Extract images enhancements (#1757)

* fix

* extarct images

* langs

* logging

* cuke fix

---------

Co-authored-by: a <a>

cucumber/features/general.feature

@@ -95,7 +95,7 @@ Feature: API Validation
 
 
   @extract-images
-  Scenario Outline: Extract Image Scans
+  Scenario Outline: Extract Image Scans duplicates
     Given I use an example file at "exampleFiles/images.pdf" as parameter "fileInput"
     And the request data includes
       | parameter        | value       |
@@ -103,7 +103,7 @@ Feature: API Validation
     When I send the API request to the endpoint "/api/v1/misc/extract-images"
     Then the response content type should be "application/octet-stream"
 	And the response file should have extension ".zip"
-	And the response ZIP should contain 20 files
+	And the response ZIP should contain 2 files
     And the response file should have size greater than 0
 	And the response status code should be 200
 	
@@ -112,5 +112,3 @@ Feature: API Validation
     | png        | 
     | gif         |
     | jpeg        | 
-
-	

src/main/java/stirling/software/SPDF/controller/api/misc/ExtractImagesController.java

@@ -5,6 +5,9 @@ import java.awt.image.BufferedImage;
 import java.awt.image.RenderedImage;
 import java.io.ByteArrayOutputStream;
 import java.io.IOException;
+import java.security.MessageDigest;
+import java.security.NoSuchAlgorithmException;
+import java.util.Arrays;
 import java.util.HashSet;
 import java.util.Set;
 import java.util.concurrent.ExecutionException;
@@ -36,7 +39,8 @@ import io.github.pixee.security.Filenames;
 import io.swagger.v3.oas.annotations.Operation;
 import io.swagger.v3.oas.annotations.tags.Tag;
 
-import stirling.software.SPDF.model.api.PDFWithImageFormatRequest;
+import stirling.software.SPDF.model.api.PDFExtractImagesRequest;
+import stirling.software.SPDF.utils.ImageProcessingUtils;
 import stirling.software.SPDF.utils.WebResponseUtils;
 
 @RestController
@@ -51,11 +55,11 @@ public class ExtractImagesController {
             summary = "Extract images from a PDF file",
             description =
                     "This endpoint extracts images from a given PDF file and returns them in a zip file. Users can specify the output image format. Input: PDF Output: IMAGE/ZIP Type: SIMO")
-    public ResponseEntity<byte[]> extractImages(@ModelAttribute PDFWithImageFormatRequest request)
+    public ResponseEntity<byte[]> extractImages(@ModelAttribute PDFExtractImagesRequest request)
             throws IOException, InterruptedException, ExecutionException {
         MultipartFile file = request.getFileInput();
         String format = request.getFormat();
-
+        boolean allowDuplicates = request.isAllowDuplicates();
         System.out.println(
                 System.currentTimeMillis() + " file=" + file.getName() + ", format=" + format);
         PDDocument document = Loader.loadPDF(file.getBytes());
@@ -75,7 +79,7 @@ public class ExtractImagesController {
         String filename =
                 Filenames.toSimpleFileName(file.getOriginalFilename())
                         .replaceFirst("[.][^.]+$", "");
-        Set<Integer> processedImages = new HashSet<>();
+        Set<byte[]> processedImages = new HashSet<>();
 
         if (useMultithreading) {
             // Executor service to handle multithreading
@@ -92,7 +96,13 @@ public class ExtractImagesController {
                         executor.submit(
                                 () -> {
                                     extractImagesFromPage(
-                                            page, format, filename, pageNum, processedImages, zos);
+                                            page,
+                                            format,
+                                            filename,
+                                            pageNum,
+                                            processedImages,
+                                            zos,
+                                            allowDuplicates);
                                     return null;
                                 });
 
@@ -110,7 +120,8 @@ public class ExtractImagesController {
             // Single-threaded extraction
             for (int pgNum = 0; pgNum < document.getPages().getCount(); pgNum++) {
                 PDPage page = document.getPage(pgNum);
-                extractImagesFromPage(page, format, filename, pgNum + 1, processedImages, zos);
+                extractImagesFromPage(
+                        page, format, filename, pgNum + 1, processedImages, zos, allowDuplicates);
             }
         }
 
