Convert a unicode String In C++ To Upper Case

后端 未结 9 2066
予麋鹿
予麋鹿 2020-12-01 14:51

How we can convert a multi language string or unicode string to upper/lower case in C or C++.

相关标签:
9条回答
  • 2020-12-01 15:09

    If your system is already in UTF-8, by using std::use_facet, you can write:

    #include <iostream>
    #include <locale.h>
    
    int main() {
        std::locale::global(std::locale(""));  // (*)
        std::wcout.imbue(std::locale());
        auto& f = std::use_facet<std::ctype<wchar_t>>(std::locale());
    
        std::wstring str = L"Zoë Saldaña played in La maldición del padre Cardona.";
    
        f.toupper(&str[0], &str[0] + str.size());
        std::wcout << str << std::endl;
    
        return 0;
    }
    

    And you get (http://ideone.com/AFHoHC):

    ZOË SALDAÑA PLAYED IN LA MALDICIÓN DEL PADRE CARDONA.

    If it don't work you will have to change (*) into std::locale::global(std::locale("en_US.UTF8")); or an UTF-8 locale you actually have on the plateform.

    0 讨论(0)
  • 2020-12-01 15:09

    Set the locale first, example :

    setlocale(LC_ALL, "German")); /*This won't work as per comments below */
    
    setlocale(LC_ALL, "English"));
    
    setlocale( LC_MONETARY, "French" );
    
    setlocale( LC_ALL, "" ); //default locale 
    

    Then use

    std::use_facet std::locale as follows:-

    typedef std::string::value_type char_t;
    char_t upcase( char_t ch )
    {
     return std::use_facet< std::ctype< char_t > >( std::locale() ).toupper( ch );
    }
    
    std::string toupper( const std::string &src )
    {
     std::string result;
     std::transform( src.begin(), src.end(), std::back_inserter( result ), upcase );
     return result;
    }
    
    const std::string src  = "Hello World!";
    std::cout << toupper( src );
    
    0 讨论(0)
  • 2020-12-01 15:16

    Based on Kyle_the_hacker's -----> answer with my extras.

    Ubuntu

    In terminal List all locales
    locale -a

    Install all locales
    sudo apt-get install -y locales locales-all

    Compile main.cpp
    $ g++ main.cpp

    Run compiled program
    $ ./a.out

    Results

    Zoë Saldaña played in La maldición del padre Cardona. ëèñ αω óóChloë
    Zoë Saldaña played in La maldición del padre Cardona. ëèñ αω óóChloë
    ZOË SALDAÑA PLAYED IN LA MALDICIÓN DEL PADRE CARDONA. ËÈÑ ΑΩ ÓÓCHLOË
    ZOË SALDAÑA PLAYED IN LA MALDICIÓN DEL PADRE CARDONA. ËÈÑ ΑΩ ÓÓCHLOË
    zoë saldaña played in la maldición del padre cardona. ëèñ αω óóchloë
    zoë saldaña played in la maldición del padre cardona. ëèñ αω óóchloë
    

    Windows

    In cmd run VCVARS developer tools
    "C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Auxiliary\Build\vcvars64.bat"

    Compile main.cpp
    > cl /EHa main.cpp /D "_DEBUG" /D "_CONSOLE" /D "_UNICODE" /D "UNICODE" /std:c++17 /DYNAMICBASE "kernel32.lib" "user32.lib" "gdi32.lib" "winspool.lib" "comdlg32.lib" "advapi32.lib" "shell32.lib" "ole32.lib" "oleaut32.lib" "uuid.lib" "odbc32.lib" "odbccp32.lib" /MTd

    Compilador de optimización de C/C++ de Microsoft (R) versión 19.27.29111 para x64
    (C) Microsoft Corporation. Todos los derechos reservados.
    
    main.cpp
    Microsoft (R) Incremental Linker Version 14.27.29111.0
    Copyright (C) Microsoft Corporation.  All rights reserved.
    
