Z.Data.Text

A Text wrap a Bytes which will be interpreted using UTF-8 encoding. User should always use validate / validateMaybe to construt a Text (instead of using construtor directly or coercing), otherwise illegal UTF-8 encoded codepoints will cause undefined behaviours.

This library also provide simple unicode processing based on utf8rewind, see normalize, caseFold (current using unicode 13 databases).

Text type

data Text

Text represented as UTF-8 encoded Bytes

Instances

IsList Text

Defined in Z.Data.Text.Base

Associated Types

type Item Text

Methods

fromList :: [Item Text] -> Text

fromListN :: Int -> [Item Text] -> Text

toList :: Text -> [Item Text]

Eq Text

Defined in Z.Data.Text.Base

Methods

(==) :: Text -> Text -> Bool

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

Ord Text

Defined in Z.Data.Text.Base

Methods

compare :: Text -> Text -> Ordering

(<) :: Text -> Text -> Bool

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

(>) :: Text -> Text -> Bool

(>=) :: Text -> Text -> Bool

max :: Text -> Text -> Text

min :: Text -> Text -> Text

Read Text

Accepted syntax and escaping rules are same with String, which is different from Show instance.

Defined in Z.Data.Text.Base

Methods

readsPrec :: Int -> ReadS Text

readList :: ReadS [Text]

readPrec :: ReadPrec Text

readListPrec :: ReadPrec [Text]

Show Text

The escaping rules is different from String 's Show instance, see "Z.Data.Text.Builder.escapeTextJSON"

Defined in Z.Data.Text.Base

Methods

showsPrec :: Int -> Text -> ShowS

show :: Text -> String

showList :: [Text] -> ShowS

IsString Text

Defined in Z.Data.Text.Base

Methods

fromString :: String -> Text

Semigroup Text

Defined in Z.Data.Text.Base

Methods

(<>) :: Text -> Text -> Text

sconcat :: NonEmpty Text -> Text

stimes :: Integral b => b -> Text -> Text

Monoid Text

Defined in Z.Data.Text.Base

Methods

mempty :: Text

mappend :: Text -> Text -> Text

mconcat :: [Text] -> Text

Arbitrary Text

Defined in Z.Data.Text.Base

Methods

arbitrary :: Gen Text

shrink :: Text -> [Text]

CoArbitrary Text

Defined in Z.Data.Text.Base

Methods

coarbitrary :: Text -> Gen b -> Gen b

FoldCase Text

case fold with default locale.

Defined in Z.Data.Text.Base

Methods

foldCase :: Text -> Text

foldCaseList :: [Text] -> [Text]

NFData Text

Defined in Z.Data.Text.Base

Methods

rnf :: Text -> ()

Hashable Text

Defined in Z.Data.Text.Base

Methods

hashWithSalt :: Int -> Text -> Int

hash :: Text -> Int

Print Text

The escaping rules is same with Show instance: we reuse JSON escaping rules here, so it will be faster.

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Text -> Builder ()

JSON Text

Defined in Z.Data.JSON.Base

Methods

fromValue :: Value -> Converter Text

toValue :: Text -> Value

encodeJSON :: Text -> Builder ()

JSON a => JSON (Map Text a)

Defined in Z.Data.JSON.Base

Methods

fromValue :: Value -> Converter (Map Text a)

toValue :: Map Text a -> Value

encodeJSON :: Map Text a -> Builder ()

JSON a => JSON (HashMap Text a)

default instance prefer later key

Defined in Z.Data.JSON.Base

Methods

fromValue :: Value -> Converter (HashMap Text a)

toValue :: HashMap Text a -> Value

encodeJSON :: HashMap Text a -> Builder ()

JSON a => JSON (FlatMap Text a)

default instance prefer later key

Defined in Z.Data.JSON.Base

Methods

fromValue :: Value -> Converter (FlatMap Text a)

toValue :: FlatMap Text a -> Value

encodeJSON :: FlatMap Text a -> Builder ()

type Item Text

Defined in Z.Data.Text.Base

type Item Text = Char

getUTF8Bytes :: Text -> Bytes

Extract UTF-8 encoded Bytes from Text

validate :: HasCallStack => Bytes -> Text

O(n) Validate a sequence of bytes is UTF-8 encoded.

Throw InvalidUTF8Exception in case of invalid codepoint.

validateASCII :: HasCallStack => Bytes -> Text

O(n) Validate a sequence of bytes is all ascii char byte(<128).

Throw InvalidASCIIException in case of invalid byte, It's not always faster than validate, use it only if you want to validate ASCII char sequences.

validateMaybe :: Bytes -> Maybe Text

O(n) Validate a sequence of bytes is UTF-8 encoded.

Return Nothing in case of invalid codepoint.

validateASCIIMaybe :: Bytes -> Maybe Text

O(n) Validate a sequence of bytes is all ascii char byte(<128).

Return Nothing in case of invalid byte.

data TextException

Constructors

InvalidUTF8Exception CallStack

InvalidASCIIException CallStack

IndexOutOfTextRange Int CallStack

first payload is invalid char index

EmptyText CallStack

Instances

Show TextException

Defined in Z.Data.Text.Base

Methods

showsPrec :: Int -> TextException -> ShowS

show :: TextException -> String

showList :: [TextException] -> ShowS

Exception TextException

Defined in Z.Data.Text.Base

Methods

toException :: TextException -> SomeException

fromException :: SomeException -> Maybe TextException

displayException :: TextException -> String

index :: HasCallStack => Text -> Int -> Char

O(n) Get the nth codepoint from Text, throw IndexOutOfTextRange when out of bound.

indexMaybe :: Text -> Int -> Maybe Char

O(n) Get the nth codepoint from Text.

indexR :: HasCallStack => Text -> Int -> Char

O(n) Get the nth codepoint from Text counting from the end, throw IndexOutOfVectorRange n callStack when out of bound.

indexMaybeR :: Text -> Int -> Maybe Char

O(n) Get the nth codepoint from Text counting from the end.

Basic creating

empty :: Text

O(1). Empty text.

singleton :: Char -> Text

O(1). Single char text.

copy :: Text -> Text

O(n). Copy a text from slice.

replicate :: Int -> Char -> Text

O(n) replicate char n time.

cycleN :: Int -> Text -> Text

O(n*m) cycleN a text n times.

Conversion between list

pack :: String -> Text

O(n) Convert a string into a text

Alias for packN defaultInitSize, will be rewritten to a memcpy if possible.

packN :: Int -> String -> Text

O(n) Convert a list into a text with an approximate size(in bytes, not codepoints).

