RED-3363: Fixed ignored hints in full analysis

Merge in RED/redaction-service from RED-3285 to release/2.52.x

* commit 'ca178d46d5990d1b381dca1172bf84ea5765f563':
  RED-3285: Set redacted to false if imagerecategorization type is a hint

redaction-service-image-v1/pom.xml

@@ -6,6 +6,7 @@
         <groupId>com.iqser.red</groupId>
         <artifactId>platform-docker-dependency</artifactId>
         <version>1.0.0</version>
+        <relativePath />
     </parent>
     <modelVersion>4.0.0</modelVersion>
 

redaction-service-v1/pom.xml

@@ -5,7 +5,8 @@
     <parent>
         <artifactId>platform-dependency</artifactId>
         <groupId>com.iqser.red</groupId>
-        <version>1.1.3</version>
+        <version>1.1.3.3</version>
+        <relativePath />
     </parent>
     <modelVersion>4.0.0</modelVersion>
 

redaction-service-v1/redaction-service-api-v1/src/main/java/com/iqser/red/service/redaction/v1/model/RedactionLogEntry.java

@@ -31,6 +31,11 @@ public class RedactionLogEntry {
     private String section;
     private float[] color;
 
+    private boolean hasBeenRecategorized;
+    private boolean hasLegalBasisChanged;
+    private boolean hasBeenForced;
+    private boolean hasBeenRemovedByManualOverride;
+
     @Builder.Default
     private List<Rectangle> positions = new ArrayList<>();
     private int sectionNumber;

redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/redaction/model/Entity.java

@@ -39,6 +39,8 @@ public class Entity implements ReasonHolder {
 
     private boolean isDossierDictionaryEntry;
 
+    private boolean ignored;
+
 
     public Entity(String word, String type, boolean redaction, String redactionReason, List<EntityPositionSequence> positionSequences, String headline, int matchedRule, int sectionNumber, String legalBasis, boolean isDictionaryEntry, String textBefore, String textAfter, Integer start, Integer end, boolean isDossierDictionaryEntry) {
 

redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/redaction/model/Image.java

@@ -20,6 +20,7 @@ public class Image implements ReasonHolder {
     private int sectionNumber;
     private String section;
     private int page;
+    private boolean ignored;
     private boolean hasTransparency;
 
 }

redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/redaction/model/Section.java

@@ -1,13 +1,6 @@
 package com.iqser.red.service.redaction.v1.server.redaction.model;
 
-import com.iqser.red.service.redaction.v1.model.FileAttribute;
-import com.iqser.red.service.redaction.v1.server.classification.model.TextBlock;
-import com.iqser.red.service.redaction.v1.server.redaction.utils.EntitySearchUtils;
-import com.iqser.red.service.redaction.v1.server.redaction.utils.Patterns;
-import lombok.Builder;
-import lombok.Data;
-import lombok.extern.slf4j.Slf4j;
-import org.apache.commons.lang3.StringUtils;
+import static com.iqser.red.service.redaction.v1.server.redaction.model.Dictionary.RECOMMENDATION_PREFIX;
 
 import java.util.ArrayList;
 import java.util.Collection;
@@ -20,7 +13,16 @@ import java.util.regex.Matcher;
 import java.util.regex.Pattern;
 import java.util.stream.Collectors;
 
-import static com.iqser.red.service.redaction.v1.server.redaction.model.Dictionary.RECOMMENDATION_PREFIX;
+import org.apache.commons.lang3.StringUtils;
+
+import com.iqser.red.service.redaction.v1.model.FileAttribute;
+import com.iqser.red.service.redaction.v1.server.classification.model.TextBlock;
+import com.iqser.red.service.redaction.v1.server.redaction.utils.EntitySearchUtils;
+import com.iqser.red.service.redaction.v1.server.redaction.utils.Patterns;
+
+import lombok.Builder;
+import lombok.Data;
+import lombok.extern.slf4j.Slf4j;
 
 @Data
 @Slf4j
@@ -59,29 +61,57 @@ public class Section {
     private List<FileAttribute> fileAttributes = new ArrayList<>();
 
 
-    public boolean fileAttributeByIdEquals(String id, String value){
-        return fileAttributes != null && fileAttributes.stream().filter(attribute -> id.equals(attribute.getId()) && value.equals(attribute.getValue())).findFirst().isPresent();
-    }
+    public boolean fileAttributeByIdEquals(String id, String value) {
 
-    public boolean fileAttributeByPlaceholderEquals(String placeholder, String value){
-        return fileAttributes != null && fileAttributes.stream().filter(attribute -> placeholder.equals(attribute.getPlaceholder()) && value.equals(attribute.getValue())).findFirst().isPresent();
-    }
-
-    public boolean fileAttributeByLabelEquals(String label, String value){
-        return fileAttributes != null && fileAttributes.stream().filter(attribute -> label.equals(attribute.getLabel()) && value.equals(attribute.getValue())).findFirst().isPresent();
+        return fileAttributes != null && fileAttributes.stream()
+                .filter(attribute -> id.equals(attribute.getId()) && value.equals(attribute.getValue()))
+                .findFirst()
+                .isPresent();
     }
 
 
-    public boolean fileAttributeByIdEqualsIgnoreCase(String id, String value){
-        return fileAttributes != null && fileAttributes.stream().filter(attribute -> id.equals(attribute.getId()) && value.equalsIgnoreCase(attribute.getValue())).findFirst().isPresent();
+    public boolean fileAttributeByPlaceholderEquals(String placeholder, String value) {
+
+        return fileAttributes != null && fileAttributes.stream()
+                .filter(attribute -> placeholder.equals(attribute.getPlaceholder()) && value.equals(attribute.getValue()))
+                .findFirst()
+                .isPresent();
     }
 
-    public boolean fileAttributeByPlaceholderEqualsIgnoreCase(String placeholder, String value){
-        return fileAttributes != null && fileAttributes.stream().filter(attribute -> placeholder.equals(attribute.getPlaceholder()) && value.equalsIgnoreCase(attribute.getValue())).findFirst().isPresent();
+
+    public boolean fileAttributeByLabelEquals(String label, String value) {
+
+        return fileAttributes != null && fileAttributes.stream()
+                .filter(attribute -> label.equals(attribute.getLabel()) && value.equals(attribute.getValue()))
+                .findFirst()
+                .isPresent();
     }
 
-    public boolean fileAttributeByLabelEqualsIgnoreCase(String label, String value){
-        return fileAttributes != null && fileAttributes.stream().filter(attribute -> label.equals(attribute.getLabel()) && value.equalsIgnoreCase(attribute.getValue())).findFirst().isPresent();
+
+    public boolean fileAttributeByIdEqualsIgnoreCase(String id, String value) {
+
+        return fileAttributes != null && fileAttributes.stream()
+                .filter(attribute -> id.equals(attribute.getId()) && value.equalsIgnoreCase(attribute.getValue()))
+                .findFirst()
+                .isPresent();
+    }
+
+
+    public boolean fileAttributeByPlaceholderEqualsIgnoreCase(String placeholder, String value) {
+
+        return fileAttributes != null && fileAttributes.stream()
+                .filter(attribute -> placeholder.equals(attribute.getPlaceholder()) && value.equalsIgnoreCase(attribute.getValue()))
+                .findFirst()
+                .isPresent();
+    }
+
+
+    public boolean fileAttributeByLabelEqualsIgnoreCase(String label, String value) {
+
+        return fileAttributes != null && fileAttributes.stream()
+                .filter(attribute -> label.equals(attribute.getLabel()) && value.equalsIgnoreCase(attribute.getValue()))
+                .findFirst()
+                .isPresent();
     }
 
