Example usage for org.xml.sax XMLReader parse

List of usage examples for org.xml.sax XMLReader parse

  1. HOME
  2. Java
  3. org.xml
  4. org.xml.sax.*
  5. XMLReader
  6. parse

Introduction

In this page you can find the example usage for org.xml.sax XMLReader parse.

Prototype

public void parse(String systemId) throws IOException, SAXException;

Source Link

Document

Parse an XML document from a system identifier (URI).

Usage

From source file:org.apache.hadoop.hbase.rest.TestTableScan.java

/**
 * An example to scan using listener in unmarshaller for XML.
 * @throws Exception the exception//from   w w  w  . j  a  va 2s  . c o m
 */
@Test
public void testScanUsingListenerUnmarshallerXML() throws Exception {
    StringBuilder builder = new StringBuilder();
    builder.append("/*");
    builder.append("?");
    builder.append(Constants.SCAN_COLUMN + "=" + COLUMN_1);
    builder.append("&");
    builder.append(Constants.SCAN_LIMIT + "=10");
    Response response = client.get("/" + TABLE + builder.toString(), Constants.MIMETYPE_XML);
    assertEquals(200, response.getCode());
    assertEquals(Constants.MIMETYPE_XML, response.getHeader("content-type"));
    JAXBContext context = JAXBContext.newInstance(ClientSideCellSetModel.class, RowModel.class,
            CellModel.class);
    Unmarshaller unmarshaller = context.createUnmarshaller();

    final ClientSideCellSetModel.Listener listener = new ClientSideCellSetModel.Listener() {
        @Override
        public void handleRowModel(ClientSideCellSetModel helper, RowModel row) {
            assertTrue(row.getKey() != null);
            assertTrue(row.getCells().size() > 0);
        }
    };

    // install the callback on all ClientSideCellSetModel instances
    unmarshaller.setListener(new Unmarshaller.Listener() {
        public void beforeUnmarshal(Object target, Object parent) {
            if (target instanceof ClientSideCellSetModel) {
                ((ClientSideCellSetModel) target).setCellSetModelListener(listener);
            }
        }

        public void afterUnmarshal(Object target, Object parent) {
            if (target instanceof ClientSideCellSetModel) {
                ((ClientSideCellSetModel) target).setCellSetModelListener(null);
            }
        }
    });

    // create a new XML parser
    SAXParserFactory factory = SAXParserFactory.newInstance();
    factory.setNamespaceAware(true);
    XMLReader reader = factory.newSAXParser().getXMLReader();
    reader.setContentHandler(unmarshaller.getUnmarshallerHandler());
    assertFalse(ClientSideCellSetModel.listenerInvoked);
    reader.parse(new InputSource(response.getStream()));
    assertTrue(ClientSideCellSetModel.listenerInvoked);

}

From source file:org.apache.jmeter.protocol.http.proxy.DefaultSamplerCreatorClassifier.java

/**
 * Tries parsing to see if content is xml
 * /* ww  w  .  j a  v  a2 s . c  om*/
 * @param postData
 *            String
 * @return boolean
 */
private static final boolean isPotentialXml(String postData) {
    try {
        SAXParserFactory spf = SAXParserFactory.newInstance();
        SAXParser saxParser = spf.newSAXParser();
        XMLReader xmlReader = saxParser.getXMLReader();
        ErrorDetectionHandler detectionHandler = new ErrorDetectionHandler();
        xmlReader.setContentHandler(detectionHandler);
        xmlReader.setErrorHandler(detectionHandler);
        xmlReader.parse(new InputSource(new StringReader(postData)));
        return !detectionHandler.isErrorDetected();
    } catch (ParserConfigurationException e) {
        return false;
    } catch (SAXException e) {
        return false;
    } catch (IOException e) {
        return false;
    }
}

From source file:org.apache.marmotta.ucuenca.wk.provider.gs.GoogleScholarPageProvider.java

