List of usage examples for javax.xml.parsers SAXParserFactory newSAXParser
public abstract SAXParser newSAXParser() throws ParserConfigurationException, SAXException;
From source file:edu.psu.citeseerx.updates.external.metadata.ACMMetadataUpdater.java
public void updateACM() { try {//from www .ja v a 2 s .c o m // Get the SAX factory. SAXParserFactory factory = SAXParserFactory.newInstance(); // Neither we want validation nor namespaces. factory.setNamespaceAware(false); factory.setValidating(true); SAXParser parser = factory.newSAXParser(); /*xmlReader.setFeature( "http://apache.org/xml/features/nonvalidating/load-external-dtd", false);*/ parser.parse(ACMDataFile, acmHandler); } catch (ParserConfigurationException e) { logger.error("The underlaying parser doesn't support the " + "requested feature", e); } catch (SAXException e) { logger.error("Error", e); } catch (IOException e) { logger.error("A parsing error has occurred: " + ACMDataFile, e); } }
From source file:de.tudarmstadt.ukp.dkpro.core.io.ancora.AncoraReader.java
@Override public void getNext(JCas aJCas) throws IOException, CollectionException { Resource res = nextFile();/*from w w w . j a v a 2 s . c o m*/ initCas(aJCas, res); // Set up language if (getLanguage() != null) { aJCas.setDocumentLanguage(getLanguage()); } // Configure mapping only now, because now the language is set in the CAS try { posMappingProvider.configure(aJCas.getCas()); } catch (AnalysisEngineProcessException e1) { throw new IOException(e1); } InputStream is = null; try { is = CompressionUtils.getInputStream(res.getLocation(), res.getInputStream()); // Create handler AncoraHandler handler = new AncoraHandler(); handler.setJCas(aJCas); handler.setLogger(getLogger()); // Parse XML SAXParserFactory pf = SAXParserFactory.newInstance(); SAXParser parser = pf.newSAXParser(); InputSource source = new InputSource(is); source.setPublicId(res.getLocation()); source.setSystemId(res.getLocation()); parser.parse(source, handler); } catch (ParserConfigurationException | SAXException e) { throw new IOException(e); } finally { closeQuietly(is); } if (dropSentencesMissingPosTags) { List<FeatureStructure> toRemove = new ArrayList<>(); // Remove sentences without pos TAGs for (Sentence s : select(aJCas, Sentence.class)) { boolean remove = false; for (Token t : selectCovered(Token.class, s)) { if (t.getPos() == null) { toRemove.add(s); remove = true; break; } } if (remove) { for (Token t : selectCovered(Token.class, s)) { toRemove.add(t); if (t.getLemma() != null) { toRemove.add(t.getLemma()); } if (t.getPos() != null) { toRemove.add(t.getPos()); } } } } for (FeatureStructure fs : toRemove) { aJCas.getCas().removeFsFromIndexes(fs); } // Remove tokens without pos tags that are located *BETWEEN* sentences! toRemove.clear(); for (Token t : select(aJCas, Token.class)) { if (t.getPos() == null) { toRemove.add(t); if (t.getLemma() != null) { toRemove.add(t.getLemma()); } if (t.getPos() != null) { toRemove.add(t.getPos()); } } } for (FeatureStructure fs : toRemove) { aJCas.getCas().removeFsFromIndexes(fs); } } }
From source file:eu.scape_project.planning.xml.PlanMigrator.java
/** * Detect the version of the given XML representation of plans. If the * version of the XML representation is not up to date, necessary * transformations are applied./*from w w w . j av a 2 s .c o m*/ * * @param importData * @return null if the transformation fails, otherwise an up to date XML * representation * @throws IOException * if parsing the XML representation fails * @throws SAXException * if parsing the XML representation fails */ public String getCurrentVersionData(final InputStream in, final String tempPath, final List<String> appliedTransformations) throws