Examples of HTMLScanner

This component recognizes the following properties:

@see HTMLElements @see HTMLEntities @author Andy Clark @author Marc Guillemot @author Ahmed Ashour @version $Id: HTMLScanner.java,v 1.19 2005/06/14 05:52:37 andyc Exp $
  • org.htmlparser.scanners.HtmlScanner

    • Examples of HTTP.HTMLScanner

    71
    72
    73
    74
    75
    76
    77
    78
    79
    80
    81
    82
      public int doStartTag() throws JspException
      {
        ServletRequest request = pageContext.getRequest();
        // DavidQ - Breaking out individual variables to make debugging easier.
        // DavidQ - Begin
        HTMLScanner htmlScanner = (HTMLScanner) request.getAttribute(HTML_SCANNER_ATTR);
        ExecContext context = (ExecContext) request.getAttribute(EXEC_CONTEXT_ATTR);
        this.testResult = htmlScanner.getCondition(this.getTagHandler(), this.getConditionMethod(), context, this.parameterList);
        // DavidQ - End

        return EVAL_BODY_INCLUDE;
      }
    View Full Code Here

    Examples of HTTP.HTMLScanner

    71
    72
    73
    74
    75
    76
    77
    78
    79
    80
    81
    82
      public int doStartTag() throws JspException
      {
        ServletRequest request = pageContext.getRequest();
        // DavidQ - Breaking out individual variables to make debugging easier.
        // DavidQ - Begin
        HTMLScanner htmlScanner = (HTMLScanner) request.getAttribute(HTML_SCANNER_ATTR);
        ExecContext context = (ExecContext) request.getAttribute(EXEC_CONTEXT_ATTR);
        this.testResult = htmlScanner.getCondition(this.getTagHandler(), this.getConditionMethod(), context, this.parameterList);
        // DavidQ - End

        return EVAL_BODY_INCLUDE;
      }
    View Full Code Here

    Examples of org.cyberneko.html.HTMLScanner

    106
    107
    108
    109
    110
    111
    112
    113
    114
    115
    116
    117
    118
    119
    120
    121
    122
    123
    124
    125
    126
    127
    128
    129
    130
    131
    132
    133
    134
    135
    136
    137
    138
       * @return a document handler containing the parsed source
       */
      private DocumentHandler parseHtmlImpl(String source) throws IOException {
        HTMLConfiguration config = newConfiguration();

        HTMLScanner htmlScanner = new HTMLScanner();
        HTMLTagBalancer tagBalancer = new HTMLTagBalancer();

        DocumentHandler handler = newDocumentHandler(source, htmlScanner);

        if (config.getFeature("http://xml.org/sax/features/namespaces")) {
          NamespaceBinder namespaceBinder = new NamespaceBinder();
          namespaceBinder.setDocumentHandler(handler);
          namespaceBinder.setDocumentSource(tagBalancer);
          namespaceBinder.reset(config);
          tagBalancer.setDocumentHandler(namespaceBinder);
        } else {
          tagBalancer.setDocumentHandler(handler);
        }

        tagBalancer.setDocumentSource(htmlScanner);
        htmlScanner.setDocumentHandler(tagBalancer);

        tagBalancer.reset(config);
        htmlScanner.reset(config);

        XMLInputSource inputSource = new XMLInputSource(null, null, null);
        inputSource.setEncoding("UTF-8");
        inputSource.setCharacterStream(new StringReader(source));
        htmlScanner.setInputSource(inputSource);
        htmlScanner.scanDocument(true);
        return handler;
      }
    View Full Code Here

    Examples of org.cyberneko.html.HTMLScanner

    137
    138
    139
    140
    141
    142
    143
    144
    145
    146
    147
    148
    149
    150
    151
    152
    153
    154
    155
    156
    157
    158
    159
    160
    161
    162
    163
    164
    165
    166
       */
      private DocumentHandler parseHtmlImpl(String source, HTMLConfiguration config,
          NormalizingTagBalancer tagBalancer)
          throws IOException {