    /out:main.exe
    main.obj
    kernel32.lib
    user32.lib
    gdi32.lib
    winspool.lib
    comdlg32.lib
    advapi32.lib
    shell32.lib
    ole32.lib
    oleaut32.lib
    uuid.lib
    odbc32.lib
    odbccp32.lib
    

    Run main.exe
    >main.exe

    Results

    Zoë Saldaña played in La maldición del padre Cardona. ëèñ αω óóChloë
    Zoë Saldaña played in La maldición del padre Cardona. ëèñ αω óóChloë
    ZOË SALDAÑA PLAYED IN LA MALDICIÓN DEL PADRE CARDONA. ËÈÑ ΑΩ ÓÓCHLOË
    ZOË SALDAÑA PLAYED IN LA MALDICIÓN DEL PADRE CARDONA. ËÈÑ ΑΩ ÓÓCHLOË
    zoë saldaña played in la maldición del padre cardona. ëèñ αω óóchloë
    zoë saldaña played in la maldición del padre cardona. ëèñ αω óóchloë
    

    The code - main.cpp

    This code was only tested on Windows x64 and Ubuntu Linux x64.

    /*
     * Filename: c:\Users\x\Cpp\main.cpp
     * Path: c:\Users\x\Cpp
     * Filename: /home/x/Cpp/main.cpp
     * Path: /home/x/Cpp
     * Created Date: Saturday, October 17th 2020, 10:43:31 pm
     * Author: Joma
     *
     * No Copyright 2020
     */
    
    #include <iostream>
    #include <locale>
    #include <string>
    #include <algorithm>
    #include <set>
    #include <cstdlib>
    #include <clocale>
    
    #if defined(_WIN32)
    #define WINDOWSLIB 1
    #define DLLCALL STDCALL
    #define DLLIMPORT _declspec(dllimport)
    #define DLLEXPORT _declspec(dllexport)
    #define DLLPRIVATE
    
    #define NOMINMAX
    #include <Windows.h>
    #include <objbase.h>
    #include <filesystem>
    #include <intrin.h>
    #include <conio.h>
    
    #elif defined(__ANDROID__) || defined(ANDROID) //Android
    #define ANDROIDLIB 1
    #define DLLCALL CDECL
    #define DLLIMPORT
    #define DLLEXPORT __attribute__((visibility("default")))
    #define DLLPRIVATE __attribute__((visibility("hidden")))
    
    #elif defined(__APPLE__) //iOS, Mac OS
    #define MACOSLIB 1
    #define DLLCALL CDECL
    #define DLLIMPORT
    #define DLLEXPORT __attribute__((visibility("default")))
    #define DLLPRIVATE __attribute__((visibility("hidden")))
    
    #elif defined(__LINUX__) || defined(__gnu_linux__) || defined(__linux__) || defined(__linux) || defined(linux) //_Ubuntu - Fedora - Centos - RedHat
    #define LINUXLIB 1
    #include <cpuid.h>
    #include <experimental/filesystem>
    #include <unistd.h>
    #include <termios.h>
    #define DLLCALL CDECL
    #define DLLIMPORT
    #define DLLEXPORT __attribute__((visibility("default")))
    #define DLLPRIVATE __attribute__((visibility("hidden")))
    #define CoTaskMemAlloc(p) malloc(p)
    #define CoTaskMemFree(p) free(p)
    
    #elif defined(__EMSCRIPTEN__)
    #define EMSCRIPTENLIB 1
    #include <unistd.h>
    #include <termios.h>
    #define DLLCALL
    #define DLLIMPORT
    #define DLLEXPORT __attribute__((visibility("default")))
    #define DLLPRIVATE __attribute__((visibility("hidden")))
    
    #endif
    
    typedef std::string String;
    typedef std::wstring WString;
    #define LINE_FEED_CHAR (static_cast<char>(10))
    
    enum class ConsoleTextStyle
    {
        DEFAULT = 0,
        BOLD = 1,
        FAINT = 2,
        ITALIC = 3,
        UNDERLINE = 4,
        SLOW_BLINK = 5,
        RAPID_BLINK = 6,
        REVERSE = 7,
    };
    
