Data.Text.Lazy

A time and space-efficient implementation of Unicode text using lists of packed arrays.

Note: Read below the synopsis for important notes on the use of this module.

The representation used by this module is suitable for high performance use and for streaming large quantities of data. It provides a means to manipulate a large body of text without requiring that the entire content be resident in memory.

Some operations, such as concat, append, reverse and cons, have better time complexity than their Data.Text equivalents, due to the underlying representation being a list of chunks. For other operations, lazy Texts are usually within a few percent of strict ones, but often with better heap usage if used in a streaming fashion. For data larger than available memory, or if you have tight memory constraints, this module will be the only option.

This module is intended to be imported qualified, to avoid name clashes with Prelude functions. eg.

import qualified Data.Text.Lazy as L

Fusion

Starting from text-1.3 fusion is no longer implicit, and pipelines of transformations usually allocate intermediate Text values. Users, who observe significant changes to performances, are encouraged to use fusion framework explicitly, employing Data.Text.Internal.Fusion and Data.Text.Internal.Fusion.Common.

Acceptable data

A Text value is a sequence of Unicode scalar values, as defined in §3.9, definition D76 of the Unicode 5.2 standard. As such, a Text cannot contain values in the range U+D800 to U+DFFF inclusive. Haskell implementations admit all Unicode code points (§3.4, definition D10) as Char values, including code points from this invalid range. This means that there are some Char values (corresponding to Surrogate category) that are not valid Unicode scalar values, and the functions in this module must handle those cases.

Within this module, many functions construct a Text from one or more Char values. Those functions will substitute Char values that are not valid Unicode scalar values with the replacement character "�" (U+FFFD). Functions that perform this inspection and replacement are documented with the phrase "Performs replacement on invalid scalar values". The functions replace invalid scalar values, instead of dropping them, as a security measure. For details, see Unicode Technical Report 36, §3.5.)

Types

data Text

Instances

Data Text

This instance preserves data abstraction at the cost of inefficiency. We omit reflection services for the sake of data abstraction.

This instance was created by copying the updated behavior of Data.Text.Text

Defined in Data.Text.Lazy

Methods

gfoldl :: (forall d b. Data d => c (d -> b) -> d -> c b) -> (forall g. g -> c g) -> Text -> c Text

gunfold :: (forall b r. Data b => c (b -> r) -> c r) -> (forall r. r -> c r) -> Constr -> c Text

toConstr :: Text -> Constr

dataTypeOf :: Text -> DataType

dataCast1 :: Typeable t => (forall d. Data d => c (t d)) -> Maybe (c Text)

dataCast2 :: Typeable t => (forall d e. (Data d, Data e) => c (t d e)) -> Maybe (c Text)

gmapT :: (forall b. Data b => b -> b) -> Text -> Text

gmapQl :: (r -> r' -> r) -> r -> (forall d. Data d => d -> r') -> Text -> r

gmapQr :: forall r r'. (r' -> r -> r) -> r -> (forall d. Data d => d -> r') -> Text -> r

gmapQ :: (forall d. Data d => d -> u) -> Text -> [u]

gmapQi :: Int -> (forall d. Data d => d -> u) -> Text -> u

gmapM :: Monad m => (forall d. Data d => d -> m d) -> Text -> m Text

gmapMp :: MonadPlus m => (forall d. Data d => d -> m d) -> Text -> m Text

gmapMo :: MonadPlus m => (forall d. Data d => d -> m d) -> Text -> m Text

IsString Text

Performs replacement on invalid scalar values:

>>> :set -XOverloadedStrings
>>> "\55555" :: Data.Text.Lazy.Text
"\65533"

Defined in Data.Text.Lazy

Methods

fromString :: String -> Text

Monoid Text

Defined in Data.Text.Lazy

Methods

mempty :: Text

mappend :: Text -> Text -> Text

mconcat :: [Text] -> Text

Semigroup Text

Since: 1.2.2.0

Defined in Data.Text.Lazy

Methods

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

sconcat :: NonEmpty Text -> Text

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

IsList Text

Performs replacement on invalid scalar values:

>>> :set -XOverloadedLists
>>> ['\55555'] :: Data.Text.Lazy.Text
"\65533"

Since: 1.2.0.0

Defined in Data.Text.Lazy

Associated Types

type Item Text

Methods

fromList :: [Item Text] -> Text

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

toList :: Text -> [Item Text]

Read Text

Defined in Data.Text.Lazy

Methods

readsPrec :: Int -> ReadS Text

readList :: ReadS [Text]

readPrec :: ReadPrec Text

readListPrec :: ReadPrec [Text]

Show Text

Defined in Data.Text.Lazy

Methods

showsPrec :: Int -> Text -> ShowS

show :: Text -> String

showList :: [Text] -> ShowS

PrintfArg Text

Since: 1.2.2.0

Defined in Data.Text.Lazy

Methods

formatArg :: Text -> FieldFormatter

parseFormat :: Text -> ModifierParser

Binary Text

Since: 1.2.1.0

Defined in Data.Text.Lazy

Methods

put :: Text -> Put

get :: Get Text

putList :: [Text] -> Put

NFData Text

Defined in Data.Text.Lazy

Methods

rnf :: Text -> ()

Eq Text

Defined in Data.Text.Lazy

Methods

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

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

Ord Text

Defined in Data.Text.Lazy

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

Lift Text

Since: 1.2.4.0

Defined in Data.Text.Lazy

Methods

lift :: Quote m => Text -> m Exp

liftTyped :: forall (m :: Type -> Type). Quote m => Text -> Code m Text

type Item Text

Defined in Data.Text.Lazy

type Item Text = Char

type LazyText = Text

Type synonym for the lazy flavour of Text.

Creation and elimination

pack :: String -> Text

O(n) Convert a String into a Text.

Performs replacement on invalid scalar values, so unpack . pack is not id:

>>> Data.Text.Lazy.unpack (Data.Text.Lazy.pack "\55555")
"\65533"

unpack :: Text -> String

O(n) Convert a Text into a String.

singleton :: Char -> Text

O(1) Convert a character into a Text. Performs replacement on invalid scalar values.

empty :: Text

Smart constructor for Empty.

fromChunks :: [Text] -> Text

O(c) Convert a list of strict Texts into a lazy Text.

toChunks :: Text -> [Text]

O(n) Convert a lazy Text into a list of strict Texts.

toStrict :: LazyText -> StrictText

O(n) Convert a lazy Text into a strict Text.

fromStrict :: StrictText -> LazyText

O(c) Convert a strict Text into a lazy Text.

foldrChunks :: (Text -> a -> a) -> a -> Text -> a

Consume the chunks of a lazy Text with a natural right fold.

foldlChunks :: (a -> Text -> a) -> a -> Text -> a

Consume the chunks of a lazy Text with a strict, tail-recursive, accumulating left fold.

Pattern matching

pattern Empty :: Text

Empty text.

Since: 2.1.2

pattern (:<) :: Char -> Text -> Text infixr 5

Bidirectional pattern synonym for cons (O(n)) and uncons (O(1)), to be used together with Empty.

Since: 2.1.2

pattern (:>) :: Text -> Char -> Text infixl 5

Bidirectional pattern synonym for snoc (O(n)) and unsnoc (O(1)) to be used together with Empty.

Since: 2.1.2

Basic interface

cons :: Char -> Text -> Text infixr 5

O(1) Adds a character to the front of a Text.

snoc :: Text -> Char -> Text

O(n) Adds a character to the end of a Text. This copies the entire array in the process.

append :: Text -> Text -> Text

O(n/c) Appends one Text to another.

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

O(1) Returns the first character and rest of a Text, or Nothing if empty.

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

O(n/c) Returns the init and last of a Text, or Nothing if empty.

• It is no faster than using init and last.

