump +5 -0
  941. data/resources/unicode_data/properties/Script/Kaithi/value.dump +3 -0
  942. data/resources/unicode_data/properties/Script/Kannada/value.dump +16 -0
  943. data/resources/unicode_data/properties/Script/Katakana/value.dump +0 -0
  944. data/resources/unicode_data/properties/Script/Kayah_Li/value.dump +0 -0
  945. data/resources/unicode_data/properties/Script/Kharoshthi/value.dump +0 -0
  946. data/resources/unicode_data/properties/Script/Khmer/value.dump +6 -0
  947. data/resources/unicode_data/properties/Script/Lao/value.dump +20 -0
  948. data/resources/unicode_data/properties/Script/Latin/value.dump +0 -0
  949. data/resources/unicode_data/properties/Script/Lepcha/value.dump +0 -0
  950. data/resources/unicode_data/properties/Script/Limbu/value.dump +0 -0
  951. data/resources/unicode_data/properties/Script/Linear_B/value.dump +0 -0
  952. data/resources/unicode_data/properties/Script/Lisu/value.dump +3 -0
  953. data/resources/unicode_data/properties/Script/Lycian/value.dump +3 -0
  954. data/resources/unicode_data/properties/Script/Lydian/value.dump +4 -0
  955. data/resources/unicode_data/properties/Script/Malayalam/value.dump +13 -0
  956. data/resources/unicode_data/properties/Script/Mandaic/value.dump +4 -0
  957. data/resources/unicode_data/properties/Script/Meetei_Mayek/value.dump +5 -0
  958. data/resources/unicode_data/properties/Script/Meroitic_Cursive/value.dump +4 -0
  959. data/resources/unicode_data/properties/Script/Meroitic_Hieroglyphs/value.dump +3 -0
  960. data/resources/unicode_data/properties/Script/Miao/value.dump +0 -0
  961. data/resources/unicode_data/properties/Script/Mongolian/value.dump +0 -0
  962. data/resources/unicode_data/properties/Script/Myanmar/value.dump +0 -0
  963. data/resources/unicode_data/properties/Script/New_Tai_Lue/value.dump +6 -0
  964. data/resources/unicode_data/properties/Script/Nko/value.dump +3 -0
  965. data/resources/unicode_data/properties/Script/Ogham/value.dump +3 -0
  966. data/resources/unicode_data/properties/Script/Ol_Chiki/value.dump +3 -0
  967. data/resources/unicode_data/properties/Script/Old_Italic/value.dump +0 -0
  968. data/resources/unicode_data/properties/Script/Old_Persian/value.dump +4 -0
  969. data/resources/unicode_data/properties/Script/Old_South_Arabian/value.dump +5 -0
  970. data/resources/unicode_data/properties/Script/Old_Turkic/value.dump +0 -0
  971. data/resources/unicode_data/properties/Script/Oriya/value.dump +16 -0
  972. data/resources/unicode_data/properties/Script/Osmanya/value.dump +4 -0
  973. data/resources/unicode_data/properties/Script/Phags_Pa/value.dump +3 -0
  974. data/resources/unicode_data/properties/Script/Phoenician/value.dump +0 -0
  975. data/resources/unicode_data/properties/Script/Rejang/value.dump +4 -0
  976. data/resources/unicode_data/properties/Script/Runic/value.dump +4 -0
  977. data/resources/unicode_data/properties/Script/Samaritan/value.dump +0 -0
  978. data/resources/unicode_data/properties/Script/Saurashtra/value.dump +4 -0
  979. data/resources/unicode_data/properties/Script/Sharada/value.dump +4 -0
  980. data/resources/unicode_data/properties/Script/Shavian/value.dump +3 -0
  981. data/resources/unicode_data/properties/Script/Sinhala/value.dump +13 -0
  982. data/resources/unicode_data/properties/Script/Sora_Sompeng/value.dump +4 -0
  983. data/resources/unicode_data/properties/Script/Sundanese/value.dump +4 -0
  984. data/resources/unicode_data/properties/Script/Syloti_Nagri/value.dump +0 -0
  985. data/resources/unicode_data/properties/Script/Syriac/value.dump +0 -0
  986. data/resources/unicode_data/properties/Script/Tagalog/value.dump +0 -0
  987. data/resources/unicode_data/properties/Script/Tagbanwa/value.dump +5 -0
  988. data/resources/unicode_data/properties/Script/Tai_Le/value.dump +4 -0
  989. data/resources/unicode_data/properties/Script/Tai_Tham/value.dump +8 -0
  990. data/resources/unicode_data/properties/Script/Tai_Viet/value.dump +4 -0
  991. data/resources/unicode_data/properties/Script/Takri/value.dump +4 -0
  992. data/resources/unicode_data/properties/Script/Tamil/value.dump +18 -0
  993. data/resources/unicode_data/properties/Script/Telugu/value.dump +16 -0
  994. data/resources/unicode_data/properties/Script/Thaana/value.dump +3 -0
  995. data/resources/unicode_data/properties/Script/Thai/value.dump +4 -0
  996. data/resources/unicode_data/properties/Script/Tibetan/value.dump +0 -0
  997. data/resources/unicode_data/properties/Script/Tifinagh/value.dump +5 -0
  998. data/resources/unicode_data/properties/Script/Ugaritic/value.dump +4 -0
  999. data/resources/unicode_data/properties/Script/Vai/value.dump +0 -0
  1000. data/resources/unicode_data/properties/Script/Yi/value.dump +0 -0
  1001. data/resources/unicode_data/properties/Script_Extensions/Arab/value.dump +11 -0
  1002. data/resources/unicode_data/properties/Script_Extensions/Armn/value.dump +3 -0
  1003. data/resources/unicode_data/properties/Script_Extensions/Beng/value.dump +3 -0
  1004. data/resources/unicode_data/properties/Script_Extensions/Bopo/value.dump +19 -0
  1005. data/resources/unicode_data/properties/Script_Extensions/Bugi/value.dump +3 -0
  1006. data/resources/unicode_data/properties/Script_Extensions/Buhd/value.dump +3 -0
  1007. data/resources/unicode_data/properties/Script_Extensions/Cakm/value.dump +4 -0
  1008. data/resources/unicode_data/properties/Script_Extensions/Cprt/value.dump +0 -0
  1009. data/resources/unicode_data/properties/Script_Extensions/Cyrl/value.dump +3 -0
  1010. data/resources/unicode_data/properties/Script_Extensions/Deva/value.dump +4 -0
  1011. data/resources/unicode_data/properties/Script_Extensions/Geor/value.dump +3 -0
  1012. data/resources/unicode_data/properties/Script_Extensions/Grek/value.dump +5 -0
  1013. data/resources/unicode_data/properties/Script_Extensions/Gujr/value.dump +3 -0
  1014. data/resources/unicode_data/properties/Script_Extensions/Guru/value.dump +4 -0
  1015. data/resources/unicode_data/properties/Script_Extensions/Hang/value.dump +18 -0
  1016. data/resources/unicode_data/properties/Script_Extensions/Hani/value.dump +21 -0
  1017. data/resources/unicode_data/properties/Script_Extensions/Hano/value.dump +3 -0
  1018. data/resources/unicode_data/properties/Script_Extensions/Hira/value.dump +24 -0
  1019. data/resources/unicode_data/properties/Script_Extensions/Java/value.dump +3 -0
  1020. data/resources/unicode_data/properties/Script_Extensions/Kana/value.dump +24 -0
  1021. data/resources/unicode_data/properties/Script_Extensions/Kthi/value.dump +3 -0
  1022. data/resources/unicode_data/properties/Script_Extensions/Latn/value.dump +5 -0
  1023. data/resources/unicode_data/properties/Script_Extensions/Linb/value.dump +0 -0
  1024. data/resources/unicode_data/properties/Script_Extensions/Mand/value.dump +3 -0
  1025. data/resources/unicode_data/properties/Script_Extensions/Mong/value.dump +4 -0
  1026. data/resources/unicode_data/properties/Script_Extensions/Mymr/value.dump +3 -0
  1027. data/resources/unicode_data/properties/Script_Extensions/Orya/value.dump +3 -0
  1028. data/resources/unicode_data/properties/Script_Extensions/Phag/value.dump +4 -0
  1029. data/resources/unicode_data/properties/Script_Extensions/Sylo/value.dump +3 -0
