added documentation for EntityCreationService, RedactionEntity to prompts

DM-165: Renamed isOnPage to onPage to prevent not working drools optimizations

Closes DM-165

See merge request redactmanager/redaction-service!81

.gitignore

@@ -9,6 +9,49 @@
 **/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
@@ -26,3 +69,7 @@
 **/.DS_Store
 **/classpath-data.json
 **/dependencies-and-licenses-overview.txt
+gradle.properties
+gradlew
+gradlew.bat
+gradle/

.gitlab-ci.yml

@@ -3,4 +3,4 @@ variables:
 include:
   - project: 'gitlab/gitlab'
     ref: 'main'
-    file: 'ci-templates/maven_java.yml'
+    file: 'ci-templates/gradle_java.yml'

buildSrc/build.gradle.kts

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

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

@@ -0,0 +1,75 @@
+plugins {
+    `java-library`
+    `maven-publish`
+    pmd
+    checkstyle
+    jacoco
+}
+
+group = "com.iqser.red"
+
+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"))
+    }
+}
+
+allprojects {
+    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();
+                }
+            }
+        }
+    }
+}
+
+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

@@ -0,0 +1,39 @@
+<?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

@@ -0,0 +1,21 @@
+<?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

@@ -0,0 +1,24 @@
+<?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>

drools-prompt/EntityCreationService_doc

@@ -0,0 +1,124 @@
+/**
+* Searches the provided SemanticNode for the keyword and creates an Entity for each occurrence.
+* @param keyword the string to search for
+* @param type The type of the RedactionEntity to be created
+* @param entityType The EntityType of the RedactionEntity to be created
+* @param node The SemanticNode to search in
+* @return A Stream of RedactionEntities with the keyword as value, the type as type and the provided EntityType
+*/
+public Stream<RedactionEntity> byString(String keyword, String type, EntityType entityType, SemanticNode node)
+/**
+* Same as byString, but case insensitive.
+*/
+public Stream<RedactionEntity> byStringIgnoreCase(String keyword, String type, EntityType entityType, SemanticNode node)
+/**
+* Searches the provided SemanticNode with the regexPattern and creates a new RedactionEntity with the provided group for each occurrence.
+* @param regexPattern The regexPattern
+* @param type The type of the RedactionEntity to be created
+* @param entityType The EntityType of the RedactionEntity to be created
+* @param group the regexPattern group, that should be the entity
+* @param node The SemanticNode to search in
+* @return A Stream of RedactionEntities with the keyword as value, the type as type and the provided EntityType
+*/
+public Stream<RedactionEntity> byRegex(String regexPattern, String type, EntityType entityType, int group, SemanticNode node)
+/**
+* Same as byRegex, but case insensitive.
+*/
+public Stream<RedactionEntity> byRegexIgnoreCase(String regexPattern, String type, EntityType entityType, int group, SemanticNode node)
+/**
+* Same as byRegex, but can handle patterns with linebreaks.
+*/
+public Stream<RedactionEntity> byRegexWithLineBreaksIgnoreCase(String regexPattern, String type, EntityType entityType, int group, SemanticNode node)
+/**
+* Same as byRegexWithLineBreaks, but case insensitive.
+*/
+public Stream<RedactionEntity> byRegexWithLineBreaksIgnoreCase(String regexPattern, String type, EntityType entityType, int group, SemanticNode node)
+/**
+* Finds the provided string, and creates a new RedactionEntity from the text after until the end of the line it is found in.
+* @param string The keyword to search for
+* @param type The type of the RedactionEntity to be created
+* @param entityType The EntityType of the RedactionEntity to be created
+* @param node The SemanticNode to search in
+* @return A Stream of RedactionEntities with the keyword as value, the type as type and the provided EntityType
+*/
+public Stream<RedactionEntity> lineAfterString(String string, String type, EntityType entityType, SemanticNode node)
+/**
+* Same as lineAfterString, but with multiple keywords
+*/
+public Stream<RedactionEntity> lineAfterStrings(List<String> strings, String type, EntityType entityType, SemanticNode node)
+/**
+* Finds the provided string in a TableCell, and creates a new RedactionEntity in the same line but adjacent table cells to the right.
+* @param string The keyword to search for
+* @param type The type of the RedactionEntity to be created
+* @param entityType The EntityType of the RedactionEntity to be created
+* @param table The TableNode to search in
+* @return A Stream of RedactionEntities with the keyword as value, the type as type and the provided EntityType
+*/
+public Stream<RedactionEntity> lineAfterStringAcrossColumns(String string, String type, EntityType entityType, TableNode table)
+/**
+* Creates a redaction entity based on the given boundary, type, entity type, and semantic node.
+*
+* @param boundary   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 where the boundary is.
+* @return An Optional containing the new redaction entity.
+*/
+public Optional<RedactionEntity> byBoundary(Boundary boundary, String type, EntityType entityType, SemanticNode node)
+/**
+* Creates new RedactionEntities between the provided start and stop boundaries. The start and stop boundaries are excluded.
+* If any boundaries of the new RedactionEntities overlap, only the shortest boundary will be used.
+* @param startBoundaries List of start boundaries
+* @param stopBoundaries List of stop boundaries
+* @param type       The type of the redaction entity.
+* @param entityType The entity type of the redaction entity.
+* @param node       The semantic node where the boundaries are.
+* @return A Stream of new RedactionEntities between the start and stop boundaries
+*/
+public Stream<RedactionEntity> betweenBoundaries(List<Boundary> startBoundaries, List<Boundary> stopBoundaries, String type, EntityType entityType, SemanticNode node)
+/**
+* Same as betweenBoundaries, but it creates the start and stop boundaries by performing a text search on the provided SemanticNode.
+*/
+public Stream<RedactionEntity> betweenStrings(String start, String stop, String type, EntityType entityType, SemanticNode node)
+/**
+* Same as betweenStrings, but case insensitive.
+*/
+public Stream<RedactionEntity> betweenStringsIgnoreCase(String start, String stop, String type, EntityType entityType, SemanticNode node)
+/**
+* These 6 functions work the same as betweenStrings, but they also include the start and/or stop strings or are case insensitive, depending on their name.
+*/
+public Stream<RedactionEntity> betweenStringsIncludeStart(String start, String stop, String type, EntityType entityType, SemanticNode node)
+public Stream<RedactionEntity> betweenStringsIncludeStartIgnoreCase(String start, String stop, String type, EntityType entityType, SemanticNode node)
+public Stream<RedactionEntity> betweenStringsIncludeEnd(String start, String stop, String type, EntityType entityType, SemanticNode node)
+public Stream<RedactionEntity> betweenStringsIncludeEndIgnoreCase(String start, String stop, String type, EntityType entityType, SemanticNode node)
+public Stream<RedactionEntity> betweenStringsIncludeStartAndEnd(String start, String stop, String type, EntityType entityType, SemanticNode node)
+public Stream<RedactionEntity> betweenStringsIncludeStartAndEndIgnoreCase(String start, String stop, String type, EntityType entityType, SemanticNode node)
+/**
+* Same as betweenBoundaries, but it creates the start and stop boundaries by performing a regex search on the provided SemanticNode.
+*/
+public Stream<RedactionEntity> betweenRegexes(String regexStart, String regexStop, String type, EntityType entityType, SemanticNode node)
+/**
+* Same as betweenRegexes, but case insensitive.
+*/
+public Stream<RedactionEntity> betweenRegexesIgnoreCase(String regexStart, String regexStop, String type, EntityType entityType, SemanticNode node)
+/**
+* Creates a new RedactionEntity which has the same boundary as the provided SemanticNode.
+* @param node The SemanticNode to create a new RedactionEntity from.
+* @param type       The type of the redaction entity.
+* @param entityType The entity type of the redaction entity.
+* @return An optional RedactionEntity. Is empty, if the provided SemanticNode is empty.
+*/
+public Optional<RedactionEntity> bySemanticNode(SemanticNode node, String type, EntityType entityType)
+/**
+* Same as bySemanticNode, but ignores the SemanticNode, if its not a Paragraph and all its child SemanticNodes, that are not Paragraphs.
+*/
+public Stream<RedactionEntity> bySemanticNodeParagraphsOnly(SemanticNode node, String type, EntityType entityType)
+/**
+* Searches the provided SemanticNode for the provided string, and creates a new RedactionEntity, from the end of the first occurrence of the string until the end of the SemanticNode.
+* @param string The string to search for
+* @param type       The type of the redaction entity.
+* @param entityType The entity type of the redaction entity.
+* @param node The SemanticNode to use and search in
+* @return An optional RedactionEntity, is empty, if the SemanticNode is empty, or the string isn't found in the SemanticNode.
+*/
+public Optional<RedactionEntity> semanticNodeAfterString(String string, String type, EntityType entityType, SemanticNode node)

drools-prompt/Page_doc

@@ -0,0 +1,18 @@
+/**
+ * Retrieves the main body text block.
+ *
+ * @return The text block representing the main body of the document.
+ */
+public TextBlock getMainBodyTextBlock()
+/**
+* Gets all Entities located on the page
+*
+* @return Set of all Entities associated with this Page
+*/
+Set<RedactionEntity> getEntities();
+/**
+* Returns the Page Number
+*
+* @return The number of this page
+*/
+Integer getPageNumber();

drools-prompt/RedactionEntity_doc

@@ -0,0 +1,33 @@
+/**
+* Sets the Entity to applied, this is the default.
+* @param ruleIdentifier Should always be equal to the ruleIdentifier in the Rule name
+* @param reason Should describe the intention of the rule in a few words
+* @param legalBasis Is dependent on the rule, if none is known the default is "n-a", can't be null
+*/
+void apply(String ruleIdentifier, String reason, String legalBasis)
+/**
+* Same as apply, but legalBasis can be null.
+*/
+void force(String ruleIdentifier, String reason, String legalBasis)
+/**
+* Sets the Entity to not applied.
+* @param ruleIdentifier Should always be equal to the ruleIdentifier in the Rule name
+* @param reason Should describe the intention of the rule in a few words
+* @param legalBasis Is dependent on the rule, if none is known the default is "n-a", can't be null
+*/
+void skip(String ruleIdentifier, String reason, String legalBasis)
+/**
+* Sets the Entity to ignored, is preferred to remove in most cases.
+* @param ruleIdentifier Should always be equal to the ruleIdentifier in the Rule name
+* @param reason Should describe the intention of the rule in a few words
+* @param legalBasis Is dependent on the rule, if none is known the default is "n-a", can't be null
+*/
+void ignore(String ruleIdentifier, String reason, String legalBasis)
+/**
+* Removes the entity entirely, also removes it from all EntitySets and sets intersectingNodes and deepestFullyContainingNode to null.
+* Should only be used in a few cases!
+* @param ruleIdentifier Should always be equal to the ruleIdentifier in the Rule name
+* @param reason Should describe the intention of the rule in a few words
+* @param legalBasis Is dependent on the rule, if none is known the default is "n-a", can't be null
+*/
+void remove(String ruleIdentifier, String reason, String legalBasis)

drools-prompt/RedactionEntity_properties_doc

@@ -0,0 +1,39 @@
+/**
+* A boundary has a start and end property accessible by start() and end() respectively. It marks the start and end offset in String offsets.
+*/
+Boundary boundary
+/**
+* The type of an Entity identifies groups of Entities. Examples for Entites we want to find are "CBI_author" for authors, "CBI_address" for addresses or "PII" for personally identifiable information.
+* Other types include helper types, which interact with the main Entities, for example "published_information" or "vertebrate". These Entities are used to modify the main Entities, if they occur in the same Section.
+* A typical example would be to ignore Entities of type "CBI_author", if they occur in the same Section as "published_information" entities.
+*/
+String type
+/**
+* The EntityType can be one of four different values: ENTITY, RECOMMENDATION, FALSE_POSITIVE, FALSE_RECOMMENDATION.
+* If an ENTITY is overlapped by a FALSE_POSITIVE, the ENTITY is removed. If a RECOMMENDATION is overlapped by either an ENTITY or FALSE_RECOMMENDATION, it is removed.
+*/
+EntityType entityType
+/**
+* The text the Entity represents.
+*/
+String value
+/**
+* Up to three words after the Entity in the text.
+*/
+String textAfter
+/**
+* Up to three words before the Entity in the text.
+*/
+String textBefore
+/**
+* All pages whose TextBlock intersects the boundary of this entity. Is always equal to the Pages which have this RedactionEntity in their EntitySet.
+*/
+Set<Page> pages
+/**
+* All SemanticNodes whose TextBlock intersects the boundary of this entity. Is always equal to the SemanticNodes which have this RedactionEntity in their EntitySet.
+*/
+List<SemanticNode> intersectingNodes
+/**
+* The SemanticNode which is the deepest in the Tree structure and whose TextBlock fully contains the boundary of this Node.
+*/
+SemanticNode deepestFullyContainingNode

drools-prompt/Section_doc

@@ -0,0 +1,6 @@
+/**
+* Determines whether this Section has any tables.
+*
+* @return {@code true} if there are tables, {@code false} otherwise
+*/
+public boolean hasTables()

drools-prompt/SemanticNode_doc

@@ -0,0 +1,181 @@
+/**
+* Returns the type of this node, such as NodeType.SECTION, NodeType.PARAGRAPH, etc.
+*
+* @return NodeType of this node
+*/
+NodeType getType();
+/**
+* Any Node maintains its own Set of Entities.
+* This Set contains all Entities whose boundary intersects the boundary of this node.
+* The Entities might overlap with the Entities in other Sets
+*
+* @return Set of all Entities associated with this Node
+*/
+Set<RedactionEntity> getEntities();
+/**
+* Returns all Pages this SemanticNode is associated with.
+*
+* @return Set of Pages this node appears on.
+*/
+Set<Page> getPages()
+/**
+* Checks if this node appears on the specified page number.
+*
+* @param pageNumber The page number to check.
+* @return True if this node is found on the specified page number, false otherwise.
+*/
+boolean isOnPage(int pageNumber)
+/**
+* Returns the closest Headline associated with this SemanticNode
+*
+* @return First Headline found.
+*/
+Headline getHeadline()
+/**
+* @return The SemanticNode representing the Parent in the DocumentTree
+* throws NotFoundException, when no parent is present
+*/
+SemanticNode getParent()
+/**
+* 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
+*/
+boolean hasEntitiesOfType(String 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
+*/
+boolean hasEntitiesOfAnyType(String... types)
+/**
+* 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
+*/
+boolean hasEntitiesOfAllTypes(String... types)
+/**
+* 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
+*/
+List<RedactionEntity> getEntitiesOfType(String type)
+/**
+* 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
+*/
+List<RedactionEntity> getEntitiesOfType(List<String> types)
+/**
+* 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
+*/
+List<RedactionEntity> getEntitiesOfType(String... types)
+/**
+* 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
+*/
+boolean containsString(String 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
+*/
+boolean containsAllStrings(String... strings)
+/**
+* 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
+*/
+boolean containsAnyString(String... strings)
+/**
+* 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
+*/
+boolean containsStringIgnoreCase(String string)
+/**
+* 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
+*/
+boolean containsAnyStringIgnoreCase(String... strings)
+/**
+* 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
+*/
+boolean containsAllStringsIgnoreCase(String... strings)
+/**
+* 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
+*/
+boolean matchesRegex(String 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
+*/
+boolean matchesRegexIgnoreCase(String regexPattern)
+/**
+* Streams all children located directly underneath this node in the DocumentTree.
+*
+* @return Stream of all children
+*/
+Stream<SemanticNode> streamChildren()
+/**
+* Streams all children located directly underneath this node in the DocumentTree of the provided type.
+*
+* @param nodeType the type of nodes to stream
+* @return Stream of all children of the provided type
+*/
+Stream<SemanticNode> streamChildrenOfType(NodeType nodeType)
+/**
+* Recursively streams all SemanticNodes located underneath this node in the DocumentTree in order.
+*
+* @return Stream of all SubNodes
+*/
+Stream<SemanticNode> streamAllSubNodes()
+/**
+* Recursively streams all SemanticNodes of a specified type located underneath this node in the DocumentTree in order.
+*
+* @param nodeType the type of nodes to be streamed
+* @return a Stream of all SubNodes of the specified type
+*/
+Stream<SemanticNode> streamAllSubNodesOfType(NodeType nodeType)
+/**
+* The Boundary is the start and end string offsets in the reading order of the document.
+*
+* @return Boundary of this Node's TextBlock
+*/
+Boundary getBoundary()
+/**
+ * The SectionIdentifier uses the numeric identifiers of Headlines to infer a tree structure.
+ * It implements functions such as sectionIdentifier.isChildOf(otherSectionIdentifier) and sectionIdentifier.isParentOf(otherSectionIdentifier)
+ *
+ * @return The SectionIdentifier from the first Headline.
+ */
+SectionIdentifier getSectionIdentifier()

