will it work?

Author: ianardee

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

@@ -29,7 +29,7 @@ public ImageExtractor(LocalInputSource source) throws IOException {
     this.filename = source.getFilename();
     this.pageImages = new ArrayList<>();
 
-    if (source.isPdf()) {
+    if (source.isPDF()) {
       this.saveFormat = "jpg";
       var pdfPageImages = pdfToImages(source.getFile(), this.filename);
       for (PdfPageImage pdfPageImage : pdfPageImages) {

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

@@ -3,8 +3,8 @@
 import com.mindee.image.ImageCompressor;
 import com.mindee.pdf.PDFCompression;
 import com.mindee.pdf.PDFCompressor;
-import com.mindee.pdf.PDFInputSource;
-import com.mindee.pdf.PDFInputSourcer;
+import com.mindee.pdf.PDFInputOperation;
+import com.mindee.pdf.PDFInputOperator;
 import java.io.File;
 import java.io.IOException;
 import java.io.InputStream;
@@ -18,16 +18,18 @@
 /**
  * A source document for Mindee API operations.
  */
-public final class LocalInputSource {
+public class LocalInputSource {
 
   @Getter
   private byte[] file;
   @Getter
   private final String filename;
   @Setter
-  private PDFInputSource pdfOperation;
+  private PDFInputOperation pdfInputOperator;
   @Setter
-  private PDFCompressor pdfCompressor;
+  private PDFCompression pdfCompressor;
+  // Store here to avoid recalculating every time.
+  private Boolean isPDF;
 
   public LocalInputSource(InputStream file, String filename) throws IOException {
     this.file = IOUtils.toByteArray(file);
@@ -60,14 +62,14 @@ public LocalInputSource(String fileAsBase64, String filename) {
     this.filename = filename;
   }
 
-  public PDFInputSource getPdfOperation() {
-    if (this.pdfOperation == null) {
-      this.pdfOperation = new PDFInputSourcer();
+  private PDFInputOperation getPdfInputOperator() {
+    if (this.pdfInputOperator == null) {
+      this.pdfInputOperator = new PDFInputOperator();
     }
-    return this.pdfOperation;
+    return this.pdfInputOperator;
   }
 
-  public PDFCompression getPdfCompressor() {
+  private PDFCompression getPdfCompressor() {
     if (this.pdfCompressor == null) {
       this.pdfCompressor = new PDFCompressor();
     }
@@ -81,10 +83,10 @@ public PDFCompression getPdfCompressor() {
    * @throws IOException If an I/O error occurs during the PDF operation.
    */
   public int getPageCount() throws IOException {
-    if (!this.isPdf()) {
+    if (!this.isPDF()) {
       return 1;
     }
-    return getPdfOperation().getNumberOfPages(this.file);
+    return getPdfInputOperator().getPageCount(this.file);
   }
 
   /**
@@ -94,17 +96,19 @@ public int getPageCount() throws IOException {
    * @throws IOException If an I/O error occurs during the PDF operation.
    */
   public void applyPageOptions(PageOptions pageOptions) throws IOException {
-    if (pageOptions != null && this.isPdf()) {
-      this.file = getPdfOperation().split(this.file, pageOptions).getFile();
+    if (pageOptions != null && this.isPDF()) {
+      this.file = getPdfInputOperator().split(this.file, pageOptions).getFile();
     }
   }
 
-  public boolean isPdf() {
-    return getPdfOperation().isPdf(this.file);
-  }
-
-  public boolean hasSourceText() {
-    return getPdfOperation().hasSourceText(this.file);
+  /**
+   * Returns true if the file is a PDF.
+   */
+  public boolean isPDF() {
+    if (this.isPDF == null) {
+      this.isPDF = getPdfInputOperator().isPDF(this.file);
+    }
+    return this.isPDF;
   }
 
   public LocalInputSource compress(
@@ -114,9 +118,9 @@ public LocalInputSource compress(
       Boolean forceSourceText,
       Boolean disableSourceText
   ) throws IOException {
-    if (isPdf()) {
+    if (isPDF()) {
       this.file = getPdfCompressor()
-        .compressPdf(this.file, quality, forceSourceText, disableSourceText);
+        .compressPDF(this.file, quality, forceSourceText, disableSourceText);
     } else {
       this.file = ImageCompressor.compressImage(this.file, quality, maxWidth, maxHeight);
     }

…ava/com/mindee/pdf/PDFExtractorBase.java …ava/com/mindee/pdf/BasePDFExtractor.javasrc/main/java/com/mindee/pdf/PDFExtractorBase.java renamed to src/main/java/com/mindee/pdf/BasePDFExtractor.java src/main/java/com/mindee/pdf/PDFExtractorBase.java renamed to src/main/java/com/mindee/pdf/BasePDFExtractor.java

