c# - 在 c# 中等效于 'Base64' 在 c 编程中生成的加密字节的编码字符串将在 URL 查询字符串中发送

Question

我使用了来自网络的代码。但是在c程序中生成的结果与c#编码(ASCII、UTF-8等)不匹配。

在 c 中处理字符以克服此问题的最佳方法是什么？

这是基于 windows 的 exe。

对于文本“Í£kúæ›Ì”

in VC I get Base64 Encoded string as "zaNr+uabzADMzMzMpGICvnj/GAA2IUEAAQAAAA=="

但在 C# 中，我根据编码类型得到不同的结果

UTF-8 = > "K0FNMEFvdy1rK0FQb0E1aUE2QU13LQ=="
UTF-7 = > "w43Co2vDusOm4oC6w4w="

等等……C# 中的哪种编码/无编码会得到与 C 程序相同的结果。

#include <stdafx.h>
#include <locale.h>
#include "base64.h"

static const unsigned char pr2six[256] =
{
    /* ASCII table */
    64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64,
    64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64,
    64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 62, 64, 64, 64, 63,
    52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 64, 64, 64, 64, 64, 64,
    64,  0,  1,  2,  3,  4,  5,  6,  7,  8,  9, 10, 11, 12, 13, 14,
    15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 64, 64, 64, 64, 64,
    64, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40,
    41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 64, 64, 64, 64, 64,
    64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64,
    64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64,
    64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64,
    64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64,
    64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64,
    64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64,
    64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64,
    64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64
};

int Base64decode_len(const char *bufcoded)
{
    int nbytesdecoded;
    register const unsigned char *bufin;
    register int nprbytes;

    bufin = (const unsigned char *) bufcoded;
    while (pr2six[*(bufin++)] <= 63);

    nprbytes = (bufin - (const unsigned char *) bufcoded) - 1;
    nbytesdecoded = ((nprbytes + 3) / 4) * 3;

    return nbytesdecoded + 1;
}

int Base64decode(char *bufplain, const char *bufcoded)
{
    int nbytesdecoded;
    register const unsigned char *bufin;
    register unsigned char *bufout;
    register int nprbytes;

    bufin = (const unsigned char *) bufcoded;
    while (pr2six[*(bufin++)] <= 63);
    nprbytes = (bufin - (const unsigned char *) bufcoded) - 1;
    nbytesdecoded = ((nprbytes + 3) / 4) * 3;

    bufout = (unsigned char *) bufplain;
    bufin = (const unsigned char *) bufcoded;

    while (nprbytes > 4) {
    *(bufout++) =
        (unsigned char) (pr2six[*bufin] << 2 | pr2six[bufin[1]] >> 4);
    *(bufout++) =
        (unsigned char) (pr2six[bufin[1]] << 4 | pr2six[bufin[2]] >> 2);
    *(bufout++) =
        (unsigned char) (pr2six[bufin[2]] << 6 | pr2six[bufin[3]]);
    bufin += 4;
    nprbytes -= 4;
    }

    /* Note: (nprbytes == 1) would be an error, so just ingore that case */
    if (nprbytes > 1) {
    *(bufout++) =
        (unsigned char) (pr2six[*bufin] << 2 | pr2six[bufin[1]] >> 4);
    }
    if (nprbytes > 2) {
    *(bufout++) =
        (unsigned char) (pr2six[bufin[1]] << 4 | pr2six[bufin[2]] >> 2);
    }
    if (nprbytes > 3) {
    *(bufout++) =
        (unsigned char) (pr2six[bufin[2]] << 6 | pr2six[bufin[3]]);
    }

    *(bufout++) = '\0';
    nbytesdecoded -= (4 - nprbytes) & 3;
    return nbytesdecoded;
}

static const char basis_64[] =
    "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";

int Base64encode_len(int len)
{
    return ((len + 2) / 3 * 4) + 1;
}

int Base64encode(char *encoded, const char *string, int len)
{
    int i;
    char *p;

    p = encoded;
    for (i = 0; i < len - 2; i += 3) {
    *p++ = basis_64[(string[i] >> 2) & 0x3F];
    *p++ = basis_64[((string[i] & 0x3) << 4) |
                    ((int) (string[i + 1] & 0xF0) >> 4)];
    *p++ = basis_64[((string[i + 1] & 0xF) << 2) |
                    ((int) (string[i + 2] & 0xC0) >> 6)];
    *p++ = basis_64[string[i + 2] & 0x3F];
    }
    if (i < len) {
    *p++ = basis_64[(string[i] >> 2) & 0x3F];
    if (i == (len - 1)) {
        *p++ = basis_64[((string[i] & 0x3) << 4)];
        *p++ = '=';
    }
    else {
        *p++ = basis_64[((string[i] & 0x3) << 4) |
                        ((int) (string[i + 1] & 0xF0) >> 4)];
        *p++ = basis_64[((string[i + 1] & 0xF) << 2)];
    }
    *p++ = '=';
    }

    *p++ = '\0';
    return p - encoded;
}


int main() {
   char mysrc[] = "Hello world...";

    char mysrc[] = "Í£kúæ›Ì";
    char myb64[1024] = "";
    char mydst[1024] = "";

    //Base64encode(myb64, mysrc, 28);
    Base64encode(myb64, mysrc, strlen(mysrc); //corrected
    printf("The string\n[%s]\nencodes into base64 as:\n[%s]\n", mysrc, myb64);
    printf("\n");
    Base64decode(mydst, myb64);
    printf("The string\n[%s]\ndecodes from base64 as:\n[%s]\n", myb64, mydst);

    return 0;
}

Answer 1

您可以尝试使用 Encoding.GetEncoding("ISO-8859-1")，所以

Encoding encoding = Encoding.GetEncoding("ISO-8859-1");
string base64Encoded = Convert.ToBase64String(encoding.GetBytes("Í£kúæ›Ì"));

请注意，一般来说，您的问题是一个非常复杂的问题...参见示例 https://gcc.gnu.org/onlinedocs/cpp/Character-sets.html gcc关于源文件编码的页面。

请注意，此响应通常是错误的...因为问题非常复杂。 C/C++ 中的 char* 更类似于未编码的字节数组，而不是字符串。C 源文件中包含的字符串常量("something")是按源文件的编码方式编码的字节数组。在 Visual Studio 中，您可以通过执行文件 -> 另存为来选择它，然后单击保存按钮的小箭头，使用编码保存。例如:

printf("%d", strlen("è"));

如果文件的编码是 Windows-1252，将打印 1，如果文件的编码是 utf-8，将打印 2。

所以如果你想在 C# 中以相同的方式编码，你必须执行 Encoding.GetEncoding("encodingName")(或者 Encoding.UTF8 如果 C/C++ 文件是 UTF8 编码的)

但这仅适用于字符串常量!

例如，如果您执行 scanf("%s", str)(因此您从控制台接受一个字符串)，str 中字节的编码> 将是控制台的编码。如果您从 Windows 控件中获取字符串，则编码将是 Windows 的默认编码(因此在 C# 中为 Encoding.Default)。如果您读取外部文件，则 char* 将是文件的字节，因此 char* 的编码将是文件的编码。