drools-prompt/Table_doc

@@ -0,0 +1,77 @@
+/**
+* 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
+*/
+Stream<RedactionEntity> streamEntitiesWhereRowContainsStringsIgnoreCase(List<String> strings) 
+/**
+* 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
+*/
+boolean rowContainsStringsIgnoreCase(Integer row, List<String> strings) 
+/**
+* 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.
+*/
+Stream<RedactionEntity> streamEntitiesWhereRowHasHeaderAndValue(String header, String value) 
+/**
+* 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.
+*/
+Stream<RedactionEntity> streamEntitiesWhereRowHasHeaderAndAnyValue(String header, List<String> values) 
+/**
+* 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.
+*/
+Stream<RedactionEntity> streamEntitiesWhereRowContainsEntitiesOfType(List<String> types) 
+/**
+* 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.
+*/
+Stream<RedactionEntity> streamEntitiesWhereRowContainsNoEntitiesOfType(List<String> types) 
+/**
+* Streams all TableCells in this Table which have the provided header row-wise.
+*
+* @return Stream of all TableCells which have the provided header
+*/
+Stream<TableCell> streamTableCellsWithHeader(String 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
+*/
+boolean hasHeader(String header) 
+/**
+* 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
+*/
+boolean hasRowWithHeaderAndValue(String header, String value) 
+/**
+* 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 redactionEntity 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.
+*/
+List<RedactionEntity> getEntitiesOfTypeInSameRow(String type, RedactionEntity redactionEntity) 

drools-prompt/drools-prompt

@@ -0,0 +1,591 @@
+From now on, you are a Drools rule generator.
+
+You have a Document data structure written in Java with the following objects:
+
+- Section
+- Table
+- TableCell
+- Paragraph
+- Headline
+- Page
+- RedactionEntity
+- EntityCreationService
+
+The Section, Table, TableCell, Paragraph, and Headline implement a common interface called SemanticNode. SemanticNodes are arranged in a tree-like fashion, where any SemanticNode can have multiple SemanticNodes as children. The arrangement is as follows:
+- Tables only have TableCells as children.
+- TableCells may have any child, except TableCells.
+- Paragraphs and Headlines have no children.
+- Sections may have any child except TableCells, but if it contains Paragraphs as well as Tables, it is split into a Section with multiple Sections as children, where any child Section only contains either Tables or Paragraphs.
+   Further, if the first SemanticNode is a Headline it remains the first child in the Parent Section, before any subsections.
+
+The goal of the Software is to find pieces of Text that are relevant. Each piece of text is represented by a RedactionEntity.
+The main pieces of relevant text are Text we want to redact. For example, we want to redact all Authors of a dossier. Or all personally identifiable information, such as E-Mails and Telephone Numbers.
+RedactionEntities may also represent other pieces of text, such as published information, or certain species of vertebrates.
+The RedactionEntities are part of the document structure, such that they are referenced in each SemanticNode and Page, which contains it, and further, the RedactionEntity references each Page and SemanticNode it occurs in.
+So the same RedactionEntity occurs in the paragraph it is located, as well as all its parent Sections.
+
+Previous to the execution of rules, the Document structure is assembled and a text search is performed to create initial Entities of different types. They are then inserted into the document structure.
+Then the KieSession is created and each SemanticNode and Entity is inserted into its working memory.
+----------------------------------------------------------------
+The relevant functions for SemanticNode:
+/**
+* Returns the type of this node, such as NodeType.SECTION, NodeType.PARAGRAPH, etc.
+*
+* @return NodeType of this node
+*/
+NodeType getType();
+
+/**
+* Any Node maintains its own Set of Entities.
+* This Set contains all Entities whose boundary intersects the boundary of this node.
+* The Entities might overlap with the Entities in other Sets
+*
+* @return Set of all Entities associated with this Node
+*/
+Set<RedactionEntity> getEntities();
+
+/**
+* Returns all Pages this SemanticNode is associated with.
+*
+* @return Set of Pages this node appears on.
+*/
+Set<Page> getPages()
+
+/**
+* Checks if this node appears on the specified page number.
+*
+* @param pageNumber The page number to check.
+* @return True if this node is found on the specified page number, false otherwise.
+*/
+boolean onPage(int pageNumber)
+
+/**
+* For Sections it searches its children and returns the first Headline.
+* For Paragraphs, Tables, and TableCells it returns getHeadline() of getParent()
+* For Headline it returns itself and for Headers or Footers it returns an empty dummy Headline.
+*
+* @return First Headline found.
+*/
+Headline getHeadline()
+
+/**
+* @return The SemanticNode representing the Parent in the DocumentTree
+* When no parent is present, the Document is returned. And for the Document itself it throws an UnsupportedOperationException.
+*/
+SemanticNode getParent()
+
+/**
+* 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
+*/
+boolean hasEntitiesOfType(String 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
+*/
+boolean hasEntitiesOfAnyType(String... types)
+
+/**
+* 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
+*/
+boolean hasEntitiesOfAllTypes(String... types)
+
+/**
+* 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
+*/
+List<RedactionEntity> getEntitiesOfType(String type)
+
+/**
+* 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
+*/
+List<RedactionEntity> getEntitiesOfType(List<String> types)
+
+/**
+* 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
+*/
+List<RedactionEntity> getEntitiesOfType(String... types)
+
+/**
+* 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
+*/
+boolean containsString(String 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
+*/
+boolean containsAllStrings(String... strings)
+
+/**
+* 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
+*/
+boolean containsAnyString(String... strings)
+/**
+* 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
+*/
+boolean containsStringIgnoreCase(String string)
+
+/**
+* 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
+*/
+boolean containsAnyStringIgnoreCase(String... strings)
+
+/**
+* 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
+*/
+boolean containsAllStringsIgnoreCase(String... strings)
+
+/**
+* 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
+*/
+boolean matchesRegex(String 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
+*/
+boolean matchesRegexIgnoreCase(String regexPattern)
+
+/**
+* Streams all children located directly underneath this node in the DocumentTree.
+*
+* @return Stream of all children
+*/
+Stream<SemanticNode> streamChildren()
+
+/**
+* Streams all children located directly underneath this node in the DocumentTree of the provided type.
+*
+* @param nodeType the type of nodes to stream
+* @return Stream of all children of the provided type
+*/
+Stream<SemanticNode> streamChildrenOfType(NodeType nodeType)
+
+/**
+* Recursively streams all SemanticNodes located underneath this node in the DocumentTree in order.
+*
+* @return Stream of all SubNodes
+*/
+Stream<SemanticNode> streamAllSubNodes()
+
+/**
+* Recursively streams all SemanticNodes of a specified type located underneath this node in the DocumentTree in order.
+*
+* @param nodeType the type of nodes to be streamed
+* @return a Stream of all SubNodes of the specified type
+*/
+Stream<SemanticNode> streamAllSubNodesOfType(NodeType nodeType)
+
+/**
+* The Boundary is the start and end string offsets in the reading order of the document.
+*
+* @return Boundary of this Node's TextBlock
+*/
+Boundary getBoundary()
+
+/**
+ * The SectionIdentifier uses the numeric identifiers of Headlines to infer a tree structure.
+ * It implements functions such as sectionIdentifier.isChildOf(otherSectionIdentifier) and sectionIdentifier.isParentOf(otherSectionIdentifier)
+ *
+ * @return The SectionIdentifier from the first Headline.
+ */
+SectionIdentifier getSectionIdentifier()
+
+----------------------------------------------------------------
+The Table has the additional functions:
+/**
+* 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
+*/
+Stream<RedactionEntity> streamEntitiesWhereRowContainsStringsIgnoreCase(List<String> strings)
+
+/**
+* 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
+*/
+boolean rowContainsStringsIgnoreCase(Integer row, List<String> strings)
+
+/**
+* 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.
+*/
+Stream<RedactionEntity> streamEntitiesWhereRowHasHeaderAndValue(String header, String value)
+
+/**
+* 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.
+*/
+Stream<RedactionEntity> streamEntitiesWhereRowHasHeaderAndAnyValue(String header, List<String> values)
+
+/**
+* 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.
+*/
+Stream<RedactionEntity> streamEntitiesWhereRowContainsEntitiesOfType(List<String> types)
+
+/**
+* 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.
+*/
+Stream<RedactionEntity> streamEntitiesWhereRowContainsNoEntitiesOfType(List<String> types)
+
+/**
+* Streams all TableCells in this Table which have the provided header row-wise.
+*
+* @return Stream of all TableCells which have the provided header
+*/
+Stream<TableCell> streamTableCellsWithHeader(String 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
+*/
+boolean hasHeader(String header)
+
+/**
+* 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
+*/
+boolean hasRowWithHeaderAndValue(String header, String value)
+
+/**
+* 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 redactionEntity 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.
+*/
+List<RedactionEntity> getEntitiesOfTypeInSameRow(String type, RedactionEntity redactionEntity)
+----------------------------------------------------------------
+The Section has these additional Rules:
+/**
+* Determines whether this Section has any tables.
+*
+* @return {@code true} if there are tables, {@code false} otherwise
+*/
+boolean hasTables()
+----------------------------------------------------------------
+The Page Object has the following functions:
+/**
+* Retrieves the main body text block.
+* @return The text block representing the main body of the document.
+*/
+public TextBlock getMainBodyTextBlock()
+/**
+* @return All SemanticNodes that occur on the page, except Header and Footer
+*/
+public List<SemanticNode> getMainBody()
+/**
+* Gets all Entities located on the page
+* @return Set of all Entities associated with this Page
+*/
+Set<RedactionEntity> getEntities();
+/**
+* Returns the Page Number
+*
+* @return The number of this page
+*/
+Integer getPageNumber();
+----------------------------------------------------------------
+
+----------------------------------------------------------------
+The RedactionEntity has the following properties:
+/**
+* A boundary has a start and end property accessible by start() and end() respectively. It marks the start and end offset in String offsets.
+*/
+Boundary boundary
+/**
+* The type of an Entity identifies groups of Entities. Examples for Entites we want to find are "CBI_author" for authors, "CBI_address" for addresses or "PII" for personally identifiable information.
+* Other types include helper types, which interact with the main Entities, for example "published_information" or "vertebrate". These Entities are used to modify the main Entities, if they occur in the same Section.
+* A typical example would be to ignore Entities of type "CBI_author", if they occur in the same Section as "published_information" entities.
+*/
+String type
+/**
+* The EntityType can be one of four different values: ENTITY, RECOMMENDATION, FALSE_POSITIVE, FALSE_RECOMMENDATION.
+* If an ENTITY is overlapped by a FALSE_POSITIVE, the ENTITY is removed. If a RECOMMENDATION is overlapped by either an ENTITY or FALSE_RECOMMENDATION, it is removed.
+*/
+EntityType entityType
+/**
+* The text the Entity represents.
+*/
+String value
+/**
+* Up to three words after the Entity in the text.
+*/
+String textAfter
+/**
+* Up to three words before the Entity in the text.
+*/
+String textBefore
+/**
+* All pages whose TextBlock intersects the boundary of this entity. Is always equal to the Pages which have this RedactionEntity in their EntitySet.
+*/
+Set<Page> pages
+/**
+* All SemanticNodes whose TextBlock intersects the boundary of this entity. Is always equal to the SemanticNodes which have this RedactionEntity in their EntitySet.
+*/
+List<SemanticNode> intersectingNodes
+/**
+* The SemanticNode which is the deepest in the Tree structure and whose TextBlock fully contains the boundary of this Node.
+*/
+SemanticNode deepestFullyContainingNode
+
+The RedactionEntity also has the following methods:
+/**
+* Sets the Entity to applied, this is the default.
+* @param ruleIdentifier Should always be equal to the ruleIdentifier in the Rule name
+* @param reason Should describe the intention of the rule in a few words
+* @param legalBasis Is dependent on the rule, if none is known the default is "n-a", can't be null
+*/
+void apply(String ruleIdentifier, String reason, String legalBasis)
+/**
+* Same as apply, but legalBasis can be null.
+*/
+void force(String ruleIdentifier, String reason, String legalBasis)
+/**
+* Sets the Entity to not applied.
+* @param ruleIdentifier Should always be equal to the ruleIdentifier in the Rule name
+* @param reason Should describe the intention of the rule in a few words
+* @param legalBasis Is dependent on the rule, if none is known the default is "n-a", can't be null
+*/
+void skip(String ruleIdentifier, String reason, String legalBasis)
+/**
+* Sets the Entity to ignored, is preferred to remove in most cases.
+* @param ruleIdentifier Should always be equal to the ruleIdentifier in the Rule name
+* @param reason Should describe the intention of the rule in a few words
+* @param legalBasis Is dependent on the rule, if none is known the default is "n-a", can't be null
+*/
+void ignore(String ruleIdentifier, String reason, String legalBasis)
+/**
+* Removes the entity entirely, also removes it from all EntitySets and sets intersectingNodes and deepestFullyContainingNode to null.
+* Should only be used in a few cases!
+* @param ruleIdentifier Should always be equal to the ruleIdentifier in the Rule name
+* @param reason Should describe the intention of the rule in a few words
+* @param legalBasis Is dependent on the rule, if none is known the default is "n-a", can't be null
+*/
+void remove(String ruleIdentifier, String reason, String legalBasis)
+----------------------------------------------------------------
+The EntityCreationService offers the following functions:
+/**
+* Searches the provided SemanticNode for the keyword and creates an Entity for each occurrence.
+* @param keyword the string to search for
+* @param type The type of the RedactionEntity to be created
+* @param entityType The EntityType of the RedactionEntity to be created
+* @param node The SemanticNode to search in
+* @return A Stream of RedactionEntities with the keyword as value, the type as type and the provided EntityType
+*/
+public Stream<RedactionEntity> byString(String keyword, String type, EntityType entityType, SemanticNode node)
+/**
+* Same as byString, but case insensitive.
+*/
+public Stream<RedactionEntity> byStringIgnoreCase(String keyword, String type, EntityType entityType, SemanticNode node)
+/**
+* Searches the provided SemanticNode with the regexPattern and creates a new RedactionEntity with the provided group for each occurrence.
+* @param regexPattern The regexPattern
+* @param type The type of the RedactionEntity to be created
+* @param entityType The EntityType of the RedactionEntity to be created
+* @param group the regexPattern group, that should be the entity
+* @param node The SemanticNode to search in
+* @return A Stream of RedactionEntities with the keyword as value, the type as type and the provided EntityType
+*/
+public Stream<RedactionEntity> byRegex(String regexPattern, String type, EntityType entityType, int group, SemanticNode node)
+/**
+* Same as byRegex, but case insensitive.
+*/
+public Stream<RedactionEntity> byRegexIgnoreCase(String regexPattern, String type, EntityType entityType, int group, SemanticNode node)
+/**
+* Same as byRegex, but can handle patterns with linebreaks.
+*/
+public Stream<RedactionEntity> byRegexWithLineBreaksIgnoreCase(String regexPattern, String type, EntityType entityType, int group, SemanticNode node)
+/**
+* Same as byRegexWithLineBreaks, but case insensitive.
+*/
+public Stream<RedactionEntity> byRegexWithLineBreaksIgnoreCase(String regexPattern, String type, EntityType entityType, int group, SemanticNode node)
+/**
+* Finds the provided string, and creates a new RedactionEntity from the text after until the end of the line it is found in.
+* @param string The keyword to search for
+* @param type The type of the RedactionEntity to be created
+* @param entityType The EntityType of the RedactionEntity to be created
+* @param node The SemanticNode to search in
+* @return A Stream of RedactionEntities with the keyword as value, the type as type and the provided EntityType
+*/
+public Stream<RedactionEntity> lineAfterString(String string, String type, EntityType entityType, SemanticNode node)
+/**
+* Same as lineAfterString, but with multiple keywords
+*/
+public Stream<RedactionEntity> lineAfterStrings(List<String> strings, String type, EntityType entityType, SemanticNode node)
+/**
+* Finds the provided string in a TableCell, and creates a new RedactionEntity in the same line but adjacent table cells to the right.
+* @param string The keyword to search for
+* @param type The type of the RedactionEntity to be created
+* @param entityType The EntityType of the RedactionEntity to be created
+* @param table The TableNode to search in
+* @return A Stream of RedactionEntities with the keyword as value, the type as type and the provided EntityType
+*/
+public Stream<RedactionEntity> lineAfterStringAcrossColumns(String string, String type, EntityType entityType, TableNode table)
+/**
+* Creates a redaction entity based on the given boundary, type, entity type, and semantic node.
+*
+* @param boundary   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 where the boundary is.
+* @return An Optional containing the new redaction entity.
+*/
+public Optional<RedactionEntity> byBoundary(Boundary boundary, String type, EntityType entityType, SemanticNode node)
+/**
+* Creates new RedactionEntities between the provided start and stop boundaries. The start and stop boundaries are excluded.
+* If any boundaries of the new RedactionEntities overlap, only the shortest boundary will be used.
+* @param startBoundaries List of start boundaries
+* @param stopBoundaries List of stop boundaries
+* @param type       The type of the redaction entity.
+* @param entityType The entity type of the redaction entity.
+* @param node       The semantic node where the boundaries are.
+* @return A Stream of new RedactionEntities between the start and stop boundaries
+*/
+public Stream<RedactionEntity> betweenBoundaries(List<Boundary> startBoundaries, List<Boundary> stopBoundaries, String type, EntityType entityType, SemanticNode node)
+/**
+* Same as betweenBoundaries, but it creates the start and stop boundaries by performing a text search on the provided SemanticNode.
+*/
+public Stream<RedactionEntity> betweenStrings(String start, String stop, String type, EntityType entityType, SemanticNode node)
+/**
+* Same as betweenStrings, but case insensitive.
+*/
+public Stream<RedactionEntity> betweenStringsIgnoreCase(String start, String stop, String type, EntityType entityType, SemanticNode node)
+/**
+* These 6 functions work the same as betweenStrings, but they also include the start and/or stop strings or are case insensitive, depending on their name.
+*/
+public Stream<RedactionEntity> betweenStringsIncludeStart(String start, String stop, String type, EntityType entityType, SemanticNode node)
+public Stream<RedactionEntity> betweenStringsIncludeStartIgnoreCase(String start, String stop, String type, EntityType entityType, SemanticNode node)
+public Stream<RedactionEntity> betweenStringsIncludeEnd(String start, String stop, String type, EntityType entityType, SemanticNode node)
+public Stream<RedactionEntity> betweenStringsIncludeEndIgnoreCase(String start, String stop, String type, EntityType entityType, SemanticNode node)
+public Stream<RedactionEntity> betweenStringsIncludeStartAndEnd(String start, String stop, String type, EntityType entityType, SemanticNode node)
+public Stream<RedactionEntity> betweenStringsIncludeStartAndEndIgnoreCase(String start, String stop, String type, EntityType entityType, SemanticNode node)
+/**
+* Same as betweenBoundaries, but it creates the start and stop boundaries by performing a regex search on the provided SemanticNode.
+*/
+public Stream<RedactionEntity> betweenRegexes(String regexStart, String regexStop, String type, EntityType entityType, SemanticNode node)
+/**
+* Same as betweenRegexes, but case insensitive.
+*/
+public Stream<RedactionEntity> betweenRegexesIgnoreCase(String regexStart, String regexStop, String type, EntityType entityType, SemanticNode node)
+/**
+* Creates a new RedactionEntity which has the same boundary as the provided SemanticNode.
+* @param node The SemanticNode to create a new RedactionEntity from.
+* @param type       The type of the redaction entity.
+* @param entityType The entity type of the redaction entity.
+* @return An optional RedactionEntity. Is empty, if the provided SemanticNode is empty.
+*/
+public Optional<RedactionEntity> bySemanticNode(SemanticNode node, String type, EntityType entityType)
+/**
+* Same as bySemanticNode, but ignores the SemanticNode, if its not a Paragraph and all its child SemanticNodes, that are not Paragraphs.
+*/
+public Stream<RedactionEntity> bySemanticNodeParagraphsOnly(SemanticNode node, String type, EntityType entityType)
+/**
+* Searches the provided SemanticNode for the provided string, and creates a new RedactionEntity, from the end of the first occurrence of the string until the end of the SemanticNode.
+* @param string The string to search for
+* @param type       The type of the redaction entity.
+* @param entityType The entity type of the redaction entity.
+* @param node The SemanticNode to use and search in
+* @return An optional RedactionEntity, is empty, if the SemanticNode is empty, or the string isn't found in the SemanticNode.
+*/
+public Optional<RedactionEntity> semanticNodeAfterString(String string, String type, EntityType entityType, SemanticNode node)
+----------------------------------------------------------------
+Rules may be grouped into two categories.
+The first category changes existing RedactionEntities, and the second creates new RedactionEntities.
+
+There are two different types of rules, one you create new Entities and in the other you change or remove existing Entities.
+An Entity is any piece of text, uniquely identified in the Document by its Boundary, its Type and its EntityType. The Boundary consists of a start and stop index in the text of the document.
+The Type is a String like "PII", which stands for
+The goal is to find entities that fulfill certain conditions. Each SemanticNode has its own set of entities, but these sets may have intersections.
+For example, a Section contains all the entities in any of its children. Additionally, if an entity overlaps two SemanticNodes, both paragraphs have this entity in their sets.
+
+To generate Drools rules for the scenario of changing or updating Entities, consider the following information:
+
+1. Conditions: Specify the conditions that must be met for an entity to be selected. For example:
+- The entity has a specific attribute value.
+- The entity is within a certain range of values.
+- The entity satisfies a complex combination of conditions.
+
+2. Actions: Define the actions to be performed when an entity fulfills the conditions. This could include:
+- Adding the entity to a result set.
+- Modifying the entity's attributes.
+- Triggering some other behavior or logic.
+
+3. Rule Structure: Determine the structure of the Drools rules. This typically consists of:
+- Rule names: Choose meaningful names for your rules.
+- Rule attributes: Set the salience (priority) of rules if necessary.
+- Conditions: Define the conditions based on the requirements.
+- Actions: Specify the actions to be performed when the conditions are met.
+
+Remember to provide specific examples, use case scenarios, and any additional requirements you have for the Drools rules.
+
+Please provide any specific conditions, actions, or examples that you would like to be incorporated into the Drools rules.

