来自 fgetc, fgetwc 的 MSDN 文档
fgetc 将读取的字符返回为 int 或返回 EOF 以指示错误或文件结束。 fgetwc 返回,作为
wint_t,对应读取的字符的宽字符或
返回 WEOF 表示错误或文件结束。
WEOF 被定义为 0xFFFF,这是您之前替换的 65535
#define WEOF ((wint_t)(0xFFFF))
所以对于宽字符的EOF 测试应该改为
if ((ch = fgetwc(stream)) != WEOF) ...
编辑
int main()
{
wchar_t buf[5];
memset(buf, '\0', sizeof(buf));
wcscpy(buf, L"1234");
FILE *stream = _wfopen(L"C:\\eoftest.txt", L"rb");
if (!stream)
{
stream = _wfopen(L"C:\\eoftest.txt", L"w+b");
if (!stream)
{
printf("cannot create file\n");
return 0;
}
fwrite((char*)buf, sizeof(buf[0]), wcslen(buf), stream);
fseek(stream, 0, 0);
}
int len = sizeof(buf) / sizeof(buf[0]);
for (int i = 0; i < len; i++)
{
wchar_t ch = fgetwc(stream);
if (ch == WEOF) break;
buf[i] = ch;
}
wprintf(L"result = %s\n", buf);
return 0;
}
编辑 2:这将逐行打印 unicode 文件的内容:
int main()
{
FILE *stream = _wfopen(L"c:\\test\\test.txt", L"rb");
if (!stream) return 0;
int buflen = 256;
wchar_t* buf = (wchar_t*)malloc(buflen * sizeof(wchar_t));
if (fread(buf, 2, 1, stream))
{
if (buf[0] != 0xFEFF)
{
//BOM not detected, go back to start of file
rewind(stream);
}//else, skip the first 2 bytes
}
int i = 0, line = 0;
wint_t ch = 0;
while (ch != WEOF)
{
ch = fgetwc(stream);
if (ch == L'\n' || ch == WEOF)
{
//null-terminate the buffer at i
buf[i] = L'\0';
//trim the '\r' at the end, if any
if (i > 0 && buf[i - 1] == '\r') buf[i - 1] = L'\0';
wprintf(L"%3d %s\n", ++line, buf);
//start a new line for the next pass
i = 0;
}
else
{
buf[i] = ch;
i++;
if (i == buflen)
{
//increase buffer:
buflen += 256;
buf = (wchar_t*)realloc(buf, buflen * sizeof(wchar_t));
}
}
}
free(buf);
return 0;
}