 
@@ -104,13 +134,13 @@ public class Section {
 
     public boolean matchesType(String type) {
 
-        return entities.stream().anyMatch(entity -> entity.getType().equals(type));
+        return entities.stream().anyMatch(entity -> !entity.isIgnored() && entity.getType().equals(type));
     }
 
 
     public boolean matchesImageType(String type) {
 
-        return images.stream().anyMatch(image -> image.getType().equals(type));
+        return images.stream().anyMatch(image -> !image.isIgnored() &&  image.getType().equals(type));
     }
 
 
@@ -122,6 +152,18 @@ public class Section {
 
     public void expandByRegEx(String type, String pattern, boolean patternCaseInsensitive, int group) {
 
+        expandByRegEx(type, pattern, patternCaseInsensitive, group, null);
+    }
+
+
+    public void expandByRegEx(String type, String pattern, boolean patternCaseInsensitive, int group,
+                              String withoutPattern) {
+
+        Pattern compiledWithoutPattern = null;
+        if (withoutPattern != null) {
+            compiledWithoutPattern = Patterns.getCompiledPattern(withoutPattern, patternCaseInsensitive);
+        }
+
         Pattern compiledPattern = Patterns.getCompiledPattern(pattern, patternCaseInsensitive);
 
         Set<Entity> expanded = new HashSet<>();
@@ -131,14 +173,21 @@ public class Section {
                 continue;
             }
 
+            if (withoutPattern != null) {
+                Matcher matcherWithout = compiledWithoutPattern.matcher(entity.getWord());
+                if (matcherWithout.find()) {
+                    continue;
+                }
+            }
+
             Matcher matcher = compiledPattern.matcher(entity.getTextAfter());
 
             while (matcher.find()) {
                 String match = matcher.group(group);
-                if (StringUtils.isNotBlank(match)) {
-                    expanded.addAll(findEntities(entity.getWord() + match, type, false, entity.isRedaction(), entity.getMatchedRule(), entity
-                            .getRedactionReason(), entity.getLegalBasis()));
 
+                if (StringUtils.isNotBlank(match)) {
+                    Set<Entity> expandedEntities = findEntities(entity.getWord() + match, type, false, entity.isRedaction(), entity.getMatchedRule(), entity.getRedactionReason(), entity.getLegalBasis());
+                    expanded.addAll(EntitySearchUtils.findNonOverlappingMatchEntities(entities, expandedEntities));
                 }
             }
         }
@@ -204,6 +253,12 @@ public class Section {
     }
 
 
+    public void ignore(String type) {
+
+        entities.removeIf(entity -> entity.getType().equals(type));
+    }
+
+
     public void expandToHintAnnotationByRegEx(String type, String pattern, boolean patternCaseInsensitive, int group,
                                               String asType) {
 

redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/redaction/service/EntityRedactionService.java

@@ -105,9 +105,9 @@ public class EntityRedactionService {
             List<Table> tables = paragraph.getTables();
             for (Table table : tables) {
                 if (table.getColCount() == 2) {
-                    sectionSearchableTextPairs.addAll(processTableAsOneText(classifiedDoc, table, sectionNumber, dictionary, local, hintsPerSectionNumber, fileAttributes));
+                    sectionSearchableTextPairs.addAll(processTableAsOneText(classifiedDoc, table, sectionNumber, dictionary, local, hintsPerSectionNumber, fileAttributes, manualRedactions));
                 } else {
-                    sectionSearchableTextPairs.addAll(processTablePerRow(classifiedDoc, table, sectionNumber, dictionary, local, hintsPerSectionNumber, fileAttributes));
+                    sectionSearchableTextPairs.addAll(processTablePerRow(classifiedDoc, table, sectionNumber, dictionary, local, hintsPerSectionNumber, fileAttributes, manualRedactions));
                 }
                 sectionNumber.incrementAndGet();
             }
@@ -178,7 +178,7 @@ public class EntityRedactionService {
                                                                AtomicInteger sectionNumber, Dictionary dictionary,
                                                                boolean local,
                                                                Map<Integer, Set<Entity>> hintsPerSectionNumber,
-                                                               List<FileAttribute> fileAttributes) {
+                                                               List<FileAttribute> fileAttributes, ManualRedactions manualRedactions) {
 
         List<SectionSearchableTextPair> sectionSearchableTextPairs = new ArrayList<>();
 
@@ -229,6 +229,31 @@ public class EntityRedactionService {
             Set<Entity> rowEntities = findEntities(searchableRow, table.getHeadline(), sectionNumber.intValue(), dictionary, local);
             surroundingWordsService.addSurroundingText(rowEntities, searchableRow, dictionary, cellStarts);
 
+            if (!local && manualRedactions != null) {
+
+
+                var approvedForceRedactions = manualRedactions.getForceRedacts().stream()
+                        .filter(fr -> fr.getStatus() == Status.APPROVED)
+                        .filter(fr -> fr.getRequestDate() != null)
+                        .collect(Collectors.toList());
+                // only approved id removals, that haven't been forced back afterwards
+                var idsToRemove = manualRedactions.getIdsToRemove().stream()
+                        .filter(idr -> idr.getStatus() == Status.APPROVED)
+                        .filter(idr -> idr.getRequestDate() != null)
+                        .filter(idr -> approvedForceRedactions.stream().noneMatch(forceRedact -> forceRedact.getRequestDate().isAfter(idr.getRequestDate())))
+                        .map(IdRemoval::getId).collect(Collectors.toSet());
+
+                log.info("Removed Ids: {}", idsToRemove);
+
+                rowEntities.forEach(entity ->
+                        entity.getPositionSequences().forEach(ps -> {
+                            if (idsToRemove.contains(ps.getId())) {
+                                entity.setIgnored(true);
+                            }
+                        }));
+
+            }
+
             sectionSearchableTextPairs.add(new SectionSearchableTextPair(Section.builder()
                     .isLocal(local)
                     .dictionaryTypes(dictionary.getTypes())
@@ -266,7 +291,7 @@ public class EntityRedactionService {
                                                                   AtomicInteger sectionNumber, Dictionary dictionary,
                                                                   boolean local,
                                                                   Map<Integer, Set<Entity>> hintsPerSectionNumber,
-                                                                  List<FileAttribute> fileAttributes) {
+                                                                  List<FileAttribute> fileAttributes, ManualRedactions manualRedactions) {
 
         List<SectionSearchableTextPair> sectionSearchableTextPairs = new ArrayList<>();
         SearchableText entireTableText = new SearchableText();
@@ -297,6 +322,31 @@ public class EntityRedactionService {
         Set<Entity> rowEntities = findEntities(entireTableText, table.getHeadline(), sectionNumber.intValue(), dictionary, local);
         surroundingWordsService.addSurroundingText(rowEntities, entireTableText, dictionary);
 