    enum class ConsoleForeground
    {
        DEFAULT = 39,
        BLACK = 30,
        DARK_RED = 31,
        DARK_GREEN = 32,
        DARK_YELLOW = 33,
        DARK_BLUE = 34,
        DARK_MAGENTA = 35,
        DARK_CYAN = 36,
        GRAY = 37,
        DARK_GRAY = 90,
        RED = 91,
        GREEN = 92,
        YELLOW = 93,
        BLUE = 94,
        MAGENTA = 95,
        CYAN = 96,
        WHITE = 97
    };
    
    enum class ConsoleBackground
    {
        DEFAULT = 49,
        BLACK = 40,
        DARK_RED = 41,
        DARK_GREEN = 42,
        DARK_YELLOW = 43,
        DARK_BLUE = 44,
        DARK_MAGENTA = 45,
        DARK_CYAN = 46,
        GRAY = 47,
        DARK_GRAY = 100,
        RED = 101,
        GREEN = 102,
        YELLOW = 103,
        BLUE = 104,
        MAGENTA = 105,
        CYAN = 106,
        WHITE = 107
    };
    
    class Console
    {
    public:
        static void Clear();
        static void WriteLine(const String &s, ConsoleForeground foreground = ConsoleForeground::DEFAULT, ConsoleBackground background = ConsoleBackground::DEFAULT, std::set<ConsoleTextStyle> styles = {});
        static void Write(const String &s, ConsoleForeground foreground = ConsoleForeground::DEFAULT, ConsoleBackground background = ConsoleBackground::DEFAULT, std::set<ConsoleTextStyle> styles = {});
        static void WriteLine(const WString &s, ConsoleForeground foreground = ConsoleForeground::DEFAULT, ConsoleBackground background = ConsoleBackground::DEFAULT, std::set<ConsoleTextStyle> styles = {});
        static void Write(const WString &s, ConsoleForeground foreground = ConsoleForeground::DEFAULT, ConsoleBackground background = ConsoleBackground::DEFAULT, std::set<ConsoleTextStyle> styles = {});
        static void WriteLine();
        static void Pause();
        static int PauseAny(bool printWhenPressed = false);
    
    private:
        static void EnableVirtualTermimalProcessing();
        static void SetVirtualTerminalFormat(ConsoleForeground foreground, ConsoleBackground background, std::set<ConsoleTextStyle> styles);
        static void ResetTerminalFormat();
    };
    
    class Strings
    {
    public:
        static String WideStringToString(const WString &wstr);
        static WString StringToWideString(const String &str);
        static WString ToUpper(const WString &data);
        static String ToUpper(const String &data);
        static WString ToLower(const WString &data);
        static String ToLower(const String &data);
    };
    
    String Strings::WideStringToString(const WString &wstr)
    {
        if (wstr.empty())
        {
            return String();
        }
        size_t pos;
        size_t begin = 0;
        String ret;
        size_t size;
    #ifdef WINDOWSLIB
        pos = wstr.find(static_cast<wchar_t>(0), begin);
        while (pos != WString::npos && begin < wstr.length())
        {
            WString segment = WString(&wstr[begin], pos - begin);
            wcstombs_s(&size, nullptr, 0, &segment[0], _TRUNCATE);
            String converted = String(size, 0);
            wcstombs_s(&size, &converted[0], size, &segment[0], _TRUNCATE);
            ret.append(converted);
            begin = pos + 1;
            pos = wstr.find(static_cast<wchar_t>(0), begin);
        }
        if (begin <= wstr.length())
        {
            WString segment = WString(&wstr[begin], wstr.length() - begin);
            wcstombs_s(&size, nullptr, 0, &segment[0], _TRUNCATE);
            String converted = String(size, 0);
            wcstombs_s(&size, &converted[0], size, &segment[0], _TRUNCATE);
            converted.resize(size - 1);
            ret.append(converted);
        }
    #elif defined LINUXLIB
        pos = wstr.find(static_cast<wchar_t>(0), begin);
        while (pos != WString::npos && begin < wstr.length())
        {
            WString segment = WString(&wstr[begin], pos - begin);
            size = wcstombs(nullptr, segment.c_str(), 0);
            String converted = String(size, 0);
            wcstombs(&converted[0], segment.c_str(), converted.size());
            ret.append(converted);
            ret.append({0});
            begin = pos + 1;
            pos = wstr.find(static_cast<wchar_t>(0), begin);
        }
        if (begin <= wstr.length())
        {
            WString segment = WString(&wstr[begin], wstr.length() - begin);
            size = wcstombs(nullptr, segment.c_str(), 0);
            String converted = String(size, 0);
            wcstombs(&converted[0], segment.c_str(), converted.size());
            ret.append(converted);
        }
    #elif defined MACOSLIB
    #endif
    
        return ret;
    }
    
    WString Strings::StringToWideString(const String &str)
    {
        if (str.empty())
        {
            return WString();
        }
    
        size_t pos;
        size_t begin = 0;
        WString ret;
        size_t size;
    
