-- Hoogle documentation, generated by Haddock
-- See Hoogle, http://www.haskell.org/hoogle/


-- | Unicode 3.2.0 character properties
--   
--   Unicode 3.2.0 character properties
@package unicode-properties
@version 3.2.0.0

module Data.Char.Properties.Decomposition
data DecompositionType
DCCanonical :: DecompositionType
DCFont :: DecompositionType
DCNoBreak :: DecompositionType
DCInitial :: DecompositionType
DCMedial :: DecompositionType
DCFinal :: DecompositionType
DCIsolated :: DecompositionType
DCCircle :: DecompositionType
DCSuper :: DecompositionType
DCSub :: DecompositionType
DCVertical :: DecompositionType
DCWide :: DecompositionType
DCNarrow :: DecompositionType
DCSmall :: DecompositionType
DCSquare :: DecompositionType
DCFraction :: DecompositionType
DCCompat :: DecompositionType
data Decomposition
NoDecomposition :: Decomposition
MkDecomposition :: DecompositionType -> [Char] -> Decomposition
getDecomposition :: Char -> Decomposition
extractDecompositionCanonical :: Decomposition -> Maybe [Char]
decomposeCanonical :: String -> String
extractDecompositionCompatibility :: Decomposition -> Maybe [Char]
decomposeCompatibility :: String -> String

module Data.Char.Properties.Case
toUpperCase :: Char -> Char
toLowerCase :: Char -> Char
toTitleCase :: Char -> Char

module Data.Char.Properties.BidiCategory
data BidiCategory
BidiL :: BidiCategory
BidiLRE :: BidiCategory
BidiLRO :: BidiCategory
BidiR :: BidiCategory
BidiAL :: BidiCategory
BidiRLE :: BidiCategory
BidiRLO :: BidiCategory
BidiPDF :: BidiCategory
BidiEN :: BidiCategory
BidiES :: BidiCategory
BidiET :: BidiCategory
BidiAN :: BidiCategory
BidiCS :: BidiCategory
BidiNSM :: BidiCategory
BidiBN :: BidiCategory
BidiB :: BidiCategory
BidiS :: BidiCategory
BidiWS :: BidiCategory
BidiON :: BidiCategory
getBidiCategory :: Char -> BidiCategory

module Data.Char.Properties.GeneralCategory
data GeneralCategory
GcLu :: GeneralCategory
GcLl :: GeneralCategory
GcLt :: GeneralCategory
GcLm :: GeneralCategory
GcLo :: GeneralCategory
GcMn :: GeneralCategory
GcMc :: GeneralCategory
GcMe :: GeneralCategory
GcNd :: GeneralCategory
GcNl :: GeneralCategory
GcNo :: GeneralCategory
GcZs :: GeneralCategory
GcZl :: GeneralCategory
GcZp :: GeneralCategory
GcPc :: GeneralCategory
GcPd :: GeneralCategory
GcPs :: GeneralCategory
GcPe :: GeneralCategory
GcPi :: GeneralCategory
GcPf :: GeneralCategory
GcPo :: GeneralCategory
GcSm :: GeneralCategory
GcSc :: GeneralCategory
GcSk :: GeneralCategory
GcSo :: GeneralCategory
GcCc :: GeneralCategory
GcCf :: GeneralCategory
GcCs :: GeneralCategory
GcCo :: GeneralCategory
GcCn :: GeneralCategory
getGeneralCategory :: Char -> GeneralCategory
data GCMajorClass
ClLetter :: GCMajorClass
ClMark :: GCMajorClass
ClNumber :: GCMajorClass
ClSeparator :: GCMajorClass
ClPunctuation :: GCMajorClass
ClSymbol :: GCMajorClass
ClOther :: GCMajorClass
gcMajorClass :: GeneralCategory -> GCMajorClass
instance Eq GCMajorClass
instance Show GCMajorClass
instance Show GeneralCategory

module Data.Char.Properties.Misc
getCombiningClass :: Char -> Word8
getDecimalDigit :: Char -> Maybe Word8
getDigit :: Char -> Maybe Word8
getNumber :: Char -> Maybe Rational
isMirrored :: Char -> Bool

