Merge pull request #196 from Frooodle/compress

Compress abd cert sign

Dockerfile

@@ -1,5 +1,5 @@
 # Build jbig2enc in a separate stage
-FROM frooodle/stirling-pdf-base:beta2
+FROM frooodle/stirling-pdf-base:beta3
 
 # Create scripts folder and copy local scripts
 RUN mkdir /scripts

DockerfileBase

@@ -1,27 +1,3 @@
-# Build jbig2enc in a separate stage
-FROM debian:bullseye-slim as jbig2enc_builder
-
-RUN apt-get update && \
-    apt-get install -y --no-install-recommends \
-        git \
-        automake \
-        autoconf \
-        libtool \
-        libleptonica-dev \
-        pkg-config \
-        ca-certificates \
-        zlib1g-dev \
-		make \
-		g++
-
-RUN git clone https://github.com/agl/jbig2enc && \
-    cd jbig2enc && \
-    ./autogen.sh && \
-    ./configure && \
-    make && \
-    make install
-
-
 # Main stage
 FROM openjdk:17-jdk-slim AS base
 RUN apt-get update && \
@@ -58,5 +34,4 @@ RUN apt-get update && \
 
 # Final stage: Copy necessary files from the previous stage
 FROM base
-COPY --from=python-packages /usr/local /usr/local
-COPY --from=jbig2enc_builder /usr/local/bin/jbig2 /usr/local/bin/jbig2
+COPY --from=python-packages /usr/local /usr/local

build.gradle

@@ -5,7 +5,7 @@ plugins {
 }
 
 group = 'stirling.software'
-version = '0.8.3'
+version = '0.9.0'
 sourceCompatibility = '17'
 
 repositories {
@@ -24,8 +24,9 @@ dependencies {
 
 	//general PDF
     implementation 'org.apache.pdfbox:pdfbox:2.0.28'
-
-
+    implementation 'org.bouncycastle:bcprov-jdk15on:1.70'
+    implementation 'org.bouncycastle:bcpkix-jdk15on:1.70' 
+    implementation 'com.itextpdf:itext7-core:7.2.5'
     implementation 'org.springframework.boot:spring-boot-starter-actuator'
     implementation 'io.micrometer:micrometer-core'
 

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

@@ -49,5 +49,5 @@ public LocaleResolver localeResolver() {
         slr.setDefaultLocale(defaultLocale);
         return slr;
     }
-
+    
 }

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

@@ -1,15 +1,13 @@
 package stirling.software.SPDF.config;
 
-import java.util.HashMap;
 import java.util.HashSet;
 import java.util.Map;
-import java.util.Map.Entry;
 import java.util.Set;
 import java.util.concurrent.ConcurrentHashMap;
 
+import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 import org.springframework.stereotype.Service;
-import org.slf4j.Logger;
 @Service
 public class EndpointConfiguration {
     private static final Logger logger = LoggerFactory.getLogger(EndpointConfiguration.class);

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

@@ -1,12 +1,8 @@
 package stirling.software.SPDF.config;
 import org.springframework.context.annotation.Bean;
 import org.springframework.context.annotation.Configuration;
-import org.springframework.stereotype.Component;
-import org.springframework.web.filter.OncePerRequestFilter;
 
-import io.micrometer.core.instrument.Counter;
 import io.micrometer.core.instrument.Meter;
-import io.micrometer.core.instrument.MeterRegistry;
 import io.micrometer.core.instrument.config.MeterFilter;
 import io.micrometer.core.instrument.config.MeterFilterReply;
 

