RED-161: reverse caseSensitive

bamboo-specs/pom.xml

@@ -5,7 +5,7 @@
   <parent>
     <groupId>com.atlassian.bamboo</groupId>
     <artifactId>bamboo-specs-parent</artifactId>
-    <version>7.1.2</version>
+    <version>7.0.4</version>
     <relativePath/>
   </parent>
 
@@ -34,4 +34,4 @@
 
   <!-- run 'mvn test' to perform offline validation of the plan -->
   <!-- run 'mvn -Ppublish-specs' to upload the plan to your Bamboo server -->
-</project>
+</project>

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

@@ -1,4 +1,4 @@
-FROM red/base-image:1.0.0
+FROM gin5/platform-base:5.2.0
 
 ARG PLATFORM_JAR
 
@@ -6,4 +6,4 @@ ENV PLATFORM_JAR ${PLATFORM_JAR}
 
 ENV USES_ELASTICSEARCH false
 
-COPY ["${PLATFORM_JAR}", "/"]
+COPY ["${PLATFORM_JAR}", "/"]

redaction-service-v1/pom.xml

@@ -5,7 +5,7 @@
     <parent>
         <artifactId>platform-dependency</artifactId>
         <groupId>com.iqser.red</groupId>
-        <version>1.0.2</version>
+        <version>1.0.1</version>
     </parent>
     <modelVersion>4.0.0</modelVersion>
 
@@ -22,7 +22,7 @@
     </modules>
 
     <properties>
-        <pdfbox.version>2.0.21</pdfbox.version>
+        <pdfbox.version>2.0.16</pdfbox.version>
     </properties>
 
 
@@ -32,21 +32,21 @@
             <dependency>
                 <groupId>com.iqser.red</groupId>
                 <artifactId>platform-commons-dependency</artifactId>
-                <version>1.1.0</version>
+                <version>1.0.0</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>
+                <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>
 

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

@@ -1,20 +0,0 @@
-package com.iqser.red.service.redaction.v1.model;
-
-import java.time.OffsetDateTime;
-
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.Data;
-import lombok.NoArgsConstructor;
-
-@Data
-@Builder
-@AllArgsConstructor
-@NoArgsConstructor
-public class Comment {
-
-    private OffsetDateTime date;
-    private String text;
-    private String user;
-
-}

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

@@ -1,24 +0,0 @@
-package com.iqser.red.service.redaction.v1.model;
-
-import java.util.ArrayList;
-import java.util.List;
-
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.Data;
-import lombok.NoArgsConstructor;
-
-@Data
-@Builder
-@AllArgsConstructor
-@NoArgsConstructor
-public class IdRemoval {
-
-    private String id;
-    private boolean approved;
-    private boolean removeFromDictionary;
-
-    @Builder.Default
-    private List<Comment> comments = new ArrayList<>();
-
-}

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

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

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

@@ -1,22 +0,0 @@
-package com.iqser.red.service.redaction.v1.model;
-
-import java.util.HashSet;
-import java.util.Set;
-
-import lombok.AllArgsConstructor;
-import lombok.Builder;
-import lombok.Data;
-import lombok.NoArgsConstructor;
-
-@Data
-@Builder
-@AllArgsConstructor
-@NoArgsConstructor
-public class ManualRedactions {
-
-    @Builder.Default
-    private Set<IdRemoval> idsToRemove = new HashSet<>();
-
-    @Builder.Default
-    private Set<ManualRedactionEntry> entriesToAdd = new HashSet<>();
-}

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

@@ -11,19 +11,6 @@ import lombok.NoArgsConstructor;
 @NoArgsConstructor
 public class RedactionLog {
 
-    public RedactionLog(List<RedactionLogEntry> redactionLogEntry, long dictionaryVersion, long rulesVersion) {
-
-        this.redactionLogEntry = redactionLogEntry;
-        this.dictionaryVersion = dictionaryVersion;
-        this.rulesVersion = rulesVersion;
-    }
-
     private List<RedactionLogEntry> redactionLogEntry;
 
-    private long dictionaryVersion = -1;
-
-    private long rulesVersion = -1;
-
-    private String filename;
-
 }

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

@@ -3,15 +3,9 @@ package com.iqser.red.service.redaction.v1.model;
 import java.util.ArrayList;
 import java.util.List;
 
-import lombok.AllArgsConstructor;
-import lombok.Builder;
 import lombok.Data;
-import lombok.NoArgsConstructor;
 
 @Data
-@Builder
-@NoArgsConstructor
-@AllArgsConstructor
 public class RedactionLogEntry {
 
     private String id;
@@ -22,11 +16,6 @@ public class RedactionLogEntry {
     private boolean isHint;
     private String section;
     private float[] color;
-
-    @Builder.Default
     private List<Rectangle> positions = new ArrayList<>();
-    private int sectionNumber;
-    private boolean manual;
-    private boolean approved;
 
 }

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

@@ -13,5 +13,4 @@ public class RedactionRequest {
 
     private byte[] document;
     private boolean flatRedaction;
-    private ManualRedactions manualRedactions;
 }

