Made dictionaries Theadsafe

.gitignore

@@ -9,49 +9,6 @@
 **/tmp/
 **/.apt_generated/
 
-HELP.md
-target/
-!.mvn/wrapper/maven-wrapper.jar
-!**/src/main/**/target/
-!**/src/test/**/target/
-
-### maven build ###
-*.class
-/out/
-/build/
-/target/
-**/out/
-**/build/
-**/target/
-
-### STS ###
-.apt_generated
-.classpath
-.factorypath
-.project
-.settings
-.springBeans
-.sts4-cache
-.gradle
-
-### IntelliJ IDEA ###
-.idea
-*.iws
-*.iml
-*.ipr
-
-### NetBeans ###
-/nbproject/private/
-/nbbuild/
-/dist/
-/nbdist/
-/.nb-gradle/
-build/
-!**/src/main/**/build/
-!**/src/test/**/build/
-
-### VS Code ###
-.vscode/
 
 .factorypath
 .springBeans
@@ -69,7 +26,3 @@ build/
 **/.DS_Store
 **/classpath-data.json
 **/dependencies-and-licenses-overview.txt
-gradle.properties
-gradlew
-gradlew.bat
-gradle/

.gitlab-ci.yml

@@ -1,23 +0,0 @@
-variables:
-  SONAR_PROJECT_KEY: 'RED_redaction-service'
-include:
-  - project: 'gitlab/gitlab'
-    ref: 'main'
-    file: 'ci-templates/gradle_java.yml'
-
-deploy:
-  stage: deploy
-  tags:
-    - dind
-  script:
-    - echo "Building with gradle version ${BUILDVERSION}"
-    - gradle -Pversion=${BUILDVERSION} publish
-    - gradle bootBuildImage --cleanCache --publishImage -PbuildbootDockerHostNetwork=true -Pversion=${BUILDVERSION}
-    - echo "BUILDVERSION=$BUILDVERSION" >> version.env
-  artifacts:
-    reports:
-      dotenv: version.env
-  rules:
-    - if: $CI_COMMIT_BRANCH == $CI_DEFAULT_BRANCH
-    - if: $CI_COMMIT_BRANCH =~ /^release/
-    - if: $CI_COMMIT_TAG

CHANGELOG.md

@@ -1,5 +1,4 @@
 # Changelog
-
 All notable changes to this project will be documented in this file.
 
 ## [Unreleased]

bamboo-specs/pom.xml

@@ -0,0 +1,37 @@
+<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
+  <modelVersion>4.0.0</modelVersion>
+
+  <parent>
+    <groupId>com.atlassian.bamboo</groupId>
+    <artifactId>bamboo-specs-parent</artifactId>
+    <version>7.1.2</version>
+    <relativePath/>
+  </parent>
+
+  <artifactId>bamboo-specs</artifactId>
+  <version>1.0.0-SNAPSHOT</version>
+  <packaging>jar</packaging>
+
+  <dependencies>
+    <dependency>
+      <groupId>com.atlassian.bamboo</groupId>
+      <artifactId>bamboo-specs-api</artifactId>
+    </dependency>
+    <dependency>
+      <groupId>com.atlassian.bamboo</groupId>
+      <artifactId>bamboo-specs</artifactId>
+    </dependency>
+
+    <!-- Test dependencies -->
+    <dependency>
+      <groupId>junit</groupId>
+      <artifactId>junit</artifactId>
+      <scope>test</scope>
+    </dependency>
+  </dependencies>
+
+
+  <!-- run 'mvn test' to perform offline validation of the plan -->
+  <!-- run 'mvn -Ppublish-specs' to upload the plan to your Bamboo server -->
+</project>

bamboo-specs/src/main/java/buildjob/PlanSpec.java

@@ -0,0 +1,137 @@
+package buildjob;
+
+import static com.atlassian.bamboo.specs.builders.task.TestParserTask.createJUnitParserTask;
+
+import com.atlassian.bamboo.specs.api.BambooSpec;
+import com.atlassian.bamboo.specs.api.builders.BambooKey;
+import com.atlassian.bamboo.specs.api.builders.docker.DockerConfiguration;
+import com.atlassian.bamboo.specs.api.builders.permission.PermissionType;
+import com.atlassian.bamboo.specs.api.builders.permission.Permissions;
+import com.atlassian.bamboo.specs.api.builders.permission.PlanPermissions;
+import com.atlassian.bamboo.specs.api.builders.plan.Job;
+import com.atlassian.bamboo.specs.api.builders.plan.Plan;
+import com.atlassian.bamboo.specs.api.builders.plan.PlanIdentifier;
+import com.atlassian.bamboo.specs.api.builders.plan.Stage;
+import com.atlassian.bamboo.specs.api.builders.plan.branches.BranchCleanup;
+import com.atlassian.bamboo.specs.api.builders.plan.branches.PlanBranchManagement;
+import com.atlassian.bamboo.specs.api.builders.project.Project;
+import com.atlassian.bamboo.specs.builders.task.CheckoutItem;
+import com.atlassian.bamboo.specs.builders.task.InjectVariablesTask;
+import com.atlassian.bamboo.specs.builders.task.ScriptTask;
+import com.atlassian.bamboo.specs.builders.task.VcsCheckoutTask;
+import com.atlassian.bamboo.specs.builders.task.VcsTagTask;
+import com.atlassian.bamboo.specs.builders.trigger.BitbucketServerTrigger;
+import com.atlassian.bamboo.specs.model.task.InjectVariablesScope;
+import com.atlassian.bamboo.specs.util.BambooServer;
+
+/**
+ * Plan configuration for Bamboo.
+ * Learn more on: <a href="https://confluence.atlassian.com/display/BAMBOO/Bamboo+Specs">https://confluence.atlassian.com/display/BAMBOO/Bamboo+Specs</a>
+ */
+@BambooSpec
+public class PlanSpec {
+
+    private static final String SERVICE_NAME = "redaction-service";
+
+    private static final String SERVICE_KEY = SERVICE_NAME.toUpperCase().replaceAll("-", "");
+
+    /**
+     * Run main to publish plan on Bamboo
+     */
+    public static void main(final String[] args) throws Exception {
+        //By default credentials are read from the '.credentials' file.
+        BambooServer bambooServer = new BambooServer("http://localhost:8085");
+
+        Plan plan = new PlanSpec().createPlan();
+        bambooServer.publish(plan);
+        PlanPermissions planPermission = new PlanSpec().createPlanPermission(plan.getIdentifier());
+        bambooServer.publish(planPermission);
+    }
+
+    private PlanPermissions createPlanPermission(PlanIdentifier planIdentifier) {
+        Permissions permission = new Permissions()
+                .userPermissions("atlbamboo", PermissionType.EDIT, PermissionType.VIEW, PermissionType.ADMIN, PermissionType.CLONE, PermissionType.BUILD)
+                .groupPermissions("red-backend", PermissionType.EDIT, PermissionType.VIEW, PermissionType.CLONE, PermissionType.BUILD)
+                .loggedInUserPermissions(PermissionType.VIEW)
+                .anonymousUserPermissionView();
+        return new PlanPermissions(planIdentifier.getProjectKey(), planIdentifier.getPlanKey()).permissions(permission);
+    }
+
+    private Project project() {
+        return new Project()
+                .name("RED")
+                .key(new BambooKey("RED"));
+    }
+
+    public Plan createPlan() {
+        return new Plan(
+                project(),
+                SERVICE_NAME, new BambooKey(SERVICE_KEY))
+                .description("Plan created from (enter repository url of your plan)")
+                .stages(new Stage("Default Stage")
+                        .jobs(new Job("Default Job",
+                                new BambooKey("JOB1"))
+                                .tasks(
+                                        new ScriptTask()
+                                                .description("Clean")
+                                                .inlineBody("#!/bin/bash\n" +
+                                                        "set -e\n" +
+                                                        "rm -rf ./*"),
+                                        new VcsCheckoutTask()
+                                                .description("Checkout Default Repository")
+                                                .checkoutItems(new CheckoutItem().defaultRepository()),
+                                        new ScriptTask()
+                                                .description("Clean")
+                                                .inlineBody("#!/bin/bash\n" +
+                                                        "set -e\n" +
+                                                        "rm -rf ./*"),
+                                        new VcsCheckoutTask()
+                                                .description("Checkout Default Repository")
+                                                .checkoutItems(new CheckoutItem().defaultRepository()),
+                                        new ScriptTask()
+                                                .description("Build")
+                                                .inlineBody("#!/bin/bash\n" +
+                                                        "set -e\n" +
+
+                                                        "if [[ \"${bamboo.version_tag}\" != \"dev\" ]]; then ${bamboo_capability_system_builder_mvn3_Maven_3}/bin/mvn --no-transfer-progress -f ${bamboo_build_working_directory}/" + SERVICE_NAME + "-v1/pom.xml versions:set  -DnewVersion=${bamboo.version_tag}; fi\n" +
+                                                        "if [[ \"${bamboo.version_tag}\" != \"dev\" ]]; then ${bamboo_capability_system_builder_mvn3_Maven_3}/bin/mvn --no-transfer-progress -f ${bamboo_build_working_directory}/" + SERVICE_NAME + "-image-v1/pom.xml versions:set  -DnewVersion=${bamboo.version_tag}; fi\n" +
+
+                                                        "if [[ \"${bamboo.version_tag}\" = \"dev\" ]]; then ${bamboo_capability_system_builder_mvn3_Maven_3}/bin/mvn -f ${bamboo_build_working_directory}/" + SERVICE_NAME + "-v1/pom.xml --no-transfer-progress clean install -Djava.security.egd=file:/dev/./urandom; fi\n" +
+                                                        "if [[ \"${bamboo.version_tag}\" != \"dev\" ]]; then ${bamboo_capability_system_builder_mvn3_Maven_3}/bin/mvn -f ${bamboo_build_working_directory}/" + SERVICE_NAME + "-v1/pom.xml --no-transfer-progress clean deploy -e -DdeployAtEnd=true -Dmaven.wagon.http.ssl.insecure=true -Dmaven.wagon.http.ssl.allowall=true -Dmaven.wagon.http.ssl.ignore.validity.dates=true -DaltDeploymentRepository=iqser_release::default::https://nexus.iqser.com/repository/red-platform-releases; fi\n" +
+
+                                                        "${bamboo_capability_system_builder_mvn3_Maven_3}/bin/mvn --no-transfer-progress -f ${bamboo_build_working_directory}/" + SERVICE_NAME + "-image-v1/pom.xml package\n" +
+                                                        "${bamboo_capability_system_builder_mvn3_Maven_3}/bin/mvn --no-transfer-progress -f ${bamboo_build_working_directory}/" + SERVICE_NAME + "-image-v1/pom.xml docker:push\n" +
+
+                                                        "if [[ \"${bamboo.version_tag}\" = \"dev\" ]]; then echo \"gitTag=${bamboo.planRepository.1.branch}_${bamboo.buildNumber}\" > git.tag; fi\n" +
+                                                        "if [[ \"${bamboo.version_tag}\" != \"dev\" ]]; then echo \"gitTag=${bamboo.version_tag}\" > git.tag; fi\n"),
+                                        createJUnitParserTask()
+                                                .description("Resultparser")
+                                                .resultDirectories("**/test-reports/*.xml, **/target/surefire-reports/*.xml, **/target/failsafe-reports/*.xml")
+                                                .enabled(true),
+                                        new InjectVariablesTask()
+                                                .description("Inject git Tag")
+                                                .path("git.tag")
+                                                .namespace("g")
+                                                .scope(InjectVariablesScope.LOCAL),
+                                        new VcsTagTask()
+                                                .description("${bamboo.g.gitTag}")
+                                                .tagName("${bamboo.g.gitTag}")
+                                                .defaultRepository())
+                                .dockerConfiguration(
+                                        new DockerConfiguration()
+                                                .image("nexus.iqser.com:5001/infra/maven:3.6.2-jdk-13-3.0.0")
+                                                .volume("/etc/maven/settings.xml", "/usr/share/maven/ref/settings.xml")
+                                                .volume("/var/run/docker.sock", "/var/run/docker.sock")
+                                )
+                        )
+                )
+                .linkedRepositories("RED / " + SERVICE_NAME)
+
+                .triggers(new BitbucketServerTrigger())
+                .planBranchManagement(new PlanBranchManagement()
+                        .createForVcsBranch()
+                        .delete(new BranchCleanup()
+                                .whenInactiveInRepositoryAfterDays(14))
+                        .notificationForCommitters());
+    }
+}

bamboo-specs/src/test/java/buildjob/PlanSpecTest.java

@@ -0,0 +1,17 @@
+package buildjob;
+
+
+import org.junit.Test;
+
+import com.atlassian.bamboo.specs.api.builders.plan.Plan;
+import com.atlassian.bamboo.specs.api.exceptions.PropertiesValidationException;
+import com.atlassian.bamboo.specs.api.util.EntityPropertiesBuilders;
+
+public class PlanSpecTest {
+    @Test
+    public void checkYourPlanOffline() throws PropertiesValidationException {
+        Plan plan = new PlanSpec().createPlan();
+
+        EntityPropertiesBuilders.build(plan);
+    }
+}

buildSrc/build.gradle.kts

@@ -1,7 +0,0 @@
-plugins {
-    `kotlin-dsl`
-}
-
-repositories {
-    gradlePluginPortal()
-}

buildSrc/src/main/kotlin/com.iqser.red.service.java-conventions.gradle.kts

@@ -1,56 +0,0 @@
-plugins {
-    `java-library`
-    `maven-publish`
-    pmd
-    checkstyle
-    jacoco
-}
-
-group = "com.iqser.red.service"
-
-java.sourceCompatibility = JavaVersion.VERSION_17
-java.targetCompatibility = JavaVersion.VERSION_17
-
-tasks.pmdMain {
-    pmd.ruleSetFiles = files("${rootDir}/config/pmd/pmd.xml")
-}
-
-tasks.pmdTest {
-    pmd.ruleSetFiles = files("${rootDir}/config/pmd/test_pmd.xml")
-}
-
-tasks.named<Test>("test") {
-    useJUnitPlatform()
-    reports {
-        junitXml.outputLocation.set(layout.buildDirectory.dir("reports/junit"))
-    }
-}
-
-tasks.test {
-    finalizedBy(tasks.jacocoTestReport) // report is always generated after tests run
-}
-
-tasks.jacocoTestReport {
-    dependsOn(tasks.test) // tests are required to run before generating the report
-    reports {
-        xml.required.set(true)
-        csv.required.set(false)
-        html.outputLocation.set(layout.buildDirectory.dir("jacocoHtml"))
-    }
-}
-
-java {
-    withJavadocJar()
-}
-
-repositories {
-    mavenLocal()
-    mavenCentral()
-    maven {
-        url = uri("https://nexus.knecon.com/repository/gindev/");
-        credentials {
-            username = providers.gradleProperty("mavenUser").getOrNull();
-            password = providers.gradleProperty("mavenPassword").getOrNull();
-        }
-    }
-}

config/checkstyle/checkstyle.xml

@@ -1,39 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE module PUBLIC "-//Puppy Crawl//DTD Check Configuration 1.3//EN"
-        "http://www.puppycrawl.com/dtds/configuration_1_3.dtd">
-<module name="Checker">
-    <property
-            name="severity"
-            value="error"/>
-    <module name="TreeWalker">
-        <module name="SuppressWarningsHolder"/>
-        <module name="MissingDeprecated"/>
-        <module name="MissingOverride"/>
-        <module name="AnnotationLocation"/>
-        <module name="JavadocStyle"/>
-        <module name="NonEmptyAtclauseDescription"/>
-        <module name="IllegalImport"/>
-        <module name="RedundantImport"/>
-        <module name="RedundantModifier"/>
-        <module name="EmptyBlock"/>
-        <module name="DefaultComesLast"/>
-        <module name="EmptyStatement"/>
-        <module name="EqualsHashCode"/>
-        <module name="ExplicitInitialization"/>
-        <module name="IllegalInstantiation"/>
-        <module name="ModifiedControlVariable"/>
-        <module name="MultipleVariableDeclarations"/>
-        <module name="PackageDeclaration"/>
-        <module name="ParameterAssignment"/>
-        <module name="SimplifyBooleanExpression"/>
-        <module name="SimplifyBooleanReturn"/>
-        <module name="StringLiteralEquality"/>
-        <module name="OneStatementPerLine"/>
-        <module name="FinalClass"/>
-        <module name="ArrayTypeStyle"/>
-        <module name="UpperEll"/>
-        <module name="OuterTypeFilename"/>
-    </module>
-    <module name="FileTabCharacter"/>
-    <module name="SuppressWarningsFilter"/>
-</module>

config/pmd/pmd.xml

@@ -1,21 +0,0 @@
-<?xml version="1.0"?>
-<ruleset name="Custom ruleset"
-         xmlns="http://pmd.sourceforge.net/ruleset/2.0.0"
-         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
-         xsi:schemaLocation="http://pmd.sourceforge.net/ruleset/2.0.0 http://pmd.sourceforge.net/ruleset_2_0_0.xsd">
-
-    <description>
-        Knecon ruleset checks the code for bad stuff
-    </description>
-
-    <rule ref="category/java/errorprone.xml">
-        <exclude name="DataflowAnomalyAnalysis"/>
-        <exclude name="MissingSerialVersionUID"/>
-        <exclude name="NullAssignment"/>
-        <exclude name="AvoidLiteralsInIfCondition"/>
-        <exclude name="AvoidDuplicateLiterals"/>
-        <exclude name="AvoidFieldNameMatchingMethodName"/>
-        <exclude name="AssignmentInOperand"/>
-    </rule>
-
-</ruleset>

config/pmd/test_pmd.xml

@@ -1,24 +0,0 @@
-<?xml version="1.0"?>
-<ruleset name="Custom ruleset"
-         xmlns="http://pmd.sourceforge.net/ruleset/2.0.0"
-         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
-         xsi:schemaLocation="http://pmd.sourceforge.net/ruleset/2.0.0 http://pmd.sourceforge.net/ruleset_2_0_0.xsd">
-
-    <description>
-        Knecon test ruleset checks the code for bad stuff
-    </description>
-
-
-    <rule ref="category/java/errorprone.xml">
-        <exclude name="DataflowAnomalyAnalysis"/>
-        <exclude name="MissingSerialVersionUID"/>
-        <exclude name="NullAssignment"/>
-        <exclude name="AvoidLiteralsInIfCondition"/>
-        <exclude name="AvoidDuplicateLiterals"/>
-        <exclude name="AvoidFieldNameMatchingMethodName"/>
-        <exclude name="AvoidFieldNameMatchingTypeName"/>
-        <exclude name="AssignmentInOperand"/>
-        <exclude name="TestClassWithoutTestCases"/>
-    </rule>
-
-</ruleset>

gradle.properties.kts

@@ -1 +0,0 @@
-version = 4.0-SNAPSHOT

pom.xml

@@ -0,0 +1,21 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project xmlns="http://maven.apache.org/POM/4.0.0"
+         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+
+    <modelVersion>4.0.0</modelVersion>
+
+    <artifactId>redaction-service</artifactId>
+    <groupId>com.iqser.red.service</groupId>
+    <version>1.0-SNAPSHOT</version>
+
+
+    <packaging>pom</packaging>
+
+    <modules>
+        <module>bamboo-specs</module>
+        <module>redaction-service-v1</module>
+        <module>redaction-service-image-v1</module>
+    </modules>
+
+</project>

publish-custom-image.sh

@@ -1,15 +0,0 @@
-#!/bin/bash
-dir=${PWD##*/}
-gradle assemble
-
-# Get the current Git branch
-branch=$(git rev-parse --abbrev-ref HEAD)
-
-# Get the short commit hash (first 5 characters)
-commit_hash=$(git rev-parse --short=5 HEAD)
-
-# Combine branch and commit hash
-buildName="${branch}-${commit_hash}"
-
-gradle bootBuildImage --cleanCache --publishImage -PbuildbootDockerHostNetwork=true -Pversion=$buildName
-echo "nexus.knecon.com:5001/red/${dir}-server-v1:$buildName"

redaction-service-image-v1/pom.xml

@@ -0,0 +1,97 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project xmlns="http://maven.apache.org/POM/4.0.0"
+         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+    <parent>
+        <groupId>com.iqser.red</groupId>
+        <artifactId>platform-docker-dependency</artifactId>
+        <version>1.0.0</version>
+    </parent>
+    <modelVersion>4.0.0</modelVersion>
+
+    <artifactId>redaction-service-image-v1</artifactId>
+    <groupId>com.iqser.red.service</groupId>
+    <version>1.0-SNAPSHOT</version>
+    <packaging>pom</packaging>
+
+
+    <properties>
+        <service.server>redaction-service-server-v1</service.server>
+        <platform.jar>${service.server}.jar</platform.jar>
+        <docker.skip.push>false</docker.skip.push>
+        <docker.image.name>${docker.image.prefix}/${service.server}</docker.image.name>
+    </properties>
+
+    <build>
+        <plugins>
+            <plugin>
+                <groupId>org.apache.maven.plugins</groupId>
+                <artifactId>maven-dependency-plugin</artifactId>
+            </plugin>
+            <plugin>
+                <groupId>org.apache.maven.plugins</groupId>
+                <artifactId>maven-resources-plugin</artifactId>
+            </plugin>
+            <plugin>
+                <groupId>org.codehaus.mojo</groupId>
+                <artifactId>exec-maven-plugin</artifactId>
+            </plugin>
+            <plugin>
+                <groupId>io.fabric8</groupId>
+                <artifactId>docker-maven-plugin</artifactId>
+            </plugin>
+        </plugins>
+        
+        <pluginManagement>
+            <plugins>
+                <plugin>
+                    <groupId>org.apache.maven.plugins</groupId>
+                    <artifactId>maven-dependency-plugin</artifactId>
+                    <executions>
+                        <execution>
+                            <id>download-platform-jar</id>
+                            <phase>prepare-package</phase>
+                            <goals>
+                                <goal>copy</goal>
+                            </goals>
+                            <configuration>
+                                <artifactItems>
+                                    <dependency>
+                                        <groupId>${project.groupId}</groupId>
+                                        <artifactId>${service.server}</artifactId>
+                                        <version>${project.version}</version>
+                                        <type>jar</type>
+                                        <overWrite>true</overWrite>
+                                        <destFileName>${platform.jar}</destFileName>
+                                    </dependency>
+                                </artifactItems>
+                                <outputDirectory>${docker.build.directory}</outputDirectory>
+                            </configuration>
+                        </execution>
+                    </executions>
+                </plugin>
+                <plugin>
+                    <groupId>io.fabric8</groupId>
+                    <artifactId>docker-maven-plugin</artifactId>
+                    <configuration>
+                        <images>
+                            <image>
+                                <name>${docker.image.name}</name>
+                                <build>
+                                    <dockerFileDir>${docker.build.directory}</dockerFileDir>
+                                    <args>
+                                        <PLATFORM_JAR>${platform.jar}</PLATFORM_JAR>
+                                    </args>
+                                    <tags>
+                                        <tag>${docker.image.version}</tag>
+                                        <tag>latest</tag>
+                                    </tags>
+                                </build>
+                            </image>
+                        </images>
+                    </configuration>
+                </plugin>
+            </plugins>
+        </pluginManagement>
+    </build>
+</project>

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

@@ -0,0 +1,18 @@
+FROM red/base-image:1.0.0
+
+ARG PLATFORM_JAR
+
+ENV PLATFORM_JAR ${PLATFORM_JAR}
+
+ENV USES_ELASTICSEARCH false
+
+COPY ["${PLATFORM_JAR}", "/"]
+
+RUN apt-get update \
+ && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
+    wget cabextract xfonts-utils fonts-liberation \
+ && rm -rf /var/lib/apt/lists/*
+
+RUN curl http://ftp.br.debian.org/debian/pool/contrib/m/msttcorefonts/ttf-mscorefonts-installer_3.7_all.deb -o /tmp/ttf-mscorefonts-installer_3.7_all.deb \
+ && dpkg -i /tmp/ttf-mscorefonts-installer_3.7_all.deb \
+ && rm /tmp/ttf-mscorefonts-installer_3.7_all.deb \

redaction-service-v1/pom.xml

@@ -0,0 +1,55 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project xmlns="http://maven.apache.org/POM/4.0.0"
+         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+    <parent>
+        <artifactId>platform-dependency</artifactId>
+        <groupId>com.iqser.red</groupId>
+        <version>1.0.2</version>
+    </parent>
+    <modelVersion>4.0.0</modelVersion>
+
+    <artifactId>redaction-service-v1</artifactId>
+    <groupId>com.iqser.red.service</groupId>
+    <version>1.0-SNAPSHOT</version>
+
+
+    <packaging>pom</packaging>
+
+    <modules>
+        <module>redaction-service-api-v1</module>
+        <module>redaction-service-server-v1</module>
+    </modules>
+
+    <properties>
+        <pdfbox.version>2.0.21</pdfbox.version>
+    </properties>
+
+
+    <dependencyManagement>
+
+        <dependencies>
+            <dependency>
+                <groupId>com.iqser.red</groupId>
+                <artifactId>platform-commons-dependency</artifactId>
+                <version>1.1.0</version>
+                <scope>import</scope>
+                <type>pom</type>
+            </dependency>
+
+            <dependency>
+                <groupId>org.apache.pdfbox</groupId>
+                <artifactId>pdfbox</artifactId>
+                <version>${pdfbox.version}</version>
+            </dependency>
+            <dependency>
+                <groupId>org.apache.pdfbox</groupId>
+                <artifactId>pdfbox-tools</artifactId>
+                <version>${pdfbox.version}</version>
+            </dependency>
+
+        </dependencies>
+
+    </dependencyManagement>
+
+</project>

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

@@ -1,28 +0,0 @@
-plugins {
-    id("com.iqser.red.service.java-conventions")
-    id("io.freefair.lombok") version "8.2.2"
-}
-
-description = "redaction-service-api-v1"
-
-dependencies {
-    implementation("org.springframework:spring-web:6.0.11")
-    implementation("com.iqser.red.service:persistence-service-internal-api-v1:RED-6725")
-}
-
-publishing {
-    publications {
-        create<MavenPublication>(name) {
-            from(components["java"])
-        }
-    }
-    repositories {
-        maven {
-            url = uri("https://nexus.knecon.com/repository/red-platform-releases/")
-            credentials {
-                username = providers.gradleProperty("mavenUser").getOrNull();
-                password = providers.gradleProperty("mavenPassword").getOrNull();
-            }
-        }
-    }
-}

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

@@ -0,0 +1,21 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project xmlns="http://maven.apache.org/POM/4.0.0"
+         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+    <modelVersion>4.0.0</modelVersion>
+    <parent>
+        <artifactId>redaction-service-v1</artifactId>
+        <groupId>com.iqser.red.service</groupId>
+        <version>1.0-SNAPSHOT</version>
+    </parent>
+
+    <artifactId>redaction-service-api-v1</artifactId>
+
+    <dependencies>
+        <dependency>
+            <groupId>org.springframework</groupId>
+            <artifactId>spring-web</artifactId>
+            <optional>true</optional>
+        </dependency>
+    </dependencies>
+</project>

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

@@ -1,15 +0,0 @@
-package com.iqser.red.service.redaction.v1.model;
-
-public enum ArgumentType {
-
-    INTEGER,
-    BOOLEAN,
-    STRING,
-    FILE_ATTRIBUTE,
-    REGEX,
-    TYPE,
-    RULE_NUMBER,
-    LEGAL_BASIS,
-    REFERENCE_TYPE
-
-}

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

@@ -0,0 +1,16 @@
+package com.iqser.red.service.redaction.v1.model;
+
+import lombok.AllArgsConstructor;
+import lombok.Data;
+import lombok.NoArgsConstructor;
+
+@Data
+@AllArgsConstructor
+@NoArgsConstructor
+public class CellRectangle {
+
+    private Point topLeft;
+    private float width;
+    private float height;
+
+}

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

@@ -1,20 +1,21 @@
 package com.iqser.red.service.redaction.v1.model;
 
-import lombok.AccessLevel;
+import java.time.OffsetDateTime;
+
 import lombok.AllArgsConstructor;
 import lombok.Builder;
 import lombok.Data;
 import lombok.NoArgsConstructor;
-import lombok.experimental.FieldDefaults;
 
 @Data
 @Builder
 @AllArgsConstructor
 @NoArgsConstructor
-@FieldDefaults(level = AccessLevel.PRIVATE)
-public class DroolsSyntaxErrorMessage {
+public class Comment {
+
+    private String id;
+    private OffsetDateTime date;
+    private String text;
+    private String user;
 
-    Integer line;
-    Integer column;
-    String message;
 }

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

@@ -1,21 +0,0 @@
-package com.iqser.red.service.redaction.v1.model;
-
-import java.util.List;
-
-import lombok.AccessLevel;
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.Data;
-import lombok.NoArgsConstructor;
-import lombok.experimental.FieldDefaults;
-
-@Data
-@Builder
-@NoArgsConstructor
-@AllArgsConstructor
-@FieldDefaults(level = AccessLevel.PRIVATE)
-public class DroolsSyntaxValidation {
-
-    boolean compiled;
-    List<DroolsSyntaxErrorMessage> droolsSyntaxErrorMessages;
-}

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

@@ -0,0 +1,19 @@
+package com.iqser.red.service.redaction.v1.model;
+
+import lombok.AllArgsConstructor;
+import lombok.Builder;
+import lombok.Data;
+import lombok.NoArgsConstructor;
+
+@Data
+@Builder
+@AllArgsConstructor
+@NoArgsConstructor
+public class IdRemoval {
+
+    private String id;
+    private String user;
+    private Status status;
+    private boolean removeFromDictionary;
+
+}

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

@@ -0,0 +1,30 @@
+package com.iqser.red.service.redaction.v1.model;
+
+import java.util.ArrayList;
+import java.util.List;
+
+import lombok.AllArgsConstructor;
+import lombok.Builder;
+import lombok.Data;
+import lombok.NoArgsConstructor;
+
+@Data
+@Builder
+@AllArgsConstructor
+@NoArgsConstructor
+public class ManualRedactionEntry {
+
+    private String id;
+    private String user;
+    private String type;
+    private String value;
+    private String reason;
+    private String legalBasis;
+    private List<Rectangle> positions = new ArrayList<>();
+    private Status status;
+    private boolean addToDictionary;
+
+    private String section;
+    private int sectionNumber;
+
+}

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

@@ -0,0 +1,5 @@
+package com.iqser.red.service.redaction.v1.model;
+
+public enum ManualRedactionType {
+    ADD, REMOVE
+}

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

@@ -0,0 +1,29 @@
+package com.iqser.red.service.redaction.v1.model;
+
+import java.util.HashMap;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Map;
+import java.util.Set;
+
+import lombok.AllArgsConstructor;
+import lombok.Builder;
+import lombok.Data;
+import lombok.NoArgsConstructor;
+
+@Data
+@Builder
+@AllArgsConstructor
+@NoArgsConstructor
+public class ManualRedactions {
+
+    @Builder.Default
+    private Set<IdRemoval> idsToRemove = new HashSet<>();
+
+    @Builder.Default
+    private Set<ManualRedactionEntry> entriesToAdd = new HashSet<>();
+
+    @Builder.Default
+    private Map<String, List<Comment>> comments = new HashMap<>();
+
+}

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

@@ -5,11 +5,11 @@ import lombok.Data;
 import lombok.NoArgsConstructor;
 
 @Data
-@NoArgsConstructor
 @AllArgsConstructor
-public class Argument {
+@NoArgsConstructor
+public class Point {
 
-    private String name;
-    private ArgumentType type;
+    private float x;
+    private float y;
 
 }

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

@@ -0,0 +1,17 @@
+package com.iqser.red.service.redaction.v1.model;
+
+import lombok.AllArgsConstructor;
+import lombok.Data;
+import lombok.NoArgsConstructor;
+
+@Data
+@AllArgsConstructor
+@NoArgsConstructor
+public class Rectangle {
+
+    private Point topLeft;
+    private float width;
+    private float height;
+
+    private int page;
+}

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

@@ -0,0 +1,29 @@
+package com.iqser.red.service.redaction.v1.model;
+
+import java.util.List;
+
+import lombok.AllArgsConstructor;
+import lombok.Data;
+import lombok.NoArgsConstructor;
+
+@Data
+@AllArgsConstructor
+@NoArgsConstructor
+public class RedactionLog {
+
+    public RedactionLog(List<RedactionLogEntry> redactionLogEntry, long dictionaryVersion, long rulesVersion) {
+
+        this.redactionLogEntry = redactionLogEntry;
+        this.dictionaryVersion = dictionaryVersion;
+        this.rulesVersion = rulesVersion;
+    }
+
+    private List<RedactionLogEntry> redactionLogEntry;
+
+    private long dictionaryVersion = -1;
+
+    private long rulesVersion = -1;
+
+    private String filename;
+
+}

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

@@ -0,0 +1,36 @@
+package com.iqser.red.service.redaction.v1.model;
+
+import java.util.ArrayList;
+import java.util.List;
+
+import lombok.AllArgsConstructor;
+import lombok.Builder;
+import lombok.Data;
+import lombok.NoArgsConstructor;
+
+@Data
+@Builder
+@NoArgsConstructor
+@AllArgsConstructor
+public class RedactionLogEntry {
+
+    private String id;
+    private String type;
+    private String value;
+    private String reason;
+    private int matchedRule;
+    private String legalBasis;
+    private boolean redacted;
+    private boolean isHint;
+    private boolean isRecommendation;
+    private String section;
+    private float[] color;
+
+    @Builder.Default
+    private List<Rectangle> positions = new ArrayList<>();
+    private int sectionNumber;
+    private boolean manual;
+    private Status status;
+    private ManualRedactionType manualRedactionType;
+
+}

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

@@ -9,10 +9,9 @@ import lombok.NoArgsConstructor;
 @Builder
 @NoArgsConstructor
 @AllArgsConstructor
-public class StructureAnalyzeRequest {
-
-    private String dossierId;
-    private String fileId;
+public class RedactionRequest {
 
+    private byte[] document;
+    private boolean flatRedaction;
+    private ManualRedactions manualRedactions;
 }
-

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

@@ -1,4 +1,4 @@
-package com.iqser.red.service.redaction.v1.server.annotate;
+package com.iqser.red.service.redaction.v1.model;
 
 import lombok.AllArgsConstructor;
 import lombok.Builder;
@@ -9,8 +9,11 @@ import lombok.NoArgsConstructor;
 @Builder
 @NoArgsConstructor
 @AllArgsConstructor
-public class AnnotateResponse {
+public class RedactionResult {
 
     private byte[] document;
+    private int numberOfPages;
+    private RedactionLog redactionLog;
+    private SectionGrid sectionGrid;
 
 }

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

@@ -1,14 +0,0 @@
-package com.iqser.red.service.redaction.v1.model;
-
-import lombok.Data;
-
-import java.util.ArrayList;
-import java.util.List;
-
-@Data
-public class RuleBuilderModel {
-
-    private List<RuleElement> whenClauses = new ArrayList<>();
-    private List<RuleElement> thenConditions = new ArrayList<>();
-
-}

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

@@ -1,18 +1,18 @@
 package com.iqser.red.service.redaction.v1.model;
 
+import java.util.HashMap;
+import java.util.List;
+import java.util.Map;
+
 import lombok.AllArgsConstructor;
 import lombok.Data;
 import lombok.NoArgsConstructor;
 
