twitter_cldr 1.0.1 → 1.1.0

Sign up to get free protection for your applications and to get access to all the features.
Files changed (303) hide show
  1. data/NOTICE +95 -1
  2. data/README.md +4 -4
  3. data/Rakefile +18 -28
  4. data/lib/ext/calendars/date.rb +3 -0
  5. data/lib/ext/calendars/datetime.rb +3 -0
  6. data/lib/ext/calendars/time.rb +3 -0
  7. data/lib/ext/localized_object.rb +3 -0
  8. data/lib/ext/numbers/bignum.rb +3 -0
  9. data/lib/ext/numbers/fixnum.rb +3 -0
  10. data/lib/ext/numbers/float.rb +3 -0
  11. data/lib/ext/numbers/localized_number.rb +3 -0
  12. data/lib/ext/strings/string.rb +31 -0
  13. data/lib/ext/strings/symbol.rb +3 -0
  14. data/lib/formatters/base.rb +3 -0
  15. data/lib/formatters/calendars/date_formatter.rb +3 -0
  16. data/lib/formatters/calendars/datetime_formatter.rb +3 -0
  17. data/lib/formatters/calendars/time_formatter.rb +3 -0
  18. data/lib/formatters/numbers/currency_formatter.rb +3 -0
  19. data/lib/formatters/numbers/decimal_formatter.rb +3 -0
  20. data/lib/formatters/numbers/helpers/base.rb +3 -0
  21. data/lib/formatters/numbers/helpers/fraction.rb +3 -0
  22. data/lib/formatters/numbers/helpers/integer.rb +3 -0
  23. data/lib/formatters/numbers/number_formatter.rb +3 -0
  24. data/lib/formatters/numbers/percent_formatter.rb +3 -0
  25. data/lib/formatters/plurals/plural_formatter.rb +141 -0
  26. data/lib/formatters/plurals/rules.rb +4 -1
  27. data/lib/normalizers/base.rb +17 -0
  28. data/lib/normalizers/canonical/nfd.rb +81 -0
  29. data/lib/shared/currencies.rb +4 -1
  30. data/lib/shared/languages.rb +4 -1
  31. data/lib/shared/resources.rb +8 -28
  32. data/lib/shared/timezones.rb +3 -0
  33. data/lib/shared/unicode_data.rb +44 -0
  34. data/lib/tokenizers/base.rb +3 -0
  35. data/lib/tokenizers/calendars/date_tokenizer.rb +3 -0
  36. data/lib/tokenizers/calendars/datetime_tokenizer.rb +4 -1
  37. data/lib/tokenizers/calendars/time_tokenizer.rb +3 -0
  38. data/lib/tokenizers/key_path.rb +3 -0
  39. data/lib/tokenizers/numbers/number_tokenizer.rb +4 -1
  40. data/lib/tokenizers/token.rb +3 -0
  41. data/lib/twitter_cldr.rb +52 -29
  42. data/lib/utils/interpolation.rb +105 -0
  43. data/lib/utils.rb +28 -0
  44. data/lib/version.rb +6 -1
  45. data/resources/unicode_data/aegean_numbers.yml +913 -0
  46. data/resources/unicode_data/alchemical_symbols.yml +1857 -0
  47. data/resources/unicode_data/alphabetic_presentation_forms.yml +929 -0
  48. data/resources/unicode_data/ancient_greek_musical_notation.yml +1121 -0
  49. data/resources/unicode_data/ancient_greek_numbers.yml +1201 -0
  50. data/resources/unicode_data/ancient_symbols.yml +193 -0
  51. data/resources/unicode_data/arabic.yml +4049 -0
  52. data/resources/unicode_data/arabic_extended_a.yml +625 -0
  53. data/resources/unicode_data/arabic_mathematical_alphabetic_symbols.yml +2289 -0
  54. data/resources/unicode_data/arabic_presentation_forms_a.yml +9777 -0
  55. data/resources/unicode_data/arabic_presentation_forms_b.yml +2257 -0
  56. data/resources/unicode_data/arabic_supplement.yml +769 -0
  57. data/resources/unicode_data/armenian.yml +1393 -0
  58. data/resources/unicode_data/arrows.yml +1793 -0
  59. data/resources/unicode_data/avestan.yml +977 -0
  60. data/resources/unicode_data/balinese.yml +1937 -0
  61. data/resources/unicode_data/bamum.yml +1409 -0
  62. data/resources/unicode_data/bamum_supplement.yml +9105 -0
  63. data/resources/unicode_data/basic_latin.yml +2049 -0
  64. data/resources/unicode_data/batak.yml +897 -0
  65. data/resources/unicode_data/bengali.yml +1473 -0
  66. data/resources/unicode_data/block_elements.yml +513 -0
  67. data/resources/unicode_data/blocks.yml +881 -0
  68. data/resources/unicode_data/bopomofo.yml +657 -0
  69. data/resources/unicode_data/bopomofo_extended.yml +433 -0
  70. data/resources/unicode_data/box_drawing.yml +2049 -0
  71. data/resources/unicode_data/brahmi.yml +1729 -0
  72. data/resources/unicode_data/braille_patterns.yml +4097 -0
  73. data/resources/unicode_data/buginese.yml +481 -0
  74. data/resources/unicode_data/buhid.yml +321 -0
  75. data/resources/unicode_data/byzantine_musical_symbols.yml +3937 -0
  76. data/resources/unicode_data/carian.yml +785 -0
  77. data/resources/unicode_data/chakma.yml +1073 -0
  78. data/resources/unicode_data/cham.yml +1329 -0
  79. data/resources/unicode_data/cherokee.yml +1361 -0
  80. data/resources/unicode_data/cjk_compatibility.yml +4097 -0
  81. data/resources/unicode_data/cjk_compatibility_forms.yml +513 -0
  82. data/resources/unicode_data/cjk_compatibility_ideographs.yml +7553 -0
  83. data/resources/unicode_data/cjk_compatibility_ideographs_supplement.yml +8673 -0
  84. data/resources/unicode_data/cjk_radicals_supplement.yml +1841 -0
