Safe Haskell | Safe-Inferred |
---|---|
Language | Haskell2010 |
RIO.Text
Description
Strict Text
. Import as:
import qualified RIO.Text as T
This module does not export any partial functions. For those, see RIO.Text.Partial
Synopsis
- data Text
- pack :: String -> Text
- unpack :: Text -> String
- singleton :: Char -> Text
- empty :: Text
- cons :: Char -> Text -> Text
- snoc :: Text -> Char -> Text
- append :: Text -> Text -> Text
- uncons :: Text -> Maybe (Char, Text)
- null :: Text -> Bool
- length :: Text -> Int
- compareLength :: Text -> Int -> Ordering
- map :: (Char -> Char) -> Text -> Text
- intercalate :: Text -> [Text] -> Text
- intersperse :: Char -> Text -> Text
- transpose :: [Text] -> [Text]
- reverse :: Text -> Text
- toCaseFold :: Text -> Text
- toLower :: Text -> Text
- toUpper :: Text -> Text
- toTitle :: Text -> Text
- justifyLeft :: Int -> Char -> Text -> Text
- justifyRight :: Int -> Char -> Text -> Text
- center :: Int -> Char -> Text -> Text
- foldl :: (a -> Char -> a) -> a -> Text -> a
- foldl' :: (a -> Char -> a) -> a -> Text -> a
- foldr :: (Char -> a -> a) -> a -> Text -> a
- concat :: [Text] -> Text
- concatMap :: (Char -> Text) -> Text -> Text
- any :: (Char -> Bool) -> Text -> Bool
- all :: (Char -> Bool) -> Text -> Bool
- 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
- mapAccumL :: (a -> Char -> (a, Char)) -> a -> Text -> (a, Text)
- mapAccumR :: (a -> Char -> (a, Char)) -> a -> Text -> (a, Text)
- replicate :: Int -> Text -> Text
- unfoldr :: (a -> Maybe (Char, a)) -> a -> Text
- unfoldrN :: Int -> (a -> Maybe (Char, a)) -> a -> Text
- take :: Int -> Text -> Text
- takeEnd :: Int -> Text -> Text
- drop :: Int -> Text -> Text
- dropEnd :: Int -> Text -> Text
- takeWhile :: (Char -> Bool) -> Text -> Text
- takeWhileEnd :: (Char -> Bool) -> Text -> Text
- dropWhile :: (Char -> Bool) -> Text -> Text
- dropWhileEnd :: (Char -> Bool) -> Text -> Text
- dropAround :: (Char -> Bool) -> Text -> Text
- strip :: Text -> Text
- stripStart :: Text -> Text
- stripEnd :: Text -> Text
- splitAt :: Int -> Text -> (Text, Text)
- break :: (Char -> Bool) -> Text -> (Text, Text)
- span :: (Char -> Bool) -> Text -> (Text, Text)
- group :: Text -> [Text]
- groupBy :: (Char -> Char -> Bool) -> Text -> [Text]
- inits :: Text -> [Text]
- tails :: Text -> [Text]
- split :: (Char -> Bool) -> Text -> [Text]
- chunksOf :: Int -> Text -> [Text]
- lines :: Text -> [Text]
- linesCR :: Text -> [Text]
- words :: Text -> [Text]
- unlines :: [Text] -> Text
- unwords :: [Text] -> Text
- isPrefixOf :: Text -> Text -> Bool
- isSuffixOf :: Text -> Text -> Bool
- isInfixOf :: Text -> Text -> Bool
- stripPrefix :: Text -> Text -> Maybe Text
- stripSuffix :: Text -> Text -> Maybe Text
- dropPrefix :: Text -> Text -> Text
- dropSuffix :: Text -> Text -> Text
- commonPrefixes :: Text -> Text -> Maybe (Text, Text, Text)
- filter :: (Char -> Bool) -> Text -> Text
- find :: (Char -> Bool) -> Text -> Maybe Char
- partition :: (Char -> Bool) -> Text -> (Text, Text)
- index :: HasCallStack => Text -> Int -> Char
- findIndex :: (Char -> Bool) -> Text -> Maybe Int
- zip :: Text -> Text -> [(Char, Char)]
- zipWith :: (Char -> Char -> Char) -> Text -> Text -> Text
- copy :: Text -> Text
- unpackCString# :: Addr# -> Text
- encodeUtf8 :: Text -> ByteString
- decodeUtf8With :: OnDecodeError -> ByteString -> Text
- decodeUtf8' :: ByteString -> Either UnicodeException Text
- lenientDecode :: OnDecodeError
Types
A space efficient, packed, unboxed Unicode text type.
Creation and elimination
singleton :: Char -> Text Source #
O(1) Convert a character into a Text. Performs replacement on invalid scalar values.
Basic interface
cons :: Char -> Text -> Text infixr 5 Source #
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.
snoc :: Text -> Char -> Text Source #
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.
compareLength :: Text -> Int -> Ordering Source #
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
intercalate :: Text -> [Text] -> Text Source #
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 Source #
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.
transpose :: [Text] -> [Text] Source #
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"]
reverse :: Text -> Text Source #
O(n) Reverse the characters of a string.
Example:
>>>
T.reverse "desrever"
"reversed"
Case conversion
toCaseFold :: Text -> Text Source #
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.
toLower :: Text -> Text Source #
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).
toUpper :: Text -> Text Source #
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".
toTitle :: Text -> Text Source #
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
Justification
justifyLeft :: Int -> Char -> Text -> Text Source #
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 Source #
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 :: Int -> Char -> Text -> Text Source #
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
foldr :: (Char -> a -> a) -> a -> Text -> a Source #
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
).
Special folds
Construction
Scans
Accumulating maps
mapAccumR :: (a -> Char -> (a, Char)) -> a -> Text -> (a, Text) Source #
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
unfoldr :: (a -> Maybe (Char, a)) -> a -> Text Source #
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 Source #
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
takeEnd :: Int -> Text -> Text Source #
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
dropEnd :: Int -> Text -> Text Source #
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
takeWhileEnd :: (Char -> Bool) -> Text -> Text Source #
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
dropWhileEnd :: (Char -> Bool) -> Text -> Text Source #
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 Source #
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 Source #
O(n) Remove leading and trailing white space from a string. Equivalent to:
dropAround isSpace
stripStart :: Text -> Text Source #
O(n) Remove leading white space from a string. Equivalent to:
dropWhile isSpace
stripEnd :: Text -> Text Source #
O(n) Remove trailing white space from a string. Equivalent to:
dropWhileEnd isSpace
span :: (Char -> Bool) -> Text -> (Text, Text) Source #
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")
groupBy :: (Char -> Char -> Bool) -> Text -> [Text] Source #
O(n) Group characters in a string according to a predicate.
Breaking into many substrings
split :: (Char -> Bool) -> Text -> [Text] Source #
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 :: Int -> Text -> [Text] Source #
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
Predicates
isPrefixOf :: Text -> Text -> Bool Source #
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 Source #
O(n) The isSuffixOf
function takes two Text
s and returns
True
if and only if the first is a suffix of the second.
View patterns
stripPrefix :: Text -> Text -> Maybe Text Source #
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
stripSuffix :: Text -> Text -> Maybe Text Source #
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
Drop prefix if present, otherwise return original Text
.
Since: 0.0.0.0
Drop prefix if present, otherwise return original Text
.
Since: 0.0.0.0
commonPrefixes :: Text -> Text -> Maybe (Text, Text, Text) Source #
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
Indexing
index :: HasCallStack => Text -> Int -> Char Source #
O(n) Text
index (subscript) operator, starting from 0.
Zipping
Low level operations
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.
unpackCString# :: Addr# -> Text Source #
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
Encoding
encodeUtf8 :: Text -> ByteString Source #
Encode text using UTF-8 encoding.
decodeUtf8With :: OnDecodeError -> ByteString -> Text Source #
Decode a ByteString
containing UTF-8 encoded text.
Surrogate code points in replacement character returned by OnDecodeError
will be automatically remapped to the replacement char U+FFFD
.
decodeUtf8' :: ByteString -> Either UnicodeException Text Source #
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.
lenientDecode :: OnDecodeError Source #
Replace an invalid input byte with the Unicode replacement character U+FFFD.