-import java.util.ArrayList;
-import java.util.List;
-
 @Data
-@NoArgsConstructor
 @AllArgsConstructor
-public class RuleElement {
+@NoArgsConstructor
+public class SectionGrid {
 
-    private String conditionName;
-    private List<Argument> arguments = new ArrayList<>();
+    private Map<Integer, List<SectionRectangle>> rectanglesPerPage = new HashMap<>();
 
 }

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

@@ -0,0 +1,33 @@
+package com.iqser.red.service.redaction.v1.model;
+
+import java.util.List;
+
+import lombok.AllArgsConstructor;
+import lombok.Data;
+import lombok.NoArgsConstructor;
+import lombok.NonNull;
+import lombok.RequiredArgsConstructor;
+
+@Data
+@AllArgsConstructor
+@NoArgsConstructor
+@RequiredArgsConstructor
+public class SectionRectangle {
+
+    @NonNull
+    private Point topLeft;
+
+    @NonNull
+    private float width;
+
+    @NonNull
+    private float height;
+
+    @NonNull
+    private int part;
+
+    @NonNull
+    private int numberOfParts;
+
+    private List<CellRectangle> tableCells;
+}

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

@@ -0,0 +1,5 @@
+package com.iqser.red.service.redaction.v1.model;
+
+public enum Status {
+    REQUESTED, APPROVED, DECLINED
+}

redaction-service-v1/redaction-service-api-v1/src/main/java/com/iqser/red/service/redaction/v1/resources/RedactionResource.java

@@ -4,11 +4,26 @@ import org.springframework.http.MediaType;
 import org.springframework.web.bind.annotation.PostMapping;
 import org.springframework.web.bind.annotation.RequestBody;
 
-import com.iqser.red.service.redaction.v1.model.DroolsSyntaxValidation;
+import com.iqser.red.service.redaction.v1.model.RedactionRequest;
+import com.iqser.red.service.redaction.v1.model.RedactionResult;
 
 public interface RedactionResource {
 
-    @PostMapping(value = "/rules/test", consumes = MediaType.APPLICATION_JSON_VALUE)
-    DroolsSyntaxValidation testRules(@RequestBody String rules);
+    String SERVICE_NAME = "redaction-service-v1";
 
-}
+    @PostMapping(value = "/redact", produces = MediaType.APPLICATION_JSON_VALUE, consumes = MediaType.APPLICATION_JSON_VALUE)
+    RedactionResult redact(@RequestBody RedactionRequest redactionRequest);
+
+    @PostMapping(value = "/debug/classifications", produces = MediaType.APPLICATION_JSON_VALUE, consumes = MediaType.APPLICATION_JSON_VALUE)
+    RedactionResult classify(@RequestBody RedactionRequest redactionRequest);
+
+    @PostMapping(value = "/debug/sections", produces = MediaType.APPLICATION_JSON_VALUE, consumes = MediaType.APPLICATION_JSON_VALUE)
+    RedactionResult sections(@RequestBody RedactionRequest redactionRequest);
+
+    @PostMapping(value = "/debug/htmlTables", produces = MediaType.APPLICATION_JSON_VALUE, consumes = MediaType.APPLICATION_JSON_VALUE)
+    RedactionResult htmlTables(@RequestBody RedactionRequest redactionRequest);
+
+    @PostMapping(value = "/rules/update", consumes = MediaType.APPLICATION_JSON_VALUE)
+    void updateRules(@RequestBody String rules);
+
+}

redaction-service-v1/redaction-service-api-v1/src/main/java/com/iqser/red/service/redaction/v1/resources/RuleBuilderResource.java

@@ -1,13 +0,0 @@
-package com.iqser.red.service.redaction.v1.resources;
-
-import com.iqser.red.service.redaction.v1.model.RuleBuilderModel;
-
-import org.springframework.http.MediaType;
-import org.springframework.web.bind.annotation.PostMapping;
-
-public interface RuleBuilderResource {
-
-    @PostMapping(value = "/rule-builder-model", produces = MediaType.APPLICATION_JSON_VALUE)
-    RuleBuilderModel getRuleBuilderModel();
-
-}

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

@@ -1,95 +0,0 @@
-import org.springframework.boot.gradle.tasks.bundling.BootBuildImage
-
-plugins {
-    application
-    id("com.iqser.red.service.java-conventions")
-    id("org.springframework.boot") version "3.1.2"
-    id("io.spring.dependency-management") version "1.1.3"
-    id("org.sonarqube") version "4.3.0.3225"
-    id("io.freefair.lombok") version "8.2.2"
-}
-
-description = "redaction-service-server-v1"
-
-
-val layoutParserVersion = "0.25.0"
-val jacksonVersion = "2.15.2"
-val droolsVersion = "8.43.0.Final"
-val pdfBoxVersion = "3.0.0-alpha2"
-val persistenceServiceVersion = "2.156.0"
-
-configurations {
-    all {
-        exclude(group = "org.springframework.boot", module = "spring-boot-starter-logging")
-    }
-}
-
-dependencies {
-
-    implementation(project(":redaction-service-api-v1")) { exclude(group = "com.iqser.red.service", module = "persistence-service-internal-api-v1") }
-    implementation("com.iqser.red.service:persistence-service-internal-api-v1:${persistenceServiceVersion}") { exclude(group = "org.springframework.boot") }
-    implementation("com.knecon.fforesight:layoutparser-service-internal-api:${layoutParserVersion}")
-
-    implementation("com.iqser.red.commons:spring-commons:2.7.0")
-    implementation("com.iqser.red.commons:metric-commons:2.3.0")
-
-    implementation("com.iqser.red.commons:dictionary-merge-commons:1.5.0")
-    implementation("com.iqser.red.commons:storage-commons:2.40.0")
-    implementation("com.knecon.fforesight:tenant-commons:0.10.0")
-
-    implementation("com.fasterxml.jackson.module:jackson-module-afterburner:${jacksonVersion}")
-    implementation("com.fasterxml.jackson.datatype:jackson-datatype-jsr310:${jacksonVersion}")
-    implementation("org.ahocorasick:ahocorasick:0.6.3")
-    implementation("org.javassist:javassist:3.29.2-GA")
-
-    implementation("org.drools:drools-engine:${droolsVersion}")
-    implementation("org.drools:drools-mvel:${droolsVersion}")
-    implementation("org.kie:kie-spring:7.74.1.Final")
-
-    implementation("org.locationtech.jts:jts-core:1.19.0")
-
-    implementation("org.springframework.cloud:spring-cloud-starter-openfeign:4.0.4")
-    implementation("org.springframework.boot:spring-boot-starter-amqp:3.1.2")
-
-    testImplementation("org.apache.pdfbox:pdfbox:${pdfBoxVersion}")
-    testImplementation("org.apache.pdfbox:pdfbox-tools:${pdfBoxVersion}")
-
-    testImplementation("org.springframework.boot:spring-boot-starter-test:3.1.2")
-    testImplementation("com.knecon.fforesight:layoutparser-service-processor:${layoutParserVersion}") {
-        exclude(
-            group = "com.iqser.red.service",
-            module = "persistence-service-shared-api-v1"
-        )
-    }
-}
-
-tasks.test {
-    configure<JacocoTaskExtension> {
-        excludes = listOf("org/drools/**/*")
-    }
-}
-
-
-tasks.named<BootBuildImage>("bootBuildImage") {
-
-    environment.put("BPE_DELIM_JAVA_TOOL_OPTIONS", " ")
-    environment.put("BPE_APPEND_JAVA_TOOL_OPTIONS", "-Dfile.encoding=UTF-8")
-
-    imageName.set("nexus.knecon.com:5001/red/${project.name}:${project.version}")
-    if (project.hasProperty("buildbootDockerHostNetwork")) {
-        network.set("host")
-    }
-    docker {
-        if (project.hasProperty("buildbootDockerHostNetwork")) {
-            bindHostToBuilder.set(true)
-        }
-        verboseLogging.set(true)
-
-        publishRegistry {
-            username.set(providers.gradleProperty("mavenUser").getOrNull())
-            password.set(providers.gradleProperty("mavenPassword").getOrNull())
-            email.set(providers.gradleProperty("mavenEmail").getOrNull())
-            url.set("https://nexus.knecon.com:5001/")
-        }
-    }
-}

redaction-service-v1/redaction-service-server-v1/pom.xml

@@ -0,0 +1,150 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+         xmlns="http://maven.apache.org/POM/4.0.0"
+         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+    <modelVersion>4.0.0</modelVersion>
+    <parent>
+        <artifactId>redaction-service-v1</artifactId>
+        <groupId>com.iqser.red.service</groupId>
+        <version>1.0-SNAPSHOT</version>
+    </parent>
+
+    <artifactId>redaction-service-server-v1</artifactId>
+
+    <dependencies>
+        <dependency>
+            <groupId>com.iqser.red.service</groupId>
+            <artifactId>redaction-service-api-v1</artifactId>
+            <version>${project.version}</version>
+        </dependency>
+        <dependency>
+            <groupId>com.iqser.red.service</groupId>
+            <artifactId>configuration-service-api-v1</artifactId>
+            <version>1.3.7</version>
+        </dependency>
+        <dependency>
+            <groupId>org.drools</groupId>
+            <artifactId>drools-core</artifactId>
+            <version>7.37.0.Final</version>
+        </dependency>
+        <dependency>
+            <groupId>org.kie</groupId>
+            <artifactId>kie-spring</artifactId>
+            <version>7.37.0.Final</version>
+        </dependency>
+        <dependency>
+            <groupId>org.locationtech.jts</groupId>
+            <artifactId>jts-core</artifactId>
+            <version>1.16.1</version>
+        </dependency>
+        <dependency>
+            <groupId>com.google.guava</groupId>
+            <artifactId>guava</artifactId>
+            <version>29.0-jre</version>
+        </dependency>
+        <!-- commons -->
+        <dependency>
+            <groupId>com.iqser.red.commons</groupId>
+            <artifactId>spring-commons</artifactId>
+        </dependency>
+        <dependency>
+            <groupId>com.iqser.red.commons</groupId>
+            <artifactId>logging-commons</artifactId>
+        </dependency>
+        <dependency>
+            <groupId>com.iqser.red.commons</groupId>
+            <artifactId>metric-commons</artifactId>
+        </dependency>
+        <!-- other external -->
+        <dependency>
+            <groupId>org.apache.commons</groupId>
+            <artifactId>commons-lang3</artifactId>
+        </dependency>
+        <dependency>
+            <groupId>org.apache.pdfbox</groupId>
+            <artifactId>pdfbox</artifactId>
+        </dependency>
+        <dependency>
+            <groupId>org.apache.pdfbox</groupId>
+            <artifactId>pdfbox-tools</artifactId>
+        </dependency>
+        <!-- spring -->
+        <dependency>
+            <groupId>org.springframework.cloud</groupId>
+            <artifactId>spring-cloud-starter-openfeign</artifactId>
+        </dependency>
+        <!-- ribbon must be included because transitive a dependency on it.-->
+        <dependency>
+            <groupId>org.springframework.cloud</groupId>
+            <artifactId>spring-cloud-starter-netflix-ribbon</artifactId>
+        </dependency>
+        <!-- test dependencies -->
+        <dependency>
+            <groupId>org.springframework.boot</groupId>
+            <artifactId>spring-boot-starter-test</artifactId>
+            <scope>test</scope>
+        </dependency>
+        <dependency>
+            <groupId>com.iqser.red.commons</groupId>
+            <artifactId>test-commons</artifactId>
+            <scope>test</scope>
+        </dependency>
+    </dependencies>
+
+    <build>
+        <plugins>
+            <plugin>
+                <!-- generate git.properties for exposure in /info -->
+                <groupId>pl.project13.maven</groupId>
+                <artifactId>git-commit-id-plugin</artifactId>
+                <executions>
+                    <execution>
+                        <goals>
+                            <goal>revision</goal>
+                        </goals>
+                        <configuration>
+                            <generateGitPropertiesFile>true</generateGitPropertiesFile>
+                            <gitDescribe>
+                                <tags>true</tags>
+                            </gitDescribe>
+                        </configuration>
+                    </execution>
+                </executions>
+            </plugin>
+
+            <plugin>
+                <groupId>org.apache.maven.plugins</groupId>
+                <artifactId>maven-jar-plugin</artifactId>
+                <executions>
+                    <execution>
+                        <id>original-jar</id>
+                        <goals>
+                            <goal>jar</goal>
+                        </goals>
+                        <configuration>
+                            <classifier>original</classifier>
+                        </configuration>
+                    </execution>
+                </executions>
+            </plugin>
+
+            <plugin>
+                <!-- repackages the generated jar into a runnable fat-jar and makes it
+                    executable -->
+                <groupId>org.springframework.boot</groupId>
+                <artifactId>spring-boot-maven-plugin</artifactId>
+                <executions>
+                    <execution>
+                        <goals>
+                            <goal>repackage</goal>
+                        </goals>
+                        <configuration>
+                            <executable>true</executable>
+                        </configuration>
+                    </execution>
+                </executions>
+            </plugin>
+        </plugins>
+    </build>
+
+</project>

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

@@ -1,8 +1,19 @@
 package com.iqser.red.service.redaction.v1.server;
 
+import java.io.ByteArrayInputStream;
+import java.io.InputStream;
+import java.nio.charset.StandardCharsets;
+
+import org.apache.commons.lang3.StringUtils;
+import org.kie.api.KieServices;
+import org.kie.api.builder.KieBuilder;
+import org.kie.api.builder.KieFileSystem;
+import org.kie.api.builder.KieModule;
+import org.kie.api.runtime.KieContainer;
+import org.springframework.beans.factory.annotation.Autowired;
 import org.springframework.boot.SpringApplication;
+import org.springframework.boot.actuate.autoconfigure.metrics.web.servlet.WebMvcMetricsAutoConfiguration;
 import org.springframework.boot.actuate.autoconfigure.security.servlet.ManagementWebSecurityAutoConfiguration;
-import org.springframework.boot.autoconfigure.ImportAutoConfiguration;
 import org.springframework.boot.autoconfigure.SpringBootApplication;
 import org.springframework.boot.autoconfigure.security.servlet.SecurityAutoConfiguration;
 import org.springframework.boot.context.properties.EnableConfigurationProperties;
@@ -10,39 +21,51 @@ import org.springframework.cloud.openfeign.EnableFeignClients;
 import org.springframework.context.annotation.Bean;
 import org.springframework.context.annotation.Import;
 
-import com.iqser.red.service.dictionarymerge.commons.DictionaryMergeService;
+import com.iqser.red.commons.spring.DefaultWebMvcConfiguration;
+import com.iqser.red.service.configuration.v1.api.model.RulesResponse;
 import com.iqser.red.service.redaction.v1.server.client.RulesClient;
+import com.iqser.red.service.redaction.v1.server.exception.RulesValidationException;
 import com.iqser.red.service.redaction.v1.server.settings.RedactionServiceSettings;
-import com.iqser.red.storage.commons.StorageAutoConfiguration;
-import com.knecon.fforesight.tenantcommons.MultiTenancyAutoConfiguration;
 
-import io.micrometer.core.aop.TimedAspect;
-import io.micrometer.core.instrument.MeterRegistry;
-
-@ImportAutoConfiguration({MultiTenancyAutoConfiguration.class})
-@Import({MetricsConfiguration.class, StorageAutoConfiguration.class})
+@Import({DefaultWebMvcConfiguration.class})
 @EnableFeignClients(basePackageClasses = RulesClient.class)
 @EnableConfigurationProperties(RedactionServiceSettings.class)
-@SpringBootApplication(exclude = {SecurityAutoConfiguration.class, ManagementWebSecurityAutoConfiguration.class})
+@SpringBootApplication(exclude = {SecurityAutoConfiguration.class, ManagementWebSecurityAutoConfiguration.class, WebMvcMetricsAutoConfiguration.class})
 public class Application {
 
+    @Autowired
+    private RulesClient rulesClient;
+
+
     public static void main(String[] args) {
 
-        System.setProperty("org.apache.pdfbox.rendering.UsePureJavaCMYKConversion", "true");
         SpringApplication.run(Application.class, args);
     }
 
 
     @Bean
-    public TimedAspect timedAspect(MeterRegistry registry) {
+    public KieContainer kieContainer() {
+
+        try {
+            KieServices kieServices = KieServices.Factory.get();
+
+            KieFileSystem kieFileSystem = kieServices.newKieFileSystem();
+            RulesResponse rules = rulesClient.getRules();
+            if (StringUtils.isEmpty(rules.getRules())) {
+                throw new RuntimeException("Rules cannot be empty.");
+            }
+            InputStream input = new ByteArrayInputStream(rules.getRules().getBytes(StandardCharsets.UTF_8));
+            kieFileSystem.write("src/main/resources/drools/rules.drl", kieServices.getResources()
+                    .newInputStreamResource(input));
+            KieBuilder kieBuilder = kieServices.newKieBuilder(kieFileSystem);
+            kieBuilder.buildAll();
+            KieModule kieModule = kieBuilder.getKieModule();
+
+            return kieServices.newKieContainer(kieModule.getReleaseId());
+        } catch (Exception e) {
+            throw new RulesValidationException("Could not update rules: " + e.getMessage(), e);
+        }
 
-        return new TimedAspect(registry);
     }
 
-    @Bean
-    public DictionaryMergeService dictionaryMergeService() {
-
-        return new DictionaryMergeService();
-    }
-
-}
+}

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

@@ -1,26 +0,0 @@
-package com.iqser.red.service.redaction.v1.server;
-
-import org.springframework.beans.factory.annotation.Qualifier;
-import org.springframework.context.annotation.Bean;
-import org.springframework.context.annotation.Configuration;
-import org.springframework.context.annotation.Import;
-
-import com.iqser.gin4.commons.metrics.MetricCommonsConfiguration;
-import com.iqser.gin4.commons.metrics.meters.FunctionTimerFactory;
-import com.iqser.gin4.commons.metrics.meters.FunctionTimerValues;
-
-@Configuration
-@Import({MetricCommonsConfiguration.class})
-public class MetricsConfiguration {
-
-    private static final String REDACTMANAGER_ANALYZE_PAGEWISE_METRIC_NAME = "redactmanager_analyze.pagewise";
-
-
-    @Bean
-    @Qualifier(REDACTMANAGER_ANALYZE_PAGEWISE_METRIC_NAME)
-    public FunctionTimerValues redactmanagerAnalyzePagewise(FunctionTimerFactory factory) {
-
-        return factory.create(REDACTMANAGER_ANALYZE_PAGEWISE_METRIC_NAME);
-    }
-
-}

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

@@ -0,0 +1,32 @@
+package com.iqser.red.service.redaction.v1.server.classification.model;
+
+import java.util.ArrayList;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Map;
+
+import com.iqser.red.service.redaction.v1.model.RedactionLogEntry;
+import com.iqser.red.service.redaction.v1.model.SectionGrid;
+import com.iqser.red.service.redaction.v1.server.redaction.model.Entity;
+
+import lombok.Data;
+import lombok.NoArgsConstructor;
+
+@Data
+@NoArgsConstructor
+public class Document {
+
+    private List<Page> pages = new ArrayList<>();
+    private List<Paragraph> paragraphs = new ArrayList<>();
+    private Map<Integer, List<Entity>> entities = new HashMap<>();
+    private FloatFrequencyCounter textHeightCounter = new FloatFrequencyCounter();
+    private FloatFrequencyCounter fontSizeCounter= new FloatFrequencyCounter();
+    private StringFrequencyCounter fontCounter= new StringFrequencyCounter();
+    private StringFrequencyCounter fontStyleCounter = new StringFrequencyCounter();
+    private boolean headlines;
+
+    private List<RedactionLogEntry> redactionLogEntities = new ArrayList<>();
+    private SectionGrid sectionGrid = new SectionGrid();
+    private long dictionaryVersion;
+    private long rulesVersion;
+}

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

@@ -0,0 +1,75 @@
+package com.iqser.red.service.redaction.v1.server.classification.model;
+
+import java.util.ArrayList;
+import java.util.Collections;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Map;
+import java.util.stream.Collectors;
+
+import lombok.Getter;
+
+public class FloatFrequencyCounter
+{
+
+    @Getter
+    Map<Float, Integer> countPerValue = new HashMap<>();
+
+    public void add(float value){
+        if(!countPerValue.containsKey(value)){
+            countPerValue.put(value, 1);
+        } else {
+            countPerValue.put(value, countPerValue.get(value) + 1);
+        }
+    }
+
+    public void addAll(Map<Float, Integer> otherCounter){
+        for(Map.Entry<Float, Integer> entry: otherCounter.entrySet()){
+            if(countPerValue.containsKey(entry.getKey())){
+                countPerValue.put(entry.getKey(), countPerValue.get(entry.getKey())+ entry.getValue());
+            } else {
+                countPerValue.put(entry.getKey(), entry.getValue());
+            }
+        }
+    }
+
+    public Float getMostPopular(){
+        Map.Entry<Float, Integer> mostPopular = null;
+        for(Map.Entry<Float, Integer> entry: countPerValue.entrySet()){
+            if(mostPopular == null){
+                mostPopular = entry;
+            } else if(entry.getValue() >= mostPopular.getValue()){
+                mostPopular = entry;
+            }
+        }
+        return mostPopular != null ? mostPopular.getKey() : null;
+    }
+
+
+
+    public List<Float> getHighterThanMostPopular(){
+        Float mostPopular = getMostPopular();
+        List<Float> higher = new ArrayList<>();
+        for(Float value: countPerValue.keySet()){
+            if(value > mostPopular){
+                higher.add(value);
+            }
+        }
+
+        return higher.stream().sorted(Collections.reverseOrder()).collect(Collectors.toList());
+    }
+
+
+    public Float getHighest(){
+        Float highest = null;
+        for(Float value: countPerValue.keySet()){
+            if (highest == null){
+                highest = value;
+            } else if(value > highest){
+                highest = value;
+            }
+        }
+        return highest;
+    }
+
+}

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

@@ -0,0 +1,35 @@
+package com.iqser.red.service.redaction.v1.server.classification.model;
+
+import java.util.List;
+
+import com.iqser.red.service.redaction.v1.server.tableextraction.model.AbstractTextContainer;
+import com.iqser.red.service.redaction.v1.server.tableextraction.model.Rectangle;
+
+import lombok.Data;
+import lombok.NonNull;
+import lombok.RequiredArgsConstructor;
+
+@Data
+@RequiredArgsConstructor
+public class Page {
+
+    @NonNull
+    private List<AbstractTextContainer> textBlocks;
+
+    private Rectangle bodyTextFrame;
+
+    private boolean landscape;
+    private int rotation;
+
+    private int pageNumber;
+
+    private FloatFrequencyCounter textHeightCounter = new FloatFrequencyCounter();
+    private FloatFrequencyCounter fontSizeCounter = new FloatFrequencyCounter();
+    private StringFrequencyCounter fontCounter = new StringFrequencyCounter();
+    private StringFrequencyCounter fontStyleCounter = new StringFrequencyCounter();
+
+    public boolean isRotated() {
+        return rotation != 0;
+    }
+
+}

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

@@ -0,0 +1,56 @@
+package com.iqser.red.service.redaction.v1.server.classification.model;
+
+import java.util.ArrayList;
+import java.util.List;
+
+import com.iqser.red.service.redaction.v1.server.redaction.model.SearchableText;
+import com.iqser.red.service.redaction.v1.server.tableextraction.model.AbstractTextContainer;
+import com.iqser.red.service.redaction.v1.server.tableextraction.model.Table;
+
+import lombok.Data;
+import lombok.NoArgsConstructor;
+
+@Data
+@NoArgsConstructor
+public class Paragraph {
+
+    private List<AbstractTextContainer> pageBlocks = new ArrayList<>();
+    private String headline;
+
+
+    public SearchableText getSearchableText() {
+
+        SearchableText searchableText = new SearchableText();
+        pageBlocks.forEach(block -> {
+            if (block instanceof TextBlock) {
+                searchableText.addAll(((TextBlock) block).getSequences());
+            }
+        });
+        return searchableText;
+    }
+
+
+    public List<Table> getTables() {
+
+        List<Table> tables = new ArrayList<>();
+        pageBlocks.forEach(block -> {
+            if (block instanceof Table) {
+                tables.add((Table) block);
+            }
+        });
+        return tables;
+    }
+
+
+    public List<TextBlock> getTextBlocks() {
+
+        List<TextBlock> textBlocks = new ArrayList<>();
+        pageBlocks.forEach(block -> {
+            if (block instanceof TextBlock) {
+                textBlocks.add((TextBlock) block);
+            }
+        });
+        return textBlocks;
+    }
+
+}

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

@@ -0,0 +1,49 @@
+package com.iqser.red.service.redaction.v1.server.classification.model;
+
+import java.util.HashMap;
+import java.util.Map;
+
+import lombok.Getter;
+
+public class StringFrequencyCounter {
+
+    @Getter
+    private final Map<String, Integer> countPerValue = new HashMap<>();
+
+
+    public void add(String value) {
+
+        if (!countPerValue.containsKey(value)) {
+            countPerValue.put(value, 1);
+        } else {
+            countPerValue.put(value, countPerValue.get(value) + 1);
+        }
+    }
+
+
+    public void addAll(Map<String, Integer> otherCounter) {
+
+        for (Map.Entry<String, Integer> entry : otherCounter.entrySet()) {
+            if (countPerValue.containsKey(entry.getKey())) {
+                countPerValue.put(entry.getKey(), countPerValue.get(entry.getKey()) + entry.getValue());
+            } else {
+                countPerValue.put(entry.getKey(), entry.getValue());
+            }
+        }
+    }
+
+
+    public String getMostPopular() {
+
+        Map.Entry<String, Integer> mostPopular = null;
+        for (Map.Entry<String, Integer> entry : countPerValue.entrySet()) {
+            if (mostPopular == null) {
+                mostPopular = entry;
+            } else if (entry.getValue() > mostPopular.getValue()) {
+                mostPopular = entry;
+            }
+        }
+        return mostPopular != null ? mostPopular.getKey() : null;
+    }
+
+}

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

@@ -0,0 +1,142 @@
+package com.iqser.red.service.redaction.v1.server.classification.model;
+
+import java.util.ArrayList;
+import java.util.List;
+
+import com.iqser.red.service.redaction.v1.server.parsing.model.TextPositionSequence;
+import com.iqser.red.service.redaction.v1.server.tableextraction.model.AbstractTextContainer;
+import com.iqser.red.service.redaction.v1.server.redaction.utils.TextNormalizationUtilities;
+
+import lombok.AllArgsConstructor;
+import lombok.Builder;
+import lombok.Data;
+
+@AllArgsConstructor
+@Builder
+@Data
+public class TextBlock extends AbstractTextContainer {
+
+    @Builder.Default
+    private List<TextPositionSequence> sequences = new ArrayList<>();
+    private int rotation;
+
+    private String mostPopularWordFont;
+    private String mostPopularWordStyle;
+    private float mostPopularWordFontSize;
+    private float mostPopularWordHeight;
+    private float mostPopularWordSpaceWidth;
+
+    private float highestFontSize;
+
+    private String classification;
+
+    public TextBlock(float minX, float maxX, float minY, float maxY, List<TextPositionSequence> sequences, int rotation) {
+        this.minX = minX;
+        this.maxX = maxX;
+        this.minY = minY;
+        this.maxY = maxY;
+        this.sequences = sequences;
+        this.rotation = rotation;
+    }
+
+    public TextBlock union(TextPositionSequence r) {
+        TextBlock union = this.copy();
+        union.add(r);
+        return union;
+    }
+
+    public TextBlock union(TextBlock r) {
+        TextBlock union = this.copy();
+        union.add(r);
+        return union;
+    }
+
+    public void add(TextBlock r) {
+        if (r.getMinX() < minX) {
+            minX = r.getMinX();
+        }
+        if (r.getMaxX() > maxX) {
+            maxX = r.getMaxX();
+        }
+        if (r.getMinY() < minY) {
+            minY = r.getMinY();
+        }
+        if (r.getMaxY() > maxY) {
+            maxY = r.getMaxY();
+        }
+        sequences.addAll(r.getSequences());
+    }
+
+    public void add(TextPositionSequence r) {
+        if (r.getX1() < minX) {
+            minX = r.getX1();
+        }
+        if (r.getX2() > maxX) {
+            maxX = r.getX2();
+        }
+        if (r.getY1() < minY) {
+            minY = r.getY1();
+        }
+        if (r.getY2() > maxY) {
+            maxY = r.getY2();
+        }
+    }
+
+    public TextBlock copy() {
+        return new TextBlock(minX, maxX, minY, maxY, sequences, rotation);
+    }
+
+    public void resize(float x1, float y1, float width, float height) {
+        set(x1, y1, x1 + width, y1 + height);
+    }
+
+    public void set(float x1, float y1, float x2, float y2) {
+        this.minX = Math.min(x1, x2);
+        this.maxX = Math.max(x1, x2);
+        this.minY = Math.min(y1, y2);
+        this.maxY = Math.max(y1, y2);
+    }
+
+
+
+    @Override
+    public String toString() {
+
+        StringBuilder builder = new StringBuilder();
+
+        for (int i = 0; i < sequences.size(); i++) {
+            String sequenceAsString = sequences.get(i).toString();
+            // Fix for missing Whitespace. This is recognized in getSequences method. See PDFTextStripper Line 1730.
+            if (i != 0 && sequences.get(i - 1).charAt(sequences.get(i - 1).length() - 1) != ' ' && sequenceAsString.charAt(0) != ' ') {
+                builder.append(' ');
+            }
+            builder.append(sequenceAsString);
+        }
+
+        return builder.toString();
+
+    }
+
+    @Override
+    public String getText() {
+
+        StringBuilder sb = new StringBuilder();
+
+        TextPositionSequence previous = null;
+        for (TextPositionSequence word : sequences) {
+            if (previous != null) {
+                if (Math.abs(previous.getRotationAdjustedY() - word.getRotationAdjustedY()) > word.getTextHeight()) {
+                    sb.append('\n');
+                } else {
+                    sb.append(' ');
+                }
+            }
+            sb.append(word.toString());
+            previous = word;
+        }
+
+        return TextNormalizationUtilities.removeHyphenLineBreaks(sb.toString());
+
+    }
+
+}

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

@@ -0,0 +1,209 @@
+package com.iqser.red.service.redaction.v1.server.classification.service;
+
+import java.util.ArrayList;
+import java.util.List;
+
+import org.springframework.stereotype.Service;
+
+import com.iqser.red.service.redaction.v1.server.classification.utils.PositionUtils;
+import com.iqser.red.service.redaction.v1.server.classification.model.FloatFrequencyCounter;
+import com.iqser.red.service.redaction.v1.server.classification.model.Page;
+import com.iqser.red.service.redaction.v1.server.classification.model.StringFrequencyCounter;
+import com.iqser.red.service.redaction.v1.server.classification.model.TextBlock;
+import com.iqser.red.service.redaction.v1.server.parsing.model.TextPositionSequence;
+import com.iqser.red.service.redaction.v1.server.tableextraction.model.AbstractTextContainer;
+import com.iqser.red.service.redaction.v1.server.tableextraction.model.Cell;
+import com.iqser.red.service.redaction.v1.server.tableextraction.model.Rectangle;
+import com.iqser.red.service.redaction.v1.server.tableextraction.model.Ruling;
+import com.iqser.red.service.redaction.v1.server.tableextraction.model.Table;
+
+@Service
+@SuppressWarnings("all")
+public class BlockificationService {
+
+    public Page blockify(List<TextPositionSequence> textPositions, List<Ruling> horizontalRulingLines, List<Ruling> verticalRulingLines) {
+
+        List<TextPositionSequence> chunkWords = new ArrayList<>();
+        List<AbstractTextContainer> chunkBlockList1 = new ArrayList<>();
+
+        float minX = 1000, maxX = 0, minY = 1000, maxY = 0;
+        TextPositionSequence prev = null;
+
+        for (TextPositionSequence word : textPositions) {
+
+            boolean lineSeparation = minY - word.getY2() > word.getHeight() * 1.25;
+            boolean startFromTop = word.getY1() > maxY + word.getHeight();
+
+            if (prev != null && (lineSeparation || startFromTop || word.getRotation() == 0 && isSplittedByRuling(maxX, minY, word
+                    .getX1(), word.getY1(), verticalRulingLines) || word.getRotation() == 0 && isSplittedByRuling(minX, minY, word
+                    .getX1(), word.getY2(), horizontalRulingLines) || word.getRotation() == 90 && isSplittedByRuling(maxX, minY, word
+                    .getX1(), word.getY1(), horizontalRulingLines) || word.getRotation() == 90 && isSplittedByRuling(minX, minY, word
+                    .getX1(), word.getY2(), verticalRulingLines))) {
+
+                TextBlock cb1 = buildTextBlock(chunkWords);
+                chunkBlockList1.add(cb1);
+                chunkWords = new ArrayList<>();
+
+                minX = 1000;
+                maxX = 0;
+                minY = 1000;
+                maxY = 0;
+                prev = null;
+            }
+
+            chunkWords.add(word);
+
+            prev = word;
+            if (word.getX1() < minX) {
+                minX = word.getX1();
+            }
+            if (word.getX2() > maxX) {
+                maxX = word.getX2();
+            }
+            if (word.getY1() < minY) {
+                minY = word.getY1();
+            }
+            if (word.getY2() > maxY) {
+                maxY = word.getY2();
+            }
+        }
+
+        TextBlock cb1 = buildTextBlock(chunkWords);
+        if (cb1 != null) {
+            chunkBlockList1.add(cb1);
+        }
+
+        return new Page(chunkBlockList1);
+    }
+
+
+    private TextBlock buildTextBlock(List<TextPositionSequence> wordBlockList) {
+
+        TextBlock textBlock = null;
+
+        FloatFrequencyCounter lineHeightFrequencyCounter = new FloatFrequencyCounter();
+        FloatFrequencyCounter fontSizeFrequencyCounter = new FloatFrequencyCounter();
+        FloatFrequencyCounter spaceFrequencyCounter = new FloatFrequencyCounter();
+        StringFrequencyCounter fontFrequencyCounter = new StringFrequencyCounter();
+        StringFrequencyCounter styleFrequencyCounter = new StringFrequencyCounter();
+
+        for (TextPositionSequence wordBlock : wordBlockList) {
+
+            lineHeightFrequencyCounter.add(wordBlock.getTextHeight());
+            fontSizeFrequencyCounter.add(wordBlock.getFontSize());
+            spaceFrequencyCounter.add(wordBlock.getSpaceWidth());
+            fontFrequencyCounter.add(wordBlock.getFont());
+            styleFrequencyCounter.add(wordBlock.getFontStyle());
+
+            if (textBlock == null) {
+                textBlock = new TextBlock(wordBlock.getX1(), wordBlock.getX2(), wordBlock.getY1(), wordBlock.getY2(), wordBlockList, wordBlock
+                        .getRotation());
+            } else {
+                TextBlock spatialEntity = textBlock.union(wordBlock);
+                textBlock.resize(spatialEntity.getMinX(), spatialEntity.getMinY(), spatialEntity.getWidth(), spatialEntity
+                        .getHeight());
+            }
+        }
+
+        if (textBlock != null) {
+            textBlock.setMostPopularWordFont(fontFrequencyCounter.getMostPopular());
+            textBlock.setMostPopularWordStyle(styleFrequencyCounter.getMostPopular());
+            textBlock.setMostPopularWordFontSize(fontSizeFrequencyCounter.getMostPopular());
+            textBlock.setMostPopularWordHeight(lineHeightFrequencyCounter.getMostPopular());
+            textBlock.setMostPopularWordSpaceWidth(spaceFrequencyCounter.getMostPopular());
+            textBlock.setHighestFontSize(fontSizeFrequencyCounter.getHighest());
+        }
+
+        return textBlock;
+    }
+
+
+    private boolean isSplittedByRuling(float previousX2, float previousY1, float currentX1, float currentY1, List<Ruling> rulingLines) {
+
+        for (Ruling ruling : rulingLines) {
+            if (ruling.intersectsLine(previousX2, previousY1, currentX1, currentY1)) {
+                return true;
+            }
+        }
+        return false;
+    }
+
+
+    public Rectangle calculateBodyTextFrame(List<Page> pages, FloatFrequencyCounter documentFontSizeCounter, boolean landscape) {
+
+        float minX = 10000;
+        float maxX = -100;
+        float minY = 10000;
+        float maxY = -100;
+
+        for (Page page : pages) {
+
+            if (page.getTextBlocks().isEmpty() || landscape != page.isLandscape()) {
+                continue;
+            }
+
+            for (AbstractTextContainer container : page.getTextBlocks()) {
+
+                if (container instanceof TextBlock) {
+                    TextBlock textBlock = (TextBlock) container;
+                    if (textBlock.getMostPopularWordFont() == null || textBlock.getMostPopularWordStyle() == null) {
+                        continue;
+                    }
+
+                    float approxLineCount = PositionUtils.getApproxLineCount(textBlock);
+                    if (approxLineCount < 2.9f) {
+                        continue;
+                    }
+
+                    if (documentFontSizeCounter.getMostPopular() != null) {
+                        if (textBlock.getMostPopularWordFontSize() >= documentFontSizeCounter.getMostPopular()) {
+
+                            if (textBlock.getMinX() < minX) {
+                                minX = textBlock.getMinX();
+                            }
+                            if (textBlock.getMaxX() > maxX) {
+                                maxX = textBlock.getMaxX();
+                            }
+                            if (textBlock.getMinY() < minY) {
+                                minY = textBlock.getMinY();
+                            }
+                            if (textBlock.getMaxY() > maxY) {
+                                maxY = textBlock.getMaxY();
+                            }
+
+                        }
+                    }
+                }
+
+                if (container instanceof Table) {
+                    Table table = (Table) container;
+                    for (List<Cell> row : table.getRows()) {
+                        for (Cell cell : row) {
+
+                            if (cell == null || cell.getTextBlocks() == null) {
+                                continue;
+                            }
+                            for (TextBlock textBlock : cell.getTextBlocks()) {
+                                if (textBlock.getMinX() < minX) {
+                                    minX = textBlock.getMinX();
+                                }
+                                if (textBlock.getMaxX() > maxX) {
+                                    maxX = textBlock.getMaxX();
+                                }
+                                if (textBlock.getMinY() < minY) {
+                                    minY = textBlock.getMinY();
+                                }
+                                if (textBlock.getMaxY() > maxY) {
+                                    maxY = textBlock.getMaxY();
+                                }
+                            }
+                        }
+                    }
+                }
+            }
+
+        }
+        return new Rectangle(minY, minX, maxX - minX, maxY - minY);
+    }
+
+}

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

@@ -0,0 +1,91 @@
+package com.iqser.red.service.redaction.v1.server.classification.service;
+
+import java.util.List;
+import java.util.regex.Pattern;
+
+import org.springframework.stereotype.Service;
+
+import com.iqser.red.service.redaction.v1.server.classification.utils.PositionUtils;
+import com.iqser.red.service.redaction.v1.server.classification.model.Document;
+import com.iqser.red.service.redaction.v1.server.classification.model.Page;
+import com.iqser.red.service.redaction.v1.server.classification.model.TextBlock;
+import com.iqser.red.service.redaction.v1.server.tableextraction.model.AbstractTextContainer;
+import com.iqser.red.service.redaction.v1.server.tableextraction.model.Rectangle;
+
+import lombok.RequiredArgsConstructor;
+
+@Service
+@RequiredArgsConstructor
+public class ClassificationService {
+
+    private final BlockificationService blockificationService;
+
+
+    public void classifyDocument(Document document) {
+
+        Rectangle bodyTextFrame = blockificationService.calculateBodyTextFrame(document.getPages(), document.getFontSizeCounter(), false);
+        Rectangle landscapeBodyTextFrame = blockificationService.calculateBodyTextFrame(document.getPages(), document.getFontSizeCounter(), true);
+
+        List<Float> headlineFontSizes = document.getFontSizeCounter().getHighterThanMostPopular();
+
+        System.out.println(document.getFontSizeCounter().getCountPerValue());
+
+        for (Page page : document.getPages()) {
+            Rectangle btf = page.isLandscape() ? landscapeBodyTextFrame : bodyTextFrame;
+            page.setBodyTextFrame(btf);
+            classifyPage(btf, page, document, headlineFontSizes);
+        }
+    }
+
+
+    public void classifyPage(Rectangle bodyTextFrame, Page page, Document document, List<Float> headlineFontSizes) {
+        for (AbstractTextContainer textBlock : page.getTextBlocks()) {
+            if (textBlock instanceof TextBlock) {
+                classifyBlock((TextBlock) textBlock, bodyTextFrame, page, document, headlineFontSizes);
+            }
+        }
+    }
+
+
+    public void classifyBlock(TextBlock textBlock, Rectangle bodyTextFrame, Page page, Document document, List<Float> headlineFontSizes) {
+        if (document.getFontSizeCounter().getMostPopular() == null) {
+            // TODO Figure out why this happens.
+            return;
+        }
+        if (PositionUtils.isOverBodyTextFrame(bodyTextFrame, textBlock, page.isRotated()) && (document.getFontSizeCounter().getMostPopular() == null || textBlock.getHighestFontSize() <= document.getFontSizeCounter().getMostPopular())) {
+            textBlock.setClassification("Header");
+
+        } else if (PositionUtils.isUnderBodyTextFrame(bodyTextFrame, textBlock) && (document.getFontSizeCounter().getMostPopular() == null || textBlock.getHighestFontSize() <= document.getFontSizeCounter().getMostPopular())) {
+            textBlock.setClassification("Footer");
+        }  else if (page.getPageNumber() == 1
+                && (!PositionUtils.isTouchingUnderBodyTextFrame(bodyTextFrame, textBlock)
+                && PositionUtils.getHeightDifferenceBetweenChunkWordAndDocumentWord(textBlock, document.getTextHeightCounter().getMostPopular()) > 2.5 && textBlock.getHighestFontSize() > document.getFontSizeCounter().getMostPopular() || page.getTextBlocks().size() == 1)) {
+            if (!Pattern.matches("[0-9]+", textBlock.toString())) {
+                textBlock.setClassification("Title");
+            }
+        }
+        else if (PositionUtils.isWithinBodyTextFrame(bodyTextFrame, textBlock) && textBlock.getMostPopularWordFontSize() > document.getFontSizeCounter().getMostPopular() && PositionUtils.getApproxLineCount(textBlock) < 4.9 && textBlock.getMostPopularWordStyle().equals("bold")) {
+
+            for (int i = 1; i <= headlineFontSizes.size(); i++) {
+                if (textBlock.getMostPopularWordFontSize() == headlineFontSizes.get(i - 1)) {
+                    textBlock.setClassification("H " + i);
+                    document.setHeadlines(true);
+                }
+            }
+        }else if (!textBlock.getText().startsWith("Table ") && !textBlock.getText().startsWith("Figure ") && PositionUtils.isWithinBodyTextFrame(bodyTextFrame, textBlock) && textBlock.getMostPopularWordStyle().equals("bold") && !document.getFontStyleCounter().getMostPopular().equals("bold") && PositionUtils.getApproxLineCount(textBlock) < 2.9) {
+            textBlock.setClassification("H " + (headlineFontSizes.size() + 1));
+            document.setHeadlines(true);
+        }
+        else if (PositionUtils.isWithinBodyTextFrame(bodyTextFrame, textBlock) && textBlock.getMostPopularWordFontSize() == document.getFontSizeCounter().getMostPopular() && textBlock.getMostPopularWordStyle().equals("bold") && !document.getFontStyleCounter().getMostPopular().equals("bold")) {
+            textBlock.setClassification("TextBlock Bold");
+        }
+        else if (PositionUtils.isWithinBodyTextFrame(bodyTextFrame, textBlock) && textBlock.getMostPopularWordFont().equals(document.getFontCounter().getMostPopular()) && textBlock.getMostPopularWordStyle().equals(document.getFontStyleCounter().getMostPopular()) && textBlock.getMostPopularWordFontSize() == document.getFontSizeCounter().getMostPopular()) {
+            textBlock.setClassification("TextBlock");
+        }
+        else if (PositionUtils.isWithinBodyTextFrame(bodyTextFrame, textBlock) && textBlock.getMostPopularWordFontSize() == document.getFontSizeCounter().getMostPopular() && textBlock.getMostPopularWordStyle().equals("italic") && !document.getFontStyleCounter().getMostPopular().equals("italic") && PositionUtils.getApproxLineCount(textBlock) < 2.9) {
+            textBlock.setClassification("TextBlock Italic");
+        } else if (PositionUtils.isWithinBodyTextFrame(bodyTextFrame, textBlock)){
+            textBlock.setClassification("TextBlock Unknown");
+        }
+    }
+}

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

@@ -0,0 +1,95 @@
+package com.iqser.red.service.redaction.v1.server.classification.utils;
+
+import com.iqser.red.service.redaction.v1.server.classification.model.TextBlock;
+import com.iqser.red.service.redaction.v1.server.tableextraction.model.Rectangle;
+
+import lombok.experimental.UtilityClass;
+
+@UtilityClass
+@SuppressWarnings("all")
+public class PositionUtils {
+
+
+    public boolean isWithinBodyTextFrame(Rectangle btf, TextBlock textBlock) {
+
+        //TODO Currently this is not working for rotated pages.
+
+        if (btf == null || textBlock == null) {
+            return false;
+        }
+
+        double threshold = textBlock.getMostPopularWordHeight() * 3;
+
+        if (textBlock.getMinX() + threshold > btf.getX() &&
+                textBlock.getMaxX() - threshold < btf.getX() + btf.getWidth() &&
+                textBlock.getMinY() + threshold > btf.getY() &&
+                textBlock.getMaxY() - threshold < btf.getY() + btf.getHeight()) {
+            return true;
+        } else {
+            return false;
+        }
+
+    }
+
+
+    public boolean isOverBodyTextFrame(Rectangle btf, TextBlock textBlock, boolean rotated) {
+
+        if (btf == null || textBlock == null) {
+            return false;
+        }
+
+        if (rotated && textBlock.getMinX() < btf.getX()) {
+            // Its very strange, P{0,0} is on top left in this case, instead of lower left.
+            return true;
+        } else if (!rotated && textBlock.getMinY() > btf.getY() + btf.getHeight()) {
+            return true;
+        } else {
+            return false;
+        }
+
+    }
+
+
+    public boolean isUnderBodyTextFrame(Rectangle btf, TextBlock textBlock) {
+
+        //TODO Currently this is not working for rotated pages.
+
+        if (btf == null || textBlock == null) {
+            return false;
+        }
+
+        if (textBlock.getMaxY() < btf.getY()) {
+            return true;
+        } else {
+            return false;
+        }
+
+    }
+
+
+    public boolean isTouchingUnderBodyTextFrame(Rectangle btf, TextBlock textBlock) {
+
+        //TODO Currently this is not working for rotated pages.
+
+        if (btf == null || textBlock == null) {
+            return false;
+        }
+
+        if (textBlock.getMinY() < btf.getY()) {
+            return true;
+        } else {
+            return false;
+        }
+
+    }
+
+
+    public float getHeightDifferenceBetweenChunkWordAndDocumentWord(TextBlock textBlock, Float documentMostPopularWordHeight) {
+        return textBlock.getMostPopularWordHeight() - documentMostPopularWordHeight;
+    }
+
+
+    public Float getApproxLineCount(TextBlock textBlock) {
+        return textBlock.getHeight() / textBlock.getMostPopularWordHeight();
+    }
+}

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

@@ -2,9 +2,9 @@ package com.iqser.red.service.redaction.v1.server.client;
 
 import org.springframework.cloud.openfeign.FeignClient;
 
-import com.iqser.red.service.persistence.service.v1.api.internal.resources.DictionaryResource;
+import com.iqser.red.service.configuration.v1.api.resource.DictionaryResource;
+import com.iqser.red.service.configuration.v1.api.resource.RulesResource;
 
-@FeignClient(name = "DictionaryResource", url = "${persistence-service.url}")
+@FeignClient(name = "DictionaryResource", url = "http://" + RulesResource.SERVICE_NAME + ":8080")
 public interface DictionaryClient extends DictionaryResource {
-
-}
+}

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

@@ -1,10 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.client;
-
-import org.springframework.cloud.openfeign.FeignClient;
-
-import com.iqser.red.service.persistence.service.v1.api.internal.resources.FileStatusProcessingUpdateResource;
-
-@FeignClient(name = "FileStatusProcessingUpdateResource", url = "${persistence-service.url}")
-public interface FileStatusProcessingUpdateClient extends FileStatusProcessingUpdateResource {
-
-}

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

@@ -1,10 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.client;
-
-import org.springframework.cloud.openfeign.FeignClient;
-
-import com.iqser.red.service.persistence.service.v1.api.internal.resources.LegalBasisMappingResource;
-
-@FeignClient(name = "LegalBasisMappingResource", url = "${persistence-service.url}")
-public interface LegalBasisClient extends LegalBasisMappingResource {
-
-}

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

@@ -1,100 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.client;
-
-import java.io.ByteArrayInputStream;
-import java.io.File;
-import java.io.IOException;
-import java.io.InputStream;
-
-import org.springframework.lang.NonNull;
-import org.springframework.lang.Nullable;
-import org.springframework.util.Assert;
-import org.springframework.util.FileCopyUtils;
-import org.springframework.web.multipart.MultipartFile;
-
-public class MockMultipartFile implements MultipartFile {
-
-    private final String name;
-    private final String originalFilename;
-    @Nullable
-    private final String contentType;
-    private final byte[] content;
-
-
-    public MockMultipartFile(String name, @Nullable byte[] content) {
-
-        this(name, "", null, content);
-    }
-
-
-    public MockMultipartFile(String name, InputStream contentStream) throws IOException {
-
-        this(name, "", null, FileCopyUtils.copyToByteArray(contentStream));
-    }
-
-
-    public MockMultipartFile(String name, @Nullable String originalFilename, @Nullable String contentType, @Nullable byte[] content) {
-
-        Assert.hasLength(name, "Name must not be empty");
-        this.name = name;
-        this.originalFilename = originalFilename != null ? originalFilename : "";
-        this.contentType = contentType;
-        this.content = content != null ? content : new byte[0];
-    }
-
-
-    public MockMultipartFile(String name, @Nullable String originalFilename, @Nullable String contentType, InputStream contentStream) throws IOException {
-
-        this(name, originalFilename, contentType, FileCopyUtils.copyToByteArray(contentStream));
-    }
-
-
-    public String getName() {
-
-        return this.name;
-    }
-
-
-    @NonNull
-    public String getOriginalFilename() {
-
-        return this.originalFilename;
-    }
-
-
-    @Nullable
-    public String getContentType() {
-
-        return this.contentType;
-    }
-
-
-    public boolean isEmpty() {
-
-        return this.content.length == 0;
-    }
-
-
-    public long getSize() {
-
-        return this.content.length;
-    }
-
-
-    public byte[] getBytes() {
-
-        return this.content;
-    }
-
-
-    public InputStream getInputStream() {
-
-        return new ByteArrayInputStream(this.content);
-    }
-
-
-    public void transferTo(File dest) throws IOException, IllegalStateException {
-
-        FileCopyUtils.copy(this.content, dest);
-    }
-
-}

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

@@ -2,9 +2,8 @@ package com.iqser.red.service.redaction.v1.server.client;
 
 import org.springframework.cloud.openfeign.FeignClient;
 
-import com.iqser.red.service.persistence.service.v1.api.internal.resources.RulesResource;
+import com.iqser.red.service.configuration.v1.api.resource.RulesResource;
 
-@FeignClient(name = "RulesResource", url = "${persistence-service.url}")
+@FeignClient(name = RulesResource.SERVICE_NAME, url = "http://" + RulesResource.SERVICE_NAME + ":8080")
 public interface RulesClient extends RulesResource {
-
-}
+}

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

@@ -1,20 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.client.model;
-
-
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.Data;
-import lombok.NoArgsConstructor;
-
-@Data
-@Builder
-@AllArgsConstructor
-@NoArgsConstructor
-public class EntityRecognitionEntity {
-
-    private String value;
-    private int startOffset;
-    private int endOffset;
-    private String type;
-
-}

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

@@ -1,17 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.client.model;
-
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.Data;
-import lombok.NoArgsConstructor;
-
-@Data
-@Builder
-@AllArgsConstructor
-@NoArgsConstructor
-public class EntityRecognitionSection {
-
-    private int sectionNumber;
-    private String text;
-
-}

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

@@ -1,18 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.client.model;
-
-import java.util.HashMap;
-import java.util.List;
-import java.util.Map;
-
-import lombok.AllArgsConstructor;
-import lombok.Data;
-import lombok.NoArgsConstructor;
-
-@Data
-@NoArgsConstructor
-@AllArgsConstructor
-public class NerEntitiesModel {
-
-    private Map<Integer, List<EntityRecognitionEntity>> data = new HashMap<>();
-
-}

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

@@ -1,18 +1,17 @@
 package com.iqser.red.service.redaction.v1.server.controller;
 
+import java.time.OffsetDateTime;
+
 import com.iqser.red.commons.spring.ErrorMessage;
-import com.iqser.red.service.redaction.v1.server.exception.NotFoundException;
-import com.iqser.red.service.redaction.v1.server.exception.RulesValidationException;
-
-import lombok.extern.slf4j.Slf4j;
-
 import org.springframework.http.HttpStatus;
 import org.springframework.web.bind.annotation.ExceptionHandler;
 import org.springframework.web.bind.annotation.ResponseBody;
 import org.springframework.web.bind.annotation.ResponseStatus;
 import org.springframework.web.bind.annotation.RestControllerAdvice;
 
-import java.time.OffsetDateTime;
+import com.iqser.red.service.redaction.v1.server.exception.RulesValidationException;
+
+import lombok.extern.slf4j.Slf4j;
 
 @Slf4j
 @RestControllerAdvice
@@ -20,12 +19,10 @@ public class ControllerAdvice {
 
     /* error handling */
 
-
     @ResponseBody
     @ResponseStatus(value = HttpStatus.INTERNAL_SERVER_ERROR)
     @ExceptionHandler(value = NullPointerException.class)
     public ErrorMessage handleContentNotFoundException(NullPointerException e) {
-
         if (e != null) {
             log.error(e.getMessage(), e);
             return new ErrorMessage(OffsetDateTime.now(), e.getMessage());
@@ -34,22 +31,11 @@ public class ControllerAdvice {
         return new ErrorMessage(OffsetDateTime.now(), "Nullpointer exception");
     }
 
-
     @ResponseBody
     @ResponseStatus(value = HttpStatus.BAD_REQUEST)
     @ExceptionHandler(value = RulesValidationException.class)
     public ErrorMessage handleRulesValidationException(RulesValidationException e) {
-
         return new ErrorMessage(OffsetDateTime.now(), e.getMessage());
     }
 
-
-    @ResponseBody
-    @ResponseStatus(value = HttpStatus.NOT_FOUND)
-    @ExceptionHandler(value = NotFoundException.class)
-    public ErrorMessage handleFileNotFoundException(NotFoundException e) {
-
-        return new ErrorMessage(OffsetDateTime.now(), e.getMessage());
-    }
-
-}
+}

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

@@ -1,32 +1,163 @@
 package com.iqser.red.service.redaction.v1.server.controller;
 
+import java.io.ByteArrayInputStream;
+import java.io.ByteArrayOutputStream;
+import java.io.IOException;
+import java.util.List;
+
+import org.apache.pdfbox.pdmodel.PDDocument;
 import org.springframework.web.bind.annotation.RequestBody;
 import org.springframework.web.bind.annotation.RestController;
 
-import com.iqser.red.service.redaction.v1.model.DroolsSyntaxValidation;
+import com.iqser.red.service.redaction.v1.model.RedactionLog;
+import com.iqser.red.service.redaction.v1.model.RedactionLogEntry;
+import com.iqser.red.service.redaction.v1.model.RedactionRequest;
+import com.iqser.red.service.redaction.v1.model.RedactionResult;
+import com.iqser.red.service.redaction.v1.model.SectionGrid;
 import com.iqser.red.service.redaction.v1.resources.RedactionResource;
-import com.iqser.red.service.redaction.v1.server.exception.RulesValidationException;
+import com.iqser.red.service.redaction.v1.server.classification.model.Document;
+import com.iqser.red.service.redaction.v1.server.classification.model.Page;
+import com.iqser.red.service.redaction.v1.server.exception.RedactionException;
 import com.iqser.red.service.redaction.v1.server.redaction.service.DroolsExecutionService;
+import com.iqser.red.service.redaction.v1.server.redaction.service.EntityRedactionService;
+import com.iqser.red.service.redaction.v1.server.segmentation.PdfSegmentationService;
+import com.iqser.red.service.redaction.v1.server.tableextraction.model.AbstractTextContainer;
+import com.iqser.red.service.redaction.v1.server.tableextraction.model.Table;
+import com.iqser.red.service.redaction.v1.server.visualization.service.AnnotationHighlightService;
+import com.iqser.red.service.redaction.v1.server.visualization.service.PdfFlattenService;
+import com.iqser.red.service.redaction.v1.server.visualization.service.PdfVisualisationService;
 
 import lombok.RequiredArgsConstructor;
-import lombok.extern.slf4j.Slf4j;
 
-@Slf4j
 @RestController
 @RequiredArgsConstructor
 public class RedactionController implements RedactionResource {
 
+    private final PdfVisualisationService pdfVisualisationService;
+    private final PdfSegmentationService pdfSegmentationService;
+    private final AnnotationHighlightService annotationHighlightService;
+    private final EntityRedactionService entityRedactionService;
+    private final PdfFlattenService pdfFlattenService;
     private final DroolsExecutionService droolsExecutionService;
 
 
     @Override
-    public DroolsSyntaxValidation testRules(@RequestBody String rules) {
+    public RedactionResult redact(@RequestBody RedactionRequest redactionRequest) {
 
-        try {
-            return droolsExecutionService.testRules(rules);
-        } catch (Exception e) {
-            throw new RulesValidationException("Could not test rules: " + e.getMessage(), e);
+        try (PDDocument pdDocument = PDDocument.load(new ByteArrayInputStream(redactionRequest.getDocument()))) {
+            pdDocument.setAllSecurityToBeRemoved(true);
+
+            Document classifiedDoc = pdfSegmentationService.parseDocument(pdDocument);
+            entityRedactionService.processDocument(classifiedDoc, redactionRequest.getManualRedactions());
+            annotationHighlightService.highlight(pdDocument, classifiedDoc, redactionRequest.isFlatRedaction(), redactionRequest
+                    .getManualRedactions());
+
+            if (redactionRequest.isFlatRedaction()) {
+                PDDocument flatDocument = pdfFlattenService.flattenPDF(pdDocument);
+                return convert(flatDocument, classifiedDoc.getPages()
+                        .size(), classifiedDoc.getRedactionLogEntities(), classifiedDoc.getSectionGrid(), classifiedDoc.getDictionaryVersion(), classifiedDoc.getRulesVersion());
+            }
+
+            return convert(pdDocument, classifiedDoc.getPages()
+                    .size(), classifiedDoc.getRedactionLogEntities(), classifiedDoc.getSectionGrid(), classifiedDoc.getDictionaryVersion(), classifiedDoc.getRulesVersion());
+
+        } catch (IOException e) {
+            throw new RedactionException(e);
         }
+
+    }
+
+
+    @Override
+    public RedactionResult classify(@RequestBody RedactionRequest pdfSegmentationRequest) {
+
+        try (PDDocument pdDocument = PDDocument.load(new ByteArrayInputStream(pdfSegmentationRequest.getDocument()))) {
+            pdDocument.setAllSecurityToBeRemoved(true);
+
+            Document classifiedDoc = pdfSegmentationService.parseDocument(pdDocument);
+            pdfVisualisationService.visualizeClassifications(classifiedDoc, pdDocument);
+
+            return convert(pdDocument, classifiedDoc.getPages().size());
+
+        } catch (IOException e) {
+            throw new RedactionException(e);
+        }
+
+    }
+
+
+    @Override
+    public RedactionResult sections(@RequestBody RedactionRequest redactionRequest) {
+
+        try (PDDocument pdDocument = PDDocument.load(new ByteArrayInputStream(redactionRequest.getDocument()))) {
+            pdDocument.setAllSecurityToBeRemoved(true);
+
+            Document classifiedDoc = pdfSegmentationService.parseDocument(pdDocument);
+            pdfVisualisationService.visualizeParagraphs(classifiedDoc, pdDocument);
+
+            return convert(pdDocument, classifiedDoc.getPages().size());
+
+        } catch (IOException e) {
+            throw new RedactionException(e);
+        }
+
+    }
+
+
+    @Override
+    public RedactionResult htmlTables(@RequestBody RedactionRequest redactionRequest) {
+
+        try (PDDocument pdDocument = PDDocument.load(new ByteArrayInputStream(redactionRequest.getDocument()))) {
+            pdDocument.setAllSecurityToBeRemoved(true);
+
+            Document classifiedDoc = pdfSegmentationService.parseDocument(pdDocument);
+
+            StringBuilder sb = new StringBuilder();
+            for (Page page : classifiedDoc.getPages()) {
+                for (AbstractTextContainer textContainer : page.getTextBlocks()) {
+                    if (textContainer instanceof Table) {
+                        Table table = (Table) textContainer;
+                        sb.append(table.getTextAsHtml()).append("<br />").append("<br />");
+                    }
+                }
+            }
+
+            return RedactionResult.builder().document(sb.toString().getBytes()).build();
+
+        } catch (IOException e) {
+            throw new RedactionException(e);
+        }
+
+    }
+
+
+    @Override
+    public void updateRules(@RequestBody String rules) {
+
+        droolsExecutionService.updateRules(rules);
+    }
+
+
+    private RedactionResult convert(PDDocument document, int numberOfPages) throws IOException {
+
+        return convert(document, numberOfPages, null, null, 0, 0);
+    }
+
+
+    private RedactionResult convert(PDDocument document, int numberOfPages,
+                                    List<RedactionLogEntry> redactionLogEntities,
+                                    SectionGrid sectionGrid, long dictionaryVersion, long rulesVersion) throws IOException {
+
+        try (ByteArrayOutputStream byteArrayOutputStream = new ByteArrayOutputStream()) {
+            document.save(byteArrayOutputStream);
+            return RedactionResult.builder()
+                    .document(byteArrayOutputStream.toByteArray())
+                    .numberOfPages(numberOfPages)
+                    .redactionLog(new RedactionLog(redactionLogEntities,dictionaryVersion, rulesVersion))
+                    .sectionGrid(sectionGrid)
+                    .build();
+        }
+
     }
 
 }

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

@@ -1,24 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.controller;
-
-import org.springframework.web.bind.annotation.RestController;
-
-import com.iqser.red.service.redaction.v1.model.RuleBuilderModel;
-import com.iqser.red.service.redaction.v1.resources.RuleBuilderResource;
-import com.iqser.red.service.redaction.v1.server.redaction.service.RuleBuilderModelService;
-
-import lombok.RequiredArgsConstructor;
-
-@RestController
-@RequiredArgsConstructor
-public class RuleBuilderController implements RuleBuilderResource {
-
-    private final RuleBuilderModelService ruleBuilderModelService;
-
-
-    @Override
-    public RuleBuilderModel getRuleBuilderModel() {
-
-        return ruleBuilderModelService.getRuleBuilderModel();
-    }
-
-}

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

@@ -1,25 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.data;
-
-import com.knecon.fforesight.service.layoutparser.internal.api.data.redaction.DocumentPage;
-import com.knecon.fforesight.service.layoutparser.internal.api.data.redaction.DocumentPositionData;
-import com.knecon.fforesight.service.layoutparser.internal.api.data.redaction.DocumentStructure;
-import com.knecon.fforesight.service.layoutparser.internal.api.data.redaction.DocumentTextData;
-
-import lombok.AccessLevel;
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.Data;
-import lombok.experimental.FieldDefaults;
-
-@Data
-@Builder
-@AllArgsConstructor
-@FieldDefaults(makeFinal = true, level = AccessLevel.PRIVATE)
-public class DocumentData {
-
-    DocumentPage[] documentPages;
-    DocumentTextData[] documentTextData;
-    DocumentPositionData[] documentPositionData;
-    DocumentStructure documentStructure;
-
-}

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

@@ -1,198 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.data.mapper;
-
-import java.util.Arrays;
-import java.util.HashSet;
-import java.util.LinkedList;
-import java.util.List;
-import java.util.Map;
-import java.util.NoSuchElementException;
-
-import com.iqser.red.service.redaction.v1.server.document.graph.DocumentTree;
-import com.iqser.red.service.redaction.v1.server.document.graph.nodes.Footer;
-import com.iqser.red.service.redaction.v1.server.document.graph.nodes.Header;
-import com.iqser.red.service.redaction.v1.server.document.graph.nodes.Image;
-import com.iqser.red.service.redaction.v1.server.document.graph.nodes.Page;
-import com.iqser.red.service.redaction.v1.server.document.graph.nodes.Paragraph;
-import com.iqser.red.service.redaction.v1.server.document.graph.nodes.Section;
-import com.iqser.red.service.redaction.v1.server.document.graph.nodes.SemanticNode;
-import com.iqser.red.service.redaction.v1.server.document.graph.nodes.TableCell;
-import com.iqser.red.service.redaction.v1.server.document.graph.textblock.AtomicTextBlock;
-import com.iqser.red.service.redaction.v1.server.document.graph.textblock.TextBlock;
-import com.iqser.red.service.redaction.v1.server.document.graph.textblock.TextBlockCollector;
-import com.iqser.red.service.redaction.v1.server.document.data.DocumentData;
-import com.iqser.red.service.redaction.v1.server.document.graph.nodes.Document;
-import com.iqser.red.service.redaction.v1.server.document.graph.nodes.Headline;
-import com.iqser.red.service.redaction.v1.server.document.graph.nodes.Table;
-import com.knecon.fforesight.service.layoutparser.internal.api.data.redaction.DocumentPage;
-import com.knecon.fforesight.service.layoutparser.internal.api.data.redaction.DocumentPositionData;
-import com.knecon.fforesight.service.layoutparser.internal.api.data.redaction.DocumentStructure;
-import com.knecon.fforesight.service.layoutparser.internal.api.data.redaction.DocumentTextData;
-
-import lombok.experimental.UtilityClass;
-
-@UtilityClass
-public class DocumentGraphMapper {
-
-    public Document toDocumentGraph(DocumentData documentData) {
-
-        Document document = new Document();
-        DocumentTree documentTree = new DocumentTree(document);
-        Context context = new Context(documentData, documentTree);
-
-        context.pageData.addAll(Arrays.stream(documentData.getDocumentPages()).map(DocumentGraphMapper::buildPage).toList());
-
-        context.documentTree.getRoot().getChildren().addAll(buildEntries(documentData.getDocumentStructure().getRoot().getChildren(), context));
-
-        document.setDocumentTree(context.documentTree);
-        document.setPages(new HashSet<>(context.pageData));
-        document.setNumberOfPages(documentData.getDocumentPages().length);
-
-        document.setTextBlock(document.getTextBlock());
-        return document;
-    }
-
-
-    private List<DocumentTree.Entry> buildEntries(List<DocumentStructure.EntryData> entries, Context context) {
-
-        List<DocumentTree.Entry> newEntries = new LinkedList<>();
-        for (DocumentStructure.EntryData entryData : entries) {
-
-            List<Page> pages = Arrays.stream(entryData.getPageNumbers()).map(pageNumber -> getPage(pageNumber, context)).toList();
-
-            SemanticNode node = switch (entryData.getType()) {
-                case SECTION -> buildSection(context);
-                case PARAGRAPH -> buildParagraph(context);
-                case HEADLINE -> buildHeadline(context);
-                case HEADER -> buildHeader(context);
-                case FOOTER -> buildFooter(context);
-                case TABLE -> buildTable(context, entryData.getProperties());
-                case TABLE_CELL -> buildTableCell(context, entryData.getProperties());
-                case IMAGE -> buildImage(context, entryData.getProperties(), entryData.getPageNumbers());
-                default -> throw new UnsupportedOperationException("Not yet implemented for type " + entryData.getType());
-            };
-
-            if (entryData.getAtomicBlockIds().length > 0) {
-                TextBlock textBlock = toTextBlock(entryData.getAtomicBlockIds(), context, node);
-                node.setLeafTextBlock(textBlock);
-            }
-            List<Integer> treeId = Arrays.stream(entryData.getTreeId()).boxed().toList();
-            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;
-    }
-
-
-    private Headline buildHeadline(Context context) {
-
-        return Headline.builder().documentTree(context.documentTree).build();
-    }
-
-
-    private Image buildImage(Context context, Map<String, String> properties, Long[] pageNumbers) {
-
-        assert pageNumbers.length == 1;
-        Page page = getPage(pageNumbers[0], context);
-        var builder = Image.builder();
-        PropertiesMapper.parseImageProperties(properties, builder);
-        return builder.documentTree(context.documentTree).page(page).build();
-    }
-
-
-    private TableCell buildTableCell(Context context, Map<String, String> properties) {
-
-        TableCell.TableCellBuilder builder = TableCell.builder();
-        PropertiesMapper.parseTableCellProperties(properties, builder);
-        return builder.documentTree(context.documentTree).build();
-    }
-
-
-    private Table buildTable(Context context, Map<String, String> properties) {
-
-        Table.TableBuilder builder = Table.builder();
-        PropertiesMapper.parseTableProperties(properties, builder);
-        return builder.documentTree(context.documentTree).build();
-    }
-
-
-    private Footer buildFooter(Context context) {
-
-        return Footer.builder().documentTree(context.documentTree).build();
-    }
-
-
-    private Header buildHeader(Context context) {
-
-        return Header.builder().documentTree(context.documentTree).build();
-    }
-
-
-    private Section buildSection(Context context) {
-
-        return Section.builder().documentTree(context.documentTree).build();
-    }
-
-
-    private Paragraph buildParagraph(Context context) {
-
-        return Paragraph.builder().documentTree(context.documentTree).build();
-    }
-
-
-    private TextBlock toTextBlock(Long[] atomicTextBlockIds, Context context, SemanticNode parent) {
-
-        return Arrays.stream(atomicTextBlockIds).map(atomicTextBlockId -> getAtomicTextBlock(context, parent, atomicTextBlockId)).collect(new TextBlockCollector());
-    }
-
-
-    private AtomicTextBlock getAtomicTextBlock(Context context, SemanticNode parent, Long atomicTextBlockId) {
-
-        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));
-    }
-
-
-    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) {
-
-        return context.pageData.stream()
-                .filter(page -> page.getNumber() == Math.toIntExact(pageIndex))
-                .findFirst()
-                .orElseThrow(() -> new NoSuchElementException(String.format("ClassificationPage with number %d not found", pageIndex)));
-    }
-
-
-    static final class Context {
-
-        private final DocumentTree documentTree;
-        private final List<Page> pageData;
-        private final List<DocumentTextData> documentTextData;
-        private final List<DocumentPositionData> documentPositionData;
-
-
-        Context(DocumentData documentData, DocumentTree documentTree) {
-
-            this.documentTree = documentTree;
-            this.pageData = new LinkedList<>();
-            this.documentTextData = Arrays.stream(documentData.getDocumentTextData()).toList();
-            this.documentPositionData = Arrays.stream(documentData.getDocumentPositionData()).toList();
-
-        }
-
-    }
-
-}

redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/document/data/mapper/PropertiesMapper.java

