RED-6162 - test issue on bamboo

Merge in RED/ocr-service from shussain/Dockerfile-1677589647499 to master

* commit '4266184456ea4d97fa19b52ff37d5d9fc09dd170':
  RED-5718: Update base image version to allow using random user ids

ocr-service-image-v1/src/main/docker/Dockerfile

@@ -1,4 +1,4 @@
-FROM red/base-image:2.0.0
+FROM red/base-image:2.0.2
 
 COPY "libs/pdftron/OCRModuleLinux.tar.gz" .
 RUN tar xvzf OCRModuleLinux.tar.gz

ocr-service-v1/ocr-service-api-v1/pom.xml

@@ -14,8 +14,7 @@
     <version>1.0-SNAPSHOT</version>
 
     <properties>
-        <persistence-service.version>1.269.0</persistence-service.version>
-        <redaction-service.version>3.155.0</redaction-service.version>
+        <persistence-service.version>2.0.6</persistence-service.version>
         <dsljson.version>1.9.9</dsljson.version>
     </properties>
 
@@ -43,26 +42,9 @@
 
         <dependency>
             <groupId>com.iqser.red.service</groupId>
-            <artifactId>persistence-service-api-v1</artifactId>
-            <exclusions>
-                <exclusion>
-                    <groupId>com.iqser.red.service</groupId>
-                    <artifactId>redaction-service-api-v1</artifactId>
-                </exclusion>
-            </exclusions>
+            <artifactId>persistence-service-internal-api-v1</artifactId>
             <version>${persistence-service.version}</version>
         </dependency>
-        <dependency>
-            <groupId>com.iqser.red.service</groupId>
-            <artifactId>redaction-service-api-v1</artifactId>
-            <exclusions>
-                <exclusion>
-                    <groupId>com.iqser.red.service</groupId>
-                    <artifactId>persistence-service-api-v1</artifactId>
-                </exclusion>
-            </exclusions>
-            <version>${redaction-service.version}</version>
-        </dependency>
 
     </dependencies>
 </project>

ocr-service-v1/ocr-service-api-v1/src/test/java/com/iqser/red/service/ocr/v1/api/model/IdentityTest.java

@@ -0,0 +1,17 @@
+package com.iqser.red.service.ocr.v1.api.model;
+
+import static org.assertj.core.api.Assertions.assertThat;
+
+import org.junit.jupiter.api.Test;
+
+public class IdentityTest {
+
+    @Test
+    public void mockTest() {
+
+        int i = 1;
+        assertThat(i).isEqualTo(1);
+    }
+
+}
+

ocr-service-v1/ocr-service-server-v1/src/main/java/com/iqser/red/service/ocr/v1/server/client/FileStatusProcessingUpdateClient.java

@@ -2,7 +2,7 @@ package com.iqser.red.service.ocr.v1.server.client;
 
 import org.springframework.cloud.openfeign.FeignClient;
 
-import com.iqser.red.service.persistence.service.v1.api.resources.FileStatusProcessingUpdateResource;
+import com.iqser.red.service.persistence.service.v1.api.internal.resources.FileStatusProcessingUpdateResource;
 
 @FeignClient(name = "FileStatusProcessingUpdateResource", url = "${persistence-service.url}")
 public interface FileStatusProcessingUpdateClient extends FileStatusProcessingUpdateResource {

ocr-service-v1/ocr-service-server-v1/src/main/java/com/iqser/red/service/ocr/v1/server/initializer/PDFNetInitializer.java

@@ -1,14 +1,12 @@
 package com.iqser.red.service.ocr.v1.server.initializer;
 
-import javax.annotation.PostConstruct;
-
+import com.pdftron.pdf.PDFNet;
+import lombok.RequiredArgsConstructor;
+import lombok.SneakyThrows;
 import org.springframework.beans.factory.annotation.Value;
 import org.springframework.stereotype.Component;
 
-import com.pdftron.pdf.PDFNet;
-
-import lombok.RequiredArgsConstructor;
-import lombok.SneakyThrows;
+import javax.annotation.PostConstruct;
 
 @Component
 @RequiredArgsConstructor
@@ -29,7 +27,5 @@ public class PDFNetInitializer {
         PDFNet.setTempPath("/tmp/pdftron");
         PDFNet.addResourceSearchPath(ocrModulePath);
         PDFNet.initialize(pdftronLicense);
-
     }
-
 }

ocr-service-v1/ocr-service-server-v1/src/main/java/com/iqser/red/service/ocr/v1/server/model/ImagePosition.java

@@ -1,6 +1,7 @@
 package com.iqser.red.service.ocr.v1.server.model;
 
-import com.iqser.red.service.redaction.v1.model.Rectangle;
+
+import com.iqser.red.service.persistence.service.v1.api.shared.model.redactionlog.Rectangle;
 
 import lombok.AllArgsConstructor;
 import lombok.Data;

ocr-service-v1/ocr-service-server-v1/src/main/java/com/iqser/red/service/ocr/v1/server/service/FileStorageService.java

@@ -7,7 +7,7 @@ import org.apache.commons.io.IOUtils;
 import org.springframework.stereotype.Service;
 
 import com.iqser.red.service.ocr.v1.server.model.image.ImageServiceResponse;
-import com.iqser.red.service.persistence.service.v1.api.model.dossiertemplate.dossier.file.FileType;
+import com.iqser.red.service.persistence.service.v1.api.shared.model.dossiertemplate.dossier.file.FileType;
 import com.iqser.red.storage.commons.service.StorageService;
 
 import lombok.RequiredArgsConstructor;

ocr-service-v1/ocr-service-server-v1/src/main/java/com/iqser/red/service/ocr/v1/server/service/ImagePositionRetrievalService.java

@@ -27,9 +27,12 @@ public class ImagePositionRetrievalService {
 
     private static final double TOLERANCE = 1e-1;
 
+    // any image with smaller height and width than this gets thrown out, see everyPointInDashedLineIsImage.pdf
+    private static final int PIXEL_THRESHOLD = 10;
+
 
     /**
-     * Iterates over all elements in a PDF Document and retrieves the bounding box for each image,
+     * Iterates over all elements in a PDF Document and retrieves the bounding box for each image, that is larger than the pixel threshold of 10 in either dimension.
      * Then it adjusts the bounding boxes for the page rotation.
      * If the mirrorY flag is set, the Y Coordinates are mirrored and moved up by the page height. This is required for PDFTrons OCRModule.
      *
@@ -44,16 +47,17 @@ public class ImagePositionRetrievalService {
         ElementReader reader = new ElementReader();
         for (int pageId = 1; pageId <= pdfDoc.getPageCount(); ++pageId) {
             RectCollection imagePositions = new RectCollection();
-            reader.begin(pdfDoc.getPage(pageId));
 
+            reader.begin(pdfDoc.getPage(pageId));
             findImagePositionsOnPage(reader, imagePositions, pdfDoc.getPage(pageId), mirrorY);
             imagePositions = mergeOverlappingRects(imagePositions);
-
             reader.end();
+
             if (imagePositions.getNumRects() > 0) {
                 pageIdToImagePositions.put(pageId, imagePositions);
             }
         }
+        reader.destroy();
         return pageIdToImagePositions;
     }
 
