在Linux中将UTF-32宽字符转换为UTF-16宽字符作为补充平面字符 我们使用ICU,./P>在RHEL上部署了C++应用程序。
在linux上,我们需要将UChar*转换为wchar\u t*。我们使用u_strotwcs来执行转换在Linux中将UTF-32宽字符转换为UTF-16宽字符作为补充平面字符 我们使用ICU,./P>在RHEL上部署了C++应用程序。,c++,linux,icu,wchar-t,C++,Linux,Icu,Wchar T,在linux上,我们需要将UChar*转换为wchar\u t*。我们使用u_strotwcs来执行转换 #include <iostream> #include <wchar.h> #include "unicode/ustring.h" void convertUnicodeStringtoWideChar(const UChar* cuniszSource, const int32_t cu
#include <iostream>
#include <wchar.h>
#include "unicode/ustring.h"
void convertUnicodeStringtoWideChar(const UChar* cuniszSource,
const int32_t cunii32SourceLength,
wchar_t*& rpwcharDestination,
int32_t& destCapacity)
{
UErrorCode uniUErrorCode = U_ZERO_ERROR;
int32_t pDestLength = 0;
rpwcharDestination = 0;
destCapacity = 0;
u_strToWCS(rpwcharDestination,
destCapacity,
&pDestLength,
cuniszSource,
cunii32SourceLength,
&uniUErrorCode);
uniUErrorCode = U_ZERO_ERROR;
rpwcharDestination = new wchar_t[pDestLength+1];
if(rpwcharDestination)
{
destCapacity = pDestLength+1;
u_strToWCS(rpwcharDestination,
destCapacity,
&pDestLength,
cuniszSource,
cunii32SourceLength,
&uniUErrorCode);
destCapacity = wcslen(rpwcharDestination);
}
} //function ends
int main()
{
// a ä Š € ( In C++11 and later, this conversion is in the standard library, in the <codecvt>
header. Here is some sample code that converts between UTF-16, UCS-4 and wchar_t
. (It breaks on libstdc++ 6.4.9 due to a bug that has been fixed in the development tree.)
#include <codecvt>
#include <cstdlib>
#include <cstring>
#include <cwctype>
#include <iostream>
#include <locale>
#include <vector>
using std::cout;
using std::endl;
using std::exit;
using std::memcmp;
using std::size_t;
using std::wcout;
int main(void)
{
constexpr char16_t msg_utf16[] = u"¡Hola, mundo! \U0001F600"; // Shouldn't assume endianness.
constexpr wchar_t msg_w[] = L"¡Hola, mundo! \U0001F600";
constexpr char32_t msg_utf32[] = U"¡Hola, mundo! \U0001F600";
constexpr char msg_utf8[] = u8"¡Hola, mundo! \U0001F600";
// May vary from OS to OS> "" is the most standard, but might require, e.g. "en_US.utf8".
constexpr char locale_name[] = "";
std::locale::global(std::locale(locale_name)); //
wcout.imbue(std::locale());
const std::codecvt_utf16<wchar_t, 0x1FFFF, std::little_endian> converter_w;
const size_t max_len = sizeof(msg_utf16);
std::vector<char> out(max_len);
std::mbstate_t state;
const wchar_t* from_w = nullptr;
char* to_next = nullptr;
converter_w.out( state, msg_w, msg_w+sizeof(msg_w)/sizeof(wchar_t), from_w, out.data(), out.data() + out.size(), to_next );
if (memcmp( msg_utf8, out.data(), sizeof(msg_utf8) ) == 0 ) {
wcout << L"std::codecvt_utf16<wchar_t> converts to UTF-8, not UTF-16!" << endl;
} else if ( memcmp( msg_utf16, out.data(), max_len ) != 0 ) {
wcout << L"std::codecvt_utf16<wchar_t> conversion not equal!" << endl;
} else {
wcout << L"std::codecvt_utf16<wchar_t> conversion is correct." << endl;
}
out.clear();
out.resize(max_len);
const std::codecvt_utf16<char32_t, 0x1FFFF, std::little_endian> converter_u32;
