{-# LANGUAGE DeriveDataTypeable #-}
{-# OPTIONS_GHC -fno-warn-missing-signatures #-}
-----------------------------------------------------------------------------
-- |
-- Module      :  Data.CharSet.Unicode.Block
-- Copyright   :  (c) Edward Kmett 2010-2011
-- License     :  BSD3
-- Maintainer  :  ekmett@gmail.com
-- Stability   :  experimental
-- Portability :  portable
--
-- Provides unicode general categories, which are typically connoted by
-- @\p{InBasicLatin}@ or @\p{InIPA_Extensions}@. Lookups can be constructed using 'categories'
-- or individual character sets can be used directly.
-------------------------------------------------------------------------------

module Data.CharSet.Unicode.Block
    (
    -- * Unicode General Category
      Block(..)
    -- * Lookup
    , blocks
    , lookupBlock
    , lookupBlockCharSet
    -- * CharSets by Block
    , basicLatin
    , latin1Supplement
    , latinExtendedA
    , latinExtendedB
    , ipaExtensions
    , spacingModifierLetters
    , combiningDiacriticalMarks
    , greekAndCoptic
    , cyrillic
    , cyrillicSupplementary
    , armenian
    , hebrew
    , arabic
    , syriac
    , thaana
    , devanagari
    , bengali
    , gurmukhi
    , gujarati
    , oriya
    , tamil
    , telugu
    , kannada
    , malayalam
    , sinhala
    , thai
    , lao
    , tibetan
    , myanmar
    , georgian
    , hangulJamo
    , ethiopic
    , cherokee
    , unifiedCanadianAboriginalSyllabics
    , ogham
    , runic
    , tagalog
    , hanunoo
    , buhid
    , tagbanwa
    , khmer
    , mongolian
    , limbu
    , taiLe
    , khmerSymbols
    , phoneticExtensions
    , latinExtendedAdditional
    , greekExtended
    , generalPunctuation
    , superscriptsAndSubscripts
    , currencySymbols
    , combiningDiacriticalMarksForSymbols
    , letterlikeSymbols
    , numberForms
    , arrows
    , mathematicalOperators
    , miscellaneousTechnical
    , controlPictures
    , opticalCharacterRecognition
    , enclosedAlphanumerics
    , boxDrawing
    , blockElements
    , geometricShapes
    , miscellaneousSymbols
    , dingbats
    , miscellaneousMathematicalSymbolsA
    , supplementalArrowsA
    , braillePatterns
    , supplementalArrowsB
    , miscellaneousMathematicalSymbolsB
    , supplementalMathematicalOperators
    , miscellaneousSymbolsAndArrows
    , cjkRadicalsSupplement
    , kangxiRadicals
    , ideographicDescriptionCharacters
    , cjkSymbolsAndPunctuation
    , hiragana
    , katakana
    , bopomofo
    , hangulCompatibilityJamo
    , kanbun
    , bopomofoExtended
    , katakanaPhoneticExtensions
    , enclosedCjkLettersAndMonths
    , cjkCompatibility
    , cjkUnifiedIdeographsExtensionA
    , yijingHexagramSymbols
    , cjkUnifiedIdeographs
    , yiSyllables
    , yiRadicals
    , hangulSyllables
    , highSurrogates
    , highPrivateUseSurrogates
    , lowSurrogates
    , privateUseArea
    , cjkCompatibilityIdeographs
    , alphabeticPresentationForms
    , arabicPresentationFormsA
    , variationSelectors
    , combiningHalfMarks
    , cjkCompatibilityForms
    , smallFormVariants
    , arabicPresentationFormsB
    , halfwidthAndFullwidthForms
    , specials
    ) where

import Data.Char
import Data.CharSet
import Data.Data
import Data.HashMap.Lazy (HashMap)
import qualified Data.HashMap.Lazy as HashMap

data Block = Block
    { Block -> String
blockName :: String
    , Block -> CharSet
blockCharSet :: CharSet
    } deriving (Int -> Block -> ShowS
[Block] -> ShowS
Block -> String
(Int -> Block -> ShowS)
-> (Block -> String) -> ([Block] -> ShowS) -> Show Block
forall a.
(Int -> a -> ShowS) -> (a -> String) -> ([a] -> ShowS) -> Show a
showList :: [Block] -> ShowS
$cshowList :: [Block] -> ShowS
show :: Block -> String
$cshow :: Block -> String
showsPrec :: Int -> Block -> ShowS
$cshowsPrec :: Int -> Block -> ShowS
Show, Typeable Block
DataType
Constr
Typeable Block
-> (forall (c :: * -> *).
    (forall d b. Data d => c (d -> b) -> d -> c b)
    -> (forall g. g -> c g) -> Block -> c Block)
-> (forall (c :: * -> *).
    (forall b r. Data b => c (b -> r) -> c r)
    -> (forall r. r -> c r) -> Constr -> c Block)
-> (Block -> Constr)
-> (Block -> DataType)
-> (forall (t :: * -> *) (c :: * -> *).
    Typeable t =>
    (forall d. Data d => c (t d)) -> Maybe (c Block))
-> (forall (t :: * -> * -> *) (c :: * -> *).
    Typeable t =>
    (forall d e. (Data d, Data e) => c (t d e)) -> Maybe (c Block))
-> ((forall b. Data b => b -> b) -> Block -> Block)
-> (forall r r'.
    (r -> r' -> r) -> r -> (forall d. Data d => d -> r') -> Block -> r)
-> (forall r r'.
    (r' -> r -> r) -> r -> (forall d. Data d => d -> r') -> Block -> r)
-> (forall u. (forall d. Data d => d -> u) -> Block -> [u])
-> (forall u. Int -> (forall d. Data d => d -> u) -> Block -> u)
-> (forall (m :: * -> *).
    Monad m =>
    (forall d. Data d => d -> m d) -> Block -> m Block)
-> (forall (m :: * -> *).
    MonadPlus m =>
    (forall d. Data d => d -> m d) -> Block -> m Block)
-> (forall (m :: * -> *).
    MonadPlus m =>
    (forall d. Data d => d -> m d) -> Block -> m Block)
-> Data Block
Block -> DataType
Block -> Constr
(forall b. Data b => b -> b) -> Block -> Block
(forall d b. Data d => c (d -> b) -> d -> c b)
-> (forall g. g -> c g) -> Block -> c Block
(forall b r. Data b => c (b -> r) -> c r)
-> (forall r. r -> c r) -> Constr -> c Block
forall a.
Typeable a
-> (forall (c :: * -> *).
    (forall d b. Data d => c (d -> b) -> d -> c b)
    -> (forall g. g -> c g) -> a -> c a)
-> (forall (c :: * -> *).
    (forall b r. Data b => c (b -> r) -> c r)
    -> (forall r. r -> c r) -> Constr -> c a)
-> (a -> Constr)
-> (a -> DataType)
-> (forall (t :: * -> *) (c :: * -> *).
    Typeable t =>
    (forall d. Data d => c (t d)) -> Maybe (c a))
-> (forall (t :: * -> * -> *) (c :: * -> *).
    Typeable t =>
    (forall d e. (Data d, Data e) => c (t d e)) -> Maybe (c a))
-> ((forall b. Data b => b -> b) -> a -> a)
-> (forall r r'.
    (r -> r' -> r) -> r -> (forall d. Data d => d -> r') -> a -> r)
-> (forall r r'.
    (r' -> r -> r) -> r -> (forall d. Data d => d -> r') -> a -> r)
-> (forall u. (forall d. Data d => d -> u) -> a -> [u])
-> (forall u. Int -> (forall d. Data d => d -> u) -> a -> u)
-> (forall (m :: * -> *).
    Monad m =>
    (forall d. Data d => d -> m d) -> a -> m a)
-> (forall (m :: * -> *).
    MonadPlus m =>
    (forall d. Data d => d -> m d) -> a -> m a)
-> (forall (m :: * -> *).
    MonadPlus m =>
    (forall d. Data d => d -> m d) -> a -> m a)
-> Data a
forall u. Int -> (forall d. Data d => d -> u) -> Block -> u
forall u. (forall d. Data d => d -> u) -> Block -> [u]
forall r r'.
(r -> r' -> r) -> r -> (forall d. Data d => d -> r') -> Block -> r
forall r r'.
(r' -> r -> r) -> r -> (forall d. Data d => d -> r') -> Block -> r
forall (m :: * -> *).
Monad m =>
(forall d. Data d => d -> m d) -> Block -> m Block
forall (m :: * -> *).
MonadPlus m =>
(forall d. Data d => d -> m d) -> Block -> m Block
forall (c :: * -> *).
(forall b r. Data b => c (b -> r) -> c r)
-> (forall r. r -> c r) -> Constr -> c Block
forall (c :: * -> *).
(forall d b. Data d => c (d -> b) -> d -> c b)
-> (forall g. g -> c g) -> Block -> c Block
forall (t :: * -> *) (c :: * -> *).
Typeable t =>
(forall d. Data d => c (t d)) -> Maybe (c Block)
forall (t :: * -> * -> *) (c :: * -> *).
Typeable t =>
(forall d e. (Data d, Data e) => c (t d e)) -> Maybe (c Block)
$cBlock :: Constr
$tBlock :: DataType
gmapMo :: (forall d. Data d => d -> m d) -> Block -> m Block
$cgmapMo :: forall (m :: * -> *).
MonadPlus m =>
(forall d. Data d => d -> m d) -> Block -> m Block
gmapMp :: (forall d. Data d => d -> m d) -> Block -> m Block
$cgmapMp :: forall (m :: * -> *).
MonadPlus m =>
(forall d. Data d => d -> m d) -> Block -> m Block
gmapM :: (forall d. Data d => d -> m d) -> Block -> m Block
$cgmapM :: forall (m :: * -> *).
Monad m =>
(forall d. Data d => d -> m d) -> Block -> m Block
gmapQi :: Int -> (forall d. Data d => d -> u) -> Block -> u
$cgmapQi :: forall u. Int -> (forall d. Data d => d -> u) -> Block -> u
gmapQ :: (forall d. Data d => d -> u) -> Block -> [u]
$cgmapQ :: forall u. (forall d. Data d => d -> u) -> Block -> [u]
gmapQr :: (r' -> r -> r) -> r -> (forall d. Data d => d -> r') -> Block -> r
$cgmapQr :: forall r r'.