If the encoded bytes length is larger than the size given, we simply double the buffer size and continue building.

This function is a good consumer in the sense of build/foldr fusion.

packR :: String -> Text

O(n) Alias for packRN defaultInitSize.

packRN :: Int -> String -> Text

O(n) packN in reverse order.

This function is a good consumer in the sense of build/foldr fusion.

unpack :: Text -> String

O(n) Convert text to a char list.

Unpacking is done lazily. i.e. we will retain reference to the array until all element are consumed.

This function is a good producer in the sense of build/foldr fusion.

unpackR :: Text -> String

O(n) Convert text to a list in reverse order.

This function is a good producer in the sense of build/foldr fusion.

Conversion between codepoint vector

fromVector :: PrimVector Char -> Text

O(n) convert from a char vector.

toVector :: Text -> PrimVector Char

O(n) convert to a char vector.

Print class

class Print a where

A class similar to Show, serving the purpose that quickly convert a data type to a Text value.

You can use newtype or generic deriving to implement instance of this class quickly:

 {-# LANGUAGE GeneralizedNewtypeDeriving #-}
 {-# LANGUAGE DeriveAnyClass #-}
 {-# LANGUAGE DeriveGeneric #-}
 {-# LANGUAGE DerivingStrategies #-}

 import GHC.Generics

 newtype FooInt = FooInt Int deriving (Generic)
                           deriving anyclass Print

> toText (FooInt 3)
> "FooInt 3"

 newtype FooInt = FooInt Int deriving (Generic)
                           deriving newtype Print

> toText (FooInt 3)
> "3"

Minimal complete definition

Nothing

Methods

toUTF8BuilderP :: Int -> a -> Builder ()

Convert data to Builder with precendence.

You should return a Builder writing in UTF8 encoding only, i.e.

Z.Data.Text.validateMaybe (Z.Data.Builder.build (toUTF8BuilderP p a)) /= Nothing

default toUTF8BuilderP :: (Generic a, GToText (Rep a)) => Int -> a -> Builder ()

Instances

Print Bool

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Bool -> Builder ()

Print Char

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Char -> Builder ()

Print Double

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Double -> Builder ()

Print Float

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Float -> Builder ()

Print Int

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Int -> Builder ()

Print Int8

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Int8 -> Builder ()

Print Int16

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Int16 -> Builder ()

Print Int32

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Int32 -> Builder ()

Print Int64

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Int64 -> Builder ()

Print Integer

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Integer -> Builder ()

Print Natural

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Natural -> Builder ()

Print Ordering

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Ordering -> Builder ()

Print Word

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Word -> Builder ()

Print Word8

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Word8 -> Builder ()

Print Word16

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Word16 -> Builder ()

Print Word32

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Word32 -> Builder ()

Print Word64

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Word64 -> Builder ()

Print CallStack

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> CallStack -> Builder ()

Print ()

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> () -> Builder ()

Print Version

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Version -> Builder ()

Print ExitCode

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> ExitCode -> Builder ()

Print CChar

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> CChar -> Builder ()

Print CSChar

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> CSChar -> Builder ()

Print CUChar

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> CUChar -> Builder ()

Print CShort

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> CShort -> Builder ()

Print CUShort

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> CUShort -> Builder ()

Print CInt

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> CInt -> Builder ()

Print CUInt

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> CUInt -> Builder ()

Print CLong

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> CLong -> Builder ()

Print CULong

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> CULong -> Builder ()

Print CLLong

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> CLLong -> Builder ()

Print CULLong

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> CULLong -> Builder ()

Print CBool

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> CBool -> Builder ()

Print CFloat

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> CFloat -> Builder ()

Print CDouble

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> CDouble -> Builder ()

Print CPtrdiff

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> CPtrdiff -> Builder ()

Print CSize

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> CSize -> Builder ()

Print CWchar

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> CWchar -> Builder ()

Print CSigAtomic

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> CSigAtomic -> Builder ()

Print CClock

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> CClock -> Builder ()

Print CTime

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> CTime -> Builder ()

Print CUSeconds

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> CUSeconds -> Builder ()

Print CSUSeconds

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> CSUSeconds -> Builder ()

Print CIntPtr

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> CIntPtr -> Builder ()

Print CUIntPtr

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> CUIntPtr -> Builder ()

Print CIntMax

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> CIntMax -> Builder ()

Print CUIntMax

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> CUIntMax -> Builder ()

Print SomeException

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> SomeException -> Builder ()

Print Scientific

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Scientific -> Builder ()

Print ZonedTime

YYYY-MM-DDTHH:MM:SS.SSSZ

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> ZonedTime -> Builder ()

Print LocalTime

YYYY-MM-DDTHH:MM:SS.SSSZ

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> LocalTime -> Builder ()

Print TimeOfDay

HH:MM:SS.SSS

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> TimeOfDay -> Builder ()

Print CalendarDiffTime

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> CalendarDiffTime -> Builder ()

Print UTCTime

YYYY-MM-DDTHH:MM:SS.SSSZ

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> UTCTime -> Builder ()

Print SystemTime

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> SystemTime -> Builder ()

Print NominalDiffTime

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> NominalDiffTime -> Builder ()

Print DiffTime

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> DiffTime -> Builder ()

Print DayOfWeek

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> DayOfWeek -> Builder ()

Print Day

YYYY-MM-DD

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Day -> Builder ()

Print CalendarDiffDays

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> CalendarDiffDays -> Builder ()

Print Text

The escaping rules is same with Show instance: we reuse JSON escaping rules here, so it will be faster.

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Text -> Builder ()

Print FlatIntSet

Defined in Z.Data.Vector.FlatIntSet

Methods

toUTF8BuilderP :: Int -> FlatIntSet -> Builder ()

Print Value

Defined in Z.Data.JSON.Value

Methods

toUTF8BuilderP :: Int -> Value -> Builder ()

Print ConvertError

Defined in Z.Data.JSON.Converter

Methods

toUTF8BuilderP :: Int -> ConvertError -> Builder ()

Print HexBytes

Defined in Z.Data.Vector.Hex

Methods

toUTF8BuilderP :: Int -> HexBytes -> Builder ()

Print CBytes

This instance provide UTF8 guarantee, illegal codepoints will be written as replacementChars.

Escaping rule is same with String.

