Question

我有txt文件，其内容为：

\ u041f \ u0435 \ u0440 \ u0432 \ u044b \ u0439_ \ u0438 \ u043d \ u0442 \ u0435 \ u0440 \ u0430 \ u043a \ u0442 \ u0438 \ u0432 \ u043d \ u044b \ u0439_ \ u0438 \ u043d \ u0442 \ u0435 \ u0440 \ u043d \ u0435 \ u0442_ \ u043a \ u0430 \ u043d \ u0430 \ u043b

如何阅读此类文件以获得如下结果：

“Первый_интерактивный_интернет_канал”

如果我输入：

string str = _T("\u041f\u0435\u0440\u0432\u044b\u0439_\u0438\u043d\u0442\u0435\u0440\u0430\u043a\u0442\u0438\u0432\u043d\u044b\u0439_\u0438\u043d\u0442\u0435\u0440\u043d\u0435\u0442_\u043a\u0430\u043d\u0430\u043b");

然后str的结果是好的，但如果我从文件中读取它，那么它就像在文件中一样。我想这是因为'\ u'变成'\ u'。有没有简单的方法将\ uxxxx表示法转换为C ++中的相应符号？

Answer 1

当您阅读文件时，这并不容易。之后进行后处理步骤会更容易。您可以使用Boost::regex查找“\ u [0-9A-Fa-f] {4}”模式，并将其替换为相应的单个字符。

Answer 2

以下是MSalters建议的一个示例：

#include <iostream>
#include <string>
#include <fstream>
#include <algorithm>
#include <sstream>
#include <iomanip>
#include <locale>

#include <boost/scoped_array.hpp>
#include <boost/regex.hpp>
#include <boost/numeric/conversion/cast.hpp>

std::wstring convert_unicode_escape_sequences(const std::string& source) {
  const boost::regex regex("\\\\u([0-9A-Fa-f]{4})");  // NB: no support for non-BMP characters
  boost::scoped_array<wchar_t> buffer(new wchar_t[source.size()]);
  wchar_t* const output_begin = buffer.get();
  wchar_t* output_iter = output_begin;
  std::string::const_iterator last_match = source.begin();
  for (boost::sregex_iterator input_iter(source.begin(), source.end(), regex), input_end; input_iter != input_end; ++input_iter) {
    const boost::smatch& match = *input_iter;
    output_iter = std::copy(match.prefix().first, match.prefix().second, output_iter);
    std::stringstream stream;
    stream << std::hex << match[1].str() << std::ends;
    unsigned int value;
    stream >> value;
    *output_iter++ = boost::numeric_cast<wchar_t>(value);
    last_match = match[0].second;
  }
  output_iter = std::copy(last_match, source.end(), output_iter);
  return std::wstring(output_begin, output_iter);
}

int wmain() {
  std::locale::global(std::locale(""));
  const std::wstring filename = L"test.txt";
  std::ifstream stream(filename.c_str(), std::ios::in | std::ios::binary);
  stream.seekg(0, std::ios::end);
  const std::ifstream::streampos size = stream.tellg();
  stream.seekg(0);
  boost::scoped_array<char> buffer(new char[size]);
  stream.read(buffer.get(), size);
  const std::string source(buffer.get(), size);
  const std::wstring result = convert_unicode_escape_sequences(source);
  std::wcout << result << std::endl;
}

我总是感到惊讶的是，像C ++这样复杂的看似简单的东西。

Answer 3

我的解决方案。我使用Boost进行UTF-16 - UTF-8转换。

#include <fstream>
#include <codecvt>
#include <boost/numeric/conversion/cast.hpp>

//------------------------------------------------------------------------------

inline uint8_t get_uint8(uint8_t h, uint8_t l)
{
    uint8_t ret;

    if (h - '0' < 10)
        ret = h - '0';
    else if (h - 'A' < 6)
        ret = h - 'A' + 0x0A;
    else if (h - 'a' < 6)
        ret = h - 'a' + 0x0A;

    ret = ret << 4;

    if (l - '0' < 10)
        ret |= l - '0';
    else if (l - 'A' < 6)
        ret |= l - 'A' + 0x0A;
    else if (l - 'a' < 6)
        ret |= l - 'a' + 0x0A;
    return  ret;
}

std::string convert_unicode_escape_sequences(const std::string& source) 
{
    std::wstring ws; ws.reserve(source.size());
    std::wstringstream wis(ws);

    auto s = source.begin();
    while (s != source.end())
    {
        if (*s == '\\')
        {
            if (std::distance(s, source.end()) > 5)
            {
                if (*(s + 1) == 'u')
                {
                    unsigned int v = get_uint8(*(s + 2), *(s + 3)) << 8;
                    v |= get_uint8(*(s + 4), *(s + 5));

                    s += 6;
                    wis << boost::numeric_cast<wchar_t>(v);
                    continue;
                }
            }
        }
        wis << wchar_t(*s);
        s++;
    }

    std::wstring_convert<std::codecvt_utf8<wchar_t>> myconv;
    return myconv.to_bytes(wis.str());
}

Answer 4

检查此代码:) Windows SDK已经为您准备好了，MS geeks也考虑过这一点，您可以在这篇文章中找到更多详细信息：http://weblogs.asp.net/kennykerr/archive/2008/07/24/visual-c-in-short-converting-between-unicode-and-utf-8.aspx

#include <atlconv.h>
#include <atlstr.h>

#define ASSERT ATLASSERT

int main()
{
    const CStringW unicode1 = L"\u041f 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);   

    return 0;
}

此代码已经过我测试，效果很好。

如何在vc ++中读取包含\ uxxxx的文件

4 个答案: