/src/libunistring/lib/unistr/u8-mbtouc-aux.c
Line | Count | Source (jump to first uncovered line) |
1 | | /* Conversion UTF-8 to UCS-4. |
2 | | Copyright (C) 2001-2002, 2006-2007, 2009-2024 Free Software Foundation, Inc. |
3 | | Written by Bruno Haible <bruno@clisp.org>, 2001. |
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 | | #include <config.h> |
19 | | |
20 | | /* Specification. */ |
21 | | #include "unistr.h" |
22 | | |
23 | | #if defined IN_LIBUNISTRING || HAVE_INLINE |
24 | | |
25 | | int |
26 | | u8_mbtouc_aux (ucs4_t *puc, const uint8_t *s, size_t n) |
27 | 0 | { |
28 | 0 | uint8_t c = *s; |
29 | |
|
30 | 0 | if (c >= 0xc2) |
31 | 0 | { |
32 | 0 | if (c < 0xe0) |
33 | 0 | { |
34 | 0 | if (n >= 2) |
35 | 0 | { |
36 | 0 | if ((s[1] ^ 0x80) < 0x40) |
37 | 0 | { |
38 | 0 | *puc = ((unsigned int) (c & 0x1f) << 6) |
39 | 0 | | (unsigned int) (s[1] ^ 0x80); |
40 | 0 | return 2; |
41 | 0 | } |
42 | | /* invalid multibyte character */ |
43 | 0 | } |
44 | 0 | else |
45 | 0 | { |
46 | | /* incomplete multibyte character */ |
47 | 0 | *puc = 0xfffd; |
48 | 0 | return 1; |
49 | 0 | } |
50 | 0 | } |
51 | 0 | else if (c < 0xf0) |
52 | 0 | { |
53 | 0 | if (n >= 3) |
54 | 0 | { |
55 | 0 | if ((s[1] ^ 0x80) < 0x40 |
56 | 0 | && (c >= 0xe1 || s[1] >= 0xa0) |
57 | 0 | && (c != 0xed || s[1] < 0xa0)) |
58 | 0 | { |
59 | 0 | if ((s[2] ^ 0x80) < 0x40) |
60 | 0 | { |
61 | 0 | *puc = ((unsigned int) (c & 0x0f) << 12) |
62 | 0 | | ((unsigned int) (s[1] ^ 0x80) << 6) |
63 | 0 | | (unsigned int) (s[2] ^ 0x80); |
64 | 0 | return 3; |
65 | 0 | } |
66 | | /* invalid multibyte character */ |
67 | 0 | *puc = 0xfffd; |
68 | 0 | return 2; |
69 | 0 | } |
70 | | /* invalid multibyte character */ |
71 | 0 | *puc = 0xfffd; |
72 | 0 | return 1; |
73 | 0 | } |
74 | 0 | else |
75 | 0 | { |
76 | 0 | *puc = 0xfffd; |
77 | 0 | if (n == 1) |
78 | 0 | { |
79 | | /* incomplete multibyte character */ |
80 | 0 | return 1; |
81 | 0 | } |
82 | 0 | else |
83 | 0 | { |
84 | 0 | if ((s[1] ^ 0x80) < 0x40 |
85 | 0 | && (c >= 0xe1 || s[1] >= 0xa0) |
86 | 0 | && (c != 0xed || s[1] < 0xa0)) |
87 | 0 | { |
88 | | /* incomplete multibyte character */ |
89 | 0 | return 2; |
90 | 0 | } |
91 | 0 | else |
92 | 0 | { |
93 | | /* invalid multibyte character */ |
94 | 0 | return 1; |
95 | 0 | } |
96 | 0 | } |
97 | 0 | } |
98 | 0 | } |
99 | 0 | else if (c <= 0xf4) |
100 | 0 | { |
101 | 0 | if (n >= 4) |
102 | 0 | { |
103 | 0 | if ((s[1] ^ 0x80) < 0x40 |
104 | 0 | && (c >= 0xf1 || s[1] >= 0x90) |
105 | 0 | && (c < 0xf4 || (/* c == 0xf4 && */ s[1] < 0x90))) |
106 | 0 | { |
107 | 0 | if ((s[2] ^ 0x80) < 0x40) |
108 | 0 | { |
109 | 0 | if ((s[3] ^ 0x80) < 0x40) |
110 | 0 | { |
111 | 0 | *puc = ((unsigned int) (c & 0x07) << 18) |
112 | 0 | | ((unsigned int) (s[1] ^ 0x80) << 12) |
113 | 0 | | ((unsigned int) (s[2] ^ 0x80) << 6) |
114 | 0 | | (unsigned int) (s[3] ^ 0x80); |
115 | 0 | return 4; |
116 | 0 | } |
117 | | /* invalid multibyte character */ |
118 | 0 | *puc = 0xfffd; |
119 | 0 | return 3; |
120 | 0 | } |
121 | | /* invalid multibyte character */ |
122 | 0 | *puc = 0xfffd; |
123 | 0 | return 2; |
124 | 0 | } |
125 | | /* invalid multibyte character */ |
126 | 0 | *puc = 0xfffd; |
127 | 0 | return 1; |
128 | 0 | } |
129 | 0 | else |
130 | 0 | { |
131 | 0 | *puc = 0xfffd; |
132 | 0 | if (n == 1) |
133 | 0 | { |
134 | | /* incomplete multibyte character */ |
135 | 0 | return 1; |
136 | 0 | } |
137 | 0 | else |
138 | 0 | { |
139 | 0 | if ((s[1] ^ 0x80) < 0x40 |
140 | 0 | && (c >= 0xf1 || s[1] >= 0x90) |
141 | 0 | && (c < 0xf4 || (/* c == 0xf4 && */ s[1] < 0x90))) |
142 | 0 | { |
143 | 0 | if (n == 2) |
144 | 0 | { |
145 | | /* incomplete multibyte character */ |
146 | 0 | return 2; |
147 | 0 | } |
148 | 0 | else |
149 | 0 | { |
150 | 0 | if ((s[2] ^ 0x80) < 0x40) |
151 | 0 | { |
152 | | /* incomplete multibyte character */ |
153 | 0 | return 3; |
154 | 0 | } |
155 | 0 | else |
156 | 0 | { |
157 | | /* invalid multibyte character */ |
158 | 0 | return 2; |
159 | 0 | } |
160 | 0 | } |
161 | 0 | } |
162 | 0 | else |
163 | 0 | { |
164 | | /* invalid multibyte character */ |
165 | 0 | return 1; |
166 | 0 | } |
167 | 0 | } |
168 | 0 | } |
169 | 0 | } |
170 | 0 | } |
171 | | /* invalid multibyte character */ |
172 | 0 | *puc = 0xfffd; |
173 | 0 | return 1; |
174 | 0 | } |
175 | | |
176 | | #endif |