Develop Reference

File Not Found Exception while parsing large XML File in Java

I'm using SAX (Simple API for XML) to parse an XML document. The document is a huge XML file (dblp.xml - 1.46 GB), i wrote a few lines of parser and tested it on small files and it works.
Sample.XML and Student.XML are small files having few lines of XML, my parser parses them but when i change the path to dblp.XML it generates the file not found exception (file is still there with other sample files, but its huge in size)
here is the Exception i get:
java.io.FileNotFoundException: E:\Workspaces\Java\SaxParser\xml\dblp.dtd (The system cannot find the file specified)
here is my code:
package com.teamincredibles.sax;
import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;
import org.xml.sax.Attributes;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.DefaultHandler;
public class Parser extends DefaultHandler {
public void getXml() {
try {
SAXParserFactory saxParserFactory = SAXParserFactory.newInstance();
SAXParser saxParser = saxParserFactory.newSAXParser();
final MySet openingTagList = new MySet();
final MySet closingTagList = new MySet();
DefaultHandler defaultHandler = new DefaultHandler() {
public void startDocument() throws SAXException {
System.out.println("Starting Parsing...\n");
}
public void endDocument() throws SAXException {
System.out.print("\n\nDone Parsing!");
}
public void startElement(String uri, String localName, String qName,
Attributes attributes) throws SAXException {
if (!openingTagList.contains(qName)) {
openingTagList.add(qName);
System.out.print("<" + qName + ">\n");
}
}
public void characters(char ch[], int start, int length)
throws SAXException {
/*for(int i=start; i<(start+length);i++){
System.out.print(ch[i]);
}*/
}
public void endElement(String uri, String localName, String qName)
throws SAXException {
if (!closingTagList.contains(qName)) {
closingTagList.add(qName);
System.out.print("</" + qName + ">");
}
}
};
saxParser.parse("xml/dblp.xml", defaultHandler);
} catch (Exception e) {
e.printStackTrace();
}
}
public static void main(String args[]) {
Parser readXml = new Parser();
readXml.getXml();
}
}
What is the matter i can't figure out.

Is your XML file referencing a DTD, in this case "dblp.dtd".
If yes check if its in the location "E:\Workspaces\Java\SaxParser\xml\". If not place it in the location and run your code.

how to extract element from cxf soap message

I have below soap message.I want to extract Id and chargeBoxIdentity element.
ID: 2
Address: http://localhost:8080/ocppserver/services/CentralSystemService
Encoding: UTF-8
Http-Method: POST
Content-Type: application/soap+xml;charset=UTF-8;action="/Authorize"
Headers: {accept-encoding=[gzip,deflate], connection=[Keep-Alive], Content-Length= [852], content-type=[application/soap+xml;charset=UTF-8;action="/Authorize"], host=[localhost:8080], user-agent=[Apache-HttpClient/4.1.1 (java 1.5)]}
Payload: <s:Envelope xmlns:s="http://www.w3.org/2003/05/soap-envelope" xmlns:a="http://www.w3.org/2005/08/addressing">
<s:Header>
<h:chargeBoxIdentity xmlns:h="urn://Ocpp/Cs/2012/06/" xmlns="urn://Ocpp/Cs/2012/06/">REE001</h:chargeBoxIdentity>
<a:From>
<a:Address>http://127.0.0.1:8081/ChargeBox/Ocpp</a:Address>
</a:From>
<a:MessageID>urn:uuid:2ae9d933-4f92-4628-84fe-35024a858450</a:MessageID>
<a:ReplyTo>
<a:Address>http://www.w3.org/2005/08/addressing/anonymous</a:Address>
</a:ReplyTo>
<a:Action>/Authorize</a:Action></s:Header>
<s:Body xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema">
<authorizeRequest xmlns="urn://Ocpp/Cs/2012/06/">
<idTag>EF1234</idTag>
</authorizeRequest>
</s:Body>
</s:Envelope>
I wrote below interceptor .Below interceptor print the Header and payload field.How to extract the Id ? How to extract chargeboxIdentity from the payload ? I am using the log4j framework.
import java.io.InputStream;
import java.util.List;
import java.util.Map;
import java.util.Map.Entry;
import java.util.Set;
import org.apache.cxf.binding.soap.SoapMessage;
import org.apache.cxf.binding.soap.interceptor.AbstractSoapInterceptor;
import org.apache.cxf.helpers.CastUtils;
import org.apache.cxf.helpers.IOUtils;
import org.apache.cxf.interceptor.Fault;
import org.apache.cxf.io.CachedOutputStream;
import org.apache.cxf.message.Message;
import org.apache.cxf.phase.Phase;
public class InBoundMessage extends AbstractSoapInterceptor {
public InBoundMessage() {
super(Phase.RECEIVE);
}
public void handleMessage(SoapMessage message) throws Fault {
Map<String, List<String>> headers = CastUtils.cast((Map)message.get(Message.PROTOCOL_HEADERS));
if (headers != null) {
Set<Entry<String,List<String>>> hashSet=headers.entrySet();
for(Entry<String,List<String>> entry:hashSet ) {
System.out.println("Key="+entry.getKey()+", Value="+entry.getValue());
}
}
System.out.println("Message id = "+message.getId());
try{
InputStream is = message.getContent ( InputStream.class );
CachedOutputStream os = new CachedOutputStream ( );
IOUtils.copy ( is, os );
os.flush();
message.setContent ( InputStream.class, os.getInputStream ( ) );
is.close();
String payload=IOUtils.toString ( os.getInputStream ( ) );
System.out.println ("The request is: " + payload);
}catch(Exception e){
e.printStackTrace();
}
}
}

