First pass at adding locale support. This code only deals with the LC_CTYPE

class of locale data, but could be extended to handle other locale
classes, as well as message catalogues and other non-locale i18n
support.

I have left the old _ctype_ array in place, and moved the ctype.h
header to octype.h, so that existing shared binaries will still be
able to find and use it as they require.

See /usr/src/share/locale for information on how to create new locale
data files (eventually this procedure will be improved).  I'd like to
have a family of locale files for various countries, languages, and
character sets, so please contribute some.

This code was originally written by Paul Borman and contributed to
4.4; I did the integration, and have somewhat tested it.  crt0.c
probably ought to call setlocale() if it doesn't already, but I'd like
for people to create some locale files and try things manually first
before I make every program do this.

5 files changed, 31 insertions, 14 deletions

diff --git a/sys/i386/include/_limits.h b/sys/i386/include/_limits.h
index 72baa58..5aed870 100644
--- a/sys/i386/include/_limits.h
+++ b/sys/i386/include/_limits.h
@@ -31,15 +31,14 @@
  * SUCH DAMAGE.
  *
  *	from: @(#)limits.h	7.2 (Berkeley) 6/28/90
- *	$Id: limits.h,v 1.4 1993/12/19 05:14:46 alm Exp $
+ *	$Id: limits.h,v 1.5 1994/02/26 00:56:02 ache Exp $
  */
 
 #ifndef _MACHINE_LIMITS_H_
 #define _MACHINE_LIMITS_H_ 1
 
 #define	CHAR_BIT	8		/* number of bits in a char */
-#define	CLK_TCK		128		/* ticks per second */
-#define	MB_LEN_MAX	1		/* no multibyte characters */
+#define	MB_LEN_MAX	6		/* allow 21-bit UTF2 */
 
 #define SCHAR_MIN	(-0x7f-1)	/* max value for a signed char */
 #define	SCHAR_MAX	0x7f		/* min value for a signed char */
@@ -61,6 +60,7 @@
 #define	LONG_MIN	(-0x7fffffff-1)	/* min value for a long */
 
 #if !defined(_ANSI_SOURCE) && !defined(_POSIX_SOURCE)
+#define	CLK_TCK		128		/* ticks per second */
 #define	UQUAD_MAX	0xffffffffffffffffLL		/* max unsigned quad */
 #define	QUAD_MAX	0x7fffffffffffffffLL		/* max signed quad */
 #define	QUAD_MIN	(-0x7fffffffffffffffLL-1)	/* min signed quad */
diff --git a/sys/i386/include/ansi.h b/sys/i386/include/ansi.h
index cdb3af8..1665aad 100644
--- a/sys/i386/include/ansi.h
+++ b/sys/i386/include/ansi.h
@@ -31,7 +31,7 @@
  * SUCH DAMAGE.
  *
  *	from: @(#)ansi.h	7.1 (Berkeley) 3/9/91
- *	$Id$
+ *	$Id: ansi.h,v 1.2 1993/10/16 14:39:05 rgrimes Exp $
  */
 
 #ifndef	_ANSI_H_
@@ -53,6 +53,23 @@
 #define	_SIZE_T_	unsigned int		/* sizeof() */
 #define	_TIME_T_	long			/* time() */
 #define	_VA_LIST_	char *			/* va_list */
-#define	_WCHAR_T_	unsigned short		/* wchar_t */
+
+/*
+ * Runes (wchar_t) is declared to be an ``int'' instead of the more natural
+ * ``unsigned long'' or ``long''.  Two things are happening here.  It is not
+ * unsigned so that EOF (-1) can be naturally assigned to it and used.  Also,
+ * it looks like 10646 will be a 31 bit standard.  This means that if your
+ * ints cannot hold 32 bits, you will be in trouble.  The reason an int was
+ * chosen over a long is that the is*() and to*() routines take ints (says
+ * ANSI C), but they use _RUNE_T_ instead of int.  By changing it here, you
+ * lose a bit of ANSI conformance, but your programs will still work.
+ *
+ * Note that _WCHAR_T_ and _RUNE_T_ must be of the same type.  When wchar_t
+ * and rune_t are typedef'd, _WCHAR_T_ will be undef'd, but _RUNE_T remains
+ * defined for ctype.h.
+ */
+#define _BSD_WCHAR_T_   int                     /* wchar_t */
+#define _BSD_RUNE_T_    int                     /* rune_t */
+
 
 #endif	/* _ANSI_H_ */
diff --git a/sys/i386/include/limits.h b/sys/i386/include/limits.h
index 72baa58..5aed870 100644
--- a/sys/i386/include/limits.h
+++ b/sys/i386/include/limits.h
@@ -31,15 +31,14 @@
  * SUCH DAMAGE.
  *
  *	from: @(#)limits.h	7.2 (Berkeley) 6/28/90
- *	$Id: limits.h,v 1.4 1993/12/19 05:14:46 alm Exp $
+ *	$Id: limits.h,v 1.5 1994/02/26 00:56:02 ache Exp $
  */
 
