module Worksheets.Utils.Char (
  module Worksheets.Utils.Char,
  module Data.Char,
) where

import Data.Char
import Data.List qualified as List
import Data.Set qualified as Set
import Worksheets.Utils.Prelude

data UnicodeBlock
  = UnicodeBlockAlphabetic_Presentation_Forms
  | UnicodeBlockArabic
  | UnicodeBlockArabic_Presentation_FormsA
  | UnicodeBlockArabic_Presentation_FormsB
  | UnicodeBlockArmenian
  | UnicodeBlockArrows
  | UnicodeBlockLatin UnicodeBlockLatin
  | UnicodeBlockBengali
  | UnicodeBlockBlock_Elements
  | UnicodeBlockBopomofo
  | UnicodeBlockBopomofo_Extended
  | UnicodeBlockBox_Drawing
  | UnicodeBlockBraille_Patterns
  | UnicodeBlockBuhid
  | UnicodeBlockCJK UnicodeBlockCJK
  | UnicodeBlockCherokee
  | UnicodeBlockCombining_Diacritical_Marks
  | UnicodeBlockCombining_Diacritical_Marks_for_Symbols
  | UnicodeBlockCombining_Half_Marks
  | UnicodeBlockControl_Pictures
  | UnicodeBlockCurrency_Symbols
  | UnicodeBlockCyrillic
  | UnicodeBlockCyrillic_Supplementary
  | UnicodeBlockDevanagari
  | UnicodeBlockDingbats
  | UnicodeBlockEnclosed_Alphanumerics
  | UnicodeBlockEthiopic
  | UnicodeBlockGeneral_Punctuation
  | UnicodeBlockGeometric_Shapes
  | UnicodeBlockGeorgian
  | UnicodeBlockGreek_Extended
  | UnicodeBlockGreek_and_Coptic
  | UnicodeBlockGujarati
  | UnicodeBlockGurmukhi
  | UnicodeBlockHalfwidth_and_Fullwidth_Forms
  | UnicodeBlockHangul_Compatibility_Jamo
  | UnicodeBlockHangul_Jamo
  | UnicodeBlockHangul_Syllables
  | UnicodeBlockHanunoo
  | UnicodeBlockHebrew
  | UnicodeBlockHigh_Private_Use_Surrogates
  | UnicodeBlockHigh_Surrogates
  | UnicodeBlockHiragana
  | UnicodeBlockIPA_Extensions
  | UnicodeBlockIdeographic_Description_Characters
  | UnicodeBlockKanbun
  | UnicodeBlockKangxi_Radicals
  | UnicodeBlockKannada
  | UnicodeBlockKatakana
  | UnicodeBlockKatakana_Phonetic_Extensions
  | UnicodeBlockKhmer
  | UnicodeBlockKhmer_Symbols
  | UnicodeBlockLao
  | UnicodeBlockLetterlike_Symbols
  | UnicodeBlockLimbu
  | UnicodeBlockLow_Surrogates
  | UnicodeBlockMalayalam
  | UnicodeBlockMathematical_Operators
  | UnicodeBlockMiscellaneous_Mathematical_SymbolsA
  | UnicodeBlockMiscellaneous_Mathematical_SymbolsB
  | UnicodeBlockMiscellaneous_Symbols
  | UnicodeBlockMiscellaneous_Symbols_and_Arrows
  | UnicodeBlockMiscellaneous_Technical
  | UnicodeBlockMongolian
  | UnicodeBlockMyanmar
  | UnicodeBlockNumber_Forms
  | UnicodeBlockOgham
  | UnicodeBlockOptical_Character_Recognition
  | UnicodeBlockOriya
  | UnicodeBlockPhonetic_Extensions
  | UnicodeBlockPrivate_Use_Area
  | UnicodeBlockRunic
  | UnicodeBlockSinhala
  | UnicodeBlockSmall_Form_Variants
  | UnicodeBlockSpacing_Modifier_Letters
  | UnicodeBlockSpecials
  | UnicodeBlockSuperscripts_and_Subscripts
  | UnicodeBlockSupplemental_ArrowsA
  | UnicodeBlockSupplemental_ArrowsB
  | UnicodeBlockSupplemental_Mathematical_Operators
  | UnicodeBlockSyriac
  | UnicodeBlockTagalog
  | UnicodeBlockTagbanwa
  | UnicodeBlockTai_Le
  | UnicodeBlockTamil
  | UnicodeBlockTelugu
  | UnicodeBlockThaana
  | UnicodeBlockThai
  | UnicodeBlockTibetan
  | UnicodeBlockUnified_Canadian_Aboriginal_Syllabics
  | UnicodeBlockVariation_Selectors
  | UnicodeBlockYi_Radicals
  | UnicodeBlockYi_Syllables
  | UnicodeBlockYijing_Hexagram_Symbols
  deriving (Eq, Ord, Show)

