Text

Text

data Text

A space efficient, packed, unboxed Unicode text type.

Instances

Hashable Text

Defined in Data.Hashable.Class

Methods

hashWithSalt :: Int -> Text -> Int

hash :: Text -> Int

ToJSON Text

Defined in Data.Aeson.Types.ToJSON

Methods

toJSON :: Text -> Value

toEncoding :: Text -> Encoding

toJSONList :: [Text] -> Value

toEncodingList :: [Text] -> Encoding

KeyValue Pair

Defined in Data.Aeson.Types.ToJSON

Methods

(.=) :: ToJSON v => Text -> v -> Pair

ToJSONKey Text

Defined in Data.Aeson.Types.ToJSON

Methods

toJSONKey :: ToJSONKeyFunction Text

toJSONKeyList :: ToJSONKeyFunction [Text]

FromJSON Text

Defined in Data.Aeson.Types.FromJSON

Methods

parseJSON :: Value -> Parser Text

parseJSONList :: Value -> Parser [Text]

FromJSONKey Text

Defined in Data.Aeson.Types.FromJSON

Methods

fromJSONKey :: FromJSONKeyFunction Text

fromJSONKeyList :: FromJSONKeyFunction [Text]

FoldCase Text

Defined in Data.CaseInsensitive.Internal

Methods

foldCase :: Text -> Text

foldCaseList :: [Text] -> [Text]

Ixed Text

Defined in Control.Lens.At

Methods

ix :: Index Text -> Traversal' Text (IxValue Text)

AsEmpty Text

Defined in Control.Lens.Empty

Methods

_Empty :: Prism' Text ()

Reversing Text

Defined in Control.Lens.Internal.Iso

Methods

reversing :: Text -> Text

AsNumber Text

Defined in Data.Aeson.Lens

Methods

_Number :: Prism' Text Scientific

_Double :: Prism' Text Double

_Integer :: Prism' Text Integer

AsPrimitive Text

Defined in Data.Aeson.Lens

Methods

_Primitive :: Prism' Text Primitive

_String :: Prism' Text Text

_Bool :: Prism' Text Bool

_Null :: Prism' Text ()

AsValue Text

Defined in Data.Aeson.Lens

Methods

_Value :: Prism' Text Value

_Object :: Prism' Text (HashMap Text Value)

_Array :: Prism' Text (Vector Value)

AsJSON Text

Defined in Data.Aeson.Lens

Methods

_JSON :: (FromJSON a, ToJSON a) => Prism' Text a

Stream Text

Defined in Text.Megaparsec.Stream

Associated Types

type Token Text :: *

type Tokens Text :: *

Methods

tokenToChunk :: Proxy Text -> Token Text -> Tokens Text

tokensToChunk :: Proxy Text -> [Token Text] -> Tokens Text

chunkToTokens :: Proxy Text -> Tokens Text -> [Token Text]

chunkLength :: Proxy Text -> Tokens Text -> Int

chunkEmpty :: Proxy Text -> Tokens Text -> Bool

positionAt1 :: Proxy Text -> SourcePos -> Token Text -> SourcePos

positionAtN :: Proxy Text -> SourcePos -> Tokens Text -> SourcePos

advance1 :: Proxy Text -> Pos -> SourcePos -> Token Text -> SourcePos

advanceN :: Proxy Text -> Pos -> SourcePos -> Tokens Text -> SourcePos

take1_ :: Text -> Maybe (Token Text, Text)

takeN_ :: Int -> Text -> Maybe (Tokens Text, Text)

takeWhile_ :: (Token Text -> Bool) -> Text -> (Tokens Text, Text)

Pretty Text

Automatically converts all newlines to line.

>>> pretty ("hello\nworld" :: Text)
hello
world

Note that line can be undone by group:

>>> group (pretty ("hello\nworld" :: Text))
hello world

Manually use hardline if you definitely want newlines.

Defined in Data.Text.Prettyprint.Doc.Internal

Methods

pretty :: Text -> Doc ann

prettyList :: [Text] -> Doc ann

Serialise Text

Since: serialise-0.2.0.0

Defined in Codec.Serialise.Class

Methods

encode :: Text -> Encoding

decode :: Decoder s Text

encodeList :: [Text] -> Encoding

decodeList :: Decoder s [Text]

Strict Text Text

Defined in Control.Lens.Iso

Methods

strict :: Iso' Text Text0

(a ~ Char, b ~ Char) => Each Text Text a b

each :: Traversal Text Text Char Char

Defined in Control.Lens.Each

Methods

each :: Traversal Text Text a b

Cons Text Text Char Char

Defined in Control.Lens.Cons

Methods

_Cons :: Prism Text Text (Char, Text) (Char, Text)

