| Copyright | © 2021 Julian Ospald |
|---|---|
| License | MIT |
| Maintainer | Julian Ospald <hasufell@posteo.de> |
| Stability | experimental |
| Portability | portable |
| Safe Haskell | None |
| Language | Haskell2010 |
System.OsString
Description
An implementation of platform specific short OsString, which is:
- on windows wide char bytes (
[Word16]) - on unix char bytes (
[Word8])
It captures the notion of syscall specific encoding (or the lack thereof) to avoid roundtrip issues and memory fragmentation by using unpinned byte arrays. Bytes are not touched or interpreted.
Synopsis
- data OsString
- encodeUtf :: MonadThrow m => String -> m OsString
- unsafeEncodeUtf :: HasCallStack => String -> OsString
- encodeWith :: TextEncoding -> TextEncoding -> String -> Either EncodingException OsString
- encodeFS :: String -> IO OsString
- osstr :: QuasiQuoter
- empty :: OsString
- singleton :: OsChar -> OsString
- pack :: [OsChar] -> OsString
- decodeUtf :: MonadThrow m => OsString -> m String
- decodeWith :: TextEncoding -> TextEncoding -> OsString -> Either EncodingException String
- decodeFS :: OsString -> IO String
- unpack :: OsString -> [OsChar]
- data OsChar
- unsafeFromChar :: Char -> OsChar
- toChar :: OsChar -> Char
- snoc :: OsString -> OsChar -> OsString
- cons :: OsChar -> OsString -> OsString
- last :: HasCallStack => OsString -> OsChar
- tail :: HasCallStack => OsString -> OsString
- uncons :: OsString -> Maybe (OsChar, OsString)
- head :: HasCallStack => OsString -> OsChar
- init :: HasCallStack => OsString -> OsString
- unsnoc :: OsString -> Maybe (OsString, OsChar)
- null :: OsString -> Bool
- length :: OsString -> Int
- map :: (OsChar -> OsChar) -> OsString -> OsString
- reverse :: OsString -> OsString
- intercalate :: OsString -> [OsString] -> OsString
- foldl :: (a -> OsChar -> a) -> a -> OsString -> a
- foldl' :: (a -> OsChar -> a) -> a -> OsString -> a
- foldl1 :: (OsChar -> OsChar -> OsChar) -> OsString -> OsChar
- foldl1' :: (OsChar -> OsChar -> OsChar) -> OsString -> OsChar
- foldr :: (OsChar -> a -> a) -> a -> OsString -> a
- foldr' :: (OsChar -> a -> a) -> a -> OsString -> a
- foldr1 :: (OsChar -> OsChar -> OsChar) -> OsString -> OsChar
- foldr1' :: (OsChar -> OsChar -> OsChar) -> OsString -> OsChar
- all :: (OsChar -> Bool) -> OsString -> Bool
- any :: (OsChar -> Bool) -> OsString -> Bool
- concat :: [OsString] -> OsString
- replicate :: Int -> OsChar -> OsString
- unfoldr :: (a -> Maybe (OsChar, a)) -> a -> OsString
- unfoldrN :: Int -> (a -> Maybe (OsChar, a)) -> a -> (OsString, Maybe a)
- take :: Int -> OsString -> OsString
- takeEnd :: Int -> OsString -> OsString
- takeWhileEnd :: (OsChar -> Bool) -> OsString -> OsString
- takeWhile :: (OsChar -> Bool) -> OsString -> OsString
- drop :: Int -> OsString -> OsString
- dropEnd :: Int -> OsString -> OsString
- dropWhileEnd :: (OsChar -> Bool) -> OsString -> OsString
- dropWhile :: (OsChar -> Bool) -> OsString -> OsString
- break :: (OsChar -> Bool) -> OsString -> (OsString, OsString)
- breakEnd :: (OsChar -> Bool) -> OsString -> (OsString, OsString)
- span :: (OsChar -> Bool) -> OsString -> (OsString, OsString)
- spanEnd :: (OsChar -> Bool) -> OsString -> (OsString, OsString)
- splitAt :: Int -> OsString -> (OsString, OsString)
- split :: OsChar -> OsString -> [OsString]
- splitWith :: (OsChar -> Bool) -> OsString -> [OsString]
- stripSuffix :: OsString -> OsString -> Maybe OsString
- stripPrefix :: OsString -> OsString -> Maybe OsString
- isInfixOf :: OsString -> OsString -> Bool
- isPrefixOf :: OsString -> OsString -> Bool
- isSuffixOf :: OsString -> OsString -> Bool
- breakSubstring :: OsString -> OsString -> (OsString, OsString)
