lib/c32width.c

   1 /* Determine the number of screen columns needed for a 32-bit wide character.
   2    Copyright (C) 2020-2024 Free Software Foundation, Inc.
   3
   4    This file is free software: you can redistribute it and/or modify
   5    it under the terms of the GNU Lesser General Public License as
   6    published by the Free Software Foundation; either version 2.1 of the
   7    License, or (at your option) any later version.
   8
   9    This file is distributed in the hope that it will be useful,
  10    but WITHOUT ANY WARRANTY; without even the implied warranty of
  11    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  12    GNU Lesser General Public License for more details.
  13
  14    You should have received a copy of the GNU Lesser General Public License
  15    along with this program.  If not, see <https://www.gnu.org/licenses/>.  */
  16
  17 /* Written by Bruno Haible <bruno@clisp.org>, 2023.  */
  18
  19 #include <config.h>
  20
  21 #define IN_C32WIDTH
  22 /* Specification.  */
  23 #include <uchar.h>
  24
  25 #include <wchar.h>
  26
  27 #ifdef __CYGWIN__
  28 # include <cygwin/version.h>
  29 #endif
  30
  31 #if GNULIB_defined_mbstate_t
  32 # include "streq.h"
  33 #endif
  34
  35 #include "localcharset.h"
  36
  37 #if GL_CHAR32_T_IS_UNICODE
  38 # include "lc-charset-unicode.h"
  39 #endif
  40
  41 #include "uniwidth.h"
  42
  43 #if _GL_WCHAR_T_IS_UCS4 && !GNULIB_defined_mbstate_t
  44 _GL_EXTERN_INLINE
  45 #endif
  46 int
  47 c32width (char32_t wc)
  48 {
  49   /* The char32_t encoding of a multibyte character is defined by the way
  50      mbrtoc32() is defined.  */
  51
  52 #if GNULIB_defined_mbstate_t            /* AIX, IRIX */
  53   /* mbrtoc32() is defined on top of mbtowc() for the non-UTF-8 locales
  54      and directly for the UTF-8 locales.  */
  55   const char *encoding = locale_charset ();
  56   if (STREQ_OPT (encoding, "UTF-8", 'U', 'T', 'F', '-', '8', 0, 0, 0, 0))
  57     return uc_width (wc, encoding);
  58   else
  59     return wcwidth (wc);
  60
  61 #elif HAVE_WORKING_MBRTOC32             /* glibc, Android */
  62   /* mbrtoc32() is essentially defined by the system libc.  */
  63
  64 # if _GL_WCHAR_T_IS_UCS4
  65   /* The char32_t encoding of a multibyte character is known to be the same as
  66      the wchar_t encoding.  */
  67   return wcwidth (wc);
  68 # else
  69   /* The char32_t encoding of a multibyte character is known to be UCS-4,
  70      different from the wchar_t encoding.  */
  71   return uc_width (wc, locale_charset ());
  72 # endif
  73
  74 #elif _GL_SMALL_WCHAR_T                 /* Cygwin, mingw, MSVC */
  75   /* The wchar_t encoding is UTF-16.
  76      The char32_t encoding is UCS-4.  */
  77
  78 # if defined __CYGWIN__ && CYGWIN_VERSION_DLL_MAJOR >= 1007 && 0
  79   /* As an extension to POSIX, the wcwidth() function of Cygwin >= 1.7
  80      supports also wc arguments outside the Unicode BMP, that is, outside
  81      the 'wchar_t' range.  See
  82      <https://www.cygwin.com/cgit/newlib-cygwin/commit/?id=098a75dc51caa98f369d98a9809d773bc45329aa>.
  83      But the resulting values for these characters are not of good quality.  */
  84   return wcwidth (wc);
  85 # else
  86   if (wc == (wchar_t) wc)
  87     /* wc is in the range for the wcwidth function.  */
  88     return wcwidth (wc);
  89   else
  90     return uc_width (wc, locale_charset ());
  91 # endif
  92
  93 #else /* macOS, FreeBSD, NetBSD, OpenBSD, HP-UX, Solaris, Minix, Android */
  94   /* char32_t and wchar_t are equivalent.  */
  95   static_assert (sizeof (char32_t) == sizeof (wchar_t));
  96
  97 # if GL_CHAR32_T_IS_UNICODE && GL_CHAR32_T_VS_WCHAR_T_NEEDS_CONVERSION
  98   return uc_width (wc, locale_charset ());
  99 # endif
 100   return wcwidth (wc);
 101 #endif
 102 }