1 /* utf8_decode.c */
2
3 /* 2005-12-25 */
4
5 /*
6 Copyright (c) 2005 JSON.org
7
8 Permission is hereby granted, free of charge, to any person obtaining a copy
9 of this software and associated documentation files (the "Software"), to deal
10 in the Software without restriction, including without limitation the rights
11 to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
12 copies of the Software, and to permit persons to whom the Software is
13 furnished to do so, subject to the following conditions:
14
15 The above copyright notice and this permission notice shall be included in all
16 copies or substantial portions of the Software.
17
18 The Software shall be used for Good, not Evil.
19
20 THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
21 IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
22 FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
23 AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
24 LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
25 OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
26 SOFTWARE.
27 */
28
29 #include "utf8_decode.h"
30
31 /*
32 Very Strict UTF-8 Decoder
33
34 UTF-8 is a multibyte character encoding of Unicode. A character can be
35 represented by 1-4 bytes. The bit pattern of the first byte indicates the
36 number of continuation bytes.
37
38 Most UTF-8 decoders tend to be lenient, attempting to recover as much
39 information as possible, even from badly encoded input. This UTF-8
40 decoder is not lenient. It will reject input which does not include
41 proper continuation bytes. It will reject aliases (or suboptimal
42 codings). It will reject surrogates. (Surrogate encoding should only be
43 used with UTF-16.)
44
45 Code Contination Minimum Maximum
46 0xxxxxxx 0 0 127
47 10xxxxxx error
48 110xxxxx 1 128 2047
49 1110xxxx 2 2048 65535 excluding 55296 - 57343
50 11110xxx 3 65536 1114111
51 11111xxx error
52 */
53
54
55 /*
56 Get the next byte. It returns UTF8_END if there are no more bytes.
57 */
58 static int
get(json_utf8_decode * utf8)59 get(json_utf8_decode *utf8)
60 {
61 int c;
62 if (utf8->the_index >= utf8->the_length) {
63 return UTF8_END;
64 }
65 c = utf8->the_input[utf8->the_index] & 0xFF;
66 utf8->the_index += 1;
67 return c;
68 }
69
70
71 /*
72 Get the 6-bit payload of the next continuation byte.
73 Return UTF8_ERROR if it is not a contination byte.
74 */
75 static int
cont(json_utf8_decode * utf8)76 cont(json_utf8_decode *utf8)
77 {
78 int c = get(utf8);
79 return ((c & 0xC0) == 0x80) ? (c & 0x3F) : UTF8_ERROR;
80 }
81
82
83 /*
84 Initialize the UTF-8 decoder. The decoder is not reentrant,
85 */
86 void
utf8_decode_init(json_utf8_decode * utf8,char p[],int length)87 utf8_decode_init(json_utf8_decode *utf8, char p[], int length)
88 {
89 utf8->the_index = 0;
90 utf8->the_input = p;
91 utf8->the_length = length;
92 utf8->the_char = 0;
93 utf8->the_byte = 0;
94 }
95
96
97 /*
98 Get the current byte offset. This is generally used in error reporting.
99 */
100 int
utf8_decode_at_byte(json_utf8_decode * utf8)101 utf8_decode_at_byte(json_utf8_decode *utf8)
102 {
103 return utf8->the_byte;
104 }
105
106
107 /*
108 Get the current character offset. This is generally used in error reporting.
109 The character offset matches the byte offset if the text is strictly ASCII.
110 */
111 int
utf8_decode_at_character(json_utf8_decode * utf8)112 utf8_decode_at_character(json_utf8_decode *utf8)
113 {
114 return utf8->the_char > 0 ? utf8->the_char - 1 : 0;
115 }
116
117
118 /*
119 Extract the next character.
120 Returns: the character (between 0 and 1114111)
121 or UTF8_END (the end)
122 or UTF8_ERROR (error)
123 */
124 int
utf8_decode_next(json_utf8_decode * utf8)125 utf8_decode_next(json_utf8_decode *utf8)
126 {
127 int c; /* the first byte of the character */
128 int r; /* the result */
129
130 if (utf8->the_index >= utf8->the_length) {
131 return utf8->the_index == utf8->the_length ? UTF8_END : UTF8_ERROR;
132 }
133 utf8->the_byte = utf8->the_index;
134 utf8->the_char += 1;
135 c = get(utf8);
136 /*
137 Zero continuation (0 to 127)
138 */
139 if ((c & 0x80) == 0) {
140 return c;
141 }
142 /*
143 One contination (128 to 2047)
144 */
145 if ((c & 0xE0) == 0xC0) {
146 int c1 = cont(utf8);
147 if (c1 < 0) {
148 return UTF8_ERROR;
149 }
150 r = ((c & 0x1F) << 6) | c1;
151 return r >= 128 ? r : UTF8_ERROR;
152 }
153 /*
154 Two continuation (2048 to 55295 and 57344 to 65535)
155 */
156 if ((c & 0xF0) == 0xE0) {
157 int c1 = cont(utf8);
158 int c2 = cont(utf8);
159 if (c1 < 0 || c2 < 0) {
160 return UTF8_ERROR;
161 }
162 r = ((c & 0x0F) << 12) | (c1 << 6) | c2;
163 return r >= 2048 && (r < 55296 || r > 57343) ? r : UTF8_ERROR;
164 }
165 /*
166 Three continuation (65536 to 1114111)
167 */
168 if ((c & 0xF8) == 0xF0) {
169 int c1 = cont(utf8);
170 int c2 = cont(utf8);
171 int c3 = cont(utf8);
172 if (c1 < 0 || c2 < 0 || c3 < 0) {
173 return UTF8_ERROR;
174 }
175 r = ((c & 0x0F) << 18) | (c1 << 12) | (c2 << 6) | c3;
176 return r >= 65536 && r <= 1114111 ? r : UTF8_ERROR;
177 }
178 return UTF8_ERROR;
179 }
180
