Split a PDF and email based on text contained in the PDF

// get first Page in PDF Document
PDFPage page = pdfDoc.getPage(0);
// Get text contained within a rectangle in a PDF page 
TextSelection selection = page.getTextInArea(rectangle);

import java.awt.Color;
import java.awt.Graphics2D;
import java.awt.Rectangle;
import java.io.File;
import java.io.IOException;
import java.text.SimpleDateFormat;
import java.util.Date;
import java.util.Hashtable;
import java.util.logging.Level;
 
import com.qoppa.pas.api.CustomProcess;
import com.qoppa.pas.api.JobStatus;
import com.qoppa.pas.api.ServerContext;
import com.qoppa.pas.api.WorkingBundle;
import com.qoppa.pas.api.service.EmailService;
import com.qoppa.pas.api.service.EmailService.Email;
import com.qoppa.pas.api.service.LogService;
import com.qoppa.pdf.PDFException;
import com.qoppa.pdf.TextSelection;
import com.qoppa.pdfProcess.PDFDocument;
import com.qoppa.pdfProcess.PDFPage;
 
public class SplitAndEmail implements CustomProcess
{
// Change this to always show the "search" rectangles 
// on the output documents so you can identify them visually 
private static final boolean DEBUG_RECTANGLES = false;
 
// Define the rectangles for the text / fields to be identified on the page 
// These coordinates are in 72 dpi.
	private static final Rectangle RECT_DEPT = new Rectangle(90, 133, 250, 10);
	private static final Rectangle RECT_RECORD_NUMBER = new Rectangle(220, 298, 80, 10);
	private static final Rectangle RECT_DATE = new Rectangle(220, 320, 90, 10);
	private static final Rectangle RECT_TIME = new Rectangle(400, 320, 70, 10);
 
	// This is the formatter for the date/time filenames
	// Change this to meet your needs. Look at
	// https://docs.oracle.com/javase/8/docs/api/java/text/SimpleDateFormat.html
	private static final SimpleDateFormat FORMAT_DATE = new SimpleDateFormat("EEEE MMM d yyyy 'at' h_mm_ss a");
 
	// The path to the output folder
	private static final String OUTPUT_PATH = "C:\\PDFOutPut\\";
 
	// SMTP Server
	private static final String SMTP_SERVER = "mail.company.com";
 
	// Email list
	private static final String FROM_EMAIL = "sender.email@company.com";
	private static final String CC_EMAIL = "ccemail@company.com";
 
	private static final String ERROR_FROM_EMAIL = "FailedNotice@company.com";
	private static final String ERROR_TO_EMAIL = "itguy@company.com";
 
	private static Hashtable<String, String> DEPARTMENT_SENDLIST = new Hashtable<String, String>();
	static
	{
		DEPARTMENT_SENDLIST.put("DPT 1", "dept1@company.com");
		DEPARTMENT_SENDLIST.put("DPT 2", "dept2@company.com");
		DEPARTMENT_SENDLIST.put("DEPT 3", "dept3@company.com");
	}
 
	@Override
	public boolean process(ServerContext serverContext, JobStatus jobStatus, WorkingBundle bundle)
	{
		// set up log service
		LogService logService = serverContext.createLogService();
 
		// set up email service 
		EmailService emailService = serverContext.createEmailService();
		emailService.setSMTPServer(SMTP_SERVER);
		emailService.setSMTPFromName(FROM_EMAIL);
 
           // get the PDF document from the bundle
		PDFDocument pdfDoc = bundle.getPDFDocument();
 
		// Loop through the pages, incrementing pageIndex by 2
		for (int pageIndex = 0; pageIndex < pdfDoc.getPageCount(); pageIndex += 2)
		{
			String filePath = null;
			try
			{
				logService.log(Level.INFO, "Processing page " + (pageIndex + 1) + " of " + pdfDoc.getPageCount());
 
				try
				{
					Thread.sleep(1500);
				}
				catch (InterruptedException e)
				{
					e.printStackTrace();
				}
 