I parsed the soap message by using SAX parser.
import java.io.StringReader;
import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;
import org.xml.sax.Attributes;
import org.xml.sax.InputSource;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.DefaultHandler;
public class ParseInBoundSoapMessage {
private static InBoundSoapMessage inBoundSoapMessage=null;
public static InBoundSoapMessage getInBoundSoapMessage(String xml) {
try {
inBoundSoapMessage=new InBoundSoapMessage();
SAXParserFactory factory = SAXParserFactory.newInstance();
factory.setNamespaceAware(true);
SAXParser saxParser = factory.newSAXParser();
DefaultHandler handler = new DefaultHandler() {
boolean ischargeBoxIdentityPresent = false;
boolean isAddressPresent = false;
boolean isFromPresent=false;
boolean isActionPresent=false;
boolean isMessageID=false;
boolean isRelatesTo=false;
public void startElement(String uri, String localName, String qName, Attributes attributes) throws SAXException {
if (localName.equals("chargeBoxIdentity")) {
ischargeBoxIdentityPresent = true;
}
if (localName.equals("From")) {
isFromPresent = true;
}
if (localName.equals("Address")) {
isAddressPresent = true;
}
if(localName.equals("Action")){
isActionPresent=true;
}
if(localName.equals("MessageID")){
isMessageID=true;
}
if(localName.equals("RelatesTo")){
isRelatesTo=true;
}
}
public void characters(char ch[], int start, int length) throws SAXException {
if (ischargeBoxIdentityPresent) {
inBoundSoapMessage.setChargeBoxIdentity(new String(ch, start, length));
ischargeBoxIdentityPresent = false;
}
if(isAddressPresent && isFromPresent){
inBoundSoapMessage.setAddressInFrom(new String(ch, start, length));
isAddressPresent = false;
isFromPresent=false;
}
if(isActionPresent){
inBoundSoapMessage.setAction(new String(ch, start, length));
isActionPresent=false;
}
if(isMessageID){
inBoundSoapMessage.setMessageId(new String(ch, start, length));
isMessageID=false;
}
if(isRelatesTo){
inBoundSoapMessage.setRelatesTo(new String(ch, start, length));
isRelatesTo=false;
}
}
};
saxParser.parse(new InputSource(new StringReader(xml)), handler);
} catch (Exception e) {
e.printStackTrace();
}
return inBoundSoapMessage;
}
}