  1030. data/resources/unicode_data/properties/Script_Extensions/Syrc/value.dump +8 -0
  1031. data/resources/unicode_data/properties/Script_Extensions/Tagb/value.dump +3 -0
  1032. data/resources/unicode_data/properties/Script_Extensions/Takr/value.dump +3 -0
  1033. data/resources/unicode_data/properties/Script_Extensions/Tale/value.dump +3 -0
  1034. data/resources/unicode_data/properties/Script_Extensions/Tglg/value.dump +3 -0
  1035. data/resources/unicode_data/properties/Script_Extensions/Thaa/value.dump +8 -0
  1036. data/resources/unicode_data/properties/Script_Extensions/Yiii/value.dump +8 -0
  1037. data/resources/unicode_data/properties/Sentence_Break/ATerm/value.dump +6 -0
  1038. data/resources/unicode_data/properties/Sentence_Break/CR/value.dump +3 -0
  1039. data/resources/unicode_data/properties/Sentence_Break/Close/value.dump +0 -0
  1040. data/resources/unicode_data/properties/Sentence_Break/Extend/value.dump +0 -0
  1041. data/resources/unicode_data/properties/Sentence_Break/Format/value.dump +0 -0
  1042. data/resources/unicode_data/properties/Sentence_Break/LF/value.dump +3 -0
  1043. data/resources/unicode_data/properties/Sentence_Break/Lower/value.dump +0 -0
  1044. data/resources/unicode_data/properties/Sentence_Break/Numeric/value.dump +0 -0
  1045. data/resources/unicode_data/properties/Sentence_Break/OLetter/value.dump +0 -0
  1046. data/resources/unicode_data/properties/Sentence_Break/SContinue/value.dump +21 -0
  1047. data/resources/unicode_data/properties/Sentence_Break/STerm/value.dump +0 -0
  1048. data/resources/unicode_data/properties/Sentence_Break/Sep/value.dump +4 -0
  1049. data/resources/unicode_data/properties/Sentence_Break/Sp/value.dump +0 -0
  1050. data/resources/unicode_data/properties/Sentence_Break/Upper/value.dump +0 -0
  1051. data/resources/unicode_data/properties/Soft_Dotted/value.dump +33 -0
  1052. data/resources/unicode_data/properties/Terminal_Punctuation/value.dump +0 -0
  1053. data/resources/unicode_data/properties/Unified_Ideograph/value.dump +0 -0
  1054. data/resources/unicode_data/properties/Uppercase/value.dump +0 -0
  1055. data/resources/unicode_data/properties/Variation_Selector/value.dump +0 -0
  1056. data/resources/unicode_data/properties/White_Space/value.dump +0 -0
  1057. data/resources/unicode_data/properties/Word_Break/ALetter/value.dump +0 -0
  1058. data/resources/unicode_data/properties/Word_Break/CR/value.dump +3 -0
  1059. data/resources/unicode_data/properties/Word_Break/Double_Quote/value.dump +3 -0
  1060. data/resources/unicode_data/properties/Word_Break/Extend/value.dump +0 -0
  1061. data/resources/unicode_data/properties/Word_Break/ExtendNumLet/value.dump +8 -0
  1062. data/resources/unicode_data/properties/Word_Break/Format/value.dump +0 -0
  1063. data/resources/unicode_data/properties/Word_Break/Hebrew_Letter/value.dump +12 -0
  1064. data/resources/unicode_data/properties/Word_Break/Katakana/value.dump +0 -0
  1065. data/resources/unicode_data/properties/Word_Break/LF/value.dump +3 -0
  1066. data/resources/unicode_data/properties/Word_Break/MidLetter/value.dump +10 -0
  1067. data/resources/unicode_data/properties/Word_Break/MidNum/value.dump +16 -0
  1068. data/resources/unicode_data/properties/Word_Break/MidNumLet/value.dump +9 -0
  1069. data/resources/unicode_data/properties/Word_Break/Newline/value.dump +5 -0
  1070. data/resources/unicode_data/properties/Word_Break/Numeric/value.dump +0 -0
  1071. data/resources/unicode_data/properties/Word_Break/Regional_Indicator/value.dump +3 -0
  1072. data/resources/unicode_data/properties/Word_Break/Single_Quote/value.dump +3 -0
