1 /* Look at first character in UTF-8 string.
2 Copyright (C) 1999-2002, 2006-2007, 2009-2023 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 #if defined IN_LIBUNISTRING
21 /* Tell unistr.h to declare u8_mbtouc as 'extern', not 'static inline'. */
22 # include "unistring-notinline.h"
23 #endif
24
25 /* Specification. */
26 #include "unistr.h"
27
28 #if !HAVE_INLINE
29
30 int
31 u8_mbtouc (ucs4_t *puc, const uint8_t *s, size_t n)
32 {
33 uint8_t c = *s;
34
35 if (c < 0x80)
36 {
37 *puc = c;
38 return 1;
39 }
40 else if (c >= 0xc2)
41 {
42 if (c < 0xe0)
43 {
44 if (n >= 2)
45 {
46 if ((s[1] ^ 0x80) < 0x40)
47 {
48 *puc = ((unsigned int) (c & 0x1f) << 6)
49 | (unsigned int) (s[1] ^ 0x80);
50 return 2;
51 }
52 /* invalid multibyte character */
53 }
54 else
55 {
56 /* incomplete multibyte character */
57 *puc = 0xfffd;
58 return 1;
59 }
60 }
61 else if (c < 0xf0)
62 {
63 if (n >= 3)
64 {
65 if ((s[1] ^ 0x80) < 0x40
66 && (c >= 0xe1 || s[1] >= 0xa0)
67 && (c != 0xed || s[1] < 0xa0))
68 {
69 if ((s[2] ^ 0x80) < 0x40)
70 {
71 *puc = ((unsigned int) (c & 0x0f) << 12)
72 | ((unsigned int) (s[1] ^ 0x80) << 6)
73 | (unsigned int) (s[2] ^ 0x80);
74 return 3;
75 }
76 /* invalid multibyte character */
77 *puc = 0xfffd;
78 return 2;
79 }
80 /* invalid multibyte character */
81 *puc = 0xfffd;
82 return 1;
83 }
84 else
85 {
86 *puc = 0xfffd;
87 if (n == 1)
88 {
89 /* incomplete multibyte character */
90 return 1;
91 }
92 else
93 {
94 if ((s[1] ^ 0x80) < 0x40
95 && (c >= 0xe1 || s[1] >= 0xa0)
96 && (c != 0xed || s[1] < 0xa0))
97 {
98 /* incomplete multibyte character */
99 return 2;
100 }
101 else
102 {
103 /* invalid multibyte character */
104 return 1;
105 }
106 }
107 }
108 }
109 else if (c <= 0xf4)
110 {
111 if (n >= 4)
112 {
113 if ((s[1] ^ 0x80) < 0x40
114 && (c >= 0xf1 || s[1] >= 0x90)
115 && (c < 0xf4 || (/* c == 0xf4 && */ s[1] < 0x90)))
116 {
117 if ((s[2] ^ 0x80) < 0x40)
118 {
119 if ((s[3] ^ 0x80) < 0x40)
120 {
121 *puc = ((unsigned int) (c & 0x07) << 18)
122 | ((unsigned int) (s[1] ^ 0x80) << 12)
123 | ((unsigned int) (s[2] ^ 0x80) << 6)
124 | (unsigned int) (s[3] ^ 0x80);
125 return 4;
126 }
127 /* invalid multibyte character */
128 *puc = 0xfffd;
129 return 3;
130 }
131 /* invalid multibyte character */
132 *puc = 0xfffd;
133 return 2;
134 }
135 /* invalid multibyte character */
136 *puc = 0xfffd;
137 return 1;
138 }
139 else
140 {
141 *puc = 0xfffd;
142 if (n == 1)
143 {
144 /* incomplete multibyte character */
145 return 1;
146 }
147 else
148 {
149 if ((s[1] ^ 0x80) < 0x40
150 && (c >= 0xf1 || s[1] >= 0x90)
151 && (c < 0xf4 || (/* c == 0xf4 && */ s[1] < 0x90)))
152 {
153 if (n == 2)
154 {
155 /* incomplete multibyte character */
156 return 2;
157 }
158 else
159 {
160 if ((s[2] ^ 0x80) < 0x40)
161 {
162 /* incomplete multibyte character */
163 return 3;
164 }
165 else
166 {
167 /* invalid multibyte character */
168 return 2;
169 }
170 }
171 }
172 else
173 {
174 /* invalid multibyte character */
175 return 1;
176 }
177 }
178 }
179 }
180 }
181 /* invalid multibyte character */
182 *puc = 0xfffd;
183 return 1;
184 }
185
186 #endif