我正试图在二进制模式下使用ofstream将wstring写入文件，但我觉得我做错了什么。这是我尝试过的：
ofstream outFile("test.txt", std::ios::out | std::ios::binary);
wstring hello = L"hello";
outFile.write((char *) hello.c_str(), hello.length() * sizeof(wchar_t));
outFile.close();
以UTF16编码在例如Firefox中打开test.txt，它会显示为：
h�e�l�l�o�
有人可以告诉我这是为什么吗？
编辑：
在十六进制编辑器中打开文件，我得到：
FF FE 68 00 00 00 65 00 00 00 6C 00 00 00 6C 00 00 00 6F 00 00 00
看起来每个字符之间我多了两个额外的字节，不知道为什么？
在这里，我们遇到了很少使用的本地化属性。如果您将字符串输出为字符串（而不是原始数据），则可以让本地化自动执行适当的转换。
N.B.此代码未考虑wchar_t字符的字节序。
#include <locale>
#include <fstream>
#include <iostream>
// See Below for the facet
#include "UTF16Facet.h"
int main(int argc,char* argv[])
{
// construct a custom unicode facet and add it to a local.
UTF16Facet *unicodeFacet = new UTF16Facet();
const std::locale unicodeLocale(std::cout.getloc(), unicodeFacet);
// Create a stream and imbue it with the facet
std::wofstream saveFile;
saveFile.imbue(unicodeLocale);
// Now the stream is imbued we can open it.
// NB If you open the file stream first. Any attempt to imbue it with a local will silently fail.
saveFile.open("output.uni");
saveFile << L"This is my Data\n";
return(0);
}
文件: UTF16Facet.h
#include <locale>
class UTF16Facet: public std::codecvt<wchar_t,char,std::char_traits<wchar_t>::state_type>
{
typedef std::codecvt<wchar_t,char,std::char_traits<wchar_t>::state_type> MyType;
typedef MyType::state_type state_type;
typedef MyType::result result;
/* This function deals with converting data from the input stream into the internal stream.*/
/*
* from, from_end: Points to the beginning and end of the input that we are converting 'from'.
* to, to_limit: Points to where we are writing the conversion 'to'
* from_next: When the function exits this should have been updated to point at the next location
* to read from. (ie the first unconverted input character)
* to_next: When the function exits this should have been updated to point at the next location
* to write to.
*
* status: This indicates the status of the conversion.
* possible values are:
* error: An error occurred the bad file bit will be set.
* ok: Everything went to plan
* partial: Not enough input data was supplied to complete any conversion.
* nonconv: no conversion was done.
*/
virtual result do_in(state_type &s,
const char *from,const char *from_end,const char* &from_next,
wchar_t *to, wchar_t *to_limit,wchar_t* &to_next) const
{
// Loop over both the input and output array/
for(;(from < from_end) && (to < to_limit);from += 2,++to)
{
/*Input the Data*/
/* As the input 16 bits may not fill the wchar_t object
* Initialise it so that zero out all its bit's. This
* is important on systems with 32bit wchar_t objects.
*/
(*to) = L'\0';
/* Next read the data from the input stream into
* wchar_t object. Remember that we need to copy
* into the bottom 16 bits no matter what size the
* the wchar_t object is.
*/
reinterpret_cast<char*>(to)[0] = from[0];
reinterpret_cast<char*>(to)[1] = from[1];
}
from_next = from;
to_next = to;
return((from > from_end)?partial:ok);
}
/* This function deals with converting data from the internal stream to a C/C++ file stream.*/
/*
* from, from_end: Points to the beginning and end of the input that we are converting 'from'.
* to, to_limit: Points to where we are writing the conversion 'to'
* from_next: When the function exits this should have been updated to point at the next location
* to read from. (ie the first unconverted input character)
* to_next: When the function exits this should have been updated to point at the next location
* to write to.
*
* status: This indicates the status of the conversion.
* possible values are:
* error: An error occurred the bad file bit will be set.
* ok: Everything went to plan
* partial: Not enough input data was supplied to complete any conversion.
* nonconv: no conversion was done.
*/
virtual result do_out(state_type &state,
const wchar_t *from, const wchar_t *from_end, const wchar_t* &from_next,
char *to, char *to_limit, char* &to_next) const
{
for(;(from < from_end) && (to < to_limit);++from,to += 2)
{
/* Output the Data */
/* NB I am assuming the characters are encoded as UTF-16.
* This means they are 16 bits inside a wchar_t object.
* As the size of wchar_t varies between platforms I need
* to take this into consideration and only take the bottom
* 16 bits of each wchar_t object.
*/
to[0] = reinterpret_cast<const char*>(from)[0];
to[1] = reinterpret_cast<const char*>(from)[1];
}
from_next = from;
to_next = to;
return((to > to_limit)?partial:ok);
}
};
stxutif.h to your project from sources above Open the file in ANSI mode and add the BOM to the start of a file, like this:
std::ofstream fs;
fs.open(filepath, std::ios::out|std::ios::binary);
unsigned char smarker[3];
smarker[0] = 0xEF;
smarker[1] = 0xBB;
smarker[2] = 0xBF;
fs << smarker;
fs.close();
Then open the file as UTF and write your content there:
std::wofstream fs;
fs.open(filepath, std::ios::out|std::ios::app);
std::locale utf8_locale(std::locale(), new utf8cvt<false>);
fs.imbue(utf8_locale);
fs << .. // Write anything you want...
Utf16Facet 在处理大字符串时在 gcc 中无法正常工作，这是我使用的版本... 这样文件将以 UTF-16LE 保存。对于 UTF-16BE，只需反转 do_in 和 do_out 中的赋值，例如 to[0] = from[1] 和 to[1] = from[0]。#include <locale>
#include <bits/codecvt.h>
class UTF16Facet: public std::codecvt<wchar_t,char,std::char_traits<wchar_t>::state_type>
{
typedef std::codecvt<wchar_t,char,std::char_traits<wchar_t>::state_type> MyType;
typedef MyType::state_type state_type;
typedef MyType::result result;
/* This function deals with converting data from the input stream into the internal stream.*/
/*
* from, from_end: Points to the beginning and end of the input that we are converting 'from'.
* to, to_limit: Points to where we are writing the conversion 'to'
* from_next: When the function exits this should have been updated to point at the next location
* to read from. (ie the first unconverted input character)
* to_next: When the function exits this should have been updated to point at the next location
* to write to.
*
* status: This indicates the status of the conversion.
* possible values are:
* error: An error occurred the bad file bit will be set.
* ok: Everything went to plan
* partial: Not enough input data was supplied to complete any conversion.
* nonconv: no conversion was done.
*/
virtual result do_in(state_type &s,
const char *from,const char *from_end,const char* &from_next,
wchar_t *to, wchar_t *to_limit,wchar_t* &to_next) const
{
for(;from < from_end;from += 2,++to)
{
if(to<=to_limit){
(*to) = L'\0';
reinterpret_cast<char*>(to)[0] = from[0];
reinterpret_cast<char*>(to)[1] = from[1];
from_next = from;
to_next = to;
}
}
return((to != to_limit)?partial:ok);
}
/* This function deals with converting data from the internal stream to a C/C++ file stream.*/
/*
* from, from_end: Points to the beginning and end of the input that we are converting 'from'.
* to, to_limit: Points to where we are writing the conversion 'to'
* from_next: When the function exits this should have been updated to point at the next location
* to read from. (ie the first unconverted input character)
* to_next: When the function exits this should have been updated to point at the next location
* to write to.
*
* status: This indicates the status of the conversion.
* possible values are:
* error: An error occurred the bad file bit will be set.
* ok: Everything went to plan
* partial: Not enough input data was supplied to complete any conversion.
* nonconv: no conversion was done.
*/
virtual result do_out(state_type &state,
const wchar_t *from, const wchar_t *from_end, const wchar_t* &from_next,
char *to, char *to_limit, char* &to_next) const
{
for(;(from < from_end);++from, to += 2)
{
if(to <= to_limit){
to[0] = reinterpret_cast<const char*>(from)[0];
to[1] = reinterpret_cast<const char*>(from)[1];
from_next = from;
to_next = to;
}
}
return((to != to_limit)?partial:ok);
}
};
您应该使用十六进制编辑器（例如WinHex）查看输出文件，以便查看实际的位和字节，以验证输出是否实际上是UTF-16。请在此处发布并告诉我们结果。这将告诉我们是要责怪Firefox还是您的C++程序。
但我认为您的C++程序是有效的，而Firefox没有正确解释您的UTF-16。UTF-16要求每个字符使用两个字节。但Firefox打印的字符数是应有数量的两倍，因此它可能试图将您的字符串解释为UTF-8或ASCII，这些通常只有每个字符1个字节。
当您说“使用UTF16编码的Firefox”时，您是什么意思？我对此持怀疑态度。