@@ -63,7 +67,12 @@ public class ImagePositionRetrievalService {
         Element element;
         while ((element = reader.next()) != null) {
             switch (element.getType()) {
-                case Element.e_image, Element.e_inline_image -> imagePositions.addRect(toRotationAdjustedRect(element.getBBox(), currentPage, mirrorY));
+                case Element.e_image, Element.e_inline_image -> {
+                    // see everyPointInDashedLineIsImage.pdf TestFile
+                    if (element.getImageHeight() > PIXEL_THRESHOLD || element.getImageWidth() > PIXEL_THRESHOLD) {
+                        imagePositions.addRect(toRotationAdjustedRect(element.getBBox(), currentPage, mirrorY));
+                    }
+                }
                 case Element.e_form -> {
                     reader.formBegin();
                     findImagePositionsOnPage(reader, imagePositions, currentPage, mirrorY);
@@ -77,39 +86,49 @@ public class ImagePositionRetrievalService {
     @SneakyThrows
     public RectCollection mergeOverlappingRects(RectCollection imagePositions) {
 
-        if (imagePositions.getNumRects() == 1) {
+        if (imagePositions.getNumRects() < 2) {
             return imagePositions;
         }
 
         List<Rectangle2D> rectangleList = toSortedRectangleList(imagePositions);
 
-        rectangleList = mergeRectangleListRecursive(rectangleList, 0);
+        mergeRectangleList(rectangleList);
+
         return toRectCollection(rectangleList);
     }
 
 
     // Sometimes images are split up into stripes, here we merge the positions of aligned and intersecting rectangles into one larger rectangle
-    private List<Rectangle2D> mergeRectangleListRecursive(List<Rectangle2D> rectangleList, int currentIdx) {
+    private void mergeRectangleList(List<Rectangle2D> rectangleList) {
 
-        if (rectangleList.size() < currentIdx + 2) {
-            return rectangleList;
+        for (int idx = 0; rectangleList.size() >= idx + 2; ) {
+
+            var rect1 = rectangleList.get(idx);
+            var rect2 = rectangleList.get(idx + 1);
+
+            if (intersects(rect1, rect2) && isAlignedXOrY(rect1, rect2)) {
+                rectangleList.remove(idx + 1);
+                rectangleList.remove(idx);
+                rectangleList.add(idx, rect1.createUnion(rect2));
+            } else {
+                ++idx;
+            }
         }
+    }
 
-        var rect1 = rectangleList.get(currentIdx);
-        var rect2 = rectangleList.get(currentIdx + 1);
+
+    private boolean intersects(Rectangle2D rect1, Rectangle2D rect2) {
+
+        return rect1.intersects(rect2.getMinX() - TOLERANCE, rect2.getMinY() - TOLERANCE, rect2.getWidth() + (2 * TOLERANCE), rect2.getHeight() + (2 * TOLERANCE));
+    }
+
+
+    private boolean isAlignedXOrY(Rectangle2D rect1, Rectangle2D rect2) {
 
         boolean isAlignedX = Math.abs(rect1.getMinX() - rect2.getMinX()) < TOLERANCE && Math.abs(rect1.getMaxX() - rect2.getMaxX()) < TOLERANCE;
         boolean isAlignedY = Math.abs(rect1.getMinY() - rect2.getMinY()) < TOLERANCE && Math.abs(rect1.getMaxY() - rect2.getMaxY()) < TOLERANCE;
-        boolean intersects = rect1.intersects(rect2.getMinX() - TOLERANCE, rect2.getMinY() - TOLERANCE, rect2.getWidth() + (2 * TOLERANCE), rect2.getHeight() + (2 * TOLERANCE));
 
-        if (intersects && (isAlignedX || isAlignedY)) {
-            rectangleList.remove(currentIdx + 1);
-            rectangleList.remove(currentIdx);
-            rectangleList.add(currentIdx, rect1.createUnion(rect2));
-            return mergeRectangleListRecursive(rectangleList, currentIdx);
-        } else {
-            return mergeRectangleListRecursive(rectangleList, currentIdx + 1);
-        }
+        return isAlignedX || isAlignedY;
     }
 
 

ocr-service-v1/ocr-service-server-v1/src/main/java/com/iqser/red/service/ocr/v1/server/service/InvisibleElementRemovalService.java

@@ -76,6 +76,7 @@ public class InvisibleElementRemovalService {
             Page page = iterator.next();
 
             visitedXObjIds.add(page.getSDFObj().getObjNum());
+
             InvisibleElementRemovalContext context = InvisibleElementRemovalContext.builder()
                     .reader(reader)
                     .clippingPathStack(new ClippingPathStack(page.getMediaBox()))
@@ -90,8 +91,20 @@ public class InvisibleElementRemovalService {
             context.visitedXObjIds().clear();
 
             removeOverlappedElements(page, writer, context);
+            reader.end();
+            writer.end();
         }
-        pdfDoc.save(out, SDFDoc.SaveMode.REMOVE_UNUSED, null);
+
+        try {
+            pdfDoc.save(out, SDFDoc.SaveMode.LINEARIZED, null);
+        } catch (Exception e) {
+            log.error("File could not be saved after invisible element removal");
+            throw new RuntimeException(e);
+        }
+
+        writer.destroy();
+        reader.destroy();
+        pdfDoc.close();
     }
 
 
@@ -214,7 +227,7 @@ public class InvisibleElementRemovalService {
             formWriter.setDefaultGState(context.reader());
 
             processElements(formWriter, context);
-            formWriter.end();
+            formWriter.destroy();
             context.reader().end();
         }
     }
@@ -222,7 +235,14 @@ public class InvisibleElementRemovalService {
 
     private void processPath(Element pathElement, ElementWriter writer, InvisibleElementRemovalContext context) throws PDFNetException {
 
-        GeneralPath linePath = convertToGeneralPath(pathElement.getPathData());
+        PathData pathData = pathElement.getPathData();
+
+        if (pathData.getOperators().length == 0 && pathData.getPoints().length == 0) {
+            writer.writeGStateChanges(pathElement);
+            return;
+        }
+
+        GeneralPath linePath = convertToGeneralPath(pathData);
 
         //transform path to initial user space
         var ctm = pathElement.getCTM();
@@ -344,7 +364,7 @@ public class InvisibleElementRemovalService {
             formWriter.setDefaultGState(context.reader());
 
             processOverlappedElements(formWriter, context);
-            formWriter.end();
+            formWriter.destroy();
             context.reader().end();
         }
     }
@@ -419,6 +439,9 @@ public class InvisibleElementRemovalService {
         rect.getGState().setStrokeColorSpace(ColorSpace.createDeviceRGB());
         rect.getGState().setStrokeColor(colorPt);
         writer.writePlacedElement(rect);
+
+        colorPt.destroy();
+        eb.destroy();
     }
 
 

ocr-service-v1/ocr-service-server-v1/src/main/java/com/iqser/red/service/ocr/v1/server/service/OCRService.java

@@ -1,31 +1,23 @@
 package com.iqser.red.service.ocr.v1.server.service;
 
