import java.io.File;
import java.io.IOException;
import java.util.List;
import org.jdom.Document;
import org.jdom.Element;
import org.jdom.JDOMException;
import org.jdom.input.SAXBuilder;
public class ReadXMLFile {
public static void main(String[] args) {
SAXBuilder builder = new SAXBuilder();
File xmlFile = new File("c:\\test.xml");
try {
Document document = (Document) builder.build(xmlFile);
Element rootNode = document.getRootElement();
List list = rootNode.getChildren("raum");
for (int i = 0; i < list.size(); i++) {
Element node = (Element) list.get(i);
System.out.println("ID : " + node.getChildText("ID"));
}
} catch (IOException io) {
System.out.println(io.getMessage());
} catch (JDOMException jdomex) {
System.out.println(jdomex.getMessage());
}
}
}
I don't understand how the step in between has to look like in order to insert the imported coordinates into the polygon.. Maybe someone can help me with this?
You can follow any sample JDOM parser example and do it.
For example, this explains how to read the xml and take the data in a list and iterate over it. Just follow the steps and understand what you are doing, you can easily get it done.
For the sake of completeness?
This is how to achieve it using SAX parser.
Note that it is not clear to me, from your question, which Polygon you are referring to. I presume it is a java class. It can't be java.awt.Polygon because its points are all int whereas your sample XML file contains only double values. The only other class I thought of was javafx.scene.shape.Polygon that contains an array of points where each point is a double. Hence in the below code, I create an instance of javafx.scene.shape.Polygon.
For the situation you describe in your question, I don't see the point (no pun intended) in loading the entire DOM tree into memory. You simply need to create a point every time you encounter a x and a y coordinate in the XML file and add those coordinates to a collection of points.
Here is the code. Note that I created an XML file named polygon0.xml that contains the entire XML from your question. Also note that you can extend class org.xml.sax.helpers.DefaultHandler rather than implement interface ContentHandler.
import java.io.FileReader;
import java.io.IOException;
import java.nio.file.Path;
import java.nio.file.Paths;
import javax.xml.parsers.ParserConfigurationException;
import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;
import org.xml.sax.Attributes;
import org.xml.sax.ContentHandler;
import org.xml.sax.InputSource;
import org.xml.sax.Locator;
import org.xml.sax.SAXException;
import org.xml.sax.XMLReader;
import javafx.scene.shape.Polygon;
public class Polygons implements ContentHandler {
private boolean isX;
private boolean isY;
private Polygon polygon;
/* Start 'ContentHandler' interface methods. */
#Override // org.xml.sax.ContentHandler
public void setDocumentLocator(Locator locator) {
// Do nothing.
}
#Override // org.xml.sax.ContentHandler
public void startDocument() throws SAXException {
polygon = new Polygon();
}
#Override // org.xml.sax.ContentHandler
public void endDocument() throws SAXException {
// Do nothing.
}
#Override // org.xml.sax.ContentHandler
public void startPrefixMapping(String prefix, String uri) throws SAXException {
// Do nothing.
}
#Override // org.xml.sax.ContentHandler
public void endPrefixMapping(String prefix) throws SAXException {
// Do nothing.
}
#Override // org.xml.sax.ContentHandler
public void startElement(String uri, String localName, String qName, Attributes atts) throws SAXException {
isX = "x".equals(qName);
isY = "y".equals(qName);
}
#Override // org.xml.sax.ContentHandler
public void endElement(String uri, String localName, String qName) throws SAXException {
if (isX) {
isX = false;
}
if (isY) {
isY = false;
}
}
#Override // org.xml.sax.ContentHandler
public void characters(char[] ch, int start, int length) throws SAXException {
if (isX || isY) {
StringBuilder sb = new StringBuilder(length);
int end = start + length;
for (int i = start; i < end; i++) {
sb.append(ch[i]);
}
polygon.getPoints().add(Double.parseDouble(sb.toString()));
}
}
#Override // org.xml.sax.ContentHandler
public void ignorableWhitespace(char[] ch, int start, int length) throws SAXException {
// Do nothing.
}
#Override // org.xml.sax.ContentHandler
public void processingInstruction(String target, String data) throws SAXException {
// Do nothing.
}
#Override // org.xml.sax.ContentHandler
public void skippedEntity(String name) throws SAXException {
// Do nothing.
}
/* End 'ContentHandler' interface methods. */
public static void main(String[] args) {
Polygons instance = new Polygons();
Path path = Paths.get("polygon0.xml");
SAXParserFactory spf = SAXParserFactory.newInstance();
try (FileReader reader = new FileReader(path.toFile())) { // throws java.io.IOException
SAXParser saxParser = spf.newSAXParser(); // throws javax.xml.parsers.ParserConfigurationException , org.xml.sax.SAXException
XMLReader xmlReader = saxParser.getXMLReader(); // throws org.xml.sax.SAXException
xmlReader.setContentHandler(instance);
InputSource input = new InputSource(reader);
xmlReader.parse(input);
System.out.println(instance.polygon);
}
catch (IOException |
ParserConfigurationException |
SAXException x) {
x.printStackTrace();
}
}
}
Here is the output from running the above code:
Polygon[points=[400.3, 997.2, 400.3, 833.1, 509.9, 833.1, 509.9, 700.0, 242.2, 700.0, 242.2, 600.1, 111.1, 600.1, 111.1, 300.0, 300.0, 300.0, 300.0, 420.0, 600.5, 420.0, 600.5, 101.9, 717.8, 101.9, 717.8, 200.0, 876.5, 200.0, 876.5, 500.8, 1012.1, 500.8, 1012.1, 900.2, 902.0, 900.2, 902.0, 997.2], fill=0x000000ff]
EDIT
As requested, by OP, here is an implementation using JDOM (version 2.0.6)
import java.io.IOException;
import java.nio.file.Path;
import java.nio.file.Paths;
import org.jdom2.Document;
import org.jdom2.Element;
import org.jdom2.JDOMException;
import org.jdom2.filter.ElementFilter;
import org.jdom2.input.SAXBuilder;
import org.jdom2.util.IteratorIterable;
import javafx.scene.shape.Polygon;
public class Polygon2 {
public static void main(String[] args) {
Polygon polygon = new Polygon();
Path path = Paths.get("polygon0.xml");
SAXBuilder builder = new SAXBuilder();
try {
Document jdomDoc = builder.build(path.toFile()); // throws java.io.IOException , org.jdom2.JDOMException
Element root = jdomDoc.getRootElement();
IteratorIterable<Element> iter = root.getDescendants(new ElementFilter("edge"));
while (iter.hasNext()) {
Element elem = iter.next();
Element childX = elem.getChild("x");
polygon.getPoints().add(Double.parseDouble(childX.getText()));
Element childY = elem.getChild("y");
polygon.getPoints().add(Double.parseDouble(childY.getText()));
}
}
catch (IOException | JDOMException x) {
x.printStackTrace();
}
System.out.println(polygon);
}
}
You can read XML files DOM parser library check this article.
I assume you are working on a Desktop application so you might want to use FileChooser for file selection. Here is an example of this.
Also, I think you would need to make some structural changes (for convinience) to your XML file so that it would have something like this:
<xpoints>
<x>5<x/>
...
</xpoints>
<ypoints>
<y>5<y/>
...
</ypoints>
But for existing structure doing something like this would be enogh:
File file = new File("file");
DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
DocumentBuilder db = dbf.newDocumentBuilder();
Document doc = db.parse(file);
doc.getDocumentElement().normalize();
NodeList nodeList = doc.getElementsByTagName("edge");
// you can iterate over all edges
for (int itr = 0; itr < nodeList.getLength(); itr++)
{
Node node = nodeList.item(itr);
if (node.getNodeType() == Node.ELEMENT_NODE)
{
Element eElement = (Element) node;
//then you can access values, for example, to pass them to an array
array.add(eElement.getElementsByTagName("x").item(0).getTextContent()));
}
}
Related
I'm reading XML file using SAX parser utility.