PlatoException { String originalFile = tempPath + "_original.xml"; try { FileUtils.writeToFile(in, new FileOutputStream(originalFile)); /** check for the version of the file **/ // The version of the read xml file is unknown, so it is not possible to // validate it // moreover, in old plans the version attribute was on different // nodes(project, projects), // with a different name (fileVersion) // to be backwards compatible we create rules for all these attributes fileVersion = "xxx"; SAXParserFactory factory = SAXParserFactory.newInstance(); factory.setNamespaceAware(false); Digester d = new Digester(factory.newSAXParser()); d.setValidating(false); // StrictErrorHandler errorHandler = new StrictErrorHandler(); // d.setErrorHandler(errorHandler); d.push(this); // to read the version we have to support all versions: d.addSetProperties("*/projects", "version", "fileVersion"); // manually migrated projects may have the file version in the node // projects/project d.addSetProperties("*/projects/project", "version", "fileVersion"); // pre V1.3 version info was stored in the project node d.addSetProperties("*/project", "version", "fileVersion"); // since V1.9 the root node is plans: d.addSetProperties("plans", "version", "fileVersion"); InputStream inV = new FileInputStream(originalFile); d.parse(inV); inV.close(); /** this could be more sophisticated, but for now this is enough **/ String version = "1.0"; if (fileVersion != null) { version = fileVersion; } String fileTo = originalFile; String fileFrom = originalFile; boolean success = true; if ("xxx".equals(version)) { fileFrom = fileTo; fileTo = fileFrom + "_V1.3.xml"; /** this is an old export file, transform it to the 1.3 schema **/ success = transformXmlData(fileFrom, fileTo, "data/xslt/Vxxx-to-V1.3.xsl"); appliedTransformations.add("Vxxx-to-V1.3.xsl"); version = "1.3"; } if (success && "1.3".equals(version)) { fileFrom = fileTo; fileTo = fileFrom + "_V1.9.xml"; success = transformXmlData(fileFrom, fileTo, "data/xslt/V1.3-to-V1.9.xsl"); appliedTransformations.add("V1.3-to-V1.9.xsl"); version = "1.9"; } // with release of Plato 2.0 and its schema ProjectExporter creates // documents with version 2.0 if (success && "1.9".equals(version)) { version = "2.0"; } if (success && "2.0".equals(version)) { // transform the document to version 2.1 fileFrom = fileTo; fileTo = fileFrom + "_V2.1.xml"; success = transformXmlData(fileFrom, fileTo, "data/xslt/V2.0-to-V2.1.xsl"); appliedTransformations.add("V2.0-to-V2.1.xsl"); version = "2.1"; } if (success && "2.1".equals(version)) { // transform the document to version 2.1.2 fileFrom = fileTo; fileTo = fileFrom + "_V2.1.2.xml"; success = transformXmlData(fileFrom, fileTo, "data/xslt/V2.1-to-V2.1.2.xsl"); appliedTransformations.add("V2.1-to-V2.1.2.xsl"); version = "2.1.2"; } if (success && "2.1.1".equals(version)) { // transform the document to version 2.1.2 fileFrom = fileTo; fileTo = fileFrom + "_V2.1.2.xml"; success = transformXmlData(fileFrom, fileTo, "data/xslt/V2.1.1-to-V2.1.2.xsl"); appliedTransformations.add("V2.1.1-to-V2.1.2.xsl"); version = "2.1.2"; } if (success && "2.1.2".equals(version)) { // transform the document to version 3.0.0 fileFrom = fileTo; fileTo = fileFrom + "_V3.0.0.xml"; success = transformXmlData(fileFrom, fileTo, "data/xslt/V2.1.2-to-V3.0.0.xsl"); appliedTransformations.add("V2.1.2-to-V3.0.0.xsl"); version = "3.0.0"; } if (success && "3.0.0".equals(version)) { // transform the document to version 3.0.1 fileFrom = fileTo; fileTo = fileFrom + "_V3.0.1.xml"; success = transformXmlData(fileFrom, fileTo, "data/xslt/V3.0.0-to-V3.0.1.xsl"); appliedTransformations.add("V3.0.0-to-V3.0.1.xsl"); version = "3.0.1"; } if (success && "3.0.1".equals(version)) { // transform