每个使用C或者C++直到D的人都要认识到的Unicode问题:
如果你的程序要在更广的国度使用,或者要进入Internet,你都要使用Unicode!
先列个提纲,细节解释待续!
1.编码 ansi,mbcs/dbcs,unicode,ucs2
2.类型 ansi char ,utf8 char,wchar,dchar
3.类型的指针和内存复制
4.windows的知识
windwos98,2000,windowsCE
D代码
- public import std.c.string;
- public import std.string;
- public import std.utf;
- //win32
- import win32.windows;
- template zstr(T)
- {
- T[] zstr(T[] chars)
- {
- uint l = chars.length;
- chars.length = l + 1;
- chars[l] = 0;
- return chars;
- }
- }
- char[] w2a( wchar[] w ) { return toUTF8(w); }
- char[] w2az( wchar[] w ) { return zstr!(char)(w2a(w)); }
- char[] wz2a( wchar* w ) { return toUTF8( wz2w(w) ); }
- char[] wz2az( wchar* w ) { return zstr!(char)(wz2a(w)); }
- wchar[] a2w( char[] a ) { return toUTF16(a); }
- wchar[] a2wz( char[] a ) { return zstr!(wchar)(a2w(a)); }
- wchar[] az2w( char* a ) { return toUTF16( az2a(a) ); }
- wchar[] az2wz( char* a ) { return zstr!(wchar)(az2w(a)); }
- wchar[] wz2w( wchar* w ) { return w? w[0..wcslen(w)]: null; }
- char[] az2a( char* a ) { return a? a[0..strlen(a)]: null; }
- wchar[] w2wz( wchar[] w ) { return zstr!(wchar)(w); }
- char[] a2az( char[] a ) { return zstr!(char)(a); }
- const uint CP_ACP = 0; /* default to ANSI code page */
- const uint CP_OEMCP = 1; /* default to OEM code page */
- // wchar[] to multibyte string, zero terminated
- char[] wcs2mbz(wchar[] ws)
- {
- uint codepage = CP_OEMCP; //2000/+
- char[] rz;
- rz.length = WideCharToMultiByte(codepage, 0, ws.ptr, ws.length, null, 0, null, null) + 1;
- WideCharToMultiByte(codepage, 0, ws.ptr, ws.length, rz.ptr, rz.length, null, null);
- rz[rz.length-1] = 0;
- rz.length = rz.length-1;
- return rz;
- }
- // multibyte string to wide string
- wchar[] mbz2wcs(char[] s)
- {
- uint codepage = CP_OEMCP; //2000/+
- wchar[] rz;
- rz.length = MultiByteToWideChar(codepage, 0, s.ptr, s.length, null, 0) + 1;
- MultiByteToWideChar(codepage, 0, s.ptr, s.length, rz.ptr, rz.length);
- rz[rz.length-1] = 0;
- rz.length = rz.length-1;
- return rz;
- }
- void main()
- {
- char[] ctext,ccaption;
- wchar[] wtext,wcaption;
- wcaption="中文软件a1A";
- ccaption="中文软件a1A";
- wtext="1.unicode的windows函数 调用宽字符:直接转换为0结尾的字符串,";
- MessageBoxW(null, w2wz(wtext).ptr, w2wz(wcaption).ptr, MB_OK | MB_ICONEXCLAMATION);
- ctext="2.unicode的windows函数 调用普通字符:转换utf16的0结尾的字符串,";
- MessageBoxW(null, a2wz(ctext).ptr, a2wz(ccaption).ptr, MB_OK | MB_ICONEXCLAMATION);
- wtext="3.ANSI的windows函数 调用宽字符:转换为toUTF8的0结尾的字符串,标题乱码,";
- MessageBoxA(null, wcs2mbz(wtext).ptr, w2az(wcaption).ptr, MB_OK | MB_ICONEXCLAMATION);
- wtext="4.ANSI的windows函数 调用宽字符:用WideCharToMultiByte转换为0结尾的ANSI字符串,";
- MessageBoxA(null, wcs2mbz(wtext).ptr, wcs2mbz(wcaption).ptr, MB_OK | MB_ICONEXCLAMATION);
- ctext="5.ANSI的windows函数 调用普通字符:用WideCharToMultiByte转换为0结尾的ANSI字符串,标题乱码.";
- convert UTF-8 to MBCS
- MessageBoxA(null, wcs2mbz(a2w(ctext)).ptr, a2az(ccaption).ptr, MB_OK | MB_ICONEXCLAMATION);
- }
- /*
- 1.调用ANSI函数
- 2.调用Unicode函数
- 3.函数返回值,分配内存:
- 4.调用要使用字符数量:chars.sizeof/wchar.sizeof =chars.length
- */