유니코드에서 UTF-8 변환표
#define _CRT_SECURE_NO_WARNINGS
#include <stdio.h>
#include <stdlib.h>
#include <inttypes.h>
#include <windows.h>
typedef struct {
char mask; /* char data will be bitwise AND with this */
char lead; /* start bytes of current char in utf-8 encoded character */
uint32_t beg; /* beginning of codepoint range */
uint32_t end; /* end of codepoint range */
int bits_stored; /* the number of bits from the codepoint that fits in char */
}utf_t;
utf_t* utf[] = {
/* mask lead beg end bits */
[0] = &(utf_t) { 0b00111111, 0b10000000, 0, 0, 6 }, //utf[0]
[1] = &(utf_t) { 0b01111111, 0b00000000, 0000, 0177, 7 }, //utf[1] 1byte lead는 0 beg 8진수 시작값, end 는 8진수 최대값
[2] = &(utf_t) { 0b00011111, 0b11000000, 0200, 03777, 5 }, //utf[2] 2byte lead는 110
[3] = &(utf_t) { 0b00001111, 0b11100000, 04000, 0177777, 4 }, //utf[3] 3byte lead는 1110
[4] = &(utf_t) { 0b00000111, 0b11110000, 0200000, 04177777, 3 }, //utf[4] 4byte lead는 11110
&(utf_t) {0},
};
/* All lengths are in bytes */
int codepoint_len(const uint32_t cp); /* len of associated utf-8 char */
int utf8_len(const char ch); /* len of utf-8 encoded char */
char* to_utf8(const uint32_t cp);
uint32_t to_cp(const char chr[4]); // uint32_t 유형을 선언한다.
// 몇 byte인지 계산한다.
int codepoint_len(const uint32_t cp)
{
int len = 0;
for (utf_t** u = utf; *u; ++u) {
if ((cp >= (*u)->beg) && (cp <= (*u)->end)) {
//printf(“\n%s\n”, “====”);
//printf(“%hhx”, (*u)->beg);
//printf(“\n%s\n”, “====”);
break;
}
++len;
}
if (len > 4) /* Out of bounds */
exit(1);
return len;
}
int utf8_len(const char ch)
{
int len = 0;
for (utf_t** u = utf; *u; ++u) {
if ((ch & ~(*u)->mask) == (*u)->lead) {
break;
}
++len;
}
if (len > 4) { /* Malformed leading byte */
exit(1);
}
return len;
}
char* to_utf8(const uint32_t cp)
{
static char ret[5];
//printf(“%hhx\n”, cp);
const int bytes = codepoint_len(cp);
//printf(“%d\n”, bytes);
//00000001 01110110
//
int shift = utf[0]->bits_stored * (bytes — 1);
//printf(“%d\n”, (shift & utf[bytes]->mask));
ret[0] = (cp >> shift & utf[bytes]->mask) | utf[bytes]->lead;
shift -= utf[0]->bits_stored;
//printf(“%d\n”, shift);
for (int i = 1; i < bytes; ++i) {
ret[i] = (cp >> shift & utf[0]->mask) | utf[0]->lead;
shift -= utf[0]->bits_stored;
}
ret[bytes] = ‘\0’;
return ret;
}
int main(void)
{
const uint32_t* in, input[] = { 0x0041, 0x00f6, 0x0416, 0x20ac, 0x1d11e, 0x0 };
printf(“Character Unicode UTF-8 encoding (hex)\n”);
printf(“ — — — — — — — — — — — — — — — — — — — — \n”);
char* utf8;
uint32_t codepoint;
for (in = input; *in; ++in) {
// 16진수 출력하려면 hhx
//printf(“%hhx\n”, *in);
utf8 = to_utf8(*in);
for (int i = 0; utf8[i] && i < 4; ++i) {
printf(“%hhx “, utf8[i]);
}
printf(“\n”);
}
return 0;
}