-import java.io.ByteArrayInputStream;
-import java.io.ByteArrayOutputStream;
-import java.io.InputStream;
-import java.io.OutputStream;
-import java.util.Map;
-
-import org.springframework.amqp.rabbit.core.RabbitTemplate;
-import org.springframework.stereotype.Service;
-
 import com.fasterxml.jackson.databind.ObjectMapper;
 import com.iqser.red.service.ocr.v1.api.model.OCRStatusUpdateResponse;
 import com.iqser.red.service.ocr.v1.server.configuration.MessagingConfiguration;
 import com.iqser.red.service.ocr.v1.server.settings.OcrServiceSettings;
 import com.pdftron.common.PDFNetException;
-import com.pdftron.pdf.OCRModule;
-import com.pdftron.pdf.OCROptions;
-import com.pdftron.pdf.Optimizer;
-import com.pdftron.pdf.PDFDoc;
-import com.pdftron.pdf.Page;
-import com.pdftron.pdf.RectCollection;
+import com.pdftron.pdf.*;
 import com.pdftron.sdf.SDFDoc;
-
 import io.micrometer.core.annotation.Timed;
 import lombok.RequiredArgsConstructor;
 import lombok.SneakyThrows;
 import lombok.extern.slf4j.Slf4j;
+import org.springframework.amqp.rabbit.core.RabbitTemplate;
+import org.springframework.stereotype.Service;
+
+import java.io.*;
+import java.util.Map;
+
+import static java.lang.String.format;
 
 @Slf4j
 @Service
@@ -59,16 +51,22 @@ public class OCRService {
      * @param fileId    The file id
      * @param out       OutputStream to write the file to
      */
-    @SneakyThrows
     @Timed("redactmanager_runOcrOnDocument")
-    public void runOcrOnDocument(String dossierId, String fileId, OutputStream out) {
+    public void runOcrOnDocument(String dossierId, String fileId, OutputStream out) throws IOException {
 
         try (ByteArrayOutputStream transferOutputStream = new ByteArrayOutputStream()) {
             try (InputStream fileStream = fileStorageService.getOriginalFileAsStream(dossierId, fileId)) {
+                long removalStart = System.currentTimeMillis();
+                log.debug("Start invisible element removal for file with dossierId {} and fileId {}", dossierId, fileId);
                 invisibleElementRemovalService.removeInvisibleElements(fileStream, transferOutputStream, false);
+                long removalEnd = System.currentTimeMillis();
+                log.debug("Invisible element removal successful for file with dossierId {} and fileId {}, took {}s", dossierId, fileId, format("%.1f", (removalEnd - removalStart) / 1000.0));
             }
             try (InputStream transferInputStream = new ByteArrayInputStream(transferOutputStream.toByteArray())) {
+                long ocrStart = System.currentTimeMillis();
                 runOcr(transferInputStream, out, fileId);
+                long ocrEnd = System.currentTimeMillis();
+                log.info("ocr successful for file with dossierId {} and fileId {}, took {}s", dossierId, fileId, format("%.1f", (ocrEnd - ocrStart) / 1000.0));
             }
         }
     }
@@ -81,36 +79,27 @@ public class OCRService {
 
         Map<Integer, RectCollection> pageIdToRectCollection = imagePositionRetrievalService.getImagePositionPerPage(pdfDoc, true);
 
+        // Optimization:
+        // When a page does not have a TextZone, PDFTron whites out the page. But, PDFTron scans it anyway, resulting in a longer runtime.
+        // So, we need to remove pages without images.
+        // Furthermore, creating a new document is *much* faster than reusing the same document and adding/removing pages one by one.
+        // Therefore, we create a new Document with a single page for every page that contains an image.
         int numProcessedPages = 0;
         for (Integer pageId : pageIdToRectCollection.keySet()) {
             try {
-                // optimization: creating a new document is faster than reusing the same and adding/removing pages one by one
-                OCROptions options = new OCROptions();
-                PDFDoc ocrPageDoc = new PDFDoc();
-                // optimization: only scanning pages that contain images
-                Page pdfPage = pdfDoc.getPage(pageId);
-                // optimization: this line ensures the ocr text is placed correctly by PDFTron
-                pdfPage.setMediaBox(pdfPage.getCropBox());
-                ocrPageDoc.pagePushBack(pdfPage);
-                options.addTextZonesForPage(pageIdToRectCollection.get(pageId), 1);
-                options.addLang(ENGLISH);
-                options.addDPI(settings.getOcrDPI());
-
-                OCRModule.processPDF(ocrPageDoc, options);
+                PDFDoc singlePagePdfDoc = extractSinglePagePdfDoc(pdfDoc, pageId);
+                processOcr(pageIdToRectCollection, pageId, singlePagePdfDoc);
                 ++numProcessedPages;
 
-                StringBuilder zonesString = new StringBuilder();
-                for (int j = 0; j < pageIdToRectCollection.get(pageId).getNumRects(); ++j) {
-                    var r = pageIdToRectCollection.get(pageId).getRectAt(j);
-                    zonesString.append(String.format("[lower left (%.1f|%.1f) upper right (%.1f|%.1f)]", r.getX1(), r.getY1(), r.getX2(), r.getY2()));
-                }
-                log.info("{}/{} Page {} done, OCR regions {}", numProcessedPages, pageIdToRectCollection.size(), pageId, zonesString);
+                log.info("{}/{} Page {} done, OCR regions {}",
+                        numProcessedPages,
+                        pageIdToRectCollection.size(),
+                        pageId,
+                        getAllOcrTextZonesAsString(pageIdToRectCollection, pageId));
 
-                // re-adding OCR pages
-                Page ocrPage = ocrPageDoc.getPage(1);
-                pdfDoc.pageInsert(pdfDoc.getPageIterator(pageId), ocrPage);
-                pdfDoc.pageRemove(pdfDoc.getPageIterator(pageId + 1));
-                ocrPageDoc.close();
+                replaceOriginalPageWithOcrPage(pdfDoc, pageId, singlePagePdfDoc);
+
+                singlePagePdfDoc.close();
 
                 rabbitTemplate.convertAndSend(MessagingConfiguration.OCR_STATUS_UPDATE_RESPONSE_QUEUE,
                         objectMapper.writeValueAsString(OCRStatusUpdateResponse.builder()
@@ -120,7 +109,7 @@ public class OCRService {
                                 .build()));
 
             } catch (PDFNetException e) {
-                log.error("failed to process page {}", pageId);
+                log.error("Failed to process page {}", pageId);
                 throw new RuntimeException(e);
             }
         }
@@ -134,7 +123,53 @@ public class OCRService {
                         .build()));
 
         Optimizer.optimize(pdfDoc);
-        pdfDoc.save(out, SDFDoc.SaveMode.LINEARIZED, null);
+        try {
+            pdfDoc.save(out, SDFDoc.SaveMode.LINEARIZED, null);
+        } catch (Exception e) {
+            log.error("Processed File with fileId {} could not be saved", fileId);
+            throw new RuntimeException(e);
+        }
+        pdfDoc.close();
+    }
+
+
+    private void processOcr(Map<Integer, RectCollection> pageIdToRectCollection, Integer pageId, PDFDoc singlePagePdfDoc) throws PDFNetException {
+
+        OCROptions options = new OCROptions();
+        options.addTextZonesForPage(pageIdToRectCollection.get(pageId), 1);
+        options.addLang(ENGLISH);
+        options.addDPI(settings.getOcrDPI());
+
+        OCRModule.processPDF(singlePagePdfDoc, options);
+    }
+
+
+    private static PDFDoc extractSinglePagePdfDoc(PDFDoc pdfDoc, Integer pageId) throws PDFNetException {
+
+        PDFDoc singlePagePdfDoc = new PDFDoc();
+        Page page = pdfDoc.getPage(pageId);
+        page.setMediaBox(page.getCropBox()); // this line ensures the ocr text is placed correctly by PDFTron, see TestFile MediaBoxBiggerThanCropBox.pdf
+        singlePagePdfDoc.pagePushBack(page);
+        return singlePagePdfDoc;
+    }
+
+
+    private static void replaceOriginalPageWithOcrPage(PDFDoc pdfDoc, Integer pageId, PDFDoc ocrPageDoc) throws PDFNetException {
+
+        Page ocrPage = ocrPageDoc.getPage(1);
+        pdfDoc.pageInsert(pdfDoc.getPageIterator(pageId), ocrPage);
+        pdfDoc.pageRemove(pdfDoc.getPageIterator(pageId + 1));
+    }
+
+
+    private static StringBuilder getAllOcrTextZonesAsString(Map<Integer, RectCollection> pageIdToRectCollection, Integer pageId) throws PDFNetException {
+
+        StringBuilder zonesString = new StringBuilder();
+        for (int j = 0; j < pageIdToRectCollection.get(pageId).getNumRects(); ++j) {
+            var r = pageIdToRectCollection.get(pageId).getRectAt(j);
+            zonesString.append(format("[lower left (%.1f|%.1f) upper right (%.1f|%.1f)]", r.getX1(), r.getY1(), r.getX2(), r.getY2()));
+        }
+        return zonesString;
     }
 
 }

ocr-service-v1/ocr-service-server-v1/src/main/java/com/iqser/red/service/ocr/v1/server/service/OcrMessageReceiver.java

@@ -1,24 +1,23 @@
 package com.iqser.red.service.ocr.v1.server.service;
 
-import java.io.ByteArrayInputStream;
-import java.io.ByteArrayOutputStream;
-import java.io.IOException;
-
-import org.springframework.amqp.AmqpRejectAndDontRequeueException;
-import org.springframework.amqp.rabbit.annotation.RabbitHandler;
-import org.springframework.amqp.rabbit.annotation.RabbitListener;
-import org.springframework.http.HttpStatus;
-import org.springframework.stereotype.Service;
-
 import com.fasterxml.jackson.core.JsonProcessingException;
 import com.fasterxml.jackson.databind.ObjectMapper;
 import com.iqser.red.service.ocr.v1.api.model.DocumentRequest;
 import com.iqser.red.service.ocr.v1.server.client.FileStatusProcessingUpdateClient;
 import com.iqser.red.service.ocr.v1.server.configuration.MessagingConfiguration;
-
+import com.iqser.red.service.ocr.v1.server.initializer.PDFNetInitializer;
 import feign.FeignException;
 import lombok.RequiredArgsConstructor;
 import lombok.extern.slf4j.Slf4j;
+import org.springframework.amqp.AmqpRejectAndDontRequeueException;
+import org.springframework.amqp.rabbit.annotation.RabbitHandler;
+import org.springframework.amqp.rabbit.annotation.RabbitListener;
+import org.springframework.http.HttpStatus;
+import org.springframework.stereotype.Service;
+
+import java.io.ByteArrayInputStream;
+import java.io.ByteArrayOutputStream;
+import java.io.IOException;
 
 @Slf4j
 @Service
@@ -38,7 +37,6 @@ public class OcrMessageReceiver {
 
         DocumentRequest ocrRequestMessage = objectMapper.readValue(in, DocumentRequest.class);
 
-        long start = System.currentTimeMillis();
         log.info("Start ocr for file with dossierId {} and fileId {}", ocrRequestMessage.getDossierId(), ocrRequestMessage.getFileId());
 
         setStatusOcrProcessing(ocrRequestMessage.getDossierId(), ocrRequestMessage.getFileId());
@@ -48,18 +46,16 @@ public class OcrMessageReceiver {
             fileStorageService.storeUntouchedFile(ocrRequestMessage.getDossierId(), ocrRequestMessage.getFileId(), originalFile);
         }
 
-        try (var out = new ByteArrayOutputStream()) {
-            ocrService.runOcrOnDocument(ocrRequestMessage.getDossierId(), ocrRequestMessage.getFileId(), out);
-
-            fileStorageService.storeOriginalFile(ocrRequestMessage.getDossierId(), ocrRequestMessage.getFileId(), new ByteArrayInputStream(out.toByteArray()));
+        try (var transferStream = new ByteArrayOutputStream()) {
+            ocrService.runOcrOnDocument(ocrRequestMessage.getDossierId(), ocrRequestMessage.getFileId(), transferStream);
+            try (var inputStream = new ByteArrayInputStream(transferStream.toByteArray())) {
+                fileStorageService.storeOriginalFile(ocrRequestMessage.getDossierId(), ocrRequestMessage.getFileId(), inputStream);
+            }
         } catch (IOException e) {
+            log.error("Failed to store file with dossierId {} and fileId {}", ocrRequestMessage.getDossierId(), ocrRequestMessage.getFileId());
             throw new RuntimeException(e);
         }
 
-
-        long end = System.currentTimeMillis();
-        log.info("Successfully processed ocr for file with dossierId {} and fileId {}, took {}", ocrRequestMessage.getDossierId(), ocrRequestMessage.getFileId(), end - start);
-
         fileStatusProcessingUpdateClient.ocrSuccessful(ocrRequestMessage.getDossierId(), ocrRequestMessage.getFileId());
     }
 

ocr-service-v1/ocr-service-server-v1/src/test/java/com/iqser/red/service/ocr/v1/server/AbstractTest.java

@@ -0,0 +1,76 @@
+package com.iqser.red.service.ocr.v1.server;
+
+import static org.assertj.core.api.Assertions.assertThat;
+
+import org.junit.jupiter.api.AfterAll;
+import org.junit.jupiter.api.AfterEach;
+import org.junit.jupiter.api.extension.ExtendWith;
+import org.springframework.amqp.rabbit.core.RabbitTemplate;
+import org.springframework.beans.factory.annotation.Autowired;
+import org.springframework.boot.autoconfigure.EnableAutoConfiguration;
+import org.springframework.boot.autoconfigure.amqp.RabbitAutoConfiguration;
+import org.springframework.boot.test.context.SpringBootTest;
+import org.springframework.boot.test.mock.mockito.MockBean;
+import org.springframework.context.annotation.Bean;
+import org.springframework.context.annotation.Configuration;
+import org.springframework.context.annotation.Import;
+import org.springframework.context.annotation.Primary;
+import org.springframework.test.context.junit.jupiter.SpringExtension;
+
+import com.iqser.red.service.ocr.v1.server.utils.FileSystemBackedStorageService;
+import com.iqser.red.storage.commons.StorageAutoConfiguration;
+import com.iqser.red.storage.commons.service.StorageService;
+import com.pdftron.pdf.PDFNet;
+
+import lombok.SneakyThrows;
+
+@ExtendWith(SpringExtension.class)
+@SpringBootTest(classes = Application.class, webEnvironment = SpringBootTest.WebEnvironment.RANDOM_PORT)
+@Import(AbstractTest.TestConfiguration.class)
+public class AbstractTest {
+
+    @Autowired
+    protected StorageService storageService;
+
+    @MockBean
+    protected RabbitTemplate rabbitTemplate;
+
+
+    @AfterAll
+    public static void terminatePDFNet() {
+        PDFNet.terminate();
+        System.out.println("PDFNet Terminated");
+    }
+
+
+    @SneakyThrows
+    public void dummyTest() {
+
+        // Build needs one test to not fail.
+        assertThat(1).isEqualTo(1);
+    }
+
+
+    @AfterEach
+    public void cleanupStorage() {
+
+        if (this.storageService instanceof FileSystemBackedStorageService) {
+            ((FileSystemBackedStorageService) this.storageService).clearStorage();
+        }
+    }
+
+
+
+    @Configuration
+    @EnableAutoConfiguration(exclude = {StorageAutoConfiguration.class, RabbitAutoConfiguration.class})
+    public static class TestConfiguration {
+
+        @Bean
+        @Primary
+        public StorageService inMemoryStorage() {
+
+            return new FileSystemBackedStorageService();
+        }
+
+    }
+}

