List of usage examples for javax.xml.stream XMLStreamConstants START_ELEMENT
int START_ELEMENT
To view the source code for javax.xml.stream XMLStreamConstants START_ELEMENT.
Click Source Link
From source file:act.installer.pubchem.PubchemParser.java
/** * Incrementally parses a stream of XML events from a PubChem file, extracting the next available PC-Compound entry * as a Chemical object.//w ww.j ava 2s . com * @param eventReader The xml event reader we are parsing the XML from * @return The constructed chemical * @throws XMLStreamException * @throws XPathExpressionException */ public Chemical extractNextChemicalFromXMLStream(XMLEventReader eventReader) throws XMLStreamException, JaxenException { Document bufferDoc = null; Element currentElement = null; StringBuilder textBuffer = null; /* With help from * http://stackoverflow.com/questions/7998733/loading-local-chunks-in-dom-while-parsing-a-large-xml-file-in-sax-java */ while (eventReader.hasNext()) { XMLEvent event = eventReader.nextEvent(); switch (event.getEventType()) { case XMLStreamConstants.START_ELEMENT: String eventName = event.asStartElement().getName().getLocalPart(); if (COMPOUND_DOC_TAG.equals(eventName)) { // Create a new document if we've found the start of a compound object. bufferDoc = documentBuilder.newDocument(); currentElement = bufferDoc.createElement(eventName); bufferDoc.appendChild(currentElement); } else if (currentElement != null) { // Wait until we've found a compound entry to start slurping up data. // Create a new child element and push down the current pointer when we find a new node. Element newElement = bufferDoc.createElement(eventName); currentElement.appendChild(newElement); currentElement = newElement; } // If we aren't in a PC-Compound tree, we just let the elements pass by. break; case XMLStreamConstants.CHARACTERS: if (currentElement == null) { // Ignore this event if we're not in a PC-Compound tree. continue; } Characters chars = event.asCharacters(); // Ignore only whitespace strings, which just inflate the size of the DOM. Text coalescing makes this safe. if (chars.isWhiteSpace()) { continue; } // Rely on the XMLEventStream to coalesce consecutive text events. Text textNode = bufferDoc.createTextNode(chars.getData()); currentElement.appendChild(textNode); break; case XMLStreamConstants.END_ELEMENT: if (currentElement == null) { // Ignore this event if we're not in a PC-Compound tree. continue; } eventName = event.asEndElement().getName().getLocalPart(); Node parentNode = currentElement.getParentNode(); if (parentNode instanceof Element) { currentElement = (Element) parentNode; } else if (parentNode instanceof Document && eventName.equals(COMPOUND_DOC_TAG)) { // We're back at the top of the node stack! Convert the buffered document into a Chemical. PubchemEntry entry = extractPCCompoundFeatures(bufferDoc); if (entry != null) { return entry.asChemical(); } else { // Skip this entry if we can't process it correctly by resetting the world and continuing on. bufferDoc = null; currentElement = null; } } else { // This should not happen, but is here as a sanity check. throw new RuntimeException(String.format("Parent of XML element %s is of type %d, not Element", currentElement.getTagName(), parentNode.getNodeType())); } break; // TODO: do we care about attributes or other XML structures? } } // Return null when we run out of chemicals, just like readLine(). return null; }
From source file:de.uzk.hki.da.cb.CreatePremisAction.java