+        if (!local && manualRedactions != null) {
+
+
+            var approvedForceRedactions = manualRedactions.getForceRedacts().stream()
+                    .filter(fr -> fr.getStatus() == Status.APPROVED)
+                    .filter(fr -> fr.getRequestDate() != null)
+                    .collect(Collectors.toList());
+            // only approved id removals, that haven't been forced back afterwards
+            var idsToRemove = manualRedactions.getIdsToRemove().stream()
+                    .filter(idr -> idr.getStatus() == Status.APPROVED)
+                    .filter(idr -> idr.getRequestDate() != null)
+                    .filter(idr -> approvedForceRedactions.stream().noneMatch(forceRedact -> forceRedact.getRequestDate().isAfter(idr.getRequestDate())))
+                    .map(IdRemoval::getId).collect(Collectors.toSet());
+
+            log.info("Removed Ids: {}", idsToRemove);
+
+            rowEntities.forEach(entity ->
+                    entity.getPositionSequences().forEach(ps -> {
+                        if (idsToRemove.contains(ps.getId())) {
+                            entity.setIgnored(true);
+                        }
+                    }));
+
+        }
+
         sectionSearchableTextPairs.add(new SectionSearchableTextPair(Section.builder()
                 .isLocal(local)
                 .dictionaryTypes(dictionary.getTypes())
@@ -353,6 +403,31 @@ public class EntityRedactionService {
         Set<Entity> entities = findEntities(searchableText, headline, sectionNumber.intValue(), dictionary, local);
         surroundingWordsService.addSurroundingText(entities, searchableText, dictionary);
 
+        if (!local && manualRedactions != null) {
+
+
+            var approvedForceRedactions = manualRedactions.getForceRedacts().stream()
+                    .filter(fr -> fr.getStatus() == Status.APPROVED)
+                    .filter(fr -> fr.getRequestDate() != null)
+                    .collect(Collectors.toList());
+            // only approved id removals, that haven't been forced back afterwards
+            var idsToRemove = manualRedactions.getIdsToRemove().stream()
+                    .filter(idr -> idr.getStatus() == Status.APPROVED)
+                    .filter(idr -> idr.getRequestDate() != null)
+                    .filter(idr -> approvedForceRedactions.stream().noneMatch(forceRedact -> forceRedact.getRequestDate().isAfter(idr.getRequestDate())))
+                    .map(IdRemoval::getId).collect(Collectors.toSet());
+
+            log.info("Removed Ids: {}", idsToRemove);
+
+            entities.forEach(entity ->
+                    entity.getPositionSequences().forEach(ps -> {
+                        if (idsToRemove.contains(ps.getId())) {
+                            entity.setIgnored(true);
+                        }
+                    }));
+
+        }
+
         return new SectionSearchableTextPair(Section.builder()
                 .isLocal(local)
                 .dictionaryTypes(dictionary.getTypes())

redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/redaction/service/ReanalyzeService.java

@@ -213,19 +213,45 @@ public class ReanalyzeService {
                 surroundingWordsService.addSurroundingText(entities, reanalysisSection.getSearchableText(), dictionary);
             }
 
-            if (!local && reanalysisSection.getImages() != null && !reanalysisSection.getImages()
-                    .isEmpty() && analyzeRequest.getManualRedactions() != null && analyzeRequest.getManualRedactions()
-                    .getImageRecategorizations() != null) {
-                for (Image image : reanalysisSection.getImages()) {
-                    String imageId = IdBuilder.buildId(image.getPosition(), image.getPage());
-                    for (ManualImageRecategorization imageRecategorization : analyzeRequest.getManualRedactions()
-                            .getImageRecategorizations()) {
-                        if (imageRecategorization.getStatus().equals(Status.APPROVED) && imageRecategorization.getId()
-                                .equals(imageId)) {
-                            image.setType(imageRecategorization.getType());
+            if (!local && analyzeRequest.getManualRedactions() != null) {
+
+
+                var approvedForceRedactions = analyzeRequest.getManualRedactions().getForceRedacts().stream()
+                        .filter(fr -> fr.getStatus() == Status.APPROVED)
+                        .filter(fr -> fr.getRequestDate() != null)
+                        .collect(Collectors.toList());
+                // only approved id removals, that haven't been forced back afterwards
+                var idsToRemove = analyzeRequest.getManualRedactions().getIdsToRemove().stream()
+                        .filter(idr -> idr.getStatus() == Status.APPROVED)
+                        .filter(idr -> idr.getRequestDate() != null)
+                        .filter(idr -> approvedForceRedactions.stream().noneMatch(forceRedact -> forceRedact.getRequestDate().isAfter(idr.getRequestDate())))
+                        .map(IdRemoval::getId).collect(Collectors.toSet());
+
+                log.info("Removed Ids: {}", idsToRemove);
+
+                if (reanalysisSection.getImages() != null && !reanalysisSection.getImages().isEmpty() && analyzeRequest.getManualRedactions().getImageRecategorizations() != null) {
+                    for (Image image : reanalysisSection.getImages()) {
+                        String imageId = IdBuilder.buildId(image.getPosition(), image.getPage());
+                        for (ManualImageRecategorization imageRecategorization : analyzeRequest.getManualRedactions()
+                                .getImageRecategorizations()) {
+                            if (imageRecategorization.getStatus().equals(Status.APPROVED) && imageRecategorization.getId()
+                                    .equals(imageId)) {
+                                image.setType(imageRecategorization.getType());
+                            }
+                        }
+                        if (idsToRemove.contains(imageId)) {
+                            image.setIgnored(true);
                         }
                     }
                 }
+
+                entities.forEach(entity ->
+                        entity.getPositionSequences().forEach(ps -> {
+                            if (idsToRemove.contains(ps.getId())) {
+                                entity.setIgnored(true);
+                            }
+                        }));
+
             }
 
             sectionSearchableTextPairs.add(new SectionSearchableTextPair(Section.builder()

redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/redaction/service/RedactionLogCreatorService.java

@@ -1,5 +1,15 @@
 package com.iqser.red.service.redaction.v1.server.redaction.service;
 
+import java.util.ArrayList;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Map;
+import java.util.Set;
+import java.util.stream.Collectors;
+
+import org.apache.commons.collections4.CollectionUtils;
+import org.springframework.stereotype.Service;
+
 import com.iqser.red.service.redaction.v1.model.CellRectangle;
 import com.iqser.red.service.redaction.v1.model.Point;
 import com.iqser.red.service.redaction.v1.model.Rectangle;
@@ -17,16 +27,8 @@ import com.iqser.red.service.redaction.v1.server.redaction.utils.IdBuilder;
 import com.iqser.red.service.redaction.v1.server.tableextraction.model.AbstractTextContainer;
 import com.iqser.red.service.redaction.v1.server.tableextraction.model.Cell;
 import com.iqser.red.service.redaction.v1.server.tableextraction.model.Table;
-import lombok.RequiredArgsConstructor;
-import org.apache.commons.collections4.CollectionUtils;
-import org.springframework.stereotype.Service;
 
-import java.util.ArrayList;
-import java.util.HashSet;
-import java.util.List;
-import java.util.Map;
-import java.util.Set;
-import java.util.stream.Collectors;
+import lombok.RequiredArgsConstructor;
 
 @Service
 @RequiredArgsConstructor
@@ -54,7 +56,8 @@ public class RedactionLogCreatorService {
     }
 
 
-    public List<RedactionLogEntry> addImageEntries(Map<Integer, Set<Image>> images, int pageNumber, String dossierTemplateId) {
+    public List<RedactionLogEntry> addImageEntries(Map<Integer, Set<Image>> images, int pageNumber,
+                                                   String dossierTemplateId) {
 
         List<RedactionLogEntry> redactionLogEntities = new ArrayList<>();
 
@@ -81,11 +84,10 @@ public class RedactionLogCreatorService {
                     .sectionNumber(image.getSectionNumber())
                     //.section(image.getSection())
                     // RED-2622
-                    .section("Image:"+image.getType())
+                    .section("Image:" + image.getType())
                     .imageHasTransparency(image.isHasTransparency())
                     .build();
 
