read UTF-8 text file in C++_read utf-8 text file c++-优快云博客

本文链接：https://blog.youkuaiyun.com/masterz/article/details/6854328

本文探讨了使用C++读取文件并处理UTF-8编码的流程，包括设置区域、读取文件内容、检测UTF-8 BOM及转换为宽字符。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

#include <windows.h>
#include <stdio.h>
#include <stdlib.h>
#include <locale>
#include <iostream>
int main(int argc, char* argv[])
{
    if (argc>1)
    {
        char* full_path= argv[1];
        FILE * fp ;
        char * test = setlocale(LC_ALL,"chs");
        char tmpbuff[1024];
        fp = fopen(full_path,"r, ccs=UTF-8"); // linux does not support ccs=UTF-8
        size_t result = fread(tmpbuff, 1, sizeof(tmpbuff)-1,fp);
        if (result >0)
        {
            tmpbuff[result] = 0;
            printf("result is %d.\n", result);
        }
        wchar_t* mbyte_buf=new wchar_t[result*4];
        char* start_pos = tmpbuff;
        if(start_pos[0]==(char)0xEF && start_pos[1]==(char)0xBB && start_pos[2]==(char)0xBF) //0xEF,0xBB,0xBF
        {
            start_pos += 3;
            result -= 3;
            std::cout<< "There is UTF-8 BOM in " << full_path << std::endl;
        }
        else
        {
            std::cout<< "There is no UTF-8 BOM in " << full_path << std::endl;
        }
        int n = ::MultiByteToWideChar(CP_UTF8, 0, (LPCSTR)start_pos, result, mbyte_buf, result/*, NULL, NULL*/);
        std::wcout<<mbyte_buf<<std::endl;
    }
    return 0;

}