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

@@ -11,6 +11,25 @@
 
     <artifactId>redaction-service-server-v1</artifactId>
 
+    <properties>
+        <pdfbox.version>2.0.20</pdfbox.version>
+    </properties>
+
+    <dependencyManagement>
+        <dependencies>
+            <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>
+
     <dependencies>
         <dependency>
             <groupId>com.iqser.red.service</groupId>
@@ -20,7 +39,7 @@
         <dependency>
             <groupId>com.iqser.red.service</groupId>
             <artifactId>configuration-service-api-v1</artifactId>
-            <version>1.0.12</version>
+            <version>1.0.6</version>
         </dependency>
         <dependency>
             <groupId>org.drools</groupId>
@@ -37,22 +56,17 @@
             <artifactId>jts-core</artifactId>
             <version>1.16.1</version>
         </dependency>
-        <dependency>
-            <groupId>com.google.guava</groupId>
-            <artifactId>guava</artifactId>
-            <version>29.0-jre</version>
-        </dependency>
         <!-- commons -->
         <dependency>
-            <groupId>com.iqser.red.commons</groupId>
+            <groupId>com.iqser.gin4.commons</groupId>
             <artifactId>spring-commons</artifactId>
         </dependency>
         <dependency>
-            <groupId>com.iqser.red.commons</groupId>
+            <groupId>com.iqser.gin4.commons</groupId>
             <artifactId>logging-commons</artifactId>
         </dependency>
         <dependency>
-            <groupId>com.iqser.red.commons</groupId>
+            <groupId>com.iqser.gin4.commons</groupId>
             <artifactId>metric-commons</artifactId>
         </dependency>
         <!-- other external -->
@@ -85,7 +99,7 @@
             <scope>test</scope>
         </dependency>
         <dependency>
-            <groupId>com.iqser.red.commons</groupId>
+            <groupId>com.iqser.gin4.commons</groupId>
             <artifactId>test-commons</artifactId>
             <scope>test</scope>
         </dependency>

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

@@ -4,7 +4,6 @@ import java.io.ByteArrayInputStream;
 import java.io.InputStream;
 import java.nio.charset.StandardCharsets;
 
-import org.apache.commons.lang3.StringUtils;
 import org.kie.api.KieServices;
 import org.kie.api.builder.KieBuilder;
 import org.kie.api.builder.KieFileSystem;
@@ -20,10 +19,9 @@ import org.springframework.cloud.openfeign.EnableFeignClients;
 import org.springframework.context.annotation.Bean;
 import org.springframework.context.annotation.Import;
 
-import com.iqser.red.commons.spring.DefaultWebMvcConfiguration;
+import com.iqser.gin4.commons.spring.DefaultWebMvcConfiguration;
 import com.iqser.red.service.configuration.v1.api.model.RulesResponse;
 import com.iqser.red.service.redaction.v1.server.client.RulesClient;
-import com.iqser.red.service.redaction.v1.server.exception.RulesValidationException;
 import com.iqser.red.service.redaction.v1.server.settings.RedactionServiceSettings;
 
 @Import({DefaultWebMvcConfiguration.class})
@@ -35,35 +33,24 @@ public class Application {
     @Autowired
     private RulesClient rulesClient;
 
-
     public static void main(String[] args) {
-
         SpringApplication.run(Application.class, args);
     }
 
-
     @Bean
     public KieContainer kieContainer() {
 
-        try {
-            KieServices kieServices = KieServices.Factory.get();
+        KieServices kieServices = KieServices.Factory.get();
 
-            KieFileSystem kieFileSystem = kieServices.newKieFileSystem();
-            RulesResponse rules = rulesClient.getRules();
-            if (StringUtils.isEmpty(rules.getRules())) {
-                throw new RuntimeException("Rules cannot be empty.");
-            }
-            InputStream input = new ByteArrayInputStream(rules.getRules().getBytes(StandardCharsets.UTF_8));
-            kieFileSystem.write("src/main/resources/drools/rules.drl", kieServices.getResources()
-                    .newInputStreamResource(input));
-            KieBuilder kieBuilder = kieServices.newKieBuilder(kieFileSystem);
-            kieBuilder.buildAll();
-            KieModule kieModule = kieBuilder.getKieModule();
+        KieFileSystem kieFileSystem = kieServices.newKieFileSystem();
+        RulesResponse rules = rulesClient.getRules();
+        InputStream input = new ByteArrayInputStream(rules.getRules().getBytes(StandardCharsets.UTF_8));
+        kieFileSystem.write("src/main/resources/drools/rules.drl", kieServices.getResources().newInputStreamResource(input));
+        KieBuilder kieBuilder = kieServices.newKieBuilder(kieFileSystem);
+        kieBuilder.buildAll();
+        KieModule kieModule = kieBuilder.getKieModule();
 
-            return kieServices.newKieContainer(kieModule.getReleaseId());
-        } catch (Exception e) {
-            throw new RulesValidationException("Could not update rules: " + e.getMessage(), e);
-        }
+        return kieServices.newKieContainer(kieModule.getReleaseId());
 