@@ -1,52 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.data.mapper;
-
-import java.awt.geom.Rectangle2D;
-import java.util.Arrays;
-import java.util.List;
-import java.util.Map;
-
-import com.iqser.red.service.redaction.v1.server.document.graph.nodes.Image;
-import com.iqser.red.service.redaction.v1.server.document.graph.nodes.ImageType;
-import com.iqser.red.service.redaction.v1.server.document.graph.nodes.Table;
-import com.iqser.red.service.redaction.v1.server.document.graph.nodes.TableCell;
-import com.knecon.fforesight.service.layoutparser.internal.api.data.redaction.DocumentStructure;
-
-import lombok.AccessLevel;
-import lombok.experimental.FieldDefaults;
-import lombok.experimental.UtilityClass;
-
-@UtilityClass
-public class PropertiesMapper {
-
-    public void parseImageProperties(Map<String, String> properties, Image.ImageBuilder builder) {
-
-        builder.imageType(ImageType.fromString(properties.get(DocumentStructure.ImageProperties.IMAGE_TYPE)));
-        builder.transparent(Boolean.parseBoolean(properties.get(DocumentStructure.ImageProperties.TRANSPARENT)));
-        builder.position(parseRectangle2D(properties.get(DocumentStructure.ImageProperties.POSITION)));
-        builder.id(properties.get(DocumentStructure.ImageProperties.ID));
-    }
-
-
-    public void parseTableCellProperties(Map<String, String> properties, TableCell.TableCellBuilder builder) {
-
-        builder.row(Integer.parseInt(properties.get(DocumentStructure.TableCellProperties.ROW)));
-        builder.col(Integer.parseInt(properties.get(DocumentStructure.TableCellProperties.COL)));
-        builder.header(Boolean.parseBoolean(properties.get(DocumentStructure.TableCellProperties.HEADER)));
-        builder.bBox(parseRectangle2D(properties.get(DocumentStructure.TableCellProperties.B_BOX)));
-    }
-
-
-    public void parseTableProperties(Map<String, String> properties, Table.TableBuilder builder) {
-
-        builder.numberOfRows(Integer.parseInt(properties.get(DocumentStructure.TableProperties.NUMBER_OF_ROWS)));
-        builder.numberOfCols(Integer.parseInt(properties.get(DocumentStructure.TableProperties.NUMBER_OF_COLS)));
-    }
-
-
-    private Rectangle2D parseRectangle2D(String bBox) {
-
-        List<Float> floats = Arrays.stream(bBox.split(DocumentStructure.RECTANGLE_DELIMITER)).map(Float::parseFloat).toList();
-        return new Rectangle2D.Float(floats.get(0), floats.get(1), floats.get(2), floats.get(3));
-    }
-
-}

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

@@ -1,70 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.graph;
-
-import java.util.LinkedList;
-import java.util.List;
-import java.util.Set;
-import java.util.function.BiConsumer;
-import java.util.function.BinaryOperator;
-import java.util.function.Function;
-import java.util.function.Supplier;
-import java.util.stream.Collector;
-
-import com.google.common.base.Functions;
-
-public class ConsecutiveBoundaryCollector implements Collector<TextRange, List<TextRange>, List<TextRange>> {
-
-    @Override
-    public Supplier<List<TextRange>> supplier() {
-
-        return LinkedList::new;
-    }
-
-
-    @Override
-    public BiConsumer<List<TextRange>, TextRange> accumulator() {
-
-        return (existingList, boundary) -> {
-            if (existingList.isEmpty()) {
-                existingList.add(boundary);
-                return;
-            }
-
-            TextRange prevTextRange = existingList.get(existingList.size() - 1);
-            if (prevTextRange.end() > boundary.start()) {
-                throw new IllegalArgumentException(String.format("Can't concatenate %s and %s. Boundaries must be ordered!", prevTextRange, boundary));
-            }
-
-            if (prevTextRange.end() == boundary.start()) {
-                existingList.remove(existingList.size() - 1);
-                existingList.add(TextRange.merge(List.of(prevTextRange, boundary)));
-            } else {
-                existingList.add(boundary);
-            }
-        };
-    }
-
-
-    @Override
-    public BinaryOperator<List<TextRange>> combiner() {
-
-        return (list1, list2) -> {
-            list1.addAll(list2);
-            return list1;
-        };
-    }
-
-
-    @Override
-    public Function<List<TextRange>, List<TextRange>> finisher() {
-
-        return Functions.identity();
-    }
-
-
-    @Override
-    public Set<Characteristics> characteristics() {
-
-        return Set.of(Characteristics.IDENTITY_FINISH);
-    }
-
-}

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

@@ -1,217 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.graph;
-
-import static java.lang.String.format;
-
-import java.util.Collections;
-import java.util.LinkedList;
-import java.util.List;
-import java.util.stream.Stream;
-
-import com.iqser.red.service.redaction.v1.server.document.graph.nodes.GenericSemanticNode;
-import com.iqser.red.service.redaction.v1.server.document.graph.nodes.NodeType;
-import com.iqser.red.service.redaction.v1.server.document.graph.nodes.SemanticNode;
-import com.iqser.red.service.redaction.v1.server.document.graph.nodes.TableCell;
-import com.iqser.red.service.redaction.v1.server.document.graph.nodes.Document;
-import com.iqser.red.service.redaction.v1.server.document.graph.nodes.Table;
-import com.iqser.red.service.redaction.v1.server.document.graph.textblock.TextBlock;
-import com.iqser.red.service.redaction.v1.server.document.graph.textblock.TextBlockCollector;
-
-import lombok.AccessLevel;
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.Data;
-import lombok.EqualsAndHashCode;
-import lombok.Getter;
-import lombok.experimental.FieldDefaults;
-
-@Data
-@EqualsAndHashCode
-public class DocumentTree {
-
-    private final Entry root;
-
-
-    public DocumentTree(Document document) {
-
-        root = Entry.builder().treeId(Collections.emptyList()).children(new LinkedList<>()).node(document).build();
-    }
-
-
-    public TextBlock buildTextBlock() {
-
-        return allEntriesInOrder().map(Entry::getNode).filter(SemanticNode::isLeaf).map(SemanticNode::getLeafTextBlock).collect(new TextBlockCollector());
-    }
-
-
-    public List<Integer> createNewMainEntryAndReturnId(GenericSemanticNode node) {
-
-        return createNewChildEntryAndReturnIdImpl(Collections.emptyList(), node);
-    }
-
-
-    public List<Integer> createNewChildEntryAndReturnId(GenericSemanticNode parentNode, GenericSemanticNode node) {
-
-        return createNewChildEntryAndReturnIdImpl(parentNode.getTreeId(), node);
-    }
-
-
-    public List<Integer> createNewChildEntryAndReturnId(GenericSemanticNode parentNode, Table node) {
-
-        return createNewChildEntryAndReturnIdImpl(parentNode.getTreeId(), node);
-    }
-
-
-    public List<Integer> createNewTableChildEntryAndReturnId(Table parentTable, TableCell tableCell) {
-
-        return createNewChildEntryAndReturnIdImpl(parentTable.getTreeId(), tableCell);
-    }
-
-
-    @SuppressWarnings("PMD.UnusedPrivateMethod") // PMD actually flags this wrong
-    private List<Integer> createNewChildEntryAndReturnIdImpl(List<Integer> parentId, SemanticNode node) {
-
-        if (!entryExists(parentId)) {
-            throw new IllegalArgumentException(format("parentId %s does not exist!", parentId));
-        }
-
-        Entry parent = getEntryById(parentId);
-        List<Integer> newId = new LinkedList<>(parentId);
-        newId.add(parent.children.size());
-        parent.children.add(Entry.builder().treeId(newId).node(node).build());
-
-        return newId;
-    }
-
-
-    private boolean entryExists(List<Integer> treeId) {
-
-        if (treeId.isEmpty()) {
-            return root != null;
-        }
-        Entry entry = root.children.get(treeId.get(0));
-        for (int id : treeId.subList(1, treeId.size())) {
-            if (id >= entry.children.size() || 0 > id) {
-                return false;
-            }
-            entry = entry.children.get(id);
-        }
-        return true;
-    }
-
-
-    public Entry getParentEntryById(List<Integer> treeId) {
-
-        return getEntryById(getParentId(treeId));
-    }
-
-
-    public boolean hasParentById(List<Integer> treeId) {
-
-        return !treeId.isEmpty();
-    }
-
-
-    public Stream<SemanticNode> childNodes(List<Integer> treeId) {
-
-        return getEntryById(treeId).children.stream().map(Entry::getNode);
-    }
-
-
-    public Stream<SemanticNode> childNodesOfType(List<Integer> treeId, NodeType nodeType) {
-
-        return getEntryById(treeId).children.stream().filter(entry -> entry.node.getType().equals(nodeType)).map(Entry::getNode);
-    }
-
-
-    private static List<Integer> getParentId(List<Integer> treeId) {
-
-        if (treeId.isEmpty()) {
-            throw new UnsupportedOperationException("Root has no parent!");
-        }
-        if (treeId.size() < 2) {
-            return Collections.emptyList();
-        }
-        return treeId.subList(0, treeId.size() - 1);
-    }
-
-
-    public Entry getEntryById(List<Integer> treeId) {
-
-        if (treeId.isEmpty()) {
-            return root;
-        }
-        Entry entry = root.children.get(treeId.get(0));
-        for (int id : treeId.subList(1, treeId.size())) {
-            entry = entry.children.get(id);
-        }
-        return entry;
-    }
-
-
-    public Stream<Entry> mainEntries() {
-
-        return root.children.stream();
-    }
-
-
-    public Stream<Entry> allEntriesInOrder() {
-
-        return Stream.of(root).flatMap(DocumentTree::flatten);
-    }
-
-
-    public Stream<Entry> allSubEntriesInOrder(List<Integer> parentId) {
-
-        return getEntryById(parentId).children.stream().flatMap(DocumentTree::flatten);
-    }
-
-
-    @Override
-    public String toString() {
-
-        return String.join("\n", allEntriesInOrder().map(Entry::toString).toList());
-    }
-
-
-    private static Stream<Entry> flatten(Entry entry) {
-
-        return Stream.concat(Stream.of(entry), entry.children.stream().flatMap(DocumentTree::flatten));
-    }
-
-
-    public SemanticNode getHighestParentById(List<Integer> treeId) {
-
-        if (treeId.isEmpty()) {
-            return root.node;
-        }
-        return root.children.get(treeId.get(0)).node;
-    }
-
-
-    @Builder
-    @Getter
-    @AllArgsConstructor
-    @FieldDefaults(level = AccessLevel.PRIVATE, makeFinal = true)
-    public static class Entry {
-
-        List<Integer> treeId;
-        SemanticNode node;
-        @Builder.Default
-        List<Entry> children = new LinkedList<>();
-
-
-        @Override
-        public String toString() {
-
-            return node.toString();
-        }
-
-
-        public NodeType getType() {
-
-            return node.getType();
-        }
-
-    }
-
-}

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

@@ -1,166 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.graph;
-
-import static java.lang.String.format;
-
-import java.util.Collection;
-import java.util.LinkedList;
-import java.util.List;
-
-import com.iqser.red.service.redaction.v1.server.document.graph.textblock.TextBlock;
-
-import lombok.EqualsAndHashCode;
-import lombok.Setter;
-
-@Setter
-@EqualsAndHashCode
-public class TextRange implements Comparable<TextRange> {
-
-    private int start;
-    private int end;
-
-
-    public TextRange(int start, int end) {
-
-        if (start > end) {
-            throw new IllegalArgumentException(format("start: %d > end: %d", start, end));
-        }
-        this.start = start;
-        this.end = end;
-    }
-
-
-    public int length() {
-
-        return end - start;
-    }
-
-
-    public int start() {
-
-        return start;
-    }
-
-
-    public int end() {
-
-        return end;
-    }
-
-
-    public boolean contains(TextRange textRange) {
-
-        return start <= textRange.start() && textRange.end() <= end;
-    }
-
-
-    public boolean containedBy(TextRange textRange) {
-
-        return textRange.contains(this);
-    }
-
-
-    public boolean contains(int start, int end) {
-
-        if (start > end) {
-            throw new IllegalArgumentException(format("start: %d > end: %d", start, end));
-        }
-        return this.start <= start && end <= this.end;
-    }
-
-
-    public boolean containedBy(int start, int end) {
-
-        if (start > end) {
-            throw new IllegalArgumentException(format("start: %d > end: %d", start, end));
-        }
-        return start <= this.start && this.end <= end;
-    }
-
-
-    public boolean contains(int index) {
-
-        return start <= index && index < end;
-    }
-
-
-    public boolean intersects(TextRange textRange) {
-
-        return textRange.start() < this.end && this.start < textRange.end();
-    }
-
-
-    public List<TextRange> split(List<Integer> splitIndices) {
-
-        if (splitIndices.stream().anyMatch(idx -> !this.contains(idx))) {
-            throw new IndexOutOfBoundsException(format("%s splitting indices are out of range for %s", splitIndices.stream().filter(idx -> !this.contains(idx)).toList(), this));
-        }
-        List<TextRange> splitBoundaries = new LinkedList<>();
-        int previousIndex = start;
-        for (int splitIndex : splitIndices) {
-
-            // skip split if it would produce a boundary of length 0
-            if (splitIndex == previousIndex) {
-                continue;
-            }
-            splitBoundaries.add(new TextRange(previousIndex, splitIndex));
-            previousIndex = splitIndex;
-        }
-        splitBoundaries.add(new TextRange(previousIndex, end));
-        return splitBoundaries;
-    }
-
-
-    public static TextRange merge(Collection<TextRange> boundaries) {
-
-        int minStart = boundaries.stream().mapToInt(TextRange::start).min().orElseThrow(IllegalArgumentException::new);
-        int maxEnd = boundaries.stream().mapToInt(TextRange::end).max().orElseThrow(IllegalArgumentException::new);
-        return new TextRange(minStart, maxEnd);
-    }
-
-
-    @Override
-    public String toString() {
-
-        return format("Boundary [%d|%d)", start, end);
-    }
-
-
-    @Override
-    public int compareTo(TextRange textRange) {
-
-        if (end < textRange.end() && start < textRange.start()) {
-            return -1;
-        }
-        if (start > textRange.start() && end > textRange.end()) {
-            return 1;
-        }
-
-        return 0;
-    }
-
-
-    /**
-     * shrinks the boundary, such that textBlock.subSequence(boundary) returns a string without trailing or preceding whitespaces.
-     *
-     * @param textBlock TextBlock to check whitespaces against
-     * @return trimmed boundary
-     */
-    public TextRange trim(TextBlock textBlock) {
-
-        if (this.length() == 0) {
-            return this;
-        }
-        int trimmedStart = this.start;
-        while (textBlock.containsIndex(trimmedStart) && trimmedStart < end && Character.isWhitespace(textBlock.charAt(trimmedStart))) {
-            trimmedStart++;
-        }
-
-        int trimmedEnd = this.end;
-        while (textBlock.containsIndex(trimmedEnd - 1) && trimmedStart < trimmedEnd && Character.isWhitespace(textBlock.charAt(trimmedEnd - 1))) {
-            trimmedEnd--;
-        }
-
-        return new TextRange(trimmedStart, Math.max(trimmedEnd, trimmedStart));
-    }
-
-}

redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/document/graph/entity/Entity.java

@@ -1,206 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.graph.entity;
-
-import java.util.Collection;
-import java.util.HashSet;
-import java.util.PriorityQueue;
-import java.util.Set;
-
-import lombok.NonNull;
-
-public interface Entity {
-
-    PriorityQueue<MatchedRule> getMatchedRuleList();
-
-
-    ManualChangeOverwrite getManualOverwrite();
-
-
-    // Don't use default accessor pattern (e.g. isIgnored()), as it might lead to errors in drools due to property-specific optimization of the drools planner.
-    default boolean ignored() {
-
-        return getManualOverwrite().getIgnored().orElse(getMatchedRule().isIgnored());
-    }
-
-
-    default boolean removed() {
-
-        return getManualOverwrite().getRemoved().orElse(getMatchedRule().isRemoved());
-    }
-
-
-    default boolean resized() {
-
-        return getManualOverwrite().getResized().orElse(false);
-    }
-
-
-    default boolean applied() {
-
-        return getManualOverwrite().getApplied().orElse(getMatchedRule().isApplied());
-    }
-
-
-    default boolean hasManualChanges() {
-
-        return !getManualOverwrite().getManualChangeLog().isEmpty();
-    }
-
-
-    default Set<TextEntity> references() {
-
-        return getMatchedRule().getReferences();
-    }
-
-
-    default boolean active() {
-
-        return !(removed() || ignored());
-    }
-
-
-    default void redact(@NonNull String ruleIdentifier, String reason, @NonNull String legalBasis) {
-
-        if (legalBasis.isBlank() || legalBasis.isEmpty()) {
-            throw new IllegalArgumentException("legal basis cannot be empty when redacting an entity");
-        }
-        apply(ruleIdentifier, reason, legalBasis);
-    }
-
-
-    default void apply(@NonNull String ruleIdentifier, String reason, String legalBasis) {
-
-        addMatchedRule(MatchedRule.builder().ruleIdentifier(RuleIdentifier.fromString(ruleIdentifier)).reason(reason).legalBasis(legalBasis).applied(true).build());
-    }
-
-
-    default void apply(@NonNull String ruleIdentifier, String reason) {
-
-        apply(ruleIdentifier, reason, "n-a");
-    }
-
-
-    default void force(@NonNull String ruleIdentifier, String reason, String legalBasis) {
-
-        addMatchedRule(MatchedRule.builder()
-                .ruleIdentifier(RuleIdentifier.fromString(ruleIdentifier))
-                .reason(reason)
-                .legalBasis(getLegalBasisOrPreviousLegalBasisOrPlaceHolder(legalBasis))
-                .applied(true)
-                .build());
-    }
-
-
-    default void skip(@NonNull String ruleIdentifier, String reason) {
-
-        addMatchedRule(MatchedRule.builder().ruleIdentifier(RuleIdentifier.fromString(ruleIdentifier)).reason(reason).build());
-    }
-
-
-    default void remove(String ruleIdentifier, String reason) {
-
-        addMatchedRule(MatchedRule.builder().ruleIdentifier(RuleIdentifier.fromString(ruleIdentifier)).reason(reason).removed(true).build());
-    }
-
-
-    default void ignore(String ruleIdentifier, String reason) {
-
-        addMatchedRule(MatchedRule.builder().ruleIdentifier(RuleIdentifier.fromString(ruleIdentifier)).reason(reason).ignored(true).build());
-    }
-
-
-    private String getLegalBasisOrPreviousLegalBasisOrPlaceHolder(String legalBasis) {
-
-        if (legalBasis == null || legalBasis.isBlank() || legalBasis.isEmpty()) {
-            if (getMatchedRule() == null || !getMatchedRule().isApplied()) {
-                return "n-a";
-            }
-            return getMatchedRule().getLegalBasis();
-        }
-        return legalBasis;
-    }
-
-
-    default void applyWithLineBreaks(@NonNull String ruleIdentifier, String reason, @NonNull String legalBasis) {
-
-        if (legalBasis.isBlank() || legalBasis.isEmpty()) {
-            throw new IllegalArgumentException("legal basis cannot be empty when redacting an entity");
-        }
-        getMatchedRuleList().add(MatchedRule.builder()
-                .ruleIdentifier(RuleIdentifier.fromString(ruleIdentifier))
-                .reason(reason)
-                .legalBasis(legalBasis)
-                .applied(true)
-                .writeValueWithLineBreaks(true)
-                .build());
-    }
-
-
-    default void applyWithReferences(@NonNull String ruleIdentifier, String reason, @NonNull String legalBasis, Collection<TextEntity> references) {
-
-        if (legalBasis.isBlank() || legalBasis.isEmpty()) {
-            throw new IllegalArgumentException("legal basis cannot be empty when redacting an entity");
-        }
-        getMatchedRuleList().add(MatchedRule.builder()
-                .ruleIdentifier(RuleIdentifier.fromString(ruleIdentifier))
-                .reason(reason)
-                .legalBasis(legalBasis)
-                .applied(true)
-                .references(new HashSet<>(references))
-                .build());
-    }
-
-
-    default void skipWithReferences(@NonNull String ruleIdentifier, String reason, Collection<TextEntity> references) {
-
-        getMatchedRuleList().add(MatchedRule.builder().ruleIdentifier(RuleIdentifier.fromString(ruleIdentifier)).reason(reason).references(new HashSet<>(references)).build());
-    }
-
-
-    default void addMatchedRule(MatchedRule matchedRule) {
-
-        getMatchedRuleList().add(matchedRule);
-    }
-
-
-    default void addMatchedRules(Collection<MatchedRule> matchedRules) {
-
-        if (getMatchedRuleList().equals(matchedRules)) {
-            return;
-        }
-        getMatchedRuleList().addAll(matchedRules);
-    }
-
-
-    default int getMatchedRuleUnit() {
-
-        return getMatchedRule().getRuleIdentifier().unit();
-    }
-
-
-    default MatchedRule getMatchedRule() {
-
-        if (getMatchedRuleList().isEmpty()) {
-            return MatchedRule.empty();
-        }
-        return getMatchedRuleList().peek();
-    }
-
-
-    default String buildReasonWithManualChangeDescriptions() {
-
-        if (getManualOverwrite().getDescriptions().isEmpty()) {
-            return getMatchedRule().getReason();
-        }
-        if (getMatchedRule().getReason().isEmpty()) {
-            return String.join(", ", getManualOverwrite().getDescriptions());
-        }
-        return getMatchedRule().getReason() + ", " + String.join(", ", getManualOverwrite().getDescriptions());
-    }
-
-
-    default String legalBasis() {
-
-        return getManualOverwrite().getLegalBasis().orElse(getMatchedRule().getLegalBasis());
-    }
-
-}

redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/document/graph/entity/EntityType.java

@@ -1,8 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.graph.entity;
-
-public enum EntityType {
-    ENTITY,
-    RECOMMENDATION,
-    FALSE_POSITIVE,
-    FALSE_RECOMMENDATION
-}

redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/document/graph/entity/ManualChangeOverwrite.java

@@ -1,200 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.graph.entity;
-
-import java.util.Collections;
-import java.util.Comparator;
-import java.util.LinkedList;
-import java.util.List;
-import java.util.Map;
-import java.util.Optional;
-
-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.ManualRecategorization;
-import com.iqser.red.service.persistence.service.v1.api.shared.model.annotations.entitymapped.ManualLegalBasisChange;
-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 lombok.AccessLevel;
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.NoArgsConstructor;
-import lombok.experimental.FieldDefaults;
-
-@Builder
-@NoArgsConstructor
-@AllArgsConstructor
-@FieldDefaults(level = AccessLevel.PRIVATE)
-public class ManualChangeOverwrite {
-
-    private static final Map<Class<? extends BaseAnnotation>, String> MANUAL_CHANGE_DESCRIPTIONS = Map.of(//
-            ManualRedactionEntry.class, "created by manual change", //
-            ManualLegalBasisChange.class, "legal basis was manually changed", //
-            ManualResizeRedaction.class, "resized by manual override", //
-            ManualForceRedaction.class, "forced by manual override", //
-            IdRemoval.class, "removed by manual override", //
-            ManualRecategorization.class, "recategorized by manual override");
-
-    List<BaseAnnotation> manualChanges = new LinkedList<>();
-    boolean changed;
-    List<String> descriptions;
-    String type;
-    String legalBasis;
-    String section;
-    String value;
-    Boolean applied;
-    Boolean removed;
-    Boolean ignored;
-    Boolean resized;
-    Boolean recategorized;
-
-
-    public void calculateCurrentOverride() {
-
-        if (!changed) {
-            return;
-        }
-        List<BaseAnnotation> sortedManualChanges = getManualChangeLog();
-        updateFields(sortedManualChanges);
-    }
-
-
-    public List<BaseAnnotation> getManualChangeLog() {
-
-        if (!changed) {
-            return manualChanges;
-        }
-        manualChanges.sort(Comparator.comparing(BaseAnnotation::getRequestDate));
-        updateFields(manualChanges);
-        // make list unmodifiable.
-        return manualChanges.stream().toList();
-    }
-
-
-    private void updateFields(List<BaseAnnotation> sortedManualChanges) {
-
-        descriptions = new LinkedList<>();
-
-        for (BaseAnnotation manualChange : sortedManualChanges) {
-            // ManualRedactionEntries are created prior to rule execution in analysis service.
-
-            if (manualChange instanceof IdRemoval) {
-                applied = false;
-                ignored = true;
-            }
-
-            if (manualChange instanceof ManualForceRedaction manualForceRedaction) {
-                removed = false;
-                ignored = false;
-                applied = true;
-                legalBasis = manualForceRedaction.getLegalBasis();
-            }
-
-            if (manualChange instanceof ManualLegalBasisChange manualLegalBasisChange) {
-                section = manualLegalBasisChange.getSection();
-                legalBasis = manualLegalBasisChange.getLegalBasis();
-                value = manualLegalBasisChange.getValue();
-            }
-
-            if (manualChange instanceof ManualResizeRedaction) {
-                // resizing logic happens in ManualChangesApplicationService.
-                resized = true;
-            }
-
-            if (manualChange instanceof ManualRecategorization recategorization) {
-                // recategorization logic happens in ManualChangesApplicationService.
-                recategorized = true;
-                // this is only relevant for ManualEntities. Image and TextEntity is recategorized in the ManualChangesApplicationService.
-                type = recategorization.getType();
-            }
-
-            descriptions.add(MANUAL_CHANGE_DESCRIPTIONS.get(manualChange.getClass()));
-        }
-        changed = false;
-    }
-
-
-    public void addChange(BaseAnnotation manualChange) {
-
-        changed = true;
-        manualChanges.add(manualChange);
-    }
-
-
-    public void addChanges(List<BaseAnnotation> manualChangeLog) {
-
-        changed = true;
-        manualChanges.addAll(manualChangeLog);
-    }
-
-
-    public Optional<String> getLegalBasis() {
-
-        calculateCurrentOverride();
-        return legalBasis == null ? Optional.empty() : Optional.of(legalBasis);
-    }
-
-
-    public Optional<String> getType() {
-
-        calculateCurrentOverride();
-        return type == null ? Optional.empty() : Optional.of(type);
-    }
-
-
-    public Optional<String> getSection() {
-
-        calculateCurrentOverride();
-        return section == null ? Optional.empty() : Optional.of(section);
-    }
-
-
-    public Optional<String> getValue() {
-
-        calculateCurrentOverride();
-        return value == null ? Optional.empty() : Optional.of(value);
-    }
-
-
-    public Optional<Boolean> getApplied() {
-
-        calculateCurrentOverride();
-        return applied == null ? Optional.empty() : Optional.of(applied);
-    }
-
-
-    public Optional<Boolean> getRemoved() {
-
-        calculateCurrentOverride();
-        return removed == null ? Optional.empty() : Optional.of(removed);
-    }
-
-
-    public Optional<Boolean> getIgnored() {
-
-        calculateCurrentOverride();
-        return ignored == null ? Optional.empty() : Optional.of(ignored);
-    }
-
-
-    public Optional<Boolean> getResized() {
-
-        calculateCurrentOverride();
-        return resized == null ? Optional.empty() : Optional.of(resized);
-    }
-
-
-    public Optional<Boolean> getRecategorized() {
-
-        calculateCurrentOverride();
-        return recategorized == null ? Optional.empty() : Optional.of(recategorized);
-    }
-
-
-    public List<String> getDescriptions() {
-
-        calculateCurrentOverride();
-        return descriptions == null ? Collections.emptyList() : descriptions;
-    }
-
-}

redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/document/graph/entity/MatchedRule.java

@@ -1,86 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.graph.entity;
-
-import java.util.Collections;
-import java.util.List;
-import java.util.Objects;
-import java.util.Set;
-
-import lombok.AccessLevel;
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.EqualsAndHashCode;
-import lombok.Getter;
-import lombok.experimental.FieldDefaults;
-
-@Getter
-@Builder
-@AllArgsConstructor
-@EqualsAndHashCode
-@FieldDefaults(makeFinal = true, level = AccessLevel.PRIVATE)
-public final class MatchedRule implements Comparable<MatchedRule> {
-
-    public static final String FINAL_TYPE = "FINAL";
-    public static final String ELIMINATION_RULE_TYPE = "X";
-    private static final List<String> RULE_TYPE_PRIORITIES = List.of(FINAL_TYPE, ELIMINATION_RULE_TYPE);
-
-    @Builder.Default
-    RuleIdentifier ruleIdentifier = RuleIdentifier.empty();
-    @Builder.Default
-    String reason = "";
-    @Builder.Default
-    String legalBasis = "";
-    boolean applied;
-    boolean writeValueWithLineBreaks;
-    boolean removed;
-    boolean ignored;
-    boolean resized;
-    @Builder.Default
-    Set<TextEntity> references = Collections.emptySet();
-
-
-    public static MatchedRule empty() {
-
-        return MatchedRule.builder().build();
-    }
-
-
-    @Override
-    public int compareTo(MatchedRule matchedRule) {
-
-        // Only the highest ranked rule is actually applied, this method defines the highest order.
-        // First, it compares the Rule Type, RULE_TYPE_PRIORITIES defines the order of types.
-        // Types not in the list have the lowest priority.
-        // The ones in the list are technical exceptions and should override any other Rule.
-        // Aside from them Entities should never match from more than one type!
-        // E.g. a CBI_author entity should **always** only match CBI.*.* rules.
-        // Otherwise, something went wrong with the rules. :)
-        RuleIdentifier otherRuleIdentifier = matchedRule.getRuleIdentifier();
-        boolean thisInList = RULE_TYPE_PRIORITIES.contains(this.getRuleIdentifier().type());
-        boolean otherInList = RULE_TYPE_PRIORITIES.contains(otherRuleIdentifier.type());
-
-        // Compare the types
-        if (thisInList && !otherInList) {
-            return -1;
-        } else if (!thisInList && otherInList) {
-            return 1;
-        } else if (thisInList && otherInList) {
-            int thisIndex = RULE_TYPE_PRIORITIES.indexOf(this.getRuleIdentifier().type());
-            int otherIndex = RULE_TYPE_PRIORITIES.indexOf(otherRuleIdentifier.type());
-            return Integer.compare(thisIndex, otherIndex);
-        }
-        // Then compare the unit
-        if (!Objects.equals(otherRuleIdentifier.unit(), getRuleIdentifier().unit())) {
-            return Integer.compare(otherRuleIdentifier.unit(), ruleIdentifier.unit());
-        }
-        // Then compare the id inside the unit
-        return Integer.compare(otherRuleIdentifier.id(), ruleIdentifier.id());
-    }
-
-
-    @Override
-    public String toString() {
-
-        return "MatchedRule[ruleIdentifier=" + ruleIdentifier + ", reason=" + reason + ", legalBasis=" + legalBasis + ", applied=" + applied + ", writeValueWithLineBreaks=" + writeValueWithLineBreaks + ", references=" + references + ']';
-    }
-
-}

redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/document/graph/entity/PositionOnPage.java

@@ -1,25 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.graph.entity;
-
-import java.awt.geom.Rectangle2D;
-import java.util.List;
-
-import com.iqser.red.service.redaction.v1.server.document.graph.nodes.Page;
-
-import lombok.AccessLevel;
-import lombok.AllArgsConstructor;
-import lombok.Data;
-import lombok.experimental.FieldDefaults;
-
-@Data
-@AllArgsConstructor
-@FieldDefaults(level = AccessLevel.PRIVATE)
-public class PositionOnPage {
-
-    // Each entry in this list corresponds to an entry in the redaction log, this means:
-    // A single entity might be represented by multiple redaction log entries
-    // This is due to the RedactionLog only being able to handle a single page per entry.
-    final String id;
-    Page page;
-    List<Rectangle2D> rectanglePerLine;
-
-}

redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/document/graph/entity/RuleIdentifier.java

@@ -1,41 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.graph.entity;
-
-import java.util.Objects;
-
-public record RuleIdentifier(String type, Integer unit, Integer id) {
-
-    public static RuleIdentifier fromString(String identifier) {
-
-        String[] values = identifier.split("\\.");
-        if (values.length != 3) {
-            throw new IllegalArgumentException("Illegal rule identifier provided: " + identifier);
-        }
-        String type = values[0];
-        Integer group = Integer.parseInt(values[1]);
-        Integer id = Integer.parseInt(values[2]);
-        return new RuleIdentifier(type, group, id);
-    }
-
-
-    public static RuleIdentifier empty() {
-
-        return new RuleIdentifier("", null, null);
-    }
-
-
-    @Override
-    public String toString() {
-
-        StringBuilder sb = new StringBuilder();
-        sb.append(type());
-        if (Objects.nonNull(unit()) && Objects.nonNull(id())) {
-            sb.append(".").append(unit()).append(".").append(id());
-        } else if (Objects.nonNull(id())) {
-            sb.append(".*.").append(id());
-        } else if (Objects.nonNull(unit())) {
-            sb.append(".").append(unit()).append(".*");
-        }
-        return sb.toString();
-    }
-
-}

redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/document/graph/entity/TextEntity.java