				// Create a new document with 2 next pages
				PDFDocument singleDoc = new PDFDocument();
				singleDoc.appendPage(pdfDoc.getPage(pageIndex));
 
				singleDoc.appendPage(pdfDoc.getPage(pageIndex + 1));
				}
 
				// Get the first page
				PDFPage page = singleDoc.getPage(0);
 
// Read information from page
				String department = getTextOnPage(page, RECT_DEPT);
				String recordNumber = getTextOnPage(page, RECT_RECORD_NUMBER);
				String date = getTextOnPage(page, RECT_DATE);
				String time = getTextOnPage(page, RECT_TIME);
 
				if (recordNumber == null)
				{
					recordNumber = "MISSING_RECORD_NUMBER";
				}
 
				// Define the file name, in this case a combination of the record number and the current date
				Date now = new Date();
				String fileName = recordNumber + " " + FORMAT_DATE.format(now) + ".pdf";
 
				// Save the document
				filePath = OUTPUT_PATH + fileName;
				singleDoc.saveDocument(filePath);
 
// send an error email in case we were unable to identify the text / fields on the document 
				if (department == null || recordNumber == null || date == null || time == null)
				{
					// ERROR - missing data
					StringBuffer message = new StringBuffer("File " + fileName + " is missing data. Page " + (pageIndex + 1) + " of " + bundle.getInitialFileName());
					sendErrorEmail(emailService, logService, message.toString(), filePath, fileName);
				}
				else
				{
					// Make sure we can match up the department to the email info
					String sendList = DEPARTMENT_SENDLIST.get(department.toUpperCase());
					// send error email if we could not match the department
					if (sendList == null)
					{
						// ERROR
						StringBuffer message = new StringBuffer("Unable to match department for file " + fileName + ". Page " + (pageIndex + 1) + " of " + bundle.getInitialFileName());
						sendErrorEmail(emailService, logService, message.toString(), filePath, fileName);
					}
					// send email to appropriate email address if we were able to match the department
					else
					{
						// Add the CC_EMAIL
						sendList = sendList + "," + CC_EMAIL;
 
						Email email = emailService.createNewEmail();
// set your email subject
						email.setSubject("RECORD NUMBER " + recordNumber + " FOR DEPT " + department.toUpperCase());
// add your content
						email.setMessage("Your content here");
						email.setSendList(sendList);
// 2 page document is attached to the email 
						email.addAttachment(fileName, new File(filePath));
 
						// Send the Email
						emailService.sendEmail(email);
					}
				}
			}
			catch (PDFException ex)
			{
				logService.log(Level.SEVERE, "PDFExeption processing document", ex);
			}
			catch (IOException ex)
			{
				logService.log(Level.SEVERE, "IOException processing document. Unable to save document " + filePath, ex);
			}
		}
 
		return true;
	}
 
// this is the method using Qoppa's PDF library jPDFProcess
// to identify text in a PDF document given a specific 
// rectangle on the page
	private String getTextOnPage(PDFPage page, Rectangle rectangle) throws PDFException
	{
		// Get the text for the page
		TextSelection selection = page.getTextInArea(rectangle);
 
		String text = null;
 
		if (selection != null && selection.getText().trim().length() > 0)
		{
			text = selection.getText().trim();
		}
 
		// This will draw a red rectangle around the search area on the PDF page
		if (DEBUG_RECTANGLES || text == null)
		{
			Graphics2D g2d = page.createGraphics();
			g2d.setColor(Color.red);
			g2d.draw(rectangle);
		}
 
		return text;
	}
 
// Method to send an email
	private void sendErrorEmail(EmailService emailService, LogService logService, String message, String filePath, String fileName)
	{
		logService.log(Level.SEVERE, message);
 
		Email email = emailService.createNewEmail();
		email.setSubject("failed email - please check");
		email.setMessage(message);
		email.setSendList(ERROR_TO_EMAIL);
		email.setImportance(Email.IMPORTANT_MORE);
           // add file attachment
		email.addAttachment(fileName, new File(filePath));
 
		// Change the FROM email
		emailService.setSMTPFromName(ERROR_FROM_EMAIL);
 
		// Send the email
		emailService.sendEmail(email);
 
		// Change the FROM email back
		emailService.setSMTPFromName(FROM_EMAIL);
	}
}