Since: 1.2.3.0

head :: HasCallStack => Text -> Char

O(1) Returns the first character of a Text, which must be non-empty. This is a partial function, consider using uncons instead.

last :: HasCallStack => Text -> Char

O(n/c) Returns the last character of a Text, which must be non-empty. This is a partial function, consider using unsnoc instead.

tail :: HasCallStack => Text -> Text

O(1) Returns all characters after the head of a Text, which must be non-empty. This is a partial function, consider using uncons instead.

init :: HasCallStack => Text -> Text

O(n/c) Returns all but the last character of a Text, which must be non-empty. This is a partial function, consider using unsnoc instead.

null :: Text -> Bool

O(1) Tests whether a Text is empty or not.

length :: Text -> Int64

O(n) Returns the number of characters in a Text.

compareLength :: Text -> Int64 -> Ordering

O(min(n,c)) Compare the count of characters in a Text to a number.

compareLength t c = compare (length t) c

This function gives the same answer as comparing against the result of length, but can short circuit if the count of characters is greater than the number, and hence be more efficient.

Transformations

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

O(n) map f t is the Text obtained by applying f to each element of t. 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.

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.

transpose :: [Text] -> [Text]

O(n) The transpose function transposes the rows and columns of its Text argument. Note that this function uses pack, unpack, and the list version of transpose, and is thus not very efficient.

reverse :: Text -> Text

O(n) reverse t returns the elements of t in reverse order.

replace

Arguments

:: HasCallStack

=> Text

needle to search for. If this string is empty, an error will occur.

-> Text

replacement to replace needle with.

-> Text

haystack in which to search.

-> Text

O(m+n) Replace every non-overlapping occurrence of needle in haystack with replacement.

This function behaves as though it was defined as follows:

replace needle replacement haystack =
  intercalate replacement (splitOn needle haystack)

As this suggests, each occurrence is replaced exactly once. So if needle occurs in replacement, that occurrence will not itself be replaced recursively:

replace "oo" "foo" "oo" == "foo"

In cases where several instances of needle overlap, only the first one will be replaced:

replace "ofo" "bar" "ofofo" == "barfo"

In (unlikely) bad cases, this function's time complexity degrades towards O(n*m).

Case conversion

With Unicode text, it is incorrect to use combinators like map toUpper to case convert each character of a string individually. Instead, use the whole-string case conversion functions from this module. For correctness in different writing systems, these functions may map one input character to two or three output characters.

toCaseFold :: Text -> Text

O(n) Convert a string to folded case.

This function is mainly useful for performing caseless (or case insensitive) string comparisons.

A string x is a caseless match for a string y if and only if:

toCaseFold x == toCaseFold y

The result string may be longer than the input string, and may differ from applying toLower to the input string. For instance, the Armenian small ligature men now (U+FB13) is case folded to the bigram men now (U+0574 U+0576), while the micro sign (U+00B5) is case folded to the Greek small letter letter mu (U+03BC) instead of itself.

toLower :: Text -> Text

O(n) Convert a string to lower case, using simple case conversion.

The result string may be longer than the input string. For instance, the Latin capital letter I with dot above (U+0130) maps to the sequence Latin small letter i (U+0069) followed by combining dot above (U+0307).

toUpper :: Text -> Text

O(n) Convert a string to upper case, using simple case conversion.

The result string may be longer than the input string. For instance, the German eszett (U+00DF) maps to the two-letter sequence SS.

toTitle :: Text -> Text

O(n) Convert a string to title case, using simple case conversion.

The first letter (as determined by isLetter) of the input is converted to title case, as is every subsequent letter that immediately follows a non-letter. Every letter that immediately follows another letter is converted to lower case.

The result string may be longer than the input string. For example, the Latin small ligature fl (U+FB02) is converted to the sequence Latin capital letter F (U+0046) followed by Latin small letter l (U+006C).

This function is not idempotent. Consider lower-case letter ʼn (U+0149 LATIN SMALL LETTER N PRECEDED BY APOSTROPHE). Then toTitle "ʼn" = "ʼN": the first (and the only) letter of the input is converted to title case, becoming two letters. Now ʼ (U+02BC MODIFIER LETTER APOSTROPHE) is a modifier letter and as such is recognised as a letter by isLetter, so toTitle "ʼN" = "'n".

