Using Lucene to parse the content of PDF text

/*
* The function of this code is to use Pdfbox.zip's package
* Use Lucene to parse the content of PDF text
* Read the contents of the PDF file. It is then re-written to a. txt file of the same name

* */

Results:

Package PDFBox;


Import Java.io.File;
Import Java.io.FileOutputStream;
Import Java.io.OutputStreamWriter;
Import Java.io.Writer;
Import java.net.MalformedURLException;
Import Java.net.URL;


Import org.pdfbox.pdmodel.PDDocument;
Import Org.pdfbox.util.PDFTextStripper;


public class PDFBox {


Public PDFBox () {
TODO auto-generated Constructor stub

}
public void Getext (String file) throws exception{
Whether to sort
Boolean sort = false;

PDF name
String pdffile = file;

Enter a text file name
String textfile = null;


Setting the Encoding method
String encoding = "UTF-8";

Start extracting pages
int startpage = 1;

End Fetch Pages
int endpage = Integer.max_value;

File input stream, generating a text file
Writer output = null;

In-Memory stored PDF Document
PDDocument document = null;

try{
try{
To load a file first as a URL,
If you get an exception and then load the file from the local file system
URL url = new URL (pdffile);
Document = Pddocument.load (URL);

Get the file name of the PDF
String fileName = Url.getfile ();

Original PDF names to name the newly generated TXT file
if (Filename.length () > 4) {
File OutputFile = new file (filename.substring (0, Filename.length ()-4) + ". txt");
Textfile = Outputfile.getname ();
}
}catch (Malformedurlexception R) {

Mount from file system if loaded as URL to exception
Document = Pddocument.load (Pdffile);
if (Pdffile.length () > 4) {
Textfile = pdffile.substring (0, Pdffile.length ()-4) + ". txt";
}

}
File input stream, write file to Textfile
Output = new OutputStreamWriter (new FileOutputStream (textfile), encoding);

Pdftextstripprt to extract Files
Pdftextstripper stripper = null;
Stripper = new Pdftextstripper ();

Set whether to sort
Stripper.setsortbyposition (sort);

Set Start Page
Stripper.setstartpage (StartPage);

Set End page
Stripper.setendpage (EndPage);

Call Pdftextstripper's Writertext extract and output
Stripper.writetext (document, output);




}finally{
Turn off the output stream
if (output! = NULL)
Output.close ();
}
Close PDF Document
if (document! = NULL) {
Document.close ();
}


}


public static void Main (string[] args) {
TODO auto-generated Method Stub
PDFBox test = new PDFBox ();
try{
Gets the C language code under the E:\Lucene project. PDF content
Test.getext ("E:\\lucene Project \\c language code. pdf");

}catch (Exception e) {
E.printstacktrace ();
}



}


}

Using Lucene to parse the content of PDF text