/src/libunistring/lib/unistr/u8-prev.c
Line | Count | Source (jump to first uncovered line) |
1 | | /* Iterate over previous character in UTF-8 string. |
2 | | Copyright (C) 2002, 2006-2007, 2009-2025 Free Software Foundation, Inc. |
3 | | Written by Bruno Haible <bruno@clisp.org>, 2002. |
4 | | |
5 | | This file is free software: you can redistribute it and/or modify |
6 | | it under the terms of the GNU Lesser General Public License as |
7 | | published by the Free Software Foundation; either version 2.1 of the |
8 | | License, or (at your option) any later version. |
9 | | |
10 | | This file 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 |
13 | | GNU 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 | | /* Don't use the const-improved function macros in this compilation unit. */ |
19 | | #define _LIBUNISTRING_NO_CONST_GENERICS |
20 | | |
21 | | #include <config.h> |
22 | | |
23 | | /* Specification. */ |
24 | | #include "unistr.h" |
25 | | |
26 | | const uint8_t * |
27 | | u8_prev (ucs4_t *puc, const uint8_t *s, const uint8_t *start) |
28 | 0 | { |
29 | | /* Keep in sync with unistr.h and u8-mbtouc-aux.c. */ |
30 | 0 | if (s != start) |
31 | 0 | { |
32 | 0 | uint8_t c_1 = s[-1]; |
33 | |
|
34 | 0 | if (c_1 < 0x80) |
35 | 0 | { |
36 | 0 | *puc = c_1; |
37 | 0 | return s - 1; |
38 | 0 | } |
39 | 0 | if ((c_1 ^ 0x80) < 0x40) |
40 | 0 | if (s - 1 != start) |
41 | 0 | { |
42 | 0 | uint8_t c_2 = s[-2]; |
43 | |
|
44 | 0 | if (c_2 >= 0xc2 && c_2 < 0xe0) |
45 | 0 | { |
46 | 0 | *puc = ((unsigned int) (c_2 & 0x1f) << 6) |
47 | 0 | | (unsigned int) (c_1 ^ 0x80); |
48 | 0 | return s - 2; |
49 | 0 | } |
50 | 0 | if ((c_2 ^ 0x80) < 0x40) |
51 | 0 | if (s - 2 != start) |
52 | 0 | { |
53 | 0 | uint8_t c_3 = s[-3]; |
54 | |
|
55 | 0 | if (c_3 >= 0xe0 && c_3 < 0xf0 |
56 | 0 | && (c_3 >= 0xe1 || c_2 >= 0xa0) |
57 | 0 | && (c_3 != 0xed || c_2 < 0xa0)) |
58 | 0 | { |
59 | 0 | *puc = ((unsigned int) (c_3 & 0x0f) << 12) |
60 | 0 | | ((unsigned int) (c_2 ^ 0x80) << 6) |
61 | 0 | | (unsigned int) (c_1 ^ 0x80); |
62 | 0 | return s - 3; |
63 | 0 | } |
64 | 0 | if ((c_3 ^ 0x80) < 0x40) |
65 | 0 | if (s - 3 != start) |
66 | 0 | { |
67 | 0 | uint8_t c_4 = s[-4]; |
68 | |
|
69 | 0 | if (c_4 >= 0xf0 && c_4 <= 0xf4 |
70 | 0 | && (c_4 >= 0xf1 || c_3 >= 0x90) |
71 | 0 | && (c_4 < 0xf4 || (/* c_4 == 0xf4 && */ c_3 < 0x90))) |
72 | 0 | { |
73 | 0 | *puc = ((unsigned int) (c_4 & 0x07) << 18) |
74 | 0 | | ((unsigned int) (c_3 ^ 0x80) << 12) |
75 | 0 | | ((unsigned int) (c_2 ^ 0x80) << 6) |
76 | 0 | | (unsigned int) (c_1 ^ 0x80); |
77 | 0 | return s - 4; |
78 | 0 | } |
79 | 0 | } |
80 | 0 | } |
81 | 0 | } |
82 | 0 | } |
83 | 0 | return NULL; |
84 | 0 | } |