Note: this function does not take language or culture specific rules into account. For instance, in English, different style guides disagree on whether the book name "The Hill of the Red Fox" is correctly title cased—but this function will capitalize every word.

Since: 1.0.0.0

Justification

justifyLeft :: Int64 -> Char -> Text -> Text

O(n) Left-justify a string to the given length, using the specified fill character on the right. Performs replacement on invalid scalar values.

Examples:

justifyLeft 7 'x' "foo"    == "fooxxxx"
justifyLeft 3 'x' "foobar" == "foobar"

justifyRight :: Int64 -> Char -> Text -> Text

O(n) Right-justify a string to the given length, using the specified fill character on the left. Performs replacement on invalid scalar values.

Examples:

justifyRight 7 'x' "bar"    == "xxxxbar"
justifyRight 3 'x' "foobar" == "foobar"

center :: Int64 -> Char -> Text -> Text

O(n) Center a string to the given length, using the specified fill character on either side. Performs replacement on invalid scalar values.

Examples:

center 8 'x' "HS" = "xxxHSxxx"

Folds

foldl :: (a -> Char -> a) -> a -> Text -> a

O(n) foldl, applied to a binary operator, a starting value (typically the left-identity of the operator), and a Text, reduces the Text using the binary operator, from left to right.

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

O(n) A strict version of foldl.

foldl1 :: HasCallStack => (Char -> Char -> Char) -> Text -> Char

O(n) A variant of foldl that has no starting value argument, and thus must be applied to a non-empty Text.

foldl1' :: HasCallStack => (Char -> Char -> Char) -> Text -> Char

O(n) A strict version of foldl1.

foldr :: (Char -> a -> a) -> a -> Text -> a

O(n) foldr, applied to a binary operator, a starting value (typically the right-identity of the operator), and a Text, reduces the Text using the binary operator, from right to left.

foldr is lazy like foldr for lists: evaluation actually traverses the Text from left to right, only as far as it needs to.

For example, head can be defined with O(1) complexity using foldr:

head :: Text -> Char
head = foldr const (error "head empty")

foldr1 :: HasCallStack => (Char -> Char -> Char) -> Text -> Char

O(n) A variant of foldr that has no starting value argument, and thus must be applied to a non-empty Text.

foldlM' :: Monad m => (a -> Char -> m a) -> a -> Text -> m a

O(n) A monadic version of foldl'.

Since: 2.1.2

Special folds

concat :: [Text] -> Text

O(n) Concatenate a list of Texts.

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

O(n) Map a function over a Text that results in a Text, and concatenate the results.

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

O(n) any p t determines whether any character in the Text t satisfies the predicate p.

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

O(n) all p t determines whether all characters in the Text t satisfy the predicate p.

maximum :: HasCallStack => Text -> Char

O(n) maximum returns the maximum value from a Text, which must be non-empty.

minimum :: HasCallStack => Text -> Char

O(n) minimum returns the minimum value from a Text, which must be non-empty.

isAscii :: Text -> Bool

O(n) Test whether Text contains only ASCII code-points (i.e. only U+0000 through U+007F).

This is a more efficient version of all isAscii.

>>> isAscii ""
True

>>> isAscii "abc\NUL"
True

>>> isAscii "abcd€"
False

isAscii t == all (< '\x80') t

Since: 2.0.2

Construction

Scans

scanl :: (Char -> Char -> Char) -> Char -> Text -> Text

O(n) scanl is similar to foldl, but returns a list of successive reduced values from the left. Performs replacement on invalid scalar values.

scanl f z [x1, x2, ...] == [z, z `f` x1, (z `f` x1) `f` x2, ...]

