Package org.apache.tika.sax

Examples of org.apache.tika.sax.TeeContentHandler


    }
   
    @Override
    public ParsedDatum call() throws Exception {
        try {
            TeeContentHandler teeContentHandler;
            ProfilingHandler profilingHandler = null;
           
            if (_extractLanguage) {
                profilingHandler = new ProfilingHandler();
                teeContentHandler = new TeeContentHandler(_contentExtractor, _linkExtractor, profilingHandler);
            } else {
                teeContentHandler = new TeeContentHandler(_contentExtractor, _linkExtractor);
            }

            if (_parseContext == null) {
                _parseContext = makeParseContext();
            }
View Full Code Here


            "<p>It is located in Amherst, MA.</p></body></html>";
    //<start id="tika-html"/>
    InputStream input = new ByteArrayInputStream(html.getBytes(Charset.forName("UTF-8")));
    ContentHandler text = new BodyContentHandler();//<co id="html.text.co"/>
    LinkContentHandler links = new LinkContentHandler();//<co id="html.link.co"/>
    ContentHandler handler = new TeeContentHandler(links, text);//<co id="html.merge"/>
    Metadata metadata = new Metadata();//<co id="html.store"/>
    Parser parser = new HtmlParser();//<co id="html.parser"/>
    ParseContext context = new ParseContext();
    parser.parse(input, handler, metadata, context);//<co id="html.parse"/>
    System.out.println("Title: " + metadata.get(Metadata.TITLE));
View Full Code Here

                        }
                    }
                }
            };
            new HtmlParser().parse(
                    stream, new TeeContentHandler(body, link),
                    metadata, new ParseContext());
        } finally {
            stream.close();
        }
View Full Code Here

            StringWriter htmlBuffer = new StringWriter();
            StringWriter textBuffer = new StringWriter();
            StringWriter xmlBuffer = new StringWriter();
            StringBuilder metadataBuffer = new StringBuilder();

            ContentHandler handler = new TeeContentHandler(
                    getHtmlHandler(htmlBuffer),
                    getTextContentHandler(textBuffer),
                    getXmlContentHandler(xmlBuffer));

            input = new ProgressMonitorInputStream(
View Full Code Here

     */
    public void parse(
            InputStream stream, ContentHandler handler, Metadata metadata)
            throws IOException, SAXException, TikaException {
        StringWriter writer = new StringWriter();
        handler = new TeeContentHandler(
                handler, new WriteOutContentHandler(writer));
        super.parse(stream, handler, metadata);

        String content = writer.toString();
        metadata.set("fulltext", content);
View Full Code Here

        Matcher matcher = new CompositeMatcher(
                META_XPATH.parse("//meta:" + element),
                META_XPATH.parse("//meta:" + element + "//text()"));
        ContentHandler branch =
            new MatchingContentHandler(new MetadataHandler(md, name), matcher);
        return new TeeContentHandler(ch, branch);
    }
View Full Code Here

                META_XPATH.parse("//meta:user-defined/@meta:name"),
                META_XPATH.parse("//meta:user-defined//text()"));
        ContentHandler branch = new MatchingContentHandler(
              new AttributeDependantMetadataHandler(md, "meta:name", USER_DEFINED_METADATA_NAME_PREFIX),
              matcher);
        return new TeeContentHandler(ch, branch);
    }
View Full Code Here

            ContentHandler ch, Metadata md, String name, String attribute) {
        Matcher matcher =
            META_XPATH.parse("//meta:document-statistic/@meta:" + attribute);
        ContentHandler branch =
            new MatchingContentHandler(new MetadataHandler(md, name), matcher);
        return new TeeContentHandler(ch, branch);
    }
View Full Code Here

                        }
                    }
                }
            };
            new HtmlParser().parse(
                    stream, new TeeContentHandler(body, link),
                    metadata, new ParseContext());
        } finally {
            stream.close();
        }
View Full Code Here

                    (Property) tikaMetadata);
        }
       
        protected ContentHandler getContentHandler(
                ContentHandler handler, Metadata metadata, ParseContext context) {
            return new TeeContentHandler(
                    super.getContentHandler(handler, metadata, context),
                    getCustomElementHandler(metadata, FIRST_NAME, "FirstName"),
                    getCustomElementHandler(metadata, LAST_NAME, "LastName"));
        }
View Full Code Here

TOP

Related Classes of org.apache.tika.sax.TeeContentHandler

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.