We Keep Coding

Transform XML to declare all namespaces on root element

Is there a simple Java method way of "moving" all XML namespace declarations of an XML document to the root element? Due to a bug in parser implementation of an unnamed huge company, I need to programmatically rewrite our well formed and valid RPC requests in a way that the root element declares all used namespaces.
Not OK:
<document-element xmlns="uri:ns1">
<foo>
<bar xmlns="uri:ns2" xmlns:ns3="uri:ns3">
<ns3:foobar/>
<ns1:sigh xmlns:ns1="uri:ns1"/>
</bar>
</foo>
</document-element>
OK:
<document-element xmlns="uri:ns1" xmlns:ns1="uri:ns1" xmlns:ns2="uri:ns2" xmlns:ns3="uri:ns3">
<foo>
<ns2:bar>
<ns3:foobar/>
<ns1:sigh/>
</ns2:bar>
</foo>
</document-element>
Generic names for missing prefixes are acceptable. Default namespace may stay or be replaced/added as long as it is defined on the root element. I don't really mind which specific XML technology is used to achieve this (I would prefer to avoid DOM though).
To clarify, this answer refers to what I'd like to achieve as redeclaring namespace declarations within root element scope (entire document) on the root element. Essentially the related question is asking why oh why would anyone implement what I now need to work around.

Wrote a two-pass StAX reader/writer, which is simple enough.
import java.io.*;
import java.util.*;
import javax.xml.stream.*;
import javax.xml.stream.events.*;
public class NamespacesToRoot {
private static final String GENERATED_PREFIX = "pfx";
private final XMLInputFactory inputFact;
private final XMLOutputFactory outputFact;
private final XMLEventFactory eventFactory;
private NamespacesToRoot() {
inputFact = XMLInputFactory.newInstance();
outputFact = XMLOutputFactory.newInstance();
eventFactory = XMLEventFactory.newInstance();
}
public String transform(String xmlString) throws XMLStreamException {
Map<String, String> pfxToNs = new HashMap<String, String>();
XMLEventReader reader = null;
// first pass - analyze
try {
if (xmlString == null || xmlString.isEmpty()) {
throw new IllegalArgumentException("xmlString is null or empty");
}
StringReader stringReader = new StringReader(xmlString);
XMLStreamReader streamReader = inputFact.createXMLStreamReader(stringReader);
reader = inputFact.createXMLEventReader(streamReader);
while (reader.hasNext()) {
XMLEvent event = reader.nextEvent();
if (event.isStartElement()) {
buildNamespaces(event, pfxToNs);
}
}
System.out.println(pfxToNs);
} finally {
try {
if (reader != null) {
reader.close();
}
} catch (XMLStreamException ex) {
}
}
// reverse mapping, also gets rid of duplicates
Map<String, String> nsToPfx = new HashMap<String, String>();
for (Map.Entry<String, String> entry : pfxToNs.entrySet()) {
nsToPfx.put(entry.getValue(), entry.getKey());
}
List<Namespace> namespaces = new ArrayList<Namespace>(nsToPfx.size());
for (Map.Entry<String, String> entry : nsToPfx.entrySet()) {
namespaces.add(eventFactory.createNamespace(entry.getValue(), entry.getKey()));
}
// second pass - rewrite
XMLEventWriter writer = null;
try {
StringWriter stringWriter = new StringWriter();
writer = outputFact.createXMLEventWriter(stringWriter);
StringReader stringReader = new StringReader(xmlString);
XMLStreamReader streamReader = inputFact.createXMLStreamReader(stringReader);
reader = inputFact.createXMLEventReader(streamReader);
boolean rootElement = true;
while (reader.hasNext()) {
XMLEvent event = reader.nextEvent();
if (event.isStartElement()) {
StartElement origStartElement = event.asStartElement();
String prefix = nsToPfx.get(origStartElement.getName().getNamespaceURI());
String namespace = origStartElement.getName().getNamespaceURI();
String localName = origStartElement.getName().getLocalPart();
Iterator attributes = origStartElement.getAttributes();
Iterator namespaces_;
if (rootElement) {
namespaces_ = namespaces.iterator();
rootElement = false;
} else {
namespaces_ = null;
}
writer.add(eventFactory.createStartElement(
prefix, namespace, localName, attributes, namespaces_));
} else {
writer.add(event);
}
}
writer.flush();
return stringWriter.toString();
} finally {
try {
if (reader != null) {
reader.close();
}
} catch (XMLStreamException ex) {
}
try {
if (writer != null) {
writer.close();
}
} catch (XMLStreamException ex) {
}
}
}
private void buildNamespaces(XMLEvent event, Map<String, String> pfxToNs) {
System.out.println("el: " + event);
StartElement startElement = event.asStartElement();
Iterator nsIternator = startElement.getNamespaces();
while (nsIternator.hasNext()) {
Namespace nsAttr = (Namespace) nsIternator.next();
if (nsAttr.isDefaultNamespaceDeclaration()) {
System.out.println("need to generate a prefix for " + nsAttr.getNamespaceURI());
generatePrefix(nsAttr.getNamespaceURI(), pfxToNs);
} else {
System.out.println("add prefix binding for " + nsAttr.getPrefix() + " --> " + nsAttr.getNamespaceURI());
addPrefix(nsAttr.getPrefix(), nsAttr.getNamespaceURI(), pfxToNs);
}
}
}
private void generatePrefix(String namespace, Map<String, String> pfxToNs) {
int i = 1;
String prefix = GENERATED_PREFIX + i;
while (pfxToNs.keySet().contains(prefix)) {
i++;
prefix = GENERATED_PREFIX + i;
}
pfxToNs.put(prefix, namespace);
}
private void addPrefix(String prefix, String namespace, Map<String, String> pfxToNs) {
String existingNs = pfxToNs.get(prefix);
if (existingNs != null) {
if (existingNs.equals(namespace)) {
// nothing to do
} else {
// prefix clash, need to rename this prefix or reuse an existing
// one
if (pfxToNs.values().contains(namespace)) {
// reuse matching prefix
} else {
// rename
generatePrefix(namespace, pfxToNs);
}
}
} else {
// need to add this prefix
pfxToNs.put(prefix, namespace);
}
}
public static void main(String[] args) throws XMLStreamException {
String xmlString = "" +
"<document-element xmlns=\"uri:ns1\" attr=\"1\">\n" +
" <foo>\n" +
" <bar xmlns=\"uri:ns2\" xmlns:ns3=\"uri:ns3\">\n" +
" <ns3:foobar ns3:attr1=\"meh\" />\n" +
" <ns1:sigh xmlns:ns1=\"uri:ns1\"/>\n" +
" </bar>\n" +
" </foo>\n" +
"</document-element>";
System.out.println(xmlString);
NamespacesToRoot transformer = new NamespacesToRoot();
System.out.println(transformer.transform(xmlString));
}
}
Note that this is just fast example code which could use some tweaks, but is also a good start for anyone with a similar problem.