@@ -137,22 +148,35 @@ public class ExtractImagesController {
             String format,
             String filename,
             int pageNum,
-            Set<Integer> processedImages,
+            Set<byte[]> processedImages,
-            ZipOutputStream zos)
+            ZipOutputStream zos,
+            boolean allowDuplicates)
             throws IOException {
+        MessageDigest md;
+        try {
+            md = MessageDigest.getInstance("MD5");
+        } catch (NoSuchAlgorithmException e) {
+            logger.error("MD5 algorithm not available for extractImages hash.", e);
+            return;
+        }
         if (page.getResources() == null || page.getResources().getXObjectNames() == null) {
             return;
         }
+        int count = 1;
         for (COSName name : page.getResources().getXObjectNames()) {
             if (page.getResources().isImageXObject(name)) {
                 PDImageXObject image = (PDImageXObject) page.getResources().getXObject(name);
-                int imageHash = image.hashCode();
+                if (!allowDuplicates) {
+                    byte[] data = ImageProcessingUtils.getImageData(image.getImage());
+                    byte[] imageHash = md.digest(data);
                     synchronized (processedImages) {
-                    if (processedImages.contains(imageHash)) {
+                        if (processedImages.stream()
+                                .anyMatch(hash -> Arrays.equals(hash, imageHash))) {
                             continue; // Skip already processed images
                         }
                         processedImages.add(imageHash);
                     }
+                }
 
                 RenderedImage renderedImage = image.getImage();
 
@@ -160,7 +184,7 @@ public class ExtractImagesController {
                 BufferedImage bufferedImage = convertToRGB(renderedImage, format);
 
                 // Write image to zip file
-                String imageName = filename + "_" + imageHash + " (Page " + pageNum + ")." + format;
+                String imageName = filename + "_page_" + pageNum + "_" + count++ + "." + format;
                 synchronized (zos) {
                     zos.putNextEntry(new ZipEntry(imageName));
                     ByteArrayOutputStream imageBaos = new ByteArrayOutputStream();

src/main/java/stirling/software/SPDF/model/api/PDFExtractImagesRequest.java

@@ -0,0 +1,16 @@
+package stirling.software.SPDF.model.api;
+
+import io.swagger.v3.oas.annotations.media.Schema;
+
+import lombok.Data;
+import lombok.EqualsAndHashCode;
+
+@Data
+@EqualsAndHashCode(callSuper = true)
+public class PDFExtractImagesRequest extends PDFWithImageFormatRequest {
+
+    @Schema(
+            description =
+                    "Boolean to enable/disable the saving of duplicate images, true to enable duplicates")
+    private boolean allowDuplicates;
+}

src/main/java/stirling/software/SPDF/utils/GeneralUtils.java

@@ -262,4 +262,5 @@ public class GeneralUtils {
         }
         return true;
     }
+
 }

src/main/java/stirling/software/SPDF/utils/ImageProcessingUtils.java

@@ -1,6 +1,10 @@
 package stirling.software.SPDF.utils;
 
 import java.awt.image.BufferedImage;
+import java.awt.image.DataBuffer;
+import java.awt.image.DataBufferByte;
+import java.awt.image.DataBufferInt;
+import java.nio.ByteBuffer;
 
 public class ImageProcessingUtils {
 
@@ -29,4 +33,30 @@ public class ImageProcessingUtils {
         }
         return convertedImage;
     }
+
+    public static byte[] getImageData(BufferedImage image) {
+        DataBuffer dataBuffer = image.getRaster().getDataBuffer();
+        if (dataBuffer instanceof DataBufferByte) {
+            return ((DataBufferByte) dataBuffer).getData();
+        } else if (dataBuffer instanceof DataBufferInt) {
+            int[] intData = ((DataBufferInt) dataBuffer).getData();
+            ByteBuffer byteBuffer = ByteBuffer.allocate(intData.length * 4);
+            byteBuffer.asIntBuffer().put(intData);
+            return byteBuffer.array();
+        } else {
+            int width = image.getWidth();
+            int height = image.getHeight();
+            byte[] data = new byte[width * height * 3];
+            int index = 0;
+            for (int y = 0; y < height; y++) {
+                for (int x = 0; x < width; x++) {
+                    int rgb = image.getRGB(x, y);
+                    data[index++] = (byte) ((rgb >> 16) & 0xFF); // Red
+                    data[index++] = (byte) ((rgb >> 8) & 0xFF); // Green
+                    data[index++] = (byte) (rgb & 0xFF); // Blue
+                }
+            }
+            return data;
+        }
+    }
 }