    #ifdef WINDOWSLIB
        pos = str.find(static_cast<char>(0), begin);
        while (pos != String::npos)
        {
            String segment = String(&str[begin], pos - begin);
            WString converted = WString(segment.size() + 1, 0);
    
            mbstowcs_s(&size, &converted[0], converted.size(), &segment[0], _TRUNCATE);
            converted.resize(size - 1);
            ret.append(converted);
            ret.append({0});
            begin = pos + 1;
            pos = str.find(static_cast<char>(0), begin);
        }
        if (begin < str.length())
        {
            String segment = String(&str[begin], str.length() - begin);
            WString converted = WString(segment.size() + 1, 0);
            mbstowcs_s(&size, &converted[0], converted.size(), &segment[0], _TRUNCATE);
            converted.resize(size - 1);
            ret.append(converted);
        }
    #elif defined LINUXLIB
        pos = str.find(static_cast<char>(0), begin);
        while (pos != String::npos)
        {
            String segment = String(&str[begin], pos - begin);
            WString converted = WString(segment.size(), 0);
            size = mbstowcs(&converted[0], &segment[0], converted.size());
            converted.resize(size);
            ret.append(converted);
            ret.append({0});
            begin = pos + 1;
            pos = str.find(static_cast<char>(0), begin);
        }
        if (begin < str.length())
        {
            String segment = String(&str[begin], str.length() - begin);
            WString converted = WString(segment.size(), 0);
            size = mbstowcs(&converted[0], &segment[0], converted.size());
            converted.resize(size);
            ret.append(converted);
        }
    #elif defined MACOSLIB
    #endif
    
        return ret;
    }
    
    WString Strings::ToUpper(const WString &data)
    {
        WString result = data;
        auto &f = std::use_facet<std::ctype<wchar_t>>(std::locale());
    
        f.toupper(&result[0], &result[0] + result.size());
        return result;
    }
    
    String Strings::ToUpper(const String &data)
    {
        return WideStringToString(ToUpper(StringToWideString(data)));
    }
    
    WString Strings::ToLower(const WString &data)
    {
        WString result = data;
        auto &f = std::use_facet<std::ctype<wchar_t>>(std::locale());
        f.tolower(&result[0], &result[0] + result.size());
        return result;
    }
    
    String Strings::ToLower(const String &data)
    {
        return WideStringToString(ToLower(StringToWideString(data)));
    }
    
    void Console::Clear()
    {
    
    #ifdef WINDOWSLIB
        std::system(u8"cls");
    #elif defined LINUXLIB
        std::system(u8"clear");
    #elif defined EMSCRIPTENLIB
        emscripten::val::global()["console"].call<void>(u8"clear");
    #elif defined MACOSLIB
    #endif
    }
    
    void Console::Pause()
    {
        char c;
        do
        {
            c = getchar();
        } while (c != LINE_FEED_CHAR);
    }
    
    int Console::PauseAny(bool printWhenPressed)
    {
        int ch;
    #ifdef WINDOWSLIB
        ch = _getch();
    #elif defined LINUXLIB
        struct termios oldt, newt;
        tcgetattr(STDIN_FILENO, &oldt);
        newt = oldt;
        newt.c_lflag &= ~(ICANON | ECHO);
        tcsetattr(STDIN_FILENO, TCSANOW, &newt);
        ch = getchar();
        tcsetattr(STDIN_FILENO, TCSANOW, &oldt);
    #elif defined MACOSLIB
    #endif
        return ch;
    }
    
