UTF-8转ANSI

最新推荐文章于 2024-10-19 12:18:22 发布

原创最新推荐文章于 2024-10-19 12:18:22 发布 · 1.9k 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#utf-8 #编码

代码片段专栏收录该内容

27 篇文章

订阅专栏

本文详细介绍了如何将UTF-8编码的文本转换为ANSI编码，包括手动转换步骤和使用工具的方法，帮助读者理解两种编码系统的差异并顺利完成转换操作。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

#include <windows.h>
#include "FileOp.h"

/**
* @brief        将UTF-8编码格式的字符串转换为ANSI编码格式的字符串
* @param[in]    strUTF8     输入字符串
* @param[out]   strAnsi     输出字符串缓冲区
* @param[in]    iLen        strAnsi缓冲区的大小
*/
int Utf8ToAnsi(const char* strUTF8, char* strAnsi, int iLen)
{
    int len = MultiByteToWideChar(CP_UTF8, 0,strUTF8, -1, NULL, 0);
    if ( len < 1 )
    {
        return len;
    }
    wchar_t *strUnicode = (wchar_t *)malloc(sizeof(wchar_t)*len);
    if ( NULL == strUnicode )
    {
        return -1;
    }
    len = MultiByteToWideChar(CP_UTF8, 0, strUTF8, -1, strUnicode, len);
    if ( len < 1 )
    {
        free(strUnicode);
        return len;
    }

    len = WideCharToMultiByte(CP_ACP, 0, strUnicode, -1, NULL, 0, NULL, NULL);
    if ( len < 1 )
    {
        free(strUnicode);
        return len;
    }
    if ( iLen < len )
    {
        return len;
    }
    len = WideCharToMultiByte(CP_ACP, 0, strUnicode, -1, strAnsi, iLen, NULL, NULL);
    free(strUnicode);

    return len;
}

/**
* @brief        将ANSI编码格式的字符串转换为UTF-8编码格式的字符串
* @param[in]    strAnsi     输入字符串
* @param[out]   strUTF8     输出字符串缓冲区
* @param[in]    iLen        strUTF8缓冲区的大小
*/
int AnsiToUtf8(const char* strAnsi, char* strUTF8, int iLen)
{
    int len = MultiByteToWideChar(CP_ACP, 0,strAnsi, -1, NULL, 0);
    if ( len < 1 )
    {
        return len;
    }
    wchar_t *strUnicode = (wchar_t *)malloc(sizeof(wchar_t)*len);
    if ( NULL == strUnicode )
    {
        return -1;
    }
    len = MultiByteToWideChar(CP_ACP, 0, strAnsi, -1, strUnicode, len);
    if ( len < 1 )
    {
        free(strUnicode);
        return len;
    }

    len = WideCharToMultiByte(CP_UTF8, 0, strUnicode, -1, NULL, 0, NULL, NULL);
    if ( len < 1 )
    {
        free(strUnicode);
        return len;
    }
    if ( iLen < len )
    {
        return len;
    }
    len = WideCharToMultiByte(CP_UTF8, 0, strUnicode, -1, strUTF8, iLen, NULL, NULL);
    free(strUnicode);

    return len;
}

int main()
{
    // 备注：需要自行判断并去除 EF BB BF
    const char* szInFileName = "D:/utf-8.txt";
    const char* szOutFileName = "D:/gb2312.txt";

    char* pbInData = FILE_OP_ReadAllDataFromFileEx(szInFileName, FLAG_SZ_END_WITH_ZERO);
    printf("utf8[%d] = [%s]\n", FILE_OP_RetFileSize(szInFileName), pbInData);

    int len = Utf8ToAnsi(pbInData, NULL, 0);
    char* pbOutData = new char[len];
    len = Utf8ToAnsi(pbInData, pbOutData, len);
    if ( len > 0 )
    {
        printf("gb2312[%d] = [%s]\n", len,pbOutData);
        FILE_OP_WriteDataToFile(szOutFileName, (PBYTE)pbOutData, len-1); // 去掉末尾的'\0'
    }

    SAFE_FREE(pbOutData);
    SAFE_FREE(pbInData);
    return 0;
}

int main_test_AnsiToUtf8()
{
    const char* szInFileName = "D:/gb2312.txt";
    const char* szOutFileName = "D:/utf-8.txt";

    char* pbInData = FILE_OP_ReadAllDataFromFileEx(szInFileName, FLAG_SZ_END_WITH_ZERO);
    printf("gb2312[%d] = [%s]\n", FILE_OP_RetFileSize(szInFileName), pbInData);

    int len = AnsiToUtf8(pbInData, NULL, 0);
    char* pbOutData = new char[len];
    len = AnsiToUtf8(pbInData, pbOutData, len);
    if ( len > 0 )
    {
        printf("utf8[%d] = [%s]\n", len,pbOutData);
        FILE_OP_WriteDataToFile(szOutFileName, (PBYTE)pbOutData, len-1);
    }

    SAFE_FREE(pbOutData);
    SAFE_FREE(pbInData);
    return 0;
}