-- | Space characters and those format control characters (such as TAB, CR
--   and LF) which should be treated by programming languages as "white
--   space" for the purpose of parsing elements. Note: ZERO WIDTH SPACE and
--   ZERO WIDTH NO-BREAK SPACE are not included, since their functions are
--   restricted to line-break control. Their names are unfortunately
--   misleading in this respect. Note: There are other senses of
--   "whitespace" that encompass a different set of characters.
isWhiteSpace :: Char -> Bool

-- | Those format control characters which have specific functions in the
--   Bidirectional Algorithm.
isBidiControl :: Char -> Bool

-- | Those format control characters which have specific functions for
--   control of cursive joining and ligation.
isJoinControl :: Char -> Bool

-- | Those punctuation characters explicitly called out as dashes in the
--   Unicode Standard, plus compatibility equivalents to those. Most of
--   these have the Pd General Category, but some have the Sm General
--   Category because of their use in mathematics.
isDash :: Char -> Bool

-- | Those dashes used to mark connections between pieces of words, plus
--   the Katakana middle dot. The Katakana middle dot functions like a
--   hyphen, but is shaped like a dot rather than a dash.
isHyphen :: Char -> Bool

-- | Those punctuation characters that function as quotation marks.
isQuotationMark :: Char -> Bool

-- | Those punctuation characters that generally mark the end of textual
--   units.
isTerminalPunctuation :: Char -> Bool

-- | Used in deriving the Math property.
isOtherMath :: Char -> Bool

-- | Characters commonly used for the representation of hexadecimal
--   numbers, plus their compatibility equivalents.
isHexDigit :: Char -> Bool

-- | ASCII characters commonly used for the representation of hexadecimal
--   numbers.
isASCIIHexDigit :: Char -> Bool

-- | Used in deriving the Alphabetic property.
isOtherAlphabetic :: Char -> Bool

-- | Characters considered to be CJKV (Chinese, Japanese, Korean, and
--   Vietnamese) ideographs.
isIdeographic :: Char -> Bool

-- | Characters that linguistically modify the meaning of another character
--   to which they apply. Some diacritics are not combining characters, and
--   some combining characters are not diacritics.
isDiacritic :: Char -> Bool

-- | Characters whose principal function is to extend the value or shape of
--   a preceding alphabetic character. Typical of these are length and
--   iteration marks.
isExtender :: Char -> Bool

-- | Used in deriving the Lowercase property.
isOtherLowercase :: Char -> Bool

-- | Used in deriving the Uppercase property.
isOtherUppercase :: Char -> Bool

-- | Code points that are explicitly defined as illegal for the encoding of
--   characters. See Unicode 3.1 for more information.
isNoncharacterCodePoint :: Char -> Bool

-- | Used in deriving the Grapheme_Extend property.
isOtherGraphemeExtend :: Char -> Bool

-- | Used in determining default grapheme cluster boundaries. For more
--   information, see UTR #29: Text Boundaries (in proposed draft status at
--   publication of Unicode 3.2).
isGraphemeLink :: Char -> Bool

-- | For a machine-readable list of Ideographic Description Sequences. For
--   more information, see Unicode 3.2.
isIDSBinaryOperator :: Char -> Bool

-- | For a machine-readable list of Ideographic Description Sequences. For
--   more information, see Unicode 3.2.
isIDSTrinaryOperator :: Char -> Bool

-- | For a machine-readable list of Ideographic Description Sequences. For
--   more information, see Unicode 3.2.
isRadical :: Char -> Bool

-- | For a machine-readable list of Ideographic Description Sequences. For
--   more information, see Unicode 3.2.
isUnifiedIdeograph :: Char -> Bool

