Mutual conversion between ANSI and UTF8 format files

Original link: https://blog.csdn.net/qq_23313467/article/details/104842156

Mutual conversion between ANSI and UTF8 format files

This article describes how to convert between UTF8 and ANSI.

Conversion key point 1:

UTF8 files have a unique file header flag, the first 3 bytes are: 0xEF, 0xBB, 0xBF;

ANSI files do not have a header file and start placing content directly.

Conversion key point 2:

When UTF8 and ANSI are converted to each other, UNICODE is required as the intermediate conversion value; that is, UTF8 is converted to UNICODE first, and then UNICODE is converted to ANSI; and vice versa.

The following code can convert ANSI-encoded files to UTF8-encoded files:

#include <iostream>
#include <direct.h>
#include <string>
#include <io.h>
#include <stdio.h>

#include <windows.h>

using namespace std;

int FileAnsi2UTF8(char* strFileName)
{
    //CopyFile(strFileName,("newUtf8.txt"),FALSE);//

    FILE *fp = fopen(strFileName, "r");//FILE *fp = fopen("cc.cfg", "r+");
    if(fp == NULL)
    {
        cout << "open error";//printf("open error");
        return -1;
    }
    byte head[3];
    fread(head,3,1,fp);//fileReader.Read(head, 3);
    //判断是否带有BOM文件头
    if (head[0] == 0xef && head[1] == 0xbb && head[2] == 0xbf)
    {
        fclose(fp);//fileReader.Close();
        return -30;
    }
    fseek(fp,0,SEEK_SET);fileReader.SeekToBegin();

    char linebuffer[512] = {0};
    char linenew[1024]={0};

    FILE *fpnew = fopen("newUtf8.txt", "w+");//FILE *fp = fopen("cc.cfg", "r+");
    if(fpnew == NULL)
    {
        cout << "open new error";//printf("open new error");
        fclose(fp);
        return -1;
    }
    const unsigned char aryBOM[] = { 0xEF, 0xBB, 0xBF };
    fwrite(aryBOM, sizeof(aryBOM),1,fpnew);

    while(fgets(linebuffer, 512, fp))
    {
        int len = MultiByteToWideChar(CP_ACP, 0, linebuffer, -1, NULL, 0);//strlen(gb2312);//
        wchar_t* wstr = new wchar_t[len + 1];
        memset(wstr, 0, len + 1);
        MultiByteToWideChar(CP_ACP, 0, linebuffer, -1, wstr, len);
        len = WideCharToMultiByte(CP_UTF8, 0, wstr, -1, NULL, 0, NULL, NULL);
        char* str = new char[len + 1];
        memset(str, 0, len + 1);
        len = WideCharToMultiByte(CP_UTF8, 0, wstr, -1, str, len, NULL, NULL);

        if (wstr) delete[] wstr;
        str[len] = 0;//'\n';
        fwrite(str, len-1,1,fpnew);//fp.Write(str, len);
        delete[] str;
    }
    fclose(fp);
    fclose(fpnew);
    return 0;
}

The following code can convert a UTF8-encoded file to an ANSI-encoded file:

int FileUtf82ANSI(char* strFileName)
{
    FILE *fp = fopen(strFileName, "r");//FILE *fp = fopen("cc.cfg", "r+");
    if(fp == NULL)
    {
        cout << "open error";//printf("open error");
        return -1;
    }
    byte head[3];
    fread(head,3,1,fp);//fileReader.Read(head, 3);
    //判断是否带有BOM文件头
    if (head[0] != 0xef || head[1] != 0xbb || head[2] != 0xbf)
    {
        fclose(fp);//fileReader.Close();
        return -30;
    }
    fseek(fp,3,SEEK_SET);fileReader.SeekToBegin();

    char linebuffer[512] = {0};
    char linenew[1024]={0};

    FILE *fpnew = fopen("newAnsi.txt", "w+");//FILE *fp = fopen("cc.cfg", "r+");
    if(fpnew == NULL)
    {
        cout << "open new error";//printf("open new error");
        fclose(fp);
        return -1;
    }
    //const unsigned char aryBOM[] = { 0xEF, 0xBB, 0xBF };
    //fwrite(aryBOM, sizeof(aryBOM),1,fpnew);

    while(fgets(linebuffer, 512, fp))
    {
        //预转换，得到所需空间的大小
        int wcsLen = ::MultiByteToWideChar(CP_UTF8, NULL, linebuffer, -1, NULL, 0);
        //分配空间要给'\0'留个空间，MultiByteToWideChar不会给'\0'空间
        wchar_t * pUcs2 = new wchar_t[wcsLen + 1];
        //转换
        ::MultiByteToWideChar(CP_UTF8, NULL, linebuffer, -1, pUcs2, wcsLen);
        //最后加上'\0'
        pUcs2[wcsLen] = '\0';
        //预转换，得到所需空间的大小，这次用的函数和上面名字相反
        int ansiLen = ::WideCharToMultiByte(CP_ACP, NULL, pUcs2, wcslen(pUcs2), NULL, 0, NULL, NULL);
        //同上，分配空间要给'\0'留个空间
        char * pAnsi = new char[ansiLen + 1];
        //转换
        //unicode版对应的strlen是wcslen
        ::WideCharToMultiByte(CP_ACP, NULL, pUcs2, wcslen(pUcs2), pAnsi, ansiLen, NULL, NULL);
        //最后加上'\0'
        pAnsi[ansiLen] = '\0';

        if (pUcs2) delete[] pUcs2;
        fwrite(pAnsi, ansiLen,1,fpnew);//fp.Write(str, len);
        delete[] pAnsi;
    }
    fclose(fp);
    fclose(fpnew);
    return 0;
}
————————————————