Last active
July 29, 2022 22:14
-
-
Save opsJson/b785cb90f766f3cdfe519202418b6fa2 to your computer and use it in GitHub Desktop.
UTF8 codec in C
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
void utf8_encode(int codepoint, unsigned char encoded[5]) { | |
if (codepoint < 0x80) { | |
encoded[1] = 0; | |
encoded[0] = codepoint; | |
encoded[0] &= ~(1 << 7); | |
return; | |
} | |
if (codepoint < 0x800) { | |
encoded[2] = 0; | |
encoded[1] = codepoint; | |
encoded[1] &= ~(1 << 6); | |
encoded[1] |= 1 << 7; | |
encoded[0] = codepoint >> 6; | |
encoded[0] &= ~(1 << 5); | |
encoded[0] |= 1 << 6; | |
encoded[0] |= 1 << 7; | |
return; | |
} | |
if (codepoint < 0x10000) { | |
encoded[3] = 0; | |
encoded[2] = codepoint; | |
encoded[2] &= ~(1 << 6); | |
encoded[2] |= 1 << 7; | |
encoded[1] = codepoint >> 6; | |
encoded[1] &= ~(1 << 6); | |
encoded[1] |= 1 << 7; | |
encoded[0] = codepoint >> 12; | |
encoded[0] &= ~(1 << 4); | |
encoded[0] |= 1 << 5; | |
encoded[0] |= 1 << 6; | |
encoded[0] |= 1 << 7; | |
return; | |
} | |
if (codepoint < 0x200000) { | |
encoded[4] = 0; | |
encoded[3] = codepoint; | |
encoded[3] &= ~(1 << 6); | |
encoded[3] |= 1 << 7; | |
encoded[2] = codepoint >> 6; | |
encoded[2] &= ~(1 << 6); | |
encoded[2] |= 1 << 7; | |
encoded[1] = codepoint >> 12; | |
encoded[1] &= ~(1 << 6); | |
encoded[1] |= 1 << 7; | |
encoded[0] = codepoint >> 18; | |
encoded[0] &= ~(1 << 3); | |
encoded[0] |= 1 << 4; | |
encoded[0] |= 1 << 5; | |
encoded[0] |= 1 << 6; | |
encoded[0] |= 1 << 7; | |
return; | |
} | |
} | |
unsigned int utf8_decode(unsigned char encoded[5]) { | |
unsigned int header = (unsigned int)encoded[0]; | |
unsigned int decoded = 0; | |
if (header <= 0x7F) | |
decoded = encoded[0] & 127; | |
else if (header <= 0xDF) | |
decoded = ((header & 31) << 6) | ((encoded[1] & 63) << 0); | |
else if (header <= 0xEF) | |
decoded = ((header & 15) << 12) | ((encoded[1] & 63) << 6) | ((encoded[2] & 63) << 0); | |
else if (header <= 0xF7) | |
decoded = ((header & 7) << 18) | ((encoded[1] & 63) << 12) | ((encoded[2] & 63) << 6) | ((encoded[3] & 63) << 0); | |
return decoded; | |
} | |
/*/////////////////////////////////// | |
Testing: | |
///////////////////////////////////*/ | |
#include <stdio.h> | |
int main(void) { | |
int i; | |
char encoded[5] = {0}; | |
FILE *fp; | |
if ((fp = fopen("unicode_test.txt", "w")) == NULL) return 1; | |
for (i=0x1F300; i<0x1F300+1000; i++) { | |
utf8_encode(i, encoded); | |
fprintf(fp, "%s", encoded); | |
printf("0x%x == 0x%x\n", utf8_decode(encoded), i); | |
if ((i+1) % 100 == 0) fprintf(fp, "\n"); | |
} | |
fclose(fp); | |
return 0; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment