| Safe Haskell | Safe-Inferred |
|---|---|
| Language | Haskell2010 |
RIO.Char
Description
Unicode Char. Import as:
import qualified RIO.Char as C
This module does not export any partial functions. For those, see RIO.Char.Partial
Synopsis
- data Char
- isControl :: Char -> Bool
- isSpace :: Char -> Bool
- isLower :: Char -> Bool
- isUpper :: Char -> Bool
- isAlpha :: Char -> Bool
- isAlphaNum :: Char -> Bool
- isPrint :: Char -> Bool
- isDigit :: Char -> Bool
- isOctDigit :: Char -> Bool
- isHexDigit :: Char -> Bool
- isLetter :: Char -> Bool
- isMark :: Char -> Bool
- isNumber :: Char -> Bool
- isPunctuation :: Char -> Bool
- isSymbol :: Char -> Bool
- isSeparator :: Char -> Bool
- isAscii :: Char -> Bool
- isLatin1 :: Char -> Bool
- isAsciiUpper :: Char -> Bool
- isAsciiLower :: Char -> Bool
- data GeneralCategory
- = UppercaseLetter
- | LowercaseLetter
- | TitlecaseLetter
- | ModifierLetter
- | OtherLetter
- | NonSpacingMark
- | SpacingCombiningMark
- | EnclosingMark
- | DecimalNumber
- | LetterNumber
- | OtherNumber
- | ConnectorPunctuation
- | DashPunctuation
- | OpenPunctuation
- | ClosePunctuation
- | InitialQuote
- | FinalQuote
- | OtherPunctuation
- | MathSymbol
- | CurrencySymbol
- | ModifierSymbol
- | OtherSymbol
- | Space
- | LineSeparator
- | ParagraphSeparator
- | Control
- | Format
- | Surrogate
- | PrivateUse
- | NotAssigned
- generalCategory :: Char -> GeneralCategory
- toUpper :: Char -> Char
- toLower :: Char -> Char
- toTitle :: Char -> Char
- ord :: Char -> Int
- showLitChar :: Char -> ShowS
- lexLitChar :: ReadS String
- readLitChar :: ReadS Char
Documentation
The character type Char is an enumeration whose values represent
Unicode (or equivalently ISO/IEC 10646) code points (i.e. characters, see
http://www.unicode.org/ for details). This set extends the ISO 8859-1
(Latin-1) character set (the first 256 characters), which is itself an extension
of the ASCII character set (the first 128 characters). A character literal in
Haskell has type Char.
To convert a Char to or from the corresponding Int value defined
by Unicode, use toEnum and fromEnum from the
Enum class respectively (or equivalently ord and
chr).
Instances
| Bounded Char | Since: base-2.1 |
| Enum Char | Since: base-2.1 |
| Eq Char | |
| Data Char | Since: base-4.0.0.0 |
Defined in Data.Data Methods gfoldl :: (forall d b. Data d => c (d -> b) -> d -> c b) -> (forall g. g -> c g) -> Char -> c Char # gunfold :: (forall b r. Data b => c (b -> r) -> c r) -> (forall r. r -> c r) -> Constr -> c Char # dataTypeOf :: Char -> DataType # dataCast1 :: Typeable t => (forall d. Data d => c (t d)) -> Maybe (c Char) # dataCast2 :: Typeable t => (forall d e. (Data d, Data e) => c (t d e)) -> Maybe (c Char) # gmapT :: (forall b. Data b => b -> b) -> Char -> Char # gmapQl :: (r -> r' -> r) -> r -> (forall d. Data d => d -> r') -> Char -> r # gmapQr :: forall r r'. (r' -> r -> r) -> r -> (forall d. Data d => d -> r') -> Char -> r # gmapQ :: (forall d. Data d => d -> u) -> Char -> [u] # gmapQi :: Int -> (forall d. Data d => d -> u) -> Char -> u # gmapM :: Monad m => (forall d. Data d => d -> m d) -> Char -> m Char # gmapMp :: MonadPlus m => (forall d. Data d => d -> m d) -> Char -> m Char # gmapMo :: MonadPlus m => (forall d. Data d => d -> m d) -> Char -> m Char # | |
| Ord Char | |
| Read Char | Since: base-2.1 |
| Show Char | Since: base-2.1 |
| Ix Char | Since: base-2.1 |
| Storable Char | Since: base-2.1 |
Defined in Foreign.Storable | |
| NFData Char | |
Defined in Control.DeepSeq | |
| Hashable Char | |
Defined in Data.Hashable.Class | |
| Prim Char | |