Below is a simple app does the namespace re-declaration... based on XPath and VTD-XML.
import com.ximpleware.*;
import java.io.*;
public class moveNSDeclaration {
public static void main(String[] args) throws IOException, VTDException{
// TODO Auto-generated method stub
VTDGen vg = new VTDGen();
String xml="<document-element xmlns=\"uri:ns1\">\n"+
"<foo>\n"+
"<bar xmlns=\"uri:ns2\" xmlns:ns3=\"uri:ns3\">\n"+
"<ns3:foobar/>\n"+
"<ns1:sigh xmlns:ns1=\"uri:ns1\"/>\n"+
"</bar>\n"+
"</foo>\n"+
"</document-element>\n";
vg.setDoc(xml.getBytes());
vg.parse(false); // namespace unaware to all name space nodes addressable using xpath #*
VTDNav vn = vg.getNav();
XMLModifier xm = new XMLModifier(vn);
FastIntBuffer fib = new FastIntBuffer();
ByteArrayOutputStream baos = new ByteArrayOutputStream();
// get the index value of xmlns declaration of root element
AutoPilot ap =new AutoPilot (vn);
ap.selectXPath("//#*");
int i=0;
//remove all ns node under root element
//save those nodes to be re-inserted into the root element up on verification of uniqueness
while((i=ap.evalXPath())!=-1){
if (vn.getTokenType(i)==VTDNav.TOKEN_ATTR_NS){
xm.remove(); //remove all ns node
fib.append(i);
}
}
//remove redundant ns nodes
for (int j=0;j<fib.size();j++){
if (fib.intAt(j)!=-1){
for (i=j+1;i<fib.size();i++){
if (fib.intAt(i)!=-1)
if (vn.compareTokens(fib.intAt(j), vn, fib.intAt(i))==0){
fib.modifyEntry(i, -1);
}
}
}
}
// compose a string to insert back into the root element containing all subordinate ns nodes
for (int j=0;j<fib.size();j++){
if (fib.intAt(j)!=-1){
int os = vn.getTokenOffset(fib.intAt(j));
int len = vn.getTokenOffset(fib.intAt(j)+1)+vn.getTokenLength(fib.intAt(j)+1)+1-os;
//System.out.println(" os len "+ os + " "+len);
//System.out.println(vn.toString(os,len));
baos.write(" ".getBytes());
baos.write(vn.getXML().getBytes(),os,len);
}
}
byte[] attrBytes = baos.toByteArray();
vn.toElement(VTDNav.ROOT);
xm.insertAttribute(attrBytes);
//System.out.println(baos.toString());
baos.reset();
xm.output(baos);
System.out.println(baos.toString());
}
}
Output looks like
<document-element xmlns="uri:ns2" xmlns:ns3="uri:ns3" xmlns:ns1="uri:ns1" >
<foo>
<bar >
<ns3:foobar/>
<ns1:sigh />
</bar>
</foo>
</document-element>

Junit4 test implementation with parameters passed from XML, (attribute value + nodevalue)?

I know I can hardcode it (parse xml, extract), but is there a way to feed (attribute value + nodevalue) like it is done with Feed4TestNG (it currently support only csv, and excel files)?
I am new to Java, and any expert insight would be helpful. Thanks!

The body of a #Parameters is not limited to data only, you are able to use any java code you like in this method, including throwing exceptions:
#Parameters
public static Collection<Object[]> data() throws IOException {
List<Object[]> data = new ArrayList<>();
// replace getClass() with <nameofclass>.class
try(InputStream in = this.getClass().getResourceAsStream()) {
//parse body here
data.add(new Object[]{attribute, value});
}
return data;
}
Depending on what XML framework you use, you need to parse your XML nodes, and put it in the list, that you are going to return.

So this is what I end up doing here:
Please submit your correction if you think I can improve my code.
.
#RunWith(Parameterized.class)
public class DataDrivenTests {
private String c;
private String b;
private static Collection<Object[]> a;
#Parameters
public static Collection<Object[]> xmlData() throws IOException{
File file = new File("xmlfile.xml");
InputStream xml1 = new FileInputStream(file);
return new xmlData(xml1).getData();
}
public DataDrivenTests(String c, String b) {
super();
this.c = c;
this.b = b;
}
#Test
public void shouldCalculateATimesB() {
boolean assertion = false;
if(c.equals(Parser.parse("Parse this string to Attribute and Value"))){
assertion = true;
}
assertTrue(assertion);
}
}
xmlData.java
public class xmlData{
private transient Collection<Object[]> data = null;
public xmlData(final InputStream xml)throws IOException{
this.data = loadFromXml(xml);
}
public Collection<Object[]> getData(){
return data;
}
private Collection<Object[]> loadFromXml(final InputStream xml)
throws IOException {
List <Object[]> ism_code_map = new ArrayList<Object[]>();
try{
DocumentBuilderFactory dbFactory = DocumentBuilderFactory.newInstance();
dbFactory.setNamespaceAware(true);
DocumentBuilder dBuilder;
dBuilder = dbFactory.newDocumentBuilder();
Document doc = dBuilder.parse(xml);
doc.getDocumentElement().normalize();
XPath xPath = XPathFactory.newInstance().newXPath();
XPathExpression expression = xPath.compile("//e");
NodeList nodes = (NodeList) expression.evaluate(doc, XPathConstants.NODESET);
for (int i =0; i< nodes.getLength(); i++){
Node nNode = nodes.item(i);
//System.out.println("\nCurrent Element:" + nNode.getTextContent());
if (nNode.getNodeType() == Node.ELEMENT_NODE){
Element eElement = (Element) nNode;
if(eElement.getAttribute("attrname") != null && !eElement.getAttribute("attrname").isEmpty()){
code_map.add(new Object[]{"attrname",eElement.getAttribute("attrname")});
}
}catch(ParserConfigurationException e){
e.printStackTrace();
}catch(SAXException e){
e.printStackTrace();
}catch(IOException e){
e.printStackTrace();
}catch(XPathExpressionException e){
e.printStackTrace();
}
catch(NullPointerException e){
e.printStackTrace();
}
return code_map;
}
}

How do I get all the attachments from a .nsf(lotus notes) file using java

Steps followed :
Took a back of my lotus notes as sample.nsf
And then tried to read the attachments from the sample.nsf
Code snippet :
Database db = session.getDatabase("","C:\\Projects\\NotesToJava\\sample.nsf");
DocumentCollection dc = db.getAllDocuments();
Document doc = dc.getFirstDocument();
while (doc != null) {
RichTextItem body = (RichTextItem) doc.getFirstItem("Body");
if (body.getEmbeddedObject("Request.xlsx") != null)
System.out.println("Found BPM_Dev_Access_Request.xlsx in " + doc.getItemValueString("Subject"));
doc = dc.getNextDocument();
}

No need to use evaluate, look up the extractFile in the Lotus Designer Help
From the Lotus help:
import lotus.domino.*;
import java.util.Vector;
import java.util.Enumeration;
public class JavaAgent extends AgentBase {
public void NotesMain() {
try {
Session session = getSession();
AgentContext agentContext = session.getAgentContext();
// (Your code goes here)
Database db = agentContext.getCurrentDatabase();
DocumentCollection dc = db.getAllDocuments();
Document doc = dc.getFirstDocument();
boolean saveFlag = false;
while (doc != null) {
RichTextItem body =
(RichTextItem)doc.getFirstItem("Body");
System.out.println(doc.getItemValueString("Subject"));
Vector v = body.getEmbeddedObjects();
Enumeration e = v.elements();
while (e.hasMoreElements()) {
EmbeddedObject eo = (EmbeddedObject)e.nextElement();
if (eo.getType() == EmbeddedObject.EMBED_ATTACHMENT) {
eo.extractFile("c:\\extracts\\" + eo.getSource());
eo.remove();
saveFlag = true;
}
}
if (saveFlag) {
doc.save(true, true);
saveFlag = false;
}
doc = dc.getNextDocument();
}
} catch(NotesException e) {
System.out.println(e.id + " " + e.text);
e.printStackTrace();
}
}
}

