All Downloads are FREE. Search and download functionalities are using the official Maven repository.

weka.gui.graphvisualizer.BIFParser Maven / Gradle / Ivy

Go to download

The Waikato Environment for Knowledge Analysis (WEKA), a machine learning workbench. This is the stable version. Apart from bugfixes, this version does not receive any other updates.

There is a newer version: 3.8.6
Show newest version
/*
 *    This program 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 2 of the License, or
 *    (at your option) any later version.
 *
 *    This program 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 this program; if not, write to the Free Software
 *    Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 */

/*
 *    BIFParser.java
 *    Copyright (C) 2003 University of Waikato, Hamilton, New Zealand
 *
 */
package weka.gui.graphvisualizer;

import java.io.InputStream;
import java.io.FileWriter;
import java.io.IOException;
import java.io.StringReader;
import java.util.StringTokenizer;

import weka.core.FastVector;

import org.w3c.dom.Document;
import org.w3c.dom.NodeList;
import org.w3c.dom.Element;


/**
 * This class parses an inputstream or a string in
 * XMLBIF ver. 0.3 format, and builds the datastructures
 * that are passed to it through the constructor.
 *
 * @author Ashraf M. Kibriya ([email protected])
 * @version $Revision: 7059 $ - 24 Apr 2003 - Initial version (Ashraf M. Kibriya)
 */
public class BIFParser implements GraphConstants {
  
  /** These holds the nodes and edges of the graph */
  protected FastVector m_nodes, m_edges;
  /**  This holds the name of the graph (i.e. the name of network tag in XMLBIF
   * input)
   */
  protected String graphName;
  /** This holds the string to be parsed */
  protected String inString;
  /** This holds the InputStream to be parsed */
  protected InputStream inStream;
  
  
  /**
   * Constructor (if our input is a String)
   *
   * @param input the string to be parsed (should not be null)
   * @param nodes vector containing GraphNode objects (should be empty)
   * @param edges vector containing GraphEdge objects (should be empty)
   */
  public BIFParser(String input, FastVector nodes, FastVector edges) {
    m_nodes = nodes; m_edges = edges; inString = input;
  }
  
  
  /**
   * Constructor (if our input is an InputStream)
   *
   * @param instream the InputStream to be parsed (should not be null)
   * @param nodes vector containing GraphNode objects (should be empty)
   * @param edges vector containing GraphEdge objects (should be empty)
   */
  public BIFParser(InputStream instream, FastVector nodes, FastVector edges) {
    m_nodes = nodes; m_edges = edges; inStream = instream;
  }
  
  
  /**
   * This method parses the string or the InputStream that we
   * passed in through the constructor and builds up the
   * m_nodes and m_edges vectors
   * @exception Exception if both the inString and inStream are
   *              null, i.e. no input has been provided
   * @exception BIFFormatException if there is format of the
   *              input is not correct. The format should conform to
   *              XMLBIF version 0.3
   * @exception NumberFormatException if there is an invalid
   *              char in the probability table of a node.
   * @return    returns the name of the graph
   */
  public String parse() throws Exception {
    Document dc=null;
    
    javax.xml.parsers.DocumentBuilderFactory dbf =
    javax.xml.parsers.DocumentBuilderFactory.newInstance();
    dbf.setIgnoringElementContentWhitespace(true);
    javax.xml.parsers.DocumentBuilder db = dbf.newDocumentBuilder();
    
    if(inStream!=null)
      dc = db.parse(inStream);
    else if(inString!=null)
      dc = db.parse(new org.xml.sax.InputSource(new StringReader(inString)));
    else
    { throw new Exception(Messages.getInstance().getString("BIFParser_Parse_Exception_Text")); }
    
    NodeList nl = dc.getElementsByTagName( "NETWORK" );
    
    if(nl.getLength()==0) {
      throw new BIFFormatException( Messages.getInstance().getString("BIFParser_Parse_BIFFormatException_Text_First"));
    }
    
    //take only the first network node
    NodeList templist = ((Element)nl.item(0)).getElementsByTagName( "NAME" );
    graphName = templist.item(0).getFirstChild().getNodeValue();
    //System.out.println("The name of the network is "+
    //templist.item(0).getFirstChild().getNodeValue());
    
