1 /*
2 * Copyright (c) 2009-2021, Google LLC
3 * All rights reserved.
4 *
5 * Redistribution and use in source and binary forms, with or without
6 * modification, are permitted provided that the following conditions are met:
7 * * Redistributions of source code must retain the above copyright
8 * notice, this list of conditions and the following disclaimer.
9 * * Redistributions in binary form must reproduce the above copyright
10 * notice, this list of conditions and the following disclaimer in the
11 * documentation and/or other materials provided with the distribution.
12 * * Neither the name of Google LLC nor the
13 * names of its contributors may be used to endorse or promote products
14 * derived from this software without specific prior written permission.
15 *
16 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
17 * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
18 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
19 * ARE DISCLAIMED. IN NO EVENT SHALL Google LLC BE LIABLE FOR ANY DIRECT,
20 * INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
21 * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
22 * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
23 * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
24 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
25 * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
26 */
27
28 #include "upb/lex/unicode.h"
29
30 // Must be last.
31 #include "upb/port/def.inc"
32
upb_Unicode_ToUTF8(uint32_t cp,char * out)33 int upb_Unicode_ToUTF8(uint32_t cp, char* out) {
34 if (cp <= 0x7f) {
35 out[0] = cp;
36 return 1;
37 }
38 if (cp <= 0x07ff) {
39 out[0] = (cp >> 6) | 0xc0;
40 out[1] = (cp & 0x3f) | 0x80;
41 return 2;
42 }
43 if (cp <= 0xffff) {
44 out[0] = (cp >> 12) | 0xe0;
45 out[1] = ((cp >> 6) & 0x3f) | 0x80;
46 out[2] = (cp & 0x3f) | 0x80;
47 return 3;
48 }
49 if (cp <= 0x10ffff) {
50 out[0] = (cp >> 18) | 0xf0;
51 out[1] = ((cp >> 12) & 0x3f) | 0x80;
52 out[2] = ((cp >> 6) & 0x3f) | 0x80;
53 out[3] = (cp & 0x3f) | 0x80;
54 return 4;
55 }
56 return 0;
57 }
58