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

@@ -3,15 +3,11 @@
 import java.io.IOException;
 
 import org.springframework.beans.factory.annotation.Autowired;
-import org.springframework.context.annotation.Bean;
 import org.springframework.stereotype.Component;
 import org.springframework.web.filter.OncePerRequestFilter;
 
 import io.micrometer.core.instrument.Counter;
-import io.micrometer.core.instrument.Meter;
 import io.micrometer.core.instrument.MeterRegistry;
-import io.micrometer.core.instrument.config.MeterFilter;
-import io.micrometer.core.instrument.config.MeterFilterReply;
 import jakarta.servlet.FilterChain;
 import jakarta.servlet.ServletException;
 import jakarta.servlet.http.HttpServletRequest;

src/main/java/stirling/software/SPDF/controller/api/other/CompressController.java

@@ -1,11 +1,24 @@
 package stirling.software.SPDF.controller.api.other;
 
-import java.io.IOException;
+import java.awt.Image;
+import java.awt.image.BufferedImage;
+import java.io.ByteArrayInputStream;
+import java.io.ByteArrayOutputStream;
+import java.io.File;
 import java.nio.file.Files;
 import java.nio.file.Path;
 import java.util.ArrayList;
 import java.util.List;
 
+import javax.imageio.ImageIO;
+
+import org.apache.commons.io.FileUtils;
+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.apache.pdfbox.pdmodel.graphics.image.PDImageXObject;
 import org.slf4j.Logger;
 import org.slf4j.LoggerFactory;
 import org.springframework.http.ResponseEntity;
@@ -17,67 +30,190 @@
 
 import io.swagger.v3.oas.annotations.Operation;
 import io.swagger.v3.oas.annotations.Parameter;
+import io.swagger.v3.oas.annotations.media.Schema;
 import stirling.software.SPDF.utils.PdfUtils;
 import stirling.software.SPDF.utils.ProcessExecutor;
-import io.swagger.v3.oas.annotations.media.Schema;
+
 @RestController
 public class CompressController {
 
     private static final Logger logger = LoggerFactory.getLogger(CompressController.class);
 
     @PostMapping(consumes = "multipart/form-data", value = "/compress-pdf")
-    @Operation(
-        summary = "Optimize PDF file",
-        description = "This endpoint accepts a PDF file and optimizes it based on the provided parameters."
-    )
+    @Operation(summary = "Optimize PDF file", description = "This endpoint accepts a PDF file and optimizes it based on the provided parameters.")
     public ResponseEntity<byte[]> optimizePdf(
-        @RequestPart(required = true, value = "fileInput")
-        @Parameter(description = "The input PDF file to be optimized.", required = true)
-            MultipartFile inputFile,
-        @RequestParam("optimizeLevel")
-        @Parameter(description = "The level of optimization to apply to the PDF file. Higher values indicate greater compression but may reduce quality.", 
-                    schema = @Schema(allowableValues = {"0", "1", "2", "3"}), example = "1")
-            int optimizeLevel,
-        @RequestParam(name = "fastWebView", required = false)
-        @Parameter(description = "If true, optimize the PDF for fast web view. This increases the file size by about 25%.", example = "false")
-            Boolean fastWebView,
-        @RequestParam(name = "jbig2Lossy", required = false)
-        @Parameter(description = "If true, apply lossy JB2 compression to the PDF file.", example = "false")
-            Boolean jbig2Lossy)
-        throws IOException, InterruptedException {
+            @RequestPart(value = "fileInput") @Parameter(description = "The input PDF file to be optimized.", required = true) MultipartFile inputFile,
+            @RequestParam(required = false, value = "optimizeLevel") @Parameter(description = "The level of optimization to apply to the PDF file. Higher values indicate greater compression but may reduce quality.", schema = @Schema(allowableValues = {
+                    "1", "2", "3", "4", "5" })) Integer optimizeLevel,
+            @RequestParam(value = "expectedOutputSize", required = false) @Parameter(description = "The expected output size, e.g. '100MB', '25KB', etc.", required = false) String expectedOutputSizeString)
+            throws Exception {
+
+        if(expectedOutputSizeString == null && optimizeLevel == null) {
+            throw new Exception("Both expected output size and optimize level are not specified");
+        }
+
+        Long expectedOutputSize = 0L;
+        boolean autoMode = false;
+        if (expectedOutputSizeString != null && expectedOutputSizeString.length() > 1 ) {
+            expectedOutputSize = PdfUtils.convertSizeToBytes(expectedOutputSizeString);
+            autoMode = true;
+        }
 
