Move GeneralCategory et al to GHC.Unicode

This allows these to be used from Text.Read.Lex import cycles.

Reviewed By: thomie, austin

Differential Revision: https://phabricator.haskell.org/D1121

GHC Trac Issues: #10444

1 files changed, 1 insertions, 208 deletions

diff --git a/libraries/base/Data/Char.hs b/libraries/base/Data/Char.hs
index e4e7fbfcb8..c8dd9331c6 100644
--- a/libraries/base/Data/Char.hs
+++ b/libraries/base/Data/Char.hs
@@ -53,14 +53,12 @@ module Data.Char
     ) where
 
 import GHC.Base
-import GHC.Arr (Ix)
 import GHC.Char
 import GHC.Real (fromIntegral)
 import GHC.Show
-import GHC.Read (Read, readLitChar, lexLitChar)
+import GHC.Read (readLitChar, lexLitChar)
 import GHC.Unicode
 import GHC.Num
-import GHC.Enum
 
 -- $setup
 -- Allow the use of Prelude in doctests.
@@ -105,121 +103,6 @@ digitToInt c
     hexl = ord c - ord 'a'
     hexu = ord c - ord 'A'
 
--- | Unicode General Categories (column 2 of the UnicodeData table) in
--- the order they are listed in the Unicode standard (the Unicode
--- Character Database, in particular).
---
--- ==== __Examples__
---
--- Basic usage:
---
--- >>> :t OtherLetter
--- OtherLetter :: GeneralCategory
---
--- 'Eq' instance:
---
--- >>> UppercaseLetter == UppercaseLetter
--- True
--- >>> UppercaseLetter == LowercaseLetter
--- False
---
--- 'Ord' instance:
---
--- >>> NonSpacingMark <= MathSymbol
--- True
---
--- 'Enum' instance:
---
--- >>> enumFromTo ModifierLetter SpacingCombiningMark
--- [ModifierLetter,OtherLetter,NonSpacingMark,SpacingCombiningMark]
---
--- 'Read' instance:
---
--- >>> read "DashPunctuation" :: GeneralCategory
--- DashPunctuation
--- >>> read "17" :: GeneralCategory
--- *** Exception: Prelude.read: no parse
---
--- 'Show' instance:
---
--- >>> show EnclosingMark
--- "EnclosingMark"
---
--- 'Bounded' instance:
---
--- >>> minBound :: GeneralCategory
--- UppercaseLetter
--- >>> maxBound :: GeneralCategory
--- NotAssigned
---
--- 'Ix' instance:
---
---  >>> import Data.Ix ( index )
---  >>> index (OtherLetter,Control) FinalQuote
---  12
---  >>> index (OtherLetter,Control) Format
---  *** Exception: Error in array index
---
-data GeneralCategory
-        = UppercaseLetter       -- ^ Lu: Letter, Uppercase
-        | LowercaseLetter       -- ^ Ll: Letter, Lowercase
-        | TitlecaseLetter       -- ^ Lt: Letter, Titlecase
-        | ModifierLetter        -- ^ Lm: Letter, Modifier
-        | OtherLetter           -- ^ Lo: Letter, Other
-        | NonSpacingMark        -- ^ Mn: Mark, Non-Spacing
-        | SpacingCombiningMark  -- ^ Mc: Mark, Spacing Combining
-        | EnclosingMark         -- ^ Me: Mark, Enclosing
-        | DecimalNumber         -- ^ Nd: Number, Decimal
-        | LetterNumber          -- ^ Nl: Number, Letter
-        | OtherNumber           -- ^ No: Number, Other
-        | ConnectorPunctuation  -- ^ Pc: Punctuation, Connector
-        | DashPunctuation       -- ^ Pd: Punctuation, Dash
-        | OpenPunctuation       -- ^ Ps: Punctuation, Open
-        | ClosePunctuation      -- ^ Pe: Punctuation, Close
-        | InitialQuote          -- ^ Pi: Punctuation, Initial quote
-        | FinalQuote            -- ^ Pf: Punctuation, Final quote
-        | OtherPunctuation      -- ^ Po: Punctuation, Other
-        | MathSymbol            -- ^ Sm: Symbol, Math
-        | CurrencySymbol        -- ^ Sc: Symbol, Currency
-        | ModifierSymbol        -- ^ Sk: Symbol, Modifier
-        | OtherSymbol           -- ^ So: Symbol, Other
-        | Space                 -- ^ Zs: Separator, Space
-        | LineSeparator         -- ^ Zl: Separator, Line
-        | ParagraphSeparator    -- ^ Zp: Separator, Paragraph
-        | Control               -- ^ Cc: Other, Control
-        | Format                -- ^ Cf: Other, Format
-        | Surrogate             -- ^ Cs: Other, Surrogate
-        | PrivateUse            -- ^ Co: Other, Private Use
-        | NotAssigned           -- ^ Cn: Other, Not Assigned
-        deriving (Eq, Ord, Enum, Read, Show, Bounded, Ix)
-
--- | The Unicode general category of the character. This relies on the
--- 'Enum' instance of 'GeneralCategory', which must remain in the
--- same order as the categories are presented in the Unicode
--- standard.
---
--- ==== __Examples__
---
--- Basic usage:
---
--- >>> generalCategory 'a'
--- LowercaseLetter
--- >>> generalCategory 'A'
--- UppercaseLetter
--- >>> generalCategory '0'
--- DecimalNumber
--- >>> generalCategory '%'
--- OtherPunctuation
--- >>> generalCategory '♥'
--- OtherSymbol
--- >>> generalCategory '\31'
--- Control
--- >>> generalCategory ' '
--- Space
---
-generalCategory :: Char -> GeneralCategory
-generalCategory c = toEnum $ fromIntegral $ wgencat $ fromIntegral $ ord c
-
 -- derived character classifiers
 
