c语言对utf8字符串的截取

最新推荐文章于 2023-05-15 09:05:27 发布

witto_sdy

最新推荐文章于 2023-05-15 09:05:27 发布

阅读量1.2k

点赞数

分类专栏： c/c++ 文章标签： utf8字符串截取

本文链接：https://blog.csdn.net/witto_sdy/article/details/88051263

版权

c/c++ 专栏收录该内容

11 篇文章 3 订阅

订阅专栏

utf8编码的汉字一般占用3字节，下面默认汉字全是常规的3字节汉字。

void splitUtf8(const char *s, char* store, int l)
{                                                     
    if (strlen(s) <= 0 || l <=0)
    {
        return;
    }

    int i = 0, len = 0;
    int f_len = strlen(s) >= l ? l : strlen(s);
    while (i < f_len)
    {
        if (s[i] >> 7 & 1 && s[i+1] >> 7 & 1)
        {
            cout << "汉字 i = " << i << '\t';
            i = i + 3;
            len = 3;
        }
        else
        {
            cout << s[i] << "-i=" << i << '\t';
            i = i + 1;
            len = 1;
        }
        cout << "end-i=" << i << '\t';
    }
    //i += 1;
    cout << "\ni = " << i << ",len = " << len << endl;
    if (i > f_len)
        i = i - len;
    strncpy(store, s, i);
    *(store + i) = 0;
    cout << "desc len=" << strlen(store) << endl;
}

int main()
{
    string str = "一二三";
    //string str = "一二三四五六sss";
    char desc[64];
    memset(desc, 0, sizeof(desc));
    splitUtf8(str.c_str(), desc, 12);
    printf("desc =%s]\n", desc);
    strcat(desc, "123");
    printf("desc =%s]\n", desc);
}