@Override
public List<String> parseResponse(String resource, String requestUrl, Model triples, InputStream input,
        String contentType) throws DataRetrievalException {
    log.debug("Request Successful to {0}", requestUrl);
    final GSXMLHandler gsXMLHandler = new GSXMLHandler();
    gsXMLHandler.clearGSresultList();/* w  w  w. j  a  va  2 s . c  om*/
    try {
        XMLReader xr = XMLReaderFactory.createXMLReader("org.ccil.cowan.tagsoup.Parser");
        xr.setContentHandler(gsXMLHandler);
        InputSource gsxml = new InputSource(input);
        gsxml.setEncoding("iso-8859-1");
        xr.parse(gsxml);

        final Set<GSresult> gsresultlist = gsXMLHandler.getGSresultList();
        Gson gson = new Gson();
        JsonArray json = new JsonArray();
        for (GSresult d : gsresultlist) {
            json.add(gson.toJsonTree(d).getAsJsonObject());
        }
        JSONtoRDF parser = new JSONtoRDF(resource, GoogleScholarProvider.MAPPINGSCHEMA, json, triples);
        try {
            parser.parse();
        } catch (Exception e) {
            throw new DataRetrievalException("I/O exception while retrieving resource: " + requestUrl, e);
        }

    } catch (SAXException | IOException e) {
        throw new DataRetrievalException("I/O exception while retrieving resource: " + requestUrl, e);
    }

    //       try {
    //          List<String> candidates = new ArrayList<String>();
    //          ValueFactory factory = ValueFactoryImpl.getInstance();
    //          final Document doc = new SAXBuilder(XMLReaders.NONVALIDATING).build(input);
    //          for(Element element: queryElements(doc, "/result/hits/hit/info/url")) {
    //             String candidate = element.getText();
    //             triples.add(factory.createStatement(factory.createURI( resource ), FOAF.member, factory.createURI( candidate ) ));
    //             candidates.add(candidate);
    //          }
    //          ClientConfiguration conf = new ClientConfiguration();
    //           LDClient ldClient = new LDClient(conf);
    //           if(!candidates.isEmpty()) {
    //              Model candidateModel = null;
    //             for(String author: candidates) {
    //                ClientResponse response = ldClient.retrieveResource(author);
    //                 Model authorModel = response.getData();
    //                 if(candidateModel == null) {
    //                    candidateModel = authorModel;
    //                 } else {
    //                    candidateModel.addAll(authorModel);
    //                 }
    //             }
    //             triples.addAll(candidateModel);
    //           }
    //       }catch (IOException e) {
    //            throw new DataRetrievalException("I/O error while parsing HTML response", e);
    //        }catch (JDOMException e) {
    //            throw new DataRetrievalException("could not parse XML response. It is not in proper XML format", e);
    //        }
    return Collections.emptyList();
}

From source file:org.apache.marmotta.ucuenca.wk.provider.gs.GoogleScholarProvider.java

@Override
public List<String> parseResponse(String resource, String requestUrl, Model triples, InputStream input,
        String contentType) throws DataRetrievalException {
    log.debug("Request Successful to {0}", requestUrl);
    final GSXMLHandler gsXMLHandler = new GSXMLHandler();
    gsXMLHandler.clearGSresultList();//from w  w w  .  j a  va 2  s  . c o m
    try {
        XMLReader xr = XMLReaderFactory.createXMLReader("org.ccil.cowan.tagsoup.Parser");
        xr.setContentHandler(gsXMLHandler);
        InputSource gsxml = new InputSource(input);
        gsxml.setEncoding("iso-8859-1");
        xr.parse(gsxml);

        final Set<GSresult> gsresultlist = gsXMLHandler.getGSresultList();
        Gson gson = new Gson();
        JsonArray json = new JsonArray();
        for (GSresult d : gsresultlist) {
            json.add(gson.toJsonTree(d).getAsJsonObject());
        }
        JSONtoRDF parser = new JSONtoRDF(resource, MAPPINGSCHEMA, json, triples);
        try {
            parser.parse();
        } catch (Exception e) {
            throw new DataRetrievalException("I/O exception while retrieving resource: " + requestUrl, e);
        }
        int numPages = (int) ((double) (gsXMLHandler.getNumResults() / 10)) + 1;
        int pagesLoaded = 1;
        Model model = null;
        while (pagesLoaded < numPages) {