ocr-service-v1/ocr-service-server-v1/src/test/java/com/iqser/red/service/ocr/v1/server/OcrServiceIntegrationTest.java

@@ -1,100 +1,67 @@
 package com.iqser.red.service.ocr.v1.server;
 
 import static com.iqser.red.service.ocr.v1.server.utils.OsUtils.getTemporaryDirectory;
+import static com.iqser.red.service.ocr.v1.server.utils.PdfTextExtraction.extractAllTextFromDocument;
 import static org.assertj.core.api.Assertions.assertThat;
 
 import java.io.FileInputStream;
 import java.io.FileOutputStream;
-import java.util.ArrayList;
-import java.util.List;
 import java.util.concurrent.TimeUnit;
 
-import io.micrometer.prometheus.PrometheusMeterRegistry;
-import io.micrometer.prometheus.PrometheusTimer;
-import org.junit.jupiter.api.AfterEach;
 import org.junit.jupiter.api.BeforeEach;
 import org.junit.jupiter.api.Disabled;
 import org.junit.jupiter.api.Test;
-import org.junit.jupiter.api.extension.ExtendWith;
-import org.springframework.amqp.rabbit.core.RabbitTemplate;
 import org.springframework.beans.factory.annotation.Autowired;
-import org.springframework.boot.autoconfigure.EnableAutoConfiguration;
-import org.springframework.boot.autoconfigure.amqp.RabbitAutoConfiguration;
 import org.springframework.boot.test.context.SpringBootTest;
-import org.springframework.boot.test.mock.mockito.MockBean;
-import org.springframework.context.annotation.Bean;
-import org.springframework.context.annotation.Configuration;
-import org.springframework.context.annotation.Import;
-import org.springframework.context.annotation.Primary;
 import org.springframework.core.io.ClassPathResource;
-import org.springframework.test.context.junit.jupiter.SpringExtension;
 
 import com.fasterxml.jackson.databind.ObjectMapper;
 import com.iqser.red.service.ocr.v1.server.service.FileStorageService;
 import com.iqser.red.service.ocr.v1.server.service.OCRService;
-import com.iqser.red.service.ocr.v1.server.utils.FileSystemBackedStorageService;
-import com.iqser.red.service.persistence.service.v1.api.model.dossiertemplate.dossier.file.FileType;
-import com.iqser.red.storage.commons.StorageAutoConfiguration;
-import com.iqser.red.storage.commons.service.StorageService;
+import com.iqser.red.service.persistence.service.v1.api.shared.model.dossiertemplate.dossier.file.FileType;
 import com.pdftron.pdf.OCRModule;
-import com.pdftron.pdf.PDFDoc;
-import com.pdftron.pdf.Page;
-import com.pdftron.pdf.PageIterator;
-import com.pdftron.pdf.TextExtractor;
 
+import io.micrometer.prometheus.PrometheusMeterRegistry;
+import io.micrometer.prometheus.PrometheusTimer;
 import lombok.SneakyThrows;
 
-@ExtendWith(SpringExtension.class)
-@SpringBootTest(classes = Application.class, webEnvironment = SpringBootTest.WebEnvironment.RANDOM_PORT //
-        , properties = {"pdftron.ocrmodule.path=/YourOCRModulePath"})
-@Import(OcrServiceIntegrationTest.TestConfiguration.class)
-public class OcrServiceIntegrationTest {
 
-    @Autowired
-    protected StorageService storageService;
-
-    @Autowired
-    protected FileStorageService fileStorageService;
+@Disabled // OCRModule is not available on build server. If you want to run the test set the property at the top.
+@SpringBootTest(properties = {"pdftron.ocrmodule.path=/YourOCRModulePath"})
+public class OcrServiceIntegrationTest extends AbstractTest {
 
     @Autowired
     protected ObjectMapper objectMapper;
 
-    @MockBean
-    protected RabbitTemplate rabbitTemplate;
-
     @Autowired
     private OCRService ocrService;
 
     @Autowired
     private PrometheusMeterRegistry registry;
 
-
     @BeforeEach
     @SneakyThrows
-    @Disabled // OCRModule is not available on build server. If you want to run the test set the property at the top.
     public void assertOCRModuleIsLoaded() {
-
         assert OCRModule.isModuleAvailable();
     }
 
 
     @Test
-    @Disabled // OCRModule is not available on build server. If you want to run the test set the property at the top.
-    public void testOCRMetrics(){
+    public void testOCRMetrics() {
+
         testOCR("Watermark");
         testOCR("Watermark");
         testOCR("Watermark");
 
-        var ocrOnDocumentMeter = registry.getMeters().stream()
-                .filter(m -> m.getId().getName().equalsIgnoreCase("redactmanager_runOcrOnDocument")).findAny();
+        var ocrOnDocumentMeter = registry.getMeters().stream().filter(m -> m.getId().getName().equalsIgnoreCase("redactmanager_runOcrOnDocument")).findAny();
         assertThat(ocrOnDocumentMeter.isPresent()).isTrue();
         PrometheusTimer timer = (PrometheusTimer) ocrOnDocumentMeter.get();
         assertThat(timer.count()).isEqualTo(3);
         assertThat(timer.mean(TimeUnit.SECONDS)).isGreaterThan(0.1);
     }
 
+
     @Test
-    @Disabled // OCRModule is not available on build server. If you want to run the test set the property at the top.
     public void testOcr() {
         // check visually for most of the images containing text, the resulting text is kind of nonsense, just ensure it is there
         String text = testOCR("StitchedImagesMultiPage");
@@ -102,7 +69,6 @@ public class OcrServiceIntegrationTest {
 
 
     @Test
-    @Disabled // OCRModule is not available on build server. If you want to run the test set the property at the top.
     public void testManyRotatedImages() {
         // check visually for most of the images containing text, the resulting text is kind of nonsense, just ensure it is there
         String text = testOCR("manyRotatedImages");
@@ -111,7 +77,6 @@ public class OcrServiceIntegrationTest {
 
 
     @Test
-    @Disabled // OCRModule is not available on build server. If you want to run the test set the property at the top.
     public void testMergeImages() {
         // check visually for most of the images containing text, the resulting text is kind of nonsense, just ensure it is there
         String text = testOCR("merge_images");
@@ -132,7 +97,6 @@ public class OcrServiceIntegrationTest {
 