const char32_t* from_u32 = nullptr;
converter_u32.out( state, msg_utf32, msg_utf32+sizeof(msg_utf32)/sizeof(char32_t), from_u32, out.data(), out.data() + out.size(), to_next );
if ( memcmp( msg_utf16, out.data(), max_len ) != 0 ) {
wcout << L"std::codecvt_utf16<char32_t> conversion not equal!" << endl;
} else {
wcout << L"std::codecvt_utf16<char32_t> conversion is correct." << endl;
}
wcout << msg_w << endl;
return EXIT_SUCCESS;
}
#包括
#包括
#包括“unicode/usting.h”
void convertUnicode DestingToWideChar(常量UChar*cuniszSource,
常量int32\u t cunii32SourceLength,
wchar_t*&RPWChard估计,
int32_t&dest容量)
{
UErrorCode uniUErrorCode=U_零_错误;
int32_t pDestLength=0;
rpwcharDestination=0;
容量=0;
u_STROTOWCS(RPWChardDestination,
容量,
&pDestLength,
cuniszSource,
cunii32SourceLength,
&统一代码);
uniUErrorCode=U_零_错误;
rpwcharDestination=新的wchar_t[pDestLength+1];
if(rpwcharDestination)
{
destCapacity=pDestLength+1;
u_STROTOWCS(RPWChardDestination,
容量,
&pDestLength,
cuniszSource,
cunii32SourceLength,
&统一代码);
destCapacity=wcslen(rpwcharDestination);
}
}//函数结束
int main()
{
//a䊀(在C++11及更高版本中,此转换位于标准库中的
标题中。以下是一些在UTF-16、UCS-4和wchar\u t
之间转换的示例代码(由于开发树中已修复的错误,它在libstdc++6.4.9上中断。)
以下是将UTF-32编码的宽字符转换为UTF-16的代码
//将Unicode字符串从特定于平台的“宽字符”(wchar\u t)转换为UTF-16的函数。
void convertutf32toff16(wchar\u t*源、,
const uint32_t sourceLength,
wchar_t*&目的地,
uint32(运输和目的地长度)
{
wchar_t wcharCharacter;
uint32\u t UNIUI32计数器=0;
wchar_t*pwszDestinationStart=目的地;
wchar_t*sourceStart=source;
如果(0!=目的地)
{
while(uniui32计数器<源长度)
{
wcharCharacter=*source++;
如果(wcharCharacter=0xD800&&
wcharCharacter 0x0010FFFF)
{
/*U+10FFFF是Unicode字符集的最大代码点*/
*目的地++=0x0000FFFD;
目标长度+=1;
}
其他的
{
/*源是0xFFFF-0x10FFFF范围内的字符*/
wcharCharacter-=0x0010000UL;
*目的地+=(wchar_t)((wcharCharacter>>10)+0xD800);
*目的地+=(wchar_t)((wcharCharacter&0x3FFUL)+0xDC00);
目标长度+=2;
}
++UNIUI32计数器;
}
目的地=pwszDestinationStart;
目的地[destinationLength]='\0';
}
source=sourceStart;
}//函数结束
“它失败了…”——输入、观察到的输出、预期的输出?Amain()
提供这些信息,并将此函数(加上必要的#include
语句)包装到可编译示例中?是否将字符编码为代理项对,例如使用u“\U0001F600”
或使用u8的多字节字符串“\U0001F600”
,工作?我冒昧地拍了一些粗糙的main()
,使其成为MCVE。输出是61
,e4
,160
,20ac
,2f929
,这是我所期望的。(注意最后一个单元,它是输入中的非BMP/UTF-16代理项对。)向OP重复这个问题,inhowfar会“失败”吗"?ICU常见问题解答声称,该库支持UTF-16,而不是UCS-2,因此代理项对应该可以工作。这是否回答了如何在BMP之外编码字符的问题?好的。我看错了方向。u_strToWCS工作正常。出现问题的原因是,我需要使用CORBA将宽字符串传递给windows上的java应用程序。由于linux中的wchar__t是32位的,我需要找到一种方法将32位wchar__t转换为16位wchar_t1)应该是注释,而不是答案(因为OP指定的ICU--C++11可能不可用,或者ICU被设置为需求,我们不知道)2)在C++ 11. 3中出现了“代码转换> <代码>转换,在代码> >代码>中由C++ 17来修改;-)纠正了当添加了方面时的错误。谢谢。如果Linux C++构建环境支持LIbc++或任何最近版本的LIbSTDC++ +,它支持这些方面。无论如何,这是我在HA上遇到的示例代码。nd,我现在用ICU写一个演示已经太晚了。我明天可以回来。@DevSolar:OT,但你知道为什么它们被弃用了吗?@DevSolar更新了我的答案。@Davidslor如果你能分享你写的手动wchar\u t*到UTF-16的转换,那将很有帮助
#include <cassert>
#include <cwctype>
#include <cstdlib>
#include <iomanip>
#include <iostream>
#include <locale>
#include <string>
#if _WIN32 || _WIN64
// Windows needs a little non-standard magic for this to work.
#include <io.h>
#include <fcntl.h>
#include <locale.h>
#endif
using std::size_t;
void init_locale(void)
// Does magic so that wcout can work.
