Package org.apache.tika.sax

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


            xhtml.characters("\n");

            xhtml.element("p", year);
            xhtml.characters("\n");

            xhtml.element("p", comment);
            xhtml.characters("\n");

            xhtml.element("p", GENRES[Math.min(genre, GENRES.length - 1)]);
            xhtml.characters("\n");
        }
View Full Code Here


                parse((DocumentEntry) entry, metadata);
            } else if ("WordDocument".equals(name)) {
                setType(metadata, "application/msword");
                WordExtractor extractor = new WordExtractor(filesystem);
                for (String paragraph : extractor.getParagraphText()) {
                    xhtml.element("p", paragraph);
                }
            } else if ("PowerPoint Document".equals(name)) {
                setType(metadata, "application/vnd.ms-powerpoint");
                PowerPointExtractor extractor =
                    new PowerPointExtractor(filesystem);
View Full Code Here

                }
            } else if ("PowerPoint Document".equals(name)) {
                setType(metadata, "application/vnd.ms-powerpoint");
                PowerPointExtractor extractor =
                    new PowerPointExtractor(filesystem);
                xhtml.element("p", extractor.getText(true, true));
            } else if ("Workbook".equals(name)) {
                setType(metadata, "application/vnd.ms-excel");
                new ExcelExtractor().parse(filesystem, xhtml);
            } else if ("VisioDocument".equals(name)) {
                setType(metadata, "application/vnd.visio");
View Full Code Here

            xhtml.characters("\n");

            xhtml.element("p", comment);
            xhtml.characters("\n");

            xhtml.element("p", GENRES[Math.min(genre, GENRES.length - 1)]);
            xhtml.characters("\n");
        }

        xhtml.endDocument();
    }
View Full Code Here

            } else if ("VisioDocument".equals(name)) {
                setType(metadata, "application/vnd.visio");
                VisioTextExtractor extractor =
                    new VisioTextExtractor(filesystem);
                for (String text : extractor.getAllText()) {
                    xhtml.element("p", text);
                }
            } else if (name.startsWith("__substg1.0_")) {
                setType(metadata, "application/vnd.ms-outlook");
                new OutlookExtractor(filesystem).parse(xhtml, metadata);
            }
View Full Code Here

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

            xhtml.element("h1", title);
            xhtml.element("p", description);

            xhtml.startElement("ul");
            for (Object e : feed.getEntries()) {
                SyndEntry entry = (SyndEntry) e;
View Full Code Here

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

            xhtml.element("h1", title);
            xhtml.element("p", description);

            xhtml.startElement("ul");
            for (Object e : feed.getEntries()) {
                SyndEntry entry = (SyndEntry) e;
                String link = entry.getLink();
View Full Code Here

            switch (type) {
                case PUBLISHER:
                    PublisherTextExtractor publisherTextExtractor =
                        new PublisherTextExtractor(filesystem);
                    xhtml.element("p", publisherTextExtractor.getText());
                    break;
                case WORDDOCUMENT:
                    new WordExtractor(context).parse(filesystem, xhtml);
                    break;
                case POWERPOINT:
View Full Code Here

                    break;
                case VISIO:
                    VisioTextExtractor visioTextExtractor =
                        new VisioTextExtractor(filesystem);
                    for (String text : visioTextExtractor.getAllText()) {
                        xhtml.element("p", text);
                    }
                    break;
                case OUTLOOK:
                    if (!outlookExtracted) {
                        outlookExtracted = true;
View Full Code Here

           metadata.set(XMPDM.ALBUM, tag.getAlbum());
           metadata.set(XMPDM.RELEASE_DATE, tag.getYear());
           metadata.set(XMPDM.GENRE, tag.getGenre());
           metadata.set(XMPDM.LOG_COMMENT, tag.getComment());

           xhtml.element("h1", tag.getTitle());
           xhtml.element("p", tag.getArtist());

            // ID3v1.1 Track addition
            if (tag.getTrackNumber() != null) {
                xhtml.element("p", tag.getAlbum() + ", track " + tag.getTrackNumber());
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.