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