lib/localeinfo.h

   1 /* locale information
   2
   3    Copyright 2016-2024 Free Software Foundation, Inc.
   4
   5    This program is free software; you can redistribute it and/or modify
   6    it under the terms of the GNU General Public License as published by
   7    the Free Software Foundation, either version 3, or (at your option)
   8    any later version.
   9
  10    This program is distributed in the hope that it will be useful,
  11    but WITHOUT ANY WARRANTY; without even the implied warranty of
  12    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  13    GNU General Public License for more details.
  14
  15    You should have received a copy of the GNU General Public License
  16    along with this program; if not, write to the Free Software
  17    Foundation, Inc., 51 Franklin Street - Fifth Floor, Boston, MA
  18    02110-1301, USA.  */
  19
  20 /* Written by Paul Eggert.  */
  21
  22 #include <limits.h>
  23 #include <wchar.h>
  24 #if GAWK
  25 /* Use ISO C 99 API.  */
  26 # define char32_t wchar_t
  27 #else
  28 /* Use ISO C 11 + gnulib API.  */
  29 # include <uchar.h>
  30 #endif
  31
  32 struct localeinfo
  33 {
  34   /* MB_CUR_MAX > 1.  */
  35   bool multibyte;
  36
  37   /* The locale is simple, like the C locale.  These locales can be
  38      processed more efficiently, as they are single-byte, their native
  39      character set is in collating-sequence order, and they do not
  40      have multi-character collating elements.  */
  41   bool simple;
  42
  43   /* The locale uses UTF-8.  */
  44   bool using_utf8;
  45
  46   /* An array indexed by byte values B that contains 1 if B is a
  47      single-byte character, -1 if B is an encoding error, and -2 if B
  48      is the leading byte of a multibyte character that contains more
  49      than one byte.  */
  50   signed char sbclen[UCHAR_MAX + 1];
  51
  52   /* An array indexed by byte values B that contains the corresponding
  53      32-bit wide character (if any) for B if sbclen[B] == 1.  WEOF means
  54      the byte is not a valid single-byte character, i.e., sbclen[B] == -1
  55      or -2.  */
  56   wint_t sbctowc[UCHAR_MAX + 1];
  57 };
  58
  59 extern void init_localeinfo (struct localeinfo *);
  60
  61 /* Maximum number of characters that can be the case-folded
  62    counterparts of a single character, not counting the character
  63    itself.  This is a generous upper bound.  */
  64 enum { CASE_FOLDED_BUFSIZE = 32 };
  65
  66 extern int case_folded_counterparts (wint_t, char32_t[CASE_FOLDED_BUFSIZE]);