| Copyright | © 2015–2017 Megaparsec contributors © 2007 Paolo Martini © 1999–2001 Daan Leijen |
|---|---|
| License | FreeBSD |
| Maintainer | Mark Karpov <markkarpov92@gmail.com> |
| Stability | experimental |
| Portability | non-portable |
| Safe Haskell | None |
| Language | Haskell2010 |
Text.Megaparsec.Char
Description
Commonly used character parsers.
- newline :: (MonadParsec e s m, Token s ~ Char) => m Char
- crlf :: (MonadParsec e s m, Token s ~ Char) => m String
- eol :: (MonadParsec e s m, Token s ~ Char) => m String
- tab :: (MonadParsec e s m, Token s ~ Char) => m Char
- space :: (MonadParsec e s m, Token s ~ Char) => m ()
- controlChar :: (MonadParsec e s m, Token s ~ Char) => m Char
- spaceChar :: (MonadParsec e s m, Token s ~ Char) => m Char
- upperChar :: (MonadParsec e s m, Token s ~ Char) => m Char
- lowerChar :: (MonadParsec e s m, Token s ~ Char) => m Char
- letterChar :: (MonadParsec e s m, Token s ~ Char) => m Char
- alphaNumChar :: (MonadParsec e s m, Token s ~ Char) => m Char
- printChar :: (MonadParsec e s m, Token s ~ Char) => m Char
- digitChar :: (MonadParsec e s m, Token s ~ Char) => m Char
- octDigitChar :: (MonadParsec e s m, Token s ~ Char) => m Char
- hexDigitChar :: (MonadParsec e s m, Token s ~ Char) => m Char
- markChar :: (MonadParsec e s m, Token s ~ Char) => m Char
- numberChar :: (MonadParsec e s m, Token s ~ Char) => m Char
- punctuationChar :: (MonadParsec e s m, Token s ~ Char) => m Char
- symbolChar :: (MonadParsec e s m, Token s ~ Char) => m Char
- separatorChar :: (MonadParsec e s m, Token s ~ Char) => m Char
- asciiChar :: (MonadParsec e s m, Token s ~ Char) => m Char
- latin1Char :: (MonadParsec e s m, Token s ~ Char) => m Char
- charCategory :: (MonadParsec e s m, Token s ~ Char) => GeneralCategory -> m Char
- categoryName :: GeneralCategory -> String
- char :: (MonadParsec e s m, Token s ~ Char) => Char -> m Char
- char' :: (MonadParsec e s m, Token s ~ Char) => Char -> m Char
- anyChar :: (MonadParsec e s m, Token s ~ Char) => m Char
- oneOf :: (Foldable f, MonadParsec e s m, Token s ~ Char) => f Char -> m Char
- oneOf' :: (Foldable f, MonadParsec e s m, Token s ~ Char) => f Char -> m Char
- noneOf :: (Foldable f, MonadParsec e s m, Token s ~ Char) => f Char -> m Char
- noneOf' :: (Foldable f, MonadParsec e s m, Token s ~ Char) => f Char -> m Char
- satisfy :: (MonadParsec e s m, Token s ~ Char) => (Char -> Bool) -> m Char
- string :: (MonadParsec e s m, Token s ~ Char) => String -> m String
- string' :: (MonadParsec e s m, Token s ~ Char) => String -> m String
Simple parsers
crlf :: (MonadParsec e s m, Token s ~ Char) => m String #
Parse a carriage return character followed by a newline character. Return the sequence of characters parsed.
space :: (MonadParsec e s m, Token s ~ Char) => m () #
Categories of characters
controlChar :: (MonadParsec e s m, Token s ~ Char) => m Char #
Parse a control character (a non-printing character of the Latin-1 subset of Unicode).
spaceChar :: (MonadParsec e s m, Token s ~ Char) => m Char #
Parse a Unicode space character, and the control characters: tab, newline, carriage return, form feed, and vertical tab.
upperChar :: (MonadParsec e s m, Token s ~ Char) => m Char #
Parse an upper-case or title-case alphabetic Unicode character. Title case is used by a small number of letter ligatures like the single-character form of Lj.
lowerChar :: (MonadParsec e s m, Token s ~ Char) => m Char #
Parse a lower-case alphabetic Unicode character.
letterChar :: (MonadParsec e s m, Token s ~ Char) => m Char #
Parse an alphabetic Unicode character: lower-case, upper-case, or title-case letter, or a letter of case-less scripts/modifier letter.
alphaNumChar :: (MonadParsec e s m, Token s ~ Char) => m Char #
Parse an alphabetic or numeric digit Unicode characters.