@@ -1,204 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.graph.entity;
-
-import java.awt.geom.Rectangle2D;
-import java.util.Collection;
-import java.util.Comparator;
-import java.util.HashSet;
-import java.util.LinkedList;
-import java.util.List;
-import java.util.Map;
-import java.util.PriorityQueue;
-import java.util.Set;
-
-import com.iqser.red.service.persistence.service.v1.api.shared.model.redactionlog.Engine;
-import com.iqser.red.service.redaction.v1.server.document.graph.TextRange;
-import com.iqser.red.service.redaction.v1.server.document.graph.nodes.Page;
-import com.iqser.red.service.redaction.v1.server.document.graph.nodes.SemanticNode;
-import com.iqser.red.service.redaction.v1.server.redaction.utils.IdBuilder;
-
-import lombok.AccessLevel;
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.Data;
-import lombok.EqualsAndHashCode;
-import lombok.experimental.FieldDefaults;
-
-@Data
-@Builder
-@AllArgsConstructor
-@FieldDefaults(level = AccessLevel.PRIVATE)
-@EqualsAndHashCode(onlyExplicitlyIncluded = true)
-public class TextEntity implements Entity {
-
-    // primary key
-    @EqualsAndHashCode.Include
-    final TextRange textRange;
-    @EqualsAndHashCode.Include
-    final String type;
-    @EqualsAndHashCode.Include
-    final EntityType entityType;
-    // primary key end
-
-    @Builder.Default
-    final PriorityQueue<MatchedRule> matchedRuleList = new PriorityQueue<>();
-    @Builder.Default
-    final ManualChangeOverwrite manualOverwrite = new ManualChangeOverwrite();
-
-    boolean dictionaryEntry;
-    boolean dossierDictionaryEntry;
-
-    @Builder.Default
-    Set<Engine> engines = new HashSet<>();
-
-
-    // inferred on graph insertion
-    String value;
-    String textBefore;
-    String textAfter;
-    @Builder.Default
-    Set<Page> pages = new HashSet<>();
-    List<PositionOnPage> positionsOnPagePerPage;
-    @Builder.Default
-    List<SemanticNode> intersectingNodes = new LinkedList<>();
-    SemanticNode deepestFullyContainingNode;
-
-
-    public static TextEntity initialEntityNode(TextRange textRange, String type, EntityType entityType) {
-
-        return TextEntity.builder().type(type).entityType(entityType).textRange(textRange).build();
-    }
-
-
-    public boolean occursInNodeOfType(Class<? extends SemanticNode> clazz) {
-
-        return intersectingNodes.stream().anyMatch(clazz::isInstance);
-    }
-
-
-    public boolean occursInNode(SemanticNode semanticNode) {
-
-        return intersectingNodes.stream().anyMatch(node -> node.equals(semanticNode));
-    }
-
-
-    public boolean isType(String type) {
-
-        return this.type.equals(type);
-    }
-
-
-    public boolean isAnyType(List<String> types) {
-
-        return types.contains(type);
-    }
-
-
-    public void addIntersectingNode(SemanticNode containingNode) {
-
-        intersectingNodes.add(containingNode);
-    }
-
-
-    public String getValueWithLineBreaks() {
-
-        return getDeepestFullyContainingNode().getTextBlock().subSequenceWithLineBreaks(getTextRange());
-    }
-
-
-    public void removeFromGraph() {
-
-        intersectingNodes.forEach(node -> node.getEntities().remove(this));
-        pages.forEach(page -> page.getEntities().remove(this));
-        intersectingNodes = new LinkedList<>();
-        deepestFullyContainingNode = null;
-        pages = new HashSet<>();
-        remove("FINAL.0.0", "removed completely");
-    }
-
-
-    public List<PositionOnPage> getPositionsOnPagePerPage() {
-
-        if (positionsOnPagePerPage == null || positionsOnPagePerPage.isEmpty()) {
-            Map<Page, List<Rectangle2D>> rectanglesPerLinePerPage = deepestFullyContainingNode.getTextBlock().getPositionsPerPage(textRange);
-
-            Page firstPage = rectanglesPerLinePerPage.keySet()
-                    .stream()
-                    .min(Comparator.comparingInt(Page::getNumber))
-                    .orElseThrow(() -> new RuntimeException("No Positions found on any page!"));
-
-            String id = IdBuilder.buildId(pages, rectanglesPerLinePerPage.values().stream().flatMap(Collection::stream).toList(), type, entityType.name());
-            positionsOnPagePerPage = rectanglesPerLinePerPage.entrySet().stream().map(entry -> buildPositionOnPage(firstPage, id, entry)).toList();
-        }
-        return positionsOnPagePerPage;
-    }
-
-
-    private static PositionOnPage buildPositionOnPage(Page firstPage, String id, Map.Entry<Page, List<Rectangle2D>> entry) {
-
-        if (entry.getKey().equals(firstPage)) {
-            return new PositionOnPage(id, entry.getKey(), entry.getValue());
-        } else {
-            return new PositionOnPage(id + "-" + entry.getKey().getNumber(), entry.getKey(), entry.getValue());
-        }
-    }
-
-
-    public boolean containedBy(TextEntity textEntity) {
-
-        return this.textRange.containedBy(textEntity.getTextRange());
-    }
-
-
-    public boolean contains(TextEntity textEntity) {
-
-        return this.textRange.contains(textEntity.getTextRange());
-    }
-
-
-    public boolean intersects(TextEntity textEntity) {
-
-        return this.textRange.intersects(textEntity.getTextRange());
-    }
-
-
-    public void addEngine(Engine engine) {
-
-        engines.add(engine);
-    }
-
-
-    public void addEngines(Set<Engine> engines) {
-
-        this.engines.addAll(engines);
-    }
-
-
-    public boolean matchesAnnotationId(String manualRedactionId) {
-
-        return getPositionsOnPagePerPage().stream().anyMatch(entityPosition -> entityPosition.getId().equals(manualRedactionId));
-    }
-
-
-    @Override
-    public String toString() {
-
-        StringBuilder sb = new StringBuilder();
-        sb.append("Entity[\"");
-        sb.append(value);
-        sb.append("\", ");
-        sb.append(textRange);
-        sb.append(", pages[");
-        pages.forEach(page -> {
-            sb.append(page.getNumber());
-            sb.append(", ");
-        });
-        sb.delete(sb.length() - 2, sb.length());
-        sb.append("], type = \"");
-        sb.append(type);
-        sb.append("\", EntityType.");
-        sb.append(entityType);
-        sb.append("]");
-        return sb.toString();
-    }
-
-}

redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/document/graph/nodes/Document.java

@@ -1,127 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.graph.nodes;
-
-import java.awt.geom.Rectangle2D;
-import java.util.Collections;
-import java.util.HashMap;
-import java.util.HashSet;
-import java.util.List;
-import java.util.Map;
-import java.util.Set;
-import java.util.stream.Collectors;
-import java.util.stream.Stream;
-
-import com.iqser.red.service.redaction.v1.server.document.graph.DocumentTree;
-import com.iqser.red.service.redaction.v1.server.document.graph.entity.TextEntity;
-import com.iqser.red.service.redaction.v1.server.document.graph.textblock.TextBlock;
-import com.iqser.red.service.redaction.v1.server.document.graph.textblock.TextBlockCollector;
-
-import lombok.AccessLevel;
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.Data;
-import lombok.NoArgsConstructor;
-import lombok.experimental.FieldDefaults;
-
-@Data
-@Builder
-@AllArgsConstructor
-@NoArgsConstructor
-@FieldDefaults(level = AccessLevel.PRIVATE)
-public class Document implements GenericSemanticNode {
-
-    Set<Page> pages;
-    DocumentTree documentTree;
-    Integer numberOfPages;
-    TextBlock textBlock;
-    @Builder.Default
-    Set<TextEntity> entities = new HashSet<>();
-    @Builder.Default
-    static final SectionIdentifier sectionIdentifier = SectionIdentifier.document();
-
-
-    @Override
-    public NodeType getType() {
-
-        return NodeType.DOCUMENT;
-    }
-
-
-    public TextBlock getTextBlock() {
-
-        if (textBlock == null) {
-            textBlock = streamTerminalTextBlocksInOrder().collect(new TextBlockCollector());
-        }
-        return textBlock;
-    }
-
-
-    public List<Section> getMainSections() {
-
-        return streamChildrenOfType(NodeType.SECTION).map(node -> (Section) node).collect(Collectors.toList());
-    }
-
-
-    public Stream<TextBlock> streamTerminalTextBlocksInOrder() {
-
-        return streamAllNodes().filter(SemanticNode::isLeaf).map(SemanticNode::getLeafTextBlock);
-    }
-
-
-    @Override
-    public List<Integer> getTreeId() {
-
-        return Collections.emptyList();
-    }
-
-
-    @Override
-    public void setTreeId(List<Integer> tocId) {
-
-        throw new UnsupportedOperationException("Document is always the root of the TablePageBlock of Contents");
-    }
-
-
-    @Override
-    public SectionIdentifier getSectionIdentifier() {
-
-        return sectionIdentifier;
-    }
-
-
-    @Override
-    public Headline getHeadline() {
-
-        return streamAllSubNodesOfType(NodeType.HEADLINE).map(node -> (Headline) node).findFirst().orElseGet(Headline::empty);
-    }
-
-
-    private Stream<SemanticNode> streamAllNodes() {
-
-        return documentTree.allEntriesInOrder().map(DocumentTree.Entry::getNode);
-    }
-
-
-    public Stream<Image> streamAllImages() {
-
-        return streamAllSubNodesOfType(NodeType.IMAGE).map(node -> (Image) node);
-    }
-
-
-    @Override
-    public String toString() {
-
-        return NodeType.DOCUMENT + ": " + this.getTextBlock().buildSummary();
-    }
-
-
-    @Override
-    public Map<Page, Rectangle2D> getBBox() {
-
-        Map<Page, Rectangle2D> bBox = new HashMap<>();
-        for (Page page : pages) {
-            bBox.put(page, new Rectangle2D.Double(0, 0, page.getWidth(), page.getHeight()));
-        }
-        return bBox;
-    }
-
-}

redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/document/graph/nodes/Footer.java

@@ -1,74 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.graph.nodes;
-
-import java.util.HashSet;
-import java.util.List;
-import java.util.Set;
-
-import com.iqser.red.service.redaction.v1.server.document.graph.DocumentTree;
-import com.iqser.red.service.redaction.v1.server.document.graph.entity.TextEntity;
-import com.iqser.red.service.redaction.v1.server.document.graph.textblock.TextBlock;
-
-import lombok.AccessLevel;
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.Data;
-import lombok.EqualsAndHashCode;
-import lombok.NoArgsConstructor;
-import lombok.experimental.FieldDefaults;
-
-@Data
-@Builder
-@AllArgsConstructor
-@NoArgsConstructor
-@FieldDefaults(level = AccessLevel.PRIVATE)
-public class Footer implements GenericSemanticNode {
-
-    @Builder.Default
-    final static SectionIdentifier sectionIdentifier = SectionIdentifier.empty();
-
-    List<Integer> treeId;
-    TextBlock leafTextBlock;
-
-    @EqualsAndHashCode.Exclude
-    DocumentTree documentTree;
-
-    @Builder.Default
-    @EqualsAndHashCode.Exclude
-    Set<TextEntity> entities = new HashSet<>();
-
-
-    @Override
-    public NodeType getType() {
-
-        return NodeType.FOOTER;
-    }
-
-
-    @Override
-    public boolean isLeaf() {
-
-        return true;
-    }
-
-
-    @Override
-    public TextBlock getTextBlock() {
-
-        return leafTextBlock;
-    }
-
-
-    @Override
-    public SectionIdentifier getSectionIdentifier() {
-
-        return sectionIdentifier;
-    }
-
-
-    @Override
-    public String toString() {
-
-        return treeId + ": " + NodeType.FOOTER + ": " + leafTextBlock.buildSummary();
-    }
-
-}

redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/document/graph/nodes/GenericSemanticNode.java

@@ -1,5 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.graph.nodes;
-
-public interface GenericSemanticNode extends SemanticNode {
-
-}

redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/document/graph/nodes/Header.java

@@ -1,74 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.graph.nodes;
-
-import java.util.HashSet;
-import java.util.List;
-import java.util.Set;
-
-import com.iqser.red.service.redaction.v1.server.document.graph.entity.TextEntity;
-import com.iqser.red.service.redaction.v1.server.document.graph.DocumentTree;
-import com.iqser.red.service.redaction.v1.server.document.graph.textblock.TextBlock;
-
-import lombok.AccessLevel;
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.Data;
-import lombok.EqualsAndHashCode;
-import lombok.NoArgsConstructor;
-import lombok.experimental.FieldDefaults;
-
-@Data
-@Builder
-@AllArgsConstructor
-@NoArgsConstructor
-@FieldDefaults(level = AccessLevel.PRIVATE)
-public class Header implements GenericSemanticNode {
-
-    @Builder.Default
-    final static SectionIdentifier sectionIdentifier = SectionIdentifier.empty();
-
-    List<Integer> treeId;
-    TextBlock leafTextBlock;
-
-    @EqualsAndHashCode.Exclude
-    DocumentTree documentTree;
-
-    @Builder.Default
-    @EqualsAndHashCode.Exclude
-    Set<TextEntity> entities = new HashSet<>();
-
-
-    @Override
-    public boolean isLeaf() {
-
-        return true;
-    }
-
-
-    @Override
-    public NodeType getType() {
-
-        return NodeType.HEADER;
-    }
-
-
-    @Override
-    public TextBlock getTextBlock() {
-
-        return leafTextBlock;
-    }
-
-
-    @Override
-    public SectionIdentifier getSectionIdentifier() {
-
-        return sectionIdentifier;
-    }
-
-
-    @Override
-    public String toString() {
-
-        return treeId + ": " + NodeType.HEADER + ": " + leafTextBlock.buildSummary();
-    }
-
-}

redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/document/graph/nodes/Headline.java

@@ -1,95 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.graph.nodes;
-
-import java.util.HashSet;
-import java.util.List;
-import java.util.Set;
-
-import com.iqser.red.service.redaction.v1.server.document.graph.DocumentTree;
-import com.iqser.red.service.redaction.v1.server.document.graph.entity.TextEntity;
-import com.iqser.red.service.redaction.v1.server.document.graph.textblock.AtomicTextBlock;
-import com.iqser.red.service.redaction.v1.server.document.graph.textblock.TextBlock;
-
-import lombok.AccessLevel;
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.Data;
-import lombok.EqualsAndHashCode;
-import lombok.NoArgsConstructor;
-import lombok.experimental.FieldDefaults;
-
-@Data
-@Builder
-@AllArgsConstructor
-@NoArgsConstructor
-@FieldDefaults(level = AccessLevel.PRIVATE)
-public class Headline implements GenericSemanticNode {
-
-    List<Integer> treeId;
-    TextBlock leafTextBlock;
-    SectionIdentifier sectionIdentifier;
-
-    @EqualsAndHashCode.Exclude
-    DocumentTree documentTree;
-
-    @Builder.Default
-    @EqualsAndHashCode.Exclude
-    Set<TextEntity> entities = new HashSet<>();
-
-
-    @Override
-    public NodeType getType() {
-
-        return NodeType.HEADLINE;
-    }
-
-
-    @Override
-    public boolean isLeaf() {
-
-        return true;
-    }
-
-
-    @Override
-    public TextBlock getTextBlock() {
-
-        return leafTextBlock;
-    }
-
-
-    @Override
-    public String toString() {
-
-        return treeId + ": " + NodeType.HEADLINE + ": " + leafTextBlock.buildSummary();
-    }
-
-
-    @Override
-    public Headline getHeadline() {
-
-        return this;
-    }
-
-
-    @Override
-    public SectionIdentifier getSectionIdentifier() {
-
-        if (sectionIdentifier == null) {
-            sectionIdentifier = SectionIdentifier.fromSearchText(getTextBlock().getSearchText());
-        }
-        return sectionIdentifier;
-    }
-
-
-    public static Headline empty() {
-
-        return Headline.builder().leafTextBlock(AtomicTextBlock.empty(-1L, 0, new Page(), -1, null)).build();
-    }
-
-
-    public boolean hasParagraphs() {
-
-        return getParent().streamAllSubNodesOfType(NodeType.PARAGRAPH).findFirst().isPresent();
-    }
-
-}

redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/document/graph/nodes/Image.java

@@ -1,95 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.graph.nodes;
-
-import java.awt.geom.Rectangle2D;
-import java.util.Collections;
-import java.util.HashMap;
-import java.util.HashSet;
-import java.util.List;
-import java.util.Map;
-import java.util.PriorityQueue;
-import java.util.Set;
-
-import com.iqser.red.service.redaction.v1.server.document.graph.DocumentTree;
-import com.iqser.red.service.redaction.v1.server.document.graph.entity.Entity;
-import com.iqser.red.service.redaction.v1.server.document.graph.entity.ManualChangeOverwrite;
-import com.iqser.red.service.redaction.v1.server.document.graph.entity.MatchedRule;
-import com.iqser.red.service.redaction.v1.server.document.graph.entity.TextEntity;
-import com.iqser.red.service.redaction.v1.server.document.graph.textblock.TextBlock;
-import com.iqser.red.service.redaction.v1.server.document.graph.textblock.TextBlockCollector;
-
-import lombok.AccessLevel;
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.Data;
-import lombok.EqualsAndHashCode;
-import lombok.NoArgsConstructor;
-import lombok.experimental.FieldDefaults;
-
-@Data
-@Builder
-@AllArgsConstructor
-@NoArgsConstructor
-@FieldDefaults(level = AccessLevel.PRIVATE)
-public class Image implements GenericSemanticNode, Entity {
-
-    List<Integer> treeId;
-    String id;
-
-    ImageType imageType;
-    boolean transparent;
-    Rectangle2D position;
-
-    @Builder.Default
-    PriorityQueue<MatchedRule> matchedRuleList = new PriorityQueue<>();
-
-    @Builder.Default
-    ManualChangeOverwrite manualOverwrite = new ManualChangeOverwrite();
-
-    @EqualsAndHashCode.Exclude
-    Page page;
-
-    @EqualsAndHashCode.Exclude
-    DocumentTree documentTree;
-
-    @Builder.Default
-    @EqualsAndHashCode.Exclude
-    Set<TextEntity> entities = new HashSet<>();
-
-
-    @Override
-    public NodeType getType() {
-
-        return NodeType.IMAGE;
-    }
-
-
-    @Override
-    public TextBlock getTextBlock() {
-
-        return streamAllSubNodes().filter(SemanticNode::isLeaf).map(SemanticNode::getLeafTextBlock).collect(new TextBlockCollector());
-    }
-
-
-    @Override
-    public Set<Page> getPages() {
-
-        return Collections.singleton(page);
-    }
-
-
-    @Override
-    public String toString() {
-
-        return treeId + ": " + NodeType.IMAGE + ": " + imageType.toString() + " " + position;
-    }
-
-
-    @Override
-    public Map<Page, Rectangle2D> getBBox() {
-
-        Map<Page, Rectangle2D> bBoxPerPage = new HashMap<>();
-        bBoxPerPage.put(page, position);
-        return bBoxPerPage;
-    }
-
-}

redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/document/graph/nodes/ImageType.java

@@ -1,23 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.graph.nodes;
-
-import java.util.Locale;
-
-public enum ImageType {
-    LOGO,
-    FORMULA,
-    SIGNATURE,
-    OTHER,
-    OCR;
-
-
-    public static ImageType fromString(String imageType) {
-
-        return switch (imageType.toLowerCase(Locale.ROOT)) {
-            case "logo" -> ImageType.LOGO;
-            case "formula" -> ImageType.FORMULA;
-            case "signature" -> ImageType.SIGNATURE;
-            case "ocr" -> ImageType.OCR;
-            default -> ImageType.OTHER;
-        };
-    }
-}

redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/document/graph/nodes/NodeType.java

@@ -1,21 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.graph.nodes;
-
-import java.util.Locale;
-
-public enum NodeType {
-    DOCUMENT,
-    SECTION,
-    HEADLINE,
-    PARAGRAPH,
-    TABLE,
-    TABLE_CELL,
-    IMAGE,
-    HEADER,
-    FOOTER;
-
-
-    public String toString() {
-
-        return this.name().charAt(0) + this.name().substring(1).toLowerCase(Locale.ROOT);
-    }
-}

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

@@ -1,75 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.graph.nodes;
-
-import java.util.HashSet;
-import java.util.List;
-import java.util.Set;
-
-import com.iqser.red.service.redaction.v1.server.document.graph.entity.TextEntity;
-import com.iqser.red.service.redaction.v1.server.document.graph.textblock.TextBlock;
-import com.iqser.red.service.redaction.v1.server.document.graph.textblock.TextBlockCollector;
-
-import lombok.AccessLevel;
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.EqualsAndHashCode;
-import lombok.Getter;
-import lombok.NoArgsConstructor;
-import lombok.Setter;
-import lombok.experimental.FieldDefaults;
-
-@Getter
-@Setter
-@Builder
-@NoArgsConstructor
-@AllArgsConstructor
-@FieldDefaults(level = AccessLevel.PRIVATE)
-public class Page {
-
-    Integer number;
-    Integer height;
-    Integer width;
-    Integer rotation;
-
-    @EqualsAndHashCode.Exclude
-    List<SemanticNode> mainBody;
-    @EqualsAndHashCode.Exclude
-    Header header;
-    @EqualsAndHashCode.Exclude
-    Footer footer;
-
-    @Builder.Default
-    @EqualsAndHashCode.Exclude
-    Set<TextEntity> entities = new HashSet<>();
-
-    @Builder.Default
-    @EqualsAndHashCode.Exclude
-    Set<Image> images = new HashSet<>();
-
-
-    public TextBlock getMainBodyTextBlock() {
-
-        return mainBody.stream().filter(SemanticNode::isLeaf).map(SemanticNode::getLeafTextBlock).collect(new TextBlockCollector());
-    }
-
-
-    @Override
-    public String toString() {
-
-        return String.valueOf(number);
-    }
-
-
-    @Override
-    public int hashCode() {
-
-        return number;
-    }
-
-
-    @Override
-    public boolean equals(Object o) {
-
-        return o instanceof Page && o.hashCode() == this.hashCode();
-    }
-
-}

redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/document/graph/nodes/Paragraph.java

@@ -1,62 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.graph.nodes;
-
-import java.util.HashSet;
-import java.util.List;
-import java.util.Set;
-
-import com.iqser.red.service.redaction.v1.server.document.graph.DocumentTree;
-import com.iqser.red.service.redaction.v1.server.document.graph.entity.TextEntity;
-import com.iqser.red.service.redaction.v1.server.document.graph.textblock.TextBlock;
-
-import lombok.AccessLevel;
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.Data;
-import lombok.EqualsAndHashCode;
-import lombok.experimental.FieldDefaults;
-
-@Data
-@Builder
-@AllArgsConstructor
-@FieldDefaults(level = AccessLevel.PRIVATE)
-public class Paragraph implements GenericSemanticNode {
-
-    List<Integer> treeId;
-    TextBlock leafTextBlock;
-
-    @EqualsAndHashCode.Exclude
-    DocumentTree documentTree;
-
-    @Builder.Default
-    @EqualsAndHashCode.Exclude
-    Set<TextEntity> entities = new HashSet<>();
-
-
-    @Override
-    public NodeType getType() {
-
-        return NodeType.PARAGRAPH;
-    }
-
-
-    @Override
-    public boolean isLeaf() {
-
-        return true;
-    }
-
-
-    @Override
-    public TextBlock getTextBlock() {
-
-        return leafTextBlock;
-    }
-
-
-    @Override
-    public String toString() {
-
-        return treeId + ": " + NodeType.PARAGRAPH + ": " + leafTextBlock.buildSummary();
-    }
-
-}

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

@@ -1,95 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.graph.nodes;
-
-import java.util.HashSet;
-import java.util.List;
-import java.util.Set;
-
-import com.iqser.red.service.redaction.v1.server.document.graph.entity.TextEntity;
-import com.iqser.red.service.redaction.v1.server.document.graph.DocumentTree;
-import com.iqser.red.service.redaction.v1.server.document.graph.textblock.TextBlock;
-import com.iqser.red.service.redaction.v1.server.document.graph.textblock.TextBlockCollector;
-
-import lombok.AccessLevel;
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.Data;
-import lombok.EqualsAndHashCode;
-import lombok.experimental.FieldDefaults;
-import lombok.extern.slf4j.Slf4j;
-
-@Slf4j
-@Data
-@Builder
-@AllArgsConstructor
-@FieldDefaults(level = AccessLevel.PRIVATE)
-public class Section implements GenericSemanticNode {
-
-    List<Integer> treeId;
-
-    TextBlock textBlock;
-    @EqualsAndHashCode.Exclude
-    DocumentTree documentTree;
-
-    @Builder.Default
-    @EqualsAndHashCode.Exclude
-    Set<TextEntity> entities = new HashSet<>();
-
-
-    @Override
-    public NodeType getType() {
-
-        return NodeType.SECTION;
-    }
-
-
-    public boolean hasTables() {
-
-        return streamAllSubNodesOfType(NodeType.TABLE).findAny().isPresent();
-    }
-
-
-    @Override
-    public SectionIdentifier getSectionIdentifier() {
-
-        return getHeadline().getSectionIdentifier();
-    }
-
-
-    @Override
-    public TextBlock getTextBlock() {
-
-        if (textBlock == null) {
-            textBlock = streamAllSubNodes().filter(SemanticNode::isLeaf).map(SemanticNode::getLeafTextBlock).collect(new TextBlockCollector());
-        }
-        return textBlock;
-    }
-
-
-    @Override
-    public String toString() {
-
-        return treeId.toString() + ": " + NodeType.SECTION + ": " + this.getTextBlock().buildSummary();
-    }
-
-
-    public Headline getHeadline() {
-
-        return streamChildrenOfType(NodeType.HEADLINE)//
-                .map(node -> (Headline) node)//
-                .findFirst()//
-                .orElseGet(() -> getParent().getHeadline());
-    }
-
-
-    public boolean anyHeadlineContainsString(String value) {
-
-        return streamAllSubNodesOfType(NodeType.HEADLINE).anyMatch(h -> h.containsString(value));
-    }
-
-
-    public boolean anyHeadlineContainsStringIgnoreCase(String value) {
-
-        return streamAllSubNodesOfType(NodeType.HEADLINE).anyMatch(h -> h.containsStringIgnoreCase(value));
-    }
-
-}

redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/document/graph/nodes/SectionIdentifier.java

@@ -1,123 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.graph.nodes;
-
-import java.util.Collections;
-import java.util.LinkedList;
-import java.util.List;
-import java.util.regex.Matcher;
-import java.util.regex.Pattern;
-
-import lombok.AccessLevel;
-import lombok.AllArgsConstructor;
-import lombok.experimental.FieldDefaults;
-
-@AllArgsConstructor
-@FieldDefaults(makeFinal = true, level = AccessLevel.PRIVATE)
-public class SectionIdentifier {
-
-    static Pattern numericalIdentifierPattern = Pattern.compile("^[\\s]?(\\d+)[\\s.,;]?(\\d+)?[\\s.,;]?(\\d+)?[\\s.,;]?(\\d+)?");
-
-    private enum Format {
-        EMPTY,
-        NUMERICAL,
-        DOCUMENT
-    }
-
-    Format format;
-    String identifierString;
-    List<Integer> identifiers;
-    boolean asChild;
-
-
-    public static SectionIdentifier fromSearchText(String headline) {
-
-        if (headline == null || headline.isEmpty() || headline.isBlank()) {
-            return SectionIdentifier.empty();
-        }
-
-        Matcher numericalIdentifierMatcher = numericalIdentifierPattern.matcher(headline);
-        if (numericalIdentifierMatcher.find()) {
-            return buildNumericalSectionIdentifier(headline, numericalIdentifierMatcher);
-        }
-        // more formats here
-        return SectionIdentifier.empty();
-    }
-
-
-    public static SectionIdentifier asChildOf(SectionIdentifier sectionIdentifier) {
-
-        return new SectionIdentifier(sectionIdentifier.format, sectionIdentifier.toString(), sectionIdentifier.identifiers, true);
-    }
-
-
-    public static SectionIdentifier document() {
-
-        return new SectionIdentifier(Format.DOCUMENT, "document", Collections.emptyList(), false);
-    }
-
-
-    public static SectionIdentifier empty() {
-
-        return new SectionIdentifier(Format.EMPTY, "empty", Collections.emptyList(), false);
-    }
-
-
-    private static SectionIdentifier buildNumericalSectionIdentifier(String headline, Matcher numericalIdentifierMatcher) {
-
-        String identifierString = headline.substring(numericalIdentifierMatcher.start(), numericalIdentifierMatcher.end());
-        List<Integer> identifiers = new LinkedList<>();
-        for (int i = 1; i <= 4; i++) {
-            String numericalIdentifier = numericalIdentifierMatcher.group(i);
-            if (numericalIdentifier == null || numericalIdentifier.equals("0") || numericalIdentifier.isEmpty() || numericalIdentifier.isBlank()) {
-                break;
-            }
-            identifiers.add(Integer.parseInt(numericalIdentifier.trim()));
-        }
-        return new SectionIdentifier(Format.NUMERICAL, identifierString, identifiers.stream().toList(), false);
-    }
-
-
-    /**
-     * Determines if the current section is the parent of the given section.
-     *
-     * @param sectionIdentifier The section identifier to compare against.
-     * @return true if the current section is the parent of the given section, false otherwise.
-     */
-    public boolean isParentOf(SectionIdentifier sectionIdentifier) {
-
-        if (this.format.equals(Format.EMPTY)) {
-            return false;
-        }
-        if (this.format.equals(Format.DOCUMENT)) {
-            return true;
-        }
-        if (!this.format.equals(sectionIdentifier.format)) {
-            return false;
-        }
-        if (this.identifiers.size() >= sectionIdentifier.identifiers.size() && !(this.identifiers.size() == sectionIdentifier.identifiers.size() && sectionIdentifier.asChild)) {
-            return false;
-        }
-        for (int i = 0; i < this.identifiers.size(); i++) {
-            if (!this.identifiers.get(i).equals(sectionIdentifier.identifiers.get(i))) {
-                return false;
-            }
-        }
-        return true;
-    }
-
-
-    public boolean isChildOf(SectionIdentifier sectionIdentifier) {
-
-        if (this.format.equals(Format.DOCUMENT) || this.format.equals(Format.EMPTY)) {
-            return false;
-        }
-        return sectionIdentifier.isParentOf(this);
-    }
-
-
-    @Override
-    public String toString() {
-
-        return identifierString;
-    }
-
-}

