I\'m interested in advice/pseudocode code/explanation rather than actual implementation.
Here is how this can be done with SAX:
import java.util.HashMap;
import java.util.Map;
import org.xml.sax.Attributes;
import org.xml.sax.SAXException;
import org.xml.sax.XMLReader;
import org.xml.sax.helpers.DefaultHandler;
public class FragmentContentHandler extends DefaultHandler {
private String xPath = "/";
private XMLReader xmlReader;
private FragmentContentHandler parent;
private StringBuilder characters = new StringBuilder();
private Map elementNameCount = new HashMap();
public FragmentContentHandler(XMLReader xmlReader) {
this.xmlReader = xmlReader;
}
private FragmentContentHandler(String xPath, XMLReader xmlReader, FragmentContentHandler parent) {
this(xmlReader);
this.xPath = xPath;
this.parent = parent;
}
@Override
public void startElement(String uri, String localName, String qName, Attributes atts) throws SAXException {
Integer count = elementNameCount.get(qName);
if(null == count) {
count = 1;
} else {
count++;
}
elementNameCount.put(qName, count);
String childXPath = xPath + "/" + qName + "[" + count + "]";
int attsLength = atts.getLength();
for(int x=0; x 0) {
System.out.println(xPath + "='" + characters.toString() + "'");
}
xmlReader.setContentHandler(parent);
}
@Override
public void characters(char[] ch, int start, int length) throws SAXException {
characters.append(ch, start, length);
}
}
It can be tested with:
import java.io.FileInputStream;
import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;
import org.xml.sax.InputSource;
import org.xml.sax.XMLReader;
public class Demo {
public static void main(String[] args) throws Exception {
SAXParserFactory spf = SAXParserFactory.newInstance();
SAXParser sp = spf.newSAXParser();
XMLReader xr = sp.getXMLReader();
xr.setContentHandler(new FragmentContentHandler(xr));
xr.parse(new InputSource(new FileInputStream("input.xml")));
}
}
This will produce the desired output:
//root[1]/elemA[1]='one'
//root[1]/elemA[2][@attribute1='first]
//root[1]/elemA[2][@attribute2='second]
//root[1]/elemA[2]='two'
//root[1]/elemB[1]='three'
//root[1]/elemA[3]='four'
//root[1]/elemC[1]/elemB[1]='five'