RED-9859: update intersecting nodes on kie session insertion

- modify unit test

redaction-service-v1/redaction-service-api-v1/build.gradle.kts

@@ -4,7 +4,7 @@ plugins {
 }
 
 description = "redaction-service-api-v1"
-val persistenceServiceVersion = "2.439.0"
+val persistenceServiceVersion = "2.465.60"
 
 dependencies {
     implementation("org.springframework:spring-web:6.0.12")

redaction-service-v1/redaction-service-server-v1/build.gradle.kts

@@ -12,11 +12,11 @@ plugins {
 description = "redaction-service-server-v1"
 
 
-val layoutParserVersion = "0.141.0"
+val layoutParserVersion = "0.142.6"
 val jacksonVersion = "2.15.2"
 val droolsVersion = "9.44.0.Final"
 val pdfBoxVersion = "3.0.0"
-val persistenceServiceVersion = "2.444.0"
+val persistenceServiceVersion = "2.465.60"
 val springBootStarterVersion = "3.1.5"
 val springCloudVersion = "4.0.4"
 val testContainersVersion = "1.19.7"
@@ -43,6 +43,7 @@ dependencies {
     implementation("com.iqser.red.commons:storage-commons:2.45.0")
     implementation("com.knecon.fforesight:tenant-commons:0.24.0")
     implementation("com.knecon.fforesight:tracing-commons:0.5.0")
+    implementation("com.knecon.fforesight:lifecycle-commons:0.6.0")
 
     implementation("com.fasterxml.jackson.module:jackson-module-afterburner:${jacksonVersion}")
     implementation("com.fasterxml.jackson.datatype:jackson-datatype-jsr310:${jacksonVersion}")
@@ -130,18 +131,19 @@ tasks.named<BootBuildImage>("bootBuildImage") {
     }
 }
 
-fun parseDroolsImports(droolsFilePath: String): List<String> {
-
+fun parseDroolsImports(vararg droolsFilePaths: String): List<String> {
     val imports = mutableListOf<String>()
     val importPattern = Regex("^import\\s+(com\\.iqser\\.red\\.service\\.redaction\\.v1\\.[\\w.]+);")
     val desiredPrefix = "com.iqser.red.service.redaction.v1"
 
-    File(droolsFilePath).forEachLine { line ->
-        importPattern.find(line)?.let { matchResult ->
-            val importPath = matchResult.groupValues[1].trim()
-            if (importPath.startsWith(desiredPrefix)) {
-                val formattedPath = importPath.replace('.', '/')
-                imports.add("$formattedPath.java")
+    droolsFilePaths.forEach { filePath ->
+        File(filePath).forEachLine { line ->
+            importPattern.find(line)?.let { matchResult ->
+                val importPath = matchResult.groupValues[1].trim()
+                if (importPath.startsWith(desiredPrefix)) {
+                    val formattedPath = importPath.replace('.', '/')
+                    imports.add("$formattedPath.java")
+                }
             }
         }
     }
@@ -149,7 +151,11 @@ fun parseDroolsImports(droolsFilePath: String): List<String> {
     return imports
 }
 
-val droolsImports = parseDroolsImports("redaction-service-v1/redaction-service-server-v1/src/main/resources/drools/all_rules_documine.drl")
+// Combine imports from both drools files
+val droolsImports = parseDroolsImports(
+    "redaction-service-v1/redaction-service-server-v1/src/main/resources/drools/all_rules_documine.drl",
+    "redaction-service-v1/redaction-service-server-v1/src/main/resources/drools/base_component_rules.drl"
+)
 
 tasks.register("generateJavaDoc", Javadoc::class) {
 

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

@@ -13,6 +13,7 @@ import org.springframework.boot.context.properties.EnableConfigurationProperties
 import org.springframework.cache.annotation.EnableCaching;
 import org.springframework.cloud.openfeign.EnableFeignClients;
 import org.springframework.context.annotation.Bean;
+import org.springframework.context.annotation.EnableAspectJAutoProxy;
 import org.springframework.context.annotation.Import;
 import org.springframework.data.mongodb.repository.config.EnableMongoRepositories;
 
@@ -20,6 +21,7 @@ import com.iqser.red.service.dictionarymerge.commons.DictionaryMergeService;
 import com.iqser.red.service.persistence.service.v1.api.shared.mongo.SharedMongoAutoConfiguration;
 import com.iqser.red.service.redaction.v1.server.client.RulesClient;
 import com.iqser.red.storage.commons.StorageAutoConfiguration;
+import com.knecon.fforesight.lifecyclecommons.LifecycleAutoconfiguration;
 import com.knecon.fforesight.mongo.database.commons.MongoDatabaseCommonsAutoConfiguration;
 import com.knecon.fforesight.mongo.database.commons.liquibase.EnableMongoLiquibase;
 import com.knecon.fforesight.tenantcommons.MultiTenancyAutoConfiguration;
@@ -32,13 +34,14 @@ import lombok.extern.slf4j.Slf4j;
 
 @Slf4j
 @EnableCaching
-@ImportAutoConfiguration({MultiTenancyAutoConfiguration.class, SharedMongoAutoConfiguration.class})
+@ImportAutoConfiguration({MultiTenancyAutoConfiguration.class, SharedMongoAutoConfiguration.class, LifecycleAutoconfiguration.class})
 @Import({MetricsConfiguration.class, StorageAutoConfiguration.class, MongoDatabaseCommonsAutoConfiguration.class})
 @EnableFeignClients(basePackageClasses = RulesClient.class)
 @EnableConfigurationProperties(RedactionServiceSettings.class)
 @EnableMongoRepositories(basePackages = "com.iqser.red.service.persistence")
 @EnableMongoLiquibase
 @SpringBootApplication(exclude = {SecurityAutoConfiguration.class, ManagementWebSecurityAutoConfiguration.class, DataSourceAutoConfiguration.class, LiquibaseAutoConfiguration.class, MongoAutoConfiguration.class, MongoDataAutoConfiguration.class})
+@EnableAspectJAutoProxy
 public class Application {
 
     public static void main(String[] args) {

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

@@ -21,6 +21,7 @@ import com.iqser.red.service.persistence.service.v1.api.shared.model.analysislog
 import com.iqser.red.service.persistence.service.v1.api.shared.model.annotations.ManualRedactions;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.annotations.entitymapped.BaseAnnotation;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.annotations.entitymapped.IdRemoval;
+import com.iqser.red.service.persistence.service.v1.api.shared.model.annotations.entitymapped.ManualForceRedaction;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.annotations.entitymapped.ManualRedactionEntry;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.annotations.entitymapped.ManualResizeRedaction;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.redactionlog.Rectangle;
@@ -119,9 +120,14 @@ public class RedactionLogToEntityLogMigrationService {
                 .filter(MigrationEntity::needsManualEntry)
                 .map(MigrationEntity::buildManualRedactionEntry)
                 .toList();
-
         idsToMigrateInDb.setManualRedactionEntriesToAdd(manualRedactionEntriesToAdd);
 
+        List<String> manualForceRedactionIdsToDelete = entitiesToMigrate.stream()
+                .filter(MigrationEntity::needsForceDeletion)
+                .map(MigrationEntity::getNewId)
+                .toList();
+        idsToMigrateInDb.setForceRedactionIdsToDelete(manualForceRedactionIdsToDelete);
+
         return new MigratedEntityLog(idsToMigrateInDb, entityLog);
     }
 

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

@@ -23,6 +23,7 @@ import com.iqser.red.service.persistence.service.v1.api.shared.model.analysislog
 import com.iqser.red.service.persistence.service.v1.api.shared.model.annotations.ManualChangeFactory;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.annotations.Rectangle;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.annotations.entitymapped.BaseAnnotation;
+import com.iqser.red.service.persistence.service.v1.api.shared.model.annotations.entitymapped.ManualForceRedaction;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.annotations.entitymapped.ManualRecategorization;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.annotations.entitymapped.ManualRedactionEntry;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.annotations.entitymapped.ManualResizeRedaction;
@@ -220,6 +221,11 @@ public final class MigrationEntity {
            && !entityLogEntry.getChanges().isEmpty()
            && entityLogEntry.getChanges().stream().map(Change::getType).toList().get(entityLogEntry.getChanges().size() - 1).equals(ChangeType.REMOVED)) {
             entityLogEntry.setState(EntryState.REMOVED);
+            if (!entityLogEntry.getManualChanges().isEmpty()) {
+                entityLogEntry.getManualChanges()
+                        .removeIf(manualChange -> manualChange.getManualRedactionType()
+                                .equals(com.iqser.red.service.persistence.service.v1.api.shared.model.analysislog.entitylog.ManualRedactionType.FORCE));
+            }
         }
 
         return entityLogEntry;
@@ -466,4 +472,10 @@ public final class MigrationEntity {
                        .anyMatch(mc -> mc instanceof ManualResizeRedaction && !((ManualResizeRedaction) mc).getUpdateDictionary()) && !(migratedEntity instanceof Image);
     }
 
+    public boolean needsForceDeletion() {
+
+        return manualChanges.stream()
+                       .anyMatch(mc -> mc instanceof ManualForceRedaction) && this.precursorEntity != null && this.precursorEntity.removed();
+    }
+
 }

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

@@ -120,7 +120,8 @@ public class PrecursorEntity implements IEntity {
         EntityType entityType = getEntityType(entryType);
         String value = Optional.ofNullable(importedRedaction.getValue())
                 .orElse("");
-        return PrecursorEntity.builder()
+
+        PrecursorEntityBuilder precursorEntityBuilder = PrecursorEntity.builder()
                 .id(importedRedaction.getId())
                 .value(value)
                 .entityPosition(rectangleWithPages)
@@ -130,14 +131,21 @@ public class PrecursorEntity implements IEntity {
                                     .orElse(""))
                 .type(Optional.ofNullable(importedRedaction.getType())
                               .orElse(IMPORTED_REDACTION_TYPE))
-                .section(importedRedaction.getManualOverwriteSection())
+                .section(Optional.ofNullable(importedRedaction.getSection())
+                                 .orElse(""))
                 .entityType(entityType)
                 .isDictionaryEntry(false)
                 .isDossierDictionaryEntry(false)
+                .manualOverwrite(new ManualChangeOverwrite(entityType))
                 .rectangle(value.isBlank() || entryType.equals(EntryType.IMAGE) || entryType.equals(EntryType.IMAGE_HINT) || entryType.equals(EntryType.AREA))
-                .manualOverwrite(new ManualChangeOverwrite(entityType, importedRedaction.getManualOverwriteSection()))
-                .engines(Set.of(Engine.IMPORTED))
-                .build();
+                .engines(Set.of(Engine.IMPORTED));
+
+        if (importedRedaction.getManualOverwriteSection() != null && !importedRedaction.getManualOverwriteSection().isEmpty()) {
+            precursorEntityBuilder.section(importedRedaction.getManualOverwriteSection())
+                    .manualOverwrite(new ManualChangeOverwrite(entityType, importedRedaction.getManualOverwriteSection()));
+        }
+
+        return precursorEntityBuilder.build();
     }
 
 

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

@@ -288,8 +288,8 @@ public class DocumentTree {
         if (treeId.isEmpty()) {
             return root;
         }
-        Entry entry = root.children.get(treeId.get(0));
-        for (int id : treeId.subList(1, treeId.size())) {
+        Entry entry = root;
+        for (int id : treeId) {
             entry = entry.children.get(id);
         }
         return entry;

redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/model/document/nodes/Page.java

@@ -3,8 +3,10 @@ package com.iqser.red.service.redaction.v1.server.model.document.nodes;
 import java.util.HashSet;
 import java.util.List;
 import java.util.Set;
+import java.util.stream.Stream;
 
 import com.iqser.red.service.redaction.v1.server.model.document.entity.TextEntity;
+import com.iqser.red.service.redaction.v1.server.model.document.textblock.AtomicTextBlock;
 import com.iqser.red.service.redaction.v1.server.model.document.textblock.TextBlock;
 import com.iqser.red.service.redaction.v1.server.model.document.textblock.TextBlockCollector;
 
@@ -35,7 +37,7 @@ public class Page {
     Integer width;
     Integer rotation;
 
-    List<SemanticNode> mainBody;
+    List<AtomicTextBlock> textBlocksOnPage;
     Header header;
     Footer footer;
 
@@ -53,13 +55,63 @@ public class Page {
      */
     public TextBlock getMainBodyTextBlock() {
 
-        return mainBody.stream()
-                .filter(SemanticNode::isLeaf)
-                .map(SemanticNode::getTextBlock)
+        return textBlocksOnPage.stream()
+                .filter(atb -> !atb.isEmpty())
                 .collect(new TextBlockCollector());
     }
 
 
+    /**
+     * Retrieves the highest SemanticNodes, which appear only on this page. It is achieved by traversing the DocumentTree up, until a SemanticNode's direct parent is no longer exclusively on this page.
+     *
+     * @return A list which contains the highes SemanticNodes, which appear only on this page.
+     */
+    public List<SemanticNode> getMainBody() {
+
+        return textBlocksOnPage.stream()
+                .map(AtomicTextBlock::getParent)
+                .map(this::getHighestParentOnlyOnPage)
+                .distinct()
+                .toList();
+    }
+
+
+    /**
+     * Retrieves the highest SemanticNodes which are present on the page. There might be multiples, as two or more Main Sections start on a page.
+     * This is achieved by traversing up the document tree and returning all SemanticNodes whose direct parent is the Document
+     *
+     * @return A list of the highest SemanticNodes present on this page
+     */
+    public Stream<SemanticNode> streamHighestSemanticNodesOnPage() {
+
+        return textBlocksOnPage.stream()
+                .map(AtomicTextBlock::getParent)
+                .map(this::getHighestSemanticNodeOnPage)
+                .distinct();
+    }
+
+
+    private SemanticNode getHighestParentOnlyOnPage(SemanticNode node) {
+
+        SemanticNode currentNode = node;
+        while (currentNode.hasParent() && currentNode.getParent().onlyOnPage(this)) {
+            currentNode = currentNode.getParent();
+        }
+        return currentNode;
+    }
+
+
+    private SemanticNode getHighestSemanticNodeOnPage(SemanticNode node) {
+
+        SemanticNode currentNode = node;
+        while (currentNode.hasParent() //
+               && !currentNode.getParent().getType().equals(NodeType.DOCUMENT)) {
+            currentNode = currentNode.getParent();
+        }
+        return currentNode;
+    }
+
+
     @Override
     public String toString() {
 

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

@@ -1,10 +1,12 @@
 package com.iqser.red.service.redaction.v1.server.model.document.nodes;
 
 import java.awt.geom.Rectangle2D;
+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 com.iqser.red.service.redaction.v1.server.model.document.entity.TextEntity;
 import com.iqser.red.service.redaction.v1.server.model.document.DocumentTree;
@@ -33,7 +35,6 @@ import lombok.extern.slf4j.Slf4j;
 @EqualsAndHashCode(onlyExplicitlyIncluded = true, callSuper = true)
 public class Section extends AbstractSemanticNode {
 
-
     @Override
     public NodeType getType() {
 
@@ -60,7 +61,6 @@ public class Section extends AbstractSemanticNode {
     }
 
 
-
     @Override
     public String toString() {
 
@@ -85,7 +85,14 @@ public class Section extends AbstractSemanticNode {
      */
     public boolean anyHeadlineContainsString(String value) {
 
-        return streamAllSubNodesOfType(NodeType.HEADLINE).anyMatch(h -> h.containsString(value));
+        boolean found = streamAllSubNodesOfType(NodeType.HEADLINE).anyMatch(h -> h.containsString(value)) || getHeadline().containsString(value);
+        if (!found) {
+            List<Headline> previousHeadlines = new ArrayList<>();
+            headlinesByPreviousSibling(this, previousHeadlines);
+            return previousHeadlines.stream()
+                    .anyMatch(headline -> headline.containsString(value));
+        }
+        return true;
     }
 
 
@@ -97,8 +104,37 @@ public class Section extends AbstractSemanticNode {
      */
     public boolean anyHeadlineContainsStringIgnoreCase(String value) {
 
-        return streamAllSubNodesOfType(NodeType.HEADLINE).anyMatch(h -> h.containsStringIgnoreCase(value));
+        boolean found = streamAllSubNodesOfType(NodeType.HEADLINE).anyMatch(h -> h.containsStringIgnoreCase(value)) || getHeadline().containsStringIgnoreCase(value);
+        if (!found) {
+            List<Headline> previousHeadlines = new ArrayList<>();
+            headlinesByPreviousSibling(this, previousHeadlines);
+            return previousHeadlines.stream()
+                    .anyMatch(headline -> headline.containsStringIgnoreCase(value));
+        }
+        return true;
     }
 
