src/Worksheets/Utils/Char.hs

   1 module Worksheets.Utils.Char (
   2   module Worksheets.Utils.Char,
   3   module Data.Char,
   4 ) where
   5
   6 import Data.Char
   7 import Data.List qualified as List
   8 import Data.Set qualified as Set
   9 import Worksheets.Utils.Prelude
  10
  11 data UnicodeBlock
  12   = UnicodeBlockAlphabetic_Presentation_Forms
  13   | UnicodeBlockArabic
  14   | UnicodeBlockArabic_Presentation_FormsA
  15   | UnicodeBlockArabic_Presentation_FormsB
  16   | UnicodeBlockArmenian
  17   | UnicodeBlockArrows
  18   | UnicodeBlockLatin UnicodeBlockLatin
  19   | UnicodeBlockBengali
  20   | UnicodeBlockBlock_Elements
  21   | UnicodeBlockBopomofo
  22   | UnicodeBlockBopomofo_Extended
  23   | UnicodeBlockBox_Drawing
  24   | UnicodeBlockBraille_Patterns
  25   | UnicodeBlockBuhid
  26   | UnicodeBlockCJK UnicodeBlockCJK
  27   | UnicodeBlockCherokee
  28   | UnicodeBlockCombining_Diacritical_Marks
  29   | UnicodeBlockCombining_Diacritical_Marks_for_Symbols
  30   | UnicodeBlockCombining_Half_Marks
  31   | UnicodeBlockControl_Pictures
  32   | UnicodeBlockCurrency_Symbols
  33   | UnicodeBlockCyrillic
  34   | UnicodeBlockCyrillic_Supplementary
  35   | UnicodeBlockDevanagari
  36   | UnicodeBlockDingbats
  37   | UnicodeBlockEnclosed_Alphanumerics
  38   | UnicodeBlockEthiopic
  39   | UnicodeBlockGeneral_Punctuation
  40   | UnicodeBlockGeometric_Shapes
  41   | UnicodeBlockGeorgian
  42   | UnicodeBlockGreek_Extended
  43   | UnicodeBlockGreek_and_Coptic
  44   | UnicodeBlockGujarati
  45   | UnicodeBlockGurmukhi
  46   | UnicodeBlockHalfwidth_and_Fullwidth_Forms
  47   | UnicodeBlockHangul_Compatibility_Jamo
  48   | UnicodeBlockHangul_Jamo
  49   | UnicodeBlockHangul_Syllables
  50   | UnicodeBlockHanunoo
  51   | UnicodeBlockHebrew
  52   | UnicodeBlockHigh_Private_Use_Surrogates
  53   | UnicodeBlockHigh_Surrogates
  54   | UnicodeBlockHiragana
  55   | UnicodeBlockIPA_Extensions
  56   | UnicodeBlockIdeographic_Description_Characters
  57   | UnicodeBlockKanbun
  58   | UnicodeBlockKangxi_Radicals
  59   | UnicodeBlockKannada
  60   | UnicodeBlockKatakana
  61   | UnicodeBlockKatakana_Phonetic_Extensions
  62   | UnicodeBlockKhmer
  63   | UnicodeBlockKhmer_Symbols
  64   | UnicodeBlockLao
  65   | UnicodeBlockLetterlike_Symbols
  66   | UnicodeBlockLimbu
  67   | UnicodeBlockLow_Surrogates
  68   | UnicodeBlockMalayalam
  69   | UnicodeBlockMathematical_Operators
  70   | UnicodeBlockMiscellaneous_Mathematical_SymbolsA
  71   | UnicodeBlockMiscellaneous_Mathematical_SymbolsB
  72   | UnicodeBlockMiscellaneous_Symbols
  73   | UnicodeBlockMiscellaneous_Symbols_and_Arrows
  74   | UnicodeBlockMiscellaneous_Technical
  75   | UnicodeBlockMongolian
  76   | UnicodeBlockMyanmar
  77   | UnicodeBlockNumber_Forms