     }
 

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

@@ -4,6 +4,7 @@ import java.util.ArrayList;
 import java.util.HashMap;
 import java.util.List;
 import java.util.Map;
+import java.util.Set;
 
 import com.iqser.red.service.redaction.v1.model.RedactionLogEntry;
 import com.iqser.red.service.redaction.v1.server.redaction.model.Entity;
@@ -17,7 +18,7 @@ public class Document {
 
     private List<Page> pages = new ArrayList<>();
     private List<Paragraph> paragraphs = new ArrayList<>();
-    private Map<Integer, List<Entity>> entities = new HashMap<>();
+    private Map<Integer, Set<Entity>> entities = new HashMap<>();
     private FloatFrequencyCounter textHeightCounter = new FloatFrequencyCounter();
     private FloatFrequencyCounter fontSizeCounter= new FloatFrequencyCounter();
     private StringFrequencyCounter fontCounter= new StringFrequencyCounter();

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

@@ -10,6 +10,7 @@ import com.iqser.red.service.redaction.v1.server.tableextraction.model.Table;
 import lombok.Data;
 import lombok.NoArgsConstructor;
 
+
 @Data
 @NoArgsConstructor
 public class Paragraph {
@@ -17,12 +18,10 @@ public class Paragraph {
     private List<AbstractTextContainer> pageBlocks = new ArrayList<>();
     private String headline;
 
-
-    public SearchableText getSearchableText() {
-
+    public SearchableText getSearchableText(){
         SearchableText searchableText = new SearchableText();
         pageBlocks.forEach(block -> {
-            if (block instanceof TextBlock) {
+            if(block instanceof TextBlock){
                 searchableText.addAll(((TextBlock) block).getSequences());
             }
         });
@@ -30,27 +29,14 @@ public class Paragraph {
     }
 
 
-    public List<Table> getTables() {
-
+    public List<Table> getTables(){
         List<Table> tables = new ArrayList<>();
         pageBlocks.forEach(block -> {
-            if (block instanceof Table) {
+            if(block instanceof Table){
                 tables.add((Table) block);
             }
         });
         return tables;
     }
 
-
-    public List<TextBlock> getTextBlocks() {
-
-        List<TextBlock> textBlocks = new ArrayList<>();
-        pageBlocks.forEach(block -> {
-            if (block instanceof TextBlock) {
-                textBlocks.add((TextBlock) block);
-            }
-        });
-        return textBlocks;
-    }
-
-}
+}

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

@@ -5,45 +5,43 @@ import java.util.Map;
 
 import lombok.Getter;
 
+/**
+ *
+ */
 public class StringFrequencyCounter {
 
     @Getter
-    private final Map<String, Integer> countPerValue = new HashMap<>();
+    Map<String, Integer> countPerValue = new HashMap<>();
 
-
-    public void add(String value) {
-
-        if (!countPerValue.containsKey(value)) {
+    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());
+    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() {
-
+    public String getMostPopular(){
         Map.Entry<String, Integer> mostPopular = null;
-        for (Map.Entry<String, Integer> entry : countPerValue.entrySet()) {
-            if (mostPopular == null) {
+        for(Map.Entry<String, Integer> entry: countPerValue.entrySet()){
+            if(mostPopular == null){
                 mostPopular = entry;
-            } else if (entry.getValue() > mostPopular.getValue()) {
+            } else if(entry.getValue() > mostPopular.getValue()){
                 mostPopular = entry;
             }
         }
         return mostPopular != null ? mostPopular.getKey() : null;
     }
 
-}
+
+}

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

@@ -131,7 +131,7 @@ public class TextBlock extends AbstractTextContainer {
         TextPositionSequence previous = null;
         for (TextPositionSequence word : sequences) {
             if (previous != null) {
-                if (Math.abs(previous.getRotationAdjustedY() - word.getRotationAdjustedY()) > word.getTextHeight()) {
+                if (Math.abs(previous.getY1() - word.getY1()) > word.getTextHeight()) {
                     sb.append('\n');
                 } else {
                     sb.append(' ');

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

@@ -29,16 +29,20 @@ public class BlockificationService {
         float minX = 1000, maxX = 0, minY = 1000, maxY = 0;
         TextPositionSequence prev = null;
 
+
         for (TextPositionSequence word : textPositions) {
 
             boolean lineSeparation = minY - word.getY2() > word.getHeight() * 1.25;
             boolean startFromTop = word.getY1() > maxY + word.getHeight();
 
-            if (prev != null && (lineSeparation || startFromTop || word.getRotation() == 0 && isSplittedByRuling(maxX, minY, word
-                    .getX1(), word.getY1(), verticalRulingLines) || word.getRotation() == 0 && isSplittedByRuling(minX, minY, word
-                    .getX1(), word.getY2(), horizontalRulingLines) || word.getRotation() == 90 && isSplittedByRuling(maxX, minY, word
-                    .getX1(), word.getY1(), horizontalRulingLines) || word.getRotation() == 90 && isSplittedByRuling(minX, minY, word
-                    .getX1(), word.getY2(), verticalRulingLines))) {
+            if (prev != null &&
+                    (lineSeparation
+                            || startFromTop
+                            || word.getRotation() == 0 && isSplittedByRuling(maxX, minY, word.getX1(), word.getY1(), verticalRulingLines)
+                            || word.getRotation() == 0 && isSplittedByRuling(minX, minY, word.getX1(), word.getY2(), horizontalRulingLines)
+                            || word.getRotation() == 90 && isSplittedByRuling(maxX, minY, word.getX1(), word.getY1(), horizontalRulingLines)
+                            || word.getRotation() == 90 && isSplittedByRuling(minX, minY, word.getX1(), word.getY2(), verticalRulingLines)
+                    )) {
 
