C++ 實現包含中文字符用Base64編碼傳輸 和 解碼讀取數據

QT實現包含中文字符用base64編碼和解碼

#include <QCoreApplication>
#include <QDebug>
#include <QTextCodec>
//
QString GetCorrectUnicode(const QByteArray &ba)
{
    QTextCodec::ConverterState state;
    QTextCodec *codec = QTextCodec::codecForName("UTF-8");
    QString text = codec->toUnicode(ba.constData(), ba.size(), &state);
    if (state.invalidChars > 0)
    {
        text = QTextCodec::codecForName("GBK")->toUnicode(ba);
    }
    else
    {
        text = ba;
    }
    return text;
}

int main(int argc, char *argv[])
{
    QCoreApplication a(argc, argv);

    //包含中文的字符串，windows默認字符集是gbk
    QString text("adg/.\]1098&^%!@#$%^&*()_+][,`婦發水電asdfad費發送斯蒂芬sdfasdfa");
    /*因爲base64是基於unicode字符集的utf-8的二進制，然後每三個8Bit的字節轉換爲四個6Bit的字節
     * 先把gbk字符集轉換成unicode字符集的utf-8編碼
     */
    QByteArray str = text.toUtf8();
    //輸出用base64編碼後的字符
    qInfo()<<str.toBase64()<<endl;
    QByteArray param = str.toBase64();
    //用base64解碼 之前編碼得到的字符
    QByteArray arr = QByteArray::fromBase64(param);
    //因爲得到的是unicode字符集的utf-8編碼字符，而控制檯是gbk輸出，所以避免輸出亂碼，unicode轉gbk
    QString out = GetCorrectUnicode(arr);
    //輸出base64解碼後gbk輸出
    qInfo()<<out<<endl;
    
    return a.exec();
}

包含中文 base64編碼關鍵

Base64要求把每三個8Bit的字節轉換爲四個6Bit的字節（38 = 46 = 24），然後把6Bit再添兩位高位0，組成四個8Bit的字節，也就是說，轉換後的字符串理論上將要比原來的長1/3。

關於這個編碼的規則：
①.把3個字節變成4個字節。
②每76個字符加一個換行符。
③.最後的結束符也要處理。

例：
轉換前 10101101,10111010,01110110
轉換後 00101011, 00011011 ,00101001 ,00110110
十進制 43 27 41 54
對應碼錶中的值 r b p 2
所以上面的24位編碼，編碼後的Base64值爲 rbp2
解碼同理，把 rbq2 的二進制位連接上再重組得到三個8位值，得出原碼。

包含中文處理

    //1、包含中文的字符串 字符編碼（windows默認是gbk）轉換成unicode
    //2、字符編碼方式是utf-8的二進制
    //代碼
    //3、用base64對utf-8編碼的二進制處理
    //代碼
    //4、得到base64編碼的字符
    //代碼
    //5、用base64解碼得到tuf-8編碼的二進制
    //6、把utf-8編碼的unicode字符集轉換成gbk輸出（保證控制檯默認gbk輸出中文不亂碼）
    //代碼

VS上C++ 包含中文字符 實現base64編碼和解碼

win32 控制檯應用程序

#include "stdafx.h"
#include <string.h>
#include <stdlib.h>
#include <wchar.h> 
#include <assert.h>
#include <windows.h>
#include <iostream>
using namespace std;
typedef unsigned char     uint8;
typedef unsigned long    uint32;

static uint8 alphabet_map[] = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
static uint8 reverse_map[] =
{
255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255,
	255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255,
	255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 62, 255, 255, 255, 63,
	52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 255, 255, 255, 255, 255, 255,
	255, 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, 255, 255, 255, 255, 255,
	255, 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, 255, 255, 255, 255, 255
};

uint32 base64_encode(const uint8 *text, uint32 text_len, uint8 *encode)
{
	uint32 i, j;
	for (i = 0, j = 0; i + 3 <= text_len; i += 3)
	{
		encode[j++] = alphabet_map[text[i] >> 2];                             //取出第一個字符的前6位並找出對應的結果字符
		encode[j++] = alphabet_map[((text[i] << 4) & 0x30) | (text[i + 1] >> 4)];     //將第一個字符的後2位與第二個字符的前4位進行組合並找到對應的結果字符
		encode[j++] = alphabet_map[((text[i + 1] << 2) & 0x3c) | (text[i + 2] >> 6)];   //將第二個字符的後4位與第三個字符的前2位組合並找出對應的結果字符
		encode[j++] = alphabet_map[text[i + 2] & 0x3f];                         //取出第三個字符的後6位並找出結果字符
	}