You need to get the attachments out of each document, as opposed to the EmbeddedObjects. Something like this:
import java.util.Iterator;
import lotus.domino.*;
public final class DocAttachmentParser implements Iterator {
private Session s;
private Document doc;
private Double count ;
private Iterator attIterator = null;
public Double getCount() {
return count;
}
public DocAttachmentParser(Session s, Document doc) throws NotesException {
this.s = s;
this.doc = doc;
if (s!=null && doc !=null){
this.count = (Double) s.evaluate("#Attachments", doc).elementAt(0);
if (count.intValue() > 0){
attIterator = s.evaluate("#AttachmentNames", doc).iterator();
}
}
}
public boolean hasNext() {
return count.intValue() > 0 ? attIterator.hasNext(): false;
}
public Object next() {
return count.intValue() > 0 ? attIterator.next(): null;
}
private String nextAttName(){
return count.intValue() > 0 ? attIterator.next().toString(): null;
}
public void remove() {
if (count.intValue() > 0) attIterator.remove();
}
public String getAll(){
StringBuilder sb = new StringBuilder();
if (count.intValue()>0){
while (hasNext()) {
sb.append(nextAttName());
}
}
return sb.toString();
}
}

To get all attachment from a notes document then i wrote this method(part of my class).
This method takes the document and extract the attachment(Rich Text field)from Notes Document. This class also help you to know consider Example: In two document if there is same Attachment it extracts only one.
Here just you have to set "filePath" where you have to extract your attachment.
public boolean export(Document doc ) throws NotesException {
if (doc.hasEmbedded()) {
Vector<Item> allItems;
allItems = doc.getItems();
HashSet<String> attNames = new HashSet<String>();
for (int i = 0; i < allItems.size(); i++) {
Item item = allItems.get(i);
if (item.getType() == Item.RICHTEXT) {
RichTextItem riItem = (RichTextItem) item;
Vector emb = riItem.getEmbeddedObjects();
String[] doublette = new String[emb.size()];
Set<String> atts = new HashSet<String>();
for (int j = 0; j < emb.size(); j++) {
EmbeddedObject embObj = (EmbeddedObject) emb.get(j);
if (!attNames.contains(embObj.getName())) {
attNames.add(embObj.getName());
StringBuffer test = new StringBuffer(
embObj.getSource());
test.append('-');
test.append(embObj.getName());
test.append('-');
test.append(embObj.getFileSize());
String attDesc = test.toString();
if (atts.contains(attDesc)) {
doublette[j] = attDesc;
} else {
doublette[j] = "";
atts.add(attDesc);
}
}
}
for (int j = 0; j < emb.size(); j++) {
try {
EmbeddedObject embObj = (EmbeddedObject) emb.get(j);
String itemName = riItem.getName();
bOk = extractFile(embObj, itemName);
embObj.recycle();
} catch (NotesException e) {
bOk = false;
if (!"".equals(doublette[j])) {
bOk = true;
System.out.println(" duplicated attachment:")
log.append(doublette[j]);
}
}
}
}
}
}
return bOk;
}
private boolean extractFile(EmbeddedObject embObj, String itemName)
throws NotesException {
boolean bOk = true;
if (embObj.getType() == EmbeddedObject.EMBED_ATTACHMENT) {
String fileName = embObj.getName();
String filePath = this.filesPath + fileName;
// Check if file already exists, then delete
if (FileUtils.killFile(filePath, false, true, true)) {
embObj.extractFile(filePath);
} else {
bOk = false;
System.out.println(", error in kill: " + filePath);
}
}
return bOk;
}

Easy way to get all the attachments from Lotus Notes using Java.
Document doc = dc.getFirstDocument();
for(var att :session.evaluate("#AttachmentNames", doc)){
if (att == null || att.toString().isEmpty()) {
continue;
}
EmbeddedObject eb = doc.getAttachment(att.toString());
System.out.println(eb.getName());
System.out.println(eb.getFileSize());
eb.extractFile("a.txt");// give file name what u want
}

