The problem is: currently our single byte ctype(3) functions are broken

for wide characters locales in the argument range >= 0x80 - they may
return false positives.

Example 1: for UTF-8 locale we currently have:
iswspace(0xA0)==1 and isspace(0xA0)==1
(because iswspace() and isspace() are the same code)
but must have
iswspace(0xA0)==1 and isspace(0xA0)==0
(because there is no such character and all others in the range
0x80..0xff for the UTF-8 locale, it keeps ASCII only in the single byte
range because our internal wchar_t representation for UTF-8 is UCS-4).

Example 2: for all wide character locales isalpha(arg) when arg > 0xFF may
return false positives (must be 0).
(because iswalpha() and isalpha() are the same code)

This change address this issue separating single byte and wide ctype
and also fix iswascii() (currently iswascii() is broken for
arguments > 0xFF).
This change is 100% binary compatible with old binaries.

Reviewied by: i18n@

1 files changed, 34 insertions, 1 deletions

diff --git a/include/_ctype.h b/include/_ctype.h
index 1a42952..e27ab24 100644
--- a/include/_ctype.h
+++ b/include/_ctype.h
@@ -87,6 +87,8 @@ __END_DECLS
 #define	__inline
 #endif
 
+extern int __mb_sb_limit;
+
 /*
  * Use inline functions if we are allowed to and the compiler supports them.
  */
@@ -103,15 +105,28 @@ __maskrune(__ct_rune_t _c, unsigned long _f)
 }
 
 static __inline int
+__sbmaskrune(__ct_rune_t _c, unsigned long _f)
+{
+	return (_c < 0 || _c >= __mb_sb_limit) ? 0 :
+	       _CurrentRuneLocale->__runetype[_c] & _f;
+}
+
+static __inline int
 __istype(__ct_rune_t _c, unsigned long _f)
 {
 	return (!!__maskrune(_c, _f));
 }
 
 static __inline int
+__sbistype(__ct_rune_t _c, unsigned long _f)
+{
+	return (!!__sbmaskrune(_c, _f));
+}
+
+static __inline int
 __isctype(__ct_rune_t _c, unsigned long _f)
 {
-	return (_c < 0 || _c >= _CACHED_RUNES) ? 0 :
+	return (_c < 0 || _c >= __mb_sb_limit) ? 0 :
 	       !!(_DefaultRuneLocale.__runetype[_c] & _f);
 }
 
@@ -123,12 +138,26 @@ __toupper(__ct_rune_t _c)
 }
 
 static __inline __ct_rune_t
+__sbtoupper(__ct_rune_t _c)
+{
+	return (_c < 0 || _c >= __mb_sb_limit) ? _c :
+	       _CurrentRuneLocale->__mapupper[_c];
+}
+
+static __inline __ct_rune_t
 __tolower(__ct_rune_t _c)
 {
 	return (_c < 0 || _c >= _CACHED_RUNES) ? ___tolower(_c) :
 	       _CurrentRuneLocale->__maplower[_c];
 }
 
+static __inline __ct_rune_t
+__sbtolower(__ct_rune_t _c)
+{
+	return (_c < 0 || _c >= __mb_sb_limit) ? _c :
+	       _CurrentRuneLocale->__maplower[_c];
+}
+
 static __inline int
 __wcwidth(__ct_rune_t _c)
 {
@@ -146,10 +175,14 @@ __wcwidth(__ct_rune_t _c)
 
 __BEGIN_DECLS
 int		__maskrune(__ct_rune_t, unsigned long);
+int		__sbmaskrune(__ct_rune_t, unsigned long);
 int		__istype(__ct_rune_t, unsigned long);
+int		__sbistype(__ct_rune_t, unsigned long);
 int		__isctype(__ct_rune_t, unsigned long);
 __ct_rune_t	__toupper(__ct_rune_t);
+__ct_rune_t	__sbtoupper(__ct_rune_t);
 __ct_rune_t	__tolower(__ct_rune_t);
+__ct_rune_t	__sbtolower(__ct_rune_t);
 int		__wcwidth(__ct_rune_t);
 __END_DECLS
 #endif /* using inlines */