SAXParser Android, ArrayList repeating elements

I am currently just trying to process the elements within the item nodes. I am just focusing on the title at this point for simplicity, but I am finding that when it parses, I am just getting the same element three times.
http://open.live.bbc.co.uk/weather/feeds/en/2643123/3dayforecast.rss
import java.io.InputStream;
import java.net.URL;
import java.util.ArrayList;
import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;
import org.xml.sax.Attributes;
import org.xml.sax.InputSource;
import org.xml.sax.SAXException;
import org.xml.sax.XMLReader;
import org.xml.sax.helpers.DefaultHandler;
import android.util.Log;
public class XMLHelper extends DefaultHandler {
private String URL_Main="http://open.live.bbc.co.uk/weather/feeds/en/2643123/3dayforecast.rss";
String TAG = "XMLHelper";
Boolean currTag = false;
String currTagVal = "";
public ItemData item = null;
public ArrayList<ItemData> items = new ArrayList<ItemData>();
public void get() {
try {
SAXParserFactory factory = SAXParserFactory.newInstance();
SAXParser parser = factory.newSAXParser();
XMLReader reader = parser.getXMLReader();
reader.setContentHandler(this);
InputStream inputStream = new URL(URL_Main).openStream();
reader.parse(new InputSource(inputStream));
} catch (Exception e) {
Log.e(TAG, "Exception: " + e.getMessage());
}
}
// Receives notification of the start of an element
public void startElement(String uri, String localName, String qName,
Attributes attributes) throws SAXException {
Log.i(TAG, "TAG: " + localName);
currTag = true;
currTagVal = "";
if (localName.equals("channel")) {
item = new ItemData();
}
}
// Receives notification of end of element
public void endElement(String uri, String localName, String qName)
throws SAXException {
currTag = false;
if (localName.equalsIgnoreCase("title"))
item.setTitle(currTagVal);
else if (localName.equalsIgnoreCase("item"))
items.add(item);
}
// Receives notification of character data inside an element
public void characters(char[] ch, int start, int length)
throws SAXException {
if (currTag) {
currTagVal = currTagVal + new String(ch, start, length);
currTag = false;
}
}
}

The reason you are getting the same value thrice is because you are creating the object when there is a channel tag in startElement method.
if (localName.equals("channel")) {
item = new ItemData();
}
I guess you should initiate the object whenever there is a item tag as below
if (localName.equals("item")) { // check for item tag
item = new ItemData();
}

Remodify your whole project, you need 3 classes :
1.ItemList
2.XMLHandler extends Default handler
3.SAXParsing activity
Make your code organized first
In your XMLHandler class extend default handler your code should look like
public class MyXMLHandler extends DefaultHandler
{
public static ItemList itemList;
public boolean current = false;
public String currentValue = null;
#Override
public void startElement(String uri, String localName, String qName,
Attributes attributes) throws SAXException {
// TODO Auto-generated method stub
current = true;
if (localName.equals("channel"))
{
/** Start */
itemList = new ItemList();
}
}
#Override
public void endElement(String uri, String localName, String qName)
throws SAXException {
// TODO Auto-generated method stub
current = false;
if(localName.equals("item"))
{
itemList.setItem(currentValue);
}
else if(localName.equals("title"))
{
itemList.setManufacturer(currentValue);
}
}
#Override
public void characters(char[] ch, int start, int length)
throws SAXException {
// TODO Auto-generated method stub
if(current)
{
currentValue = new String(ch, start, length);
current=false;
}
}
}
ItemList class is used to set , setter and getter methods to pass in values of arraylist and retrieve those array lists in the SAXParsing activity.
I hope this solution helps. :D

Why is my variable is null?

I do this
package file;
import java.io.IOException;
import org.apache.log4j.Logger;
import org.xml.sax.Attributes;
import org.xml.sax.ContentHandler;
import org.xml.sax.Locator;
import org.xml.sax.SAXException;
import org.xml.sax.XMLReader;
import org.xml.sax.helpers.LocatorImpl;
import org.xml.sax.helpers.XMLReaderFactory;
public class GetNatureSax implements ContentHandler {
private final static Logger _logger = Logger.getLogger(GetNatureSax.class.getName());
private boolean isCurrentElement = false;
private Locator locator;
private String _parameterValue = null;
public GetNatureSax() {
super();
locator = new LocatorImpl();
}
public String getValeurParametre() {
return _parameterValue;
}
public void setDocumentLocator(Locator value) {
locator = value;
}
public void startDocument() throws SAXException {}
public void endDocument() throws SAXException {}
public void startPrefixMapping(String prefix, String URI) throws SAXException {
}
public void endPrefixMapping(String prefix) throws SAXException {}
public void startElement(String nameSpaceURI, String localName, String rawName, Attributes attributs)
throws SAXException {
if (localName.equals("Nature")) {
isCurrentElement = true;
}
}
public void endElement(String nameSpaceURI, String localName, String rawName) throws SAXException {
if (localName.equals("Nature")) {
isCurrentElement = false;
}
}
public void characters(char[] ch, int start, int end) throws SAXException {
if (isCurrentElement) {
_parameterValue = new String(ch, start, end);
}
}
public void ignorableWhitespace(char[] ch, int start, int end) throws SAXException {
System.out.println("espaces inutiles rencontres : ..." + new String(ch, start, end) + "...");
}
public void processingInstruction(String target, String data) throws SAXException {
System.out.println("Instruction de fonctionnement : " + target);
System.out.println(" dont les arguments sont : " + data);
}
public void skippedEntity(String arg0) throws SAXException {}
public void parseFichier(String i_fichierATraiter) {
XMLReader saxReader;
try {
saxReader = XMLReaderFactory.createXMLReader("org.apache.xerces.parsers.SAXParser");
saxReader.setContentHandler(new GetNatureSax());
saxReader.parse(i_fichierATraiter);
System.out.println(_parameterValue);
} catch (SAXException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
}
My XML:
...
<Reference>
<Nature>ACHAT</Nature>
<Statut>2</Statut>
<Type-Gest>RE</Type-Gest>
<Gest>RE_ELECTRA</Gest>
<Type-Res>D</Type-Res>
<Nb-h>24</Nb-h>
</Reference>
...
why when it execute this line
System.out.println(_parameterValue);
my variable is null and before when i debug my variable is not null