Read escaped quote as escaped quote from xml

I load xml file into DOM model and analyze it.
The code for that is:
public class MyTest {
public static void main(String[] args) {
Document doc = XMLUtils.fileToDom("MyTest.xml");//Loads xml data to DOM
Element rootElement = doc.getDocumentElement();
NodeList nodes = rootElement.getChildNodes();
Node child1 = nodes.item(1);
Node child2 = nodes.item(3);
String str1 = child1.getTextContent();
String str2 = child2.getTextContent();
if(str1 != null){
System.out.println(str1.equals(str2));
}
System.out.println();
System.out.println(str1);
System.out.println(str2);
}
}
MyTest.xml
<tests>
<test name="1">ff1 "</test>
<test name="2">ff1 "</test>
</tests>
Result:
true
ff1 "
ff1 "
Desired result:
false
ff1 "
ff1 "
So I need to distinguish these two cases: when the quote is escaped and is not.
Please help.
Thank you in advance.
P.S. The code for XMLUtils#fileToDom(String filePath), a snippet from XMLUtils class:
static {
DocumentBuilderFactory dFactory = DocumentBuilderFactory.newInstance();
dFactory.setNamespaceAware(false);
dFactory.setValidating(false);
try {
docNonValidatingBuilder = dFactory.newDocumentBuilder();
} catch (ParserConfigurationException e) {
}
}
public static DocumentBuilder getNonValidatingBuilder() {
return docNonValidatingBuilder;
}
public static Document fileToDom(String filePath) {
Document doc = getNonValidatingBuilder().newDocument();
File f = new File(filePath);
if(!f.exists())
return doc;
try {
Transformer transformer = TransformerFactory.newInstance().newTransformer();
DOMResult result = new DOMResult(doc);
StreamSource source = new StreamSource(f);
transformer.transform(source, result);
} catch (Exception e) {
return doc;
}
return doc;
}

I've take a look on source code of apache xerces and propose my solution (but it is monkey patch).
I've wrote simple class
package a;
import java.io.IOException;
import org.apache.xerces.impl.XMLDocumentScannerImpl;
import org.apache.xerces.parsers.NonValidatingConfiguration;
import org.apache.xerces.xni.XMLString;
import org.apache.xerces.xni.XNIException;
import org.apache.xerces.xni.parser.XMLComponent;
public class MyConfig extends NonValidatingConfiguration {
private MyScanner myScanner;
#Override
#SuppressWarnings("unchecked")
protected void configurePipeline() {
if (myScanner == null) {
myScanner = new MyScanner();
addComponent((XMLComponent) myScanner);
}
super.fProperties.put(DOCUMENT_SCANNER, myScanner);
super.fScanner = myScanner;
super.fScanner.setDocumentHandler(this.fDocumentHandler);
super.fLastComponent = fScanner;
}
private static class MyScanner extends XMLDocumentScannerImpl {
#Override
protected void scanEntityReference() throws IOException, XNIException {
// name
String name = super.fEntityScanner.scanName();
if (name == null) {
reportFatalError("NameRequiredInReference", null);
return;
}
super.fDocumentHandler.characters(new XMLString(("&" + name + ";")
.toCharArray(), 0, name.length() + 2), null);
// end
if (!super.fEntityScanner.skipChar(';')) {
reportFatalError("SemicolonRequiredInReference",
new Object[] { name });
}
fMarkupDepth--;
}
}
}
You need to add only next line to your main method before start parsing
System.setProperty(
"org.apache.xerces.xni.parser.XMLParserConfiguration",
"a.MyConfig");
And you will have expected result:
false
ff1 "
ff1 "

Looks like you can get the TEXT_NODE child and use getNodeValue (assuming it's not NULL):
public static String getRawContent(Node n) {
if (n == null) {
return null;
}
Node n1 = getChild(n, Node.TEXT_NODE);
if (n1 == null) {
return null;
}
return n1.getNodeValue();
}
Grabbed that from:
http://www.java2s.com/Code/Java/XML/Gettherawtextcontentofanodeornullifthereisnotext.htm

There is no way to do this for the internal entities. XML does not support this concept. Internal entities are just a different way to write the same PSVI content into the text, they are not distinctive.

Reading multiple xml documents from a socket in java

I'm writing a client which needs to read multiple consecutive small XML documents over a socket. I can assume that the encoding is always UTF-8 and that there is optionally delimiting whitespace between documents. The documents should ultimately go into DOM objects. What is the best way to accomplish this?
The essense of the problem is that the parsers expect a single document in the stream and consider the rest of the content junk. I thought that I could artificially end the document by tracking the element depth, and creating a new reader using the existing input stream. E.g. something like:
// Broken
public void parseInputStream(InputStream inputStream) throws Exception
{
XMLInputFactory factory = XMLInputFactory.newInstance();
XMLOutputFactory xof = XMLOutputFactory.newInstance();
XMLEventFactory eventFactory = XMLEventFactory.newInstance();
DocumentBuilderFactory documentBuilderFactory = DocumentBuilderFactory.newInstance();
DocumentBuilder documentBuilder = documentBuilderFactory.newDocumentBuilder();
Document doc = documentBuilder.newDocument();
XMLEventWriter domWriter = xof.createXMLEventWriter(new DOMResult(doc));
XMLStreamReader xmlStreamReader = factory.createXMLStreamReader(inputStream);
XMLEventReader reader = factory.createXMLEventReader(xmlStreamReader);
int depth = 0;
while (reader.hasNext()) {
XMLEvent evt = reader.nextEvent();
domWriter.add(evt);
switch (evt.getEventType()) {
case XMLEvent.START_ELEMENT:
depth++;
break;
case XMLEvent.END_ELEMENT:
depth--;
if (depth == 0)
{
domWriter.add(eventFactory.createEndDocument());
System.out.println(doc);
reader.close();
xmlStreamReader.close();
xmlStreamReader = factory.createXMLStreamReader(inputStream);
reader = factory.createXMLEventReader(xmlStreamReader);
doc = documentBuilder.newDocument();
domWriter = xof.createXMLEventWriter(new DOMResult(doc));
domWriter.add(eventFactory.createStartDocument());
}
break;
}
}
}
However running this on input such as <a></a><b></b><c></c> prints the first document and throws an XMLStreamException. Whats the right way to do this?
Clarification: Unfortunately the protocol is fixed by the server and cannot be changed, so prepending a length or wrapping the contents would not work.