 
     @Test
-    @Disabled // OCRModule is not available on build server. If you want to run the test set the property at the top.
     public void testOCRWatermark() {
 
         assertThat(testOCR("Watermark")).contains("syngenta");
@@ -140,7 +104,6 @@ public class OcrServiceIntegrationTest {
 
 
     @Test
-    @Disabled // OCRModule is not available on build server. If you want to run the test set the property at the top.
     public void testOCRInvisibleText() {
 
         String text = testOCR("InvisibleText");
@@ -153,62 +116,17 @@ public class OcrServiceIntegrationTest {
     private String testOCR(String fileName) {
 
         ClassPathResource pdfFileResource = new ClassPathResource("files/" + fileName + ".pdf");
-
         var originId = FileStorageService.getStorageId("dossier", "file", FileType.ORIGIN);
         try (var fileStream = pdfFileResource.getInputStream()) {
             storageService.storeObject(originId, fileStream);
         }
-
         try (var out = new FileOutputStream(getTemporaryDirectory() + "/" + fileName + ".pdf")) {
             ocrService.runOcrOnDocument("dossier", "file", out);
+            System.out.println("File:" + getTemporaryDirectory() + "/" + fileName + ".pdf");
         }
 
-        TextExtractor extractor = new TextExtractor();
-        List<String> texts = new ArrayList<>();
-        PDFDoc pdfDoc;
-
         try (var fileStream = new FileInputStream(getTemporaryDirectory() + "/" + fileName + ".pdf")) {
-            pdfDoc = new PDFDoc(fileStream);
-        }
-        PageIterator iterator = pdfDoc.getPageIterator();
-        while (iterator.hasNext()) {
-            Page page = iterator.next();
-            extractor.begin(page);
-            texts.add(extractor.getAsText());
-        }
-        System.out.println("File:" + getTemporaryDirectory() + "/" + fileName + ".pdf");
-        return String.join("\n", texts);
-    }
-
-
-    @SneakyThrows
-    public void dummyTest() {
-
-        // Build needs one text to not fail.
-        assertThat(1).isEqualTo(1);
-    }
-
-
-    @AfterEach
-    public void cleanupStorage() {
-
-        if (this.storageService instanceof FileSystemBackedStorageService) {
-            ((FileSystemBackedStorageService) this.storageService).clearStorage();
+            return extractAllTextFromDocument(fileStream);
         }
     }
-
-
-    @Configuration
-    @EnableAutoConfiguration(exclude = {StorageAutoConfiguration.class, RabbitAutoConfiguration.class})
-    public static class TestConfiguration {
-
-        @Bean
-        @Primary
-        public StorageService inmemoryStorage() {
-
-            return new FileSystemBackedStorageService();
-        }
-
-    }
-
 }

ocr-service-v1/ocr-service-server-v1/src/test/java/com/iqser/red/service/ocr/v1/server/service/ImagePositionRetrievalServiceTest.java

@@ -1,6 +1,8 @@
 package com.iqser.red.service.ocr.v1.server.service;
 
 import static com.iqser.red.service.ocr.v1.server.utils.OsUtils.getTemporaryDirectory;
+import static com.iqser.red.service.ocr.v1.server.utils.PdfDraw.drawGrid;
+import static com.iqser.red.service.ocr.v1.server.utils.PdfDraw.drawRectCollection;
 import static org.assertj.core.api.Assertions.assertThat;
 
 import java.io.FileInputStream;
@@ -13,43 +15,24 @@ import java.util.Map;
 import java.util.stream.Collectors;
 
 import org.junit.jupiter.api.Test;
-import org.junit.jupiter.api.extension.ExtendWith;
-import org.springframework.amqp.rabbit.core.RabbitTemplate;
 import org.springframework.beans.factory.annotation.Autowired;
-import org.springframework.boot.test.context.SpringBootTest;
-import org.springframework.boot.test.mock.mockito.MockBean;
-import org.springframework.context.annotation.Import;
 import org.springframework.core.io.ClassPathResource;
-import org.springframework.test.context.junit.jupiter.SpringExtension;
 
-import com.iqser.red.service.ocr.v1.server.Application;
-import com.iqser.red.service.ocr.v1.server.OcrServiceIntegrationTest;
+import com.iqser.red.service.ocr.v1.server.AbstractTest;
 import com.pdftron.common.PDFNetException;
-import com.pdftron.pdf.ColorPt;
-import com.pdftron.pdf.ColorSpace;
-import com.pdftron.pdf.Element;
-import com.pdftron.pdf.ElementBuilder;
 import com.pdftron.pdf.ElementWriter;
 import com.pdftron.pdf.PDFDoc;
-import com.pdftron.pdf.Page;
-import com.pdftron.pdf.Rect;
 import com.pdftron.pdf.RectCollection;
 import com.pdftron.sdf.SDFDoc;
 
 import lombok.SneakyThrows;
 
-@ExtendWith(SpringExtension.class)
-@SpringBootTest(classes = Application.class, webEnvironment = SpringBootTest.WebEnvironment.RANDOM_PORT)
-@Import(OcrServiceIntegrationTest.TestConfiguration.class)
-class ImagePositionRetrievalServiceTest {
+
+class ImagePositionRetrievalServiceTest extends AbstractTest {
 
     @Autowired
     private ImagePositionRetrievalService imagePositionRetrievalService;
 
-    @MockBean
-    protected RabbitTemplate rabbitTemplate;
-
-
     @Test
     @SneakyThrows
     public void testImagePositionRetrievalForRotateTestFileWithImages() {
@@ -122,40 +105,49 @@ class ImagePositionRetrievalServiceTest {
         assertThat(allRectCoords.size()).isEqualTo(48);
     }
 
+    @Test
+    @SneakyThrows
+    public void testEveryPointInDashedLineIsImage() {
+        String fileName = "everyPointInDashedLineIsImage";
+        List<int[]> allRectCoords = testImagePositionDetection(fileName);
+        assertThat(allRectCoords.size()).isEqualTo(0);
+    }
+
 
     private List<int[]> testImagePositionDetection(String fileName) throws IOException, PDFNetException {
 
-        InputStream fileStream = new FileInputStream(new ClassPathResource("files/" + fileName + ".pdf").getFile().getAbsolutePath());
-        PDFDoc pdfDoc = new PDFDoc(fileStream);
+        try (InputStream fileStream = new FileInputStream(new ClassPathResource("files/" + fileName + ".pdf").getFile().getAbsolutePath())) {
+            PDFDoc pdfDoc = new PDFDoc(fileStream);
 
-        Map<Integer, RectCollection> pageIdToRectCollection = imagePositionRetrievalService.getImagePositionPerPage(pdfDoc, false);
+            Map<Integer, RectCollection> pageIdToRectCollection = imagePositionRetrievalService.getImagePositionPerPage(pdfDoc, false);
 
