如何在 C++ 中将字符串从十进制代码转换为西里尔文/unicode16？

Posted 2023-02-22

【中文标题】如何在 C++ 中将字符串从十进制代码转换为西里尔文/unicode16？

【英文标题】：How to convert string from decimal code to cyrillic / unicode16 in C++?

【发布时间】：2021-02-03 21:54:33

【问题描述】：

在我的 c++ 程序中，我有一个“十进制代码字符串”，我想使用 unicode 字符将它打印到一个文件中。

这是十进制代码字符串：квартира 这是西里尔解码后的字符串：Квартира 这是我的代码：

#include "stdafx.h"
#include<iostream>
#include<algorithm>
#include<cmath>
#include<cstdio>

using namespace std;

int _tmain(int argc, _TCHAR* argv[])

// string I have:
string decimal_code_string = "&#1082;&#1074;&#1072;&#1088;&#1090;&#1080;&#1088;&#1072;";

FILE *stream;
fopen_s( &stream, "C:\\Users\\Luze\\Desktop\\myFile.txt", "w+, ccs=UTF-8" );
//printf("--> %s", decimal_code_string.c_str()); 
// string I would like to write: "Квартира"
fwprintf(stream, L"%hs", decimal_code_string.c_str());
fclose(stream);

return 0;

[编辑]

我尝试了@MarkRansom 解决方案，但它似乎不起作用：

#include "stdafx.h"
#include<iostream>
#include<algorithm>
#include<cmath>
#include<cstdio>

using namespace std;

std::string wchar_to_UTF8(const wchar_t * in)

    std::string out;
    unsigned int codepoint = 0;
    for (in;  *in != 0;  ++in)
    
        if (*in >= 0xd800 && *in <= 0xdbff)
            codepoint = ((*in - 0xd800) << 10) + 0x10000;
        else
        
            if (*in >= 0xdc00 && *in <= 0xdfff)
                codepoint |= *in - 0xdc00;
            else
                codepoint = *in;

            if (codepoint <= 0x7f)
                out.append(1, static_cast<char>(codepoint));
            else if (codepoint <= 0x7ff)
            
                out.append(1, static_cast<char>(0xc0 | ((codepoint >> 6) & 0x1f)));
                out.append(1, static_cast<char>(0x80 | (codepoint & 0x3f)));
            
            else if (codepoint <= 0xffff)
            
                out.append(1, static_cast<char>(0xe0 | ((codepoint >> 12) & 0x0f)));
                out.append(1, static_cast<char>(0x80 | ((codepoint >> 6) & 0x3f)));
                out.append(1, static_cast<char>(0x80 | (codepoint & 0x3f)));
            
            else
            
                out.append(1, static_cast<char>(0xf0 | ((codepoint >> 18) & 0x07)));
                out.append(1, static_cast<char>(0x80 | ((codepoint >> 12) & 0x3f)));
                out.append(1, static_cast<char>(0x80 | ((codepoint >> 6) & 0x3f)));
                out.append(1, static_cast<char>(0x80 | (codepoint & 0x3f)));
            
            codepoint = 0;
        
    
    return out;


std::wstring UTF8_to_wchar(const char * in)

    std::wstring out;
    unsigned int codepoint;
    while (*in != 0)
    
        unsigned char ch = static_cast<unsigned char>(*in);
        if (ch <= 0x7f)
            codepoint = ch;
        else if (ch <= 0xbf)
            codepoint = (codepoint << 6) | (ch & 0x3f);
        else if (ch <= 0xdf)
            codepoint = ch & 0x1f;
        else if (ch <= 0xef)
            codepoint = ch & 0x0f;
        else
            codepoint = ch & 0x07;
        ++in;
        if (((*in & 0xc0) != 0x80) && (codepoint <= 0x10ffff))
        
            if (sizeof(wchar_t) > 2)
                out.append(1, static_cast<wchar_t>(codepoint));
            else if (codepoint > 0xffff)
            
                out.append(1, static_cast<wchar_t>(0xd800 + (codepoint >> 10)));
                out.append(1, static_cast<wchar_t>(0xdc00 + (codepoint & 0x03ff)));
            
            else if (codepoint < 0xd800 || codepoint >= 0xe000)
                out.append(1, static_cast<wchar_t>(codepoint));
        
    
    return out;


int _tmain(int argc, _TCHAR* argv[])

string decimal_code_string = "&#1082;&#1074;&#1072;&#1088;&#1090;&#1080;&#1088;&#1072;";
printf("decimal_code: %s\n", decimal_code_string.c_str());
 
// string I would like to write: "Квартира"

wstring temp_string = wstring(decimal_code_string.begin(), decimal_code_string.end());
const wchar_t* result = temp_string.c_str();
string utf8_string=  wchar_to_UTF8( result );
printf("wchar_to_UTF8: %s\n", utf8_string);

const char* resultcp = decimal_code_string.c_str();
wstring wide_string = UTF8_to_wchar( resultcp );
printf("UTF8_to_wchar: %s\n", wide_string);
 
cout << "End\n";
return 0;

【问题讨论】：

这能回答你的问题吗？ How to decode html Entities in C?

@trentcl 该问题的最高投票答案转换为 UTF-8，而不是宽字符。

@MarkRansom 可以适配UTF-16等

@tadman 是的，我知道，我什至在 *** 上有一些代码可以做到这一点：***.com/a/148766/5987。看起来有些人急于将其作为副本关闭，但事实并非如此。

我链接到的代码并不是整个解决方案，而是要与@trentcl 提供的答案相结合。

【参考方案1】：

只需提取每个字符内的数字实体：这正是该字符的 Unicode/UTF32 代码。

提取该字符串后，您可以使用任何 UTF32 到 UTF8 字符串转换算法，例如实验性的 StringSuite C++20 库。