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.betaconceptframework.astroboa.test.util.JAXBValidationUtils.java

public void validateUsingSAX(InputStream is) throws Exception {
    SAXParser saxParser = parserFactory.newSAXParser();

    XMLReader xmlReader = saxParser.getXMLReader();
    xmlReader.setEntityResolver(entityResolver);
    xmlReader.setErrorHandler(errorHandler);

    errorHandler.setIgnoreInvalidElementSequence(false);

    is = encodeURLsFoundInXML(is);//from  w ww .ja  v a 2s.  c  o m

    xmlReader.parse(new InputSource(is));
}

From source file:org.carrot2.source.pubmed.PubMedDocumentSource.java

/**
 * Gets PubMed entry ids matching the query.
 *//*from  w w  w.  j av a 2 s.c o m*/
private List<String> getPubMedIds(final String query, final int requestedResults) throws Exception {
    final XMLReader reader = SAXParserFactory.newInstance().newSAXParser().getXMLReader();
    reader.setFeature("http://xml.org/sax/features/validation", false);
    reader.setFeature("http://xml.org/sax/features/namespaces", true);

    PubMedSearchHandler searchHandler = new PubMedSearchHandler();
    reader.setContentHandler(searchHandler);

    final String url = E_SEARCH_URL + "?db=pubmed&usehistory=n&term="
            + StringUtils.urlEncodeWrapException(query, "UTF-8") + "&retmax="
            + Integer.toString(requestedResults);

    final HttpUtils.Response response = HttpUtils.doGET(url, null, null);

    // Get document IDs
    if (response.status == HttpStatus.SC_OK) {
        reader.parse(new InputSource(response.getPayloadAsStream()));
    } else {
        throw new IOException("PubMed returned HTTP Error: " + response.status + ", HTTP payload: "
                + new String(response.payload, "iso8859-1"));
    }

    return searchHandler.getPubMedPrimaryIds();
}

From source file:org.carrot2.source.pubmed.PubMedDocumentSource.java

/**
 * Gets PubMed abstracts corresponding to the provided ids.
 *///from  www . ja v  a 2  s  . co m
private SearchEngineResponse getPubMedAbstracts(List<String> ids) throws Exception {
    if (ids.isEmpty()) {
        return new SearchEngineResponse();
    }

    final XMLReader reader = SAXParserFactory.newInstance().newSAXParser().getXMLReader();
    reader.setFeature("http://xml.org/sax/features/validation", false);
    reader.setFeature("http://xml.org/sax/features/namespaces", true);

    final PubMedFetchHandler fetchHandler = new PubMedFetchHandler();
    reader.setContentHandler(fetchHandler);

    final String url = E_FETCH_URL + "?db=pubmed&retmode=xml&rettype=abstract&id=" + getIdsString(ids);

    final HttpUtils.Response response = HttpUtils.doGET(url, null, null);

    // Get document contents
    // No URL logging here, as the url can get really long
    if (response.status == HttpStatus.SC_OK) {
        reader.parse(new InputSource(response.getPayloadAsStream()));
    } else {
        throw new IOException("PubMed returned HTTP Error: " + response.status + ", HTTP payload: "
                + new String(response.payload, "iso8859-1"));
    }

    return fetchHandler.getResponse();
}

From source file:org.carrot2.source.yahoo.YahooSearchService.java

/**
 * Parse the response stream, assuming it is XML.
 *///from w ww  .j a  v  a2s.  co m
private static SearchEngineResponse parseResponseXML(final InputStream is) throws IOException {
    try {
        final XMLResponseParser parser = new XMLResponseParser();
        final XMLReader reader = SAXParserFactory.newInstance().newSAXParser().getXMLReader();

        reader.setFeature("http://xml.org/sax/features/validation", false);
        reader.setFeature("http://xml.org/sax/features/namespaces", true);
        reader.setContentHandler(parser);

        reader.parse(new InputSource(is));

        return parser.response;
    } catch (final SAXException e) {
        final Throwable cause = e.getException();
        if (cause != null && cause instanceof IOException) {
            throw (IOException) cause;
        }
        throw new IOException("XML parsing exception: " + e.getMessage());
    } catch (final ParserConfigurationException e) {
        throw new IOException("Could not acquire XML parser.");
    }
}

From source file:org.cauldron.tests.util.DigesterContext.java

protected Object unmarshal(XMLReader reader, InputSource input) throws JAXBException {
    reader.setContentHandler(digester);/*from  w w  w . j  a v  a2 s  .  com*/

    try {
        reader.parse(input);
        return digester.getRoot();
    } catch (Exception e) {
        throw new JAXBException(e);
    }
}

From source file:org.corpus_tools.pepper.core.PepperJobImpl.java

/**
 * {@inheritDoc PepperJob#load(URI)}//from  w  w  w.ja v  a2 s .c o  m
 */
@Override
public void load(URI uri) {
    if (uri.isFile()) {
        File wdFile = new File(uri.toFileString());
        // set folder containing workflow description as base dir
        setBaseDir(uri.trimSegments(1));

        SAXParser parser;
        XMLReader xmlReader;
        SAXParserFactory factory = SAXParserFactory.newInstance();

        WorkflowDescriptionReader contentHandler = new WorkflowDescriptionReader();
        contentHandler.setPepperJob(this);
        contentHandler.setLocation(uri);

        // remove all existing steps
        clear();

        try {
            parser = factory.newSAXParser();
            xmlReader = parser.getXMLReader();
            xmlReader.setContentHandler(contentHandler);
        } catch (ParserConfigurationException e) {
            throw new PepperModuleXMLResourceException("Cannot load Pepper workflow description file '"
                    + wdFile.getAbsolutePath() + "': " + e.getMessage() + ". ", e);
        } catch (Exception e) {
            throw new PepperModuleXMLResourceException("Cannot load Pepper workflow description file '"
                    + wdFile.getAbsolutePath() + "': " + e.getMessage() + ". ", e);
        }
        try {
            InputStream inputStream = new FileInputStream(wdFile);
            Reader reader = new InputStreamReader(inputStream, "UTF-8");
            InputSource is = new InputSource(reader);
            is.setEncoding("UTF-8");
            xmlReader.parse(is);
        } catch (SAXException e) {
            try {
                parser = factory.newSAXParser();
                xmlReader = parser.getXMLReader();
                xmlReader.setContentHandler(contentHandler);
                xmlReader.parse(wdFile.getAbsolutePath());
            } catch (Exception e1) {
                throw new PepperModuleXMLResourceException("Cannot load Pepper workflow description file '"
                        + wdFile.getAbsolutePath() + "': " + e1.getMessage() + ". ", e1);
            }
        } catch (Exception e) {
            if (e instanceof PepperModuleException) {
                throw (PepperModuleException) e;
            } else {
                throw new PepperModuleXMLResourceException("Cannot load Pepper workflow description file'"
                        + wdFile + "', because of a nested exception: " + e.getMessage() + ". ", e);
            }
        }
    } else {
        throw new UnsupportedOperationException(
                "Currently Pepper can only load workflow description from local files.");
    }
}

From source file:org.corpus_tools.salt.util.SaltUtil.java

/**
 * Loads a list of root objects coming from a SaltXML (.{@link #FILE_ENDING_SALT_XML})
 * and returns it.//from w w  w  .ja  va  2 s . co  m
 * 
 * @param objectURI
 *            {@link URI} to SaltXML file containing the object
 * @return loaded objects
 */
public static List<Object> loadObjects(URI location) {
    if (location == null) {
        throw new SaltResourceException("Cannot load Salt object, because the given uri is null.");
    }
    File objectFile = new File(
            (location.toFileString() == null) ? location.toString() : location.toFileString());
    if (!objectFile.exists()) {
        throw new SaltResourceException("Cannot load Salt object, because the file '"
                + objectFile.getAbsolutePath() + "' does not exist.");
    }

    SAXParser parser;
    XMLReader xmlReader;
    SAXParserFactory factory = SAXParserFactory.newInstance();
    SaltXML10Handler contentHandler = new SaltXML10Handler();

    try {
        parser = factory.newSAXParser();
        xmlReader = parser.getXMLReader();
        xmlReader.setContentHandler(contentHandler);
    } catch (ParserConfigurationException e) {
        throw new SaltResourceException(
                "Cannot load Salt object from file '" + objectFile.getAbsolutePath() + "'.", e);
    } catch (Exception e) {
        throw new SaltResourceException(
                "Cannot load Salt object from file '" + objectFile.getAbsolutePath() + "'.", e);
    }
    try {
        InputStream inputStream = new FileInputStream(objectFile);
        Reader reader = new InputStreamReader(inputStream, "UTF-8");
        InputSource is = new InputSource(reader);
        is.setEncoding("UTF-8");
        xmlReader.parse(is);
    } catch (SAXException e) {
        try {
            parser = factory.newSAXParser();
            xmlReader = parser.getXMLReader();
            xmlReader.setContentHandler(contentHandler);
            xmlReader.parse(objectFile.getAbsolutePath());
        } catch (Exception e1) {
            throw new SaltResourceException(
                    "Cannot load Salt object from file '" + objectFile.getAbsolutePath() + "'.", e1);
        }
    } catch (Exception e) {
        if (e instanceof SaltException) {
            throw (SaltException) e;
        } else {
            throw new SaltResourceException(
                    "Cannot load Salt object from file'" + objectFile + "', because of a nested exception. ",
                    e);
        }
    }
    return contentHandler.getRootObjects();
}

From source file:org.deegree.tools.metadata.ISO19139Validator.java

/**
 * @param srcOpt/*from  w  w w  . j av a2 s  . c om*/
 * @param schemaOpt
 * @param resultOpt
 * @throws IOException
 * @throws SAXException
 */
public void run(String srcOpt, String schemaOpt, String resultOpt) throws IOException, SAXException {
    File src = new File(srcOpt);
    if (!src.exists()) {
        throw new IllegalArgumentException("src does not exist: " + srcOpt + ". Check parameter " + OPT_SRC);
    }
    File result;
    if (resultOpt != null && resultOpt.length() > 0) {
        result = new File(resultOpt);
        if (!result.exists()) {
            result.createNewFile();
        }
    } else {
        result = File.createTempFile(DEFAULT_FILENAME, ".txt");
    }

    SCHEMAVERSION schemaVersion = SCHEMAVERSION.V2007;
    if (schemaOpt != null) {
        try {
            schemaVersion = SCHEMAVERSION.valueOf(schemaOpt);
        } catch (Exception e) {
            throw new IllegalArgumentException("Invalid argument for " + OPT_SCHEMA_VERSION + ": " + schemaOpt);
        }
    }

    String schema = "/META-INF/SCHEMAS_OPENGIS_NET/iso/19139/20070417/gmd/metadataEntity.xsd";
    if (SCHEMAVERSION.V2006.equals(schemaVersion)) {
        schema = "/META-INF/SCHEMAS_OPENGIS_NET/iso/19139/20060504/gmd/metadataEntity.xsd";
    }
    URL u = ISO19139Validator.class.getResource(schema);
    XMLReader parser = XMLReaderFactory.createXMLReader();
    parser.setFeature("http://xml.org/sax/features/validation", true);
    parser.setFeature("http://apache.org/xml/features/validation/schema", true);
    parser.setProperty("http://apache.org/xml/properties/schema/external-schemaLocation",
            "http://www.isotc211.org/2005/gmd " + u.toExternalForm());

    final FileWriter fw = new FileWriter(result);

