base-4.8.2.0: Basic libraries

Copyright(c) The University of Glasgow 2001
LicenseBSD-style (see the file libraries/base/LICENSE)
Maintainerlibraries@haskell.org
Stabilitystable
Portabilityportable
Safe HaskellTrustworthy
LanguageHaskell2010

Data.Char

Contents

Description

The Char type and associated operations.

Synopsis

Documentation

data Char :: *

The character type Char is an enumeration whose values represent Unicode (or equivalently ISO/IEC 10646) 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 Source 
Enum Char Source 
Eq Char 

Methods

(==) :: Char -> Char -> Bool

(/=) :: Char -> Char -> Bool

Data Char Source 

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 :: (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

Ord Char 

Methods

compare :: Char -> Char -> Ordering

(<) :: Char -> Char -> Bool

(<=) :: Char -> Char -> Bool

(>) :: Char -> Char -> Bool

(>=) :: Char -> Char -> Bool

max :: Char -> Char -> Char

min :: Char -> Char -> Char

Read Char Source 
Show Char Source 
Ix Char Source 
Generic Char Source 

Associated Types

type Rep Char :: * -> * Source

Methods

from :: Char -> Rep Char x Source

to :: Rep Char x -> Char Source

Storable Char Source 
IsChar Char Source 
PrintfArg Char Source 
IsString [Char] Source 

Methods

fromString :: String -> [Char] Source

type Rep Char Source 

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).

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.

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.

isAlphaNum :: Char -> Bool Source

Selects alphabetic or numeric digit Unicode characters.

Note that numeric digits outside the ASCII range are selected by this function but not by isDigit. Such digits may be part of identifiers but are not used by the printer and reader to represent numbers.

isPrint :: Char -> Bool Source

Selects printable Unicode characters (letters, numbers, marks, punctuation, symbols and spaces).

isDigit :: Char -> Bool Source

Selects ASCII digits, i.e. '0'..'9'.

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 '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 == alphas
True

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:

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 &nbsp;):

>>> 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

Selects ASCII upper-case letters, i.e. characters satisfying both isAscii and isUpper.

isAsciiLower :: Char -> Bool Source

Selects ASCII lower-case letters, i.e. characters satisfying both isAscii and isLower.

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 OtherLetter
OtherLetter :: GeneralCategory

Eq instance:

>>> UppercaseLetter == UppercaseLetter
True
>>> UppercaseLetter == LowercaseLetter
False

Ord instance:

>>> NonSpacingMark <= MathSymbol
True

Enum instance:

>>> enumFromTo ModifierLetter SpacingCombiningMark
[ModifierLetter,OtherLetter,NonSpacingMark,SpacingCombiningMark]

Read instance:

>>> read "DashPunctuation" :: GeneralCategory
DashPunctuation
>>> read "17" :: GeneralCategory
*** Exception: Prelude.read: no parse

Show instance:

>>> show EnclosingMark
"EnclosingMark"

Bounded instance:

>>> minBound :: GeneralCategory
UppercaseLetter
>>> maxBound :: GeneralCategory
NotAssigned

Ix instance:

>>> import Data.Ix ( index )
>>> index (OtherLetter,Control) FinalQuote
12
>>> 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

Bounded GeneralCategory Source 
Enum GeneralCategory Source 
Eq GeneralCategory Source 
Ord GeneralCategory Source 
Read GeneralCategory Source 
Show GeneralCategory Source 
Ix GeneralCategory Source 

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

Convert an Int in the range 0..15 to the corresponding single digit Char. This function fails on other inputs, and generates lower-case hexadecimal digits.

Numeric representations

ord :: Char -> Int Source

The fromEnum method restricted to the type Char.

chr :: Int -> Char Source

The toEnum method restricted to the type Char.

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")]