view src/ls-ascii-helper.cc @ 11944:278afaecddd4 release-3-0-x

fix leaving stray '\r' in stream when reading from CRLF data file * * * fix CRLF issues with text-mode reading in windows when loading ascii data
author Benjamin Lindner <lindnerb@users.sourceforge.net>
date Wed, 18 Mar 2009 15:23:14 +0100
parents
children
line wrap: on
line source

/*

Copyright (C) 2003, 2005, 2006, 2007 John W. Eaton

This file is part of Octave.

Octave is free software; you can redistribute it and/or modify it
under the terms of the GNU General Public License as published by the
Free Software Foundation; either version 3 of the License, or (at your
option) any later version.

Octave is distributed in the hope that it will be useful, but WITHOUT
ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
for more details.

You should have received a copy of the GNU General Public License
along with Octave; see the file COPYING.  If not, see
<http://www.gnu.org/licenses/>.

*/


#include "ls-ascii-helper.h"

#include <iostream>
#include <sstream>

// Helper functions when reading from ascii files.
// These function take care of CR/LF issues when files are opened in text-mode for reading 

// Skip characters from stream IS until a newline is reached.
// Depending on KEEP_NEWLINE, either eat newline from stream or
// keep it unread

void
skip_until_newline( std::istream& is, bool keep_newline )
{
  if (!is)
    return;
  
  char c,d;
  
  while (is)
  {
      c = is.peek();
      if (c == '\n' || c == '\r')
      {
	  // reached newline
	  if (keep_newline == false)
	  {
	      // eat the CR or LF character
	      is.get(d);
	      
	      // make sure that for binary-mode opened ascii files containing CRLF line endings
	      // we skip the LF after CR...
	      if (c == '\r' && is.peek()=='\n')
	      {
		  // yes, LF following CR, eat it...
		  is.get(d);
	      }
	  }
	  
	  // Newline was found, and read from stream if keep_newline==true, so exit loop
	  break;
      }
      else
	  // no newline charater peeked, so read it and proceed to next character
	  is.get(d);
  }
  
  return;
}


// If stream IS currently points to a newline (a leftover from a previous read)
// then eat newline(s) until a non-newline character is found

void
skip_preceeding_newline( std::istream& is )
{
  if (!is)
    return;
  
  char c,d;
  
  // Check if IS currently points to newline character
  c = is.peek();
  if (c == '\n' || c == '\r')
  {
      // Yes, at newline
      do {
	  // eat the CR or LF character
	  is.get(d);
	  
	  // make sure that for binary-mode opened ascii files containing CRLF line endings
	  // we skip the LF after CR...
	  if (c == '\r' && is.peek() == '\n')
	  {
	      // yes, LF following CR, eat it...
	      is.get(d);
	  }
	  
	  // Peek into next character
	  c = is.peek();
      // Loop while still a newline ahead
      } while( c == '\n' || c == '\r' );
  }
  
  return;
}


// Read charaters from stream IS until a newline is reached.
// Depending on KEEP_NEWLINE, either eat newline from stream or
// keep it unread
// Characters read are stored and returned as std::string

std::string
read_until_newline( std::istream& is, bool keep_newline )
{
  if (!is)
    return std::string();
  
  char c,d;
  std::ostringstream buf;
  
  while (is)
  {
      c = is.peek();
      if (c == '\n' || c == '\r')
      {
	  // reached newline
	  if (keep_newline == false)
	  {
	      // eat the CR or LF character
	      is.get(d);
	      
	      // make sure that for binary-mode opened ascii files containing CRLF line endings
	      // we skip the LF after CR...
	      if (c == '\r' && is.peek() == '\n')
	      {
		  // yes, LF following CR, eat it...
		  is.get(d);
	      }
	  }
	  
	  // Newline was found, and read from stream if keep_newline==true, so exit loop
	  break;
      }
      else
      {
	  // no newline charater peeked, so read it, store it, and proceed to next
	  is.get(d);
	  buf << d;
      }
  }
  
  return buf.str();
}