Here is my sample XML
<?xml version="1.0"?><company><Account AccountNumber="100"><staff><firstname>yong</firstname><firstname>jin</firstname></staff></Account></company>
Here is the code
import java.util.Arrays;
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;
public class ReadXML {
public static void main(String argv[]) {
try {
SAXParserFactory factory = SAXParserFactory.newInstance();
SAXParser saxParser = factory.newSAXParser();
DefaultHandler handler = new DefaultHandler() {
boolean bAccount = false;
public void startElement(String uri, String localName, String qName, Attributes attributes)
throws SAXException {
System.out.println("Start Element :" + qName);
if (qName.equalsIgnoreCase("ACCOUNT")) {
bAccount = true;
}
}
public void endElement(String uri, String localName, String qName) throws SAXException {
System.out.println("End Element :" + qName);
}
public void characters(char[] ch, int start, int length) throws SAXException {
System.out.println("Im here:" + bAccount);
if (bAccount) {
System.out.println("Account First Name : " + new String(ch, start, length));
bAccount = false;
StringBuilder Account = new StringBuilder();
for (int i = start; i < ch.length - 1; i--) {
if (String.valueOf(ch[i]).equals("<")) {
System.out.println("Account:" +Account);
break;
} else {
Account.append(ch[i]);
}
}
}
}
};
saxParser.parse("C:\\Lenny\\Work\\XML\\Out_SaxParsing_01.xml", handler);
} catch (Exception e) {
e.printStackTrace();
}
}
}
As you can see in XML, Account tag is something like this Account AccountNumber="100", What I want to do is, I want to capture Tag too as well.
So to achieve that, in characters method, I'm trying to read the array from right to left, So that I could get the Account AccountNumber="100", when Account encountered as event.
But am not able to reach there, The event is getting generated, but its not going to characters method. I think it should go into characters method once Account tag is encountered. But its not..!
May I know please what am missing or doing wrong ?
Any Help please..!
AccountNumber="100" is an attribute of the Account element so inside the startElement handler you have you can read out the attributes parameter to access that value.
In this program I am Reading .xlsx file. And adding cell data to vector, if vector size is less-than 12 no need to read remaining data, and i need to go main method.
How can I do in my program ?
This is my Code :
package com.read;
import java.text.SimpleDateFormat;
import java.util.Calendar;
import java.util.Vector;
import org.apache.poi.openxml4j.opc.OPCPackage;
import java.io.InputStream;
import org.apache.poi.xssf.eventusermodel.XSSFReader;
import org.apache.poi.xssf.model.SharedStringsTable;
import org.apache.poi.xssf.usermodel.XSSFRichTextString;
import org.xml.sax.Attributes;
import org.xml.sax.ContentHandler;
import org.xml.sax.InputSource;
import org.xml.sax.SAXException;
import org.xml.sax.XMLReader;
import org.xml.sax.helpers.DefaultHandler;
import org.xml.sax.helpers.XMLReaderFactory;
public class SendDataToDb {
public static void main(String[] args) {
SendDataToDb sd = new SendDataToDb();
try {
sd.processOneSheet("C:/Users/User/Desktop/New folder/Untitled 2.xlsx");
System.out.println("in Main method");
} catch (Exception e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
public void processOneSheet(String filename) throws Exception {
System.out.println("executing Process Method");
OPCPackage pkg = OPCPackage.open(filename);
XSSFReader r = new XSSFReader( pkg );
SharedStringsTable sst = r.getSharedStringsTable();
System.out.println("count "+sst.getCount());
XMLReader parser = fetchSheetParser(sst);
// To look up the Sheet Name / Sheet Order / rID,
// you need to process the core Workbook stream.
// Normally it's of the form rId# or rSheet#
InputStream sheet2 = r.getSheet("rId2");
System.out.println("Sheet2");
InputSource sheetSource = new InputSource(sheet2);
parser.parse(sheetSource);
sheet2.close();
}
public XMLReader fetchSheetParser(SharedStringsTable sst) throws SAXException {
//System.out.println("EXECUTING fetchSheetParser METHOD");
XMLReader parser = XMLReaderFactory.createXMLReader("org.apache.xerces.parsers.SAXParser");
ContentHandler handler = new SheetHandler(sst);
parser.setContentHandler(handler);
System.out.println("Method :fetchSheetParser");
return parser;
}
/**
* See org.xml.sax.helpers.DefaultHandler javadocs
*/
private class SheetHandler extends DefaultHandler {
private SharedStringsTable sst;
private String lastContents;
private boolean nextIsString;
Vector values = new Vector(20);
private SheetHandler(SharedStringsTable sst) {
this.sst = sst;
}
public void startElement(String uri, String localName, String name,
Attributes attributes) throws SAXException {
// c => cell
//long l = Long.valueOf(attributes.getValue("r"));
if(name.equals("c")){
columnNum++;
}
if(name.equals("c")) {
// Print the cell reference
// Figure out if the value is an index in the SST
String cellType = attributes.getValue("t");
if(cellType != null && cellType.equals("s")) {
nextIsString = true;
} else {
nextIsString = false;
}
}
// Clear contents cache
lastContents = "";
}
public void endElement(String uri, String localName, String name)
throws SAXException {
//System.out.println("Method :222222222");
// Process the last contents as required.
