Package org.apache.tika.sax

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

44
45
46
47
48
49
50
51
52
53
54
            DefaultStyledDocument sd = new DefaultStyledDocument();
            new RTFEditorKit().read(stream, sd, 0);

            XHTMLContentHandler xhtml =
                new XHTMLContentHandler(handler, metadata);
            xhtml.startDocument();
            xhtml.element("p", sd.getText(0, sd.getLength()));
            xhtml.endDocument();
        } catch (BadLocationException e) {
            throw new TikaException("Error parsing an RTF document", e);
        } catch (InternalError e) {
View Full Code Here
183
184
185
186
187
188
189
190
191
192
193
        metadata.set(Metadata.CONTENT_TYPE, "video/x-flv");
        metadata.set("hasVideo", Boolean.toString((typeFlags & MASK_VIDEO) != 0));
        metadata.set("hasAudio", Boolean.toString((typeFlags & MASK_AUDIO) != 0));

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

        // flv tag stream follows...
        while (true) {
            int type = datainput.read();
            if (type == -1) {
View Full Code Here
56
57
58
59
60
61
62
63
64
65
66
                throw new TikaException(type + " parse error", e);
            }
        }

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

    /**
     * @deprecated This method will be removed in Apache Tika 1.0.
View Full Code Here
62
63
64
65
66
67
68
69
70
71
72
    public void parse(
            InputStream stream, ContentHandler handler,
            Metadata metadata, ParseContext context)
            throws IOException, SAXException, TikaException {
        XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
        xhtml.startDocument();

        POIFSFileSystem filesystem = new POIFSFileSystem(stream);

        // Parse summary entries first, to make metadata available early
        parseSummaryEntryIfExists(
View Full Code Here
125
126
127
128
129
130
131
132
133
134
135
                reader.reset();
            }

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

            xhtml.startElement("p");
            char[] buffer = new char[4096];
            int n = reader.read(buffer);
            while (n != -1) {
View Full Code Here
54
55
56
57
58
59
60
61
62
63
64
                filesystem, DocumentSummaryInformation.DEFAULT_STREAM_NAME,
                metadata);

        XHTMLContentHandler xhtml =
            new XHTMLContentHandler(handler, metadata);
        xhtml.startDocument();
        xhtml.startElement("p");
        extractText(filesystem, new AppendableAdaptor(xhtml));
        xhtml.endElement("p");
        xhtml.endDocument();
    }
View Full Code Here
34
35
36
37
38
39
40
41
42
43
    public void parse(
            InputStream stream, ContentHandler handler, Metadata metadata)
            throws IOException, SAXException, TikaException {
        XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
        xhtml.startDocument();
        xhtml.endDocument();
    }

}
View Full Code Here
39
40
41
42
43
44
45
46
47
48
49
       
        Reader reader = Utils.getUTF8Reader(stream, metadata);
        metadata.set(Metadata.CONTENT_TYPE, "text/plain");

        XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
        xhtml.startDocument();
        xhtml.startElement("p");
        char[] buffer = new char[4096];
        for (int n = reader.read(buffer); n != -1; n = reader.read(buffer)) {
            xhtml.characters(buffer, 0, n);
        }
View Full Code Here
99
100
101
102
103
104
105
106
107
108
109
        xp.extractContent(xmlDoc, "nbPara", "//meta:document-statistic/@meta:paragraph-count", metadata);
        xp.extractContent(xmlDoc, "nbWord", "//meta:document-statistic/@meta:word-count", metadata);
        xp.extractContent(xmlDoc, "nbcharacter", "//meta:document-statistic/@meta:character-count", metadata);

        XHTMLContentHandler xhtml = new XHTMLContentHandler(handler, metadata);
        xhtml.startDocument();
        xhtml.startElement("p");
        xp.concatOccurrence(xmlDoc, "//*", " ", new AppendableAdaptor(xhtml));
        xhtml.endElement("p");
        xhtml.endDocument();
    }
View Full Code Here
53
54
55
56
57
58
59
60
61
62
            Metadata metadata, ParseContext context)
            throws IOException, SAXException, TikaException {
        new JpegExtractor(metadata).parse(stream);

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

}
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.