  1073. data/resources/unicode_data/properties/XID_Continue/value.dump +0 -0
  1074. data/resources/unicode_data/properties/XID_Start/value.dump +0 -0
  1075. data/resources/unicode_data/property_aliases.yml +350 -0
  1076. data/resources/unicode_data/property_value_aliases.yml +1829 -0
  1077. data/spec/bidi/bidi_spec.rb +2 -2
  1078. data/spec/collation/collation_spec.rb +1 -1
  1079. data/spec/collation/collator_spec.rb +6 -6
  1080. data/spec/collation/sort_key_builder_spec.rb +11 -11
  1081. data/spec/collation/tailoring_spec.rb +1 -1
  1082. data/spec/collation/trie_dumps_spec.rb +1 -1
  1083. data/spec/data_readers/date_time_data_reader_spec.rb +1 -1
  1084. data/spec/data_readers/number_data_reader_spec.rb +19 -6
  1085. data/spec/formatters/calendars/datetime_formatter_spec.rb +1 -1
  1086. data/spec/formatters/numbers/abbreviated/abbreviated_number_formatter_spec.rb +1 -1
  1087. data/spec/formatters/numbers/abbreviated/long_decimal_formatter_spec.rb +5 -5
  1088. data/spec/formatters/numbers/abbreviated/short_decimal_formatter_spec.rb +4 -4
  1089. data/spec/formatters/numbers/currency_formatter_spec.rb +10 -10
  1090. data/spec/formatters/numbers/decimal_formatter_spec.rb +2 -2
  1091. data/spec/formatters/numbers/helpers/fraction_spec.rb +4 -4
  1092. data/spec/formatters/numbers/helpers/integer_spec.rb +21 -16
  1093. data/spec/formatters/numbers/number_formatter_spec.rb +9 -9
  1094. data/spec/formatters/numbers/percent_formatter_spec.rb +2 -2
  1095. data/spec/formatters/numbers/rbnf/rbnf_spec.rb +5 -5
  1096. data/spec/formatters/plurals/plural_formatter_spec.rb +25 -25
  1097. data/spec/formatters/plurals/rules_spec.rb +4 -4
  1098. data/spec/localized/localized_date_spec.rb +25 -25
  1099. data/spec/localized/localized_datetime_spec.rb +7 -7
  1100. data/spec/localized/localized_hash_spec.rb +1 -1
  1101. data/spec/localized/localized_number_spec.rb +23 -23
  1102. data/spec/localized/localized_object_spec.rb +2 -2
  1103. data/spec/localized/localized_string_spec.rb +43 -16
  1104. data/spec/localized/localized_symbol_spec.rb +31 -4
  1105. data/spec/localized/localized_time_spec.rb +3 -3
  1106. data/spec/localized/localized_timespan_spec.rb +42 -42
  1107. data/spec/normalization_spec.rb +4 -4
  1108. data/spec/parsers/number_parser_spec.rb +10 -10
  1109. data/spec/parsers/parser_spec.rb +19 -3
  1110. data/spec/parsers/symbol_table_spec.rb +1 -1
  1111. data/spec/parsers/unicode_regex/character_class_spec.rb +12 -0
  1112. data/spec/parsers/unicode_regex/character_range_spec.rb +24 -5
  1113. data/spec/parsers/unicode_regex/character_set_spec.rb +9 -1
  1114. data/spec/parsers/unicode_regex_parser_spec.rb +1 -1
  1115. data/spec/resources/loader_spec.rb +6 -6
  1116. data/spec/{shared → segmentation}/break_iterator_spec.rb +45 -16
  1117. data/spec/segmentation/parser_spec.rb +107 -0
  1118. data/spec/segmentation/rule_set_spec.rb +102 -0
  1119. data/spec/shared/calendar_spec.rb +30 -30
  1120. data/spec/shared/caser_spec.rb +79 -0
  1121. data/spec/shared/code_point_spec.rb +52 -151
  1122. data/spec/shared/currencies_spec.rb +8 -8
  1123. data/spec/shared/language_codes_spec.rb +13 -13
  1124. data/spec/shared/likely_subtags_spec.rb +58 -0
  1125. data/spec/shared/locale_spec.rb +211 -0
  1126. data/spec/shared/numbers_spec.rb +4 -4
  1127. data/spec/shared/postal_codes_spec.rb +24 -4
  1128. data/spec/shared/properties_database_spec.rb +157 -0
  1129. data/spec/shared/property_name_aliases_spec.rb +56 -0
  1130. data/spec/shared/property_normalizer_spec.rb +64 -0
  1131. data/spec/shared/property_set_spec.rb +218 -0