Defined in Z.Data.CBytes

Methods

toUTF8BuilderP :: Int -> CBytes -> Builder ()

Print RegexOpts

Defined in Z.Data.Text.Regex

Methods

toUTF8BuilderP :: Int -> RegexOpts -> Builder ()

Print Regex

Defined in Z.Data.Text.Regex

Methods

toUTF8BuilderP :: Int -> Regex -> Builder ()

Print a => Print [a]

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> [a] -> Builder ()

Print a => Print (Maybe a)

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Maybe a -> Builder ()

(Print a, Integral a) => Print (Ratio a)

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Ratio a -> Builder ()

Print (Ptr a)

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Ptr a -> Builder ()

Print (ForeignPtr a)

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> ForeignPtr a -> Builder ()

Print a => Print (Min a)

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Min a -> Builder ()

Print a => Print (Max a)

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Max a -> Builder ()

Print a => Print (First a)

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> First a -> Builder ()

Print a => Print (Last a)

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Last a -> Builder ()

Print a => Print (WrappedMonoid a)

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> WrappedMonoid a -> Builder ()

Print a => Print (Identity a)

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Identity a -> Builder ()

Print a => Print (First a)

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> First a -> Builder ()

Print a => Print (Last a)

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Last a -> Builder ()

Print a => Print (Dual a)

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Dual a -> Builder ()

Print a => Print (NonEmpty a)

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> NonEmpty a -> Builder ()

(Prim a, Print a) => Print (PrimArray a)

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> PrimArray a -> Builder ()

Print a => Print (SmallArray a)

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> SmallArray a -> Builder ()

Print a => Print (Array a)

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Array a -> Builder ()

(Prim a, Print a) => Print (PrimVector a)

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> PrimVector a -> Builder ()

Print a => Print (Vector a)

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Vector a -> Builder ()

Print v => Print (FlatSet v)

Defined in Z.Data.Vector.FlatSet

Methods

toUTF8BuilderP :: Int -> FlatSet v -> Builder ()

Print v => Print (FlatIntMap v)

Defined in Z.Data.Vector.FlatIntMap

Methods

toUTF8BuilderP :: Int -> FlatIntMap v -> Builder ()

Print (CPtr a)

Defined in Z.Foreign.CPtr

Methods

toUTF8BuilderP :: Int -> CPtr a -> Builder ()

(Print a, Print b) => Print (Either a b)

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Either a b -> Builder ()

(Print a, Print b) => Print (a, b)

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> (a, b) -> Builder ()

HasResolution a => Print (Fixed a)

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Fixed a -> Builder ()

Print (Proxy a)

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Proxy a -> Builder ()

(PrimUnlifted a, Print a) => Print (UnliftedArray a)

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> UnliftedArray a -> Builder ()

(Print k, Print v) => Print (FlatMap k v)

Defined in Z.Data.Vector.FlatMap

Methods

toUTF8BuilderP :: Int -> FlatMap k v -> Builder ()

(Print a, Print b, Print c) => Print (a, b, c)

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> (a, b, c) -> Builder ()

Print a => Print (Const a b)

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Const a b -> Builder ()

Print b => Print (Tagged a b)

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Tagged a b -> Builder ()

(Print a, Print b, Print c, Print d) => Print (a, b, c, d)

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> (a, b, c, d) -> Builder ()

(Print (f a), Print (g a)) => Print (Product f g a)

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Product f g a -> Builder ()

(Print (f a), Print (g a), Print a) => Print (Sum f g a)

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Sum f g a -> Builder ()

(Print a, Print b, Print c, Print d, Print e) => Print (a, b, c, d, e)

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> (a, b, c, d, e) -> Builder ()

Print (f (g a)) => Print (Compose f g a)

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> Compose f g a -> Builder ()

(Print a, Print b, Print c, Print d, Print e, Print f) => Print (a, b, c, d, e, f)

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> (a, b, c, d, e, f) -> Builder ()

(Print a, Print b, Print c, Print d, Print e, Print f, Print g) => Print (a, b, c, d, e, f, g)

Defined in Z.Data.Text.Print

Methods

toUTF8BuilderP :: Int -> (a, b, c, d, e, f, g) -> Builder ()

toText :: Print a => a -> Text

Convert data to Text.

toString :: Print a => a -> String

Convert data to String, faster show replacement.

toUTF8Builder :: Print a => a -> Builder ()

Convert data to Builder.

toUTF8Bytes :: Print a => a -> Bytes

Convert data to Bytes in UTF8 encoding.

Basic interface

null :: Text -> Bool

O(1) Test whether a text is empty.

length :: Text -> Int

O(n) The char length of a text.

append :: Text -> Text -> Text

O(m+n)

There's no need to guard empty vector because we guard them for you, so appending empty text are no-ops.

map' :: (Char -> Char) -> Text -> Text

O(n) map f t is the Text obtained by applying f to each char of t. Performs replacement on invalid scalar values.

imap' :: (Int -> Char -> Char) -> Text -> Text

Strict mapping with index.

foldl' :: (b -> Char -> b) -> b -> Text -> b

Strict left to right fold.

ifoldl' :: (b -> Int -> Char -> b) -> b -> Text -> b

Strict left to right fold with index.

foldr' :: (Char -> b -> b) -> b -> Text -> b

Strict right to left fold

ifoldr' :: (Int -> Char -> b -> b) -> b -> Text -> b

Strict right to left fold with index

NOTE: the index is counting from 0, not backwards

concat :: [Text] -> Text

O(n) Concatenate a list of text.

Note: concat have to force the entire list to filter out empty text and calculate the length for allocation.

concatMap :: (Char -> Text) -> Text -> Text

Map a function over a text and concatenate the results

Special folds

count :: Char -> Text -> Int

O(n) count returns count of an element from a text.

all :: (Char -> Bool) -> Text -> Bool

O(n) Applied to a predicate and text, all determines if all chars of the text satisfy the predicate.

any :: (Char -> Bool) -> Text -> Bool

O(n) Applied to a predicate and a text, any determines if any chars of the text satisfy the predicate.

Text display width

displayWidth :: Text -> Int

Get the display width of a piece of text.

You shouldn't pass texts with control characters(<0x20, \DEL), which are counted with -1 width.

>>> displayWidth "你好世界！"
>>> 10
>>> displayWidth "hello world!"
>>> 12

displayWidthChar :: Char -> Int

Get the display width of a Char.

You shouldn't pass texts with control characters(<0x20, \DEL), which are counted with -1 width.

