tutorial.PDFtoText.java Source code

Java tutorial

Introduction

Here is the source code for tutorial.PDFtoText.java

Source

/*
 * To change this license header, choose License Headers in Project Properties.
 * To change this template file, choose Tools | Templates
 * and open the template in the editor.
 */

package tutorial;

import com.itextpdf.text.pdf.PdfReader;
import com.itextpdf.text.pdf.parser.PdfReaderContentParser;
import com.itextpdf.text.pdf.parser.SimpleTextExtractionStrategy;
import com.itextpdf.text.pdf.parser.TextExtractionStrategy;
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.PrintWriter;
import java.util.StringTokenizer;
import javax.swing.JFileChooser;
import javax.swing.filechooser.FileNameExtensionFilter;

/**
 *
 * @author Zakaria
 */
public class PDFtoText extends javax.swing.JFrame {
    public JFileChooser fileChooser = new JFileChooser();

    /**
     * Creates new form PDFtoText
     */
    public PDFtoText() {
        initComponents();
    }

    /**
     * This method is called from within the constructor to initialize the form.
     * WARNING: Do NOT modify this code. The content of this method is always
     * regenerated by the Form Editor.
     */
    @SuppressWarnings("unchecked")
    // <editor-fold defaultstate="collapsed" desc="Generated Code">//GEN-BEGIN:initComponents
    private void initComponents() {

        jFileChooser1 = new javax.swing.JFileChooser();
        converting = new javax.swing.JButton();
        txtDirektori = new javax.swing.JTextField();
        tombolBrowse = new javax.swing.JButton();
        jLabel1 = new javax.swing.JLabel();
        jLabel2 = new javax.swing.JLabel();
        jLabel3 = new javax.swing.JLabel();

        setDefaultCloseOperation(javax.swing.WindowConstants.EXIT_ON_CLOSE);
        setBackground(new java.awt.Color(204, 204, 0));

        converting.setText("Converting");
        converting.addActionListener(new java.awt.event.ActionListener() {
            public void actionPerformed(java.awt.event.ActionEvent evt) {
                convertingActionPerformed(evt);
            }
        });

        tombolBrowse.setText("Browse..");
        tombolBrowse.addActionListener(new java.awt.event.ActionListener() {
            public void actionPerformed(java.awt.event.ActionEvent evt) {
                tombolBrowseActionPerformed(evt);
            }
        });

        jLabel1.setFont(new java.awt.Font("Tahoma", 1, 14)); // NOI18N
        jLabel1.setText("Convert PDF to Text");

        jLabel2.setText("zakariandys.com");

        jLabel3.setText("Browse file pdf:");

        javax.swing.GroupLayout layout = new javax.swing.GroupLayout(getContentPane());
        getContentPane().setLayout(layout);
        layout.setHorizontalGroup(layout.createParallelGroup(javax.swing.GroupLayout.Alignment.LEADING)
                .addGroup(layout.createSequentialGroup()
                        .addContainerGap(javax.swing.GroupLayout.DEFAULT_SIZE, Short.MAX_VALUE)
                        .addComponent(jLabel2))
                .addGroup(layout.createSequentialGroup().addGroup(layout
                        .createParallelGroup(javax.swing.GroupLayout.Alignment.LEADING)
                        .addGroup(layout.createSequentialGroup().addGap(135, 135, 135).addComponent(jLabel1))
                        .addGroup(layout.createSequentialGroup().addContainerGap()
                                .addGroup(layout.createParallelGroup(javax.swing.GroupLayout.Alignment.LEADING)
                                        .addComponent(converting)
                                        .addGroup(layout.createSequentialGroup()
                                                .addComponent(txtDirektori, javax.swing.GroupLayout.PREFERRED_SIZE,
                                                        319, javax.swing.GroupLayout.PREFERRED_SIZE)
                                                .addPreferredGap(javax.swing.LayoutStyle.ComponentPlacement.RELATED)
                                                .addComponent(tombolBrowse))
                                        .addGroup(layout.createSequentialGroup().addComponent(jLabel3).addGap(134,
                                                134, 134)))))
                        .addGap(0, 22, Short.MAX_VALUE)));
        layout.setVerticalGroup(layout.createParallelGroup(javax.swing.GroupLayout.Alignment.LEADING)
                .addGroup(layout.createSequentialGroup().addGap(10, 10, 10).addComponent(jLabel1).addGap(18, 18, 18)
                        .addComponent(jLabel3).addGap(8, 8, 8)
                        .addGroup(layout.createParallelGroup(javax.swing.GroupLayout.Alignment.BASELINE)
                                .addComponent(txtDirektori, javax.swing.GroupLayout.PREFERRED_SIZE,
                                        javax.swing.GroupLayout.DEFAULT_SIZE,
                                        javax.swing.GroupLayout.PREFERRED_SIZE)
                                .addComponent(tombolBrowse))
                        .addPreferredGap(javax.swing.LayoutStyle.ComponentPlacement.RELATED)
                        .addComponent(converting)
                        .addPreferredGap(javax.swing.LayoutStyle.ComponentPlacement.RELATED, 57, Short.MAX_VALUE)
                        .addComponent(jLabel2)));

        pack();
    }// </editor-fold>//GEN-END:initComponents

    private void convertingActionPerformed(java.awt.event.ActionEvent evt) {//GEN-FIRST:event_convertingActionPerformed
        try {
            convertPDFtoText();
        } catch (Exception e) {
            e.printStackTrace();
        }
    }//GEN-LAST:event_convertingActionPerformed

    private void tombolBrowseActionPerformed(java.awt.event.ActionEvent evt) {//GEN-FIRST:event_tombolBrowseActionPerformed
        // TODO add your handling code here:
        fileChooser.setFileSelectionMode(JFileChooser.FILES_ONLY);
        fileChooser.addChoosableFileFilter(new FileNameExtensionFilter("PDF Document", "pdf"));
        int result = fileChooser.showOpenDialog(this);
        if (result == JFileChooser.APPROVE_OPTION) {
            try {
                File selectedFile = fileChooser.getSelectedFile();
                txtDirektori.setText(selectedFile.getAbsolutePath());
            } catch (Exception ex) {
                System.out.println(ex);
            }
        } else {
            System.out.println("FIle acces cancelled by user");
        }
    }//GEN-LAST:event_tombolBrowseActionPerformed

    /**
     * @param args the command line arguments
     */
    public static void main(String args[]) {
        /* Set the Nimbus look and feel */
        //<editor-fold defaultstate="collapsed" desc=" Look and feel setting code (optional) ">
        /* If Nimbus (introduced in Java SE 6) is not available, stay with the default look and feel.
         * For details see http://download.oracle.com/javase/tutorial/uiswing/lookandfeel/plaf.html 
         */
        try {
            for (javax.swing.UIManager.LookAndFeelInfo info : javax.swing.UIManager.getInstalledLookAndFeels()) {
                if ("Nimbus".equals(info.getName())) {
                    javax.swing.UIManager.setLookAndFeel(info.getClassName());
                    break;
                }
            }
        } catch (ClassNotFoundException ex) {
            java.util.logging.Logger.getLogger(PDFtoText.class.getName()).log(java.util.logging.Level.SEVERE, null,
                    ex);
        } catch (InstantiationException ex) {
            java.util.logging.Logger.getLogger(PDFtoText.class.getName()).log(java.util.logging.Level.SEVERE, null,
                    ex);
        } catch (IllegalAccessException ex) {
            java.util.logging.Logger.getLogger(PDFtoText.class.getName()).log(java.util.logging.Level.SEVERE, null,
                    ex);
        } catch (javax.swing.UnsupportedLookAndFeelException ex) {
            java.util.logging.Logger.getLogger(PDFtoText.class.getName()).log(java.util.logging.Level.SEVERE, null,
                    ex);
        }
        //</editor-fold>

        /* Create and display the form */
        java.awt.EventQueue.invokeLater(new Runnable() {
            public void run() {
                new PDFtoText().setVisible(true);
            }
        });
    }

    // Variables declaration - do not modify//GEN-BEGIN:variables
    private javax.swing.JButton converting;
    private javax.swing.JFileChooser jFileChooser1;
    private javax.swing.JLabel jLabel1;
    private javax.swing.JLabel jLabel2;
    private javax.swing.JLabel jLabel3;
    private javax.swing.JButton tombolBrowse;
    private javax.swing.JTextField txtDirektori;
    // End of variables declaration//GEN-END:variables

    public void convertPDFtoText() throws IOException {
        /*variabel "pdf" digunakan untuk menampung alamat direktori tempat file pdf disimpan.*/
        String pdf = txtDirektori.getText();
        StringBuilder text = new StringBuilder();
        String resultText;

        /*Buat file Text ".txt"*/
        File namaFile = new File(txtDirektori.getText().replace("pdf", "txt"));
        if (namaFile.createNewFile()) {
            System.out.println("File .txt berhasil dibuat.");
        }

        try {
            /*Panggil class yang ada pada library iText untuk membaca file PDF*/
            PdfReader reader = new PdfReader(pdf);
            PdfReaderContentParser parser = new PdfReaderContentParser(reader);
            TextExtractionStrategy strategy;
            for (int i = 1; i <= reader.getNumberOfPages(); i++) {
                strategy = parser.processContent(i, new SimpleTextExtractionStrategy());
                text.append(strategy.getResultantText());
            }
            resultText = text.toString();

            /*Code untuk menuliskan hasil pembacaan file PDF ke file Text*/
            StringTokenizer stringTokenizer = new StringTokenizer(resultText, "\n");
            PrintWriter lineWriter = new PrintWriter(new FileOutputStream(namaFile));
            while (stringTokenizer.hasMoreTokens()) {
                String curToken = stringTokenizer.nextToken();
                lineWriter.println(curToken);
            }
            lineWriter.flush();
            lineWriter.close();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

}