Package org.cyberneko.html.parsers

Examples of org.cyberneko.html.parsers.SAXParser

27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
        return; // this test makes sense only for more recent Xerces versions
      }
     
      final String content = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n<html></html>";
        ByteArrayInputStream input = new ByteArrayInputStream(content.getBytes("UTF-8"));
        SAXParser parser = new SAXParser();
       
        final Locator[] locators = { null };
       
        final ContentHandler contentHandler = new ContentHandler() {
      public void startPrefixMapping(String prefix, String uri) throws SAXException {
      }
     
      public void startElement(String uri, String localName, String qName, Attributes atts) throws SAXException {
      }
     
      public void startDocument() throws SAXException {
      }
     
      public void skippedEntity(String name) throws SAXException {
      }
     
      public void setDocumentLocator(Locator locator) {
        locators[0] = locator;
      }
     
      public void processingInstruction(String target, String data)
          throws SAXException {
      }
     
      public void ignorableWhitespace(char[] ch, int start, int length) throws SAXException {
      }
     
      public void endPrefixMapping(String prefix) throws SAXException {
      }
     
      public void endElement(String uri, String localName, String qName) throws SAXException {
      }
     
      public void endDocument() throws SAXException {
      }
     
      public void characters(char[] ch, int start, int length) throws SAXException {
      }
    };
        parser.setContentHandler(contentHandler);
        parser.parse(new InputSource(input));
        assertEquals("UTF8", ((Locator2) locators[0]).getEncoding());
    }
View Full Code Here
82
83
84
85
86
87
88
89
90
91
92
    @Override
    public void setup(Map<String, Object> parameters) {
        super.setup(parameters);

        this.saxParser = new SAXParser();
        try {
            this.saxParser.setFeature(BALANCE_TAGS_URI, true);
            this.saxParser.setProperty(ELEMS_URI, "lower");
            this.saxParser.setFeature(OVERRIDE_NAMESPACES_URI, true);
            this.saxParser.setFeature(INSERT_NAMESPACES_URI, true);
View Full Code Here
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
     */
    public void rewrite(Rewriter rewriter, java.io.Reader reader, java.io.Writer writer)
            throws RewriterException
    {
        // use a cyberneko SAXParser
        SAXParser parser = new SAXParser() ;

        // setup filter chain
        XMLDocumentFilter[] filters = {
            new Purifier(),                                                                                  // [1] standard neko purifications (tag balancing, etc)
            new CallbackElementRemover( rewriter ),                                                          // [2] accept / reject tags based on advice from rewriter
            writer != null ? new org.cyberneko.html.filters.Writer( writer, null ) : new DefaultFilter()     // [3] propagate results to specified writer (or do nothing -- Default -- when writer is null)
        };
       
        String filtersPropName = "http://cyberneko.org/html/properties/filters";
  
        try
        {
            parser.setProperty(filtersPropName, filters);
        }
        catch (SAXException e)
        {
            // either no longer supported (SAXNotSupportedException), or no logner recognized (SAXNotRecognizedException)
            log.error(filtersPropName + " is, unexpectedly, no longer defined for the cyberneko HTML parser",e);
            throw new RewriterException("cyberneko parser version not supported",e);
        }

        try
        {
            // parse from reader
            parser.parse(new XMLInputSource( null, null, null, reader, null )) ;
        }
        catch (IOException e)
        {
            String msg = "cyberneko HTML parsing failure";
            log.error(msg,e);
View Full Code Here
70
71
72
73
74
75
76
77
78
79
80
    @Override
    public void setup(Map<String, Object> parameters) {
        super.setup(parameters);

        this.saxParser = new SAXParser();
        try {
            this.saxParser.setFeature("http://cyberneko.org/html/features/balance-tags", true);
            this.saxParser.setProperty("http://cyberneko.org/html/properties/names/elems", "lower");
            this.saxParser.setFeature("http://cyberneko.org/html/features/override-namespaces", true);
            this.saxParser.setFeature("http://cyberneko.org/html/features/insert-namespaces", true);
View Full Code Here
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
        }
*/       
    }

    protected void parseHTML(String text) throws SAXException {
        SAXParser parser = new SAXParser();
        parser.setProperty(
            "http://cyberneko.org/html/properties/names/elems",
            "lower"
        );
        parser.setProperty(
            "http://cyberneko.org/html/properties/names/attrs",
            "lower"
        );
        parser.setContentHandler(
            new DefaultHandler() {
                public void startElement(String namespaceURI, String localName, String qName, Attributes atts) throws SAXException {
                    if ( validDocElementName( localName ) ) {
                        cm.startElement(namespaceURI, localName, qName, atts);
                    }
                }
                public void endElement(String namespaceURI, String localName, String qName) throws SAXException {
                    if ( validDocElementName( localName ) ) {
                        cm.endElement(namespaceURI, localName, qName);
                    }
                }
                public void characters(char[] ch, int start, int length) throws SAXException {
                    cm.characters(ch, start, length);
                }
            }
        );
        try {
            parser.parse( new InputSource(new StringReader( text )) );
        }
        catch (IOException e) {
            System.err.println( "This should never happen!" + e );
        }
    }
View Full Code Here
102
103
104
105
106
107
108
109
110
111
                new MatchingContentHandler(getTitleHandler(metadata), title),
                new MatchingContentHandler(getMetaHandler(metadata), meta));