Slice manipulation

cons :: Char -> Text -> Text

O(n) cons is analogous to (:) for lists, but of different complexity, as it requires making a copy.

snoc :: Text -> Char -> Text

O(n) Append a char to the end of a text.

uncons :: Text -> Maybe (Char, Text)

O(1) Extract the head and tail of a text, return Nothing if it is empty.

unsnoc :: Text -> Maybe (Text, Char)

O(1) Extract the init and last of a text, return Nothing if text is empty.

headMaybe :: Text -> Maybe Char

O(1) Extract the first char of a text.

tailMayEmpty :: Text -> Text

O(1) Extract the chars after the head of a text.

NOTE: tailMayEmpty return empty text in the case of an empty text.

lastMaybe :: Text -> Maybe Char

O(1) Extract the last char of a text.

initMayEmpty :: Text -> Text

O(1) Extract the chars before of the last one.

NOTE: initMayEmpty return empty text in the case of an empty text.

head :: Text -> Char

O(1) Extract the first char of a text.

Throw EmptyText if text is empty.

tail :: Text -> Text

O(1) Extract the chars after the head of a text.

Throw EmptyText if text is empty.

last :: Text -> Char

O(1) Extract the last char of a text.

Throw EmptyText if text is empty.

init :: Text -> Text

O(1) Extract the chars before of the last one.

Throw EmptyText if text is empty.

inits :: Text -> [Text]

O(n) Return all initial segments of the given text, empty first.

tails :: Text -> [Text]

O(n) Return all final segments of the given text, whole text first.

take :: Int -> Text -> Text

O(1) take n, applied to a text xs, returns the prefix of xs of length n, or xs itself if n > length xs.

drop :: Int -> Text -> Text

O(1) drop n xs returns the suffix of xs after the first n char, or [] if n > length xs.

takeR :: Int -> Text -> Text

O(1) takeR n, applied to a text xs, returns the suffix of xs of length n, or xs itself if n > length xs.

dropR :: Int -> Text -> Text

O(1) dropR n xs returns the prefix of xs before the last n char, or [] if n > length xs.

slice :: Int -> Int -> Text -> Text

O(1) Extract a sub-range text with give start index and length.

This function is a total function just like 'takedrop', indexlength exceeds range will be ingored, e.g.

slice 1 3 "hello"   == "ell"
slice -1 -1 "hello" == ""
slice -2 2 "hello"  == ""
slice 2 10 "hello"  == "llo"

This holds for all x y: slice x y vs == drop x . take (x+y) vs

splitAt :: Int -> Text -> (Text, Text)

O(n) splitAt n xs is equivalent to (take n xs, drop n xs).

takeWhile :: (Char -> Bool) -> Text -> Text

O(n) Applied to a predicate p and a text t, returns the longest prefix (possibly empty) of t of elements that satisfy p.

takeWhileR :: (Char -> Bool) -> Text -> Text

O(n) Applied to a predicate p and a text t, returns the longest suffix (possibly empty) of t of elements that satisfy p.

dropWhile :: (Char -> Bool) -> Text -> Text

O(n) Applied to a predicate p and a text vs, returns the suffix (possibly empty) remaining after takeWhile p vs.

dropWhileR :: (Char -> Bool) -> Text -> Text

O(n) Applied to a predicate p and a text vs, returns the prefix (possibly empty) remaining before takeWhileR p vs.

dropAround :: (Char -> Bool) -> Text -> Text

O(n) dropAround f = dropWhile f . dropWhileR f

break :: (Char -> Bool) -> Text -> (Text, Text)

O(n) Split the text into the longest prefix of elements that do not satisfy the predicate and the rest without copying.

span :: (Char -> Bool) -> Text -> (Text, Text)

O(n) Split the text into the longest prefix of elements that satisfy the predicate and the rest without copying.

breakR :: (Char -> Bool) -> Text -> (Text, Text)

breakR behaves like break but from the end of the text.

breakR p == spanR (not.p)

spanR :: (Char -> Bool) -> Text -> (Text, Text)

spanR behaves like span but from the end of the text.

breakOn :: Text -> Text -> (Text, Text)

Break a text on a subtext, returning a pair of the part of the text prior to the match, and the rest of the text, e.g.

break "wor" "hello, world" = ("hello, ", "world")

breakOnAll

Arguments

:: Text

needle to search for

-> Text

haystack in which to search

-> [(Text, Text)]

O(n+m) Find all non-overlapping instances of needle in haystack. Each element of the returned list consists of a pair:

• The entire string prior to the kth match (i.e. the prefix)
• The kth match, followed by the remainder of the string

Examples:

breakOnAll "::" ""
==> []
breakOnAll "" "abc"
==> [("a", "bc"), ("ab", "c"), ("abc", "/")]

The result list is lazy, search is performed when you force the list.

group :: Text -> [Text]

The group function takes a text and returns a list of texts such that the concatenation of the result is equal to the argument. Moreover, each sublist in the result contains only equal elements. For example,

group Mississippi = [M,"i","ss","i","ss","i","pp","i"]

It is a special case of groupBy, which allows the programmer to supply their own equality test.

groupBy :: (Char -> Char -> Bool) -> Text -> [Text]

The groupBy function is the non-overloaded version of group.

stripPrefix :: Text -> Text -> Maybe Text

O(n) The stripPrefix function takes two texts and returns Just the remainder of the second iff the first is its prefix, and otherwise Nothing.

stripSuffix :: Text -> Text -> Maybe Text

O(n) The stripSuffix function takes two texts and returns Just the remainder of the second iff the first is its suffix, and otherwise Nothing.

split :: Char -> Text -> [Text]

O(n) Break a text into pieces separated by the delimiter element consuming the delimiter. I.e.

split '\n' "a\nb\nd\ne" == ["a","b","d","e"]
split 'a'  "aXaXaXa"    == ["","X","X","X",""]
split 'x'  "x"          == ["",""]

and

intercalate [c] . split c == id
split == splitWith . (==)

NOTE, this function behavior different with bytestring's. see #56.

splitWith :: (Char -> Bool) -> Text -> [Text]

O(n) Splits a text into components delimited by separators, where the predicate returns True for a separator char. The resulting components do not contain the separators. Two adjacent separators result in an empty component in the output. eg.

splitWith (=='a') "aabbaca" == ["","","bb","c",""]
splitWith (=='a') []        == [""]

splitOn :: Text -> Text -> [Text]

O(m+n) Break haystack into pieces separated by needle.

Note: An empty needle will essentially split haystack element by element.

