How to convert from UTF-8 to ANSI using standard c

问题:

I have some strings read from the database, stored in a char* and in UTF-8 format (you know, "á" is encoded as 0xC3 0xA1). But, in order to write them to a file, I first need to convert them to ANSI (can't make the file in UTF-8 format... it's only read as ANSI), so that my "á" doesn't become "á". Yes, I know some data will be lost (chinese characters, and in general anything not in the ANSI code page) but that's exactly what I need.

But the thing is, I need the code to compile in various platforms, so it has to be standard C++ (i.e. no Winapi, only stdlib, stl, crt or any custom library with available source).

Anyone has any suggestions?

回答1:

A few days ago, somebody answered that if I had a C++11 compiler, I could try this:

#include <string>
#include <codecvt>
#include <locale>

string utf8_to_string(const char *utf8str, const locale& loc)
{
    // UTF-8 to wstring
    wstring_convert<codecvt_utf8<wchar_t>> wconv;
    wstring wstr = wconv.from_bytes(utf8str);
    // wstring to string
    vector<char> buf(wstr.size());
    use_facet<ctype<wchar_t>>(loc).narrow(wstr.data(), wstr.data() + wstr.size(), '?', buf.data());
    return string(buf.data(), buf.size());
}

int main(int argc, char* argv[])
{
    string ansi;
    char utf8txt[] = {0xc3, 0xa1, 0};

    // I guess you want to use Windows-1252 encoding...
    ansi = utf8_to_string(utf8txt, locale(".1252"));
    // Now do something with the string
    return 0;
}

Don't know what happened to the response, apparently someone deleted it. But, turns out that it is the perfect solution. To whoever posted, thanks a lot, and you deserve the AC and upvote!!

回答2:

If you mean ASCII, just discard any byte that has bit 7 set, this will remove all multibyte sequences. Note that you could create more advanced algorithms, like removing the accent from the "á", but that would require much more work.

回答3:

This should work:

#include <string>
#include <codecvt>

using namespace std::string_literals;

std::string to_utf8(const std::string& str, const std::locale& loc = std::locale{}) {
  using wcvt = std::wstring_convert<std::codecvt_utf8<char32_t>, char32_t>;
  std::u32string wstr(str.size(), U'\0');
  std::use_facet<std::ctype<char32_t>>(loc).widen(str.data(), str.data() + str.size(), &wstr[0]);
  return wcvt{}.to_bytes(wstr.data(),wstr.data() + wstr.size());
}

std::string from_utf8(const std::string& str, const std::locale& loc = std::locale{}) {
  using wcvt = std::wstring_convert<std::codecvt_utf8<char32_t>, char32_t>;
  auto wstr = wcvt{}.from_bytes(str);
  std::string result(wstr.size(), '0');
  std::use_facet<std::ctype<char32_t>>(loc).narrow(wstr.data(), wstr.data() + wstr.size(), '?', &result[0]);
  return result;
}

int main() {
  auto s0 = u8"Blöde C++ Scheiße äöü!!1Elf"s;
  auto s1 = from_utf8(s0);
  auto s2 = to_utf8(s1);

  return 0;
}

For VC++:

#include <string>
#include <codecvt>

using namespace std::string_literals;

std::string to_utf8(const std::string& str, const std::locale& loc = std::locale{}) {
  using wcvt = std::wstring_convert<std::codecvt_utf8<int32_t>, int32_t>;
  std::u32string wstr(str.size(), U'\0');
  std::use_facet<std::ctype<char32_t>>(loc).widen(str.data(), str.data() + str.size(), &wstr[0]);
  return wcvt{}.to_bytes(
    reinterpret_cast<const int32_t*>(wstr.data()),
    reinterpret_cast<const int32_t*>(wstr.data() + wstr.size())
  );
}

std::string from_utf8(const std::string& str, const std::locale& loc = std::locale{}) {
  using wcvt = std::wstring_convert<std::codecvt_utf8<int32_t>, int32_t>;
  auto wstr = wcvt{}.from_bytes(str);
  std::string result(wstr.size(), '0');
  std::use_facet<std::ctype<char32_t>>(loc).narrow(
    reinterpret_cast<const char32_t*>(wstr.data()),
    reinterpret_cast<const char32_t*>(wstr.data() + wstr.size()),
    '?', &result[0]);
  return result;
}

int main() {
  auto s0 = u8"Blöde C++ Scheiße äöü!!1Elf"s;
  auto s1 = from_utf8(s0);
  auto s2 = to_utf8(s1);

  return 0;
}

回答4:

#include <stdio.h>
#include <string>
#include <codecvt>
#include <locale>
#include <vector>

using namespace std;
std::string utf8_to_string(const char *utf8str, const locale& loc){
    // UTF-8 to wstring
    wstring_convert<codecvt_utf8<wchar_t>> wconv;
    wstring wstr = wconv.from_bytes(utf8str);
    // wstring to string
    vector<char> buf(wstr.size());
    use_facet<ctype<wchar_t>>(loc).narrow(wstr.data(), wstr.data() + wstr.size(), '?', buf.data());
    return string(buf.data(), buf.size());
}

int main(int argc, char* argv[]){
    std::string ansi;
    char utf8txt[] = {0xc3, 0xa1, 0};

    // I guess you want to use Windows-1252 encoding...
    ansi = utf8_to_string(utf8txt, locale(".1252"));
    // Now do something with the string
    return 0;
}