(r' -> r -> r) -> r -> (forall d. Data d => d -> r') -> Block -> r
gmapQl :: (r -> r' -> r) -> r -> (forall d. Data d => d -> r') -> Block -> r
$cgmapQl :: forall r r'.
(r -> r' -> r) -> r -> (forall d. Data d => d -> r') -> Block -> r
gmapT :: (forall b. Data b => b -> b) -> Block -> Block
$cgmapT :: (forall b. Data b => b -> b) -> Block -> Block
dataCast2 :: (forall d e. (Data d, Data e) => c (t d e)) -> Maybe (c Block)
$cdataCast2 :: forall (t :: * -> * -> *) (c :: * -> *).
Typeable t =>
(forall d e. (Data d, Data e) => c (t d e)) -> Maybe (c Block)
dataCast1 :: (forall d. Data d => c (t d)) -> Maybe (c Block)
$cdataCast1 :: forall (t :: * -> *) (c :: * -> *).
Typeable t =>
(forall d. Data d => c (t d)) -> Maybe (c Block)
dataTypeOf :: Block -> DataType
$cdataTypeOf :: Block -> DataType
toConstr :: Block -> Constr
$ctoConstr :: Block -> Constr
gunfold :: (forall b r. Data b => c (b -> r) -> c r)
-> (forall r. r -> c r) -> Constr -> c Block
$cgunfold :: forall (c :: * -> *).
(forall b r. Data b => c (b -> r) -> c r)
-> (forall r. r -> c r) -> Constr -> c Block
gfoldl :: (forall d b. Data d => c (d -> b) -> d -> c b)
-> (forall g. g -> c g) -> Block -> c Block
$cgfoldl :: forall (c :: * -> *).
(forall d b. Data d => c (d -> b) -> d -> c b)
-> (forall g. g -> c g) -> Block -> c Block
$cp1Data :: Typeable Block
Data, Typeable)

blocks :: [Block]
blocks :: [Block]
blocks =
    [ String -> CharSet -> Block
Block String
"Basic_Latin" CharSet
basicLatin
    , String -> CharSet -> Block
Block String
"Latin-1_Supplement" CharSet
latin1Supplement
    , String -> CharSet -> Block
Block String
"Latin_Extended-A" CharSet
latinExtendedA
    , String -> CharSet -> Block
Block String
"Latin_Extended-B" CharSet
latinExtendedB
    , String -> CharSet -> Block
Block String
"IPA_Extensions" CharSet
ipaExtensions
    , String -> CharSet -> Block
Block String
"Spacing_Modifier_Letters" CharSet
spacingModifierLetters
    , String -> CharSet -> Block
Block String
"Combining_Diacritical_Marks" CharSet
combiningDiacriticalMarks
    , String -> CharSet -> Block
Block String
"Greek_and_Coptic" CharSet
greekAndCoptic
    , String -> CharSet -> Block
Block String
"Cyrillic" CharSet
cyrillic
    , String -> CharSet -> Block
Block String
"Cyrillic_Supplementary" CharSet
cyrillicSupplementary
    , String -> CharSet -> Block
Block String
"Armenian" CharSet
armenian
    , String -> CharSet -> Block
Block String
"Hebrew" CharSet
hebrew
    , String -> CharSet -> Block
Block String
"Arabic" CharSet
arabic
    , String -> CharSet -> Block
Block String
"Syriac" CharSet
syriac
    , String -> CharSet -> Block
Block String
"Thaana" CharSet
thaana
    , String -> CharSet -> Block
Block String
"Devanagari" CharSet
devanagari
    , String -> CharSet -> Block
Block String
"Bengali" CharSet
bengali
    , String -> CharSet -> Block
Block String
"Gurmukhi" CharSet
gurmukhi
    , String -> CharSet -> Block
Block String
"Gujarati" CharSet
gujarati
    , String -> CharSet -> Block
Block String
"Oriya" CharSet
oriya
    , String -> CharSet -> Block
Block String
"Tamil" CharSet
tamil
    , String -> CharSet -> Block
Block String
"Telugu" CharSet
telugu
    , String -> CharSet -> Block
Block String
"Kannada" CharSet
kannada
    , String -> CharSet -> Block
Block String
"Malayalam" CharSet
malayalam
    , String -> CharSet -> Block
Block String
"Sinhala" CharSet
sinhala
    , String -> CharSet -> Block
Block String
"Thai" CharSet
thai
    , String -> CharSet -> Block
Block String
"Lao" CharSet
lao
    , String -> CharSet -> Block
Block String
"Tibetan" CharSet
tibetan
    , String -> CharSet -> Block
Block String
"Myanmar" CharSet
myanmar
    , String -> CharSet -> Block
Block String
"Georgian" CharSet
georgian
    , String -> CharSet -> Block
Block String
"Hangul_Jamo" CharSet
hangulJamo
    , String -> CharSet -> Block
Block String
"Ethiopic" CharSet
ethiopic