unicodeBlocks =
  [ unicodeBlockCJK
  , unicodeBlockLatin
  , [ UnicodeBlockHalfwidth_and_Fullwidth_Forms
    , UnicodeBlockMiscellaneous_Technical
    ]
      & Set.fromList
  ]
    & mconcat

unicodeBlockCJK = UnicodeBlockCJK <$> enumAll & Set.fromList
unicodeBlockLatin = UnicodeBlockLatin <$> enumAll & Set.fromList

data UnicodeBlockLatin
  = UnicodeBlockLatin_Basic
  | UnicodeBlockLatin1_Supplement
  | UnicodeBlockLatin_ExtendedA
  | UnicodeBlockLatin_ExtendedB
  | UnicodeBlockLatin_Extended_Additional
  deriving (Eq, Ord, Show, Enum)

data UnicodeBlockCJK
  = UnicodeBlockCJK_Compatibility
  | UnicodeBlockCJK_Compatibility_Forms
  | UnicodeBlockCJK_Compatibility_Ideographs
  | UnicodeBlockCJK_Radicals_Supplement
  | UnicodeBlockCJK_Symbols_and_Punctuation
  | -- | CJK Unified Ideographs: U+4E00 to U+9FFF.
    -- This block contains the most commonly used Chinese characters in modern writing.
    UnicodeBlockCJK_Unified_Ideographs
  | -- | CJK Unified Ideographs Extension A: U+3400 to U+4DBF.
    -- Includes rare and historical characters.
    UnicodeBlockCJK_Unified_Ideographs_Extension_A
  | -- | CJK Unified Ideographs Extension B: U+20000 to U+2A6DF.
    -- Contains rare and historic characters, often used in academic or specialized contexts.
    UnicodeBlockCJK_Unified_Ideographs_Extension_B
  | -- | CJK Unified Ideographs Extension C: U+2A700 to U+2B73F.
    -- Include additional rare and historic characters.
    UnicodeBlockCJK_Unified_Ideographs_Extension_C
  | -- | CJK Unified Ideographs Extension D: U+2B740 to U+2B81F.
    -- Include additional rare and historic characters.
    UnicodeBlockCJK_Unified_Ideographs_Extension_D
  | -- | CJK Unified Ideographs Extension E: U+2B820 to U+2CEAF.
    -- Include additional rare and historic characters.
    UnicodeBlockCJK_Unified_Ideographs_Extension_E
  | -- | CJK Unified Ideographs Extension F: U+2CEB0 to U+2EBEF.
    -- Include additional rare and historic characters.
    UnicodeBlockCJK_Unified_Ideographs_Extension_F
  | -- | CJK Unified Ideographs Extension G: U+30000 to U+3134F.
    -- Include additional rare and historic characters.
    UnicodeBlockCJK_Unified_Ideographs_Extension_G
  | -- | CJK Unified Ideographs Extension H: U+31350 to U+323AF.
    -- Include additional rare and historic characters.
    UnicodeBlockCJK_Unified_Ideographs_Extension_H
  | UnicodeBlockCJK_Enclosed_Letters_and_Months
  deriving (Eq, Ord, Show, Enum)

-- TODO:
-- CJK Compatibility Ideographs: U+F900 to U+FAFF
-- Contains duplicate characters and variants for compatibility with older encodings.