/** * Accepts a premis.xml file and creates a new xml file for each jhove section * //from w w w .java2 s . c om * @author Thomas Kleinke * Extract jhove data. * * @param premisFilePath the premis file path * @param outputFolder the output folder * @throws XMLStreamException the xML stream exception */ public void extractJhoveData(String premisFilePath, String outputFolder) throws XMLStreamException { outputFolder += "/premis_output/"; FileInputStream inputStream = null; try { inputStream = new FileInputStream(premisFilePath); } catch (FileNotFoundException e) { throw new RuntimeException("Couldn't find file " + premisFilePath, e); } XMLInputFactory inputFactory = XMLInputFactory.newInstance(); XMLStreamReader streamReader = inputFactory.createXMLStreamReader(inputStream); boolean textElement = false; boolean jhoveSection = false; boolean objectIdentifierValue = false; int tab = 0; String fileId = ""; while (streamReader.hasNext()) { int event = streamReader.next(); switch (event) { case XMLStreamConstants.START_ELEMENT: if (streamReader.getLocalName().equals("jhove")) { jhoveSection = true; String outputFilePath = outputFolder + fileId.replace('/', '_').replace('.', '_') + ".xml"; if (!new File(outputFolder).exists()) new File(outputFolder).mkdirs(); writer = startNewDocument(outputFilePath); } if (streamReader.getLocalName().equals("objectIdentifierValue")) objectIdentifierValue = true; if (jhoveSection) { writer.writeDTD("\n"); indent(tab); tab++; String prefix = streamReader.getPrefix(); if (prefix != null && !prefix.equals("")) { writer.setPrefix(prefix, streamReader.getNamespaceURI()); writer.writeStartElement(streamReader.getNamespaceURI(), streamReader.getLocalName()); } else writer.writeStartElement(streamReader.getLocalName()); for (int i = 0; i < streamReader.getNamespaceCount(); i++) writer.writeNamespace(streamReader.getNamespacePrefix(i), streamReader.getNamespaceURI(i)); for (int i = 0; i < streamReader.getAttributeCount(); i++) { QName qname = streamReader.getAttributeName(i); String attributeName = qname.getLocalPart(); String attributePrefix = qname.getPrefix(); if (attributePrefix != null && !attributePrefix.equals("")) attributeName = attributePrefix + ":" + attributeName; writer.writeAttribute(attributeName, streamReader.getAttributeValue(i)); } } break; case XMLStreamConstants.CHARACTERS: if (objectIdentifierValue) { fileId = streamReader.getText(); objectIdentifierValue = false; } if (jhoveSection && !streamReader.isWhiteSpace()) { writer.writeCharacters(streamReader.getText()); textElement = true; } break; case XMLStreamConstants.END_ELEMENT: if (jhoveSection) { tab--; if (!textElement) { writer.writeDTD("\n"); indent(tab); } writer.writeEndElement(); textElement = false; if (streamReader.getLocalName().equals("jhove")) { jhoveSection = false; finalizeDocument(); } } break; case XMLStreamConstants.END_DOCUMENT: streamReader.close(); try { inputStream.close(); } catch (IOException e) { throw new RuntimeException("Failed to close input stream", e); } break; default: break; } } }
From source file:com.microsoft.windowsazure.services.table.client.AtomPubParser.java
/** * Reserved for internal use. Reads the properties of an entity from the stream into a map of property names to * typed values. Reads the entity data as an AtomPub Entry Resource from the specified {@link XMLStreamReader} into * a map of <code>String</code> property names to {@link EntityProperty} data typed values. * /* www . jav a 2 s . c o m*/ * @param xmlr * The <code>XMLStreamReader</code> to read the data from. * @param opContext * An {@link OperationContext} object used to track the execution of the operation. * * @return * A <code>java.util.HashMap</code> containing a map of <code>String</code> property names to * {@link EntityProperty} data typed values found in the entity data. * @throws XMLStreamException * if an error occurs accessing the stream. * @throws ParseException * if an error occurs converting the input to a particular data type. */ protected static HashMap<String, EntityProperty> readProperties(final XMLStreamReader xmlr, final OperationContext opContext) throws XMLStreamException, ParseException { int eventType = xmlr.getEventType(); xmlr.require(XMLStreamConstants.START_ELEMENT, null, ODataConstants.PROPERTIES); final HashMap<String, EntityProperty> properties = new HashMap<String, EntityProperty>(); while (xmlr.hasNext()) { eventType = xmlr.next(); if (eventType == XMLStreamConstants.CHARACTERS) { xmlr.getText(); continue; } if (eventType == XMLStreamConstants.START_ELEMENT && xmlr.getNamespaceURI().equals(ODataConstants.DATA_SERVICES_NS)) { final