    , String -> CharSet -> Block
Block String
"Cherokee" CharSet
cherokee
    , String -> CharSet -> Block
Block String
"Unified_Canadian_Aboriginal_Syllabics" CharSet
unifiedCanadianAboriginalSyllabics
    , String -> CharSet -> Block
Block String
"Ogham" CharSet
ogham
    , String -> CharSet -> Block
Block String
"Runic" CharSet
runic
    , String -> CharSet -> Block
Block String
"Tagalog" CharSet
tagalog
    , String -> CharSet -> Block
Block String
"Hanunoo" CharSet
hanunoo
    , String -> CharSet -> Block
Block String
"Buhid" CharSet
buhid
    , String -> CharSet -> Block
Block String
"Tagbanwa" CharSet
tagbanwa
    , String -> CharSet -> Block
Block String
"Khmer" CharSet
khmer
    , String -> CharSet -> Block
Block String
"Mongolian" CharSet
mongolian
    , String -> CharSet -> Block
Block String
"Limbu" CharSet
limbu
    , String -> CharSet -> Block
Block String
"Tai_Le" CharSet
taiLe
    , String -> CharSet -> Block
Block String
"Khmer_Symbols" CharSet
khmerSymbols
    , String -> CharSet -> Block
Block String
"Phonetic_Extensions" CharSet
phoneticExtensions
    , String -> CharSet -> Block
Block String
"Latin_Extended_Additional" CharSet
latinExtendedAdditional
    , String -> CharSet -> Block
Block String
"Greek_Extended" CharSet
greekExtended
    , String -> CharSet -> Block
Block String
"General_Punctuation" CharSet
generalPunctuation
    , String -> CharSet -> Block
Block String
"Superscripts_and_Subscripts" CharSet
superscriptsAndSubscripts
    , String -> CharSet -> Block
Block String
"Currency_Symbols" CharSet
currencySymbols
    , String -> CharSet -> Block
Block String
"Combining_Diacritical_Marks_for_Symbols" CharSet
combiningDiacriticalMarksForSymbols
    , String -> CharSet -> Block
Block String
"Letterlike_Symbols" CharSet
letterlikeSymbols
    , String -> CharSet -> Block
Block String
"Number_Forms" CharSet
numberForms
    , String -> CharSet -> Block
Block String
"Arrows" CharSet
arrows
    , String -> CharSet -> Block
Block String
"Mathematical_Operators" CharSet
mathematicalOperators
    , String -> CharSet -> Block
Block String
"Miscellaneous_Technical" CharSet
miscellaneousTechnical
    , String -> CharSet -> Block
Block String
"Control_Pictures" CharSet
controlPictures
    , String -> CharSet -> Block
Block String
"Optical_Character_Recognition" CharSet
opticalCharacterRecognition
    , String -> CharSet -> Block
Block String
"Enclosed_Alphanumerics" CharSet
enclosedAlphanumerics
    , String -> CharSet -> Block
Block String
"Box_Drawing" CharSet
boxDrawing
    , String -> CharSet -> Block
Block String
"Block_Elements" CharSet
blockElements
    , String -> CharSet -> Block
Block String
"Geometric_Shapes" CharSet
geometricShapes
    , String -> CharSet -> Block
Block String
"Miscellaneous_Symbols" CharSet
miscellaneousSymbols
    , String -> CharSet -> Block
Block String
"Dingbats" CharSet
dingbats
    , String -> CharSet -> Block
Block String
"Miscellaneous_Mathematical_Symbols-A" CharSet
miscellaneousMathematicalSymbolsA
    , String -> CharSet -> Block
Block String
"Supplemental_Arrows-A" CharSet
supplementalArrowsA
    , String -> CharSet -> Block
Block String
"Braille_Patterns" CharSet
braillePatterns
    , String -> CharSet -> Block
Block String
"Supplemental_Arrows-B" CharSet
supplementalArrowsB
    , String -> CharSet -> Block
Block String
"Miscellaneous_Mathematical_Symbols-B" CharSet
miscellaneousMathematicalSymbolsB
    , String -> CharSet -> Block
Block String
"Supplemental_Mathematical_Operators" CharSet
supplementalMathematicalOperators
    , String -> CharSet -> Block
Block String
"Miscellaneous_Symbols_and_Arrows" CharSet
miscellaneousSymbolsAndArrows
    , String -> CharSet -> Block
Block String
"CJK_Radicals_Supplement" CharSet
cjkRadicalsSupplement
    , String -> CharSet -> Block
Block String
"Kangxi_Radicals" CharSet
kangxiRadicals
    , String -> CharSet -> Block
Block String