Because you instantiate a new GetNatureSax and give it to the SaxReader has a Content Handler.
So when the parsing has ended, it is the new GetNatureSax instance that have been modified and which have the field _parameterValue set, not the current instance (this).
Just modify your parseFichier method like this:
saxReader = XMLReaderFactory.createXMLReader("org.apache.xerces.parsers.SAXParser");
saxReader.setContentHandler(this); // here
saxReader.parse(i_fichierATraiter);
System.out.println("Found: " + getValeurParametre());

Using my debugger I can see you are using two GetNatureSax
saxReader.setContentHandler(new GetNatureSax());
This creates a second GetNatureSax object where is where the value is being set.
Changing it to
saxReader.setContentHandler(this);
fixed the problem.

Java Sax XML Parser, parsing custom "values" within XML tags?

I haven't worked much with XML before so maybe my ignorance on proper terminology is hurting me in my searches on how to do this. I have the code snippet below which I am using to parse an XML file like the one below. The problem is that it only picks up XML values within <Tag>Value</Tag> but not for the one below where I need to get the value of TagValue, which in this case would be "Russell Diamond".
I would appreciate if anyone can offer assistance as to how to get custom values like this. Thanks.
<Tag TagName="#Subject" TagDataType="Text" TagValue="Russell Diamond"/>
The snippet I am using:
public void printElementNames(String fileName) throws IOException {
//test write to file
FileWriter fstream = new FileWriter("/home/user/Desktop/readEDRMtest.txt");
final BufferedWriter out = new BufferedWriter(fstream);
//
try {
SAXParserFactory parserFact = SAXParserFactory.newInstance();
SAXParser parser = parserFact.newSAXParser();
System.out.println("XML Elements: ");
DefaultHandler handler = new DefaultHandler() {
public void startElement(String uri, String lName, String ele,
Attributes attributes) throws SAXException {
// print elements of xml
System.out.println(ele);
try {
out.write(ele);
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
public void characters(char ch[], int start, int length)
throws SAXException {
System.out.println("Value : "
+ new String(ch, start, length));
try {
out.write("Value : "
+ new String(ch, start, length));
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
};

You want to look into extracting attributes. Search on that and you'll find your answer.
The DefaultHandler class's startElement(...) method passes a parameter called attributes that refers to an Attribute object. The API for the Attribute interface will describe how to extract the information you need from this object.
For example:
out.write(attributes.getValue("TagValue"));

This is a stripped down and working version of your code snippet:
import java.io.File;
import java.io.IOException;
import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;
import org.xml.sax.Attributes;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.DefaultHandler;
public class SAX
{
public static void main(String[] args) throws IOException {
new SAX().printElementNames("Delete.xml");
}
public void printElementNames(String fileName) throws IOException
{
try {
SAXParserFactory parserFact = SAXParserFactory.newInstance();
SAXParser parser = parserFact.newSAXParser();
DefaultHandler handler = new DefaultHandler()
{
public void startElement(String uri, String lName, String ele, Attributes attributes) throws SAXException {
System.out.println(ele);
System.out.println(attributes.getValue("TagValue"));
}
public void characters(char ch[], int start, int length) throws SAXException {
System.out.println("Value : " + new String(ch, start, length));
}
};
parser.parse(new File(fileName), handler);
}catch(Exception e){
e.printStackTrace();
}
}
}
Content of Delete.xml
<Tag TagName="#Subject" TagDataType="Text" TagValue="Russell Diamond"/>
Further reading:
http://www.java-samples.com/showtutorial.php?tutorialid=152