 
+    private void headlinesByPreviousSibling(SemanticNode section, List<Headline> found) {
+
+        if (section.getPreviousSibling()
+                    .isPresent() && section.getPreviousSibling()
+                    .get() instanceof Section previousSection) {
+
+            var subnodes = previousSection.streamAllSubNodes()
+                    .toList();
+            if (subnodes.size() == 1 && subnodes.get(0) instanceof Headline previousHeadline) {
+                found.add(previousHeadline);
+                headlinesByPreviousSibling(previousSection, found);
+            }
+        }
+
+        if (section.getPreviousSibling()
+                    .isPresent() && section.getPreviousSibling()
+                    .get() instanceof Headline previousHeadline) {
+            found.add(previousHeadline);
+            headlinesByPreviousSibling(previousHeadline, found);
+        }
+    }
+
 }

redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/model/document/nodes/SemanticNode.java

@@ -808,4 +808,17 @@ public interface SemanticNode {
         streamChildren().forEach(childNode -> childNode.accept(visitor));
     }
 
+
+    /**
+     * Checks wether this SemanticNode appears on a single page only, and if that page is the provided one.
+     *
+     * @param page the page to check
+     * @return true, when SemanticNode is on a single page only and the page is the provided page. Otherwise, false.
+     */
+    default boolean onlyOnPage(Page page) {
+
+        Set<Page> pages = getPages();
+        return pages.size() == 1 && pages.contains(page);
+    }
+
 }

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

@@ -110,7 +110,14 @@ public class RedactionMessageReceiver {
                     log.info("-------------------------------------------------------------------------------------------------");
                     shouldRespond = false;
                     break;
-
+                case IMPORTED_REDACTIONS_ONLY:
+                    log.info("------------------------------Imported Redactions Analysis Only------------------------------------------");
+                    log.info("Starting Imported Redactions Analysis Only for file {} in dossier {}", analyzeRequest.getFileId(), analyzeRequest.getDossierId());
+                    log.debug(analyzeRequest.getManualRedactions().toString());
+                    result = analyzeService.analyzeImportedRedactionsOnly(analyzeRequest);
+                    log.info("Successful Imported Redactions Analysis Only dossier {} file {}", analyzeRequest.getDossierId(), analyzeRequest.getFileId());
+                    log.info("-------------------------------------------------------------------------------------------------");
+                    break;
                 default:
                     throw new IllegalArgumentException("Unknown MessageType: " + analyzeRequest.getMessageType());
             }

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

@@ -23,8 +23,10 @@ import com.iqser.red.service.persistence.service.v1.api.shared.model.RuleFileTyp
 import com.iqser.red.service.persistence.service.v1.api.shared.model.analysislog.componentlog.ComponentLog;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.analysislog.entitylog.EntityLog;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.analysislog.entitylog.EntityLogChanges;
+import com.iqser.red.service.persistence.service.v1.api.shared.model.analysislog.entitylog.imported.ImportedLegalBases;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.analysislog.entitylog.imported.ImportedRedactions;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.dossiertemplate.dossier.file.FileType;
+import com.iqser.red.service.persistence.service.v1.api.shared.model.mapper.ImportedLegalBasisMapper;
 import com.iqser.red.service.redaction.v1.server.RedactionServiceSettings;
 import com.iqser.red.service.redaction.v1.server.client.model.NerEntitiesModel;
 import com.iqser.red.service.redaction.v1.server.model.KieWrapper;
@@ -76,6 +78,7 @@ public class AnalyzeService {
     ImportedRedactionEntryService importedRedactionEntryService;
     ObservedStorageService observedStorageService;
     FunctionTimerValues redactmanagerAnalyzePagewiseValues;
+    ImportedLegalBasisMapper importedLegalBasisMapper = ImportedLegalBasisMapper.INSTANCE;
 
 
     @Timed("redactmanager_reanalyze")
@@ -128,7 +131,7 @@ public class AnalyzeService {
                                     document,
                                     document.getNumberOfPages(),
                                     true,
-                                    Collections.emptySet());
+                                    new HashSet<>());
         }
 
         KieWrapper kieWrapperEntityRules = kieContainerCreationService.getLatestKieContainer(analyzeRequest.getDossierTemplateId(), RuleFileType.ENTITY);
@@ -245,6 +248,39 @@ public class AnalyzeService {
     }
 
 
+    @Timed("redactmanager_analyzeImportedRedactionsOnly")
+    @Observed(name = "AnalyzeService", contextualName = "analyzeImportedRedactionsOnly")
+    public AnalyzeResult analyzeImportedRedactionsOnly(AnalyzeRequest analyzeRequest) {
+
+        long startTime = System.currentTimeMillis();
+
+        dictionaryService.updateDictionary(analyzeRequest.getDossierTemplateId(), analyzeRequest.getDossierId());
+
+        Document document = DocumentGraphMapper.toDocumentGraph(observedStorageService.getDocumentData(analyzeRequest.getDossierId(), analyzeRequest.getFileId()));
+        log.info("Loaded Document Graph for file {} in dossier {}", analyzeRequest.getFileId(), analyzeRequest.getDossierId());
+
+        ImportedRedactions importedRedactions = redactionStorageService.getImportedRedactions(analyzeRequest.getDossierId(), analyzeRequest.getFileId());
+        log.info("Loaded Imported Redactions for file {} in dossier {}", analyzeRequest.getFileId(), analyzeRequest.getDossierId());
+
+        ImportedLegalBases importedLegalBases = redactionStorageService.getImportedLegalBases(analyzeRequest.getDossierId(), analyzeRequest.getFileId());
+        log.info("Loaded Imported Legal Bases for file {} in dossier {}", analyzeRequest.getFileId(), analyzeRequest.getDossierId());
+
+        var notFoundImportedEntries = importedRedactionEntryService.addImportedEntriesAndReturnNotFoundEntries(analyzeRequest, importedRedactions, document);
+
+        EntityLogChanges entityLogChanges = entityLogCreatorService.createInitialEntityLog(analyzeRequest, document, notFoundImportedEntries, new DictionaryVersion(0, 0), 0);
+
+        entityLogChanges.getEntityLog()
+                .setLegalBasis(importedLegalBases.getImportedLegalBases()
+                                       .stream()
+                                       .map(importedLegalBasisMapper::toEntityLogLegalBasis)
+                                       .toList());
+
+        notFoundImportedEntitiesService.processEntityLog(entityLogChanges.getEntityLog(), analyzeRequest, notFoundImportedEntries);
+
+        return finalizeAnalysis(analyzeRequest, startTime, KieWrapper.empty(), entityLogChanges, document, document.getNumberOfPages(), false, new HashSet<>());
+    }
+
+
     private AnalyzeResult finalizeAnalysis(AnalyzeRequest analyzeRequest,
                                            long startTime,
                                            KieWrapper kieWrapperComponentRules,
@@ -367,7 +403,7 @@ public class AnalyzeService {
 
         return new NerEntitiesModel(nerEntitiesModel.getData().entrySet()
                                             .stream() //
-                                            .filter(entry -> sectionsToReanalyseIds.contains(entry.getKey())) //
+                                            .filter(entry -> sectionsToReanalyseIds.contains(getSuperSectionID(entry.getKey()))) //
                                             .collect(Collectors.toMap(Map.Entry::getKey, Map.Entry::getValue)));
     }
 
@@ -383,4 +419,11 @@ public class AnalyzeService {
         return nerEntities;
     }
 
+
+    private static Integer getSuperSectionID(String section) {
+
+        return NerEntitiesAdapter.sectionNumberToTreeId(section)
+                .get(0);
+    }
+
 }

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

@@ -223,7 +223,6 @@ public class EntityLogCreatorService {
 
         String type = precursorEntity.getManualOverwrite().getType()
                 .orElse(precursorEntity.getType());
-        boolean isHint = isHint(precursorEntity.getEntityType());
         return EntityLogEntry.builder()
                 .id(precursorEntity.getId())
                 .reason(precursorEntity.buildReasonWithManualChangeDescriptions())

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

@@ -40,7 +40,8 @@ public class ComponentMappingFileSystemCache {
     public File getComponentMappingFile(ComponentMappingMetadata metadata) {
 
         Path mappingFile = getMappingFileFromMetadata(metadata);
-        Path mappingFileMetaDataFile = mappingFile.resolveSibling(metadata.getName() + METADATA_SUFFIX);
+        Path mappingFileMetaDataFile = getMappingMetadataFileFromMetadata(metadata);
+
         synchronized (ComponentMappingFileSystemCache.class) {
 
             if (fileExistsAndUpToDate(metadata, mappingFile, mappingFileMetaDataFile)) {
@@ -52,7 +53,7 @@ public class ComponentMappingFileSystemCache {
             InputStreamResource inputStreamResource = storageService.getObject(TenantContext.getTenantId(), metadata.getStorageId());
 
             Files.write(mappingFile, inputStreamResource.getContentAsByteArray(), StandardOpenOption.WRITE, StandardOpenOption.TRUNCATE_EXISTING, StandardOpenOption.CREATE);
-            
+
             mapper.writeValue(mappingFileMetaDataFile.toFile(), metadata);
 
             return mappingFile.toFile();
@@ -87,6 +88,13 @@ public class ComponentMappingFileSystemCache {
     }
 
 
+    private Path getMappingMetadataFileFromMetadata(ComponentMappingMetadata metadata) {
+
+        Path tenantStem = mappingFileDir.resolve(TenantContext.getTenantId());
+        return tenantStem.resolve(metadata.getStorageId() + METADATA_SUFFIX);
+    }
+
+
     private boolean fileExistsAndUpToDate(ComponentMappingMetadata metadata, Path mappingFile, Path mappingFileMetaDataFile) {
 
         if (mappingFile.toFile().exists() && mappingFile.toFile().isFile() && mappingFileMetaDataFile.toFile().exists() && mappingFileMetaDataFile.toFile().isFile()) {

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

@@ -4,6 +4,7 @@ import java.io.File;
 import java.io.FileReader;
 import java.io.Reader;
 import java.nio.charset.Charset;
+import java.time.Duration;
 import java.util.List;
 
 import org.springframework.stereotype.Service;
@@ -36,7 +37,7 @@ public class ComponentMappingMemoryCache {
     public ComponentMappingMemoryCache(ComponentMappingFileSystemCache componentMappingFileSystemCache) {
 
         this.fileSystemCache = componentMappingFileSystemCache;
-        cache = CacheBuilder.newBuilder().maximumWeight(MAX_NUMBER_OF_LINES).weigher(COMPONENT_MAPPING_WEIGHER).build();
+        cache = CacheBuilder.newBuilder().maximumWeight(MAX_NUMBER_OF_LINES).weigher(COMPONENT_MAPPING_WEIGHER).expireAfterAccess(Duration.ofDays(1)).build();
     }
 
 

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

@@ -1,6 +1,5 @@
 package com.iqser.red.service.redaction.v1.server.service.document;
 
-
 import java.util.ArrayList;
 import java.util.Arrays;
 import java.util.Collections;
@@ -64,7 +63,7 @@ public class DocumentGraphMapper {
         for (DocumentStructure.EntryData entryData : entries) {
 
             List<Page> pages = Arrays.stream(entryData.getPageNumbers())
-                    .map(pageNumber -> getPage(pageNumber, context))
+                    .map(context::getPage)
                     .toList();
 
             SemanticNode node = switch (entryData.getType()) {
@@ -83,6 +82,15 @@ public class DocumentGraphMapper {
             if (entryData.getAtomicBlockIds().length > 0) {
                 TextBlock textBlock = toTextBlock(entryData.getAtomicBlockIds(), context, node);
                 node.setLeafTextBlock(textBlock);
+
+                switch (entryData.getType()) {
+                    case HEADER -> pages.forEach(page -> page.setHeader((Header) node));
+                    case FOOTER -> pages.forEach(page -> page.setFooter((Footer) node));
+                    case IMAGE -> pages.forEach(page -> page.getImages().add((Image) node));
+                    default -> textBlock.getAtomicTextBlocks()
+                            .forEach(atb -> atb.getPage().getTextBlocksOnPage().add(atb));
+                }
+
             }
             List<Integer> treeId = Arrays.stream(entryData.getTreeId()).boxed()
                     .toList();
@@ -94,13 +102,8 @@ public class DocumentGraphMapper {
             }
             node.setTreeId(treeId);
 
-            switch (entryData.getType()) {
-                case HEADER -> pages.forEach(page -> page.setHeader((Header) node));
-                case FOOTER -> pages.forEach(page -> page.setFooter((Footer) node));
-                default -> pages.forEach(page -> page.getMainBody().add(node));
-            }
-
             newEntries.add(DocumentTree.Entry.builder().treeId(treeId).children(buildEntries(entryData.getChildren(), context)).node(node).build());
+
         }
         return newEntries;
     }
@@ -115,7 +118,7 @@ public class DocumentGraphMapper {
     private Image buildImage(Context context, Map<String, String> properties, Long[] pageNumbers) {
 
         assert pageNumbers.length == 1;
-        Page page = getPage(pageNumbers[0], context);
+        Page page = context.getPage(pageNumbers[0]);
         var builder = Image.builder();
         PropertiesMapper.parseImageProperties(properties, builder);
         return builder.documentTree(context.documentTree).page(page).build();
@@ -161,6 +164,7 @@ public class DocumentGraphMapper {
         return SuperSection.builder().documentTree(context.documentTree).build();
     }
 
+
     private Paragraph buildParagraph(Context context, Map<String, String> properties) {
 
         if (PropertiesMapper.isDuplicateParagraph(properties)) {
@@ -189,21 +193,13 @@ public class DocumentGraphMapper {
         return AtomicTextBlock.fromAtomicTextBlockData(context.documentTextData.get(Math.toIntExact(atomicTextBlockId)),
                                                        context.documentPositionData.get(Math.toIntExact(atomicTextBlockId)),
                                                        parent,
-                                                       getPage(context.documentTextData.get(Math.toIntExact(atomicTextBlockId)).getPage(), context));
+                                                       context.getPage(context.documentTextData.get(Math.toIntExact(atomicTextBlockId)).getPage()));
     }
 
 
     private Page buildPage(DocumentPage p) {
 
-        return Page.builder().rotation(p.getRotation()).height(p.getHeight()).width(p.getWidth()).number(p.getNumber()).mainBody(new LinkedList<>()).build();
-    }
-
-
-    private Page getPage(Long pageIndex, Context context) {
-
-        Page page = context.pageData.get(Math.toIntExact(pageIndex) - 1);
-        assert page.getNumber() == Math.toIntExact(pageIndex);
-        return page;
+        return Page.builder().rotation(p.getRotation()).height(p.getHeight()).width(p.getWidth()).number(p.getNumber()).textBlocksOnPage(new LinkedList<>()).build();
     }
 
 
@@ -226,6 +222,14 @@ public class DocumentGraphMapper {
 
         }
 
+
+        private Page getPage(Long pageIndex) {
+
+            Page page = pageData.get(Math.toIntExact(pageIndex) - 1);
+            assert page.getNumber() == Math.toIntExact(pageIndex);
+            return page;
+        }
+
     }
 
 }

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

@@ -614,21 +614,21 @@ public class EntityCreationService {
     /**
      * Looks across the remaining table row to the right of the provided TableCell if any line intersects the y coordinates of the found text.
      *
-     * @param TextRanges a list of textRanges
+     * @param textRanges a list of textRanges
      * @param tableCell  the table cell
      * @param type       the type
      * @param entityType the entity type
      * @param tableNode  the table node
      * @return a stream of RedactionEntities
      */
-    private Stream<TextEntity> lineAfterBoundariesAcrossColumns(List<TextRange> TextRanges, TableCell tableCell, String type, EntityType entityType, Table tableNode) {
+    private Stream<TextEntity> lineAfterBoundariesAcrossColumns(List<TextRange> textRanges, TableCell tableCell, String type, EntityType entityType, Table tableNode) {
 
-        return TextRanges.stream()
+        return textRanges.stream()
                 .map(boundary -> RectangleTransformations.rectangle2DBBox(tableCell.getTextBlock().getPositions(boundary)))
                 .map(bBox -> Pair.of(bBox.getMaxY(), bBox.getMinY()))
                 .map(maxMinPair -> tableNode.streamRow(tableCell.getRow())
                         .filter(nextTableCell -> nextTableCell.getCol() > tableCell.getCol())
-                        .map(nextTableCell -> RedactionSearchUtility.findTextRangesOfAllLinesInYRange(maxMinPair.getLeft(), maxMinPair.getRight(), nextTableCell.getTextBlock()))
+                        .map(nextTableCell -> RedactionSearchUtility.findTextRangesOfAllLinesWithCloseYCoordinates(maxMinPair.getLeft(), maxMinPair.getRight(), nextTableCell.getTextBlock()))
                         .map(b -> b.trim(tableNode.getTextBlock()))
                         .filter(boundary -> isValidEntityTextRange(tableNode.getTextBlock(), boundary))
                         .map(boundary -> byTextRange(boundary, type, entityType, tableNode))
@@ -1160,6 +1160,10 @@ public class EntityCreationService {
 
         if (kieSession != null) {
             kieSession.insert(textEntity);
+            textEntity.getIntersectingNodes()
+                    .stream()
+                    .filter(nodesInKieSession::contains)
+                    .forEach(o -> kieSession.update(kieSession.getFactHandle(o), o));
         }
     }
 