            String pagenumquery = Integer.toString(pagesLoaded * 10);
            String moreDataUrl = String.format(API, pagenumquery, stringSearch, authorSearch, advancedSearch);
            ClientConfiguration conf = new ClientConfiguration();
            LDClient ldClient = new LDClient(conf);
            ClientResponse response = ldClient.retrieveResource(moreDataUrl);
            Model pageModel = response.getData();
            if (model == null) {
                model = pageModel;
            } else {
                model.addAll(pageModel);
            }
            pagesLoaded++;
        }
        triples.addAll(model);

    } catch (SAXException | IOException e) {
        throw new DataRetrievalException("I/O exception while retrieving resource: " + requestUrl, e);
    }

    //       try {
    //          List<String> candidates = new ArrayList<String>();
    //          ValueFactory factory = ValueFactoryImpl.getInstance();
    //          final Document doc = new SAXBuilder(XMLReaders.NONVALIDATING).build(input);
    //          for(Element element: queryElements(doc, "/result/hits/hit/info/url")) {
    //             String candidate = element.getText();
    //             triples.add(factory.createStatement(factory.createURI( resource ), FOAF.member, factory.createURI( candidate ) ));
    //             candidates.add(candidate);
    //          }
    //          ClientConfiguration conf = new ClientConfiguration();
    //           LDClient ldClient = new LDClient(conf);
    //           if(!candidates.isEmpty()) {
    //              Model candidateModel = null;
    //             for(String author: candidates) {
    //                ClientResponse response = ldClient.retrieveResource(author);
    //                 Model authorModel = response.getData();
    //                 if(candidateModel == null) {
    //                    candidateModel = authorModel;
    //                 } else {
    //                    candidateModel.addAll(authorModel);
    //                 }
    //             }
    //             triples.addAll(candidateModel);
    //           }
    //       }catch (IOException e) {
    //            throw new DataRetrievalException("I/O error while parsing HTML response", e);
    //        }catch (JDOMException e) {
    //            throw new DataRetrievalException("could not parse XML response. It is not in proper XML format", e);
    //        }
    return Collections.emptyList();
}

From source file:org.apache.maven.plugin.cxx.utils.svn.SvnService.java

public static SvnInfo getSvnInfo(File basedir, Credential cred, String uri, Log log, boolean noParsingFailure)
        throws MojoExecutionException {
    ByteArrayOutputStream out = new ByteArrayOutputStream();

    execSvnCommand(basedir, cred, new String[] { "info", uri, "--xml" }, out, log);

    SvnInfo svnInfo = new SvnInfo();
    try {//from   ww w  . java  2  s  . c  o  m
        SAXParserFactory sfactory = SAXParserFactory.newInstance();
        SAXParser parser = sfactory.newSAXParser();
        XMLReader xmlparser = parser.getXMLReader();
        xmlparser.setContentHandler(svnInfo);
        xmlparser.parse(new InputSource(new ByteArrayInputStream(out.toByteArray())));
    } catch (Exception e) {
        if (noParsingFailure) {
            log.error("svn info xml parsing failed : " + e);
        } else {
            throw new MojoExecutionException("svn info xml parsing failed.", e);
        }
    }
    return svnInfo;
}

From source file:org.apache.nifi.processors.poi.ConvertExcelToCSVProcessor.java

/**
 * Handles an individual Excel sheet from the entire Excel document. Each sheet will result in an individual flowfile.
 *
 * @param session//w w w.j  a  va 2  s . c  o  m
 *  The NiFi ProcessSession instance for the current invocation.
 */
private void handleExcelSheet(ProcessSession session, FlowFile originalParentFF,
        final InputStream sheetInputStream, ExcelSheetReadConfig readConfig, CSVFormat csvFormat)
        throws IOException {

    FlowFile ff = session.create();
    try {
        final DataFormatter formatter = new DataFormatter();
        final InputSource sheetSource = new InputSource(sheetInputStream);

        final SheetToCSV sheetHandler = new SheetToCSV(readConfig, csvFormat);

        final XMLReader parser = SAXHelper.newXMLReader();