-        ElementWriter writer = new ElementWriter();
-        pageIdToRectCollection.forEach((pageId, rectCollection) -> {
-            try {
-                writer.begin(pdfDoc.getPage(pageId));
-                drawRectCollection(writer, rectCollection, pdfDoc.getPage(pageId));
-                drawGrid(writer, pdfDoc.getPage(pageId));
-                writer.end();
-                StringBuilder zonesString = new StringBuilder();
-                for (int j = 0; j < rectCollection.getNumRects(); ++j) {
-                    var r = rectCollection.getRectAt(j);
-                    zonesString.append(String.format("%d:[lower left (%.1f|%.1f) upper right (%.1f|%.1f)]; ", j, r.getX1(), r.getY1(), r.getX2(), r.getY2()));
+            ElementWriter writer = new ElementWriter();
+            pageIdToRectCollection.forEach((pageId, rectCollection) -> {
+                try {
+                    writer.begin(pdfDoc.getPage(pageId));
+                    drawRectCollection(writer, rectCollection);
+                    drawGrid(writer, pdfDoc.getPage(pageId));
+                    writer.end();
+                    StringBuilder zonesString = new StringBuilder();
+                    for (int j = 0; j < rectCollection.getNumRects(); ++j) {
+                        var r = rectCollection.getRectAt(j);
+                        zonesString.append(String.format("%d:[lower left (%.1f|%.1f) upper right (%.1f|%.1f)]; ", j, r.getX1(), r.getY1(), r.getX2(), r.getY2()));
+                    }
+                    System.out.printf("Page %d: rotation: %d OCR regions %s \n", pageId, pdfDoc.getPage(pageId).getRotation(), zonesString);
+                } catch (PDFNetException e) {
+                    throw new RuntimeException(e);
                 }
-                System.out.printf("Page %d: rotation: %d OCR regions %s \n", pageId, pdfDoc.getPage(pageId).getRotation(), zonesString);
-            } catch (PDFNetException e) {
-                throw new RuntimeException(e);
-            }
-        });
+            });
 
-        // Check visually for red Rectangles to match images in the saved pdf file
-        try (var out = new FileOutputStream(getTemporaryDirectory() + "/" + fileName + "_IMAGE_BBOX.pdf")) {
-            out.write(pdfDoc.save(SDFDoc.SaveMode.LINEARIZED, null));
+            // Check visually for red Rectangles to match images in the saved pdf file
+            try (var out = new FileOutputStream(getTemporaryDirectory() + "/" + fileName + "_IMAGE_BBOX.pdf")) {
+                out.write(pdfDoc.save(SDFDoc.SaveMode.LINEARIZED, null));
+            }
+            pdfDoc.close();
+            System.out.println("result file: " + getTemporaryDirectory() + "/" + fileName + "_IMAGE_BBOX.pdf");
+            // round all coords to nearest int to account for inconsistencies with the calculation of the bounding box
+            return pageIdToRectCollection.values().stream().map(this::toRoundedCoordinateArrayList).flatMap(List::stream).collect(Collectors.toList());
         }
-        System.out.println("result file: " + getTemporaryDirectory() + "/" + fileName + "_IMAGE_BBOX.pdf");
-        fileStream.close();
-        // round all coords to nearest int to account for inconsistencies with the calculation of the bounding box
-        return pageIdToRectCollection.values().stream().map(this::toRoundedCoordinateArrayList).flatMap(List::stream).collect(Collectors.toList());
     }
 
 
@@ -170,59 +162,4 @@ class ImagePositionRetrievalServiceTest {
         return coords;
     }
 
-
-    @SneakyThrows
-    private void drawGrid(ElementWriter writer, Page page) {
-
-        ElementBuilder eb = new ElementBuilder();
-        double dX = 15;
-        double dY = 15;
-        int nRows = (int) (page.getPageHeight() / dY) + 1;
-        int nCols = (int) (page.getPageWidth() / dX) + 1;
-        for (int row = 0; row < nRows; ++row) {
-            for (int col = 0; col < nCols; ++col) {
-                Element cell = eb.createRect(col * dX, row * dY, dX, dY);
-                cell.setPathStroke(true);
-                cell.getGState().setLineWidth(1);
-                cell.getGState().setStrokeOpacity(0.1);
-                cell.getGState().setStrokeColorSpace(ColorSpace.createDeviceRGB());
-                if (row == 0 && col == 0) {
-                    cell.getGState().setStrokeColor(new ColorPt(0, 0, 1));
-                    cell.setPathFill(true);
-                    cell.getGState().setFillOpacity(0.8);
-                    cell.getGState().setFillColorSpace(ColorSpace.createDeviceRGB());
-                    cell.getGState().setFillColor(new ColorPt(0, 0, 1));
-                } else {
-                    cell.setPathFill(false);
-                    cell.getGState().setStrokeColor(new ColorPt(0.1, 0.1, 0.1));
-                }
-                writer.writePlacedElement(cell);
-            }
-        }
-    }
-
-
-    @SneakyThrows
-    public static void drawRectCollection(ElementWriter writer, RectCollection rectCollection, Page page) {
-
-        ColorPt colorPt = new ColorPt(1, 0, 0);
-        ElementBuilder eb = new ElementBuilder();
-        for (int i = 0; i < rectCollection.getNumRects(); ++i) {
-            Rect r = rectCollection.getRectAt(i);
-            Element rect = eb.createRect(r.getX1(), r.getY1(), r.getWidth(), r.getHeight());
-
-            rect.setPathStroke(true);
-            rect.getGState().setLineWidth(5);
-            rect.getGState().setStrokeColorSpace(ColorSpace.createDeviceRGB());
-            rect.getGState().setStrokeColor(colorPt);
-
-            rect.setPathFill(true);
-            rect.getGState().setFillColorSpace(ColorSpace.createDeviceRGB());
-            rect.getGState().setFillColor(colorPt);
-            rect.getGState().setFillOpacity(0.5);
-
-            writer.writePlacedElement(rect);
-        }
-    }
-
 }

ocr-service-v1/ocr-service-server-v1/src/test/java/com/iqser/red/service/ocr/v1/server/service/InvisibleElementRemovalServiceTest.java

@@ -1,41 +1,25 @@
 package com.iqser.red.service.ocr.v1.server.service;
 
 import static com.iqser.red.service.ocr.v1.server.utils.OsUtils.getTemporaryDirectory;
+import static com.iqser.red.service.ocr.v1.server.utils.PdfTextExtraction.extractAllTextFromDocument;
 import static org.assertj.core.api.AssertionsForClassTypes.assertThat;
 
 import java.io.FileInputStream;
 import java.io.FileOutputStream;
 
 import org.junit.jupiter.api.Test;
-import org.junit.jupiter.api.extension.ExtendWith;
-import org.springframework.amqp.rabbit.core.RabbitTemplate;
 import org.springframework.beans.factory.annotation.Autowired;
-import org.springframework.boot.test.context.SpringBootTest;
-import org.springframework.boot.test.mock.mockito.MockBean;
-import org.springframework.context.annotation.Import;
 import org.springframework.core.io.ClassPathResource;
-import org.springframework.test.context.junit.jupiter.SpringExtension;
 
-import com.iqser.red.service.ocr.v1.server.Application;
-import com.iqser.red.service.ocr.v1.server.OcrServiceIntegrationTest;
-import com.pdftron.pdf.PDFDoc;
-import com.pdftron.pdf.Page;
-import com.pdftron.pdf.PageIterator;
-import com.pdftron.pdf.TextExtractor;
+import com.iqser.red.service.ocr.v1.server.AbstractTest;
 
 import lombok.SneakyThrows;
 