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

@@ -1,589 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.graph.nodes;
-
-import static java.lang.String.format;
-
-import java.awt.geom.Rectangle2D;
-import java.util.Arrays;
-import java.util.Comparator;
-import java.util.HashMap;
-import java.util.List;
-import java.util.Locale;
-import java.util.Map;
-import java.util.Set;
-import java.util.stream.Collectors;
-import java.util.stream.Stream;
-
-import com.iqser.red.service.redaction.v1.server.document.graph.TextRange;
-import com.iqser.red.service.redaction.v1.server.document.graph.DocumentTree;
-import com.iqser.red.service.redaction.v1.server.document.graph.entity.TextEntity;
-import com.iqser.red.service.redaction.v1.server.document.graph.textblock.AtomicTextBlock;
-import com.iqser.red.service.redaction.v1.server.document.graph.textblock.TextBlock;
-import com.iqser.red.service.redaction.v1.server.document.utils.RectangleTransformations;
-import com.iqser.red.service.redaction.v1.server.document.utils.RedactionSearchUtility;
-
-public interface SemanticNode {
-
-    /**
-     * Returns the type of this node, such as Section, Paragraph, etc.
-     *
-     * @return NodeType of this node
-     */
-    NodeType getType();
-
-
-    /**
-     * Searches all Nodes located underneath this Node in the DocumentTree and concatenates their AtomicTextBlocks into a single TextBlock.
-     * So, for a Section all TextBlocks of Subsections, Paragraphs, and Tables are concatenated into a single TextBlock
-     * If the Node is a Leaf, the LeafTextBlock will be returned instead.
-     *
-     * @return TextBlock containing all AtomicTextBlocks that are located under this Node.
-     */
-    TextBlock getTextBlock();
-
-
-    /**
-     * Any Node maintains its own Set of Entities.
-     * This Set contains all Entities whose TextRange intersects the TextRange of this node.
-     *
-     * @return Set of all Entities associated with this Node
-     */
-    Set<TextEntity> getEntities();
-
-
-    /**
-     * Each AtomicTextBlock is assigned a page, so to get the pages this node appears on, it collects the PageNodes from each AtomicTextBlock belonging to this node's TextBlock.
-     *
-     * @return Set of PageNodes this node appears on.
-     */
-    default Set<Page> getPages() {
-
-        return getTextBlock().getPages();
-    }
-
-    /**
-     * Finds the first page associated with this Node.
-     *
-     * @return Set of PageNodes this node appears on.
-     */
-    default Page getFirstPage() {
-
-        return getTextBlock().getPages().stream().min(Comparator.comparingInt(Page::getNumber)).orElseThrow();
-    }
-
-
-    /**
-     * Each AtomicTextBlock is assigned a page, so to get the pages for this TextRange, it collects the PageNodes from each AtomicTextBlock belonging to this node's TextBlock.
-     *
-     * @return Set of PageNodes this node appears on.
-     */
-    default Set<Page> getPages(TextRange textRange) {
-
-        if (!getTextRange().contains(textRange)) {
-            throw new IllegalArgumentException(format("%s which was used to query for pages is not contained in the %s of this node!", textRange, getTextRange()));
-        }
-        return getTextBlock().getPages(textRange);
-    }
-
-
-    default boolean onPage(int pageNumber) {
-
-        return getPages().stream().anyMatch(page -> page.getNumber() == pageNumber);
-    }
-
-
-    /**
-     * Returns the DocumentTree Object.
-     *
-     * @return the DocumentTree of the Document this node belongs to
-     */
-    DocumentTree getDocumentTree();
-
-
-    /**
-     * The id is a List of Integers uniquely identifying this node in the DocumentTree.
-     *
-     * @return the DocumentTree ID
-     */
-    List<Integer> getTreeId();
-
-
-    /**
-     * This should only be used during graph construction.
-     *
-     * @param tocId List of Integers
-     */
-    void setTreeId(List<Integer> tocId);
-
-
-    /**
-     * Traverses the Tree up, until it hits a Headline or hits a Section which will then return the first Headline from its children.
-     * If no Headline is found this way, it will recursively traverse the tree up and try again until it hits the root, where it will perform a BFS.
-     * If no Headline exists anywhere in the Document a dummy Headline is returned.
-     *
-     * @return First Headline found.
-     */
-    default Headline getHeadline() {
-
-        return getParent().getHeadline();
-    }
-
-
-    /**
-     * Returns a SectionIdentifier, such that it acts as a child of the first Headline associated with this SemanticNode.
-     *
-     * @return The SectionIdentifier from the first Headline.
-     */
-    default SectionIdentifier getSectionIdentifier() {
-
-        return SectionIdentifier.asChildOf(getHeadline().getSectionIdentifier());
-    }
-
-
-    /**
-     * Checks if its TreeId has a length greater than zero.
-     *
-     * @return boolean indicating whether this Node has a Parent in the DocumentTree
-     */
-    default boolean hasParent() {
-
-        return getDocumentTree().hasParentById(getTreeId());
-    }
-
-
-    /**
-     * @return The SemanticNode representing the Parent in the DocumentTree
-     * throws NotFoundException, when no parent is present
-     */
-    default SemanticNode getParent() {
-
-        return getDocumentTree().getParentEntryById(getTreeId()).getNode();
-    }
-
-
-    /**
-     * @return The SemanticNode which is directly underneath the document and also under which this node is.
-     * if this is the highest child node or the document itself, it returns itself.
-     */
-    default SemanticNode getHighestParent() {
-
-        return getDocumentTree().getHighestParentById(getTreeId());
-    }
-
-
-    /**
-     * Leaf means a SemanticNode has direct access to a TextBlock, by default this is false and must be overridden.
-     * Currently only Sections, Images, and Tables are not leaves.
-     * A TableCell might be a leaf depending on its area compared to the page.
-     *
-     * @return boolean, indicating if a Node has direct access to a TextBlock
-     */
-    default boolean isLeaf() {
-
-        return false;
-    }
-
-
-    /**
-     * Leaf means a SemanticNode has direct access to a TextBlock, by default this is false and must be overridden.
-     * Currently only Sections and Tables are no leaves.
-     *
-     * @return AtomicTextBlock
-     */
-    default TextBlock getLeafTextBlock() {
-
-        throw new UnsupportedOperationException("Only leaf Nodes have access to LeafTextBlocks!");
-    }
-
-
-    /**
-     * Should only be used during construction of the Graph. Sets the LeafTextBlock of this SemanticNode.
-     *
-     * @param textBlock the TextBlock to set as the LeafTextBlock of this SemanticNode
-     */
-    default void setLeafTextBlock(TextBlock textBlock) {
-
-        throw new UnsupportedOperationException();
-    }
-
-
-    /**
-     * Checks whether this SemanticNode has any Entity of the provided type.
-     * Ignores Entity with ignored == true or removed == true.
-     *
-     * @param type string representing the type of entity to check for
-     * @return true, if this SemanticNode has at least one Entity of the provided type
-     */
-    default boolean hasEntitiesOfType(String type) {
-
-        return getEntities().stream().filter(TextEntity::active).anyMatch(redactionEntity -> redactionEntity.getType().equals(type));
-    }
-
-
-    /**
-     * Checks whether this SemanticNode has any Entity of the provided types.
-     * Ignores Entity with ignored == true or removed == true.
-     *
-     * @param types an array of strings representing the types of entities to check for
-     * @return true, if this SemanticNode has at least one Entity of any of the provided types
-     */
-    default boolean hasEntitiesOfAnyType(String... types) {
-
-        return getEntities().stream().filter(TextEntity::active).anyMatch(redactionEntity -> Arrays.stream(types).anyMatch(type -> redactionEntity.getType().equals(type)));
-    }
-
-
-    /**
-     * Checks whether this SemanticNode has at least one Entity of each of the provided types.
-     * Ignores Entity with ignored == true or removed == true.
-     *
-     * @param types an array of strings representing the types of entities to check for
-     * @return true, if this SemanticNode has at least one Entity of each of the provided types
-     */
-    default boolean hasEntitiesOfAllTypes(String... types) {
-
-        return getEntities().stream()
-                .filter(TextEntity::active)
-                .map(TextEntity::getType)
-                .collect(Collectors.toUnmodifiableSet())
-                .containsAll(Arrays.stream(types).toList());
-    }
-
-
-    /**
-     * Returns a List of Entities in this SemanticNode which are of the provided type such as "CBI_author".
-     * Ignores Entity with ignored == true or removed == true.
-     *
-     * @param type string representing the type of entities to return
-     * @return List of RedactionEntities of any the type
-     */
-    default List<TextEntity> getEntitiesOfType(String type) {
-
-        return getEntities().stream().filter(TextEntity::active).filter(redactionEntity -> redactionEntity.getType().equals(type)).toList();
-    }
-
-
-    /**
-     * Returns a List of Entities in this SemanticNode which have any of the provided types such as "CBI_author".
-     * Ignores Entity with ignored == true or removed == true.
-     *
-     * @param types A list of strings representing the types of entities to return
-     * @return List of RedactionEntities of any provided type
-     */
-    default List<TextEntity> getEntitiesOfType(List<String> types) {
-
-        return getEntities().stream().filter(TextEntity::active).filter(redactionEntity -> redactionEntity.isAnyType(types)).toList();
-    }
-
-
-    /**
-     * Returns a List of Entities in this SemanticNode which have any of the provided types.
-     * Ignores Entity with the ignored flag set to true or the removed flag set to true.
-     *
-     * @param types A list of strings representing the types of entities to return
-     * @return List of RedactionEntities that match any of the provided types
-     */
-    default List<TextEntity> getEntitiesOfType(String... types) {
-
-        return getEntities().stream().filter(TextEntity::active).filter(redactionEntity -> redactionEntity.isAnyType(Arrays.stream(types).toList())).toList();
-    }
-
-
-    /**
-     * Each AtomicTextBlock has an index on its page, this returns the number of the first AtomicTextBlock underneath this node.
-     * If this node does not have any AtomicTexBlocks underneath it, e.g. an empty TableCell. It returns -1.
-     *
-     * @return Integer representing the number on the page
-     */
-    default Integer getNumberOnPage() {
-
-        TextBlock textBlock = getTextBlock();
-        if (!textBlock.getAtomicTextBlocks().isEmpty()) {
-            return getTextBlock().getAtomicTextBlocks().get(0).getNumberOnPage();
-        } else {
-            return -1;
-        }
-    }
-
-
-    /**
-     * Checks if the SemanticNode contains any text.
-     *
-     * @return true, if this node's TextBlock is not empty
-     */
-    default boolean hasText() {
-
-        return !getTextBlock().isEmpty();
-    }
-
-
-    /**
-     * Checks whether this SemanticNode contains the provided String.
-     *
-     * @param string A String which the TextBlock might contain
-     * @return true, if this node's TextBlock contains the string
-     */
-    default boolean containsString(String string) {
-
-        return getTextBlock().getSearchText().contains(string);
-    }
-
-
-    /**
-     * Checks whether this SemanticNode contains all the provided Strings.
-     *
-     * @param strings A List of Strings which the TextBlock might contain
-     * @return true, if this node's TextBlock contains all strings
-     */
-    default boolean containsAllStrings(String... strings) {
-
-        return Arrays.stream(strings).allMatch(this::containsString);
-    }
-
-
-    /**
-     * Checks whether this SemanticNode contains any of the provided Strings.
-     *
-     * @param strings A List of Strings to check if they are contained in the TextBlock
-     * @return true, if this node's TextBlock contains any of the provided strings
-     */
-    default boolean containsAnyString(String... strings) {
-
-        return Arrays.stream(strings).anyMatch(this::containsString);
-    }
-
-
-    /**
-     * Checks whether this SemanticNode contains any of the provided Strings.
-     *
-     * @param strings A List of Strings which the TextBlock might contain
-     * @return true, if this node's TextBlock contains any of the strings
-     */
-    default boolean containsAnyString(List<String> strings) {
-
-        return strings.stream().anyMatch(this::containsString);
-    }
-
-
-    /**
-     * Checks whether this SemanticNode contains all the provided Strings ignoring case.
-     *
-     * @param string A String which the TextBlock might contain
-     * @return true, if this node's TextBlock contains the string ignoring case
-     */
-    default boolean containsStringIgnoreCase(String string) {
-
-        return getTextBlock().getSearchText().toLowerCase(Locale.ROOT).contains(string.toLowerCase(Locale.ROOT));
-    }
-
-
-    /**
-     * Checks whether this SemanticNode contains any of the provided Strings ignoring case.
-     *
-     * @param strings A List of Strings which the TextBlock might contain
-     * @return true, if this node's TextBlock contains any of the strings
-     */
-    default boolean containsAnyStringIgnoreCase(String... strings) {
-
-        return Arrays.stream(strings).anyMatch(this::containsStringIgnoreCase);
-    }
-
-
-    /**
-     * Checks whether this SemanticNode contains any of the provided Strings ignoring case.
-     *
-     * @param strings A List of Strings which the TextBlock might contain
-     * @return true, if this node's TextBlock contains any of the strings
-     */
-    default boolean containsAllStringsIgnoreCase(String... strings) {
-
-        return Arrays.stream(strings).allMatch(this::containsStringIgnoreCase);
-    }
-
-
-    /**
-     * Checks whether this SemanticNode matches the provided regex pattern.
-     *
-     * @param regexPattern A String representing a regex pattern, which the TextBlock might contain
-     * @return true, if this node's TextBlock contains the regex pattern
-     */
-    default boolean matchesRegex(String regexPattern) {
-
-        return RedactionSearchUtility.anyMatch(getTextBlock(), regexPattern);
-    }
-
-
-    /**
-     * Checks whether this SemanticNode matches the provided regex pattern ignoring case.
-     *
-     * @param regexPattern A String representing a regex pattern, which the TextBlock might contain
-     * @return true, if this node's TextBlock contains the regex pattern ignoring case
-     */
-    default boolean matchesRegexIgnoreCase(String regexPattern) {
-
-        return RedactionSearchUtility.anyMatchIgnoreCase(getTextBlock(), regexPattern);
-    }
-
-
-    /**
-     * Checks whether this SemanticNode intersects the provided rectangle.
-     * @param x the lower left corner X value
-     * @param y the lower left corner Y value
-     * @param w width
-     * @param h height
-     * @param pageNumber the pagenumber of the rectangle
-     * @return true if intersects, false otherwise
-     */
-    default boolean intersectsRectangle(int x, int y, int w, int h, int pageNumber) {
-
-        return getBBox().entrySet().stream().filter(entry -> entry.getKey().getNumber() == pageNumber).map(Map.Entry::getValue).anyMatch(rect -> rect.intersects(x, y, w, h));
-    }
-
-
-    /**
-     * This function is used during insertion of EntityNodes into the graph, it checks if the TextRange of the RedactionEntity intersects or even contains the RedactionEntity.
-     * It sets the fields accordingly and recursively calls this function on all its children.
-     *
-     * @param textEntity RedactionEntity, which is being inserted into the graph
-     */
-    default void addThisToEntityIfIntersects(TextEntity textEntity) {
-
-        TextBlock textBlock = getTextBlock();
-        if (textBlock.getTextRange().intersects(textEntity.getTextRange())) {
-            if (textBlock.containsTextRange(textEntity.getTextRange())) {
-                textEntity.setDeepestFullyContainingNode(this);
-            }
-
-            textEntity.addIntersectingNode(this);
-            streamChildren().filter(semanticNode -> semanticNode.getTextRange().intersects(textEntity.getTextRange()))
-                    .forEach(node -> node.addThisToEntityIfIntersects(textEntity));
-        }
-    }
-
-
-    /**
-     * Streams all children located directly underneath this node in the DocumentTree.
-     *
-     * @return Stream of all children
-     */
-    default Stream<SemanticNode> streamChildren() {
-
-        return getDocumentTree().childNodes(getTreeId());
-    }
-
-
-    /**
-     * Streams all children located directly underneath this node in the DocumentTree of the provided type.
-     *
-     * @return Stream of all children
-     */
-    default Stream<SemanticNode> streamChildrenOfType(NodeType nodeType) {
-
-        return getDocumentTree().childNodesOfType(getTreeId(), nodeType);
-    }
-
-
-    /**
-     * Recursively streams all SemanticNodes located underneath this node in the DocumentTree in order.
-     *
-     * @return Stream of all SubNodes
-     */
-    default Stream<SemanticNode> streamAllSubNodes() {
-
-        return getDocumentTree().allSubEntriesInOrder(getTreeId()).map(DocumentTree.Entry::getNode);
-    }
-
-
-    /**
-     * Recursively streams all SemanticNodes of the provided type located underneath this node in the DocumentTree in order.
-     *
-     * @return Stream of all SubNodes
-     */
-    default Stream<SemanticNode> streamAllSubNodesOfType(NodeType nodeType) {
-
-        return getDocumentTree().allSubEntriesInOrder(getTreeId()).filter(entry -> entry.getType().equals(nodeType)).map(DocumentTree.Entry::getNode);
-    }
-
-
-    /**
-     * The TextRange is the start and end string offsets in the reading order of the document.
-     *
-     * @return TextRange of this Node's TextBlock
-     */
-    default TextRange getTextRange() {
-
-        return getTextBlock().getTextRange();
-    }
-
-
-    /**
-     * Returns the length of the text content in this Node's TextBlock.
-     *
-     * @return The length of the text content
-     */
-    default int length() {
-
-        return getTextRange().length();
-    }
-
-
-    /**
-     * If this Node is a Leaf it will calculate the boundingBox of its LeafTextBlock, otherwise it will calculate the Union of the BoundingBoxes of all its Children.
-     * If called on the Document, it will return the cropbox of each page
-     *
-     * @return Rectangle2D fully encapsulating this Node for each page.
-     */
-    default Map<Page, Rectangle2D> getBBox() {
-
-        Map<Page, Rectangle2D> bBoxPerPage = new HashMap<>();
-        if (isLeaf()) {
-            return getBBoxFromLeafTextBlock(bBoxPerPage);
-        }
-
-        return getBBoxFromChildren(bBoxPerPage);
-    }
-
-
-    /**
-     * Checks whether the Bounding Box of this SemanticNode contains the provided rectangle on the provided page.
-     *
-     * @param rectangle2D The rectangle to check if it is contained
-     * @param pageNumber  The Page number on which the rectangle should be checked
-     * @return boolean
-     */
-    default boolean containsRectangle(Rectangle2D rectangle2D, Integer pageNumber) {
-
-        Page helperPage = Page.builder().number(pageNumber).build();
-        if (!getPages().contains(helperPage)) {
-            return false;
-        }
-        return getBBox().get(helperPage).contains(rectangle2D);
-    }
-
-
-    /**
-     * TODO: this produces unwanted results for sections spanning multiple columns.
-     *
-     * @param bBoxPerPage initial empty BoundingBox
-     * @return The union of the BoundingBoxes of all children
-     */
-    private Map<Page, Rectangle2D> getBBoxFromChildren(Map<Page, Rectangle2D> bBoxPerPage) {
-
-        return streamChildren().map(SemanticNode::getBBox).reduce((map1, map2) -> {
-            map1.forEach((page, rectangle) -> map2.merge(page, rectangle, (rect1, rect2) -> rect1.createUnion(rect2).getBounds2D()));
-            return map2;
-        }).orElse(bBoxPerPage);
-    }
-
-
-    /**
-     * @param bBoxPerPage initial empty BoundingBox
-     * @return The union of all BoundingBoxes of the TextBlock of this node
-     */
-    private Map<Page, Rectangle2D> getBBoxFromLeafTextBlock(Map<Page, Rectangle2D> bBoxPerPage) {
-
-        Map<Page, List<AtomicTextBlock>> atomicTextBlockPerPage = getTextBlock().getAtomicTextBlocks().stream().collect(Collectors.groupingBy(AtomicTextBlock::getPage));
-        atomicTextBlockPerPage.forEach((page, atbs) -> bBoxPerPage.put(page, RectangleTransformations.atomicTextBlockBBox(atbs)));
-        return bBoxPerPage;
-    }
-
-}

redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/document/graph/nodes/Table.java

@@ -1,332 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.graph.nodes;
-
-import static java.lang.String.format;
-
-import java.util.Collection;
-import java.util.HashSet;
-import java.util.List;
-import java.util.Locale;
-import java.util.Set;
-import java.util.stream.IntStream;
-import java.util.stream.Stream;
-
-import com.iqser.red.service.redaction.v1.server.document.graph.DocumentTree;
-import com.iqser.red.service.redaction.v1.server.document.graph.entity.TextEntity;
-import com.iqser.red.service.redaction.v1.server.document.graph.textblock.TextBlock;
-import com.iqser.red.service.redaction.v1.server.document.graph.textblock.TextBlockCollector;
-
-import lombok.AccessLevel;
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.Data;
-import lombok.EqualsAndHashCode;
-import lombok.experimental.FieldDefaults;
-
-@Data
-@Builder
-@AllArgsConstructor
-@FieldDefaults(level = AccessLevel.PRIVATE)
-public class Table implements SemanticNode {
-
-    List<Integer> treeId;
-    DocumentTree documentTree;
-
-    int numberOfRows;
-    int numberOfCols;
-
-    TextBlock textBlock;
-
-    @Builder.Default
-    @EqualsAndHashCode.Exclude
-    Set<TextEntity> entities = new HashSet<>();
-
-
-    /**
-     * Streams all entities in this table, that appear in a row, which contains any of the provided strings.
-     *
-     * @param strings Strings to check whether a row contains them
-     * @return Stream of all entities in this table, that appear in a row, which contains any of the provided strings
-     */
-    public Stream<TextEntity> streamEntitiesWhereRowContainsStringsIgnoreCase(List<String> strings) {
-
-        return IntStream.range(0, numberOfRows)
-                .boxed()
-                .filter(row -> rowContainsStringsIgnoreCase(row, strings))
-                .flatMap(this::streamRow)
-                .map(TableCell::getEntities)
-                .flatMap(Collection::stream);
-    }
-
-
-    /**
-     * Checks whether the specified row contains all the provided strings.
-     *
-     * @param row     the row to check as an Integer, must be smaller than numberOfRows
-     * @param strings a list of strings to check for
-     * @return true, if all strings appear in the provided row
-     */
-    public boolean rowContainsStringsIgnoreCase(Integer row, List<String> strings) {
-
-        String rowText = streamRow(row).map(TableCell::getTextBlock).collect(new TextBlockCollector()).getSearchText().toLowerCase(Locale.ROOT);
-        return strings.stream().map(String::toLowerCase).allMatch(rowText::contains);
-    }
-
-
-    /**
-     * Streams all entities which appear in a row where at least one cell has the provided header and the provided value.
-     *
-     * @param header the header value to search for
-     * @param value  the string which the table cell should contain
-     * @return a stream of all entities, which appear in a row where at least one cell has the provided header and the provided value.
-     */
-    public Stream<TextEntity> streamEntitiesWhereRowHasHeaderAndValue(String header, String value) {
-
-        List<Integer> vertebrateStudyCols = streamHeaders().filter(headerNode -> headerNode.containsString(header)).map(TableCell::getCol).toList();
-        return streamTableCells().filter(tableCellNode -> vertebrateStudyCols.stream()
-                .anyMatch(vertebrateStudyCol -> getCell(tableCellNode.getRow(), vertebrateStudyCol).containsString(value))).map(TableCell::getEntities).flatMap(Collection::stream);
-    }
-
-
-    /**
-     * Streams all entities which appear in a row where at least one cell has the provided header and any provided value.
-     *
-     * @param header the header value to search for
-     * @param values the strings which the table cell should contain
-     * @return a stream of all entities, which appear in a row where at least one cell has the provided header and any provided value.
-     */
-    public Stream<TextEntity> streamEntitiesWhereRowHasHeaderAndAnyValue(String header, List<String> values) {
-
-        List<Integer> colsWithHeader = streamHeaders().filter(headerNode -> headerNode.containsString(header)).map(TableCell::getCol).toList();
-        return streamTableCells().filter(tableCellNode -> colsWithHeader.stream()
-                .anyMatch(colWithHeader -> getCell(tableCellNode.getRow(), colWithHeader).containsAnyString(values))).map(TableCell::getEntities).flatMap(Collection::stream);
-    }
-
-
-    /**
-     * Streams all entities in this table, that appear in a row, which contains at least one entity with any of the provided types.
-     * Ignores Entity with ignored == true or removed == true.
-     *
-     * @param types type strings to check whether a row contains an entity like them
-     * @return Stream of all entities in this table, that appear in a row, which contains at least one entity with any of the provided types.
-     */
-    public Stream<TextEntity> streamEntitiesWhereRowContainsEntitiesOfType(List<String> types) {
-
-        List<Integer> rowsWithEntityOfType = getEntities().stream()
-                .filter(TextEntity::active)
-                .filter(redactionEntity -> types.stream().anyMatch(type -> type.equals(redactionEntity.getType())))
-                .map(TextEntity::getIntersectingNodes)
-                .filter(node -> node instanceof TableCell)
-                .map(node -> (TableCell) node)
-                .map(TableCell::getRow)
-                .toList();
-
-        return rowsWithEntityOfType.stream().flatMap(this::streamRow).map(TableCell::getEntities).flatMap(Collection::stream);
-    }
-
-
-    /**
-     * Streams all entities in this table, that appear in a row, which contains no entity of any of the provided types.
-     * Ignores Entity with ignored == true or removed == true.
-     *
-     * @param types type strings to check whether a row contains an entity like them
-     * @return Stream of all entities in this table, that appear in a row, which contains at least one entity with any of the provided types.
-     */
-    public Stream<TextEntity> streamEntitiesWhereRowContainsNoEntitiesOfType(List<String> types) {
-
-        return IntStream.range(0, numberOfRows)
-                .boxed()
-                .filter(rowNumber -> streamRow(rowNumber).map(TableCell::getEntities)
-                        .flatMap(Collection::stream)
-                        .filter(TextEntity::active)
-                        .noneMatch(entity -> types.contains(entity.getType())))
-                .flatMap(this::streamRow)
-                .map(TableCell::getEntities)
-                .flatMap(Collection::stream);
-    }
-
-
-    /**
-     * Returns a TableCell at the provided row and column location.
-     *
-     * @param row int representing the row, must be smaller than numberOfRows
-     * @param col int representing the col, must be smaller than numberOfCols
-     * @return TableCell at the provided location in the table
-     */
-    public TableCell getCell(int row, int col) {
-
-        if (numberOfRows - row < 0 || numberOfCols - col < 0) {
-            throw new IllegalArgumentException(format("row %d, col %d is out of bounds for number of rows of %d and number of cols %d", row, col, numberOfRows, numberOfCols));
-        }
-        int idx = row * numberOfCols + col;
-        return (TableCell) documentTree.getEntryById(treeId).getChildren().get(idx).getNode();
-    }
-
-
-    /**
-     * Streams all TableCells in this Table row-wise.
-     *
-     * @return Stream of all TableCells
-     */
-    public Stream<TableCell> streamTableCells() {
-
-        return streamChildrenOfType(NodeType.TABLE_CELL).map(node -> (TableCell) node);
-    }
-
-
-    /**
-     * Streams all TableCells in this Table which have the provided header row-wise.
-     *
-     * @return Stream of all TableCells which have the provided header
-     */
-    public Stream<TableCell> streamTableCellsWithHeader(String header) {
-
-        return streamHeaders().filter(tableCellNode -> tableCellNode.getTextBlock().getSearchText().contains(header))
-                .map(TableCell::getCol)
-                .flatMap(this::streamCol)
-                .filter(tableCellNode -> !tableCellNode.isHeader());
-    }
-
-
-    /**
-     * Streams all TableCells belonging to the provided column from top down.
-     *
-     * @param col int representing the column
-     * @return Stream of all TableCell in the provided column
-     */
-    public Stream<TableCell> streamCol(int col) {
-
-        return IntStream.range(0, numberOfRows).boxed().map(row -> getCell(row, col));
-    }
-
-
-    /**
-     * Streams all TableCells belonging to the provided row from left to right.
-     *
-     * @param row int representing the row
-     * @return Stream of all TableCell in the provided row
-     */
-    public Stream<TableCell> streamRow(int row) {
-
-        return IntStream.range(0, numberOfCols).boxed().map(col -> getCell(row, col));
-    }
-
-
-    /**
-     * Streams all TableCells row-wise and filters them with header == true.
-     *
-     * @return Stream of all TableCells with header == true
-     */
-    public Stream<TableCell> streamHeaders() {
-
-        return streamTableCells().filter(TableCell::isHeader);
-    }
-
-
-    /**
-     * Streams all TableCells of the provided row and column and filters them with header == true.
-     *
-     * @param row int representing the row
-     * @param col int representing the column
-     * @return Stream of all TableCells with header == true in the provided row or col
-     */
-    public Stream<TableCell> streamHeadersForCell(int row, int col) {
-
-        return Stream.concat(streamRow(row), streamCol(col)).filter(TableCell::isHeader);
-    }
-
-
-    /**
-     * Streams all Headers and checks if any equal the provided string.
-     *
-     * @param header string to check the headers for
-     * @return true, if at least one header equals the provided string
-     */
-    public boolean hasHeader(String header) {
-
-        return streamHeaders().anyMatch(tableCellNode -> tableCellNode.getTextBlock().getSearchText().strip().equals(header));
-    }
-
-
-    /**
-     * Streams all Headers and checks if any equal the provided string.
-     *
-     * @param header string to check the headers for
-     * @return true, if at least one header equals the provided string
-     */
-    public boolean hasHeaderIgnoreCase(String header) {
-
-        return streamHeaders().anyMatch(tableCellNode -> tableCellNode.getTextBlock().getSearchText().strip().toLowerCase(Locale.ENGLISH).equals(header.toLowerCase(Locale.ENGLISH)));
-    }
-
-
-    /**
-     * Checks if this table has a column with the provided header and any of the table cells in that column contain the provided value.
-     *
-     * @param header string to find header cells
-     * @param value  string to check cells with provided header
-     * @return true, if this table has a column with the provided header and any of the table cells in that column contain the provided value
-     */
-    public boolean hasRowWithHeaderAndValue(String header, String value) {
-
-        return streamTableCellsWithHeader(header).anyMatch(tableCellNode -> tableCellNode.containsString(value));
-    }
-
-
-    /**
-     * Checks if this table has a column with the provided header and any of the table cells in that column contains any of the provided values.
-     *
-     * @param header string to find header cells
-     * @param values List of strings to check cells with provided header
-     * @return true, if this table has a column with the provided header and any of the table cells in that column contains any of the provided values.
-     */
-    public boolean hasRowWithHeaderAndAnyValue(String header, List<String> values) {
-
-        return streamTableCellsWithHeader(header).anyMatch(tableCellNode -> tableCellNode.containsAnyString(values));
-    }
-
-
-    /**
-     * Finds all entities of the provided type, which appear in the same row that the provided entity appears in.
-     * Ignores Entity with ignored == true or removed == true.
-     *
-     * @param type            the type of entities to search for
-     * @param textEntity the entity, which appears in the row to search
-     * @return List of all entities of the provided type, which appear in the same row that the provided entity appears in.
-     */
-    public List<TextEntity> getEntitiesOfTypeInSameRow(String type, TextEntity textEntity) {
-
-        return textEntity.getIntersectingNodes()
-                .stream()
-                .filter(node -> node instanceof TableCell)
-                .map(node -> (TableCell) node)
-                .flatMap(tableCellNode -> streamRow(tableCellNode.getRow()))
-                .map(cell -> cell.getEntitiesOfType(type))
-                .flatMap(Collection::stream)
-                .toList();
-    }
-
-
-    @Override
-    public NodeType getType() {
-
-        return NodeType.TABLE;
-    }
-
-
-    @Override
-    public TextBlock getTextBlock() {
-
-        if (textBlock == null) {
-            textBlock = streamAllSubNodes().filter(SemanticNode::isLeaf).map(SemanticNode::getLeafTextBlock).collect(new TextBlockCollector());
-        }
-        return textBlock;
-    }
-
-
-    @Override
-    public String toString() {
-
-        return treeId.toString() + ": " + NodeType.TABLE + ": #cols: " + numberOfCols + ", #rows: " + numberOfRows + ", " + this.getTextBlock().buildSummary();
-    }
-
-}

redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/document/graph/nodes/TableCell.java

@@ -1,90 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.graph.nodes;
-
-import java.awt.geom.Rectangle2D;
-import java.util.HashMap;
-import java.util.HashSet;
-import java.util.List;
-import java.util.Map;
-import java.util.Set;
-
-import com.iqser.red.service.redaction.v1.server.document.graph.entity.TextEntity;
-import com.iqser.red.service.redaction.v1.server.document.graph.DocumentTree;
-import com.iqser.red.service.redaction.v1.server.document.graph.textblock.TextBlock;
-import com.iqser.red.service.redaction.v1.server.document.graph.textblock.TextBlockCollector;
-
-import lombok.AccessLevel;
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.Data;
-import lombok.EqualsAndHashCode;
-import lombok.experimental.FieldDefaults;
-
-@Data
-@Builder
-@AllArgsConstructor
-@FieldDefaults(level = AccessLevel.PRIVATE)
-public class TableCell implements GenericSemanticNode {
-
-    List<Integer> treeId;
-    int row;
-    int col;
-    boolean header;
-
-    Rectangle2D bBox;
-
-    TextBlock leafTextBlock;
-
-    TextBlock textBlock;
-
-    @EqualsAndHashCode.Exclude
-    DocumentTree documentTree;
-
-    @Builder.Default
-    @EqualsAndHashCode.Exclude
-    Set<TextEntity> entities = new HashSet<>();
-
-
-    @Override
-    public Map<Page, Rectangle2D> getBBox() {
-
-        Map<Page, Rectangle2D> bBoxPerPage = new HashMap<>();
-        getPages().forEach(page -> bBoxPerPage.put(page, bBox));
-        return bBoxPerPage;
-    }
-
-
-    @Override
-    public NodeType getType() {
-
-        return NodeType.TABLE_CELL;
-    }
-
-
-    @Override
-    public boolean isLeaf() {
-
-        return getDocumentTree().getEntryById(getTreeId()).getChildren().isEmpty();
-    }
-
-
-    @Override
-    public TextBlock getTextBlock() {
-
-        if (isLeaf()) {
-            return leafTextBlock;
-        }
-
-        if (textBlock == null) {
-            textBlock = streamAllSubNodes().filter(SemanticNode::isLeaf).map(SemanticNode::getLeafTextBlock).collect(new TextBlockCollector());
-        }
-        return textBlock;
-    }
-
-
-    @Override
-    public String toString() {
-
-        return treeId + ": " + NodeType.TABLE_CELL + ": " + this.getTextBlock().buildSummary();
-    }
-
-}

redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/document/graph/textblock/AtomicTextBlock.java

@@ -1,230 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.graph.textblock;
-
-import static java.lang.String.format;
-
-import java.awt.geom.Rectangle2D;
-import java.util.Arrays;
-import java.util.Collection;
-import java.util.Collections;
-import java.util.HashMap;
-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.document.graph.TextRange;
-import com.iqser.red.service.redaction.v1.server.document.graph.nodes.Page;
-import com.iqser.red.service.redaction.v1.server.document.graph.nodes.SemanticNode;
-import com.iqser.red.service.redaction.v1.server.document.utils.RectangleTransformations;
-import com.knecon.fforesight.service.layoutparser.internal.api.data.redaction.DocumentPositionData;
-import com.knecon.fforesight.service.layoutparser.internal.api.data.redaction.DocumentTextData;
-
-import lombok.AccessLevel;
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.Data;
-import lombok.EqualsAndHashCode;
-import lombok.Getter;
-import lombok.experimental.FieldDefaults;
-
-@Data
-@Builder
-@AllArgsConstructor
-@FieldDefaults(level = AccessLevel.PRIVATE)
-public class AtomicTextBlock implements TextBlock {
-
-    Long id;
-    Integer numberOnPage;
-    Page page;
-
-    //string coordinates
-    TextRange textRange;
-    String searchText;
-    List<Integer> lineBreaks;
-
-    //position coordinates
-    List<Integer> stringIdxToPositionIdx;
-    @Getter
-    List<Rectangle2D> positions;
-
-    @EqualsAndHashCode.Exclude
-    SemanticNode parent;
-
-
-    @Override
-    public int numberOfLines() {
-
-        return lineBreaks.size() + 1;
-    }
-
-    public static AtomicTextBlock empty(Long textBlockIdx, int stringOffset, Page page, int numberOnPage, SemanticNode parent) {
-
-        return AtomicTextBlock.builder()
-                .id(textBlockIdx)
-                .textRange(new TextRange(stringOffset, stringOffset))
-                .searchText("")
-                .lineBreaks(Collections.emptyList())
-                .page(page)
-                .numberOnPage(numberOnPage)
-                .stringIdxToPositionIdx(Collections.emptyList())
-                .positions(Collections.emptyList())
-                .parent(parent)
-                .build();
-    }
-
-
-    public static AtomicTextBlock fromAtomicTextBlockData(DocumentTextData atomicTextBlockData,
-                                                          DocumentPositionData atomicPositionBlockData,
-                                                          SemanticNode parent,
-                                                          Page page) {
-
-        return AtomicTextBlock.builder()
-                .id(atomicTextBlockData.getId())
-                .numberOnPage(atomicTextBlockData.getNumberOnPage())
-                .page(page)
-                .textRange(new TextRange(atomicTextBlockData.getStart(), atomicTextBlockData.getEnd()))
-                .searchText(atomicTextBlockData.getSearchText())
-                .lineBreaks(Arrays.stream(atomicTextBlockData.getLineBreaks()).boxed().toList())
-                .stringIdxToPositionIdx(Arrays.stream(atomicPositionBlockData.getStringIdxToPositionIdx()).boxed().toList())
-                .positions(toRectangle2DList(atomicPositionBlockData.getPositions()))
-                .parent(parent)
-                .build();
-    }
-
-
-    private static List<Rectangle2D> toRectangle2DList(float[][] positions) {
-
-        return Arrays.stream(positions).map(floatArr -> (Rectangle2D) new Rectangle2D.Float(floatArr[0], floatArr[1], floatArr[2], floatArr[3])).toList();
-    }
-
-
-    public TextRange getLineTextRange(int lineNumber) {
-
-        if (lineNumber >= numberOfLines() || lineNumber < 0) {
-            return new TextRange(textRange.start(), textRange.start());
-        }
-        if (numberOfLines() == 1) {
-            return textRange;
-        }
-        if (lineNumber == 0) {
-            return new TextRange(textRange.start(), lineBreaks.get(0) + textRange.start());
-        } else if (lineNumber == numberOfLines() - 1) {
-            return new TextRange(lineBreaks.get(lineBreaks.size() - 1) + textRange.start(), textRange.end());
-        }
-        return new TextRange(lineBreaks.get(lineNumber - 1) + textRange.start(), lineBreaks.get(lineNumber) + textRange.start());
-    }
-
-
-    @Override
-    public List<AtomicTextBlock> getAtomicTextBlocks() {
-
-        return List.of(this);
-    }
-
-
-    @Override
-    public int getNextLinebreak(int fromIndex) {
-
-        return lineBreaks.stream()//
-                .filter(linebreak -> linebreak > fromIndex - textRange.start()) //
-                .findFirst() //
-                .orElse(searchText.length()) + textRange.start();
-    }
-
-
-    @Override
-    public int getPreviousLinebreak(int fromIndex) {
-
-        return lineBreaks.stream()//
-                .filter(linebreak -> linebreak <= fromIndex - textRange.start())//
-                .reduce((a, b) -> b)//
-                .orElse(0) + textRange.start();
-    }
-
-
-    @Override
-    public Rectangle2D getPosition(int stringIdx) {
-
-        return positions.get(stringIdxToPositionIdx.get(stringIdx - textRange.start()));
-    }
-
-
-    @Override
-    public List<Rectangle2D> getPositions(TextRange stringTextRange) {
-
-        if (!containsTextRange(stringTextRange)) {
-            throw new IndexOutOfBoundsException(format("%s is out of bounds for %s", stringTextRange, this.textRange));
-        }
-        if (stringTextRange.length() == 0) {
-            return Collections.emptyList();
-        }
-
-        int startPositionIdx = stringIdxToPositionIdx.get(stringTextRange.start() - this.textRange.start());
-
-        if (stringTextRange.end() == this.textRange.end()) {
-            return positions.subList(startPositionIdx, positions.size());
-        }
-
-        return positions.subList(startPositionIdx, stringIdxToPositionIdx.get(stringTextRange.end() - this.textRange.start()));
-
-    }
-
-
-    public Map<Page, List<Rectangle2D>> getPositionsPerPage(TextRange stringTextRange) {
-
-        List<Rectangle2D> rectanglesPerLine = stringTextRange.split(getAllLineBreaksInBoundary(stringTextRange))
-                .stream()
-                .map(this::getPositions)
-                .map(RectangleTransformations::rectangleBBoxWithGaps)
-                .flatMap(Collection::stream)
-                .toList();
-        Map<Page, List<Rectangle2D>> rectanglePerLinePerPage = new HashMap<>();
-        rectanglePerLinePerPage.put(page, rectanglesPerLine);
-        return rectanglePerLinePerPage;
-    }
-
-
-    @Override
-    public String subSequenceWithLineBreaks(TextRange textRange) {
-
-        if (textRange.length() == 0 || !getTextRange().contains(textRange)) {
-            return "";
-        }
-
-        Set<Integer> lbInBoundary = lineBreaks.stream().map(i -> i + textRange.start()).filter(textRange::contains).collect(Collectors.toSet());
-        if (textRange.end() == getTextRange().end()) {
-            lbInBoundary.add(getTextRange().end());
-        }
-        StringBuilder sb = new StringBuilder();
-        for (int i = textRange.start(); i < textRange.end(); i++) {
-            char character = this.charAt(i);
-            if (lbInBoundary.contains(i + 1)) {
-                // always plus one, due to the linebreaks being an exclusive end index
-                if (!Character.isWhitespace(character)) {
-                    lbInBoundary.remove(i + 1);
-                    lbInBoundary.add(i + 2);
-                    sb.append(character);
-                    continue;
-                }
-                sb.append("\n");
-            } else {
-                sb.append(character);
-            }
-        }
-        return sb.toString();
-    }
-
-
-    private List<Integer> getAllLineBreaksInBoundary(TextRange textRange) {
-
-        return getLineBreaks().stream().map(linebreak -> linebreak + this.textRange.start()).filter(textRange::contains).toList();
-    }
-
-
-    @Override
-    public String toString() {
-
-        return searchText;
-    }
-
-}

redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/document/graph/textblock/ConcatenatedTextBlock.java