Note that

last (scanl f z xs) == foldl f z xs.

scanl1 :: (Char -> Char -> Char) -> Text -> Text

O(n) scanl1 is a variant of scanl that has no starting value argument. Performs replacement on invalid scalar values.

scanl1 f [x1, x2, ...] == [x1, x1 `f` x2, ...]

scanr :: (Char -> Char -> Char) -> Char -> Text -> Text

O(n) scanr is the right-to-left dual of scanl. Performs replacement on invalid scalar values.

scanr f v == reverse . scanl (flip f) v . reverse

scanr1 :: (Char -> Char -> Char) -> Text -> Text

O(n) scanr1 is a variant of scanr that has no starting value argument. Performs replacement on invalid scalar values.

Accumulating maps

mapAccumL :: (a -> Char -> (a, Char)) -> a -> Text -> (a, Text)

O(n) Like a combination of map and foldl'. Applies a function to each element of a Text, passing an accumulating parameter from left to right, and returns a final Text. Performs replacement on invalid scalar values.

mapAccumR :: (a -> Char -> (a, Char)) -> a -> Text -> (a, Text)

The mapAccumR function behaves like a combination of map and a strict foldr; it applies a function to each element of a Text, passing an accumulating parameter from right to left, and returning a final value of this accumulator together with the new Text. Performs replacement on invalid scalar values.

Generation and unfolding

repeat :: Char -> Text

repeat x is an infinite Text, with x the value of every element.

Since: 1.2.0.5

replicate :: Int64 -> Text -> Text

O(n*m) replicate n t is a Text consisting of the input t repeated n times.

cycle :: HasCallStack => Text -> Text

cycle ties a finite, non-empty Text into a circular one, or equivalently, the infinite repetition of the original Text.

Since: 1.2.0.5

iterate :: (Char -> Char) -> Char -> Text

iterate f x returns an infinite Text of repeated applications of f to x:

iterate f x == [x, f x, f (f x), ...]

Since: 1.2.0.5

unfoldr :: (a -> Maybe (Char, a)) -> a -> Text

O(n), where n is the length of the result. The unfoldr function is analogous to the List unfoldr. unfoldr builds a Text from a seed value. The function takes the element and returns Nothing if it is done producing the Text, otherwise Just (a,b). In this case, a is the next Char in the string, and b is the seed value for further production. Performs replacement on invalid scalar values.

unfoldrN :: Int64 -> (a -> Maybe (Char, a)) -> a -> Text

O(n) Like unfoldr, unfoldrN builds a Text from a seed value. However, the length of the result should be limited by the first argument to unfoldrN. This function is more efficient than unfoldr when the maximum length of the result is known and correct, otherwise its performance is similar to unfoldr. Performs replacement on invalid scalar values.

Substrings

Breaking strings

take :: Int64 -> Text -> Text

O(n) take n, applied to a Text, returns the prefix of the Text of length n, or the Text itself if n is greater than the length of the Text.

takeEnd :: Int64 -> Text -> Text

O(n) takeEnd n t returns the suffix remaining after taking n characters from the end of t.

Examples:

takeEnd 3 "foobar" == "bar"

Since: 1.1.1.0

drop :: Int64 -> Text -> Text

O(n) drop n, applied to a Text, returns the suffix of the Text after the first n characters, or the empty Text if n is greater than the length of the Text.

dropEnd :: Int64 -> Text -> Text

O(n) dropEnd n t returns the prefix remaining after dropping n characters from the end of t.

Examples:

dropEnd 3 "foobar" == "foo"

Since: 1.1.1.0

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

O(n) takeWhile, applied to a predicate p and a Text, returns the longest prefix (possibly empty) of elements that satisfy p.

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

O(n) takeWhileEnd, applied to a predicate p and a Text, returns the longest suffix (possibly empty) of elements that satisfy p. Examples:

takeWhileEnd (=='o') "foo" == "oo"

Since: 1.2.2.0

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

O(n) dropWhile p t returns the suffix remaining after takeWhile p t.

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

O(n) dropWhileEnd p t returns the prefix remaining after dropping characters that satisfy the predicate p from the end of t.