	if (i < text_len)
	{
		uint32 tail = text_len - i;
		if (tail == 1)
		{
			encode[j++] = alphabet_map[text[i] >> 2];
			encode[j++] = alphabet_map[(text[i] << 4) & 0x30];
			encode[j++] = '=';
			encode[j++] = '=';
		}
		else //tail==2
		{
			encode[j++] = alphabet_map[text[i] >> 2];
			encode[j++] = alphabet_map[((text[i] << 4) & 0x30) | (text[i + 1] >> 4)];
			encode[j++] = alphabet_map[(text[i + 1] << 2) & 0x3c];
			encode[j++] = '=';
		}
	}
	return j;
}

uint32 base64_decode(const uint8 *code, uint32 code_len, uint8 *plain)
{
	assert((code_len & 0x03) == 0);  //如果它的條件返回錯誤，則終止程序執行。4的倍數。

	uint32 i, j = 0;
	uint8 quad[4];
	for (i = 0; i < code_len; i += 4)
	{
		for (uint32 k = 0; k < 4; k++)
		{
			quad[k] = reverse_map[code[i + k]];//分組，每組四個分別依次轉換爲base64表內的十進制數
		}

		assert(quad[0] < 64 && quad[1] < 64);

		plain[j++] = (quad[0] << 2) | (quad[1] >> 4); //取出第一個字符對應base64表的十進制數的前6位與第二個字符對應base64表的十進制數的前2位進行組合

		if (quad[2] >= 64)
			break;
		else if (quad[3] >= 64)
		{
			plain[j++] = (quad[1] << 4) | (quad[2] >> 2); //取出第二個字符對應base64表的十進制數的後4位與第三個字符對應base64表的十進制數的前4位進行組合
			break;
		}
		else
		{
			plain[j++] = (quad[1] << 4) | (quad[2] >> 2);
			plain[j++] = (quad[2] << 6) | quad[3];//取出第三個字符對應base64表的十進制數的後2位與第4個字符進行組合
		}
	}
	return j;
}

//GB2312到UTF-8的轉換
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;
}
//UTF-8到GB2312的轉換
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;
}

int main(void)
{
	//1、包含中文的字符串 字符編碼（windows默認是gbk）轉換成unicode
	char input[256] = "lsadfakdf;sdfkjsldf數量的飛機上的浪費";
	//2、字符編碼方式是utf-8的二進制
	uint8 *text = (uint8 *)G2U(input);
	uint32 text_len = (uint32)strlen((char *)text);
	uint8 buffer[1024], buffer2[4096];
	//3、用base64對utf - 8編碼的二進制處理
	//4、得到base64編碼的字符
	uint32 size = base64_encode(text, text_len, buffer2);
	buffer2[size] = 0;
	printf("%s\n", buffer2);
	//5、用base64解碼得到tuf-8編碼的二進制
	
	size = base64_decode(buffer2, size, buffer);
	buffer[size] = 0;
	/* printf("%s\n", buffer);*/

	char str[1024] = "";
	strcpy_s(str,1024,(char *)buffer);
	//6、把utf-8編碼的unicode字符集轉換成gbk輸出（保證控制檯默認gbk輸出中文不亂碼）
	printf("%s\n", U2G(str));
	return 0;
}