@@ -1,236 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.graph.textblock;
-
-import static java.lang.String.format;
-
-import java.awt.geom.Rectangle2D;
-import java.util.Collections;
-import java.util.HashMap;
-import java.util.LinkedList;
-import java.util.List;
-import java.util.Map;
-import java.util.stream.Stream;
-
-import com.iqser.red.service.redaction.v1.server.document.graph.TextRange;
-import com.iqser.red.service.redaction.v1.server.document.graph.nodes.Page;
-
-import lombok.AccessLevel;
-import lombok.Data;
-import lombok.experimental.FieldDefaults;
-
-@Data
-@FieldDefaults(level = AccessLevel.PRIVATE)
-public class ConcatenatedTextBlock implements TextBlock {
-
-    List<AtomicTextBlock> atomicTextBlocks;
-    String searchText;
-    TextRange textRange;
-
-
-    public static ConcatenatedTextBlock empty() {
-
-        return new ConcatenatedTextBlock(Collections.emptyList());
-    }
-
-
-    public ConcatenatedTextBlock(List<AtomicTextBlock> atomicTextBlocks) {
-
-        this.atomicTextBlocks = new LinkedList<>();
-        if (atomicTextBlocks.isEmpty()) {
-            textRange = new TextRange(-1, -1);
-            return;
-        }
-        var firstTextBlock = atomicTextBlocks.get(0);
-        this.atomicTextBlocks.add(firstTextBlock);
-        textRange = new TextRange(firstTextBlock.getTextRange().start(), firstTextBlock.getTextRange().end());
-
-        atomicTextBlocks.subList(1, atomicTextBlocks.size()).forEach(this::concat);
-    }
-
-
-    public ConcatenatedTextBlock concat(TextBlock textBlock) {
-
-        if (this.atomicTextBlocks.isEmpty()) {
-            textRange.setStart(textBlock.getTextRange().start());
-            textRange.setEnd(textBlock.getTextRange().end());
-        } else if (textRange.end() != textBlock.getTextRange().start()) {
-            throw new UnsupportedOperationException(format("Can only concat consecutive TextBlocks, trying to concat %s and %s", textRange, textBlock.getTextRange()));
-        }
-        this.atomicTextBlocks.addAll(textBlock.getAtomicTextBlocks());
-        textRange.setEnd(textBlock.getTextRange().end());
-        this.searchText = null;
-        return this;
-    }
-
-
-    private AtomicTextBlock getAtomicTextBlockByStringIndex(int stringIdx) {
-
-        return atomicTextBlocks.stream().filter(textBlock -> textBlock.getTextRange().contains(stringIdx)).findAny().orElseThrow(IndexOutOfBoundsException::new);
-    }
-
-
-    private List<AtomicTextBlock> getAllAtomicTextBlocksPartiallyInStringBoundary(TextRange textRange) {
-
-        return atomicTextBlocks.stream().filter(tb -> tb.getTextRange().intersects(textRange)).toList();
-    }
-
-
-    @Override
-    public String getSearchText() {
-
-        if (searchText == null) {
-            StringBuilder sb = new StringBuilder();
-            getAtomicTextBlocks().forEach(atb -> sb.append(atb.getSearchText()));
-            searchText = sb.toString();
-        }
-        return searchText;
-    }
-
-
-    @Override
-    public int numberOfLines() {
-
-        return atomicTextBlocks.stream().mapToInt(AtomicTextBlock::numberOfLines).sum();
-    }
-
-
-    @Override
-    public int getNextLinebreak(int fromIndex) {
-
-        return getAtomicTextBlockByStringIndex(fromIndex).getNextLinebreak(fromIndex);
-    }
-
-
-    @Override
-    public int getPreviousLinebreak(int fromIndex) {
-
-        return getAtomicTextBlockByStringIndex(fromIndex).getPreviousLinebreak(fromIndex);
-    }
-
-
-    @Override
-    public List<Integer> getLineBreaks() {
-
-        return getAtomicTextBlocks().stream().flatMap(atomicTextBlock -> atomicTextBlock.getLineBreaks().stream()).toList();
-    }
-
-
-
-    @Override
-    public Rectangle2D getPosition(int stringIdx) {
-
-        return getAtomicTextBlockByStringIndex(stringIdx).getPosition(stringIdx);
-    }
-
-    public TextRange getLineTextRange(int lineNumber) {
-
-        if (atomicTextBlocks.size() == 1) {
-            return atomicTextBlocks.get(0).getLineTextRange(lineNumber);
-        }
-        int lineNumberInCurrentBlock = lineNumber;
-        for (AtomicTextBlock atomicTextBlock : atomicTextBlocks) {
-            if (lineNumberInCurrentBlock < atomicTextBlock.numberOfLines()) {
-                return atomicTextBlock.getLineTextRange(lineNumberInCurrentBlock);
-            }
-            lineNumberInCurrentBlock -= atomicTextBlock.numberOfLines();
-        }
-        return new TextRange(textRange.start(), textRange.start());
-    }
-
-    @Override
-    public List<Rectangle2D> getPositions(TextRange stringTextRange) {
-
-
-        List<AtomicTextBlock> textBlocks = getAllAtomicTextBlocksPartiallyInStringBoundary(stringTextRange);
-
-        if (textBlocks.isEmpty()) {
-            return Collections.emptyList();
-        }
-        if (textBlocks.size() == 1) {
-            return textBlocks.get(0).getPositions(stringTextRange);
-        }
-
-        AtomicTextBlock firstTextBlock = textBlocks.get(0);
-        List<Rectangle2D> positions = new LinkedList<>(firstTextBlock.getPositions(new TextRange(stringTextRange.start(), firstTextBlock.getTextRange().end())));
-
-        for (AtomicTextBlock textBlock : textBlocks.subList(1, textBlocks.size() - 1)) {
-            positions.addAll(textBlock.getPositions());
-        }
-
-        var lastTextBlock = textBlocks.get(textBlocks.size() - 1);
-        positions.addAll(lastTextBlock.getPositions(new TextRange(lastTextBlock.getTextRange().start(), stringTextRange.end())));
-
-        return positions;
-    }
-
-
-    @Override
-    public Map<Page, List<Rectangle2D>> getPositionsPerPage(TextRange stringTextRange) {
-
-        List<AtomicTextBlock> textBlocks = getAllAtomicTextBlocksPartiallyInStringBoundary(stringTextRange);
-
-        if (textBlocks.isEmpty()) {
-            return new HashMap<>();
-        }
-
-        if (textBlocks.size() == 1) {
-            return textBlocks.get(0).getPositionsPerPage(stringTextRange);
-        }
-
-        AtomicTextBlock firstTextBlock = textBlocks.get(0);
-        Map<Page, List<Rectangle2D>> rectanglesPerLinePerPage = firstTextBlock.getPositionsPerPage(new TextRange(stringTextRange.start(), firstTextBlock.getTextRange().end()));
-
-        for (AtomicTextBlock textBlock : textBlocks.subList(1, textBlocks.size() - 1)) {
-            rectanglesPerLinePerPage = mergeEntityPositionsWithSamePageNode(rectanglesPerLinePerPage, textBlock.getPositionsPerPage(textBlock.getTextRange()));
-        }
-
-        AtomicTextBlock lastTextBlock = textBlocks.get(textBlocks.size() - 1);
-        rectanglesPerLinePerPage = mergeEntityPositionsWithSamePageNode(rectanglesPerLinePerPage,
-                lastTextBlock.getPositionsPerPage(new TextRange(lastTextBlock.getTextRange().start(), stringTextRange.end())));
-
-        return rectanglesPerLinePerPage;
-    }
-
-
-    @Override
-    public String subSequenceWithLineBreaks(TextRange textRange) {
-
-        if (textRange.length() == 0 || !getTextRange().contains(textRange)) {
-            return "";
-        }
-
-        List<AtomicTextBlock> textBlocks = getAllAtomicTextBlocksPartiallyInStringBoundary(textRange);
-
-        if (textBlocks.size() == 1) {
-            return textBlocks.get(0).subSequenceWithLineBreaks(textRange);
-        }
-
-        StringBuilder sb = new StringBuilder();
-        AtomicTextBlock firstTextBlock = textBlocks.get(0);
-        sb.append(firstTextBlock.subSequenceWithLineBreaks(new TextRange(textRange.start(), firstTextBlock.getTextRange().end())));
-
-        for (AtomicTextBlock textBlock : textBlocks.subList(1, textBlocks.size() - 1)) {
-            sb.append(textBlock.searchTextWithLineBreaks());
-        }
-
-        var lastTextBlock = textBlocks.get(textBlocks.size() - 1);
-        sb.append(lastTextBlock.subSequenceWithLineBreaks(new TextRange(lastTextBlock.getTextRange().start(), textRange.end())));
-
-        return sb.toString();
-    }
-
-
-    private Map<Page, List<Rectangle2D>> mergeEntityPositionsWithSamePageNode(Map<Page, List<Rectangle2D>> map1, Map<Page, List<Rectangle2D>> map2) {
-
-        Map<Page, List<Rectangle2D>> mergedMap = new HashMap<>(map1);
-        map2.forEach((pageNode, rectangles) -> mergedMap.merge(pageNode, rectangles, (l1, l2) -> Stream.concat(l1.stream(), l2.stream()).toList()));
-        return mergedMap;
-    }
-
-
-    @Override
-    public String toString() {
-
-        return getSearchText();
-    }
-
-}

redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/document/graph/textblock/TextBlock.java

@@ -1,167 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.graph.textblock;
-
-import static java.lang.String.format;
-
-import java.awt.geom.Rectangle2D;
-import java.util.ArrayList;
-import java.util.Arrays;
-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.document.graph.TextRange;
-import com.iqser.red.service.redaction.v1.server.document.graph.nodes.Page;
-import com.iqser.red.service.redaction.v1.server.document.utils.RectangleTransformations;
-
-public interface TextBlock extends CharSequence {
-
-    String getSearchText();
-
-
-    List<AtomicTextBlock> getAtomicTextBlocks();
-
-
-    TextRange getTextRange();
-
-
-    int getNextLinebreak(int fromIndex);
-
-
-    int getPreviousLinebreak(int fromIndex);
-
-
-    TextRange getLineTextRange(int lineNumber);
-
-
-
-    List<Integer> getLineBreaks();
-
-
-    Rectangle2D getPosition(int stringIdx);
-
-
-    List<Rectangle2D> getPositions(TextRange stringTextRange);
-
-
-    Map<Page, List<Rectangle2D>> getPositionsPerPage(TextRange stringTextRange);
-
-
-    String subSequenceWithLineBreaks(TextRange textRange);
-
-
-    int numberOfLines();
-
-
-    default CharSequence getLine(int lineNumber) {
-
-        return subSequence(getLineTextRange(lineNumber));
-    }
-
-
-    default List<Rectangle2D> getLinePositions(int lineNumber) {
-
-        return getPositions(getLineTextRange(lineNumber));
-    }
-
-
-    default Rectangle2D getLineBBox(int lineNumber) {
-
-        return RectangleTransformations.rectangle2DBBox(getLinePositions(lineNumber));
-    }
-
-    default String searchTextWithLineBreaks() {
-
-        return subSequenceWithLineBreaks(getTextRange());
-    }
-
-
-    default int indexOf(String searchTerm) {
-
-        return indexOf(searchTerm, getTextRange().start());
-    }
-
-
-    default Set<Page> getPages() {
-
-        return getAtomicTextBlocks().stream().map(AtomicTextBlock::getPage).collect(Collectors.toUnmodifiableSet());
-    }
-
-
-    default Set<Page> getPages(TextRange textRange) {
-
-        return getAtomicTextBlocks().stream()
-                .filter(atomicTextBlock -> atomicTextBlock.getTextRange().intersects(textRange))
-                .map(AtomicTextBlock::getPage)
-                .collect(Collectors.toUnmodifiableSet());
-    }
-
-
-    default int indexOf(String searchTerm, int startOffset) {
-
-        int start = getSearchText().indexOf(searchTerm, startOffset - getTextRange().start());
-        if (start == -1) {
-            return -1;
-        }
-        return start + getTextRange().start();
-    }
-
-
-    default CharSequence getFirstLine() {
-
-        return subSequence(getTextRange().start(), getNextLinebreak(getTextRange().start()));
-    }
-
-
-    default boolean containsTextRange(TextRange textRange) {
-
-        if (textRange.end() < textRange.start()) {
-            throw new IllegalArgumentException(format("Invalid %s, StartIndex must be smaller than EndIndex", textRange));
-        }
-        return getTextRange().contains(textRange);
-    }
-
-
-    default boolean containsIndex(int stringIndex) {
-
-        return getTextRange().contains(stringIndex);
-    }
-
-
-    default CharSequence subSequence(TextRange textRange) {
-
-        return subSequence(textRange.start(), textRange.end());
-    }
-
-
-    default String buildSummary() {
-
-        String[] words = getSearchText().split(" ");
-        int bound = Math.min(words.length, 4);
-        List<String> list = new ArrayList<>(Arrays.asList(words).subList(0, bound));
-
-        return String.join(" ", list);
-    }
-
-
-    @Override
-    default CharSequence subSequence(int start, int end) {
-
-        return getSearchText().substring(start - getTextRange().start(), end - getTextRange().start());
-    }
-
-
-    @Override
-    default int length() {
-
-        return getTextRange().length();
-    }
-
-
-    @Override
-    default char charAt(int index) {
-
-        return getSearchText().charAt(index - getTextRange().start());
-    }
-
-}

redaction-service-v1/redaction-service-server-v1/src/main/java/com/iqser/red/service/redaction/v1/server/document/graph/textblock/TextBlockCollector.java

@@ -1,49 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.graph.textblock;
-
-import java.util.Set;
-import java.util.function.BiConsumer;
-import java.util.function.BinaryOperator;
-import java.util.function.Function;
-import java.util.function.Supplier;
-import java.util.stream.Collector;
-
-import lombok.NoArgsConstructor;
-
-@NoArgsConstructor
-public class TextBlockCollector implements Collector<TextBlock, ConcatenatedTextBlock, TextBlock> {
-
-    @Override
-    public Supplier<ConcatenatedTextBlock> supplier() {
-
-        return ConcatenatedTextBlock::empty;
-    }
-
-
-    @Override
-    public BiConsumer<ConcatenatedTextBlock, TextBlock> accumulator() {
-
-        return ConcatenatedTextBlock::concat;
-    }
-
-
-    @Override
-    public BinaryOperator<ConcatenatedTextBlock> combiner() {
-
-        return ConcatenatedTextBlock::concat;
-    }
-
-
-    @Override
-    public Function<ConcatenatedTextBlock, TextBlock> finisher() {
-
-        return a -> a;
-    }
-
-
-    @Override
-    public Set<Characteristics> characteristics() {
-
-        return Set.of(Characteristics.IDENTITY_FINISH, Characteristics.CONCURRENT);
-    }
-
-}

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

@@ -1,727 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.services;
-
-import static com.iqser.red.service.redaction.v1.server.redaction.utils.SeparatorUtils.boundaryIsSurroundedBySeparators;
-
-import java.util.Collection;
-import java.util.Collections;
-import java.util.Comparator;
-import java.util.LinkedList;
-import java.util.List;
-import java.util.NoSuchElementException;
-import java.util.Optional;
-import java.util.Set;
-import java.util.stream.Collectors;
-import java.util.stream.Stream;
-
-import org.apache.commons.lang3.tuple.Pair;
-import org.kie.api.runtime.KieSession;
-
-import com.google.common.base.Functions;
-import com.iqser.red.service.persistence.service.v1.api.shared.model.redactionlog.Engine;
-import com.iqser.red.service.redaction.v1.server.document.graph.TextRange;
-import com.iqser.red.service.redaction.v1.server.document.graph.ConsecutiveBoundaryCollector;
-import com.iqser.red.service.redaction.v1.server.document.graph.DocumentTree;
-import com.iqser.red.service.redaction.v1.server.document.graph.entity.EntityType;
-import com.iqser.red.service.redaction.v1.server.document.graph.entity.ManualChangeOverwrite;
-import com.iqser.red.service.redaction.v1.server.document.graph.entity.TextEntity;
-import com.iqser.red.service.redaction.v1.server.document.graph.entity.PositionOnPage;
-import com.iqser.red.service.redaction.v1.server.document.graph.nodes.NodeType;
-import com.iqser.red.service.redaction.v1.server.document.graph.nodes.Page;
-import com.iqser.red.service.redaction.v1.server.document.graph.nodes.SemanticNode;
-import com.iqser.red.service.redaction.v1.server.document.graph.nodes.Table;
-import com.iqser.red.service.redaction.v1.server.document.graph.nodes.TableCell;
-import com.iqser.red.service.redaction.v1.server.document.graph.textblock.TextBlock;
-import com.iqser.red.service.redaction.v1.server.document.utils.RectangleTransformations;
-import com.iqser.red.service.redaction.v1.server.document.utils.RedactionSearchUtility;
-import com.iqser.red.service.redaction.v1.server.redaction.adapter.NerEntities;
-import com.iqser.red.service.redaction.v1.server.redaction.adapter.NerEntitiesAdapter;
-import com.iqser.red.service.redaction.v1.server.redaction.model.dictionary.SearchImplementation;
-import com.iqser.red.service.redaction.v1.server.redaction.utils.IdBuilder;
-
-import lombok.RequiredArgsConstructor;
-import lombok.extern.slf4j.Slf4j;
-
-@Slf4j
-@RequiredArgsConstructor
-public class EntityCreationService {
-
-    private final EntityEnrichmentService entityEnrichmentService;
-    private final KieSession kieSession;
-
-
-    public EntityCreationService(EntityEnrichmentService entityEnrichmentService) {
-
-        this.entityEnrichmentService = entityEnrichmentService;
-        this.kieSession = null;
-    }
-
-
-    public Stream<TextEntity> betweenStrings(String start, String stop, String type, EntityType entityType, SemanticNode node) {
-
-        List<TextRange> startBoundaries = RedactionSearchUtility.findBoundariesByString(start, node.getTextBlock());
-        List<TextRange> stopBoundaries = RedactionSearchUtility.findBoundariesByString(stop, node.getTextBlock());
-
-        return betweenBoundaries(startBoundaries, stopBoundaries, type, entityType, node);
-    }
-
-
-    public Stream<TextEntity> betweenStringsIgnoreCase(String start, String stop, String type, EntityType entityType, SemanticNode node) {
-
-        List<TextRange> startBoundaries = RedactionSearchUtility.findBoundariesByStringIgnoreCase(start, node.getTextBlock());
-        List<TextRange> stopBoundaries = RedactionSearchUtility.findBoundariesByStringIgnoreCase(stop, node.getTextBlock());
-
-        return betweenBoundaries(startBoundaries, stopBoundaries, type, entityType, node);
-    }
-
-
-    public Stream<TextEntity> betweenStringsIncludeStart(String start, String stop, String type, EntityType entityType, SemanticNode node) {
-
-        List<TextRange> startBoundaries = RedactionSearchUtility.findBoundariesByString(start, node.getTextBlock());
-        List<TextRange> stopBoundaries = RedactionSearchUtility.findBoundariesByString(stop, node.getTextBlock());
-
-        startBoundaries.forEach(boundary -> {
-            boundary.setStart(boundary.start() - start.length());
-            boundary.setEnd(boundary.end() - start.length());
-        });
-
-        return betweenBoundaries(startBoundaries, stopBoundaries, type, entityType, node);
-    }
-
-
-    public Stream<TextEntity> betweenStringsIncludeStartIgnoreCase(String start, String stop, String type, EntityType entityType, SemanticNode node) {
-
-        List<TextRange> startBoundaries = RedactionSearchUtility.findBoundariesByStringIgnoreCase(start, node.getTextBlock());
-        List<TextRange> stopBoundaries = RedactionSearchUtility.findBoundariesByStringIgnoreCase(stop, node.getTextBlock());
-
-        startBoundaries.forEach(boundary -> {
-            boundary.setStart(boundary.start() - start.length());
-            boundary.setEnd(boundary.end() - start.length());
-        });
-
-        return betweenBoundaries(startBoundaries, stopBoundaries, type, entityType, node);
-    }
-
-
-    public Stream<TextEntity> betweenStringsIncludeEnd(String start, String stop, String type, EntityType entityType, SemanticNode node) {
-
-        List<TextRange> startBoundaries = RedactionSearchUtility.findBoundariesByString(start, node.getTextBlock());
-        List<TextRange> stopBoundaries = RedactionSearchUtility.findBoundariesByString(stop, node.getTextBlock());
-
-        stopBoundaries.forEach(boundary -> {
-            boundary.setStart(boundary.start() + stop.length());
-            boundary.setEnd(boundary.end() + stop.length());
-        });
-
-        return betweenBoundaries(startBoundaries, stopBoundaries, type, entityType, node);
-    }
-
-
-    public Stream<TextEntity> betweenStringsIncludeEndIgnoreCase(String start, String stop, String type, EntityType entityType, SemanticNode node) {
-
-        List<TextRange> startBoundaries = RedactionSearchUtility.findBoundariesByStringIgnoreCase(start, node.getTextBlock());
-        List<TextRange> stopBoundaries = RedactionSearchUtility.findBoundariesByStringIgnoreCase(stop, node.getTextBlock());
-
-        stopBoundaries.forEach(boundary -> {
-            boundary.setStart(boundary.start() + stop.length());
-            boundary.setEnd(boundary.end() + stop.length());
-        });
-
-        return betweenBoundaries(startBoundaries, stopBoundaries, type, entityType, node);
-    }
-
-
-    public Stream<TextEntity> betweenStringsIncludeStartAndEnd(String start, String stop, String type, EntityType entityType, SemanticNode node) {
-
-        List<TextRange> startBoundaries = RedactionSearchUtility.findBoundariesByString(start, node.getTextBlock());
-        List<TextRange> stopBoundaries = RedactionSearchUtility.findBoundariesByString(stop, node.getTextBlock());
-
-        startBoundaries.forEach(boundary -> {
-            boundary.setStart(boundary.start() - start.length());
-            boundary.setEnd(boundary.end() - start.length());
-        });
-        stopBoundaries.forEach(boundary -> {
-            boundary.setStart(boundary.start() + stop.length());
-            boundary.setEnd(boundary.end() + stop.length());
-        });
-
-        return betweenBoundaries(startBoundaries, stopBoundaries, type, entityType, node);
-    }
-
-
-    public Stream<TextEntity> betweenStringsIncludeStartAndEndIgnoreCase(String start, String stop, String type, EntityType entityType, SemanticNode node) {
-
-        List<TextRange> startBoundaries = RedactionSearchUtility.findBoundariesByStringIgnoreCase(start, node.getTextBlock());
-        List<TextRange> stopBoundaries = RedactionSearchUtility.findBoundariesByStringIgnoreCase(stop, node.getTextBlock());
-
-        startBoundaries.forEach(boundary -> {
-            boundary.setStart(boundary.start() - start.length());
-            boundary.setEnd(boundary.end() - start.length());
-        });
-        stopBoundaries.forEach(boundary -> {
-            boundary.setStart(boundary.start() + stop.length());
-            boundary.setEnd(boundary.end() + stop.length());
-        });
-
-        return betweenBoundaries(startBoundaries, stopBoundaries, type, entityType, node);
-    }
-
-
-    public Stream<TextEntity> betweenRegexes(String regexStart, String regexStop, String type, EntityType entityType, SemanticNode node) {
-
-        TextBlock textBlock = node.getTextBlock();
-        List<TextRange> startBoundaries = RedactionSearchUtility.findBoundariesByRegex(regexStart, textBlock);
-        List<TextRange> stopBoundaries = RedactionSearchUtility.findBoundariesByRegex(regexStop, textBlock);
-
-        return betweenBoundaries(startBoundaries, stopBoundaries, type, entityType, node);
-    }
-
-
-    public Stream<TextEntity> betweenRegexesIgnoreCase(String regexStart, String regexStop, String type, EntityType entityType, SemanticNode node) {
-
-        TextBlock textBlock = node.getTextBlock();
-        List<TextRange> startBoundaries = RedactionSearchUtility.findBoundariesByRegexIgnoreCase(regexStart, 0, textBlock);
-        List<TextRange> stopBoundaries = RedactionSearchUtility.findBoundariesByRegexIgnoreCase(regexStop, 0, textBlock);
-
-        return betweenBoundaries(startBoundaries, stopBoundaries, type, entityType, node);
-    }
-
-
-    public Stream<TextEntity> betweenBoundaries(List<TextRange> startBoundaries, List<TextRange> stopBoundaries, String type, EntityType entityType, SemanticNode node) {
-
-        if (startBoundaries.isEmpty() || stopBoundaries.isEmpty()) {
-            return Stream.empty();
-        }
-        List<TextRange> entityBoundaries = findNonOverlappingBoundariesBetweenBoundariesWithMinimalDistances(startBoundaries, stopBoundaries);
-        return entityBoundaries.stream()
-                .map(boundary -> boundary.trim(node.getTextBlock()))
-                .filter(boundary -> isValidEntityBoundary(node.getTextBlock(), boundary))
-                .map(boundary -> byTextRange(boundary, type, entityType, node))
-                .filter(Optional::isPresent)
-                .map(Optional::get);
-    }
-
-
-    private static List<TextRange> findNonOverlappingBoundariesBetweenBoundariesWithMinimalDistances(List<TextRange> startBoundaries, List<TextRange> stopBoundaries) {
-
-        List<TextRange> entityBoundaries = new LinkedList<>();
-        for (TextRange startTextRange : startBoundaries) {
-            Optional<TextRange> optionalStopBoundaryWithMinimalDistance = stopBoundaries.stream()
-                    .filter(stopBoundary -> stopBoundary.start() > startTextRange.end())
-                    .min(Comparator.comparingInt(TextRange::start));
-            if (optionalStopBoundaryWithMinimalDistance.isEmpty()) {
-                break;
-            }
-            entityBoundaries.add(new TextRange(startTextRange.end(), optionalStopBoundaryWithMinimalDistance.get().start()));
-        }
-        return removeOuterOverlappingBoundaries(entityBoundaries);
-    }
-
-
-    private static List<TextRange> removeOuterOverlappingBoundaries(List<TextRange> entityBoundaries) {
-        /*
-        In some cases we get boundaries, where one contains the other. This happens for Example when we have two start boundaries and one stop boundary after the two start boundaries.
-        Then we get two boundaries where one is entirely contained in the other. So we want to remove the outer boundary.
-        For Example consider the text: "a this is some text. a here is more text b". If "a" is the start string and "b" is the stop string, there are two possibilities.
-        "this is some text. a here is more text" and "here is more text". We only want to keep the latter.
-         */
-        return entityBoundaries.stream()
-                .filter(boundary -> entityBoundaries.stream().noneMatch(innerBoundary -> innerBoundary != boundary && innerBoundary.containedBy(boundary)))
-                .toList();
-
-    }
-
-
-    public Stream<TextEntity> bySearchImplementation(SearchImplementation searchImplementation, String type, EntityType entityType, SemanticNode node) {
-
-        return searchImplementation.getBoundaries(node.getTextBlock(), node.getTextRange())
-                .stream()
-                .filter(boundary -> isValidEntityBoundary(node.getTextBlock(), boundary))
-                .map(bounds -> byTextRange(bounds, type, entityType, node))
-                .filter(Optional::isPresent)
-                .map(Optional::get);
-    }
-
-
-    public Stream<TextEntity> lineAfterStrings(List<String> strings, String type, EntityType entityType, SemanticNode node) {
-
-        TextBlock textBlock = node.getTextBlock();
-        SearchImplementation searchImplementation = new SearchImplementation(strings, false);
-        return searchImplementation.getBoundaries(textBlock, node.getTextRange())
-                .stream()
-                .map(boundary -> toLineAfterBoundary(textBlock, boundary))
-                .filter(boundary -> isValidEntityBoundary(textBlock, boundary))
-                .map(boundary -> byTextRange(boundary, type, entityType, node))
-                .filter(Optional::isPresent)
-                .map(Optional::get);
-    }
-
-
-    public Stream<TextEntity> lineAfterStringsIgnoreCase(List<String> strings, String type, EntityType entityType, SemanticNode node) {
-
-        TextBlock textBlock = node.getTextBlock();
-        SearchImplementation searchImplementation = new SearchImplementation(strings, true);
-        return searchImplementation.getBoundaries(textBlock, node.getTextRange())
-                .stream()
-                .map(boundary -> toLineAfterBoundary(textBlock, boundary))
-                .filter(boundary -> isValidEntityBoundary(textBlock, boundary))
-                .map(boundary -> byTextRange(boundary, type, entityType, node))
-                .filter(Optional::isPresent)
-                .map(Optional::get);
-    }
-
-
-    public Stream<TextEntity> lineAfterString(String string, String type, EntityType entityType, SemanticNode node) {
-
-        TextBlock textBlock = node.getTextBlock();
-        return RedactionSearchUtility.findBoundariesByString(string, textBlock)
-                .stream()
-                .map(boundary -> toLineAfterBoundary(textBlock, boundary))
-                .filter(boundary -> isValidEntityBoundary(textBlock, boundary))
-                .map(boundary -> byTextRange(boundary, type, entityType, node))
-                .filter(Optional::isPresent)
-                .map(Optional::get);
-    }
-
-
-    public Stream<TextEntity> lineAfterStringIgnoreCase(String string, String type, EntityType entityType, SemanticNode node) {
-
-        TextBlock textBlock = node.getTextBlock();
-        return RedactionSearchUtility.findBoundariesByStringIgnoreCase(string, textBlock)
-                .stream()
-                .map(boundary -> toLineAfterBoundary(textBlock, boundary))
-                .filter(boundary -> isValidEntityBoundary(textBlock, boundary))
-                .map(boundary -> byTextRange(boundary, type, entityType, node))
-                .filter(Optional::isPresent)
-                .map(Optional::get);
-    }
-
-
-    public Stream<TextEntity> lineAfterStringAcrossColumns(String string, String type, EntityType entityType, Table tableNode) {
-
-        return tableNode.streamTableCells()
-                .flatMap(tableCell -> lineAfterBoundariesAcrossColumns(RedactionSearchUtility.findBoundariesByString(string, tableCell.getTextBlock()),
-                        tableCell,
-                        type,
-                        entityType,
-                        tableNode));
-    }
-
-
-    public Stream<TextEntity> lineAfterStringAcrossColumnsIgnoreCase(String string, String type, EntityType entityType, Table tableNode) {
-
-        return tableNode.streamTableCells()
-                .flatMap(tableCell -> lineAfterBoundariesAcrossColumns(RedactionSearchUtility.findBoundariesByStringIgnoreCase(string, tableCell.getTextBlock()),
-                        tableCell,
-                        type,
-                        entityType,
-                        tableNode));
-    }
-
-
-    /**
-     * 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 boundaries a list of boundaries
-     * @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> boundaries, TableCell tableCell, String type, EntityType entityType, Table tableNode) {
-
-        return boundaries.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.findBoundaryOfAllLinesInYRange(maxMinPair.getLeft(), maxMinPair.getRight(), nextTableCell.getTextBlock()))
-                        .map(b -> b.trim(tableNode.getTextBlock()))
-                        .filter(boundary -> isValidEntityBoundary(tableNode.getTextBlock(), boundary))
-                        .map(boundary -> byTextRange(boundary, type, entityType, tableNode))
-                        .filter(Optional::isPresent)
-                        .map(Optional::get))
-                .flatMap(Functions.identity());
-    }
-
-
-    public Optional<TextEntity> semanticNodeAfterString(SemanticNode semanticNode, String string, String type, EntityType entityType) {
-
-        var textBlock = semanticNode.getTextBlock();
-        int startIndex = Math.min(textBlock.indexOf(string), 0);
-        var boundary = new TextRange(startIndex, semanticNode.getTextRange().end());
-        if (boundary.length() > 0) {
-            boundary = new TextRange(boundary.start(), boundary.end() - 1);
-        }
-        if (!isValidEntityBoundary(textBlock, boundary)) {
-            return Optional.empty();
-        }
-        return byTextRange(boundary, type, entityType, semanticNode);
-    }
-
-
-    public Stream<TextEntity> byRegexWithLineBreaks(String regexPattern, String type, EntityType entityType, SemanticNode node) {
-
-        return byRegexWithLineBreaks(regexPattern, type, entityType, 0, node);
-    }
-
-
-    public Stream<TextEntity> byRegexWithLineBreaksIgnoreCase(String regexPattern, String type, EntityType entityType, SemanticNode node) {
-
-        return byRegexWithLineBreaksIgnoreCase(regexPattern, type, entityType, 0, node);
-    }
-
-
-    public Stream<TextEntity> byRegex(String regexPattern, String type, EntityType entityType, SemanticNode node) {
-
-        return byRegex(regexPattern, type, entityType, 0, node);
-    }
-
-
-    public Stream<TextEntity> byRegexIgnoreCase(String regexPattern, String type, EntityType entityType, SemanticNode node) {
-
-        return byRegexIgnoreCase(regexPattern, type, entityType, 0, node);
-    }
-
-
-    public Stream<TextEntity> byRegexWithLineBreaks(String regexPattern, String type, EntityType entityType, int group, SemanticNode node) {
-
-        return RedactionSearchUtility.findBoundariesByRegexWithLineBreaks(regexPattern, group, node.getTextBlock())
-                .stream()
-                .map(boundary -> byTextRange(boundary, type, entityType, node))
-                .filter(Optional::isPresent)
-                .map(Optional::get);
-    }
-
-
-    public Stream<TextEntity> byRegexWithLineBreaksIgnoreCase(String regexPattern, String type, EntityType entityType, int group, SemanticNode node) {
-
-        return RedactionSearchUtility.findBoundariesByRegexWithLineBreaksIgnoreCase(regexPattern, group, node.getTextBlock())
-                .stream()
-                .map(boundary -> byTextRange(boundary, type, entityType, node))
-                .filter(Optional::isPresent)
-                .map(Optional::get);
-    }
-
-
-    public Stream<TextEntity> byRegex(String regexPattern, String type, EntityType entityType, int group, SemanticNode node) {
-
-        return RedactionSearchUtility.findBoundariesByRegex(regexPattern, group, node.getTextBlock())
-                .stream()
-                .map(boundary -> byTextRange(boundary, type, entityType, node))
-                .filter(Optional::isPresent)
-                .map(Optional::get);
-    }
-
-
-    public Stream<TextEntity> byRegexIgnoreCase(String regexPattern, String type, EntityType entityType, int group, SemanticNode node) {
-
-        return RedactionSearchUtility.findBoundariesByRegexIgnoreCase(regexPattern, group, node.getTextBlock())
-                .stream()
-                .map(boundary -> byTextRange(boundary, type, entityType, node))
-                .filter(Optional::isPresent)
-                .map(Optional::get);
-    }
-
-
-    public Stream<TextEntity> byString(String keyword, String type, EntityType entityType, SemanticNode node) {
-
-        return RedactionSearchUtility.findBoundariesByString(keyword, node.getTextBlock())
-                .stream()
-                .map(boundary -> byTextRange(boundary, type, entityType, node))
-                .filter(Optional::isPresent)
-                .map(Optional::get);
-    }
-
-
-    public Stream<TextEntity> byStringIgnoreCase(String keyword, String type, EntityType entityType, SemanticNode node) {
-
-        return RedactionSearchUtility.findBoundariesByStringIgnoreCase(keyword, node.getTextBlock())
-                .stream()
-                .map(boundary -> byTextRange(boundary, type, entityType, node))
-                .filter(Optional::isPresent)
-                .map(Optional::get);
-    }
-
-
-    public Stream<TextEntity> bySemanticNodeParagraphsOnly(SemanticNode node, String type, EntityType entityType) {
-
-        return node.streamAllSubNodesOfType(NodeType.PARAGRAPH).map(semanticNode -> bySemanticNode(semanticNode, type, entityType)).filter(Optional::isPresent).map(Optional::get);
-    }
-
-
-    public Stream<TextEntity> bySemanticNodeParagraphsOnlyMergeConsecutive(SemanticNode node, String type, EntityType entityType) {
-
-        return node.streamAllSubNodesOfType(NodeType.PARAGRAPH)
-                .map(SemanticNode::getTextRange)
-                .collect(new ConsecutiveBoundaryCollector())
-                .stream()
-                .map(boundary -> byTextRange(boundary, type, entityType, node))
-                .filter(Optional::isPresent)
-                .map(Optional::get);
-    }
-
-
-    public Optional<TextEntity> semanticNodeAfterString(String string, String type, EntityType entityType, SemanticNode node) {
-
-        if (!node.containsString(string)) {
-            return Optional.empty();
-        }
-        TextRange textRange = new TextRange(node.getTextBlock().indexOf(string) + string.length(), node.getTextRange().end());
-        return byTextRange(textRange, type, entityType, node);
-    }
-
-
-    public Optional<TextEntity> bySemanticNode(SemanticNode node, String type, EntityType entityType) {
-
-        TextRange textRange = node.getTextBlock().getTextRange();
-
-        if (textRange.length() > 0) {
-            textRange = new TextRange(textRange.start(), textRange.end() - 1);
-        }
-        if (!isValidEntityBoundary(node.getTextBlock(), textRange)) {
-            return Optional.empty();
-        }
-        return byTextRange(textRange, type, entityType, node);
-    }
-
-
-    public Optional<TextEntity> byPrefixExpansionRegex(TextEntity entity, String regexPattern) {
-
-        int expandedStart = RedactionSearchUtility.getExpandedStartByRegex(entity, regexPattern);
-        return byTextRange(new TextRange(expandedStart, entity.getTextRange().end()), entity.getType(), entity.getEntityType(), entity.getDeepestFullyContainingNode());
-    }
-
-
-    public Optional<TextEntity> bySuffixExpansionRegex(TextEntity entity, String regexPattern) {
-
-        int expandedEnd = RedactionSearchUtility.getExpandedEndByRegex(entity, regexPattern);
-        expandedEnd = truncateEndIfLineBreakIsBetween(entity.getTextRange().end(), expandedEnd, entity.getDeepestFullyContainingNode().getTextBlock());
-        return byTextRange(new TextRange(entity.getTextRange().start(), expandedEnd), entity.getType(), entity.getEntityType(), entity.getDeepestFullyContainingNode());
-    }
-
-
-    private int truncateEndIfLineBreakIsBetween(int end, int expandedEnd, TextBlock textBlock) {
-
-        if (textBlock.getNextLinebreak(end) < expandedEnd) {
-            return end;
-        }
-        return expandedEnd;
-    }
-
-
-    /**
-     * Creates a redaction entity based on the given boundary, type, entity type, and semantic node.
-     * If the document already contains an equal redaction entity, then the original Entity is returned.
-     * Also inserts the Entity into the kieSession.
-     *
-     * @param textRange  The boundary of the redaction entity.
-     * @param type       The type of the redaction entity.
-     * @param entityType The entity type of the redaction entity.
-     * @param node       The semantic node to associate with the redaction entity.
-     * @return An Optional containing the redaction entity, or the previous entity if the entity already exists.
-     */
-    public Optional<TextEntity> byTextRange(TextRange textRange, String type, EntityType entityType, SemanticNode node) {
-
-        if (!node.getTextRange().contains(textRange)) {
-            throw new IllegalArgumentException(String.format("%s is not in the %s of the provided semantic node %s", textRange, node.getTextRange(), node));
-        }
-        TextRange trimmedTextRange = textRange.trim(node.getTextBlock());
-        TextEntity entity = TextEntity.initialEntityNode(trimmedTextRange, type, entityType);
-        if (node.getEntities().contains(entity)) {
-            return node.getEntities().stream().filter(entity::equals).peek(e -> e.addEngine(Engine.RULE)).findAny();
-        }
-        addEntityToGraph(entity, node);
-        entity.addEngine(Engine.RULE);
-        insertToKieSession(entity);
-        return Optional.of(entity);
-    }
-
-
-    public TextEntity forceByBoundary(TextRange textRange, String type, EntityType entityType, SemanticNode node) {
-
-        TextRange trimmedTextRange = textRange.trim(node.getTextBlock());
-        TextEntity entity = TextEntity.initialEntityNode(trimmedTextRange, type, entityType);
-        addEntityToGraph(entity, node);
-        return entity;
-    }
-
-
-    public TextEntity mergeEntitiesOfSameType(List<TextEntity> entitiesToMerge, String type, EntityType entityType, SemanticNode node) {
-
-        if (!allEntitiesIntersectAndHaveSameTypes(entitiesToMerge)) {
-            throw new IllegalArgumentException("Provided entities can not be merged, since they do not intersect or are not the same type!" + entitiesToMerge);
-        }
-        if (entitiesToMerge.isEmpty()) {
-            throw new IllegalArgumentException("No Entities to merge!");
-        }
-        if (entitiesToMerge.size() == 1) {
-            return entitiesToMerge.get(0);
-        }
-
-        TextEntity mergedEntity = TextEntity.initialEntityNode(TextRange.merge(entitiesToMerge.stream().map(TextEntity::getTextRange).toList()), type, entityType);
-        mergedEntity.addEngines(entitiesToMerge.stream().flatMap(entityNode -> entityNode.getEngines().stream()).collect(Collectors.toSet()));
-        entitiesToMerge.stream().map(TextEntity::getMatchedRuleList).flatMap(Collection::stream).forEach(matchedRule -> mergedEntity.getMatchedRuleList().add(matchedRule));
-        entitiesToMerge.stream()
-                .map(TextEntity::getManualOverwrite)
-                .map(ManualChangeOverwrite::getManualChangeLog)
-                .flatMap(Collection::stream)
-                .forEach(manualChange -> mergedEntity.getManualOverwrite().addChange(manualChange));
-
-        mergedEntity.setDictionaryEntry(entitiesToMerge.stream().anyMatch(TextEntity::isDictionaryEntry));
-        mergedEntity.setDossierDictionaryEntry(entitiesToMerge.stream().anyMatch(TextEntity::isDossierDictionaryEntry));
-
-        addEntityToGraph(mergedEntity, node);
-        insertToKieSession(mergedEntity);
-        return mergedEntity;
-    }
-
-
-    public Stream<TextEntity> copyEntities(List<TextEntity> entities, String type, EntityType entityType, SemanticNode node) {
-
-        return entities.stream().map(entity -> copyEntity(entity, type, entityType, node));
-    }
-
-
-    public TextEntity copyEntity(TextEntity entity, String type, EntityType entityType, SemanticNode node) {
-
-        TextEntity newEntity = TextEntity.initialEntityNode(entity.getTextRange(), type, entityType);
-        newEntity.addEngines(entity.getEngines());
-        newEntity.addMatchedRules(entity.getMatchedRuleList());
-        newEntity.getManualOverwrite().addChanges(entity.getManualOverwrite().getManualChangeLog());
-        newEntity.setDictionaryEntry(entity.isDictionaryEntry());
-        newEntity.setDossierDictionaryEntry(entity.isDossierDictionaryEntry());
-        addEntityToGraph(newEntity, node);
-        insertToKieSession(newEntity);
-        return newEntity;
-    }
-
-
-    public void insertToKieSession(TextEntity mergedEntity) {
-
-        if (kieSession != null) {
-            kieSession.insert(mergedEntity);
-        }
-    }
-
-
-    public TextEntity byNerEntity(NerEntities.NerEntity nerEntity, EntityType entityType, SemanticNode semanticNode) {
-
-        var entity = forceByBoundary(nerEntity.textRange(), nerEntity.type(), entityType, semanticNode);
-        entity.addEngine(Engine.NER);
-        insertToKieSession(entity);
-        return entity;
-    }
-
-
-    public TextEntity byNerEntity(NerEntities.NerEntity nerEntity, String type, EntityType entityType, SemanticNode semanticNode) {
-
-        var entity = forceByBoundary(nerEntity.textRange(), type, entityType, semanticNode);
-        entity.addEngine(Engine.NER);
-        insertToKieSession(entity);
-        return entity;
-    }
-
-
-    public Stream<TextEntity> combineNerEntitiesToCbiAddressDefaults(NerEntities nerEntities, String type, EntityType entityType, SemanticNode semanticNode) {
-
-        return NerEntitiesAdapter.combineNerEntitiesToCbiAddressDefaults(nerEntities)
-                .map(boundary -> forceByBoundary(boundary, type, entityType, semanticNode))
-                .peek(entity -> entity.addEngine(Engine.NER))
-                .peek(this::insertToKieSession);
-    }
-
-
-    public TextEntity byTableCellAsHighlight(TableCell tableCell, String type, EntityType entityType) {
-
-        TextEntity highlightEntity = TextEntity.initialEntityNode(new TextRange(tableCell.getTextRange().start(), tableCell.getTextRange().start()), type, entityType);
-
-        String positionId = IdBuilder.buildId(tableCell.getBBox().keySet(), tableCell.getBBox().values().stream().toList(), type, entityType.name());
-        highlightEntity.setPositionsOnPagePerPage(tableCell.getBBox()
-                .entrySet()
-                .stream()
-                .map(entry -> new PositionOnPage(positionId, entry.getKey(), List.of(entry.getValue())))
-                .toList());
-        addEntityToGraph(highlightEntity, tableCell);
-        return highlightEntity;
-    }
-
-
-    public boolean isValidEntityBoundary(TextBlock textBlock, TextRange textRange) {
-
-        return textRange.length() > 0 && boundaryIsSurroundedBySeparators(textBlock, textRange);
-    }
-
-
-    public void addEntityToGraph(TextEntity entity, SemanticNode node) {
-
-        DocumentTree documentTree = node.getDocumentTree();
-        try {
-            addEntityToGraph(entity, documentTree);
-            entity.addIntersectingNode(documentTree.getRoot().getNode());
-            documentTree.getRoot().getNode().getEntities().add(entity);
-        } catch (NoSuchElementException e) {
-            entity.setDeepestFullyContainingNode(documentTree.getRoot().getNode());
-            entityEnrichmentService.enrichEntity(entity, entity.getDeepestFullyContainingNode().getTextBlock());
-            entity.addIntersectingNode(documentTree.getRoot().getNode());
-            addToPages(entity);
-            addEntityToNodeEntitySets(entity);
-        }
-    }
-
-
-    private void addEntityToGraph(TextEntity entity, DocumentTree documentTree) {
-
-        SemanticNode containingNode = documentTree.childNodes(Collections.emptyList())
-                .filter(node -> node.getTextBlock().containsTextRange(entity.getTextRange()))
-                .findFirst()
-                .orElseThrow(() -> new NoSuchElementException("No containing Node found!"));
-
-        containingNode.addThisToEntityIfIntersects(entity);
-
-        TextBlock textBlock = entity.getDeepestFullyContainingNode().getTextBlock();
-        entityEnrichmentService.enrichEntity(entity, textBlock);
-
-        addToPages(entity);
-        addEntityToNodeEntitySets(entity);
-    }
-
-
-    private static void addToPages(TextEntity entity) {
-
-        Set<Page> pages = entity.getDeepestFullyContainingNode().getPages(entity.getTextRange());
-        entity.getPages().addAll(pages);
-        pages.forEach(page -> page.getEntities().add(entity));
-    }
-
-
-    private static void addEntityToNodeEntitySets(TextEntity entity) {
-
-        entity.getIntersectingNodes().forEach(node -> node.getEntities().add(entity));
-    }
-
-
-    private static boolean allEntitiesIntersectAndHaveSameTypes(List<TextEntity> entitiesToMerge) {
-
-        if (entitiesToMerge.isEmpty()) {
-            return true;
-        }
-        TextEntity previousEntity = entitiesToMerge.get(0);
-        for (TextEntity textEntity : entitiesToMerge.subList(1, entitiesToMerge.size())) {
-            boolean typeMatches = textEntity.getType().equals(previousEntity.getType());
-            boolean entityTypeMatches = textEntity.getEntityType().equals(previousEntity.getEntityType());
-            boolean intersects = textEntity.intersects(previousEntity);
-            if (!typeMatches || !entityTypeMatches || !intersects) {
-                return false;
-            }
-        }
-        return true;
-    }
-
-
-    private static TextRange toLineAfterBoundary(TextBlock textBlock, TextRange textRange) {
-
-        return new TextRange(textRange.end(), textBlock.getNextLinebreak(textRange.end())).trim(textBlock);
-    }
-
-}