 #ifndef _MACHINE_LIMITS_H_
 #define _MACHINE_LIMITS_H_ 1
 
 #define	CHAR_BIT	8		/* number of bits in a char */
-#define	CLK_TCK		128		/* ticks per second */
-#define	MB_LEN_MAX	1		/* no multibyte characters */
+#define	MB_LEN_MAX	6		/* allow 21-bit UTF2 */
 
 #define SCHAR_MIN	(-0x7f-1)	/* max value for a signed char */
 #define	SCHAR_MAX	0x7f		/* min value for a signed char */
@@ -61,6 +60,7 @@
 #define	LONG_MIN	(-0x7fffffff-1)	/* min value for a long */
 
 #if !defined(_ANSI_SOURCE) && !defined(_POSIX_SOURCE)
+#define	CLK_TCK		128		/* ticks per second */
 #define	UQUAD_MAX	0xffffffffffffffffLL		/* max unsigned quad */
 #define	QUAD_MAX	0x7fffffffffffffffLL		/* max signed quad */
 #define	QUAD_MIN	(-0x7fffffffffffffffLL-1)	/* min signed quad */
diff --git a/sys/powerpc/include/_limits.h b/sys/powerpc/include/_limits.h
index 72baa58..5aed870 100644
--- a/sys/powerpc/include/_limits.h
+++ b/sys/powerpc/include/_limits.h
@@ -31,15 +31,14 @@
  * SUCH DAMAGE.
  *
  *	from: @(#)limits.h	7.2 (Berkeley) 6/28/90
- *	$Id: limits.h,v 1.4 1993/12/19 05:14:46 alm Exp $
+ *	$Id: limits.h,v 1.5 1994/02/26 00:56:02 ache Exp $
  */
 
 #ifndef _MACHINE_LIMITS_H_
 #define _MACHINE_LIMITS_H_ 1
 
 #define	CHAR_BIT	8		/* number of bits in a char */
-#define	CLK_TCK		128		/* ticks per second */
-#define	MB_LEN_MAX	1		/* no multibyte characters */
+#define	MB_LEN_MAX	6		/* allow 21-bit UTF2 */
 
 #define SCHAR_MIN	(-0x7f-1)	/* max value for a signed char */
 #define	SCHAR_MAX	0x7f		/* min value for a signed char */
@@ -61,6 +60,7 @@
 #define	LONG_MIN	(-0x7fffffff-1)	/* min value for a long */
 
 #if !defined(_ANSI_SOURCE) && !defined(_POSIX_SOURCE)
+#define	CLK_TCK		128		/* ticks per second */
 #define	UQUAD_MAX	0xffffffffffffffffLL		/* max unsigned quad */
 #define	QUAD_MAX	0x7fffffffffffffffLL		/* max signed quad */
 #define	QUAD_MIN	(-0x7fffffffffffffffLL-1)	/* min signed quad */
diff --git a/sys/powerpc/include/limits.h b/sys/powerpc/include/limits.h
index 72baa58..5aed870 100644
--- a/sys/powerpc/include/limits.h
+++ b/sys/powerpc/include/limits.h
@@ -31,15 +31,14 @@
  * SUCH DAMAGE.
  *
  *	from: @(#)limits.h	7.2 (Berkeley) 6/28/90
- *	$Id: limits.h,v 1.4 1993/12/19 05:14:46 alm Exp $
+ *	$Id: limits.h,v 1.5 1994/02/26 00:56:02 ache Exp $
  */
 
 #ifndef _MACHINE_LIMITS_H_
 #define _MACHINE_LIMITS_H_ 1
 
 #define	CHAR_BIT	8		/* number of bits in a char */
-#define	CLK_TCK		128		/* ticks per second */
-#define	MB_LEN_MAX	1		/* no multibyte characters */
+#define	MB_LEN_MAX	6		/* allow 21-bit UTF2 */
 
 #define SCHAR_MIN	(-0x7f-1)	/* max value for a signed char */
 #define	SCHAR_MAX	0x7f		/* min value for a signed char */
@@ -61,6 +60,7 @@
 #define	LONG_MIN	(-0x7fffffff-1)	/* min value for a long */
 
 #if !defined(_ANSI_SOURCE) && !defined(_POSIX_SOURCE)
+#define	CLK_TCK		128		/* ticks per second */
 #define	UQUAD_MAX	0xffffffffffffffffLL		/* max unsigned quad */
 #define	QUAD_MAX	0x7fffffffffffffffLL		/* max signed quad */
 #define	QUAD_MIN	(-0x7fffffffffffffffLL-1)	/* min signed quad */