                 TextBlock cb1 = buildTextBlock(chunkWords);
                 chunkBlockList1.add(cb1);
@@ -96,12 +100,11 @@ public class BlockificationService {
             styleFrequencyCounter.add(wordBlock.getFontStyle());
 
             if (textBlock == null) {
-                textBlock = new TextBlock(wordBlock.getX1(), wordBlock.getX2(), wordBlock.getY1(), wordBlock.getY2(), wordBlockList, wordBlock
-                        .getRotation());
+                textBlock = new TextBlock(wordBlock.getX1(), wordBlock.getX2(), wordBlock.getY1(), wordBlock.getY2(), wordBlockList, wordBlock.getRotation());
             } else {
                 TextBlock spatialEntity = textBlock.union(wordBlock);
-                textBlock.resize(spatialEntity.getMinX(), spatialEntity.getMinY(), spatialEntity.getWidth(), spatialEntity
-                        .getHeight());
+                textBlock.resize(spatialEntity.getMinX(), spatialEntity.getMinY(),
+                        spatialEntity.getWidth(), spatialEntity.getHeight());
             }
         }
 
@@ -119,7 +122,6 @@ public class BlockificationService {
 
 
     private boolean isSplittedByRuling(float previousX2, float previousY1, float currentX1, float currentY1, List<Ruling> rulingLines) {
-
         for (Ruling ruling : rulingLines) {
             if (ruling.intersectsLine(previousX2, previousY1, currentX1, currentY1)) {
                 return true;
@@ -131,6 +133,7 @@ public class BlockificationService {
 
     public Rectangle calculateBodyTextFrame(List<Page> pages, FloatFrequencyCounter documentFontSizeCounter, boolean landscape) {
 
+
         float minX = 10000;
         float maxX = -100;
         float minY = 10000;
@@ -144,6 +147,7 @@ public class BlockificationService {
 
             for (AbstractTextContainer container : page.getTextBlocks()) {
 
+
                 if (container instanceof TextBlock) {
                     TextBlock textBlock = (TextBlock) container;
                     if (textBlock.getMostPopularWordFont() == null || textBlock.getMostPopularWordStyle() == null) {
@@ -175,15 +179,16 @@ public class BlockificationService {
                     }
                 }
 
+
                 if (container instanceof Table) {
                     Table table = (Table) container;
                     for (List<Cell> row : table.getRows()) {
-                        for (Cell cell : row) {
+                        for (Cell column : row) {
 
-                            if (cell == null || cell.getTextBlocks() == null) {
+                            if (column == null || column.getTextBlocks() == null) {
                                 continue;
                             }
-                            for (TextBlock textBlock : cell.getTextBlocks()) {
+                            for (TextBlock textBlock : column.getTextBlocks()) {
                                 if (textBlock.getMinX() < minX) {
                                     minX = textBlock.getMinX();
                                 }
@@ -206,4 +211,5 @@ public class BlockificationService {
         return new Rectangle(minY, minX, maxX - minX, maxY - minY);
     }
 
+
 }

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

@@ -84,7 +84,7 @@ public class ClassificationService {
         }
         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)){
+        } else if (PositionUtils.isWithinBodyTextFrame(bodyTextFrame, textBlock) && textBlock.getSequences().size() > 3){
             textBlock.setClassification("TextBlock Unknown");
         }
     }

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

@@ -2,13 +2,13 @@ package com.iqser.red.service.redaction.v1.server.controller;
 
 import java.time.OffsetDateTime;
 
-import com.iqser.red.commons.spring.ErrorMessage;
 import org.springframework.http.HttpStatus;
 import org.springframework.web.bind.annotation.ExceptionHandler;
 import org.springframework.web.bind.annotation.ResponseBody;
 import org.springframework.web.bind.annotation.ResponseStatus;
 import org.springframework.web.bind.annotation.RestControllerAdvice;
 
+import com.iqser.gin4.commons.api.errorhandling.ErrorMessage;
 import com.iqser.red.service.redaction.v1.server.exception.RulesValidationException;
 
 import lombok.extern.slf4j.Slf4j;

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

@@ -3,21 +3,18 @@ package com.iqser.red.service.redaction.v1.server.controller;
 import java.io.ByteArrayInputStream;
 import java.io.ByteArrayOutputStream;
 import java.io.IOException;
-import java.util.List;
 
 import org.apache.pdfbox.pdmodel.PDDocument;
 import org.springframework.web.bind.annotation.RequestBody;
 import org.springframework.web.bind.annotation.RestController;
 
 import com.iqser.red.service.redaction.v1.model.RedactionLog;
-import com.iqser.red.service.redaction.v1.model.RedactionLogEntry;
 import com.iqser.red.service.redaction.v1.model.RedactionRequest;
 import com.iqser.red.service.redaction.v1.model.RedactionResult;
 import com.iqser.red.service.redaction.v1.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.redaction.service.DictionaryService;
 import com.iqser.red.service.redaction.v1.server.redaction.service.DroolsExecutionService;
 import com.iqser.red.service.redaction.v1.server.redaction.service.EntityRedactionService;
 import com.iqser.red.service.redaction.v1.server.segmentation.PdfSegmentationService;
@@ -39,7 +36,6 @@ public class RedactionController implements RedactionResource {
     private final EntityRedactionService entityRedactionService;
     private final PdfFlattenService pdfFlattenService;
     private final DroolsExecutionService droolsExecutionService;
-    private final DictionaryService dictionaryService;
 