Examples:

>>> splitOn "\r\n" "a\r\nb\r\nd\r\ne"
["a","b","d","e"]

>>> splitOn "aaa"  "aaaXaaaXaaaXaaa"
["","X","X","X",""]

>>> splitOn "x"  "x"
["",""]

and

intercalate s . splitOn s         == id
splitOn (singleton c)             == split (==c)

isPrefixOf :: Text -> Text -> Bool

The isPrefix function returns True if the first argument is a prefix of the second.

isSuffixOf :: Text -> Text -> Bool

O(n) The isSuffixOf function takes two text and returns True if the first is a suffix of the second.

isInfixOf :: Text -> Text -> Bool

Check whether one text is a subtext of another.

needle isInfixOf haystack === null haystack || indices needle haystake /= [].

commonPrefix :: Text -> Text -> (Text, Text, Text)

O(n) Find the longest non-empty common prefix of two strings and return it, along with the suffixes of each string at which they no longer match. e.g.

>>> commonPrefix "foobar" "fooquux"
("foo","bar","quux")

>>> commonPrefix "veeble" "fetzer"
("","veeble","fetzer")

words :: Text -> [Text]

O(n) Breaks a Bytes up into a list of words, delimited by unicode space.

lines :: Text -> [Text]

O(n) Breaks a text up into a list of lines, delimited by ascii n.

unwords :: [Text] -> Text

O(n) Joins words with ascii space.

unlines :: [Text] -> Text

O(n) Joins lines with ascii n.

NOTE: This functions is different from unlines, it DOES NOT add a trailing n.

padLeft :: Int -> Char -> Text -> Text

Add padding to the left so that the whole text's length is at least n.

padRight :: Int -> Char -> Text -> Text

Add padding to the right so that the whole text's length is at least n.

Transform

reverse :: Text -> Text

O(n) Reverse the characters of a string.

intersperse :: Char -> Text -> Text

O(n) The intersperse function takes a character and places it between the characters of a Text. Performs replacement on invalid scalar values.

intercalate :: Text -> [Text] -> Text

O(n) The intercalate function takes a Text and a list of Texts and concatenates the list after interspersing the first argument between each element of the list.

intercalateElem :: Char -> [Text] -> Text

transpose :: [Text] -> [Text]

The transpose function transposes the rows and columns of its text argument.

Search

searching by equality

elem :: Char -> Text -> Bool

O(n) elem test if given char is in given text.

notElem :: Char -> Text -> Bool

O(n) not . elem

element-wise search

find

Arguments

:: (Char -> Bool)

-> Text

-> (Int, Maybe Char)

(char index, matching char)

O(n) find the first char matching the predicate in a text from left to right, if there isn't one, return the text length.

findR

Arguments

:: (Char -> Bool)

-> Text

-> (Int, Maybe Char)

(char index(counting backwards), matching char)

O(n) find the first char matching the predicate in a text from right to left.

filter :: (Char -> Bool) -> Text -> Text

O(n) filter, applied to a predicate and a text, returns a text containing those chars that satisfy the predicate.

partition :: (Char -> Bool) -> Text -> (Text, Text)

O(n) The partition function takes a predicate, a text, returns a pair of text with codepoints which do and do not satisfy the predicate, respectively; i.e.,

partition p txt == (filter p txt, filter (not . p) txt)

Unicode processing

normalization

data NormalizationResult

Constructors

NormalizedYes

NormalizedMaybe

NormalizedNo

Instances

Eq NormalizationResult

Defined in Z.Data.Text.UTF8Rewind

Methods

(==) :: NormalizationResult -> NormalizationResult -> Bool

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

Ord NormalizationResult

Defined in Z.Data.Text.UTF8Rewind

Methods

compare :: NormalizationResult -> NormalizationResult -> Ordering

(<) :: NormalizationResult -> NormalizationResult -> Bool

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

(>) :: NormalizationResult -> NormalizationResult -> Bool

(>=) :: NormalizationResult -> NormalizationResult -> Bool

max :: NormalizationResult -> NormalizationResult -> NormalizationResult

min :: NormalizationResult -> NormalizationResult -> NormalizationResult

Show NormalizationResult

Defined in Z.Data.Text.UTF8Rewind

Methods

showsPrec :: Int -> NormalizationResult -> ShowS

show :: NormalizationResult -> String

showList :: [NormalizationResult] -> ShowS

Generic NormalizationResult

Defined in Z.Data.Text.UTF8Rewind

Associated Types

type Rep NormalizationResult :: Type -> Type

Methods

from :: NormalizationResult -> Rep NormalizationResult x

to :: Rep NormalizationResult x -> NormalizationResult

type Rep NormalizationResult

Defined in Z.Data.Text.UTF8Rewind

type Rep NormalizationResult = D1 ('MetaData "NormalizationResult" "Z.Data.Text.UTF8Rewind" "Z-Data-0.9.0.0-9CZLncR3XfBEnMnIuwgUs7" 'False) (C1 ('MetaCons "NormalizedYes" 'PrefixI 'False) (U1 :: Type -> Type) :+: (C1 ('MetaCons "NormalizedMaybe" 'PrefixI 'False) (U1 :: Type -> Type) :+: C1 ('MetaCons "NormalizedNo" 'PrefixI 'False) (U1 :: Type -> Type)))

data NormalizeMode

These are the Unicode Normalization Forms:

Form                         | Description
---------------------------- | ---------------------------------------------
Normalization Form D (NFD)   | Canonical decomposition
Normalization Form C (NFC)   | Canonical decomposition, followed by canonical composition
Normalization Form KD (NFKD) | Compatibility decomposition
Normalization Form KC (NFKC) | Compatibility decomposition, followed by canonical composition

Constructors

NFC

NFKC

NFD

NFKD

Instances

Eq NormalizeMode

Defined in Z.Data.Text.UTF8Rewind

Methods

(==) :: NormalizeMode -> NormalizeMode -> Bool

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

Ord NormalizeMode

Defined in Z.Data.Text.UTF8Rewind

Methods

compare :: NormalizeMode -> NormalizeMode -> Ordering

(<) :: NormalizeMode -> NormalizeMode -> Bool

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

(>) :: NormalizeMode -> NormalizeMode -> Bool

(>=) :: NormalizeMode -> NormalizeMode -> Bool

max :: NormalizeMode -> NormalizeMode -> NormalizeMode

min :: NormalizeMode -> NormalizeMode -> NormalizeMode

Show NormalizeMode

Defined in Z.Data.Text.UTF8Rewind

Methods

showsPrec :: Int -> NormalizeMode -> ShowS

show :: NormalizeMode -> String

showList :: [NormalizeMode] -> ShowS

Generic NormalizeMode

Defined in Z.Data.Text.UTF8Rewind

Associated Types

type Rep NormalizeMode :: Type -> Type

Methods

from :: NormalizeMode -> Rep NormalizeMode x

to :: Rep NormalizeMode x -> NormalizeMode

type Rep NormalizeMode

Defined in Z.Data.Text.UTF8Rewind

type Rep NormalizeMode = D1 ('MetaData "NormalizeMode" "Z.Data.Text.UTF8Rewind" "Z-Data-0.9.0.0-9CZLncR3XfBEnMnIuwgUs7" 'False) ((C1 ('MetaCons "NFC" 'PrefixI 'False) (U1 :: Type -> Type) :+: C1 ('MetaCons "NFKC" 'PrefixI 'False) (U1 :: Type -> Type)) :+: (C1 ('MetaCons "NFD" 'PrefixI 'False) (U1 :: Type -> Type) :+: C1 ('MetaCons "NFKD" 'PrefixI 'False) (U1 :: Type -> Type)))

isNormalized :: Text -> NormalizationResult

Check if a string is stable in the NFC (Normalization Form C).