  85. data/resources/unicode_data/cjk_strokes.yml +577 -0
  86. data/resources/unicode_data/cjk_symbols_and_punctuation.yml +1025 -0
  87. data/resources/unicode_data/cjk_unified_ideographs.yml +33 -0
  88. data/resources/unicode_data/cjk_unified_ideographs_extension_a.yml +33 -0
  89. data/resources/unicode_data/cjk_unified_ideographs_extension_b.yml +33 -0
  90. data/resources/unicode_data/cjk_unified_ideographs_extension_c.yml +33 -0
  91. data/resources/unicode_data/cjk_unified_ideographs_extension_d.yml +33 -0
  92. data/resources/unicode_data/combining_diacritical_marks.yml +1793 -0
  93. data/resources/unicode_data/combining_diacritical_marks_for_symbols.yml +529 -0
  94. data/resources/unicode_data/combining_diacritical_marks_supplement.yml +689 -0
  95. data/resources/unicode_data/combining_half_marks.yml +113 -0
  96. data/resources/unicode_data/common_indic_number_forms.yml +161 -0
  97. data/resources/unicode_data/control_pictures.yml +625 -0
  98. data/resources/unicode_data/coptic.yml +1969 -0
  99. data/resources/unicode_data/counting_rod_numerals.yml +289 -0
  100. data/resources/unicode_data/cuneiform.yml +14065 -0
  101. data/resources/unicode_data/cuneiform_numbers_and_punctuation.yml +1649 -0
  102. data/resources/unicode_data/currency_symbols.yml +417 -0
  103. data/resources/unicode_data/cypriot_syllabary.yml +881 -0
  104. data/resources/unicode_data/cyrillic.yml +4097 -0
  105. data/resources/unicode_data/cyrillic_extended_a.yml +513 -0
  106. data/resources/unicode_data/cyrillic_extended_b.yml +1425 -0
  107. data/resources/unicode_data/cyrillic_supplement.yml +641 -0
  108. data/resources/unicode_data/deseret.yml +1281 -0
  109. data/resources/unicode_data/devanagari.yml +2033 -0
  110. data/resources/unicode_data/devanagari_extended.yml +449 -0
  111. data/resources/unicode_data/dingbats.yml +3057 -0
  112. data/resources/unicode_data/domino_tiles.yml +1601 -0
  113. data/resources/unicode_data/egyptian_hieroglyphs.yml +17137 -0
  114. data/resources/unicode_data/emoticons.yml +1217 -0
  115. data/resources/unicode_data/enclosed_alphanumeric_supplement.yml +2737 -0
  116. data/resources/unicode_data/enclosed_alphanumerics.yml +2561 -0
  117. data/resources/unicode_data/enclosed_cjk_letters_and_months.yml +4065 -0
  118. data/resources/unicode_data/enclosed_ideographic_supplement.yml +913 -0
  119. data/resources/unicode_data/ethiopic.yml +5729 -0
  120. data/resources/unicode_data/ethiopic_extended.yml +1265 -0
  121. data/resources/unicode_data/ethiopic_extended_a.yml +513 -0
  122. data/resources/unicode_data/ethiopic_supplement.yml +417 -0
  123. data/resources/unicode_data/general_punctuation.yml +1713 -0
  124. data/resources/unicode_data/geometric_shapes.yml +1537 -0
  125. data/resources/unicode_data/georgian.yml +1409 -0
  126. data/resources/unicode_data/georgian_supplement.yml +641 -0
  127. data/resources/unicode_data/glagolitic.yml +1505 -0
  128. data/resources/unicode_data/gothic.yml +433 -0
  129. data/resources/unicode_data/greek_and_coptic.yml +2145 -0
  130. data/resources/unicode_data/greek_extended.yml +3729 -0
  131. data/resources/unicode_data/gujarati.yml +1345 -0
  132. data/resources/unicode_data/gurmukhi.yml +1265 -0
  133. data/resources/unicode_data/halfwidth_and_fullwidth_forms.yml +3601 -0
  134. data/resources/unicode_data/hangul_compatibility_jamo.yml +1505 -0
  135. data/resources/unicode_data/hangul_jamo.yml +4097 -0
  136. data/resources/unicode_data/hangul_jamo_extended_a.yml +465 -0
  137. data/resources/unicode_data/hangul_jamo_extended_b.yml +1153 -0
  138. data/resources/unicode_data/hangul_syllables.yml +33 -0
  139. data/resources/unicode_data/hanunoo.yml +369 -0
  140. data/resources/unicode_data/hebrew.yml +1393 -0
  141. data/resources/unicode_data/high_private_use_surrogates.yml +33 -0
  142. data/resources/unicode_data/high_surrogates.yml +33 -0
  143. data/resources/unicode_data/hiragana.yml +1489 -0
  144. data/resources/unicode_data/ideographic_description_characters.yml +193 -0
  145. data/resources/unicode_data/imperial_aramaic.yml +497 -0
  146. data/resources/unicode_data/inscriptional_pahlavi.yml +433 -0
  147. data/resources/unicode_data/inscriptional_parthian.yml +481 -0
  148. data/resources/unicode_data/ipa_extensions.yml +1537 -0
  149. data/resources/unicode_data/javanese.yml +1457 -0
  150. data/resources/unicode_data/kaithi.yml +1057 -0
  151. data/resources/unicode_data/kana_supplement.yml +33 -0
  152. data/resources/unicode_data/kanbun.yml +257 -0
  153. data/resources/unicode_data/kangxi_radicals.yml +3425 -0
  154. data/resources/unicode_data/kannada.yml +1377 -0
  155. data/resources/unicode_data/katakana.yml +1537 -0
  156. data/resources/unicode_data/katakana_phonetic_extensions.yml +257 -0
