How to change wchar.h to make wchar_t the same type as wint_t?

[Igor Liferenko <igor dot liferenko at gmail dot com>]

Hi all,

wchar_t is defined in wchar.h

Currently, if the developers want to use only wchar_t, the can not do
this without getting type conversion warnings from the compiler. If
wchar_t will be made the same type as wint_t, both parties will be happy.
The developers who want to have both wint_t and wchar_t in their
(for example if they want their code to be compiled not only under
glibc) can do this without getting compiler warnings. The developers who
want to use only wchar_t (to avoid unnecessary hassle with wint_t and
explicit typecasting) can not do this without getting compiler warnings.

The C standard (9899:201x 7.29) mentions: "wchar_t and wint_t can be the
same integer type." Also, in glibc wide characters are always
ISO10646/Unicode/UCS-4, so they always use 4 bytes. Thus, nothing
prevents making wchar_t the same type as wint_t in glibc.

But it seems that developers of glibc do not want to make wint_t and
wchar_t the same type. As such, I want to change the local copy of
wchar.h.

ISO10646/Unicode/UCS-4 uses 2^31 values for the extended character set
(MSB being "0"):

    0xxxxxxx xxxxxxxx xxxxxxxx xxxxxxxx

Notice, that a 4-byte type can hold 2^31 extra values (MSB being "1"):

    1xxxxxxx xxxxxxxx xxxxxxxx xxxxxxxx

Any of those extra values can be used to represent WEOF, thus one
4-byte type can be used to hold all the character set _and_ WEOF.

Notice, that no recompilation of glibc is necessary, because
wint_t can be signed or unsigned (since both -1 and 0xffffffff have MSB
"1", in any representation, and since MSB is not used in
ISO10646/Unicode/UCS-4).

Definition of wchar_t is done somewhere in the following excerpt from wchar.h.
How to change it to make wchar_t the same type as wint_t?

    #ifndef _WCHAR_H

    #if !defined __need_mbstate_t && !defined __need_wint_t
    # define _WCHAR_H 1
    # include <features.h>
    #endif

    #ifdef _WCHAR_H
    /* Get FILE definition.  */
    # define __need___FILE
    # if defined __USE_UNIX98 || defined __USE_XOPEN2K
    #  define __need_FILE
    # endif
    # include <stdio.h>
    /* Get va_list definition.  */
    # define __need___va_list
    # include <stdarg.h>

    # include <bits/wchar.h>

    /* Get size_t, wchar_t, wint_t and NULL from <stddef.h>.  */
    # define __need_size_t
    # define __need_wchar_t
    # define __need_NULL
    #endif
    #if defined _WCHAR_H || defined __need_wint_t || !defined __WINT_TYPE__
    # undef __need_wint_t
    # define __need_wint_t
    # include <stddef.h>

    /* We try to get wint_t from <stddef.h>, but not all GCC versions define it
       there.  So define it ourselves if it remains undefined.  */
    # ifndef _WINT_T
    /* Integral type unchanged by default argument promotions that can
       hold any value corresponding to members of the extended character
       set, as well as at least one value that does not correspond to any
       member of the extended character set.  */
    #  define _WINT_T
    typedef unsigned int wint_t;
    # else
    /* Work around problems with the <stddef.h> file which doesn't put
       wint_t in the std namespace.  */
    #  if defined __cplusplus && defined _GLIBCPP_USE_NAMESPACES \
          && defined __WINT_TYPE__
    __BEGIN_NAMESPACE_STD
    typedef __WINT_TYPE__ wint_t;
    __END_NAMESPACE_STD
    #  endif
    # endif

    /* Tell the caller that we provide correct C++ prototypes.  */
    # if defined __cplusplus && __GNUC_PREREQ (4, 4)
    #  define __CORRECT_ISO_CPP_WCHAR_H_PROTO
    # endif
    #endif

    #if (defined _WCHAR_H || defined __need_mbstate_t) && !defined
____mbstate_t_defined
    # define ____mbstate_t_defined	1
    /* Conversion state information.  */
    typedef struct
    {
      int __count;
      union
      {
    # ifdef __WINT_TYPE__
        __WINT_TYPE__ __wch;
    # else
        wint_t __wch;
    # endif
        char __wchb[4];
      } __value;		/* Value so far.  */
    } __mbstate_t;
    #endif
    #undef __need_mbstate_t


    /* The rest of the file is only used if used if __need_mbstate_t is not
       defined.  */
    #ifdef _WCHAR_H

    # ifndef __mbstate_t_defined
    __BEGIN_NAMESPACE_C99
    /* Public type.  */
    typedef __mbstate_t mbstate_t;
    __END_NAMESPACE_C99
    #  define __mbstate_t_defined 1
    # endif

    #ifdef __USE_GNU
    __USING_NAMESPACE_C99(mbstate_t)
    #endif

    #ifndef WCHAR_MIN
    /* These constants might also be defined in <inttypes.h>.  */
    # define WCHAR_MIN __WCHAR_MIN
    # define WCHAR_MAX __WCHAR_MAX
    #endif

    #ifndef WEOF
    # define WEOF (0xffffffffu)
    #endif

    /* For XPG4 compliance we have to define the stuff from <wctype.h> here
       as well.  */
    #if defined __USE_XOPEN && !defined __USE_UNIX98
    # include <wctype.h>
    #endif


    __BEGIN_DECLS

    __BEGIN_NAMESPACE_STD
    /* This incomplete type is defined in <time.h> but needed here because
       of `wcsftime'.  */
    struct tm;
    __END_NAMESPACE_STD
    /* XXX We have to clean this up at some point.  Since tm is in the std
       namespace but wcsftime is in __c99 the type wouldn't be found
       without inserting it in the global namespace.  */
    __USING_NAMESPACE_STD(tm)