⬆️ Bump pdfbox from 2.0.31 to 3.0.5 (#240)

* bump pdfbox

* fix breaking changes in `org.apache.pdfbox:pdfbox`

* Update src/main/java/com/mindee/input/InputSourceUtils.java

* Update src/main/java/com/mindee/input/InputSourceUtils.java

---------

Co-authored-by: zhouzhuotong <1160490625@qq.com>
Co-authored-by: sebastianMindee <130448732+sebastianMindee@users.noreply.github.com>

Author: 3 people

pom.xml

@@ -415,7 +415,7 @@
     <org.apache.maven.project.info.reports.version>3.0.0</org.apache.maven.project.info.reports.version>
     <org.apache.maven.site.version>3.7.1</org.apache.maven.site.version>
     <org.apache.maven.surfire.version>3.2.5</org.apache.maven.surfire.version>
-    <org.apache.pdfbox.version>2.0.31</org.apache.pdfbox.version>
+    <org.apache.pdfbox.version>3.0.5</org.apache.pdfbox.version>
     <org.junit.jupiter.version>5.8.2</org.junit.jupiter.version>
     <org.junit.pioneer.version>1.9.1</org.junit.pioneer.version>
     <org.junit.platform.version>1.8.2</org.junit.platform.version>

src/main/java/com/mindee/extraction/PDFExtractor.java

@@ -14,6 +14,7 @@
 import java.util.List;
 import java.util.stream.Collectors;
 import javax.imageio.ImageIO;
+import org.apache.pdfbox.Loader;
 import org.apache.pdfbox.pdmodel.PDDocument;
 import org.apache.pdfbox.pdmodel.PDPage;
 import org.apache.pdfbox.pdmodel.PDPageContentStream;
@@ -46,7 +47,7 @@ public PDFExtractor(String filePath) throws IOException {
   public PDFExtractor(LocalInputSource source) throws IOException {
     this.filename = source.getFilename();
     if (source.isPdf()) {
-      this.sourcePdf = PDDocument.load(source.getFile());
+      this.sourcePdf = Loader.loadPDF(source.getFile());
     } else {
       PDDocument document = new PDDocument();
       PDPage page = new PDPage();
@@ -104,7 +105,7 @@ public List<ExtractedPDF> extractSubDocuments(List<List<Integer>> pageIndexes)
           + String.format("%3s", pageIndexElement.get(pageIndexElement.size() - 1) + 1)
             .replace(" ", "0") + "." + splitName[1];
       extractedPDFs.add(
-        new ExtractedPDF(PDDocument.load(mergePdfPages(this.sourcePdf, pageIndexElement, false)),
+        new ExtractedPDF(Loader.loadPDF(mergePdfPages(this.sourcePdf, pageIndexElement, false)),
           fieldFilename));
     }
     return extractedPDFs;

src/main/java/com/mindee/input/InputSourceUtils.java

@@ -5,6 +5,8 @@
 import java.io.IOException;
 import java.net.URL;
 import javax.imageio.ImageIO;
+import org.apache.pdfbox.Loader;
+import org.apache.pdfbox.io.RandomAccessReadBuffer;
 import org.apache.pdfbox.pdmodel.PDDocument;
 import org.apache.pdfbox.text.PDFTextStripper;
 
@@ -70,7 +72,7 @@ public static String[] splitNameStrict(String filename) throws MindeeException {
    * Returns true if the file is a PDF.
    */
   public static boolean isPdf(byte[] fileBytes) {
-    try (PDDocument document = PDDocument.load(new ByteArrayInputStream(fileBytes))) {
+    try (PDDocument document = Loader.loadPDF(new RandomAccessReadBuffer(new ByteArrayInputStream(fileBytes)))) {
       return true;
     } catch (IOException e) {
       return false;
@@ -95,7 +97,7 @@ public static void validateUrl(URL inputUrl) {
    */
   public static boolean hasSourceText(byte[] fileBytes) {
     try {
-      PDDocument document = PDDocument.load(new ByteArrayInputStream(fileBytes));
+      PDDocument document = Loader.loadPDF(new RandomAccessReadBuffer(new ByteArrayInputStream(fileBytes)));
       PDFTextStripper stripper = new PDFTextStripper();
 