  157. data/resources/unicode_data/kayah_li.yml +769 -0
  158. data/resources/unicode_data/kharoshthi.yml +1041 -0
  159. data/resources/unicode_data/khmer.yml +1825 -0
  160. data/resources/unicode_data/khmer_symbols.yml +513 -0
  161. data/resources/unicode_data/lao.yml +1073 -0
  162. data/resources/unicode_data/latin_1_supplement.yml +2049 -0
  163. data/resources/unicode_data/latin_extended_a.yml +2049 -0
  164. data/resources/unicode_data/latin_extended_additional.yml +4097 -0
  165. data/resources/unicode_data/latin_extended_b.yml +3329 -0
  166. data/resources/unicode_data/latin_extended_c.yml +513 -0
  167. data/resources/unicode_data/latin_extended_d.yml +2145 -0
  168. data/resources/unicode_data/lepcha.yml +1185 -0
  169. data/resources/unicode_data/letterlike_symbols.yml +1281 -0
  170. data/resources/unicode_data/limbu.yml +1057 -0
  171. data/resources/unicode_data/linear_b_ideograms.yml +1969 -0
  172. data/resources/unicode_data/linear_b_syllabary.yml +1409 -0
  173. data/resources/unicode_data/lisu.yml +769 -0
  174. data/resources/unicode_data/low_surrogates.yml +33 -0
  175. data/resources/unicode_data/lycian.yml +465 -0
  176. data/resources/unicode_data/lydian.yml +433 -0
  177. data/resources/unicode_data/mahjong_tiles.yml +705 -0
  178. data/resources/unicode_data/malayalam.yml +1569 -0
  179. data/resources/unicode_data/mandaic.yml +465 -0
  180. data/resources/unicode_data/mathematical_alphanumeric_symbols.yml +15937 -0
  181. data/resources/unicode_data/mathematical_operators.yml +4097 -0
  182. data/resources/unicode_data/meetei_mayek.yml +897 -0
  183. data/resources/unicode_data/meetei_mayek_extensions.yml +369 -0
  184. data/resources/unicode_data/meroitic_cursive.yml +417 -0
  185. data/resources/unicode_data/meroitic_hieroglyphs.yml +513 -0
  186. data/resources/unicode_data/miao.yml +2129 -0
  187. data/resources/unicode_data/miscellaneous_mathematical_symbols_a.yml +769 -0
  188. data/resources/unicode_data/miscellaneous_mathematical_symbols_b.yml +2049 -0
  189. data/resources/unicode_data/miscellaneous_symbols.yml +4097 -0
  190. data/resources/unicode_data/miscellaneous_symbols_and_arrows.yml +1393 -0
  191. data/resources/unicode_data/miscellaneous_symbols_and_pictographs.yml +8529 -0
  192. data/resources/unicode_data/miscellaneous_technical.yml +3905 -0
  193. data/resources/unicode_data/modifier_tone_letters.yml +513 -0
  194. data/resources/unicode_data/mongolian.yml +2497 -0
  195. data/resources/unicode_data/musical_symbols.yml +3521 -0
  196. data/resources/unicode_data/myanmar.yml +2561 -0
  197. data/resources/unicode_data/myanmar_extended_a.yml +449 -0
  198. data/resources/unicode_data/new_tai_lue.yml +1329 -0
  199. data/resources/unicode_data/nko.yml +945 -0
  200. data/resources/unicode_data/number_forms.yml +929 -0
  201. data/resources/unicode_data/ogham.yml +465 -0
  202. data/resources/unicode_data/ol_chiki.yml +769 -0
  203. data/resources/unicode_data/old_italic.yml +561 -0
  204. data/resources/unicode_data/old_persian.yml +801 -0
  205. data/resources/unicode_data/old_south_arabian.yml +513 -0
  206. data/resources/unicode_data/old_turkic.yml +1169 -0
  207. data/resources/unicode_data/optical_character_recognition.yml +177 -0
  208. data/resources/unicode_data/oriya.yml +1441 -0
  209. data/resources/unicode_data/osmanya.yml +641 -0
  210. data/resources/unicode_data/phags_pa.yml +897 -0
  211. data/resources/unicode_data/phaistos_disc.yml +737 -0
  212. data/resources/unicode_data/phoenician.yml +465 -0
  213. data/resources/unicode_data/phonetic_extensions.yml +2049 -0
  214. data/resources/unicode_data/phonetic_extensions_supplement.yml +1025 -0
  215. data/resources/unicode_data/playing_cards.yml +945 -0
  216. data/resources/unicode_data/private_use_area.yml +33 -0
  217. data/resources/unicode_data/rejang.yml +593 -0
  218. data/resources/unicode_data/rumi_numeral_symbols.yml +497 -0
  219. data/resources/unicode_data/runic.yml +1297 -0
  220. data/resources/unicode_data/samaritan.yml +977 -0
  221. data/resources/unicode_data/saurashtra.yml +1297 -0
  222. data/resources/unicode_data/sharada.yml +1329 -0
  223. data/resources/unicode_data/shavian.yml +769 -0
  224. data/resources/unicode_data/sinhala.yml +1281 -0
  225. data/resources/unicode_data/small_form_variants.yml +417 -0
  226. data/resources/unicode_data/sora_sompeng.yml +561 -0
  227. data/resources/unicode_data/spacing_modifier_letters.yml +1281 -0
  228. data/resources/unicode_data/specials.yml +81 -0
  229. data/resources/unicode_data/sundanese.yml +1025 -0
  230. data/resources/unicode_data/sundanese_supplement.yml +129 -0
  231. data/resources/unicode_data/superscripts_and_subscripts.yml +673 -0
  232. data/resources/unicode_data/supplemental_arrows_a.yml +257 -0
