♻️ use an interface to define PDF rasterization

src/main/java/com/mindee/image/ImageExtractor.java

@@ -10,11 +10,6 @@
 import java.util.ArrayList;
 import java.util.List;
 import javax.imageio.ImageIO;
-import org.apache.pdfbox.Loader;
-import org.apache.pdfbox.pdmodel.PDDocument;
-import org.apache.pdfbox.pdmodel.common.PDRectangle;
-import org.apache.pdfbox.rendering.ImageType;
-import org.apache.pdfbox.rendering.PDFRenderer;
 
 /**
  * Extract sub-images from an image.
@@ -30,7 +25,7 @@ public ImageExtractor(LocalInputSource source) throws IOException {
 
     if (source.isPDF()) {
       this.saveFormat = "jpg";
-      var pdfPageImages = pdfToImages(source.getFile(), source.getFilename());
+      var pdfPageImages = getPDFRasterizer().PDFToImages(source.getFile(), source.getFilename());
       for (PDFPageImage pdfPageImage : pdfPageImages) {
         this.pageImages.add(pdfPageImage.getImage());
       }
@@ -45,34 +40,14 @@ public ImageExtractor(LocalInputSource source) throws IOException {
     }
   }
 
-  private List<PDFPageImage> pdfToImages(byte[] fileBytes, String filename) throws IOException {
-    PDDocument document = Loader.loadPDF(fileBytes);
-    var pdfRenderer = new PDFRenderer(document);
-    List<PDFPageImage> pdfPageImages = new ArrayList<>();
-    for (int i = 0; i < document.getNumberOfPages(); i++) {
-      var imageBuffer = pdfPageToImageBuffer(i, document, pdfRenderer);
-      pdfPageImages.add(new PDFPageImage(imageBuffer, i, filename, "jpg"));
-    }
-    document.close();
-    return pdfPageImages;
-  }
-
-  private BufferedImage pdfPageToImageBuffer(
-      int index,
-      PDDocument document,
-      PDFRenderer pdfRenderer
-  ) throws IOException {
-    PDRectangle bbox = document.getPage(index).getBBox();
-    float dimension = bbox.getWidth() * bbox.getHeight();
-    int dpi;
-    if (dimension < 200000) {
-      dpi = 300;
-    } else if (dimension < 300000) {
-      dpi = 250;
-    } else {
-      dpi = 200;
-    }
-    return pdfRenderer.renderImageWithDPI(index, dpi, ImageType.RGB);
+  /**
+   * Get the PDF rasterization implementation.
+   * Override this method to provide custom PDF rasterization handling.
+   *
+   * @return The PDF rasterization implementation.
+   */
+  protected PDFRasterization getPDFRasterizer() {
+    return new PDFRasterizer();
   }
 
   /**

src/main/java/com/mindee/image/PDFRasterization.java

@@ -0,0 +1,14 @@
+package com.mindee.image;
+
+import java.io.IOException;
+import java.util.List;
+
+/**
+ * Rasterize a PDF into images.
+ */
+public interface PDFRasterization {
+  /**
+   * Rasterize a PDF into a list of images, one image per page.
+   */
+  List<PDFPageImage> PDFToImages(byte[] fileBytes, String filename) throws IOException;
+}