        //If Value Formatting is set to false then don't pass in the styles table.
        // This will cause the XSSF Handler to return the raw value instead of the formatted one.
        final StylesTable sst = readConfig.getFormatValues() ? readConfig.getStyles() : null;

        final XSSFSheetXMLHandler handler = new XSSFSheetXMLHandler(sst, null,
                readConfig.getSharedStringsTable(), sheetHandler, formatter, false);

        parser.setContentHandler(handler);

        ff = session.write(ff, new OutputStreamCallback() {
            @Override
            public void process(OutputStream out) throws IOException {
                PrintStream outPrint = new PrintStream(out);
                sheetHandler.setOutput(outPrint);

                try {
                    parser.parse(sheetSource);

                    sheetInputStream.close();

                    sheetHandler.close();
                    outPrint.close();
                } catch (SAXException se) {
                    getLogger().error("Error occurred while processing Excel sheet {}",
                            new Object[] { readConfig.getSheetName() }, se);
                }
            }
        });

        ff = session.putAttribute(ff, SHEET_NAME, readConfig.getSheetName());
        ff = session.putAttribute(ff, ROW_NUM, new Long(sheetHandler.getRowCount()).toString());

        if (StringUtils.isNotEmpty(originalParentFF.getAttribute(CoreAttributes.FILENAME.key()))) {
            ff = session.putAttribute(ff, SOURCE_FILE_NAME,
                    originalParentFF.getAttribute(CoreAttributes.FILENAME.key()));
        } else {
            ff = session.putAttribute(ff, SOURCE_FILE_NAME, UNKNOWN_SHEET_NAME);
        }

        //Update the CoreAttributes.FILENAME to have the .csv extension now. Also update MIME.TYPE
        ff = session.putAttribute(ff, CoreAttributes.FILENAME.key(),
                updateFilenameToCSVExtension(ff.getAttribute(CoreAttributes.UUID.key()),
                        ff.getAttribute(CoreAttributes.FILENAME.key()), readConfig.getSheetName()));
        ff = session.putAttribute(ff, CoreAttributes.MIME_TYPE.key(), CSV_MIME_TYPE);

        session.transfer(ff, SUCCESS);

    } catch (SAXException | ParserConfigurationException saxE) {
        getLogger().error("Failed to create instance of Parser.", saxE);
        ff = session.putAttribute(ff, ConvertExcelToCSVProcessor.class.getName() + ".error", saxE.getMessage());
        session.transfer(ff, FAILURE);
    } finally {
        sheetInputStream.close();
    }
}

From source file:org.apache.nifi.processors.standard.SplitXml.java

@Override
public void onTrigger(final ProcessContext context, final ProcessSession session) {
    final FlowFile original = session.get();
    if (original == null) {
        return;// www .ja  v a  2  s.com
    }

    final int depth = context.getProperty(SPLIT_DEPTH).asInteger();
    final ComponentLog logger = getLogger();

    final List<FlowFile> splits = new ArrayList<>();
    final String fragmentIdentifier = UUID.randomUUID().toString();
    final AtomicInteger numberOfRecords = new AtomicInteger(0);
    final XmlSplitterSaxParser parser = new XmlSplitterSaxParser(xmlTree -> {
        FlowFile split = session.create(original);
        split = session.write(split, out -> out.write(xmlTree.getBytes("UTF-8")));
        split = session.putAttribute(split, FRAGMENT_ID.key(), fragmentIdentifier);
        split = session.putAttribute(split, FRAGMENT_INDEX.key(),
                Integer.toString(numberOfRecords.getAndIncrement()));
        split = session.putAttribute(split, SEGMENT_ORIGINAL_FILENAME.key(),
                split.getAttribute(CoreAttributes.FILENAME.key()));
        splits.add(split);
    }, depth);

    final AtomicBoolean failed = new AtomicBoolean(false);
    session.read(original, rawIn -> {
        try (final InputStream in = new BufferedInputStream(rawIn)) {
            SAXParser saxParser = null;
            try {
                saxParser = saxParserFactory.newSAXParser();
                final XMLReader reader = saxParser.getXMLReader();
                reader.setContentHandler(parser);
                reader.parse(new InputSource(in));
            } catch (final ParserConfigurationException | SAXException e) {
                logger.error("Unable to parse {} due to {}", new Object[] { original, e });
                failed.set(true);
            }
        }
    });