src/main/resources/messages_ar_AR.properties

@@ -802,6 +802,7 @@ ocr.submit=معالجة PDF باستخدام OCR
 extractImages.title=استخراج الصور
 extractImages.header=استخراج الصور
 extractImages.selectText=حدد تنسيق الصورة لتحويل الصور المستخرجة إلى
+extractImages.allowDuplicates=Save duplicate images
 extractImages.submit=استخراج
 
 

src/main/resources/messages_bg_BG.properties

@@ -802,6 +802,7 @@ ocr.submit=Обработка на PDF чрез OCR
 extractImages.title=Извличане на изображения
 extractImages.header=Извличане на изображения
 extractImages.selectText=Изберете формат на изображението, в който да преобразувате извлечените изображения
+extractImages.allowDuplicates=Save duplicate images
 extractImages.submit=Извличане
 
 

src/main/resources/messages_ca_CA.properties

@@ -802,6 +802,7 @@ ocr.submit=Processa PDF amb OCR
 extractImages.title=Extreu Imatges
 extractImages.header=Extreu Imatges
 extractImages.selectText=Selecciona el format d'imatge al qual convertir les imatges extretes
+extractImages.allowDuplicates=Save duplicate images
 extractImages.submit=Extreu
 
 

src/main/resources/messages_cs_CZ.properties

@@ -802,6 +802,7 @@ ocr.submit=Zpracovat PDF s OCR
 extractImages.title=Extrahovat obrázky
 extractImages.header=Extrahovat obrázky
 extractImages.selectText=Vyberte formát obrázku pro extrahované obrázky
+extractImages.allowDuplicates=Save duplicate images
 extractImages.submit=Extrahovat
 
 

src/main/resources/messages_da_DK.properties

@@ -802,6 +802,7 @@ ocr.submit=Process PDF with OCR
 extractImages.title=Extract Images
 extractImages.header=Extract Images
 extractImages.selectText=Select image format to convert extracted images to
+extractImages.allowDuplicates=Save duplicate images
 extractImages.submit=Extract
 
 

src/main/resources/messages_de_DE.properties

@@ -4,7 +4,7 @@
 # the direction that the language is written (ltr=left to right, rtl = right to left)
 language.direction=ltr
 
-pdfPrompwt=PDF auswählen
+pdfPrompt=Select PDF(s)
 multiPdfPrompt=PDFs auswählen(2+)
 multiPdfDropPrompt=Wählen Sie alle gewünschten PDFs aus (oder ziehen Sie sie per Drag & Drop hierhin)
 imgPrompt=Wählen Sie ein Bild
@@ -802,6 +802,7 @@ ocr.submit=PDF mit OCR verarbeiten
 extractImages.title=Bilder extrahieren
 extractImages.header=Bilder extrahieren
 extractImages.selectText=Wählen Sie das Bildformat aus, in das extrahierte Bilder konvertiert werden sollen
+extractImages.allowDuplicates=Save duplicate images
 extractImages.submit=Extrahieren
 
 

src/main/resources/messages_el_GR.properties

@@ -802,6 +802,7 @@ ocr.submit=Επεξεργασία PDF με OCR
 extractImages.title=Εξαγωγή Εικόνων
 extractImages.header=Εξαγωγή Εικόνων
 extractImages.selectText=Επιλέξτε μορφή εικόνας για να μετατρέψετε τις εξαγόμενες εικόνες
+extractImages.allowDuplicates=Save duplicate images
 extractImages.submit=Εξαγωγή
 
