c++ - utf8 character counting not working -

can please explain why 1st function works 2nd doesn't?

unsigned int utf8_count(char* in) {     unsigned int = 0, c = 0;     while (in[i])     {         if ((in[i] & 0xc0) != 0x80)             c++;          i++;     }      return c; }  unsigned int utf8_count(char* in, unsigned int in_size) {     unsigned int = 0, c = 0;     while (i < in_size)     {         if ((in[i] & 0xc0) != 0x80)             c++;          i++;     }      return c; } 

i understand (in[i] & 0xc0) != 0x80 don't understand why i < in_size != in[i]?

example string: ゴールデンタイムラバー／スキマスイッチ 57 bytes, 19 characters.

why utf8_count(in, 57) return 57 , not 19?

the binary representation of example string:

works fine here.. http://ideone.com/oepqg1

i tested in both codeblocks on windows 8 using g++ 4.8.1 , msvc 2013. tried on linux.. works. both print 19..

so whatever you're feeding not same string have in op..

// utf8test.cpp : defines entry point console application. //  #include "stdafx.h" #include <iostream> #include <cstring> #include <clocale>  int strlen_u8(const char* str) {     int = 0, j = 0;      while (str[i])     {         if ((str[i] & 0xc0) != 0x80)         {             ++j;         }         ++i;     }     return j; }  int strlen_s_u8(const char* str, unsigned int size) {     unsigned int = 0, j = 0;     while (i < size)     {         if ((str[i] & 0xc0) != 0x80)         {             ++j;         }         ++i;     }     return j; }   #if defined _msc_ver || defined _win32 || defined _win64 int _tmain(int argc, _tchar* argv[]) #else int main(int argc, char* argv[]) #endif {     #ifdef _msc_ver     const char* str = "ゴールデンタイムラバー／スキマスイッチ";     #else     const char* str = u8"ゴールデンタイムラバー／スキマスイッチ";     std::setlocale(lc_all, "ja_jp.utf-8");     #endif      std::cout << strlen_u8(str) << "\n";     std::cout << strlen_s_u8(str, strlen(str)) << "\n"; //can use 57 instead of strlen.     std::cin.get(); }