该解码器由比约恩德国霍曼集团是我发现最简单的。 它也可以通过喂养它一个字节,以及保持状态。 国家是解析UTF8未来在通过网络块非常有用的。
http://bjoern.hoehrmann.de/utf-8/decoder/dfa/
// Copyright (c) 2008-2009 Bjoern Hoehrmann <bjoern@hoehrmann.de>
// See http://bjoern.hoehrmann.de/utf-8/decoder/dfa/ for details.
#define UTF8_ACCEPT 0
#define UTF8_REJECT 1
static const uint8_t utf8d[] = {
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, // 00..1f
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, // 20..3f
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, // 40..5f
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, // 60..7f
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9,9, // 80..9f
7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7,7, // a0..bf
8,8,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, // c0..df
0xa,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x3,0x4,0x3,0x3, // e0..ef
0xb,0x6,0x6,0x6,0x5,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8,0x8, // f0..ff
0x0,0x1,0x2,0x3,0x5,0x8,0x7,0x1,0x1,0x1,0x4,0x6,0x1,0x1,0x1,0x1, // s0..s0
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,0,1,1,1,1,1,0,1,0,1,1,1,1,1,1, // s1..s2
1,2,1,1,1,1,1,2,1,2,1,1,1,1,1,1,1,1,1,1,1,1,1,2,1,1,1,1,1,1,1,1, // s3..s4
1,2,1,1,1,1,1,1,1,2,1,1,1,1,1,1,1,1,1,1,1,1,1,3,1,3,1,1,1,1,1,1, // s5..s6
1,3,1,1,1,1,1,3,1,3,1,1,1,1,1,1,1,3,1,1,1,1,1,1,1,1,1,1,1,1,1,1, // s7..s8
};
uint32_t inline
decode(uint32_t* state, uint32_t* codep, uint32_t byte) {
uint32_t type = utf8d[byte];
*codep = (*state != UTF8_ACCEPT) ?
(byte & 0x3fu) | (*codep << 6) :
(0xff >> type) & (byte);
*state = utf8d[256 + *state*16 + type];
return *state;
}
一个简单的验证器/检测器并不需要的代码点,所以它可以被(初始状态被设置成这样写UTF8_ACCEPT
):
uint32_t validate_utf8(uint32_t *state, char *str, size_t len) {
size_t i;
uint32_t type;
for (i = 0; i < len; i++) {
// We don't care about the codepoint, so this is
// a simplified version of the decode function.
type = utf8d[(uint8_t)str[i]];
*state = utf8d[256 + (*state) * 16 + type];
if (*state == UTF8_REJECT)
break;
}
return *state;
}
如果文字是有效的UTF8 UTF8_ACCEPT
返回。 如果无效UTF8_REJECT
。 如果需要更多的数据,返回一些其他的整数。
在组块馈送数据使用实例(例如,从网络):
char buf[128];
size_t bytes_read;
uint32_t state = UTF8_ACCEPT;
// Validate the UTF8 data in chunks.
while ((bytes_read = get_new_data(buf, sizeof(buf))) {
if (validate_utf8(&state, buf, bytes_read) == UTF8_REJECT)) {
fprintf(stderr, "Invalid UTF8 data!\n");
return -1;
}
}
// If everything went well we should have proper UTF8,
// the data might instead have ended in the middle of a UTF8
// codepoint.
if (state != UTF8_ACCEPT) {
fprintf(stderr, "Invalid UTF8, incomplete codepoint\n");
}