Merge branch 'master' of https://github.com/JonCook/tutorials

pdf/.gitignore

@@ -0,0 +1 @@
+/target/

pdf/README.md

@@ -0,0 +1,7 @@
+## PDF
+
+This module contains articles about PDF files.
+
+### Relevant Articles:
+- [PDF Conversions in Java](https://www.baeldung.com/pdf-conversions-java)
+- [Creating PDF Files in Java](https://www.baeldung.com/java-pdf-creation)

pdf/pom.xml

@@ -0,0 +1,85 @@
+<?xml version="1.0"?>
+<project xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd" xmlns="http://maven.apache.org/POM/4.0.0"
+    xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
+    <modelVersion>4.0.0</modelVersion>
+    <artifactId>pdf</artifactId>
+    <name>pdf</name>
+    <url>http://maven.apache.org</url>
+
+    <parent>
+        <groupId>com.baeldung</groupId>
+        <artifactId>parent-modules</artifactId>
+        <version>1.0.0-SNAPSHOT</version>
+    </parent>
+
+    <dependencies>
+        <dependency>
+            <groupId>org.apache.pdfbox</groupId>
+            <artifactId>pdfbox-tools</artifactId>
+            <version>${pdfbox-tools.version}</version>
+            <exclusions>
+                <exclusion>
+                    <artifactId>commons-logging</artifactId>
+                    <groupId>commons-logging</groupId>
+                </exclusion>
+            </exclusions>
+        </dependency>
+        <dependency>
+            <groupId>net.sf.cssbox</groupId>
+            <artifactId>pdf2dom</artifactId>
+            <version>${pdf2dom.version}</version>
+            <exclusions>
+                <exclusion>
+                    <artifactId>commons-logging</artifactId>
+                    <groupId>commons-logging</groupId>
+                </exclusion>
+            </exclusions>
+        </dependency>
+        <dependency>
+            <groupId>com.itextpdf</groupId>
+            <artifactId>itextpdf</artifactId>
+            <version>${itextpdf.version}</version>
+        </dependency>
+        <dependency>
+            <groupId>com.itextpdf.tool</groupId>
+            <artifactId>xmlworker</artifactId>
+            <version>${xmlworker.version}</version>
+        </dependency>
+        <dependency>
+            <groupId>org.apache.poi</groupId>
+            <artifactId>poi-scratchpad</artifactId>
+            <version>${poi-scratchpad.version}</version>
+        </dependency>
+        <dependency>
+            <groupId>org.apache.xmlgraphics</groupId>
+            <artifactId>batik-transcoder</artifactId>
+            <version>${batik-transcoder.version}</version>
+        </dependency>
+        <dependency>
+            <groupId>org.apache.poi</groupId>
+            <artifactId>poi-ooxml</artifactId>
+            <version>${poi-ooxml.version}</version>
+        </dependency>
+    </dependencies>
+
+    <build>
+        <finalName>pdf</finalName>
+        <resources>
+            <resource>
+                <directory>src/main/resources</directory>
+                <filtering>true</filtering>
+            </resource>
+        </resources>
+    </build>
+
+    <properties>
+        <pdfbox-tools.version>2.0.3</pdfbox-tools.version>
+        <pdf2dom.version>1.6</pdf2dom.version>
+        <itextpdf.version>5.5.10</itextpdf.version>
+        <xmlworker.version>5.5.10</xmlworker.version>
+        <poi-scratchpad.version>3.15</poi-scratchpad.version>
+        <batik-transcoder.version>1.8</batik-transcoder.version>
+        <poi-ooxml.version>3.15</poi-ooxml.version>
+    </properties>
+
+</project>