-- CJK Compatibility Ideographs Supplement: U+2F800 to U+2FA1F
-- Includes unifiable variants of ideographs.

unicodeBlock c
  | '\x0000' <= c && c <= '\x007F' = Just $ UnicodeBlockLatin $ UnicodeBlockLatin_Basic
  | '\x0080' <= c && c <= '\x00FF' = Just $ UnicodeBlockLatin $ UnicodeBlockLatin1_Supplement
  | '\x0100' <= c && c <= '\x017F' = Just $ UnicodeBlockLatin $ UnicodeBlockLatin_ExtendedA
  | '\x0180' <= c && c <= '\x024F' = Just $ UnicodeBlockLatin $ UnicodeBlockLatin_ExtendedB
  | '\x0250' <= c && c <= '\x02AF' = Just UnicodeBlockIPA_Extensions
  | '\x02B0' <= c && c <= '\x02FF' = Just UnicodeBlockSpacing_Modifier_Letters
  | '\x0300' <= c && c <= '\x036F' = Just UnicodeBlockCombining_Diacritical_Marks
  | '\x0370' <= c && c <= '\x03FF' = Just UnicodeBlockGreek_and_Coptic
  | '\x0400' <= c && c <= '\x04FF' = Just UnicodeBlockCyrillic
  | '\x0500' <= c && c <= '\x052F' = Just UnicodeBlockCyrillic_Supplementary
  | '\x0530' <= c && c <= '\x058F' = Just UnicodeBlockArmenian
  | '\x0590' <= c && c <= '\x05FF' = Just UnicodeBlockHebrew
  | '\x0600' <= c && c <= '\x06FF' = Just UnicodeBlockArabic
  | '\x0700' <= c && c <= '\x074F' = Just UnicodeBlockSyriac
  | '\x0780' <= c && c <= '\x07BF' = Just UnicodeBlockThaana
  | '\x0900' <= c && c <= '\x097F' = Just UnicodeBlockDevanagari
  | '\x0980' <= c && c <= '\x09FF' = Just UnicodeBlockBengali
  | '\x0A00' <= c && c <= '\x0A7F' = Just UnicodeBlockGurmukhi
  | '\x0A80' <= c && c <= '\x0AFF' = Just UnicodeBlockGujarati
  | '\x0B00' <= c && c <= '\x0B7F' = Just UnicodeBlockOriya
  | '\x0B80' <= c && c <= '\x0BFF' = Just UnicodeBlockTamil
  | '\x0C00' <= c && c <= '\x0C7F' = Just UnicodeBlockTelugu
  | '\x0C80' <= c && c <= '\x0CFF' = Just UnicodeBlockKannada
  | '\x0D00' <= c && c <= '\x0D7F' = Just UnicodeBlockMalayalam
  | '\x0D80' <= c && c <= '\x0DFF' = Just UnicodeBlockSinhala
  | '\x0E00' <= c && c <= '\x0E7F' = Just UnicodeBlockThai
  | '\x0E80' <= c && c <= '\x0EFF' = Just UnicodeBlockLao
  | '\x0F00' <= c && c <= '\x0FFF' = Just UnicodeBlockTibetan
  | '\x1000' <= c && c <= '\x109F' = Just UnicodeBlockMyanmar
  | '\x10A0' <= c && c <= '\x10FF' = Just UnicodeBlockGeorgian
  | '\x1100' <= c && c <= '\x11FF' = Just UnicodeBlockHangul_Jamo
  | '\x1200' <= c && c <= '\x137F' = Just UnicodeBlockEthiopic
  | '\x13A0' <= c && c <= '\x13FF' = Just UnicodeBlockCherokee
  | '\x1400' <= c && c <= '\x167F' = Just UnicodeBlockUnified_Canadian_Aboriginal_Syllabics
  | '\x1680' <= c && c <= '\x169F' = Just UnicodeBlockOgham
  | '\x16A0' <= c && c <= '\x16FF' = Just UnicodeBlockRunic
  | '\x1700' <= c && c <= '\x171F' = Just UnicodeBlockTagalog
  | '\x1720' <= c && c <= '\x173F' = Just UnicodeBlockHanunoo
  | '\x1740' <= c && c <= '\x175F' = Just UnicodeBlockBuhid
  | '\x1760' <= c && c <= '\x177F' = Just UnicodeBlockTagbanwa
  | '\x1780' <= c && c <= '\x17FF' = Just UnicodeBlockKhmer
  | '\x1800' <= c && c <= '\x18AF' = Just UnicodeBlockMongolian
  | '\x1900' <= c && c <= '\x194F' = Just UnicodeBlockLimbu
  | '\x1950' <= c && c <= '\x197F' = Just UnicodeBlockTai_Le
  | '\x19E0' <= c && c <= '\x19FF' = Just UnicodeBlockKhmer_Symbols
  | '\x1D00' <= c && c <= '\x1D7F' = Just UnicodeBlockPhonetic_Extensions
  | '\x1E00' <= c && c <= '\x1EFF' = Just $ UnicodeBlockLatin $ UnicodeBlockLatin_Extended_Additional
  | '\x1F00' <= c && c <= '\x1FFF' = Just UnicodeBlockGreek_Extended
  | '\x2000' <= c && c <= '\x206F' = Just UnicodeBlockGeneral_Punctuation
  | '\x2070' <= c && c <= '\x209F' = Just UnicodeBlockSuperscripts_and_Subscripts
  | '\x20A0' <= c && c <= '\x20CF' = Just UnicodeBlockCurrency_Symbols
  | '\x20D0' <= c && c <= '\x20FF' = Just UnicodeBlockCombining_Diacritical_Marks_for_Symbols
  | '\x2100' <= c && c <= '\x214F' = Just UnicodeBlockLetterlike_Symbols
  | '\x2150' <= c && c <= '\x218F' = Just UnicodeBlockNumber_Forms
  | '\x2190' <= c && c <= '\x21FF' = Just UnicodeBlockArrows
  | '\x2200' <= c && c <= '\x22FF' = Just UnicodeBlockMathematical_Operators
  | '\x2300' <= c && c <= '\x23FF' = Just UnicodeBlockMiscellaneous_Technical
  | '\x2400' <= c && c <= '\x243F' = Just UnicodeBlockControl_Pictures
  | '\x2440' <= c && c <= '\x245F' = Just UnicodeBlockOptical_Character_Recognition
  | '\x2460' <= c && c <= '\x24FF' = Just UnicodeBlockEnclosed_Alphanumerics
  | '\x2500' <= c && c <= '\x257F' = Just UnicodeBlockBox_Drawing
  | '\x2580' <= c && c <= '\x259F' = Just UnicodeBlockBlock_Elements
  | '\x25A0' <= c && c <= '\x25FF' = Just UnicodeBlockGeometric_Shapes
  | '\x2600' <= c && c <= '\x26FF' = Just UnicodeBlockMiscellaneous_Symbols
  | '\x2700' <= c && c <= '\x27BF' = Just UnicodeBlockDingbats
  | '\x27C0' <= c && c <= '\x27EF' = Just UnicodeBlockMiscellaneous_Mathematical_SymbolsA
  | '\x27F0' <= c && c <= '\x27FF' = Just UnicodeBlockSupplemental_ArrowsA
  | '\x2800' <= c && c <= '\x28FF' = Just UnicodeBlockBraille_Patterns
  | '\x2900' <= c && c <= '\x297F' = Just UnicodeBlockSupplemental_ArrowsB
  | '\x2980' <= c && c <= '\x29FF' = Just UnicodeBlockMiscellaneous_Mathematical_SymbolsB
  | '\x2A00' <= c && c <= '\x2AFF' = Just UnicodeBlockSupplemental_Mathematical_Operators
  | '\x2B00' <= c && c <= '\x2BFF' = Just UnicodeBlockMiscellaneous_Symbols_and_Arrows
  | '\x2E80' <= c && c <= '\x2EFF' = Just $ UnicodeBlockCJK $ UnicodeBlockCJK_Radicals_Supplement
  | '\x2F00' <= c && c <= '\x2FDF' = Just UnicodeBlockKangxi_Radicals
  | '\x2FF0' <= c && c <= '\x2FFF' = Just UnicodeBlockIdeographic_Description_Characters
  | '\x3000' <= c && c <= '\x303F' = Just $ UnicodeBlockCJK $ UnicodeBlockCJK_Symbols_and_Punctuation
  | '\x3040' <= c && c <= '\x309F' = Just UnicodeBlockHiragana
  | '\x30A0' <= c && c <= '\x30FF' = Just UnicodeBlockKatakana
  | '\x3100' <= c && c <= '\x312F' = Just UnicodeBlockBopomofo
  | '\x3130' <= c && c <= '\x318F' = Just UnicodeBlockHangul_Compatibility_Jamo
  | '\x3190' <= c && c <= '\x319F' = Just UnicodeBlockKanbun
