Package org.ccil.cowan.tagsoup

Examples of org.ccil.cowan.tagsoup.Parser

119
120
121
122
123
124
125
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
163
164
165
166
167
168
169
170
171
172
173
174
        URL url = new URL(page);
        File file = new File(targetDir, ".manualCache-" + url.getFile().substring(1));
       
        try {
            HttpURLConnection con = (HttpURLConnection)url.openConnection();
            XMLReader parser = new Parser();
            parser.setFeature(Parser.namespacesFeature, false);
            parser.setFeature(Parser.namespacePrefixesFeature, false);
            parser.setProperty(Parser.schemaProperty, new org.ccil.cowan.tagsoup.HTMLSchema() {
                {
                    //problem with nested lists that the confluence {toc} macro creates
                    elementType("ul", M_LI, M_BLOCK | M_LI, 0);
                }
            });
           
            StringWriter w = new StringWriter();
            XMLWriter xmlWriter = new XMLWriter(w) {
                int inDiv = Integer.MAX_VALUE;
                int count;
                public void characters(char ch[], int start, int len)
                    throws SAXException {
                    if (inDiv <= count) {
                        super.characters(ch, start, len);
                    }
                }
                public void startElement(String uri, String localName, String qName, Attributes atts)
                    throws SAXException {
                    count++;
                    if ("div".equalsIgnoreCase(qName)
                        && "wiki-content maincontent".equalsIgnoreCase(atts.getValue("class"))) {
                        inDiv = count;
                    }
                    if (inDiv <= count) {
                        super.startElement(uri, localName, qName, atts);
                    }
                }
                public void endElement(String uri, String localName, String qName) throws SAXException {
                    if (inDiv <= count) {
                        super.endElement(uri, localName, qName);
                    }
                    count--;
                    if (inDiv > count) {
                        inDiv = Integer.MAX_VALUE;
                    }
                }
            };
            xmlWriter.setOutputProperty(XMLWriter.OMIT_XML_DECLARATION, "yes");
            xmlWriter.setOutputProperty(XMLWriter.METHOD, "html");
            parser.setContentHandler(xmlWriter);
            long date = con.getLastModified();
            parser.parse(new InputSource(new BufferedInputStream(con.getInputStream())));

           
            FileWriter writer = new FileWriter(file);
            writer.write(Long.toString(date));
            writer.close();
View Full Code Here
274
275
276
277
278
279
280
281
282
283
284
285
    }

    private XdmNode tagSoup(String text) {
        StringReader inputStream = new StringReader(text);
        InputSource source = new InputSource(inputStream);
        Parser parser = new Parser();
        parser.setEntityResolver(runtime.getResolver());
        SAXSource saxSource = new SAXSource(parser, source);
        DocumentBuilder builder = runtime.getProcessor().newDocumentBuilder();
        try {
            XdmNode doc = builder.build(saxSource);
            return doc;
View Full Code Here
252
253
254
255
256
257
258
259
260
261
262
263
264
          parser.setEntityResolver(new XMLEntityResolverDefaultHandler(validator));
          parser.parse(xml);
          return parser.getDocument();*/
        }
       
        XMLReader reader = new Parser();
            reader.setFeature(Parser.namespacesFeature, true);
            reader.setFeature(Parser.namespacePrefixesFeature, true);
       
        try {
            Transformer transformer = TransformerFactory.newInstance().newTransformer();
           
            DOMResult result = new DOMResult();
View Full Code Here
87
88
89
90
91
92
93
94
95
96
97
 
    public ConvertHTML(CommandBuilder builder, Config config, Command parent, Command child, MorphlineContext context) throws SAXNotRecognizedException, SAXNotSupportedException {
      super(builder, config, parent, child, context);
      this.charset = getConfigs().getCharset(config, "charset", null);
      this.omitXMLDeclaration = getConfigs().getBoolean(config, "omitXMLDeclaration", false);     
      this.xmlReader = new Parser(); // no reuse?
      xmlReader.setProperty(Parser.schemaProperty, htmlSchema);
      xmlReader.setFeature(Parser.CDATAElementsFeature, getConfigs().getBoolean(config, "noCDATA", false));
      xmlReader.setFeature(Parser.namespacesFeature, !getConfigs().getBoolean(config, "noNamespaces", true));
      xmlReader.setFeature(Parser.ignoreBogonsFeature, getConfigs().getBoolean(config, "noBogons", false)); // also see TIKA-599
      xmlReader.setFeature(Parser.bogonsEmptyFeature, getConfigs().getBoolean(config, "emptyBogons", false));
View Full Code Here
87
88
89
90
91
92
93
94
95
96
97
 
