我有一个由Unicode编码点组成的数组
unsigned short array[3]={0x20ac,0x20ab,0x20ac};
我只是希望将此内容转换为 utf-8 格式,以便使用 C++ 按字节写入文件。
例如:0x20ac 应该被转换为 e2 82 ac。
或者是否有其他方法可以直接将 Unicode 字符写入文件。
终于!有了C++11!
#include <string>
#include <locale>
#include <codecvt>
#include <cassert>
int main()
{
std::wstring_convert<std::codecvt_utf8<char32_t>, char32_t> converter;
std::string u8str = converter.to_bytes(0x20ac);
assert(u8str == "\xe2\x82\xac");
}
char32_t
的std::codecvt
的Visual Studio 2015和2017编译器方面存在问题。但是你可以使用 uint32_t
来替代:
std::wstring_convert< std::codecvt_utf8<uint32_t>, uint32_t > converter;
- MatthewWideCharToMultiByte
。#include <iostream>
#include <unicode\ustream.h>
using icu::UnicodeString;
int main(int, char**) {
//
// Convert from UTF-16 to UTF-8
//
std::wstring utf16 = L"foobar";
UnicodeString str(utf16.c_str());
std::string utf8;
str.toUTF8String(utf8);
std::cout << utf8 << std::endl;
}
// Assuming you have ICU\include in your include path
// and ICU\lib(64) in your library path.
#include <iostream>
#include <fstream>
#include <unicode\ustream.h>
#pragma comment(lib, "icuio.lib")
#pragma comment(lib, "icuuc.lib")
void writeUtf16ToUtf8File(char const* fileName, wchar_t const* arr, size_t arrSize) {
UnicodeString str(arr, arrSize);
std::string utf8;
str.toUTF8String(utf8);
std::ofstream out(fileName, std::ofstream::binary);
out << utf8;
out.close();
}
以下代码可能会对您有所帮助:
#include <atlconv.h>
#include <atlstr.h>
#define ASSERT ATLASSERT
int main()
{
const CStringW unicode1 = L"\x0391 and \x03A9"; // 'Alpha' and 'Omega'
const CStringA utf8 = CW2A(unicode1, CP_UTF8);
ASSERT(utf8.GetLength() > unicode1.GetLength());
const CStringW unicode2 = CA2W(utf8, CP_UTF8);
ASSERT(unicode1 == unicode2);
}
WideCharToMultiByte
函数(假定你正在使用 Windows):unsigned short wide_str[3] = {0x20ac, 0x20ab, 0x20ac};
int utf8_size = WideCharToMultiByte(CP_UTF8, 0, wide_str, 3, NULL, 0, NULL, NULL) + 1;
char* utf8_str = calloc(utf8_size);
WideCharToMultiByte(CP_UTF8, 0, wide_str, 3, utf8_str, utf8_size, NULL, NULL);
我有一个类似但略有不同的问题。我的字符串中包含Unicode代码点,以字符串表示形式存在。例如:"F\u00f3\u00f3 B\u00e1r"。我需要将字符串代码点转换为它们的Unicode字符。
这是我的C#解决方案:
using System.Globalization;
using System.Text.RegularExpressions;
static void Main(string[] args)
{
Regex CodePoint = new Regex(@"\\u(?<UTF32>....)");
Match Letter;
string s = "F\u00f3\u00f3 B\u00e1r";
string utf32;
Letter = CodePoint.Match(s);
while (Letter.Success)
{
utf32 = Letter.Groups[1].Value;
if (Int32.TryParse(utf32, NumberStyles.HexNumber, CultureInfo.GetCultureInfoByIetfLanguageTag("en-US"), out int HexNum))
s = s.Replace("\\u" + utf32, Char.ConvertFromUtf32(HexNum));
Letter = Letter.NextMatch();
}
Console.WriteLine(s);
}
输出:Fóó Bár
使用标准的C++
#include <iostream>
#include <locale>
#include <vector>
int main()
{
typedef std::codecvt<wchar_t, char, mbstate_t> Convert;
std::wstring w = L"\u20ac\u20ab\u20ac";
std::locale locale("en_GB.utf8");
const Convert& convert = std::use_facet<Convert>(locale);
std::mbstate_t state;
const wchar_t* from_ptr;
char* to_ptr;
std::vector<char> result(3 * w.size() + 1, 0);
Convert::result convert_result = convert.out(state,
w.c_str(), w.c_str() + w.size(), from_ptr,
result.data(), result.data() + result.size(), to_ptr);
if (convert_result == Convert::ok)
std::cout << result.data() << std::endl;
else std::cout << "Failure: " << convert_result << std::endl;
}
short
的代码点,并且它实际上不是UTF-16或UCS-2编码吗? - Mooing Duck