Issue1632 remove images (#1645)

* Implemented PdfImageRemovalService.java and PdfImageRemovalController.java. Image can be removed testing using Postman, but the file size doesn't change.

* Fix removal logic in service file to decrease file size.

* Implement "Remove Image" feature on the website

Updated the front-end code to integrate the "Remove Image" feature. The new functionality is now fully operational on the website, allowing users to remove images as expected.

* Add comments to PdfImageRemovalController and PdfImageRemovalService.

* Change the google material icon in navbar, homepage and remove-image-pdf.html.

src/main/java/stirling/software/SPDF/config/EndpointConfiguration.java

@@ -137,6 +137,7 @@ public class EndpointConfiguration {
         addEndpointToGroup("Other", "auto-rename");
         addEndpointToGroup("Other", "get-info-on-pdf");
         addEndpointToGroup("Other", "show-javascript");
+        addEndpointToGroup("Other", "remove-image-pdf");
 
         // CLI
         addEndpointToGroup("CLI", "compress-pdf");
@@ -221,6 +222,7 @@ public class EndpointConfiguration {
         addEndpointToGroup("Java", "split-pdf-by-sections");
         addEndpointToGroup("Java", REMOVE_BLANKS);
         addEndpointToGroup("Java", "pdf-to-text");
+        addEndpointToGroup("Java", "remove-image-pdf");
 
         // Javascript
         addEndpointToGroup("Javascript", "pdf-organizer");

src/main/java/stirling/software/SPDF/controller/api/PdfImageRemovalController.java

@@ -0,0 +1,82 @@
+package stirling.software.SPDF.controller.api;
+
+import java.io.ByteArrayOutputStream;
+import java.io.IOException;
+
+import org.apache.pdfbox.Loader;
+import org.apache.pdfbox.pdmodel.PDDocument;
+import org.springframework.beans.factory.annotation.Autowired;
+import org.springframework.http.ResponseEntity;
+import org.springframework.web.bind.annotation.*;
+import org.springframework.web.multipart.MultipartFile;
+
+import io.swagger.v3.oas.annotations.Operation;
+
+import stirling.software.SPDF.model.api.PDFFile;
+import stirling.software.SPDF.service.PdfImageRemovalService;
+import stirling.software.SPDF.utils.WebResponseUtils;
+
+
+/**
+ * Controller class for handling PDF image removal requests.
+ * Provides an endpoint to remove images from a PDF file to reduce its size.
+ */
+@RestController
+@RequestMapping("/api/v1/general")
+public class PdfImageRemovalController {
+
+    // Service for removing images from PDFs
+    @Autowired private PdfImageRemovalService pdfImageRemovalService;
+
+    /**
+     * Constructor for dependency injection of PdfImageRemovalService.
+     *
+     * @param pdfImageRemovalService The service used for removing images from PDFs.
+     */
+    public PdfImageRemovalController(PdfImageRemovalService pdfImageRemovalService) {
+        this.pdfImageRemovalService = pdfImageRemovalService;
+    }
+
+    /**
+     * Endpoint to remove images from a PDF file.
+     *
+     * This method processes the uploaded PDF file, removes all images, and returns
+     * the modified PDF file with a new name indicating that images were removed.
+     *
+     * @param file The PDF file with images to be removed.
+     * @return ResponseEntity containing the modified PDF file as byte array with appropriate content type and filename.
+     * @throws IOException If an error occurs while processing the PDF file.
+     */
+    @PostMapping(consumes = "multipart/form-data", value = "/remove-image-pdf")
+    @Operation(
+            summary = "Remove images from file to reduce the file size.",
+            description =
+                    "This endpoint remove images from file to reduce the file size.Input:PDF Output:PDF Type:MISO")
+    public ResponseEntity<byte[]> removeImages(@ModelAttribute PDFFile file) throws IOException {
+
+        MultipartFile pdf = file.getFileInput();
+
+        // Convert the MultipartFile to a byte array
+        byte[] pdfBytes = pdf.getBytes();
+
+        // Load the PDF document from the byte array
+        PDDocument document = Loader.loadPDF(pdfBytes);
+
+        // Remove images from the PDF document using the service
+        PDDocument modifiedDocument = pdfImageRemovalService.removeImagesFromPdf(document);
+
+        // Create a ByteArrayOutputStream to hold the modified PDF data
+        ByteArrayOutputStream outputStream = new ByteArrayOutputStream();
+
+        // Save the modified PDF document to the output stream
+        modifiedDocument.save(outputStream);
+        modifiedDocument.close();
+
+        // Generate a new filename for the modified PDF
+        String mergedFileName =
+                pdf.getOriginalFilename().replaceFirst("[.][^.]+$", "") + "_removed_images.pdf";
+
+        // Convert the byte array to a web response and return it
+        return WebResponseUtils.bytesToWebResponse(outputStream.toByteArray(), mergedFileName);
+    }
+}

src/main/java/stirling/software/SPDF/controller/web/GeneralWebController.java

@@ -310,4 +310,11 @@ public class GeneralWebController {
         model.addAttribute("currentPage", "auto-split-pdf");
         return "auto-split-pdf";
     }
+
+    @GetMapping("/remove-image-pdf")
+    @Hidden
+    public String removeImagePdfForm(Model model) {
+        model.addAttribute("currentPage", "remove-image-pdf");
+        return "remove-image-pdf";
+    }
 }

src/main/java/stirling/software/SPDF/service/PdfImageRemovalService.java

@@ -0,0 +1,43 @@
+package stirling.software.SPDF.service;
+
+import java.io.IOException;
+
+import org.apache.pdfbox.cos.COSName;
+import org.apache.pdfbox.pdmodel.PDDocument;
+import org.apache.pdfbox.pdmodel.PDPage;
+import org.apache.pdfbox.pdmodel.PDResources;
+import org.apache.pdfbox.pdmodel.graphics.PDXObject;
+import org.springframework.stereotype.Service;
+
+/**
+ * Service class responsible for removing image objects from a PDF document.
+ */
+@Service
+public class PdfImageRemovalService {
+
+    /**
+     * Removes all image objects from the provided PDF document.
+     *
+     * This method iterates over each page in the document and removes any
+     * image XObjects found in the page's resources.
+     *
+     * @param document The PDF document from which images will be removed.
+     * @return The modified PDF document with images removed.
+     * @throws IOException If an error occurs while processing the PDF document.
+     */
+    public PDDocument removeImagesFromPdf(PDDocument document) throws IOException {
+        // Iterate over each page in the PDF document
+        for (PDPage page : document.getPages()) {
+            PDResources resources = page.getResources();
+            // Iterate over all XObject names in the page's resources
+            for (COSName name : resources.getXObjectNames()) {
+                // Check if the XObject is an image
+                if (resources.isImageXObject(name)) {
+                    // Remove the image XObject by setting it to null
+                    resources.put(name, (PDXObject) null);
+                }
+            }
+        }
+        return document;
+    }
+}