Copyright	(c) 2024 Pierre Le Marre
Maintainer	dev@wismill.eu
Stability	experimental
Safe Haskell	None
Language	GHC2021

UCD.Parser.UnicodeData

Description

Parser for UnicodeData.txt.

Since: 0.1.0

Synopsis

data GeneralCategory
- = Lu
- | Ll
- | Lt
- | Lm
- | Lo
- | Mn
- | Mc
- | Me
- | Nd
- | Nl
- | No
- | Pc
- | Pd
- | Ps
- | Pe
- | Pi
- | Pf
- | Po
- | Sm
- | Sc
- | Sk
- | So
- | Zs
- | Zl
- | Zp
- | Cc
- | Cf
- | Cs
- | Co
- | Cn
data DecompositionType
- = DTCanonical
- | DTCompat
- | DTFont
- | DTNoBreak
- | DTInitial
- | DTMedial
- | DTFinal
- | DTIsolated
- | DTCircle
- | DTSuper
- | DTSub
- | DTVertical
- | DTWide
- | DTNarrow
- | DTSmall
- | DTSquare
- | DTFraction
data Decomposition
- = Self
- | Decomposition !DecompositionType ![Char]
data Entry = Entry {
- _range :: !(UnicodeRange ShortByteString)
- _details :: !CharDetails
}
data NumericValue
- = NotNumeric
- | Digit !Word8
- | Integer !Integer
- | Rational !Rational
data CharDetails = CharDetails {
- _generalCategory :: !GeneralCategory
- _combiningClass :: !Int
- _decomposition :: !Decomposition
- _numericValue :: !NumericValue
- _simpleUpperCaseMapping :: !(Maybe Char)
- _simpleLowerCaseMapping :: !(Maybe Char)
- _simpleTitleCaseMapping :: !(Maybe Char)
}
parse :: ByteString -> [Entry]

Documentation

data GeneralCategory Source #

See: https://www.unicode.org/reports/tr44/#General_Category

Since: 0.1.0

Constructors

Lu	Letter, Uppercase
Ll	Letter, Lowercase
Lt	Letter, Titlecase
Lm	Letter, Modifier
Lo	Letter, Other
Mn	Mark, Non-Spacing
Mc	Mark, Spacing Combining
Me	Mark, Enclosing
Nd	Number, Decimal
Nl	Number, Letter
No	Number, Other
Pc	Punctuation, Connector
Pd	Punctuation, Dash
Ps	Punctuation, Open
Pe	Punctuation, Close
Pi	Punctuation, Initial quote
Pf	Punctuation, Final quote
Po	Punctuation, Other
Sm	Symbol, Math
Sc	Symbol, Currency
Sk	Symbol, Modifier
So	Symbol, Other
Zs	Separator, Space
Zl	Separator, Line
Zp	Separator, Paragraph
Cc	Other, Control
Cf	Other, Format
Cs	Other, Surrogate
Co	Other, Private Use
Cn	Other, Not Assigned

Instances

Instances details

Bounded GeneralCategory Source #
Instance details Defined in UCD.Parser.UnicodeData Methods minBound :: GeneralCategory maxBound :: GeneralCategory
Enum GeneralCategory Source #
Instance details Defined in UCD.Parser.UnicodeData Methods succ :: GeneralCategory -> GeneralCategory pred :: GeneralCategory -> GeneralCategory toEnum :: Int -> GeneralCategory fromEnum :: GeneralCategory -> Int enumFrom :: GeneralCategory -> [GeneralCategory] enumFromThen :: GeneralCategory -> GeneralCategory -> [GeneralCategory] enumFromTo :: GeneralCategory -> GeneralCategory -> [GeneralCategory] enumFromThenTo :: GeneralCategory -> GeneralCategory -> GeneralCategory -> [GeneralCategory]
Read GeneralCategory Source #
Instance details Defined in UCD.Parser.UnicodeData Methods readsPrec :: Int -> ReadS GeneralCategory readList :: ReadS [GeneralCategory] readPrec :: ReadPrec GeneralCategory readListPrec :: ReadPrec [GeneralCategory]
Show GeneralCategory Source #
Instance details Defined in UCD.Parser.UnicodeData Methods showsPrec :: Int -> GeneralCategory -> ShowS show :: GeneralCategory -> String showList :: [GeneralCategory] -> ShowS
Eq GeneralCategory Source #
Instance details Defined in UCD.Parser.UnicodeData Methods (==) :: GeneralCategory -> GeneralCategory -> Bool (/=) :: GeneralCategory -> GeneralCategory -> Bool