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

@@ -11,10 +11,12 @@ import java.util.stream.Collectors;
 
 import org.springframework.stereotype.Service;
 
+import com.iqser.red.service.persistence.service.v1.api.shared.model.analysislog.entitylog.Engine;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.analysislog.entitylog.imported.ImportedRedactions;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.annotations.ManualRedactions;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.annotations.entitymapped.BaseAnnotation;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.annotations.entitymapped.IdRemoval;
+import com.iqser.red.service.redaction.v1.server.RedactionServiceSettings;
 import com.iqser.red.service.redaction.v1.server.model.PrecursorEntity;
 import com.iqser.red.service.redaction.v1.server.model.document.entity.EntityType;
 import com.iqser.red.service.redaction.v1.server.model.document.entity.TextEntity;
@@ -35,6 +37,7 @@ public class EntityFromPrecursorCreationService {
     static double MATCH_THRESHOLD = 10; // Is compared to the average sum of distances in pdf coordinates for each corner of the bounding box of the entities
     EntityFindingUtility entityFindingUtility;
     DictionaryService dictionaryService;
+    RedactionServiceSettings settings;
 
 
     public List<PrecursorEntity> createEntitiesIfFoundAndReturnNotFoundEntries(ManualRedactions manualRedactions, SemanticNode node, String dossierTemplateId) {
@@ -92,7 +95,7 @@ public class EntityFromPrecursorCreationService {
                 notFoundEntities.add(precursorEntity);
                 continue;
             }
-            createCorrectEntity(precursorEntity, optionalClosestEntity.get());
+            createCorrectEntity(precursorEntity, optionalClosestEntity.get(), settings.isAnnotationMode());
         }
 
         tempEntitiesByValue.values()
@@ -125,12 +128,16 @@ public class EntityFromPrecursorCreationService {
                                                          precursorEntity.getEntityType(),
                                                          closestEntity.getDeepestFullyContainingNode());
         } else {
-            correctEntity = TextEntity.initialEntityNode(closestEntity.getTextRange(),
-                                                         precursorEntity.type(),
-                                                         precursorEntity.getEntityType(),
-                                                         precursorEntity.getId(),
-                                                         precursorEntity.getManualOverwrite().getSection()
-                                                                 .orElse(null));
+            String section = precursorEntity.getManualOverwrite().getSection()
+                    .orElse(null);
+            if ((section == null || section.isBlank())
+                && precursorEntity.getSection() != null
+                && !precursorEntity.getSection().isBlank()
+                && precursorEntity.getEngines().contains(Engine.IMPORTED)) {
+                section = precursorEntity.getSection();
+            }
+
+            correctEntity = TextEntity.initialEntityNode(closestEntity.getTextRange(), precursorEntity.type(), precursorEntity.getEntityType(), precursorEntity.getId(), section);
         }
         correctEntity.setDeepestFullyContainingNode(closestEntity.getDeepestFullyContainingNode());
         correctEntity.setIntersectingNodes(new ArrayList<>(closestEntity.getIntersectingNodes()));

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

@@ -177,7 +177,7 @@ public class NerEntitiesAdapter {
     }
 
 
-    private static List<Integer> sectionNumberToTreeId(String sectionNumber) {
+    public static List<Integer> sectionNumberToTreeId(String sectionNumber) {
 
         return Arrays.stream(sectionNumber.split("\\."))
                 .map(Integer::parseInt)

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

@@ -11,7 +11,6 @@ import java.util.stream.Stream;
 import org.springframework.stereotype.Service;
 
 import com.iqser.red.service.persistence.service.v1.api.shared.model.AnalyzeRequest;
-import com.iqser.red.service.persistence.service.v1.api.shared.model.analysislog.entitylog.EntityLogEntry;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.analysislog.entitylog.Position;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.analysislog.entitylog.imported.ImportedRedaction;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.analysislog.entitylog.imported.ImportedRedactions;
@@ -27,7 +26,6 @@ import com.iqser.red.service.redaction.v1.server.model.dictionary.DictionaryIncr
 import com.iqser.red.service.redaction.v1.server.model.dictionary.DictionaryIncrementValue;
 import com.iqser.red.service.redaction.v1.server.model.dictionary.SearchImplementation;
 import com.iqser.red.service.redaction.v1.server.model.document.nodes.Document;
-import com.iqser.red.service.redaction.v1.server.model.document.nodes.NodeType;
 
 import io.micrometer.core.annotation.Timed;
 import lombok.AccessLevel;
@@ -51,7 +49,6 @@ public class SectionFinderService {
         long start = System.currentTimeMillis();
         Set<Integer> sectionsToReanalyse = new HashSet<>();
 
-
         var dictionaryIncrementsSearch = new SearchImplementation(dictionaryIncrement.getValues()
                                                                           .stream()
                                                                           .map(DictionaryIncrementValue::getValue)
@@ -82,9 +79,7 @@ public class SectionFinderService {
         return document.getPages()
                 .stream()
                 .filter(page -> relevantPagesForReanalysis.contains(page.getNumber()))
-                .flatMap(page -> Stream.concat(page.getMainBody()
-                                                       .stream()
-                                                       .filter(node -> node.getType().equals(NodeType.SECTION)), Stream.of(page.getHeader(), page.getFooter())))
+                .flatMap(page -> Stream.concat(page.streamHighestSemanticNodesOnPage(), Stream.of(page.getHeader(), page.getFooter())))
                 .map(node -> node.getTreeId()
                         .get(0))
                 .toList();

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

@@ -73,9 +73,10 @@ public class ComponentDroolsExecutionService {
                     entities.add(Entity.fromEntityLogEntry(entry, document, entry.getStartOffset(), entry.getEndOffset()));
                     if (entry.getDuplicatedTextRanges() != null && !entry.getDuplicatedTextRanges().isEmpty()) {
                         entry.getDuplicatedTextRanges()
-                                .forEach(duplicatedTextRange -> {
-                                    entities.add(Entity.fromEntityLogEntry(entry, document, duplicatedTextRange.getStart(), duplicatedTextRange.getEnd()));
-                                });
+                                .forEach(duplicatedTextRange -> entities.add(Entity.fromEntityLogEntry(entry,
+                                                                                                       document,
+                                                                                                       duplicatedTextRange.getStart(),
+                                                                                                       duplicatedTextRange.getEnd())));
                     }
                     return entities.stream();
                 })
@@ -94,8 +95,7 @@ public class ComponentDroolsExecutionService {
         });
 
         try {
-            completableFuture.orTimeout(settings.getDroolsExecutionTimeoutSecs(document.getNumberOfPages()), TimeUnit.SECONDS)
-                    .get();
+            completableFuture.get(settings.getDroolsExecutionTimeoutSecs(document.getNumberOfPages()), TimeUnit.SECONDS);
         } catch (ExecutionException e) {
             kieSession.dispose();
             if (e.getCause() instanceof TimeoutException) {
@@ -105,6 +105,8 @@ public class ComponentDroolsExecutionService {
         } catch (InterruptedException e) {
             kieSession.dispose();
             throw new RuntimeException(e);
+        } catch (TimeoutException e) {
+            throw new DroolsTimeoutException(e, false, RuleFileType.COMPONENT);
         }
 
         List<FileAttribute> resultingFileAttributes = getFileAttributes(kieSession);

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

@@ -45,7 +45,7 @@ public class DroolsValidationService {
     private final KieContainerCreationService kieContainerCreationService;
     private final DeprecatedElementsFinder deprecatedElementsFinder;
     private static final Pattern allowedImportsPattern = Pattern.compile(
-            "^(?:import\\s+static\\s+)?(?:import\\s+)?(?:com\\.knecon\\.fforesight|com\\.iqser\\.red|java\\.util)\\..*;$");
+            "^(?:import\\s+static\\s+)?(?:import\\s+)?(?:com\\.knecon\\.fforesight|com\\.iqser\\.red|java\\.util|java\\.text)\\..*;$");
     public static final String LINEBREAK_MATCHER = "\\R";
 
 
@@ -283,7 +283,9 @@ public class DroolsValidationService {
 
     private DroolsBlacklistErrorMessage checkAndGetBlackListedMessages(SearchImplementation blacklistedKeywordSearchImplementation, String stringToCheck, int lineIndexStart) {
 
-        String sanitizedRuleText = StringUtils.deleteWhitespace(stringToCheck);
+        String nonWhitespaceRuleText = StringUtils.deleteWhitespace(stringToCheck);
+        String sanitizedRuleText= nonWhitespaceRuleText.replaceAll("\"(\\\\.|[^\"\\\\])*\"|'(\\\\.|[^'\\\\])*'" ,"");
+
         List<SearchImplementation.MatchPosition> matches = blacklistedKeywordSearchImplementation.getMatches(sanitizedRuleText);
 
         if (!matches.isEmpty()) {

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

@@ -129,8 +129,7 @@ public class EntityDroolsExecutionService {
         });
 
         try {
-            completableFuture.orTimeout(settings.getDroolsExecutionTimeoutSecs(document.getNumberOfPages()), TimeUnit.SECONDS)
-                    .get();
+            completableFuture.get(settings.getDroolsExecutionTimeoutSecs(document.getNumberOfPages()), TimeUnit.SECONDS);
         } catch (ExecutionException e) {
             kieSession.dispose();
             if (e.getCause() instanceof TimeoutException) {
@@ -140,6 +139,8 @@ public class EntityDroolsExecutionService {
         } catch (InterruptedException e) {
             kieSession.dispose();
             throw new RuntimeException(e);
+        } catch (TimeoutException e) {
+            throw new DroolsTimeoutException(e, false, RuleFileType.ENTITY);
         }
 
         List<FileAttribute> resultingFileAttributes = getFileAttributes(kieSession);

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

@@ -32,7 +32,7 @@ import lombok.experimental.UtilityClass;
 public class RuleFileParser {
 
     private final static Pattern ruleIdentifierInCodeFinder = Pattern.compile(
-            "\\b(?:redact|apply|skip|remove|ignore|applyWithLineBreaks|applyWithReferences|skipWithReferences)\\s*\\(\"([a-zA-Z0-9]+.\\d+.\\d+)\",.*(?:, .*)?\\)");
+            "\\b(?:redact|apply|skip|remove|ignore|applyWithLineBreaks|applyWithReferences|skipWithReferences)\\s*\\(\\s*\"([a-zA-Z0-9]+.\\d+.\\d+)\"\\s*,\\s*.*(?:\\s*,\\s*.*)\\s*?\\)");
 
 
     @SneakyThrows
@@ -78,7 +78,8 @@ public class RuleFileParser {
                                              .map(GlobalDescr::getLine)
                                              .orElse(0),
                                      allQueries,
-                                     ruleClasses, customDroolsValidation);
+                                     ruleClasses,
+                                     customDroolsValidation);
     }
 
 

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

@@ -9,10 +9,12 @@ import java.util.Set;
 import java.util.stream.Collectors;
 
 import org.springframework.cache.annotation.Cacheable;
+import org.springframework.context.annotation.Import;
 import org.springframework.stereotype.Service;
 
 import com.iqser.red.service.persistence.service.v1.api.shared.model.analysislog.componentlog.ComponentLog;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.analysislog.entitylog.EntityLogEntry;
+import com.iqser.red.service.persistence.service.v1.api.shared.model.analysislog.entitylog.imported.ImportedLegalBases;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.analysislog.entitylog.imported.ImportedRedactions;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.analysislog.entitylog.imported.ImportedRedactionsPerPage;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.dossiertemplate.dossier.file.FileType;
@@ -147,6 +149,21 @@ public class RedactionStorageService {
     }
 
 
+
+    @Timed("redactmanager_getImportedLegalBases")
+    public ImportedLegalBases getImportedLegalBases(String dossierId, String fileId) {
+
+        try {
+            return storageService.readJSONObject(TenantContext.getTenantId(),
+                                                                             StorageIdUtils.getStorageId(dossierId, fileId, FileType.IMPORTED_LEGAL_BASES),
+                                                                             ImportedLegalBases.class);
+        } catch (StorageObjectDoesNotExist e) {
+            log.debug("Imported legal bases not available.");
+            return new ImportedLegalBases();
+        }
+    }
+
+
     @Deprecated(forRemoval = true)
     @Timed("redactmanager_getRedactionLog")
     public RedactionLog getRedactionLog(String dossierId, String fileId) {

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

@@ -18,7 +18,7 @@ public class MigratedIdsCollector implements Collector<MigrationEntity, Migrated
     @Override
     public Supplier<MigratedIds> supplier() {
 
-        return () -> new MigratedIds(new LinkedList<>(), Collections.emptyList());
+        return () -> new MigratedIds(new LinkedList<>(), Collections.emptyList(), Collections.emptyList());
     }
 
 

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

@@ -3,8 +3,10 @@ package com.iqser.red.service.redaction.v1.server.utils;
 import static java.lang.String.format;
 
 import java.awt.geom.Rectangle2D;
+import java.awt.geom.RectangularShape;
 import java.util.LinkedList;
 import java.util.List;
+import java.util.function.Predicate;
 import java.util.regex.Matcher;
 import java.util.regex.Pattern;
 import java.util.stream.IntStream;
@@ -154,14 +156,8 @@ public class RedactionSearchUtility {
      */
     public static TextRange findTextRangesOfAllLinesInYRange(double maxY, double minY, TextBlock textBlock) {
 
-        List<TextRange> lineBoundaries = IntStream.range(0, textBlock.numberOfLines()).boxed()
-                .map(textBlock::getLineTextRange)
-                .filter(lineBoundary -> isWithinYRange(maxY, minY, textBlock, lineBoundary))
-                .toList();
-        if (lineBoundaries.isEmpty()) {
-            return new TextRange(textBlock.getTextRange().start(), textBlock.getTextRange().start());
-        }
-        return TextRange.merge(lineBoundaries);
+        Predicate<TextRange> isWithinYRange = lineBoundary -> isWithinYRange(maxY, minY, textBlock, lineBoundary);
+        return filterLineBoundaries(textBlock, isWithinYRange);
     }
 
 
@@ -172,6 +168,49 @@ public class RedactionSearchUtility {
     }
 
 
+    /**
+     * Identifies all lines within a text block that have roughly the same vertical coordinates.
+     *
+     * @param maxY      The maximum Y-coordinate of the vertical range.
+     * @param minY      The minimum Y-coordinate of the vertical range.
+     * @param textBlock The text block containing the lines to be checked.
+     * @return A {@link TextRange} encompassing all lines within the specified Y-coordinate range.
+     */
+    public static TextRange findTextRangesOfAllLinesWithCloseYCoordinates(Double maxY, Double minY, TextBlock textBlock) {
+
+        double averageLineHeight = IntStream.range(0, textBlock.numberOfLines()).boxed()
+                .map(textBlock::getLineTextRange)
+                .flatMap((TextRange stringTextRange) -> textBlock.getPositions(stringTextRange)
+                        .stream())
+                .map(RectangularShape::getHeight)
+                .mapToDouble(Double::doubleValue).average()
+                .orElse(0);
+        Predicate<TextRange> hasCloseYRange = lineBoundary -> areYCoordinatesClose(maxY, minY, textBlock, lineBoundary, averageLineHeight);
+
+        return filterLineBoundaries(textBlock, hasCloseYRange);
+    }
+
+
+    private static boolean areYCoordinatesClose(Double maxY, Double minY, TextBlock textBlock, TextRange lineTextRange, double averageLineHeight) {
+
+        Rectangle2D lineBBox = RectangleTransformations.rectangle2DBBox(textBlock.getPositions(lineTextRange));
+        return Math.abs(lineBBox.getMinY() - minY) <= averageLineHeight && Math.abs(maxY - lineBBox.getMaxY()) <= averageLineHeight;
+    }
+
+
+    private static TextRange filterLineBoundaries(TextBlock textBlock, Predicate<TextRange> textRangePredicate) {
+
+        List<TextRange> lineBoundaries = IntStream.range(0, textBlock.numberOfLines()).boxed()
+                .map(textBlock::getLineTextRange)
+                .filter(textRangePredicate)
+                .toList();
+        if (lineBoundaries.isEmpty()) {
+            return new TextRange(textBlock.getTextRange().start(), textBlock.getTextRange().start());
+        }
+        return TextRange.merge(lineBoundaries);
+    }
+
+
     /**
      * Finds TextRanges matching a regex pattern within a TextBlock.
      *

redaction-service-v1/redaction-service-server-v1/src/main/resources/application.yml