Examples:

dropWhileEnd (=='.') "foo..." == "foo"

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

O(n) dropAround p t returns the substring remaining after dropping characters that satisfy the predicate p from both the beginning and end of t.

strip :: Text -> Text

O(n) Remove leading and trailing white space from a string. Equivalent to:

dropAround isSpace

stripStart :: Text -> Text

O(n) Remove leading white space from a string. Equivalent to:

dropWhile isSpace

stripEnd :: Text -> Text

O(n) Remove trailing white space from a string. Equivalent to:

dropWhileEnd isSpace

splitAt :: Int64 -> Text -> (Text, Text)

O(n) splitAt n t returns a pair whose first element is a prefix of t of length n, and whose second is the remainder of the string. It is equivalent to (take n t, drop n t).

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

O(n) span, applied to a predicate p and text t, returns a pair whose first element is the longest prefix (possibly empty) of t of elements that satisfy p, and whose second is the remainder of the text.

>>> T.span (=='0') "000AB"
("000","AB")

spanM :: Monad m => (Char -> m Bool) -> Text -> m (Text, Text)

O(length of prefix) spanM, applied to a monadic predicate p, a text t, returns a pair (t1, t2) where t1 is the longest prefix of t whose elements satisfy p, and t2 is the remainder of the text.

>>> T.spanM (\c -> state $ \i -> (fromEnum c == i, i+1)) "abcefg" `runState` 97
(("abc","efg"),101)

span is spanM specialized to Identity:

-- for all p :: Char -> Bool
span p = runIdentity . spanM (pure . p)

Since: 2.0.1

spanEndM :: Monad m => (Char -> m Bool) -> Text -> m (Text, Text)

O(length of suffix) spanEndM, applied to a monadic predicate p, a text t, returns a pair (t1, t2) where t2 is the longest suffix of t whose elements satisfy p, and t1 is the remainder of the text.

>>> T.spanEndM (\c -> state $ \i -> (fromEnum c == i, i-1)) "tuvxyz" `runState` 122
(("tuv","xyz"),118)

spanEndM p . reverse = fmap (bimap reverse reverse) . spanM p

Since: 2.0.1

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

O(n+m) Find the first instance of needle (which must be non-null) in haystack. The first element of the returned tuple is the prefix of haystack before needle is matched. The second is the remainder of haystack, starting with the match.

Examples:

breakOn "::" "a::b::c" ==> ("a", "::b::c")
breakOn "/" "foobar"   ==> ("foobar", "")

Laws:

append prefix match == haystack
  where (prefix, match) = breakOn needle haystack

If you need to break a string by a substring repeatedly (e.g. you want to break on every instance of a substring), use breakOnAll instead, as it has lower startup overhead.

This function is strict in its first argument, and lazy in its second.

In (unlikely) bad cases, this function's time complexity degrades towards O(n*m).

breakOnEnd :: HasCallStack => Text -> Text -> (Text, Text)

O(n+m) Similar to breakOn, but searches from the end of the string.

The first element of the returned tuple is the prefix of haystack up to and including the last match of needle. The second is the remainder of haystack, following the match.

breakOnEnd "::" "a::b::c" ==> ("a::b::", "c")

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

O(n) break is like span, but the prefix returned is over elements that fail the predicate p.

>>> T.break (=='c') "180cm"
("180","cm")

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.

inits :: Text -> [Text]

O(n²) Return all initial segments of the given Text, shortest first.

initsNE :: Text -> NonEmpty Text

O(n²) Return all initial segments of the given Text, shortest first.

Since: 2.1.2

tails :: Text -> [Text]

O(n) Return all final segments of the given Text, longest first.

tailsNE :: Text -> NonEmpty Text

O(n) Return all final segments of the given Text, longest first.

Since: 2.1.2

Breaking into many substrings

Splitting functions in this library do not perform character-wise copies to create substrings; they just construct new Texts that are slices of the original.

splitOn

Arguments

:: HasCallStack

=> Text

String to split on. If this string is empty, an error will occur.

-> Text

Input text.

-> [Text]

O(m+n) Break a Text into pieces separated by the first Text argument (which cannot be an empty string), consuming the delimiter. An empty delimiter is invalid, and will cause an error to be raised.

