Examples with XMLStreamReader javax.xml.stream.XMLStreamReader used on opensource projects

Example 46 with XMLStreamReader

use of javax.xml.stream.XMLStreamReader in project aries by apache.

the class NamespaceHandlerRegistryImpl method wrapIfNeeded.

/**
     * Wrap the handler if needed to fix its behavior.
     * When asked for a schema location, some simple handlers always return
     * the same url, whatever the asked location is.  This can lead to lots
     * of problems, so we need to verify and fix those behaviors.
     */
private static NamespaceHandler wrapIfNeeded(final NamespaceHandler handler) {
    URL result = null;
    try {
        result = handler.getSchemaLocation("");
    } catch (Throwable t) {
    // Ignore
    }
    if (result != null) {
        LOGGER.warn("NamespaceHandler " + handler.getClass().getName() + " is behaving badly and should be fixed");
        final URL res = result;
        return new NamespaceHandler() {

            final ConcurrentMap<String, Boolean> cache = new ConcurrentHashMap<String, Boolean>();

            @Override
            public URL getSchemaLocation(String s) {
                URL url = handler.getSchemaLocation(s);
                if (url != null && url.equals(res)) {
                    Boolean v, newValue;
                    Boolean valid = ((v = cache.get(s)) == null && (newValue = isValidSchema(s, url)) != null && (v = cache.putIfAbsent(s, newValue)) == null) ? newValue : v;
                    return valid ? url : null;
                }
                return url;
            }

            @Override
            public Set<Class> getManagedClasses() {
                return handler.getManagedClasses();
            }

            @Override
            public Metadata parse(Element element, ParserContext parserContext) {
                return handler.parse(element, parserContext);
            }

            @Override
            public ComponentMetadata decorate(Node node, ComponentMetadata componentMetadata, ParserContext parserContext) {
                return handler.decorate(node, componentMetadata, parserContext);
            }

            private boolean isValidSchema(String ns, URL url) {
                try {
                    InputStream is = url.openStream();
                    try {
                        XMLStreamReader reader = XMLInputFactory.newFactory().createXMLStreamReader(is);
                        try {
                            reader.nextTag();
                            String nsuri = reader.getNamespaceURI();
                            String name = reader.getLocalName();
                            if ("http://www.w3.org/2001/XMLSchema".equals(nsuri) && "schema".equals(name)) {
                                String target = reader.getAttributeValue(null, "targetNamespace");
                                if (ns.equals(target)) {
                                    return true;
                                }
                            }
                        } finally {
                            reader.close();
                        }
                    } finally {
                        is.close();
                    }
                } catch (Throwable t) {
                // Ignore
                }
                return false;
            }
        };
    } else {
        return handler;
    }
}

Example 47 with XMLStreamReader

use of javax.xml.stream.XMLStreamReader in project jackrabbit-oak by apache.

the class WikipediaImport method importWikipedia.

public int importWikipedia(Session session) throws Exception {
    long start = System.currentTimeMillis();
    int count = 0;
    int code = 0;
    if (doReport) {
        System.out.format("Importing %s...%n", dump);
    }
    String type = "nt:unstructured";
    if (session.getWorkspace().getNodeTypeManager().hasNodeType("oak:Unstructured")) {
        type = "oak:Unstructured";
    }
    Node wikipedia = session.getRootNode().addNode("wikipedia", type);
    int levels = 0;
    if (!flat) {
        // estimate that the average XML size of a page is about 1kB
        for (long pages = dump.length() / 1024; pages > 256; pages /= 256) {
            levels++;
        }
    }
    String title = null;
    String text = null;
    XMLInputFactory factory = XMLInputFactory.newInstance();
    StreamSource source;
    if (dump.getName().endsWith(".xml")) {
        source = new StreamSource(dump);
    } else {
        CompressorStreamFactory csf = new CompressorStreamFactory();
        source = new StreamSource(csf.createCompressorInputStream(new BufferedInputStream(new FileInputStream(dump))));
    }
    haltImport = false;
    XMLStreamReader reader = factory.createXMLStreamReader(source);
    while (reader.hasNext() && !haltImport) {
        switch(reader.next()) {
            case XMLStreamConstants.START_ELEMENT:
                if ("title".equals(reader.getLocalName())) {
                    title = reader.getElementText();
                } else if ("text".equals(reader.getLocalName())) {
                    text = reader.getElementText();
                }
                break;
            case XMLStreamConstants.END_ELEMENT:
                if ("page".equals(reader.getLocalName())) {
                    String name = Text.escapeIllegalJcrChars(title);
                    Node parent = wikipedia;
                    if (levels > 0) {
                        int n = name.length();
                        for (int i = 0; i < levels; i++) {
                            int hash = name.substring(min(i, n)).hashCode();
                            parent = JcrUtils.getOrAddNode(parent, String.format("%02x", hash & 0xff));
                        }
                    }
                    Node page = parent.addNode(name);
                    page.setProperty("title", title);
                    page.setProperty("text", text);
                    code += title.hashCode();
                    code += text.hashCode();
                    count++;
                    if (count % 1000 == 0) {
                        batchDone(session, start, count);
                    }
                    pageAdded(title, text);
                }
                break;
        }
    }
    session.save();
    if (doReport) {
        long millis = System.currentTimeMillis() - start;
        System.out.format("Imported %d pages in %d seconds (%.2fms/page)%n", count, millis / 1000, (double) millis / count);
    }
    return code;
}

