CPython.Types.Unicode

Unicode objects

data Unicode

Instances

Concrete Unicode

Methods

concreteType :: Unicode -> Type

Object Unicode

Methods

toObject :: Unicode -> SomeObject

fromForeignPtr :: ForeignPtr Unicode -> Unicode

type Encoding = Text

data ErrorHandling

Constructors

Strict

Replace

Ignore

Instances

Eq ErrorHandling

Methods

(==) :: ErrorHandling -> ErrorHandling -> Bool

(/=) :: ErrorHandling -> ErrorHandling -> Bool

Show ErrorHandling

Methods

showsPrec :: Int -> ErrorHandling -> ShowS

show :: ErrorHandling -> String

showList :: [ErrorHandling] -> ShowS

unicodeType :: Type

toUnicode :: Text -> IO Unicode

fromUnicode :: Unicode -> IO Text

length :: Unicode -> IO Integer

fromEncodedObject :: Object obj => obj -> Encoding -> ErrorHandling -> IO Unicode

Coerce an encoded object obj to an Unicode object.

Bytes and other char buffer compatible objects are decoded according to the given encoding and error handling mode.

All other objects, including Unicode objects, cause a TypeError to be thrown.

fromObject :: Object obj => obj -> IO Unicode

Shortcut for fromEncodedObject "utf-8" Strict

encode :: Unicode -> Encoding -> ErrorHandling -> IO Bytes

Encode a Unicode object and return the result as Bytes object. The encoding and error mode have the same meaning as the parameters of the the str.encode() method. The codec to be used is looked up using the Python codec registry.

decode :: Bytes -> Encoding -> ErrorHandling -> IO Unicode

Create a Unicode object by decoding a Bytes object. The encoding and error mode have the same meaning as the parameters of the the str.encode() method. The codec to be used is looked up using the Python codec registry.

Methods and slot functions

append :: Unicode -> Unicode -> IO Unicode

split

Arguments

:: Unicode

-> Maybe Unicode

Separator

-> Maybe Integer

Maximum splits

-> IO List

Split a string giving a List of Unicode objects. If the separator is Nothing, splitting will be done at all whitespace substrings. Otherwise, splits occur at the given separator. Separators are not included in the resulting list.

splitLines :: Unicode -> Bool -> IO List

Split a Unicode string at line breaks, returning a list of Unicode strings. CRLF is considered to be one line break. If the second parameter is False, the line break characters are not included in the resulting strings.

translate :: Object table => Unicode -> table -> ErrorHandling -> IO Unicode

Translate a string by applying a character mapping table to it.

The mapping table must map Unicode ordinal integers to Unicode ordinal integers or None (causing deletion of the character).

Mapping tables need only provide the getitem() interface; dictionaries and sequences work well. Unmapped character ordinals (ones which cause a LookupError) are left untouched and are copied as-is.

The error mode has the usual meaning for codecs.

join :: Sequence seq => Unicode -> seq -> IO Unicode

Join a sequence of strings using the given separator.

data MatchDirection

Constructors

Prefix

Suffix

Instances

Eq MatchDirection

Methods

(==) :: MatchDirection -> MatchDirection -> Bool

(/=) :: MatchDirection -> MatchDirection -> Bool

Show MatchDirection

Methods

showsPrec :: Int -> MatchDirection -> ShowS

show :: MatchDirection -> String

showList :: [MatchDirection] -> ShowS

tailMatch

Arguments

:: Unicode

String

-> Unicode

Substring

-> Integer

Start

-> Integer

End

-> MatchDirection

-> IO Bool

Return True if the substring matches string*[*start:end] at the given tail end (either a Prefix or Suffix match), False otherwise.

data FindDirection

Constructors

Forwards

Backwards

Instances

Eq FindDirection

Methods

(==) :: FindDirection -> FindDirection -> Bool

(/=) :: FindDirection -> FindDirection -> Bool

Show FindDirection

Methods

showsPrec :: Int -> FindDirection -> ShowS

show :: FindDirection -> String

showList :: [FindDirection] -> ShowS

find

Arguments

:: Unicode

String

-> Unicode

Substring

-> Integer

Start

-> Integer

End

-> FindDirection

-> IO (Maybe Integer)

Return the first position of the substring in string*[*start:end] using the given direction. The return value is the index of the first match; a value of Nothing indicates that no match was found.

count

Arguments

:: Unicode

String

-> Unicode

Substring

-> Integer

Start

-> Integer

End

-> IO Integer

Return the number of non-overlapping occurrences of the substring in string[start:end].

replace

Arguments

:: Unicode

String

-> Unicode

Substring

-> Unicode

Replacement

-> Maybe Integer

Maximum count

-> IO Unicode

Replace occurrences of the substring with a given replacement. If the maximum count is Nothing, replace all occurences.

format :: Unicode -> Tuple -> IO Unicode

Return a new Unicode object from the given format and args; this is analogous to format % args.

contains :: Object element => Unicode -> element -> IO Bool

Check whether element is contained in a string.

element has to coerce to a one element string.