gradle.properties.kts

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

pom.xml

@@ -1,20 +0,0 @@
-<?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>3.0-SNAPSHOT</version>
-
-
-    <packaging>pom</packaging>
-
-    <modules>
-        <module>redaction-service-v1</module>
-        <module>redaction-service-image-v1</module>
-    </modules>
-
-</project>

redaction-service-image-v1/pom.xml

@@ -1,98 +0,0 @@
-<?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.knecon.fforesight</groupId>
-        <artifactId>platform-docker-dependency</artifactId>
-        <version>0.1.0</version>
-        <relativePath/>
-    </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

@@ -1,9 +0,0 @@
-FROM red/redaction-service-base-v1:2.0.0
-
-ARG PLATFORM_JAR
-
-ENV PLATFORM_JAR ${PLATFORM_JAR}
-
-ENV USES_ELASTICSEARCH false
-
-COPY ["${PLATFORM_JAR}", "/"]

redaction-service-v1/pom.xml

@@ -1,93 +0,0 @@
-<?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>1.13.0</version>
-        <relativePath/>
-    </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>2.0.24</pdfbox.version>
-        <dsljson.version>1.9.9</dsljson.version>
-    </properties>
-
-
-    <dependencyManagement>
-        <dependencies>
-            <dependency>
-                <groupId>com.iqser.red</groupId>
-                <artifactId>platform-commons-dependency</artifactId>
-                <version>1.20.0</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>
-
-    <build>
-        <pluginManagement>
-            <plugins>
-                <plugin>
-                    <groupId>org.sonarsource.scanner.maven</groupId>
-                    <artifactId>sonar-maven-plugin</artifactId>
-                </plugin>
-                <plugin>
-                    <groupId>org.owasp</groupId>
-                    <artifactId>dependency-check-maven</artifactId>
-                    <configuration>
-                        <format>ALL</format>
-                    </configuration>
-                </plugin>
-                <plugin>
-                    <groupId>org.jacoco</groupId>
-                    <artifactId>jacoco-maven-plugin</artifactId>
-                    <version>0.8.8</version>
-                    <configuration>
-                        <excludes>
-                            <exclude>org/drools/**/*</exclude>
-                        </excludes>
-                    </configuration>
-                    <executions>
-                        <execution>
-                            <id>prepare-agent</id>
-                            <goals>
-                                <goal>prepare-agent</goal>
-                            </goals>
-                        </execution>
-                        <execution>
-                            <id>report</id>
-                            <goals>
-                                <goal>report</goal>
-                            </goals>
-                        </execution>
-                    </executions>
-                </plugin>
-            </plugins>
-        </pluginManagement>
-    </build>
-</project>

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

@@ -0,0 +1,14 @@
+
+plugins {
+    id("com.iqser.red.service.java-conventions")
+    id("io.freefair.lombok") version "8.1.0"
+}
+
+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")
+}
+
+

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

@@ -1,61 +0,0 @@
-<?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>
-
-    <properties>
-        <persistence-service.version>1.299.0</persistence-service.version>
-    </properties>
-
-    <dependencies>
-
-        <!-- https://mvnrepository.com/artifact/com.dslplatform/dsl-json-java8 -->
-        <dependency>
-            <groupId>com.dslplatform</groupId>
-            <artifactId>dsl-json-java8</artifactId>
-            <version>${dsljson.version}</version>
-        </dependency>
-
-        <dependency>
-            <groupId>org.springframework</groupId>
-            <artifactId>spring-web</artifactId>
-            <optional>true</optional>
-        </dependency>
-
-        <dependency>
-            <groupId>com.iqser.red.service</groupId>
-            <artifactId>persistence-service-api-v1</artifactId>
-            <version>${persistence-service.version}</version>
-            <exclusions>
-                <exclusion>
-                    <groupId>com.iqser.red.service</groupId>
-                    <artifactId>redaction-service-api-v1</artifactId>
-                </exclusion>
-            </exclusions>
-        </dependency>
-
-    </dependencies>
-
-    <build>
-        <plugins>
-            <plugin>
-                <groupId>org.apache.maven.plugins</groupId>
-                <artifactId>maven-compiler-plugin</artifactId>
-                <configuration>
-                    <annotationProcessors>
-                        <annotationProcessor>lombok.launch.AnnotationProcessorHider$AnnotationProcessor</annotationProcessor>
-                        <annotationProcessor>com.dslplatform.json.processor.CompiledJsonAnnotationProcessor</annotationProcessor>
-                    </annotationProcessors>
-                </configuration>
-            </plugin>
-        </plugins>
-    </build>
-</project>

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

@@ -1,40 +0,0 @@
-package com.iqser.red.service.redaction.v1.model;
-
-import com.iqser.red.service.persistence.service.v1.api.model.annotations.ManualRedactions;
-
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.Data;
-import lombok.NoArgsConstructor;
-
-import java.time.OffsetDateTime;
-import java.util.ArrayList;
-import java.util.HashSet;
-import java.util.List;
-import java.util.Set;
-
-@Data
-@Builder
-@NoArgsConstructor
-@AllArgsConstructor
-public class AnalyzeRequest {
-
-    private MessageType messageType;
-
-    private String dossierId;
-    private String fileId;
-    private String dossierTemplateId;
-    private ManualRedactions manualRedactions;
-    private OffsetDateTime lastProcessed;
-    private int analysisNumber;
-
-    @Builder.Default
-    private Set<Integer> excludedPages = new HashSet<>();
-    @Builder.Default
-    private Set<Integer> sectionsToReanalyse = new HashSet<>();
-
-    @Builder.Default
-    private List<FileAttribute> fileAttributes = new ArrayList<>();
-
-}
-

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

@@ -1,40 +0,0 @@
-package com.iqser.red.service.redaction.v1.model;
-
-import java.util.Set;
-
-import com.iqser.red.service.persistence.service.v1.api.model.annotations.ManualRedactions;
-
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.Data;
-import lombok.NoArgsConstructor;
-
-@Data
-@Builder
-@NoArgsConstructor
-@AllArgsConstructor
-public class AnalyzeResult {
-
-    private MessageType messageType;
-
-    private String dossierId;
-    private String fileId;
-    private long duration;
-    private int numberOfPages;
-    private boolean hasUpdates;
-    private long dictionaryVersion;
-    private long dossierDictionaryVersion;
-    private long rulesVersion;
-    private long legalBasisVersion;
-
-    private boolean wasReanalyzed;
-
-    private int analysisVersion;
-    private int analysisNumber;
-
-    private ManualRedactions manualRedactions;
-
-    private Set<FileAttribute> addedFileAttributes;
-
-}
-

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

@@ -1,16 +0,0 @@
-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/Change.java

@@ -1,20 +0,0 @@
-package com.iqser.red.service.redaction.v1.model;
-
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.Data;
-import lombok.NoArgsConstructor;
-
-import java.time.OffsetDateTime;
-
-@Data
-@Builder
-@AllArgsConstructor
-@NoArgsConstructor
-public class Change {
-
-    private int analysisNumber;
-    private ChangeType type;
-    private OffsetDateTime dateTime;
-
-}

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

@@ -1,7 +0,0 @@
-package com.iqser.red.service.redaction.v1.model;
-
-public enum ChangeType {
-    ADDED,
-    REMOVED,
-    CHANGED
-}

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

@@ -1,7 +0,0 @@
-package com.iqser.red.service.redaction.v1.model;
-
-public enum Engine {
-    DICTIONARY,
-    NER,
-    RULE
-}

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

@@ -1,19 +0,0 @@
-package com.iqser.red.service.redaction.v1.model;
-
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.Data;
-import lombok.NoArgsConstructor;
-
-@Data
-@Builder
-@NoArgsConstructor
-@AllArgsConstructor
-public class FileAttribute {
-
-    private String id;
-    private String label;
-    private String placeholder;
-    private String value;
-
-}

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

@@ -1,22 +0,0 @@
-package com.iqser.red.service.redaction.v1.model;
-
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.Data;
-import lombok.NoArgsConstructor;
-
-import java.util.ArrayList;
-import java.util.List;
-
-@Data
-@Builder
-@NoArgsConstructor
-@AllArgsConstructor
-public class ImportedRedaction {
-
-    private String id;
-
-    @Builder.Default
-    private List<Rectangle> positions = new ArrayList<>();
-
-}

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

@@ -1,24 +0,0 @@
-package com.iqser.red.service.redaction.v1.model;
-
-import com.dslplatform.json.CompiledJson;
-
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.Data;
-import lombok.NoArgsConstructor;
-
-import java.util.HashMap;
-import java.util.List;
-import java.util.Map;
-
-@Data
-@Builder
-@CompiledJson
-@NoArgsConstructor
-@AllArgsConstructor
-public class ImportedRedactions {
-
-    @Builder.Default
-    private Map<Integer, List<ImportedRedaction>> importedRedactions = new HashMap<>();
-
-}

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

@@ -1,59 +0,0 @@
-package com.iqser.red.service.redaction.v1.model;
-
-import com.iqser.red.service.persistence.service.v1.api.model.annotations.AnnotationStatus;
-import com.iqser.red.service.persistence.service.v1.api.model.annotations.entitymapped.BaseAnnotation;
-
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.Data;
-import lombok.NoArgsConstructor;
-
-import java.time.OffsetDateTime;
-import java.util.HashMap;
-import java.util.Map;
-
-@Data
-@AllArgsConstructor
-@NoArgsConstructor
-@Builder
-public class ManualChange {
-
-    private AnnotationStatus annotationStatus;
-    private ManualRedactionType manualRedactionType;
-    private OffsetDateTime processedDate;
-    private OffsetDateTime requestedDate;
-    private String userId;
-    private Map<String, String> propertyChanges = new HashMap<>();
-
-
-    public static ManualChange from(BaseAnnotation baseAnnotation) {
-
-        ManualChange manualChange = new ManualChange();
-        manualChange.annotationStatus = baseAnnotation.getStatus();
-        manualChange.processedDate = baseAnnotation.getProcessedDate();
-        manualChange.requestedDate = baseAnnotation.getRequestDate();
-        manualChange.userId = baseAnnotation.getUser();
-        return manualChange;
-    }
-
-
-    public boolean isProcessed() {
-
-        return processedDate != null;
-    }
-
-
-    public ManualChange withManualRedactionType(ManualRedactionType manualRedactionType) {
-
-        this.manualRedactionType = manualRedactionType;
-        return this;
-    }
-
-
-    public ManualChange withChange(String property, String value) {
-
-        this.propertyChanges.put(property, value);
-        return this;
-    }
-
-}

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

@@ -1,13 +0,0 @@
-package com.iqser.red.service.redaction.v1.model;
-
-public enum ManualRedactionType {
-    ADD_LOCALLY,
-    ADD_TO_DICTIONARY,
-    REMOVE_LOCALLY,
-    REMOVE_FROM_DICTIONARY,
-    FORCE_REDACT,
-    FORCE_HINT,
-    RECATEGORIZE,
-    LEGAL_BASIS_CHANGE,
-    RESIZE
-}

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

@@ -1,10 +0,0 @@
-package com.iqser.red.service.redaction.v1.model;
-
-public enum MessageType {
-
-    ANALYSE,
-    REANALYSE,
-    STRUCTURE_ANALYSE,
-    SURROUNDING_TEXT
-
-}

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

@@ -1,15 +0,0 @@
-package com.iqser.red.service.redaction.v1.model;
-
-import lombok.AllArgsConstructor;
-import lombok.Data;
-import lombok.NoArgsConstructor;
-
-@Data
-@AllArgsConstructor
-@NoArgsConstructor
-public class Point {
-
-    private float x;
-    private float y;
-
-}

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

@@ -1,16 +0,0 @@
-package com.iqser.red.service.redaction.v1.model;
-
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.Data;
-import lombok.NoArgsConstructor;
-
-@Data
-@Builder
-@NoArgsConstructor
-@AllArgsConstructor
-public class ReanalyzeResult {
-
-    private RedactionLog redactionLog;
-
-}

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

@@ -1,18 +0,0 @@
-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

@@ -1,37 +0,0 @@
-package com.iqser.red.service.redaction.v1.model;
-
-import com.dslplatform.json.CompiledJson;
-
-import lombok.AllArgsConstructor;
-import lombok.Data;
-import lombok.NoArgsConstructor;
-
-import java.util.ArrayList;
-import java.util.List;
-
-@Data
-@CompiledJson
-@AllArgsConstructor
-@NoArgsConstructor
-public class RedactionLog {
-
-    /**
-     * Version 0 Redaction Logs have manual redactions merged inside them
-     * Version 1 Redaction Logs only contain system ( rule/dictionary ) redactions. Manual Redactions are merged in at runtime.
-     */
-    private long analysisVersion;
-
-    /**
-     * Which analysis created this redactionLog.
-     */
-    private int analysisNumber;
-
-    private List<RedactionLogEntry> redactionLogEntry = new ArrayList<>();
-    private List<RedactionLogLegalBasis> legalBasis = new ArrayList<>();
-
-    private long dictionaryVersion = -1;
-    private long dossierDictionaryVersion = -1;
-    private long rulesVersion = -1;
-    private long legalBasisVersion = -1;
-
-}

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

@@ -1,17 +0,0 @@
-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 RedactionLogChanges {
-
-    private RedactionLog redactionLog;
-    private boolean hasChanges;
-
-}

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

@@ -1,22 +0,0 @@
-package com.iqser.red.service.redaction.v1.model;
-
-import lombok.AllArgsConstructor;
-import lombok.Data;
-import lombok.NoArgsConstructor;
-
-import java.time.OffsetDateTime;
-
-@Data
-@NoArgsConstructor
-@AllArgsConstructor
-public class RedactionLogComment {
-
-    private long id;
-    private String user;
-    private String text;
-    private String annotationId;
-    private String fileId;
-    private OffsetDateTime date;
-    private OffsetDateTime softDeletedTime;
-
-}

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

@@ -1,96 +0,0 @@
-package com.iqser.red.service.redaction.v1.model;
-
-import com.iqser.red.service.persistence.service.v1.api.model.annotations.AnnotationStatus;
-
-import lombok.*;
-
-import java.util.*;
-
-@Data
-@Builder
-@NoArgsConstructor
-@AllArgsConstructor
-@EqualsAndHashCode
-public class RedactionLogEntry {
-
-    private String id;
-    private String type;
-    private String value;
-    private String reason;
-    private int matchedRule;
-    private boolean rectangle;
-    private String legalBasis;
-
-    private boolean imported;
-
-    private boolean redacted;
-    private boolean isHint;
-    private boolean isRecommendation;
-    private boolean isFalsePositive;
-
-    private String section;
-    private float[] color;
-
-    @Builder.Default
-    private List<Rectangle> positions = new ArrayList<>();
-    private int sectionNumber;
-
-    private String textBefore;
-    private String textAfter;
-
-    @Builder.Default
-    private List<RedactionLogComment> comments = new ArrayList<>();
-
-    private int startOffset;
-    private int endOffset;
-
-    private boolean isImage;
-    private boolean imageHasTransparency;
-
-    private boolean isDictionaryEntry;
-    private boolean isDossierDictionaryEntry;
-
-    private boolean excluded;
-
-    private String sourceId;
-
-    @EqualsAndHashCode.Exclude
-    @Builder.Default
-    private List<Change> changes = new ArrayList<>();
-
-    @EqualsAndHashCode.Exclude
-    @Builder.Default
-    private List<ManualChange> manualChanges = new ArrayList<>();
-
-    private Set<Engine> engines = new HashSet<>();
-
-    private Set<String> reference = new HashSet<>();
-
-    @Builder.Default
-    private Set<String> importedRedactionIntersections = new HashSet<>();
-
-
-    public boolean lastChangeIsRemoved() {
-
-        return last(changes).map(c -> c.getType() == ChangeType.REMOVED).orElse(false);
-    }
-
-
-    public boolean isLocalManualRedaction() {
-
-        return manualChanges.stream().anyMatch(mc -> mc.getManualRedactionType() == ManualRedactionType.ADD_LOCALLY && mc.getAnnotationStatus() == AnnotationStatus.APPROVED);
-    }
-
-
-    public boolean isManuallyRemoved() {
-
-        return manualChanges.stream().anyMatch(mc -> mc.getManualRedactionType() == ManualRedactionType.REMOVE_LOCALLY && mc.getAnnotationStatus() == AnnotationStatus.APPROVED);
-    }
-
-
-    private <T> Optional<T> last(List<T> list) {
-
-        return list.isEmpty() ? Optional.empty() : Optional.of(list.get(list.size() - 1));
-    }
-
-}

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

@@ -1,16 +0,0 @@
-package com.iqser.red.service.redaction.v1.model;
-
-import lombok.AllArgsConstructor;
-import lombok.Data;
-import lombok.NoArgsConstructor;
-
-@Data
-@NoArgsConstructor
-@AllArgsConstructor
-public class RedactionLogLegalBasis {
-
-    private String name;
-    private String description;
-    private String reason;
-
-}

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

@@ -1,34 +0,0 @@
-package com.iqser.red.service.redaction.v1.model;
-
-import com.iqser.red.service.persistence.service.v1.api.model.annotations.ManualRedactions;
-import com.iqser.red.service.persistence.service.v1.api.model.dossiertemplate.configuration.Colors;
-import com.iqser.red.service.persistence.service.v1.api.model.dossiertemplate.type.Type;
-
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.Data;
-import lombok.NoArgsConstructor;
-
-import java.util.HashSet;
-import java.util.List;
-import java.util.Set;
-
-@Data
-@Builder
-@NoArgsConstructor
-@AllArgsConstructor
-public class RedactionRequest {
-
-    private String dossierId;
-    private String fileId;
-    private String dossierTemplateId;
-    private ManualRedactions manualRedactions;
-    @Builder.Default
-    private Set<Integer> excludedPages = new HashSet<>();
-
-    private Colors colors;
-    private List<Type> types;
-
-    private boolean includeFalsePositives;
-
-}

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

@@ -1,17 +0,0 @@
-package com.iqser.red.service.redaction.v1.model;
-
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.Data;
-import lombok.NoArgsConstructor;
-
-@Data
-@Builder
-@NoArgsConstructor
-@AllArgsConstructor
-public class RedactionResult {
-
-    private byte[] document;
-    private int numberOfPages;
-
-}

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

@@ -1,34 +0,0 @@
-package com.iqser.red.service.redaction.v1.model;
-
-import lombok.AllArgsConstructor;
-import lombok.Data;
-import lombok.NoArgsConstructor;
-
-@Data
-@NoArgsConstructor
-@AllArgsConstructor
-public class SectionArea {
-
-    private Point topLeft;
-    private float width;
-    private float height;
-    private int page;
-    private String header;
-
-
-    public boolean contains(Rectangle other) {
-
-        return page == other.getPage() && this.topLeft.getX() <= other.getTopLeft().getX() && this.topLeft.getX() + this.getWidth() >= other.getTopLeft()
-                .getX() + other.getWidth() && this.getTopLeft().getY() <= other.getTopLeft().getY() && this.getTopLeft().getY() + this.getHeight() >= other.getTopLeft()
-                .getY() + other.getHeight();
-    }
-
-
-    // TODO we should only use one rectangle class.
-    public boolean contains(com.iqser.red.service.persistence.service.v1.api.model.annotations.Rectangle other) {
-
-        return page == other.getPage() && this.topLeft.getX() <= other.getTopLeftX() && this.topLeft.getX() + this.getWidth() >= other.getTopLeftX() + other.getWidth() && this.getTopLeft()
-                .getY() <= other.getTopLeftY() && this.getTopLeft().getY() + this.getHeight() >= other.getTopLeftY() + other.getHeight();
-    }
-
-}

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

@@ -1,33 +0,0 @@
-package com.iqser.red.service.redaction.v1.model;
-
-import com.dslplatform.json.CompiledJson;
-
-import lombok.AllArgsConstructor;
-import lombok.Data;
-import lombok.NoArgsConstructor;
-
-import java.util.*;
-
-@Data
-@CompiledJson
-@AllArgsConstructor
-@NoArgsConstructor
-public class SectionGrid {
-
-    private Map<Integer, List<SectionRectangle>> rectanglesPerPage = new HashMap<>();
-
-    private List<SectionGridSection> sections = new ArrayList<>();
-
-    @Data
-    @NoArgsConstructor
-    @AllArgsConstructor
-    public static class SectionGridSection {
-
-        private int sectionNumber;
-        private String headline;
-        private Set<Integer> pages;
-        private List<SectionArea> sectionAreas;
-
-    }
-
-}

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

@@ -1,22 +0,0 @@
-package com.iqser.red.service.redaction.v1.model;
-
-import lombok.AllArgsConstructor;
-import lombok.Data;
-import lombok.NoArgsConstructor;
-
-import java.util.List;
-
-@Data
-@AllArgsConstructor
-@NoArgsConstructor
-public class SectionRectangle {
-
-    private Point topLeft;
-    private float width;
-    private float height;
-    private int part;
-    private int numberOfParts;
-
-    private List<CellRectangle> tableCells;
-
-}

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

@@ -1,38 +1,12 @@
 package com.iqser.red.service.redaction.v1.resources;
 
-import com.iqser.red.service.persistence.service.v1.api.model.annotations.ManualRedactions;
-import com.iqser.red.service.redaction.v1.model.RedactionLog;
-import com.iqser.red.service.redaction.v1.model.RedactionRequest;
-import com.iqser.red.service.redaction.v1.model.RedactionResult;
-
 import org.springframework.http.MediaType;
-import org.springframework.web.bind.annotation.PathVariable;
 import org.springframework.web.bind.annotation.PostMapping;
 import org.springframework.web.bind.annotation.RequestBody;
 
 public interface RedactionResource {
 
-    @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/test", consumes = MediaType.APPLICATION_JSON_VALUE)
     void testRules(@RequestBody String rules);
 
-
-    @PostMapping(value = "/redaction-log/preview", consumes = MediaType.APPLICATION_JSON_VALUE)
-    RedactionLog getRedactionLog(@RequestBody RedactionRequest redactionRequest);
-
-
-    @PostMapping(value = "/manual/surrounding-text/{dossierId}/{fileId}", consumes = MediaType.APPLICATION_JSON_VALUE, produces = MediaType.APPLICATION_JSON_VALUE)
-    ManualRedactions addSurroundingText(@PathVariable("dossierId") String dossierId, @PathVariable("fileId") String fileId, @RequestBody ManualRedactions manualRedactions);
-
 }

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

@@ -0,0 +1,90 @@
+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 "1.1.2"
+    id("org.sonarqube") version "4.3.0.3225"
+    id("io.freefair.lombok") version "8.1.0"
+}
+
+description = "redaction-service-server-v1"
+
+
+val layoutParserVersion = "0.23.0"
+val jacksonVersion = "2.15.2"
+val droolsVersion = "8.42.0.Final"
+val pdfBoxVersion = "3.0.0-alpha2"
+
+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-v1:2.119.0") { exclude(group = "org.springframework.boot") }
+    implementation("com.knecon.fforesight:layoutparser-service-internal-api:${layoutParserVersion}")
+
+    implementation("com.iqser.red.commons:spring-commons:2.6.0")
+    implementation("com.iqser.red.commons:metric-commons:2.3.0")
+
+    implementation("com.iqser.red.commons:dictionary-merge-commons:1.5.0")
+    implementation("com.iqser.red.commons:storage-commons:2.24.0")
+    implementation("com.knecon.fforesight:tenant-commons:0.10.0")
+
+    implementation("com.fasterxml.jackson.module:jackson-module-afterburner:${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") {
+    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

@@ -1,199 +0,0 @@
-<?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>
-
-    <properties>
-        <drools.version>7.73.0.Final</drools.version>
-        <kie.version>7.73.0.Final</kie.version>
-        <locationtech.version>1.18.2</locationtech.version>
-        <javaassist.version>3.28.0-GA</javaassist.version>
-        <ahocorasick.version>0.6.3</ahocorasick.version>
-        <jackson.version>2.13.2</jackson.version>
-    </properties>
-
-    <dependencies>
-
-        <dependency>
-            <groupId>org.springframework.boot</groupId>
-            <artifactId>spring-boot-starter-aop</artifactId>
-        </dependency>
-
-        <dependency>
-            <groupId>com.iqser.red.commons</groupId>
-            <artifactId>storage-commons</artifactId>
-            <version>1.8.5</version>
-        </dependency>
-
-        <dependency>
-            <groupId>com.fasterxml.jackson.module</groupId>
-            <artifactId>jackson-module-afterburner</artifactId>
-            <version>${jackson.version}</version>
-        </dependency>
-
-        <dependency>
-            <groupId>com.fasterxml.jackson.datatype</groupId>
-            <artifactId>jackson-datatype-jsr310</artifactId>
-            <version>${jackson.version}</version>
-        </dependency>
-
-        <dependency>
-            <groupId>org.ahocorasick</groupId>
-            <artifactId>ahocorasick</artifactId>
-            <version>${ahocorasick.version}</version>
-        </dependency>
-
-        <dependency>
-            <groupId>org.javassist</groupId>
-            <artifactId>javassist</artifactId>
-            <version>${javaassist.version}</version>
-        </dependency>
-
-        <dependency>
-            <groupId>com.iqser.red.service</groupId>
-            <artifactId>redaction-service-api-v1</artifactId>
-            <version>${project.version}</version>
-        </dependency>
-        <dependency>
-            <groupId>org.drools</groupId>
-            <artifactId>drools-core</artifactId>
-            <version>${drools.version}</version>
-        </dependency>
-        <dependency>
-            <groupId>org.kie</groupId>
-            <artifactId>kie-spring</artifactId>
-            <version>${kie.version}</version>
-        </dependency>
-        <dependency>
-            <groupId>org.locationtech.jts</groupId>
-            <artifactId>jts-core</artifactId>
-            <version>${locationtech.version}</version>
-        </dependency>
-        <dependency>
-            <groupId>com.google.guava</groupId>
-            <artifactId>guava</artifactId>
-        </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.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>
-
-        <dependency>
-            <groupId>org.springframework.boot</groupId>
-            <artifactId>spring-boot-starter-amqp</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>
-                <groupId>org.apache.maven.plugins</groupId>
-                <artifactId>maven-compiler-plugin</artifactId>
-                <configuration>
-                    <annotationProcessors>
-                        <annotationProcessor>lombok.launch.AnnotationProcessorHider$AnnotationProcessor</annotationProcessor>
-                        <annotationProcessor>com.dslplatform.json.processor.CompiledJsonAnnotationProcessor</annotationProcessor>
-                    </annotationProcessors>
-                </configuration>
-            </plugin>
-
-            <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

@@ -1,11 +1,8 @@
 package com.iqser.red.service.redaction.v1.server;
 
-import com.iqser.red.commons.spring.DefaultWebMvcConfiguration;
-import com.iqser.red.service.redaction.v1.server.client.RulesClient;
-import com.iqser.red.service.redaction.v1.server.settings.RedactionServiceSettings;
-
 import org.springframework.boot.SpringApplication;
 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;
@@ -13,10 +10,17 @@ 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.service.redaction.v1.server.client.RulesClient;
+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;
 
-@Import({DefaultWebMvcConfiguration.class})
+@ImportAutoConfiguration({MultiTenancyAutoConfiguration.class})
+@Import({MetricsConfiguration.class, StorageAutoConfiguration.class})
 @EnableFeignClients(basePackageClasses = RulesClient.class)
 @EnableConfigurationProperties(RedactionServiceSettings.class)
 @SpringBootApplication(exclude = {SecurityAutoConfiguration.class, ManagementWebSecurityAutoConfiguration.class})
@@ -35,4 +39,10 @@ public class Application {
         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

@@ -0,0 +1,26 @@
+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

@@ -1,31 +0,0 @@
-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.model.SectionGrid;
-import com.iqser.red.service.redaction.v1.server.redaction.model.DictionaryVersion;
-
-import lombok.Data;
-import lombok.NoArgsConstructor;
-
-@Data
-@NoArgsConstructor
-public class Document {
-
-    private List<Page> pages = new ArrayList<>();
-    private List<Paragraph> paragraphs = new ArrayList<>();
-    private List<Header> headers = new ArrayList<>();
-    private List<Footer> footers = new ArrayList<>();
-    private List<UnclassifiedText> unclassifiedTexts = new ArrayList<>();
-    private FloatFrequencyCounter textHeightCounter = new FloatFrequencyCounter();
-    private FloatFrequencyCounter fontSizeCounter = new FloatFrequencyCounter();
-    private StringFrequencyCounter fontCounter = new StringFrequencyCounter();
-    private StringFrequencyCounter fontStyleCounter = new StringFrequencyCounter();
-    private boolean headlines;
-
-    private SectionGrid sectionGrid = new SectionGrid();
-    private DictionaryVersion 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

@@ -1,77 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.classification.model;
-
-import lombok.Getter;
-
-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;
-
-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 || 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 || 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/Footer.java

@@ -1,28 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.classification.model;
-
-import com.dslplatform.json.JsonAttribute;
-import com.fasterxml.jackson.annotation.JsonIgnore;
-import com.iqser.red.service.redaction.v1.server.redaction.model.SearchableText;
-
-import lombok.AllArgsConstructor;
-import lombok.Data;
-
-import java.util.List;
-
-@Data
-@AllArgsConstructor
-public class Footer {
-
-    private List<TextBlock> textBlocks;
-
-
-    @JsonIgnore
-    @JsonAttribute(ignore = true)
-    public SearchableText getSearchableText() {
-
-        SearchableText searchableText = new SearchableText();
-        textBlocks.forEach(block -> searchableText.addAll(block.getSequences()));
-        return searchableText;
-    }
-
-}

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

@@ -1,28 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.classification.model;
-
-import com.dslplatform.json.JsonAttribute;
-import com.fasterxml.jackson.annotation.JsonIgnore;
-import com.iqser.red.service.redaction.v1.server.redaction.model.SearchableText;
-
-import lombok.AllArgsConstructor;
-import lombok.Data;
-
-import java.util.List;
-
-@Data
-@AllArgsConstructor
-public class Header {
-
-    private List<TextBlock> textBlocks;
-
-
-    @JsonIgnore
-    @JsonAttribute(ignore = true)
-    public SearchableText getSearchableText() {
-
-        SearchableText searchableText = new SearchableText();
-        textBlocks.forEach(block -> searchableText.addAll(block.getSequences()));
-        return searchableText;
-    }
-
-}

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

@@ -1,8 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.classification.model;
-
-public enum Orientation {
-
-    NONE,
-    LEFT,
-    RIGHT
-}

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

@@ -1,46 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.classification.model;
-
-import java.util.ArrayList;
-import java.util.List;
-
-import org.apache.pdfbox.pdmodel.common.PDRectangle;
-
-import com.iqser.red.service.redaction.v1.model.Rectangle;
-import com.iqser.red.service.redaction.v1.server.redaction.model.PdfImage;
-import com.iqser.red.service.redaction.v1.server.tableextraction.model.AbstractTextContainer;
-
-import lombok.Data;
-import lombok.NonNull;
-import lombok.RequiredArgsConstructor;
-
-@Data
-@RequiredArgsConstructor
-public class Page {
-
-    @NonNull
-    private List<AbstractTextContainer> textBlocks;
-
-    private List<PdfImage> images = new ArrayList<>();
-
-    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();
-
-    private float pageWidth;
-    private float pageHeight;
-
-
-    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

@@ -1,65 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.classification.model;
-
-import com.iqser.red.service.redaction.v1.server.redaction.model.PdfImage;
-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;
-
-import java.util.ArrayList;
-import java.util.List;
-
-@Data
-@NoArgsConstructor
-public class Paragraph implements Comparable {
-
-    private List<AbstractTextContainer> pageBlocks = new ArrayList<>();
-    private List<PdfImage> images = 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;
-    }
-
-
-    @Override
-    public int compareTo(Object o) {
-
-        return 0;
-    }
-
-}

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

@@ -1,63 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.classification.model;
-
-import com.dslplatform.json.CompiledJson;
-import com.dslplatform.json.JsonAttribute;
-import com.fasterxml.jackson.annotation.JsonIgnore;
-import com.iqser.red.service.redaction.v1.model.SectionArea;
-import com.iqser.red.service.redaction.v1.server.redaction.model.CellValue;
-import com.iqser.red.service.redaction.v1.server.redaction.model.Image;
-import com.iqser.red.service.redaction.v1.server.redaction.model.SearchableText;
-
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.Data;
-import lombok.NoArgsConstructor;
-
-import java.util.*;
-
-@Data
-@Builder
-@CompiledJson
-@NoArgsConstructor
-@AllArgsConstructor
-public class SectionText {
-
-    private int sectionNumber;
-    private String text;
-
-    private boolean isTable;
-    private String headline;
-
-    @Builder.Default
-    private List<SectionArea> sectionAreas = new ArrayList<>();
-    @Builder.Default
-    private Set<Image> images = new HashSet<>();
-    @Builder.Default
-    private List<TextBlock> textBlocks = new ArrayList<>();
-    @Builder.Default
-    private Map<String, CellValue> tabularData = new HashMap<>();
-    @Builder.Default
-    private List<Integer> cellStarts = new ArrayList<>();
-
-
-    public void setTabularData(Map<String, CellValue> tabularData) {
-
-        tabularData.remove(null);
-        this.tabularData = tabularData;
-    }
-
-
-    @JsonIgnore
-    @JsonAttribute(ignore = true)
-    public SearchableText getSearchableText() {
-
-        SearchableText searchableText = new SearchableText();
-        textBlocks.forEach(block -> {
-            if (block != null) {
-                searchableText.addAll(block.getSequences());
-            }
-        });
-        return searchableText;
-    }
-
-}

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

@@ -1,20 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.classification.model;
-
-import com.dslplatform.json.CompiledJson;
-
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.Data;
-import lombok.NoArgsConstructor;
-
-@Data
-@Builder
-@CompiledJson
-@NoArgsConstructor
-@AllArgsConstructor
-public class SimplifiedSectionText {
-
-    private int sectionNumber;
-    private String text;
-
-}

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

@@ -1,23 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.classification.model;
-
-import java.util.ArrayList;
-import java.util.List;
-
-import com.dslplatform.json.CompiledJson;
-
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.Data;
-import lombok.NoArgsConstructor;
-
-@Data
-@Builder
-@CompiledJson
-@NoArgsConstructor
-@AllArgsConstructor
-public class SimplifiedText {
-
-    private int numberOfPages;
-    private List<SimplifiedSectionText> sectionTexts = new ArrayList<>();
-
-}

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

@@ -1,47 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.classification.model;
-
-import lombok.Getter;
-
-import java.util.HashMap;
-import java.util.Map;
-
-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 || 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/Text.java

@@ -1,21 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.classification.model;
-
-import com.dslplatform.json.CompiledJson;
-
-import lombok.AllArgsConstructor;
-import lombok.Data;
-import lombok.NoArgsConstructor;
-
-import java.util.ArrayList;
-import java.util.List;
-
-@Data
-@CompiledJson
-@NoArgsConstructor
-@AllArgsConstructor
-public class Text {
-
-    private int numberOfPages;
-    private List<SectionText> sectionTexts = new ArrayList<>();
-
-}

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

@@ -1,313 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.classification.model;
-
-import java.util.ArrayList;
-import java.util.List;
-
-import com.dslplatform.json.CompiledJson;
-import com.dslplatform.json.JsonAttribute;
-import com.fasterxml.jackson.annotation.JsonIgnore;
-import com.iqser.red.service.redaction.v1.server.parsing.model.TextDirection;
-import com.iqser.red.service.redaction.v1.server.parsing.model.TextPositionSequence;
-import com.iqser.red.service.redaction.v1.server.redaction.utils.TextNormalizationUtilities;
-import com.iqser.red.service.redaction.v1.server.tableextraction.model.AbstractTextContainer;
-
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.Data;
-import lombok.NoArgsConstructor;
-
-@AllArgsConstructor
-@Builder
-@Data
-@CompiledJson
-@NoArgsConstructor
-public class TextBlock extends AbstractTextContainer {
-
-    @Builder.Default
-    private List<TextPositionSequence> sequences = new ArrayList<>();
-
-    @JsonIgnore
-    private int rotation;
-
-    @JsonIgnore
-    private String mostPopularWordFont;
-
-    @JsonIgnore
-    private String mostPopularWordStyle;
-
-    @JsonIgnore
-    private float mostPopularWordFontSize;
-
-    @JsonIgnore
-    private float mostPopularWordHeight;
-
-    @JsonIgnore
-    private float mostPopularWordSpaceWidth;
-
-    @JsonIgnore
-    private float highestFontSize;
-
-    @JsonIgnore
-    private String classification;
-
-
-    @JsonIgnore
-    @JsonAttribute(ignore = true)
-    public TextDirection getDir() {
-
-        return sequences.get(0).getDir();
-    }
-
-
-    @JsonIgnore
-    @JsonAttribute(ignore = true)
-    private float getPageHeight() {
-
-        return sequences.get(0).getPageHeight();
-    }
-
-
-    @JsonIgnore
-    @JsonAttribute(ignore = true)
-    private float getPageWidth() {
-
-        return sequences.get(0).getPageWidth();
-    }
-
-
-    /**
-     * Returns the minX value in pdf coordinate system.
-     * Note: This needs to use Pdf Coordinate System where {0,0} rotated with the page rotation.
-     * 0 -> LowerLeft
-     * 90 -> UpperLeft
-     * 180 -> UpperRight
-     * 270 -> LowerRight
-     *
-     * @return the minX value in pdf coordinate system
-     */
-    @JsonIgnore
-    @JsonAttribute(ignore = true)
-    public float getPdfMinX() {
-
-        if (getDir().getDegrees() == 90) {
-            return minY;
-        } else if (getDir().getDegrees() == 180) {
-            return getPageWidth() - maxX;
-
-        } else if (getDir().getDegrees() == 270) {
-
-            return getPageWidth() - maxY;
-        } else {
-            return minX;
-        }
-    }
-
-    /**
-     * Returns the maxX value in pdf coordinate system.
-     * Note: This needs to use Pdf Coordinate System where {0,0} rotated with the page rotation.
-     * 0 -> LowerLeft
-     * 90 -> UpperLeft
-     * 180 -> UpperRight
-     * 270 -> LowerRight
-     *
-     * @return the maxX value in pdf coordinate system
-     */
-    @JsonIgnore
-    @JsonAttribute(ignore = true)
-    public float getPdfMaxX() {
-
-        if (getDir().getDegrees() == 90) {
-            return maxY;
-        } else if (getDir().getDegrees() == 180) {
-            return getPageWidth() - minX;
-        } else if (getDir().getDegrees() == 270) {
-            return getPageWidth() - minY;
-
-        } else {
-            return maxX;
-        }
-    }
-
-
-    /**
-     * Returns the minY value in pdf coordinate system.
-     * Note: This needs to use Pdf Coordinate System where {0,0} rotated with the page rotation.
-     * 0 -> LowerLeft
-     * 90 -> UpperLeft
-     * 180 -> UpperRight
-     * 270 -> LowerRight
-     *
-     * @return the minY value in pdf coordinate system
-     */
-    @JsonIgnore
-    @JsonAttribute(ignore = true)
-    public float getPdfMinY() {
-
-        if (getDir().getDegrees() == 90) {
-            return minX;
-        } else if (getDir().getDegrees() == 180) {
-            return maxY;
-
-        } else if (getDir().getDegrees() == 270) {
-            return getPageHeight() - maxX;
-
-        } else {
-            return getPageHeight() - maxY;
-        }
-    }
-
-
-    /**
-     * Returns the maxY value in pdf coordinate system.
-     * Note: This needs to use Pdf Coordinate System where {0,0} rotated with the page rotation.
-     * 0 -> LowerLeft
-     * 90 -> UpperLeft
-     * 180 -> UpperRight
-     * 270 -> LowerRight
-     *
-     * @return the maxY value in pdf coordinate system
-     */
-    @JsonIgnore
-    @JsonAttribute(ignore = true)
-    public float getPdfMaxY() {
-
-        if (getDir().getDegrees() == 90) {
-            return maxX;
-        } else if (getDir().getDegrees() == 180) {
-
-            return minY;
-        } else if (getDir().getDegrees() == 270) {
-            return getPageHeight() - minX;
-        } else {
-            return getPageHeight() - minY;
-        }
-    }
-
-
-    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.getMinXDirAdj() < minX) {
-            minX = r.getMinXDirAdj();
-        }
-        if (r.getMaxXDirAdj() > maxX) {
-            maxX = r.getMaxXDirAdj();
-        }
-        if (r.getMinYDirAdj() < minY) {
-            minY = r.getMinYDirAdj();
-        }
-        if (r.getMaxYDirAdj() > maxY) {
-            maxY = r.getMaxYDirAdj();
-        }
-    }
-
-
-    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
-    @JsonIgnore
-    @JsonAttribute(ignore = true)
-    public String getText() {
-
-        StringBuilder sb = new StringBuilder();
-
-        TextPositionSequence previous = null;
-        for (TextPositionSequence word : sequences) {
-            if (previous != null) {
-                if (Math.abs(previous.getMaxYDirAdj() - word.getMaxYDirAdj()) > 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/model/UnclassifiedText.java