Length-prefix each document (in bytes).
Read the length of the first document from the socket
Read that much data from the socket, dumping it into a ByteArrayOutputStream
Create a ByteArrayInputStream from the results
Parse that ByteArrayInputStream to get the first document
Repeat for the second document etc

IIRC, XML documents can have comments and processing-instructions at the end, so there's no real way of telling exactly when you have come to the end of the file.
A couple of ways of handling the situation have already been mentioned. Another alternative is to put in an illegal character or byte into the stream, such as NUL or zero. This has the advantage that you don't need to alter the documents and you never need to buffer an entire file.

just change to whatever stream
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.StringReader;
import javax.xml.namespace.QName;
import javax.xml.stream.XMLInputFactory;
import javax.xml.stream.XMLStreamConstants;
import javax.xml.stream.XMLStreamReader;
public class LogParser {
private XMLInputFactory inputFactory = null;
private XMLStreamReader xmlReader = null;
InputStream is;
private int depth;
private QName rootElement;
private static class XMLStream extends InputStream
{
InputStream delegate;
StringReader startroot = new StringReader("<root>");
StringReader endroot = new StringReader("</root>");
XMLStream(InputStream delegate)
{
this.delegate = delegate;
}
public int read() throws IOException {
int c = startroot.read();
if(c==-1)
{
c = delegate.read();
}
if(c==-1)
{
c = endroot.read();
}
return c;
}
}
public LogParser() {
inputFactory = XMLInputFactory.newInstance();
}
public void read() throws Exception {
is = new XMLStream(new FileInputStream(new File(
"./myfile.log")));
xmlReader = inputFactory.createXMLStreamReader(is);
while (xmlReader.hasNext()) {
printEvent(xmlReader);
xmlReader.next();
}
xmlReader.close();
}
public void printEvent(XMLStreamReader xmlr) throws Exception {
switch (xmlr.getEventType()) {
case XMLStreamConstants.END_DOCUMENT:
System.out.println("finished");
break;
case XMLStreamConstants.START_ELEMENT:
System.out.print("<");
printName(xmlr);
printNamespaces(xmlr);
printAttributes(xmlr);
System.out.print(">");
if(rootElement==null && depth==1)
{
rootElement = xmlr.getName();
}
depth++;
break;
case XMLStreamConstants.END_ELEMENT:
System.out.print("</");
printName(xmlr);
System.out.print(">");
depth--;
if(depth==1 && rootElement.equals(xmlr.getName()))
{
rootElement=null;
System.out.println("finished element");
}
break;
case XMLStreamConstants.SPACE:
case XMLStreamConstants.CHARACTERS:
int start = xmlr.getTextStart();
int length = xmlr.getTextLength();
System.out
.print(new String(xmlr.getTextCharacters(), start, length));
break;
case XMLStreamConstants.PROCESSING_INSTRUCTION:
System.out.print("<?");
if (xmlr.hasText())
System.out.print(xmlr.getText());
System.out.print("?>");
break;
case XMLStreamConstants.CDATA:
System.out.print("<![CDATA[");
start = xmlr.getTextStart();
length = xmlr.getTextLength();
System.out
.print(new String(xmlr.getTextCharacters(), start, length));
System.out.print("]]>");
break;
case XMLStreamConstants.COMMENT:
System.out.print("<!--");
if (xmlr.hasText())
System.out.print(xmlr.getText());
System.out.print("-->");
break;
case XMLStreamConstants.ENTITY_REFERENCE:
System.out.print(xmlr.getLocalName() + "=");
if (xmlr.hasText())
System.out.print("[" + xmlr.getText() + "]");
break;
case XMLStreamConstants.START_DOCUMENT:
System.out.print("<?xml");
System.out.print(" version='" + xmlr.getVersion() + "'");
System.out.print(" encoding='" + xmlr.getCharacterEncodingScheme()
+ "'");
if (xmlr.isStandalone())
System.out.print(" standalone='yes'");
else
System.out.print(" standalone='no'");
System.out.print("?>");
break;
}
}
/**
* #param args
*/
public static void main(String[] args) {
// TODO Auto-generated method stub
try {
new LogParser().read();
} catch (Exception e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
private static void printName(XMLStreamReader xmlr) {
if (xmlr.hasName()) {
System.out.print(getName(xmlr));
}
}
private static String getName(XMLStreamReader xmlr) {
if (xmlr.hasName()) {
String prefix = xmlr.getPrefix();
String uri = xmlr.getNamespaceURI();
String localName = xmlr.getLocalName();
return getName(prefix, uri, localName);
}
return null;
}
private static String getName(String prefix, String uri, String localName) {
String name = "";
if (uri != null && !("".equals(uri)))
name += "['" + uri + "']:";
if (prefix != null)
name += prefix + ":";
if (localName != null)
name += localName;
return name;
}
private static void printAttributes(XMLStreamReader xmlr) {
for (int i = 0; i < xmlr.getAttributeCount(); i++) {
printAttribute(xmlr, i);
}
}
private static void printAttribute(XMLStreamReader xmlr, int index) {
String prefix = xmlr.getAttributePrefix(index);
String namespace = xmlr.getAttributeNamespace(index);
String localName = xmlr.getAttributeLocalName(index);
String value = xmlr.getAttributeValue(index);
System.out.print(" ");
System.out.print(getName(prefix, namespace, localName));
System.out.print("='" + value + "'");
}
private static void printNamespaces(XMLStreamReader xmlr) {
for (int i = 0; i < xmlr.getNamespaceCount(); i++) {
printNamespace(xmlr, i);
}
}
private static void printNamespace(XMLStreamReader xmlr, int index) {
String prefix = xmlr.getNamespacePrefix(index);
String uri = xmlr.getNamespaceURI(index);
System.out.print(" ");
if (prefix == null)
System.out.print("xmlns='" + uri + "'");
else
System.out.print("xmlns:" + prefix + "='" + uri + "'");
}
}