Defined in Data.Primitive.Types Methods alignment# :: Char -> Int# # indexByteArray# :: ByteArray# -> Int# -> Char # readByteArray# :: MutableByteArray# s -> Int# -> State# s -> (# State# s, Char #) # writeByteArray# :: MutableByteArray# s -> Int# -> Char -> State# s -> State# s # setByteArray# :: MutableByteArray# s -> Int# -> Int# -> Char -> State# s -> State# s # indexOffAddr# :: Addr# -> Int# -> Char # readOffAddr# :: Addr# -> Int# -> State# s -> (# State# s, Char #) # writeOffAddr# :: Addr# -> Int# -> Char -> State# s -> State# s # setOffAddr# :: Addr# -> Int# -> Int# -> Char -> State# s -> State# s # | |
| ErrorList Char | |
Defined in Control.Monad.Trans.Error | |
| Unbox Char | |
Defined in Data.Vector.Unboxed.Base | |
| Display Char Source # | Since: 0.1.0.0 |
Defined in RIO.Prelude.Display | |
| Lift Char | |
| Vector Vector Char | |
Defined in Data.Vector.Unboxed.Base Methods basicUnsafeFreeze :: PrimMonad m => Mutable Vector (PrimState m) Char -> m (Vector Char) # basicUnsafeThaw :: PrimMonad m => Vector Char -> m (Mutable Vector (PrimState m) Char) # basicLength :: Vector Char -> Int # basicUnsafeSlice :: Int -> Int -> Vector Char -> Vector Char # basicUnsafeIndexM :: Monad m => Vector Char -> Int -> m Char # basicUnsafeCopy :: PrimMonad m => Mutable Vector (PrimState m) Char -> Vector Char -> m () # | |
| MVector MVector Char | |
Defined in Data.Vector.Unboxed.Base Methods basicLength :: MVector s Char -> Int # basicUnsafeSlice :: Int -> Int -> MVector s Char -> MVector s Char # basicOverlaps :: MVector s Char -> MVector s Char -> Bool # basicUnsafeNew :: PrimMonad m => Int -> m (MVector (PrimState m) Char) # basicInitialize :: PrimMonad m => MVector (PrimState m) Char -> m () # basicUnsafeReplicate :: PrimMonad m => Int -> Char -> m (MVector (PrimState m) Char) # basicUnsafeRead :: PrimMonad m => MVector (PrimState m) Char -> Int -> m Char # basicUnsafeWrite :: PrimMonad m => MVector (PrimState m) Char -> Int -> Char -> m () # basicClear :: PrimMonad m => MVector (PrimState m) Char -> m () # basicSet :: PrimMonad m => MVector (PrimState m) Char -> Char -> m () # basicUnsafeCopy :: PrimMonad m => MVector (PrimState m) Char -> MVector (PrimState m) Char -> m () # basicUnsafeMove :: PrimMonad m => MVector (PrimState m) Char -> MVector (PrimState m) Char -> m () # basicUnsafeGrow :: PrimMonad m => MVector (PrimState m) Char -> Int -> m (MVector (PrimState m) Char) # | |
| Generic1 (URec Char :: k -> Type) | Since: base-4.9.0.0 |
| Foldable (UChar :: Type -> Type) | Since: base-4.9.0.0 |
Defined in Data.Foldable Methods fold :: Monoid m => UChar m -> m # foldMap :: Monoid m => (a -> m) -> UChar a -> m # foldMap' :: Monoid m => (a -> m) -> UChar a -> m # foldr :: (a -> b -> b) -> b -> UChar a -> b # foldr' :: (a -> b -> b) -> b -> UChar a -> b # foldl :: (b -> a -> b) -> b -> UChar a -> b # foldl' :: (b -> a -> b) -> b -> UChar a -> b # foldr1 :: (a -> a -> a) -> UChar a -> a # foldl1 :: (a -> a -> a) -> UChar a -> a # elem :: Eq a => a -> UChar a -> Bool # maximum :: Ord a => UChar a -> a # minimum :: Ord a => UChar a -> a # | |
| Traversable (UChar :: Type -> Type) | Since: base-4.9.0.0 |
| Functor (URec Char :: Type -> Type) | Since: base-4.9.0.0 |
| Eq (URec Char p) | Since: base-4.9.0.0 |
| Ord (URec Char p) | Since: base-4.9.0.0 |
Defined in GHC.Generics | |
| Show (URec Char p) | Since: base-4.9.0.0 |
| Generic (URec Char p) | Since: base-4.9.0.0 |
| newtype Vector Char | |
| data URec Char (p :: k) | Used for marking occurrences of Since: base-4.9.0.0 |
| newtype MVector s Char | |
| type Rep1 (URec Char :: k -> Type) | |
Defined in GHC.Generics | |
| type Rep (URec Char p) | |
Defined in GHC.Generics | |
Character classification
Unicode characters are divided into letters, Data.Char.numbers, marks, punctuation, Data.Char.symbols, separators (including spaces) and others (including control characters).
