Copyright | (C) 2016-2025 David M. Johnson |
---|---|
License | BSD3-style (see the file LICENSE) |
Maintainer | David M. Johnson <code@dmj.io> |
Stability | experimental |
Portability | non-portable |
Safe Haskell | None |
Language | Haskell2010 |
Miso.String
Contents
Description
Synopsis
- class ToMisoString str where
- toMisoString :: str -> MisoString
- class FromMisoString t where
- fromMisoStringEither :: MisoString -> Either String t
- type MisoString = Text
- ms :: ToMisoString str => str -> MisoString
- fromMisoString :: FromMisoString a => MisoString -> a
- module Data.Monoid
- pattern (:<) :: Char -> Text -> Text
- pattern (:>) :: Text -> Char -> Text
- pattern Empty :: Text
- all :: (Char -> Bool) -> Text -> Bool
- any :: (Char -> Bool) -> Text -> Bool
- break :: (Char -> Bool) -> Text -> (Text, Text)
- breakOn :: HasCallStack => Text -> Text -> (Text, Text)
- breakOnAll :: HasCallStack => Text -> Text -> [(Text, Text)]
- breakOnEnd :: HasCallStack => Text -> Text -> (Text, Text)
- center :: Int -> Char -> Text -> Text
- chunksOf :: Int -> Text -> [Text]
- commonPrefixes :: Text -> Text -> Maybe (Text, Text, Text)
- compareLength :: Text -> Int -> Ordering
- concat :: [Text] -> Text
- concatMap :: (Char -> Text) -> Text -> Text
- cons :: Char -> Text -> Text
- copy :: Text -> Text
- count :: HasCallStack => Text -> Text -> Int
- drop :: Int -> Text -> Text
- dropAround :: (Char -> Bool) -> Text -> Text
- dropEnd :: Int -> Text -> Text
- dropWhile :: (Char -> Bool) -> Text -> Text
- dropWhileEnd :: (Char -> Bool) -> Text -> Text
- filter :: (Char -> Bool) -> Text -> Text
- find :: (Char -> Bool) -> Text -> Maybe Char
- findIndex :: (Char -> Bool) -> Text -> Maybe Int
- foldl :: (a -> Char -> a) -> a -> Text -> a
- foldl' :: (a -> Char -> a) -> a -> Text -> a
- foldl1 :: HasCallStack => (Char -> Char -> Char) -> Text -> Char
- foldl1' :: HasCallStack => (Char -> Char -> Char) -> Text -> Char
- foldlM' :: Monad m => (a -> Char -> m a) -> a -> Text -> m a
- foldr :: (Char -> a -> a) -> a -> Text -> a
- foldr' :: (Char -> a -> a) -> a -> Text -> a
- foldr1 :: HasCallStack => (Char -> Char -> Char) -> Text -> Char
- group :: Text -> [Text]
- groupBy :: (Char -> Char -> Bool) -> Text -> [Text]
- head :: HasCallStack => Text -> Char
- index :: HasCallStack => Text -> Int -> Char
- init :: HasCallStack => Text -> Text
- inits :: Text -> [Text]
- initsNE :: Text -> NonEmpty Text
- intercalate :: Text -> [Text] -> Text
- intersperse :: Char -> Text -> Text
- isInfixOf :: Text -> Text -> Bool
- isPrefixOf :: Text -> Text -> Bool
- isSuffixOf :: Text -> Text -> Bool
- justifyLeft :: Int -> Char -> Text -> Text
- justifyRight :: Int -> Char -> Text -> Text
- last :: HasCallStack => Text -> Char
- length :: Text -> Int
- lines :: Text -> [Text]
- map :: (Char -> Char) -> Text -> Text
- mapAccumL :: (a -> Char -> (a, Char)) -> a -> Text -> (a, Text)
- mapAccumR :: (a -> Char -> (a, Char)) -> a -> Text -> (a, Text)
- maximum :: HasCallStack => Text -> Char
- measureOff :: Int -> Text -> Int
- minimum :: HasCallStack => Text -> Char
- null :: Text -> Bool
- partition :: (Char -> Bool) -> Text -> (Text, Text)
- replace :: HasCallStack => Text -> Text -> Text -> Text
- replicate :: Int -> Text -> Text
- scanl :: (Char -> Char -> Char) -> Char -> Text -> Text
- scanl1 :: (Char -> Char -> Char) -> Text -> Text
- scanr :: (Char -> Char -> Char) -> Char -> Text -> Text
- scanr1 :: (Char -> Char -> Char) -> Text -> Text
- snoc :: Text -> Char -> Text
- span :: (Char -> Bool) -> Text -> (Text, Text)
- spanEndM :: Monad m => (Char -> m Bool) -> Text -> m (Text, Text)
- spanM :: Monad m => (Char -> m Bool) -> Text -> m (Text, Text)
- split :: (Char -> Bool) -> Text -> [Text]
- splitAt :: Int -> Text -> (Text, Text)
- splitOn :: HasCallStack => Text -> Text -> [Text]
- strip :: Text -> Text
- stripEnd :: Text -> Text
- stripPrefix :: Text -> Text -> Maybe Text
- stripStart :: Text -> Text
- stripSuffix :: Text -> Text -> Maybe Text
- tail :: HasCallStack => Text -> Text
- tails :: Text -> [Text]
- tailsNE :: Text -> NonEmpty Text
- take :: Int -> Text -> Text
- takeEnd :: Int -> Text -> Text
- takeWhile :: (Char -> Bool) -> Text -> Text
- takeWhileEnd :: (Char -> Bool) -> Text -> Text
- toCaseFold :: Text -> Text
- toLower :: Text -> Text
- toTitle :: Text -> Text
- toUpper :: Text -> Text
- transpose :: [Text] -> [Text]
- uncons :: Text -> Maybe (Char, Text)
- unfoldr :: (a -> Maybe (Char, a)) -> a -> Text
- unfoldrN :: Int -> (a -> Maybe (Char, a)) -> a -> Text
- unlines :: [Text] -> Text
- unsnoc :: Text -> Maybe (Text, Char)
- unwords :: [Text] -> Text
- words :: Text -> [Text]
- zip :: Text -> Text -> [(Char, Char)]
- zipWith :: (Char -> Char -> Char) -> Text -> Text -> Text
- append :: Text -> Text -> Text
- empty :: Text
- pack :: String -> Text
- isAscii :: Text -> Bool
- reverse :: Text -> Text
- singleton :: Char -> Text
- unpack :: Text -> String
- unpackCString# :: Addr# -> Text
- unpackCStringAscii# :: Addr# -> Text
- type StrictText = Text
- data Text
Classes
class ToMisoString str where Source #
Convenience class for creating MisoString
from other string-like types
Methods
toMisoString :: str -> MisoString Source #
Instances
class FromMisoString t where Source #
Class from safely parsing MisoString
Methods
fromMisoStringEither :: MisoString -> Either String t Source #
Instances
Types
type MisoString = Text Source #
String type swappable based on compiler
Functions
ms :: ToMisoString str => str -> MisoString Source #
Convenience function, shorthand for toMisoString
fromMisoString :: FromMisoString a => MisoString -> a Source #
Parses a MisoString
, throws an error when decoding
fails. Use fromMisoStringEither
for as a safe alternative.