// Do now, as characters() may be called more than once
if(nextIsString) {
int idx = Integer.parseInt(lastContents);
lastContents = new XSSFRichTextString(sst.getEntryAt(idx)).toString();
nextIsString = false;
}
// v => contents of a cell
// Output after we've seen the string contents
if(name.equals("v")) {
values.add(lastContents);
}
if(name.equals("row")) {
System.out.println(values);
//values.setSize(50);
System.out.println(values.size()+" "+values.capacity());
//********************************************************
//I AM CHECKING CONDITION HERE, IF CONDITION IS TRUE I NEED STOP THE REMAINING PROCESS AND GO TO MAIN METHOD.
if(values.size() < 12)
values.removeAllElements();
//WHAT CODE I NEED TO WRITE HERE TO STOP THE EXECUTION OF REMAINING PROCESS AND GO TO MAIN
//***************************************************************
}
}
public void characters(char[] ch, int start, int length)
throws SAXException {
//System.out.println("method : 333333333333");
lastContents += new String(ch, start, length);
}
}
}
check the code in between lines of //******************************
and
//******************************************
You can throw a SAXException wherever you want the parsing to stop:
throw new SAXException("<Your message>")
and handle it in the main method.
After your checking, you should throw the Exception to get out from there and get it back to the main method.
throw new Exception("vector size has to be less than 12");
I am trying to parse attached xml(Please find attachment) file.
xml document is as given below.check the attachment 1 and 2
sample data of xml file
In order to parse this xml, I used SAX parser. program is as follows.
package com.dom;
import java.io.File;
import java.io.IOException;
import java.util.Enumeration;
import java.util.Hashtable;
import javax.xml.parsers.ParserConfigurationException;
import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;
import org.xml.sax.helpers.DefaultHandler;
import org.xml.sax.Attributes;
import org.xml.sax.SAXException;
public class DemoXML {
File file;
SAXParserFactory factory;
SAXParser saxParser;
UserHandler handler;
public void loadXML()
{
file = new File("E:/fifthWorkbenchProjects/XMLUtility/src/input/FIXBOND.xml");
System.out.println(file.exists());
}
public void readXML()
{
factory = SAXParserFactory.newInstance();
try {
saxParser = factory.newSAXParser();
handler = new UserHandler();
try {
saxParser.parse(file,handler);
} catch (IOException e) {
e.printStackTrace();
}
} catch (ParserConfigurationException e) {
e.printStackTrace();
} catch (SAXException e) {
e.printStackTrace();
}
}
public static void main(String args[])
{
DemoXML ob = new DemoXML();
ob.loadXML();
ob.readXML();
}
}
class UserHandler extends DefaultHandler
{
Hashtable tags;
#Override
public void startDocument()
{
System.out.println("Document started");
tags = new Hashtable();
}
#Override
public void endDocument()
{
System.out.println("Documents ended");
}
#Override
public void startElement(String namespaceURI,String localName,String qname,Attributes atts) throws SAXException
{
// System.out.println("Element started");
// if(qname.equals("Currency"))
System.out.print(qname+"-->");
}
#Override
public void endElement(String uri,String localName, String qname)
{
}
#Override
public void characters(char[] ch, int start, int length)
{
String str = new String(ch,start,length);
System.out.println(str);
System.out.println();
}
}
I get output in following manner.
true
Document started
FIgovcorpagncy-->InstrumentDescription-->InstrumentType-->FI GOVCORPAGNCY
InstrumentSubType-->FIXDBOND
InstrumentName-->QUEENSNR 0% 07/06/2016
InstrumentDescription-->QUEENSNR 0% 07/06/2016
Currency-->GBP
InstrumentStatus-->ACTIVE
AmountOutstanding-->48384375
AmtOutstandingDate-->2012-06-27T00:00:00.000
PrincipalExchange-->N
CountryOfRisk-->GB
InstrumentCompleteness-->50
CapitalRanking-->1
AtIssuance-->IssueDate-->2012-06-27T00:00:00.000
OriginalIssueAmount-->48384375
PrivatePlacementFlag-->Y
MinimumDenomination-->1000
MinimumIncrement-->0.01
and so on ....I am able to access all nodes but observe one thing over here for first element in tree,complete element address is printed like
FIgovcorpagncy-->InstrumentDescription-->InstrumentType-->FI GOVCORPAGNCY
then for rest of the elements in tree, it prints tag name and corresponding value like
InstrumentSubType-->FIXDBOND
InstrumentName-->QUEENSNR 0% 07/06/2016
InstrumentDescription-->QUEENSNR 0% 07/06/2016
Currency-->GBP
InstrumentStatus-->ACTIVE
AmountOutstanding-->48384375
so on....
