c++ 读取、输出txt文件

下面这段话转自：https://blog.csdn.net/lightlater/article/details/6326338

关于文本文件的文件头

第一 ANSI文件的文件头为空，不需要处理；

第二 UNICODE文件的文件头为0xFF,0xFE共计两个字节，读取时需要偏移两个字节再行读取；

第三 UTF-8文件的文件头为0xEF,0xBB,0xBF共计三个字节，读取时需要偏移三个字节后再行读取；

 

1.ansi格式txt文件

void readAnsiTXT(){
    string filename = "ansi.txt";
    ifstream fin(filename.c_str());
    if (!fin.is_open()){
        cout << "open failed!
";
    }
    char ch;
    string msg = "";
    while (fin.get(ch)){
        msg += ch;
    }
    cout << msg << "
";
}

2.Unicode格式

转载：https://blog.csdn.net/hxfhq1314/article/details/80344669

memset函数:https://baike.baidu.com/item/memset/4747579?fr=aladdin

setlocal函数:https://www.runoob.com/cprogramming/c-function-setlocale.html

void readUnicodeTXT(){
    string filename = "unicode.txt";
    ifstream fin;
    fin.open(filename, ios::binary);
    fin.seekg(2, ios::beg);
    wstring wstrLine;
    while (!fin.eof())
    {
        wchar_t wch;
        fin.read((char *)(&wch), 2);
        wstrLine.append(1, wch);
    }
    string str = ws2s(wstrLine);
    str.erase(str.size()-1, 1);//删除结尾重复的一个字符
    cout << str << endl;
}

std::string ws2s(const std::wstring& ws)
{
    std::string curLocale = setlocale(LC_ALL, NULL); // C 库函数 char *setlocale(int category, const char *locale) 设置或读取地域化信息。
    setlocale(LC_ALL, "chs");
    const wchar_t* _Source = ws.c_str();
    size_t _Dsize = 2 * ws.size() + 1;
    char *_Dest = new char[_Dsize];
    memset(_Dest, 0, _Dsize);
    wcstombs(_Dest, _Source, _Dsize);
    std::string result = _Dest;
    delete[]_Dest;
    setlocale(LC_ALL, curLocale.c_str());
    return result;
}

utf8格式:

void readUtf8TXT(){
    string str = "utf8.txt";
    wstring res=L"";
    std::locale loc("chs");
    std::wcout.imbue(loc);
    std::wifstream wif(str, ios::binary);
    codecvt_utf8<wchar_t, 0x10ffff, std::consume_header>* codecvToUnicode = new codecvt_utf8<wchar_t, 0x10ffff, std::consume_header>;
    if (wif.is_open()){
        wif.imbue(std::locale(wif.getloc(), codecvToUnicode));
        wstring wline;
        while (getline(wif, wline)){
            wstring convert;
            for (auto c : wline){
                if (c != L'' && c != L'?') convert += c;
            }
            res = res + convert;        
        }
        wif.close();
    }    
    for (wstring::iterator i = res.begin(); i != res.end(); i++){//将res中的'
'换成'
'，否则输出异常
        if (*i == '
'){
            *i = '
';
        }
    }
    wcout << res << endl;
}

Windows下用std::wifstream读取Unicode和UTF-8文本

转载：http://101.132.192.87/2019/08/29/windows%e4%b8%8b%e7%94%a8stdwifstream%e8%af%bb%e5%8f%96unicode%e6%96%87%e6%9c%ac/

Windows下使用std::wifstream读取Unicode文本的方法：

std::locale loc("chs");                //windows下ok
    std::wcout.imbue(loc);
    // open as a byte stream
    std::wifstream wif("路径", std::ios::binary);
    std::codecvt_utf16<wchar_t, 0x10ffff, std::consume_header>* codecvtToUnicode = new std::codecvt_utf16 < wchar_t, 0x10ffff, std::consume_header >;
    if (wif.is_open())
    {
        // apply BOM-sensitive UTF-16 facet
        wif.imbue(std::locale(wif.getloc(), codecvtToUnicode));
        std::wstring wline;
        while (std::getline(wif, wline))
        {
            std::wstring convert;
            for (auto c : wline)
            {
                if (c != L'' && c != L'?')
                    convert += c;
            }
            wcout << convert << endl;
        }
        wif.close();
        //delete codecvtToUnicode;     //new和delete，应该不用手动delete,在哪里delete都会崩溃(亲测)
    }

Windows下使用std::wifstream读取UTF-8文本的方法：

std::locale loc("chs");                //windows下ok
    std::wcout.imbue(loc);
    // open as a byte stream
    std::wifstream wif("路径", std::ios::binary);
    std::codecvt_utf8<wchar_t, 0x10ffff, std::consume_header>* codecvtToUnicode = new std::codecvt_utf8 < wchar_t, 0x10ffff, std::consume_header >;
    if (wif.is_open())
    {
        // apply BOM-sensitive UTF-8 facet
        wif.imbue(std::locale(wif.getloc(), codecvtToUnicode));
        std::wstring wline;
        while (std::getline(wif, wline))
        {
            std::wstring convert;
            for (auto c : wline)
            {
                if (c != L'' && c != L'?')
                    convert += c;
            }
            wcout << convert << endl;
        }
        wif.close();
        //delete codecvtToUnicode;     //new和delete，应该不用手动delete,在哪里delete都会崩溃(亲测)
    }