JAVA-29281 Create new module Text Processing Libraries Modules (#15479)

text-processing-libraries-modules/pdf/src/test/java/com/baeldung/pdf/base64/EncodeDecodeUnitTest.java

@@ -0,0 +1,84 @@
+package com.baeldung.pdf.base64;
+
+import org.junit.BeforeClass;
+import org.junit.Test;
+
+import java.io.FileInputStream;
+import java.io.FileOutputStream;
+import java.io.IOException;
+import java.io.OutputStream;
+import java.nio.file.Files;
+import java.nio.file.Paths;
+
+import static org.junit.Assert.*;
+
+public class EncodeDecodeUnitTest {
+
+    private static final String IN_FILE = "src/test/resources/input.pdf";
+    private static final String OUT_FILE = "src/test/resources/output.pdf";
+    private static byte[] inFileBytes;
+
+    @BeforeClass
+    public static void fileToByteArray() throws IOException {
+        inFileBytes = Files.readAllBytes(Paths.get(IN_FILE));
+    }
+
+    @Test
+    public void givenJavaBase64_whenEncoded_thenDecodedOK() throws IOException {
+
+        byte[] encoded = java.util.Base64.getEncoder().encode(inFileBytes);
+
+        byte[] decoded = java.util.Base64.getDecoder().decode(encoded);
+
+        writeToFile(OUT_FILE, decoded);
+
+        assertNotEquals(encoded.length, decoded.length);
+        assertEquals(inFileBytes.length, decoded.length);
+
+        assertArrayEquals(decoded, inFileBytes);
+
+    }
+
+    @Test
+    public void givenJavaBase64_whenEncodedStream_thenDecodedStreamOK() throws IOException {
+
+        try (OutputStream os = java.util.Base64.getEncoder().wrap(new FileOutputStream(OUT_FILE));
+          FileInputStream fis = new FileInputStream(IN_FILE)) {
+            byte[] bytes = new byte[1024];
+            int read;
+            while ((read = fis.read(bytes)) > -1) {
+                os.write(bytes, 0, read);
+            }
+        }
+
+        byte[] encoded = java.util.Base64.getEncoder().encode(inFileBytes);
+        byte[] encodedOnDisk = Files.readAllBytes(Paths.get(OUT_FILE));
+        assertArrayEquals(encoded, encodedOnDisk);
+
+        byte[] decoded = java.util.Base64.getDecoder().decode(encoded);
+        byte[] decodedOnDisk = java.util.Base64.getDecoder().decode(encodedOnDisk);
+        assertArrayEquals(decoded, decodedOnDisk);
+    }
+
+    @Test
+    public void givenApacheCommons_givenJavaBase64_whenEncoded_thenDecodedOK() throws IOException {
+
+        byte[] encoded = org.apache.commons.codec.binary.Base64.encodeBase64(inFileBytes);
+
+        byte[] decoded = org.apache.commons.codec.binary.Base64.decodeBase64(encoded);
+
+        writeToFile(OUT_FILE, decoded);
+
+        assertNotEquals(encoded.length, decoded.length);
+        assertEquals(inFileBytes.length, decoded.length);
+
+        assertArrayEquals(decoded, inFileBytes);
+    }
+
+    private void writeToFile(String fileName, byte[] bytes) throws IOException {
+        FileOutputStream fos = new FileOutputStream(fileName);
+        fos.write(bytes);
+        fos.flush();
+        fos.close();
+    }
+}

text-processing-libraries-modules/pdf/src/test/java/com/baeldung/pdfreadertest/ReadPdfFileUnitTest.java

@@ -0,0 +1,52 @@
+package com.baeldung.pdfreadertest;
+
+import static org.junit.jupiter.api.Assertions.*;
+
+import java.io.File;
+import java.io.IOException;
+
+import org.apache.pdfbox.pdmodel.PDDocument;
+import org.apache.pdfbox.text.PDFTextStripper;
+import org.junit.jupiter.api.Test;
+
+import com.itextpdf.text.pdf.PdfReader;
+import com.itextpdf.text.pdf.parser.PdfTextExtractor;
+
+class ReadPdfFileUnitTest {
+
+    @Test
+    public void givenSamplePdf_whenUsingApachePdfBox_thenCompareOutput() throws IOException {
+        String expectedText = "Hello World!\n";
+
+        File file = new File("sample.pdf");
+        PDDocument document = PDDocument.load(file);
+
+        PDFTextStripper stripper = new PDFTextStripper();
+
+        String text = stripper.getText(document);
+
+        document.close();
+
+        assertEquals(expectedText, text);
+
+    }
+
+    @Test
+    public void givenSamplePdf_whenUsingiTextPdf_thenCompareOutput() throws IOException {
+        String expectedText = "Hello World!";
+
+        PdfReader reader = new PdfReader("sample.pdf");
+        int pages = reader.getNumberOfPages();
+        StringBuilder text = new StringBuilder();
+
+        for (int i = 1; i <= pages; i++) {
+
+            text.append(PdfTextExtractor.getTextFromPage(reader, i));
+
+        }
+        reader.close();
+        assertEquals(expectedText, text.toString());
+
+    }
+
+}

text-processing-libraries-modules/pdf/src/test/java/com/baeldung/pdfthymeleaf/PDFThymeleafUnitTest.java

@@ -0,0 +1,52 @@
+package com.baeldung.pdfthymeleaf;
+
+import com.lowagie.text.DocumentException;
+import org.junit.Test;
+import org.thymeleaf.TemplateEngine;
+import org.thymeleaf.context.Context;
+import org.thymeleaf.templatemode.TemplateMode;
+import org.thymeleaf.templateresolver.ClassLoaderTemplateResolver;
+import org.xhtmlrenderer.pdf.ITextRenderer;
+
+import java.io.ByteArrayOutputStream;
+import java.io.IOException;
+
+import static org.junit.Assert.assertTrue;
+
+public class PDFThymeleafUnitTest {
+
+    @Test
+    public void givenThymeleafTemplate_whenParsedAndRenderedToPDF_thenItShouldNotBeEmpty() throws DocumentException, IOException {
+        String html = parseThymeleafTemplate();
+
+        ByteArrayOutputStream outputStream = generatePdfOutputStreamFromHtml(html);
+
+        assertTrue(outputStream.size() > 0);
+    }
+
+    private ByteArrayOutputStream generatePdfOutputStreamFromHtml(String html) throws IOException, DocumentException {
+        ByteArrayOutputStream outputStream = new ByteArrayOutputStream();
+
+        ITextRenderer renderer = new ITextRenderer();
+        renderer.setDocumentFromString(html);
+        renderer.layout();
+        renderer.createPDF(outputStream);
+
+        outputStream.close();
+        return outputStream;
+    }
+
+    private String parseThymeleafTemplate() {
+        ClassLoaderTemplateResolver templateResolver = new ClassLoaderTemplateResolver();
+        templateResolver.setSuffix(".html");
+        templateResolver.setTemplateMode(TemplateMode.HTML);
+
+        TemplateEngine templateEngine = new TemplateEngine();
+        templateEngine.setTemplateResolver(templateResolver);
+
+        Context context = new Context();
+        context.setVariable("to", "Baeldung.com");
+
+        return templateEngine.process("thymeleaf_template", context);
+    }
+}