| Copyright | (c) The University of Glasgow 2001 |
|---|---|
| License | BSD-style (see the file libraries/base/LICENSE) |
| Maintainer | libraries@haskell.org |
| Stability | stable |
| Portability | portable |
| Safe Haskell | Trustworthy |
| Language | Haskell2010 |
Data.Char
Description
The Char type and associated operations.
Synopsis
- data Char
- isControl :: Char -> Bool
- isSpace :: Char -> Bool
- isLower :: Char -> Bool
- isLowerCase :: Char -> Bool
- isUpper :: Char -> Bool
- isUpperCase :: 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
- digitToInt :: Char -> Int
- intToDigit :: Int -> Char
- ord :: Char -> Int
- chr :: Int -> Char
- showLitChar :: Char -> ShowS
- lexLitChar :: ReadS String
- readLitChar :: ReadS Char
Documentation
The character type Char represents Unicode codespace
and its elements are code points as in definitions
D9 and D10 of the Unicode Standard.
Character literals in Haskell are single-quoted: 'Q', 'Я' or 'Ω'.
To represent a single quote itself use '\'', and to represent a backslash
use '\\'. The full grammar can be found in the section 2.6 of the
Haskell 2010 Language Report.
To specify a character by its code point one can use decimal, hexadecimal
or octal notation: '\65', '\x41' and '\o101' are all alternative forms
of 'A'. The largest code point is '\x10ffff'.
There is a special escape syntax for ASCII control characters:
| Escape | Alternatives | Meaning |
|---|---|---|
'\NUL' | '\0' | null character |
'\SOH' | '\1' | start of heading |
'\STX' | '\2' | start of text |
'\ETX' | '\3' | end of text |
'\EOT' | '\4' | end of transmission |
'\ENQ' | '\5' | enquiry |
'\ACK' | '\6' | acknowledge |
'\BEL' | '\7', '\a' | bell (alert) |
'\BS' | '\8', '\b' | backspace |
'\HT' | '\9', '\t' | horizontal tab |
'\LF' | '\10', '\n' | line feed (new line) |
'\VT' | '\11', '\v' | vertical tab |
'\FF' | '\12', '\f' | form feed |
'\CR' | '\13', '\r' | carriage return |
'\SO' | '\14' | shift out |
'\SI' | '\15' | shift in |
'\DLE' | '\16' | data link escape |
'\DC1' | '\17' | device control 1 |
'\DC2' | '\18' | device control 2 |
'\DC3' | '\19' | device control 3 |
'\DC4' | '\20' | device control 4 |
'\NAK' | '\21' | negative acknowledge |
'\SYN' | '\22' | synchronous idle |
'\ETB' | '\23' | end of transmission block |
'\CAN' | '\24' | cancel |
'\EM' | '\25' | end of medium |
'\SUB' | '\26' | substitute |
'\ESC' | '\27' | escape |
'\FS' | '\28' | file separator |
'\GS' | '\29' | group separator |
'\RS' | '\30' | record separator |
'\US' | '\31' | unit separator |
'\SP' | '\32', ' ' | space |
'\DEL' | '\127' | delete |
Instances
| IsChar Char Source # | Since: base-2.1 | ||||
| PrintfArg Char Source # | Since: base-2.1 | ||||
Defined in Text.Printf | |||||
| Data Char | Since: base-4.0.0.0 | ||||
Defined in GHC.Internal.Data.Data Methods gfoldl :: (forall d b. Data d => c (d -> b) -> d -> c b) -> (forall g. g -> c g) -> Char -> c Char Source # gunfold :: (forall b r. Data b => c (b -> r) -> c r) -> (forall r. r -> c r) -> Constr -> c Char Source # toConstr :: Char -> Constr Source # dataTypeOf :: Char -> DataType Source # dataCast1 :: Typeable t => (forall d. Data d => c (t d)) -> Maybe (c Char) Source # dataCast2 :: Typeable t => (forall d e. (Data d, Data e) => c (t d e)) -> Maybe (c Char) Source # gmapT :: (forall b. Data b => b -> b) -> Char -> Char Source # gmapQl :: (r -> r' -> r) -> r -> (forall d. Data d => d -> r') -> Char -> r Source # gmapQr :: forall r r'. (r' -> r -> r) -> r -> (forall d. Data d => d -> r') -> Char -> r Source # gmapQ :: (forall d. Data d => d -> u) -> Char -> [u] Source # gmapQi :: Int -> (forall d. Data d => d -> u) -> Char -> u Source # gmapM :: Monad m => (forall d. Data d => d -> m d) -> Char -> m Char Source # gmapMp :: MonadPlus m => (forall d. Data d => d -> m d) -> Char -> m Char Source # gmapMo :: MonadPlus m => (forall d. Data d => d -> m d) -> Char -> m Char Source # | |||||