    public ConvertHTML(CommandBuilder builder, Config config, Command parent, Command child, MorphlineContext context) throws SAXNotRecognizedException, SAXNotSupportedException {
      super(builder, config, parent, child, context);
      this.charset = getConfigs().getCharset(config, "charset", null);
      this.omitXMLDeclaration = getConfigs().getBoolean(config, "omitXMLDeclaration", false);     
      this.xmlReader = new Parser(); // no reuse?
      xmlReader.setProperty(Parser.schemaProperty, htmlSchema);
      xmlReader.setFeature(Parser.CDATAElementsFeature, getConfigs().getBoolean(config, "noCDATA", false));
      xmlReader.setFeature(Parser.namespacesFeature, !getConfigs().getBoolean(config, "noNamespaces", true));
      xmlReader.setFeature(Parser.ignoreBogonsFeature, getConfigs().getBoolean(config, "noBogons", false)); // also see TIKA-599
      xmlReader.setFeature(Parser.bogonsEmptyFeature, getConfigs().getBoolean(config, "emptyBogons", false));
View Full Code Here
28
29
30
31
32
33
34
35
36
37
38
import fueltrack.server.motormouth.model.FuelPriceRecord;

public class HTMLParser {
  public static List<FuelPriceRecord> parseHTML(Reader htmlInputReader) throws IOException, SAXException, TransformerException, TransformerFactoryConfigurationError {
    SimpleDateFormat format = new SimpleDateFormat("dd/MM/yy h:mm a");
    XMLReader reader = new Parser();
   
    Source s = new SAXSource(reader, new InputSource(htmlInputReader));
    DOMResult r = new DOMResult();
   
    TransformerFactory.newInstance().newTransformer(new StreamSource(HTMLParser.class.getClassLoader().getResourceAsStream("fueltrack/server/motormouth/TransformHTML.xsl"))).transform(s, r);
View Full Code Here
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
      return null;
    }
   
    final StringBuilder builder = new StringBuilder();
   
    XMLReader reader = new Parser();
   
    reader.setContentHandler(new DefaultHandler() {
      @Override
      public void startElement(String uri, String localName, String qName, Attributes attributes) throws SAXException {
        super.startElement(uri, localName, qName, attributes);
       
        if ("input".equalsIgnoreCase(localName)) {
          if (tagName.equalsIgnoreCase(attributes.getValue("name"))) {
            builder.append(attributes.getValue("value"));
            throw new SAXTerminateProcessing();
          }
        }
      }
    });
   
    try {
      reader.parse(new InputSource(htmlInputReader));
    } catch (SAXTerminateProcessing e) {}
   
    return builder.toString();
  }
View Full Code Here
84
85
86
87
88
89
90
91
92
93
94
  private Parser getParser() throws SAXNotSupportedException, SAXNotRecognizedException
    {
    if( parser != null )
      return parser;

    parser = new Parser();
    parser.setProperty( Parser.schemaProperty, getSchema() );

    if( features != null )
      {
      for( Map.Entry<String, Boolean> entry : features.entrySet() )
View Full Code Here
96
97
98
99
100
101
102
103
104
105
106
107
108
                    builderFactory.setIgnoringElementContentWhitespace(true);
                    DocumentBuilder builder = builderFactory.newDocumentBuilder();
                    document = builder.parse(is);
                } else if (contentType.matches("text/html.*")) {
                    DOMHandler domHandler = new DOMHandler();
                    Parser parser = new Parser();
                    parser.setContentHandler(domHandler);
                    parser.parse(new InputSource(is));
                    document = domHandler.getDocument();
                }
                if (document != null) {
                    document.getDocumentElement().normalize();
                    rootElement = document.getDocumentElement();
View Full Code Here
TOP

Related Classes of org.ccil.cowan.tagsoup.Parser

  • bixo.parser.DOMParser
  • bixo.parser.SimpleParserTest
  • cascading.operation.xml.TagSoupParser
  • ch.randelshofer.scorm.TagSoupAutoDetector
  • com.cloudera.cdk.morphline.saxon.ConvertHTMLBuilder$ConvertHTML
  • com.xmlcalabash.library.UnescapeMarkup
  • de.danet.an.workflow.tools.webclient.BrowserTool
  • fueltrack.server.motormouth.HTMLParser
  • helma.util.XmlUtils
  • info.bliki.wiki.addon.test.util.TagSoupConversion
    • 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.