  1132. data/spec/shared/property_value_aliases_spec.rb +58 -0
  1133. data/spec/shared/territories_spec.rb +1 -1
  1134. data/spec/shared/unicode_regex_spec.rb +35 -2
  1135. data/spec/spec_helper.rb +3 -3
  1136. data/spec/tokenizers/calendars/date_tokenizer_spec.rb +23 -23
  1137. data/spec/tokenizers/calendars/datetime_tokenizer_spec.rb +18 -18
  1138. data/spec/tokenizers/calendars/time_tokenizer_spec.rb +19 -19
  1139. data/spec/tokenizers/composite_token_spec.rb +4 -4
  1140. data/spec/tokenizers/numbers/number_tokenizer_spec.rb +16 -16
  1141. data/spec/tokenizers/token_spec.rb +2 -2
  1142. data/spec/tokenizers/unicode_regex/unicode_regex_tokenizer_spec.rb +94 -94
  1143. data/spec/utils/file_system_trie_spec.rb +98 -0
  1144. data/spec/utils/range_set_spec.rb +53 -1
  1145. data/spec/utils/script_detector_spec.rb +58 -0
  1146. data/spec/utils/yaml/yaml_spec.rb +22 -22
  1147. data/spec/utils_spec.rb +21 -21
  1148. metadata +832 -28
  1149. data/lib/twitter_cldr/parsers/segmentation_parser.rb +0 -137
  1150. data/lib/twitter_cldr/resources/canonical_compositions_updater.rb +0 -51
  1151. data/lib/twitter_cldr/resources/composition_exclusions_importer.rb +0 -62
  1152. data/lib/twitter_cldr/resources/normalization_quick_check_importer.rb +0 -73
  1153. data/lib/twitter_cldr/resources/unicode_properties_importer.rb +0 -79
  1154. data/lib/twitter_cldr/shared/break_iterator.rb +0 -213
  1155. data/lib/twitter_cldr/tokenizers/segmentation/segmentation_tokenizer.rb +0 -39
  1156. data/resources/shared/segments/tailorings/en.yml +0 -8
  1157. data/resources/unicode_data/canonical_compositions.yml +0 -4925
  1158. data/resources/unicode_data/composition_exclusions.yml +0 -297
  1159. data/resources/unicode_data/hangul_blocks.yml +0 -21
  1160. data/resources/unicode_data/indices/bidi_class.yml +0 -4572
  1161. data/resources/unicode_data/indices/bidi_mirrored.yml +0 -3087
  1162. data/resources/unicode_data/indices/category.yml +0 -10918
  1163. data/resources/unicode_data/indices/keys.yml +0 -101
  1164. data/resources/unicode_data/nfc_quick_check.yml +0 -293
  1165. data/resources/unicode_data/nfd_quick_check.yml +0 -909
  1166. data/resources/unicode_data/nfkc_quick_check.yml +0 -989
  1167. data/resources/unicode_data/nfkd_quick_check.yml +0 -1537
  1168. data/resources/unicode_data/properties/line_break.yml +0 -9269
  1169. data/resources/unicode_data/properties/sentence_break.yml +0 -8067
  1170. data/resources/unicode_data/properties/word_break.yml +0 -3001
  1171. data/spec/parsers/segmentation_parser_spec.rb +0 -100
  1172. data/spec/tokenizers/segmentation/segmentation_tokenizer_spec.rb +0 -40
data/resources/unicode_data/blocks/khojki.yml ADDED
@@ -0,0 +1,977 @@
1
+ ---
2
+ 70144:
3
+ - 70144
4
+ - KHOJKI LETTER A
5
+ - Lo
6
+ - '0'
7
+ - L
8
+ - ''
9
+ - ''
10
+ - ''
11
+ - ''
12
+ - N
13
+ - ''
14
+ - ''
15
+ - ''
16
+ - ''
17
+ - ''
18
+ 70145:
19
+ - 70145
20
+ - KHOJKI LETTER AA
21
+ - Lo
22
+ - '0'
23
+ - L
24
+ - ''
25
+ - ''
26
+ - ''
27
+ - ''
28
+ - N
29
+ - ''
30
+ - ''
31
+ - ''
32
+ - ''
33
+ - ''
34
+ 70146:
35
+ - 70146
36
+ - KHOJKI LETTER I
37
+ - Lo
38
+ - '0'
39
+ - L
40
+ - ''
41
+ - ''
42
+ - ''
43
+ - ''
44
+ - N
45
+ - ''
46
+ - ''
47
+ - ''
48
+ - ''
49
+ - ''
50
+ 70147:
51
+ - 70147
52
+ - KHOJKI LETTER U
53
+ - Lo
54
+ - '0'
55
+ - L
56
+ - ''
57
+ - ''
58
+ - ''
59
+ - ''
60
+ - N
61
+ - ''
62
+ - ''
63
+ - ''
64
+ - ''
65
+ - ''
66
+ 70148:
67
+ - 70148
68
+ - KHOJKI LETTER E
69
+ - Lo
70
+ - '0'
71
+ - L
72
+ - ''
73
+ - ''
74
+ - ''
75
+ - ''
76
+ - N
77
+ - ''
78
+ - ''
79
+ - ''
80
+ - ''
81
+ - ''
82
+ 70149:
83
+ - 70149
84
+ - KHOJKI LETTER AI