@@ -16,6 +16,9 @@ project.version: 1.0-SNAPSHOT
 server:
   port: 8080
 
+lifecycle:
+  base-package: com.iqser.red.service.redaction
+
 spring:
   application:
     name: redaction-service

redaction-service-v1/redaction-service-server-v1/src/main/resources/date_formats.txt

@@ -14,6 +14,8 @@ dd MMMM yyyy
 d MMMM yyyy
 MMMM dd, yyyy
 MMMM d, yyyy
+MMMM, d yyyy
+MMMM d,yyyy
 dd.MM.yyyy
 d.MM.yyyy
 yyyy/MM/dd
@@ -28,6 +30,7 @@ dd['.'] MMM yyyy
 d['.'] MMM yyyy
 dd['th']['st']['nd']['rd'] 'of' MMMM, yyyy
 d['th']['st']['nd']['rd'] 'of' MMMM, yyyy
+d['st']['nd']['rd']['th'] MMMM yyyy
 MMMM dd['th']['st']['nd']['rd'], yyyy
 MMMM d['th']['st']['nd']['rd'], yyyy
 yyyy, MMMM dd
@@ -72,3 +75,5 @@ dd.MM.yy
 d.MM.yy
 dd MMM. yyyy
 d MMM. yyyy
+d-MMMM-yyyy
+dd-MMMM-yyyy

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

@@ -114,13 +114,14 @@ public abstract class AbstractRedactionIntegrationTest {
     public static final String PII_TYPE_ID = DICTIONARY_PII + ":" + TEST_DOSSIER_TEMPLATE_ID;
     public static final String TEST_METHOD_TYPE_ID = TEST_METHOD_INDICATOR + ":" + TEST_DOSSIER_TEMPLATE_ID;
     public static final String PUBLISHED_INFORMATION_TYPE_ID = PUBLISHED_INFORMATION_INDICATOR + ":" + TEST_DOSSIER_TEMPLATE_ID;
-    public static final String DOSSIER_PUBLISHED_INFORMATION_TYPE_ID = PUBLISHED_INFORMATION_TYPE_ID+ ":" + TEST_DOSSIER_ID;
+    public static final String DOSSIER_PUBLISHED_INFORMATION_TYPE_ID = PUBLISHED_INFORMATION_TYPE_ID + ":" + TEST_DOSSIER_ID;
     public static final String MUST_REDACT_TYPE_ID = MUST_REDACT_INDICATOR + ":" + TEST_DOSSIER_TEMPLATE_ID;
     public static final String HINT_ONLY_TYPE_ID = HINT_ONLY_INDICATOR + ":" + TEST_DOSSIER_TEMPLATE_ID;
     public static final String REDACTION_TYPE_ID = REDACTION_INDICATOR + ":" + TEST_DOSSIER_TEMPLATE_ID;
     public static final String NO_REDACTION_TYPE_ID = NO_REDACTION_INDICATOR + ":" + TEST_DOSSIER_TEMPLATE_ID;
     public static final String SPONSOR_TYPE_ID = DICTIONARY_SPONSOR + ":" + TEST_DOSSIER_TEMPLATE_ID;
     public static final String AUTHOR_TYPE_ID = DICTIONARY_AUTHOR + ":" + TEST_DOSSIER_TEMPLATE_ID;
+    public static final String DOSSIER_AUTHOR_TYPE_ID = AUTHOR_TYPE_ID + ":" + TEST_DOSSIER_ID;
     public static final String ADDRESS_TYPE_ID = DICTIONARY_ADDRESS + ":" + TEST_DOSSIER_TEMPLATE_ID;
     public static final String VERTEBRATE_TYPE_ID = VERTEBRATE_INDICATOR + ":" + TEST_DOSSIER_TEMPLATE_ID;
 
@@ -250,8 +251,10 @@ public abstract class AbstractRedactionIntegrationTest {
                                                                                                                                                  true));
         when(dictionaryClient.getDictionaryForType(IMPORTED_REDACTION_TYPE_ID, version)).then((Answer<Type>) invocation -> getDictionaryResponse(IMPORTED_REDACTION_INDICATOR,
                                                                                                                                                  true));
-        when(dictionaryClient.getDictionaryForType(DOSSIER_PUBLISHED_INFORMATION_TYPE_ID, version)).then((Answer<Type>) invocation -> getDictionaryResponse(PUBLISHED_INFORMATION_INDICATOR,
-                                                                                                                                                 true));
+        when(dictionaryClient.getDictionaryForType(DOSSIER_PUBLISHED_INFORMATION_TYPE_ID, version)).then((Answer<Type>) invocation -> getDictionaryResponse(
+                PUBLISHED_INFORMATION_INDICATOR,
+                true));
+        when(dictionaryClient.getDictionaryForType(DOSSIER_AUTHOR_TYPE_ID, version)).then((Answer<Type>) invocation -> getDictionaryResponse(DICTIONARY_AUTHOR, true));
 
     }
 
@@ -350,6 +353,7 @@ public abstract class AbstractRedactionIntegrationTest {
                                 .collect(Collectors.toSet()));
         dossierDictionary.put(IMPORTED_REDACTION_INDICATOR, new ArrayList<>());
         dossierDictionary.put(PUBLISHED_INFORMATION_INDICATOR, new ArrayList<>());
+        dossierDictionary.put(DICTIONARY_AUTHOR, new ArrayList<>());
 
         falsePositive.computeIfAbsent(DICTIONARY_PII, v -> new ArrayList<>())
                 .addAll(ResourceLoader.load("dictionaries/PII_false_positive.txt")

redaction-service-v1/redaction-service-server-v1/src/test/java/com/iqser/red/service/redaction/v1/server/AnalysisEnd2EndTest.java

@@ -9,6 +9,7 @@ import static org.mockito.Mockito.when;
 
 import java.io.File;
 import java.io.FileInputStream;
+import java.io.IOException;
 import java.nio.file.Files;
 import java.nio.file.Path;
 import java.util.Arrays;
@@ -17,11 +18,13 @@ import java.util.HashMap;
 import java.util.HashSet;
 import java.util.List;
 import java.util.Map;
+import java.util.Objects;
 import java.util.Optional;
 import java.util.Set;
 import java.util.UUID;
 import java.util.concurrent.atomic.AtomicInteger;
 import java.util.stream.Collectors;
+import java.util.stream.Stream;
 import java.util.zip.GZIPInputStream;
 
 import org.junit.jupiter.api.BeforeEach;
@@ -56,7 +59,6 @@ import com.iqser.red.service.redaction.v1.server.service.AnalyzeService;
 import com.iqser.red.service.redaction.v1.server.service.DictionaryService;
 import com.iqser.red.service.redaction.v1.server.storage.RedactionStorageService;
 import com.iqser.red.service.redaction.v1.server.testcontainers.MongoDBTestContainer;
-import com.iqser.red.service.redaction.v1.server.utils.exception.NotFoundException;
 import com.iqser.red.storage.commons.service.StorageService;
 import com.knecon.fforesight.mongo.database.commons.liquibase.TenantMongoLiquibaseExecutor;
 import com.knecon.fforesight.mongo.database.commons.service.MongoConnectionProvider;
@@ -80,7 +82,25 @@ import lombok.extern.slf4j.Slf4j;
  * This way you can recreate what is happening on the stack almost exactly.
  */ public class AnalysisEnd2EndTest {
 
-    Path dossierTemplateToUse = Path.of("/home/kschuettler/iqser/fforesight/dossier-templates-v2/dev/LayoutParsingDatasetEvaluation"); // Add your dossier-template here
+    // These files will be uploaded if they are present in the folder
+    public static final Set<FileType> ENDINGS_TO_UPLOAD = Set.of(FileType.ORIGIN,
+                                                                 FileType.DOCUMENT_PAGES,
+                                                                 FileType.DOCUMENT_POSITION,
+                                                                 FileType.DOCUMENT_STRUCTURE,
+                                                                 FileType.DOCUMENT_TEXT,
+                                                                 FileType.IMAGE_INFO,
+                                                                 FileType.NER_ENTITIES,
+                                                                 FileType.TABLES,
+                                                                 FileType.IMPORTED_REDACTIONS);
+
+    // These files must be present in the folder or the test will skip the file
+    public static final Set<FileType> REQUIRED_FILES = Set.of(FileType.ORIGIN,
+                                                              FileType.DOCUMENT_PAGES,
+                                                              FileType.DOCUMENT_POSITION,
+                                                              FileType.DOCUMENT_STRUCTURE,
+                                                              FileType.DOCUMENT_TEXT);
+
+    Path dossierTemplateToUse = Path.of("/home/kschuettler/Downloads/mainBodyFailed/DOSSIER_TEMPLATE"); // Add your dossier-template here
     ObjectMapper mapper = ObjectMapperFactory.create();
     final String TENANT_ID = "tenant";
 
@@ -121,7 +141,7 @@ import lombok.extern.slf4j.Slf4j;
     @SneakyThrows
     public void runAnalysisEnd2End() {
 
-        String folder = "/home/kschuettler/Dokumente/analysisend2end/file1"; // Should contain all files from minio directly, still zipped. Can contain multiple files.
+        String folder = "/home/kschuettler/Downloads/mainBodyFailed/728d0af4-f4c4-4bc9-acf8-7d2632b02962/"; // Should contain all files from minio directly, still zipped. Can contain multiple files.
 
         Path absoluteFolderPath;
         if (folder.startsWith("files")) { // if it starts with "files" it is most likely in the resources folder, else it should be an absolute path
@@ -133,11 +153,14 @@ import lombok.extern.slf4j.Slf4j;
 
         log.info("Starting end2end analyses for all distinct filenames in folder: {}", folder);
         List<AnalyzeRequest> analyzeRequests = prepareStorageForFolder(absoluteFolderPath);
-        log.info("Found {} distinct fileIds", analyzeRequests.size());
+        log.info("Found {} distinct fileIds with all required files", analyzeRequests.size());
         for (int i = 0; i < analyzeRequests.size(); i++) {
             AnalyzeRequest analyzeRequest = analyzeRequests.get(i);
+            log.info("----------------------------------------------------------------------------------");
             log.info("{}/{}: Starting analysis for file {}", i + 1, analyzeRequests.size(), analyzeRequest.getFileId());
             analyzeService.analyze(analyzeRequest);
+            log.info("----------------------------------------------------------------------------------");
+            log.info("");
         }
     }
 
@@ -188,22 +211,36 @@ import lombok.extern.slf4j.Slf4j;
     @SneakyThrows
     private List<AnalyzeRequest> prepareStorageForFolder(Path folder) {
 
-        return Files.list(folder)
-                .map(this::parseFileId)
-                .distinct()
+        return findOriginFiles(folder).stream()
                 .map(fileId -> prepareStorageForFile(fileId, folder))
+                .filter(Optional::isPresent)
+                .map(Optional::get)
                 .toList();
     }
 
 
-    private String parseFileId(Path path) {
+    private Set<String> findOriginFiles(Path folder) throws IOException {
 
-        return path.getFileName().toString().split("\\.")[0];
+        return Files.walk(folder)
+                .map(this::parseFileName)
+                .filter(Objects::nonNull)
+                .collect(Collectors.toSet());
+    }
+
+
+    private String parseFileName(Path path) {
+
+        String suffix = ".ORIGIN.pdf";
+        if (!path.getFileName().toString().endsWith(suffix)) {
+            return null;
+        }
+
+        return path.getFileName().toString().replace(suffix, "");
     }
 
 
     @SneakyThrows
-    private AnalyzeRequest prepareStorageForFile(String fileId, Path folder) {
+    private Optional<AnalyzeRequest> prepareStorageForFile(String fileName, Path folder) {
 
         AnalyzeRequest request = new AnalyzeRequest();
         request.setDossierId(UUID.randomUUID().toString());
@@ -211,53 +248,65 @@ import lombok.extern.slf4j.Slf4j;
         request.setDossierTemplateId(testDossierTemplate.id);
         request.setAnalysisNumber(-1);
 
-        Path manualRedactionFile = folder.resolve(fileId + ".MANUAL_REDACTIONS.json");
+        Path manualRedactionFile = folder.resolve(fileName + ".MANUAL_REDACTIONS.json");
         if (Files.exists(manualRedactionFile)) {
-            request.setManualRedactions(mapper.readValue(manualRedactionFile.toFile(), ManualRedactions.class));
+            request.setManualRedactions(parseManualRedactions(manualRedactionFile));
         } else {
             request.setManualRedactions(new ManualRedactions());
         }
 
-        Set<FileType> endingsToUpload = Set.of("ORIGIN",
-                                               "DOCUMENT_PAGES",
-                                               "DOCUMENT_POSITION",
-                                               "DOCUMENT_STRUCTURE",
-                                               "DOCUMENT_TEXT",
-                                               "IMAGE_INFO",
-                                               "NER_ENTITIES",
-                                               "TABLES",
-                                               "IMPORTED_REDACTIONS")
-                .stream()
-                .map(FileType::valueOf)
-                .collect(Collectors.toSet());
-
-        Set<FileType> uploadedFileTypes = Files.walk(folder)
-                .filter(path -> path.toFile().isFile())
-                .filter(path -> parseFileTypeFromPath(path).map(endingsToUpload::contains)
-                        .orElse(false))
-                .map(filePath -> uploadFile(filePath, request))
-                .filter(Optional::isPresent)
-                .map(Optional::get)
+        Set<FileType> uploadedFileTypes = findFilesToUpload(fileName, folder, ENDINGS_TO_UPLOAD).map(filePath -> uploadFile(filePath, request))
+                .map(FileToUpload::fileType)
                 .collect(Collectors.toUnmodifiableSet());
 
-        Set<FileType> missingFileTypes = Sets.difference(endingsToUpload, uploadedFileTypes);
+        Set<FileType> missingFileTypes = Sets.difference(REQUIRED_FILES, uploadedFileTypes);
+
         if (!missingFileTypes.isEmpty()) {
             log.error("Folder {} is missing files of type {}",
                       folder.toFile(),
                       missingFileTypes.stream()
                               .map(Enum::toString)
                               .collect(Collectors.joining(", ")));
-            throw new NotFoundException("Not all required file types are present.");
+            return Optional.empty();
         }
-        return request;
+        return Optional.of(request);
     }
 
 
-    private static Optional<FileType> parseFileTypeFromPath(Path path) {
+    private static Stream<FileToUpload> findFilesToUpload(String fileName, Path folder, Set<FileType> endingsToUpload) throws IOException {
+
+        return Files.walk(folder)
+                .filter(path -> path.toFile().isFile())
+                .map(path -> parseFileTypeFromPath(path, fileName, endingsToUpload))
+                .filter(Optional::isPresent)
+                .map(Optional::get);
+    }
+
+
+    private ManualRedactions parseManualRedactions(Path manualRedactionFile) {
 
-        String fileType = path.getFileName().toString().split("\\.")[1];
         try {
-            return Optional.of(FileType.valueOf(fileType));
+            return mapper.readValue(manualRedactionFile.toFile(), ManualRedactions.class);
+        } catch (IOException e) {
+            log.error("Could not parse manual redactions");
+            return new ManualRedactions();
+        }
+    }
+
+
+    private static Optional<FileToUpload> parseFileTypeFromPath(Path path, String fileName, Set<FileType> endingsToUpload) {
+
+        if (!path.getFileName().toString().startsWith(fileName)) {
+            return Optional.empty();
+        }
+
+        try {
+            String fileTypeString = path.getFileName().toString().split("\\.")[1];
+            FileType fileType = FileType.valueOf(fileTypeString);
+            if (!endingsToUpload.contains(fileType)) {
+                return Optional.empty();
+            }
+            return Optional.of(new FileToUpload(path, fileType));
         } catch (IllegalArgumentException e) {
             return Optional.empty();
         }
@@ -265,21 +314,26 @@ import lombok.extern.slf4j.Slf4j;
 
 
     @SneakyThrows
-    private Optional<FileType> uploadFile(Path path, AnalyzeRequest request) {
+    private FileToUpload uploadFile(FileToUpload fileToUpload, AnalyzeRequest request) {
 
