ReadUtf8ToString

UTF-8文件读取转换

最新推荐文章于 2025-09-13 10:25:19 发布

原创最新推荐文章于 2025-09-13 10:25:19 发布 · 1.2k 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#null #string #delete #file

中文处理专栏收录该内容

20 篇文章

订阅专栏

本文介绍了一种从UTF-8编码的文件中读取数据并将其转换为ANSI字符串的方法。通过使用C++实现的函数，可以处理文件读取过程中的多种错误情况，并详细展示了如何利用Windows API进行编码转换。

部署运行你感兴趣的模型镜像

	bool ReadUtf8ToString(const string &filename, string &content){
		content = "";
		FILE *myfile;
		wchar_t *name= new wchar_t[filename.length() * 2 + 5];
		if(name == NULL){
			cerr << "ReadUtf8ToString: Memory allocate error for " << filename << endl;
			return false;
		}
		swprintf(name, L"%S", filename.c_str()); 
		//ANSI string => Uicode string，注意，S要大写
		myfile=_wfopen(name,L"rb");  //以二进制方式读
		if(myfile == NULL){
			cerr << "ReadUtf8ToString: Can't open file: " << filename << endl;
			return false;
		}
		fseek(myfile,3,0);
		char buff[4098];
		//取得所有UTF-8字节
		while(fgets(buff,4098,myfile)){
			//先把UTF-8转换为UNICODE
			int num=MultiByteToWideChar(CP_UTF8,0,buff,-1,NULL,0);
			if(num <= 0){
				cerr << "UTF-8 Converting to UNICODE error for " << filename << endl;
				return false;
			}
			wchar_t *buffw2=new wchar_t[num];
			if(buffw2 == NULL){
				cerr << "ReadUtf8ToString: Memory allocate error for " << filename << endl;
				return false;
			}
			MultiByteToWideChar(CP_UTF8,0,buff,-1,buffw2,num);

			//再将Unicode转换为ANSI字符串
			int len = WideCharToMultiByte(CP_ACP, 0, buffw2, num, NULL, 0, NULL, NULL);
			if(len <= 0){
				cerr << "UNICODE Converting to ANSIC error for " << filename << endl;
				return false;
			}
			LPSTR lpsz = new CHAR[len+1];
			if(lpsz == NULL){
				cerr << "ReadUtf8ToString: Memory allocate error for " << filename << endl;
				return false;
			}
			WideCharToMultiByte(CP_ACP, 0, buffw2, num, lpsz, len, NULL, NULL);
			lpsz[len]='\0';
			content += string(lpsz);
			delete []buffw2;
			delete []lpsz;
		}
		delete []name;
		return true;
	}

您可能感兴趣的与本文相关的镜像