c32width: New module.

* lib/uchar.in.h (c32width): New declaration.
* lib/c32width.c: New file, based on lib/c32is-impl.h.
* modules/c32width: New file.
* m4/uchar_h.m4 (gl_UCHAR_H_REQUIRE_DEFAULTS): Initialize
GNULIB_C32WIDTH.
* modules/uchar (Makefile.am): Substitute GNULIB_C32WIDTH.

6 files changed, 174 insertions, 1 deletions

diff --git a/ChangeLog b/ChangeLog
index 5e5943e4f5..9bfa9e0c48 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,5 +1,15 @@
 2023-05-04  Bruno Haible  <bruno@clisp.org>
 
+	c32width: New module.
+	* lib/uchar.in.h (c32width): New declaration.
+	* lib/c32width.c: New file, based on lib/c32is-impl.h.
+	* modules/c32width: New file.
+	* m4/uchar_h.m4 (gl_UCHAR_H_REQUIRE_DEFAULTS): Initialize
+	GNULIB_C32WIDTH.
+	* modules/uchar (Makefile.am): Substitute GNULIB_C32WIDTH.
+
+2023-05-04  Bruno Haible  <bruno@clisp.org>
+
 	doc: Mention macOS wcwidth bug.
 	* m4/wcwidth.m4 (gl_FUNC_WCWIDTH): Mention macOS bugs.
 	* doc/posix-functions/wcwidth.texi: Update regarding macOS.
diff --git a/lib/c32width.c b/lib/c32width.c
new file mode 100644
index 0000000000..4149e06b25
--- /dev/null
+++ b/lib/c32width.c
@@ -0,0 +1,102 @@
+/* Determine the number of screen columns needed for a 32-bit wide character.
+   Copyright (C) 2020-2023 Free Software Foundation, Inc.
+
+   This file is free software.
+   It is dual-licensed under "the GNU LGPLv3+ or the GNU GPLv2+".
+   You can redistribute it and/or modify it under either
+     - the terms of the GNU Lesser General Public License as published
+       by the Free Software Foundation, either version 3, or (at your
+       option) any later version, or
+     - the terms of the GNU General Public License as published by the
+       Free Software Foundation; either version 2, or (at your option)
+       any later version, or
+     - the same dual license "the GNU LGPLv3+ or the GNU GPLv2+".
+
+   This file is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+   Lesser General Public License and the GNU General Public License
+   for more details.
+
+   You should have received a copy of the GNU Lesser General Public
+   License and of the GNU General Public License along with this
+   program.  If not, see <https://www.gnu.org/licenses/>.  */
+
+/* Written by Bruno Haible <bruno@clisp.org>, 2023.  */
+
+#include <config.h>
+
+#define IN_C32WIDTH
+/* Specification.  */
+#include <uchar.h>
+
+#include <wchar.h>
+
+#ifdef __CYGWIN__
+# include <cygwin/version.h>
+#endif
+
+#if GNULIB_defined_mbstate_t
+# include "streq.h"
+#endif
+
+#include "localcharset.h"
+#include "uniwidth.h"
+
+#if _GL_WCHAR_T_IS_UCS4 && !GNULIB_defined_mbstate_t
+_GL_EXTERN_INLINE
+#endif
+int
+c32width (char32_t wc)
+{
+  /* The char32_t encoding of a multibyte character is defined by the way
+     mbrtoc32() is defined.  */
+
+#if GNULIB_defined_mbstate_t            /* AIX, IRIX */
+  /* mbrtoc32() is defined on top of mbtowc() for the non-UTF-8 locales
+     and directly for the UTF-8 locales.  */
+  const char *encoding = locale_charset ();
+  if (STREQ_OPT (encoding, "UTF-8", 'U', 'T', 'F', '-', '8', 0, 0, 0, 0))
+    return uc_width (wc, encoding);
+  else
+    return wcwidth (wc);
+
+#elif HAVE_WORKING_MBRTOC32             /* glibc */
+  /* mbrtoc32() is essentially defined by the system libc.  */
+
+# if _GL_WCHAR_T_IS_UCS4
+  /* The char32_t encoding of a multibyte character is known to be the same as
+     the wchar_t encoding.  */
+  return wcwidth (wc);
+# else
+  /* The char32_t encoding of a multibyte character is known to be UCS-4,
+     different from the wchar_t encoding.  */
+  return uc_width (wc, locale_charset ());
+# endif
+
+#elif _GL_SMALL_WCHAR_T                 /* Cygwin, mingw, MSVC */
+  /* The wchar_t encoding is UTF-16.
+     The char32_t encoding is UCS-4.  */
+
+# if defined __CYGWIN__ && CYGWIN_VERSION_DLL_MAJOR >= 1007 && 0
+  /* As an extension to POSIX, the wcwidth() function of Cygwin >= 1.7
+     supports also wc arguments outside the Unicode BMP, that is, outside
+     the 'wchar_t' range.  See
+     <https://www.cygwin.com/cgit/newlib-cygwin/commit/?id=098a75dc51caa98f369d98a9809d773bc45329aa>.
+     But the resulting values for these characters are not of good quality.  */
+  return wcwidth (wc);
+# else
+  if (wc == (wchar_t) wc)
+    /* wc is in the range for the wcwidth function.  */
+    return wcwidth (wc);
+  else
+    return uc_width (wc, locale_charset ());
+# endif
+
+#else /* macOS, FreeBSD, NetBSD, OpenBSD, HP-UX, Solaris, Minix, Android */
+  /* char32_t and wchar_t are equivalent.  */
+  static_assert (sizeof (char32_t) == sizeof (wchar_t));
+
+  return wcwidth (wc);
+#endif
+}
diff --git a/lib/uchar.in.h b/lib/uchar.in.h
index cc4f2adee5..3815af4c26 100644
--- a/lib/uchar.in.h
+++ b/lib/uchar.in.h
@@ -379,6 +379,24 @@ _GL_CXXALIASWARN (c32toupper);
 #endif
 