the document to version 3.9.0 fileFrom = fileTo; fileTo = fileFrom + "_V3.9.0.xml"; success = transformXmlData(fileFrom, fileTo, "data/xslt/V3.0.1-to-V3.9.0.xsl"); appliedTransformations.add("V3.0.1-to-V3.9.0.xsl"); version = "3.9.0"; } if (success && "3.9.0".equals(version)) { // transform the document to version 3.9.9 fileFrom = fileTo; fileTo = fileFrom + "_V3.9.9.xml"; success = transformXmlData(fileFrom, fileTo, "data/xslt/V3.9.0-to-V3.9.9.xsl"); appliedTransformations.add("V3.9.0-to-V3.9.9.xsl"); version = "3.9.9"; } if (success && "3.9.9".equals(version)) { // transform the document to version 4.0.0 fileFrom = fileTo; fileTo = fileFrom + "_V4.0.1.xml"; success = transformXmlData(fileFrom, fileTo, "data/xslt/V3.9.9-to-V4.0.1.xsl"); appliedTransformations.add("V3.9.9-to-V4.0.1.xsl"); version = "4.0.1"; } if (success && "4.0.1".equals(version)) { // transform the document to version 4.0.0 fileFrom = fileTo; fileTo = fileFrom + "_V4.0.2.xml"; success = transformXmlData(fileFrom, fileTo, "data/xslt/V4.0.1-to-V4.0.2.xsl"); appliedTransformations.add("V4.0.1-to-V4.0.2.xsl"); version = "4.0.2"; } if (success) { return fileTo; } else { return null; } } catch (Exception e) { throw new PlatoException("Failed to update plan to current version.", e); } }
From source file:com.trailmagic.image.util.ImagesParserImpl.java
@Transactional(propagation = Propagation.REQUIRED, readOnly = false) public void parseFile(File metadataFile) { try {//from w ww .ja va 2s .c o m SAXParserFactory factory = SAXParserFactory.newInstance(); factory.setValidating(true); SAXParser parser = factory.newSAXParser(); s_logger.info("Parsing " + metadataFile.getPath() + "..."); parser.parse(metadataFile, this); s_logger.info("done"); } catch (Throwable t) { t.printStackTrace(); System.exit(1); } }
From source file:com.trailmagic.image.util.ImagesParserImpl.java
@Transactional(propagation = Propagation.REQUIRED, readOnly = false) public void parse(InputStream inputStream) { try {//ww w .j av a 2 s . c o m SAXParserFactory factory = SAXParserFactory.newInstance(); factory.setValidating(true); SAXParser parser = factory.newSAXParser(); XMLReader reader = parser.getXMLReader(); // CatalogManager cm = new CatalogManager(); // Catalog catalog = cm.getCatalog(); // catalog.parseCatalog(getClass().getClassLoader().getResource("CatalogManager.properties")); // reader.setEntityResolver(new CatalogResolver(cm)); s_logger.info("Parsing input stream..."); parser.parse(inputStream, this); s_logger.info("done"); } catch (Throwable t) { t.printStackTrace(); System.exit(1); } }
From source file:com.determinato.feeddroid.parser.RssParser.java
/** * Persists RSS item to the database./*www .ja va 2 s . c o m*/ * @param id item ID * @param folderId ID of containing folder * @param rssurl URL of RSS feed * @return long containing ID of inserted item * @throws Exception */ public long syncDb(long id, long folderId, String rssurl) throws Exception { mId = id; mFolderId = folderId; mRssUrl = rssurl; SAXParserFactory factory = SAXParserFactory.newInstance(); SAXParser parser = factory.newSAXParser(); XMLReader reader = parser.getXMLReader(); reader.setContentHandler(this); reader.setErrorHandler(this); URL url = new URL(mRssUrl); URLConnection c = url.openConnection(); // TODO: Is this a known user agent, or do I need to come up with my own? c.setRequestProperty("User-Agent", "Android/m3-rc37a"); try { BufferedReader bufReader = new BufferedReader(new InputStreamReader(c.getInputStream()), 65535); reader.parse(new InputSource(bufReader)); } catch (NullPointerException e) { Log.e(TAG, Log.getStackTraceString(e)); Log.e(TAG, "Failed to load URL" + url.toString()); } return mId; }