    File[] filesToValidate;
    if (src.isDirectory()) {
        filesToValidate = src.listFiles();
        fw.write("validate " + filesToValidate.length + " files from directory " + src);
        fw.write("\n");
    } else {
        filesToValidate = new File[] { src };
    }
    System.out.println("Start validation");
    int noOfValidRecords = 0;
    for (int i = 0; i < filesToValidate.length; i++) {
        FileErrorHandler feh = new FileErrorHandler(fw);
        parser.setErrorHandler(feh);
        if (filesToValidate.length > 1) {
            fw.write("validate record " + i + " of " + filesToValidate.length);
            fw.write("\n");
        }
        File fileToValidate = filesToValidate[i];
        System.out.println(fileToValidate);
        fw.write("validate file " + fileToValidate.getAbsolutePath());
        fw.write("\n");
        try {
            parser.parse(new InputSource(new FileInputStream(fileToValidate)));
        } catch (Exception e) {
            String msg = "Could not validate current occured: " + e.getMessage()
                    + ". Continue with next record";
            System.err.println(msg);
            fw.write(msg);
            fw.write("\n");
            continue;
        }
        fw.flush();
        if (feh.isValid())
            noOfValidRecords++;
    }
    fw.write(noOfValidRecords + " of " + filesToValidate.length + " records are valid.");
    fw.close();
    System.out.println("Validation finished, result file: " + result.getAbsolutePath());
}

From source file:org.devtcg.five.meta.LastfmMetaTask.java

public void run() throws Exception {
    System.out.println("Accessing " + getMethodUrl());
    HttpGet request = new HttpGet(getMethodUrl());

    HttpResponse response = mClient.execute(request);

    if (mTask.isCancelled())
        return;//w  w  w.  ja v a  2 s .  co  m

    if (response.getStatusLine().getStatusCode() != HttpStatus.SC_OK) {
        if (LOG.isWarnEnabled())
            LOG.warn(getMethodUrl() + " replied " + response.getStatusLine());
        response.getEntity().consumeContent();
        return;
    }

    HttpEntity entity = response.getEntity();
    InputStream in = entity.getContent();

    try {
        XMLReader reader = XMLReaderFactory.createXMLReader();
        reader.setContentHandler(getContentHandler());
        reader.parse(new InputSource(in));
    } finally {
        IOUtils.closeQuietlyNullSafe(in);
    }

    if (mTask.isCancelled())
        return;

    onPostParse();
}

From source file:org.dhatim.delivery.dom.DOMParser.java

/**
* Perform the actual parse into the supplied content handler.
* @param source Source content stream to be parsed.
* @param contentHandler Content handler instance that will build/append-to the DOM.
* @throws SAXException Unable to parse the content.
* @throws IOException Unable to read the input stream.
*///from   w  ww.  j  a  v a 2  s . c  o m
private void parse(Source source, DOMBuilder contentHandler) throws SAXException, IOException {
    ExecutionContext executionContext = getExecContext();

    if (executionContext != null) {
        ContentDeliveryConfig deliveryConfig = executionContext.getDeliveryConfig();

        XMLReader domReader = getXMLReader(executionContext);

        try {
            if (domReader == null) {
                domReader = deliveryConfig.getXMLReader();
            }
            if (domReader == null) {
                domReader = createXMLReader();
            }

            if (domReader instanceof HierarchyChangeReader) {
                ((HierarchyChangeReader) domReader)
                        .setHierarchyChangeListener(new XMLReaderHierarchyChangeListener(executionContext));
            }

            NamespaceDeclarationStack namespaceDeclarationStack = new NamespaceDeclarationStack();
            NamespaceMappings.setNamespaceDeclarationStack(namespaceDeclarationStack, executionContext);
            attachNamespaceDeclarationStack(domReader, executionContext);

            attachXMLReader(domReader, executionContext);
            configureReader(domReader, contentHandler, executionContext, source);
            domReader.parse(createInputSource(source, executionContext.getContentEncoding()));
        } finally {
            try {
                if (domReader instanceof HierarchyChangeReader) {
                    ((HierarchyChangeReader) domReader).setHierarchyChangeListener(null);
                }
            } finally {
                try {
                    try {
                        detachXMLReader(executionContext);
                    } finally {
                        if (domReader != null) {
                            deliveryConfig.returnXMLReader(domReader);
                        }
                    }
                } finally {
                    contentHandler.detachHandler();
                }
            }
        }
    } else {
        XMLReader domReader = createXMLReader();
        configureReader(domReader, contentHandler, null, source);
        domReader.parse(createInputSource(source, Charset.defaultCharset().name()));
    }
}