 
+/* Number of screen columns needed for a 32-bit wide character.  */
+#if @GNULIB_C32WIDTH@
+# if (_GL_WCHAR_T_IS_UCS4 && !GNULIB_defined_mbstate_t) && !defined IN_C32WIDTH
+_GL_BEGIN_C_LINKAGE
+_GL_INLINE int
+c32width (char32_t wc)
+{
+  return wcwidth (wc);
+}
+_GL_END_C_LINKAGE
+# else
+_GL_FUNCDECL_SYS (c32width, int, (char32_t wc));
+# endif
+_GL_CXXALIAS_SYS (c32width, int, (char32_t wc));
+_GL_CXXALIASWARN (c32width);
+#endif
+
+
 /* Converts a 32-bit wide character to a multibyte character.  */
 #if @GNULIB_C32RTOMB@
 # if @REPLACE_C32RTOMB@
diff --git a/m4/uchar_h.m4 b/m4/uchar_h.m4
index 2679371716..5c04e2a6ee 100644
--- a/m4/uchar_h.m4
+++ b/m4/uchar_h.m4
@@ -1,4 +1,4 @@
-# uchar_h.m4 serial 24
+# uchar_h.m4 serial 25
 dnl Copyright (C) 2019-2023 Free Software Foundation, Inc.
 dnl This file is free software; the Free Software Foundation
 dnl gives unlimited permission to copy and/or distribute it,
@@ -216,6 +216,7 @@ AC_DEFUN([gl_UCHAR_H_REQUIRE_DEFAULTS],
     gl_MODULE_INDICATOR_INIT_VARIABLE([GNULIB_C32ISXDIGIT])
     gl_MODULE_INDICATOR_INIT_VARIABLE([GNULIB_C32TOLOWER])
     gl_MODULE_INDICATOR_INIT_VARIABLE([GNULIB_C32TOUPPER])
+    gl_MODULE_INDICATOR_INIT_VARIABLE([GNULIB_C32WIDTH])
     gl_MODULE_INDICATOR_INIT_VARIABLE([GNULIB_C32RTOMB])
     gl_MODULE_INDICATOR_INIT_VARIABLE([GNULIB_C32SNRTOMBS])
     gl_MODULE_INDICATOR_INIT_VARIABLE([GNULIB_C32SRTOMBS])
diff --git a/modules/c32width b/modules/c32width
new file mode 100644
index 0000000000..f91e67f37f
--- /dev/null
+++ b/modules/c32width
@@ -0,0 +1,41 @@
+Description:
+c32width() function: Determine the number of screen columns needed for
+a 32-bit wide character.
+
+Files:
+lib/c32width.c
+m4/mbrtoc32.m4
+m4/mbrtowc.m4
+m4/locale-fr.m4
+m4/locale-ja.m4
+m4/locale-zh.m4
+m4/codeset.m4
+
+Depends-on:
+uchar
+wchar
+wcwidth
+uniwidth/width
+
+configure.ac:
+AC_REQUIRE([gl_UCHAR_H])
+dnl Determine REPLACE_MBSTATE_T, from which GNULIB_defined_mbstate_t is
+dnl determined.  It describes how mbrtoc32 is implemented.
+AC_REQUIRE([gl_MBSTATE_T_BROKEN])
+AC_REQUIRE([gl_MBRTOC32_SANITYCHECK])
+gl_UCHAR_MODULE_INDICATOR([c32width])
+
+Makefile.am:
+lib_SOURCES += c32width.c
+
+Include:
+<uchar.h>
+
+Link:
+$(LTLIBUNISTRING) when linking with libtool, $(LIBUNISTRING) otherwise
+
+License:
+LGPLv3+ or GPLv2+
+
+Maintainer:
+Bruno Haible
diff --git a/modules/uchar b/modules/uchar
index 6363d543d9..3c6f3963b9 100644
--- a/modules/uchar
+++ b/modules/uchar
@@ -53,6 +53,7 @@ uchar.h: uchar.in.h $(top_builddir)/config.status $(CXXDEFS_H)
 	      -e 's/@''GNULIB_C32ISXDIGIT''@/$(GNULIB_C32ISXDIGIT)/g' \
 	      -e 's/@''GNULIB_C32TOLOWER''@/$(GNULIB_C32TOLOWER)/g' \
 	      -e 's/@''GNULIB_C32TOUPPER''@/$(GNULIB_C32TOUPPER)/g' \
+	      -e 's/@''GNULIB_C32WIDTH''@/$(GNULIB_C32WIDTH)/g' \
 	      -e 's/@''GNULIB_C32RTOMB''@/$(GNULIB_C32RTOMB)/g' \
 	      -e 's/@''GNULIB_C32SNRTOMBS''@/$(GNULIB_C32SNRTOMBS)/g' \
 	      -e 's/@''GNULIB_C32SRTOMBS''@/$(GNULIB_C32SRTOMBS)/g' \