  233. data/resources/unicode_data/supplemental_arrows_b.yml +2049 -0
  234. data/resources/unicode_data/supplemental_mathematical_operators.yml +4097 -0
  235. data/resources/unicode_data/supplemental_punctuation.yml +961 -0
  236. data/resources/unicode_data/supplementary_private_use_area_a.yml +33 -0
  237. data/resources/unicode_data/supplementary_private_use_area_b.yml +33 -0
  238. data/resources/unicode_data/syloti_nagri.yml +705 -0
  239. data/resources/unicode_data/syriac.yml +1233 -0
  240. data/resources/unicode_data/tagalog.yml +321 -0
  241. data/resources/unicode_data/tagbanwa.yml +289 -0
  242. data/resources/unicode_data/tags.yml +1553 -0
  243. data/resources/unicode_data/tai_le.yml +561 -0
  244. data/resources/unicode_data/tai_tham.yml +2033 -0
  245. data/resources/unicode_data/tai_viet.yml +1153 -0
  246. data/resources/unicode_data/tai_xuan_jing_symbols.yml +1393 -0
  247. data/resources/unicode_data/takri.yml +1057 -0
  248. data/resources/unicode_data/tamil.yml +1153 -0
  249. data/resources/unicode_data/telugu.yml +1489 -0
  250. data/resources/unicode_data/thaana.yml +801 -0
  251. data/resources/unicode_data/thai.yml +1393 -0
  252. data/resources/unicode_data/tibetan.yml +3377 -0
  253. data/resources/unicode_data/tifinagh.yml +945 -0
  254. data/resources/unicode_data/transport_and_map_symbols.yml +1121 -0
  255. data/resources/unicode_data/ugaritic.yml +497 -0
  256. data/resources/unicode_data/unified_canadian_aboriginal_syllabics.yml +10241 -0
  257. data/resources/unicode_data/unified_canadian_aboriginal_syllabics_extended.yml +1121 -0
  258. data/resources/unicode_data/vai.yml +4801 -0
  259. data/resources/unicode_data/variation_selectors.yml +257 -0
  260. data/resources/unicode_data/variation_selectors_supplement.yml +3841 -0
  261. data/resources/unicode_data/vedic_extensions.yml +625 -0
  262. data/resources/unicode_data/vertical_forms.yml +161 -0
  263. data/resources/unicode_data/yi_radicals.yml +881 -0
  264. data/resources/unicode_data/yi_syllables.yml +18641 -0
  265. data/resources/unicode_data/yijing_hexagram_symbols.yml +1025 -0
  266. data/spec/ext/calendars/date_spec.rb +5 -1
  267. data/spec/ext/calendars/datetime_spec.rb +5 -1
  268. data/spec/ext/calendars/time_spec.rb +5 -1
  269. data/spec/ext/numbers/bignum_spec.rb +5 -1
  270. data/spec/ext/numbers/fixnum_spec.rb +5 -1
  271. data/spec/ext/numbers/float_spec.rb +5 -1
  272. data/spec/ext/numbers/localized_number_spec.rb +5 -1
  273. data/spec/ext/strings/string_spec.rb +102 -0
  274. data/spec/ext/strings/symbol_spec.rb +5 -1
  275. data/spec/formatters/base_spec.rb +5 -1
  276. data/spec/formatters/calendars/datetime_formatter_spec.rb +5 -1
  277. data/spec/formatters/numbers/currency_formatter_spec.rb +5 -1
  278. data/spec/formatters/numbers/decimal_formatter_spec.rb +5 -1
  279. data/spec/formatters/numbers/helpers/fraction_spec.rb +5 -1
  280. data/spec/formatters/numbers/helpers/integer_spec.rb +5 -1
  281. data/spec/formatters/numbers/number_formatter_spec.rb +6 -2
  282. data/spec/formatters/numbers/percent_formatter_spec.rb +5 -1
  283. data/spec/formatters/plurals/plural_formatter_spec.rb +205 -0
  284. data/spec/formatters/plurals/rules_spec.rb +28 -28
  285. data/spec/normalizers/NormalizationTest.txt +602 -0
  286. data/spec/normalizers/base_spec.rb +16 -0
  287. data/spec/normalizers/canonical/nfd_spec.rb +50 -0
  288. data/spec/shared/currencies_spec.rb +5 -1
  289. data/spec/shared/languages_spec.rb +5 -1
  290. data/spec/shared/resources_spec.rb +5 -18
  291. data/spec/shared/unicode_data_spec.rb +51 -0
  292. data/spec/spec_helper.rb +6 -3
  293. data/spec/tokenizers/base_spec.rb +3 -0
  294. data/spec/tokenizers/calendars/date_tokenizer_spec.rb +5 -1
  295. data/spec/tokenizers/calendars/datetime_tokenizer_spec.rb +5 -1
  296. data/spec/tokenizers/calendars/time_tokenizer_spec.rb +5 -1
  297. data/spec/tokenizers/key_path_spec.rb +3 -0
  298. data/spec/tokenizers/numbers/number_tokenizer_spec.rb +5 -1
  299. data/spec/tokenizers/token_spec.rb +5 -1
  300. data/spec/twitter_cldr_spec.rb +23 -1
  301. data/spec/utils/interpolation_spec.rb +124 -0
  302. data/spec/utils_spec.rb +32 -0
  303. metadata +285 -21
@@ -0,0 +1,881 @@
1
+ ---
2
+ basic_latin: !ruby/range
3
+ begin: 0
4
+ end: 127
5
+ excl: false
6
+ latin_1_supplement: !ruby/range
7
+ begin: 128
8
+ end: 255
9
+ excl: false
10
+ latin_extended_a: !ruby/range
11
+ begin: 256
12
+ end: 383
13
+ excl: false
14
+ latin_extended_b: !ruby/range
15
+ begin: 384
16
+ end: 591
17
+ excl: false
18
+ ipa_extensions: !ruby/range
19
+ begin: 592
20
+ end: 687
21
+ excl: false
22
+ spacing_modifier_letters: !ruby/range
23
+ begin: 688
24
+ end: 767
25
+ excl: false
26
