我曾经编程过Windows，但我想尝试制作跨平台的应用程序。我有一些问题，如果你不介意的话：
问题1
有没有办法打开UNICODE \ ASCII文件并使用裸ANSI C自动检测它的编码.MSDN说fopen（）可以在各种UNICODE格式（utf-8，utf-16，UNICODE BI \ LI）之间切换我将使用“ccs = UNICODE”标志。通过实验发现，从UNICODE切换到ASCII没有发生，但试图解决这个问题，我发现文本Unicode文件有一些前缀，如0xFFFE，0xFEFF或0xFEBB。
FILE *file;
{
__int16 isUni;
file = _tfopen(filename, _T("rb"));
fread(&(isUni),1,2,file);
fclose(file);
if( isUni == (__int16)0xFFFE || isUni == (__int16)0xFEFF || isUni == (__int16)0xFEBB)
file = _tfopen(filename, _T("r,ccs=UNICODE"));
else
file = _tfopen(filename, _T("r"));
}
那么，我可以制作这样的跨平台而不是那么难看的东西吗？
问题2
我可以在Windows中执行类似的操作，但是它可以在Linux中运行吗？
file = fopen(filename, "r");
fwscanf(file,"%lf",buffer);
如果没有，那么是否有某种ANSI C函数将ASCII字符串转换为Unicode？我想在我的程序中使用Unicode字符串。
问题3
此外，我需要将Unicode字符串输出到控制台。在windows中有setlocale（*），但我应该在Linux中做什么？似乎控制台已经是Unicode了。
问题4
一般来说，我想在我的程序中使用Unicode，但我遇到了一些奇怪的问题：
f = fopen("inc.txt","rt");
fwprintf(f,L"Текст"); // converted successfully
fclose(f);
f = fopen("inc_u8.txt","rt, ccs = UNICODE");
fprintf(f,"text"); // failed to convert
fclose(f);
P.S。是否有一些关于跨平台编程的好书，有什么比较windows和linux程序代码？还有一些关于使用Unicode的方法，实用方法，即。我不想沉浸在简单的UNICODE BI \ LI历史中，我对特定的C / C ++库感兴趣。
答案 0 :(得分：2)
问题1：
是的，您可以检测字节顺序标记，即您发现的字节序列 - 如果您的文件有一个。
在Google和stackoverflow上搜索将完成剩下的工作。
至于“不那么难看”：你可以重构/美化你的代码，例如：编写一个确定BOM的函数，并在开始时执行，然后根据需要调用fopen或_tfopen。
然后你可以再次重构，并编写自己的fopen函数。但它仍然是丑陋的。
问题2：
是的，但Linux上的unicode函数并不总是与在Windows上相同。
使用定义。
也许写自己的TCHAR.H
问题3：
#include <locale.h>
setlocale(LC_ALL, "en.UTF-8")
man 3 setlocale
问题4：
只需使用fwprintf。
另一个不是标准。
您可以使用wxWidgets工具包 它使用unicode，它使用的类在Windows，Linux，Unix和Mac上具有相同的实现。
更好的问题是如何将ASCII转换为Unicode，反之亦然。 就是这样：
std::string Unicode2ASCII( std::wstring wstrStringToConvert )
{
size_t sze_StringLength = wstrStringToConvert.length() ;
if(0 == sze_StringLength)
return "" ;
char* chrarry_Buffer = new char[ sze_StringLength + 1 ] ;
wcstombs( chrarry_Buffer, wstrStringToConvert.c_str(), sze_StringLength ) ; // Unicode2ASCII, const wchar_t* C-String 2 mulibyte C-String
chrarry_Buffer[sze_StringLength] = '\0' ;
std::string strASCIIstring = chrarry_Buffer ;
delete chrarry_Buffer ;
return strASCIIstring ;
}
std::wstring ASCII2Unicode( std::string strStringToConvert )
{
size_t sze_StringLength = strStringToConvert.length() ;
if(0 == sze_StringLength)
return L"" ;
wchar_t* wchrarry_Buffer = new wchar_t[ sze_StringLength + 1 ] ;
mbstowcs( wchrarry_Buffer, strStringToConvert.c_str(), sze_StringLength ) ; // Unicode2ASCII, const. mulibyte C-String 2 wchar_t* C-String
wchrarry_Buffer[sze_StringLength] = L'\0' ;
std::wstring wstrUnicodeString = wchrarry_Buffer ;
delete wchrarry_Buffer ;
return wstrUnicodeString ;
}
编辑： 这里有一些关于Linux（wchar.h）上可用的Unicode函数的见解：
__BEGIN_NAMESPACE_STD
/* Copy SRC to DEST. */
extern wchar_t *wcscpy (wchar_t *__restrict __dest,
__const wchar_t *__restrict __src) __THROW;
/* Copy no more than N wide-characters of SRC to DEST. */
extern wchar_t *wcsncpy (wchar_t *__restrict __dest,
__const wchar_t *__restrict __src, size_t __n)
__THROW;
/* Append SRC onto DEST. */
extern wchar_t *wcscat (wchar_t *__restrict __dest,