    if (failed.get()) {
        session.transfer(original, REL_FAILURE);
        session.remove(splits);
    } else {
        splits.forEach((split) -> {
            split = session.putAttribute(split, FRAGMENT_COUNT.key(), Integer.toString(numberOfRecords.get()));
            session.transfer(split, REL_SPLIT);
        });

        final FlowFile originalToTransfer = copyAttributesToOriginal(session, original, fragmentIdentifier,
                numberOfRecords.get());
        session.transfer(originalToTransfer, REL_ORIGINAL);
        logger.info("Split {} into {} FlowFiles", new Object[] { originalToTransfer, splits.size() });
    }
}

From source file:org.apache.nutch.tools.DmozParser.java

/**
 * Iterate through all the items in this structured DMOZ file.
 * Add each URL to the web db./*from  w ww  . j  av a2 s .  c o  m*/
 */
public void parseDmozFile(File dmozFile, int subsetDenom, boolean includeAdult, int skew, Pattern topicPattern)

        throws IOException, SAXException, ParserConfigurationException {

    SAXParserFactory parserFactory = SAXParserFactory.newInstance();
    SAXParser parser = parserFactory.newSAXParser();
    XMLReader reader = parser.getXMLReader();

    // Create our own processor to receive SAX events
    RDFProcessor rp = new RDFProcessor(reader, subsetDenom, includeAdult, skew, topicPattern);
    reader.setContentHandler(rp);
    reader.setErrorHandler(rp);
    LOG.info("skew = " + rp.hashSkew);

    //
    // Open filtered text stream.  The TextFilter makes sure that
    // only appropriate XML-approved Text characters are received.
    // Any non-conforming characters are silently skipped.
    //
    XMLCharFilter in = new XMLCharFilter(new BufferedReader(
            new InputStreamReader(new BufferedInputStream(new FileInputStream(dmozFile)), "UTF-8")));
    try {
        InputSource is = new InputSource(in);
        reader.parse(is);
    } catch (Exception e) {
        if (LOG.isFatalEnabled()) {
            LOG.fatal(e.toString());
            e.printStackTrace(LogUtil.getFatalStream(LOG));
        }
        System.exit(0);
    } finally {
        in.close();
    }
}

From source file:org.apache.ode.bpel.compiler.bom.BpelObjectFactory.java

/**
 * Parse a BPEL process found at the input source.
 * @param isrc input source.//from w  w  w  .j a v  a 2s. co  m
 * @return
 * @throws SAXException
 */
public Process parse(InputSource isrc, URI systemURI) throws IOException, SAXException {
    XMLReader _xr = XMLParserUtils.getXMLReader();
    LocalEntityResolver resolver = new LocalEntityResolver();
    resolver.register(Bpel11QNames.NS_BPEL4WS_2003_03, getClass().getResource("/bpel4ws_1_1-fivesight.xsd"));
    resolver.register(Bpel20QNames.NS_WSBPEL2_0, getClass().getResource("/wsbpel_main-draft-Apr-29-2006.xsd"));
    resolver.register(Bpel20QNames.NS_WSBPEL2_0_FINAL_ABSTRACT,
            getClass().getResource("/ws-bpel_abstract_common_base.xsd"));
    resolver.register(Bpel20QNames.NS_WSBPEL2_0_FINAL_EXEC, getClass().getResource("/ws-bpel_executable.xsd"));
    resolver.register(Bpel20QNames.NS_WSBPEL2_0_FINAL_PLINK, getClass().getResource("/ws-bpel_plnktype.xsd"));
    resolver.register(Bpel20QNames.NS_WSBPEL2_0_FINAL_SERVREF,
            getClass().getResource("/ws-bpel_serviceref.xsd"));
    resolver.register(Bpel20QNames.NS_WSBPEL2_0_FINAL_VARPROP, getClass().getResource("/ws-bpel_varprop.xsd"));
    resolver.register(XML, getClass().getResource("/xml.xsd"));
    resolver.register(WSDL, getClass().getResource("/wsdl.xsd"));
    resolver.register(Bpel20QNames.NS_WSBPEL_PARTNERLINK_2004_03,
            getClass().getResource("/wsbpel_plinkType-draft-Apr-29-2006.xsd"));
    _xr.setEntityResolver(resolver);
    Document doc = DOMUtils.newDocument();
    _xr.setContentHandler(new DOMBuilderContentHandler(doc));
    _xr.setFeature("http://xml.org/sax/features/namespaces", true);
    _xr.setFeature("http://xml.org/sax/features/namespace-prefixes", true);