@@ -6,7 +6,6 @@
 import java.awt.image.BufferedImage;
 import java.io.ByteArrayInputStream;
 import java.io.ByteArrayOutputStream;
-import java.io.File;
 import java.io.IOException;
 import java.util.ArrayList;
 import java.util.List;
@@ -17,16 +16,13 @@
 import org.apache.pdfbox.pdmodel.PDDocument;
 import org.apache.pdfbox.pdmodel.PDPage;
 import org.apache.pdfbox.pdmodel.PDPageContentStream;
-import org.apache.pdfbox.pdmodel.common.PDRectangle;
 import org.apache.pdfbox.pdmodel.graphics.image.LosslessFactory;
 import org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject;
-import org.apache.pdfbox.rendering.ImageType;
-import org.apache.pdfbox.rendering.PDFRenderer;
 
 /**
  * PDF extraction class.
  */
-public class PDFExtractorBase implements PDFExtraction {
+public class BasePDFExtractor {
   protected final PDDocument sourcePdf;
   protected final String filename;
 
@@ -36,9 +32,9 @@ public class PDFExtractorBase implements PDFExtraction {
    * @param source The local source.
    * @throws IOException Throws if the file can't be accessed.
    */
-  public PDFExtractorBase(LocalInputSource source) throws IOException {
+  public BasePDFExtractor(LocalInputSource source) throws IOException {
     this.filename = source.getFilename();
-    if (source.isPdf()) {
+    if (source.isPDF()) {
       this.sourcePdf = Loader.loadPDF(source.getFile());
     } else {
       var document = new PDDocument();
@@ -60,60 +56,6 @@ public PDFExtractorBase(LocalInputSource source) throws IOException {
     }
   }
 
-//  @Override
-//  public PdfPageImage pdfPageToImage(
-//      byte[] fileBytes,
-//      String filename,
-//      int pageNumber
-//  ) throws IOException {
-//    int index = pageNumber - 1;
-//    PDDocument document = Loader.loadPDF(fileBytes);
-//    var pdfRenderer = new PDFRenderer(document);
-//    BufferedImage imageBuffer = pdfPageToImageBuffer(index, document, pdfRenderer);
-//    document.close();
-//    return new PdfPageImage(imageBuffer, index, filename, "jpg");
-//  }
-//
-//  @Override
-//  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);
-  }
-
-  /**
-   * Get the number of pages in the PDF file.
-   *
-   * @return The number of pages in the PDF file.
-   */
-  public int getPageCount() {
-    return sourcePdf.getNumberOfPages();
-  }
-
   /**
    * Converts an array to a buffered image.
    *
@@ -197,24 +139,6 @@ private static byte[] createPdfFromExistingPdf(
     return output;
   }
 
-  /**
-   * Merge specified PDF pages together.
-   *
-   * @param file The PDF file.
-   * @param pageNumbers Lit of page numbers to merge together.
-   */
-  @Override
-  public byte[] mergePdfPages(File file, List<Integer> pageNumbers) throws IOException {
-    PDDocument document = Loader.loadPDF(file);
-    return mergePdfPages(document, pageNumbers, true);
-  }
-
-  @Override
-  public byte[] mergePdfPages(PDDocument document, List<Integer> pageNumbers) throws IOException {
-    return mergePdfPages(document, pageNumbers, true);
-  }
-
-  @Override
   public byte[] mergePdfPages(
       PDDocument document,
       List<Integer> pageNumbers,

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

@@ -3,26 +3,26 @@
 import java.io.IOException;
 
 public interface PDFCompression {
-  byte[] compressPdf(
-      byte[] pdfData,
+  byte[] compressPDF(
+      byte[] fileBytes,
       Integer imageQuality,
       Boolean forceSourceTextCompression,
       Boolean disableSourceText
   ) throws IOException;
 
-  default byte[] compressPdf(
-      byte[] pdfData,
+  default byte[] compressPDF(
+      byte[] fileBytes,
       Integer imageQuality,
       Boolean forceSourceTextCompression
   ) throws IOException {
-    return compressPdf(pdfData, imageQuality, forceSourceTextCompression, true);
+    return compressPDF(fileBytes, imageQuality, forceSourceTextCompression, true);
   }
 
-  default byte[] compressPdf(byte[] pdfData, Integer imageQuality) throws IOException {
-    return compressPdf(pdfData, imageQuality, false, true);
+  default byte[] compressPDF(byte[] fileBytes, Integer imageQuality) throws IOException {
+    return compressPDF(fileBytes, imageQuality, false, true);
   }
 