here my requirement is I want to print these elements also with full hierarchic manner as the first element.
how to go about it?
class UserHandler extends DefaultHandler
{
List li_elements,li_values;
LinkedHashMap<List<String>,List<String>> hm;
boolean endElementFlag;
#Override
public void startDocument()
{
System.out.println("Document started");
li_elements = new ArrayList<String>();
li_values=new ArrayList<String>();
}
#Override
public void endDocument()
{
System.out.println("Documents ended"+hm.size());
for(Map.Entry m:hm.entrySet())
{
System.out.println(m.getKey()+""+m.getValue());
}
}
#Override
public void startElement(String namespaceURI,String localName,String qname,Attributes atts) throws SAXException
{
li_elements.add(qname);
//System.out.println("Element Started");
//System.out.println(qname+" added in element list");
}
#Override
public void endElement(String uri,String localName, String qname)
{
if(!li_values.isEmpty())
{
System.out.println("Element address list:-"+li_elements+"and Corresponding Value:-"+li_values);
System.out.println();
}
li_elements.remove(li_elements.size()-1);
li_values.clear();
}
#Override
public void characters(char[] ch, int start, int length)
{
String str = new String(ch,start,length);
li_values.add(str);
}
}
I was expecting something like this. this prints the output in a format that I was hoping for.
I'm using SAX (Simple API for XML) to parse an XML document. I'm getting output for all the tags the file have, but i want it to show the tags in parent child hierarchy.
For Example:
This is my output
<dblp>
<www>
<author>
</author><title>
</title><url>
</url><year>
</year></www><inproceedings>
<month>
</month><pages>
</pages><booktitle>
</booktitle><note>
</note><cdrom>
</cdrom></inproceedings><article>
<journal>
</journal><volume>
</volume></article><ee>
</ee><book>
<publisher>
</publisher><isbn>
</isbn></book><incollection>
<crossref>
</crossref></incollection><editor>
</editor><series>
</series></dblp>
But i want it to display the output like this (it displays the children with extra spacing (that's how i want it to be))
<dblp>
<www>
<author>
</author>
<title>
</title>
<url>
</url>
<year>
</year>
</www>
<inproceedings>
<month>
</month>
<pages>
</pages>
<booktitle>
</booktitle>
<note>
</note>
<cdrom>
</cdrom>
</inproceedings>
<article>
<journal>
</journal>
<volume>
</volume>
</article>
<ee>
</ee>
<book>
<publisher>
</publisher>
<isbn>
</isbn>
</book>
<incollection>
<crossref>
</crossref>
</incollection>
<editor>
</editor>
<series>
</series>
</dblp>
But i can't figure out how can i detect that parser is parsing a parent tag or a children.