 

src/main/resources/messages_en_GB.properties

@@ -802,6 +802,7 @@ ocr.submit=Process PDF with OCR
 extractImages.title=Extract Images
 extractImages.header=Extract Images
 extractImages.selectText=Select image format to convert extracted images to
+extractImages.allowDuplicates=Save duplicate images
 extractImages.submit=Extract
 
 

src/main/resources/messages_en_US.properties

@@ -802,6 +802,7 @@ ocr.submit=Process PDF with OCR
 extractImages.title=Extract Images
 extractImages.header=Extract Images
 extractImages.selectText=Select image format to convert extracted images to
+extractImages.allowDuplicates=Save duplicate images
 extractImages.submit=Extract
 
 

src/main/resources/messages_es_ES.properties

@@ -802,6 +802,7 @@ ocr.submit=Procesar PDF con OCR
 extractImages.title=Extraer imágenes
 extractImages.header=Extraer imágenes
 extractImages.selectText=Seleccionar el formato de imagen para convertir las imágenes extraídas
+extractImages.allowDuplicates=Save duplicate images
 extractImages.submit=Extraer
 
 

src/main/resources/messages_eu_ES.properties

@@ -802,6 +802,7 @@ ocr.submit=PDF prozesatu OCR-rekin
 extractImages.title=Atera irudiak
 extractImages.header=Atera irudiak
 extractImages.selectText=Hautatu irudi-formatua ateratako irudiak bihurtzeko
+extractImages.allowDuplicates=Save duplicate images
 extractImages.submit=Atera
 
 

src/main/resources/messages_fr_FR.properties

@@ -802,6 +802,7 @@ ocr.submit=Traiter
 extractImages.title=Extraire les images
 extractImages.header=Extraire les images
 extractImages.selectText=Format d’image dans lequel convertir les images extraites
+extractImages.allowDuplicates=Save duplicate images
 extractImages.submit=Extraire
 
 

src/main/resources/messages_ga_IE.properties

@@ -802,6 +802,7 @@ ocr.submit=Próiseáil PDF le OCR
 extractImages.title=Sliocht Íomhánna
 extractImages.header=Sliocht Íomhánna
 extractImages.selectText=Roghnaigh formáid íomhá chun íomhánna bainte a thiontú go
+extractImages.allowDuplicates=Save duplicate images
 extractImages.submit=Sliocht
 
 

src/main/resources/messages_hi_IN.properties

@@ -802,6 +802,7 @@ ocr.submit=OCR के साथ PDF प्रोसेस करें
 extractImages.title=छवियां निकालें
 extractImages.header=छवियां निकालें
 extractImages.selectText=निकाली गई छवियों को कन्वर्ट करने के लिए छवि प्रारूप चुनें
+extractImages.allowDuplicates=Save duplicate images
 extractImages.submit=निकालें
 
 

src/main/resources/messages_hr_HR.properties

@@ -802,6 +802,7 @@ ocr.submit=Obradi PDF sa OCR-om
 extractImages.title=Ekstrakt slika
 extractImages.header=Ekstrakt slika
 extractImages.selectText=Odaberite format slike za pretvaranje izdvojenih slika
+extractImages.allowDuplicates=Save duplicate images
 extractImages.submit=Izdvajanje
 
 

src/main/resources/messages_hu_HU.properties

@@ -802,6 +802,7 @@ ocr.submit=PDF feldolgozása OCR-rel
 extractImages.title=Képek kinyerése
 extractImages.header=Képek kinyerése
 extractImages.selectText=Válassza ki a képformátumot a kinyert képek konvertálásához
+extractImages.allowDuplicates=Save duplicate images
 extractImages.submit=Kinyerés
 
 

src/main/resources/messages_id_ID.properties

@@ -802,6 +802,7 @@ ocr.submit=Memproses PDF dengan OCR
 extractImages.title=Ekstrak Gambar
 extractImages.header=Mengekstrak Gambar
 extractImages.selectText=Pilih format gambar yang akan dikonversi
+extractImages.allowDuplicates=Save duplicate images
 extractImages.submit=Ekstrak
 
 

src/main/resources/messages_it_IT.properties

@@ -802,6 +802,7 @@ ocr.submit=Scansiona testo nel PDF con OCR
 extractImages.title=Estrai immagini
 extractImages.header=Estrai immagini
 extractImages.selectText=Seleziona il formato in cui salvare le immagini estratte
+extractImages.allowDuplicates=Save duplicate images
 extractImages.submit=Estrai
 