"Ideographic_Description_Characters" CharSet
ideographicDescriptionCharacters
    , String -> CharSet -> Block
Block String
"CJK_Symbols_and_Punctuation" CharSet
cjkSymbolsAndPunctuation
    , String -> CharSet -> Block
Block String
"Hiragana" CharSet
hiragana
    , String -> CharSet -> Block
Block String
"Katakana" CharSet
katakana
    , String -> CharSet -> Block
Block String
"Bopomofo" CharSet
bopomofo
    , String -> CharSet -> Block
Block String
"Hangul_Compatibility_Jamo" CharSet
hangulCompatibilityJamo
    , String -> CharSet -> Block
Block String
"Kanbun" CharSet
kanbun
    , String -> CharSet -> Block
Block String
"Bopomofo_Extended" CharSet
bopomofoExtended
    , String -> CharSet -> Block
Block String
"Katakana_Phonetic_Extensions" CharSet
katakanaPhoneticExtensions
    , String -> CharSet -> Block
Block String
"Enclosed_CJK_Letters_and_Months" CharSet
enclosedCjkLettersAndMonths
    , String -> CharSet -> Block
Block String
"CJK_Compatibility" CharSet
cjkCompatibility
    , String -> CharSet -> Block
Block String
"CJK_Unified_Ideographs_Extension_A" CharSet
cjkUnifiedIdeographsExtensionA
    , String -> CharSet -> Block
Block String
"Yijing_Hexagram_Symbols" CharSet
yijingHexagramSymbols
    , String -> CharSet -> Block
Block String
"CJK_Unified_Ideographs" CharSet
cjkUnifiedIdeographs
    , String -> CharSet -> Block
Block String
"Yi_Syllables" CharSet
yiSyllables
    , String -> CharSet -> Block
Block String
"Yi_Radicals" CharSet
yiRadicals
    , String -> CharSet -> Block
Block String
"Hangul_Syllables" CharSet
hangulSyllables
    , String -> CharSet -> Block
Block String
"High_Surrogates" CharSet
highSurrogates
    , String -> CharSet -> Block
Block String
"High_Private_Use_Surrogates" CharSet
highPrivateUseSurrogates
    , String -> CharSet -> Block
Block String
"Low_Surrogates" CharSet
lowSurrogates
    , String -> CharSet -> Block
Block String
"Private_Use_Area" CharSet
privateUseArea
    , String -> CharSet -> Block
Block String
"CJK_Compatibility_Ideographs" CharSet
cjkCompatibilityIdeographs
    , String -> CharSet -> Block
Block String
"Alphabetic_Presentation_Forms" CharSet
alphabeticPresentationForms
    , String -> CharSet -> Block
Block String
"Arabic_Presentation_Forms-A" CharSet
arabicPresentationFormsA
    , String -> CharSet -> Block
Block String
"Variation_Selectors" CharSet
variationSelectors
    , String -> CharSet -> Block
Block String
"Combining_Half_Marks" CharSet
combiningHalfMarks
    , String -> CharSet -> Block
Block String
"CJK_Compatibility_Forms" CharSet
cjkCompatibilityForms
    , String -> CharSet -> Block
Block String
"Small_Form_Variants" CharSet
smallFormVariants
    , String -> CharSet -> Block
Block String
"Arabic_Presentation_Forms-B" CharSet
arabicPresentationFormsB
    , String -> CharSet -> Block
Block String
"Halfwidth_and_Fullwidth_Forms" CharSet
halfwidthAndFullwidthForms
    , String -> CharSet -> Block
Block String
"Specials" CharSet
specials ]

lookupTable :: HashMap String Block
lookupTable :: HashMap String Block
lookupTable = [(String, Block)] -> HashMap String Block
forall k v. (Eq k, Hashable k) => [(k, v)] -> HashMap k v
HashMap.fromList ([(String, Block)] -> HashMap String Block)
-> [(String, Block)] -> HashMap String Block
forall a b. (a -> b) -> a -> b
$
              (Block -> (String, Block)) -> [Block] -> [(String, Block)]
forall a b. (a -> b) -> [a] -> [b]
Prelude.map (\y :: Block
y@(Block String
x CharSet
_) -> (ShowS
canonicalize String
x, Block
y))
              [Block]
blocks

canonicalize :: String -> String
canonicalize :: ShowS
canonicalize String
s = case (Char -> Char) -> ShowS
forall a b. (a -> b) -> [a] -> [b]
Prelude.map Char -> Char
toLower String
s of
    Char
'i': Char
'n' : String
xs -> ShowS
go String
xs
    String
xs -> ShowS
go String
xs
    where
        go :: ShowS
go (Char
'-':String
xs) = ShowS
go String
xs
        go (Char
'_':String
xs) = ShowS
