Examples of nu.validator.htmlparser.sax.HtmlParser

nu.validator.htmlparser.sax.HtmlParser
This class implements an HTML5 parser that exposes data through the SAX2 interface.
By default, when using the constructor without arguments, the this parser coerces XML 1.0-incompatible infosets into XML 1.0-compatible infosets. This corresponds to ALTER_INFOSET as the general XML violation policy. To make the parser support non-conforming HTML fully per the HTML 5 spec while on the other hand potentially violating the SAX2 API contract, set the general XML violation policy to ALLOW. It is possible to treat XML 1.0 infoset violations as fatal by setting the general XML violation policy to FATAL.
By default, this parser doesn't do true streaming but buffers everything first. The parser can be made truly streaming by calling setStreamabilityViolationPolicy(XmlViolationPolicy.FATAL). This has the consequence that errors that require non-streamable recovery are treated as fatal.
By default, in order to make the parse events emulate the parse events for a DTDless XML document, the parser does not report the doctype through LexicalHandler. Doctype reporting through LexicalHandler can be turned on by calling setReportingDoctype(true). @version $Id$ @author hsivonen

@SupportedFormat("text/html")
public class HTMLRDFaParser extends ClerezzaRDFaParser {


  @Override
  public XMLReader getReader() {
    HtmlParser reader = new HtmlParser();
    reader.setXmlPolicy(XmlViolationPolicy.ALLOW);
    reader.setXmlnsPolicy(XmlViolationPolicy.ALLOW);
    reader.setMappingLangToXmlLang(false);
    return reader;
  }

View Full Code Here

                    new UsemapChecker(), jingPropertyMap));
            validator = new CombineValidator(validator, new CheckerValidator(
                    new XmlPiChecker(), jingPropertyMap));
        }


        htmlParser = new HtmlParser();
        htmlParser.setCommentPolicy(XmlViolationPolicy.ALLOW);
        htmlParser.setContentNonXmlCharPolicy(XmlViolationPolicy.ALLOW);
        htmlParser.setContentSpacePolicy(XmlViolationPolicy.ALTER_INFOSET);
        htmlParser.setNamePolicy(XmlViolationPolicy.ALLOW);
        htmlParser.setXmlnsPolicy(XmlViolationPolicy.ALTER_INFOSET);

View Full Code Here


    /**
     * 
     */
    protected void newHtmlParser() {
        htmlParser = new HtmlParser();
        htmlParser.setCommentPolicy(XmlViolationPolicy.ALLOW);
        htmlParser.setContentNonXmlCharPolicy(XmlViolationPolicy.ALLOW);
        htmlParser.setContentSpacePolicy(XmlViolationPolicy.ALTER_INFOSET);
        htmlParser.setNamePolicy(XmlViolationPolicy.ALLOW);
        htmlParser.setStreamabilityViolationPolicy(XmlViolationPolicy.FATAL);

View Full Code Here


    /**
     * 
     */
    protected void newHtmlParser() {
        htmlParser = new HtmlParser();
        htmlParser.setCommentPolicy(XmlViolationPolicy.ALLOW);
        htmlParser.setContentNonXmlCharPolicy(XmlViolationPolicy.ALLOW);
        htmlParser.setContentSpacePolicy(XmlViolationPolicy.ALTER_INFOSET);
        htmlParser.setNamePolicy(XmlViolationPolicy.ALLOW);
        htmlParser.setStreamabilityViolationPolicy(XmlViolationPolicy.FATAL);

View Full Code Here


    private final List<DocumentFragment> fragments = new LinkedList<DocumentFragment>();


    public static List<DocumentFragment> parseAltAdvice()
            throws IOException, SAXException {
        HtmlParser parser = new HtmlParser(XmlViolationPolicy.ALTER_INFOSET);
        ImageReportAdviceBuilder handler = new ImageReportAdviceBuilder();
        parser.setContentHandler(handler);
        InputSource in = new InputSource(
                ImageReportAdviceBuilder.class.getClassLoader().getResourceAsStream(
                        "nu/validator/localentities/files/wiki_whatwg_org_wiki_Validator_nu_alt_advice"));
        parser.parse(in);
        return handler.getFragments();
    }

