Remove special handling for character types of characters >= 128, <= 255

Many of the character types were wrong. Now the asc* names really do mean
ASCII, rather than latin-1.

compiler/parser/Ctype.lhs

@@ -219,133 +219,5 @@ charType c = case c of
    '\125' -> cAny                      -- }
    '\126' -> cAny + cSymbol            -- ~
    '\127' -> 0                         -- \177
-   '\128' -> 0                         -- \200
-   '\129' -> 0                         -- \201
-   '\130' -> 0                         -- \202
-   '\131' -> 0                         -- \203
-   '\132' -> 0                         -- \204
-   '\133' -> 0                         -- \205
-   '\134' -> 0                         -- \206
-   '\135' -> 0                         -- \207
-   '\136' -> 0                         -- \210
-   '\137' -> 0                         -- \211
-   '\138' -> 0                         -- \212
-   '\139' -> 0                         -- \213
-   '\140' -> 0                         -- \214
-   '\141' -> 0                         -- \215
-   '\142' -> 0                         -- \216
-   '\143' -> 0                         -- \217
-   '\144' -> 0                         -- \220
-   '\145' -> 0                         -- \221
-   '\146' -> 0                         -- \222
-   '\147' -> 0                         -- \223
-   '\148' -> 0                         -- \224
-   '\149' -> 0                         -- \225
-   '\150' -> 0                         -- \226
-   '\151' -> 0                         -- \227
-   '\152' -> 0                         -- \230
-   '\153' -> 0                         -- \231
-   '\154' -> 0                         -- \232
-   '\155' -> 0                         -- \233
-   '\156' -> 0                         -- \234
-   '\157' -> 0                         -- \235
-   '\158' -> 0                         -- \236
-   '\159' -> 0                         -- \237
-   '\160' -> cSpace                    --
-   '\161' -> cAny + cSymbol            -- ¡
-   '\162' -> cAny + cSymbol            -- ¢
-   '\163' -> cAny + cSymbol            -- £
-   '\164' -> cAny + cSymbol            -- ¤
-   '\165' -> cAny + cSymbol            -- ¥
-   '\166' -> cAny + cSymbol            -- ¦
-   '\167' -> cAny + cSymbol            -- §
-   '\168' -> cAny + cSymbol            -- ¨
-   '\169' -> cAny + cSymbol            -- ©
-   '\170' -> cAny + cSymbol            -- ª
-   '\171' -> cAny + cSymbol            -- «
-   '\172' -> cAny + cSymbol            -- ¬
-   '\173' -> cAny + cSymbol            -- ­
-   '\174' -> cAny + cSymbol            -- ®
-   '\175' -> cAny + cSymbol            -- ¯
-   '\176' -> cAny + cSymbol            -- °
-   '\177' -> cAny + cSymbol            -- ±
-   '\178' -> cAny + cSymbol            -- ²
-   '\179' -> cAny + cSymbol            -- ³
-   '\180' -> cAny + cSymbol            -- ´
-   '\181' -> cAny + cSymbol            -- µ
-   '\182' -> cAny + cSymbol            -- ¶
-   '\183' -> cAny + cSymbol            -- ·
-   '\184' -> cAny + cSymbol            -- ¸
-   '\185' -> cAny + cSymbol            -- ¹
-   '\186' -> cAny + cSymbol            -- º
-   '\187' -> cAny + cSymbol            -- »
-   '\188' -> cAny + cSymbol            -- ¼
-   '\189' -> cAny + cSymbol            -- ½
-   '\190' -> cAny + cSymbol            -- ¾
-   '\191' -> cAny + cSymbol            -- ¿
-   '\192' -> cAny + cIdent  + cUpper   -- À
-   '\193' -> cAny + cIdent  + cUpper   -- Á
-   '\194' -> cAny + cIdent  + cUpper   -- Â
-   '\195' -> cAny + cIdent  + cUpper   -- Ã
-   '\196' -> cAny + cIdent  + cUpper   -- Ä
-   '\197' -> cAny + cIdent  + cUpper   -- Å
-   '\198' -> cAny + cIdent  + cUpper   -- Æ
-   '\199' -> cAny + cIdent  + cUpper   -- Ç
-   '\200' -> cAny + cIdent  + cUpper   -- È
-   '\201' -> cAny + cIdent  + cUpper   -- É
-   '\202' -> cAny + cIdent  + cUpper   -- Ê
-   '\203' -> cAny + cIdent  + cUpper   -- Ë
-   '\204' -> cAny + cIdent  + cUpper   -- Ì
-   '\205' -> cAny + cIdent  + cUpper   -- Í
-   '\206' -> cAny + cIdent  + cUpper   -- Î
-   '\207' -> cAny + cIdent  + cUpper   -- Ï
-   '\208' -> cAny + cIdent  + cUpper   -- Ð
-   '\209' -> cAny + cIdent  + cUpper   -- Ñ
-   '\210' -> cAny + cIdent  + cUpper   -- Ò
-   '\211' -> cAny + cIdent  + cUpper   -- Ó
-   '\212' -> cAny + cIdent  + cUpper   -- Ô
-   '\213' -> cAny + cIdent  + cUpper   -- Õ
-   '\214' -> cAny + cIdent  + cUpper   -- Ö
-   '\215' -> cAny + cSymbol + cLower   -- ×
-   '\216' -> cAny + cIdent  + cUpper   -- Ø
-   '\217' -> cAny + cIdent  + cUpper   -- Ù
-   '\218' -> cAny + cIdent  + cUpper   -- Ú
-   '\219' -> cAny + cIdent  + cUpper   -- Û
-   '\220' -> cAny + cIdent  + cUpper   -- Ü
-   '\221' -> cAny + cIdent  + cUpper   -- Ý
-   '\222' -> cAny + cIdent  + cUpper   -- Þ
-   '\223' -> cAny + cIdent             -- ß
-   '\224' -> cAny + cIdent  + cLower   -- à
-   '\225' -> cAny + cIdent  + cLower   -- á
-   '\226' -> cAny + cIdent  + cLower   -- â
-   '\227' -> cAny + cIdent  + cLower   -- ã
-   '\228' -> cAny + cIdent  + cLower   -- ä
-   '\229' -> cAny + cIdent  + cLower   -- å
-   '\230' -> cAny + cIdent  + cLower   -- æ
-   '\231' -> cAny + cIdent  + cLower   -- ç
-   '\232' -> cAny + cIdent  + cLower   -- è
-   '\233' -> cAny + cIdent  + cLower   -- é
-   '\234' -> cAny + cIdent  + cLower   -- ê
-   '\235' -> cAny + cIdent  + cLower   -- ë
-   '\236' -> cAny + cIdent  + cLower   -- ì
-   '\237' -> cAny + cIdent  + cLower   -- í
-   '\238' -> cAny + cIdent  + cLower   -- î
-   '\239' -> cAny + cIdent  + cLower   -- ï
-   '\240' -> cAny + cIdent  + cLower   -- ð
-   '\241' -> cAny + cIdent  + cLower   -- ñ
-   '\242' -> cAny + cIdent  + cLower   -- ò
-   '\243' -> cAny + cIdent  + cLower   -- ó
-   '\244' -> cAny + cIdent  + cLower   -- ô
-   '\245' -> cAny + cIdent  + cLower   -- õ
-   '\246' -> cAny + cIdent  + cLower   -- ö
-   '\247' -> cAny + cSymbol            -- ÷
-   '\248' -> cAny + cIdent             -- ø
-   '\249' -> cAny + cIdent  + cLower   -- ù
-   '\250' -> cAny + cIdent  + cLower   -- ú
-   '\251' -> cAny + cIdent  + cLower   -- û
-   '\252' -> cAny + cIdent  + cLower   -- ü
-   '\253' -> cAny + cIdent  + cLower   -- ý
-   '\254' -> cAny + cIdent  + cLower   -- þ
-   '\255' -> cAny + cIdent  + cLower   -- ÿ
    _ -> panic ("charType: " ++ show c)
 \end{code}

