c++ - 如何将文本文件从 Windows 转换为 Unix

Question

从 Unix 转换到 Windows 时，我得到了正确的输出；然而，当从 Windows 转到 Unix 时，我得到了一些奇怪的输出。我认为我所允许的只是删除回车符“\r”。但这不起作用。当我在运行代码后打开文本文件时，我得到了一些奇怪的结果，第一行是正确的，然后一切都失败了。

   int main( )
{
   bool windows = false;
   char source[256];
   char destination[256]; // Allocate the max amount of space for the filenames.

   cout << "Please enter the name of the source file: ";
   cin >> source;

   ifstream fin( source, ios::binary );
   if ( !fin )          // Check to make sure the source file exists.
   {
      cerr << "File " << source << " not found!";
      getch();
      return 1;
   }//endif

   cout << "Please enter the name of the destination file: ";
   cin >> destination;

   ifstream fest( destination );
   if ( fest )          // Check to see if the destination file already exists.
   {
      cout << "The file " << destination << " already exists!" << endl;
      cout << "If you would like to truncate the data, please enter 'Y', "
           << "otherwise enter 'N' to quit: ";
      char answer = char( getch() );
      if ( answer == 'n' || answer == 'N' )
      {
         return 1;
      }//endif
   }//endif
   clrscr();            // Clear screen for neatness.

   ofstream fout( destination, ios::binary );
   if ( !fout.good() )  // Check to see if the destination file can be edited.
   {
      cout << destination << "could not be opened!" << endl;
      getch();
      return 1;
   }//endif
                        // Open the destination file in binary mode.
   fout.open( destination, ios::binary );
   char ch = fin.get(); // Set ch to the first char in the source file.
   while ( !fin.eof() )
   {
      if ( ch == '\x0D' ) // If ch is a carriage return, then the source file
      {                   // must be in a windows format.
         windows = true;
      }//endif
      if ( windows == true )
      {
         ch = fin.get();  // Advance ch, so that at the bottom of the loop, the
      }//endif            // carriage return is not coppied into the new file.
      if ( windows == false )
      {
         if ( ch == '\x0A' )    // If the file is in the Unix format..
         {
            fout.put( '\x0D' ); // When a new line is found, output a carriage
         }//endif               // return.
      }//endif

      fout.put( ch );
      ch = fin.get();
   }//endwh
   if ( windows == true )
   {
      fout.put( '\x0A' );
   }//endif
   fout.close();
   fin.close();                 // Close yer files.

   if ( windows == true )       // A little output for user-friendly-ness.
   {
      cout << "The contents of " << source << " have been coppied to "
           << destination << " and converted to Unix format." << endl;
   }else{
      cout << "The contents of " << source << " have been coppied to "
           << destination << " and converted to Windows format." << endl;
   }//endif
   cout << "Enter any key to quit.." << endl;
   getch();
   return 0;
}//endmn

Answer 1

*如果*您只需要转换简单的 ascii(可能还有 utf-8)文本文件，您可以在翻译模式下循环逐行读取源文件(在这种情况下为您处理足够的换行符)使用非成员 getline() 然后将行输出到输出文件，同时在除最后一行之外的每行之后插入\n 或\r\n。

然后，您可以删除原始文件并将临时文件重命名为原始文件的名称。或者，如果您愿意，您可以将这些行 push_back 到 vector 中。然后，您可以关闭文件的输入句柄，执行 ofstream out("filename", ios_base::trunc) 并将 vector 的元素写入文件，同时用您想要的换行符分隔它们。

这完全取决于您的要求。

以下是一个错误处理最少的示例。但是，我想在这里展示的只是 FOR 循环和逐行阅读，作为一种不同的做事方式。

convert_file.exe "test.txt""linux"

convert_file.exe "test.txt""赢"

#include <iostream>
#include <string>
#include <fstream>
#include <ostream>
#include <cstdlib>
#include <cstdio>
using namespace std;

int main(int argc, char* argv[]) {
    if (argc != 3) {
        cerr << "Usage: this.exe file_to_convert newline_format(\"linux\" or \"win\")" << endl;
        return EXIT_FAILURE;
    }
    string fmt(argv[2]);
    if (fmt != "linux" && fmt != "win") {
        cerr << "Invalid newline format specified" << endl;
        return EXIT_FAILURE;
    }
    ifstream in(argv[1]);
    if (!in) {
        cerr << "Error reading test.txt" << endl;
        return EXIT_FAILURE;
    }
    string tmp(argv[1]);
    tmp += "converted";
    ofstream out(tmp.c_str(), ios_base::binary);
    if (!out) {
        cerr << "Error writing " << tmp << endl;
        return EXIT_FAILURE;
    }
    bool first = true;
    for (string line; getline(in, line); ) {
        if (!first) {
            if (fmt == "linux") {
                out << "\n";
            } else {
                out << "\r\n";
            }
        }
        out << line;
        first = false;
    }
    in.close();
    out.close();
    if (remove(argv[1]) != 0) {
        cerr << "Error deleting " << argv[1] << endl;
        return EXIT_FAILURE;
    }
    if (rename(tmp.c_str(), argv[1]) != 0) {
        cerr << "Error renaming " << tmp << " to " << argv[1] << endl;
        return EXIT_FAILURE;
    }
}

不过正如其他人所说，已经有一些实用程序(包括像 Notepadd++ 这样的文本编辑器)可以为您进行换行符转换。因此，除非出于其他原因(您未指定)这样做，否则您不需要自己实现任何事情。