String key = xmlr.getLocalName(); String val = Constants.EMPTY_STRING; String edmType = null; if (xmlr.getAttributeCount() > 0) { edmType = xmlr.getAttributeValue(ODataConstants.DATA_SERVICES_METADATA_NS, ODataConstants.TYPE); } // move to chars eventType = xmlr.next(); if (eventType == XMLStreamConstants.CHARACTERS) { val = xmlr.getText(); // end element eventType = xmlr.next(); } xmlr.require(XMLStreamConstants.END_ELEMENT, null, key); final EntityProperty newProp = new EntityProperty(val, EdmType.parse(edmType)); properties.put(key, newProp); } else if (eventType == XMLStreamConstants.END_ELEMENT && xmlr.getName().toString() .equals(ODataConstants.BRACKETED_DATA_SERVICES_METADATA_NS + ODataConstants.PROPERTIES)) { // End read properties break; } } xmlr.require(XMLStreamConstants.END_ELEMENT, null, ODataConstants.PROPERTIES); return properties; }
From source file:com.msopentech.odatajclient.testservice.utils.XMLUtilities.java
public static XmlElement getAtomElement(final StartElement start, final XMLEventReader reader) throws Exception { final XmlElement res = new XmlElement(); res.setStart(start);// w ww . ja va 2 s .c o m StringWriter content = new StringWriter(); int depth = 1; while (reader.hasNext() && depth > 0) { final XMLEvent event = reader.nextEvent(); if (event.getEventType() == XMLStreamConstants.START_ELEMENT && start.getName().getLocalPart().equals(event.asStartElement().getName().getLocalPart())) { depth++; } else if (event.getEventType() == XMLStreamConstants.END_ELEMENT && start.getName().getLocalPart().equals(event.asEndElement().getName().getLocalPart())) { depth--; } if (depth == 0) { res.setEnd(event.asEndElement()); } else { event.writeAsEncodedUnicode(content); } } content.flush(); content.close(); res.setContent(new ByteArrayInputStream(content.toString().getBytes())); return res; }
From source file:edu.harvard.iq.dvn.ingest.statdataio.impl.plugins.ddi.DDIFileReader.java
private void processFileDscr(XMLStreamReader xmlr, SDIOMetadata smd) throws XMLStreamException { for (int event = xmlr.next(); event != XMLStreamConstants.END_DOCUMENT; event = xmlr.next()) { if (event == XMLStreamConstants.START_ELEMENT) { if (xmlr.getLocalName().equals("fileTxt")) { processFileTxt(xmlr, smd); } else if (xmlr.getLocalName().equals("notes")) { // ignore, at least for now. // (the only notes in our fileDscr sections are those with // the UNFs and original file information, i.e., things we // supply during ingest -- so there's no reason for us to // be interested in what's in them; we may, however want to // treat is as an error when any notes are encountered // during TAB+DDI ingest. -- TBD) } else { throw new XMLStreamException( "Unsupported DDI Element: codeBook/fileDscr/" + xmlr.getLocalName()); }/*from w w w . j a v a 2 s.c o m*/ } else if (event == XMLStreamConstants.END_ELEMENT) {// </codeBook> if (xmlr.getLocalName().equals("fileDscr")) { return; } else if (xmlr.getLocalName().equals("notes")) { // continue; } else { throw new XMLStreamException( "Mismatched DDI Formatting: </fileDscr> expected, found " + xmlr.getLocalName()); } } } }
From source file:edu.indiana.d2i.htrc.portal.HTRCPersistenceAPIClient.java
private AlgorithmDetailsBean parseAlgorithmDetailBean(InputStream stream) throws XMLStreamException { AlgorithmDetailsBean res = new AlgorithmDetailsBean(); XMLStreamReader parser = factory.createXMLStreamReader(stream); List<AlgorithmDetailsBean.Parameter> parameters = new ArrayList<AlgorithmDetailsBean.Parameter>(); List<String> authors = new ArrayList<String>(); while (parser.hasNext()) { int event = parser.next(); if (event == XMLStreamConstants.START_ELEMENT) { if (parser.hasName()) { // only parse the info tag! if (parser.getLocalName().equals(AlgorithmDetailsBean.NAME)) { res.setName(parser.getElementText()); } else if (parser.getLocalName().equals(AlgorithmDetailsBean.VERSION)) { res.setVersion(parser.getElementText()); } else if (parser.getLocalName().equals(AlgorithmDetailsBean.DESCRIPTION)) { res.setDescription(parser.getElementText()); } else