85
+ - Lo
86
+ - '0'
87
+ - L
88
+ - ''
89
+ - ''
90
+ - ''
91
+ - ''
92
+ - N
93
+ - ''
94
+ - ''
95
+ - ''
96
+ - ''
97
+ - ''
98
+ 70150:
99
+ - 70150
100
+ - KHOJKI LETTER O
101
+ - Lo
102
+ - '0'
103
+ - L
104
+ - ''
105
+ - ''
106
+ - ''
107
+ - ''
108
+ - N
109
+ - ''
110
+ - ''
111
+ - ''
112
+ - ''
113
+ - ''
114
+ 70151:
115
+ - 70151
116
+ - KHOJKI LETTER AU
117
+ - Lo
118
+ - '0'
119
+ - L
120
+ - ''
121
+ - ''
122
+ - ''
123
+ - ''
124
+ - N
125
+ - ''
126
+ - ''
127
+ - ''
128
+ - ''
129
+ - ''
130
+ 70152:
131
+ - 70152
132
+ - KHOJKI LETTER KA
133
+ - Lo
134
+ - '0'
135
+ - L
136
+ - ''
137
+ - ''
138
+ - ''
139
+ - ''
140
+ - N
141
+ - ''
142
+ - ''
143
+ - ''
144
+ - ''
145
+ - ''
146
+ 70153:
147
+ - 70153
148
+ - KHOJKI LETTER KHA
149
+ - Lo
150
+ - '0'
151
+ - L
152
+ - ''
153
+ - ''
154
+ - ''
155
+ - ''
156
+ - N
157
+ - ''
158
+ - ''
159
+ - ''
160
+ - ''
161
+ - ''
162
+ 70154:
163
+ - 70154
164
+ - KHOJKI LETTER GA
165
+ - Lo
166
+ - '0'
167
+ - L
168
+ - ''
169
+ - ''
170
+ - ''
171
+ - ''
172
+ - N
173
+ - ''
174
+ - ''
175
+ - ''
176
+ - ''
177
+ - ''
178
+ 70155:
179
+ - 70155
180
+ - KHOJKI LETTER GGA
181
+ - Lo
182
+ - '0'
183
+ - L
184
+ - ''
185
+ - ''
186
+ - ''
187
+ - ''
188
+ - N
189
+ - ''
190
+ - ''
191
+ - ''
192
+ - ''
193
+ - ''
194
+ 70156:
195
+ - 70156
196
+ - KHOJKI LETTER GHA
197
+ - Lo
198
+ - '0'
199
+ - L
200
+ - ''
201
+ - ''
202
+ - ''
203
+ - ''
204
+ - N
205
+ - ''
206
+ - ''
207
+ - ''
208
+ - ''
209
+ - ''
210
+ 70157:
211
+ - 70157
212
+ - KHOJKI LETTER NGA
213
+ - Lo
214
+ - '0'
215
+ - L
216
+ - ''
217
+ - ''
218
+ - ''
219
+ - ''
220
+ - N
221
+ - ''
222
+ - ''
223
+ - ''
224
+ - ''
225
+ - ''
226
+ 70158:
227
+ - 70158
228
+ - KHOJKI LETTER CA
229
+ - Lo
230
+ - '0'
231
+ - L
232
+ - ''
233
+ - ''
234
+ - ''
235
+ - ''
236
+ - N
237
+ - ''
238
+ - ''
239
+ - ''
240
+ - ''
241
+ - ''
242
+ 70159:
243
+ - 70159
244
+ - KHOJKI LETTER CHA
245
+ - Lo
246
+ - '0'
247
+ - L
248
+ - ''
249
+ - ''
250
+ - ''
251
+ - ''
252
+ - N
253
+ - ''
254
+ - ''
255
+ - ''
256
+ - ''
257
+ - ''
258
+ 70160:
259
+ - 70160
260
+ - KHOJKI LETTER JA
261
+ - Lo
262
+ - '0'
263
+ - L
264
+ - ''
265
+ - ''
266
+ - ''
267
+ - ''
268
+ - N
269
+ - ''
270
+ - ''
271
+ - ''
272
+ - ''
273
+ - ''
274
+ 70161:
275
+ - 70161
276
+ - KHOJKI LETTER JJA
277
+ - Lo
278
+ - '0'
279
+ - L
280
+ - ''
281
+ - ''
282
+ - ''
283
+ - ''
284
+ - N
285
+ - ''
286
+ - ''
287
+ - ''
288
+ - ''
289
+ - ''
290
+ 70163:
291
+ - 70163
292
+ - KHOJKI LETTER NYA
293
+ - Lo
294
+ - '0'
295
+ - L
296
+ - ''
297
+ - ''
298
+ - ''
299
+ - ''
300
+ - N
301
+ - ''
302
+ - ''
303
+ - ''
304
+ - ''
305
+ - ''
306
+ 70164:
307
+ - 70164
308
+ - KHOJKI LETTER TTA
309
+ - Lo
310
+ - '0'
311
+ - L
312
+ - ''
313
+ - ''
314
+ - ''
315
+ - ''
316
+ - N
317
+ - ''
318
+ - ''
319
+ - ''
320
+ - ''
321
+ - ''
322
+ 70165:
323
+ - 70165
324
+ - KHOJKI LETTER TTHA
325
+ - Lo
326
+ - '0'
327
+ - L
328
+ - ''
329
+ - ''
330
+ - ''
331
+ - ''
332
+ - N
333
+ - ''
334
+ - ''
335
+ - ''
336
+ - ''
337
+ - ''
338
+ 70166:
339
+ - 70166
340
+ - KHOJKI LETTER DDA
341
+ - Lo
342
+ - '0'
343
+ - L
344
+ - ''
345
+ - ''
346
+ - ''
347
+ - ''
348
+ - N
349
+ - ''
350
+ - ''
351
+ - ''
352
+ - ''
353
+ - ''
354
+ 70167:
355
+ - 70167
356
+ - KHOJKI LETTER DDHA
357
+ - Lo
358
+ - '0'
359
+ - L
360
+ - ''
361
+ - ''
362
+ - ''
363
+ - ''
364
+ - N
365
+ - ''
366
+ - ''
367
+ - ''
368
+ - ''
369
+ - ''
370
+ 70168:
371
+ - 70168
372
+ - KHOJKI LETTER NNA
373
+ - Lo
374
+ - '0'
375
+ - L
376
+ - ''
377
+ - ''
378
+ - ''
379
+ - ''
380
+ - N
381
+ - ''
382
+ - ''
383
+ - ''
384
+ - ''
385
