Fix startsVarSym and refactor operator predicates (fixes #4239)

startsVarSym used isSymbol which does not recognize valid operators
beginning with OtherPunctuation generalCategory (e. g. (·)).
Move it to ghc-boot-th for reducing duplication.

This patch fixes template-haskell pretty printer, which is used by
-ddump-minimal-imports.

Reviewers: austin, bgamari

Reviewed By: bgamari

Subscribers: thomie

Differential Revision: https://phabricator.haskell.org/D2480

GHC Trac Issues: #4239

2 files changed, 23 insertions, 8 deletions

diff --git a/libraries/ghc-boot-th/GHC/Lexeme.hs b/libraries/ghc-boot-th/GHC/Lexeme.hs
index 677c9a65e6..2ecee61ea6 100644
--- a/libraries/ghc-boot-th/GHC/Lexeme.hs
+++ b/libraries/ghc-boot-th/GHC/Lexeme.hs
@@ -11,14 +11,31 @@
 module GHC.Lexeme (
           -- * Lexical characteristics of Haskell names
         startsVarSym, startsVarId, startsConSym, startsConId,
-        startsVarSymASCII, isVarSymChar
+        startsVarSymASCII, isVarSymChar, okSymChar
   ) where
 
 import Data.Char
 
+-- | Is this character acceptable in a symbol (after the first char)?
+-- See alexGetByte in Lexer.x
+okSymChar :: Char -> Bool
+okSymChar c
+  | c `elem` "(),;[]`{}_\"'"
+  = False
+  | otherwise
+  = case generalCategory c of
+      ConnectorPunctuation -> True
+      DashPunctuation      -> True
+      OtherPunctuation     -> True
+      MathSymbol           -> True
+      CurrencySymbol       -> True
+      ModifierSymbol       -> True
+      OtherSymbol          -> True
+      _                    -> False
+
 startsVarSym, startsVarId, startsConSym, startsConId :: Char -> Bool
-startsVarSym c = startsVarSymASCII c || (ord c > 0x7f && isSymbol c)  -- Infix Ids
-startsConSym c = c == ':'               -- Infix data constructors
+startsVarSym c = okSymChar c && c /= ':' -- Infix Ids
+startsConSym c = c == ':'                -- Infix data constructors
 startsVarId c  = c == '_' || case generalCategory c of  -- Ordinary Ids
   LowercaseLetter -> True
   OtherLetter     -> True   -- See #1103
diff --git a/libraries/template-haskell/Language/Haskell/TH/Ppr.hs b/libraries/template-haskell/Language/Haskell/TH/Ppr.hs
index bdd4dd388a..0462a8da25 100644
--- a/libraries/template-haskell/Language/Haskell/TH/Ppr.hs
+++ b/libraries/template-haskell/Language/Haskell/TH/Ppr.hs
@@ -10,8 +10,9 @@ import Text.PrettyPrint (render)
 import Language.Haskell.TH.PprLib
 import Language.Haskell.TH.Syntax
 import Data.Word ( Word8 )
-import Data.Char ( toLower, chr, ord, isSymbol )
+import Data.Char ( toLower, chr)
 import GHC.Show  ( showMultiLineString )
+import GHC.Lexeme( startsVarSym )
 import Data.Ratio ( numerator, denominator )
 
 nestDepth :: Int
@@ -114,12 +115,9 @@ isSymOcc :: Name -> Bool
 isSymOcc n
   = case nameBase n of
       []    -> True  -- Empty name; weird
-      (c:_) -> isSymbolASCII c || (ord c > 0x7f && isSymbol c)
+      (c:_) -> startsVarSym c
                    -- c.f. OccName.startsVarSym in GHC itself
 
-isSymbolASCII :: Char -> Bool
-isSymbolASCII c = c `elem` "!#$%&*+./<=>?@\\^|~-"
-
 pprInfixExp :: Exp -> Doc
 pprInfixExp (VarE v) = pprName' Infix v
 pprInfixExp (ConE v) = pprName' Infix v