utf、gb2312、url常用字符的转换

最新推荐文章于 2024-09-30 12:39:45 发布

余生半杯酒

最新推荐文章于 2024-09-30 12:39:45 发布

阅读量374

点赞数

分类专栏： c/c++ 文章标签： c++ 算法 c语言

本文链接：https://blog.youkuaiyun.com/xinxinnigexx/article/details/128932740

版权

c/c++ 专栏收录该内容

9 篇文章

订阅专栏

这段代码提供了两个函数，G2U和U2G，用于在GBK（GB2312）和UTF-8之间进行字符串转换。此外，还提供了一个url_decode函数，用于解码URL中的编码字符。这些函数利用WindowsAPIMultiByteToWideChar和WideCharToMultiByte进行编码转换，并包含边界检查和错误处理。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

utf和gb2312相互转换

char* G2U(const char* gb2312)
{
    int len = MultiByteToWideChar(CP_ACP, 0, gb2312, -1, NULL, 0);
    wchar_t* wstr = new wchar_t[len + 1];
    memset(wstr, 0, len + 1);
    MultiByteToWideChar(CP_ACP, 0, gb2312, -1, wstr, len);
    len = WideCharToMultiByte(CP_UTF8, 0, wstr, -1, NULL, 0, NULL, NULL);
    char* str = new char[len + 1];
    memset(str, 0, len + 1);
    WideCharToMultiByte(CP_UTF8, 0, wstr, -1, str, len, NULL, NULL);
    if (wstr) delete[] wstr;
    return str;
}

char* U2G(const char* utf8)
{
    int len = MultiByteToWideChar(CP_UTF8, 0, utf8, -1, NULL, 0);
    wchar_t* wstr = new wchar_t[len + 1];
    memset(wstr, 0, len + 1);
    MultiByteToWideChar(CP_UTF8, 0, utf8, -1, wstr, len);
    len = WideCharToMultiByte(CP_ACP, 0, wstr, -1, NULL, 0, NULL, NULL);
    char* str = new char[len + 1];
    memset(str, 0, len + 1);
    WideCharToMultiByte(CP_ACP, 0, wstr, -1, str, len, NULL, NULL);
    if (wstr) delete[] wstr;
    return str;
}

url字符转换

static unsigned char dec_tab[256] = {
    0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
    0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
    0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
    0,  1,  2,  3,  4,  5,  6,  7,  8,  9,  0,  0,  0,  0,  0,  0,
    0, 10, 11, 12, 13, 14, 15,  0,  0,  0,  0,  0,  0,  0,  0,  0,
    0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
    0, 10, 11, 12, 13, 14, 15,  0,  0,  0,  0,  0,  0,  0,  0,  0,
    0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
    0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
    0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
    0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
    0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
    0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
    0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
    0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
    0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
};

char* HttpServer::url_decode(const char *str) {
    int len = (int)strlen(str);
    char *tmp = (char *)malloc(len + 1);

    int i = 0, pos = 0;
    for (i = 0; i < len; i++) {
        if (str[i] != '%')
            tmp[pos] = str[i];
        else if (i + 2 >= len) {  /* check boundary */
            tmp[pos++] = '%';  /* keep it */
            if (++i >= len)
                break;
            tmp[pos] = str[i];
            break;
        }
        else if (isalnum(str[i + 1]) && isalnum(str[i + 2])) {
            tmp[pos] = (dec_tab[(unsigned char)str[i + 1]] << 4)
                + dec_tab[(unsigned char)str[i + 2]];
            i += 2;
        }
        else
            tmp[pos] = str[i];

        pos++;
    }

    tmp[pos] = '\0';
    return tmp;
}