isNormalizedTo :: NormalizeMode -> Text -> NormalizationResult

Check if a string is stable in the specified Unicode Normalization Form.

This function can be used as a preprocessing step, before attempting to normalize a string. Normalization is a very expensive process, it is often cheaper to first determine if the string is unstable in the requested normalization form.

The result of the check will be YES if the string is stable and MAYBE or NO if it is unstable. If the result is MAYBE, the string does not necessarily have to be normalized.

For more information, please review <http://www.unicode.org/reports/tr15/ Unicode Standard Annex #15 - Unicode Normalization Forms>.

normalize :: Text -> Text

Normalize a string to NFC (Normalization Form C).

normalizeTo :: NormalizeMode -> Text -> Text

Normalize a string to the specified Unicode Normalization Form.

The Unicode standard defines two standards for equivalence between characters: canonical and compatibility equivalence. Canonically equivalent characters and sequence represent the same abstract character and must be rendered with the same appearance and behavior. Compatibility equivalent characters have a weaker equivalence and may be rendered differently.

Unicode Normalization Forms are formally defined standards that can be used to test whether any two strings of characters are equivalent to each other. This equivalence may be canonical or compatibility.

The algorithm puts all combining marks into a specified order and uses the rules for decomposition and composition to transform the string into one of four Unicode Normalization Forms. A binary comparison can then be used to determine equivalence.

Case conversion

envLocale :: IO Locale

Get environment locale

caseFold :: Text -> Text

Remove case distinction from UTF-8 encoded text with default locale.

caseFoldWith :: Locale -> Text -> Text

Remove case distinction from UTF-8 encoded text.

Case folding is the process of eliminating differences between code points concerning case mapping. It is most commonly used for comparing strings in a case-insensitive manner. Conversion is fully compliant with the Unicode 7.0 standard.

Although similar to lowercasing text, there are significant differences. For one, case folding does _not_ take locale into account when converting. In some cases, case folding can be up to 20% faster than lowercasing the same text, but the result cannot be treated as correct lowercased text.

Only two locale-specific exception are made when case folding text. In Turkish, U+0049 LATIN CAPITAL LETTER I maps to U+0131 LATIN SMALL LETTER DOTLESS I and U+0130 LATIN CAPITAL LETTER I WITH DOT ABOVE maps to U+0069 LATIN SMALL LETTER I.

Although most code points can be case folded without changing length, there are notable exceptions. For example, U+0130 (LATIN CAPITAL LETTER I WITH DOT ABOVE) maps to "U+0069 U+0307" (LATIN SMALL LETTER I and COMBINING DOT ABOVE) when converted to lowercase.

Only a handful of scripts make a distinction between upper- and lowercase. In addition to modern scripts, such as Latin, Greek, Armenian and Cyrillic, a few historic or archaic scripts have case. The vast majority of scripts do not have case distinctions.

toLower :: Text -> Text

Convert UTF-8 encoded text to lowercase with default locale.

toLowerWith :: Locale -> Text -> Text

Convert UTF-8 encoded text to lowercase.

This function allows conversion of UTF-8 encoded strings to lowercase without first changing the encoding to UTF-32. Conversion is fully compliant with the Unicode 7.0 standard.

Although most code points can be converted to lowercase with changing length, there are notable exceptions. For example, U+0130 (LATIN CAPITAL LETTER I WITH DOT ABOVE) maps to "U+0069 U+0307" (LATIN SMALL LETTER I and COMBINING DOT ABOVE) when converted to lowercase.

Only a handful of scripts make a distinction between upper- and lowercase. In addition to modern scripts, such as Latin, Greek, Armenian and Cyrillic, a few historic or archaic scripts have case. The vast majority of scripts do not have case distinctions.

Case mapping is not reversible. That is, toUpper(toLower(x)) != toLower(toUpper(x)).

Certain code points (or combinations of code points) apply rules based on the locale. For more information about these exceptional code points, please refer to the Unicode standard: ftp://ftp.unicode.org/Public/UNIDATA/SpecialCasing.txt

toUpper :: Text -> Text

Convert UTF-8 encoded text to uppercase with default locale.

toUpperWith :: Locale -> Text -> Text

Convert UTF-8 encoded text to uppercase.

Conversion is fully compliant with the Unicode 7.0 standard.

Although most code points can be converted without changing length, there are notable exceptions. For example, U+00DF (LATIN SMALL LETTER SHARP S) maps to "U+0053 U+0053" (LATIN CAPITAL LETTER S and LATIN CAPITAL LETTER S) when converted to uppercase.

Only a handful of scripts make a distinction between upper and lowercase. In addition to modern scripts, such as Latin, Greek, Armenian and Cyrillic, a few historic or archaic scripts have case. The vast majority of scripts do not have case distinctions.

Case mapping is not reversible. That is, toUpper(toLower(x)) != toLower(toUpper(x)).

Certain code points (or combinations of code points) apply rules based on the locale. For more information about these exceptional code points, please refer to the Unicode standard: ftp://ftp.unicode.org/Public/UNIDATA/SpecialCasing.txt

toTitle :: Text -> Text

Convert UTF-8 encoded text to titlecase with default locale.

toTitleWith :: Locale -> Text -> Text

Convert UTF-8 encoded text to titlecase.

This function allows conversion of UTF-8 encoded strings to titlecase. Conversion is fully compliant with the Unicode 7.0 standard.

Titlecase requires a bit more explanation than uppercase and lowercase, because it is not a common text transformation. Titlecase uses uppercase for the first letter of each word and lowercase for the rest. Words are defined as "collections of code points with general category Lu, Ll, Lt, Lm or Lo according to the Unicode database".

Effectively, any type of punctuation can break up a word, even if this is not grammatically valid. This happens because the titlecasing algorithm does not and cannot take grammar rules into account.

Text                                 | Titlecase
-------------------------------------|-------------------------------------
The running man                      | The Running Man
NATO Alliance                        | Nato Alliance
You're amazing at building libraries | You'Re Amazing At Building Libraries

Although most code points can be converted to titlecase without changing length, there are notable exceptions. For example, U+00DF (LATIN SMALL LETTER SHARP S) maps to "U+0053 U+0073" (LATIN CAPITAL LETTER S and LATIN SMALL LETTER S) when converted to titlecase.

Certain code points (or combinations of code points) apply rules based on the locale. For more information about these exceptional code points, please refer to the Unicode standard: ftp://ftp.unicode.org/Public/UNIDATA/SpecialCasing.txt

Unicode category

isCategory :: Category -> Text -> Bool

Check if the input string conforms to the category specified by the flags.

This function can be used to check if the code points in a string are part of a category. Valid flags are members of the "list of categories". The category for a code point is defined as part of the entry in UnicodeData.txt, the data file for the Unicode code point database.

By default, the function will treat grapheme clusters as a single code point. This means that the following string:

Code point | Canonical combining class | General category      | Name
---------- | ------------------------- | --------------------- | ----------------------
U+0045     | 0                         | Lu (Uppercase letter) | LATIN CAPITAL LETTER E
U+0300     | 230                       | Mn (Non-spacing mark) | COMBINING GRAVE ACCENT

Will match with CategoryLetterUppercase in its entirety, because the COMBINING GRAVE ACCENT is treated as part of the grapheme cluster. This is useful when e.g. creating a text parser, because you do not have to normalize the text first.

If this is undesired behavior, specify the CategoryIgnoreGraphemeCluster flag.

In order to maintain backwards compatibility with POSIX functions like isdigit and isspace, compatibility flags have been provided. Note, however, that the result is only guaranteed to be correct for code points in the Basic Latin range, between U+0000 and 0+007F. Combining a compatibility flag with a regular category flag will result in undefined behavior.

spanCategory :: Category -> Text -> (Text, Text)

Try to match as many code points with the matching category flags as possible and return the prefix and suffix.

Collate

collate :: Collator -> Text -> Text -> Ordering

Compare two Texts with Unicode Collation Algorithm

data Collator

Instances

IsString Collator

Defined in Text.Collate.Collator

Methods

fromString :: String -> Collator

Re-exports

collatorFor :: Lang -> Collator

Returns a collator based on a BCP 47 language tag. If no exact match is found, we try to find the best match (falling back to the root collation if nothing else succeeds). If something other than the default collation for a language is desired, the co keyword of the unicode extensions can be used (e.g. es-u-co-trad for traditional Spanish). Other unicode extensions affect the collator options:

• The kb keyword has the same effect as setFrenchAccents (e.g. fr-FR-u-kb-true).
• The ka keyword has the same effect as setVariableWeight (e.g. fr-FR-u-kb-ka-shifted or en-u-ka-noignore).
• The kf keyword has the same effect as setUpperBeforeLower (e.g. fr-u-kf-upper or fr-u-kf-lower).
• The kk keyword has the same effect as setNormalization (e.g. fr-u-kk-false).

collator :: QuasiQuoter

Create a collator at compile time based on a BCP 47 language tag: e.g., [collator|es-u-co-trad|]. Requires the QuasiQuotes extension.

setUpperBeforeLower :: Bool -> Collator -> Collator

Most collations default to sorting lowercase letters before uppercase (exceptions: mt, da, cu). To select the opposite behavior, use setUpperBeforeLower True.

setFrenchAccents :: Bool -> Collator -> Collator

setFrenchAccents True causes secondary weights to be scanned in reverse order, so we get the sorting cote côte coté côté instead of cote coté côte côté. The default is usually False, except for fr-CA where it is True.

setNormalization :: Bool -> Collator -> Collator

The Unicode Collation Algorithm expects input to be normalized into its canonical decomposition (NFD). By default, collators perform this normalization. If your input is already normalized, you can increase performance by disabling this step: setNormalization False.

setVariableWeighting :: VariableWeighting -> Collator -> Collator

Set method for handling variable elements (punctuation and spaces): see http://www.unicode.org/reports/tr10/, Tables 11 and 12.

collatorLang :: Collator -> Maybe Lang

Lang used for tailoring. Because of fallback rules, this may be somewhat different from the Lang passed to collatorFor. This Lang won't contain unicode extensions used to set options, but it will specify the collation if a non-default collation is being used.

rootCollator :: Collator

Default collator based on DUCET table (allkeys.txt).

renderSortKey :: SortKey -> String

Render sort key in the manner used in the CLDR collation test data: the character '|' is used to separate the levels of the key and corresponds to a 0 in the actual sort key.

data VariableWeighting

VariableWeighting affects how punctuation is treated. See http://www.unicode.org/reports/tr10/#Variable_Weighting.

Constructors

NonIgnorable

Don't ignore punctuation (Deluge < deluge-)

Blanked

Completely ignore punctuation (Deluge = deluge-)

Shifted

Consider punctuation at lower priority (de-luge < delu-ge < deluge < deluge- < Deluge)

ShiftTrimmed

Variant of Shifted (deluge < de-luge < delu-ge)

Instances

Eq VariableWeighting

Defined in Text.Collate.Collator

Methods

(==) :: VariableWeighting -> VariableWeighting -> Bool

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

Ord VariableWeighting

Defined in Text.Collate.Collator

Methods

compare :: VariableWeighting -> VariableWeighting -> Ordering

(<) :: VariableWeighting -> VariableWeighting -> Bool

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

(>) :: VariableWeighting -> VariableWeighting -> Bool

(>=) :: VariableWeighting -> VariableWeighting -> Bool

max :: VariableWeighting -> VariableWeighting -> VariableWeighting

min :: VariableWeighting -> VariableWeighting -> VariableWeighting

Show VariableWeighting

Defined in Text.Collate.Collator

Methods

showsPrec :: Int -> VariableWeighting -> ShowS

show :: VariableWeighting -> String

showList :: [VariableWeighting] -> ShowS

data CollatorOptions

Constructors

CollatorOptions

Fields

• optLang :: Maybe Lang

  Lang used for tailoring. Note that because of fallback rules, this may be somewhat different from the Lang passed to collatorFor. This Lang won't contain unicode extensions used to set options, but it will specify the collation if a non-default collation is being used.