-@ExtendWith(SpringExtension.class)
-@SpringBootTest(classes = Application.class, webEnvironment = SpringBootTest.WebEnvironment.RANDOM_PORT)
-@Import(OcrServiceIntegrationTest.TestConfiguration.class)
-public class InvisibleElementRemovalServiceTest {
+public class InvisibleElementRemovalServiceTest extends AbstractTest {
 
     @Autowired
     private InvisibleElementRemovalService invisibleElementRemovalService;
 
-    @MockBean
-    protected RabbitTemplate rabbitTemplate;
-
 
     @Test
     @SneakyThrows
@@ -46,27 +30,18 @@ public class InvisibleElementRemovalServiceTest {
         ClassPathResource pdfFileResource = new ClassPathResource("files/" + fileName + ".pdf");
 
         try (var initialFileStream = pdfFileResource.getInputStream(); var out = new FileOutputStream(getTemporaryDirectory() + "/" + fileName + ".pdf")) {
-            invisibleElementRemovalService.removeInvisibleElements(initialFileStream, out,false);
+            invisibleElementRemovalService.removeInvisibleElements(initialFileStream, out, false);
         }
 
         try (var initialFileStream = pdfFileResource.getInputStream(); var out = new FileOutputStream(getTemporaryDirectory() + "/" + fileName + "_delta.pdf")) {
-            invisibleElementRemovalService.removeInvisibleElements(initialFileStream, out,true);
+            invisibleElementRemovalService.removeInvisibleElements(initialFileStream, out, true);
         }
 
         System.out.println("Output File without invisible elements: files/" + fileName + ".pdf");
         System.out.println("Output Delta File without invisible elements: files/" + fileName + "_delta.pdf");
-        TextExtractor extractor = new TextExtractor();
 
-        PDFDoc pdfDoc;
-        try(var fileStream = new FileInputStream(getTemporaryDirectory() + "/" + fileName + ".pdf")) {
-            pdfDoc = new PDFDoc(fileStream);
-        }
-
-        PageIterator iterator = pdfDoc.getPageIterator();
-        while (iterator.hasNext()) {
-            Page page = iterator.next();
-            extractor.begin(page);
-            String[] text = extractor.getAsText().split("\n");
+        try (var fileStream = new FileInputStream(getTemporaryDirectory() + "/" + fileName + ".pdf")) {
+            String[] text = extractAllTextFromDocument(fileStream).split("\n");
             assertThat(text).contains("APPENDIX 16 Pathology Report", "Amendment 1", "Page 255 of 260");
         }
     }

ocr-service-v1/ocr-service-server-v1/src/test/java/com/iqser/red/service/ocr/v1/server/utils/PdfDraw.java

@@ -0,0 +1,74 @@
+package com.iqser.red.service.ocr.v1.server.utils;
+
+import com.pdftron.pdf.ColorPt;
+import com.pdftron.pdf.ColorSpace;
+import com.pdftron.pdf.Element;
+import com.pdftron.pdf.ElementBuilder;
+import com.pdftron.pdf.ElementWriter;
+import com.pdftron.pdf.Page;
+import com.pdftron.pdf.Rect;
+import com.pdftron.pdf.RectCollection;
+
+import lombok.SneakyThrows;
+
+
+public class PdfDraw {
+
+    @SneakyThrows
+    public static void drawGrid(ElementWriter writer, Page page) {
+
+        ElementBuilder eb = new ElementBuilder();
+        double dX = 15;
+        double dY = 15;
+        int nRows = (int) (page.getPageHeight() / dY) + 1;
+        int nCols = (int) (page.getPageWidth() / dX) + 1;
+        for (int row = 0; row < nRows; ++row) {
+            for (int col = 0; col < nCols; ++col) {
+                Element cell = eb.createRect(col * dX, row * dY, dX, dY);
+                cell.setPathStroke(true);
+                cell.getGState().setLineWidth(1);
+                cell.getGState().setStrokeOpacity(0.1);
+                cell.getGState().setStrokeColorSpace(ColorSpace.createDeviceRGB());
+                if (row == 0 && col == 0) {
+                    cell.getGState().setStrokeColor(new ColorPt(0, 0, 1));
+                    cell.setPathFill(true);
+                    cell.getGState().setFillOpacity(0.8);
+                    cell.getGState().setFillColorSpace(ColorSpace.createDeviceRGB());
+                    cell.getGState().setFillColor(new ColorPt(0, 0, 1));
+                } else {
+                    cell.setPathFill(false);
+                    cell.getGState().setStrokeColor(new ColorPt(0.1, 0.1, 0.1));
+                }
+                writer.writePlacedElement(cell);
+            }
+        }
+        eb.destroy();
+    }
+
+
+    @SneakyThrows
+    public static void drawRectCollection(ElementWriter writer, RectCollection rectCollection) {
+
+        ColorPt colorPt = new ColorPt(1, 0, 0);
+        ElementBuilder eb = new ElementBuilder();
+        for (int i = 0; i < rectCollection.getNumRects(); ++i) {
+            Rect r = rectCollection.getRectAt(i);
+            Element rect = eb.createRect(r.getX1(), r.getY1(), r.getWidth(), r.getHeight());
+
+            rect.setPathStroke(true);
+            rect.getGState().setLineWidth(5);
+            rect.getGState().setStrokeColorSpace(ColorSpace.createDeviceRGB());
+            rect.getGState().setStrokeColor(colorPt);
+
+            rect.setPathFill(true);
+            rect.getGState().setFillColorSpace(ColorSpace.createDeviceRGB());
+            rect.getGState().setFillColor(colorPt);
+            rect.getGState().setFillOpacity(0.5);
+
+            writer.writePlacedElement(rect);
+        }
+        colorPt.destroy();
+        eb.destroy();
+    }
+
+}

ocr-service-v1/ocr-service-server-v1/src/test/java/com/iqser/red/service/ocr/v1/server/utils/PdfTextExtraction.java

@@ -0,0 +1,35 @@
+package com.iqser.red.service.ocr.v1.server.utils;
+
+import java.io.IOException;
+import java.io.InputStream;
+import java.util.ArrayList;
+import java.util.List;
+
+import com.pdftron.common.PDFNetException;
+import com.pdftron.pdf.PDFDoc;
+import com.pdftron.pdf.Page;
+import com.pdftron.pdf.PageIterator;
+import com.pdftron.pdf.TextExtractor;
+
+
+public class PdfTextExtraction {
+
+    public static String extractAllTextFromDocument(InputStream fileStream) throws IOException, PDFNetException {
+
+        PDFDoc pdfDoc = new PDFDoc(fileStream);
+        TextExtractor extractor = new TextExtractor();
+        List<String> texts = new ArrayList<>();
+
+        PageIterator iterator = pdfDoc.getPageIterator();
+        while (iterator.hasNext()) {
+            Page page = iterator.next();
+            extractor.begin(page);
+            texts.add(extractor.getAsText());
+        }
+
+        extractor.destroy();
+        pdfDoc.close();
+        return String.join("\n", texts);
+    }
+
+}

ocr-service-v1/pom.xml

@@ -7,7 +7,7 @@
     <parent>
         <groupId>com.iqser.red</groupId>
         <artifactId>platform-dependency</artifactId>
-        <version>1.16.0</version>
+        <version>1.17.0</version>
         <relativePath/>
     </parent>