Re-exports
module Data.Monoid
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.
In (unlikely) bad cases, this function's time complexity degrades towards O(n*m).
Arguments
:: HasCallStack | |
=> Text |
|
-> Text |
|
-> [(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 :: 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")
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(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.
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. Performs replacement on
invalid scalar values.
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.
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
.
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
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"
foldlM' :: Monad m => (a -> Char -> m a) -> a -> Text -> m a #
O(n) A monadic version of foldl'
.
Since: text-2.1.2
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.
If the binary operator is strict in its second argument, use foldr'
instead.
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")
Searches from left to right with short-circuiting behavior can
also be defined using foldr
(e.g., any
, all
, find
, elem
).
groupBy :: (Char -> Char -> Bool) -> Text -> [Text] #
O(n) Group characters in a string according to a predicate.
head :: HasCallStack => Text -> Char #
index :: HasCallStack => Text -> Int -> Char #
O(n) Text
index (subscript) operator, starting from 0.
init :: HasCallStack => Text -> Text #
initsNE :: Text -> NonEmpty Text #
O(n) Return all initial segments of the given Text
, shortest
first.
Since: text-2.1.2
intercalate :: Text -> [Text] -> Text #
O(n) The intercalate
function takes a Text
and a list of
Text
s 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"
Performs replacement on invalid scalar values.
isPrefixOf :: Text -> Text -> Bool #
O(n) The isPrefixOf
function takes two Text
s 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 Text
s and returns
True
if and only if 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. 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"
last :: HasCallStack => Text -> Char #
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.
maximum :: HasCallStack => Text -> Char #
measureOff :: Int -> Text -> Int #
O(n) If t
is long enough to contain n
characters, measureOff
n
t
returns a non-negative number, measuring their size in Word8
. Otherwise,
if t
is shorter, return a non-positive number, which is a negated total count
of Char
available in t
. If t
is empty or n = 0
, return 0.
This function is used to implement take
, drop
, splitAt
and length
and is useful on its own in streaming and parsing libraries.
Since: text-2.0
minimum :: HasCallStack => Text -> Char #
Arguments
:: HasCallStack | |
=> Text |
|
-> Text |
|
-> Text |
|
-> 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).
snoc :: Text -> Char -> Text #
O(n) Adds a character to the end of a Text
. This copies the
entire array in the process.
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 text.
>>>
T.span (=='0') "000AB"
("000","AB")
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: text-2.0.1
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 -> Boolspan
p =runIdentity
.spanM
(pure
. p)
Since: text-2.0.1
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') ""
[""]
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 empty), 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.)
In (unlikely) bad cases, this function's time complexity degrades towards O(n*m).
O(n) Remove leading and trailing white space from a string. Equivalent to:
dropAround isSpace
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
tail :: HasCallStack => Text -> Text #
tailsNE :: Text -> NonEmpty Text #
O(n) Return all final segments of the given Text
, longest
first.
Since: text-2.1.2
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
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: text-1.2.2.0
toCaseFold :: Text -> Text #
O(n) Convert a string to folded case.
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.
O(n) Convert a string to lower case, using simple case conversion.
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).
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.
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"
.
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
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 "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"]
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 :: 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
.
Performs replacement on invalid scalar values.
O(1) Convert a character into a Text. Performs replacement on invalid scalar values.
unpackCString# :: Addr# -> Text #
O(n) Convert a null-terminated
modified UTF-8
(but with a standard UTF-8 representation of characters from supplementary planes)
string to a Text
. Counterpart to unpackCStringUtf8#
.
No validation is performed, malformed input can lead to memory access violation.
Since: text-1.2.1.1
unpackCStringAscii# :: Addr# -> Text #
O(n) Convert a null-terminated ASCII string to a Text
.
Counterpart to unpackCString#
.
No validation is performed, malformed input can lead to memory access violation.
Since: text-2.0
type StrictText = Text #
Type synonym for the strict flavour of Text
.
A space efficient, packed, unboxed Unicode text type.