source: trunk/gsdl3/src/java/org/greenstone/gsdl3/gs3build/doctypes/METSDocument.java@ 6897

package org.greenstone.gsdl3.gs3build.doctypes;

import java.io.*;

import java.net.URL;

import javax.xml.parsers.*;

import org.w3c.dom.Document;
import org.w3c.dom.Element;
import org.w3c.dom.NamedNodeMap;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;
import org.w3c.dom.Text;

import org.xml.sax.SAXException;
import org.xml.sax.SAXParseException;

import org.greenstone.gsdl3.gs3build.metadata.*;

public class METSDocument extends AbstractDocument
{
  public static final String METS_DOCUMENT_TYPE = "METS";

  public METSDocument(URL url)
  { super(url);
  
    if (url.toString().startsWith("file://"))
    { this._parseFile(new File(url.toString().substring(7)));
    }
  }
  
  private void _parseFile(File file)
  {
    try {
      DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
      DocumentBuilder builder = factory.newDocumentBuilder();
      Document document = builder.parse(file);

      // TODO: get all the types in the tree
      
      // TODO: do a traverse, and thus cope with elements-within-elements if needsbe, but
      // this shouldn't happen except in a directly defined situation - actually doing the
      // parsing in part inside each node would work well provided one checked for a node
      // having already been done...
      System.out.println("Read");
      
      NodeList fileSecs = document.getElementsByTagName("mets:fileSec");
      
      for (int g = 0; g < fileSecs.getLength(); g ++) {
    //              Schema schema = new Schema(schemas.item(s));
    this._parseFileSec(fileSecs.item(g));
      }
      
      // Get document metadata sections
      NodeList dmdSecs = document.getElementsByTagName("mets:dmdSec");
      
      //                Schema schema = new Schema(schemas.item(s));
      this.metadata = METSDescriptiveSet.parseXML(fileSecs);
    }
    catch (FactoryConfigurationError e) {
      System.out.println(e);
    }
    catch (ParserConfigurationException ex) {
      System.out.println(ex);
    }
    catch (SAXException ex) {
      System.out.println(ex);
    }
    catch (IOException ex) {
      System.out.println(ex);
    }
  }

  private void _parseFileSec(Node fileSec)
  { // this is in effect a group without a sense of 'self'...
    this._parseFileGroup((Element) fileSec, null);
  }

  private void _parseFileGroup(Element groupTag, METSFileGroup group)
  { NodeList children = groupTag.getChildNodes();

    for (int c = 0; c < children.getLength(); c ++)
    { if (children.item(c).getNodeType() != org.w3c.dom.Node.ELEMENT_NODE) {
        continue;
      }

      System.out.println(children.item(c));
    
      Element element = (Element) children.item(c);

      if (element.getNodeName().equals("mets:File"))
      { if (group != null)
    { METSFile file = METSFile.parseXML(element, group);
    }
        else
    { // TODO: error
    }
      }
      else if (element.getNodeName().equals("mets:fileGrp"))
      { // recurse
    METSFileGroup childGroup = new METSFileGroup(element.getAttribute("ID"));

    this._parseFileGroup(element, childGroup);
    if (group != null)
    { group.addGroup(childGroup);
    }
    else
    { this.fileSet.addGroup(childGroup);
    }
      }
    }
  }

  public String getDocumentType()
  { return METS_DOCUMENT_TYPE;
  }

  public String getDocumentText()
  { // TODO: make this more than a dummy function!
    return null;
  }

  public String getSectionText(String sectionId)
  { return null;
  }

}