C++ source code to get substrings of UTF-8.

SubStrUtf8.cpp

#include <iostream>
#include <string.h>

using namespace std;

/*
 * [CLASS] Proc
 */
class Proc
{
    int cntByte(unsigned char);           // Count bytes

public:
    char* subStr(const char*, int, int);  // Get substring
};

/*
 * Get substring
 */
char* Proc::subStr(const char *cStr, int iStart, int iLength)
{
    static char cRes[1024];
    char* pRes = cRes;
    int i = 0, iPos = 0;
    int iByte;

    while (cStr[i] != '\0') {
        iByte = cntByte(cStr[i]);
        if (iStart <= iPos && iPos < iStart + iLength) {
            memcpy(pRes, (cStr + i), iByte);
            pRes += iByte;
        }
        i += iByte;
        iPos++;
    }
    *pRes = '\0';

    return cRes;
}

/*
 * Count bytes
 */
int Proc::cntByte(unsigned char cChar)
{
   int iByte;

   if ((cChar >= 0x00) && (cChar <= 0x7f)) {
       iByte = 1;
   } else if ((cChar >= 0xc2) && (cChar <= 0xdf)) {
       iByte = 2;
   } else if ((cChar >= 0xe0) && (cChar <= 0xef)) {
       iByte = 3;
   } else if ((cChar >= 0xf0) && (cChar <= 0xf7)) {
       iByte = 4;
   } else if ((cChar >= 0xf8) && (cChar <= 0xfb)) {
       iByte = 5;
   } else if ((cChar >= 0xfc) && (cChar <= 0xfd)) {
       iByte = 6;
   } else {
       iByte = 0;
   }

   return iByte;
}

/*
 * Execution
 */
int main(){
    const char* cStr = "ｺﾚﾊ 部分文字列取得の TEST です。";
    char* cRes;

    try {
        Proc objMain;
        cRes = objMain.subStr(cStr, 2, 13);
        cout << "* " << cStr << "\n"
             << "  => " << cRes << endl;
    } catch (const char* e) {
        cerr << "[EXCEPTION] " << e << endl;
        return 1;
    }
    return 0;
}