if (parser.getLocalName().equals(AlgorithmDetailsBean.SUPPORTURL)) { res.setSupportUrl(parser.getElementText()); } else if (parser.getLocalName().equals(AlgorithmDetailsBean.PARAMETER)) { AlgorithmDetailsBean.Parameter parameter = new AlgorithmDetailsBean.Parameter(); int count = parser.getAttributeCount(); for (int i = 0; i < count; i++) { if (parser.getAttributeLocalName(i).equals("required")) parameter.setRequired(Boolean.valueOf(parser.getAttributeValue(i))); if (parser.getAttributeLocalName(i).equals("type")) parameter.setType(parser.getAttributeValue(i)); if (parser.getAttributeLocalName(i).equals("name")) parameter.setName(parser.getAttributeValue(i)); if (parser.getAttributeLocalName(i).equals("defaultValue")) parameter.setDefaultValue(parser.getAttributeValue(i)); if (parser.getAttributeLocalName(i).equals("validation")) parameter.setValidation(parser.getAttributeValue(i)); if (parser.getAttributeLocalName(i).equals("validationError")) parameter.setValidationError(parser.getAttributeValue(i)); if (parser.getAttributeLocalName(i).equals("readOnly")) parameter.setReadOnly(Boolean.parseBoolean(parser.getAttributeValue(i))); }//ww w.j a v a 2 s .com parser.nextTag(); if (parser.getLocalName().equals("label")) parameter.setLabel(parser.getElementText()); parser.nextTag(); if (parser.getLocalName().equals("description")) parameter.setDescription(parser.getElementText()); parameters.add(parameter); } else if (parser.getLocalName().equals(AlgorithmDetailsBean.AUTHOR)) { int count = parser.getAttributeCount(); for (int i = 0; i < count; i++) { if (parser.getAttributeLocalName(i).equals("name")) authors.add(parser.getAttributeValue(i)); } } } } } res.setParameters(parameters); res.setAuthors(authors); return res; }
From source file:com.marklogic.contentpump.AggregateXMLReader.java
@Override public boolean nextKeyValue() throws IOException, InterruptedException { if (xmlSR == null) { hasNext = false;//from w w w. j a va 2 s . com return false; } try { while (xmlSR.hasNext()) { int eventType; //getCharacterOffset() returns int; //int will overflows if file is larger than 2GB if (!overflow && xmlSR.getLocation().getCharacterOffset() < -1) { overflow = true; LOG.info("In progress..."); } //do not update pos if offset overflows if (!overflow) { pos = xmlSR.getLocation().getCharacterOffset(); } eventType = xmlSR.next(); switch (eventType) { case XMLStreamConstants.START_ELEMENT: if (startOfRecord) { // this is the start of the root, only copy // namespaces copyNameSpaceDecl(); startOfRecord = false; continue; } processStartElement(); break; case XMLStreamConstants.CHARACTERS: write(StringEscapeUtils.escapeXml(xmlSR.getText())); break; case XMLStreamConstants.CDATA: write("<![CDATA["); write(xmlSR.getText()); write("]]>"); break; case XMLStreamConstants.SPACE: write(xmlSR.getText()); break; case XMLStreamConstants.ENTITY_REFERENCE: write("&"); write(xmlSR.getLocalName()); write(";"); break; case XMLStreamConstants.DTD: write("<!DOCTYPE"); write(xmlSR.getText()); write(">"); break; case XMLStreamConstants.PROCESSING_INSTRUCTION: write("<?"); write(xmlSR.getPIData()); write("?>"); break; case XMLStreamConstants.COMMENT: write("<!--"); write(xmlSR.getText()); write("-->"); break; case XMLStreamConstants.END_ELEMENT: keepGoing = processEndElement(); if (!keepGoing) { keepGoing = true; return true; } break; case XMLStreamConstants.START_DOCUMENT: throw new XMLStreamException("unexpected start of document within record!\n" + "recordName = " + recordName + ", recordNamespace = " + recordNamespace + " at " + xmlSR.getLocation()); case XMLStreamConstants.END_DOCUMENT: if (currentId != null) { throw new XMLStreamException( "end of document before end of current record!\n" + "recordName = " + recordName + ", recordNamespace = " + recordNamespace + " at " + xmlSR.getLocation()); } else { if (compressed) { //this doc is done, refer to the zip for next doc hasNext = false; return false; } else { //get next file from FileIterator if (iterator != null && iterator.hasNext()) { close(); initStreamReader(iterator.next()); continue; } else { hasNext = false; return false; } } } default: throw new XMLStreamException("UNIMPLEMENTED: " + eventType); } } } catch (XMLStreamException e) { LOG.error("Parsing error", e); throw new IOException("Parsing error", e); } return false; }