        HTMLScanner htmlScanner = new HTMLScanner();
        tagBalancer.setScanner(htmlScanner);

        DocumentHandler handler = newDocumentHandler(source);

        NamespaceBinder namespaceBinder = new NamespaceBinder();
        namespaceBinder.setDocumentHandler(handler);
        namespaceBinder.setDocumentSource(tagBalancer);
        namespaceBinder.reset(config);
        tagBalancer.setDocumentHandler(namespaceBinder);

        // Order of filter is Scanner -> OSMLFilter -> Tag Balancer
        tagBalancer.setDocumentSource(htmlScanner);
        htmlScanner.setDocumentHandler(tagBalancer);

        tagBalancer.reset(config);
        htmlScanner.reset(config);

        XMLInputSource inputSource = new XMLInputSource(null, null, null);
        inputSource.setEncoding("UTF-8");
        inputSource.setCharacterStream(new StringReader(source));
        htmlScanner.setInputSource(inputSource);
        htmlScanner.scanDocument(true);
        return handler;
      }
    View Full Code Here

    Examples of org.cyberneko.html.HTMLScanner

    134
    135
    136
    137
    138
    139
    140
    141
    142
    143
    144
    145
    146
    147
    148
    149
    150
    151
    152
    153
    154
    155
    156
    157
    158
    159
    160
    161
    162
    163
       */
      private DocumentHandler parseHtmlImpl(String source, HTMLConfiguration config,
          NormalizingTagBalancer tagBalancer)
          throws IOException {

        HTMLScanner htmlScanner = new HTMLScanner();
        tagBalancer.setScanner(htmlScanner);

        DocumentHandler handler = newDocumentHandler(source);

        NamespaceBinder namespaceBinder = new NamespaceBinder();
        namespaceBinder.setDocumentHandler(handler);
        namespaceBinder.setDocumentSource(tagBalancer);
        namespaceBinder.reset(config);
        tagBalancer.setDocumentHandler(namespaceBinder);

        // Order of filter is Scanner -> OSMLFilter -> Tag Balancer
        tagBalancer.setDocumentSource(htmlScanner);
        htmlScanner.setDocumentHandler(tagBalancer);

        tagBalancer.reset(config);
        htmlScanner.reset(config);

        XMLInputSource inputSource = new XMLInputSource(null, null, null);
        inputSource.setEncoding("UTF-8");
        inputSource.setCharacterStream(new StringReader(source));
        htmlScanner.setInputSource(inputSource);
        htmlScanner.scanDocument(true);
        return handler;
      }
    View Full Code Here

    Examples of org.cyberneko.html.HTMLScanner

    56
    57
    58
    59
    60
    61
    62
    63
    64
    65
    66
    67
    68
    69
    70
    71
    72
    73
    74
    75
    76
    77
    78
    79
    80
    81
    82
    83
    84
    85
    86
    87
    88
        this.documentFactory = documentFactory;
      }

      @Override
      protected Document parseDomImpl(String source) {
        HTMLScanner htmlScanner = new HTMLScanner();
        HTMLTagBalancer tagBalancer = new HTMLTagBalancer();
        DocumentHandler handler = new DocumentHandler(source);
        tagBalancer.setDocumentHandler(handler);
        htmlScanner.setDocumentHandler(tagBalancer);