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

@@ -0,0 +1,52 @@
+package com.baeldung.pdf;
+
+import java.io.File;
+import java.io.FileInputStream;
+import java.io.FileOutputStream;
+import java.io.IOException;
+import java.io.PrintWriter;
+import java.io.Writer;
+
+import javax.xml.parsers.ParserConfigurationException;
+
+import org.apache.pdfbox.pdmodel.PDDocument;
+import org.fit.pdfdom.PDFDomTree;
+
+import com.itextpdf.text.Document;
+import com.itextpdf.text.DocumentException;
+import com.itextpdf.text.pdf.PdfWriter;
+import com.itextpdf.tool.xml.XMLWorkerHelper;
+
+public class PDF2HTMLExample {
+
+	private static final String PDF = "src/main/resources/pdf.pdf";
+	private static final String HTML = "src/main/resources/html.html";
+
+	public static void main(String[] args) {
+		try {
+			generateHTMLFromPDF(PDF);
+			generatePDFFromHTML(HTML);
+		} catch (IOException | ParserConfigurationException | DocumentException e) {
+			e.printStackTrace();
+		}
+	}
+
+	private static void generateHTMLFromPDF(String filename) throws ParserConfigurationException, IOException {
+		PDDocument pdf = PDDocument.load(new File(filename));
+		PDFDomTree parser = new PDFDomTree();
+		Writer output = new PrintWriter("src/output/pdf.html", "utf-8");
+		parser.writeText(pdf, output);
+		output.close();
+		if (pdf != null) {
+			pdf.close();
+		}
+	}
+
+	private static void generatePDFFromHTML(String filename) throws ParserConfigurationException, IOException, DocumentException {
+		Document document = new Document();
+		PdfWriter writer = PdfWriter.getInstance(document, new FileOutputStream("src/output/html.pdf"));
+		document.open();
+		XMLWorkerHelper.getInstance().parseXHtml(writer, document, new FileInputStream(filename));
+		document.close();
+	}
+}

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

@@ -0,0 +1,62 @@
+package com.baeldung.pdf;
+
+import java.awt.image.BufferedImage;
+import java.io.File;
+import java.io.FileOutputStream;
+import java.io.IOException;
+import java.net.URL;
+
+import org.apache.pdfbox.pdmodel.PDDocument;
+import org.apache.pdfbox.rendering.ImageType;
+import org.apache.pdfbox.rendering.PDFRenderer;
+import org.apache.pdfbox.tools.imageio.ImageIOUtil;
+
+import com.itextpdf.text.BadElementException;
+import com.itextpdf.text.Document;
+import com.itextpdf.text.DocumentException;
+import com.itextpdf.text.Image;
+import com.itextpdf.text.pdf.PdfWriter;
+
+public class PDF2ImageExample {
+
+	private static final String PDF = "src/main/resources/pdf.pdf";
+	private static final String JPG = "http://cdn2.baeldung.netdna-cdn.com/wp-content/uploads/2016/05/baeldung-rest-widget-main-1.2.0";
+	private static final String GIF = "https://media.giphy.com/media/l3V0x6kdXUW9M4ONq/giphy";
+
+	public static void main(String[] args) {
+		try {
+			generateImageFromPDF(PDF, "png");
+			generateImageFromPDF(PDF, "jpeg");
+			generateImageFromPDF(PDF, "gif");
+			generatePDFFromImage(JPG, "jpg");
+			generatePDFFromImage(GIF, "gif");
+		} catch (IOException | DocumentException e) {
+			e.printStackTrace();
+		}
+	}
+
+	private static void generateImageFromPDF(String filename, String extension) throws IOException {
+		PDDocument document = PDDocument.load(new File(filename));
+		PDFRenderer pdfRenderer = new PDFRenderer(document);
+		for (int page = 0; page < document.getNumberOfPages(); ++page) {
+			BufferedImage bim = pdfRenderer.renderImageWithDPI(page, 300, ImageType.RGB);
+			ImageIOUtil.writeImage(bim, String.format("src/output/pdf-%d.%s", page + 1, extension), 300);
+		}
+		document.close();
+	}
+
+	private static void generatePDFFromImage(String filename, String extension)
+			throws IOException, BadElementException, DocumentException {
+		Document document = new Document();
+		String input = filename + "." + extension;
+		String output = "src/output/" + extension + ".pdf";
+		FileOutputStream fos = new FileOutputStream(output);
+		PdfWriter writer = PdfWriter.getInstance(document, fos);
+		writer.open();
+		document.open();
+		document.add(Image.getInstance((new URL(input))));
+		document.close();
+		writer.close();
+	}
+
+}