-- | Used in deriving the Default_Ignorable_Code_Point property.
isOtherDefaultIgnorableCodePoint :: Char -> Bool

-- | For a machine-readable list of deprecated characters. No characters
--   will ever be removed from the standard, but the usage of deprecated
--   characters is strongly discouraged. For more information, see Unicode
--   3.2.
isDeprecated :: Char -> Bool

-- | Characters with a "soft dot", like i or j. An accent placed on these
--   characters causes the dot to disappear. An explicit dot above can be
--   added where required, such as in Lithuanian. For more information, see
--   Unicode 3.0, Chapter 7, Diacritics on i and j
isSoftDotted :: Char -> Bool

-- | There are a small number of characters that do not use logical order.
--   These characters require special handling in most processing. For more
--   information, see Unicode 3.2.
isLogicalOrderException :: Char -> Bool

-- | Combining Grapheme Joiner character.
isCGJ :: Char -> Bool

-- | Characters with the Math property. For more information, see Chapter
--   4, Character Properties.
--   
--   Math = Sm + Other_Math.
isMath :: Char -> Bool

-- | Characters with the Alphabetic property. For more information, see
--   Chapter 4, Character Properties.
--   
--   Alphabetic = Lu+Ll+Lt+Lm+Lo+ Other_Alphabetic.
isAlphabetic :: Char -> Bool

-- | Characters with the Lowercase property. For more information, see
--   Chapter 4, Character Properties and UAX #21: Case Mappings.
--   
--   Lowercase = Ll + Other_Lowercase.
isLowercase :: Char -> Bool

-- | Characters with the Uppercase property. For more information, see
--   Chapter 4, Character Properties and UAX #21: Case Mappings.
--   
--   Uppercase = Lu + Other_Uppercase.
isUppercase :: Char -> Bool

-- | Characters that can start an identifier.
--   
--   ID_Start = Lu+Ll+Lt+Lm+Lo+Nl.
isIDStart :: Char -> Bool

-- | Characters that can continue an identifier. See Cf Note.
--   
--   ID_Continue = ID_Start + Mn+Mc+Nd+Pc.
isIDContinue :: Char -> Bool

-- | For programmatic determination of default-ignorable code points. New
--   characters that should be ignored in processing (unless explicitly
--   supported) will be assigned in these ranges, permitting programs to
--   correctly handle the default behavior of such characters when not
--   otherwise supported. For more information, see UTR #29: Text
--   Boundaries (in proposed draft status at release time for Unicode 3.2).
--   
--   Default_Ignorable_Code_Point = Other_Default_Ignorable_Code_Point + Cf
--   + Cc + Cs - White_Space.
isDefaultIgnorableCodePoint :: Char -> Bool

-- | For programmatic determination of grapheme cluster boundaries. For
--   more information, see UTR #29: Text Boundaries (in proposed draft
--   status at publication of Unicode 3.2).
--   
--   Grapheme_Base = [0..10FFFF] - Cc - Cf - Cs - Co - Cn - Zl - Zp -
--   Grapheme_Extend - Grapheme_Link - CGJ.
isGraphemeBase :: Char -> Bool

-- | For programmatic determination of grapheme cluster boundaries. For
--   more information, see UTR #29: Text Boundaries (in proposed draft
--   status at publication of Unicode 3.2).
--   
--   Grapheme_Extend = Me + Mn + Mc + Other_Grapheme_Extend - Grapheme_Link
--   - CGJ.
isGraphemeExtend :: Char -> Bool

-- | Returns true if the general category is Lt.
isTitlecase :: Char -> Bool
isLineBreak :: Char -> Bool

module Data.Char.Properties

-- | This is Unicode version 3.2.0 or later.
data Version_Unicode_AtLeast_3_2_0

-- | This is Unicode version 3.2.0.
data Version_Unicode_Exactly_3_2_0

-- | This is the Unicode version. ([3,2,0])
version_Unicode :: [Int]