+ combining_diacritical_marks: !ruby/range
27
+ begin: 768
28
+ end: 879
29
+ excl: false
30
+ greek_and_coptic: !ruby/range
31
+ begin: 880
32
+ end: 1023
33
+ excl: false
34
+ cyrillic: !ruby/range
35
+ begin: 1024
36
+ end: 1279
37
+ excl: false
38
+ cyrillic_supplement: !ruby/range
39
+ begin: 1280
40
+ end: 1327
41
+ excl: false
42
+ armenian: !ruby/range
43
+ begin: 1328
44
+ end: 1423
45
+ excl: false
46
+ hebrew: !ruby/range
47
+ begin: 1424
48
+ end: 1535
49
+ excl: false
50
+ arabic: !ruby/range
51
+ begin: 1536
52
+ end: 1791
53
+ excl: false
54
+ syriac: !ruby/range
55
+ begin: 1792
56
+ end: 1871
57
+ excl: false
58
+ arabic_supplement: !ruby/range
59
+ begin: 1872
60
+ end: 1919
61
+ excl: false
62
+ thaana: !ruby/range
63
+ begin: 1920
64
+ end: 1983
65
+ excl: false
66
+ nko: !ruby/range
67
+ begin: 1984
68
+ end: 2047
69
+ excl: false
70
+ samaritan: !ruby/range
71
+ begin: 2048
72
+ end: 2111
73
+ excl: false
74
+ mandaic: !ruby/range
75
+ begin: 2112
76
+ end: 2143
77
+ excl: false
78
+ arabic_extended_a: !ruby/range
79
+ begin: 2208
80
+ end: 2303
81
+ excl: false
82
+ devanagari: !ruby/range
83
+ begin: 2304
84
+ end: 2431
85
+ excl: false
86
+ bengali: !ruby/range
87
+ begin: 2432
88
+ end: 2559
89
+ excl: false
90
+ gurmukhi: !ruby/range
91
+ begin: 2560
92
+ end: 2687
93
+ excl: false
94
+ gujarati: !ruby/range
95
+ begin: 2688
96
+ end: 2815
97
+ excl: false
98
+ oriya: !ruby/range
99
+ begin: 2816
100
+ end: 2943
101
+ excl: false
102
+ tamil: !ruby/range
103
+ begin: 2944
104
+ end: 3071
105
+ excl: false
106
+ telugu: !ruby/range
107
+ begin: 3072
108
+ end: 3199
109
+ excl: false
110
+ kannada: !ruby/range
111
+ begin: 3200
112
+ end: 3327
113
+ excl: false
114
+ malayalam: !ruby/range
115
+ begin: 3328
116
+ end: 3455
117
+ excl: false
118
+ sinhala: !ruby/range
119
+ begin: 3456
120
+ end: 3583
121
+ excl: false
122
+ thai: !ruby/range
123
+ begin: 3584
124
+ end: 3711
125
+ excl: false
126
+ lao: !ruby/range
127
+ begin: 3712
128
+ end: 3839
129
+ excl: false
130
+ tibetan: !ruby/range
131
+ begin: 3840
132
+ end: 4095
133
+ excl: false
134
+ myanmar: !ruby/range
135
+ begin: 4096
136
+ end: 4255
137
+ excl: false
138
+ georgian: !ruby/range
139
+ begin: 4256
140
+ end: 4351
141
+ excl: false
142
+ hangul_jamo: !ruby/range
143
+ begin: 4352
144
+ end: 4607
145
+ excl: false
146
+ ethiopic: !ruby/range
147
+ begin: 4608
148
+ end: 4991
149
+ excl: false
150
+ ethiopic_supplement: !ruby/range
151
+ begin: 4992
152
+ end: 5023
153
+ excl: false
154
+ cherokee: !ruby/range
155
+ begin: 5024
156
+ end: 5119
157
+ excl: false
158
+ unified_canadian_aboriginal_syllabics: !ruby/range
159
+ begin: 5120
160
+ end: 5759
161
+ excl: false
162
+ ogham: !ruby/range
163
+ begin: 5760
164
+ end: 5791
165
+ excl: false
166
+ runic: !ruby/range
167
+ begin: 5792
168
+ end: 5887
169
+ excl: false
170
+ tagalog: !ruby/range
171
+ begin: 5888
172
+ end: 5919
173
+ excl: false
174
+ hanunoo: !ruby/range
175
+ begin: 5920
176
+ end: 5951
177
+ excl: false
178
+ buhid: !ruby/range
179
+ begin: 5952
180
+ end: 5983
181
+ excl: false
182
+ tagbanwa: !ruby/range
183
+ begin: 5984
184
+ end: 6015
185
+ excl: false
186
+ khmer: !ruby/range
187
+ begin: 6016
188
+ end: 6143
189
+ excl: false
190
+ mongolian: !ruby/range
191
+ begin: 6144
192
+ end: 6319
193
+ excl: false
194
+ unified_canadian_aboriginal_syllabics_extended: !ruby/range
195
+ begin: 6320
196
+ end: 6399
197
+ excl: false
198
+ limbu: !ruby/range
199
+ begin: 6400
200
+ end: 6479
201
+ excl: false
202
+ tai_le: !ruby/range
203
+ begin: 6480
204
+ end: 6527
205
+ excl: false
206
+ new_tai_lue: !ruby/range
207
+ begin: 6528
208
+ end: 6623
209
+ excl: false
210
+ khmer_symbols: !ruby/range
211
+ begin: 6624
212
+ end: 6655
213
+ excl: false
214
+ buginese: !ruby/range
215
+ begin: 6656
216
+ end: 6687
217
+ excl: false
218
+ tai_tham: !ruby/range
219
+ begin: 6688
220
+ end: 6831
221
+ excl: false
222
+ balinese: !ruby/range
223
+ begin: 6912
224
+ end: 7039
225
+ excl: false
226
+ sundanese: !ruby/range
227
+ begin: 7040
228
+ end: 7103
229
+ excl: false
230
+ batak: !ruby/range
231
+ begin: 7104
232
+ end: 7167
233
+ excl: false
234
+ lepcha: !ruby/range
235
+ begin: 7168
236
+ end: 7247
237
+ excl: false
238
+ ol_chiki: !ruby/range
239
+ begin: 7248
240
+ end: 7295
241
+ excl: false
242
+ sundanese_supplement: !ruby/range
243
+ begin: 7360
244
+ end: 7375
245
+ excl: false
246
+ vedic_extensions: !ruby/range
247
+ begin: 7376
248
+ end: 7423
249
+ excl: false
250
+ phonetic_extensions: !ruby/range
251
+ begin: 7424
252
+ end: 7551
253
+ excl: false
254
+ phonetic_extensions_supplement: !ruby/range
255
+ begin: 7552
256
+ end: 7615
257
+ excl: false
258
+ combining_diacritical_marks_supplement: !ruby/range
259
+ begin: 7616