+ - ''
386
+ 70169:
387
+ - 70169
388
+ - KHOJKI LETTER TA
389
+ - Lo
390
+ - '0'
391
+ - L
392
+ - ''
393
+ - ''
394
+ - ''
395
+ - ''
396
+ - N
397
+ - ''
398
+ - ''
399
+ - ''
400
+ - ''
401
+ - ''
402
+ 70170:
403
+ - 70170
404
+ - KHOJKI LETTER THA
405
+ - Lo
406
+ - '0'
407
+ - L
408
+ - ''
409
+ - ''
410
+ - ''
411
+ - ''
412
+ - N
413
+ - ''
414
+ - ''
415
+ - ''
416
+ - ''
417
+ - ''
418
+ 70171:
419
+ - 70171
420
+ - KHOJKI LETTER DA
421
+ - Lo
422
+ - '0'
423
+ - L
424
+ - ''
425
+ - ''
426
+ - ''
427
+ - ''
428
+ - N
429
+ - ''
430
+ - ''
431
+ - ''
432
+ - ''
433
+ - ''
434
+ 70172:
435
+ - 70172
436
+ - KHOJKI LETTER DDDA
437
+ - Lo
438
+ - '0'
439
+ - L
440
+ - ''
441
+ - ''
442
+ - ''
443
+ - ''
444
+ - N
445
+ - ''
446
+ - ''
447
+ - ''
448
+ - ''
449
+ - ''
450
+ 70173:
451
+ - 70173
452
+ - KHOJKI LETTER DHA
453
+ - Lo
454
+ - '0'
455
+ - L
456
+ - ''
457
+ - ''
458
+ - ''
459
+ - ''
460
+ - N
461
+ - ''
462
+ - ''
463
+ - ''
464
+ - ''
465
+ - ''
466
+ 70174:
467
+ - 70174
468
+ - KHOJKI LETTER NA
469
+ - Lo
470
+ - '0'
471
+ - L
472
+ - ''
473
+ - ''
474
+ - ''
475
+ - ''
476
+ - N
477
+ - ''
478
+ - ''
479
+ - ''
480
+ - ''
481
+ - ''
482
+ 70175:
483
+ - 70175
484
+ - KHOJKI LETTER PA
485
+ - Lo
486
+ - '0'
487
+ - L
488
+ - ''
489
+ - ''
490
+ - ''
491
+ - ''
492
+ - N
493
+ - ''
494
+ - ''
495
+ - ''
496
+ - ''
497
+ - ''
498
+ 70176:
499
+ - 70176
500
+ - KHOJKI LETTER PHA
501
+ - Lo
502
+ - '0'
503
+ - L
504
+ - ''
505
+ - ''
506
+ - ''
507
+ - ''
508
+ - N
509
+ - ''
510
+ - ''
511
+ - ''
512
+ - ''
513
+ - ''
514
+ 70177:
515
+ - 70177
516
+ - KHOJKI LETTER BA
517
+ - Lo
518
+ - '0'
519
+ - L
520
+ - ''
521
+ - ''
522
+ - ''
523
+ - ''
524
+ - N
525
+ - ''
526
+ - ''
527
+ - ''
528
+ - ''
529
+ - ''
530
+ 70178:
531
+ - 70178
532
+ - KHOJKI LETTER BBA
533
+ - Lo
534
+ - '0'
535
+ - L
536
+ - ''
537
+ - ''
538
+ - ''
539
+ - ''
540
+ - N
541
+ - ''
542
+ - ''
543
+ - ''
544
+ - ''
545
+ - ''
546
+ 70179:
547
+ - 70179
548
+ - KHOJKI LETTER BHA
549
+ - Lo
550
+ - '0'
551
+ - L
552
+ - ''
553
+ - ''
554
+ - ''
555
+ - ''
556
+ - N
557
+ - ''
558
+ - ''
559
+ - ''
560
+ - ''
561
+ - ''
562
+ 70180:
563
+ - 70180
564
+ - KHOJKI LETTER MA
565
+ - Lo
566
+ - '0'
567
+ - L
568
+ - ''
569
+ - ''
570
+ - ''
571
+ - ''
572
+ - N
573
+ - ''
574
+ - ''
575
+ - ''
576
+ - ''
577
+ - ''
578
+ 70181:
579
+ - 70181
580
+ - KHOJKI LETTER YA
581
+ - Lo
582
+ - '0'
583
+ - L
584
+ - ''
585
+ - ''
586
+ - ''
587
+ - ''
588
+ - N
589
+ - ''
590
+ - ''
591
+ - ''
592
+ - ''
593
+ - ''
594
+ 70182:
595
+ - 70182
596
+ - KHOJKI LETTER RA
597
+ - Lo
598
+ - '0'
599
+ - L
600
+ - ''
601
+ - ''
602
+ - ''
603
+ - ''
604
+ - N
605
+ - ''
606
+ - ''
607
+ - ''
608
+ - ''
609
+ - ''
610
+ 70183:
611
+ - 70183
612
+ - KHOJKI LETTER LA
613
+ - Lo
614
+ - '0'
615
+ - L
616
+ - ''
617
+ - ''
618
+ - ''
619
+ - ''
620
+ - N
621
+ - ''
622
+ - ''
623
+ - ''
624
+ - ''
625
+ - ''
626
+ 70184:
627
+ - 70184
628
+ - KHOJKI LETTER VA
629
+ - Lo
630
+ - '0'
631
+ - L
632
+ - ''
633
+ - ''
634
+ - ''
635
+ - ''
636
+ - N
637
+ - ''
638
+ - ''
639
+ - ''
640
+ - ''
641
+ - ''
642
+ 70185:
643
+ - 70185
644
+ - KHOJKI LETTER SA
645
+ - Lo
646
+ - '0'
647
+ - L
648
+ - ''
649
+ - ''
650
+ - ''
651
+ - ''
652
+ - N
653
+ - ''
654
+ - ''
655
+ - ''
656
+ - ''
657
+ - ''
658
+ 70186:
659
+ - 70186
660
+ - KHOJKI LETTER HA
661
+ - Lo
662
+ - '0'
663
+ - L
664
+ - ''
665
+ - ''
666
+ - ''
667
+ - ''
668
+ - N
669
+ - ''
670
+ - ''
671
+ - ''
672
+ - ''
673
+ - ''
674
+ 70187:
675
+ - 70187
676
+ - KHOJKI LETTER LLA
677
+ - Lo
678
+ - '0'
679
+ - L
680
+ - ''
681
+ - ''
682
+ - ''
683
+ - ''