-        Optional<FileType> fileType = parseFileTypeFromPath(path);
-        if (fileType.isEmpty()) {
-            return Optional.empty();
+        if (fileToUpload.path().getFileName().toString().endsWith(".gz")) {
+            try (var fis = new FileInputStream(fileToUpload.path().toFile()); var in = new GZIPInputStream(fis);) {
+                storageService.storeObject(TENANT_ID,
+                                           RedactionStorageService.StorageIdUtils.getStorageId(request.getDossierId(), request.getFileId(), fileToUpload.fileType()),
+                                           in);
+            }
+        } else {
+            try (var in = new FileInputStream(fileToUpload.path().toFile())) {
+                storageService.storeObject(TENANT_ID,
+                                           RedactionStorageService.StorageIdUtils.getStorageId(request.getDossierId(), request.getFileId(), fileToUpload.fileType()),
+                                           in);
+            }
         }
-        try (var fis = new FileInputStream(path.toFile()); var in = new GZIPInputStream(fis);) {
-            storageService.storeObject(TENANT_ID, RedactionStorageService.StorageIdUtils.getStorageId(request.getDossierId(), request.getFileId(), fileType.get()), in);
-
-        }
-        return fileType;
+        return fileToUpload;
     }
 
 
-    private class TestDossierTemplate {
+    public class TestDossierTemplate {
 
         String id;
         Dictionary testDictionary;
@@ -379,4 +433,8 @@ import lombok.extern.slf4j.Slf4j;
 
     }
 
+    private record FileToUpload(Path path, FileType fileType) {
+
+    }
+
 }

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

@@ -174,6 +174,16 @@ public class DocumineFloraTest extends AbstractRedactionIntegrationTest {
         expectedDates.add("03/08/1992");
         expectedDates.add("13/08/1992");
         expectedDates.add("27/02/1992");
+        expectedDates.add("27/10/1989");
+        expectedDates.add("07/10/1989");
+        expectedDates.add("21/08/1998");
+        expectedDates.add("02/08/1998");
+        expectedDates.add("01/05/1988");
+        expectedDates.add("02/06/2003");
+        expectedDates.add("03/09/2005");
+        expectedDates.add("06/09/2005");
+        expectedDates.add("17/08/2005");
+        expectedDates.add("22/08/2035");
 
         String dates = experimentalDates.getComponentValues()
                 .get(0).getValue();

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

@@ -107,7 +107,7 @@ public class MigrationIntegrationTest extends BuildDocumentIntegrationTest {
     @SneakyThrows
     public void testSave() {
 
-        MigratedIds ids = new MigratedIds(new LinkedList<>(), null);
+        MigratedIds ids = new MigratedIds(new LinkedList<>(), null, null);
         ids.addMapping("123", "321");
         ids.addMapping("123", "321");
         ids.addMapping("123", "321");

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

@@ -10,6 +10,7 @@ import java.time.OffsetDateTime;
 import java.util.ArrayList;
 import java.util.List;
 import java.util.Set;
+import java.util.UUID;
 import java.util.stream.Stream;
 
 import org.junit.jupiter.api.BeforeEach;
@@ -25,24 +26,30 @@ import org.springframework.context.annotation.Configuration;
 import org.springframework.context.annotation.FilterType;
 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.iqser.red.commons.jackson.ObjectMapperFactory;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.AnalyzeRequest;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.AnalyzeResult;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.RuleFileType;
+import com.iqser.red.service.persistence.service.v1.api.shared.model.analysislog.entitylog.Engine;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.analysislog.entitylog.EntityLog;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.analysislog.entitylog.EntityLogEntry;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.analysislog.entitylog.EntryState;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.analysislog.entitylog.EntryType;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.annotations.ManualRedactions;
+import com.iqser.red.service.persistence.service.v1.api.shared.model.annotations.Rectangle;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.annotations.entitymapped.IdRemoval;
+import com.iqser.red.service.persistence.service.v1.api.shared.model.annotations.entitymapped.ManualRedactionEntry;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.common.JSONPrimitive;
+import com.iqser.red.service.persistence.service.v1.api.shared.model.dossiertemplate.dossier.file.FileType;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.dossiertemplate.type.Type;
 import com.iqser.red.service.redaction.v1.server.annotate.AnnotateRequest;
 import com.iqser.red.service.redaction.v1.server.annotate.AnnotateResponse;
 import com.iqser.red.service.redaction.v1.server.redaction.utils.OsUtils;
 import com.iqser.red.service.redaction.v1.server.service.DictionaryService;
+import com.iqser.red.service.redaction.v1.server.storage.RedactionStorageService;
 import com.iqser.red.storage.commons.StorageAutoConfiguration;
 import com.iqser.red.storage.commons.service.StorageService;
 import com.iqser.red.storage.commons.utils.FileSystemBackedStorageService;
@@ -50,6 +57,8 @@ import com.knecon.fforesight.service.layoutparser.internal.api.queue.LayoutParsi
 import com.knecon.fforesight.service.layoutparser.processor.LayoutParsingServiceProcessorConfiguration;
 import com.knecon.fforesight.tenantcommons.TenantContext;
 
+import lombok.SneakyThrows;
+
 @ExtendWith(SpringExtension.class)
 @SpringBootTest(classes = Application.class, webEnvironment = SpringBootTest.WebEnvironment.RANDOM_PORT)
 @Import(RedactionIntegrationTest.RedactionIntegrationTestConfiguration.class)
@@ -103,6 +112,17 @@ public class RedactionAcceptanceTest extends AbstractRedactionIntegrationTest {
                                                                                                        .isRecommendation(recommendationTypeMap.get(DOSSIER_REDACTIONS_INDICATOR))
                                                                                                        .rank(rankTypeMap.get(DOSSIER_REDACTIONS_INDICATOR))
                                                                                                        .build(),
+                                                                                               Type.builder()
+                                                                                                       .id(DOSSIER_AUTHOR_TYPE_ID)
+                                                                                                       .type(DICTIONARY_AUTHOR)
+                                                                                                       .dossierTemplateId(TEST_DOSSIER_TEMPLATE_ID)
+                                                                                                       .dossierId(TEST_DOSSIER_ID)
+                                                                                                       .hexColor("#ffe184")
+                                                                                                       .isHint(hintTypeMap.get(DICTIONARY_AUTHOR))
+                                                                                                       .isCaseInsensitive(caseInSensitiveMap.get(DICTIONARY_AUTHOR))
+                                                                                                       .isRecommendation(recommendationTypeMap.get(DICTIONARY_AUTHOR))
+                                                                                                       .rank(rankTypeMap.get(DICTIONARY_AUTHOR))
+                                                                                                       .build(),
                                                                                                Type.builder()
                                                                                                        .id(DOSSIER_PUBLISHED_INFORMATION_TYPE_ID)
                                                                                                        .type(PUBLISHED_INFORMATION_INDICATOR)
@@ -158,10 +178,10 @@ public class RedactionAcceptanceTest extends AbstractRedactionIntegrationTest {
 
         var publishedInformationEntry1 = findEntityByTypeAndValue(entityLog, "published_information", "Oxford University Press").findFirst()
                 .orElseThrow();
-        assertThat(publishedInformationEntry1.getSection().startsWith("Paragraph:"));
+        assertThat(publishedInformationEntry1.getSection()).startsWith("Paragraph:");
         var asyaLyon1 = findEntityByTypeAndValueAndSectionNumber(entityLog, "CBI_author", "Asya Lyon", publishedInformationEntry1.getContainingNodeId()).findFirst()
                 .orElseThrow();
-        assertThat(asyaLyon1.getSection().startsWith("Paragraph:"));
+        assertThat(asyaLyon1.getSection()).startsWith("Paragraph:");
         assertEquals(EntryState.SKIPPED, asyaLyon1.getState());
 
         var idRemoval = buildIdRemoval(publishedInformationEntry1.getId());
@@ -212,10 +232,10 @@ public class RedactionAcceptanceTest extends AbstractRedactionIntegrationTest {
 
         var publishedInformationEntry1 = findEntityByTypeAndValue(entityLog, "published_information", "Oxford University Press").findFirst()
                 .orElseThrow();
-        assertThat(publishedInformationEntry1.getSection().startsWith("Paragraph:"));
+        assertThat(publishedInformationEntry1.getSection()).startsWith("Paragraph:");
         var asyaLyon1 = findEntityByTypeAndValueAndSectionNumber(entityLog, "CBI_author", "Asya Lyon", publishedInformationEntry1.getContainingNodeId()).findFirst()
                 .orElseThrow();
-        assertThat(publishedInformationEntry1.getSection().startsWith("Paragraph:"));
+        assertThat(publishedInformationEntry1.getSection()).startsWith("Paragraph:");
         assertEquals(EntryState.SKIPPED, asyaLyon1.getState());
 
         var idRemoval = buildIdRemoval(publishedInformationEntry1.getId());
@@ -244,6 +264,7 @@ public class RedactionAcceptanceTest extends AbstractRedactionIntegrationTest {
         assertThat(dictionary.get(PUBLISHED_INFORMATION_INDICATOR).contains("Press")).isFalse();
     }
 
+
     @Test
     public void testPublishedInformationRemovalAtDossierLevel() throws IOException {
 
@@ -348,7 +369,7 @@ public class RedactionAcceptanceTest extends AbstractRedactionIntegrationTest {
         var entityLog = redactionStorageService.getEntityLog(TEST_DOSSIER_ID, TEST_FILE_ID);
 
         var desireeEtAl = findEntityByTypeAndValue(entityLog, "CBI_author", "Desiree").filter(e -> e.getEntryType().equals(EntryType.ENTITY))
-                .filter(e -> e.getMatchedRule().startsWith("CBI.16"))
+                .filter(e -> e.getMatchedRule().startsWith("CBI.7"))
                 .findAny()
                 .orElseThrow();
         IdRemoval removal = buildIdRemoval(desireeEtAl.getId());
@@ -365,6 +386,75 @@ public class RedactionAcceptanceTest extends AbstractRedactionIntegrationTest {
     }
 
 
+    @Test
+    @SneakyThrows
+    void testNerEntitiesAfterReanalysis() {
+
+        String EFSA_SANITISATION_RULES = loadFromClassPath("drools/efsa_sanitisation.drl");
+        when(rulesClient.getRules(TEST_DOSSIER_TEMPLATE_ID, RuleFileType.ENTITY)).thenReturn(JSONPrimitive.of(EFSA_SANITISATION_RULES));
+
+        ClassPathResource responseJson = new ClassPathResource("files/new/SYNGENTA_EFSA_sanitisation_GFL_v1 3.NER_ENTITIES.json");
+        storageService.storeObject(TenantContext.getTenantId(),
+                                   RedactionStorageService.StorageIdUtils.getStorageId(TEST_DOSSIER_ID, TEST_FILE_ID, FileType.NER_ENTITIES),
+                                   responseJson.getInputStream());
+
+        String pdfFile = "files/new/SYNGENTA_EFSA_sanitisation_GFL_v1 3.pdf";
+
+        AnalyzeRequest request = uploadFileToStorage(pdfFile);
+
+        analyzeDocumentStructure(LayoutParsingType.REDACT_MANAGER, request);
+        request.setAnalysisNumber(1);
+        dossierDictionary.put(DICTIONARY_AUTHOR, new ArrayList<>());
+        mockDictionaryCalls(0L);
+
+        analyzeService.analyze(request);
+
+        var entityLog = redactionStorageService.getEntityLog(TEST_DOSSIER_ID, TEST_FILE_ID);
+
+        String nerValue = "Osip S.";
+        var nerEntity = findEntityByTypeAndValue(entityLog, DICTIONARY_AUTHOR, nerValue).findFirst()
+                .orElseThrow();
+        assertThat(nerEntity.getEngines()).contains(Engine.NER);
+
+        String dictionaryAddValue = "cooperation";
+        ManualRedactionEntry manualRedactionEntry = ManualRedactionEntry.builder()
+                .value(dictionaryAddValue)
+                .type(DICTIONARY_AUTHOR)
+                .user("user")
+                .addToDossierDictionary(true)
+                .positions(List.of(Rectangle.builder().topLeftX(180.748f).topLeftY(546.564f).width(56.592f).height(15.408f).page(1).build()))
+                .type("dossier_redaction")
+                .fileId(TEST_FILE_ID)
+                .requestDate(OffsetDateTime.now())
+                .annotationId(UUID.randomUUID().toString())
+                .build();
+        request.setManualRedactions(ManualRedactions.builder().entriesToAdd(Set.of(manualRedactionEntry)).build());
+
+        request.setAnalysisNumber(2);
+        dossierDictionary.get(DICTIONARY_AUTHOR).add(dictionaryAddValue);
+        reanlysisVersions.put(dictionaryAddValue, 2L);
+        when(dictionaryClient.getVersionForDossier(TEST_DOSSIER_ID)).thenReturn(2L);
+        mockDictionaryCalls(1L);
+
+        AnalyzeResult reanalyzeResult = analyzeService.reanalyze(request);
+
+        entityLog = redactionStorageService.getEntityLog(TEST_DOSSIER_ID, TEST_FILE_ID);
+
+        EntityLogEntry entityLogEntryAdded = entityLog.getEntityLogEntry()
+                .stream()
+                .filter(entityLogEntry -> entityLogEntry.getValue().equals(dictionaryAddValue))
+                .findFirst()
+                .get();
+        assertEquals(EntryState.APPLIED, entityLogEntryAdded.getState());
+
+        nerEntity = findEntityByTypeAndValue(entityLog, DICTIONARY_AUTHOR, nerValue).findFirst()
+                .orElseThrow();
+        assertThat(nerEntity.getEngines()).contains(Engine.NER);
+        dossierDictionary.get(DICTIONARY_AUTHOR).remove(dictionaryAddValue);
+
+    }
+
+
     private static IdRemoval buildIdRemoval(String id) {
 
         return IdRemoval.builder().annotationId(id).user("user").requestDate(OffsetDateTime.now()).fileId(TEST_FILE_ID).build();

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

@@ -43,7 +43,17 @@ public class DateConverterTest {
                                                          "28 March 2018 (animal 1 - 5000 mg/kg bw)",
                                                          "28 March 2018 (animal1 - 5000 mg/kg bw)",
                                                          "28 August 2018 (animal 1)",
-                                                         "31 August 2018 (animal 1)");
+                                                         "31 August 2018 (animal 1)",
+                                                         "October, 27 1989",
+                                                         "October, 7 1989",
+                                                         "August 21,1998",
+                                                         "August 2,1998",
+                                                         "1st May 1988",
+                                                         "2nd June 2003",
+                                                         "3rd September 2005",
+                                                         "6th September 2005",
+                                                         "17th August 2005",
+                                                         "22nd August 2035");
 
         for (String dateStr : goldenStandardDates) {
             Optional<Date> parsedDate = DateConverter.parseDate(dateStr);

redaction-service-v1/redaction-service-server-v1/src/test/java/com/iqser/red/service/redaction/v1/server/drools/files/management/services/DroolsValidationServiceTest.java

@@ -361,7 +361,6 @@ class DroolsValidationServiceTest {
     }
 
 
-
     @Test
     @SneakyThrows
     void testRulesWithBlacklistedKeyword() {
@@ -379,16 +378,16 @@ class DroolsValidationServiceTest {
         String rulesString1 = rulesString.substring(0, indexGlobalStart) + importTenantContext + rulesString.substring(indexGlobalStart);
 
         String evilRulePart1 = """
-                                
+                
                 //------------------------------------ All the evil rules ------------------------------------
-
+                
                 // Rule unit: EV.1
                 rule "EV.1.0: Remove duplicate FileAttributes but also do very evil things"
                     salience 999
                     when
                         $fileAttribute: FileAttribute($label: label, $value: value)
                         $duplicate: FileAttribute(this != $fileAttribute, label == $label, value == $value)
-                        """;
+                """;
         String evilRulePart2 = """
                     then
                         retract($duplicate);
@@ -408,11 +407,13 @@ class DroolsValidationServiceTest {
                 .forEach(System.out::println);
         assertFalse(droolsValidation.isCompiled());
         assertEquals(2, droolsValidation.getBlacklistErrorMessages().size());
-        assertEquals(1, droolsValidation.getBlacklistErrorMessages()
+        assertEquals(1,
+                     droolsValidation.getBlacklistErrorMessages()
                              .get(0).getBlacklistedKeywords().size());
         assertTrue(droolsValidation.getBlacklistErrorMessages()
                            .get(0).getBlacklistedKeywords().contains("TenantContext"));
-        assertEquals(2, droolsValidation.getBlacklistErrorMessages()
+        assertEquals(2,
+                     droolsValidation.getBlacklistErrorMessages()
                              .get(1).getBlacklistedKeywords().size());
         assertTrue(droolsValidation.getBlacklistErrorMessages()
                            .get(1).getBlacklistedKeywords().contains("TenantContext"));
@@ -429,14 +430,39 @@ class DroolsValidationServiceTest {
                 .forEach(System.out::println);
         assertFalse(droolsValidation2.isCompiled());
         assertEquals(2, droolsValidation2.getBlacklistErrorMessages().size());
-        assertEquals(1, droolsValidation2.getBlacklistErrorMessages()
+        assertEquals(1,
+                     droolsValidation2.getBlacklistErrorMessages()
                              .get(0).getBlacklistedKeywords().size());
         assertTrue(droolsValidation2.getBlacklistErrorMessages()
                            .get(0).getBlacklistedKeywords().contains("TenantContext"));
-        assertEquals(1, droolsValidation2.getBlacklistErrorMessages()
+        assertEquals(1,
+                     droolsValidation2.getBlacklistErrorMessages()
                              .get(1).getBlacklistedKeywords().size());
         assertTrue(droolsValidation2.getBlacklistErrorMessages()
                            .get(1).getBlacklistedKeywords().contains("System."));
     }
 