        // Parse the HTML document
        xhtml.startDocument();
        SAXParser parser = new SAXParser();
        parser.setContentHandler(new XHTMLDowngradeHandler(handler));
        parser.parse(new InputSource(Utils.getUTF8Reader(stream, metadata)));
        xhtml.endDocument();
    }
View Full Code Here
101
102
103
104
105
106
107
108
109
                new MatchingContentHandler(getBodyHandler(xhtml), body),
                new MatchingContentHandler(getTitleHandler(metadata), title),
                new MatchingContentHandler(getMetaHandler(metadata), meta));

        // Parse the HTML document
        SAXParser parser = new SAXParser();
        parser.setContentHandler(new XHTMLDowngradeHandler(handler));
        parser.parse(new InputSource(Utils.getUTF8Reader(stream, metadata)));
    }
View Full Code Here
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
     */
    public void rewrite(Rewriter rewriter, java.io.Reader reader, java.io.Writer writer)
            throws RewriterException
    {
        // use a cyberneko SAXParser
        SAXParser parser = new SAXParser() ;

        // setup filter chain
        XMLDocumentFilter[] filters = {
            new Purifier(),                                                                                  // [1] standard neko purifications (tag balancing, etc)
            new CallbackElementRemover( rewriter ),                                                          // [2] accept / reject tags based on advice from rewriter
            writer != null ? new org.cyberneko.html.filters.Writer( writer, null ) : new DefaultFilter()     // [3] propagate results to specified writer (or do nothing -- Default -- when writer is null)
        };
       
        String filtersPropName = "http://cyberneko.org/html/properties/filters";
  
        try
        {
            parser.setProperty(filtersPropName, filters);
        }
        catch (SAXException e)
        {
            // either no longer supported (SAXNotSupportedException), or no logner recognized (SAXNotRecognizedException)
            log.error(filtersPropName + " is, unexpectedly, no longer defined for the cyberneko HTML parser",e);
            throw new RewriterException("cyberneko parser version not supported",e);
        }

        try
        {
            // parse from reader
            parser.parse(new XMLInputSource( null, null, null, reader, null )) ;
        }
        catch (IOException e)
        {
            String msg = "cyberneko HTML parsing failure";
            log.error(msg,e);
View Full Code Here
161
162
163
164
165
166
167
168
169
170
171
   * Initialize a Cyber Necko parser configured to return lower case element's names
   *
   * @return
   */
  private SAXParser initParser() {
    parser = new SAXParser();
    try {
      parser.setProperty("http://cyberneko.org/html/properties/names/elems", "lower");
      parser.setFeature("http://cyberneko.org/html/features/balance-tags/ignore-outside-content", false);
      parser.setFeature("http://cyberneko.org/html/features/balance-tags/document-fragment", true);
      parser.setFeature("http://cyberneko.org/html/features/report-errors", false);
View Full Code Here
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
  @Override
  public Parse parse(ContentEntity entity, Task newLink) throws DroidsException, IOException {
    // setup filter chain
    XMLDocumentFilter[] filters = { getRemover() };
    // create HTML parser
    SAXParser parser = getParser(filters);
    LinkExtractor linkExtractor = new LinkExtractor((Link)newLink, elements);
    parser.setContentHandler(linkExtractor);
    InputStream instream = entity.obtainContent();
    try {
      parser.parse(new InputSource(instream));
    } catch (SAXException ex) {
      throw new ContentFormatViolationException("Failure parsing HTML content", ex);
    } finally {
      instream.close();
    }
View Full Code Here
TOP

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

  • com.collabnet.labmanagement.api.LabManagementConnector
  • nokogiri.HtmlSaxParserContext
  • org.apache.cocoon.optional.pipeline.components.sax.neko.NekoGenerator
  • org.apache.commons.jelly.tags.html.ParseTag
  • org.apache.commons.jelly.util.TagXMLDoclet
  • org.apache.droids.parse.html.HtmlParser
  • org.apache.droids.solr.AdvancedSolrHandler
  • org.apache.jetspeed.rewriter.html.neko.NekoParserAdaptor
  • org.apache.lucene.benchmark.byTask.feeds.DemoHTMLParser$Parser
  • org.apache.portals.applications.webcontent.rewriter.html.neko.NekoParserAdaptor
    • 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.