     @Override
     public RedactionResult redact(@RequestBody RedactionRequest redactionRequest) {
@@ -48,15 +44,15 @@ public class RedactionController implements RedactionResource {
             pdDocument.setAllSecurityToBeRemoved(true);
 
             Document classifiedDoc = pdfSegmentationService.parseDocument(pdDocument);
-            entityRedactionService.processDocument(classifiedDoc, redactionRequest.getManualRedactions());
-            annotationHighlightService.highlight(pdDocument, classifiedDoc, redactionRequest.isFlatRedaction(), redactionRequest.getManualRedactions());
+            entityRedactionService.processDocument(classifiedDoc);
+            annotationHighlightService.highlight(pdDocument, classifiedDoc, redactionRequest.isFlatRedaction());
 
             if (redactionRequest.isFlatRedaction()) {
                 PDDocument flatDocument = pdfFlattenService.flattenPDF(pdDocument);
-                return convert(flatDocument, classifiedDoc.getPages().size(), classifiedDoc.getRedactionLogEntities());
+                return convert(flatDocument, classifiedDoc.getPages().size(), new RedactionLog(classifiedDoc.getRedactionLogEntities()));
             }
 
-            return convert(pdDocument, classifiedDoc.getPages().size(), classifiedDoc.getRedactionLogEntities());
+            return convert(pdDocument, classifiedDoc.getPages().size(), new RedactionLog(classifiedDoc.getRedactionLogEntities()));
 
         } catch (IOException e) {
             throw new RedactionException(e);
@@ -134,14 +130,14 @@ public class RedactionController implements RedactionResource {
         return convert(document, numberOfPages, null);
     }
 
-    private RedactionResult convert(PDDocument document, int numberOfPages, List<RedactionLogEntry> redactionLogEntities) throws IOException {
+    private RedactionResult convert(PDDocument document, int numberOfPages, RedactionLog redactionLog) throws IOException {
 
         try (ByteArrayOutputStream byteArrayOutputStream = new ByteArrayOutputStream()) {
             document.save(byteArrayOutputStream);
             return RedactionResult.builder()
                     .document(byteArrayOutputStream.toByteArray())
                     .numberOfPages(numberOfPages)
-                    .redactionLog(new RedactionLog(redactionLogEntities,  dictionaryService.getDictionaryVersion(), droolsExecutionService.getRulesVersion()))
+                    .redactionLog(redactionLog)
                     .build();
         }
 

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

@@ -44,10 +44,10 @@ import lombok.extern.slf4j.Slf4j;
 public class PDFLinesTextStripper extends PDFTextStripper {
 
     @Getter
-    private int maxCharWidths;
+    private float minCharWidth = Float.MAX_VALUE;
 
     @Getter
-    private int maxCharHeight;
+    private float minCharHeight = Float.MAX_VALUE;
 
     @Getter
     private final List<TextPositionSequence> textPositionSequences = new ArrayList<>();
@@ -201,16 +201,8 @@ public class PDFLinesTextStripper extends PDFTextStripper {
 
         int startIndex = 0;
         for (int i = 0; i <= textPositions.size() - 1; i++) {
-
-            int charHeight = (int) textPositions.get(i).getHeightDir();
-            if(charHeight > maxCharHeight){
-                maxCharHeight = charHeight;
-            }
-
-            int charWidth = (int) textPositions.get(i).getWidthDirAdj();
-            if(charWidth > maxCharWidths){
-                maxCharWidths = charWidth;
-            }
+            minCharWidth = Math.min(minCharWidth, textPositions.get(i).getWidthDirAdj());
+            minCharHeight = Math.min(minCharHeight, textPositions.get(i).getHeightDir());
 
             if (i == 0 && textPositions.get(i).getUnicode().equals(" ")) {
                 startIndex++;
@@ -249,8 +241,8 @@ public class PDFLinesTextStripper extends PDFTextStripper {
     @Override
     public String getText(PDDocument doc) throws IOException {
 
-        maxCharWidths = 0;
-        maxCharWidths = 0;
+        minCharWidth = Float.MAX_VALUE;
+        minCharHeight = Float.MAX_VALUE;
         textPositionSequences.clear();
         rulings.clear();
         graphicsPath.clear();

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

@@ -17,6 +17,6 @@ public class ParsedElements {
     private boolean landscape;
     private boolean rotated;
 
-    private float maxCharWidth;
-    private float maxCharHeight;
+    private float minCharWidth;
+    private float minCharHeight;
 }

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

@@ -5,11 +5,10 @@ import java.util.List;
 
 import org.apache.pdfbox.text.TextPosition;
 