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/sample.xml", defaultHandler);
} catch (Exception e) {
e.printStackTrace();
}
}
public static void main(String args[]) {
Parser readXml = new Parser();
readXml.getXml();
}
}
You can consider a StAX implementation:
package be.duo.stax;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import javax.xml.stream.XMLInputFactory;
import javax.xml.stream.XMLStreamConstants;
import javax.xml.stream.XMLStreamException;
import javax.xml.stream.XMLStreamReader;
public class StaxExample {
public void getXml() {
InputStream is = null;
try {
is = new FileInputStream("c:\\dev\\sample.xml");
XMLInputFactory inputFactory = XMLInputFactory.newInstance();
XMLStreamReader reader = inputFactory.createXMLStreamReader(is);
parse(reader, 0);
} catch(Exception ex) {
System.out.println(ex.getMessage());
} finally {
if(is != null) {
try {
is.close();
} catch(IOException ioe) {
System.out.println(ioe.getMessage());
}
}
}
}
private void parse(XMLStreamReader reader, int depth) throws XMLStreamException {
while(true) {
if(reader.hasNext()) {
switch(reader.next()) {
case XMLStreamConstants.START_ELEMENT:
writeBeginTag(reader.getLocalName(), depth);
parse(reader, depth+1);
break;
case XMLStreamConstants.END_ELEMENT:
writeEndTag(reader.getLocalName(), depth-1);
return;
}
}
}
}
private void writeBeginTag(String tag, int depth) {
for(int i = 0; i < depth; i++) {
System.out.print(" ");
}
System.out.println("<" + tag + ">");
}
private void writeEndTag(String tag, int depth) {
for(int i = 0; i < depth; i++) {
System.out.print(" ");
}
System.out.println("</" + tag + ">");
}
public static void main(String[] args) {
StaxExample app = new StaxExample();
app.getXml();
}
}
There is an idiom for StAX with a loop like this for every tag in the XML:
private MyTagObject parseMyTag(XMLStreamReader reader, String myTag) throws XMLStreamException {
MyTagObject myTagObject = new MyTagObject();
while (true) {
switch (reader.next()) {
case XMLStreamConstants.START_ELEMENT:
String localName = reader.getLocalName();
if(localName.equals("myOtherTag1")) {
myTagObject.setMyOtherTag1(parseMyOtherTag1(reader, localName));
} else if(localName.equals("myOtherTag2")) {
myTagObject.setMyOtherTag2(parseMyOtherTag2(reader, localName));
}
// and so on
break;
case XMLStreamConstants.END_ELEMENT:
if(reader.getLocalName().equals(myTag) {
return myTagObject;
}
break;
}
}
well what have you tried? you should use a transformer found here: How to pretty print XML from Java?
Transformer transformer = TransformerFactory.newInstance().newTransformer();
transformer.setOutputProperty(OutputKeys.INDENT, "yes");
//initialize StreamResult with File object to save to file
StreamResult result = new StreamResult(new StringWriter());
DOMSource source = new DOMSource(doc);
transformer.transform(source, result);
String xmlString = result.getWriter().toString();
System.out.println(xmlString);
Almost any useful SAX application needs to maintain a stack. When startElement is called, you push information to the stack, when endElement is called, you pop the stack. Exactly what you put on the stack depends on the application; it's often the element name. For your application, you don't actually need a full stack, you only need to know its depth. You could get by with maintaining this using depth++ in startElement and depth-- in endElement(). Then you just output depth spaces before the element name.
I have a situation similar to an earlier question about emitting XML. I am analyzing data in a SAX ContentHandler while serializing it to a stream. I am suspicious that the solution in the linked question -- though it is exactly what I am looking for in terms of the API -- is not memory-efficient, since it involves an identity transform with the XSLT processor. I want the memory consumption of the program to be bounded, rather than it growing with the input size.
How can I easily forward the parameters to my ContentHandler methods to a serializer without doing acrobatics to adapt e.g. StAX to SAX, or worse yet, copying the SAX event contents to the output stream?
Edit: here's a minimal example of what I am after. thingIWant should just write to the OutputStream given to it. Like I said, the earlier question has a TransformerHandler that gives me the right API, but it uses the XSLT processor instead of just a simple serialization.
public class MyHandler implements ContentHandler {
ContentHandler thingIWant;
MyHandler(OutputStream outputStream) {
thingIWant = setup(outputStream);
}
public void startDocument() throws SAXException {
// parsing logic
thingIWant.startDocument();
}
public void startElement(String uri, String localName, String qName,
Attributes atts) throws SAXException {
// parsing logic
thingIWant.startElement(uri, localName, qName, atts);
}
public void characters(char[] ch, int start, int length) throws SAXException {
// parsing logic
thingIWant.characters(ch, start, length);
}
// etc...