  | '\x31A0' <= c && c <= '\x31BF' = Just UnicodeBlockBopomofo_Extended
  | '\x31F0' <= c && c <= '\x31FF' = Just UnicodeBlockKatakana_Phonetic_Extensions
  | '\x3200' <= c && c <= '\x32FF' = Just $ UnicodeBlockCJK $ UnicodeBlockCJK_Enclosed_Letters_and_Months
  | '\x3300' <= c && c <= '\x33FF' = Just $ UnicodeBlockCJK $ UnicodeBlockCJK_Compatibility
  | '\x3400' <= c && c <= '\x4DBF' = Just $ UnicodeBlockCJK $ UnicodeBlockCJK_Unified_Ideographs_Extension_A
  | '\x4DC0' <= c && c <= '\x4DFF' = Just UnicodeBlockYijing_Hexagram_Symbols
  | '\x4E00' <= c && c <= '\x9FFF' = Just $ UnicodeBlockCJK $ UnicodeBlockCJK_Unified_Ideographs
  | '\xA000' <= c && c <= '\xA48F' = Just UnicodeBlockYi_Syllables
  | '\xA490' <= c && c <= '\xA4CF' = Just UnicodeBlockYi_Radicals
  | '\xAC00' <= c && c <= '\xD7AF' = Just UnicodeBlockHangul_Syllables
  | '\xD800' <= c && c <= '\xDB7F' = Just UnicodeBlockHigh_Surrogates
  | '\xDB80' <= c && c <= '\xDBFF' = Just UnicodeBlockHigh_Private_Use_Surrogates
  | '\xDC00' <= c && c <= '\xDFFF' = Just UnicodeBlockLow_Surrogates
  | '\xE000' <= c && c <= '\xF8FF' = Just UnicodeBlockPrivate_Use_Area
  | '\xF900' <= c && c <= '\xFAFF' = Just $ UnicodeBlockCJK $ UnicodeBlockCJK_Compatibility_Ideographs
  | '\xFB00' <= c && c <= '\xFB4F' = Just UnicodeBlockAlphabetic_Presentation_Forms
  | '\xFB50' <= c && c <= '\xFDFF' = Just UnicodeBlockArabic_Presentation_FormsA
  | '\xFE00' <= c && c <= '\xFE0F' = Just UnicodeBlockVariation_Selectors
  | '\xFE20' <= c && c <= '\xFE2F' = Just UnicodeBlockCombining_Half_Marks
  | '\xFE30' <= c && c <= '\xFE4F' = Just $ UnicodeBlockCJK $ UnicodeBlockCJK_Compatibility_Forms
  | '\xFE50' <= c && c <= '\xFE6F' = Just UnicodeBlockSmall_Form_Variants
  | '\xFE70' <= c && c <= '\xFEFF' = Just UnicodeBlockArabic_Presentation_FormsB
  | '\xFF00' <= c && c <= '\xFFEF' = Just UnicodeBlockHalfwidth_and_Fullwidth_Forms
  | '\xFFF0' <= c && c <= '\xFFFF' = Just UnicodeBlockSpecials
  | '\x20000' <= c && c <= '\x2A6DF' = Just $ UnicodeBlockCJK $ UnicodeBlockCJK_Unified_Ideographs_Extension_B
  | '\x2A700' <= c && c <= '\x2B73F' = Just $ UnicodeBlockCJK $ UnicodeBlockCJK_Unified_Ideographs_Extension_C
  | '\x2B740' <= c && c <= '\x2B81F' = Just $ UnicodeBlockCJK $ UnicodeBlockCJK_Unified_Ideographs_Extension_D
  | '\x2B820' <= c && c <= '\x2CEAF' = Just $ UnicodeBlockCJK $ UnicodeBlockCJK_Unified_Ideographs_Extension_E
  | '\x2CEB0' <= c && c <= '\x2EBEF' = Just $ UnicodeBlockCJK $ UnicodeBlockCJK_Unified_Ideographs_Extension_F
  | '\x30000' <= c && c <= '\x3134F' = Just $ UnicodeBlockCJK $ UnicodeBlockCJK_Unified_Ideographs_Extension_G
  | '\x31350' <= c && c <= '\x323AF' = Just $ UnicodeBlockCJK $ UnicodeBlockCJK_Unified_Ideographs_Extension_H
  | otherwise = Nothing

consecutiveGroups :: Eq k => [(k, v)] -> [(k, [v])]
consecutiveGroups [] = []
consecutiveGroups ((k, v) : nexts) = ((k, v : List.map snd ks)) : consecutiveGroups notKs
  where
    (ks, notKs) = List.span (\(k', _v) -> k == k') nexts