Example 48 with XMLStreamReader

use of javax.xml.stream.XMLStreamReader in project karaf by apache.

the class MavenConfigService method getLocalRepositoryFromSettings.

private static String getLocalRepositoryFromSettings(File file) {
    XMLStreamReader reader = null;
    try (InputStream fin = new FileInputStream(file)) {
        reader = XMLInputFactory.newFactory().createXMLStreamReader(fin);
        int event;
        String elementName = null;
        while ((event = reader.next()) != XMLStreamConstants.END_DOCUMENT) {
            if (event == XMLStreamConstants.START_ELEMENT) {
                elementName = reader.getLocalName();
            } else if (event == XMLStreamConstants.END_ELEMENT) {
                elementName = null;
            } else if (event == XMLStreamConstants.CHARACTERS && "localRepository".equals(elementName)) {
                return reader.getText().trim();
            }
        }
    } catch (Exception e) {
        logger.error("Error retrieving maven configuration", e);
    } finally {
        if (reader != null) {
            try {
                reader.close();
            } catch (XMLStreamException e) {
            // Ignore
            }
        }
    }
    return null;
}

Example 49 with XMLStreamReader

use of javax.xml.stream.XMLStreamReader in project lucene-solr by apache.

the class AddBlockUpdateTest method testXML.

//This is the same as testSolrJXML above but uses the XMLLoader
// to illustrate the structure of the XML documents
@Test
public void testXML() throws IOException, XMLStreamException {
    UpdateRequest req = new UpdateRequest();
    List<SolrInputDocument> docs = new ArrayList<>();
    String xml_doc1 = "<doc >" + "  <field name=\"id\">1</field>" + "  <field name=\"parent_s\">X</field>" + "<doc>  " + "  <field name=\"id\" >2</field>" + "  <field name=\"child_s\">y</field>" + "</doc>" + "<doc>  " + "  <field name=\"id\" >3</field>" + "  <field name=\"child_s\">z</field>" + "</doc>" + "</doc>";
    String xml_doc2 = "<doc >" + "  <field name=\"id\">4</field>" + "  <field name=\"parent_s\">A</field>" + "<doc>  " + "  <field name=\"id\" >5</field>" + "  <field name=\"child_s\">b</field>" + "</doc>" + "<doc>  " + "  <field name=\"id\" >6</field>" + "  <field name=\"child_s\">c</field>" + "</doc>" + "</doc>";
    XMLStreamReader parser = inputFactory.createXMLStreamReader(new StringReader(xml_doc1));
    // read the START document...
    parser.next();
    //null for the processor is all right here
    XMLLoader loader = new XMLLoader();
    SolrInputDocument document1 = loader.readDoc(parser);
    XMLStreamReader parser2 = inputFactory.createXMLStreamReader(new StringReader(xml_doc2));
    // read the START document...
    parser2.next();
    //null for the processor is all right here
    //XMLLoader loader = new XMLLoader();
    SolrInputDocument document2 = loader.readDoc(parser2);
    docs.add(document1);
    docs.add(document2);
    Collections.shuffle(docs, random());
    req.add(docs);
    RequestWriter requestWriter = new RequestWriter();
    OutputStream os = new ByteArrayOutputStream();
    requestWriter.write(req, os);
    assertBlockU(os.toString());
    assertU(commit());
    final SolrIndexSearcher searcher = getSearcher();
    assertSingleParentOf(searcher, one("yz"), "X");
    assertSingleParentOf(searcher, one("bc"), "A");
}

Example 50 with XMLStreamReader

use of javax.xml.stream.XMLStreamReader in project lucene-solr by apache.

the class DocumentAnalysisRequestHandler method resolveAnalysisRequest.

//================================================ Helper Methods ==================================================
/**
   * Resolves the {@link DocumentAnalysisRequest} from the given solr request.
   *
   * @param req The solr request.
   *
   * @return The resolved document analysis request.
   *
   * @throws IOException        Thrown when reading/parsing the content stream of the request fails.
   * @throws XMLStreamException Thrown when reading/parsing the content stream of the request fails.
   */
DocumentAnalysisRequest resolveAnalysisRequest(SolrQueryRequest req) throws IOException, XMLStreamException {
    DocumentAnalysisRequest request = new DocumentAnalysisRequest();
    SolrParams params = req.getParams();
    String query = params.get(AnalysisParams.QUERY, params.get(CommonParams.Q, null));
    request.setQuery(query);
    boolean showMatch = params.getBool(AnalysisParams.SHOW_MATCH, false);
    request.setShowMatch(showMatch);
    ContentStream stream = extractSingleContentStream(req);
    InputStream is = null;
    XMLStreamReader parser = null;
    try {
        is = stream.getStream();
        final String charset = ContentStreamBase.getCharsetFromContentType(stream.getContentType());
        parser = (charset == null) ? inputFactory.createXMLStreamReader(is) : inputFactory.createXMLStreamReader(is, charset);
        while (true) {
            int event = parser.next();
            switch(event) {
                case XMLStreamConstants.END_DOCUMENT:
                    {
                        parser.close();
                        return request;
                    }
                case XMLStreamConstants.START_ELEMENT:
                    {
                        String currTag = parser.getLocalName();
                        if ("doc".equals(currTag)) {
                            log.trace("Reading doc...");
                            SolrInputDocument document = readDocument(parser, req.getSchema());
                            request.addDocument(document);
                        }
                        break;
                    }
            }
        }
    } finally {
        if (parser != null)
            parser.close();
        IOUtils.closeQuietly(is);
    }
}