 

src/main/resources/messages_ja_JP.properties

@@ -802,6 +802,7 @@ ocr.submit=OCRでPDFを処理する
 extractImages.title=画像の抽出
 extractImages.header=画像の抽出
 extractImages.selectText=抽出した画像のフォーマットを選択
+extractImages.allowDuplicates=Save duplicate images
 extractImages.submit=抽出
 
 

src/main/resources/messages_ko_KR.properties

@@ -802,6 +802,7 @@ ocr.submit=인식
 extractImages.title=이미지 추출
 extractImages.header=이미지 추출
 extractImages.selectText=추출된 이미지를 변환할 이미지 형식을 선택합니다.
+extractImages.allowDuplicates=Save duplicate images
 extractImages.submit=추출
 
 

src/main/resources/messages_nl_NL.properties

@@ -802,6 +802,7 @@ ocr.submit=Verwerk PDF met OCR
 extractImages.title=Afbeeldingen extraheren
 extractImages.header=Afbeeldingen extraheren
 extractImages.selectText=Selecteer het beeldformaat voor geëxtraheerde afbeeldingen
+extractImages.allowDuplicates=Save duplicate images
 extractImages.submit=Extraheer
 
 

src/main/resources/messages_no_NB.properties

@@ -802,6 +802,7 @@ ocr.submit=Behandle PDF med OCR
 extractImages.title=Hent ut bilder
 extractImages.header=Hent ut bilder
 extractImages.selectText=Velg bildeformat for å konvertere de hentede bildene til
+extractImages.allowDuplicates=Save duplicate images
 extractImages.submit=Hent ut
 
 

src/main/resources/messages_pl_PL.properties

@@ -802,6 +802,7 @@ ocr.submit=Przetwarzaj PDF za pomocą OCR
 extractImages.title=Wyodrębnij obrazy
 extractImages.header=Wyodrębnij obrazy
 extractImages.selectText=Wybierz format obrazu, na który chcesz przekonwertować wyodrębniony obraz.
+extractImages.allowDuplicates=Save duplicate images
 extractImages.submit=Wyodrębnij
 
 

src/main/resources/messages_pt_BR.properties

@@ -802,6 +802,7 @@ ocr.submit=Processar PDF com OCR
 extractImages.title=Extrair imagens
 extractImages.header=Extrair imagens
 extractImages.selectText=Selecione o formato de imagem para converter as imagens extraídas
+extractImages.allowDuplicates=Save duplicate images
 extractImages.submit=Extrair
 
 

src/main/resources/messages_pt_PT.properties

@@ -802,6 +802,7 @@ ocr.submit=Processar PDF com OCR
 extractImages.title=Extrair Imagens
 extractImages.header=Extrair Imagens
 extractImages.selectText=Selecione o formato de imagem para converter as imagens extraídas
+extractImages.allowDuplicates=Save duplicate images
 extractImages.submit=Extrair
 
 

src/main/resources/messages_ro_RO.properties

@@ -802,6 +802,7 @@ ocr.submit=Procesează PDF-ul cu OCR
 extractImages.title=Extrage Imagini
 extractImages.header=Extrage Imagini
 extractImages.selectText=Selectați formatul imaginii în care să se convertească imaginile extrase
+extractImages.allowDuplicates=Save duplicate images
 extractImages.submit=Extrage
 
 

src/main/resources/messages_ru_RU.properties

@@ -802,6 +802,7 @@ ocr.submit=Обработка PDF с OCR
 extractImages.title=Извлечь изображения
 extractImages.header=Извлечь изображения
 extractImages.selectText=Выберите формат изображения для преобразования извлеченных изображений в
+extractImages.allowDuplicates=Save duplicate images
 extractImages.submit=Извлечь
 