-import com.iqser.red.service.redaction.v1.model.Point;
-import com.iqser.red.service.redaction.v1.model.Rectangle;
-
 import lombok.Data;
+import lombok.Getter;
 import lombok.RequiredArgsConstructor;
+import lombok.Setter;
 
 @Data
 @RequiredArgsConstructor
@@ -17,50 +16,36 @@ public class TextPositionSequence implements CharSequence {
 
     private List<TextPosition> textPositions = new ArrayList<>();
 
+    @Getter
+    @Setter
+    private float[] annotationColor;
+
     private final int page;
 
-
-    public TextPositionSequence(List<TextPosition> textPositions, int page) {
-
+    public TextPositionSequence(List<TextPosition> textPositions, int page){
         this.textPositions = textPositions;
         this.page = page;
     }
 
-
     @Override
     public int length() {
-
         return textPositions.size();
     }
 
-
     @Override
     public char charAt(int index) {
-
         TextPosition textPosition = textPositionAt(index);
         String text = textPosition.getUnicode();
         return text.charAt(0);
     }
 
-
-    public char charAt(int index, boolean caseInSensitive) {
-
-        TextPosition textPosition = textPositionAt(index);
-        String text = textPosition.getUnicode();
-        return caseInSensitive ? text.toLowerCase().charAt(0) : text.charAt(0);
-    }
-
-
     @Override
     public TextPositionSequence subSequence(int start, int end) {
-
         return new TextPositionSequence(textPositions.subList(start, end), page);
     }
 
-
     @Override
     public String toString() {
-
         StringBuilder builder = new StringBuilder(length());
         for (int i = 0; i < length(); i++) {
             builder.append(charAt(i));
@@ -68,21 +53,15 @@ public class TextPositionSequence implements CharSequence {
         return builder.toString();
     }
 
-
     public TextPosition textPositionAt(int index) {
-
         return textPositions.get(index);
     }
 
-
     public void add(TextPosition textPosition) {
-
         this.textPositions.add(textPosition);
     }
 
-
     public float getX1() {
-
         if (textPositions.get(0).getRotation() == 90) {
             return textPositions.get(0).getYDirAdj() - getTextHeight();
         } else {
@@ -90,23 +69,15 @@ public class TextPositionSequence implements CharSequence {
         }
     }
 
-
     public float getX2() {
-
         if (textPositions.get(0).getRotation() == 90) {
             return textPositions.get(0).getYDirAdj();
         } else {
-            return textPositions.get(textPositions.size() - 1)
-                    .getXDirAdj() + textPositions.get(textPositions.size() - 1).getWidth() + 1;
+            return textPositions.get(textPositions.size() - 1).getXDirAdj() + textPositions.get(textPositions.size() - 1).getWidth() + 1;
         }
     }
 
-    public float getRotationAdjustedY() {
-        return textPositions.get(0).getY();
-    }
-
     public float getY1() {
-
         if (textPositions.get(0).getRotation() == 90) {
             return textPositions.get(0).getXDirAdj();
         } else {
@@ -114,46 +85,30 @@ public class TextPositionSequence implements CharSequence {
         }
     }
 
-
     public float getY2() {
-
         if (textPositions.get(0).getRotation() == 90) {
-            return textPositions.get(textPositions.size() - 1).getXDirAdj() + getTextHeight() - 2;
+            return textPositions.get(textPositions.size() - 1).getXDirAdj() + getTextHeight() -2 ;
         } else {
             return textPositions.get(0).getPageHeight() - textPositions.get(0).getYDirAdj() + getTextHeight();
         }
     }
 
-
     public float getTextHeight() {
-
         return textPositions.get(0).getHeightDir() + 2;
     }
 
-
     public float getHeight() {
-
         return getY2() - getY1();
     }
 
-
     public float getWidth() {
-
         return getX2() - getX1();
     }
 
-
     public String getFont() {
-
-        return textPositions.get(0)
-                .getFont()
-                .toString()
-                .toLowerCase()
-                .replaceAll(",bold", "")
-                .replaceAll(",italic", "");
+        return textPositions.get(0).getFont().toString().toLowerCase().replaceAll(",bold", "").replaceAll(",italic", "");
     }
 
-
     public String getFontStyle() {
 
         String lowercaseFontName = textPositions.get(0).getFont().toString().toLowerCase();
@@ -170,48 +125,16 @@ public class TextPositionSequence implements CharSequence {
 
     }
 
-
     public float getFontSize() {
-
         return textPositions.get(0).getFontSizeInPt();
     }
 
-
     public float getSpaceWidth() {
-
         return textPositions.get(0).getWidthOfSpace();
     }
 
-
     public int getRotation() {
-
         return textPositions.get(0).getRotation();
     }
 
