Examples of org.apache.tika.sax.xpath.MatchingContentHandler

org.apache.tika.sax.xpath.MatchingContentHandler
Content handler decorator that only passes the elements, attributes, and text nodes that match the given XPath expression. Note especially that {@link #startDocument()} and {@link #endDocument()} events are notpassed to the decorated handler.

          }
          if (xpathExpr != null) {
            Matcher matcher =
                    PARSER.parse(xpathExpr);
            serializer.startDocument();//The MatchingContentHandler does not invoke startDocument.  See http://tika.markmail.org/message/kknu3hw7argwiqin
            parsingHandler = new MatchingContentHandler(serializer, matcher);
          } else {
            parsingHandler = serializer;
          }
        } else if (xpathExpr != null) {
          Matcher matcher =
                  PARSER.parse(xpathExpr);
          parsingHandler = new MatchingContentHandler(handler, matcher);
        } //else leave it as is


        //potentially use a wrapper handler for parsing, but we still need the SolrContentHandler for getting the document.
        parser.parse(inputStream, parsingHandler, metadata);
        if (extractOnly == false) {

View Full Code Here

            ContentHandler ch, Metadata md, Property property, String element) {
        Matcher matcher = new CompositeMatcher(
                META_XPATH.parse("//meta:" + element),
                META_XPATH.parse("//meta:" + element + "//text()"));
        ContentHandler branch =
            new MatchingContentHandler(new MetadataHandler(md, property), matcher);
        return new TeeContentHandler(ch, branch);
    }

View Full Code Here

            ContentHandler ch, Metadata md) {
        Matcher matcher = new CompositeMatcher(
                META_XPATH.parse("//meta:user-defined/@meta:name"),
                META_XPATH.parse("//meta:user-defined//text()"));
        // eg <meta:user-defined meta:name="Info1">Text1</meta:user-defined> becomes custom:Info1=Text1
        ContentHandler branch = new MatchingContentHandler(
              new AttributeDependantMetadataHandler(md, "meta:name", Metadata.USER_DEFINED_METADATA_NAME_PREFIX),
              matcher);
        return new TeeContentHandler(ch, branch);
    }

View Full Code Here


    @Deprecated private static ContentHandler getStatistic(
            ContentHandler ch, Metadata md, String name, String attribute) {
        Matcher matcher =
            META_XPATH.parse("//meta:document-statistic/@meta:"+attribute);
        ContentHandler branch = new MatchingContentHandler(
              new AttributeMetadataHandler(META_NS, attribute, md, name), matcher);
        return new TeeContentHandler(ch, branch);
    }

View Full Code Here

    }
    private static ContentHandler getStatistic(
          ContentHandler ch, Metadata md, Property property, String attribute) {
      Matcher matcher =
          META_XPATH.parse("//meta:document-statistic/@meta:"+attribute);
      ContentHandler branch = new MatchingContentHandler(
            new AttributeMetadataHandler(META_NS, attribute, md, property), matcher);
      return new TeeContentHandler(ch, branch);
  }

View Full Code Here

     * given underlying content handler.
     *
     * @param handler content handler
     */
    public BodyContentHandler(ContentHandler handler) {
        super(new MatchingContentHandler(handler, MATCHER));
    }

View Full Code Here

     * given underlying content handler.
     *
     * @param handler content handler
     */
    public BodyContentHandler(ContentHandler handler) {
        super(new MatchingContentHandler(handler, MATCHER));
    }

View Full Code Here

            ContentHandler ch, Metadata md, String name, String element) {
        Matcher matcher = new CompositeMatcher(
                DC_XPATH.parse("//dc:" + element),
                DC_XPATH.parse("//dc:" + element + "//text()"));
        ContentHandler branch =
            new MatchingContentHandler(new MetadataHandler(md, name), matcher);
        return new TeeContentHandler(ch, branch);
    }

View Full Code Here

        XPathParser xpath = new XPathParser(null, "");
        Matcher body = xpath.parse("/HTML/BODY//node()");
        Matcher title = xpath.parse("/HTML/HEAD/TITLE//node()");
        Matcher meta = xpath.parse("/HTML/HEAD/META//node()");
        handler = new TeeContentHandler(
                new MatchingContentHandler(getBodyHandler(xhtml), body),
                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));

View Full Code Here

            ContentHandler ch, Metadata md, String name, String element) {
        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

0 1 2 3 4

TOP

Related Classes of org.apache.tika.sax.xpath.MatchingContentHandler

com.cloudera.cdk.morphline.solrcell.SolrCellBuilder$SolrCell

org.apache.solr.handler.extraction.ExtractingDocumentLoader

org.apache.tika.example.ContentHandlerExample

org.apache.tika.parser.html.HtmlParser

org.apache.tika.parser.odf.OpenDocumentMetaParser

org.apache.tika.parser.opendocument.OpenOfficeMetaParser

org.apache.tika.parser.xml.DcXMLParser

org.apache.tika.sax.BodyContentHandler

org.kitesdk.morphline.solrcell.SolrCellBuilder$SolrCell

org.xml.sax.helpers.AttributesImpl

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.