+
+    @Test
+    void assertRuleIdentifierDoesNotMatch() {
+
+        String ruleString = RuleManagementResources.getBaseRuleFileString() + """
+                rule "CBI.0.0: Redact CBI Authors (non vertebrate Study)"
+                    when
+                        not FileAttribute(label == "Vertebrate Study", value soundslike "Yes" || value.toLowerCase() == "y")
+                        $entity: TextEntity(type() == "CBI_author", dictionaryEntry)
+                    then
+                        $entity.redact(
+                        "CBI.1.0", 
+                        "Author found", 
+                        "Article 39(e)(3) of Regulation (EC) No 178/2002"
+                        );
+                    end
+                """;
+
+        RuleFileBluePrint ruleFileBluePrint = RuleFileParser.buildBluePrintFromRulesString(ruleString);
+
+        assertFalse(ruleFileBluePrint.getDroolsValidation().isCompiled());
+    }
+
 }

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

@@ -129,56 +129,54 @@ rule "CBI.2.0: Do not redact genitive CBI Author"
 
 
 // Rule unit: CBI.7
-rule "CBI.7.0: Do not redact Names and Addresses if published information found in Section without tables"
+rule "CBI.7.0: Add CBI_author with \"et al.\" RegEx"
+    agenda-group "LOCAL_DICTIONARY_ADDS"
     when
-        $section: Section(!hasTables(),
-                          hasEntitiesOfType("published_information"),
-                          (hasEntitiesOfType("CBI_author") || hasEntitiesOfType("CBI_address")))
+        $section: Section(containsString("et al."))
     then
-        $section.getEntitiesOfType(List.of("CBI_author", "CBI_address"))
-            .forEach(redactionEntity -> {
-                redactionEntity.skipWithReferences(
-                        "CBI.7.0",
-                        "Published Information found in section",
-                        $section.getEntitiesOfType("published_information")
-                );
+        entityCreationService.byRegex("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", "CBI_author", EntityType.ENTITY, 1, $section)
+            .forEach(entity -> {
+                entity.redact("CBI.7.0", "Author found by \"et al\" regex", "Reg (EC) No 1107/2009 Art. 63 (2g)");
+                dictionary.recommendEverywhere(entity);
             });
     end
 
-rule "CBI.7.1: Do not redact Names and Addresses if published information found in same table row"
+rule "CBI.7.1: Add CBI_author with \"et al.\" RegEx (non vertebrate study)"
+    agenda-group "LOCAL_DICTIONARY_ADDS"
     when
-        $table: Table(hasEntitiesOfType("published_information"), hasEntitiesOfType("CBI_author") || hasEntitiesOfType("CBI_address"))
-        $cellsWithPublishedInformation: TableCell() from $table.streamTableCellsWhichContainType("published_information").toList()
-        $tableCell: TableCell(row == $cellsWithPublishedInformation.row) from $table.streamTableCells().toList()
-        $authorOrAddress: TextEntity(type() == "CBI_author" || type() == "CBI_address", active()) from $tableCell.getEntities()
+        not FileAttribute(label == "Vertebrate Study", value soundslike "Yes" || value.toLowerCase() == "y")
+        $section: Section(containsString("et al."))
     then
-        $authorOrAddress.skipWithReferences("CBI.7.1", "Published Information found in row", $table.getEntitiesOfTypeInSameRow("published_information", $authorOrAddress));
-    end
-
-rule "CBI.7.2: Do not redact PII if published information found in Section without tables"
-    when
-        $section: Section(!hasTables(),
-                          hasEntitiesOfType("published_information"),
-                          hasEntitiesOfType("PII"))
-    then
-        $section.getEntitiesOfType("PII")
-            .forEach(redactionEntity -> {
-                redactionEntity.skipWithReferences(
-                        "CBI.7.2",
-                        "Published Information found in section",
-                        $section.getEntitiesOfType("published_information")
-                );
+        entityCreationService.byRegex("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", "CBI_author", EntityType.ENTITY, 1, $section)
+            .forEach(entity -> {
+                entity.redact("CBI.7.1", "Author found by \"et al\" regex", "Article 39(e)(3) of Regulation (EC) No 178/2002");
+                dictionary.recommendEverywhere(entity);
             });
     end
 
-rule "CBI.7.3: Do not redact PII if published information found in same table row"
+rule "CBI.7.2: Add CBI_author with \"et al.\" RegEx (vertebrate study)"
+    agenda-group "LOCAL_DICTIONARY_ADDS"
     when
-        $table: Table(hasEntitiesOfType("published_information"), hasEntitiesOfType("PII"))
-        $cellsWithPublishedInformation: TableCell() from $table.streamTableCellsWhichContainType("published_information").toList()
-        $tableCell: TableCell(row == $cellsWithPublishedInformation.row) from $table.streamTableCells().toList()
-        $pii: TextEntity(type() == "PII", active()) from $tableCell.getEntities()
+        FileAttribute(label == "Vertebrate Study", value soundslike "Yes" || value.toLowerCase() == "y")
+        $section: Section(containsString("et al."))
     then
-        $pii.skipWithReferences("CBI.7.3", "Published Information found in row", $table.getEntitiesOfTypeInSameRow("published_information", $pii));
+        entityCreationService.byRegex("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", "CBI_author", EntityType.ENTITY, 1, $section)
+            .forEach(entity -> {
+                entity.redact("CBI.7.2", "Author found by \"et al\" regex", "Article 39(e)(2) of Regulation (EC) No 178/2002");
+                dictionary.recommendEverywhere(entity);
+            });
+    end
+
+rule "CBI.7.3: Add CBI_author with \"et al.\" RegEx"
+    agenda-group "LOCAL_DICTIONARY_ADDS"
+    when
+        $section: Section(containsString("et al."))
+    then
+        entityCreationService.byRegex("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", "CBI_author", EntityType.ENTITY, 1, $section)
+            .forEach(entity -> {
+                entity.redact("CBI.7.3", "Author found by \"et al\" regex", "Article 4(1)(b), Regulation (EC) No 1049/2001 (Personal data)");
+                dictionary.recommendEverywhere(entity);
+            });
     end
 
 
@@ -289,54 +287,56 @@ rule "CBI.11.0: Recommend all CBI_author entities in Table with Vertebrate Study
 
 
 // Rule unit: CBI.16
-rule "CBI.16.0: Add CBI_author with \"et al.\" RegEx"
-    agenda-group "LOCAL_DICTIONARY_ADDS"
+rule "CBI.16.0: Do not redact Names and Addresses if published information found in Section without tables"
     when
-        $section: Section(containsString("et al."))
+        $section: Section(!hasTables(),
+                          hasEntitiesOfType("published_information"),
+                          (hasEntitiesOfType("CBI_author") || hasEntitiesOfType("CBI_address")))
     then
-        entityCreationService.byRegex("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", "CBI_author", EntityType.ENTITY, 1, $section)
-            .forEach(entity -> {
-                entity.redact("CBI.16.0", "Author found by \"et al\" regex", "Reg (EC) No 1107/2009 Art. 63 (2g)");
-                dictionary.recommendEverywhere(entity);
+        $section.getEntitiesOfType(List.of("CBI_author", "CBI_address"))
+            .forEach(redactionEntity -> {
+                redactionEntity.skipWithReferences(
+                        "CBI.16.0",
+                        "Published Information found in section",
+                        $section.getEntitiesOfType("published_information")
+                );
             });
     end
 
-rule "CBI.16.1: Add CBI_author with \"et al.\" RegEx (non vertebrate study)"
-    agenda-group "LOCAL_DICTIONARY_ADDS"
+rule "CBI.16.1: Do not redact Names and Addresses if published information found in same table row"
     when
-        not FileAttribute(label == "Vertebrate Study", value soundslike "Yes" || value.toLowerCase() == "y")
-        $section: Section(containsString("et al."))
+        $table: Table(hasEntitiesOfType("published_information"), hasEntitiesOfType("CBI_author") || hasEntitiesOfType("CBI_address"))
+        $cellsWithPublishedInformation: TableCell() from $table.streamTableCellsWhichContainType("published_information").toList()
+        $tableCell: TableCell(row == $cellsWithPublishedInformation.row) from $table.streamTableCells().toList()
+        $authorOrAddress: TextEntity(type() == "CBI_author" || type() == "CBI_address", active()) from $tableCell.getEntities()
     then
-        entityCreationService.byRegex("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", "CBI_author", EntityType.ENTITY, 1, $section)
-            .forEach(entity -> {
-                entity.redact("CBI.16.1", "Author found by \"et al\" regex", "Article 39(e)(3) of Regulation (EC) No 178/2002");
-                dictionary.recommendEverywhere(entity);
+        $authorOrAddress.skipWithReferences("CBI.16.1", "Published Information found in row", $table.getEntitiesOfTypeInSameRow("published_information", $authorOrAddress));
+    end
+
+rule "CBI.16.2: Do not redact PII if published information found in Section without tables"
+    when
+        $section: Section(!hasTables(),
+                          hasEntitiesOfType("published_information"),
+                          hasEntitiesOfType("PII"))
+    then
+        $section.getEntitiesOfType("PII")
+            .forEach(redactionEntity -> {
+                redactionEntity.skipWithReferences(
+                        "CBI.16.2",
+                        "Published Information found in section",
+                        $section.getEntitiesOfType("published_information")
+                );
             });
     end
 
-rule "CBI.16.2: Add CBI_author with \"et al.\" RegEx (vertebrate study)"
-    agenda-group "LOCAL_DICTIONARY_ADDS"
+rule "CBI.16.3: Do not redact PII if published information found in same table row"
     when
-        FileAttribute(label == "Vertebrate Study", value soundslike "Yes" || value.toLowerCase() == "y")
-        $section: Section(containsString("et al."))
+        $table: Table(hasEntitiesOfType("published_information"), hasEntitiesOfType("PII"))
+        $cellsWithPublishedInformation: TableCell() from $table.streamTableCellsWhichContainType("published_information").toList()
+        $tableCell: TableCell(row == $cellsWithPublishedInformation.row) from $table.streamTableCells().toList()
+        $pii: TextEntity(type() == "PII", active()) from $tableCell.getEntities()
     then
-        entityCreationService.byRegex("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", "CBI_author", EntityType.ENTITY, 1, $section)
-            .forEach(entity -> {
-                entity.redact("CBI.16.2", "Author found by \"et al\" regex", "Article 39(e)(2) of Regulation (EC) No 178/2002");
-                dictionary.recommendEverywhere(entity);
-            });
-    end
-
-rule "CBI.16.3: Add CBI_author with \"et al.\" RegEx"
-    agenda-group "LOCAL_DICTIONARY_ADDS"
-    when
-        $section: Section(containsString("et al."))
-    then
-        entityCreationService.byRegex("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", "CBI_author", EntityType.ENTITY, 1, $section)
-            .forEach(entity -> {
-                entity.redact("CBI.16.3", "Author found by \"et al\" regex", "Article 4(1)(b), Regulation (EC) No 1049/2001 (Personal data)");
-                dictionary.recommendEverywhere(entity);
-            });
+        $pii.skipWithReferences("CBI.16.3", "Published Information found in row", $table.getEntitiesOfTypeInSameRow("published_information", $pii));
     end
 
 

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

@@ -312,56 +312,54 @@ rule "CBI.6.1: Do not redact Names and Addresses if vertebrate but also publishe
 
 
 // Rule unit: CBI.7
-rule "CBI.7.0: Do not redact Names and Addresses if published information found in Section without tables"
+rule "CBI.7.0: Add CBI_author with \"et al.\" RegEx"
+    agenda-group "LOCAL_DICTIONARY_ADDS"
     when
-        $section: Section(!hasTables(),
-                          hasEntitiesOfType("published_information"),
-                          (hasEntitiesOfType("CBI_author") || hasEntitiesOfType("CBI_address")))
+        $section: Section(containsString("et al."))
     then
-        $section.getEntitiesOfType(List.of("CBI_author", "CBI_address"))
-            .forEach(redactionEntity -> {
-                redactionEntity.skipWithReferences(
-                        "CBI.7.0",
-                        "Published Information found in section",
-                        $section.getEntitiesOfType("published_information")
-                );
+        entityCreationService.byRegex("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", "CBI_author", EntityType.ENTITY, 1, $section)
+            .forEach(entity -> {
+                entity.redact("CBI.7.0", "Author found by \"et al\" regex", "Reg (EC) No 1107/2009 Art. 63 (2g)");
+                dictionary.recommendEverywhere(entity);
             });
     end
 
-rule "CBI.7.1: Do not redact Names and Addresses if published information found in same table row"
+rule "CBI.7.1: Add CBI_author with \"et al.\" RegEx (non vertebrate study)"
+    agenda-group "LOCAL_DICTIONARY_ADDS"
     when
-        $table: Table(hasEntitiesOfType("published_information"), hasEntitiesOfType("CBI_author") || hasEntitiesOfType("CBI_address"))
-        $cellsWithPublishedInformation: TableCell() from $table.streamTableCellsWhichContainType("published_information").toList()
-        $tableCell: TableCell(row == $cellsWithPublishedInformation.row) from $table.streamTableCells().toList()
-        $authorOrAddress: TextEntity(type() == "CBI_author" || type() == "CBI_address", active()) from $tableCell.getEntities()
+        not FileAttribute(label == "Vertebrate Study", value soundslike "Yes" || value.toLowerCase() == "y")
+        $section: Section(containsString("et al."))
     then
-        $authorOrAddress.skipWithReferences("CBI.7.1", "Published Information found in row", $table.getEntitiesOfTypeInSameRow("published_information", $authorOrAddress));
-    end
-
-rule "CBI.7.2: Do not redact PII if published information found in Section without tables"
-    when
-        $section: Section(!hasTables(),
-                          hasEntitiesOfType("published_information"),
-                          hasEntitiesOfType("PII"))
-    then
-        $section.getEntitiesOfType("PII")
-            .forEach(redactionEntity -> {
-                redactionEntity.skipWithReferences(
-                        "CBI.7.2",
-                        "Published Information found in section",
-                        $section.getEntitiesOfType("published_information")
-                );
+        entityCreationService.byRegex("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", "CBI_author", EntityType.ENTITY, 1, $section)
+            .forEach(entity -> {
+                entity.redact("CBI.7.1", "Author found by \"et al\" regex", "Article 39(e)(3) of Regulation (EC) No 178/2002");
+                dictionary.recommendEverywhere(entity);
             });
     end
 
-rule "CBI.7.3: Do not redact PII if published information found in same table row"
+rule "CBI.7.2: Add CBI_author with \"et al.\" RegEx (vertebrate study)"
+    agenda-group "LOCAL_DICTIONARY_ADDS"
     when
-        $table: Table(hasEntitiesOfType("published_information"), hasEntitiesOfType("PII"))
-        $cellsWithPublishedInformation: TableCell() from $table.streamTableCellsWhichContainType("published_information").toList()
-        $tableCell: TableCell(row == $cellsWithPublishedInformation.row) from $table.streamTableCells().toList()
-        $pii: TextEntity(type() == "PII", active()) from $tableCell.getEntities()
+        FileAttribute(label == "Vertebrate Study", value soundslike "Yes" || value.toLowerCase() == "y")
+        $section: Section(containsString("et al."))
     then
-        $pii.skipWithReferences("CBI.7.3", "Published Information found in row", $table.getEntitiesOfTypeInSameRow("published_information", $pii));
+        entityCreationService.byRegex("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", "CBI_author", EntityType.ENTITY, 1, $section)
+            .forEach(entity -> {
+                entity.redact("CBI.7.2", "Author found by \"et al\" regex", "Article 39(e)(2) of Regulation (EC) No 178/2002");
+                dictionary.recommendEverywhere(entity);
+            });
+    end
+
+rule "CBI.7.3: Add CBI_author with \"et al.\" RegEx"
+    agenda-group "LOCAL_DICTIONARY_ADDS"
+    when
+        $section: Section(containsString("et al."))
+    then
+        entityCreationService.byRegex("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", "CBI_author", EntityType.ENTITY, 1, $section)
+            .forEach(entity -> {
+                entity.redact("CBI.7.3", "Author found by \"et al\" regex", "Article 4(1)(b), Regulation (EC) No 1049/2001 (Personal data)");
+                dictionary.recommendEverywhere(entity);
+            });
     end
 
