1 /* Compare 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 file is free software. 6 It is dual-licensed under "the GNU LGPLv3+ or the GNU GPLv2+". 7 You can redistribute it and/or modify it under either 8 - the terms of the GNU Lesser General Public License as published 9 by the Free Software Foundation; either version 3, or (at your 10 option) any later version, or 11 - the terms of the GNU General Public License as published by the 12 Free Software Foundation; either version 2, or (at your option) 13 any later version, or 14 - the same dual license "the GNU LGPLv3+ or the GNU GPLv2+". 15 16 This file is distributed in the hope that it will be useful, 17 but WITHOUT ANY WARRANTY; without even the implied warranty of 18 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU 19 Lesser General Public License and the GNU General Public License 20 for more details. 21 22 You should have received a copy of the GNU Lesser General Public 23 License and of the GNU General Public License along with this 24 program. If not, see <https://www.gnu.org/licenses/>. */ 25 26 #include <config.h> 27 28 /* Specification. */ 29 #include "unistr.h" 30 31 int 32 u16_strcmp (const uint16_t *s1, const uint16_t *s2) /* */ 33 { 34 /* Note that the UTF-16 encoding does NOT preserve lexicographic order. 35 Namely, if uc1 is a 16-bit character and [uc2a,uc2b] is a surrogate pair, 36 we must enforce uc1 < [uc2a,uc2b], even if uc1 > uc2a. */ 37 for (;;) 38 { 39 uint16_t c1 = *s1++; 40 uint16_t c2 = *s2++; 41 if (c1 != 0 && c1 == c2) 42 continue; 43 if (c1 < 0xd800 || c1 >= 0xe000) 44 { 45 if (!(c2 < 0xd800 || c2 >= 0xe000)) 46 /* c2 is a surrogate, but c1 is not. */ 47 return -1; 48 } 49 else 50 { 51 if (c2 < 0xd800 || c2 >= 0xe000) 52 /* c1 is a surrogate, but c2 is not. */ 53 return 1; 54 } 55 return (int)c1 - (int)c2; 56 /* > 0 if c1 > c2, < 0 if c1 < c2. */ 57 } 58 }