/* UCS-4 to UTF-8 converter by Sami Farin
   v1.0.0 (20020405)
   released under GPL
   references: rfc2279

   UCS-4 range (hex.)    UTF-8 octet sequence (binary)
   0000 0000-0000 007F   0xxxxxxx
   0000 0080-0000 07FF   110xxxxx 10xxxxxx
   0000 0800-0000 FFFF   1110xxxx 10xxxxxx 10xxxxxx

   0001 0000-001F FFFF   11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
   0020 0000-03FF FFFF   111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
   0400 0000-7FFF FFFF   1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
*/

#include <stdio.h>
#include <stdlib.h>
#include <stdint.h>
#include <inttypes.h>
#include <string.h>
#include <errno.h>
#include <unistd.h>

int main(int argc, char* argv[])
{
	const uint8_t mask1[6] = {0x00, 0xC0, 0xE0, 0xF0, 0xF8, 0xFC};
	const uint8_t mask2[6] = {0x7F, 0x1F, 0x0F, 0x07, 0x03, 0x01};
	uint32_t uni;
	uint8_t utf8_out[7];
	int utf8_len, i, curr_arg;
	char* endptr = 0;

	if(argc < 2) {
		fprintf(stderr, "usage: \"%.100s value1 value2 ... (UCS-4, e.g. 308E)\n",
				argv[0]);
		exit(EXIT_FAILURE);
	}

	for(curr_arg = 1; curr_arg < argc; curr_arg++) {
		memset(utf8_out, 0, sizeof(utf8_out));
		errno = 0;
		uni = strtoull(argv[curr_arg], &endptr, 16);
		if((argv[1] == endptr) || (errno != 0) || (uni > 0x7FFFFFFF)) {
			fprintf(stderr, "invalid value, must be 0 ... 7FFFFFFF\n");
			exit(EXIT_FAILURE);
		}
		
		if(uni <= 0x0000007F) {
			utf8_len = 0;
		} else if(uni <= 0x000007FF) {
			utf8_len = 1;
		} else if(uni <= 0x0000FFFF) {
			utf8_len = 2;
		} else if(uni <= 0x001FFFFF) {
			utf8_len = 3;
		} else if(uni <= 0x03FFFFFF) {
			utf8_len = 4;
		} else {
			utf8_len = 5;
		}

		fprintf(stdout, "0x%08" PRIx32 ":", uni);

		utf8_out[0] = ((uni >> (utf8_len*6)) & mask2[utf8_len]) | mask1[utf8_len];
		for(i = utf8_len; i > 0; i--) {
			utf8_out[i] = (uni & 0x3F) | 0x80;
			uni >>= 6;
		}
		
		for(i = 0; i < (utf8_len + 1); i++) {
			fprintf(stdout, " %" PRIx8, utf8_out[i]);
		}

		fprintf(stdout, ": [ ");
		fprintf(stdout, "%s", utf8_out);
		fprintf(stdout, " ]\n");
	}
	
	return EXIT_SUCCESS;
}