  78   | UnicodeBlockOgham
  79   | UnicodeBlockOptical_Character_Recognition
  80   | UnicodeBlockOriya
  81   | UnicodeBlockPhonetic_Extensions
  82   | UnicodeBlockPrivate_Use_Area
  83   | UnicodeBlockRunic
  84   | UnicodeBlockSinhala
  85   | UnicodeBlockSmall_Form_Variants
  86   | UnicodeBlockSpacing_Modifier_Letters
  87   | UnicodeBlockSpecials
  88   | UnicodeBlockSuperscripts_and_Subscripts
  89   | UnicodeBlockSupplemental_ArrowsA
  90   | UnicodeBlockSupplemental_ArrowsB
  91   | UnicodeBlockSupplemental_Mathematical_Operators
  92   | UnicodeBlockSyriac
  93   | UnicodeBlockTagalog
  94   | UnicodeBlockTagbanwa
  95   | UnicodeBlockTai_Le
  96   | UnicodeBlockTamil
  97   | UnicodeBlockTelugu
  98   | UnicodeBlockThaana
  99   | UnicodeBlockThai
 100   | UnicodeBlockTibetan
 101   | UnicodeBlockUnified_Canadian_Aboriginal_Syllabics
 102   | UnicodeBlockVariation_Selectors
 103   | UnicodeBlockYi_Radicals
 104   | UnicodeBlockYi_Syllables
 105   | UnicodeBlockYijing_Hexagram_Symbols
 106   deriving (Eq, Ord, Show)
 107
 108 unicodeBlocks =
 109   [ unicodeBlockCJK
 110   , unicodeBlockLatin
 111   , [ UnicodeBlockHalfwidth_and_Fullwidth_Forms
 112     , UnicodeBlockMiscellaneous_Technical
 113     ]
 114       & Set.fromList
 115   ]
 116     & mconcat
 117
 118 unicodeBlockCJK = UnicodeBlockCJK <$> enumAll & Set.fromList
 119 unicodeBlockLatin = UnicodeBlockLatin <$> enumAll & Set.fromList
 120
 121 data UnicodeBlockLatin
 122   = UnicodeBlockLatin_Basic
 123   | UnicodeBlockLatin1_Supplement
 124   | UnicodeBlockLatin_ExtendedA
 125   | UnicodeBlockLatin_ExtendedB
 126   | UnicodeBlockLatin_Extended_Additional
 127   deriving (Eq, Ord, Show, Enum)
 128
 129 data UnicodeBlockCJK
 130   = UnicodeBlockCJK_Compatibility
 131   | UnicodeBlockCJK_Compatibility_Forms
 132   | UnicodeBlockCJK_Compatibility_Ideographs
 133   | UnicodeBlockCJK_Radicals_Supplement
 134   | UnicodeBlockCJK_Symbols_and_Punctuation
 135   | -- | CJK Unified Ideographs: U+4E00 to U+9FFF.
 136     -- This block contains the most commonly used Chinese characters in modern writing.
 137     UnicodeBlockCJK_Unified_Ideographs
 138   | -- | CJK Unified Ideographs Extension A: U+3400 to U+4DBF.
 139     -- Includes rare and historical characters.
 140     UnicodeBlockCJK_Unified_Ideographs_Extension_A
 141   | -- | CJK Unified Ideographs Extension B: U+20000 to U+2A6DF.
 142     -- Contains rare and historic characters, often used in academic or specialized contexts.
 143     UnicodeBlockCJK_Unified_Ideographs_Extension_B
 144   | -- | CJK Unified Ideographs Extension C: U+2A700 to U+2B73F.
 145     -- Include additional rare and historic characters.
 146     UnicodeBlockCJK_Unified_Ideographs_Extension_C
 147   | -- | CJK Unified Ideographs Extension D: U+2B740 to U+2B81F.
 148     -- Include additional rare and historic characters.
 149     UnicodeBlockCJK_Unified_Ideographs_Extension_D
 150   | -- | CJK Unified Ideographs Extension E: U+2B820 to U+2CEAF.
 151     -- Include additional rare and historic characters.
 152     UnicodeBlockCJK_Unified_Ideographs_Extension_E
 153   | -- | CJK Unified Ideographs Extension F: U+2CEB0 to U+2EBEF.
 154     -- Include additional rare and historic characters.
 155     UnicodeBlockCJK_Unified_Ideographs_Extension_F
 156   | -- | CJK Unified Ideographs Extension G: U+30000 to U+3134F.
 157     -- Include additional rare and historic characters.
 158     UnicodeBlockCJK_Unified_Ideographs_Extension_G
 159   | -- | CJK Unified Ideographs Extension H: U+31350 to U+323AF.
 160     -- Include additional rare and historic characters.
 161     UnicodeBlockCJK_Unified_Ideographs_Extension_H
 162   | UnicodeBlockCJK_Enclosed_Letters_and_Months
 163   deriving (Eq, Ord, Show, Enum)
 164
 165 -- TODO:
 166 -- CJK Compatibility Ideographs: U+F900 to U+FAFF
 167 -- Contains duplicate characters and variants for compatibility with older encodings.
 168
 169 -- CJK Compatibility Ideographs Supplement: U+2F800 to U+2FA1F
 170 -- Includes unifiable variants of ideographs.
 171
 172 unicodeBlock c
 173   | '\x0000' <= c && c <= '\x007F' = Just $ UnicodeBlockLatin $ UnicodeBlockLatin_Basic
 174   | '\x0080' <= c && c <= '\x00FF' = Just $ UnicodeBlockLatin $ UnicodeBlockLatin1_Supplement
 175   | '\x0100' <= c && c <= '\x017F' = Just $ UnicodeBlockLatin $ UnicodeBlockLatin_ExtendedA
 176   | '\x0180' <= c && c <= '\x024F' = Just $ UnicodeBlockLatin $ UnicodeBlockLatin_ExtendedB
 177   | '\x0250' <= c && c <= '\x02AF' = Just UnicodeBlockIPA_Extensions
 178   | '\x02B0' <= c && c <= '\x02FF' = Just UnicodeBlockSpacing_Modifier_Letters
 179   | '\x0300' <= c && c <= '\x036F' = Just UnicodeBlockCombining_Diacritical_Marks
 180   | '\x0370' <= c && c <= '\x03FF' = Just UnicodeBlockGreek_and_Coptic
 181   | '\x0400' <= c && c <= '\x04FF' = Just UnicodeBlockCyrillic
 182   | '\x0500' <= c && c <= '\x052F' = Just UnicodeBlockCyrillic_Supplementary
 183   | '\x0530' <= c && c <= '\x058F' = Just UnicodeBlockArmenian
 184   | '\x0590' <= c && c <= '\x05FF' = Just UnicodeBlockHebrew
 185   | '\x0600' <= c && c <= '\x06FF' = Just UnicodeBlockArabic
 186   | '\x0700' <= c && c <= '\x074F' = Just UnicodeBlockSyriac
 187   | '\x0780' <= c && c <= '\x07BF' = Just UnicodeBlockThaana
 188   | '\x0900' <= c && c <= '\x097F' = Just UnicodeBlockDevanagari
 189   | '\x0980' <= c && c <= '\x09FF' = Just UnicodeBlockBengali
 190   | '\x0A00' <= c && c <= '\x0A7F' = Just UnicodeBlockGurmukhi