 
@@ -654,54 +652,56 @@ rule "CBI.15.1: Redact CBI_author and CBI_address if row contains \"determinatio
 
 
 // Rule unit: CBI.16
-rule "CBI.16.0: Add CBI_author with \"et al.\" RegEx"
-    agenda-group "LOCAL_DICTIONARY_ADDS"
+rule "CBI.16.0: Do not redact Names and Addresses if published information found in Section without tables"
     when
-        $section: Section(containsString("et al."))
+        $section: Section(!hasTables(),
+                          hasEntitiesOfType("published_information"),
+                          (hasEntitiesOfType("CBI_author") || hasEntitiesOfType("CBI_address")))
     then
-        entityCreationService.byRegex("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", "CBI_author", EntityType.ENTITY, 1, $section)
-            .forEach(entity -> {
-                entity.redact("CBI.16.0", "Author found by \"et al\" regex", "Reg (EC) No 1107/2009 Art. 63 (2g)");
-                dictionary.recommendEverywhere(entity);
+        $section.getEntitiesOfType(List.of("CBI_author", "CBI_address"))
+            .forEach(redactionEntity -> {
+                redactionEntity.skipWithReferences(
+                        "CBI.16.0",
+                        "Published Information found in section",
+                        $section.getEntitiesOfType("published_information")
+                );
             });
     end
 
-rule "CBI.16.1: Add CBI_author with \"et al.\" RegEx (non vertebrate study)"
-    agenda-group "LOCAL_DICTIONARY_ADDS"
+rule "CBI.16.1: Do not redact Names and Addresses if published information found in same table row"
     when
-        not FileAttribute(label == "Vertebrate Study", value soundslike "Yes" || value.toLowerCase() == "y")
-        $section: Section(containsString("et al."))
+        $table: Table(hasEntitiesOfType("published_information"), hasEntitiesOfType("CBI_author") || hasEntitiesOfType("CBI_address"))
+        $cellsWithPublishedInformation: TableCell() from $table.streamTableCellsWhichContainType("published_information").toList()
+        $tableCell: TableCell(row == $cellsWithPublishedInformation.row) from $table.streamTableCells().toList()
+        $authorOrAddress: TextEntity(type() == "CBI_author" || type() == "CBI_address", active()) from $tableCell.getEntities()
     then
-        entityCreationService.byRegex("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", "CBI_author", EntityType.ENTITY, 1, $section)
-            .forEach(entity -> {
-                entity.redact("CBI.16.1", "Author found by \"et al\" regex", "Article 39(e)(3) of Regulation (EC) No 178/2002");
-                dictionary.recommendEverywhere(entity);
+        $authorOrAddress.skipWithReferences("CBI.16.1", "Published Information found in row", $table.getEntitiesOfTypeInSameRow("published_information", $authorOrAddress));
+    end
+
+rule "CBI.16.2: Do not redact PII if published information found in Section without tables"
+    when
+        $section: Section(!hasTables(),
+                          hasEntitiesOfType("published_information"),
+                          hasEntitiesOfType("PII"))
+    then
+        $section.getEntitiesOfType("PII")
+            .forEach(redactionEntity -> {
+                redactionEntity.skipWithReferences(
+                        "CBI.16.2",
+                        "Published Information found in section",
+                        $section.getEntitiesOfType("published_information")
+                );
             });
     end
 
-rule "CBI.16.2: Add CBI_author with \"et al.\" RegEx (vertebrate study)"
-    agenda-group "LOCAL_DICTIONARY_ADDS"
+rule "CBI.16.3: Do not redact PII if published information found in same table row"
     when
-        FileAttribute(label == "Vertebrate Study", value soundslike "Yes" || value.toLowerCase() == "y")
-        $section: Section(containsString("et al."))
+        $table: Table(hasEntitiesOfType("published_information"), hasEntitiesOfType("PII"))
+        $cellsWithPublishedInformation: TableCell() from $table.streamTableCellsWhichContainType("published_information").toList()
+        $tableCell: TableCell(row == $cellsWithPublishedInformation.row) from $table.streamTableCells().toList()
+        $pii: TextEntity(type() == "PII", active()) from $tableCell.getEntities()
     then
-        entityCreationService.byRegex("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", "CBI_author", EntityType.ENTITY, 1, $section)
-            .forEach(entity -> {
-                entity.redact("CBI.16.2", "Author found by \"et al\" regex", "Article 39(e)(2) of Regulation (EC) No 178/2002");
-                dictionary.recommendEverywhere(entity);
-            });
-    end
-
-rule "CBI.16.3: Add CBI_author with \"et al.\" RegEx"
-    agenda-group "LOCAL_DICTIONARY_ADDS"
-    when
-        $section: Section(containsString("et al."))
-    then
-        entityCreationService.byRegex("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", "CBI_author", EntityType.ENTITY, 1, $section)
-            .forEach(entity -> {
-                entity.redact("CBI.16.3", "Author found by \"et al\" regex", "Article 4(1)(b), Regulation (EC) No 1049/2001 (Personal data)");
-                dictionary.recommendEverywhere(entity);
-            });
+        $pii.skipWithReferences("CBI.16.3", "Published Information found in row", $table.getEntitiesOfTypeInSameRow("published_information", $pii));
     end
 
 

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

@@ -129,30 +129,30 @@ rule "CBI.2.0: Do not redact genitive CBI Author"
 
 
 // Rule unit: CBI.7
-rule "CBI.7.0: Do not redact Names and Addresses if published information found in Section without tables"
+rule "CBI.7.1: Add CBI_author with \"et al.\" RegEx (non vertebrate study)"
+    agenda-group "LOCAL_DICTIONARY_ADDS"
     when
-        $section: Section(!hasTables(),
-                          hasEntitiesOfType("published_information"),
-                          (hasEntitiesOfType("CBI_author") || hasEntitiesOfType("CBI_address")))
+        not FileAttribute(label == "Vertebrate Study", value soundslike "Yes" || value.toLowerCase() == "y")
+        $section: Section(containsString("et al."))
     then
-        $section.getEntitiesOfType(List.of("CBI_author", "CBI_address"))
-            .forEach(redactionEntity -> {
-                redactionEntity.skipWithReferences(
-                        "CBI.7.0",
-                        "Published Information found in section",
-                        $section.getEntitiesOfType("published_information")
-                );
+        entityCreationService.byRegex("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", "CBI_author", EntityType.ENTITY, 1, $section)
+            .forEach(entity -> {
+                entity.redact("CBI.7.1", "Author found by \"et al\" regex", "Article 39(e)(3) of Regulation (EC) No 178/2002");
+                dictionary.recommendEverywhere(entity);
             });
     end
 
-rule "CBI.7.1: Do not redact Names and Addresses if published information found in same table row"
+rule "CBI.7.2: Add CBI_author with \"et al.\" RegEx (vertebrate study)"
+    agenda-group "LOCAL_DICTIONARY_ADDS"
     when
-        $table: Table(hasEntitiesOfType("published_information"), hasEntitiesOfType("CBI_author") || hasEntitiesOfType("CBI_address"))
-        $cellsWithPublishedInformation: TableCell() from $table.streamTableCellsWhichContainType("published_information").toList()
-        $tableCell: TableCell(row == $cellsWithPublishedInformation.row) from $table.streamTableCells().toList()
-        $authorOrAddress: TextEntity(type() == "CBI_author" || type() == "CBI_address", active()) from $tableCell.getEntities()
+        FileAttribute(label == "Vertebrate Study", value soundslike "Yes" || value.toLowerCase() == "y")
+        $section: Section(containsString("et al."))
     then
-        $authorOrAddress.skipWithReferences("CBI.7.1", "Published Information found in row", $table.getEntitiesOfTypeInSameRow("published_information", $authorOrAddress));
+        entityCreationService.byRegex("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", "CBI_author", EntityType.ENTITY, 1, $section)
+            .forEach(entity -> {
+                entity.redact("CBI.7.2", "Author found by \"et al\" regex", "Article 39(e)(2) of Regulation (EC) No 178/2002");
+                dictionary.recommendEverywhere(entity);
+            });
     end
 
 
@@ -224,30 +224,30 @@ rule "CBI.11.0: Recommend all CBI_author entities in Table with Vertebrate Study
 
 
 // Rule unit: CBI.16
-rule "CBI.16.1: Add CBI_author with \"et al.\" RegEx (non vertebrate study)"
-    agenda-group "LOCAL_DICTIONARY_ADDS"
+rule "CBI.16.0: Do not redact Names and Addresses if published information found in Section without tables"
     when
-        not FileAttribute(label == "Vertebrate Study", value soundslike "Yes" || value.toLowerCase() == "y")
-        $section: Section(containsString("et al."))
+        $section: Section(!hasTables(),
+                          hasEntitiesOfType("published_information"),
+                          (hasEntitiesOfType("CBI_author") || hasEntitiesOfType("CBI_address")))
     then
-        entityCreationService.byRegex("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", "CBI_author", EntityType.ENTITY, 1, $section)
-            .forEach(entity -> {
-                entity.redact("CBI.16.1", "Author found by \"et al\" regex", "Article 39(e)(3) of Regulation (EC) No 178/2002");
-                dictionary.recommendEverywhere(entity);
+        $section.getEntitiesOfType(List.of("CBI_author", "CBI_address"))
+            .forEach(redactionEntity -> {
+                redactionEntity.skipWithReferences(
+                        "CBI.16.0",
+                        "Published Information found in section",
+                        $section.getEntitiesOfType("published_information")
+                );
             });
     end
 
-rule "CBI.16.2: Add CBI_author with \"et al.\" RegEx (vertebrate study)"
-    agenda-group "LOCAL_DICTIONARY_ADDS"
+rule "CBI.16.1: Do not redact Names and Addresses if published information found in same table row"
     when
-        FileAttribute(label == "Vertebrate Study", value soundslike "Yes" || value.toLowerCase() == "y")
-        $section: Section(containsString("et al."))
+        $table: Table(hasEntitiesOfType("published_information"), hasEntitiesOfType("CBI_author") || hasEntitiesOfType("CBI_address"))
+        $cellsWithPublishedInformation: TableCell() from $table.streamTableCellsWhichContainType("published_information").toList()
+        $tableCell: TableCell(row == $cellsWithPublishedInformation.row) from $table.streamTableCells().toList()
+        $authorOrAddress: TextEntity(type() == "CBI_author" || type() == "CBI_address", active()) from $tableCell.getEntities()
     then
-        entityCreationService.byRegex("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", "CBI_author", EntityType.ENTITY, 1, $section)
-            .forEach(entity -> {
-                entity.redact("CBI.16.2", "Author found by \"et al\" regex", "Article 39(e)(2) of Regulation (EC) No 178/2002");
-                dictionary.recommendEverywhere(entity);
-            });
+        $authorOrAddress.skipWithReferences("CBI.16.1", "Published Information found in row", $table.getEntitiesOfTypeInSameRow("published_information", $authorOrAddress));
     end
 
 

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

@@ -214,6 +214,58 @@ rule "CBI.5.1: Redact Names and Addresses if no_redaction_indicator but also red
     end
 
 
+// Rule unit: CBI.7
+rule "CBI.7.0: Add CBI_author with \"et al.\" RegEx"
+    agenda-group "LOCAL_DICTIONARY_ADDS"
+    when
+        $section: Section(containsString("et al."))
+    then
+        entityCreationService.byRegex("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", "CBI_author", EntityType.ENTITY, 1, $section)
+            .forEach(entity -> {
+                entity.redact("CBI.7.0", "Author found by \"et al\" regex", "Reg (EC) No 1107/2009 Art. 63 (2g)");
+                dictionary.recommendEverywhere(entity);
+            });
+    end
+
+rule "CBI.7.1: Add CBI_author with \"et al.\" RegEx (non vertebrate study)"
+    agenda-group "LOCAL_DICTIONARY_ADDS"
+    when
+        not FileAttribute(label == "Vertebrate Study", value soundslike "Yes" || value.toLowerCase() == "y")
+        $section: Section(containsString("et al."))
+    then
+        entityCreationService.byRegex("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", "CBI_author", EntityType.ENTITY, 1, $section)
+            .forEach(entity -> {
+                entity.redact("CBI.7.1", "Author found by \"et al\" regex", "Article 39(e)(3) of Regulation (EC) No 178/2002");
+                dictionary.recommendEverywhere(entity);
+            });
+    end
+
+rule "CBI.7.2: Add CBI_author with \"et al.\" RegEx (vertebrate study)"
+    agenda-group "LOCAL_DICTIONARY_ADDS"
+    when
+        FileAttribute(label == "Vertebrate Study", value soundslike "Yes" || value.toLowerCase() == "y")
+        $section: Section(containsString("et al."))
+    then
+        entityCreationService.byRegex("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", "CBI_author", EntityType.ENTITY, 1, $section)
+            .forEach(entity -> {
+                entity.redact("CBI.7.2", "Author found by \"et al\" regex", "Article 39(e)(2) of Regulation (EC) No 178/2002");
+                dictionary.recommendEverywhere(entity);
+            });
+    end
+
+rule "CBI.7.3: Add CBI_author with \"et al.\" RegEx"
+    agenda-group "LOCAL_DICTIONARY_ADDS"
+    when
+        $section: Section(containsString("et al."))
+    then
+        entityCreationService.byRegex("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", "CBI_author", EntityType.ENTITY, 1, $section)
+            .forEach(entity -> {
+                entity.redact("CBI.7.3", "Author found by \"et al\" regex", "Article 4(1)(b), Regulation (EC) No 1049/2001 (Personal data)");
+                dictionary.recommendEverywhere(entity);
+            });
+    end
+
+
 // Rule unit: CBI.8
 rule "CBI.8.0: Redacted because Section contains must_redact entity"
     when
@@ -424,58 +476,6 @@ rule "CBI.15.1: Redact CBI_author and CBI_address if row contains \"determinatio
     end
 
 
-// Rule unit: CBI.16
-rule "CBI.16.0: Add CBI_author with \"et al.\" RegEx"
-    agenda-group "LOCAL_DICTIONARY_ADDS"
-    when
-        $section: Section(containsString("et al."))
-    then
-        entityCreationService.byRegex("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", "CBI_author", EntityType.ENTITY, 1, $section)
-            .forEach(entity -> {
-                entity.redact("CBI.16.0", "Author found by \"et al\" regex", "Reg (EC) No 1107/2009 Art. 63 (2g)");
-                dictionary.recommendEverywhere(entity);
-            });
-    end
-
-rule "CBI.16.1: Add CBI_author with \"et al.\" RegEx (non vertebrate study)"
-    agenda-group "LOCAL_DICTIONARY_ADDS"
-    when
-        not FileAttribute(label == "Vertebrate Study", value soundslike "Yes" || value.toLowerCase() == "y")
-        $section: Section(containsString("et al."))
-    then
-        entityCreationService.byRegex("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", "CBI_author", EntityType.ENTITY, 1, $section)
-            .forEach(entity -> {
-                entity.redact("CBI.16.1", "Author found by \"et al\" regex", "Article 39(e)(3) of Regulation (EC) No 178/2002");
-                dictionary.recommendEverywhere(entity);
-            });
-    end
-
-rule "CBI.16.2: Add CBI_author with \"et al.\" RegEx (vertebrate study)"
-    agenda-group "LOCAL_DICTIONARY_ADDS"
-    when
-        FileAttribute(label == "Vertebrate Study", value soundslike "Yes" || value.toLowerCase() == "y")
-        $section: Section(containsString("et al."))
-    then
-        entityCreationService.byRegex("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", "CBI_author", EntityType.ENTITY, 1, $section)
-            .forEach(entity -> {
-                entity.redact("CBI.16.2", "Author found by \"et al\" regex", "Article 39(e)(2) of Regulation (EC) No 178/2002");
-                dictionary.recommendEverywhere(entity);
-            });
-    end
-
-rule "CBI.16.3: Add CBI_author with \"et al.\" RegEx"
-    agenda-group "LOCAL_DICTIONARY_ADDS"
-    when
-        $section: Section(containsString("et al."))
-    then
-        entityCreationService.byRegex("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", "CBI_author", EntityType.ENTITY, 1, $section)
-            .forEach(entity -> {
-                entity.redact("CBI.16.3", "Author found by \"et al\" regex", "Article 4(1)(b), Regulation (EC) No 1049/2001 (Personal data)");
-                dictionary.recommendEverywhere(entity);
-            });
-    end
-
-
 // Rule unit: CBI.17
 rule "CBI.17.0: Add recommendation for Addresses in Test Organism sections, without colon"
     when

redaction-service-v1/rules-management/src/main/java/com/knecon/fforesight/utility/rules/management/migration/RuleFileMigrator.java