       for (int i = 0; i < document.getNumberOfPages(); i++) {

src/main/java/com/mindee/pdf/PDFUtils.java

@@ -8,6 +8,7 @@
 import java.io.IOException;
 import java.util.ArrayList;
 import java.util.List;
+import org.apache.pdfbox.Loader;
 import org.apache.pdfbox.cos.COSDictionary;
 import org.apache.pdfbox.cos.COSName;
 import org.apache.pdfbox.pdmodel.PDDocument;
@@ -16,6 +17,7 @@
 import org.apache.pdfbox.pdmodel.PDResources;
 import org.apache.pdfbox.pdmodel.common.PDRectangle;
 import org.apache.pdfbox.pdmodel.font.PDType1Font;
+import org.apache.pdfbox.pdmodel.font.Standard14Fonts;
 import org.apache.pdfbox.pdmodel.graphics.color.PDColor;
 import org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject;
 import org.apache.pdfbox.rendering.ImageType;
@@ -37,7 +39,7 @@ private PDFUtils() {
    * @param inputSource The PDF file.
    */
   public static int getNumberOfPages(LocalInputSource inputSource) throws IOException {
-    PDDocument document = PDDocument.load(inputSource.getFile());
+    PDDocument document = Loader.loadPDF(inputSource.getFile());
     int pageCount = document.getNumberOfPages();
     document.close();
     return pageCount;
@@ -81,7 +83,7 @@ private static byte[] createPdfFromExistingPdf(
    * @param pageNumbers Lit of page numbers to merge together.
    */
   public static byte[] mergePdfPages(File file, List<Integer> pageNumbers) throws IOException {
-    PDDocument document = PDDocument.load(file);
+    PDDocument document = Loader.loadPDF(file);
     return createPdfFromExistingPdf(document, pageNumbers, true);
   }
 
@@ -100,7 +102,7 @@ public static byte[] mergePdfPages(
 
 
   public static boolean isPdfEmpty(File file) throws IOException {
-    return checkIfPdfIsEmpty(PDDocument.load(file));
+    return checkIfPdfIsEmpty(Loader.loadPDF(file));
   }
 
   private static boolean checkIfPdfIsEmpty(PDDocument document) throws IOException {
@@ -143,7 +145,7 @@ public static List<PdfPageImage> pdfToImages(String filePath) throws IOException
    * @return List of all pages as images.
    */
   public static List<PdfPageImage> pdfToImages(LocalInputSource source) throws IOException {
-    PDDocument document = PDDocument.load(source.getFile());
+    PDDocument document = Loader.loadPDF(source.getFile());
     PDFRenderer pdfRenderer = new PDFRenderer(document);
     List<PdfPageImage> pdfPageImages = new ArrayList<>();
     for (int i = 0; i < document.getNumberOfPages(); i++) {
@@ -182,7 +184,7 @@ public static PdfPageImage pdfPageToImage(
       int pageNumber
   ) throws IOException {
     int index = pageNumber - 1;
-    PDDocument document = PDDocument.load(source.getFile());
+    PDDocument document = Loader.loadPDF(source.getFile());
     PDFRenderer pdfRenderer = new PDFRenderer(document);
     BufferedImage imageBuffer = pdfPageToImageBuffer(index, document, pdfRenderer);
     document.close();
@@ -242,7 +244,7 @@ protected void writeString(String text, List<TextPosition> textPositions) throws
         try {
           contentStream.showText(text);
         } catch (IllegalArgumentException | UnsupportedOperationException e) {
-          contentStream.setFont(PDType1Font.HELVETICA, fontSize);
+          contentStream.setFont(new PDType1Font(Standard14Fonts.FontName.HELVETICA), fontSize);
           contentStream.showText(text);
         }
         contentStream.endText();

src/main/java/com/mindee/pdf/PdfBoxApi.java

@@ -12,6 +12,7 @@
 import java.util.stream.Collectors;
 import java.util.stream.IntStream;
 import java.util.stream.Stream;
+import org.apache.pdfbox.Loader;
 import org.apache.pdfbox.pdmodel.PDDocument;
 
 /**
@@ -26,7 +27,7 @@ public SplitPdf split(SplitQuery splitQuery) throws IOException {
       throw new MindeeException("This document cannot be open and cannot be split.");
     }
 