@@ -1,28 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.classification.model;
-
-import com.dslplatform.json.JsonAttribute;
-import com.fasterxml.jackson.annotation.JsonIgnore;
-import com.iqser.red.service.redaction.v1.server.redaction.model.SearchableText;
-
-import lombok.AllArgsConstructor;
-import lombok.Data;
-
-import java.util.List;
-
-@Data
-@AllArgsConstructor
-public class UnclassifiedText {
-
-    private List<TextBlock> textBlocks;
-
-
-    @JsonIgnore
-    @JsonAttribute(ignore = true)
-    public SearchableText getSearchableText() {
-
-        SearchableText searchableText = new SearchableText();
-        textBlocks.forEach(block -> searchableText.addAll(block.getSequences()));
-        return searchableText;
-    }
-
-}

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

@@ -1,241 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.classification.service;
-
-import static java.util.stream.Collectors.toSet;
-
-import java.util.ArrayList;
-import java.util.Comparator;
-import java.util.Iterator;
-import java.util.List;
-
-import org.springframework.stereotype.Service;
-
-import com.iqser.red.service.redaction.v1.server.classification.model.FloatFrequencyCounter;
-import com.iqser.red.service.redaction.v1.server.classification.model.Orientation;
-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.classification.utils.RulingTextDirAdjustUtil;
-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.Ruling;
-
-@Service
-@SuppressWarnings("all")
-public class BlockificationService {
-
-    static final float THRESHOLD = 1f;
-
-
-    /**
-     * This method is building blocks by expanding the minX/maxX and minY/maxY value on each word that is not split by the conditions.
-     * This method must use text direction adjusted postions (DirAdj). Where {0,0} is on the upper left. Never try to change this!
-     * Rulings (Table lines) must be adjusted to the text directions as well, when checking if a block is split by a ruling.
-     * @param textPositions The words of a page.
-     * @param horizontalRulingLines Horizontal table lines.
-     * @param verticalRulingLines Vertical table lines.
-     * @return Page object that contains the Textblock and text statistics.
-     */
-    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;
-
-        boolean wasSplitted = false;
-        Float splitX1 = null;
-        for (TextPositionSequence word : textPositions) {
-
-            boolean lineSeparation = word.getMinYDirAdj() - maxY > word.getHeight() * 1.25;
-            boolean startFromTop = prev != null && word.getMinYDirAdj() < prev.getMinYDirAdj() - prev.getTextHeight();
-            boolean splitByX = prev != null && maxX + 50 < word.getMinXDirAdj() && prev.getMinYDirAdj() == word.getMinYDirAdj();
-            boolean xIsBeforeFirstX = prev != null && word.getMinXDirAdj() < minX;
-            boolean newLineAfterSplit = prev != null && word.getMinYDirAdj() != prev.getMinYDirAdj() && wasSplitted && splitX1 != word.getMinXDirAdj();
-            boolean isSplitByRuling = isSplitByRuling(minX, minY, maxX, maxY, word, horizontalRulingLines, verticalRulingLines);
-            boolean splitByDir = prev != null && !prev.getDir().equals(word.getDir());
-
-            if (prev != null && (lineSeparation || startFromTop || splitByX || splitByDir || isSplitByRuling)) {
-
-                Orientation prevOrientation = null;
-                if (!chunkBlockList1.isEmpty()) {
-                    prevOrientation = chunkBlockList1.get(chunkBlockList1.size() - 1).getOrientation();
-                }
-
-                TextBlock cb1 = buildTextBlock(chunkWords);
-                chunkBlockList1.add(cb1);
-                chunkWords = new ArrayList<>();
-
-                if (splitByX && !isSplitByRuling) {
-                    wasSplitted = true;
-                    cb1.setOrientation(Orientation.LEFT);
-                    splitX1 = word.getMinXDirAdj();
-                } else if (newLineAfterSplit && !isSplitByRuling) {
-                    wasSplitted = false;
-                    cb1.setOrientation(Orientation.RIGHT);
-                    splitX1 = null;
-                } else if (prevOrientation != null && prevOrientation.equals(Orientation.RIGHT) && (lineSeparation || !startFromTop || !splitByX || !newLineAfterSplit || !isSplitByRuling)) {
-                    cb1.setOrientation(Orientation.LEFT);
-                }
-
-                minX = 1000;
-                maxX = 0;
-                minY = 1000;
-                maxY = 0;
-                prev = null;
-            }
-
-            chunkWords.add(word);
-
-            prev = word;
-            if (word.getMinXDirAdj() < minX) {
-                minX = word.getMinXDirAdj();
-            }
-            if (word.getMaxXDirAdj() > maxX) {
-                maxX = word.getMaxXDirAdj();
-            }
-            if (word.getMinYDirAdj() < minY) {
-                minY = word.getMinYDirAdj();
-            }
-            if (word.getMaxYDirAdj() > maxY) {
-                maxY = word.getMaxYDirAdj();
-            }
-        }
-
-        TextBlock cb1 = buildTextBlock(chunkWords);
-        if (cb1 != null) {
-            chunkBlockList1.add(cb1);
-        }
-
-        Iterator<AbstractTextContainer> itty = chunkBlockList1.iterator();
-
-        TextBlock previousLeft = null;
-        TextBlock previousRight = null;
-        while (itty.hasNext()) {
-            TextBlock block = (TextBlock) itty.next();
-
-            if (previousLeft != null && block.getOrientation().equals(Orientation.LEFT)) {
-                if (previousLeft.getMinY() > block.getMinY() && block.getMaxY() + block.getMostPopularWordHeight() > previousLeft.getMinY()) {
-                    previousLeft.add(block);
-                    itty.remove();
-                    continue;
-                }
-            }
-
-            if (previousRight != null && block.getOrientation().equals(Orientation.RIGHT)) {
-                if (previousRight.getMinY() > block.getMinY() && block.getMaxY() + block.getMostPopularWordHeight() > previousRight.getMinY()) {
-                    previousRight.add(block);
-                    itty.remove();
-                    continue;
-                }
-            }
-
-            if (block.getOrientation().equals(Orientation.LEFT)) {
-                previousLeft = block;
-            } else if (block.getOrientation().equals(Orientation.RIGHT)) {
-                previousRight = block;
-            }
-        }
-
-        itty = chunkBlockList1.iterator();
-        TextBlock previous = null;
-        while (itty.hasNext()) {
-            TextBlock block = (TextBlock) itty.next();
-
-            if (previous != null && previous.getOrientation().equals(Orientation.LEFT) && block.getOrientation().equals(Orientation.LEFT) && equalsWithThreshold(block.getMaxY(),
-                    previous.getMaxY()) || previous != null && previous.getOrientation().equals(Orientation.LEFT) && block.getOrientation()
-                    .equals(Orientation.RIGHT) && equalsWithThreshold(block.getMaxY(), previous.getMaxY())) {
-                previous.add(block);
-                itty.remove();
-                continue;
-            }
-
-            previous = block;
-        }
-
-        return new Page(chunkBlockList1);
-    }
-
-
-    private boolean equalsWithThreshold(float f1, float f2) {
-
-        return Math.abs(f1 - f2) < THRESHOLD;
-    }
-
-
-    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.getMinXDirAdj(), wordBlock.getMaxXDirAdj(), wordBlock.getMinYDirAdj(), wordBlock.getMaxYDirAdj(), 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());
-        }
-
-        if (textBlock != null && textBlock.getSequences() != null && textBlock.getSequences().stream().map(t -> round(t.getMinYDirAdj(), 3)).collect(toSet()).size() == 1) {
-            textBlock.getSequences().sort(Comparator.comparing(TextPositionSequence::getMinXDirAdj));
-        }
-        return textBlock;
-    }
-
-
-    private boolean isSplitByRuling(float minX,
-                                    float minY,
-                                    float maxX,
-                                    float maxY,
-                                    TextPositionSequence word,
-                                    List<Ruling> horizontalRulingLines,
-                                    List<Ruling> verticalRulingLines) {
-
-        return isSplitByRuling(maxX, minY, word.getMinXDirAdj(), word.getMinYDirAdj(), verticalRulingLines, word.getDir().getDegrees(), word.getPageWidth(), word.getPageHeight()) //
-                || isSplitByRuling(minX, minY, word.getMinXDirAdj(), word.getMaxYDirAdj(), horizontalRulingLines, word.getDir().getDegrees(), word.getPageWidth(), word.getPageHeight()) //
-                || isSplitByRuling(maxX, minY, word.getMinXDirAdj(), word.getMinYDirAdj(), horizontalRulingLines, word.getDir().getDegrees(), word.getPageWidth(), word.getPageHeight()) //
-                || isSplitByRuling(minX, minY, word.getMinXDirAdj(), word.getMaxYDirAdj(), verticalRulingLines, word.getDir().getDegrees(), word.getPageWidth(), word.getPageHeight()); //
-    }
-
-
-    private boolean isSplitByRuling(float previousX2, float previousY1, float currentX1, float currentY1, List<Ruling> rulingLines, float dir, float pageWidth, float pageHeight) {
-
-        for (Ruling ruling : rulingLines) {
-            var line = RulingTextDirAdjustUtil.convertToDirAdj(ruling, dir, pageWidth, pageHeight);
-            if (line.intersectsLine(previousX2, previousY1, currentX1, currentY1)) {
-                return true;
-            }
-        }
-        return false;
-    }
-
-
-    private double round(float value, int decimalPoints) {
-
-        var d = Math.pow(10, decimalPoints);
-        return Math.round(value * d) / d;
-    }
-
-}

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

@@ -1,161 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.classification.service;
-
-import java.util.List;
-
-import org.springframework.stereotype.Service;
-
-import com.iqser.red.service.redaction.v1.model.Point;
-import com.iqser.red.service.redaction.v1.model.Rectangle;
-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.TextBlock;
-import com.iqser.red.service.redaction.v1.server.classification.utils.PositionUtils;
-import com.iqser.red.service.redaction.v1.server.tableextraction.model.AbstractTextContainer;
-import com.iqser.red.service.redaction.v1.server.tableextraction.model.Cell;
-import com.iqser.red.service.redaction.v1.server.tableextraction.model.Table;
-
-@Service
-public class BodyTextFrameService {
-
-    /**
-     * Adjusts and sets the body text frame to a page.
-     * Note: This needs to use Pdf Coordinate System where {0,0} rotated with the page rotation.
-     * 0 -> LowerLeft
-     * 90 -> UpperLeft
-     * 180 -> UpperRight
-     * 270 -> LowerRight
-     * The aspect ratio of the page is also regarded.
-     *
-     * @param page                   The page
-     * @param bodyTextFrame          frame that contains the main text on portrait pages
-     * @param landscapeBodyTextFrame frame that contains the main text on landscape pages
-     */
-    public void setBodyTextFrameAdjustedToPage(Page page, Rectangle bodyTextFrame, Rectangle landscapeBodyTextFrame) {
-
-        Rectangle textFrame = page.isLandscape() ? landscapeBodyTextFrame : bodyTextFrame;
-
-        if (page.getPageWidth() > page.getPageHeight() && page.getRotation() == 270) {
-            textFrame = new Rectangle(new Point(textFrame.getTopLeft().getY(), page.getPageHeight() - textFrame.getTopLeft().getX() - textFrame.getWidth()),
-                    textFrame.getHeight(),
-                    textFrame.getWidth(),
-                    0);
-        } else if (page.getPageWidth() > page.getPageHeight() && page.getRotation() != 0) {
-            textFrame = new Rectangle(new Point(textFrame.getTopLeft().getY(), textFrame.getTopLeft().getX()), textFrame.getHeight(), textFrame.getWidth(), page.getPageNumber());
-        } else if (page.getRotation() == 180) {
-            textFrame = new Rectangle(new Point(textFrame.getTopLeft().getX(), page.getPageHeight() - textFrame.getTopLeft().getY() - textFrame.getHeight()),
-                    textFrame.getWidth(),
-                    textFrame.getHeight(),
-                    0);
-        }
-        page.setBodyTextFrame(textFrame);
-    }
-
-
-    /**
-     * Calculates the frame that contains the main text, text outside the frame will be e.g. headers or footers.
-     * Note: This needs to use Pdf Coordinate System where {0,0} rotated with the page rotation.
-     * 0 -> LowerLeft
-     * 90 -> UpperLeft
-     * 180 -> UpperRight
-     * 270 -> LowerRight
-     * The aspect ratio of the page is also regarded.
-     *
-     * @param pages                   List of all pages
-     * @param documentFontSizeCounter Statistics of the document
-     * @param landscape               Calculate for landscape or portrait
-     * @return Rectangle of the text frame
-     */
-    public Rectangle calculateBodyTextFrame(List<Page> pages, FloatFrequencyCounter documentFontSizeCounter, boolean landscape) {
-
-        BodyTextFrameExpansionsRectangle expansionsRectangle = new BodyTextFrameExpansionsRectangle();
-
-        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 && textBlock.getMostPopularWordFontSize() >= documentFontSizeCounter.getMostPopular()) {
-
-                        expandRectangle(textBlock, page, expansionsRectangle);
-                    }
-                }
-
-                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()) {
-                                expandRectangle(textBlock, page, expansionsRectangle);
-                            }
-                        }
-                    }
-                }
-            }
-        }
-        return new Rectangle(new Point(expansionsRectangle.minX, expansionsRectangle.minY),
-                expansionsRectangle.maxX - expansionsRectangle.minX,
-                expansionsRectangle.maxY - expansionsRectangle.minY,
-                0);
-    }
-
-
-    private void expandRectangle(TextBlock textBlock, Page page, BodyTextFrameExpansionsRectangle expansionsRectangle) {
-
-        if (page.getPageWidth() > page.getPageHeight() && page.getRotation() != 0) {
-            if (textBlock.getPdfMinY() < expansionsRectangle.minX) {
-                expansionsRectangle.minX = textBlock.getPdfMinY();
-            }
-            if (textBlock.getPdfMaxY() > expansionsRectangle.maxX) {
-                expansionsRectangle.maxX = textBlock.getPdfMaxY();
-            }
-            if (textBlock.getPdfMinX() < expansionsRectangle.minY) {
-                expansionsRectangle.minY = textBlock.getPdfMinX();
-            }
-            if (textBlock.getPdfMaxX() > expansionsRectangle.maxY) {
-                expansionsRectangle.maxY = textBlock.getPdfMaxX();
-            }
-        } else {
-            if (textBlock.getPdfMinX() < expansionsRectangle.minX) {
-                expansionsRectangle.minX = textBlock.getPdfMinX();
-            }
-            if (textBlock.getPdfMaxX() > expansionsRectangle.maxX) {
-                expansionsRectangle.maxX = textBlock.getPdfMaxX();
-            }
-            if (textBlock.getPdfMinY() < expansionsRectangle.minY) {
-                expansionsRectangle.minY = textBlock.getPdfMinY();
-            }
-            if (textBlock.getPdfMaxY() > expansionsRectangle.maxY) {
-                expansionsRectangle.maxY = textBlock.getPdfMaxY();
-            }
-        }
-    }
-
-
-    private class BodyTextFrameExpansionsRectangle {
-
-        float minX = 10000;
-        float maxX = -100;
-        float minY = 10000;
-        float maxY = -100;
-
-    }
-
-}