-
             redactionLogEntities.add(redactionLogEntry);
         }
 
@@ -103,7 +105,6 @@ public class RedactionLogCreatorService {
         entityLoop:
         for (Entity entity : entities.get(page)) {
 
-
             for (EntityPositionSequence entityPositionSequence : entity.getPositionSequences()) {
 
                 RedactionLogEntry redactionLogEntry = createRedactionLogEntry(entity, dossierTemplateId);
@@ -123,12 +124,10 @@ public class RedactionLogCreatorService {
                             .flatMap(seq -> seq.getTextPositions().stream())
                             .collect(Collectors.toList()), page);
 
-
                     redactionLogEntry.getPositions().addAll(rectanglesPerLine);
 
                 }
 
-
                 // FIXME ids should never be null. Figure out why this happens.
                 if (redactionLogEntry.getId() != null) {
                     redactionLogEntities.add(redactionLogEntry);
@@ -146,16 +145,27 @@ public class RedactionLogCreatorService {
         if (textPositions.size() == 1) {
             rectangles.add(TextPositionSequence.fromData(textPositions, page).getRectangle());
         } else {
+            float x = textPositions.get(0).getXDirAdj();
             float y = textPositions.get(0).getYDirAdj();
+            float width = textPositions.get(0).getWidth();
+            float height = textPositions.get(0).getHeightDir();
             int startIndex = 0;
+
             for (int i = 1; i < textPositions.size(); i++) {
+                float xDirAdj = textPositions.get(i).getXDirAdj();
                 float yDirAdj = textPositions.get(i).getYDirAdj();
-                if (round(yDirAdj,3) != round(y, 3)) {
+                float widthDir = textPositions.get(i).getWidth();
+                float heightDir = textPositions.get(i).getHeightDir();
+
+                if (!(isCharInSameLine(y, yDirAdj, height, heightDir) && isCharClose(x, xDirAdj, width))) {
                     rectangles.add(TextPositionSequence.fromData(textPositions.subList(startIndex, i), page)
                             .getRectangle());
                     y = yDirAdj;
+                    width = widthDir;
+                    height = heightDir;
                     startIndex = i;
                 }
+                x = xDirAdj;
             }
             if (startIndex != textPositions.size()) {
                 rectangles.add(TextPositionSequence.fromData(textPositions.subList(startIndex, textPositions.size()), page)
@@ -166,9 +176,32 @@ public class RedactionLogCreatorService {
         return rectangles;
     }
 
-    private double round(float value, int decimalPoints) {
-        var d = Math.pow(10, decimalPoints);
-        return Math.round(value * d) / d;
+
+    private boolean isCharClose(float x, float xDirAdj, float width) {
+
+        float max = x + (5 * width);
+        if (xDirAdj < max) {
+            return true;
+        }
+        return false;
+    }
+
+
+    private boolean isCharInSameLine(float y, float yCompare, float height, float heightCompare) {
+
+        float offsetHeight = height / 2;
+        float minHeight = height - offsetHeight;
+        float maxHeight = height + offsetHeight;
+
+        float offsetY = height / 10;
+        float minY = y - offsetY;
+        float maxY = y + offsetY;
+
+        if (yCompare > minY && yCompare < maxY && heightCompare > minHeight && heightCompare < maxHeight) {
+            return true;
+        }
+
+        return false;
     }
 
 
@@ -213,8 +246,8 @@ public class RedactionLogCreatorService {
                     classifiedDoc.getSectionGrid()
                             .getRectanglesPerPage()
                             .computeIfAbsent(page, (x) -> new ArrayList<>())
-                            .add(new SectionRectangle(new Point(textBlock.getMinX(), textBlock.getMinY()), textBlock.getWidth(), textBlock
-                                    .getHeight(), i + 1, paragraph.getPageBlocks().size()));
+                            .add(new SectionRectangle(new Point(textBlock.getMinX(), textBlock.getMinY()), textBlock.getWidth(), textBlock.getHeight(), i + 1, paragraph.getPageBlocks()
+                                    .size()));
 
                 } else if (textBlock instanceof Table) {
 
@@ -222,8 +255,7 @@ public class RedactionLogCreatorService {
                     for (List<Cell> row : ((Table) textBlock).getRows()) {
                         for (Cell cell : row) {
                             if (cell != null) {
-                                cellRectangles.add(new CellRectangle(new Point((float) cell.getX(), (float) cell.getY()), (float) cell
-                                        .getWidth(), (float) cell.getHeight()));
+                                cellRectangles.add(new CellRectangle(new Point((float) cell.getX(), (float) cell.getY()), (float) cell.getWidth(), (float) cell.getHeight()));
                             }
                         }
                     }
@@ -231,8 +263,8 @@ public class RedactionLogCreatorService {
                     classifiedDoc.getSectionGrid()
                             .getRectanglesPerPage()
                             .computeIfAbsent(page, (x) -> new ArrayList<>())
-                            .add(new SectionRectangle(new Point(textBlock.getMinX(), textBlock.getMinY()), textBlock.getWidth(), textBlock
-                                    .getHeight(), i + 1, paragraph.getPageBlocks().size(), cellRectangles));
+                            .add(new SectionRectangle(new Point(textBlock.getMinX(), textBlock.getMinY()), textBlock.getWidth(), textBlock.getHeight(), i + 1, paragraph.getPageBlocks()
+                                    .size(), cellRectangles));
 
                 }
             }
@@ -260,5 +292,4 @@ public class RedactionLogCreatorService {
         return dictionaryService.isRecommendation(type, dossierTemplateId);
     }
 
-
 }

redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/redaction/service/RedactionLogMergeService.java

@@ -50,6 +50,14 @@ public class RedactionLogMergeService {
 
         }
 
+        Set<String> processedIds = new HashSet<>();
+        redactionLog.getRedactionLogEntry().removeIf(entry -> {
+            if(processedIds.contains(entry.getId())){
+                return true;
+            }
+            processedIds.add(entry.getId());
+            return false;
+        });
         return redactionLog;
     }
 