A simple solution is to wrap the documents on the sending side in a new root element:
<?xml version="1.0"?>
<documents>
... document 1 ...
... document 2 ...
</documents>
You must make sure that you don't include the XML header (<?xml ...?>), though. If all documents use the same encoding, this can be accomplished with a simple filter which just ignores the first line of each document if it starts with <?xml

Found this forum message (which you probably already saw), which has a solution by wrapping the input stream and testing for one of two ascii characters (see post).
You could try an adaptation on this by first converting to use a reader (for proper character encoding) and then doing element counting until you reach the closing element, at which point you trigger the EOM.

Hi
I also had this problem at work (so won't post resulting the code). The most elegant solution that I could think of, and which works pretty nicely imo, is as follows
Create a class for example DocumentSplittingInputStream which extends InputStream and takes the underlying inputstream in its constructor (or gets set after construction...).
Add a field with a byte array closeTag containing the bytes of the closing root node you are looking for.
Add a field int called matchCount or something, initialised to zero.
Add a field boolean called underlyingInputStreamNotFinished, initialised to true
On the read() implementation:
Check if matchCount == closeTag.length, if it does, set matchCount to -1, return -1
If matchCount == -1, set matchCount = 0, call read() on the underlying inputstream until you get -1 or '<' (the xml declaration of the next document on the stream) and return it. Note that for all I know the xml spec allows comments after the document element, but I knew I was not going to get that from the source so did not bother handling it - if you can not be sure you'll need to change the "gobble" slightly.
Otherwise read an int from the underlying inputstream (if it equals closeTag[matchCount] then increment matchCount, if it doesn't then reset matchCount to zero) and return the newly read byte
Add a method which returns the boolean on whether the underlying stream has closed.
All reads on the underlying input stream should go through a separate method where it checks if the value read is -1 and if so, sets the field "underlyingInputStreamNotFinished" to false.
I may have missed some minor points but i'm sure you get the picture.
Then in the using code you do something like, if you are using xstream:
DocumentSplittingInputStream dsis = new DocumentSplittingInputStream(underlyingInputStream);
while (dsis.underlyingInputStreamNotFinished()) {
MyObject mo = xstream.fromXML(dsis);
mo.doSomething(); // or something.doSomething(mo);
}
David

I had to do something like this and during my research on how to approach it, I found this thread that even though it is quite old, I just replied (to myself) here wrapping everything in its own Reader for simpler use