__const wchar_t *__restrict __src) __THROW;
/* Append no more than N wide-characters of SRC onto DEST. */
extern wchar_t *wcsncat (wchar_t *__restrict __dest,
__const wchar_t *__restrict __src, size_t __n)
__THROW;
/* Compare S1 and S2. */
extern int wcscmp (__const wchar_t *__s1, __const wchar_t *__s2)
__THROW __attribute_pure__;
/* Compare N wide-characters of S1 and S2. */
extern int wcsncmp (__const wchar_t *__s1, __const wchar_t *__s2, size_t __n)
__THROW __attribute_pure__;
__END_NAMESPACE_STD
#ifdef __USE_XOPEN2K8
/* Compare S1 and S2, ignoring case. */
extern int wcscasecmp (__const wchar_t *__s1, __const wchar_t *__s2) __THROW;
/* Compare no more than N chars of S1 and S2, ignoring case. */
extern int wcsncasecmp (__const wchar_t *__s1, __const wchar_t *__s2,
size_t __n) __THROW;
/* Similar to the two functions above but take the information from
the provided locale and not the global locale. */
# include <xlocale.h>
extern int wcscasecmp_l (__const wchar_t *__s1, __const wchar_t *__s2,
__locale_t __loc) __THROW;
extern int wcsncasecmp_l (__const wchar_t *__s1, __const wchar_t *__s2,
size_t __n, __locale_t __loc) __THROW;
#endif
/* Special versions of the functions above which take the locale to
use as an additional parameter. */
extern long int wcstol_l (__const wchar_t *__restrict __nptr,
wchar_t **__restrict __endptr, int __base,
__locale_t __loc) __THROW;
extern unsigned long int wcstoul_l (__const wchar_t *__restrict __nptr,
wchar_t **__restrict __endptr,
int __base, __locale_t __loc) __THROW;
__extension__
extern long long int wcstoll_l (__const wchar_t *__restrict __nptr,
wchar_t **__restrict __endptr,
int __base, __locale_t __loc) __THROW;
__extension__
extern unsigned long long int wcstoull_l (__const wchar_t *__restrict __nptr,
wchar_t **__restrict __endptr,
int __base, __locale_t __loc)
__THROW;
extern double wcstod_l (__const wchar_t *__restrict __nptr,
wchar_t **__restrict __endptr, __locale_t __loc)
__THROW;
extern float wcstof_l (__const wchar_t *__restrict __nptr,
wchar_t **__restrict __endptr, __locale_t __loc)
__THROW;
extern long double wcstold_l (__const wchar_t *__restrict __nptr,
wchar_t **__restrict __endptr,
__locale_t __loc) __THROW;
/* Copy SRC to DEST, returning the address of the terminating L'\0' in
DEST. */
extern wchar_t *wcpcpy (wchar_t *__restrict __dest,
__const wchar_t *__restrict __src) __THROW;
/* Copy no more than N characters of SRC to DEST, returning the address of
the last character written into DEST. */
extern wchar_t *wcpncpy (wchar_t *__restrict __dest,
__const wchar_t *__restrict __src, size_t __n)
__THROW;
#endif /* use GNU */
/* Wide character I/O functions. */
#ifdef __USE_XOPEN2K8
/* Like OPEN_MEMSTREAM, but the stream is wide oriented and produces
a wide character string. */
extern __FILE *open_wmemstream (wchar_t **__bufloc, size_t *__sizeloc) __THROW;
#endif
#if defined __USE_ISOC95 || defined __USE_UNIX98
__BEGIN_NAMESPACE_STD
/* Select orientation for stream. */
extern int fwide (__FILE *__fp, int __mode) __THROW;
/* Write formatted output to STREAM.