Note that the numeric digits outside the ASCII range are parsed by this
parser but not by digitChar. Such digits may be part of identifiers but
are not used by the printer and reader to represent numbers.
printChar :: (MonadParsec e s m, Token s ~ Char) => m Char #
Parse a printable Unicode character: letter, number, mark, punctuation, symbol or space.
digitChar :: (MonadParsec e s m, Token s ~ Char) => m Char #
Parse an ASCII digit, i.e between “0” and “9”.
octDigitChar :: (MonadParsec e s m, Token s ~ Char) => m Char #
Parse an octal digit, i.e. between “0” and “7”.
hexDigitChar :: (MonadParsec e s m, Token s ~ Char) => m Char #
Parse a hexadecimal digit, i.e. between “0” and “9”, or “a” and “f”, or “A” and “F”.
markChar :: (MonadParsec e s m, Token s ~ Char) => m Char #
Parse a Unicode mark character (accents and the like), which combines with preceding characters.
numberChar :: (MonadParsec e s m, Token s ~ Char) => m Char #
Parse a Unicode numeric character, including digits from various scripts, Roman numerals, etc.
punctuationChar :: (MonadParsec e s m, Token s ~ Char) => m Char #
Parse a Unicode punctuation character, including various kinds of connectors, brackets and quotes.
symbolChar :: (MonadParsec e s m, Token s ~ Char) => m Char #
Parse a Unicode symbol characters, including mathematical and currency symbols.
separatorChar :: (MonadParsec e s m, Token s ~ Char) => m Char #
Parse a Unicode space and separator characters.
asciiChar :: (MonadParsec e s m, Token s ~ Char) => m Char #
Parse a character from the first 128 characters of the Unicode character set, corresponding to the ASCII character set.
latin1Char :: (MonadParsec e s m, Token s ~ Char) => m Char #
Parse a character from the first 256 characters of the Unicode character set, corresponding to the ISO 8859-1 (Latin-1) character set.
charCategory :: (MonadParsec e s m, Token s ~ Char) => GeneralCategory -> m Char #
charCategory cat parses character in Unicode General Category cat,
see GeneralCategory.
categoryName :: GeneralCategory -> String #
Return the human-readable name of Unicode General Category.
More general parsers
char :: (MonadParsec e s m, Token s ~ Char) => Char -> m Char #
char c parses a single character c.
semicolon = char ';'
char' :: (MonadParsec e s m, Token s ~ Char) => Char -> m Char #
The same as char but case-insensitive. This parser returns the
actually parsed character preserving its case.
>>>parseTest (char' 'e') "E"'E'>>>parseTest (char' 'e') "G"1:1: unexpected 'G' expecting 'E' or 'e'
anyChar :: (MonadParsec e s m, Token s ~ Char) => m Char #
This parser succeeds for any character. Returns the parsed character.
oneOf :: (Foldable f, MonadParsec e s m, Token s ~ Char) => f Char -> m Char #
oneOf cs succeeds if the current character is in the supplied
collection of characters cs. Returns the parsed character. Note that
this parser cannot automatically generate the “expected” component of
error message, so usually you should label it manually with label or
(<?>).
See also: satisfy.
digit = oneOf ['0'..'9'] <?> "digit"
oneOf' :: (Foldable f, MonadParsec e s m, Token s ~ Char) => f Char -> m Char #
The same as oneOf, but case-insensitive. Returns the parsed character
preserving its case.
vowel = oneOf' "aeiou" <?> "vowel"
noneOf :: (Foldable f, MonadParsec e s m, Token s ~ Char) => f Char -> m Char #
As the dual of oneOf, noneOf cs succeeds if the current character
not in the supplied list of characters cs. Returns the parsed
character.
noneOf' :: (Foldable f, MonadParsec e s m, Token s ~ Char) => f Char -> m Char #
The same as noneOf, but case-insensitive.
consonant = noneOf' "aeiou" <?> "consonant"
satisfy :: (MonadParsec e s m, Token s ~ Char) => (Char -> Bool) -> m Char #
The parser satisfy f succeeds for any character for which the
supplied function f returns True. Returns the character that is
actually parsed.
digitChar = satisfy isDigit <?> "digit" oneOf cs = satisfy (`elem` cs)