         // Save the uploaded file to a temporary location
         Path tempInputFile = Files.createTempFile("input_", ".pdf");
         inputFile.transferTo(tempInputFile.toFile());
 
+        long inputFileSize = Files.size(tempInputFile);
+
         // Prepare the output file path
         Path tempOutputFile = Files.createTempFile("output_", ".pdf");
 
-        // Prepare the OCRmyPDF command
-        List<String> command = new ArrayList<>();
-        command.add("ocrmypdf");
-        command.add("--skip-text");
-        command.add("--tesseract-timeout=0");
-        command.add("--optimize");
-        command.add(String.valueOf(optimizeLevel));
-        command.add("--output-type");
-        command.add("pdf");
-
-        if (fastWebView != null && fastWebView) {
-            long fileSize = inputFile.getSize();
-            long fastWebViewSize = (long) (fileSize * 1.25); // 25% higher than file size
-            command.add("--fast-web-view");
-            command.add(String.valueOf(fastWebViewSize));
+        // Determine initial optimization level based on expected size reduction, only if in autoMode
+        if(autoMode) {
+            double sizeReductionRatio = expectedOutputSize / (double) inputFileSize;
+            if (sizeReductionRatio > 0.7) {
+                optimizeLevel = 1;
+            } else if (sizeReductionRatio > 0.5) {
+                optimizeLevel = 2;
+            } else if (sizeReductionRatio > 0.35) {
+                optimizeLevel = 3;
+            } else {
+                optimizeLevel = 3;
+            }
         }
 
-        if (jbig2Lossy != null && jbig2Lossy) {
-            command.add("--jbig2-lossy");
+        boolean sizeMet = false;
+        while (!sizeMet && optimizeLevel <= 4) {
+            // Prepare the Ghostscript command
+            List<String> command = new ArrayList<>();
+            command.add("gs");
+            command.add("-sDEVICE=pdfwrite");
+            command.add("-dCompatibilityLevel=1.4");
+
+            switch (optimizeLevel) {
+            case 1:
+                command.add("-dPDFSETTINGS=/prepress");
+                break;
+            case 2:
+                command.add("-dPDFSETTINGS=/printer");
+                break;    
+            case 3:
+                command.add("-dPDFSETTINGS=/ebook");
+                break;
+            case 4:
+                command.add("-dPDFSETTINGS=/screen");
+                break;
+            default:
+                command.add("-dPDFSETTINGS=/default");
+            }
+
+            command.add("-dNOPAUSE");
+            command.add("-dQUIET");
+            command.add("-dBATCH");
+            command.add("-sOutputFile=" + tempOutputFile.toString());
+            command.add(tempInputFile.toString());
+
+            int returnCode = ProcessExecutor.getInstance(ProcessExecutor.Processes.GHOSTSCRIPT).runCommandWithOutputHandling(command);
+
+            // Check if file size is within expected size or not auto mode so instantly finish
+            long outputFileSize = Files.size(tempOutputFile);
+            if (outputFileSize <= expectedOutputSize || !autoMode) {
+                sizeMet = true;
+            } else {
+                // Increase optimization level for next iteration
+                optimizeLevel++;
+                if(autoMode && optimizeLevel > 3) {
+                    System.out.println("Skipping level 4 due to bad results in auto mode");
+                    sizeMet = true;
+                } else if(optimizeLevel == 5) {
+
+                } else {
+                    System.out.println("Increasing ghostscript optimisation level to " + optimizeLevel);
+                }
+            }
         }
 