I was faced with a similar problem. A web service I'm consuming will (in some cases) return multiple xml documents in response to a single HTTP GET request. I could read the entire response into a String and split it, but instead I implemented a splitting input stream based on user467257's post above. Here is the code:
public class AnotherSplittingInputStream extends InputStream {
private final InputStream realStream;
private final byte[] closeTag;
private int matchCount;
private boolean realStreamFinished;
private boolean reachedCloseTag;
public AnotherSplittingInputStream(InputStream realStream, String closeTag) {
this.realStream = realStream;
this.closeTag = closeTag.getBytes();
}
#Override
public int read() throws IOException {
if (reachedCloseTag) {
return -1;
}
if (matchCount == closeTag.length) {
matchCount = 0;
reachedCloseTag = true;
return -1;
}
int ch = realStream.read();
if (ch == -1) {
realStreamFinished = true;
}
else if (ch == closeTag[matchCount]) {
matchCount++;
} else {
matchCount = 0;
}
return ch;
}
public boolean hasMoreData() {
if (realStreamFinished == true) {
return false;
} else {
reachedCloseTag = false;
return true;
}
}
}
And to use it:
String xml =
"<?xml version=\"1.0\" encoding=\"UTF-8\"?>" +
"<root>first root</root>" +
"<?xml version=\"1.0\" encoding=\"UTF-8\"?>" +
"<root>second root</root>";
ByteArrayInputStream is = new ByteArrayInputStream(xml.getBytes());
SplittingInputStream splitter = new SplittingInputStream(is, "</root>");
BufferedReader reader = new BufferedReader(new InputStreamReader(splitter));
while (splitter.hasMoreData()) {
System.out.println("Starting next stream");
String line = null;
while ((line = reader.readLine()) != null) {
System.out.println("line ["+line+"]");
}
}

I use JAXB approach to unmarshall messages from multiply stream:
MultiInputStream.java
public class MultiInputStream extends InputStream {
private final Reader source;
private final StringReader startRoot = new StringReader("<root>");
private final StringReader endRoot = new StringReader("</root>");
public MultiInputStream(Reader source) {
this.source = source;
}
#Override
public int read() throws IOException {
int count = startRoot.read();
if (count == -1) {
count = source.read();
}
if (count == -1) {
count = endRoot.read();
}
return count;
}
}
MultiEventReader.java
public class MultiEventReader implements XMLEventReader {
private final XMLEventReader reader;
private boolean isXMLEvent = false;
private int level = 0;
public MultiEventReader(XMLEventReader reader) throws XMLStreamException {
this.reader = reader;
startXML();
}
private void startXML() throws XMLStreamException {
while (reader.hasNext()) {
XMLEvent event = reader.nextEvent();
if (event.isStartElement()) {
return;
}
}
}
public boolean hasNextXML() {
return reader.hasNext();
}
public void nextXML() throws XMLStreamException {
while (reader.hasNext()) {
XMLEvent event = reader.peek();
if (event.isStartElement()) {
isXMLEvent = true;
return;
}
reader.nextEvent();
}
}
#Override
public XMLEvent nextEvent() throws XMLStreamException {
XMLEvent event = reader.nextEvent();
if (event.isStartElement()) {
level++;
}
if (event.isEndElement()) {
level--;
if (level == 0) {
isXMLEvent = false;
}
}
return event;
}
#Override
public boolean hasNext() {
return isXMLEvent;
}
#Override
public XMLEvent peek() throws XMLStreamException {
XMLEvent event = reader.peek();
if (level == 0) {
while (event != null && !event.isStartElement() && reader.hasNext()) {
reader.nextEvent();
event = reader.peek();
}
}
return event;
}
#Override
public String getElementText() throws XMLStreamException {
throw new NotImplementedException();
}
#Override
public XMLEvent nextTag() throws XMLStreamException {
throw new NotImplementedException();
}
#Override
public Object getProperty(String name) throws IllegalArgumentException {
throw new NotImplementedException();
}
#Override
public void close() throws XMLStreamException {
throw new NotImplementedException();
}
#Override
public Object next() {
throw new NotImplementedException();
}
#Override
public void remove() {
throw new NotImplementedException();
}
}
Message.java
#XmlAccessorType(XmlAccessType.FIELD)
#XmlRootElement(name = "Message")
public class Message {
public Message() {
}
#XmlAttribute(name = "ID", required = true)
protected long id;
public long getId() {
return id;
}
public void setId(long id) {
this.id = id;
}
#Override
public String toString() {
return "Message{id=" + id + '}';
}
}
Read multiply messages:
public static void main(String[] args) throws Exception{
StringReader stringReader = new StringReader(
"<Message ID=\"123\" />\n" +
"<Message ID=\"321\" />"
);
JAXBContext context = JAXBContext.newInstance(Message.class);
Unmarshaller unmarshaller = context.createUnmarshaller();
XMLInputFactory inputFactory = XMLInputFactory.newFactory();
MultiInputStream multiInputStream = new MultiInputStream(stringReader);
XMLEventReader xmlEventReader = inputFactory.createXMLEventReader(multiInputStream);
MultiEventReader multiEventReader = new MultiEventReader(xmlEventReader);
while (multiEventReader.hasNextXML()) {
Object message = unmarshaller.unmarshal(multiEventReader);
System.out.println(message);
multiEventReader.nextXML();
}
}
results:
Message{id=123}
Message{id=321}