- elem :: OsChar -> OsString -> Bool
- find :: (OsChar -> Bool) -> OsString -> Maybe OsChar
- filter :: (OsChar -> Bool) -> OsString -> OsString
- partition :: (OsChar -> Bool) -> OsString -> (OsString, OsString)
- index :: HasCallStack => OsString -> Int -> OsChar
- indexMaybe :: OsString -> Int -> Maybe OsChar
- (!?) :: OsString -> Int -> Maybe OsChar
- elemIndex :: OsChar -> OsString -> Maybe Int
- elemIndices :: OsChar -> OsString -> [Int]
- count :: OsChar -> OsString -> Int
- findIndex :: (OsChar -> Bool) -> OsString -> Maybe Int
- findIndices :: (OsChar -> Bool) -> OsString -> [Int]
- coercionToPlatformTypes :: Either (Coercion OsChar WindowsChar, Coercion OsString WindowsString) (Coercion OsChar PosixChar, Coercion OsString PosixString)
String types
Newtype representing short operating system specific strings.
Internally this is either WindowsString or PosixString,
depending on the platform. Both use unpinned
ShortByteString for efficiency.
The constructor is only exported via System.OsString.Internal.Types, since dealing with the internals isn't generally recommended, but supported in case you need to write platform specific code.
Instances
| Monoid OsString # | "String-Concatenation" for | ||||
| Semigroup OsString # | |||||
| Generic OsString # | |||||
Defined in System.OsString.Internal.Types Associated Types
| |||||
| Show OsString # | On windows, decodes as UCS-2. On unix prints the raw bytes without decoding. | ||||
| NFData OsString # | |||||
Defined in System.OsString.Internal.Types | |||||
| Eq OsString # | Byte equality of the internal representation. | ||||
| Ord OsString # | Byte ordering of the internal representation. | ||||
Defined in System.OsString.Internal.Types | |||||
| Lift OsString # | |||||
| type Rep OsString # | |||||
Defined in System.OsString.Internal.Types type Rep OsString = D1 ('MetaData "OsString" "System.OsString.Internal.Types" "os-string-2.0.2.1-Hjy1RWYob6R165kcPeCUb" 'True) (C1 ('MetaCons "OsString" 'PrefixI 'True) (S1 ('MetaSel ('Just "getOsString") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedLazy) (Rec0 PlatformString))) | |||||
OsString construction
encodeUtf :: MonadThrow m => String -> m OsString #
Partial unicode friendly encoding.
On windows this encodes as UTF16-LE (strictly), which is a pretty good guess. On unix this encodes as UTF8 (strictly), which is a good guess.
Throws an EncodingException if encoding fails. If the input does not
contain surrogate chars, you can use unsafeEncodeUtf.
unsafeEncodeUtf :: HasCallStack => String -> OsString #
Unsafe unicode friendly encoding.
Like encodeUtf, except it crashes when the input contains
surrogate chars. For sanitized input, this can be useful.
Arguments
| :: TextEncoding | unix text encoding |
| -> TextEncoding | windows text encoding |
| -> String | |
| -> Either EncodingException OsString |
Encode an OsString given the platform specific encodings.
encodeFS :: String -> IO OsString #
Like encodeUtf, except this mimics the behavior of the base library when doing filesystem
operations, which is:
- on unix, uses shady PEP 383 style encoding (based on the current locale, but PEP 383 only works properly on UTF-8 encodings, so good luck)
- on windows does permissive UTF-16 encoding, where coding errors generate Chars in the surrogate range
Looking up the locale requires IO. If you're not worried about calls
to setFileSystemEncoding, then unsafePerformIO may be feasible (make sure
to deeply evaluate the result to catch exceptions).
osstr :: QuasiQuoter #
QuasiQuote an OsString. This accepts Unicode characters
and encodes as UTF-8 on unix and UTF-16 on windows.