| Bounded Char | Since: base-2.1 | ||||
| Enum Char | Since: base-2.1 | ||||
| Storable Char | Since: base-2.1 | ||||
Defined in GHC.Internal.Foreign.Storable Methods sizeOf :: Char -> Int Source # alignment :: Char -> Int Source # peekElemOff :: Ptr Char -> Int -> IO Char Source # pokeElemOff :: Ptr Char -> Int -> Char -> IO () Source # peekByteOff :: Ptr b -> Int -> IO Char Source # pokeByteOff :: Ptr b -> Int -> Char -> IO () Source # | |||||
| Ix Char | Since: base-2.1 | ||||
Defined in GHC.Internal.Ix | |||||
| Read Char | Since: base-2.1 | ||||
| Show Char | Since: base-2.1 | ||||
| Eq Char | |||||
| Ord Char | |||||
| TestCoercion SChar | Since: base-4.18.0.0 | ||||
Defined in GHC.Internal.TypeLits | |||||
| TestEquality SChar | Since: base-4.18.0.0 | ||||
Defined in GHC.Internal.TypeLits | |||||
| Generic1 (URec Char :: k -> Type) | |||||
Defined in GHC.Internal.Generics Associated Types
| |||||
| Foldable (UChar :: Type -> Type) | Since: base-4.9.0.0 | ||||
Defined in GHC.Internal.Data.Foldable Methods fold :: Monoid m => UChar m -> m Source # foldMap :: Monoid m => (a -> m) -> UChar a -> m Source # foldMap' :: Monoid m => (a -> m) -> UChar a -> m Source # foldr :: (a -> b -> b) -> b -> UChar a -> b Source # foldr' :: (a -> b -> b) -> b -> UChar a -> b Source # foldl :: (b -> a -> b) -> b -> UChar a -> b Source # foldl' :: (b -> a -> b) -> b -> UChar a -> b Source # foldr1 :: (a -> a -> a) -> UChar a -> a Source # foldl1 :: (a -> a -> a) -> UChar a -> a Source # toList :: UChar a -> [a] Source # null :: UChar a -> Bool Source # length :: UChar a -> Int Source # elem :: Eq a => a -> UChar a -> Bool Source # maximum :: Ord a => UChar a -> a Source # minimum :: Ord a => UChar a -> a Source # | |||||
| Traversable (UChar :: Type -> Type) | Since: base-4.9.0.0 | ||||
Defined in GHC.Internal.Data.Traversable | |||||
| Functor (URec Char :: Type -> Type) | Since: base-4.9.0.0 | ||||
| Generic (URec Char p) | |||||
Defined in GHC.Internal.Generics Associated Types
| |||||
| Show (URec Char p) | 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.Internal.Generics Methods compare :: URec Char p -> URec Char p -> Ordering Source # (<) :: URec Char p -> URec Char p -> Bool Source # (<=) :: URec Char p -> URec Char p -> Bool Source # (>) :: URec Char p -> URec Char p -> Bool Source # (>=) :: URec Char p -> URec Char p -> Bool Source # | |||||
| data URec Char (p :: k) | Used for marking occurrences of Since: base-4.9.0.0 | ||||
| type Compare (a :: Char) (b :: Char) | |||||
Defined in GHC.Internal.Data.Type.Ord | |||||
| type Rep1 (URec Char :: k -> Type) | Since: base-4.9.0.0 | ||||
Defined in GHC.Internal.Generics | |||||
| type Rep (URec Char p) | Since: base-4.9.0.0 | ||||
Defined in GHC.Internal.Generics | |||||
Character classification
Unicode characters are divided into letters, numbers, marks, punctuation, symbols, separators (including spaces) and others (including control characters).
isControl :: Char -> Bool Source #
Selects control characters, which are the non-printing characters of the Latin-1 subset of Unicode.
isSpace :: Char -> Bool Source #
Returns True for any Unicode space character, and the control
characters \t, \n, \r, \f, \v.
isLower :: Char -> Bool Source #
Selects lower-case alphabetic Unicode characters (letters).
Note: this predicate does not work for letter-like characters such as:
'ⓐ' (U+24D0 circled Latin small letter a) and
'ⅳ' (U+2173 small Roman numeral four). This is due to selecting only
characters with the GeneralCategory LowercaseLetter.
See isLowerCase for a more intuitive predicate.
isLowerCase :: Char -> Bool Source #
Selects lower-case Unicode letter-like characters.