View Full Code Here

    private Map<Name, DocumentFragment> attributesByElement = new HashMap<Name, DocumentFragment>();


    private boolean ignoreTextNodes = false;


    public static Spec parseSpec(InputSource in) throws IOException, SAXException {
        HtmlParser parser = new HtmlParser(XmlViolationPolicy.ALTER_INFOSET);
        Html5SpecBuilder handler = new Html5SpecBuilder();
        parser.setContentHandler(handler);
        parser.parse(in);
        return handler.buildSpec();
    }

View Full Code Here

                    new UsemapChecker(), jingPropertyMap));
            validator = new CombineValidator(validator, new CheckerValidator(
                    new XmlPiChecker(), jingPropertyMap));
        }


        htmlParser = new HtmlParser();
        htmlParser.setCommentPolicy(XmlViolationPolicy.ALLOW);
        htmlParser.setContentNonXmlCharPolicy(XmlViolationPolicy.ALLOW);
        htmlParser.setContentSpacePolicy(XmlViolationPolicy.ALTER_INFOSET);
        htmlParser.setNamePolicy(XmlViolationPolicy.ALLOW);
        htmlParser.setXmlnsPolicy(XmlViolationPolicy.ALTER_INFOSET);

View Full Code Here


    /**
     * 
     */
    protected void newHtmlParser() {
        htmlParser = new HtmlParser();
        htmlParser.setCommentPolicy(XmlViolationPolicy.ALLOW);
        htmlParser.setContentNonXmlCharPolicy(XmlViolationPolicy.ALLOW);
        htmlParser.setContentSpacePolicy(XmlViolationPolicy.ALTER_INFOSET);
        htmlParser.setNamePolicy(XmlViolationPolicy.ALLOW);
        htmlParser.setStreamabilityViolationPolicy(XmlViolationPolicy.FATAL);

View Full Code Here


    private final List<DocumentFragment> fragments = new LinkedList<DocumentFragment>();


    public static List<DocumentFragment> parseAltAdvice()
            throws IOException, SAXException {
        HtmlParser parser = new HtmlParser(XmlViolationPolicy.ALTER_INFOSET);
        ImageReportAdviceBuilder handler = new ImageReportAdviceBuilder();
        parser.setContentHandler(handler);
        InputSource in = new InputSource(
                ImageReportAdviceBuilder.class.getClassLoader().getResourceAsStream(
                        "nu/validator/localentities/files/wiki_whatwg_org_wiki_Validator_nu_alt_advice"));
        parser.parse(in);
        return handler.getFragments();
    }

View Full Code Here

    private TreeBuilder treeBuilder;


    private Map<Class, DocumentFragment> adviceByClass = new HashMap<Class, DocumentFragment>();


    public static Map<Class, DocumentFragment> parseSyntaxDescriptions() throws IOException, SAXException {
        HtmlParser parser = new HtmlParser(XmlViolationPolicy.ALTER_INFOSET);
        Html5AttributeDatatypeBuilder handler = new Html5AttributeDatatypeBuilder();
        parser.setContentHandler(handler);
        InputSource in = new InputSource(
                Html5AttributeDatatypeBuilder.class.getClassLoader().getResourceAsStream(
                        "nu/validator/localentities/files/wiki_whatwg_org_wiki_MicrosyntaxDescriptions"));
        parser.parse(in);
        return handler.getAdvice();
    }

View Full Code Here

0 1

TOP

Related Classes of nu.validator.htmlparser.sax.HtmlParser

nu.validator.htmlparser.impl.ErrorReportingTokenizer

nu.validator.htmlparser.impl.Tokenizer

nu.validator.htmlparser.io.Driver

nu.validator.saxtree.Document

nu.validator.saxtree.DocumentFragment

nu.validator.saxtree.TreeParser

nu.validator.servlet.VerifierServletTransaction

nu.validator.spec.html5.Html5AttributeDatatypeBuilder

nu.validator.spec.html5.Html5SpecBuilder

nu.validator.spec.html5.ImageReportAdviceBuilder

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.