lib/unistr/u-strcoll.h

   1 /* Compare UTF-8/UTF-16/UTF-32 strings using the collation rules of the current
   2    locale.
   3    Copyright (C) 2009-2021 Free Software Foundation, Inc.
   4    Written by Bruno Haible <bruno@clisp.org>, 2009.
   5
   6    This program is free software: you can redistribute it and/or modify it
   7    under the terms of the GNU Lesser General Public License as published
   8    by the Free Software Foundation; either version 3 of the License, or
   9    (at your option) any later version.
  10
  11    This program is distributed in the hope that it will be useful,
  12    but WITHOUT ANY WARRANTY; without even the implied warranty of
  13    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  14    Lesser General Public License for more details.
  15
  16    You should have received a copy of the GNU Lesser General Public License
  17    along with this program.  If not, see <https://www.gnu.org/licenses/>.  */
  18
  19 int
  20 FUNC (const UNIT *s1, const UNIT *s2)
  21 {
  22   /* When this function succeeds, it sets errno back to its original value.
  23      When it fails, it sets errno, but also returns a meaningful return value,
  24      for the sake of callers which ignore errno.  */
  25   int final_errno = errno;
  26   const char *encoding = locale_charset ();
  27   char *sl1;
  28   char *sl2;
  29   int result;
  30
  31   /* Pass iconveh_error here, not iconveh_question_mark.  Otherwise the
  32      conversion to locale encoding can do transliteration or map some
  33      characters to question marks, leading to results that depend on the
  34      iconv() implementation and are not obvious.  */
  35   sl1 = U_STRCONV_TO_ENCODING (s1, encoding, iconveh_error);
  36   if (sl1 != NULL)
  37     {
  38       sl2 = U_STRCONV_TO_ENCODING (s2, encoding, iconveh_error);
  39       if (sl2 != NULL)
  40         {
  41           /* Compare sl1 and sl2.  */
  42           errno = 0;
  43           result = strcoll (sl1, sl2);
  44           if (errno == 0)
  45             {
  46               /* strcoll succeeded.  */
  47               free (sl1);
  48               free (sl2);
  49               /* The conversion to locale encoding can drop Unicode TAG
  50                  characters.  Therefore sl1 and sl2 may be equal when s1
  51                  and s2 were in fact different.  Return a nonzero result
  52                  in this case.  */
  53               if (result == 0)
  54                 result = U_STRCMP (s1, s2);
  55             }
  56           else
  57             {
  58               /* strcoll failed.  */
  59               final_errno = errno;
  60               free (sl1);
  61               free (sl2);
  62               result = U_STRCMP (s1, s2);
  63             }
  64         }
  65       else
  66         {
  67           /* s1 could be converted to locale encoding, s2 not.  */
  68           final_errno = errno;
  69           free (sl1);
  70           result = -1;
  71         }
  72     }
  73   else
  74     {
  75       final_errno = errno;
  76       sl2 = U_STRCONV_TO_ENCODING (s2, encoding, iconveh_error);
  77       if (sl2 != NULL)
  78         {
  79           /* s2 could be converted to locale encoding, s1 not.  */
  80           free (sl2);
  81           result = 1;
  82         }
  83       else
  84         {
  85           /* Neither s1 nor s2 could be converted to locale encoding.  */
  86           result = U_STRCMP (s1, s2);
  87         }
  88     }
  89
  90   errno = final_errno;
  91   return result;
  92 }