Snoc Text Text Char Char

Defined in Control.Lens.Cons

Methods

_Snoc :: Prism Text Text (Text, Char) (Text, Char)

FromPairs Value (DList Pair)

Defined in Data.Aeson.Types.ToJSON

Methods

fromPairs :: DList Pair -> Value

v ~ Value => KeyValuePair v (DList Pair)

Defined in Data.Aeson.Types.ToJSON

Methods

pair :: String -> v -> DList Pair

type Item Text

Defined in Data.Text

type Item Text = Char

type Index Text

Defined in Control.Lens.At

type Index Text = Int

type IxValue Text

Defined in Control.Lens.At

type IxValue Text = Char

type Tokens Text

Defined in Text.Megaparsec.Stream

type Tokens Text = Text

type Token Text

Defined in Text.Megaparsec.Stream

type Token Text = Char

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

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

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

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

append :: Text -> Text -> Text

O(n) Appends one Text to the other by copying both of them into a new Text. Subject to fusion.

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

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

breakOn :: 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.

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

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

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

The needle parameter may not be empty.

breakOnEnd :: 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")

center :: Int -> 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"

chunksOf :: Int -> 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"]

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

compareLength :: Text -> Int -> Ordering

O(n) Compare the count of characters in a Text to a number. Subject to fusion.

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.

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.

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

O(n) Adds a character to the front of a Text. This function is more costly than its List counterpart because it requires copying a new array. Subject to fusion. Performs replacement on invalid scalar values.

copy :: Text -> Text

O(n) Make a distinct copy of the given string, sharing no storage with the original string.

As an example, suppose you read a large string, of which you need only a small portion. If you do not use copy, the entire original array will be kept alive in memory by the smaller string. Making a copy "breaks the link" to the original array, allowing it to be garbage collected if there are no other live references to it.

decodeUtf8' :: ByteString -> Either UnicodeException Text

Decode a ByteString containing UTF-8 encoded text.

If the input contains any invalid UTF-8 data, the relevant exception will be returned, otherwise the decoded text.

double :: Reader Double

Read a rational number.

The syntax accepted by this function is the same as for rational.

Note: This function is almost ten times faster than rational, but is slightly less accurate.

The Double type supports about 16 decimal places of accuracy. For 94.2% of numbers, this function and rational give identical results, but for the remaining 5.8%, this function loses precision around the 15th decimal place. For 0.001% of numbers, this function will lose precision at the 13th or 14th decimal place.

drop :: Int -> 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. Subject to fusion.

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. Subject to fusion.

dropEnd :: Int -> 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: text-1.1.1.0

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

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

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. Subject to fusion.

Examples:

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

empty :: Text

O(1) The empty Text.

encodeUtf16BE :: Text -> ByteString

Encode text using big endian UTF-16 encoding.

encodeUtf16LE :: Text -> ByteString

Encode text using little endian UTF-16 encoding.

encodeUtf32BE :: Text -> ByteString

Encode text using big endian UTF-32 encoding.

encodeUtf32LE :: Text -> ByteString

Encode text using little endian UTF-32 encoding.

encodeUtf8 :: Text -> ByteString

Encode text using UTF-8 encoding.

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 matching the predicate, or Nothing if there is no such element.

findIndex :: (Char -> Bool) -> Text -> Maybe Int

O(n) The findIndex function takes a predicate and a Text and returns the index of the first element in the Text satisfying the predicate. Subject to fusion.

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

O(n) A strict version of foldl. Subject to fusion.

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. Subject to fusion.

group :: Text -> [Text]

O(n) Group characters in a string by equality.

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

O(n) Group characters in a string according to a predicate.

inits :: Text -> [Text]

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

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.

Example:

>>> T.intercalate "NI!" ["We", "seek", "the", "Holy", "Grail"]
"WeNI!seekNI!theNI!HolyNI!Grail"

intersperse :: Char -> Text -> Text

O(n) The intersperse function takes a character and places it between the characters of a Text.

Example:

>>> T.intersperse '.' "SHIELD"
"S.H.I.E.L.D"

Subject to fusion. Performs replacement on invalid scalar values.

isInfixOf :: Text -> Text -> Bool

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

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

isPrefixOf :: Text -> Text -> Bool

O(n) The isPrefixOf function takes two Texts and returns True iff the first is a prefix of the second. Subject to fusion.

isSuffixOf :: Text -> Text -> Bool

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

justifyLeft :: Int -> Char -> Text -> Text

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

Examples:

>>> justifyLeft 7 'x' "foo"
"fooxxxx"

>>> justifyLeft 3 'x' "foobar"
"foobar"

justifyRight :: Int -> 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"

length :: Text -> Int

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

lines :: Text -> [Text]

O(n) Breaks a Text up into a list of Texts at newline Chars. The resulting strings do not contain newlines.

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

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

Example:

>>> let message = pack "I am not angry. Not at all."
>>> T.map (\c -> if c == '.' then '!' else c) message
"I am not angry! Not at all!"

Subject to fusion. Performs replacement on invalid scalar values.

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.

null :: Text -> Bool

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

pack :: String -> Text

O(n) Convert a String into a Text. Subject to fusion. Performs replacement on invalid scalar values.

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)

rational :: Fractional a => Reader a

Read a rational number.

This function accepts an optional leading sign character, followed by at least one decimal digit. The syntax similar to that accepted by the read function, with the exception that a trailing '.' or 'e' not followed by a number is not consumed.

Examples (with behaviour identical to read):

rational "3"     == Right (3.0, "")
rational "3.1"   == Right (3.1, "")
rational "3e4"   == Right (30000.0, "")
rational "3.1e4" == Right (31000.0, "")
rational ".3"    == Left "input does not start with a digit"
rational "e3"    == Left "input does not start with a digit"

Examples of differences from read:

rational "3.foo" == Right (3.0, ".foo")
rational "3e"    == Right (3.0, "e")

replace

Arguments

:: 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).

replicate :: Int -> Text -> Text

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

reverse :: Text -> Text

O(n) Reverse the characters of a string.

Example:

>>> T.reverse "desrever"
"reversed"

Subject to fusion.

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. Subject to fusion. 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. Subject to fusion. 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. Subject to fusion. Performs replacement on invalid scalar values.

singleton :: Char -> Text

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

snoc :: Text -> Char -> Text

O(n) Adds a character to the end of a Text. This copies the entire array in the process, unless fused. Subject to fusion. Performs replacement on invalid scalar values.

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 list.

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') ""
[""]

splitAt :: Int -> 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).

strip :: Text -> Text

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

dropAround isSpace

stripEnd :: Text -> Text

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

dropWhileEnd isSpace

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 as T

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

stripStart :: Text -> Text

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

dropWhile isSpace

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 as T

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

tails :: Text -> [Text]

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

take :: Int -> 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. Subject to fusion.

takeEnd :: Int -> 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: text-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. Subject to fusion.

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. Subject to fusion. Examples:

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

Since: text-1.2.2.0

toCaseFold :: Text -> Text

O(n) Convert a string to folded case. Subject to fusion.

This function is mainly useful for performing caseless (also known as 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 "ﬓ" (men now, U+FB13) is case folded to the sequence "մ" (men, U+0574) followed by "ն" (now, U+0576), while the Greek "µ" (micro sign, U+00B5) is case folded to "μ" (small letter mu, U+03BC) instead of itself.

toLower :: Text -> Text

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

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

toTitle :: Text -> Text

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

The first letter 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).

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: text-1.0.0.0

toUpper :: Text -> Text

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

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

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.

Examples:

>>> transpose ["green","orange"]
["go","rr","ea","en","ng","e"]

>>> transpose ["blue","red"]
["br","le","ud","e"]

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

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

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. Subject to fusion. Performs replacement on invalid scalar values.

unfoldrN :: Int -> (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. Subject to fusion. Performs replacement on invalid scalar values.

unlines :: [Text] -> Text

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

unpack :: Text -> String

O(n) Convert a Text into a String. Subject to fusion.

unpackCString# :: Addr# -> Text

O(n) Convert a literal string into a Text. Subject to fusion.

This is exposed solely for people writing GHC rewrite rules.

Since: text-1.2.1.1

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

O(1) Returns all but the last character and the last character of a Text, or Nothing if empty.

Since: text-1.2.3.0

unwords :: [Text] -> Text

O(n) Joins words using single space characters.

words :: Text -> [Text]

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

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.

Similarity metrics

levenshtein :: Text -> Text -> Int

Return Levenshtein distance between two Text values. Classic Levenshtein distance between two strings is the minimal number of operations necessary to transform one string into another. For Levenshtein distance allowed operations are: deletion, insertion, and substitution.

See also: https://en.wikipedia.org/wiki/Levenshtein_distance.

Heads up, before version 0.3.0 this function returned Natural.

levenshteinNorm :: Text -> Text -> Ratio Int

Return normalized Levenshtein distance between two Text values. Result is a non-negative rational number (represented as Ratio Natural), where 0 signifies no similarity between the strings, while 1 means exact match.

See also: https://en.wikipedia.org/wiki/Levenshtein_distance.

Heads up, before version 0.3.0 this function returned Ratio Natural.

damerauLevenshtein :: Text -> Text -> Int

Return Damerau-Levenshtein distance between two Text values. The function works like levenshtein, but the collection of allowed operations also includes transposition of two adjacent characters.

See also: https://en.wikipedia.org/wiki/Damerau%E2%80%93Levenshtein_distance.