@@ -99,7 +107,15 @@ public class RedactionLogMergeService {
                 if (imageRecategorization.getStatus().equals(Status.APPROVED)) {
                     redactionLogEntry.setStatus(Status.APPROVED);
                     redactionLogEntry.setType(imageRecategorization.getType());
-                    // RED-2622
+                    redactionLogEntry.setHasBeenRecategorized(true);
+
+                    if (dictionaryService.isHint(imageRecategorization.getType(), dossierTemplateId)) {
+                        redactionLogEntry.setRedacted(false);
+                        redactionLogEntry.setHint(true);
+                    } else {
+                        redactionLogEntry.setHint(false);
+                    }
+
                     redactionLogEntry.setSection("Image:" + redactionLogEntry.getType());
                     manualOverrideReason = mergeReasonIfNecessary(redactionLogEntry.getReason(), ", recategorized by manual override");
                 } else if (imageRecategorization.getStatus().equals(Status.REQUESTED)) {
@@ -127,6 +143,8 @@ public class RedactionLogMergeService {
                     manualOverrideReason = mergeReasonIfNecessary(redactionLogEntry.getReason(), ", removed by manual override");
                     redactionLogEntry.setColor(getColor(redactionLogEntry.getType(), dossierTemplateId, false, redactionLogEntry
                             .isRedacted(), true));
+                    redactionLogEntry.setHint(false);
+                    redactionLogEntry.setHasBeenRemovedByManualOverride(true);
                 } else if (manualRemoval.getStatus().equals(Status.REQUESTED)) {
                     manualOverrideReason = mergeReasonIfNecessary(redactionLogEntry.getReason(), ", requested to remove");
                     redactionLogEntry.setStatus(Status.REQUESTED);
@@ -148,12 +166,20 @@ public class RedactionLogMergeService {
                 var manualForceRedact = (ManualForceRedact) mrw.getItem();
                 String manualOverrideReason = null;
                 if (manualForceRedact.getStatus().equals(Status.APPROVED)) {
-                    redactionLogEntry.setRedacted(true);
+
+                    // Forcing a skipped hint should result in a hint
+                    if (dictionaryService.isHint(redactionLogEntry.getType(), dossierTemplateId)) {
+                        redactionLogEntry.setHint(true);
+                    } else {
+                        redactionLogEntry.setRedacted(true);
+                    }
+
                     redactionLogEntry.setStatus(Status.APPROVED);
                     redactionLogEntry.setColor(getColor(redactionLogEntry.getType(), dossierTemplateId, false, redactionLogEntry
                             .isRedacted(), false));
                     manualOverrideReason = mergeReasonIfNecessary(redactionLogEntry.getReason(), ", forced by manual override");
                     redactionLogEntry.setLegalBasis(manualForceRedact.getLegalBasis());
+                    redactionLogEntry.setHasBeenForced(true);
                 } else if (manualForceRedact.getStatus().equals(Status.REQUESTED)) {
                     manualOverrideReason = mergeReasonIfNecessary(redactionLogEntry.getReason(), ", requested to force redact");
                     redactionLogEntry.setStatus(Status.REQUESTED);
@@ -185,6 +211,7 @@ public class RedactionLogMergeService {
                     if (redactionLogEntry.isRectangle() && manualLegalBasisChange.getValue() != null) {
                         redactionLogEntry.setValue(manualLegalBasisChange.getValue());
                     }
+                    redactionLogEntry.setHasLegalBasisChanged(true);
                 } else if (manualLegalBasisChange.getStatus().equals(Status.REQUESTED)) {
                     manualOverrideReason = mergeReasonIfNecessary(redactionLogEntry.getReason(), ", legal basis change requested");
                     redactionLogEntry.setStatus(Status.REQUESTED);

redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/redaction/utils/EntitySearchUtils.java

@@ -1,5 +1,16 @@
 package com.iqser.red.service.redaction.v1.server.redaction.utils;
 
+import java.util.ArrayList;
+import java.util.Comparator;
+import java.util.HashMap;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Locale;
+import java.util.Map;
+import java.util.Set;
+import java.util.regex.Pattern;
+import java.util.stream.Collectors;
+
 import com.iqser.red.service.redaction.v1.server.redaction.model.Dictionary;
 import com.iqser.red.service.redaction.v1.server.redaction.model.DictionaryIncrementValue;
 import com.iqser.red.service.redaction.v1.server.redaction.model.Entity;
@@ -9,10 +20,6 @@ import com.iqser.red.service.redaction.v1.server.redaction.model.SearchableText;
 import lombok.experimental.UtilityClass;
 import lombok.extern.slf4j.Slf4j;
 
-import java.util.*;
-import java.util.regex.Pattern;
-import java.util.stream.Collectors;
-
 @Slf4j
 @UtilityClass
 @SuppressWarnings("PMD")
@@ -152,6 +159,44 @@ public class EntitySearchUtils {
         // HashSet keeps old value but we want the new.
         entities.removeAll(found);
         entities.addAll(found);
+
+        removeEntitiesContainedInLarger(entities);
+    }
+
+
+    public Set<Entity> findNonOverlappingMatchEntities(Set<Entity> existingEntities, Set<Entity> foundEntities) {
+
+        Set<Entity> result = new HashSet<>();
+        if (existingEntities != null && foundEntities != null) {
+            for (Entity foundEntity : foundEntities) {
+
+                if (!overlaps(existingEntities, foundEntity)) {
+                    result.add(foundEntity);
+                }
+
+            }
+        }
+        return result;
+    }
+
+
+    private boolean overlaps(Set<Entity> existingEntities, Entity found) {
+
+        for (Entity existing : existingEntities) {
+
+            if(existing.getStart().equals(found.getStart())){
+                continue;
+            }
+
+            for (int i = existing.getStart(); i <= existing.getEnd(); i++) {
+                for (int j = found.getStart(); j <= found.getEnd(); j++) {
+                    if (i == j) {
+                        return true;
+                    }
+                }
+            }
+        }
+        return false;
     }
 
 }

redaction-service-v1/redaction-service-server-v1/src/test/java/com/iqser/red/service/redaction/v1/server/RedactionIntegrationTest.java

@@ -18,10 +18,10 @@ import com.iqser.red.service.redaction.v1.server.redaction.utils.ResourceLoader;
 import com.iqser.red.service.redaction.v1.server.redaction.utils.TextNormalizationUtilities;
 import com.iqser.red.service.redaction.v1.server.storage.RedactionStorageService;
 import com.iqser.red.storage.commons.service.StorageService;
-
 import lombok.SneakyThrows;
-
 import org.apache.commons.io.IOUtils;
+import org.apache.commons.lang3.StringUtils;
+import org.assertj.core.util.Sets;
 import org.junit.After;
 import org.junit.Before;
 import org.junit.Ignore;
@@ -569,7 +569,7 @@ public class RedactionIntegrationTest {
                 .fileId(TEST_FILE_ID)
                 .build());
 
-        try (FileOutputStream fileOutputStream = new FileOutputStream("/tmp/Annotated3.pdf")) {
+        try (FileOutputStream fileOutputStream = new FileOutputStream(getTemporaryDirectory() + "/Annotated3.pdf")) {
             fileOutputStream.write(annotateResponse.getDocument());
         }
         long rstart = System.currentTimeMillis();
@@ -652,11 +652,28 @@ public class RedactionIntegrationTest {
     }
 
 
+    @Test
+    public void redactionExpansionOverlap() throws IOException {
+
+        ClassPathResource pdfFileResource = new ClassPathResource("files/Minimal Examples/ExpansionTest.pdf");
+        AnalyzeRequest request = prepareStorage(pdfFileResource.getInputStream());
+
+
+        AnalyzeResult result = reanalyzeService.analyze(request);
+
+        var redactionLog = redactionStorageService.getRedactionLog(TEST_DOSSIER_ID, TEST_FILE_ID);
+
+        var values = redactionLog.getRedactionLogEntry().stream().map(RedactionLogEntry::getValue).collect(Collectors.toList());
+
+        assertThat(values).containsExactlyInAnyOrder("Lastname M.", "Doe", "Doe J.", "M. Mustermann", "Mustermann M.", "F. Lastname");
+    }
+
+
     @Test
     public void redactionTest() throws IOException {
 
         long start = System.currentTimeMillis();
-        ClassPathResource pdfFileResource = new ClassPathResource("files/new/VV-919901.pdf");
+        ClassPathResource pdfFileResource = new ClassPathResource("files/new/just-a-document-20211215.pdf");
         AnalyzeRequest request = prepareStorage(pdfFileResource.getInputStream());
         request.setExcludedPages(Set.of(1));
 
@@ -682,7 +699,7 @@ public class RedactionIntegrationTest {
 
         System.out.println("first analysis duration: " + (end - start));
 
-        try (FileOutputStream fileOutputStream = new FileOutputStream("/tmp/Test.json")) {
+        try (FileOutputStream fileOutputStream = new FileOutputStream(getTemporaryDirectory() + "/Test.json")) {
             fileOutputStream.write(objectMapper.writeValueAsBytes(redactionStorageService.getText(TEST_DOSSIER_ID, TEST_FILE_ID)));
         }
 