 -- | Selects alphabetic Unicode characters (lower-case, upper-case and
@@ -360,96 +243,6 @@ isNumber c = case generalCategory c of
         OtherNumber             -> True
         _                       -> False
 
--- | Selects Unicode punctuation characters, including various kinds
--- of connectors, brackets and quotes.
---
--- This function returns 'True' if its argument has one of the
--- following 'GeneralCategory's, or 'False' otherwise:
---
--- * 'ConnectorPunctuation'
--- * 'DashPunctuation'
--- * 'OpenPunctuation'
--- * 'ClosePunctuation'
--- * 'InitialQuote'
--- * 'FinalQuote'
--- * 'OtherPunctuation'
---
--- These classes are defined in the
--- <http://www.unicode.org/reports/tr44/tr44-14.html#GC_Values_Table Unicode Character Database>,
--- part of the Unicode standard. The same document defines what is
--- and is not a \"Punctuation\".
---
--- ==== __Examples__
---
--- Basic usage:
---
--- >>> isPunctuation 'a'
--- False
--- >>> isPunctuation '7'
--- False
--- >>> isPunctuation '♥'
--- False
--- >>> isPunctuation '"'
--- True
--- >>> isPunctuation '?'
--- True
--- >>> isPunctuation '—'
--- True
---
-isPunctuation :: Char -> Bool
-isPunctuation c = case generalCategory c of
-        ConnectorPunctuation    -> True
-        DashPunctuation         -> True
-        OpenPunctuation         -> True
-        ClosePunctuation        -> True
-        InitialQuote            -> True
-        FinalQuote              -> True
-        OtherPunctuation        -> True
-        _                       -> False
-
--- | Selects Unicode symbol characters, including mathematical and
--- currency symbols.
---
--- This function returns 'True' if its argument has one of the
--- following 'GeneralCategory's, or 'False' otherwise:
---
--- * 'MathSymbol'
--- * 'CurrencySymbol'
--- * 'ModifierSymbol'
--- * 'OtherSymbol'
---
--- These classes are defined in the
--- <http://www.unicode.org/reports/tr44/tr44-14.html#GC_Values_Table Unicode Character Database>,
--- part of the Unicode standard. The same document defines what is
--- and is not a \"Symbol\".
---
--- ==== __Examples__
---
--- Basic usage:
---
--- >>> isSymbol 'a'
--- False
--- >>> isSymbol '6'
--- False
--- >>> isSymbol '='
--- True
---
--- The definition of \"math symbol\" may be a little
--- counter-intuitive depending on one's background:
---
--- >>> isSymbol '+'
--- True
--- >>> isSymbol '-'
--- False
---
-isSymbol :: Char -> Bool
-isSymbol c = case generalCategory c of
-        MathSymbol              -> True
-        CurrencySymbol          -> True
-        ModifierSymbol          -> True
-        OtherSymbol             -> True
-        _                       -> False
-
 -- | Selects Unicode space and separator characters.
 --
 -- This function returns 'True' if its argument has one of the