-
-    public Rectangle getRectangle() {
-
-        float height = getTextHeight();
-
-        float posXInit = getX1();
-        float posXEnd;
-        float posYInit;
-        float posYEnd;
-
-        if (textPositions.get(0).getRotation() == 90) {
-            posXEnd = textPositions.get(0).getYDirAdj() + 2;
-            posYInit = getY1();
-            posYEnd = textPositions.get(textPositions.size() - 1).getXDirAdj() - height + 4;
-        } else {
-            posXEnd = textPositions.get(textPositions.size() - 1)
-                    .getXDirAdj() + textPositions.get(textPositions.size() - 1).getWidth() + 1;
-            posYInit = textPositions.get(0).getPageHeight() - textPositions.get(0).getYDirAdj() - 2;
-            posYEnd = textPositions.get(0).getPageHeight() - textPositions.get(textPositions.size() - 1)
-                    .getYDirAdj() + 2;
-        }
-
-        return new Rectangle(new Point(posXInit, posYInit), posXEnd - posXInit, posYEnd - posYInit + height, page);
-    }
-
-
 }

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

@@ -1,40 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.redaction.model;
-
-import com.iqser.red.service.redaction.v1.server.classification.model.TextBlock;
-import com.iqser.red.service.redaction.v1.server.parsing.model.TextPositionSequence;
-import com.iqser.red.service.redaction.v1.server.redaction.utils.TextNormalizationUtilities;
-
-import lombok.Value;
-
-@Value
-public class CellValue {
-
-    TextBlock textBlock;
-
-    int rowSpanStart;
-
-
-    @Override
-    public String toString() {
-
-        StringBuilder sb = new StringBuilder();
-
-        TextPositionSequence previous = null;
-        for (TextPositionSequence word : textBlock.getSequences()) {
-            if (previous != null) {
-                if (Math.abs(previous.getRotationAdjustedY() - word.getRotationAdjustedY()) > word.getTextHeight()) {
-                    sb.append('\n');
-                } else {
-                    sb.append(' ');
-                }
-            }
-            sb.append(word.toString());
-            previous = word;
-        }
-
-        return TextNormalizationUtilities.removeHyphenLineBreaks(sb.toString())
-                .replaceAll("\n", " ")
-                .replaceAll(" {2}", " ");
-    }
-
-}

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

@@ -1,37 +1,25 @@
 package com.iqser.red.service.redaction.v1.server.redaction.model;
 
+
 import java.util.ArrayList;
 import java.util.List;
 
-import com.iqser.red.service.redaction.v1.server.parsing.model.TextPositionSequence;
-
 import lombok.Data;
-import lombok.EqualsAndHashCode;
 
 @Data
-@EqualsAndHashCode(onlyExplicitlyIncluded = true)
 public class Entity {
 
-    @EqualsAndHashCode.Include
     private final String word;
     private final String type;
     private boolean redaction;
     private String redactionReason;
     private List<EntityPositionSequence> positionSequences = new ArrayList<>();
-    private List<TextPositionSequence> targetSequences;
     private Integer start;
     private Integer end;
-
-    @EqualsAndHashCode.Include
     private String headline;
     private int matchedRule;
 
-    @EqualsAndHashCode.Include
-    private int sectionNumber;
-
-
-    public Entity(String word, String type, boolean redaction, String redactionReason, List<EntityPositionSequence> positionSequences, String headline, int matchedRule, int sectionNumber) {
-
+    public Entity(String word, String type, boolean redaction, String redactionReason, List<EntityPositionSequence> positionSequences, String headline, int matchedRule) {
         this.word = word;
         this.type = type;
         this.redaction = redaction;
@@ -39,18 +27,13 @@ public class Entity {
         this.positionSequences = positionSequences;
         this.headline = headline;
         this.matchedRule = matchedRule;
-        this.sectionNumber = sectionNumber;
     }
 
-
-    public Entity(String word, String type, Integer start, Integer end, String headline, int sectionNumber) {
-
+    public Entity(String word, String type, Integer start, Integer end, String headline) {
         this.word = word;
         this.type = type;
         this.start = start;
         this.end = end;
         this.headline = headline;
-        this.sectionNumber = sectionNumber;
     }
-
 }

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

@@ -2,23 +2,19 @@ package com.iqser.red.service.redaction.v1.server.redaction.model;
 
 import java.util.ArrayList;
 import java.util.List;
+import java.util.UUID;
 
 import com.iqser.red.service.redaction.v1.server.parsing.model.TextPositionSequence;
 
-import lombok.AllArgsConstructor;
 import lombok.Data;
-import lombok.EqualsAndHashCode;
 import lombok.RequiredArgsConstructor;
 
+
 @Data
 @RequiredArgsConstructor
-@AllArgsConstructor
-@EqualsAndHashCode
 public class EntityPositionSequence {
 
-    @EqualsAndHashCode.Exclude
     private List<TextPositionSequence> sequences = new ArrayList<>();
     private int pageNumber;
-    private final String id;
-
+    private final UUID id;
 }

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

@@ -1,98 +1,57 @@
 package com.iqser.red.service.redaction.v1.server.redaction.model;
 
 import java.util.ArrayList;
-import java.util.Collections;
 import java.util.List;
+import java.util.UUID;
 import java.util.regex.Pattern;
 
 import com.iqser.red.service.redaction.v1.server.parsing.model.TextPositionSequence;
-import com.iqser.red.service.redaction.v1.server.redaction.utils.IdBuilder;
 import com.iqser.red.service.redaction.v1.server.redaction.utils.TextNormalizationUtilities;
 