@@ -750,13 +767,85 @@ public class RedactionIntegrationTest {
                 .fileId(TEST_FILE_ID)
                 .build());
 
-        try (FileOutputStream fileOutputStream = new FileOutputStream("/tmp/Annotated.pdf")) {
+        try (FileOutputStream fileOutputStream = new FileOutputStream(getTemporaryDirectory() + "/Annotated.pdf")) {
             fileOutputStream.write(annotateResponse.getDocument());
         }
 
     }
 
 
+    @Test
+    public void testIgnoreHint() {
+
+        System.out.println("testIgnoreHint");
+
+        AnalyzeRequest request = prepareStorage("files/new/test-ignore-hint.pdf");
+        reanalyzeService.analyze(request);
+        var redactionLog = redactionStorageService.getRedactionLog(TEST_DOSSIER_ID, TEST_FILE_ID);
+
+        var manualRedactions = ManualRedactions.builder().idsToRemove(Sets.newLinkedHashSet(
+                IdRemoval.builder()
+                        .id("c630599611e6e3db314518374bcf70f7")
+                        .status(Status.APPROVED)
+                        .user("test")
+                        .removeFromDictionary(false)
+                        .processedDate(OffsetDateTime.now())
+                        .requestDate(OffsetDateTime.now())
+                        .build())).build();
+
+        request.setManualRedactions(manualRedactions);
+        reanalyzeService.reanalyze(request);
+
+
+        var mergedRedactionLog = redactionController.getRedactionLog(RedactionRequest.builder().withSectionDataForManualRedactions(true)
+                .manualRedactions(manualRedactions)
+                .dossierTemplateId(TEST_DOSSIER_TEMPLATE_ID)
+                .dossierId(TEST_DOSSIER_ID)
+                .fileId(TEST_FILE_ID)
+                .build());
+
+        var cbiAddressBeforeHintRemoval = redactionLog.getRedactionLogEntry().stream().filter(re -> re.getType().equalsIgnoreCase("CBI_Address")).findAny().get();
+        assertThat(cbiAddressBeforeHintRemoval.isRedacted()).isFalse();
+
+        var cbiAddressAfterHintRemoval = mergedRedactionLog.getRedactionLogEntry().stream().filter(re -> re.getType().equalsIgnoreCase("CBI_Address")).findAny().get();
+        assertThat(cbiAddressAfterHintRemoval.isRedacted()).isTrue();
+    }
+
+
+
+    @Test
+    public void testIgnoreHintFirstAnalysis() {
+
+        System.out.println("testIgnoreHintFirstAnalysis");
+
+        AnalyzeRequest request = prepareStorage("files/new/test-ignore-hint.pdf");
+
+        var manualRedactions = ManualRedactions.builder().idsToRemove(Sets.newLinkedHashSet(
+                IdRemoval.builder()
+                        .id("c630599611e6e3db314518374bcf70f7")
+                        .status(Status.APPROVED)
+                        .user("test")
+                        .removeFromDictionary(false)
+                        .processedDate(OffsetDateTime.now())
+                        .requestDate(OffsetDateTime.now())
+                        .build())).build();
+
+        request.setManualRedactions(manualRedactions);
+        reanalyzeService.analyze(request);
+
+        var mergedRedactionLog = redactionController.getRedactionLog(RedactionRequest.builder().withSectionDataForManualRedactions(true)
+                .manualRedactions(manualRedactions)
+                .dossierTemplateId(TEST_DOSSIER_TEMPLATE_ID)
+                .dossierId(TEST_DOSSIER_ID)
+                .fileId(TEST_FILE_ID)
+                .build());
+
+        var cbiAddressAfterHintRemoval = mergedRedactionLog.getRedactionLogEntry().stream().filter(re -> re.getType().equalsIgnoreCase("CBI_Address")).findAny().get();
+        assertThat(cbiAddressAfterHintRemoval.isRedacted()).isTrue();
+    }
+
+
+
     @Test
     public void testTableRedaction() throws IOException {
 
@@ -771,7 +860,30 @@ public class RedactionIntegrationTest {
                 .fileId(TEST_FILE_ID)
                 .build());
 
-        try (FileOutputStream fileOutputStream = new FileOutputStream("/tmp/Annotated.pdf")) {
+        try (FileOutputStream fileOutputStream = new FileOutputStream(getTemporaryDirectory() + "/Annotated.pdf")) {
+            fileOutputStream.write(annotateResponse.getDocument());
+        }
+        long end = System.currentTimeMillis();
+
+        System.out.println("duration: " + (end - start));
+        System.out.println("numberOfPages: " + result.getNumberOfPages());
+    }
+
+
+    @Test
+    public void testIgnoreDossierRedactionIfConfidential() throws IOException {
+
+        long start = System.currentTimeMillis();
+
+        AnalyzeRequest request = prepareStorage("files/new/VV-919901.pdf");
+        AnalyzeResult result = reanalyzeService.analyze(request);
+
+        AnnotateResponse annotateResponse = redactionController.annotate(AnnotateRequest.builder()
+                .dossierId(TEST_DOSSIER_ID)
+                .fileId(TEST_FILE_ID)
+                .build());
+
+        try (FileOutputStream fileOutputStream = new FileOutputStream(getTemporaryDirectory() + "/Annotated.pdf")) {
             fileOutputStream.write(annotateResponse.getDocument());
         }
         long end = System.currentTimeMillis();
@@ -847,7 +959,7 @@ public class RedactionIntegrationTest {
                 .fileId(TEST_FILE_ID)
                 .build());
 
-        try (FileOutputStream fileOutputStream = new FileOutputStream("/tmp/Annotated.pdf")) {
+        try (FileOutputStream fileOutputStream = new FileOutputStream(getTemporaryDirectory() + "/Annotated.pdf")) {
             fileOutputStream.write(annotateResponse.getDocument());
         }
         long end = System.currentTimeMillis();
@@ -873,7 +985,7 @@ public class RedactionIntegrationTest {
 
         RedactionResult result = redactionController.classify(redactionRequest);
 
-        try (FileOutputStream fileOutputStream = new FileOutputStream("/tmp/Classified.pdf")) {
+        try (FileOutputStream fileOutputStream = new FileOutputStream(getTemporaryDirectory() + "/Classified.pdf")) {
             fileOutputStream.write(result.getDocument());
         }
     }
@@ -895,7 +1007,7 @@ public class RedactionIntegrationTest {
 
         RedactionResult result = redactionController.sections(redactionRequest);
 
-        try (FileOutputStream fileOutputStream = new FileOutputStream("/tmp/Sections.pdf")) {
+        try (FileOutputStream fileOutputStream = new FileOutputStream(getTemporaryDirectory() + "/Sections.pdf")) {
             fileOutputStream.write(result.getDocument());
         }
     }
@@ -917,7 +1029,7 @@ public class RedactionIntegrationTest {
 
         RedactionResult result = redactionController.htmlTables(redactionRequest);
 
-        try (FileOutputStream fileOutputStream = new FileOutputStream("/tmp/Tables.html")) {
+        try (FileOutputStream fileOutputStream = new FileOutputStream(getTemporaryDirectory() + "/Tables.html")) {
             fileOutputStream.write(result.getDocument());
         }
     }
@@ -939,7 +1051,7 @@ public class RedactionIntegrationTest {
 
         RedactionResult result = redactionController.htmlTables(redactionRequest);
 
