Package org.cyberneko.html.parsers

Examples of org.cyberneko.html.parsers.DOMFragmentParser

126
127
128
129
130
131
132
133
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
  };

  private URL[][] currURLsAndAnswers;

  public void testRobotsMetaProcessor() {
    DOMFragmentParser parser= new DOMFragmentParser();;

    try {
      currURLsAndAnswers= new URL[][] {
        {new URL("http://www.nutch.org"), null},
        {new URL("http://www.nutch.org"), null},
        {new URL("http://www.nutch.org"), null},
        {new URL("http://www.nutch.org"), null},
        {new URL("http://www.nutch.org"), null},
        {new URL("http://www.nutch.org"), null},
        {new URL("http://www.nutch.org"), null},
        {new URL("http://www.nutch.org/foo/"),
         new URL("http://www.nutch.org/")},
        {new URL("http://www.nutch.org"),
         new URL("http://www.nutch.org/base/")}
      };
    } catch (Exception e) {
      assertTrue("couldn't make test URLs!", false);
    }

    for (int i= 0; i < tests.length; i++) {
      byte[] bytes= tests[i].getBytes();

      DocumentFragment node = new HTMLDocumentImpl().createDocumentFragment();

      try {
        parser.parse(new InputSource(new ByteArrayInputStream(bytes)), node);
      } catch (Exception e) {
        e.printStackTrace();
      }

      HTMLMetaTags robotsMeta= new HTMLMetaTags();
View Full Code Here
132
133
134
135
136
137
138
139
140
141
142
    properties = OutputPropertiesFactory.getDefaultMethodProperties(Method.HTML);
    _HTMLserialiser = SerializerFactory.getSerializer(properties);
    _serializer = _HTMLserialiser;
    // serializer.setOutputStream(output);
    // _parser.setContentHandler(serializer.asContentHandler());
    viewStateParser = new DOMFragmentParser();
    // Set parser features
    try {
      viewStateParser
          .setProperty(
              "http://cyberneko.org/html/properties/names/elems",
View Full Code Here
29
30
31
32
33
34
35
36
37
38
39
40
41
    // MAIN
    //

    /** Main. */
    public static void main(String[] argv) throws Exception {
        DOMFragmentParser parser = new DOMFragmentParser();
        HTMLDocument document = new HTMLDocumentImpl();
        for (int i = 0; i < argv.length; i++) {
            DocumentFragment fragment = document.createDocumentFragment();
            parser.parse(argv[i], fragment);
            print(fragment, "");
        }
    } // main(String[])
View Full Code Here
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
    if(commentText.startsWith("<p>")==false) {
      commentText="<p>"+commentText;
    }
   
    commentText=replaceLinks(commentText);
    DOMFragmentParser parser = new DOMFragmentParser();
   
   
    Document doc=builder.newDocument();
    DocumentFragment fragment = doc.createDocumentFragment();
   
        try {
          parser.parse(new InputSource(new StringReader(commentText)), fragment);
     
    } catch (SAXException e) {
      IOException ioe = new IOException();
      ioe.initCause(e);
      throw ioe;
View Full Code Here
TOP

Related Classes of org.cyberneko.html.parsers.DOMFragmentParser

  • org.ajax4jsf.webapp.nekko.NekkoParser
  • org.apache.kato.anttasks.xmlgen.XMLWriter
  • org.apache.myfaces.tobago.example.test.SeleniumScript
  • org.apache.nutch.parse.html.HtmlParser
  • org.apache.nutch.tika.TestDOMContentUtils
  • org.apache.nutch.tika.TestRobotsMetaProcessor
  • org.apache.shindig.gadgets.parse.nekohtml.NekoHtmlParser
  • org.apache.xerces.util.ErrorHandlerWrapper
  • org.apache.xerces.xni.parser.XMLErrorHandler
  • org.apache.xerces.xni.parser.XMLInputSource
    • Copyright © 2018 www.massapicom. 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.