260
+ end: 7679
261
+ excl: false
262
+ latin_extended_additional: !ruby/range
263
+ begin: 7680
264
+ end: 7935
265
+ excl: false
266
+ greek_extended: !ruby/range
267
+ begin: 7936
268
+ end: 8191
269
+ excl: false
270
+ general_punctuation: !ruby/range
271
+ begin: 8192
272
+ end: 8303
273
+ excl: false
274
+ superscripts_and_subscripts: !ruby/range
275
+ begin: 8304
276
+ end: 8351
277
+ excl: false
278
+ currency_symbols: !ruby/range
279
+ begin: 8352
280
+ end: 8399
281
+ excl: false
282
+ combining_diacritical_marks_for_symbols: !ruby/range
283
+ begin: 8400
284
+ end: 8447
285
+ excl: false
286
+ letterlike_symbols: !ruby/range
287
+ begin: 8448
288
+ end: 8527
289
+ excl: false
290
+ number_forms: !ruby/range
291
+ begin: 8528
292
+ end: 8591
293
+ excl: false
294
+ arrows: !ruby/range
295
+ begin: 8592
296
+ end: 8703
297
+ excl: false
298
+ mathematical_operators: !ruby/range
299
+ begin: 8704
300
+ end: 8959
301
+ excl: false
302
+ miscellaneous_technical: !ruby/range
303
+ begin: 8960
304
+ end: 9215
305
+ excl: false
306
+ control_pictures: !ruby/range
307
+ begin: 9216
308
+ end: 9279
309
+ excl: false
310
+ optical_character_recognition: !ruby/range
311
+ begin: 9280
312
+ end: 9311
313
+ excl: false
314
+ enclosed_alphanumerics: !ruby/range
315
+ begin: 9312
316
+ end: 9471
317
+ excl: false
318
+ box_drawing: !ruby/range
319
+ begin: 9472
320
+ end: 9599
321
+ excl: false
322
+ block_elements: !ruby/range
323
+ begin: 9600
324
+ end: 9631
325
+ excl: false
326
+ geometric_shapes: !ruby/range
327
+ begin: 9632
328
+ end: 9727
329
+ excl: false
330
+ miscellaneous_symbols: !ruby/range
331
+ begin: 9728
332
+ end: 9983
333
+ excl: false
334
+ dingbats: !ruby/range
335
+ begin: 9984
336
+ end: 10175
337
+ excl: false
338
+ miscellaneous_mathematical_symbols_a: !ruby/range
339
+ begin: 10176
340
+ end: 10223
341
+ excl: false
342
+ supplemental_arrows_a: !ruby/range
343
+ begin: 10224
344
+ end: 10239
345
+ excl: false
346
+ braille_patterns: !ruby/range
347
+ begin: 10240
348
+ end: 10495
349
+ excl: false
350
+ supplemental_arrows_b: !ruby/range
351
+ begin: 10496
352
+ end: 10623
353
+ excl: false
354
+ miscellaneous_mathematical_symbols_b: !ruby/range
355
+ begin: 10624
356
+ end: 10751
357
+ excl: false
358
+ supplemental_mathematical_operators: !ruby/range
359
+ begin: 10752
360
+ end: 11007
361
+ excl: false
362
+ miscellaneous_symbols_and_arrows: !ruby/range
363
+ begin: 11008
364
+ end: 11263
365
+ excl: false
366
+ glagolitic: !ruby/range
367
+ begin: 11264
368
+ end: 11359
369
+ excl: false
370
+ latin_extended_c: !ruby/range
371
+ begin: 11360
372
+ end: 11391
373
+ excl: false
374
+ coptic: !ruby/range
375
+ begin: 11392
376
+ end: 11519
377
+ excl: false
378
+ georgian_supplement: !ruby/range
379
+ begin: 11520
380
+ end: 11567
381
+ excl: false
382
+ tifinagh: !ruby/range
383
+ begin: 11568
384
+ end: 11647
385
+ excl: false
386
+ ethiopic_extended: !ruby/range
387
+ begin: 11648
388
+ end: 11743
389
+ excl: false
390
+ cyrillic_extended_a: !ruby/range
391
+ begin: 11744
392
+ end: 11775
393
+ excl: false
394
+ supplemental_punctuation: !ruby/range
395
+ begin: 11776
396
+ end: 11903
397
+ excl: false
398
+ cjk_radicals_supplement: !ruby/range
399
+ begin: 11904
400
+ end: 12031
401
+ excl: false
402
+ kangxi_radicals: !ruby/range
403
+ begin: 12032
404
+ end: 12255
405
+ excl: false
406
+ ideographic_description_characters: !ruby/range
407
+ begin: 12272
408
+ end: 12287
409
+ excl: false
410
+ cjk_symbols_and_punctuation: !ruby/range
411
+ begin: 12288
412
+ end: 12351
413
+ excl: false
414
+ hiragana: !ruby/range
415
+ begin: 12352
416
+ end: 12447
417
+ excl: false
418
+ katakana: !ruby/range
419
+ begin: 12448
420
+ end: 12543
421
+ excl: false
422
+ bopomofo: !ruby/range
423
+ begin: 12544
424
+ end: 12591
425
+ excl: false
426
+ hangul_compatibility_jamo: !ruby/range
427
+ begin: 12592
428
+ end: 12687
429
+ excl: false
430
+ kanbun: !ruby/range
431
+ begin: 12688
432
+ end: 12703
433
+ excl: false
434
+ bopomofo_extended: !ruby/range
435
+ begin: 12704
436
+ end: 12735
437
+ excl: false
438
+ cjk_strokes: !ruby/range
439
+ begin: 12736
440
+ end: 12783
441
+ excl: false
442
+ katakana_phonetic_extensions: !ruby/range
443
+ begin: 12784
444
+ end: 12799
445
+ excl: false
446
+ enclosed_cjk_letters_and_months: !ruby/range
447
+ begin: 12800
448
+ end: 13055
449
+ excl: false
450
+ cjk_compatibility: !ruby/range
451
+ begin: 13056
452
+ end: 13311
453
+ excl: false
454
+ cjk_unified_ideographs_extension_a: !ruby/range
455
+ begin: 13312
456
+ end: 19903
457
+ excl: false
458
+ yijing_hexagram_symbols: !ruby/range
459
+ begin: 19904
460
+ end: 19967
461
+ excl: false
462
+ cjk_unified_ideographs: !ruby/range
463
+ begin: 19968
464
+ end: 40959
