BAEL-9267: Determine If a File is a PDF File in Java

Author: manfred106

text-processing-libraries-modules/pdf-2/pom.xml

@@ -40,6 +40,11 @@
             <artifactId>poi-ooxml</artifactId>
             <version>${poi-ooxml.version}</version>
         </dependency>
+        <dependency>
+            <groupId>org.apache.tika</groupId>
+            <artifactId>tika-core</artifactId>
+            <version>${tika.version}</version>
+        </dependency>
         <dependency>
             <groupId>org.apache.logging.log4j</groupId>
             <artifactId>log4j-api</artifactId>
@@ -70,8 +75,9 @@
         <itextpdf.version>5.5.13.3</itextpdf.version>
         <itextpdf.core.version>7.2.3</itextpdf.core.version>
         <itextpdf.cleanup.version>3.0.1</itextpdf.cleanup.version>
-        <pdfbox.version>3.0.0</pdfbox.version>
+        <pdfbox.version>3.0.4</pdfbox.version>
         <poi-ooxml.version>5.2.5</poi-ooxml.version>
+        <tika.version>3.1.0</tika.version>
         <log4j-api.version>2.20.0</log4j-api.version>
         <log4j-core.version>2.20.0</log4j-core.version>
     </properties>

text-processing-libraries-modules/pdf-2/src/test/java/com/baeldung/detect/PdfDetectTest.java

@@ -0,0 +1,67 @@
+package com.baeldung.detect;
+
+import org.apache.pdfbox.Loader;
+import org.apache.pdfbox.pdmodel.PDDocument;
+import org.apache.tika.Tika;
+import org.junit.jupiter.api.Test;
+
+import static org.assertj.core.api.Assertions.assertThat;
+import static org.junit.jupiter.api.Assertions.assertTrue;
+
+import java.io.*;
+import java.util.Objects;
+
+import com.itextpdf.commons.exceptions.ITextException;
+import com.itextpdf.kernel.pdf.PdfDocument;
+import com.itextpdf.kernel.pdf.PdfReader;
+
+
+public class PdfDetectTest {
+
+    private static final File PDF_FILE = new File("src/test/resources/input.pdf");
+    private static final File NON_PDF_FILE = new File("src/test/resources/test.jpg");
+
+
+    @Test
+    void whenDetectPdfByPdfBox_thenCorrect() throws IOException {
+        boolean isPdf;
+        try (PDDocument document = Loader.loadPDF(PDF_FILE)) {
+            isPdf = true;
+        } catch (IOException ioe) {
+            isPdf = false;
+        }
+        assertTrue(isPdf);
+    }
+
+    @Test
+    void whenDetectPdfByItext_thenCorrect() throws IOException {
+        boolean isPdf;
+        try (PdfDocument pdfDoc = new PdfDocument(new PdfReader(PDF_FILE))) {
+            isPdf = true;
+        } catch (ITextException ite) {
+            isPdf = false;
+        }
+        assertTrue(isPdf);
+    }
+
+    @Test
+    void whenDetectPdfByFileSignature_thenCorrect() throws IOException {
+        boolean isPdf = false;
+        try (InputStream fis = new BufferedInputStream(new FileInputStream(PDF_FILE))) {
+            byte[] bytes = new byte[5];
+            if (fis.read(bytes) >= 5) {
+                String header = new String(bytes);
+                isPdf = Objects.equals(header, "%PDF-");
+            }
+        }
+        assertTrue(isPdf);
+    }
+
+    @Test
+    void whenDetectPdfByTika_thenCorrect() throws IOException {
+        Tika tika = new Tika();
+        boolean isPdf = Objects.equals(tika.detect(PDF_FILE), "application/pdf");
+        assertTrue(isPdf);
+    }
+
+}