• optVariableWeighting :: VariableWeighting

  Method for handling variable elements (see http://www.unicode.org/reports/tr10/, Tables 11 and 12).

• optFrenchAccents :: Bool

  If True, secondary weights are scanned in reverse order, so we get the sorting "cote côte coté côté" instead of "cote coté côte côté"

• optUpperBeforeLower :: Bool

  Sort uppercase letters before lower

• optNormalize :: Bool

  If True, strings are normalized to NFD before collation elements are constructed. If the input is already normalized, this option can be set to False for better performance.

Instances

Eq CollatorOptions

Defined in Text.Collate.Collator

Methods

(==) :: CollatorOptions -> CollatorOptions -> Bool

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

Ord CollatorOptions

Defined in Text.Collate.Collator

Methods

compare :: CollatorOptions -> CollatorOptions -> Ordering

(<) :: CollatorOptions -> CollatorOptions -> Bool

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

(>) :: CollatorOptions -> CollatorOptions -> Bool

(>=) :: CollatorOptions -> CollatorOptions -> Bool

max :: CollatorOptions -> CollatorOptions -> CollatorOptions

min :: CollatorOptions -> CollatorOptions -> CollatorOptions

Show CollatorOptions

Defined in Text.Collate.Collator

Methods

showsPrec :: Int -> CollatorOptions -> ShowS

show :: CollatorOptions -> String

showList :: [CollatorOptions] -> ShowS

newtype SortKey

Constructors

SortKey [Word16]

Instances

Eq SortKey

Defined in Text.Collate.Collator

Methods

(==) :: SortKey -> SortKey -> Bool

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

Ord SortKey

Defined in Text.Collate.Collator

Methods

compare :: SortKey -> SortKey -> Ordering

(<) :: SortKey -> SortKey -> Bool

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

(>) :: SortKey -> SortKey -> Bool

(>=) :: SortKey -> SortKey -> Bool

max :: SortKey -> SortKey -> SortKey

min :: SortKey -> SortKey -> SortKey

Show SortKey

Defined in Text.Collate.Collator

Methods

showsPrec :: Int -> SortKey -> ShowS

show :: SortKey -> String

showList :: [SortKey] -> ShowS

data Collator

Instances

IsString Collator

Defined in Text.Collate.Collator

Methods

fromString :: String -> Collator

tailorings :: [(Lang, Collation)]

An association list matching Langs with tailored Collations.

parseLang :: Text -> Either String Lang

Parse a BCP 47 language tag as a Lang.

renderLang :: Lang -> Text

Render a Lang in BCP 47 form.

lookupLang :: Lang -> [(Lang, a)] -> Maybe (Lang, a)

Find best match for a Lang in an association list.

data Lang

Represents a BCP 47 language tag (https://tools.ietf.org/html/bcp47).

Constructors

Lang

Fields

• langLanguage :: Text
• langScript :: Maybe Text
• langRegion :: Maybe Text
• langVariants :: [Text]
• langExtensions :: [(Text, [(Text, Text)])]
• langPrivateUse :: [Text]

Instances

Eq Lang

Defined in Text.Collate.Lang

Methods

(==) :: Lang -> Lang -> Bool

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

Ord Lang

Defined in Text.Collate.Lang

Methods

compare :: Lang -> Lang -> Ordering

(<) :: Lang -> Lang -> Bool

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

(>) :: Lang -> Lang -> Bool

(>=) :: Lang -> Lang -> Bool

max :: Lang -> Lang -> Lang

min :: Lang -> Lang -> Lang

Show Lang

Defined in Text.Collate.Lang

Methods

showsPrec :: Int -> Lang -> ShowS

show :: Lang -> String

showList :: [Lang] -> ShowS

IsString Lang

Defined in Text.Collate.Lang

Methods

fromString :: String -> Lang

Binary Lang

Defined in Text.Collate.Lang

Methods

put :: Lang -> Put

get :: Get Lang

putList :: [Lang] -> Put

Lift Lang

Defined in Text.Collate.Lang

Methods

lift :: Lang -> Q Exp

liftTyped :: Lang -> Q (TExp Lang)

Constants

Locale

type Locale = CSize

Locale for case mapping.

pattern LocaleDefault :: Locale

pattern LocaleLithuanian :: Locale

pattern LocaleTurkishAndAzeriLatin :: Locale

Category

type Category = CSize

Unicode categories.

See isCategory, you can combine categories with bitwise or.

pattern CategoryLetterUppercase :: Category

pattern CategoryLetterLowercase :: Category

pattern CategoryLetterTitlecase :: Category

pattern CategoryLetterOther :: Category

pattern CategoryLetter :: Category

pattern CategoryCaseMapped :: Category

pattern CategoryMarkNonSpacing :: Category

pattern CategoryMarkSpacing :: Category

pattern CategoryMarkEnclosing :: Category

pattern CategoryMark :: Category

pattern CategoryNumberDecimal :: Category

pattern CategoryNumberLetter :: Category

pattern CategoryNumberOther :: Category

pattern CategoryNumber :: Category

pattern CategoryPunctuationConnector :: Category

pattern CategoryPunctuationDash :: Category

pattern CategoryPunctuationOpen :: Category

pattern CategoryPunctuationClose :: Category

pattern CategoryPunctuationInitial :: Category

pattern CategoryPunctuationFinal :: Category

pattern CategoryPunctuationOther :: Category

pattern CategoryPunctuation :: Category

pattern CategorySymbolMath :: Category

pattern CategorySymbolCurrency :: Category

pattern CategorySymbolModifier :: Category

pattern CategorySymbolOther :: Category

pattern CategorySymbol :: Category

pattern CategorySeparatorSpace :: Category

pattern CategorySeparatorLine :: Category

pattern CategorySeparatorParagraph :: Category

pattern CategorySeparator :: Category

pattern CategoryControl :: Category

pattern CategoryFormat :: Category

pattern CategorySurrogate :: Category

pattern CategoryPrivateUse :: Category

pattern CategoryUnassigned :: Category

pattern CategoryCompatibility :: Category

pattern CategoryIgnoreGraphemeCluster :: Category

pattern CategoryIscntrl :: Category

pattern CategoryIsprint :: Category

pattern CategoryIsspace :: Category

pattern CategoryIsblank :: Category

pattern CategoryIsgraph :: Category

pattern CategoryIspunct :: Category

pattern CategoryIsalnum :: Category

pattern CategoryIsalpha :: Category

pattern CategoryIsupper :: Category

pattern CategoryIslower :: Category

pattern CategoryIsdigit :: Category

pattern CategoryIsxdigit :: Category