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

@@ -1,91 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.services;
-
-import java.util.Arrays;
-import java.util.List;
-import java.util.Objects;
-
-import org.springframework.stereotype.Service;
-
-import com.iqser.red.service.redaction.v1.server.document.graph.entity.TextEntity;
-import com.iqser.red.service.redaction.v1.server.document.graph.textblock.TextBlock;
-import com.iqser.red.service.redaction.v1.server.settings.RedactionServiceSettings;
-
-import lombok.RequiredArgsConstructor;
-
-@Service
-@RequiredArgsConstructor
-public class EntityEnrichmentService {
-
-    private final RedactionServiceSettings redactionServiceSettings;
-
-
-    public void enrichEntity(TextEntity entity, TextBlock textBlock) {
-
-        entity.setValue(textBlock.subSequence(entity.getTextRange()).toString());
-        entity.setTextAfter(findTextAfter(entity.getTextRange().end(), textBlock));
-        entity.setTextBefore(findTextBefore(entity.getTextRange().start(), textBlock));
-    }
-
-
-    private String findTextAfter(int index, TextBlock textBlock) {
-
-        int endOffset = Math.min(index + redactionServiceSettings.getSurroundingWordsOffsetWindow(), textBlock.getTextRange().end());
-        String textAfter = textBlock.subSequence(index, endOffset).toString();
-        if (!textAfter.isBlank()) {
-            List<String> wordsAfter = splitToWordsAndRemoveEmptyWords(textAfter);
-            int numberOfWordsAfter = Math.min(wordsAfter.size(), redactionServiceSettings.getNumberOfSurroundingWords());
-            if (!wordsAfter.isEmpty()) {
-                return concatWordsAfter(wordsAfter.subList(0, numberOfWordsAfter), textAfter.startsWith(" "));
-            }
-        }
-        return "";
-    }
-
-
-    private String findTextBefore(int index, TextBlock textBlock) {
-
-        int offsetBefore = Math.max(index - redactionServiceSettings.getSurroundingWordsOffsetWindow(), textBlock.getTextRange().start());
-        String textBefore = textBlock.subSequence(offsetBefore, index).toString();
-        if (!textBefore.isBlank()) {
-            List<String> wordsBefore = splitToWordsAndRemoveEmptyWords(textBefore);
-            int numberOfWordsBefore = Math.min(wordsBefore.size(), redactionServiceSettings.getNumberOfSurroundingWords());
-            if (!wordsBefore.isEmpty()) {
-                return concatWordsBefore(wordsBefore.subList(wordsBefore.size() - numberOfWordsBefore, wordsBefore.size()), textBefore.endsWith(" "));
-            }
-        }
-        return "";
-    }
-
-
-    private static List<String> splitToWordsAndRemoveEmptyWords(String textAfter) {
-
-        return Arrays.stream(textAfter.split(" ")).filter(word -> !Objects.equals("", word)).toList();
-    }
-
-
-    private static String concatWordsBefore(List<String> words, boolean endWithSpace) {
-
-        StringBuilder sb = new StringBuilder();
-
-        for (String word : words) {
-            sb.append(word).append(" ");
-        }
-
-        String result = sb.toString().trim();
-        return endWithSpace ? result + " " : result;
-    }
-
-
-    private static String concatWordsAfter(List<String> words, boolean startWithSpace) {
-
-        StringBuilder sb = new StringBuilder();
-
-        for (String word : words) {
-            sb.append(word).append(" ");
-        }
-
-        String result = sb.toString().trim();
-        return startWithSpace ? " " + result : result;
-    }
-
-}

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

@@ -1,95 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.services;
-
-import java.awt.geom.Rectangle2D;
-import java.util.HashSet;
-import java.util.LinkedList;
-import java.util.NoSuchElementException;
-
-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.ManualResizeRedaction;
-import com.iqser.red.service.redaction.v1.server.document.graph.entity.Entity;
-import com.iqser.red.service.redaction.v1.server.document.graph.entity.PositionOnPage;
-import com.iqser.red.service.redaction.v1.server.document.graph.entity.TextEntity;
-import com.iqser.red.service.redaction.v1.server.document.graph.nodes.Image;
-import com.iqser.red.service.redaction.v1.server.document.graph.nodes.ImageType;
-import com.iqser.red.service.redaction.v1.server.document.graph.nodes.SemanticNode;
-import com.iqser.red.service.redaction.v1.server.document.utils.RectangleTransformations;
-
-import lombok.RequiredArgsConstructor;
-
-@RequiredArgsConstructor
-public class ManualChangesApplicationService {
-
-    private final EntityCreationService entityCreationService;
-
-
-    public void recategorize(Entity entityToBeReCategorized, ManualRecategorization manualRecategorization) {
-
-        if (entityToBeReCategorized instanceof Image image) {
-            image.setImageType(ImageType.fromString(manualRecategorization.getType()));
-            return;
-        }
-        // need to create a new entity and copy over all values, since type is part of the primary key for entities and should never be changed!
-        if (entityToBeReCategorized instanceof TextEntity textEntity) {
-            TextEntity recategorizedEntity = entityCreationService.copyEntity(textEntity, manualRecategorization.getType(), textEntity.getEntityType(), textEntity.getDeepestFullyContainingNode());
-            recategorizedEntity.setPositionsOnPagePerPage(textEntity.getPositionsOnPagePerPage());
-            recategorizedEntity.getManualOverwrite().addChange(manualRecategorization);
-            textEntity.removeFromGraph();
-        }
-    }
-
-
-    public void resizeEntityAndReinsert(TextEntity entityToBeResized, ManualResizeRedaction manualResizeRedaction) {
-
-        PositionOnPage positionOnPageToBeResized = entityToBeResized.getPositionsOnPagePerPage()
-                .stream()
-                .filter(redactionPosition -> redactionPosition.getId().equals(manualResizeRedaction.getAnnotationId()))
-                .findFirst()
-                .orElseThrow(() -> new NoSuchElementException("No redaction position with matching annotation id found!"));
-
-        positionOnPageToBeResized.setRectanglePerLine(manualResizeRedaction.getPositions().stream().map(ManualChangesApplicationService::toRectangle2D).toList());
-
-        int newStartOffset;
-        if (manualResizeRedaction.getValue().length() > entityToBeResized.getValue().length()) {
-            newStartOffset = entityToBeResized.getTextRange().start() - manualResizeRedaction.getValue().indexOf(entityToBeResized.getValue());
-        } else {
-            newStartOffset = entityToBeResized.getTextRange().start() + entityToBeResized.getValue().indexOf(manualResizeRedaction.getValue());
-        }
-
-        // need to reinsert the entity, due to the boundary having changed.
-        removeAndUpdateAndReInsertEntity(entityToBeResized, manualResizeRedaction, newStartOffset);
-        entityToBeResized.getManualOverwrite().addChange(manualResizeRedaction);
-    }
-
-
-    private void removeAndUpdateAndReInsertEntity(TextEntity entityToBeResized, ManualResizeRedaction manualResizeRedaction, int newStartOffset) {
-
-        SemanticNode nodeToInsertInto = entityToBeResized.getDeepestFullyContainingNode().getDocumentTree().getRoot().getNode();
-        entityToBeResized.getIntersectingNodes().forEach(node -> node.getEntities().remove(this));
-        entityToBeResized.getPages().forEach(page -> page.getEntities().remove(this));
-        entityToBeResized.setIntersectingNodes(new LinkedList<>());
-        entityToBeResized.setDeepestFullyContainingNode(null);
-        entityToBeResized.setPages(new HashSet<>());
-        entityToBeResized.getTextRange().setStart(newStartOffset);
-        entityToBeResized.getTextRange().setEnd(newStartOffset + manualResizeRedaction.getValue().length());
-        entityCreationService.addEntityToGraph(entityToBeResized, nodeToInsertInto);
-    }
-
-
-    public void resizeImage(Image image, ManualResizeRedaction manualResizeRedaction) {
-
-        if (manualResizeRedaction.getPositions().isEmpty() || manualResizeRedaction.getPositions() == null) {
-            return;
-        }
-        var bBox = RectangleTransformations.rectangle2DBBox(manualResizeRedaction.getPositions().stream().map(ManualChangesApplicationService::toRectangle2D).toList());
-        image.setPosition(bBox);
-        image.getManualOverwrite().addChange(manualResizeRedaction);
-    }
-
-
-    private static Rectangle2D toRectangle2D(com.iqser.red.service.persistence.service.v1.api.shared.model.annotations.Rectangle rect) {
-
-        return new Rectangle2D.Double(rect.getTopLeftX() - rect.getWidth(), rect.getTopLeftY() - rect.getHeight(), rect.getWidth(), rect.getHeight());
-    }
-
-}

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

@@ -1,175 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.utils;
-
-import java.awt.geom.Rectangle2D;
-import java.awt.geom.RectangularShape;
-import java.util.Collections;
-import java.util.LinkedList;
-import java.util.List;
-import java.util.Set;
-import java.util.function.BiConsumer;
-import java.util.function.BinaryOperator;
-import java.util.function.Function;
-import java.util.function.Supplier;
-import java.util.stream.Collector;
-
-import com.iqser.red.service.persistence.service.v1.api.shared.model.redactionlog.Rectangle;
-import com.iqser.red.service.redaction.v1.server.document.graph.textblock.AtomicTextBlock;
-
-import lombok.AllArgsConstructor;
-import lombok.NoArgsConstructor;
-
-public class RectangleTransformations {
-
-    public static Rectangle2D atomicTextBlockBBox(List<AtomicTextBlock> atomicTextBlocks) {
-
-        return atomicTextBlocks.stream().flatMap(atomicTextBlock -> atomicTextBlock.getPositions().stream()).collect(new Rectangle2DBBoxCollector());
-    }
-
-
-    public static Rectangle2D rectangleBBox(List<Rectangle> rectangles) {
-
-        return rectangles.stream().map(RectangleTransformations::toRectangle2D).collect(new Rectangle2DBBoxCollector());
-    }
-
-
-    public static Rectangle2D toRectangle2D(Rectangle redactionLogRectangle) {
-
-        return new Rectangle2D.Double(redactionLogRectangle.getTopLeft().getX(),
-                redactionLogRectangle.getTopLeft().getY() + redactionLogRectangle.getHeight(),
-                redactionLogRectangle.getWidth(),
-                -redactionLogRectangle.getHeight());
-    }
-
-
-    public static Rectangle2D rectangle2DBBox(List<Rectangle2D> rectangle2DList) {
-
-        return rectangle2DList.stream().collect(new Rectangle2DBBoxCollector());
-    }
-
-
-    /**
-     * If two rectangles are further apart than five times the average width of a rectangle, a gap is inserted.
-     *
-     * @param rectangle2DList A list of rectangles to combine
-     * @return A list of rectangles which are combined if they are closer than the split threshold
-     */
-    public static List<Rectangle2D> rectangleBBoxWithGaps(List<Rectangle2D> rectangle2DList) {
-
-        if (rectangle2DList.isEmpty()) {
-            return Collections.emptyList();
-        }
-        double splitThreshold = rectangle2DList.stream().mapToDouble(RectangularShape::getWidth).average().orElse(5) * 5.0;
-
-        List<List<Rectangle2D>> rectangleListsWithGaps = new LinkedList<>();
-        List<Rectangle2D> rectangleListWithoutGaps = new LinkedList<>();
-        rectangleListsWithGaps.add(rectangleListWithoutGaps);
-        Rectangle2D previousRectangle = rectangle2DList.get(0);
-        for (Rectangle2D currentRectangle : rectangle2DList) {
-            if (Math.abs(currentRectangle.getMinX() - previousRectangle.getMaxX()) > splitThreshold) {
-                rectangleListWithoutGaps = new LinkedList<>();
-                rectangleListWithoutGaps.add(currentRectangle);
-                rectangleListsWithGaps.add(rectangleListWithoutGaps);
-                previousRectangle = currentRectangle;
-            } else {
-                rectangleListWithoutGaps.add(currentRectangle);
-                previousRectangle = currentRectangle;
-            }
-        }
-        return rectangleListsWithGaps.stream().map(RectangleTransformations::rectangle2DBBox).toList();
-    }
-
-
-    private static class Rectangle2DBBoxCollector implements Collector<Rectangle2D, Rectangle2DBBoxCollector.BBox, Rectangle2D> {
-
-        @Override
-        public Supplier<BBox> supplier() {
-
-            return BBox::new;
-        }
-
-
-        @Override
-        public BiConsumer<BBox, Rectangle2D> accumulator() {
-
-            return BBox::addRectangle;
-        }
-
-
-        @Override
-        public BinaryOperator<BBox> combiner() {
-
-            return (b1, b2) -> new BBox(Math.min(b1.lowerLeftX, b2.lowerLeftX),
-                    Math.min(b1.lowerLeftY, b2.lowerLeftY),
-                    Math.max(b1.upperRightX, b2.upperRightX),
-                    Math.max(b1.upperRightY, b2.upperRightY));
-        }
-
-
-        @Override
-        public Function<BBox, Rectangle2D> finisher() {
-
-            return BBox::toRectangle2D;
-        }
-
-
-        @Override
-        public Set<Characteristics> characteristics() {
-
-            return Set.of(Characteristics.UNORDERED);
-        }
-
-
-        @AllArgsConstructor
-        @NoArgsConstructor
-        private static class BBox {
-
-            Double lowerLeftX;
-            Double lowerLeftY;
-            Double upperRightX;
-            Double upperRightY;
-
-
-            public Rectangle2D toRectangle2D() {
-
-                if (lowerLeftX == null || lowerLeftY == null || upperRightX == null || upperRightY == null) {
-                    return new Rectangle2D.Double(0, 0, 0, 0);
-                }
-                return new Rectangle2D.Double(lowerLeftX, lowerLeftY, upperRightX - lowerLeftX, upperRightY - lowerLeftY);
-            }
-
-
-            public void addRectangle(Rectangle2D rectangle2D) {
-
-                double lowerLeftX = Math.min(rectangle2D.getMinX(), rectangle2D.getMaxX());
-                double lowerLeftY = Math.min(rectangle2D.getMinY(), rectangle2D.getMaxY());
-                double upperRightX = Math.max(rectangle2D.getMinX(), rectangle2D.getMaxX());
-                double upperRightY = Math.max(rectangle2D.getMinY(), rectangle2D.getMaxY());
-
-                if (this.lowerLeftX == null) {
-                    this.lowerLeftX = lowerLeftX;
-                } else if (this.lowerLeftX > lowerLeftX) {
-                    this.lowerLeftX = lowerLeftX;
-                }
-                if (this.lowerLeftY == null) {
-                    this.lowerLeftY = lowerLeftY;
-                } else if (this.lowerLeftY > lowerLeftY) {
-                    this.lowerLeftY = lowerLeftY;
-                }
-                if (this.upperRightX == null) {
-                    this.upperRightX = upperRightX;
-                } else if (this.upperRightX < upperRightX) {
-                    this.upperRightX = upperRightX;
-                }
-                if (this.upperRightY == null) {
-                    this.upperRightY = upperRightY;
-                } else if (this.upperRightY < upperRightY) {
-                    this.upperRightY = upperRightY;
-                }
-
-            }
-
-        }
-
-    }
-
-}

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

@@ -1,182 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.document.utils;
-
-import static java.lang.String.format;
-
-import java.awt.geom.Rectangle2D;
-import java.util.LinkedList;
-import java.util.List;
-import java.util.regex.Matcher;
-import java.util.regex.Pattern;
-import java.util.stream.IntStream;
-
-import com.iqser.red.service.redaction.v1.server.document.graph.TextRange;
-import com.iqser.red.service.redaction.v1.server.document.graph.entity.TextEntity;
-import com.iqser.red.service.redaction.v1.server.document.graph.textblock.TextBlock;
-import com.iqser.red.service.redaction.v1.server.redaction.utils.Patterns;
-
-import lombok.experimental.UtilityClass;
-
-@UtilityClass
-public class RedactionSearchUtility {
-
-    public static boolean anyMatch(CharSequence charSequence, String regexPattern) {
-
-        Pattern pattern = Patterns.getCompiledPattern(regexPattern, false);
-        return pattern.matcher(charSequence).find();
-    }
-
-
-    public static boolean anyMatchIgnoreCase(CharSequence charSequence, String regexPattern) {
-
-        Pattern pattern = Patterns.getCompiledPattern(regexPattern, true);
-        return pattern.matcher(charSequence).find();
-    }
-
-
-    public static boolean exactMatch(CharSequence charSequence, String regexPattern) {
-
-        return charSequence.toString().matches(regexPattern);
-    }
-
-
-    public static boolean anyMatchIgnoreCase(TextBlock textBlock, String regexPattern) {
-
-        return anyMatchIgnoreCase(textBlock.getSearchText(), regexPattern);
-    }
-
-
-    public static boolean anyMatch(TextBlock textBlock, String regexPattern) {
-
-        return anyMatch(textBlock.getSearchText(), regexPattern);
-    }
-
-
-    public static TextRange findFirstBoundary(String regexPattern, CharSequence searchText) {
-
-        Pattern pattern = Patterns.getCompiledPattern(regexPattern, false);
-        Matcher matcher = pattern.matcher(searchText);
-        if (matcher.find()) {
-            return new TextRange(matcher.start(), matcher.end());
-        }
-        throw new IllegalArgumentException(format("Charsequence %s does not contain any matches for pattern %s", searchText, regexPattern));
-    }
-
-
-    public static int getExpandedEndByRegex(TextEntity entity, String regexPattern) {
-
-        int expandedEnd;
-        if (anyMatch(entity.getTextAfter(), regexPattern)) {
-            TextRange postfixTextRange = findFirstBoundary(regexPattern, entity.getTextAfter());
-            expandedEnd = postfixTextRange.end() + entity.getTextRange().end();
-        } else {
-            expandedEnd = entity.getTextRange().end();
-        }
-        return expandedEnd;
-    }
-
-
-    public static int getExpandedStartByRegex(TextEntity entity, String regexPattern) {
-
-        int expandedStart;
-        if (anyMatch(entity.getTextBefore(), regexPattern)) {
-            TextRange prefixTextRange = findFirstBoundary(regexPattern, entity.getTextBefore());
-            expandedStart = prefixTextRange.start() + entity.getTextRange().start() - entity.getTextBefore().length();
-        } else {
-            expandedStart = entity.getTextRange().start();
-        }
-        return expandedStart;
-    }
-
-    public static TextRange findBoundaryOfAllLinesInYRange(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);
-    }
-
-
-    private static boolean isWithinYRange(double maxY, double minY, TextBlock textBlock, TextRange lineTextRange) {
-
-        Rectangle2D lineBBox = RectangleTransformations.rectangle2DBBox(textBlock.getPositions(lineTextRange));
-        return lineBBox.getMinY() < maxY && minY < lineBBox.getMaxY();
-    }
-
-
-    public static List<TextRange> findBoundariesByRegex(String regexPattern, TextBlock textBlock) {
-
-        Pattern pattern = Patterns.getCompiledPattern(regexPattern, false);
-        return getBoundariesByPattern(textBlock, 0, pattern);
-
-    }
-
-
-    public static List<TextRange> findBoundariesByRegex(String regexPattern, int group, TextBlock textBlock) {
-
-        Pattern pattern = Patterns.getCompiledPattern(regexPattern, false);
-        return getBoundariesByPattern(textBlock, group, pattern);
-    }
-
-
-    public static List<TextRange> findBoundariesByRegexWithLineBreaks(String regexPattern, int group, TextBlock textBlock) {
-
-        Pattern pattern = Patterns.getCompiledMultilinePattern(regexPattern, false);
-        return getBoundariesByPatternWithLineBreaks(textBlock, group, pattern);
-    }
-
-
-    public static List<TextRange> findBoundariesByRegexWithLineBreaksIgnoreCase(String regexPattern, int group, TextBlock textBlock) {
-
-        Pattern pattern = Patterns.getCompiledMultilinePattern(regexPattern, true);
-        return getBoundariesByPatternWithLineBreaks(textBlock, group, pattern);
-    }
-
-
-    public static List<TextRange> findBoundariesByRegexIgnoreCase(String regexPattern, int group, TextBlock textBlock) {
-
-        Pattern pattern = Patterns.getCompiledPattern(regexPattern, true);
-        return getBoundariesByPattern(textBlock, group, pattern);
-    }
-
-
-    private static List<TextRange> getBoundariesByPattern(TextBlock textBlock, int group, Pattern pattern) {
-
-        Matcher matcher = pattern.matcher(textBlock.subSequence(textBlock.getTextRange()));
-        List<TextRange> boundaries = new LinkedList<>();
-        while (matcher.find()) {
-            boundaries.add(new TextRange(matcher.start(group) + textBlock.getTextRange().start(), matcher.end(group) + textBlock.getTextRange().start()));
-        }
-        return boundaries;
-    }
-
-
-    private static List<TextRange> getBoundariesByPatternWithLineBreaks(TextBlock textBlock, int group, Pattern pattern) {
-
-        String searchTextWithLineBreaks = textBlock.searchTextWithLineBreaks();
-        Matcher matcher = pattern.matcher(searchTextWithLineBreaks);
-        List<TextRange> boundaries = new LinkedList<>();
-        while (matcher.find()) {
-            boundaries.add(new TextRange(matcher.start(group) + textBlock.getTextRange().start(), matcher.end(group) + textBlock.getTextRange().start()));
-        }
-        return boundaries;
-    }
-
-
-    public static List<TextRange> findBoundariesByString(String searchString, TextBlock textBlock) {
-
-        List<TextRange> boundaries = new LinkedList<>();
-        for (int index = textBlock.indexOf(searchString); index >= 0; index = textBlock.indexOf(searchString, index + 1)) {
-            boundaries.add(new TextRange(index, index + searchString.length()));
-        }
-        return boundaries;
-    }
-
-
-    public static List<TextRange> findBoundariesByStringIgnoreCase(String searchString, TextBlock textBlock) {
-
-        Pattern pattern = Pattern.compile(Pattern.quote(searchString), Pattern.CASE_INSENSITIVE);
-        return getBoundariesByPattern(textBlock, 0, pattern);
-    }
-
-}