465
+ excl: false
466
+ yi_syllables: !ruby/range
467
+ begin: 40960
468
+ end: 42127
469
+ excl: false
470
+ yi_radicals: !ruby/range
471
+ begin: 42128
472
+ end: 42191
473
+ excl: false
474
+ lisu: !ruby/range
475
+ begin: 42192
476
+ end: 42239
477
+ excl: false
478
+ vai: !ruby/range
479
+ begin: 42240
480
+ end: 42559
481
+ excl: false
482
+ cyrillic_extended_b: !ruby/range
483
+ begin: 42560
484
+ end: 42655
485
+ excl: false
486
+ bamum: !ruby/range
487
+ begin: 42656
488
+ end: 42751
489
+ excl: false
490
+ modifier_tone_letters: !ruby/range
491
+ begin: 42752
492
+ end: 42783
493
+ excl: false
494
+ latin_extended_d: !ruby/range
495
+ begin: 42784
496
+ end: 43007
497
+ excl: false
498
+ syloti_nagri: !ruby/range
499
+ begin: 43008
500
+ end: 43055
501
+ excl: false
502
+ common_indic_number_forms: !ruby/range
503
+ begin: 43056
504
+ end: 43071
505
+ excl: false
506
+ phags_pa: !ruby/range
507
+ begin: 43072
508
+ end: 43135
509
+ excl: false
510
+ saurashtra: !ruby/range
511
+ begin: 43136
512
+ end: 43231
513
+ excl: false
514
+ devanagari_extended: !ruby/range
515
+ begin: 43232
516
+ end: 43263
517
+ excl: false
518
+ kayah_li: !ruby/range
519
+ begin: 43264
520
+ end: 43311
521
+ excl: false
522
+ rejang: !ruby/range
523
+ begin: 43312
524
+ end: 43359
525
+ excl: false
526
+ hangul_jamo_extended_a: !ruby/range
527
+ begin: 43360
528
+ end: 43391
529
+ excl: false
530
+ javanese: !ruby/range
531
+ begin: 43392
532
+ end: 43487
533
+ excl: false
534
+ cham: !ruby/range
535
+ begin: 43520
536
+ end: 43615
537
+ excl: false
538
+ myanmar_extended_a: !ruby/range
539
+ begin: 43616
540
+ end: 43647
541
+ excl: false
542
+ tai_viet: !ruby/range
543
+ begin: 43648
544
+ end: 43743
545
+ excl: false
546
+ meetei_mayek_extensions: !ruby/range
547
+ begin: 43744
548
+ end: 43775
549
+ excl: false
550
+ ethiopic_extended_a: !ruby/range
551
+ begin: 43776
552
+ end: 43823
553
+ excl: false
554
+ meetei_mayek: !ruby/range
555
+ begin: 43968
556
+ end: 44031
557
+ excl: false
558
+ hangul_syllables: !ruby/range
559
+ begin: 44032
560
+ end: 55215
561
+ excl: false
562
+ hangul_jamo_extended_b: !ruby/range
563
+ begin: 55216
564
+ end: 55295
565
+ excl: false
566
+ high_surrogates: !ruby/range
567
+ begin: 55296
568
+ end: 56191
569
+ excl: false
570
+ high_private_use_surrogates: !ruby/range
571
+ begin: 56192
572
+ end: 56319
573
+ excl: false
574
+ low_surrogates: !ruby/range
575
+ begin: 56320
576
+ end: 57343
577
+ excl: false
578
+ private_use_area: !ruby/range
579
+ begin: 57344
580
+ end: 63743
581
+ excl: false
582
+ cjk_compatibility_ideographs: !ruby/range
583
+ begin: 63744
584
+ end: 64255
585
+ excl: false
586
+ alphabetic_presentation_forms: !ruby/range
587
+ begin: 64256
588
+ end: 64335
589
+ excl: false
590
+ arabic_presentation_forms_a: !ruby/range
591
+ begin: 64336
592
+ end: 65023
593
+ excl: false
594
+ variation_selectors: !ruby/range
595
+ begin: 65024
596
+ end: 65039
597
+ excl: false
598
+ vertical_forms: !ruby/range
599
+ begin: 65040
600
+ end: 65055
601
+ excl: false
602
+ combining_half_marks: !ruby/range
603
+ begin: 65056
604
+ end: 65071
605
+ excl: false
606
+ cjk_compatibility_forms: !ruby/range
607
+ begin: 65072
608
+ end: 65103
609
+ excl: false
610
+ small_form_variants: !ruby/range
611
+ begin: 65104
612
+ end: 65135
613
+ excl: false
614
+ arabic_presentation_forms_b: !ruby/range
615
+ begin: 65136
616
+ end: 65279
617
+ excl: false
618
+ halfwidth_and_fullwidth_forms: !ruby/range
619
+ begin: 65280
620
+ end: 65519
621
+ excl: false
622
+ specials: !ruby/range
623
+ begin: 65520
624
+ end: 65535
625
+ excl: false
626
+ linear_b_syllabary: !ruby/range
627
+ begin: 65536
628
+ end: 65663
629
+ excl: false
630
+ linear_b_ideograms: !ruby/range
631
+ begin: 65664
632
+ end: 65791
633
+ excl: false
634
+ aegean_numbers: !ruby/range
635
+ begin: 65792
636
+ end: 65855
637
+ excl: false
638
+ ancient_greek_numbers: !ruby/range
639
+ begin: 65856
640
+ end: 65935
641
+ excl: false
642
+ ancient_symbols: !ruby/range
643
+ begin: 65936
644
+ end: 65999
645
+ excl: false
646
+ phaistos_disc: !ruby/range
647
+ begin: 66000
648
+ end: 66047
649
+ excl: false
650
+ lycian: !ruby/range
651
+ begin: 66176
652
+ end: 66207
653
+ excl: false
654
+ carian: !ruby/range
655
+ begin: 66208
656
+ end: 66271
657
+ excl: false
658
+ old_italic: !ruby/range
659
+ begin: 66304
660
+ end: 66351
661
+ excl: false
662
+ gothic: !ruby/range
663
+ begin: 66352
664
+ end: 66383
665
+ excl: false
666
+ ugaritic: !ruby/range
667
+ begin: 66432
668
+ end: 66463
669
+ excl: false
670
+ old_persian: !ruby/range
671
+ begin: 66464
672
+ end: 66527
673
+ excl: false
674
+ deseret: !ruby/range
675
+ begin: 66560
676
+ end: 66639
677
+ excl: false
678
+ shavian: !ruby/range