This function is a possible cancellation point and therefore not
marked with __THROW. */
extern int fwprintf (__FILE *__restrict __stream,
__const wchar_t *__restrict __format, ...)
/* __attribute__ ((__format__ (__wprintf__, 2, 3))) */;
/* Write formatted output to stdout.
This function is a possible cancellation point and therefore not
marked with __THROW. */
extern int wprintf (__const wchar_t *__restrict __format, ...)
/* __attribute__ ((__format__ (__wprintf__, 1, 2))) */;
/* Write formatted output of at most N characters to S. */
extern int swprintf (wchar_t *__restrict __s, size_t __n,
__const wchar_t *__restrict __format, ...)
__THROW /* __attribute__ ((__format__ (__wprintf__, 3, 4))) */;
/* Write formatted output to S from argument list ARG.
This function is a possible cancellation point and therefore not
marked with __THROW. */
extern int vfwprintf (__FILE *__restrict __s,
__const wchar_t *__restrict __format,
__gnuc_va_list __arg)
/* __attribute__ ((__format__ (__wprintf__, 2, 0))) */;
/* Write formatted output to stdout from argument list ARG.
This function is a possible cancellation point and therefore not
marked with __THROW. */
extern int vwprintf (__const wchar_t *__restrict __format,
__gnuc_va_list __arg)
/* __attribute__ ((__format__ (__wprintf__, 1, 0))) */;
/* Write formatted output of at most N character to S from argument
list ARG. */
extern int vswprintf (wchar_t *__restrict __s, size_t __n,
__const wchar_t *__restrict __format,
__gnuc_va_list __arg)
__THROW /* __attribute__ ((__format__ (__wprintf__, 3, 0))) */;
/* Read formatted input from STREAM.
This function is a possible cancellation point and therefore not
marked with __THROW. */
extern int fwscanf (__FILE *__restrict __stream,
__const wchar_t *__restrict __format, ...)
/* __attribute__ ((__format__ (__wscanf__, 2, 3))) */;
/* Read formatted input from stdin.
This function is a possible cancellation point and therefore not
marked with __THROW. */
extern int wscanf (__const wchar_t *__restrict __format, ...)
/* __attribute__ ((__format__ (__wscanf__, 1, 2))) */;
/* Read formatted input from S. */
extern int swscanf (__const wchar_t *__restrict __s,
__const wchar_t *__restrict __format, ...)
__THROW /* __attribute__ ((__format__ (__wscanf__, 2, 3))) */;
# if defined __USE_ISOC99 && !defined __USE_GNU \
&& (!defined __LDBL_COMPAT || !defined __REDIRECT) \
&& (defined __STRICT_ANSI__ || defined __USE_XOPEN2K)
# ifdef __REDIRECT
/* For strict ISO C99 or POSIX compliance disallow %as, %aS and %a[
GNU extension which conflicts with valid %a followed by letter
s, S or [. */
extern int __REDIRECT (fwscanf, (__FILE *__restrict __stream,
__const wchar_t *__restrict __format, ...),
__isoc99_fwscanf)
/* __attribute__ ((__format__ (__wscanf__, 2, 3))) */;
extern int __REDIRECT (wscanf, (__const wchar_t *__restrict __format, ...),
__isoc99_wscanf)
/* __attribute__ ((__format__ (__wscanf__, 1, 2))) */;
extern int __REDIRECT_NTH (swscanf, (__const wchar_t *__restrict __s,
__const wchar_t *__restrict __format,
...), __isoc99_swscanf)
/* __attribute__ ((__format__ (__wscanf__, 2, 3))) */;
# else
extern int __isoc99_fwscanf (__FILE *__restrict __stream,
__const wchar_t *__restrict __format, ...);
extern int __isoc99_wscanf (__const wchar_t *__restrict __format, ...);
extern int __isoc99_swscanf (__const wchar_t *__restrict __s,
__const wchar_t *__restrict __format, ...)
答案 1 :(得分：1)
正如我在评论中所建议的那样，您应该查看ICU，它是由IBM创建的用于Unicode处理的跨平台C库。它使用非常强大的String类为C ++和Java提供了额外的支持。它在Android和iOS等很多地方使用，因此它非常稳定和成熟。