Haskus.Format.Text.Unicode.UCDParser

Unicode character database parsers

Documentation

parseCodePointValue :: Parser CodePoint

Parse a code-point value without the "U+" prefix

>>> runParser parseCodePointValue "" "1234"
Right U+1234

parseCodePoint :: Parser CodePoint

Parse a code-point value with the "U+" prefix

>>> runParser parseCodePoint "" "U+1234"
Right U+1234

parseCodePointRange :: Parser CodePointRange

Parse a range of code-points separated by ".."

>>> runParser parseCodePointRange "" "1234..5678"
Right U+1234..U+5678

parseCodePointValueOrRange :: Parser (Either CodePoint CodePointRange)

Parse either a range of code-points or a single code-point

>>> runParser parseCodePointValueOrRange "" "1234..5678"
Right (Right U+1234..U+5678)

>>> runParser parseCodePointValueOrRange "" "1234"
Right (Left U+1234)

parseCommentLine :: Parser String

Parse a comment line ("^# ...eol")

>>> runParser parseCommentLine "" "# comment"
Right " comment"

skipCommentLines :: Parser a -> Parser [a]

Parse valid line with the given parser, skipping comment lines

parseFile :: Lift a => FilePath -> Parser a -> ExpQ

Parse a file and lift the result into a TH expression

stripComments :: Parser [String]

Strip comments

File specific

parseBlocks :: Parser [(CodePointRange, String)]

Parse Blocks.txt file

parseDerivedName :: Parser [(Either CodePoint CodePointRange, String)]

Parse DerivedName.txt file