import
org.apache.tika.exception.TikaException;
import
org.apache.tika.metadata.Metadata;
import
org.apache.tika.parser.ParseContext;
import
org.apache.tika.parser.odf.OpenDocumentParser;
import
org.apache.tika.sax.BodyContentHandler;
import
org.xml.sax.SAXException;
import
java.io.File;
import
java.io.FileInputStream;
import
java.io.IOException;
import
sun.security.util.Length;
public
class
OdfContentExtractor {
public
static
void
main(String[] args)
{
try
{
BodyContentHandler handler
=
new
BodyContentHandler();
Metadata metadata =
new
Metadata();
FileInputStream inputstream
=
new
FileInputStream(
new
File(
"F:\\geeks.odt"
));
ParseContext parsecontent =
new
ParseContext();
OpenDocumentParser opendocumentparser
=
new
OpenDocumentParser();
opendocumentparser.parse(inputstream, handler,
metadata,
parsecontent);
System.out.println(
"Content in the document :"
+ handler.toString());
System.out.println(
"Metadata of the document:"
);
String[] metaName = metadata.names();
int
l = metaName.length;
for
(
int
i =
0
; i < l; i++) {
System.out.println(
metaName[i]
+
" : = "
+ metadata.get(metaName[i]));
}
}
catch
(Exception e) {
System.out.println(
"failed to extract content due to "
+ e);
}
}
}