    void Console::EnableVirtualTermimalProcessing()
    {
    #if defined WINDOWSLIB
        HANDLE hOut = GetStdHandle(STD_OUTPUT_HANDLE);
        DWORD dwMode = 0;
        GetConsoleMode(hOut, &dwMode);
        if (!(dwMode & ENABLE_VIRTUAL_TERMINAL_PROCESSING))
        {
            dwMode |= ENABLE_VIRTUAL_TERMINAL_PROCESSING;
            SetConsoleMode(hOut, dwMode);
        }
    #endif
    }
    
    void Console::ResetTerminalFormat()
    {
        std::cout << u8"\033[0m";
    }
    
    void Console::SetVirtualTerminalFormat(ConsoleForeground foreground, ConsoleBackground background, std::set<ConsoleTextStyle> styles)
    {
        String format = u8"\033[";
        format.append(std::to_string(static_cast<int>(foreground)));
        format.append(u8";");
        format.append(std::to_string(static_cast<int>(background)));
        if (styles.size() > 0)
        {
            for (auto it = styles.begin(); it != styles.end(); ++it)
            {
                format.append(u8";");
                format.append(std::to_string(static_cast<int>(*it)));
            }
        }
        format.append(u8"m");
        std::cout << format;
    }
    
    void Console::Write(const String &s, ConsoleForeground foreground, ConsoleBackground background, std::set<ConsoleTextStyle> styles)
    {
        EnableVirtualTermimalProcessing();
        SetVirtualTerminalFormat(foreground, background, styles);
        String str = s;
    #ifdef WINDOWSLIB
        WString unicode = Strings::StringToWideString(str);
        WriteConsole(GetStdHandle(STD_OUTPUT_HANDLE), unicode.c_str(), static_cast<DWORD>(unicode.length()), nullptr, nullptr);
    #elif defined LINUXLIB
        std::cout << str;
    #elif defined MACOSLIB
    #endif
        ResetTerminalFormat();
    }
    
    void Console::WriteLine(const String &s, ConsoleForeground foreground, ConsoleBackground background, std::set<ConsoleTextStyle> styles)
    {
        Write(s, foreground, background, styles);
        std::cout << std::endl;
    }
    
    void Console::Write(const WString &s, ConsoleForeground foreground, ConsoleBackground background, std::set<ConsoleTextStyle> styles)
    {
        EnableVirtualTermimalProcessing();
        SetVirtualTerminalFormat(foreground, background, styles);
        WString str = s;
    
    #ifdef WINDOWSLIB
        WriteConsole(GetStdHandle(STD_OUTPUT_HANDLE), str.c_str(), static_cast<DWORD>(str.length()), nullptr, nullptr);
    #elif defined LINUXLIB
        std::cout << Strings::WideStringToString(str); //NEED TO BE FIXED. ADD locale parameter
    #elif defined MACOSLIB
    #endif
        ResetTerminalFormat();
    }
    
    void Console::WriteLine(const WString &s, ConsoleForeground foreground, ConsoleBackground background, std::set<ConsoleTextStyle> styles)
    {
        Write(s, foreground, background, styles);
        std::cout << std::endl;
    }
    
    int main()
    {
        std::locale::global(std::locale(u8"en_US.UTF-8"));
        String dataStr = u8"Zoë Saldaña played in La maldición del padre Cardona. ëèñ αω óóChloë";
        WString dataWStr = L"Zoë Saldaña played in La maldición del padre Cardona. ëèñ αω óóChloë";
        std::string locale = u8"";
        //std::string locale = u8"de_DE.UTF-8";
        //std::string locale = u8"en_US.UTF-8";
        Console::WriteLine(dataStr);
        Console::WriteLine(dataWStr);
        dataStr = Strings::ToUpper(dataStr);
        dataWStr = Strings::ToUpper(dataWStr);
        Console::WriteLine(dataStr);
        Console::WriteLine(dataWStr);
        dataStr = Strings::ToLower(dataStr);
        dataWStr = Strings::ToLower(dataWStr);
        Console::WriteLine(dataStr);
        Console::WriteLine(dataWStr);
        Console::PauseAny();
        return 0;
    }
    
    
    0 讨论(0)
提交回复
热议问题