我的C程序粘贴在下面。在bash中,程序打印"char is",Ω不打印。我的语言环境都是en_US.utf8。
#include <stdio.h>
#include <wchar.h>
#include <stdlib.h>
int main() {
int r;
wchar_t myChar1 = L'Ω';
r = wprintf(L"char is %cn", myChar1);
}
这很有趣。显然,编译器将omega从UTF-8翻译为UNICODE,但不知怎么的,libc把它弄乱了。
首先:%c
-格式说明符期望char
(即使在wprintf版本中),因此您必须指定%lc
(因此对于字符串指定%ls
)。
其次,如果您像这样运行代码,区域设置设置为C
(它不会自动从环境中获取)。您必须使用一个空字符串调用setlocale
来从环境中获取区域设置,这样libc就可以正常运行了。
#include <stdio.h>
#include <wchar.h>
#include <stdlib.h>
#include <locale.h>
int main() {
int r;
wchar_t myChar1 = L'Ω';
setlocale(LC_CTYPE, "");
r = wprintf(L"char is %lc (%x)n", myChar1, myChar1);
}
对于建议修复LIBC的答案,您可以这样做:
#include <stdio.h>
#include <wchar.h>
#include <stdlib.h>
// NOTE: *NOT* thread safe, not re-entrant
const char* unicode_to_utf8(wchar_t c)
{
static unsigned char b_static[5];
unsigned char* b = b_static;
if (c<(1<<7))// 7 bit Unicode encoded as plain ascii
{
*b++ = (unsigned char)(c);
}
else if (c<(1<<11))// 11 bit Unicode encoded in 2 UTF-8 bytes
{
*b++ = (unsigned char)((c>>6)|0xC0);
*b++ = (unsigned char)((c&0x3F)|0x80);
}
else if (c<(1<<16))// 16 bit Unicode encoded in 3 UTF-8 bytes
{
*b++ = (unsigned char)(((c>>12))|0xE0);
*b++ = (unsigned char)(((c>>6)&0x3F)|0x80);
*b++ = (unsigned char)((c&0x3F)|0x80);
}
else if (c<(1<<21))// 21 bit Unicode encoded in 4 UTF-8 bytes
{
*b++ = (unsigned char)(((c>>18))|0xF0);
*b++ = (unsigned char)(((c>>12)&0x3F)|0x80);
*b++ = (unsigned char)(((c>>6)&0x3F)|0x80);
*b++ = (unsigned char)((c&0x3F)|0x80);
}
*b = ' ';
return b_static;
}
int main() {
int r;
wchar_t myChar1 = L'Ω';
r = printf("char is %sn", unicode_to_utf8(myChar1));
return 0;
}
在输出前使用{glib,libiconv,ICU}将其转换为UTF-8