go String
xs
        go (Char
' ':String
xs) = ShowS
go String
xs
        go (Char
x:String
xs) = Char
x Char -> ShowS
forall a. a -> [a] -> [a]
: ShowS
go String
xs
        go [] = []

lookupBlock :: String -> Maybe Block
lookupBlock :: String -> Maybe Block
lookupBlock String
s = String -> HashMap String Block -> Maybe Block
forall k v. (Eq k, Hashable k) => k -> HashMap k v -> Maybe v
HashMap.lookup (ShowS
canonicalize String
s) HashMap String Block
lookupTable

lookupBlockCharSet :: String -> Maybe CharSet
lookupBlockCharSet :: String -> Maybe CharSet
lookupBlockCharSet = (Block -> CharSet) -> Maybe Block -> Maybe CharSet
forall (f :: * -> *) a b. Functor f => (a -> b) -> f a -> f b
fmap Block -> CharSet
blockCharSet (Maybe Block -> Maybe CharSet)
-> (String -> Maybe Block) -> String -> Maybe CharSet
forall b c a. (b -> c) -> (a -> b) -> a -> c
. String -> Maybe Block
lookupBlock

basicLatin :: CharSet
basicLatin = Char -> Char -> CharSet
range Char
'\x0000' Char
'\x007f'
latin1Supplement :: CharSet
latin1Supplement = Char -> Char -> CharSet
range Char
'\x0080' Char
'\x00ff'
latinExtendedA :: CharSet
latinExtendedA = Char -> Char -> CharSet
range Char
'\x0100' Char
'\x017F'
latinExtendedB :: CharSet
latinExtendedB = Char -> Char -> CharSet
range Char
'\x0180' Char
'\x024F'
ipaExtensions :: CharSet
ipaExtensions = Char -> Char -> CharSet
range Char
'\x0250' Char
'\x02AF'
spacingModifierLetters :: CharSet
spacingModifierLetters = Char -> Char -> CharSet
range Char
'\x02B0' Char
'\x02FF'
combiningDiacriticalMarks :: CharSet
combiningDiacriticalMarks = Char -> Char -> CharSet
range Char
'\x0300' Char
'\x036F'
greekAndCoptic :: CharSet
greekAndCoptic = Char -> Char -> CharSet
range Char
'\x0370' Char
'\x03FF'
cyrillic :: CharSet
cyrillic = Char -> Char -> CharSet
range Char
'\x0400' Char
'\x04FF'
cyrillicSupplementary :: CharSet
cyrillicSupplementary = Char -> Char -> CharSet
range Char
'\x0500' Char
'\x052F'
armenian :: CharSet
armenian = Char -> Char -> CharSet
range Char
'\x0530' Char
'\x058F'
hebrew :: CharSet
hebrew = Char -> Char -> CharSet
range Char
'\x0590' Char
'\x05FF'
arabic :: CharSet
arabic = Char -> Char -> CharSet
range Char
'\x0600' Char
'\x06FF'
syriac :: CharSet
syriac = Char -> Char -> CharSet
range Char
'\x0700' Char
'\x074F'
thaana :: CharSet
thaana = Char -> Char -> CharSet
range Char
'\x0780' Char
'\x07BF'
devanagari :: CharSet
devanagari = Char -> Char -> CharSet
range Char
'\x0900' Char
'\x097F'
bengali :: CharSet
bengali = Char -> Char -> CharSet
range Char
'\x0980' Char
'\x09FF'
gurmukhi :: CharSet
gurmukhi = Char -> Char -> CharSet
range Char
'\x0A00' Char
'\x0A7F'
gujarati :: CharSet
gujarati = Char -> Char -> CharSet
range Char
'\x0A80' Char
'\x0AFF'
oriya :: CharSet
oriya = Char -> Char -> CharSet
range Char
'\x0B00' Char
'\x0B7F'
tamil :: CharSet
tamil = Char -> Char -> CharSet
range Char
'\x0B80' Char
'\x0BFF'
telugu :: CharSet
telugu = Char -> Char -> CharSet
range Char
'\x0C00' Char
'\x0C7F'
kannada :: CharSet
kannada = Char -> Char -> CharSet
range Char
'\x0C80' Char
'\x0CFF'
malayalam :: CharSet
malayalam = Char -> Char -> CharSet
range Char
'\x0D00' Char
'\x0D7F'
sinhala :: CharSet
sinhala = Char -> Char -> CharSet
range Char
'\x0D80' Char
'\x0DFF'
thai :: CharSet
thai = Char -> Char -> CharSet
range Char
'\x0E00' Char
'\x0E7F'
lao :: CharSet
lao = Char -> Char -> CharSet
range Char
'\x0E80' Char
'\x0EFF'
tibetan :: CharSet
tibetan = Char -> Char -> CharSet
range Char
'\x0F00' Char
'\x0FFF'
myanmar :: CharSet
myanmar = Char -> Char -> CharSet
range Char
'\x1000' Char
'\x109F'
georgian :: CharSet
georgian = Char -> Char -> CharSet
range Char
'\x10A0' Char
'\x10FF'
hangulJamo :: CharSet
hangulJamo = Char -> Char -> CharSet
range Char
'\x1100' Char
'\x11FF'
ethiopic :: CharSet
ethiopic = Char -> Char -> CharSet
range Char
'\x1200' Char
'\x137F'
cherokee :: CharSet
cherokee = Char -> Char -> CharSet
