Package org.apache.tika.sax

Examples of org.apache.tika.sax.XHTMLContentHandler.startElement()


        extractContent(xmlDoc, Metadata.LANGUAGE, "//dc:language", metadata);
        extractContent(xmlDoc, Metadata.RIGHTS, "//dc:rights", metadata);

        XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
        xhtml.startDocument();
        xhtml.startElement("p");
        concatOccurrence(xmlDoc, "//*", " ", new AppendableAdaptor(xhtml));
        xhtml.endElement("p");
        xhtml.endDocument();
    }

View Full Code Here


            XHTMLContentHandler xhtml =
                new XHTMLContentHandler(handler, metadata);
            xhtml.startDocument();

            xhtml.startElement("p");
            char[] buffer = new char[4096];
            int n = reader.read(buffer);
            while (n != -1) {
                xhtml.characters(buffer, 0, n);
                n = reader.read(buffer);
View Full Code Here

        xhtml.startDocument();

        ArchiveEntry entry = archive.getNextEntry();
        while (entry != null) {
            if (!entry.isDirectory()) {
                xhtml.startElement("div", "class", "package-entry");
                Metadata entrydata = new Metadata();
                String name = entry.getName();
                if (name != null && name.length() > 0) {
                    entrydata.set(Metadata.RESOURCE_NAME_KEY, name);
                    xhtml.element("h1", name);
View Full Code Here

                    // Blank line is signal that we're transitioning to the content.
                    saveHeaderInMetadata(numEmails, metadata, multiLine);
                    parseState = ParseStates.IN_CONTENT;

                    // Mimic what PackageParser does between entries.
                    xhtml.startElement("div", "class", "email-entry");
                    xhtml.startElement("p");
                    inQuote = false;
                } else if (curLine.startsWith(" ") || curLine.startsWith("\t")) {
                    multiLine += " " + curLine.trim();
                } else {
View Full Code Here

                    saveHeaderInMetadata(numEmails, metadata, multiLine);
                    parseState = ParseStates.IN_CONTENT;

                    // Mimic what PackageParser does between entries.
                    xhtml.startElement("div", "class", "email-entry");
                    xhtml.startElement("p");
                    inQuote = false;
                } else if (curLine.startsWith(" ") || curLine.startsWith("\t")) {
                    multiLine += " " + curLine.trim();
                } else {
                    saveHeaderInMetadata(numEmails, metadata, multiLine);
View Full Code Here

            } else if (type == Sequence.SMPTE_24) {
                metadata.set("divisionType", String.valueOf(type));
            }

            for (Track track : tracks) {
                xhtml.startElement("p");
                for (int i = 0; i < track.size(); i++) {
                    MidiMessage message = track.get(i).getMessage();
                    if (message instanceof MetaMessage) {
                        MetaMessage meta = (MetaMessage) message;
                        // Types 1-15 are reserved for text events
View Full Code Here

                        if (!quoted) {
                            xhtml.endElement("q");
                            inQuote = false;
                        }
                    } else if (quoted) {
                        xhtml.startElement("q");
                        inQuote = true;
                    }

                    xhtml.characters(curLine);
View Full Code Here

                // call next handler if no filtering
                if (completelyFiltered == 0) {
                    // special handling of text:h, that are directly passed
                    // to xhtml handler
                    if (TEXT_NS.equals(namespaceURI) && "h".equals(localName)) {
                        xhtml.startElement(headingStack.push(
                                getXHTMLHeaderTagName(atts)));
                    } else {
                        super.startElement(
                                namespaceURI, localName, qName, atts);
                    }
View Full Code Here

        }

        final XHTMLContentHandler xhtml =
            new XHTMLContentHandler(handler, metadata);
        xhtml.startDocument();
        xhtml.startElement("p");

        getSAXParser(context).parse(
                new CloseShieldInputStream(stream),
                new OfflineContentHandler(
                        getContentHandler(handler, metadata)));
View Full Code Here

            if (link == null)
                continue;
            SyndContent description = entry.getDescription();

            String title = stripTags(entry.getTitleEx());
            xhtml.startElement("a", "href", link);
            xhtml.characters(title);
            xhtml.endElement("a");
            xhtml.startElement("p");
            if (description != null)
                xhtml.characters(description.getValue());
View Full Code Here

TOP
Copyright © 2018 www.massapi.com. 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.