If used as pattern, requires turning on the ViewPatterns extension.
pack :: [OsChar] -> OsString #
Pack a list of OsChar to an OsString
Note that using this in conjunction with unsafeFromChar to
convert from [Char] to OsString is probably not what
you want, because it will truncate unicode code points.
OsString deconstruction
decodeUtf :: MonadThrow m => OsString -> m String #
Partial unicode friendly decoding.
On windows this decodes as UTF16-LE (strictly), which is a pretty good guess. On unix this decodes as UTF8 (strictly), which is a good guess. Note that filenames on unix are encoding agnostic char arrays.
Throws a EncodingException if decoding fails.
Arguments
| :: TextEncoding | unix text encoding |
| -> TextEncoding | windows text encoding |
| -> OsString | |
| -> Either EncodingException String |
Decode an OsString with the specified encoding.
The String is forced into memory to catch all exceptions.
decodeFS :: OsString -> IO String #
Like decodeUtf, except this mimics the behavior of the base library when doing filesystem
operations, which is:
- on unix, uses shady PEP 383 style encoding (based on the current locale, but PEP 383 only works properly on UTF-8 encodings, so good luck)
- on windows does permissive UTF-16 encoding, where coding errors generate Chars in the surrogate range
Looking up the locale requires IO. If you're not worried about calls
to setFileSystemEncoding, then unsafePerformIO may be feasible (make sure
to deeply evaluate the result to catch exceptions).
Word types
Newtype representing a code unit.
On Windows, this is restricted to two-octet codepoints Word16,
on POSIX one-octet (Word8).
Instances
| Generic OsChar # | |||||
Defined in System.OsString.Internal.Types Associated Types
| |||||
| Show OsChar # | |||||
| NFData OsChar # | |||||
Defined in System.OsString.Internal.Types | |||||
| Eq OsChar # | Byte equality of the internal representation. | ||||
| Ord OsChar # | Byte ordering of the internal representation. | ||||
| type Rep OsChar # | |||||
Defined in System.OsString.Internal.Types type Rep OsChar = D1 ('MetaData "OsChar" "System.OsString.Internal.Types" "os-string-2.0.2.1-Hjy1RWYob6R165kcPeCUb" 'True) (C1 ('MetaCons "OsChar" 'PrefixI 'True) (S1 ('MetaSel ('Just "getOsChar") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedLazy) (Rec0 PlatformChar))) | |||||
Word construction
unsafeFromChar :: Char -> OsChar #
Truncates on unix to 1 and on Windows to 2 octets.
Word deconstruction
Basic interface
last :: HasCallStack => OsString -> OsChar #
O(1) Extract the last element of a OsString, which must be finite and non-empty. An exception will be thrown in the case of an empty OsString.
This is a partial function, consider using unsnoc instead.
Since: 1.4.200.0
tail :: HasCallStack => OsString -> OsString #
O(n) Extract the elements after the head of a OsString, which must be non-empty. An exception will be thrown in the case of an empty OsString.
This is a partial function, consider using uncons instead.
Since: 1.4.200.0
head :: HasCallStack => OsString -> OsChar #
O(1) Extract the first element of a OsString, which must be non-empty. An exception will be thrown in the case of an empty OsString.
This is a partial function, consider using uncons instead.
Since: 1.4.200.0
init :: HasCallStack => OsString -> OsString #
Transforming OsString
map :: (OsChar -> OsChar) -> OsString -> OsString #
O(n) map f xs is the OsString obtained by applying f to each
element of xs.
Since: 1.4.200.0
reverse :: OsString -> OsString #
O(n) reverse xs efficiently returns the elements of xs in reverse order.
Since: 1.4.200.0
intercalate :: OsString -> [OsString] -> OsString #
O(n) The intercalate function takes a OsString and a list of
OsStrings and concatenates the list after interspersing the first
argument between each element of the list.
Since: 1.4.200.0
Reducing OsStrings (folds)
foldl :: (a -> OsChar -> a) -> a -> OsString -> a #
foldl, applied to a binary operator, a starting value (typically
the left-identity of the operator), and a OsString, reduces the
OsString using the binary operator, from left to right.