range Char
'\x13A0' Char
'\x13FF'
unifiedCanadianAboriginalSyllabics :: CharSet
unifiedCanadianAboriginalSyllabics = Char -> Char -> CharSet
range Char
'\x1400' Char
'\x167F'
ogham :: CharSet
ogham = Char -> Char -> CharSet
range Char
'\x1680' Char
'\x169F'
runic :: CharSet
runic = Char -> Char -> CharSet
range Char
'\x16A0' Char
'\x16FF'
tagalog :: CharSet
tagalog = Char -> Char -> CharSet
range Char
'\x1700' Char
'\x171F'
hanunoo :: CharSet
hanunoo = Char -> Char -> CharSet
range Char
'\x1720' Char
'\x173F'
buhid :: CharSet
buhid = Char -> Char -> CharSet
range Char
'\x1740' Char
'\x175F'
tagbanwa :: CharSet
tagbanwa = Char -> Char -> CharSet
range Char
'\x1760' Char
'\x177F'
khmer :: CharSet
khmer = Char -> Char -> CharSet
range Char
'\x1780' Char
'\x17FF'
mongolian :: CharSet
mongolian = Char -> Char -> CharSet
range Char
'\x1800' Char
'\x18AF'
limbu :: CharSet
limbu = Char -> Char -> CharSet
range Char
'\x1900' Char
'\x194F'
taiLe :: CharSet
taiLe = Char -> Char -> CharSet
range Char
'\x1950' Char
'\x197F'
khmerSymbols :: CharSet
khmerSymbols = Char -> Char -> CharSet
range Char
'\x19E0' Char
'\x19FF'
phoneticExtensions :: CharSet
phoneticExtensions = Char -> Char -> CharSet
range Char
'\x1D00' Char
'\x1D7F'
latinExtendedAdditional :: CharSet
latinExtendedAdditional = Char -> Char -> CharSet
range Char
'\x1E00' Char
'\x1EFF'
greekExtended :: CharSet
greekExtended = Char -> Char -> CharSet
range Char
'\x1F00' Char
'\x1FFF'
generalPunctuation :: CharSet
generalPunctuation = Char -> Char -> CharSet
range Char
'\x2000' Char
'\x206F'
superscriptsAndSubscripts :: CharSet
superscriptsAndSubscripts = Char -> Char -> CharSet
range Char
'\x2070' Char
'\x209F'
currencySymbols :: CharSet
currencySymbols = Char -> Char -> CharSet
range Char
'\x20A0' Char
'\x20CF'
combiningDiacriticalMarksForSymbols :: CharSet
combiningDiacriticalMarksForSymbols = Char -> Char -> CharSet
range Char
'\x20D0' Char
'\x20FF'
letterlikeSymbols :: CharSet
letterlikeSymbols = Char -> Char -> CharSet
range Char
'\x2100' Char
'\x214F'
numberForms :: CharSet
numberForms = Char -> Char -> CharSet
range Char
'\x2150' Char
'\x218F'
arrows :: CharSet
arrows = Char -> Char -> CharSet
range Char
'\x2190' Char
'\x21FF'
mathematicalOperators :: CharSet
mathematicalOperators = Char -> Char -> CharSet
range Char
'\x2200' Char
'\x22FF'
miscellaneousTechnical :: CharSet
miscellaneousTechnical = Char -> Char -> CharSet
range Char
'\x2300' Char
'\x23FF'
controlPictures :: CharSet
controlPictures = Char -> Char -> CharSet
range Char
'\x2400' Char
'\x243F'
opticalCharacterRecognition :: CharSet
opticalCharacterRecognition = Char -> Char -> CharSet
range Char
'\x2440' Char
'\x245F'
enclosedAlphanumerics :: CharSet
enclosedAlphanumerics = Char -> Char -> CharSet
range Char
'\x2460' Char
'\x24FF'
boxDrawing :: CharSet
boxDrawing = Char -> Char -> CharSet
range Char
'\x2500' Char
'\x257F'
blockElements :: CharSet
blockElements = Char -> Char -> CharSet
range Char
'\x2580' Char
'\x259F'
geometricShapes :: CharSet
geometricShapes = Char -> Char -> CharSet
range Char
'\x25A0' Char
'\x25FF'
miscellaneousSymbols :: CharSet
miscellaneousSymbols = Char -> Char -> CharSet
range Char
'\x2600' Char
'\x26FF'
dingbats :: CharSet
dingbats = Char -> Char -> CharSet
range Char
'\x2700' Char
'\x27BF'
miscellaneousMathematicalSymbolsA :: CharSet
miscellaneousMathematicalSymbolsA = Char -> Char -> CharSet
range Char
'\x27C0' Char
'\x27EF'
supplementalArrowsA :: CharSet
supplementalArrowsA = Char -> Char -> CharSet
range Char
'\x27F0' Char
'\x27FF'
braillePatterns :: CharSet
braillePatterns = Char -> Char -> CharSet
range Char
'\x2800' Char
'\x28FF'
supplementalArrowsB :: CharSet
supplementalArrowsB = Char -> Char -> CharSet
range Char
'\x2900' Char
'\x297F'
miscellaneousMathematicalSymbolsB :: CharSet
miscellaneousMathematicalSymbolsB = Char -> Char -> CharSet
range Char
'\x2980' Char
'\x29FF'
