Data.String.CodePoints
- Package
- purescript-strings
- Repository
- purescript/purescript-strings
These functions allow PureScript strings to be treated as if they were
sequences of Unicode code points instead of their true underlying
implementation (sequences of UTF-16 code units). For nearly all uses of
strings, these functions should be preferred over the ones in Data.String
.
#codePointAt Source
codePointAt :: Int -> String -> Maybe CodePoint
Returns the first code point of the string after dropping the given number of code points from the beginning, if there is such a code point. Operates in constant space and in time linear to the given index.
>>> codePointAt 1 "ππππ"
Just (CodePoint 0x1D400) -- represents "π"
-- compare to Data.String:
>>> charAt 1 "ππππ"
Just 'οΏ½'
#codePointFromInt Source
codePointFromInt :: Int -> Maybe CodePoint
>>> it = codePointFromInt 0x1D400 -- U+1D400 MATHEMATICAL BOLD CAPITAL A
Just (CodePoint 0x1D400)
>>> map singleton it
Just "π"
>>> codePointFromInt 0x110000 -- does not correspond to a Unicode code point
Nothing
#codePointToInt Source
codePointToInt :: CodePoint -> Int
>>> codePointToInt (codePointFromChar 'B')
66
>>> boldA = codePointFromInt 0x1D400
>>> boldA
Just (CodePoint 0x1D400)
>>> map codePointToInt boldA
Just 119808 -- is the same as 0x1D400
#codePointFromChar Source
codePointFromChar :: Char -> CodePoint
Creates a CodePoint from a given Char.
>>> codePointFromChar 'B'
CodePoint 0x42 -- represents 'B'
#count Source
count :: (CodePoint -> Boolean) -> String -> Int
Returns the number of code points in the leading sequence of code points which all match the given predicate. Operates in constant space and in time linear to the length of the string.
>>> count (\c -> codePointToInt c == 0x1D400) "ππ b c π"
2
#drop Source
drop :: Int -> String -> String
Drops the given number of code points from the beginning of the string. If the string does not have that many code points, returns the empty string. Operates in constant space and in time linear to the given number.
>>> drop 5 "ππ b c"
"c"
-- compared to Data.String:
>>> drop 5 "ππ b c"
"b c" -- because "π" occupies 2 code units
#dropWhile Source
dropWhile :: (CodePoint -> Boolean) -> String -> String
Drops the leading sequence of code points which all match the given predicate from the string. Operates in constant space and in time linear to the length of the string.
>>> dropWhile (\c -> codePointToInt c == 0x1D400) "ππ b c π"
" b c π"
#fromCodePointArray Source
fromCodePointArray :: Array CodePoint -> String
Creates a string from an array of code points. Operates in space and time linear to the length of the array.
>>> codePointArray = toCodePointArray "c π"
>>> codePointArray
[CodePoint 0x63, CodePoint 0x20, CodePoint 0x1D400]
>>> fromCodePointArray codePointArray
"c π"
#indexOf' Source
indexOf' :: Pattern -> Int -> String -> Maybe Int
Returns the number of code points preceding the first match of the given pattern in the string. Pattern matches preceding the given index will be ignored. Returns Nothing when no matches are found.
>>> indexOf' (Pattern "π") 4 "b ππ c π"
Just 7
>>> indexOf' (Pattern "o") 4 "b ππ c π"
Nothing
#lastIndexOf Source
lastIndexOf :: Pattern -> String -> Maybe Int
Returns the number of code points preceding the last match of the given pattern in the string. Returns Nothing when no matches are found.
>>> lastIndexOf (Pattern "π") "b ππ c π"
Just 7
>>> lastIndexOf (Pattern "o") "b ππ c π"
Nothing
#lastIndexOf' Source
lastIndexOf' :: Pattern -> Int -> String -> Maybe Int
Returns the number of code points preceding the first match of the given pattern in the string. Pattern matches following the given index will be ignored. Returns Nothing when no matches are found.
