Module:Unicode data/scripts

Documentation for this module may be created at Module:Unicode data/scripts/doc

---- Module:Unicode data/scripts  (static data; no mw.ext.data)
return {
  singles = {},

  -- Minimal but safe ranges (expand later if you like)
  ranges = {
    -- Common/ASCII pieces
    {0x0000,0x002F,'Zyyy'},{0x0030,0x0039,'Zyyy'},{0x003A,0x0040,'Zyyy'},
    {0x005B,0x0060,'Zyyy'},{0x007B,0x007E,'Zyyy'},

    -- Latin
    {0x0041,0x005A,'Latn'},{0x0061,0x007A,'Latn'},
    {0x00C0,0x00FF,'Latn'},      -- rough Latin-1
    {0x0100,0x017F,'Latn'},      -- Latin Extended-A

    -- Greek
    {0x0370,0x03FF,'Grek'},

    -- Japanese
    {0x3040,0x309F,'Hira'},      -- Hiragana
    {0x30A0,0x30FF,'Kana'},      -- Katakana
    {0x31F0,0x31FF,'Kana'},      -- Katakana Phonetic Extensions
    {0x3400,0x4DBF,'Hani'},      -- CJK Ext A
    {0x4E00,0x9FFF,'Hani'},      -- CJK Unified Ideographs

    -- Combining (Inherited) + punctuation (Common)
    {0x0300,0x036F,'Zinh'},
    {0x2000,0x206F,'Zyyy'},
  },

  -- Needed by is_rtl()
  rtl = { Hebr=true, Arab=true, Syrc=true, Thaa=true, Nkoo=true, Adlm=true },
}