 191   | '\x0A80' <= c && c <= '\x0AFF' = Just UnicodeBlockGujarati
 192   | '\x0B00' <= c && c <= '\x0B7F' = Just UnicodeBlockOriya
 193   | '\x0B80' <= c && c <= '\x0BFF' = Just UnicodeBlockTamil
 194   | '\x0C00' <= c && c <= '\x0C7F' = Just UnicodeBlockTelugu
 195   | '\x0C80' <= c && c <= '\x0CFF' = Just UnicodeBlockKannada
 196   | '\x0D00' <= c && c <= '\x0D7F' = Just UnicodeBlockMalayalam
 197   | '\x0D80' <= c && c <= '\x0DFF' = Just UnicodeBlockSinhala
 198   | '\x0E00' <= c && c <= '\x0E7F' = Just UnicodeBlockThai
 199   | '\x0E80' <= c && c <= '\x0EFF' = Just UnicodeBlockLao
 200   | '\x0F00' <= c && c <= '\x0FFF' = Just UnicodeBlockTibetan
 201   | '\x1000' <= c && c <= '\x109F' = Just UnicodeBlockMyanmar
 202   | '\x10A0' <= c && c <= '\x10FF' = Just UnicodeBlockGeorgian
 203   | '\x1100' <= c && c <= '\x11FF' = Just UnicodeBlockHangul_Jamo
 204   | '\x1200' <= c && c <= '\x137F' = Just UnicodeBlockEthiopic
 205   | '\x13A0' <= c && c <= '\x13FF' = Just UnicodeBlockCherokee
 206   | '\x1400' <= c && c <= '\x167F' = Just UnicodeBlockUnified_Canadian_Aboriginal_Syllabics
 207   | '\x1680' <= c && c <= '\x169F' = Just UnicodeBlockOgham
 208   | '\x16A0' <= c && c <= '\x16FF' = Just UnicodeBlockRunic
 209   | '\x1700' <= c && c <= '\x171F' = Just UnicodeBlockTagalog
 210   | '\x1720' <= c && c <= '\x173F' = Just UnicodeBlockHanunoo
 211   | '\x1740' <= c && c <= '\x175F' = Just UnicodeBlockBuhid
 212   | '\x1760' <= c && c <= '\x177F' = Just UnicodeBlockTagbanwa
 213   | '\x1780' <= c && c <= '\x17FF' = Just UnicodeBlockKhmer
 214   | '\x1800' <= c && c <= '\x18AF' = Just UnicodeBlockMongolian
 215   | '\x1900' <= c && c <= '\x194F' = Just UnicodeBlockLimbu
 216   | '\x1950' <= c && c <= '\x197F' = Just UnicodeBlockTai_Le
 217   | '\x19E0' <= c && c <= '\x19FF' = Just UnicodeBlockKhmer_Symbols
 218   | '\x1D00' <= c && c <= '\x1D7F' = Just UnicodeBlockPhonetic_Extensions
 219   | '\x1E00' <= c && c <= '\x1EFF' = Just $ UnicodeBlockLatin $ UnicodeBlockLatin_Extended_Additional
 220   | '\x1F00' <= c && c <= '\x1FFF' = Just UnicodeBlockGreek_Extended
 221   | '\x2000' <= c && c <= '\x206F' = Just UnicodeBlockGeneral_Punctuation
 222   | '\x2070' <= c && c <= '\x209F' = Just UnicodeBlockSuperscripts_and_Subscripts
 223   | '\x20A0' <= c && c <= '\x20CF' = Just UnicodeBlockCurrency_Symbols
 224   | '\x20D0' <= c && c <= '\x20FF' = Just UnicodeBlockCombining_Diacritical_Marks_for_Symbols
 225   | '\x2100' <= c && c <= '\x214F' = Just UnicodeBlockLetterlike_Symbols
 226   | '\x2150' <= c && c <= '\x218F' = Just UnicodeBlockNumber_Forms
 227   | '\x2190' <= c && c <= '\x21FF' = Just UnicodeBlockArrows