-        try (FileOutputStream fileOutputStream = new FileOutputStream("/tmp/Tables.html")) {
+        try (FileOutputStream fileOutputStream = new FileOutputStream(getTemporaryDirectory() + "/Tables.html")) {
             fileOutputStream.write(result.getDocument());
         }
     }
@@ -1007,7 +1119,31 @@ public class RedactionIntegrationTest {
                 .fileId(TEST_FILE_ID)
                 .build());
 
-        try (FileOutputStream fileOutputStream = new FileOutputStream("/tmp/Annotated.pdf")) {
+        try (FileOutputStream fileOutputStream = new FileOutputStream(getTemporaryDirectory() + "/Annotated.pdf")) {
+            fileOutputStream.write(annotateResponse.getDocument());
+        }
+        long end = System.currentTimeMillis();
+
+        System.out.println("duration: " + (end - start));
+        System.out.println("numberOfPages: " + result.getNumberOfPages());
+    }
+
+
+    @Test
+    public void testExpandByRegEx() throws IOException {
+
+        System.out.println("expandByRegex");
+        long start = System.currentTimeMillis();
+
+        AnalyzeRequest request = prepareStorage("files/Metolachlor/S-Metolachlor_RAR_02_Volume_2_2018-09-06.pdf");
+        AnalyzeResult result = reanalyzeService.analyze(request);
+
+        AnnotateResponse annotateResponse = redactionController.annotate(AnnotateRequest.builder()
+                .dossierId(TEST_DOSSIER_ID)
+                .fileId(TEST_FILE_ID)
+                .build());
+
+        try (FileOutputStream fileOutputStream = new FileOutputStream(getTemporaryDirectory() + "/Annotated.pdf")) {
             fileOutputStream.write(annotateResponse.getDocument());
         }
         long end = System.currentTimeMillis();
@@ -1035,4 +1171,13 @@ public class RedactionIntegrationTest {
         }
     }
 
+    private static String getTemporaryDirectory() {
+
+//        String tmpdir = System.getProperty("java.io.tmpdir");
+//        if (StringUtils.isNotBlank(tmpdir)) {
+//            return tmpdir;
+//        }
+        return "/tmp";
+    }
+
 }

redaction-service-v1/redaction-service-server-v1/src/test/java/com/iqser/red/service/redaction/v1/server/redaction/utils/EntitySearchUtilsTest.java

@@ -0,0 +1,171 @@
+package com.iqser.red.service.redaction.v1.server.redaction.utils;
+
+import static org.assertj.core.api.Assertions.assertThat;
+
+import java.util.HashSet;
+import java.util.Set;
+
+import org.junit.Test;
+
+import com.iqser.red.service.redaction.v1.server.redaction.model.Entity;
+
+public class EntitySearchUtilsTest {
+
+    /*
+     * Text:     Batman X. Superman Y.
+     * Position: 0123456789
+     *                     0123456789
+     *                               0123456789
+     */
+    @Test
+    public void testNotOverlappingEntitiesExpandedEnd() {
+
+        // Arrange
+        Set<Entity> existingEntities = new HashSet<>();
+        Entity existingEntity1 = new Entity("Batman", "fake type", 0, 5, "fake headline", 0, false, false);
+        Entity existingEntity2 = new Entity("Superman", "fake type", 10, 17, "fake headline", 0, false, false);
+        existingEntities.add(existingEntity1);
+        existingEntities.add(existingEntity2);
+
+        Set<Entity> foundEntities = new HashSet<>();
+        Entity foundEntities1 = new Entity("Batman X.", "fake type", 0, 8, "fake headline", 0, false, false);
+        Entity foundEntities2 = new Entity("Superman Y.", "fake type", 10, 20, "fake headline", 0, false, false);
+        foundEntities.add(foundEntities1);
+        foundEntities.add(foundEntities2);
+
+        // Act
+        Set<Entity> result = EntitySearchUtils.findNonOverlappingMatchEntities(existingEntities, foundEntities);
+
+        // Assert
+        assertThat(result.size()).isEqualTo(2);
+        assertThat(result).contains(foundEntities1);
+        assertThat(result).contains(foundEntities2);
+
+    }
+
+
+    /*
+     * Text:     Batman X. Superman Y.
+     * Position: 0123456789
+     *                     0123456789
+     *                               0123456789
+     */
+    @Test
+    public void testNotOverlappingEntitiesExpandedStartAndEndOverlapping() {
+
+        // Arrange
+        Set<Entity> existingEntities = new HashSet<>();
+        Entity existingEntity1 = new Entity("Batman X.", "fake type", 0, 8, "fake headline", 0, false, false);
+        Entity existingEntity2 = new Entity("Superman", "fake type", 10, 17, "fake headline", 0, false, false);
+        existingEntities.add(existingEntity1);
+        existingEntities.add(existingEntity2);
+
+        Set<Entity> foundEntities = new HashSet<>();
+        Entity foundEntities1 = new Entity("Batman X.", "fake type", 0, 8, "fake headline", 0, false, false);
+        Entity foundEntities2 = new Entity("X. Superman Y.", "fake type", 7, 20, "fake headline", 0, false, false);
+        foundEntities.add(foundEntities1);
+        foundEntities.add(foundEntities2);
+
+        // Act
+        Set<Entity> result = EntitySearchUtils.findNonOverlappingMatchEntities(existingEntities, foundEntities);
+
+        // Assert
+        assertThat(result.size()).isEqualTo(1);
+        assertThat(result).contains(foundEntities1);
+
+    }
+
+
+    /*
+     * Text:     Batman X. Superman Y.
+     * Position: 0123456789
+     *                     0123456789
+     *                               0123456789
+     */
+    @Test
+    public void testNotOverlappingEntitiesExpandedStartAndEnd() {
+
+        // Arrange
+        Set<Entity> existingEntities = new HashSet<>();
+        Entity existingEntity1 = new Entity("Batman X.", "fake type", 0, 8, "fake headline", 0, false, false);
+        Entity existingEntity2 = new Entity("Superman", "fake type", 10, 17, "fake headline", 0, false, false);
+        existingEntities.add(existingEntity1);
+        existingEntities.add(existingEntity2);
+
+        Set<Entity> foundEntities = new HashSet<>();
+        Entity foundEntities1 = new Entity("Batman X.", "fake type", 0, 8, "fake headline", 0, false, false);
+        Entity foundEntities2 = new Entity("X. Superman", "fake type", 7, 17, "fake headline", 0, false, false);
+        foundEntities.add(foundEntities1);
+        foundEntities.add(foundEntities2);
+
+        // Act
+        Set<Entity> result = EntitySearchUtils.findNonOverlappingMatchEntities(existingEntities, foundEntities);
+
+        // Assert
+        assertThat(result.size()).isEqualTo(1);
+        assertThat(result).contains(foundEntities1);
+
+    }
+
+
+    /*
+     * Text:     Batman X. Superman Y.
+     * Position: 0123456789
+     *                     0123456789
+     *                               0123456789
+     */
+    @Test
+    public void testNotOverlappingEntitiesExpandedExistingAndExpandedEnd() {
+
+        // Arrange
+        Set<Entity> existingEntities = new HashSet<>();
+        Entity existingEntity1 = new Entity("X. Superman", "fake type", 7, 17, "fake headline", 0, false, false);
+        Entity existingEntity2 = new Entity("Batman", "fake type", 0, 5, "fake headline", 0, false, false);
+        existingEntities.add(existingEntity1);
+        existingEntities.add(existingEntity2);
+
+        Set<Entity> foundEntities = new HashSet<>();
+        Entity foundEntities1 = new Entity("Batman X.", "fake type", 0, 8, "fake headline", 0, false, false);
+        Entity foundEntities2 = new Entity("Superman", "fake type", 10, 17, "fake headline", 0, false, false);
+        foundEntities.add(foundEntities1);
+        foundEntities.add(foundEntities2);
+
+        // Act
+        Set<Entity> result = EntitySearchUtils.findNonOverlappingMatchEntities(existingEntities, foundEntities);
+
+        // Assert
+        assertThat(result.size()).isEqualTo(0);
+
+    }
+
+    /*
+     * Text:     Batman X. Superman Y.
+     * Position: 0123456789
+     *                     0123456789
+     *                               0123456789
+     */
+    @Test
+    public void testNotOverlappingEntitiesExpandedEndLong() {
+
+        // Arrange
+        Set<Entity> existingEntities = new HashSet<>();
+        Entity existingEntity1 = new Entity("X. Superman", "fake type", 7, 17, "fake headline", 0, false, false);
+        Entity existingEntity2 = new Entity("Batman", "fake type", 0, 5, "fake headline", 0, false, false);
+        existingEntities.add(existingEntity1);
+        existingEntities.add(existingEntity2);
+
+        Set<Entity> foundEntities = new HashSet<>();
+        Entity foundEntities1 = new Entity("Batman X. Superman", "fake type", 0, 17, "fake headline", 0, false, false);
+        Entity foundEntities2 = new Entity("Superman", "fake type", 10, 17, "fake headline", 0, false, false);
+        foundEntities.add(foundEntities1);
+        foundEntities.add(foundEntities2);
+
+        // Act
+        Set<Entity> result = EntitySearchUtils.findNonOverlappingMatchEntities(existingEntities, foundEntities);
+
+        // Assert
+        assertThat(result.size()).isEqualTo(0);
+
+    }
+
+}