-    try (PDDocument originalDocument = PDDocument.load(splitQuery.getFile())) {
+    try (PDDocument originalDocument = Loader.loadPDF(splitQuery.getFile())) {
       try (PDDocument splitDocument = new PDDocument()) {
         int totalOriginalPages = countPages(splitQuery.getFile());
 
@@ -73,7 +74,7 @@ private List<Integer> getPageRanges(PageOptions pageOptions, Integer numberOfPag
   private boolean checkPdfOpen(byte[] documentFile) {
     boolean opens = false;
     try {
-      PDDocument.load(documentFile).close();
+      Loader.loadPDF(documentFile).close();
       opens = true;
     } catch (IOException e) {
       e.printStackTrace();
@@ -82,7 +83,7 @@ private boolean checkPdfOpen(byte[] documentFile) {
   }
 
   private int countPages(byte[] documentFile) throws IOException {
-    PDDocument document = PDDocument.load(documentFile);
+    PDDocument document = Loader.loadPDF(documentFile);
     int pageCount = document.getNumberOfPages();
     document.close();
     return pageCount;

src/main/java/com/mindee/pdf/PdfCompressor.java

@@ -5,6 +5,7 @@
 
 import java.awt.image.BufferedImage;
 import java.io.IOException;
+import org.apache.pdfbox.Loader;
 import org.apache.pdfbox.pdmodel.PDDocument;
 import org.apache.pdfbox.pdmodel.PDPage;
 import org.apache.pdfbox.pdmodel.PDPageContentStream;
@@ -38,7 +39,7 @@ public static byte[] compressPdf(
           "MINDEE WARNING: Found text inside of the provided PDF file. Compression operation aborted.");
       return pdfData;
     }
-    try (PDDocument inputDoc = PDDocument.load(pdfData);
+    try (PDDocument inputDoc = Loader.loadPDF(pdfData);
          PDDocument outputDoc = new PDDocument()) {
 
       PDFRenderer pdfRenderer = new PDFRenderer(inputDoc);

src/test/java/com/mindee/input/LocalInputSourceTest.java

@@ -14,6 +14,7 @@
 import java.util.stream.Collectors;
 import javax.imageio.ImageIO;
 import org.apache.commons.codec.binary.Base64;
+import org.apache.pdfbox.Loader;
 import org.apache.pdfbox.pdmodel.PDDocument;
 import org.apache.pdfbox.text.PDFTextStripper;
 import org.junit.jupiter.api.Assertions;
@@ -338,8 +339,8 @@ public void testPdfResizeWithTextKeepsText() throws IOException {
     byte[] compressedWithText =
         PdfCompressor.compressPdf(initialWithText.getFile(), 100, true, false);
 
-    PDDocument originalDoc = PDDocument.load(initialWithText.getFile());
-    PDDocument compressedDoc = PDDocument.load(compressedWithText);
+    PDDocument originalDoc = Loader.loadPDF(initialWithText.getFile());
+    PDDocument compressedDoc = Loader.loadPDF(compressedWithText);
 
     Assertions.assertEquals(originalDoc.getNumberOfPages(), compressedDoc.getNumberOfPages());
     Assertions.assertNotEquals(originalDoc.hashCode(), compressedDoc.hashCode());

src/test/java/com/mindee/pdf/PDFUtilsTest.java

@@ -10,6 +10,8 @@
 import java.util.Arrays;
 import java.util.List;
 import java.util.Random;
+
+import org.apache.pdfbox.Loader;
 import org.apache.pdfbox.pdmodel.PDDocument;
 import org.apache.pdfbox.pdmodel.PDPage;
 import org.junit.jupiter.api.Assertions;
@@ -43,7 +45,7 @@ public void givenADocumentAndListOfPages_whenMerged_thenReturnsCorrectDocument()
     File file = new File("src/test/resources/output/fileToTest.pdf");
     List<Integer> pageList = Arrays.asList(0, 2, 3, 1, 10, 2, 1);
     byte[] newPdf = PDFUtils.mergePdfPages(file, pageList);
-    PDDocument document = PDDocument.load(newPdf);
+    PDDocument document = Loader.loadPDF(newPdf);
 
     Assertions.assertEquals(7, document.getNumberOfPages());
     document.close();