@@ -4,11 +4,13 @@ import java.io.File;
 import java.io.FileOutputStream;
 import java.nio.charset.StandardCharsets;
 import java.util.List;
+import java.util.Map;
 
 import com.knecon.fforesight.utility.rules.management.factory.RuleFileFactory;
 import com.knecon.fforesight.utility.rules.management.factory.RuleFileParser;
 import com.knecon.fforesight.utility.rules.management.models.BasicRule;
 import com.knecon.fforesight.utility.rules.management.models.RuleFileBluePrint;
+import com.knecon.fforesight.utility.rules.management.models.RuleIdentifier;
 import com.knecon.fforesight.utility.rules.management.utils.RuleFileIO;
 
 import lombok.SneakyThrows;
@@ -21,17 +23,15 @@ import lombok.experimental.UtilityClass;
 @UtilityClass
 public class RuleFileMigrator {
 
+
     @SneakyThrows
     public void migrateFile(File ruleFile) {
 
         RuleFileBluePrint ruleFileBluePrint = RuleFileParser.buildBluePrintFromRulesString(RuleFileIO.getRulesString(ruleFile.getAbsolutePath()));
         RuleFileBluePrint combinedBluePrint = RuleFileParser.buildBluePrintFromAllRuleFiles();
 
-        for (BasicRule ruleToReplace : ruleFileBluePrint.getAllRules()) {
-            List<BasicRule> rulesToAdd = combinedBluePrint.findRuleByIdentifier(ruleToReplace.identifier());
-            ruleFileBluePrint.removeRule(ruleToReplace.identifier());
-            rulesToAdd.forEach(ruleFileBluePrint::addRule);
-        }
+        //replaceRules(ruleFileBluePrint, combinedBluePrint);
+        replaceRuleIdentifiers(combinedBluePrint, ruleFileBluePrint);
 
         String migratedRulesString = RuleFileFactory.buildRuleString(ruleFileBluePrint);
         String migratedFilePath = ruleFile.getAbsolutePath();
@@ -40,4 +40,35 @@ public class RuleFileMigrator {
         }
     }
 
+
+    private static void replaceRules(RuleFileBluePrint ruleFileBluePrint, RuleFileBluePrint combinedBluePrint) {
+
+        for (BasicRule ruleToReplace : ruleFileBluePrint.getAllRules()) {
+            List<BasicRule> rulesToAdd = combinedBluePrint.findRuleByIdentifier(ruleToReplace.identifier());
+            ruleFileBluePrint.removeRule(ruleToReplace.identifier());
+            rulesToAdd.forEach(ruleFileBluePrint::addRule);
+        }
+    }
+
+
+    private static void replaceRuleIdentifiers(RuleFileBluePrint combinedBluePrint, RuleFileBluePrint ruleFileBluePrint) {
+
+        Map<String, String> identifierReplaceMap = Map.of("CBI.7.0", "CBI.16.0", "CBI.7.1", "CBI.16.1", "CBI.7.2", "CBI.16.2", "CBI.7.3", "CBI.16.3");
+        for (String identifier : identifierReplaceMap.keySet()) {
+            RuleIdentifier ruleId = RuleIdentifier.fromString(identifier);
+            RuleIdentifier otherRuleId = RuleIdentifier.fromString(identifierReplaceMap.get(identifier));
+
+            List<BasicRule> rulesToAdd = combinedBluePrint.findRuleByIdentifier(otherRuleId);
+            List<BasicRule> otherRulesToAdd = combinedBluePrint.findRuleByIdentifier(ruleId);
+            boolean removeRules = ruleFileBluePrint.removeRule(ruleId);
+            boolean removeOtherRules = ruleFileBluePrint.removeRule(otherRuleId);
+            if (removeRules) {
+                rulesToAdd.forEach(ruleFileBluePrint::addRule);
+            }
+            if (removeOtherRules) {
+                otherRulesToAdd.forEach(ruleFileBluePrint::addRule);
+            }
+        }
+    }
+
 }

redaction-service-v1/rules-management/src/main/java/com/knecon/fforesight/utility/rules/management/models/RuleFileBluePrint.java

@@ -7,15 +7,19 @@ import java.util.List;
 import java.util.Objects;
 import java.util.Optional;
 import java.util.Set;
+import java.util.concurrent.atomic.AtomicBoolean;
 import java.util.stream.Collectors;
 
 public record RuleFileBluePrint(String imports, String globals, String queries, List<RuleClass> ruleClasses) {
 
-    public void removeRule(RuleIdentifier ruleIdentifier) {
+    public boolean removeRule(RuleIdentifier ruleIdentifier) {
+
+        AtomicBoolean wasRemoved = new AtomicBoolean(false);
 
         findRuleClassByType(ruleIdentifier.type()).ifPresent(ruleClass -> ruleClass.findRuleUnitByInteger(ruleIdentifier.unit())
                 .ifPresent(ruleUnit -> {
-                    ruleUnit.rules().removeIf(rule -> rule.identifier().matches(ruleIdentifier));
+                    boolean removed = ruleUnit.rules().removeIf(rule -> rule.identifier().matches(ruleIdentifier));
+                    wasRemoved.set(removed);
                     if (ruleUnit.rules().isEmpty()) {
                         ruleClass.ruleUnits().remove(ruleUnit);
                     }
@@ -23,7 +27,7 @@ public record RuleFileBluePrint(String imports, String globals, String queries,
                         ruleClasses().remove(ruleClass);
                     }
                 }));
-
+        return wasRemoved.get();
     }
 
 

redaction-service-v1/rules-management/src/main/resources/all_redact_manager_rules.drl

@@ -312,58 +312,55 @@ rule "CBI.6.1: Do not redact Names and Addresses if vertebrate but also publishe
 
 
 // Rule unit: CBI.7
-rule "CBI.7.0: Do not redact Names and Addresses if published information found in Section without tables"
+rule "CBI.7.0: Add CBI_author with \"et al.\" RegEx"
+    agenda-group "LOCAL_DICTIONARY_ADDS"
     when
-        $section: Section(!hasTables(),
-                          hasEntitiesOfType("published_information"),
-                          (hasEntitiesOfType("CBI_author") || hasEntitiesOfType("CBI_address")))
+        $section: Section(containsString("et al."))
     then
-        $section.getEntitiesOfType(List.of("CBI_author", "CBI_address"))
-            .forEach(redactionEntity -> {
-                redactionEntity.skipWithReferences(
-                        "CBI.7.0",
-                        "Published Information found in section",
-                        $section.getEntitiesOfType("published_information")
-                );
+        entityCreationService.byRegex("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", "CBI_author", EntityType.ENTITY, 1, $section)
+            .forEach(entity -> {
+                entity.redact("CBI.7.0", "Author found by \"et al\" regex", "Reg (EC) No 1107/2009 Art. 63 (2g)");
+                dictionary.recommendEverywhere(entity);
             });
     end
 
-rule "CBI.7.1: Do not redact Names and Addresses if published information found in same table row"
+rule "CBI.7.1: Add CBI_author with \"et al.\" RegEx (non vertebrate study)"
+    agenda-group "LOCAL_DICTIONARY_ADDS"
     when
-        $table: Table(hasEntitiesOfType("published_information"), hasEntitiesOfType("CBI_author") || hasEntitiesOfType("CBI_address"))
-        $cellsWithPublishedInformation: TableCell() from $table.streamTableCellsWhichContainType("published_information").toList()
-        $tableCell: TableCell(row == $cellsWithPublishedInformation.row) from $table.streamTableCells().toList()
-        $authorOrAddress: TextEntity(type() == "CBI_author" || type() == "CBI_address", active()) from $tableCell.getEntities()
+        not FileAttribute(label == "Vertebrate Study", value soundslike "Yes" || value.toLowerCase() == "y")
+        $section: Section(containsString("et al."))
     then
-        $authorOrAddress.skipWithReferences("CBI.7.1", "Published Information found in row", $table.getEntitiesOfTypeInSameRow("published_information", $authorOrAddress));
-    end
-
-rule "CBI.7.2: Do not redact PII if published information found in Section without tables"
-    when
-        $section: Section(!hasTables(),
-                          hasEntitiesOfType("published_information"),
-                          hasEntitiesOfType("PII"))
-    then
-        $section.getEntitiesOfType("PII")
-            .forEach(redactionEntity -> {
-                redactionEntity.skipWithReferences(
-                        "CBI.7.2",
-                        "Published Information found in section",
-                        $section.getEntitiesOfType("published_information")
-                );
+        entityCreationService.byRegex("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", "CBI_author", EntityType.ENTITY, 1, $section)
+            .forEach(entity -> {
+                entity.redact("CBI.7.1", "Author found by \"et al\" regex", "Article 39(e)(3) of Regulation (EC) No 178/2002");
+                dictionary.recommendEverywhere(entity);
             });
     end
 
-rule "CBI.7.3: Do not redact PII if published information found in same table row"
+rule "CBI.7.2: Add CBI_author with \"et al.\" RegEx (vertebrate study)"
+    agenda-group "LOCAL_DICTIONARY_ADDS"
     when
-        $table: Table(hasEntitiesOfType("published_information"), hasEntitiesOfType("PII"))
-        $cellsWithPublishedInformation: TableCell() from $table.streamTableCellsWhichContainType("published_information").toList()
-        $tableCell: TableCell(row == $cellsWithPublishedInformation.row) from $table.streamTableCells().toList()
-        $pii: TextEntity(type() == "PII", active()) from $tableCell.getEntities()
+        FileAttribute(label == "Vertebrate Study", value soundslike "Yes" || value.toLowerCase() == "y")
+        $section: Section(containsString("et al."))
     then
-        $pii.skipWithReferences("CBI.7.3", "Published Information found in row", $table.getEntitiesOfTypeInSameRow("published_information", $pii));
+        entityCreationService.byRegex("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", "CBI_author", EntityType.ENTITY, 1, $section)
+            .forEach(entity -> {
+                entity.redact("CBI.7.2", "Author found by \"et al\" regex", "Article 39(e)(2) of Regulation (EC) No 178/2002");
+                dictionary.recommendEverywhere(entity);
+            });
     end
 
+rule "CBI.7.3: Add CBI_author with \"et al.\" RegEx"
+    agenda-group "LOCAL_DICTIONARY_ADDS"
+    when
+        $section: Section(containsString("et al."))
+    then
+        entityCreationService.byRegex("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", "CBI_author", EntityType.ENTITY, 1, $section)
+            .forEach(entity -> {
+                entity.redact("CBI.7.3", "Author found by \"et al\" regex", "Article 4(1)(b), Regulation (EC) No 1049/2001 (Personal data)");
+                dictionary.recommendEverywhere(entity);
+            });
+    end
 
 // Rule unit: CBI.8
 rule "CBI.8.0: Redacted because Section contains must_redact entity"
@@ -653,54 +650,56 @@ rule "CBI.15.1: Redact CBI_author and CBI_address if row contains \"determinatio
 
 
 // Rule unit: CBI.16
-rule "CBI.16.0: Add CBI_author with \"et al.\" RegEx"
-    agenda-group "LOCAL_DICTIONARY_ADDS"
+rule "CBI.16.0: Do not redact Names and Addresses if published information found in Section without tables"
     when
-        $section: Section(containsString("et al."))
+        $section: Section(!hasTables(),
+                          hasEntitiesOfType("published_information"),
+                          (hasEntitiesOfType("CBI_author") || hasEntitiesOfType("CBI_address")))
     then
-        entityCreationService.byRegex("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", "CBI_author", EntityType.ENTITY, 1, $section)
-            .forEach(entity -> {
-                entity.redact("CBI.16.0", "Author found by \"et al\" regex", "Reg (EC) No 1107/2009 Art. 63 (2g)");
-                dictionary.recommendEverywhere(entity);
+        $section.getEntitiesOfType(List.of("CBI_author", "CBI_address"))
+            .forEach(redactionEntity -> {
+                redactionEntity.skipWithReferences(
+                        "CBI.16.0",
+                        "Published Information found in section",
+                        $section.getEntitiesOfType("published_information")
+                );
             });
     end
 
-rule "CBI.16.1: Add CBI_author with \"et al.\" RegEx (non vertebrate study)"
-    agenda-group "LOCAL_DICTIONARY_ADDS"
+rule "CBI.16.1: Do not redact Names and Addresses if published information found in same table row"
     when
-        not FileAttribute(label == "Vertebrate Study", value soundslike "Yes" || value.toLowerCase() == "y")
-        $section: Section(containsString("et al."))
+        $table: Table(hasEntitiesOfType("published_information"), hasEntitiesOfType("CBI_author") || hasEntitiesOfType("CBI_address"))
+        $cellsWithPublishedInformation: TableCell() from $table.streamTableCellsWhichContainType("published_information").toList()
+        $tableCell: TableCell(row == $cellsWithPublishedInformation.row) from $table.streamTableCells().toList()
+        $authorOrAddress: TextEntity(type() == "CBI_author" || type() == "CBI_address", active()) from $tableCell.getEntities()
     then
-        entityCreationService.byRegex("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", "CBI_author", EntityType.ENTITY, 1, $section)
-            .forEach(entity -> {
-                entity.redact("CBI.16.1", "Author found by \"et al\" regex", "Article 39(e)(3) of Regulation (EC) No 178/2002");
-                dictionary.recommendEverywhere(entity);
+        $authorOrAddress.skipWithReferences("CBI.16.1", "Published Information found in row", $table.getEntitiesOfTypeInSameRow("published_information", $authorOrAddress));
+    end
+
+rule "CBI.16.2: Do not redact PII if published information found in Section without tables"
+    when
+        $section: Section(!hasTables(),
+                          hasEntitiesOfType("published_information"),
+                          hasEntitiesOfType("PII"))
+    then
+        $section.getEntitiesOfType("PII")
+            .forEach(redactionEntity -> {
+                redactionEntity.skipWithReferences(
+                        "CBI.16.2",
+                        "Published Information found in section",
+                        $section.getEntitiesOfType("published_information")
+                );
             });
     end
 
-rule "CBI.16.2: Add CBI_author with \"et al.\" RegEx (vertebrate study)"
-    agenda-group "LOCAL_DICTIONARY_ADDS"
+rule "CBI.16.3: Do not redact PII if published information found in same table row"
     when
-        FileAttribute(label == "Vertebrate Study", value soundslike "Yes" || value.toLowerCase() == "y")
-        $section: Section(containsString("et al."))
+        $table: Table(hasEntitiesOfType("published_information"), hasEntitiesOfType("PII"))
+        $cellsWithPublishedInformation: TableCell() from $table.streamTableCellsWhichContainType("published_information").toList()
+        $tableCell: TableCell(row == $cellsWithPublishedInformation.row) from $table.streamTableCells().toList()
+        $pii: TextEntity(type() == "PII", active()) from $tableCell.getEntities()
     then
-        entityCreationService.byRegex("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", "CBI_author", EntityType.ENTITY, 1, $section)
-            .forEach(entity -> {
-                entity.redact("CBI.16.2", "Author found by \"et al\" regex", "Article 39(e)(2) of Regulation (EC) No 178/2002");
-                dictionary.recommendEverywhere(entity);
-            });
-    end
-
-rule "CBI.16.3: Add CBI_author with \"et al.\" RegEx"
-    agenda-group "LOCAL_DICTIONARY_ADDS"
-    when
-        $section: Section(containsString("et al."))
-    then
-        entityCreationService.byRegex("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", "CBI_author", EntityType.ENTITY, 1, $section)
-            .forEach(entity -> {
-                entity.redact("CBI.16.3", "Author found by \"et al\" regex", "Article 4(1)(b), Regulation (EC) No 1049/2001 (Personal data)");
-                dictionary.recommendEverywhere(entity);
-            });
+        $pii.skipWithReferences("CBI.16.3", "Published Information found in row", $table.getEntitiesOfTypeInSameRow("published_information", $pii));
     end
 
 

redaction-service-v1/rules-management/src/test/java/com/knecon/fforesight/utility/rules/management/RuleFileMigrationTest.java

@@ -25,10 +25,12 @@ public class RuleFileMigrationTest {
 
     // Put your redaction service drools paths and dossier-templates paths both RM and DM here
     static final List<String> ruleFileDirs = List.of(
-            "/home/kschuettler/iqser/redaction/redaction-service/redaction-service-v1/redaction-service-server-v1/src/test/resources/drools",
-            "/home/kschuettler/iqser/redaction/dossier-templates-v2",
-            "/home/kschuettler/iqser/fforesight/dossier-templates-v2",
-            "/home/kschuettler/iqser/business-logic");
+            //"/Users/maverickstuder/Documents/RedactManager/redaction-service/redaction-service-v1/redaction-service-server-v1/src/test/resources/drools",
+            //                                 "/Users/maverickstuder/Documents/RedactManager/dossier-templates-v2"
+            "/Users/maverickstuder/Documents/PM"
+
+            );
+
 
 
     @Test