From source file:com.esri.gpt.server.csw.client.CswCatalog.java
/** * Execute GetCapabilities using SAX objects. Send GetCapabilities request, * receive the response from a service, and parse the response to get URLs for * "GetRecords" and "GetRecordsById"./* www .j a v a2 s. co m*/ * * @return the csw catalog capabilities * @throws SAXException the sAX exception * @throws IOException Signals that an I/O exception has occurred. * @throws ParserConfigurationException the parser configuration exception * @return Csw Capabilities object */ private CswCatalogCapabilities executeGetCapabilitiesWithSAX() throws SAXException, IOException, ParserConfigurationException { CswCatalogCapabilities capabilities = new CswCatalogCapabilities(); CswClient client = new CswClient(); client.setConnectTimeout(this.getConnectionTimeoutMs()); client.setReadTimeout(this.getResponseTimeoutMs()); client.setBatchHttpClient(getBatchHttpClient()); // Execute submission and parsing into response element InputStream responseStream = client.submitHttpRequest("GET", url, ""); SAXParserFactory factory = SAXParserFactory.newInstance(); factory.setNamespaceAware(true); CapabilitiesParse cParse = new CapabilitiesParse(capabilities); factory.newSAXParser().parse(new InputSource(responseStream), cParse); this.capabilities = capabilities; Utils.close(responseStream); return capabilities; }
From source file:org.semantictools.frame.api.OntologyManager.java
private void loadXsd(File file) throws SchemaParseException { try {// w ww.j a va2 s. c o m SAXParserFactory factory = SAXParserFactory.newInstance(); SAXParser parser = factory.newSAXParser(); XMLReader reader = parser.getXMLReader(); reader.setFeature("http://xml.org/sax/features/namespaces", true); NamespaceReader handler = new NamespaceReader(); reader.setContentHandler(handler); parser.parse(file, handler); String namespace = handler.getTargetNamespace(); if (namespace == null) { logger.warn("Ignoring schema since targetNamespace is not declared: " + file.getPath()); } else { OntologyEntity entity = new OntologyEntity(XML_FORMAT, file, namespace); uri2OntologyEntity.put(namespace, entity); } } catch (Throwable oops) { throw new SchemaParseException(oops); } }
From source file:architecture.common.util.L10NUtils.java
private void loadProps(String resource, boolean breakOnError) throws IOException { HashSet<URL> hashset = new HashSet<URL>(); if (log.isDebugEnabled()) { log.debug((new StringBuilder()).append("Searching ").append(resource).toString()); }//from ww w .j a v a2s. c om Enumeration<URL> urls = Thread.currentThread().getContextClassLoader().getResources(resource); if (urls != null) { URL url; for (; urls.hasMoreElements(); hashset.add(url)) { url = urls.nextElement(); if (log.isDebugEnabled()) log.debug((new StringBuilder()).append("Adding ").append(url).toString()); } } for (URL url : hashset) { if (log.isDebugEnabled()) log.debug((new StringBuilder()).append("Loading from ").append(url).toString()); InputStream is = null; try { is = url.openStream(); InputSource input = new InputSource(is); SAXParserFactory factory = SAXParserFactory.newInstance(); factory.setNamespaceAware(true); XMLReader xmlreader = factory.newSAXParser().getXMLReader(); I18nParsingHandler handler = new I18nParsingHandler(); xmlreader.setContentHandler(handler); xmlreader.setDTDHandler(handler); xmlreader.setEntityResolver(handler); xmlreader.setErrorHandler(handler); xmlreader.parse(input); localizers.addAll(handler.localizers); } catch (IOException e) { if (log.isDebugEnabled()) log.debug((new StringBuilder()).append("Skipping ").append(url).toString()); if (breakOnError) throw e; } catch (Exception e) { log.error(e); } finally { if (is != null) IOUtils.closeQuietly(is); } } }