679
+ begin: 66640
680
+ end: 66687
681
+ excl: false
682
+ osmanya: !ruby/range
683
+ begin: 66688
684
+ end: 66735
685
+ excl: false
686
+ cypriot_syllabary: !ruby/range
687
+ begin: 67584
688
+ end: 67647
689
+ excl: false
690
+ imperial_aramaic: !ruby/range
691
+ begin: 67648
692
+ end: 67679
693
+ excl: false
694
+ phoenician: !ruby/range
695
+ begin: 67840
696
+ end: 67871
697
+ excl: false
698
+ lydian: !ruby/range
699
+ begin: 67872
700
+ end: 67903
701
+ excl: false
702
+ meroitic_hieroglyphs: !ruby/range
703
+ begin: 67968
704
+ end: 67999
705
+ excl: false
706
+ meroitic_cursive: !ruby/range
707
+ begin: 68000
708
+ end: 68095
709
+ excl: false
710
+ kharoshthi: !ruby/range
711
+ begin: 68096
712
+ end: 68191
713
+ excl: false
714
+ old_south_arabian: !ruby/range
715
+ begin: 68192
716
+ end: 68223
717
+ excl: false
718
+ avestan: !ruby/range
719
+ begin: 68352
720
+ end: 68415
721
+ excl: false
722
+ inscriptional_parthian: !ruby/range
723
+ begin: 68416
724
+ end: 68447
725
+ excl: false
726
+ inscriptional_pahlavi: !ruby/range
727
+ begin: 68448
728
+ end: 68479
729
+ excl: false
730
+ old_turkic: !ruby/range
731
+ begin: 68608
732
+ end: 68687
733
+ excl: false
734
+ rumi_numeral_symbols: !ruby/range
735
+ begin: 69216
736
+ end: 69247
737
+ excl: false
738
+ brahmi: !ruby/range
739
+ begin: 69632
740
+ end: 69759
741
+ excl: false
742
+ kaithi: !ruby/range
743
+ begin: 69760
744
+ end: 69839
745
+ excl: false
746
+ sora_sompeng: !ruby/range
747
+ begin: 69840
748
+ end: 69887
749
+ excl: false
750
+ chakma: !ruby/range
751
+ begin: 69888
752
+ end: 69967
753
+ excl: false
754
+ sharada: !ruby/range
755
+ begin: 70016
756
+ end: 70111
757
+ excl: false
758
+ takri: !ruby/range
759
+ begin: 71296
760
+ end: 71375
761
+ excl: false
762
+ cuneiform: !ruby/range
763
+ begin: 73728
764
+ end: 74751
765
+ excl: false
766
+ cuneiform_numbers_and_punctuation: !ruby/range
767
+ begin: 74752
768
+ end: 74879
769
+ excl: false
770
+ egyptian_hieroglyphs: !ruby/range
771
+ begin: 77824
772
+ end: 78895
773
+ excl: false
774
+ bamum_supplement: !ruby/range
775
+ begin: 92160
776
+ end: 92735
777
+ excl: false
778
+ miao: !ruby/range
779
+ begin: 93952
780
+ end: 94111
781
+ excl: false
782
+ kana_supplement: !ruby/range
783
+ begin: 110592
784
+ end: 110847
785
+ excl: false
786
+ byzantine_musical_symbols: !ruby/range
787
+ begin: 118784
788
+ end: 119039
789
+ excl: false
790
+ musical_symbols: !ruby/range
791
+ begin: 119040
792
+ end: 119295
793
+ excl: false
794
+ ancient_greek_musical_notation: !ruby/range
795
+ begin: 119296
796
+ end: 119375
797
+ excl: false
798
+ tai_xuan_jing_symbols: !ruby/range
799
+ begin: 119552
800
+ end: 119647
801
+ excl: false
802
+ counting_rod_numerals: !ruby/range
803
+ begin: 119648
804
+ end: 119679
805
+ excl: false
806
+ mathematical_alphanumeric_symbols: !ruby/range
807
+ begin: 119808
808
+ end: 120831
809
+ excl: false
810
+ arabic_mathematical_alphabetic_symbols: !ruby/range
811
+ begin: 126464
812
+ end: 126719
813
+ excl: false
814
+ mahjong_tiles: !ruby/range
815
+ begin: 126976
816
+ end: 127023
817
+ excl: false
818
+ domino_tiles: !ruby/range
819
+ begin: 127024
820
+ end: 127135
821
+ excl: false
822
+ playing_cards: !ruby/range
823
+ begin: 127136
824
+ end: 127231
825
+ excl: false
826
+ enclosed_alphanumeric_supplement: !ruby/range
827
+ begin: 127232
828
+ end: 127487
829
+ excl: false
830
+ enclosed_ideographic_supplement: !ruby/range
831
+ begin: 127488
832
+ end: 127743
833
+ excl: false
834
+ miscellaneous_symbols_and_pictographs: !ruby/range
835
+ begin: 127744
836
+ end: 128511
837
+ excl: false
838
+ emoticons: !ruby/range
839
+ begin: 128512
840
+ end: 128591
841
+ excl: false
842
+ transport_and_map_symbols: !ruby/range
843
+ begin: 128640
844
+ end: 128767
845
+ excl: false
846
+ alchemical_symbols: !ruby/range
847
+ begin: 128768
848
+ end: 128895
849
+ excl: false
850
+ cjk_unified_ideographs_extension_b: !ruby/range
851
+ begin: 131072
852
+ end: 173791
853
+ excl: false
854
+ cjk_unified_ideographs_extension_c: !ruby/range
855
+ begin: 173824
856
+ end: 177983
857
+ excl: false
858
+ cjk_unified_ideographs_extension_d: !ruby/range
859
+ begin: 177984
860
+ end: 178207
861
+ excl: false
862
+ cjk_compatibility_ideographs_supplement: !ruby/range
863
+ begin: 194560
864
+ end: 195103
865
+ excl: false
866
+ tags: !ruby/range
867
+ begin: 917504
868
+ end: 917631
869
+ excl: false
870
+ variation_selectors_supplement: !ruby/range
871
+ begin: 917760
872
+ end: 917999
873
+ excl: false
874
+ supplementary_private_use_area_a: !ruby/range
875
+ begin: 983040
876
+ end: 1048575
877
+ excl: false
878
+ supplementary_private_use_area_b: !ruby/range
879
+ begin: 1048576
880
+ end: 1114111
881
+ excl: false