        HTMLConfiguration config = new HTMLConfiguration();
        // Maintain original case for elements and attributes
        config.setProperty("http://cyberneko.org/html/properties/names/elems", "match");
        config.setProperty("http://cyberneko.org/html/properties/names/attrs", "no-change");
        // Parse as fragment.
        config.setFeature("http://cyberneko.org/html/features/balance-tags/document-fragment", true);
        // Get notified of entity and character references
        config.setFeature("http://apache.org/xml/features/scanner/notify-char-refs", true);
        config.setFeature("http://cyberneko.org/html/features/scanner/notify-builtin-refs", true);
        tagBalancer.reset(config);
        htmlScanner.reset(config);
        XMLInputSource inputSource = new XMLInputSource(null, null, null);
        inputSource.setEncoding("UTF-8");
        inputSource.setCharacterStream(new StringReader(source));
        try {
          htmlScanner.setInputSource(inputSource);
          htmlScanner.scanDocument(true);
          Document document = handler.getDocument();
          DocumentFragment fragment = handler.getFragment();
          normalizeFragment(document, fragment);
          HtmlSerializer.attach(document, new NekoSerializer(), source);
          return document;
    View Full Code Here

    Examples of org.cyberneko.html.HTMLScanner

    139
    140
    141
    142
    143
    144
    145
    146
    147
    148
    149
    150
    151
    152
    153
    154
    155
    156
    157
    158
    159
    160
    161
    162
    163
    164
    165
    166
    167
    168
       */
      private DocumentHandler parseHtmlImpl(String source, HTMLConfiguration config,
          NormalizingTagBalancer tagBalancer)
          throws IOException {

        HTMLScanner htmlScanner = new HTMLScanner();
        tagBalancer.setScanner(htmlScanner);

        DocumentHandler handler = newDocumentHandler(source);

        NamespaceBinder namespaceBinder = new NamespaceBinder();
        namespaceBinder.setDocumentHandler(handler);
        namespaceBinder.setDocumentSource(tagBalancer);
        namespaceBinder.reset(config);
        tagBalancer.setDocumentHandler(namespaceBinder);

        // Order of filter is Scanner -> OSMLFilter -> Tag Balancer
        tagBalancer.setDocumentSource(htmlScanner);
        htmlScanner.setDocumentHandler(tagBalancer);

        tagBalancer.reset(config);
        htmlScanner.reset(config);

        XMLInputSource inputSource = new XMLInputSource(null, null, null);
        inputSource.setEncoding("UTF-8");
        inputSource.setCharacterStream(new StringReader(source));
        htmlScanner.setInputSource(inputSource);
        htmlScanner.scanDocument(true);
        return handler;
      }
    View Full Code Here

    Examples of org.htmlparser.scanners.HtmlScanner

    58
    59
    60
    61
    62
    63
    64
    65
    66
    67
    68
                    + "  <body>"
                    + "    Some data"
                    + "  </body>"
                    + "</html>");
            parser.addScanner(new TitleScanner(""));
            parser.addScanner(new HtmlScanner());
            parseAndAssertNodeCount(1);
            assertType("html tag", Html.class, node[0]);
            Html html = (Html) node[0];
            NodeList nodeList = new NodeList();
            html.collectInto(nodeList, TitleTag.class);
    View Full Code Here

    Examples of org.htmlparser.scanners.HtmlScanner

    1098
    1099
    1100
    1101
    1102
    1103
    1104
    1105
    1106
         * with methods to access the body and the head.
         */
        public void registerDomScanners()
        {
            registerScanners();
            addScanner(new HtmlScanner());
            addScanner(new BodyScanner());
            addScanner(new HeadScanner());
        }
    View Full Code Here

    Examples of org.htmlparser.scanners.HtmlScanner

    47
    48
    49
    50
    51
    52
    53
    54
    55
    56
    57
      public void testScan() throws Exception {
        createParser("<html>" + "  <head>" + "    <title>Some Title</title>" + "  </head>" + "  <body>" + "    Some data"
            + "  </body>" + "</html>");
        parser.addScanner(new TitleScanner(""));
        parser.addScanner(new HtmlScanner());
        parseAndAssertNodeCount(1);
        assertType("html tag", Html.class, node[0]);
        Html html = (Html) node[0];
        NodeList nodeList = new NodeList();
        html.collectInto(nodeList, TitleTag.class);
    View Full Code Here
    TOP
    Copyright © 2018 www.massapi.com. All rights reserved.
    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.