-        command.add(tempInputFile.toString());
-        command.add(tempOutputFile.toString());
-
-        int returnCode = ProcessExecutor.getInstance(ProcessExecutor.Processes.OCR_MY_PDF).runCommandWithOutputHandling(command);
+
+
+        if (expectedOutputSize != null && autoMode) {
+            long outputFileSize = Files.size(tempOutputFile);
+            if (outputFileSize > expectedOutputSize) {
+                try (PDDocument doc = PDDocument.load(new File(tempOutputFile.toString()))) {
+                    long previousFileSize = 0;
+                    double scaleFactor = 1.0;
+                    while (true) {
+                        for (PDPage page : doc.getPages()) {
+                            PDResources res = page.getResources();
+
+                            for (COSName name : res.getXObjectNames()) {
+                                PDXObject xobj = res.getXObject(name);
+                                if (xobj instanceof PDImageXObject) {
+                                    PDImageXObject image = (PDImageXObject) xobj;
+
+                                    // Get the image in BufferedImage format
+                                    BufferedImage bufferedImage = image.getImage();
+
+                                    // Calculate the new dimensions
+                                    int newWidth = (int)(bufferedImage.getWidth() * scaleFactor);
+                                    int newHeight = (int)(bufferedImage.getHeight() * scaleFactor);
+
+                                    // If the new dimensions are zero, skip this iteration
+                                    if (newWidth == 0 || newHeight == 0) {
+                                        continue;
+                                    }
+
+                                    // Otherwise, proceed with the scaling
+                                    Image scaledImage = bufferedImage.getScaledInstance(newWidth, newHeight, Image.SCALE_SMOOTH);
+
+                                    // Convert the scaled image back to a BufferedImage
+                                    BufferedImage scaledBufferedImage = new BufferedImage(newWidth, newHeight, BufferedImage.TYPE_INT_RGB);
+                                    scaledBufferedImage.getGraphics().drawImage(scaledImage, 0, 0, null);
+
+                                    // Compress the scaled image
+                                    ByteArrayOutputStream compressedImageStream = new ByteArrayOutputStream();
+                                    ImageIO.write(scaledBufferedImage, "jpeg", compressedImageStream);
+                                    byte[] imageBytes = compressedImageStream.toByteArray();
+                                    compressedImageStream.close();
+
+                                    // Convert compressed image back to PDImageXObject
+                                    ByteArrayInputStream bais = new ByteArrayInputStream(imageBytes);
+                                    PDImageXObject compressedImage = PDImageXObject.createFromByteArray(doc, imageBytes, image.getCOSObject().toString());
+
+                                    // Replace the image in the resources with the compressed version
+                                    res.put(name, compressedImage);
+                                }
+                            }
+                        }
+
+                        // save the document to tempOutputFile again
+                        doc.save(tempOutputFile.toString());
+
+                        long currentSize = Files.size(tempOutputFile);
+                        // Check if the overall PDF size is still larger than expectedOutputSize
+                        if (currentSize > expectedOutputSize) {
+                         // Log the current file size and scaleFactor
+
+                            System.out.println("Current file size: " + FileUtils.byteCountToDisplaySize(currentSize));
+                            System.out.println("Current scale factor: " + scaleFactor);
+
+                            // The file is still too large, reduce scaleFactor and try again
+                            scaleFactor *= 0.9; // reduce scaleFactor by 10%
+                            // Avoid scaleFactor being too small, causing the image to shrink to 0
+                            if(scaleFactor < 0.2 || previousFileSize == currentSize){
+                                throw new RuntimeException("Could not reach the desired size without excessively degrading image quality, lowest size recommended is " + FileUtils.byteCountToDisplaySize(currentSize) + ", " + currentSize + " bytes");
+                            }
+                            previousFileSize = currentSize;
+                        } else {
+                            // The file is small enough, break the loop
+                            break;
+                        }
+                    }
+
+                }
+
+
+            }
+        }
 
         // Read the optimized PDF file
         byte[] pdfBytes = Files.readAllBytes(tempOutputFile);