瀏覽器端網頁裏JS 用Base64編碼和解碼 包含中文和其他字符的字符串

<html>

<head>
    <script>
	var base64EncodeChars = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
var base64DecodeChars = new Array(-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 62, -1, -1, -1, 63, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, -1, -1, -1, -1, -1, -1, -1, 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, -1, -1, -1, -1, -1, -1, 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, -1, -1, -1, -1, -1);
/**
 * base64編碼
 * @param {Object} str
 */
function base64encode(str){
    var out, i, len;
    var c1, c2, c3;
    len = str.length;
    i = 0;
    out = "";
    while (i < len) {
        c1 = str.charCodeAt(i++) & 0xff;
        if (i == len) {
            out += base64EncodeChars.charAt(c1 >> 2);
            out += base64EncodeChars.charAt((c1 & 0x3) << 4);
            out += "==";
            break;
        }
        c2 = str.charCodeAt(i++);
        if (i == len) {
            out += base64EncodeChars.charAt(c1 >> 2);
            out += base64EncodeChars.charAt(((c1 & 0x3) << 4) | ((c2 & 0xF0) >> 4));
            out += base64EncodeChars.charAt((c2 & 0xF) << 2);
            out += "=";
            break;
        }
        c3 = str.charCodeAt(i++);
        out += base64EncodeChars.charAt(c1 >> 2);
        out += base64EncodeChars.charAt(((c1 & 0x3) << 4) | ((c2 & 0xF0) >> 4));
        out += base64EncodeChars.charAt(((c2 & 0xF) << 2) | ((c3 & 0xC0) >> 6));
        out += base64EncodeChars.charAt(c3 & 0x3F);
    }
    return out;
}
/**
 * base64解碼
 * @param {Object} str
 */
function base64decode(str){
    var c1, c2, c3, c4;
    var i, len, out;
    len = str.length;
    i = 0;
    out = "";
    while (i < len) {
        /* c1 */
        do {
            c1 = base64DecodeChars[str.charCodeAt(i++) & 0xff];
        }
        while (i < len && c1 == -1);
        if (c1 == -1) 
            break;
        /* c2 */
        do {
            c2 = base64DecodeChars[str.charCodeAt(i++) & 0xff];
        }
        while (i < len && c2 == -1);
        if (c2 == -1) 
            break;
        out += String.fromCharCode((c1 << 2) | ((c2 & 0x30) >> 4));
        /* c3 */
        do {
            c3 = str.charCodeAt(i++) & 0xff;
            if (c3 == 61) 
                return out;
            c3 = base64DecodeChars[c3];
        }
        while (i < len && c3 == -1);
        if (c3 == -1) 
            break;
        out += String.fromCharCode(((c2 & 0XF) << 4) | ((c3 & 0x3C) >> 2));
        /* c4 */
        do {
            c4 = str.charCodeAt(i++) & 0xff;
            if (c4 == 61) 
                return out;
            c4 = base64DecodeChars[c4];
        }
        while (i < len && c4 == -1);
        if (c4 == -1) 
            break;
        out += String.fromCharCode(((c3 & 0x03) << 6) | c4);
    }
    return out;
}
/**
 * utf16轉utf8
 * @param {Object} str
 */
function utf16to8(str){
    var out, i, len, c;
    out = "";
    len = str.length;
    for (i = 0; i < len; i++) {
        c = str.charCodeAt(i);
        if ((c >= 0x0001) && (c <= 0x007F)) {
            out += str.charAt(i);
        }
        else 
            if (c > 0x07FF) {
                out += String.fromCharCode(0xE0 | ((c >> 12) & 0x0F));
                out += String.fromCharCode(0x80 | ((c >> 6) & 0x3F));
                out += String.fromCharCode(0x80 | ((c >> 0) & 0x3F));
            }
            else {
                out += String.fromCharCode(0xC0 | ((c >> 6) & 0x1F));
                out += String.fromCharCode(0x80 | ((c >> 0) & 0x3F));
            }
    }
    return out;
}
/**
 * utf8轉utf16
 * @param {Object} str
 */
function utf8to16(str){
    var out, i, len, c;
    var char2, char3;
    out = "";
    len = str.length;
    i = 0;
    while (i < len) {
        c = str.charCodeAt(i++);
        switch (c >> 4) {
            case 0:
            case 1:
            case 2:
            case 3:
            case 4:
            case 5:
            case 6:
            case 7:
                // 0xxxxxxx
                out += str.charAt(i - 1);
                break;
            case 12:
            case 13:
                // 110x xxxx 10xx xxxx
                char2 = str.charCodeAt(i++);
                out += String.fromCharCode(((c & 0x1F) << 6) | (char2 & 0x3F));
                break;
            case 14:
                // 1110 xxxx10xx xxxx10xx xxxx
                char2 = str.charCodeAt(i++);
                char3 = str.charCodeAt(i++);
                out += String.fromCharCode(((c & 0x0F) << 12) | ((char2 & 0x3F) << 6) | ((char3 & 0x3F) << 0));
                break;
        }
    }
    return out;
}
   //1、包含中文的字符串 字符編碼（windows默認是gbk）轉換成unicode
    //2、字符編碼方式是utf-8的二進制
    //代碼
    //3、用base64對utf-8編碼的二進制處理
    //代碼
    //4、得到base64編碼的字符
    //代碼
    //5、用base64解碼得到tuf-8編碼的二進制
    //6、把utf-8編碼的unicode字符集轉換成gbk輸出（保證控制檯默認gbk輸出中文不亂碼）
    //代碼
        function onSyncPayInvokeMethodClicked(){
        //1、包含中文的字符串 字符編碼（windows默認是gbk）轉換成unicode
        //2、字符編碼方式是utf-8的二進制
            var array = "包含中文和其他字符的字符串";
            //3、用base64對utf-8編碼的二進制處理
            var encode = base64encode(utf16to8(array));
			//5、用base64解碼得到tuf-8編碼的二進制
    //6、把utf-8編碼的unicode字符集轉換成gbk輸出（保證控制檯默認gbk輸出中文不亂碼）
			var decode = utf8to16(base64decode(encode));
        }

    </script>
</head>

<body onload="onLoad()" id="main">
    <h1 align="center" style="font-size:12pt; font-family:MS Shell Dlg 2;">Web Area</h1>
  
    <div align="center">
        <br />
        <br />
        <input type="button" value="測試按鈕" onclick="onSyncPayInvokeMethodClicked()" />
        <br />
        <br />

    </div>

</body>

</html>