Since: 1.4.200.0
foldr :: (OsChar -> a -> a) -> a -> OsString -> a #
foldr, applied to a binary operator, a starting value
(typically the right-identity of the operator), and a OsString,
reduces the OsString using the binary operator, from right to left.
Since: 1.4.200.0
Special folds
Generating and unfolding OsStrings
replicate :: Int -> OsChar -> OsString #
O(n) replicate n x is a OsString of length n with x
the value of every element. The following holds:
replicate w c = unfoldr w (\u -> Just (u,u)) c
Since: 1.4.200.0
unfoldr :: (a -> Maybe (OsChar, a)) -> a -> OsString #
O(n), where n is the length of the result. The unfoldr
function is analogous to the List 'unfoldr'. unfoldr builds a
OsString from a seed value. The function takes the element and
returns Nothing if it is done producing the OsString or returns
Just (a,b), in which case, a is the next byte in the string,
and b is the seed value for further production.
This function is not efficient/safe. It will build a list of [Word8]
and run the generator until it returns Nothing, otherwise recurse infinitely,
then finally create a OsString.
If you know the maximum length, consider using unfoldrN.
Examples:
unfoldr (\x -> if x <= 5 then Just (x, x + 1) else Nothing) 0 == pack [0, 1, 2, 3, 4, 5]
Since: 1.4.200.0
unfoldrN :: Int -> (a -> Maybe (OsChar, a)) -> a -> (OsString, Maybe a) #
O(n) Like unfoldr, unfoldrN builds a OsString from a seed
value. However, the length of the result is limited by the first
argument to unfoldrN. This function is more efficient than unfoldr
when the maximum length of the result is known.
The following equation relates unfoldrN and unfoldr:
fst (unfoldrN n f s) == take n (unfoldr f s)
Since: 1.4.200.0
Substrings
Breaking strings
takeWhileEnd :: (OsChar -> Bool) -> OsString -> OsString #
Returns the longest (possibly empty) suffix of elements satisfying the predicate.
is equivalent to takeWhileEnd p.reverse . takeWhile p . reverse
Since: 1.4.200.0
takeWhile :: (OsChar -> Bool) -> OsString -> OsString #
Similar to takeWhile,
returns the longest (possibly empty) prefix of elements
satisfying the predicate.
Since: 1.4.200.0
dropWhileEnd :: (OsChar -> Bool) -> OsString -> OsString #
Similar to dropWhileEnd,
drops the longest (possibly empty) suffix of elements
satisfying the predicate and returns the remainder.
is equivalent to dropWhileEnd p.reverse . dropWhile p . reverse
Since: 1.4.200.0
dropWhile :: (OsChar -> Bool) -> OsString -> OsString #
Similar to dropWhile,
drops the longest (possibly empty) prefix of elements
satisfying the predicate and returns the remainder.
Since: 1.4.200.0
breakEnd :: (OsChar -> Bool) -> OsString -> (OsString, OsString) #
Returns the longest (possibly empty) suffix of elements which do not satisfy the predicate and the remainder of the string.
breakEnd p is equivalent to and to spanEnd (not . p)(.takeWhileEnd (not . p) &&& dropWhileEnd (not . p))
Since: 1.4.200.0
spanEnd :: (OsChar -> Bool) -> OsString -> (OsString, OsString) #
Returns the longest (possibly empty) suffix of elements satisfying the predicate and the remainder of the string.
spanEnd p is equivalent to and to breakEnd (not . p)(.takeWhileEnd p &&& dropWhileEnd p)
We have
spanEnd (not . isSpace) "x y z" == ("x y ", "z")and
spanEnd (not . isSpace) sbs == let (x, y) = span (not . isSpace) (reverse sbs) in (reverse y, reverse x)
Since: 1.4.200.0
split :: OsChar -> OsString -> [OsString] #
O(n) Break a OsString into pieces separated by the byte
argument, consuming the delimiter. I.e.
split 10 "a\nb\nd\ne" == ["a","b","d","e"] -- fromEnum '\n' == 10 split 97 "aXaXaXa" == ["","X","X","X",""] -- fromEnum 'a' == 97 split 120 "x" == ["",""] -- fromEnum 'x' == 120 split undefined "" == [] -- and not [""]
and
intercalate [c] . split c == id split == splitWith . (==)
Since: 1.4.200.0
splitWith :: (OsChar -> Bool) -> OsString -> [OsString] #
O(n) Splits a OsString 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.
splitWith (==97) "aabbaca" == ["","","bb","c",""] -- fromEnum 'a' == 97 splitWith undefined "" == [] -- and not [""]
Since: 1.4.200.0
stripSuffix :: OsString -> OsString -> Maybe OsString #
O(n) The stripSuffix function takes two OsStrings and returns Just
the remainder of the second iff the first is its suffix, and otherwise
Nothing.
Since: 1.4.200.0
stripPrefix :: OsString -> OsString -> Maybe OsString #
O(n) The stripPrefix function takes two OsStrings and returns Just
the remainder of the second iff the first is its prefix, and otherwise
Nothing.
Since: 1.4.200.0
Predicates
isInfixOf :: OsString -> OsString -> Bool #
Check whether one string is a substring of another.
Since: 1.4.200.0
isPrefixOf :: OsString -> OsString -> Bool #
O(n) The isPrefixOf function takes two OsStrings and returns True
Since: 1.4.200.0
isSuffixOf :: OsString -> OsString -> Bool #
O(n) The isSuffixOf function takes two OsStrings and returns True
iff the first is a suffix of the second.
The following holds:
isSuffixOf x y == reverse x `isPrefixOf` reverse y
Since: 1.4.200.0
Search for arbitrary susbstrings
breakSubstring :: OsString -> OsString -> (OsString, OsString) #
Break a string on a substring, returning a pair of the part of the string prior to the match, and the rest of the string.
The following relationships hold:
break (== c) l == breakSubstring (singleton c) l
For example, to tokenise a string, dropping delimiters:
tokenise x y = h : if null t then [] else tokenise x (drop (length x) t)
where (h,t) = breakSubstring x yTo skip to the first occurrence of a string:
snd (breakSubstring x y)
To take the parts of a string before a delimiter:
fst (breakSubstring x y)
Note that calling `breakSubstring x` does some preprocessing work, so you should avoid unnecessarily duplicating breakSubstring calls with the same pattern.
Since: 1.4.200.0
Searching OsStrings
Searching by equality
filter :: (OsChar -> Bool) -> OsString -> OsString #
O(n) filter, applied to a predicate and a OsString,
returns a OsString containing those characters that satisfy the
predicate.
Since: 1.4.200.0
partition :: (OsChar -> Bool) -> OsString -> (OsString, OsString) #
O(n) The partition function takes a predicate a OsString and returns
the pair of OsStrings with elements which do and do not satisfy the
predicate, respectively; i.e.,
partition p bs == (filter p sbs, filter (not . p) sbs)
Since: 1.4.200.0
Indexing OsStrings
index :: HasCallStack => OsString -> Int -> OsChar #
O(1) OsString index (subscript) operator, starting from 0.
Since: 1.4.200.0
elemIndices :: OsChar -> OsString -> [Int] #
O(n) The elemIndices function extends elemIndex, by returning
the indices of all elements equal to the query element, in ascending order.
Since: 1.4.200.0
count :: OsChar -> OsString -> Int #
count returns the number of times its argument appears in the OsString
Since: 1.4.200.0
findIndices :: (OsChar -> Bool) -> OsString -> [Int] #
O(n) The findIndices function extends findIndex, by returning the
indices of all elements satisfying the predicate, in ascending order.
Since: 1.4.200.0
Coercions
coercionToPlatformTypes :: Either (Coercion OsChar WindowsChar, Coercion OsString WindowsString) (Coercion OsChar PosixChar, Coercion OsString PosixString) #
This is a type-level evidence that OsChar is a newtype wrapper
over WindowsChar or PosixChar and OsString is a newtype wrapper
over WindowsString or PosixString. If you pattern match on
coercionToPlatformTypes, GHC will know that relevant types
are coercible to each other. This helps to avoid CPP in certain scenarios.