If you ever worry about C++ and character sets...
Posted: Sun Aug 14, 2011 9:18 am
Yesterday I had trouble finding out what the problem was when
just printed an "õ" (o with tilde above) to the console, when it should print an a with diaeresis. Turned out I had trouble with character sets. More specifically was it the console to display text in the IBM-850 charset (which you can access on windows using Alt+Num [0 to 255]) and my c++ char variables to represent ISO/IEC 8859-15 characters (on Windows: Alt+Num [00 to 0255]), the standard whereof unicode is the superset.
I asked some stuff on the irc afterwards and followed Ginto's advice to make a conversion table. Because I don't want you to ever have the pain, here is my ready-to-use result.
Now, if you want to display IBM-850 characters in Unicode, use this conversion table. (attention! I said unicode, so this one is of type wchar)
Possibly someday you might find this useful 
btw, If the code snippet section ever has a revival, feel free to move this topic there.
Code: Select all
std::cout << "ä" << std::endl;I asked some stuff on the irc afterwards and followed Ginto's advice to make a conversion table. Because I don't want you to ever have the pain, here is my ready-to-use result.
Code: Select all
#include <string>
using namespace std;
char T_IsoToIbm[ 256 ] = {
0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x09, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x19, 0x1A, 0x1B, 0x1C, 0x1D, 0x1E, 0x1F,
0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, 0x28, 0x29, 0x2A, 0x2B, 0x2C, 0x2D, 0x2E, 0x2F,
0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0x3A, 0x3B, 0x3C, 0x3D, 0x3E, 0x3F,
0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F,
0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5A, 0x5B, 0x5C, 0x5D, 0x5E, 0x5F,
0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F,
0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7A, 0x7B, 0x7C, 0x7D, 0x7E, 0x7F,
0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x8A, 0x8B, 0x8C, 0x8D, 0x8E, 0x8F,
0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, 0x98, 0x99, 0x9A, 0x9B, 0x9C, 0x9D, 0x9E, 0x9F,
0xFF, 0xAD, 0xBD, 0x9C, 0xCF, 0xBE, 0xDD, 0xF5, 0xF9, 0xB8, 0xA6, 0xAE, 0xAA, 0xF0, 0xA9, 0xEE,
0xF8, 0xF1, 0xFD, 0xFC, 0xEF, 0xE6, 0xF4, 0xFA, 0xF7, 0xFB, 0xA7, 0xAF, 0xAC, 0xAB, 0xF3, 0xA8,
0xB7, 0xB5, 0xB6, 0xC7, 0x8E, 0x8F, 0x92, 0x80, 0xD4, 0x90, 0xD2, 0xD3, 0xDE, 0xD6, 0xD7, 0xD8,
0xD1, 0xA5, 0xE3, 0xE0, 0xE2, 0xE5, 0x99, 0x9E, 0x9D, 0xEB, 0xE9, 0xEA, 0x9A, 0xED, 0xE8, 0xE1,
0x85, 0xA0, 0x83, 0xC6, 0x84, 0x86, 0x91, 0x87, 0x8A, 0x82, 0x88, 0x89, 0x8D, 0xA1, 0x8C, 0x8B,
0xD0, 0xA4, 0x95, 0xA2, 0x93, 0xE4, 0x94, 0xF6, 0x9B, 0x97, 0xA3, 0x96, 0x81, 0xEC, 0xE7, 0x98
};
string IsoToIbm( const string Iso8859 ) {
int i;
string result;
unsigned char current;
unsigned char converted;
for( i = 0; i < Iso8859.length(); i++ ) {
current = Iso8859[ i ];
converted = T_IsoToIbm[ current ];
result += converted;
}
return result;
}
Code: Select all
wchar_t T_IbmToIso[ 256 ] = {
/*0*/0x00, 0x263A, 0x2638, 0x2665, 0x2666, 0x2663, 0x2660, 0x2022, 0x25D8, 0x25CB, 0x25D9, 0x2642, 0x2640, 0x266A, 0x2668, 0x263C,
/*1*/0x25BA, 0x25c4, 0x2195, 0x203c, 0xb6, 0xa7, 0x25ac, 0x21a8, 0x2191, 0x2193, 0x2192, 0x2190, 0x221f, 0x2194, 0x2582, 0x258c,
/*2*/0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, 0x28, 0x29, 0x2A, 0x2B, 0x2C, 0x2D, 0x2E, 0x2F,
/*3*/0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0x3A, 0x3B, 0x3C, 0x3D, 0x3E, 0x3F,
/*4*/0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0x4A, 0x4B, 0x4C, 0x4D, 0x4E, 0x4F,
/*5*/0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5A, 0x5B, 0x5C, 0x5D, 0x5E, 0x5F,
/*6*/0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F,
/*7*/0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7A, 0x7B, 0x7C, 0x7D, 0x7E, 0x2302,
/*8*/0xc7, 0xfc, 0xe9, 0xe2, 0xe4, 0xe0, 0xe5, 0xe7, 0xea, 0xeb, 0xe8, 0xef, 0xee, 0xec, 0xc4, 0xc5,
/*9*/0xc9, 0xe6, 0xc6, 0xf4, 0xf6, 0xf2, 0xf8, 0xf9, 0xff, 0xd6, 0xdc, 0xf8, 0xa3, 0xd8, 0xd7, 0x0192,
/*A*/0xe1, 0xed, 0xf3, 0xfa, 0xf1, 0xd1, 0xaa, 0xba, 0xbf, 0xae, 0xac, 0xbd, 0xbc, 0xa1, 0xab, 0xb8,
/*B*/0x2591, 0x2592, 0x2593, 0x2502, 0x2524, 0xc1, 0xc2, 0xc0, 0xa9, 0x2563, 0x2551, 0x2557, 0x255d, 0xa2, 0xa5, 0x2510,
/*C*/0x2514, 0x2534, 0x252c, 0x251c, 0x2500, 0x253c, 0xe3, 0xc3, 0x255a, 0x2554, 0x2569, 0x2566, 0x2560, 0x2550, 0x256C, 0xA4,
/*D*/0xF0, 0xD0, 0xCA, 0xCB, 0xC8, 0x0131, 0xCD, 0xCE, 0xCF, 0x2518, 0x250c, 0x2588, 0x2584, 0xA6, 0xCC, 0x2580,
/*E*/0xD3, 0xDF, 0xD4, 0xD2, 0xF5, 0xD5, 0xB5, 0xFE, 0xDE, 0xDA, 0xDB, 0xD9, 0xFD, 0xDD, 0xAF, 0xB4,
/*F*/0xAD, 0xB1, 0x2017, 0xBE, 0xB6, 0xA7, 0xF7, 0xB8, 0xB0, 0xA8, 0xB7, 0xB9, 0xB3, 0xB2, 0x25A0, 0xA0
};
btw, If the code snippet section ever has a revival, feel free to move this topic there.