}
I recently had a similar problem. Here is the class I wrote to get you thingIWant:
import java.io.OutputStream;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.TransformerException;
import javax.xml.transform.sax.SAXSource;
import javax.xml.transform.stream.StreamResult;
import org.xml.sax.*;
public class XMLSerializer implements ContentHandler {
static final private TransformerFactory tf = TransformerFactory.newInstance();
private ContentHandler ch;
public XMLSerializer(OutputStream os) throws SAXException {
try {
final Transformer t = tf.newTransformer();
t.transform(new SAXSource(
new XMLReader() {
public ContentHandler getContentHandler() { return ch; }
public DTDHandler getDTDHandler() { return null; }
public EntityResolver getEntityResolver() { return null; }
public ErrorHandler getErrorHandler() { return null; }
public boolean getFeature(String name) { return false; }
public Object getProperty(String name) { return null; }
public void parse(InputSource input) { }
public void parse(String systemId) { }
public void setContentHandler(ContentHandler handler) { ch = handler; }
public void setDTDHandler(DTDHandler handler) { }
public void setEntityResolver(EntityResolver resolver) { }
public void setErrorHandler(ErrorHandler handler) { }
public void setFeature(String name, boolean value) { }
public void setProperty(String name, Object value) { }
}, new InputSource()),
new StreamResult(os));
}
catch (TransformerException e) {
throw new SAXException(e);
}
if (ch == null)
throw new SAXException("Transformer didn't set ContentHandler");
}
public void setDocumentLocator(Locator locator) {
ch.setDocumentLocator(locator);
}
public void startDocument() throws SAXException {
ch.startDocument();
}
public void endDocument() throws SAXException {
ch.endDocument();
}
public void startPrefixMapping(String prefix, String uri) throws SAXException {
ch.startPrefixMapping(prefix, uri);
}
public void endPrefixMapping(String prefix) throws SAXException {
ch.endPrefixMapping(prefix);
}
public void startElement(String uri, String localName, String qName, Attributes atts)
throws SAXException {
ch.startElement(uri, localName, qName, atts);
}
public void endElement(String uri, String localName, String qName)
throws SAXException {
ch.endElement(uri, localName, qName);
}
public void characters(char[] ch, int start, int length)
throws SAXException {
this.ch.characters(ch, start, length);
}
public void ignorableWhitespace(char[] ch, int start, int length)
throws SAXException {
this.ch.ignorableWhitespace(ch, start, length);
}
public void processingInstruction(String target, String data)
throws SAXException {
ch.processingInstruction(target, data);
}
public void skippedEntity(String name) throws SAXException {
ch.skippedEntity(name);
}
}
Basically, it intercepts the Transformer's call to parse(), and grabs a reference to its internal ContentHandler. After that, the class acts as a proxy to the snagged ContentHandler.
Not very clean, but it works.
First: don't worry about the identity transform; it does not build an in-memory representation of the data.
To implement your "tee" functionality, you have to create a content handler that listens to the stream of events produced by the parser, and passes them on to the handler provided for you by the transformer. Unfortunately, this is not as easy as it sounds: the parser wants to send events to a DefaultHandler, while the transformer wants to read events from an XMLReader. The former is an abstract class, the latter is an interface. The JDK also provides the class XMLFilterImpl, which implements all of the interfaces of DefaultHandler, but does not extend from it ... that's what you get for incorporating two different projects as your "reference implementations."
So, you need to write a bridge class between the two:
import java.io.IOException;
import java.io.StringReader;
import java.io.StringWriter;
import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.sax.SAXSource;
import javax.xml.transform.stream.StreamResult;
import org.xml.sax.Attributes;
import org.xml.sax.InputSource;
import org.xml.sax.Locator;
import org.xml.sax.SAXException;
import org.xml.sax.SAXParseException;
import org.xml.sax.XMLReader;
import org.xml.sax.helpers.DefaultHandler;
import org.xml.sax.helpers.XMLFilterImpl;
/**
* Uses a decorator ContentHandler to insert a "tee" into a SAX parse/serialize
* stream.
*/
public class SaxTeeExample
{
public static void main(String[] argv)
throws Exception
{
StringReader src = new StringReader("<root><child>text</child></root>");
StringWriter dst = new StringWriter();
Transformer xform = TransformerFactory.newInstance().newTransformer();
XMLReader reader = new MyReader(SAXParserFactory.newInstance().newSAXParser());
xform.transform(new SAXSource(reader, new InputSource(src)),
new StreamResult(dst));
System.out.println(dst.toString());
}
private static class MyReader
extends XMLFilterImpl
{
private SAXParser _parser;
public MyReader(SAXParser parser)
{
_parser = parser;
}
#Override
public void parse(InputSource input)
throws SAXException, IOException
{
_parser.parse(input, new XMLFilterBridge(this));
}
// this is an example of a "tee" function
#Override
public void startElement(String uri, String localName, String name, Attributes atts) throws SAXException
{
System.out.println("startElement: " + name);
super.startElement(uri, localName, name, atts);
}
}
private static class XMLFilterBridge
extends DefaultHandler
{
private XMLFilterImpl _filter;
public XMLFilterBridge(XMLFilterImpl myFilter)
{
_filter = myFilter;
}
#Override
public void characters(char[] ch, int start, int length)
throws SAXException
{
_filter.characters(ch, start, length);
}
// override all other methods of DefaultHandler
// ...