{
#if _WIN32 || _WIN64
// Windows needs a little non-standard magic.
constexpr char cp_utf16le[] = ".1200";
setlocale( LC_ALL, cp_utf16le );
_setmode( _fileno(stdout), _O_U16TEXT );
#else
// The correct locale name may vary by OS, e.g., "en_US.utf8".
constexpr char locale_name[] = "";
std::locale::global(std::locale(locale_name));
std::wcout.imbue(std::locale());
#endif
}
std::u16string make_u16string( const std::wstring& ws )
/* Creates a UTF-16 string from a wide-character string. Any wide characters
* outside the allowed range of UTF-16 are mapped to the sentinel value U+FFFD,
* per the Unicode documentation. (http://www.unicode.org/faq/private_use.html
* retrieved 12 March 2017.) Unpaired surrogates in ws are also converted to
* sentinel values. Noncharacters, however, are left intact. As a fallback,
* if wide characters are the same size as char16_t, this does a more trivial
* construction using that implicit conversion.
*/
{
/* We assume that, if this test passes, a wide-character string is already
* UTF-16, or at least converts to it implicitly without needing surrogate
* pairs.
*/
if ( sizeof(wchar_t) == sizeof(char16_t) ) {
return std::u16string( ws.begin(), ws.end() );
} else {
/* The conversion from UTF-32 to UTF-16 might possibly require surrogates.
* A surrogate pair suffices to represent all wide characters, because all
* characters outside the range will be mapped to the sentinel value
* U+FFFD. Add one character for the terminating NUL.
*/
const size_t max_len = 2 * ws.length() + 1;
// Our temporary UTF-16 string.
std::u16string result;
result.reserve(max_len);
for ( const wchar_t& wc : ws ) {
const std::wint_t chr = wc;
if ( chr < 0 || chr > 0x10FFFF || (chr >= 0xD800 && chr <= 0xDFFF) ) {
// Invalid code point. Replace with sentinel, per Unicode standard:
constexpr char16_t sentinel = u'\uFFFD';
result.push_back(sentinel);
} else if ( chr < 0x10000UL ) { // In the BMP.
result.push_back(static_cast<char16_t>(wc));
} else {
const char16_t leading = static_cast<char16_t>(
((chr-0x10000UL) / 0x400U) + 0xD800U );
const char16_t trailing = static_cast<char16_t>(
((chr-0x10000UL) % 0x400U) + 0xDC00U );
result.append({leading, trailing});
} // end if
} // end for
/* The returned string is shrunken to fit, which might not be the Right
* Thing if there is more to be added to the string.
*/
result.shrink_to_fit();
// We depend here on the compiler to optimize the move constructor.
return result;
} // end if
// Not reached.
}
int main(void)
{
static const std::wstring wtest(L"☪☮∈✡℩☯✝ \U0001F644");
static const std::u16string u16test(u"☪☮∈✡℩☯✝ \U0001F644");
const std::u16string converted = make_u16string(wtest);
init_locale();
std::wcout << L"sizeof(wchar_t) == " << sizeof(wchar_t) << L".\n";
for( size_t i = 0; i <= u16test.length(); ++i ) {
if ( u16test[i] != converted[i] ) {
std::wcout << std::hex << std::showbase
<< std::right << std::setfill(L'0')
<< std::setw(4) << (unsigned)converted[i] << L" ≠ "
<< std::setw(4) << (unsigned)u16test[i] << L" at "
<< i << L'.' << std::endl;
return EXIT_FAILURE;
} // end if
} // end for
std::wcout << wtest << std::endl;
return EXIT_SUCCESS;
}
//Function to convert a Unicode string from platform-specific "wide characters" (wchar_t) to UTF-16.
void ConvertUTF32ToUTF16(wchar_t* source,
const uint32_t sourceLength,
wchar_t*& destination,
uint32_t& destinationLength)
{
wchar_t wcharCharacter;
uint32_t uniui32Counter = 0;
wchar_t* pwszDestinationStart = destination;
wchar_t* sourceStart = source;
if(0 != destination)
{
while(uniui32Counter < sourceLength)
{
wcharCharacter = *source++;
if(wcharCharacter <= 0x0000FFFF)
{
/* UTF-16 surrogate values are illegal in UTF-32
0xFFFF or 0xFFFE are both reserved values */
if(wcharCharacter >= 0xD800 &&
wcharCharacter <= 0xDFFF)
{
*destination++ = 0x0000FFFD;
destinationLength += 1;
}
else
{
/* source is a BMP Character */
destinationLength += 1;
*destination++ = wcharCharacter;
}
}
else if(wcharCharacter > 0x0010FFFF)
{
/* U+10FFFF is the largest code point of Unicode Character Set */
*destination++ = 0x0000FFFD;
destinationLength += 1;
}
else
{
/* source is a character in range 0xFFFF - 0x10FFFF */
wcharCharacter -= 0x0010000UL;
*destination++ = (wchar_t)((wcharCharacter >> 10) + 0xD800);
*destination++ = (wchar_t)((wcharCharacter & 0x3FFUL) + 0xDC00);
destinationLength += 2;
}
++uniui32Counter;
}
destination = pwszDestinationStart;
destination[destinationLength] = '\0';
}
source = sourceStart;
} //function ends