汉字utf-8转unicode

最新推荐文章于 2017-12-15 14:51:55 发布

koson_L

最新推荐文章于 2017-12-15 14:51:55 发布

阅读量580

点赞数

CC 4.0 BY-SA版权

分类专栏： C语言

本文链接：https://blog.youkuaiyun.com/liaokesen168/article/details/51567686

C语言专栏收录该内容

4 篇文章

订阅专栏

本文介绍了一个使用C语言编写的程序，该程序能够将UTF-8编码的字符转换为Unicode编码。通过解析UTF-8编码的第一个字节来确定整个字符由几个字节组成，并据此进行转换。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

#include <stdio.h>
#include <string.h>
#include <stdlib.h>

#define u8 unsigned char
#define u16 unsigned short

static int getUtf8ByteNumForWord(u8 firstCh)
{
	int num = 0;
	int temp = 0x80;

	while (firstCh & temp)
	{
		num++;
		temp = temp >> 1;
	}

	if (num == 0)
		return 1;
	else
		return num;
}


int utf8ToUnicode(u8 *utf8, u16 *unicodeKey)
{
	int i = 0;
	int j = 0;
	u8 firstCh = utf8[0];
	u8 temp[2] = {0, 0};
	int num = getUtf8ByteNumForWord(firstCh);

	switch(num) {
	case 1:
		temp[j] = utf8[i];
		break;
	case 2:
		temp[j + 1] = (utf8[i] >> 2) & 0x07;
		temp[j] = utf8[i+1] | ((utf8[i] << 6) & 0xc0);
		break;
	case 3:
		/* utf-8 >>>>>> unicode */
		temp[j + 1] = ((utf8[i] & 0x0f) << 4) | ((utf8[i + 1] >> 2) & 0x0f);
		temp[j] = ((utf8[i + 1] << 6) & 0xc0) | ((utf8[i + 2]) & 0x3f);
		break;
	case 4:
	case 5:
	case 6:
	default:
		break;
	}

	memcpy(unicodeKey, temp, 2);

	return 0;
}

int main()
{
	int i, a , b ,c;
	u8 word_utf8[10][3];
	u8 print_word[3];
	char *stdin_st = malloc(31);
	u16 unicode = 0;

	while(1) {
		a = b = c = 0;
		fgets(stdin_st, 31, stdin);

		while(c < 31) {
			if (stdin_st[c] == '\n')
				break;
			word_utf8[a][b++] = stdin_st[c++];
			if (b == 3) {
				a++;
				b = 0;
			}
		}

		for (i = 0; i < a; i++) {
			utf8ToUnicode(word_utf8[i], &unicode);
			memcpy(print_word, word_utf8[i], 3);
			printf("%s=%d\n", print_word, unicode);			
		}

	}

	return 0;
}