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

@@ -0,0 +1,84 @@
+package com.baeldung.pdf;
+
+import java.io.BufferedReader;
+import java.io.File;
+import java.io.FileOutputStream;
+import java.io.FileReader;
+import java.io.IOException;
+import java.io.PrintWriter;
+
+import org.apache.pdfbox.cos.COSDocument;
+import org.apache.pdfbox.io.RandomAccessFile;
+import org.apache.pdfbox.pdfparser.PDFParser;
+import org.apache.pdfbox.pdmodel.PDDocument;
+import org.apache.pdfbox.text.PDFTextStripper;
+
+import com.itextpdf.text.Document;
+import com.itextpdf.text.DocumentException;
+import com.itextpdf.text.Element;
+import com.itextpdf.text.Font;
+import com.itextpdf.text.PageSize;
+import com.itextpdf.text.Paragraph;
+import com.itextpdf.text.pdf.PdfWriter;
+
+public class PDF2TextExample {
+
+	private static final String PDF = "src/main/resources/pdf.pdf";
+	private static final String TXT = "src/main/resources/txt.txt";
+
+	public static void main(String[] args) {
+		try {
+			generateTxtFromPDF(PDF);
+			generatePDFFromTxt(TXT);
+		} catch (IOException | DocumentException e) {
+			e.printStackTrace();
+		}
+	}
+
+	private static void generateTxtFromPDF(String filename) throws IOException {
+		File f = new File(filename);
+		String parsedText;
+		PDFParser parser = new PDFParser(new RandomAccessFile(f, "r"));
+		parser.parse();
+
+		COSDocument cosDoc = parser.getDocument();
+
+		PDFTextStripper pdfStripper = new PDFTextStripper();
+		PDDocument pdDoc = new PDDocument(cosDoc);
+
+		parsedText = pdfStripper.getText(pdDoc);
+
+		if (cosDoc != null)
+			cosDoc.close();
+		if (pdDoc != null)
+			pdDoc.close();
+
+		PrintWriter pw = new PrintWriter("src/output/pdf.txt");
+		pw.print(parsedText);
+		pw.close();
+	}
+
+	private static void generatePDFFromTxt(String filename) throws IOException, DocumentException {
+		Document pdfDoc = new Document(PageSize.A4);
+		PdfWriter.getInstance(pdfDoc, new FileOutputStream("src/output/txt.pdf"))
+				.setPdfVersion(PdfWriter.PDF_VERSION_1_7);
+		pdfDoc.open();
+		
+		Font myfont = new Font();
+		myfont.setStyle(Font.NORMAL);
+		myfont.setSize(11);
+		pdfDoc.add(new Paragraph("\n"));
+		
+		BufferedReader br = new BufferedReader(new FileReader(filename));
+		String strLine;
+		while ((strLine = br.readLine()) != null) {
+			Paragraph para = new Paragraph(strLine + "\n", myfont);
+			para.setAlignment(Element.ALIGN_JUSTIFIED);
+			pdfDoc.add(para);
+		}
+		
+		pdfDoc.close();
+		br.close();
+	}
+
+}

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

@@ -0,0 +1,50 @@
+package com.baeldung.pdf;
+
+import java.io.FileOutputStream;
+import java.io.IOException;
+
+import org.apache.poi.xwpf.usermodel.BreakType;
+import org.apache.poi.xwpf.usermodel.XWPFDocument;
+import org.apache.poi.xwpf.usermodel.XWPFParagraph;
+import org.apache.poi.xwpf.usermodel.XWPFRun;
+
+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;
+
+public class PDF2WordExample {
+
+	private static final String FILENAME = "src/main/resources/pdf.pdf";
+
+	public static void main(String[] args) {
+		try {
+			generateDocFromPDF(FILENAME);
+		} catch (IOException e) {
+			e.printStackTrace();
+		}
+	}
+
+	private static void generateDocFromPDF(String filename) throws IOException {
+		XWPFDocument doc = new XWPFDocument();
+
+		String pdf = filename;
+		PdfReader reader = new PdfReader(pdf);
+		PdfReaderContentParser parser = new PdfReaderContentParser(reader);
+
+		for (int i = 1; i <= reader.getNumberOfPages(); i++) {
+			TextExtractionStrategy strategy = parser.processContent(i, new SimpleTextExtractionStrategy());
+			String text = strategy.getResultantText();
+			XWPFParagraph p = doc.createParagraph();
+			XWPFRun run = p.createRun();
+			run.setText(text);
+			run.addBreak(BreakType.PAGE);
+		}
+		FileOutputStream out = new FileOutputStream("src/output/pdf.docx");
+		doc.write(out);
+		out.close();
+		reader.close();
+		doc.close();
+	}
+
+}