 

src/main/resources/messages_sk_SK.properties

@@ -802,6 +802,7 @@ ocr.submit=Spracovať PDF s OCR
 extractImages.title=Extrahovať obrázky
 extractImages.header=Extrahovať obrázky
 extractImages.selectText=Vyberte formát obrázka na konverziu extrahovaných obrázkov
+extractImages.allowDuplicates=Save duplicate images
 extractImages.submit=Extrahovať
 
 

src/main/resources/messages_sr_LATN_RS.properties

@@ -802,6 +802,7 @@ ocr.submit=Obradi PDF sa OCR-om
 extractImages.title=Izdvajanje slika
 extractImages.header=Izdvajanje slika
 extractImages.selectText=Odaberite format slike za konvertovanje izdvojenih slika
+extractImages.allowDuplicates=Save duplicate images
 extractImages.submit=Izdvajanje
 
 

src/main/resources/messages_sv_SE.properties

@@ -802,6 +802,7 @@ ocr.submit=Bearbeta PDF med OCR
 extractImages.title=Extrahera bilder
 extractImages.header=Extrahera bilder
 extractImages.selectText=Välj bildformat att konvertera extraherade bilder till
+extractImages.allowDuplicates=Save duplicate images
 extractImages.submit=Extrahera
 
 

src/main/resources/messages_th_TH.properties

@@ -802,6 +802,7 @@ ocr.submit=ประมวลผล PDF ด้วย OCR
 extractImages.title=แยกรูปภาพ
 extractImages.header=แยกรูปภาพ
 extractImages.selectText=เลือกรูปแบบภาพที่จะใช้ในการแปลงรูปภาพที่แยกได้
+extractImages.allowDuplicates=Save duplicate images
 extractImages.submit=แยก
 
 

src/main/resources/messages_tr_TR.properties

@@ -802,6 +802,7 @@ ocr.submit=PDF'i OCR(Metin Tanıma) ile İşle
 extractImages.title=Resimleri Çıkar
 extractImages.header=Resimleri Çıkar
 extractImages.selectText=Çıkarılan resimleri dönüştürmek için resim formatını seçin
+extractImages.allowDuplicates=Save duplicate images
 extractImages.submit=Çıkar
 
 

src/main/resources/messages_uk_UA.properties

@@ -802,6 +802,7 @@ ocr.submit=Обробка PDF з OCR
 extractImages.title=Витягнути зображення
 extractImages.header=Витягнути зображення
 extractImages.selectText=Виберіть формат зображення для перетворення витягнутих зображень у
+extractImages.allowDuplicates=Save duplicate images
 extractImages.submit=Витягнути
 
 

src/main/resources/messages_vi_VN.properties

@@ -802,6 +802,7 @@ ocr.submit=Xử lý PDF với OCR
 extractImages.title=Trích xuất hình ảnh
 extractImages.header=Trích xuất hình ảnh
 extractImages.selectText=Chọn định dạng hình ảnh để chuyển đổi hình ảnh đã trích xuất
+extractImages.allowDuplicates=Save duplicate images
 extractImages.submit=Trích xuất
 
 

src/main/resources/messages_zh_CN.properties

@@ -802,6 +802,7 @@ ocr.submit=用OCR处理PDF
 extractImages.title=提取图像
 extractImages.header=提取图像
 extractImages.selectText=选择图像格式，将提取的图像转换为
+extractImages.allowDuplicates=Save duplicate images
 extractImages.submit=提取
 
 

src/main/resources/messages_zh_TW.properties

@@ -802,6 +802,7 @@ ocr.submit=使用 OCR 處理 PDF
 extractImages.title=提取圖片
 extractImages.header=提取圖片
 extractImages.selectText=選擇要轉換提取影像的影像格式
+extractImages.allowDuplicates=Save duplicate images
 extractImages.submit=提取
 
 

src/main/resources/templates/misc/extract-images.html

@@ -27,6 +27,10 @@
                     <option value="gif">GIF</option>
                   </select>
                 </div>
+                <div class="mb-3">
+                  <input type="checkbox" name="allowDuplicates" id="allowDuplicates">
+                  <label for="allowDuplicates" th:text="#{extractImages.allowDuplicates}"></label>
+                </div>
                 <button type="submit" id="submitBtn" class="btn btn-primary" th:text="#{extractImages.submit}"></button>
               </form>
             </div>