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

@@ -1,116 +0,0 @@
-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.model.Rectangle;
-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.classification.utils.PositionUtils;
-import com.iqser.red.service.redaction.v1.server.tableextraction.model.AbstractTextContainer;
-
-import lombok.RequiredArgsConstructor;
-import lombok.extern.slf4j.Slf4j;
-
-@Slf4j
-@Service
-@RequiredArgsConstructor
-public class ClassificationService {
-
-    private final BodyTextFrameService bodyTextFrameService;
-
-
-    public void classifyDocument(Document document) {
-
-        Rectangle bodyTextFrame = bodyTextFrameService.calculateBodyTextFrame(document.getPages(), document.getFontSizeCounter(), false);
-        Rectangle landscapeBodyTextFrame = bodyTextFrameService.calculateBodyTextFrame(document.getPages(), document.getFontSizeCounter(), true);
-        List<Float> headlineFontSizes = document.getFontSizeCounter().getHighterThanMostPopular();
-
-        log.debug("Document FontSize counters are: {}", document.getFontSizeCounter().getCountPerValue());
-
-        for (Page page : document.getPages()) {
-            bodyTextFrameService.setBodyTextFrameAdjustedToPage(page, bodyTextFrame, landscapeBodyTextFrame);
-            classifyPage(page, document, headlineFontSizes);
-        }
-    }
-
-
-    public void classifyPage(Page page, Document document, List<Float> headlineFontSizes) {
-
-        for (AbstractTextContainer textBlock : page.getTextBlocks()) {
-            if (textBlock instanceof TextBlock) {
-                classifyBlock((TextBlock) textBlock, page, document, headlineFontSizes);
-            }
-        }
-    }
-
-
-    public void classifyBlock(TextBlock textBlock, Page page, Document document, List<Float> headlineFontSizes) {
-
-        var bodyTextFrame = page.getBodyTextFrame();
-
-        if (document.getFontSizeCounter().getMostPopular() == null) {
-            textBlock.setClassification("Other");
-            return;
-        }
-        if (PositionUtils.isOverBodyTextFrame(bodyTextFrame, textBlock, page.getRotation()) && (document.getFontSizeCounter()
-                .getMostPopular() == null || textBlock.getHighestFontSize() <= document.getFontSizeCounter().getMostPopular())) {
-            textBlock.setClassification("Header");
-
-        } else if (PositionUtils.isUnderBodyTextFrame(bodyTextFrame, textBlock, page.getRotation()) && (document.getFontSizeCounter()
-                .getMostPopular() == null || textBlock.getHighestFontSize() <= document.getFontSizeCounter().getMostPopular())) {
-            textBlock.setClassification("Footer");
-        } else if (page.getPageNumber() == 1 && (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 (textBlock.getMostPopularWordFontSize() > document.getFontSizeCounter()
-                .getMostPopular() && PositionUtils.getApproxLineCount(textBlock) < 4.9 && (textBlock.getMostPopularWordStyle().equals("bold") || !document.getFontStyleCounter()
-                .getCountPerValue()
-                .containsKey("bold") && textBlock.getMostPopularWordFontSize() > document.getFontSizeCounter().getMostPopular() + 1) && textBlock.getSequences()
-                .get(0)
-                .getTextPositions()
-                .get(0)
-                .getFontSizeInPt() >= textBlock.getMostPopularWordFontSize()) {
-
-            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.getSequences()
-                .get(0)
-                .getTextPositions()
-                .get(0)
-                .getFontSizeInPt() >= textBlock.getMostPopularWordFontSize()) {
-            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");
-        } else {
-            textBlock.setClassification("Other");
-        }
-    }
-
-}

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

@@ -1,119 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.classification.utils;
-
-import com.iqser.red.service.redaction.v1.model.Rectangle;
-import com.iqser.red.service.redaction.v1.server.classification.model.TextBlock;
-
-import lombok.experimental.UtilityClass;
-
-@UtilityClass
-@SuppressWarnings("all")
-public final class PositionUtils {
-
-    // TODO This currently uses pdf coord system. In the futher this should use java coord system.
-    // Note: DirAdj (TextDirection Adjusted) can not be user for this.
-    public boolean isWithinBodyTextFrame(Rectangle btf, TextBlock textBlock) {
-
-        if (btf == null || textBlock == null) {
-            return false;
-        }
-
-        double threshold = textBlock.getMostPopularWordHeight() * 3;
-
-        if (textBlock.getPdfMinX() + threshold > btf.getTopLeft().getX() && textBlock.getPdfMaxX() - threshold < btf.getTopLeft()
-                .getX() + btf.getWidth() && textBlock.getPdfMinY() + threshold > btf.getTopLeft().getY() && textBlock.getPdfMaxY() - threshold < btf.getTopLeft()
-                .getY() + btf.getHeight()) {
-            return true;
-        } else {
-            return false;
-        }
-
-    }
-
-
-    // TODO This currently uses pdf coord system. In the futher this should use java coord system.
-    // Note: DirAdj (TextDirection Adjusted) can not be user for this.
-    public boolean isOverBodyTextFrame(Rectangle btf, TextBlock textBlock, int rotation) {
-
-        if (btf == null || textBlock == null) {
-            return false;
-        }
-
-        if (rotation == 90 && textBlock.getPdfMaxX() < btf.getTopLeft().getX()) {
-            return true;
-        }
-
-        if (rotation == 180 && textBlock.getPdfMaxY() < btf.getTopLeft().getY()) {
-            return true;
-        }
-
-        if (rotation == 270 && textBlock.getPdfMinX() > btf.getTopLeft().getX() + btf.getWidth()) {
-            return true;
-        }
-
-        if (rotation == 0 && textBlock.getPdfMinY() > btf.getTopLeft().getY() + btf.getHeight()) {
-            return true;
-        } else {
-            return false;
-        }
-
-    }
-
-    // TODO This currently uses pdf coord system. In the futher this should use java coord system.
-    // Note: DirAdj (TextDirection Adjusted) can not be user for this.
-    public boolean isUnderBodyTextFrame(Rectangle btf, TextBlock textBlock, int rotation) {
-
-        if (btf == null || textBlock == null) {
-            return false;
-        }
-
-        if (rotation == 90 && textBlock.getPdfMinX() > btf.getTopLeft().getX() + btf.getWidth()) {
-            return true;
-        }
-
-        if (rotation == 180 && textBlock.getPdfMinY() > btf.getTopLeft().getY() + btf.getHeight()) {
-            return true;
-        }
-
-        if (rotation == 270 && textBlock.getPdfMaxX() < btf.getTopLeft().getX()) {
-            return true;
-        }
-
-        if (rotation == 0 && textBlock.getPdfMaxY() < btf.getTopLeft().getY()) {
-            return true;
-        } else {
-            return false;
-        }
-
-    }
-
-    // TODO This currently uses pdf coord system. In the futher this should use java coord system.
-    // Note: DirAdj (TextDirection Adjusted) can not be user for this.
-    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.getTopLeft().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/classification/utils/RulingTextDirAdjustUtil.java

@@ -1,67 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.classification.utils;
-
-import java.awt.geom.Line2D;
-import java.awt.geom.Point2D;
-
-import com.iqser.red.service.redaction.v1.server.tableextraction.model.Ruling;
-
-import lombok.experimental.UtilityClass;
-
-@UtilityClass
-public final class RulingTextDirAdjustUtil {
-
-    /**
-     * Converts a ruling (line of a table) the same way TextPositions are converted in PDFBox.
-     * This will get the y position of the text, adjusted so that 0,0 is upper left and it is adjusted based on the text direction.
-     *
-     * See org.apache.pdfbox.text.TextPosition
-     */
-    public Line2D.Float convertToDirAdj(Ruling ruling, float dir, float pageWidth, float pageHeight) {
-
-        return new Line2D.Float(convertPoint(ruling.x1, ruling.y1, dir, pageWidth, pageHeight), convertPoint(ruling.x2, ruling.y2, dir, pageWidth, pageHeight));
-    }
-
-
-    private Point2D convertPoint(float x, float y, float dir, float pageWidth, float pageHeight) {
-
-        var xAdj = getXRot(x, y, dir, pageWidth, pageHeight);
-        var yAdj = 0f;
-        if (dir == 0 || dir == 180) {
-            yAdj = pageHeight - getYLowerLeftRot(x, y, dir, pageWidth, pageHeight);
-        } else {
-            yAdj = pageWidth - getYLowerLeftRot(x, y, dir, pageWidth, pageHeight);
-        }
-        return new Point2D.Float(xAdj, yAdj);
-    }
-
-
-    private float getXRot(float x, float y, float dir, float pageWidth, float pageHeight) {
-
-        if (dir == 0) {
-            return x;
-        } else if (dir == 90) {
-            return y;
-        } else if (dir == 180) {
-            return pageWidth - x;
-        } else if (dir == 270) {
-            return pageHeight - y;
-        }
-        return 0;
-    }
-
-
-    private float getYLowerLeftRot(float x, float y, float dir, float pageWidth, float pageHeight) {
-
-        if (dir == 0) {
-            return y;
-        } else if (dir == 90) {
-            return pageWidth - x;
-        } else if (dir == 180) {
-            return pageHeight - y;
-        } else if (dir == 270) {
-            return x;
-        }
-        return 0;
-    }
-
-}

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.resources.DictionaryResource;
+import com.iqser.red.service.persistence.service.v1.api.internal.resources.DictionaryResource;
 
 @FeignClient(name = "DictionaryResource", url = "${persistence-service.url}")
 public interface DictionaryClient extends DictionaryResource {
 
-}
+}

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

@@ -1,16 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.client;
-
-import org.springframework.cloud.openfeign.FeignClient;
-import org.springframework.http.MediaType;
-import org.springframework.web.bind.annotation.PostMapping;
-
-import com.iqser.red.service.redaction.v1.server.client.model.EntityRecognitionRequest;
-import com.iqser.red.service.redaction.v1.server.client.model.NerEntities;
-
-@FeignClient(name = "EntityRecognitionClient", url = "${entity-recognition-service.url}")
-public interface EntityRecognitionClient {
-
-    @PostMapping(value = "/find_authors", produces = MediaType.APPLICATION_JSON_VALUE, consumes = MediaType.APPLICATION_JSON_VALUE)
-    NerEntities findAuthors(EntityRecognitionRequest entityRecognitionRequest);
-
-}

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

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

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

@@ -2,7 +2,7 @@ package com.iqser.red.service.redaction.v1.server.client;
 
 import org.springframework.cloud.openfeign.FeignClient;
 
-import com.iqser.red.service.persistence.service.v1.api.resources.LegalBasisMappingResource;
+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/RulesClient.java

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

@@ -1,6 +1,5 @@
 package com.iqser.red.service.redaction.v1.server.client.model;
 
-import com.dslplatform.json.CompiledJson;
 
 import lombok.AllArgsConstructor;
 import lombok.Builder;
@@ -9,10 +8,9 @@ import lombok.NoArgsConstructor;
 
 @Data
 @Builder
-@CompiledJson
 @AllArgsConstructor
 @NoArgsConstructor
-public class EntityRecogintionEntity {
+public class EntityRecognitionEntity {
 
     private String value;
     private int startOffset;

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

@@ -1,18 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.client.model;
-
-import java.util.List;
-
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.Data;
-import lombok.NoArgsConstructor;
-
-@Data
-@Builder
-@AllArgsConstructor
-@NoArgsConstructor
-public class EntityRecognitionRequest {
-
-    private List<EntityRecognitionSection> data;
-
-}

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

@@ -1,21 +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.Builder;
-import lombok.Data;
-import lombok.NoArgsConstructor;
-
-@Data
-@Builder
-@AllArgsConstructor
-@NoArgsConstructor
-public class EntityRecognitionResult {
-
-    @Builder.Default
-    private Map<Integer, List<EntityRecogintionEntity>> entities = new HashMap<>();
-
-}

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

@@ -4,18 +4,15 @@ import java.util.HashMap;
 import java.util.List;
 import java.util.Map;
 
-import com.dslplatform.json.CompiledJson;
-
 import lombok.AllArgsConstructor;
 import lombok.Data;
 import lombok.NoArgsConstructor;
 
 @Data
-@CompiledJson
 @NoArgsConstructor
 @AllArgsConstructor
-public class NerEntities {
+public class NerEntitiesModel {
 
-    private Map<Integer, List<EntityRecogintionEntity>> data = new HashMap<>();
+    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/RedactionController.java

@@ -1,31 +1,11 @@
 package com.iqser.red.service.redaction.v1.server.controller;
 
-import java.io.ByteArrayOutputStream;
-import java.io.IOException;
-
-import org.apache.pdfbox.pdmodel.PDDocument;
-import org.springframework.web.bind.annotation.PathVariable;
 import org.springframework.web.bind.annotation.RequestBody;
 import org.springframework.web.bind.annotation.RestController;
 
-import com.iqser.red.service.persistence.service.v1.api.model.annotations.ManualRedactions;
-import com.iqser.red.service.persistence.service.v1.api.model.dossiertemplate.dossier.file.FileType;
-import com.iqser.red.service.redaction.v1.model.RedactionLog;
-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.resources.RedactionResource;
-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.exception.RulesValidationException;
 import com.iqser.red.service.redaction.v1.server.redaction.service.DroolsExecutionService;
-import com.iqser.red.service.redaction.v1.server.redaction.service.ManualRedactionSurroundingTextService;
-import com.iqser.red.service.redaction.v1.server.redaction.service.RedactionLogMergeService;
-import com.iqser.red.service.redaction.v1.server.segmentation.PdfSegmentationService;
-import com.iqser.red.service.redaction.v1.server.storage.RedactionStorageService;
-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.PdfVisualisationService;
 
 import lombok.RequiredArgsConstructor;
 import lombok.extern.slf4j.Slf4j;
@@ -35,100 +15,7 @@ import lombok.extern.slf4j.Slf4j;
 @RequiredArgsConstructor
 public class RedactionController implements RedactionResource {
 
