lib/unistr/u16-cmp.c

   1 /* Compare pieces of UTF-16 strings.
   2    Copyright (C) 1999, 2002, 2006, 2009-2021 Free Software Foundation, Inc.
   3    Written by Bruno Haible <bruno@clisp.org>, 2002.
   4
   5    This program is free software: you can redistribute it and/or modify it
   6    under the terms of the GNU Lesser General Public License as published
   7    by the Free Software Foundation; either version 3 of the License, or
   8    (at your option) 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 GNU
  13    Lesser General Public License for more details.
  14
  15    You should have received a copy of the GNU Lesser General Public License
  16    along with this program.  If not, see <https://www.gnu.org/licenses/>.  */
  17
  18 #include <config.h>
  19
  20 /* Specification.  */
  21 #include "unistr.h"
  22
  23 int
  24 u16_cmp (const uint16_t *s1, const uint16_t *s2, size_t n)
  25 {
  26   /* Note that the UTF-16 encoding does NOT preserve lexicographic order.
  27      Namely, if uc1 is a 16-bit character and [uc2a,uc2b] is a surrogate pair,
  28      we must enforce uc1 < [uc2a,uc2b], even if uc1 > uc2a.  */
  29   for (; n > 0;)
  30     {
  31       uint16_t c1 = *s1++;
  32       uint16_t c2 = *s2++;
  33       if (c1 == c2)
  34         {
  35           n--;
  36           continue;
  37         }
  38       if (c1 < 0xd800 || c1 >= 0xe000)
  39         {
  40           if (!(c2 < 0xd800 || c2 >= 0xe000))
  41             /* c2 is a surrogate, but c1 is not.  */
  42             return -1;
  43         }
  44       else
  45         {
  46           if (c2 < 0xd800 || c2 >= 0xe000)
  47             /* c1 is a surrogate, but c2 is not.  */
  48             return 1;
  49         }
  50       return (int)c1 - (int)c2;
  51       /* > 0 if c1 > c2, < 0 if c1 < c2. */
  52     }
  53   return 0;
  54 }