    _xr.setFeature("http://xml.org/sax/features/validation", true);
    XMLParserUtils.addExternalSchemaURL(_xr, Bpel11QNames.NS_BPEL4WS_2003_03, Bpel11QNames.NS_BPEL4WS_2003_03);
    XMLParserUtils.addExternalSchemaURL(_xr, Bpel20QNames.NS_WSBPEL2_0, Bpel20QNames.NS_WSBPEL2_0);
    XMLParserUtils.addExternalSchemaURL(_xr, Bpel20QNames.NS_WSBPEL2_0_FINAL_EXEC,
            Bpel20QNames.NS_WSBPEL2_0_FINAL_EXEC);
    XMLParserUtils.addExternalSchemaURL(_xr, Bpel20QNames.NS_WSBPEL2_0_FINAL_ABSTRACT,
            Bpel20QNames.NS_WSBPEL2_0_FINAL_ABSTRACT);

    boolean strict = Boolean
            .parseBoolean(System.getProperty("org.apache.ode.compiler.failOnValidationErrors", "false"));
    BOMSAXErrorHandler errorHandler = new BOMSAXErrorHandler(strict);
    _xr.setErrorHandler(errorHandler);
    _xr.parse(isrc);
    if (strict) {
        if (!errorHandler.wasOK()) {
            throw new SAXException("Validation errors during parsing");
        }
    } else {
        if (!errorHandler.wasOK()) {
            __log.warn(
                    "Validation errors during parsing, continuing due to -Dorg.apache.ode.compiler.failOnValidationErrors=false switch");
        }
    }
    return (Process) createBpelObject(doc.getDocumentElement(), systemURI);
}

From source file:org.apache.ojb.broker.metadata.RepositoryPersistor.java

/**
 * Read metadata by populating an instance of the target class
 * using SAXParser.//  w  w w  .j  a  v  a2s .  com
 */
private Object readMetadataFromXML(InputSource source, Class target)
        throws MalformedURLException, ParserConfigurationException, SAXException, IOException {
    // TODO: make this configurable
    boolean validate = false;

    // get a xml reader instance:
    SAXParserFactory factory = SAXParserFactory.newInstance();
    log.info("RepositoryPersistor using SAXParserFactory : " + factory.getClass().getName());
    if (validate) {
        factory.setValidating(true);
    }
    SAXParser p = factory.newSAXParser();
    XMLReader reader = p.getXMLReader();
    if (validate) {
        reader.setErrorHandler(new OJBErrorHandler());
    }

    Object result;
    if (DescriptorRepository.class.equals(target)) {
        // create an empty repository:
        DescriptorRepository repository = new DescriptorRepository();
        // create handler for building the repository structure
        ContentHandler handler = new RepositoryXmlHandler(repository);
        // tell parser to use our handler:
        reader.setContentHandler(handler);
        reader.parse(source);
        result = repository;
    } else if (ConnectionRepository.class.equals(target)) {
        // create an empty repository:
        ConnectionRepository repository = new ConnectionRepository();
        // create handler for building the repository structure
        ContentHandler handler = new ConnectionDescriptorXmlHandler(repository);
        // tell parser to use our handler:
        reader.setContentHandler(handler);
        reader.parse(source);
        //LoggerFactory.getBootLogger().info("loading XML took " + (stop - start) + " msecs");
        result = repository;
    } else
        throw new MetadataException(
                "Could not build a repository instance for '" + target + "', using source " + source);
    return result;
}