 228   | '\x2200' <= c && c <= '\x22FF' = Just UnicodeBlockMathematical_Operators
 229   | '\x2300' <= c && c <= '\x23FF' = Just UnicodeBlockMiscellaneous_Technical
 230   | '\x2400' <= c && c <= '\x243F' = Just UnicodeBlockControl_Pictures
 231   | '\x2440' <= c && c <= '\x245F' = Just UnicodeBlockOptical_Character_Recognition
 232   | '\x2460' <= c && c <= '\x24FF' = Just UnicodeBlockEnclosed_Alphanumerics
 233   | '\x2500' <= c && c <= '\x257F' = Just UnicodeBlockBox_Drawing
 234   | '\x2580' <= c && c <= '\x259F' = Just UnicodeBlockBlock_Elements
 235   | '\x25A0' <= c && c <= '\x25FF' = Just UnicodeBlockGeometric_Shapes
 236   | '\x2600' <= c && c <= '\x26FF' = Just UnicodeBlockMiscellaneous_Symbols
 237   | '\x2700' <= c && c <= '\x27BF' = Just UnicodeBlockDingbats
 238   | '\x27C0' <= c && c <= '\x27EF' = Just UnicodeBlockMiscellaneous_Mathematical_SymbolsA
 239   | '\x27F0' <= c && c <= '\x27FF' = Just UnicodeBlockSupplemental_ArrowsA
 240   | '\x2800' <= c && c <= '\x28FF' = Just UnicodeBlockBraille_Patterns
 241   | '\x2900' <= c && c <= '\x297F' = Just UnicodeBlockSupplemental_ArrowsB
 242   | '\x2980' <= c && c <= '\x29FF' = Just UnicodeBlockMiscellaneous_Mathematical_SymbolsB
 243   | '\x2A00' <= c && c <= '\x2AFF' = Just UnicodeBlockSupplemental_Mathematical_Operators
 244   | '\x2B00' <= c && c <= '\x2BFF' = Just UnicodeBlockMiscellaneous_Symbols_and_Arrows
 245   | '\x2E80' <= c && c <= '\x2EFF' = Just $ UnicodeBlockCJK $ UnicodeBlockCJK_Radicals_Supplement
 246   | '\x2F00' <= c && c <= '\x2FDF' = Just UnicodeBlockKangxi_Radicals
 247   | '\x2FF0' <= c && c <= '\x2FFF' = Just UnicodeBlockIdeographic_Description_Characters
 248   | '\x3000' <= c && c <= '\x303F' = Just $ UnicodeBlockCJK $ UnicodeBlockCJK_Symbols_and_Punctuation
 249   | '\x3040' <= c && c <= '\x309F' = Just UnicodeBlockHiragana
 250   | '\x30A0' <= c && c <= '\x30FF' = Just UnicodeBlockKatakana
 251   | '\x3100' <= c && c <= '\x312F' = Just UnicodeBlockBopomofo
 252   | '\x3130' <= c && c <= '\x318F' = Just UnicodeBlockHangul_Compatibility_Jamo
 253   | '\x3190' <= c && c <= '\x319F' = Just UnicodeBlockKanbun
 254   | '\x31A0' <= c && c <= '\x31BF' = Just UnicodeBlockBopomofo_Extended
 255   | '\x31F0' <= c && c <= '\x31FF' = Just UnicodeBlockKatakana_Phonetic_Extensions
 256   | '\x3200' <= c && c <= '\x32FF' = Just $ UnicodeBlockCJK $ UnicodeBlockCJK_Enclosed_Letters_and_Months
 257   | '\x3300' <= c && c <= '\x33FF' = Just $ UnicodeBlockCJK $ UnicodeBlockCJK_Compatibility
 258   | '\x3400' <= c && c <= '\x4DBF' = Just $ UnicodeBlockCJK $ UnicodeBlockCJK_Unified_Ideographs_Extension_A