compiler/parser/Lexer.x

@@ -68,7 +68,7 @@ import Compat.Unicode	( GeneralCategory(..), generalCategory, isPrint, isUpper )
 }
 
 $unispace    = \x05 -- Trick Alex into handling Unicode. See alexGetChar.
-$whitechar   = [\ \n\r\f\v\xa0 $unispace]
+$whitechar   = [\ \n\r\f\v $unispace]
 $white_no_nl = $whitechar # \n
 $tab         = \t
 
@@ -78,16 +78,16 @@ $decdigit  = $ascdigit -- for now, should really be $digit (ToDo)
 $digit     = [$ascdigit $unidigit]
 
 $special   = [\(\)\,\;\[\]\`\{\}]
-$ascsymbol = [\!\#\$\%\&\*\+\.\/\<\=\>\?\@\\\^\|\-\~ \xa1-\xbf \xd7 \xf7]
+$ascsymbol = [\!\#\$\%\&\*\+\.\/\<\=\>\?\@\\\^\|\-\~]
 $unisymbol = \x04 -- Trick Alex into handling Unicode. See alexGetChar.
 $symbol    = [$ascsymbol $unisymbol] # [$special \_\:\"\']
 
 $unilarge  = \x01 -- Trick Alex into handling Unicode. See alexGetChar.
-$asclarge  = [A-Z \xc0-\xd6 \xd8-\xde]
+$asclarge  = [A-Z]
 $large     = [$asclarge $unilarge]
 
 $unismall  = \x02 -- Trick Alex into handling Unicode. See alexGetChar.
-$ascsmall  = [a-z \xdf-\xf6 \xf8-\xff]
+$ascsmall  = [a-z]
 $small     = [$ascsmall $unismall \_]
 
 $unigraphic = \x06 -- Trick Alex into handling Unicode. See alexGetChar.
@@ -1218,7 +1218,7 @@ lex_char c inp = do
       c | isAny c -> do setInput inp; return c
       _other -> lit_error
 
-isAny c | c > '\xff' = isPrint c
+isAny c | c > '\x7f' = isPrint c
 	| otherwise  = is_any c
 
 lex_escape :: P Char
@@ -1486,7 +1486,7 @@ alexGetChar (AI loc ofs s)
 
 	adj_c 
 	  | c <= '\x06' = non_graphic
-	  | c <= '\xff' = c
+	  | c <= '\x7f' = c
           -- Alex doesn't handle Unicode, so when Unicode
           -- character is encoutered we output these values
           -- with the actual character value hidden in the state.