Decoding (ISO-8859-1) String Format

Here is a function that will do the conversion.

dest is the the destination space where to copy the result
maxspace is the maximum amount of characters dest can hold
src is the input string

---

int decodeCharEntities( wchar_t *dest, size_t maxspace, const char *src );

char *str = "أهداف للمناقشة";
int main( int argc, char **argv )
{
    wchar_t dest[ 100 ];
    int len = decodeCharEntities( dest, 100, str );
    wprintf( L"%s (len=%d)\n", dest, len );
}

// helper function for decodeCharEntities
static wchar_t parseCharEntity( const char *&src )
{
    int val = 0, base = 10;
    if( *src != '#' )
        return (wchar_t) *src;
    if( *++src == 'x' )
    {
        base = 16;
        ++src;
    }
    for(;; ++src ) switch( *src )
    {
        case '0': case '1': case '2': case '3': case '4':
        case '5': case '6': case '7': case '8': case '9':
            val = val * base + ( *src & 0xf );
            break;
        case 'a': case 'b': case 'c': case 'd': case 'e': case 'f':
        case 'A': case 'B': case 'C': case 'D': case 'E': case 'F':
            val = ( val << 4 ) + 9 + ( *src & 0xf );
            break;
        default:
            return (wchar_t) val;
        case '\0':
            return 0;
    }
}

// decodes xml-style char entities
// returns the number of characters written to dest (excluding '\0')
int decodeCharEntities( wchar_t *dest, size_t maxspace, const char *src )
{
    size_t cnt;
    if( !( cnt = maxspace ) )
        return 0;
    for( --maxspace; --cnt && *src; ++dest, ++src )
    {
        if( *src != '&' )
            *dest = (wchar_t) *src;
        else if( !( *dest = parseCharEntity( ++src ) ) )
            break;
    }
    *dest = 0;
    return maxspace - cnt;
}

You can do that like

#include <stdlib.h>
#include <string>
#include <iostream>
using namespace std;

wchar_t EntityToUnicode(const string& strEntity) {

      char* pcCnvEnd;

      long l = strtol(strEntity.c_str(), &pcCnvEnd, 10);

      if (*pcCnvEnd == ';') return (wchar_t) l;

      return 0;
}

int DecodeEntities(string strIn, wstring& strResult) {

   const string strDelim = "&#";

   int nPos = 0;
   int nCount = 0;
   int nFound;
   string strToken;

   while(1) {

      nFound = strIn.find(strDelim,nPos);

      if (-1 == nFound)  {

        strToken = strIn.substr(nPos,strIn.length() - nPos);
        strResult += EntityToUnicode(strToken);
        break;
      }

      strToken = strIn.substr(nPos,nFound - nPos);
      strResult += EntityToUnicode(strToken);

      nPos = nFound + strDelim.size();

      ++nCount;

   }

   return nCount;
}

int main () {


   wstring strResult;

   DecodeEntities("&#1571;&#1607;&#1583;&#1575;&#1601; &#1604;&#1604;&#1605;&#1606;&#1575;&#1602;&#1588;&#1577;",strResult);

   wcout << strResult;
}

See also http://en.wikipedia.org/wiki/HTML_entities and http://en.wikipedia.org/wiki/Universal_Character_Set