supplementalMathematicalOperators :: CharSet
supplementalMathematicalOperators = Char -> Char -> CharSet
range Char
'\x2A00' Char
'\x2AFF'
miscellaneousSymbolsAndArrows :: CharSet
miscellaneousSymbolsAndArrows = Char -> Char -> CharSet
range Char
'\x2B00' Char
'\x2BFF'
cjkRadicalsSupplement :: CharSet
cjkRadicalsSupplement = Char -> Char -> CharSet
range Char
'\x2E80' Char
'\x2EFF'
kangxiRadicals :: CharSet
kangxiRadicals = Char -> Char -> CharSet
range Char
'\x2F00' Char
'\x2FDF'
ideographicDescriptionCharacters :: CharSet
ideographicDescriptionCharacters = Char -> Char -> CharSet
range Char
'\x2FF0' Char
'\x2FFF'
cjkSymbolsAndPunctuation :: CharSet
cjkSymbolsAndPunctuation = Char -> Char -> CharSet
range Char
'\x3000' Char
'\x303F'
hiragana :: CharSet
hiragana = Char -> Char -> CharSet
range Char
'\x3040' Char
'\x309F'
katakana :: CharSet
katakana = Char -> Char -> CharSet
range Char
'\x30A0' Char
'\x30FF'
bopomofo :: CharSet
bopomofo = Char -> Char -> CharSet
range Char
'\x3100' Char
'\x312F'
hangulCompatibilityJamo :: CharSet
hangulCompatibilityJamo = Char -> Char -> CharSet
range Char
'\x3130' Char
'\x318F'
kanbun :: CharSet
kanbun = Char -> Char -> CharSet
range Char
'\x3190' Char
'\x319F'
bopomofoExtended :: CharSet
bopomofoExtended = Char -> Char -> CharSet
range Char
'\x31A0' Char
'\x31BF'
katakanaPhoneticExtensions :: CharSet
katakanaPhoneticExtensions = Char -> Char -> CharSet
range Char
'\x31F0' Char
'\x31FF'
enclosedCjkLettersAndMonths :: CharSet
enclosedCjkLettersAndMonths = Char -> Char -> CharSet
range Char
'\x3200' Char
'\x32FF'
cjkCompatibility :: CharSet
cjkCompatibility = Char -> Char -> CharSet
range Char
'\x3300' Char
'\x33FF'
cjkUnifiedIdeographsExtensionA :: CharSet
cjkUnifiedIdeographsExtensionA = Char -> Char -> CharSet
range Char
'\x3400' Char
'\x4DBF'
yijingHexagramSymbols :: CharSet
yijingHexagramSymbols = Char -> Char -> CharSet
range Char
'\x4DC0' Char
'\x4DFF'
cjkUnifiedIdeographs :: CharSet
cjkUnifiedIdeographs = Char -> Char -> CharSet
range Char
'\x4E00' Char
'\x9FFF'
yiSyllables :: CharSet
yiSyllables = Char -> Char -> CharSet
range Char
'\xA000' Char
'\xA48F'
yiRadicals :: CharSet
yiRadicals = Char -> Char -> CharSet
range Char
'\xA490' Char
'\xA4CF'
hangulSyllables :: CharSet
hangulSyllables = Char -> Char -> CharSet
range Char
'\xAC00' Char
'\xD7AF'
highSurrogates :: CharSet
highSurrogates = Char -> Char -> CharSet
range Char
'\xD800' Char
'\xDB7F'
highPrivateUseSurrogates :: CharSet
highPrivateUseSurrogates = Char -> Char -> CharSet
range Char
'\xDB80' Char
'\xDBFF'
lowSurrogates :: CharSet
lowSurrogates = Char -> Char -> CharSet
range Char
'\xDC00' Char
'\xDFFF'
privateUseArea :: CharSet
privateUseArea = Char -> Char -> CharSet
range Char
'\xE000' Char
'\xF8FF'
cjkCompatibilityIdeographs :: CharSet
cjkCompatibilityIdeographs = Char -> Char -> CharSet
range Char
'\xF900' Char
'\xFAFF'
alphabeticPresentationForms :: CharSet
alphabeticPresentationForms = Char -> Char -> CharSet
range Char
'\xFB00' Char
'\xFB4F'
arabicPresentationFormsA :: CharSet
arabicPresentationFormsA = Char -> Char -> CharSet
range Char
'\xFB50' Char
'\xFDFF'
variationSelectors :: CharSet
variationSelectors = Char -> Char -> CharSet
range Char
'\xFE00' Char
'\xFE0F'
combiningHalfMarks :: CharSet
combiningHalfMarks = Char -> Char -> CharSet
range Char
'\xFE20' Char
'\xFE2F'
cjkCompatibilityForms :: CharSet
cjkCompatibilityForms = Char -> Char -> CharSet
range Char
'\xFE30' Char
'\xFE4F'
smallFormVariants :: CharSet
smallFormVariants = Char -> Char -> CharSet
range Char
'\xFE50' Char
'\xFE6F'
arabicPresentationFormsB :: CharSet
arabicPresentationFormsB = Char -> Char -> CharSet
range Char
'\xFE70' Char
'\xFEFF'
halfwidthAndFullwidthForms :: CharSet
halfwidthAndFullwidthForms = Char -> Char -> CharSet
range Char
'\xFF00' Char
'\xFFEF'
specials :: CharSet
specials = Char -> Char -> CharSet
range Char
'\xFFF0' Char
'\xFFFF'