utf8.c

 1/* Copyright 2021 QMK
 2 *
 3 * This program is free software: you can redistribute it and/or modify
 4 * it under the terms of the GNU General Public License as published by
 5 * the Free Software Foundation, either version 2 of the License, or
 6 * (at your option) any later version.
 7 *
 8 * This program is distributed in the hope that it will be useful,
 9 * but WITHOUT ANY WARRANTY; without even the implied warranty of
10 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
11 * GNU General Public License for more details.
12 *
13 * You should have received a copy of the GNU General Public License
14 * along with this program.  If not, see <http://www.gnu.org/licenses/>.
15 */
16
17#include "utf8.h"
18
19// Borrowed from https://nullprogram.com/blog/2017/10/06/
20const char *decode_utf8(const char *str, int32_t *code_point) {
21    const char *next;
22
23    if (str[0] < 0x80) { // U+0000-007F
24        *code_point = str[0];
25        next        = str + 1;
26    } else if ((str[0] & 0xE0) == 0xC0) { // U+0080-07FF
27        *code_point = ((int32_t)(str[0] & 0x1F) << 6) | ((int32_t)(str[1] & 0x3F) << 0);
28        next        = str + 2;
29    } else if ((str[0] & 0xF0) == 0xE0) { // U+0800-FFFF
30        *code_point = ((int32_t)(str[0] & 0x0F) << 12) | ((int32_t)(str[1] & 0x3F) << 6) | ((int32_t)(str[2] & 0x3F) << 0);
31        next        = str + 3;
32    } else if ((str[0] & 0xF8) == 0xF0 && (str[0] <= 0xF4)) { // U+10000-10FFFF
33        *code_point = ((int32_t)(str[0] & 0x07) << 18) | ((int32_t)(str[1] & 0x3F) << 12) | ((int32_t)(str[2] & 0x3F) << 6) | ((int32_t)(str[3] & 0x3F) << 0);
34        next        = str + 4;
35    } else {
36        *code_point = -1;
37        next        = str + 1;
38    }
39
40    // part of a UTF-16 surrogate pair - invalid
41    if (*code_point >= 0xD800 && *code_point <= 0xDFFF) {
42        *code_point = -1;
43    }
44
45    return next;
46}