-    private final PdfVisualisationService pdfVisualisationService;
     private final DroolsExecutionService droolsExecutionService;
-    private final PdfSegmentationService pdfSegmentationService;
-    private final RedactionStorageService redactionStorageService;
-    private final RedactionLogMergeService redactionLogMergeService;
-    private final ManualRedactionSurroundingTextService manualRedactionSurroundingTextService;
-
-
-    @Override
-    public RedactionResult classify(@RequestBody RedactionRequest redactionRequest) {
-
-        var storedObjectStream = redactionStorageService.getStoredObject(RedactionStorageService.StorageIdUtils.getStorageId(redactionRequest.getDossierId(),
-                redactionRequest.getFileId(),
-                FileType.ORIGIN));
-        try {
-            Document classifiedDoc = pdfSegmentationService.parseDocument(redactionRequest.getDossierId(), redactionRequest.getFileId(), storedObjectStream, null);
-
-            storedObjectStream = redactionStorageService.getStoredObject(RedactionStorageService.StorageIdUtils.getStorageId(redactionRequest.getDossierId(),
-                    redactionRequest.getFileId(),
-                    FileType.ORIGIN));
-            try (PDDocument pdDocument = PDDocument.load(storedObjectStream)) {
-                pdDocument.setAllSecurityToBeRemoved(true);
-
-                pdfVisualisationService.visualizeClassifications(classifiedDoc, pdDocument);
-
-                return convert(pdDocument, classifiedDoc.getPages().size());
-
-            } catch (IOException e) {
-                throw new RedactionException(e);
-            }
-
-        } catch (IOException e) {
-            throw new RedactionException(e);
-        }
-
-    }
-
-
-    @Override
-    public RedactionResult sections(@RequestBody RedactionRequest redactionRequest) {
-
-        var storedObjectStream = redactionStorageService.getStoredObject(RedactionStorageService.StorageIdUtils.getStorageId(redactionRequest.getDossierId(),
-                redactionRequest.getFileId(),
-                FileType.ORIGIN));
-        try {
-            Document classifiedDoc = pdfSegmentationService.parseDocument(redactionRequest.getDossierId(), redactionRequest.getFileId(), storedObjectStream, null);
-
-            storedObjectStream = redactionStorageService.getStoredObject(RedactionStorageService.StorageIdUtils.getStorageId(redactionRequest.getDossierId(),
-                    redactionRequest.getFileId(),
-                    FileType.ORIGIN));
-            try (PDDocument pdDocument = PDDocument.load(storedObjectStream)) {
-                pdDocument.setAllSecurityToBeRemoved(true);
-
-                pdfVisualisationService.visualizeParagraphs(classifiedDoc, pdDocument);
-                return convert(pdDocument, classifiedDoc.getPages().size());
-
-            } catch (IOException e) {
-                throw new RedactionException(e);
-            }
-
-        } catch (IOException e) {
-            throw new RedactionException(e);
-        }
-
-    }
-
-
-    @Override
-    public RedactionResult htmlTables(@RequestBody RedactionRequest redactionRequest) {
-
-        Document classifiedDoc;
-
-        try {
-            var storedObjectStream = redactionStorageService.getStoredObject(RedactionStorageService.StorageIdUtils.getStorageId(redactionRequest.getDossierId(),
-                    redactionRequest.getFileId(),
-                    FileType.ORIGIN));
-            classifiedDoc = pdfSegmentationService.parseDocument(redactionRequest.getDossierId(), redactionRequest.getFileId(), storedObjectStream, null);
-        } catch (Exception e) {
-            throw new RedactionException(e);
-        }
-
-        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();
-
-    }
 
 
     @Override
@@ -141,30 +28,4 @@ public class RedactionController implements RedactionResource {
         }
     }
 
-
-    @Override
-    public RedactionLog getRedactionLog(RedactionRequest redactionRequest) {
-
-        return redactionLogMergeService.provideRedactionLog(redactionRequest);
-    }
-
-
-    private RedactionResult convert(PDDocument document, int numberOfPages) throws IOException {
-
-        try (ByteArrayOutputStream byteArrayOutputStream = new ByteArrayOutputStream()) {
-            document.save(byteArrayOutputStream);
-            return RedactionResult.builder().document(byteArrayOutputStream.toByteArray()).numberOfPages(numberOfPages).build();
-        }
-
-    }
-
-
-    @Override
-    public ManualRedactions addSurroundingText(@PathVariable("dossierId") String dossierId, @PathVariable("fileId") String fileId, @RequestBody ManualRedactions manualRedactions) {
-
-        var result = manualRedactionSurroundingTextService.addSurroundingText(dossierId, fileId, manualRedactions);
-        log.info("Added surrounding text for manual redaction in dossierId {} and fileId {} took: {}", dossierId, fileId, result.getDuration());
-        return result.getManualRedactions();
-    }
-
 }

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

@@ -1,13 +1,13 @@
 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.rulebuilder.RuleBuilderModelService;
+import com.iqser.red.service.redaction.v1.server.redaction.service.RuleBuilderModelService;
 
 import lombok.RequiredArgsConstructor;
 
-import org.springframework.web.bind.annotation.RestController;
-
 @RestController
 @RequiredArgsConstructor
 public class RuleBuilderController implements RuleBuilderResource {

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

@@ -0,0 +1,25 @@
+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

@@ -0,0 +1,198 @@
+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

@@ -0,0 +1,52 @@
+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/Boundary.java

@@ -0,0 +1,166 @@
+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 Boundary implements Comparable<Boundary> {
+
+    private int start;
+    private int end;
+
+
+    public Boundary(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(Boundary boundary) {
+
+        return start <= boundary.start() && boundary.end() <= end;
+    }
+
+
+    public boolean containedBy(Boundary boundary) {
+
+        return boundary.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(Boundary boundary) {
+
+        return boundary.start() < this.end && this.start < boundary.end();
+    }
+
+
+    public List<Boundary> 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<Boundary> 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 Boundary(previousIndex, splitIndex));
+            previousIndex = splitIndex;
+        }
+        splitBoundaries.add(new Boundary(previousIndex, end));
+        return splitBoundaries;
+    }
+
+
+    public static Boundary merge(Collection<Boundary> boundaries) {
+
+        int minStart = boundaries.stream().mapToInt(Boundary::start).min().orElseThrow(IllegalArgumentException::new);
+        int maxEnd = boundaries.stream().mapToInt(Boundary::end).max().orElseThrow(IllegalArgumentException::new);
+        return new Boundary(minStart, maxEnd);
+    }
+
+
+    @Override
+    public String toString() {
+
+        return format("Boundary [%d|%d)", start, end);
+    }
+
+
+    @Override
+    public int compareTo(Boundary boundary) {
+
+        if (end < boundary.end() && start < boundary.start()) {
+            return -1;
+        }
+        if (start > boundary.start() && end > boundary.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 Boundary 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 Boundary(trimmedStart, Math.max(trimmedEnd, trimmedStart));
+    }
+
+}

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

@@ -0,0 +1,70 @@
+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<Boundary, List<Boundary>, List<Boundary>> {
+
+    @Override
+    public Supplier<List<Boundary>> supplier() {
+
+        return LinkedList::new;
+    }
+
+
+    @Override
+    public BiConsumer<List<Boundary>, Boundary> accumulator() {
+
+        return (existingList, boundary) -> {
+            if (existingList.isEmpty()) {
+                existingList.add(boundary);
+                return;
+            }
+
+            Boundary prevBoundary = existingList.get(existingList.size() - 1);
+            if (prevBoundary.end() > boundary.start()) {
+                throw new IllegalArgumentException(String.format("Can't concatenate %s and %s. Boundaries must be ordered!", prevBoundary, boundary));
+            }
+
+            if (prevBoundary.end() == boundary.start()) {
+                existingList.remove(existingList.size() - 1);
+                existingList.add(Boundary.merge(List.of(prevBoundary, boundary)));
+            } else {
+                existingList.add(boundary);
+            }
+        };
+    }
+
+
+    @Override
+    public BinaryOperator<List<Boundary>> combiner() {
+
+        return (list1, list2) -> {
+            list1.addAll(list2);
+            return list1;
+        };
+    }
+
+
+    @Override
+    public Function<List<Boundary>, List<Boundary>> 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

@@ -0,0 +1,217 @@
+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/entity/EntityType.java

@@ -1,4 +1,4 @@
-package com.iqser.red.service.redaction.v1.server.redaction.model;
+package com.iqser.red.service.redaction.v1.server.document.graph.entity;
 
 public enum EntityType {
     ENTITY,

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

@@ -0,0 +1,70 @@
+package com.iqser.red.service.redaction.v1.server.document.graph.entity;
+
+import java.util.Collections;
+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> {
+
+    @Builder.Default
+    RuleIdentifier ruleIdentifier = RuleIdentifier.empty();
+    @Builder.Default
+    String reason = "";
+    @Builder.Default
+    String legalBasis = "";
+    boolean applied;
+    boolean writeValueWithLineBreaks;
+    @Builder.Default
+    Set<RedactionEntity> references = Collections.emptySet();
+
+
+    public static MatchedRule empty() {
+
+        return MatchedRule.builder().build();
+    }
+
+
+    @Override
+    public int compareTo(MatchedRule matchedRule) {
+
+        RuleIdentifier otherRuleIdentifier = matchedRule.getRuleIdentifier();
+        if (!Objects.equals(ruleIdentifier.type(), otherRuleIdentifier.type())) {
+            if (Objects.equals(otherRuleIdentifier.type(), "MAN")) {
+                return 1;
+            }
+            if (Objects.equals(ruleIdentifier.type(), "MAN")) {
+                return -1;
+            }
+            if (Objects.equals(otherRuleIdentifier.type(), "X")) {
+                return 1;
+            }
+            if (Objects.equals(ruleIdentifier.type(), "X")) {
+                return -1;
+            }
+        }
+        if (!Objects.equals(otherRuleIdentifier.unit(), getRuleIdentifier().unit())) {
+            return otherRuleIdentifier.unit() - ruleIdentifier.unit();
+        }
+        return 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/MatchedRuleHolder.java

@@ -0,0 +1,159 @@
+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 MatchedRuleHolder {
+
+    PriorityQueue<MatchedRule> getMatchedRuleList();
+
+
+    boolean isIgnored();
+
+
+    boolean isRemoved();
+
+
+    void setIgnored(boolean ignored);
+
+
+    void setRemoved(boolean ignored);
+
+
+    default boolean isApplied() {
+
+        return getMatchedRule().isApplied();
+    }
+
+
+    default Set<RedactionEntity> getReferences() {
+
+        return getMatchedRule().getReferences();
+    }
+
+
+    default boolean isActive() {
+
+        return !(isRemoved() || isIgnored());
+    }
+
+
+    default void apply(@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");
+        }
+        addMatchedRule(MatchedRule.builder().ruleIdentifier(RuleIdentifier.fromString(ruleIdentifier)).reason(reason).legalBasis(legalBasis).applied(true).build());
+    }
+
+
+    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).build());
+        setRemoved(true);
+    }
+
+
+    default void ignore(String ruleIdentifier, String reason) {
+
+        addMatchedRule(MatchedRule.builder().ruleIdentifier(RuleIdentifier.fromString(ruleIdentifier)).reason(reason).build());
+        setIgnored(true);
+    }
+
+
+    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<RedactionEntity> 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<RedactionEntity> 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) {
+
+        getMatchedRuleList().addAll(matchedRules);
+    }
+
+
+    default int getMatchedRuleUnit() {
+
+        return getMatchedRule().getRuleIdentifier().unit();
+    }
+
+
+    default MatchedRule getMatchedRule() {
+
+        if (getMatchedRuleList().isEmpty()) {
+            return MatchedRule.empty();
+        }
+        return getMatchedRuleList().peek();
+    }
+
+}

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

@@ -0,0 +1,205 @@
+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.nodes.SemanticNode;
+import com.iqser.red.service.redaction.v1.server.document.graph.Boundary;
+import com.iqser.red.service.redaction.v1.server.document.graph.nodes.Page;
+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 RedactionEntity implements MatchedRuleHolder {
+
+    // initial values
+    @EqualsAndHashCode.Include
+    final Boundary boundary;
+    @EqualsAndHashCode.Include
+    final String type;
+    @EqualsAndHashCode.Include
+    final EntityType entityType;
+
+    // empty defaults
+    boolean removed;
+    boolean ignored;
+
+    boolean resized;
+    boolean skipRemoveEntitiesContainedInLarger;
+    boolean dictionaryEntry;
+    boolean dossierDictionaryEntry;
+    @Builder.Default
+    Set<Engine> engines = new HashSet<>();
+
+    @Builder.Default
+    PriorityQueue<MatchedRule> matchedRuleList = new PriorityQueue<>();
+
+    // inferred on graph insertion
+    String value;
+    String textBefore;
+    String textAfter;
+    @Builder.Default
+    Set<Page> pages = new HashSet<>();
+    List<RedactionPosition> redactionPositionsPerPage;
+    @Builder.Default
+    List<SemanticNode> intersectingNodes = new LinkedList<>();
+    SemanticNode deepestFullyContainingNode;
+
+
+    public static RedactionEntity initialEntityNode(Boundary boundary, String type, EntityType entityType) {
+
+        return RedactionEntity.builder().type(type).entityType(entityType).boundary(boundary).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(getBoundary());
+    }
+
+
+    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<>();
+        removed = true;
+    }
+
+
+    public List<RedactionPosition> getRedactionPositionsPerPage() {
+
+        if (redactionPositionsPerPage == null || redactionPositionsPerPage.isEmpty()) {
+            Map<Page, List<Rectangle2D>> rectanglesPerLinePerPage = deepestFullyContainingNode.getTextBlock().getPositionsPerPage(boundary);
+
+            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());
+            redactionPositionsPerPage = rectanglesPerLinePerPage.entrySet().stream().map(entry -> buildRedactionPosition(firstPage, id, entry)).toList();
+        }
+        return redactionPositionsPerPage;
+    }
+
+
+    private static RedactionPosition buildRedactionPosition(Page firstPage, String id, Map.Entry<Page, List<Rectangle2D>> entry) {
+
+        if (entry.getKey().equals(firstPage)) {
+            return new RedactionPosition(id, entry.getKey(), entry.getValue());
+        } else {
+            return new RedactionPosition(id + "-" + entry.getKey().getNumber(), entry.getKey(), entry.getValue());
+        }
+    }
+
+
+    public boolean containedBy(RedactionEntity redactionEntity) {
+
+        return this.boundary.containedBy(redactionEntity.getBoundary());
+    }
+
+
+    public boolean contains(RedactionEntity redactionEntity) {
+
+        return this.boundary.contains(redactionEntity.getBoundary());
+    }
+
+
+    public boolean intersects(RedactionEntity redactionEntity) {
+
+        return this.boundary.intersects(redactionEntity.getBoundary());
+    }
+
+
+    public void addEngine(Engine engine) {
+
+        engines.add(engine);
+    }
+
+
+    public void addEngines(Set<Engine> engines) {
+
+        this.engines.addAll(engines);
+    }
+
+
+    public boolean matchesAnnotationId(String manualRedactionId) {
+
+        return getRedactionPositionsPerPage().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(boundary);
+        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/entity/RedactionPosition.java

@@ -0,0 +1,24 @@
+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 RedactionPosition {
+
+    final String id;
+    Page page;
+    // Each entry in this list corresponds to an entry in the redaction log, this means:
+    // An entity might be represented by multiple redaction log entries
+    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

@@ -0,0 +1,41 @@
+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/nodes/Document.java

@@ -0,0 +1,127 @@
+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.RedactionEntity;
+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<RedactionEntity> 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

@@ -0,0 +1,74 @@
+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.RedactionEntity;
+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<RedactionEntity> 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

@@ -0,0 +1,5 @@
+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

@@ -0,0 +1,74 @@
+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.RedactionEntity;
+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<RedactionEntity> 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

@@ -0,0 +1,95 @@
+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.RedactionEntity;
+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<RedactionEntity> 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

@@ -0,0 +1,94 @@
+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.entity.RedactionEntity;
+import com.iqser.red.service.redaction.v1.server.document.graph.DocumentTree;
+import com.iqser.red.service.redaction.v1.server.document.graph.entity.MatchedRule;
+import com.iqser.red.service.redaction.v1.server.document.graph.entity.MatchedRuleHolder;
+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, MatchedRuleHolder {
+
+    List<Integer> treeId;
+    String id;
+
+    ImageType imageType;
+    boolean transparent;
+    Rectangle2D position;
+
+    boolean removed;
+    boolean ignored;
+
+    @Builder.Default
+    PriorityQueue<MatchedRule> matchedRuleList = new PriorityQueue<>();
+
+    @EqualsAndHashCode.Exclude
+    Page page;
+
+    @EqualsAndHashCode.Exclude
+    DocumentTree documentTree;
+
+    @Builder.Default
+    @EqualsAndHashCode.Exclude
+    Set<RedactionEntity> 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;
+    }
+
+}