format.h

/**************************************************************************
 * Copyright (c) 2002-2011 T. M. Murali                                   *
 *                                                                        *
 * This file is part of Biorithm.                                         *
 *                                                                        *
 * Biorithm 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.                                    *
 *                                                                        *
 * Biorithm 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 Biorithm.  If not, see <http://www.gnu.org/licenses/>.      *
 *                                                                        *
 **************************************************************************/

#ifndef _FORMAT_H
#define _FORMAT_H

#include <set>
#include <vector>

#include "global.h"

// the file format of an affy-like file. mainly describes the content of each row.
struct MyAffyFileFormat
{
  // the character (should be a regex) that separates items in a line.
  char delimiter;
  // does the file have "CALL" information?
  bool hasCallInfo;
  // the number of names for a gene in each line of the file. e.g., if
  // there is an id and a name, this field = 2.
  int numGeneNames;
  // i have to let geneIdColumn and the like to be -1 by default so
  // that i can initliase them to some default values.
  int geneIdColumn;
  int geneNameColumn;
  string geneIdColumnName;
  string geneNameColumnName;
  
  // since i am generalising this code to non-gene expression data
  // (for example, to compute itemsets), i need to just read row names
  // without assuming they are gene names.
  int rowNameColumn;
  string rowNameColumnName;
  
  string callColumnName;
  vector< int > valueColumns;
  
  // columns and rows to ignore. these are the same type in MyClusterParams.
  map< string, bool > ignoredColumns;
  // i need to store indices corresponding to ignored columns so that
  // i dont have to look up the name of the column and check if i
  // should ignore it.
  set< unsigned int > ignoredColumnIndices;
  map< string, bool > ignoredRows;


  void print(ostream& ostr) const;

  // i need a constructor. otherwise, badly initialised values screw
  // things up.
  MyAffyFileFormat()
    : delimiter('\t'), hasCallInfo(false), numGeneNames(-1), 
      // changing default to 0 for geneIdColumn and 1 for geneNameColumn
      geneIdColumn(0), geneNameColumn(1), geneIdColumnName(""),
         geneNameColumnName(""), rowNameColumn(-1), rowNameColumnName(""),
         callColumnName(""), valueColumns(), 
         ignoredColumns(), ignoredColumnIndices(), ignoredRows()
  {}

};


// print the various fields of MyAffyFileFormat.
inline void MyAffyFileFormat::print(ostream& ostr) const
{
  ostr << "File format variables:\n";
  ostr << "\tdelimiter = \"" << delimiter << "\"\n";
  if ("" != geneIdColumnName)
    {
      ostr << "\tgene id column = " << geneIdColumn << endl;
      ostr << "\tname of gene id column = " << geneIdColumnName << endl;
    }
  if ("" != geneNameColumnName)
    {
      ostr << "\tgene name column = " << geneNameColumn << endl;
      ostr << "\tname of gene name column = " << geneNameColumnName << endl;
    }
  if ("" != rowNameColumnName)
    {
      ostr << "\trow name column = " << rowNameColumn << endl;
      ostr << "\tname of row name column = " << rowNameColumnName << endl;
    }
  

  ostr << "\thas call info = " << hasCallInfo << endl;
  ostr << "\tname of call column = " << callColumnName << endl;
//  ostr << "\tcolumns with expression values are " << valueColumns << endl;
}




#endif // _FORMAT_H