Note: this predicate selects characters with the Unicode property
Lowercase, which includes letter-like characters such as:
'ⓐ' (U+24D0 circled Latin small letter a) and
'ⅳ' (U+2173 small Roman numeral four).
See isLower for the legacy predicate.
Since: base-4.18.0.0
isUpper :: Char -> Bool Source #
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.
Note: this predicate does not work for letter-like characters such as:
'Ⓐ' (U+24B6 circled Latin capital letter A) and
'Ⅳ' (U+2163 Roman numeral four). This is due to selecting only
characters with the GeneralCategory UppercaseLetter or TitlecaseLetter.
See isUpperCase for a more intuitive predicate. Note that
unlike isUpperCase, isUpper does select title-case characters such as
'Dž' (U+01C5 Latin capital letter d with small letter z with caron) or
'ᾯ' (U+1FAF Greek capital letter omega with dasia and perispomeni and
prosgegrammeni).
isUpperCase :: Char -> Bool Source #
Selects upper-case Unicode letter-like characters.
Note: this predicate selects characters with the Unicode property
Uppercase, which include letter-like characters such as:
'Ⓐ' (U+24B6 circled Latin capital letter A) and
'Ⅳ' (U+2163 Roman numeral four).
See isUpper for the legacy predicate. Note that
unlike isUpperCase, isUpper does select title-case characters such as
'Dž' (U+01C5 Latin capital letter d with small letter z with caron) or
'ᾯ' (U+1FAF Greek capital letter omega with dasia and perispomeni and
prosgegrammeni).
Since: base-4.18.0.0
isAlpha :: Char -> Bool Source #
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.
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".
isAlphaNum :: Char -> Bool Source #
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, e.g., Roman numerals like V'１' (aka '65297').
This function returns True if its argument has one of the
following GeneralCategorys, or False otherwise:
isPrint :: Char -> Bool Source #
Selects printable Unicode characters (letters, numbers, marks, punctuation, symbols and spaces).
This function returns False if its argument has one of the
following GeneralCategorys, or True otherwise:
isOctDigit :: Char -> Bool Source #
Selects ASCII octal digits, i.e. '0'..'7'.
isHexDigit :: Char -> Bool Source #
Selects ASCII hexadecimal digits,
i.e. '0'..'9', 'a'..'f', 'A'..'F'.
isLetter :: Char -> Bool Source #
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
isMark :: Char -> Bool Source #
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
isNumber :: Char -> Bool Source #
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 Source #
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
isSymbol :: Char -> Bool Source #
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 Source #
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
isAscii :: Char -> Bool Source #
Selects the first 128 characters of the Unicode character set, corresponding to the ASCII character set.
isLatin1 :: Char -> Bool Source #
Selects the first 256 characters of the Unicode character set, corresponding to the ISO 8859-1 (Latin-1) character set.
isAsciiUpper :: Char -> Bool Source #
isAsciiLower :: Char -> Bool Source #
Unicode general categories
data GeneralCategory Source #
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 GHC.Internal.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 Source #
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
toUpper :: Char -> Char Source #
Convert a letter to the corresponding upper-case letter, if any. Any other character is returned unchanged.
toLower :: Char -> Char Source #
Convert a letter to the corresponding lower-case letter, if any. Any other character is returned unchanged.
toTitle :: Char -> Char Source #
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.
Single digit characters
digitToInt :: Char -> Int Source #
Convert a single digit Char to the corresponding Int. This
function fails unless its argument satisfies isHexDigit, but
recognises both upper- and lower-case hexadecimal digits (that
is, '0'..'9', 'a'..'f', 'A'..'F').
Examples
Characters '0' through '9' are converted properly to
0..9:
>>>map digitToInt ['0'..'9'][0,1,2,3,4,5,6,7,8,9]
Both upper- and lower-case 'A' through 'F' are converted
as well, to 10..15.
>>>map digitToInt ['a'..'f'][10,11,12,13,14,15]>>>map digitToInt ['A'..'F'][10,11,12,13,14,15]
Anything else throws an exception:
>>>digitToInt 'G'*** Exception: Char.digitToInt: not a digit 'G'>>>digitToInt '♥'*** Exception: Char.digitToInt: not a digit '\9829'
intToDigit :: Int -> Char Source #
GHC.Internal.Numeric representations
String representations
showLitChar :: Char -> ShowS Source #
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 Source #
Read a string representation of a character, using Haskell source-language escape conventions. For example:
lexLitChar "\\nHello" = [("\\n", "Hello")]readLitChar :: ReadS Char Source #
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")]