 259   | '\x4DC0' <= c && c <= '\x4DFF' = Just UnicodeBlockYijing_Hexagram_Symbols
 260   | '\x4E00' <= c && c <= '\x9FFF' = Just $ UnicodeBlockCJK $ UnicodeBlockCJK_Unified_Ideographs
 261   | '\xA000' <= c && c <= '\xA48F' = Just UnicodeBlockYi_Syllables
 262   | '\xA490' <= c && c <= '\xA4CF' = Just UnicodeBlockYi_Radicals
 263   | '\xAC00' <= c && c <= '\xD7AF' = Just UnicodeBlockHangul_Syllables
 264   | '\xD800' <= c && c <= '\xDB7F' = Just UnicodeBlockHigh_Surrogates
 265   | '\xDB80' <= c && c <= '\xDBFF' = Just UnicodeBlockHigh_Private_Use_Surrogates
 266   | '\xDC00' <= c && c <= '\xDFFF' = Just UnicodeBlockLow_Surrogates
 267   | '\xE000' <= c && c <= '\xF8FF' = Just UnicodeBlockPrivate_Use_Area
 268   | '\xF900' <= c && c <= '\xFAFF' = Just $ UnicodeBlockCJK $ UnicodeBlockCJK_Compatibility_Ideographs
 269   | '\xFB00' <= c && c <= '\xFB4F' = Just UnicodeBlockAlphabetic_Presentation_Forms
 270   | '\xFB50' <= c && c <= '\xFDFF' = Just UnicodeBlockArabic_Presentation_FormsA
 271   | '\xFE00' <= c && c <= '\xFE0F' = Just UnicodeBlockVariation_Selectors
 272   | '\xFE20' <= c && c <= '\xFE2F' = Just UnicodeBlockCombining_Half_Marks
 273   | '\xFE30' <= c && c <= '\xFE4F' = Just $ UnicodeBlockCJK $ UnicodeBlockCJK_Compatibility_Forms
 274   | '\xFE50' <= c && c <= '\xFE6F' = Just UnicodeBlockSmall_Form_Variants
 275   | '\xFE70' <= c && c <= '\xFEFF' = Just UnicodeBlockArabic_Presentation_FormsB
 276   | '\xFF00' <= c && c <= '\xFFEF' = Just UnicodeBlockHalfwidth_and_Fullwidth_Forms
 277   | '\xFFF0' <= c && c <= '\xFFFF' = Just UnicodeBlockSpecials
 278   | '\x20000' <= c && c <= '\x2A6DF' = Just $ UnicodeBlockCJK $ UnicodeBlockCJK_Unified_Ideographs_Extension_B
 279   | '\x2A700' <= c && c <= '\x2B73F' = Just $ UnicodeBlockCJK $ UnicodeBlockCJK_Unified_Ideographs_Extension_C
 280   | '\x2B740' <= c && c <= '\x2B81F' = Just $ UnicodeBlockCJK $ UnicodeBlockCJK_Unified_Ideographs_Extension_D
 281   | '\x2B820' <= c && c <= '\x2CEAF' = Just $ UnicodeBlockCJK $ UnicodeBlockCJK_Unified_Ideographs_Extension_E
 282   | '\x2CEB0' <= c && c <= '\x2EBEF' = Just $ UnicodeBlockCJK $ UnicodeBlockCJK_Unified_Ideographs_Extension_F
 283   | '\x30000' <= c && c <= '\x3134F' = Just $ UnicodeBlockCJK $ UnicodeBlockCJK_Unified_Ideographs_Extension_G
 284   | '\x31350' <= c && c <= '\x323AF' = Just $ UnicodeBlockCJK $ UnicodeBlockCJK_Unified_Ideographs_Extension_H
 285   | otherwise = Nothing
 286
 287 consecutiveGroups :: Eq k => [(k, v)] -> [(k, [v])]
 288 consecutiveGroups [] = []
 289 consecutiveGroups ((k, v) : nexts) = ((k, v : List.map snd ks)) : consecutiveGroups notKs
 290   where
 291     (ks, notKs) = List.span (\(k', _v) -> k == k') nexts