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)

(Note: the string s to split on above cannot be empty.)

This function is strict in its first argument, and lazy in its second.

In (unlikely) bad cases, this function's time complexity degrades towards O(n*m).

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

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

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

chunksOf :: Int64 -> Text -> [Text]

O(n) Splits a Text into components of length k. The last element may be shorter than the other chunks, depending on the length of the input. Examples:

chunksOf 3 "foobarbaz"   == ["foo","bar","baz"]
chunksOf 4 "haskell.org" == ["hask","ell.","org"]

Breaking into lines and words

lines :: Text -> [Text]

O(n) Breaks a Text up into a list of Texts at newline characters '\n' (LF, line feed). The resulting strings do not contain newlines.

lines does not treat '\r' (CR, carriage return) as a newline character.

words :: Text -> [Text]

O(n) Breaks a Text up into a list of words, delimited by Chars representing white space.

unlines :: [Text] -> Text

O(n) Joins lines, after appending a terminating newline to each.

unwords :: [Text] -> Text

O(n) Joins words using single space characters.

Predicates

isPrefixOf :: Text -> Text -> Bool

O(n) The isPrefixOf function takes two Texts and returns True if and only if the first is a prefix of the second.

isSuffixOf :: Text -> Text -> Bool

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

isInfixOf :: Text -> Text -> Bool

O(n+m) The isInfixOf function takes two Texts and returns True if and only if the first is contained, wholly and intact, anywhere within the second.

This function is strict in its first argument, and lazy in its second.

In (unlikely) bad cases, this function's time complexity degrades towards O(n*m).

View patterns

stripPrefix :: Text -> Text -> Maybe Text

O(n) Return the suffix of the second string if its prefix matches the entire first string.

Examples:

stripPrefix "foo" "foobar" == Just "bar"
stripPrefix ""    "baz"    == Just "baz"
stripPrefix "foo" "quux"   == Nothing

This is particularly useful with the ViewPatterns extension to GHC, as follows:

{-# LANGUAGE ViewPatterns #-}
import Data.Text.Lazy as T

fnordLength :: Text -> Int
fnordLength (stripPrefix "fnord" -> Just suf) = T.length suf
fnordLength _                                 = -1

stripSuffix :: Text -> Text -> Maybe Text

O(n) Return the prefix of the second string if its suffix matches the entire first string.

Examples:

stripSuffix "bar" "foobar" == Just "foo"
stripSuffix ""    "baz"    == Just "baz"
stripSuffix "foo" "quux"   == Nothing

This is particularly useful with the ViewPatterns extension to GHC, as follows:

{-# LANGUAGE ViewPatterns #-}
import Data.Text.Lazy as T

quuxLength :: Text -> Int
quuxLength (stripSuffix "quux" -> Just pre) = T.length pre
quuxLength _                                = -1

commonPrefixes :: Text -> Text -> Maybe (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.

If the strings do not have a common prefix or either one is empty, this function returns Nothing.

Examples:

commonPrefixes "foobar" "fooquux" == Just ("foo","bar","quux")
commonPrefixes "veeble" "fetzer"  == Nothing
commonPrefixes "" "baz"           == Nothing

Searching

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

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

find :: (Char -> Bool) -> Text -> Maybe Char

O(n) The find function takes a predicate and a Text, and returns the first element in matching the predicate, or Nothing if there is no such element.

elem :: Char -> Text -> Bool

O(n) The elem function takes a character and a Text, and returns True if the element is found in the given Text, or False otherwise.

breakOnAll

Arguments

:: HasCallStack

=> 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 "/" "a/b/c/"
==> [("a", "/b/c/"), ("a/b", "/c/"), ("a/b/c", "/")]

This function is strict in its first argument, and lazy in its second.

In (unlikely) bad cases, this function's time complexity degrades towards O(n*m).

The needle parameter may not be empty.

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

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

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

Indexing

index :: HasCallStack => Text -> Int64 -> Char

O(n) Text index (subscript) operator, starting from 0.

count :: HasCallStack => Text -> Text -> Int64

O(n+m) The count function returns the number of times the query string appears in the given Text. An empty query string is invalid, and will cause an error to be raised.