From source file:edu.harvard.iq.dvn.ingest.statdataio.impl.plugins.ddi.DDIFileReader.java
private void processFileTxt(XMLStreamReader xmlr, SDIOMetadata smd) throws XMLStreamException { for (int event = xmlr.next(); event != XMLStreamConstants.END_DOCUMENT; event = xmlr.next()) { if (event == XMLStreamConstants.START_ELEMENT) { if (xmlr.getLocalName().equals("dimensns")) { processDimensns(xmlr, smd); } else if (xmlr.getLocalName().equals("fileType")) { // ignore. } else { throw new XMLStreamException( "Unsupported DDI Element: codeBook/fileDscr/fileTxt/" + xmlr.getLocalName()); }//from w w w.ja v a 2 s .com } else if (event == XMLStreamConstants.END_ELEMENT) { if (xmlr.getLocalName().equals("fileTxt")) { return; } else if (xmlr.getLocalName().equals("fileType")) { // continue; } else { throw new XMLStreamException( "Mismatched DDI Formatting: </fileTxt> expected, found " + xmlr.getLocalName()); } } } }
From source file:edu.harvard.iq.dvn.ingest.statdataio.impl.plugins.ddi.DDIFileReader.java
private void processDimensns(XMLStreamReader xmlr, SDIOMetadata smd) throws XMLStreamException { for (int event = xmlr.next(); event != XMLStreamConstants.END_DOCUMENT; event = xmlr.next()) { if (event == XMLStreamConstants.START_ELEMENT) { if (xmlr.getLocalName().equals("caseQnty")) { try { setCaseQnty(new Integer(parseText(xmlr))); } catch (NumberFormatException ex) { throw new XMLStreamException( "Invalid case quantity value in codeBook/fileDscr/fileTxt/dimensns: " + parseText(xmlr)); }//from w w w . j a v a2 s .c o m } else if (xmlr.getLocalName().equals("varQnty")) { try { setVarQnty(new Integer(parseText(xmlr))); } catch (NumberFormatException ex) { throw new XMLStreamException( "Invalid variable quantity value in codeBook/fileDscr/fileTxt/dimensns: " + parseText(xmlr)); } } else if (xmlr.getLocalName().equals("recPrCas")) { throw new XMLStreamException( "recPrCas (Records per Case) not supported for this type of data ingest, yet"); } else { throw new XMLStreamException( "Unsupported DDI Element: codeBook/fileDscr/fileTxt/dimensns/" + xmlr.getLocalName()); } } else if (event == XMLStreamConstants.END_ELEMENT) {// </codeBook> if (xmlr.getLocalName().equals("dimensns")) { return; } else { throw new XMLStreamException( "Mismatched DDI Formatting: </dimensns> expected, found " + xmlr.getLocalName()); } } } }
From source file:jp.co.atware.solr.geta.GETAssocComponent.java
/** * GETAssoc?????<code>NamedList</code>??????? * //w w w . j ava 2 s .c om * @param inputStream GETAssoc?? * @return <code>NamedList</code>? * @throws FactoryConfigurationError * @throws IOException */ protected NamedList<Object> convertResult(InputStream inputStream) throws FactoryConfigurationError, IOException { NamedList<Object> result = new NamedList<Object>(); LinkedList<NamedList<Object>> stack = new LinkedList<NamedList<Object>>(); stack.push(result); try { XMLStreamReader xml = XMLInputFactory.newInstance().createXMLStreamReader(inputStream); while (xml.hasNext()) { switch (xml.getEventType()) { case XMLStreamConstants.START_ELEMENT: NamedList<Object> element = new NamedList<Object>(); stack.peek().add(xml.getName().toString(), element); stack.push(element); for (int i = 0; i < xml.getAttributeCount(); i++) { String name = xml.getAttributeName(i).toString(); String value = xml.getAttributeValue(i); ValueOf valueOf = valueTransMap.get(name); if (valueOf != null) { try { element.add(name, valueOf.toValue(value)); } catch (NumberFormatException e) { element.add(name, value); } } else { element.add(name, value); } } break; case XMLStreamConstants.END_ELEMENT: stack.pop(); break; default: break; } xml.next(); } xml.close(); } catch (XMLStreamException e) { throw new IOException(e); } LOG.debug(result.toString()); return result; }