Heads up, before version 0.3.0 this function returned Natural.

damerauLevenshteinNorm :: Text -> Text -> Ratio Int

Return normalized Damerau-Levenshtein distance between two Text values. 0 signifies no similarity between the strings, while 1 means exact match.

See also: https://en.wikipedia.org/wiki/Damerau%E2%80%93Levenshtein_distance.

Heads up, before version 0.3.0 this function returned Ratio Natural.

overlap :: Text -> Text -> Ratio Int

Return overlap coefficient for two Text values. Returned value is in the range from 0 (no similarity) to 1 (exact match). Return 1 if both Text values are empty.

See also: https://en.wikipedia.org/wiki/Overlap_coefficient.

Since: text-metrics-0.3.0

jaccard :: Text -> Text -> Ratio Int

Return Jaccard similarity coefficient for two Text values. Returned value is in the range from 0 (no similarity) to 1 (exact match). Return 1 if both

See also: https://en.wikipedia.org/wiki/Jaccard_index

Since: text-metrics-0.3.0

hamming :: Text -> Text -> Maybe Int

O(n) Return Hamming distance between two Text values. Hamming distance is defined as the number of positions at which the corresponding symbols are different. The input Text values should be of equal length or Nothing will be returned.

See also: https://en.wikipedia.org/wiki/Hamming_distance.

Heads up, before version 0.3.0 this function returned Maybe Natural.

jaro :: Text -> Text -> Ratio Int

Return Jaro distance between two Text values. Returned value is in the range from 0 (no similarity) to 1 (exact match).

While the algorithm is pretty clear for artificial examples (like those from the linked Wikipedia article), for arbitrary strings, it may be hard to decide which of two strings should be considered as one having “reference” order of characters (order of matching characters in an essential part of the definition of the algorithm). This makes us consider the first string the “reference” string (with correct order of characters). Thus generally,

jaro a b ≠ jaro b a

This asymmetry can be found in all implementations of the algorithm on the internet, AFAIK.

See also: https://en.wikipedia.org/wiki/Jaro%E2%80%93Winkler_distance

Heads up, before version 0.3.0 this function returned Ratio Natural.

Since: text-metrics-0.2.0

jaroWinkler :: Text -> Text -> Ratio Int

Return Jaro-Winkler distance between two Text values. Returned value is in range from 0 (no similarity) to 1 (exact match).

See also: https://en.wikipedia.org/wiki/Jaro%E2%80%93Winkler_distance

Heads up, before version 0.3.0 this function returned Ratio Natural.

Since: text-metrics-0.2.0

Number conversion

type Reader a = IReader Text a

Read some text. If the read succeeds, return its value and the remaining text, otherwise an error message.

type IReader t a = t -> Either String (a, t)

decimal :: Integral a => Reader a

Read a decimal integer. The input must begin with at least one decimal digit, and is consumed until a non-digit or end of string is reached.

This function does not handle leading sign characters. If you need to handle signed input, use signed decimal.

Note: For fixed-width integer types, this function does not attempt to detect overflow, so a sufficiently long input may give incorrect results. If you are worried about overflow, use Integer for your result type.

hexadecimal :: Integral a => Reader a

Read a hexadecimal integer, consisting of an optional leading "0x" followed by at least one hexadecimal digit. Input is consumed until a non-hex-digit or end of string is reached. This function is case insensitive.

This function does not handle leading sign characters. If you need to handle signed input, use signed hexadecimal.

Note: For fixed-width integer types, this function does not attempt to detect overflow, so a sufficiently long input may give incorrect results. If you are worried about overflow, use Integer for your result type.

signed :: Num a => Reader a -> Reader a

Read an optional leading sign character ('-' or '+') and apply it to the result of applying the given reader.

Optics

packed :: Iso' String Text

This isomorphism can be used to pack (or unpack) strict Text.

>>> "hello"^.packed -- :: Text
"hello"

pack x ≡ x ^. packed
unpack x ≡ x ^. from packed
packed ≡ from unpacked
packed ≡ iso pack unpack

unpacked :: Iso' Text String

This isomorphism can be used to unpack (or pack) lazy Text.

>>> "hello"^.unpacked -- :: String
"hello"

This Iso is provided for notational convenience rather than out of great need, since

unpacked ≡ from packed

pack x ≡ x ^. from unpacked
unpack x ≡ x ^. packed
unpacked ≡ iso unpack pack

text :: IndexedTraversal' Int Text Char

Traverse the individual characters in strict Text.

>>> anyOf text (=='o') "hello"
True

When the type is unambiguous, you can also use the more general each.

text ≡ unpacked . traversed
text ≡ each

Note that when just using this as a Setter, setting map can be more efficient.

builder :: Iso' Text Builder

Convert between strict Text and Builder .

fromText x ≡ x ^. builder
toStrict (toLazyText x) ≡ x ^. from builder