In (unlikely) bad cases, this function's time complexity degrades towards O(n*m).

Zipping and unzipping

zip :: Text -> Text -> [(Char, Char)]

O(n) zip takes two Texts and returns a list of corresponding pairs of bytes. If one input Text is short, excess elements of the longer Text are discarded. This is equivalent to a pair of unpack operations.

zipWith :: (Char -> Char -> Char) -> Text -> Text -> Text

O(n) zipWith generalises zip by zipping with the function given as the first argument, instead of a tupling function. Performs replacement on invalid scalar values.

Showing values

show :: Show a => a -> Text

Convert a value to lazy Text.

Since: 2.1.2

Orphan instances

Data Text

This instance preserves data abstraction at the cost of inefficiency. We omit reflection services for the sake of data abstraction.

This instance was created by copying the updated behavior of Data.Text.Text

Methods

gfoldl :: (forall d b. Data d => c (d -> b) -> d -> c b) -> (forall g. g -> c g) -> Text -> c Text

gunfold :: (forall b r. Data b => c (b -> r) -> c r) -> (forall r. r -> c r) -> Constr -> c Text

toConstr :: Text -> Constr

dataTypeOf :: Text -> DataType

dataCast1 :: Typeable t => (forall d. Data d => c (t d)) -> Maybe (c Text)

dataCast2 :: Typeable t => (forall d e. (Data d, Data e) => c (t d e)) -> Maybe (c Text)

gmapT :: (forall b. Data b => b -> b) -> Text -> Text

gmapQl :: (r -> r' -> r) -> r -> (forall d. Data d => d -> r') -> Text -> r

gmapQr :: forall r r'. (r' -> r -> r) -> r -> (forall d. Data d => d -> r') -> Text -> r

gmapQ :: (forall d. Data d => d -> u) -> Text -> [u]

gmapQi :: Int -> (forall d. Data d => d -> u) -> Text -> u

gmapM :: Monad m => (forall d. Data d => d -> m d) -> Text -> m Text

gmapMp :: MonadPlus m => (forall d. Data d => d -> m d) -> Text -> m Text

gmapMo :: MonadPlus m => (forall d. Data d => d -> m d) -> Text -> m Text

IsString Text

Performs replacement on invalid scalar values:

>>> :set -XOverloadedStrings
>>> "\55555" :: Data.Text.Lazy.Text
"\65533"

Methods

fromString :: String -> Text

Monoid Text

Methods

mempty :: Text

mappend :: Text -> Text -> Text

mconcat :: [Text] -> Text

Semigroup Text

Since: 1.2.2.0

Methods

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

sconcat :: NonEmpty Text -> Text

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

IsList Text

Performs replacement on invalid scalar values:

>>> :set -XOverloadedLists
>>> ['\55555'] :: Data.Text.Lazy.Text
"\65533"

Since: 1.2.0.0

Associated Types

type Item Text

Methods

fromList :: [Item Text] -> Text

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

toList :: Text -> [Item Text]

Read Text

Methods

readsPrec :: Int -> ReadS Text

readList :: ReadS [Text]

readPrec :: ReadPrec Text

readListPrec :: ReadPrec [Text]

Show Text

Methods

showsPrec :: Int -> Text -> ShowS

show :: Text -> String

showList :: [Text] -> ShowS

PrintfArg Text

Since: 1.2.2.0

Methods

formatArg :: Text -> FieldFormatter

parseFormat :: Text -> ModifierParser

Binary Text

Since: 1.2.1.0

Methods

put :: Text -> Put

get :: Get Text

putList :: [Text] -> Put

NFData Text

Methods

rnf :: Text -> ()

Eq Text

Methods

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

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

Ord Text

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

Lift Text

Since: 1.2.4.0

Methods

lift :: Quote m => Text -> m Exp

liftTyped :: forall (m :: Type -> Type). Quote m => Text -> Code m Text