Code cleanup for PDF module (#800)

* PDF to X

* PDF to X

* Remove created doc

* Code fixes and cleanup for PDF module

pdf/src/main/java/com/baeldung/pdf/PDF2HTMLExample.java

@@ -23,27 +23,17 @@ public class PDF2HTMLExample {
 	}
 
 	private static void generateHTMLFromPDF(String filename) throws ParserConfigurationException, IOException {
-		System.out.println("Creating HTML file from a PDF file: " + filename);
-		PDDocument pdf = null;
 		try {
-			// load the PDF file using PDFBox
+			PDDocument pdf = PDDocument.load(new File(filename));
-			pdf = PDDocument.load(new File(filename));
-			// create the DOM parser
 			PDFDomTree parser = new PDFDomTree();
-			// parse the file and get the DOM Document
 			Writer output = new PrintWriter("src/output/pdf.html", "utf-8");
 			parser.writeText(pdf, output);
 			output.close();
-		} finally {
 			if (pdf != null) {
-				try {
+				pdf.close();
-					pdf.close();
-				} catch (IOException e) {
-					System.err.println("Error: " + e.getMessage());
-				}
 			}
+		} catch (IOException e) {
+			e.printStackTrace();
 		}
-		System.out.println("Done.");
 	}
-
 }

pdf/src/main/java/com/baeldung/pdf/PDF2ImageExample.java

@@ -24,15 +24,12 @@ public class PDF2ImageExample {
 	}
 
 	private static void generateImageFromPDF(String filename, String extension) throws IOException {
-		System.out.println("Creating " + extension + " image from a PDF file: " + filename);
 		PDDocument document = PDDocument.load(new File(filename));
 		PDFRenderer pdfRenderer = new PDFRenderer(document);
 		for (int page = 0; page < document.getNumberOfPages(); ++page) {
-			System.out.println("Page number: " + (page + 1) + " is being rendered");
 			BufferedImage bim = pdfRenderer.renderImageWithDPI(page, 300, ImageType.RGB);
 			ImageIOUtil.writeImage(bim, "src/output/pdf" + "-" + (page + 1) + "." + extension, 300);
 		}
 		document.close();
-		System.out.println("Done.");
 	}
 }

pdf/src/main/java/com/baeldung/pdf/PDF2TextExample.java

@@ -23,43 +23,30 @@ public class PDF2TextExample {
 	}
 
 	private static void generateTxtFromPDF(String filename) throws IOException {
-		System.out.println("Parsing text from PDF file " + filename);
-		String parsedText = null;
-		PDFTextStripper pdfStripper;
-		PDDocument pdDoc = null;
-		COSDocument cosDoc = null;
-
-		File f = new File(filename);
-		PDFParser parser = new PDFParser(new RandomAccessFile(f, "r"));
-
 		try {
+			File f = new File(filename);
+			String parsedText;
+			PDFParser parser = new PDFParser(new RandomAccessFile(f, "r"));
 			parser.parse();
-			cosDoc = parser.getDocument();
+
-			pdfStripper = new PDFTextStripper();
+			COSDocument cosDoc = parser.getDocument();
-			pdDoc = new PDDocument(cosDoc);
+
+			PDFTextStripper pdfStripper = new PDFTextStripper();
+			PDDocument pdDoc = new PDDocument(cosDoc);
+
 			parsedText = pdfStripper.getText(pdDoc);
-		} catch (Exception e) {
+
-			System.err.println("An exception occured in parsing the PDF Document.");
+			if (cosDoc != null)
-			e.printStackTrace();
+				cosDoc.close();
-			try {
+			if (pdDoc != null)
-				if (cosDoc != null)
+				pdDoc.close();
-					cosDoc.close();
+			
-				if (pdDoc != null)
-					pdDoc.close();
-			} catch (Exception e1) {
-				e.printStackTrace();
-			}
-		}
-		System.out.println("Writing PDF text to output text file");
-		try {
 			PrintWriter pw = new PrintWriter("src/output/pdf.txt");
 			pw.print(parsedText);
 			pw.close();
 		} catch (Exception e) {
-			System.out.println("An exception occured in writing the pdf text to file.");
 			e.printStackTrace();
 		}
-		System.out.println("Done.");
 	}
 
 }

pdf/src/main/java/com/baeldung/pdf/PDF2WordExample.java

@@ -26,36 +26,25 @@ public class PDF2WordExample {
 	}
 
 	private static void generateDocFromPDF(String filename) throws IOException {
-		System.out.println("Creating a docx file from a PDF file: " + filename);
-		// Create the word document
 		XWPFDocument doc = new XWPFDocument();
 
-		// Open the pdf file
 		String pdf = filename;
 		PdfReader reader = new PdfReader(pdf);
 		PdfReaderContentParser parser = new PdfReaderContentParser(reader);
 
-		// Read the PDF page by page
 		for (int i = 1; i <= reader.getNumberOfPages(); i++) {
 			TextExtractionStrategy strategy = parser.processContent(i, new SimpleTextExtractionStrategy());
-			// Extract the text
 			String text = strategy.getResultantText();
-			// Create a new paragraph in the word document, adding the extracted
-			// text
 			XWPFParagraph p = doc.createParagraph();
 			XWPFRun run = p.createRun();
 			run.setText(text);
-			// Adding a page break
 			run.addBreak(BreakType.PAGE);
 		}
-		// Write the word document
 		FileOutputStream out = new FileOutputStream("src/output/pdf.docx");
 		doc.write(out);
-		// Close all open files
 		out.close();
 		reader.close();
 		doc.close();
-		System.out.println("Done.");
 	}
 
 }