}
}
The main method sets up the transformer. The interesting part is that the SAXSource is constructed around MyReader. When the transformer is ready for events, it will call the parse() method ofthat object, passing it the specified InputSource.
The next part is not obvious: XMLFilterImpl follows the Decorator pattern. The transformer will call various setter methods on this object before starting the transform, passing its own handlers. Any methods that I don't override (eg, startDocument()) will simply call the delegate. As an example override, I'm doing "analysis" (just a println) in startElement(). You'll probably override other ContentHandler methods.
And finally, XMLFilterBridge is the bridge between DefaultHandler and XmlReader; it's also a decorator, and every method simply calls the delegate. I show one override, but you'll have to do them all.
Edit: Includes default JDK version
The most efficient would be an XMLWriter which implements ContentHandler. In nutshell, you are reading and writing from and to IO buffers. There is an XMLWriter in DOM4J which is being used below. You can either subclass XMLWriter or use XMLFilter to do analysis. I am using XMLFilter in this example. Note that XMLFilter is also a ContentHandler. Here is the complete code.
import org.dom4j.io.XMLWriter;
import org.xml.sax.Attributes;
import org.xml.sax.SAXException;
import org.xml.sax.XMLReader;
import org.xml.sax.helpers.XMLFilterImpl;
import javax.xml.parsers.ParserConfigurationException;
import javax.xml.parsers.SAXParserFactory;
import java.io.IOException;
import java.io.PrintStream;
public class XMLPipeline {
public static void main(String[] args) throws Exception {
String inputFile = "build.xml";
PrintStream outputStream = System.out;
new XMLPipeline().pipe(inputFile, outputStream);
}
//dom4j
public void pipe(String inputFile, OutputStream outputStream) throws
SAXException, ParserConfigurationException, IOException {
XMLWriter xwriter = new XMLWriter(outputStream);
XMLReader xreader = XMLReaderFactory.createXMLReader();
XMLAnalyzer analyzer = new XMLAnalyzer(xreader);
analyzer.setContentHandler(xwriter);
analyzer.parse(inputFile);
//do what you want with analyzer
System.err.println(analyzer.elementCount);
}
//default JDK
public void pipeTrax(String inputFile, OutputStream outputStream) throws
SAXException, ParserConfigurationException,
IOException, TransformerException {
StreamResult xwriter = new StreamResult(outputStream);
XMLReader xreader = XMLReaderFactory.createXMLReader();
XMLAnalyzer analyzer = new XMLAnalyzer(xreader);
TransformerFactory stf = SAXTransformerFactory.newInstance();
SAXSource ss = new SAXSource(analyzer, new InputSource(inputFile));
stf.newTransformer().transform(ss, xwriter);
System.out.println(analyzer.elementCount);
}
//This method simply reads from a file, runs it through SAX parser and dumps it
//to dom4j writer
public void dom4jNoop(String inputFile, OutputStream outputStream) throws
IOException, SAXException {
XMLWriter xwriter = new XMLWriter(outputStream);
XMLReader xreader = XMLReaderFactory.createXMLReader();
xreader.setContentHandler(xwriter);
xreader.parse(inputFile);
}
//Simplest way to read a file and write it back to an output stream
public void traxNoop(String inputFile, OutputStream outputStream)
throws TransformerException {
TransformerFactory stf = SAXTransformerFactory.newInstance();
stf.newTransformer().transform(new StreamSource(inputFile),
new StreamResult(outputStream));
}
//this analyzer counts the number of elements in sax stream
public static class XMLAnalyzer extends XMLFilterImpl {
int elementCount = 0;
public XMLAnalyzer(XMLReader xmlReader) {
super(xmlReader);
}
#Override
public void startElement(String uri, String localName, String qName,
Attributes atts) throws SAXException {
super.startElement(uri, localName, qName, atts);
elementCount++;
}
}
}