redaction-service-v1/redaction-service-server-v1/src/test/resources/dictionaries/CBI_address.txt

@@ -1654,3 +1654,12 @@ Zyma SA
 Zyma SA, Nyon, Switzerland
 Mambo-Tox Ltd. Biomedical Sciences Building Bassett Crescent East Southampton SO16 7PX UK
 Syngenta Environmental Sciences Jealott’s Hill International Research Centre Bracknell, Berkshire RG42 6EY UK
+Test Ignored Hint CBI_ADDRESS
+CTL
+CTL - Central Toxicology Laboratory
+CTL/P/3557
+CTL/P/3607
+CTL/P/S 161
+CTL/Pl4333
+CTL/with dictionary entry
+

redaction-service-v1/redaction-service-server-v1/src/test/resources/dictionaries/CBI_author.txt

@@ -8585,4 +8585,9 @@ Zoriki Hosomi R.
 Zoriki Hosomi Rosana
 Zuberer D
 Zubrod J
-Zwicker R.E.
+Zwicker R.E.
+Doe
+M. Mustermann
+F. Lastname
+Mustermann
+Lastname

redaction-service-v1/redaction-service-server-v1/src/test/resources/dictionaries/dossier_redactions.txt

@@ -1 +1,2 @@
-Difenoconazole
+Difenoconazole
+FENPROPIDIN

redaction-service-v1/redaction-service-server-v1/src/test/resources/dictionaries/published_information.txt

@@ -85,3 +85,4 @@ Toxicology and Applied Pharmacology
 Toxicol Sci
 Toxicol Sci.
 Toxicol Sci. 1
+Test Ignored Hint Published Information

redaction-service-v1/redaction-service-server-v1/src/test/resources/drools/allAuthors.drl

@@ -7,12 +7,20 @@ global Section section
 
 // --------------------------------------- CBI rules -------------------------------------------------------------------
 
+//rule "0: Expand CBI Authors with firstname initials"
+//    when
+//        Section(matchesType("CBI_author") || matchesType("recommendation_CBI_author"))
+//    then
+//        section.expandByRegEx("CBI_author", "(,? [A-Z]\\.?( ?[A-Z]\\.?)?( ?[A-Z]\\.?)?\\b\\.?)", false, 1);
+//        section.expandByRegEx("recommendation_CBI_author", "(,? [A-Z]\\.?( ?[A-Z]\\.?)?( ?[A-Z]\\.?)?\\b\\.?)", false, 1);
+//    end
+
 rule "0: Expand CBI Authors with firstname initials"
     when
         Section(matchesType("CBI_author") || matchesType("recommendation_CBI_author"))
     then
-        section.expandByRegEx("CBI_author", "(,? [A-Z]\\.?( ?[A-Z]\\.?)?( ?[A-Z]\\.?)?\\b\\.?)", false, 1);
-        section.expandByRegEx("recommendation_CBI_author", "(,? [A-Z]\\.?( ?[A-Z]\\.?)?( ?[A-Z]\\.?)?\\b\\.?)", false, 1);
+        section.expandByRegEx("CBI_author", "(,? [A-Z]\\.?( ?[A-Z]\\.?)?( ?[A-Z]\\.?)?\\b\\.?)", false, 1, "[^\\s]+");
+        section.expandByRegEx("recommendation_CBI_author", "(,? [A-Z]\\.?( ?[A-Z]\\.?)?( ?[A-Z]\\.?)?\\b\\.?)", false, 1, "[^\\s]+");
     end
 
 

redaction-service-v1/redaction-service-server-v1/src/test/resources/drools/rules.drl

@@ -7,12 +7,20 @@ global Section section
 
 // --------------------------------------- CBI rules -------------------------------------------------------------------
 
+//rule "0: Expand CBI Authors with firstname initials"
+//    when
+//        Section(matchesType("CBI_author") || matchesType("recommendation_CBI_author"))
+//    then
+//        section.expandByRegEx("CBI_author", "(,? [A-Z]\\.?( ?[A-Z]\\.?)?( ?[A-Z]\\.?)?\\b\\.?)", false, 1);
+//        section.expandByRegEx("recommendation_CBI_author", "(,? [A-Z]\\.?( ?[A-Z]\\.?)?( ?[A-Z]\\.?)?\\b\\.?)", false, 1);
+//    end
+
 rule "0: Expand CBI Authors with firstname initials"
     when
         Section(matchesType("CBI_author") || matchesType("recommendation_CBI_author"))
     then
-        section.expandByRegEx("CBI_author", "(,? [A-Z]\\.?( ?[A-Z]\\.?)?( ?[A-Z]\\.?)?\\b\\.?)", false, 1);
-        section.expandByRegEx("recommendation_CBI_author", "(,? [A-Z]\\.?( ?[A-Z]\\.?)?( ?[A-Z]\\.?)?\\b\\.?)", false, 1);
+        section.expandByRegEx("CBI_author", "(,? [A-Z]\\.?( ?[A-Z]\\.?)?( ?[A-Z]\\.?)?\\b\\.?)", false, 1, "[\\s]+");
+        section.expandByRegEx("recommendation_CBI_author", "(,? [A-Z]\\.?( ?[A-Z]\\.?)?( ?[A-Z]\\.?)?\\b\\.?)", false, 1, "[\\s]+");
     end
 
 
@@ -336,4 +344,11 @@ rule "29: Redact Dossier Redactions"
          Section(matchesType("dossier_redactions"))
      then
          section.redact("dossier_redactions", 29, "Dossier Redaction found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
-     end
+     end
+
+rule "30: Ignore dossier_redactions if confidential"
+    when
+        Section(!fileAttributeByLabelEqualsIgnoreCase("Confidentiality","confidential") && matchesType("dossier_redactions"));
+    then
+        section.ignore("dossier_redactions");
+    end