    //Get all the variables
    nl = dc.getElementsByTagName("VARIABLE");
    for(int i=0; i1)
        throw new BIFFormatException(Messages.getInstance().getString("BIFParser_Parse_BIFFormatException_Text_Second") + (i+1));
      
      String nodename =
      ((org.w3c.dom.Node)templist.item(0)).getFirstChild().getNodeValue();
      GraphNode n = new GraphNode( nodename, nodename, GraphNode.NORMAL );
      m_nodes.addElement(n);
      //getting nodes position
      templist = ((Element)nl.item(i)).getElementsByTagName("PROPERTY");
      for(int j=0; j1)
        throw new BIFFormatException(Messages.getInstance().getString("BIFParser_Parse_BIFFormatException_Text_Second_Alpha") +
        n.ID);
      
      String probs = templist.item(0).getFirstChild().getNodeValue();
      StringTokenizer tk = new StringTokenizer(probs, " \n\t");
      
      if(parntOutcomes*n.outcomes.length > tk.countTokens())
        throw new BIFFormatException(Messages.getInstance().getString("BIFParser_Parse_BIFFormatException_Text_Third") + n.ID+
        		Messages.getInstance().getString("BIFParser_Parse_BIFFormatException_Text_Fourth"));
      else if(parntOutcomes*n.outcomes.length < tk.countTokens())
        throw new BIFFormatException(Messages.getInstance().getString("BIFParser_Parse_BIFFormatException_Text_Fifth") + n.ID+
        		Messages.getInstance().getString("BIFParser_Parse_BIFFormatException_Text_Sixth"));
      else {
        n.probs = new double[parntOutcomes][n.outcomes.length];
        for(int r=0; r\n");
      text.append("\n");
      text.append("\n");
      text.append("	      \n");
      text.append("	\n");
      text.append("	\n");
      text.append("	\n");
      text.append("	      \n");
      text.append("	\n");
      text.append("	\n");
      text.append("	\n");
      text.append("	\n");
      text.append("	\n");
      text.append("	\n");
      text.append("]>\n");
      text.append("\n");
      text.append("\n");
      text.append("\n");
      text.append("\n");
      text.append("" + XMLNormalize(graphName)  + "\n");
      
      //Writing all the node names and their outcomes
      //If outcome is null(ie if the graph was loaded from DOT file) then
      //simply write TRUE
      for(int nodeidx=0; nodeidx\n");
        text.append("\t" + XMLNormalize(n.ID) + "\n");
        
        if(n.outcomes!=null)
          for(int outidx=0; outidx" + XMLNormalize(n.outcomes[outidx])+
            "\n");
        else
          text.append("\ttrue\n");
        
        text.append("\tposition = ("+n.x+","+n.y+")\n");
        text.append("\n");
      }
      
      //Writing all the nodes definitions and their probability tables
      //If probability table is null then simply write 1 for all
      //the posible outcomes of the parents
      for (int nodeidx=0; nodeidx\n");
        text.append("" + XMLNormalize(n.ID) + "\n");
        int parntOutcomes = 1;
        if(n.prnts!=null)
          for(int pidx=0; pidx" + XMLNormalize(prnt.ID) + "\n");
            if(prnt.outcomes!=null)
              parntOutcomes *= prnt.outcomes.length;
          }
        
        text.append("\n");
        for(int i=0; i\n");
        text.append("\n");
      }
      
      text.append("\n");
      text.append("\n");
      
      outfile.write(text.toString());
      outfile.close();
    }
    catch(IOException ex) { ex.printStackTrace(); }
  } // writeXMLBIF
  
  /** XMLNormalize converts the five standard XML entities in a string
   * g.e. the string V&D's is returned as V&D's
   * @author Remco Bouckaert ([email protected])
   * @param sStr string to normalize
   * @return normalized string
   */
  private static String XMLNormalize(String sStr) {
    StringBuffer sStr2 = new StringBuffer();
    for (int iStr = 0; iStr < sStr.length(); iStr++) {
      char c = sStr.charAt(iStr);
      switch (c) {
        case '&': sStr2.append("&"); break;
        case '\'': sStr2.append("'"); break;
        case '\"': sStr2.append("""); break;
        case '<': sStr2.append("<"); break;
        case '>': sStr2.append(">"); break;
        default:
          sStr2.append(c);
      }
    }
    return sStr2.toString();
  } // XMLNormalize
  
  
} // BIFParser