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

@@ -0,0 +1,77 @@
+package com.baeldung.pdf;
+
+import java.io.FileOutputStream;
+import java.io.IOException;
+import java.net.URISyntaxException;
+import java.nio.file.Path;
+import java.nio.file.Paths;
+import java.util.stream.Stream;
+
+import com.itextpdf.text.BadElementException;
+import com.itextpdf.text.BaseColor;
+import com.itextpdf.text.Document;
+import com.itextpdf.text.Element;
+import com.itextpdf.text.Image;
+import com.itextpdf.text.Phrase;
+import com.itextpdf.text.pdf.PdfPCell;
+import com.itextpdf.text.pdf.PdfPTable;
+import com.itextpdf.text.pdf.PdfWriter;
+
+public class PDFSampleMain {
+
+    public static void main(String[] args) {
+        
+        try {
+            
+            Document document = new Document();
+            PdfWriter.getInstance(document, new FileOutputStream("iTextTable.pdf"));
+
+            document.open();
+
+            PdfPTable table = new PdfPTable(3);
+            addTableHeader(table);
+            addRows(table);
+            addCustomRows(table);
+
+            document.add(table);
+            document.close();
+            
+        } catch (Exception e) {
+            e.printStackTrace();
+        }
+    }
+
+    private static void addTableHeader(PdfPTable table) {
+        Stream.of("column header 1", "column header 2", "column header 3")
+        .forEach(columnTitle -> {
+            PdfPCell header = new PdfPCell();
+            header.setBackgroundColor(BaseColor.LIGHT_GRAY);
+            header.setBorderWidth(2);
+            header.setPhrase(new Phrase(columnTitle));
+            table.addCell(header);
+        });
+    }
+
+    private static void addRows(PdfPTable table) {
+        table.addCell("row 1, col 1");
+        table.addCell("row 1, col 2");
+        table.addCell("row 1, col 3");
+    }
+
+    private static void addCustomRows(PdfPTable table) throws URISyntaxException, BadElementException, IOException {
+        Path path = Paths.get(ClassLoader.getSystemResource("Java_logo.png").toURI());
+        Image img = Image.getInstance(path.toAbsolutePath().toString());
+        img.scalePercent(10);
+
+        PdfPCell imageCell = new PdfPCell(img);
+        table.addCell(imageCell);
+
+        PdfPCell horizontalAlignCell = new PdfPCell(new Phrase("row 2, col 2"));
+        horizontalAlignCell.setHorizontalAlignment(Element.ALIGN_CENTER);
+        table.addCell(horizontalAlignCell);
+
+        PdfPCell verticalAlignCell = new PdfPCell(new Phrase("row 2, col 3"));
+        verticalAlignCell.setVerticalAlignment(Element.ALIGN_BOTTOM);
+        table.addCell(verticalAlignCell);
+    }
+}

pdf/src/main/resources/html.html

@@ -0,0 +1,53 @@
+<!DOCTYPE html>
+<html>
+
+<head>
+<title>A very simple webpage</title>
+</head>
+
+<body>
+<h1>A very simple webpage. This is an "h1" level header.</h1>
+
+<h2>This is a level h2 header.</h2>
+
+<h6>This is a level h6 header.  Pretty small!</h6>
+
+<p>This is a standard paragraph.</p>
+
+<p align=center>Now I've aligned it in the center of the screen.</p>
+
+<p align=right>Now aligned to the right</p>
+
+<p><b>Bold text</b></p>
+
+<p><strong>Strongly emphasized text</strong>  Can you tell the difference vs. bold?</p>
+
+<p><i>Italics</i></p>
+
+<p><em>Emphasized text</em>  Just like Italics!</p>
+
+<h2>How about a nice ordered list!</h2>
+<ol>
+  <li>This little piggy went to market</li>
+  <li>This little piggy went to SB228 class</li>
+  <li>This little piggy went to an expensive restaurant in Downtown Palo Alto</li>
+  <li>This little piggy ate too much at Indian Buffet.</li>
+  <li>This little piggy got lost</li>
+</ol>
+
+<h2>Unordered list</h2>
+<ul>
+  <li>First element</li>
+  <li>Second element</li>
+  <li>Third element</li>
+</ul>
+
+
+<p>And finally, how about some</p><a href="http://www.google.com/">Links?</a>
+
+<p>Remember, you can view the HTMl code from this or any other page by using the "View Page Source" command of your browser.</p>
+
+</body>
+
+</html>
+

pdf/src/main/resources/logback.xml

@@ -0,0 +1,13 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<configuration>
+    <appender name="STDOUT" class="ch.qos.logback.core.ConsoleAppender">
+        <encoder>
+            <pattern>%d{HH:mm:ss.SSS} [%thread] %-5level %logger{36} - %msg%n
+            </pattern>
+        </encoder>
+    </appender>
+
+    <root level="INFO">
+        <appender-ref ref="STDOUT" />
+    </root>
+</configuration>

pdf/src/main/resources/txt.txt

@@ -0,0 +1,3 @@
+Test
+Text
+			Test	TEST