-  default byte[] compressPdf(byte[] pdfData) throws IOException {
-    return compressPdf(pdfData, 85, false, true);
+  default byte[] compressPDF(byte[] fileBytes) throws IOException {
+    return compressPDF(fileBytes, 85, false, true);
   }
 }

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

@@ -1,11 +1,14 @@
 package com.mindee.pdf;
 
+import com.mindee.MindeeException;
 import java.awt.*;
 import java.awt.image.BufferedImage;
+import java.io.ByteArrayInputStream;
 import java.io.ByteArrayOutputStream;
 import java.io.IOException;
 import java.util.List;
 import org.apache.pdfbox.Loader;
+import org.apache.pdfbox.io.RandomAccessReadBuffer;
 import org.apache.pdfbox.pdmodel.PDDocument;
 import org.apache.pdfbox.pdmodel.PDPage;
 import org.apache.pdfbox.pdmodel.PDPageContentStream;
@@ -24,21 +27,21 @@
  * PDF compression class.
  */
 public class PDFCompressor implements PDFCompression {
-  PDFInputSourcer pdfInputSourcer;
+  private final PDFInputOperator pdfInputOperator;
 
   public PDFCompressor() {
-    pdfInputSourcer = new PDFInputSourcer();
+    this.pdfInputOperator = new PDFInputOperator();
   }
 
   @Override
-  public byte[] compressPdf(
-      byte[] pdfData,
+  public byte[] compressPDF(
+      byte[] fileBytes,
       Integer imageQuality,
       Boolean forceSourceTextCompression,
       Boolean disableSourceText
   ) throws IOException {
-    if (!pdfInputSourcer.isPdf(pdfData)) {
-      return pdfData;
+    if (!pdfInputOperator.isPDF(fileBytes)) {
+      return fileBytes;
     }
 
     if (forceSourceTextCompression == null) {
@@ -47,14 +50,14 @@ public byte[] compressPdf(
     if (disableSourceText == null) {
       disableSourceText = true;
     }
-    if (!forceSourceTextCompression && pdfInputSourcer.hasSourceText(pdfData)) {
+    if (!forceSourceTextCompression && hasSourceText(fileBytes)) {
       System.out
         .println(
           "MINDEE WARNING: Found text inside of the provided PDF file. Compression operation aborted."
         );
-      return pdfData;
+      return fileBytes;
     }
-    try (PDDocument inputDoc = Loader.loadPDF(pdfData); PDDocument outputDoc = new PDDocument()) {
+    try (var inputDoc = Loader.loadPDF(fileBytes); PDDocument outputDoc = new PDDocument()) {
 
       var pdfRenderer = new PDFRenderer(inputDoc);
 
@@ -79,6 +82,35 @@ public byte[] compressPdf(
     }
   }
 
+  /**
+   * Returns true if the source PDF has source text inside. Returns false for images.
+   *
+   * @param fileBytes A byte array representing a PDF.
+   * @return True if at least one character exists in one page.
+   * @throws MindeeException if the file could not be read.
+   */
+  private boolean hasSourceText(byte[] fileBytes) {
+    try {
+      PDDocument document = Loader
+        .loadPDF(new RandomAccessReadBuffer(new ByteArrayInputStream(fileBytes)));
+      var stripper = new PDFTextStripper();
+
+      for (int i = 0; i < document.getNumberOfPages(); i++) {
+        stripper.setStartPage(i + 1);
+        stripper.setEndPage(i + 1);
+        String pageText = stripper.getText(document);
+        if (!pageText.trim().isEmpty()) {
+          document.close();
+          return true;
+        }
+      }
+      document.close();
+    } catch (IOException e) {
+      return false;
+    }
+    return false;
+  }
+
   private static byte[] documentToBytes(PDDocument document) throws IOException {
     var outputStream = new ByteArrayOutputStream();
     document.save(outputStream);
@@ -122,9 +154,9 @@ protected void writeString(String text, List<TextPosition> textPositions) throws
           return;
         }
 
-        TextPosition firstPosition = textPositions.get(0);
+        var firstPosition = textPositions.get(0);
         float fontSize = firstPosition.getFontSizeInPt();
-        PDColor color = getGraphicsState().getNonStrokingColor();
+        var color = getGraphicsState().getNonStrokingColor();
         contentStream.beginText();
         contentStream.setFont(firstPosition.getFont(), fontSize);
         contentStream.setNonStrokingColor(convertToAwtColor(color));