data DecompositionType Source #

See: https://www.unicode.org/reports/tr44/#Character_Decomposition_Mappings

Since: 0.1.0

Constructors

DTCanonical
DTCompat
DTFont
DTNoBreak
DTInitial
DTMedial
DTFinal
DTIsolated
DTCircle
DTSuper
DTSub
DTVertical
DTWide
DTNarrow
DTSmall
DTSquare
DTFraction

Instances

Instances details

Show DecompositionType Source #
Instance details Defined in UCD.Parser.UnicodeData Methods showsPrec :: Int -> DecompositionType -> ShowS show :: DecompositionType -> String showList :: [DecompositionType] -> ShowS
Eq DecompositionType Source #
Instance details Defined in UCD.Parser.UnicodeData Methods (==) :: DecompositionType -> DecompositionType -> Bool (/=) :: DecompositionType -> DecompositionType -> Bool

data Decomposition Source #

Unicode decomposition of a code point

Since: 0.1.0

Constructors

Self
Decomposition !DecompositionType ![Char]

Instances

Instances details

Show Decomposition Source #
Instance details Defined in UCD.Parser.UnicodeData Methods showsPrec :: Int -> Decomposition -> ShowS show :: Decomposition -> String showList :: [Decomposition] -> ShowS
Eq Decomposition Source #
Instance details Defined in UCD.Parser.UnicodeData Methods (==) :: Decomposition -> Decomposition -> Bool (/=) :: Decomposition -> Decomposition -> Bool

data Entry Source #

An entry in UnicodeData.txt.

Since: 0.1.0

Constructors

Entry
Fields _range :: !(UnicodeRange ShortByteString) _details :: !CharDetails

Instances

Instances details

Show Entry Source #
Instance details Defined in UCD.Parser.UnicodeData Methods showsPrec :: Int -> Entry -> ShowS show :: Entry -> String showList :: [Entry] -> ShowS
Eq Entry Source #
Instance details Defined in UCD.Parser.UnicodeData Methods (==) :: Entry -> Entry -> Bool (/=) :: Entry -> Entry -> Bool

data NumericValue Source #

Numeric value of a code point, if relevant

Since: 0.1.0

Constructors

NotNumeric
Digit !Word8
Integer !Integer
Rational !Rational

Instances

Instances details

Show NumericValue Source #
Instance details Defined in UCD.Parser.UnicodeData Methods showsPrec :: Int -> NumericValue -> ShowS show :: NumericValue -> String showList :: [NumericValue] -> ShowS
Eq NumericValue Source #
Instance details Defined in UCD.Parser.UnicodeData Methods (==) :: NumericValue -> NumericValue -> Bool (/=) :: NumericValue -> NumericValue -> Bool

data CharDetails Source #

Core characteristics of a Unicode code point

Since: 0.1.0

Constructors

CharDetails
Fields _generalCategory :: !GeneralCategory _combiningClass :: !Int _decomposition :: !Decomposition _numericValue :: !NumericValue _simpleUpperCaseMapping :: !(Maybe Char) _simpleLowerCaseMapping :: !(Maybe Char) _simpleTitleCaseMapping :: !(Maybe Char)

Instances

Instances details

Show CharDetails Source #
Instance details Defined in UCD.Parser.UnicodeData Methods showsPrec :: Int -> CharDetails -> ShowS show :: CharDetails -> String showList :: [CharDetails] -> ShowS
Eq CharDetails Source #
Instance details Defined in UCD.Parser.UnicodeData Methods (==) :: CharDetails -> CharDetails -> Bool (/=) :: CharDetails -> CharDetails -> Bool

parse :: ByteString -> [Entry] Source #

Parser for UnicodeData.txt file

Since: 0.1.0