Selects control characters, which are the non-printing characters of the Latin-1 subset of Unicode.
Returns True for any Unicode space character, and the control
characters \t, \n, \r, \f, \v.
Selects upper-case or title-case alphabetic Unicode characters (letters). Title case is used by a small number of letter ligatures like the single-character form of Lj.
Selects alphabetic Unicode characters (lower-case, upper-case and
title-case letters, plus letters of caseless scripts and modifiers letters).
This function is equivalent to isLetter.
isAlphaNum :: Char -> Bool #
Selects alphabetic or numeric Unicode characters.
Note that numeric digits outside the ASCII range, as well as numeric
characters which aren't digits, are selected by this function but not by
isDigit. Such characters may be part of identifiers but are not used by
the printer and reader to represent numbers.
Selects printable Unicode characters (letters, numbers, marks, punctuation, symbols and spaces).
isOctDigit :: Char -> Bool #
Selects ASCII octal digits, i.e. '0'..'7'.
isHexDigit :: Char -> Bool #
Selects ASCII hexadecimal digits,
i.e. '0'..'9', 'a'..'f', 'A'..'F'.
Selects alphabetic Unicode characters (lower-case, upper-case and
title-case letters, plus letters of caseless scripts and
modifiers letters). This function is equivalent to
isAlpha.
This function returns True if its argument has one of the
following GeneralCategorys, or False otherwise:
These classes are defined in the Unicode Character Database, part of the Unicode standard. The same document defines what is and is not a "Letter".
Examples
Basic usage:
>>>isLetter 'a'True>>>isLetter 'A'True>>>isLetter 'λ'True>>>isLetter '0'False>>>isLetter '%'False>>>isLetter '♥'False>>>isLetter '\31'False
Ensure that isLetter and isAlpha are equivalent.
>>>let chars = [(chr 0)..]>>>let letters = map isLetter chars>>>let alphas = map isAlpha chars>>>letters == alphasTrue
Selects Unicode mark characters, for example accents and the like, which combine with preceding characters.
This function returns True if its argument has one of the
following GeneralCategorys, or False otherwise:
These classes are defined in the Unicode Character Database, part of the Unicode standard. The same document defines what is and is not a "Mark".
Examples
Basic usage:
>>>isMark 'a'False>>>isMark '0'False
Combining marks such as accent characters usually need to follow another character before they become printable:
>>>map isMark "ò"[False,True]
Puns are not necessarily supported:
>>>isMark '✓'False
Selects Unicode numeric characters, including digits from various scripts, Roman numerals, et cetera.
This function returns True if its argument has one of the
following GeneralCategorys, or False otherwise:
These classes are defined in the Unicode Character Database, part of the Unicode standard. The same document defines what is and is not a "Number".
Examples
Basic usage:
>>>isNumber 'a'False>>>isNumber '%'False>>>isNumber '3'True
ASCII '0' through '9' are all numbers:
>>>and $ map isNumber ['0'..'9']True
Unicode Roman numerals are "numbers" as well:
>>>isNumber 'Ⅸ'True
isPunctuation :: Char -> Bool #
Selects Unicode punctuation characters, including various kinds of connectors, brackets and quotes.
This function returns True if its argument has one of the
following GeneralCategorys, or False otherwise:
ConnectorPunctuationDashPunctuationOpenPunctuationClosePunctuationInitialQuoteFinalQuoteOtherPunctuation
These classes are defined in the Unicode Character Database, part of the Unicode standard. The same document defines what is and is not a "Punctuation".
Examples
Basic usage:
>>>isPunctuation 'a'False>>>isPunctuation '7'False>>>isPunctuation '♥'False>>>isPunctuation '"'True>>>isPunctuation '?'True>>>isPunctuation '—'True
Selects Unicode symbol characters, including mathematical and currency symbols.
This function returns True if its argument has one of the
following GeneralCategorys, or False otherwise:
These classes are defined in the Unicode Character Database, part of the Unicode standard. The same document defines what is and is not a "Symbol".
Examples
Basic usage:
>>>isSymbol 'a'False>>>isSymbol '6'False>>>isSymbol '='True
The definition of "math symbol" may be a little counter-intuitive depending on one's background:
>>>isSymbol '+'True>>>isSymbol '-'False
isSeparator :: Char -> Bool #
Selects Unicode space and separator characters.
This function returns True if its argument has one of the
following GeneralCategorys, or False otherwise:
These classes are defined in the Unicode Character Database, part of the Unicode standard. The same document defines what is and is not a "Separator".
Examples
Basic usage:
>>>isSeparator 'a'False>>>isSeparator '6'False>>>isSeparator ' 'True
Warning: newlines and tab characters are not considered separators.