>>> lastIndexOf' (Pattern "π") 5 "b ππ c π"
Just 3
>>> lastIndexOf' (Pattern "o") 5 "b ππ c π"
Nothing
#splitAt Source
splitAt :: Int -> String -> Maybe { after :: String, before :: String }
Returns a record with strings created from the code points on either side of the given index. If the index is not within the string, Nothing is returned.
>>> splitAt 3 "b ππ c π"
Just { before: "b π", after: "π c π" }
#take Source
take :: Int -> String -> String
Returns a string containing the given number of code points from the beginning of the given string. If the string does not have that many code points, returns the empty string. Operates in constant space and in time linear to the given number.
>>> take 3 "b ππ c π"
"b π"
-- compare to Data.String:
>>> take 3 "b ππ c π"
"b οΏ½"
#takeWhile Source
takeWhile :: (CodePoint -> Boolean) -> String -> String
Returns a string containing the leading sequence of code points which all match the given predicate from the string. Operates in constant space and in time linear to the length of the string.
>>> takeWhile (\c -> codePointToInt c == 0x1D400) "ππ b c π"
"ππ"
#toCodePointArray Source
toCodePointArray :: String -> Array CodePoint
Creates an array of code points from a string. Operates in space and time linear to the length of the string.
>>> codePointArray = toCodePointArray "b ππ"
>>> codePointArray
[CodePoint 0x62, CodePoint 0x20, CodePoint 0x1D400, CodePoint 0x1D400]
>>> map singleton codePointArray
["b", " ", "π", "π"]
#uncons Source
uncons :: String -> Maybe { head :: CodePoint, tail :: String }
Returns a record with the first code point and the remaining code points of the string. Returns Nothing if the string is empty. Operates in constant space and time.
>>> uncons "ππ c π"
Just { head: CodePoint 0x1D400, tail: "π c π" }
>>> uncons ""
Nothing
Re-exports from Data.String
#Replacement Source
newtype Replacement
A newtype used in cases to specify a replacement for a pattern.
Constructors
Instances
#trim Source
trim :: String -> String
Removes whitespace from the beginning and end of a string, including whitespace characters and line terminators.
trim " Hello \n World\n\t " == "Hello \n World"
#toCharArray Source
toCharArray :: String -> Array Char
Converts the string into an array of characters.
toCharArray "HelloβΊ\n" == ['H','e','l','l','o','βΊ','\n']
#stripSuffix Source
stripSuffix :: Pattern -> String -> Maybe String
If the string ends with the given suffix, return the portion of the
string left after removing it, as a Just
value. Otherwise, return
Nothing
.
stripSuffix (Pattern ".exe") "psc.exe" == Just "psc"
stripSuffix (Pattern ".exe") "psc" == Nothing
#stripPrefix Source
stripPrefix :: Pattern -> String -> Maybe String
If the string starts with the given prefix, return the portion of the string left after removing it, as a Just value. Otherwise, return Nothing.
stripPrefix (Pattern "http:") "http://purescript.org" == Just "//purescript.org"
stripPrefix (Pattern "http:") "https://purescript.org" == Nothing
#replaceAll Source
replaceAll :: Pattern -> Replacement -> String -> String
Replaces all occurences of the pattern with the replacement string.
replaceAll (Pattern "<=") (Replacement "β€") "a <= b <= c" == "a β€ b β€ c"
#replace Source
replace :: Pattern -> Replacement -> String -> String
Replaces the first occurence of the pattern with the replacement string.
replace (Pattern "<=") (Replacement "β€") "a <= b <= c" == "a β€ b <= c"
#localeCompare Source
localeCompare :: String -> String -> Ordering
Compare two strings in a locale-aware fashion. This is in contrast to
the Ord
instance on String
which treats strings as arrays of code
units:
"Γ€" `localeCompare` "b" == LT
"Γ€" `compare` "b" == GT
#fromCharArray Source
fromCharArray :: Array Char -> String
Converts an array of characters into a string.
fromCharArray ['H', 'e', 'l', 'l', 'o'] == "Hello"