src/main/java/com/mindee/image/PDFRasterizer.java

@@ -0,0 +1,46 @@
+package com.mindee.image;
+
+import java.awt.image.BufferedImage;
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.List;
+import org.apache.pdfbox.Loader;
+import org.apache.pdfbox.pdmodel.PDDocument;
+import org.apache.pdfbox.pdmodel.common.PDRectangle;
+import org.apache.pdfbox.rendering.ImageType;
+import org.apache.pdfbox.rendering.PDFRenderer;
+
+/**
+ * Default PDF rasterization implementation.
+ */
+public class PDFRasterizer implements PDFRasterization {
+  public List<PDFPageImage> PDFToImages(byte[] fileBytes, String filename) throws IOException {
+    PDDocument document = Loader.loadPDF(fileBytes);
+    var pdfRenderer = new PDFRenderer(document);
+    List<PDFPageImage> pdfPageImages = new ArrayList<>();
+    for (int i = 0; i < document.getNumberOfPages(); i++) {
+      var imageBuffer = pdfPageToImageBuffer(i, document, pdfRenderer);
+      pdfPageImages.add(new PDFPageImage(imageBuffer, i, filename, "jpg"));
+    }
+    document.close();
+    return pdfPageImages;
+  }
+
+  private BufferedImage pdfPageToImageBuffer(
+      int index,
+      PDDocument document,
+      PDFRenderer pdfRenderer
+  ) throws IOException {
+    PDRectangle bbox = document.getPage(index).getBBox();
+    float dimension = bbox.getWidth() * bbox.getHeight();
+    int dpi;
+    if (dimension < 200000) {
+      dpi = 300;
+    } else if (dimension < 300000) {
+      dpi = 250;
+    } else {
+      dpi = 200;
+    }
+    return pdfRenderer.renderImageWithDPI(index, dpi, ImageType.RGB);
+  }
+}

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

@@ -61,7 +61,7 @@ public LocalInputSource(String fileAsBase64, String filename) {
 
   /**
    * Get the PDFInputOperation instance.
-   * Override this method to provide custom PDF input operation handling.
+   * Override this method to provide custom PDF input handling.
    *
    * @return PDFInputOperation instance
    */

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

@@ -82,6 +82,19 @@ public ExtractedPDFs extractSubDocuments(List<List<Integer>> pageIndexes) throws
     return extractedPDFs;
   }
 
+  /**
+   * Make a nice filename for the split.
+   */
+  protected String makeFilename(List<Integer> pageNumbers) {
+    String[] splitName = InputSourceUtils.splitNameStrict(filename);
+    return splitName[0]
+      + String.format("_%3s", pageNumbers.get(0)).replace(" ", "0")
+      + "-"
+      + String.format("%3s", pageNumbers.get(pageNumbers.size() - 1)).replace(" ", "0")
+      + "."
+      + splitName[1];
+  }
+
   /**
    * Converts an array to a buffered image.
    *
@@ -95,19 +108,6 @@ private static BufferedImage byteArrayToBufferedImage(byte[] byteArray) throws I
     }
   }
 
-  /**
-   * Make a nice filename for the split.
-   */
-  private String makeFilename(List<Integer> pageNumbers) {
-    String[] splitName = InputSourceUtils.splitNameStrict(filename);
-    return splitName[0]
-      + String.format("_%3s", pageNumbers.get(0)).replace(" ", "0")
-      + "-"
-      + String.format("%3s", pageNumbers.get(pageNumbers.size() - 1)).replace(" ", "0")
-      + "."
-      + splitName[1];
-  }
-
   private static PDPage clonePage(PDPage page) {
 
     COSDictionary pageDict = page.getCOSObject();

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

@@ -2,23 +2,26 @@
 
 import java.io.IOException;
 
+/**
+ * Compress a PDF.
+ */
 public interface PDFCompression {
   byte[] compressPDF(
       byte[] fileBytes,
-      Integer imageQuality,
+      int imageQuality,
       Boolean forceSourceTextCompression,
       Boolean disableSourceText
   ) throws IOException;
 
   default byte[] compressPDF(
       byte[] fileBytes,
-      Integer imageQuality,
+      int imageQuality,
       Boolean forceSourceTextCompression
   ) throws IOException {
     return compressPDF(fileBytes, imageQuality, forceSourceTextCompression, true);
   }
 
-  default byte[] compressPDF(byte[] fileBytes, Integer imageQuality) throws IOException {
+  default byte[] compressPDF(byte[] fileBytes, int imageQuality) throws IOException {
     return compressPDF(fileBytes, imageQuality, false, true);
   }
 

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

@@ -36,7 +36,7 @@ public PDFCompressor() {
   @Override
   public byte[] compressPDF(
       byte[] fileBytes,
-      Integer imageQuality,
+      int imageQuality,
       Boolean forceSourceTextCompression,
       Boolean disableSourceText
   ) throws IOException {

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

@@ -3,6 +3,9 @@
 import com.mindee.input.PageOptions;
 import java.io.IOException;
 
+/**
+ * Various operations required for PDF input files.
+ */
 public interface PDFInputOperation {
 
   /**