>>>isSeparator '\n'False>>>isSeparator '\t'False
But some more exotic characters are (like HTML's ):
>>>isSeparator '\160'True
Subranges
Selects the first 128 characters of the Unicode character set, corresponding to the ASCII character set.
Selects the first 256 characters of the Unicode character set, corresponding to the ISO 8859-1 (Latin-1) character set.
isAsciiUpper :: Char -> Bool #
isAsciiLower :: Char -> Bool #
Unicode general categories
data GeneralCategory #
Unicode General Categories (column 2 of the UnicodeData table) in the order they are listed in the Unicode standard (the Unicode Character Database, in particular).
Examples
Basic usage:
>>>:t OtherLetterOtherLetter :: GeneralCategory
Eq instance:
>>>UppercaseLetter == UppercaseLetterTrue>>>UppercaseLetter == LowercaseLetterFalse
Ord instance:
>>>NonSpacingMark <= MathSymbolTrue
Enum instance:
>>>enumFromTo ModifierLetter SpacingCombiningMark[ModifierLetter,OtherLetter,NonSpacingMark,SpacingCombiningMark]
Read instance:
>>>read "DashPunctuation" :: GeneralCategoryDashPunctuation>>>read "17" :: GeneralCategory*** Exception: Prelude.read: no parse
Show instance:
>>>show EnclosingMark"EnclosingMark"
Bounded instance:
>>>minBound :: GeneralCategoryUppercaseLetter>>>maxBound :: GeneralCategoryNotAssigned
Ix instance:
>>>import Data.Ix ( index )>>>index (OtherLetter,Control) FinalQuote12>>>index (OtherLetter,Control) Format*** Exception: Error in array index
Constructors
| UppercaseLetter | Lu: Letter, Uppercase |
| LowercaseLetter | Ll: Letter, Lowercase |
| TitlecaseLetter | Lt: Letter, Titlecase |
| ModifierLetter | Lm: Letter, Modifier |
| OtherLetter | Lo: Letter, Other |
| NonSpacingMark | Mn: Mark, Non-Spacing |
| SpacingCombiningMark | Mc: Mark, Spacing Combining |
| EnclosingMark | Me: Mark, Enclosing |
| DecimalNumber | Nd: Number, Decimal |
| LetterNumber | Nl: Number, Letter |
| OtherNumber | No: Number, Other |
| ConnectorPunctuation | Pc: Punctuation, Connector |
| DashPunctuation | Pd: Punctuation, Dash |
| OpenPunctuation | Ps: Punctuation, Open |
| ClosePunctuation | Pe: Punctuation, Close |
| InitialQuote | Pi: Punctuation, Initial quote |
| FinalQuote | Pf: Punctuation, Final quote |
| OtherPunctuation | Po: Punctuation, Other |
| MathSymbol | Sm: Symbol, Math |
| CurrencySymbol | Sc: Symbol, Currency |
| ModifierSymbol | Sk: Symbol, Modifier |
| OtherSymbol | So: Symbol, Other |
| Space | Zs: Separator, Space |
| LineSeparator | Zl: Separator, Line |
| ParagraphSeparator | Zp: Separator, Paragraph |
| Control | Cc: Other, Control |
| Format | Cf: Other, Format |
| Surrogate | Cs: Other, Surrogate |
| PrivateUse | Co: Other, Private Use |
| NotAssigned | Cn: Other, Not Assigned |
Instances
generalCategory :: Char -> GeneralCategory #
The Unicode general category of the character. This relies on the
Enum instance of GeneralCategory, which must remain in the
same order as the categories are presented in the Unicode
standard.
Examples
Basic usage:
>>>generalCategory 'a'LowercaseLetter>>>generalCategory 'A'UppercaseLetter>>>generalCategory '0'DecimalNumber>>>generalCategory '%'OtherPunctuation>>>generalCategory '♥'OtherSymbol>>>generalCategory '\31'Control>>>generalCategory ' 'Space
Case conversion
Convert a letter to the corresponding upper-case letter, if any. Any other character is returned unchanged.
Convert a letter to the corresponding lower-case letter, if any. Any other character is returned unchanged.
Convert a letter to the corresponding title-case or upper-case letter, if any. (Title case differs from upper case only for a small number of ligature letters.) Any other character is returned unchanged.
Numeric representations
String representations
showLitChar :: Char -> ShowS #
Convert a character to a string using only printable characters, using Haskell source-language escape conventions. For example:
showLitChar '\n' s = "\\n" ++ s
lexLitChar :: ReadS String #
Read a string representation of a character, using Haskell source-language escape conventions. For example:
lexLitChar "\\nHello" = [("\\n", "Hello")]readLitChar :: ReadS Char #
Read a string representation of a character, using Haskell source-language escape conventions, and convert it to the character that it encodes. For example:
readLitChar "\\nHello" = [('\n', "Hello")]