684
+ - N
685
+ - ''
686
+ - ''
687
+ - ''
688
+ - ''
689
+ - ''
690
+ 70188:
691
+ - 70188
692
+ - KHOJKI VOWEL SIGN AA
693
+ - Mc
694
+ - '0'
695
+ - L
696
+ - ''
697
+ - ''
698
+ - ''
699
+ - ''
700
+ - N
701
+ - ''
702
+ - ''
703
+ - ''
704
+ - ''
705
+ - ''
706
+ 70189:
707
+ - 70189
708
+ - KHOJKI VOWEL SIGN I
709
+ - Mc
710
+ - '0'
711
+ - L
712
+ - ''
713
+ - ''
714
+ - ''
715
+ - ''
716
+ - N
717
+ - ''
718
+ - ''
719
+ - ''
720
+ - ''
721
+ - ''
722
+ 70190:
723
+ - 70190
724
+ - KHOJKI VOWEL SIGN II
725
+ - Mc
726
+ - '0'
727
+ - L
728
+ - ''
729
+ - ''
730
+ - ''
731
+ - ''
732
+ - N
733
+ - ''
734
+ - ''
735
+ - ''
736
+ - ''
737
+ - ''
738
+ 70191:
739
+ - 70191
740
+ - KHOJKI VOWEL SIGN U
741
+ - Mn
742
+ - '0'
743
+ - NSM
744
+ - ''
745
+ - ''
746
+ - ''
747
+ - ''
748
+ - N
749
+ - ''
750
+ - ''
751
+ - ''
752
+ - ''
753
+ - ''
754
+ 70192:
755
+ - 70192
756
+ - KHOJKI VOWEL SIGN E
757
+ - Mn
758
+ - '0'
759
+ - NSM
760
+ - ''
761
+ - ''
762
+ - ''
763
+ - ''
764
+ - N
765
+ - ''
766
+ - ''
767
+ - ''
768
+ - ''
769
+ - ''
770
+ 70193:
771
+ - 70193
772
+ - KHOJKI VOWEL SIGN AI
773
+ - Mn
774
+ - '0'
775
+ - NSM
776
+ - ''
777
+ - ''
778
+ - ''
779
+ - ''
780
+ - N
781
+ - ''
782
+ - ''
783
+ - ''
784
+ - ''
785
+ - ''
786
+ 70194:
787
+ - 70194
788
+ - KHOJKI VOWEL SIGN O
789
+ - Mc
790
+ - '0'
791
+ - L
792
+ - ''
793
+ - ''
794
+ - ''
795
+ - ''
796
+ - N
797
+ - ''
798
+ - ''
799
+ - ''
800
+ - ''
801
+ - ''
802
+ 70195:
803
+ - 70195
804
+ - KHOJKI VOWEL SIGN AU
805
+ - Mc
806
+ - '0'
807
+ - L
808
+ - ''
809
+ - ''
810
+ - ''
811
+ - ''
812
+ - N
813
+ - ''
814
+ - ''
815
+ - ''
816
+ - ''
817
+ - ''
818
+ 70196:
819
+ - 70196
820
+ - KHOJKI SIGN ANUSVARA
821
+ - Mn
822
+ - '0'
823
+ - NSM
824
+ - ''
825
+ - ''
826
+ - ''
827
+ - ''
828
+ - N
829
+ - ''
830
+ - ''
831
+ - ''
832
+ - ''
833
+ - ''
834
+ 70197:
835
+ - 70197
836
+ - KHOJKI SIGN VIRAMA
837
+ - Mc
838
+ - '9'
839
+ - L
840
+ - ''
841
+ - ''
842
+ - ''
843
+ - ''
844
+ - N
845
+ - ''
846
+ - ''
847
+ - ''
848
+ - ''
849
+ - ''
850
+ 70198:
851
+ - 70198
852
+ - KHOJKI SIGN NUKTA
853
+ - Mn
854
+ - '7'
855
+ - NSM
856
+ - ''
857
+ - ''
858
+ - ''
859
+ - ''
860
+ - N
861
+ - ''
862
+ - ''
863
+ - ''
864
+ - ''
865
+ - ''
866
+ 70199:
867
+ - 70199
868
+ - KHOJKI SIGN SHADDA
869
+ - Mn
870
+ - '0'
871
+ - NSM
872
+ - ''
873
+ - ''
874
+ - ''
875
+ - ''
876
+ - N
877
+ - ''
878
+ - ''
879
+ - ''
880
+ - ''
881
+ - ''
882
+ 70200:
883
+ - 70200
884
+ - KHOJKI DANDA
885
+ - Po
886
+ - '0'
887
+ - L
888
+ - ''
889
+ - ''
890
+ - ''
891
+ - ''
892
+ - N
893
+ - ''
894
+ - ''
895
+ - ''
896
+ - ''
897
+ - ''
898
+ 70201:
899
+ - 70201
900
+ - KHOJKI DOUBLE DANDA
901
+ - Po
902
+ - '0'
903
+ - L
904
+ - ''
905
+ - ''
906
+ - ''
907
+ - ''
908
+ - N
909
+ - ''
910
+ - ''
911
+ - ''
912
+ - ''
913
+ - ''
914
+ 70202:
915
+ - 70202
916
+ - KHOJKI WORD SEPARATOR
917
+ - Po
918
+ - '0'
919
+ - L
920
+ - ''
921
+ - ''
922
+ - ''
923
+ - ''
924
+ - N
925
+ - ''
926
+ - ''
927
+ - ''
928
+ - ''
929
+ - ''
930
+ 70203:
931
+ - 70203
932
+ - KHOJKI SECTION MARK
933
+ - Po
934
+ - '0'
935
+ - L
936
+ - ''
937
+ - ''
938
+ - ''
939
+ - ''
940
+ - N
941
+ - ''
942
+ - ''
943
+ - ''
944
+ - ''
945
+ - ''
946
+ 70204:
947
+ - 70204
948
+ - KHOJKI DOUBLE SECTION MARK
949
+ - Po
950
+ - '0'
951
+ - L
952
+ - ''
953
+ - ''
954
+ - ''
955
+ - ''
956
+ - N
957
+ - ''
958
+ - ''
959
+ - ''
960
+ - ''
961
+ - ''
962
+ 70205:
963
+ - 70205
964
+ - KHOJKI ABBREVIATION SIGN
965
+ - Po
966
+ - '0'
967
+ - L
968
+ - ''
969
+ - ''
970
+ - ''
971
+ - ''
972
+ - N
973
+ - ''
974
+ - ''
975
+ - ''
976
+ - ''
977
+ - ''