+@SuppressWarnings("all")
 public class SearchableText {
 
-    private final List<TextPositionSequence> sequences = new ArrayList<>();
-
+    private List<TextPositionSequence> sequences = new ArrayList<>();
 
     public void add(TextPositionSequence textPositionSequence) {
-
         sequences.add(textPositionSequence);
     }
 
-
     public void addAll(List<TextPositionSequence> textPositionSequences) {
-
         sequences.addAll(textPositionSequences);
     }
 
 
-    public List<EntityPositionSequence> getSequences(String searchString, boolean caseInsensitive) {
+    public List<EntityPositionSequence> getSequences(String searchString) {
 
-        return getSequences(searchString, caseInsensitive, null);
-
-    }
-
-    @SuppressWarnings("checkstyle:ModifiedControlVariable")
-    public List<EntityPositionSequence> getSequences(String searchString, boolean caseInsensitive,
-                                                     List<TextPositionSequence> sequencesSubList) {
-
-        String normalizedSearchString;
-        if (caseInsensitive) {
-            normalizedSearchString = searchString.toLowerCase();
-        } else {
-            normalizedSearchString = searchString;
-        }
-
-        char[] searchChars = normalizedSearchString.replaceAll("\\n", " ").toCharArray();
+        char[] searchChars = searchString.replaceAll("\\n", " ").toCharArray();
         int counter = 0;
 
+
         List<TextPositionSequence> crossSequenceParts = new ArrayList<>();
         List<EntityPositionSequence> finalMatches = new ArrayList<>();
+        for (int i = 0; i < sequences.size(); i++) {
+            TextPositionSequence partMatch = new TextPositionSequence(sequences.get(i).getPage());
+            for (int j = 0; j < sequences.get(i).length(); j++) {
 
-        List<TextPositionSequence> searchSpace;
-        if (sequencesSubList != null) {
-            int subListIndex = Collections.indexOfSubList(sequences, sequencesSubList);
-            if (subListIndex != -1) {
-                searchSpace = sequences.subList(subListIndex, subListIndex + sequencesSubList.size());
-            } else {
-                searchSpace = sequences;
-            }
-        } else {
-            searchSpace = sequences;
-        }
-
-        for (int i = 0; i < searchSpace.size(); i++) {
-            TextPositionSequence partMatch = new TextPositionSequence(searchSpace.get(i).getPage());
-            for (int j = 0; j < searchSpace.get(i).length(); j++) {
-
-                if (i > 0 && j == 0 && searchSpace.get(i).charAt(0, caseInsensitive) == ' ' && searchSpace.get(i - 1)
-                        .charAt(searchSpace.get(i - 1).length() - 1, caseInsensitive) == ' ' || j > 0 && searchSpace.get(i)
-                        .charAt(j, caseInsensitive) == ' ' && searchSpace.get(i).charAt(j - 1, caseInsensitive) == ' ') {
-                    if (j == searchSpace.get(i).length() - 1 && counter != 0 && !partMatch.getTextPositions().isEmpty()) {
+                if(i > 0 && j == 0 && sequences.get(i).charAt(0) == ' ' && sequences.get(i - 1).charAt(sequences.get(i - 1).length() - 1) == ' '
+                || j > 0 && sequences.get(i).charAt(j) == ' ' && sequences.get(i).charAt(j - 1) == ' '){
+                    if(j == sequences.get(i).length() -1  && counter != 0 && !partMatch.getTextPositions().isEmpty()){
                         crossSequenceParts.add(partMatch);
                     }
                     continue;
                 }
 
-                if (j == 0 && searchSpace.get(i).charAt(j, caseInsensitive) != ' ' && i != 0 && searchSpace.get(i - 1)
-                        .charAt(searchSpace.get(i - 1)
-                                .length() - 1, caseInsensitive) != ' ' && searchChars[counter] == ' ') {
+                if(j == 0 && sequences.get(i).charAt(j) != ' ' && i != 0 && sequences.get(i - 1).charAt(sequences.get(i - 1).length() -1) != ' ' && searchChars[counter] == ' '){
                     counter++;
                 }
 
-                if (searchSpace.get(i)
-                        .charAt(j, caseInsensitive) == searchChars[counter] || counter != 0 && searchSpace.get(i)
-                        .charAt(j, caseInsensitive) == '-') {
+                if (sequences.get(i).charAt(j) == searchChars[counter] || counter != 0 && sequences.get(i).charAt(j) == '-') {
 
-                    if (counter != 0 || i == 0 && j == 0 || j != 0 && isSeparator(searchSpace.get(i)
-                            .charAt(j - 1, caseInsensitive)) || j == 0 && i != 0 && isSeparator(searchSpace.get(i - 1)
-                            .charAt(searchSpace.get(i - 1)
-                                    .length() - 1, caseInsensitive)) || j == 0 && i != 0 && searchSpace.get(i - 1)
-                            .charAt(searchSpace.get(i - 1).length() - 1, caseInsensitive) != ' ' && searchSpace.get(i)
-                            .charAt(j, caseInsensitive) != ' ') {
-                        partMatch.add(searchSpace.get(i).textPositionAt(j));
-                        if (!(j == searchSpace.get(i).length() - 1 && searchSpace.get(i)
-                                .charAt(j, caseInsensitive) == '-' && searchChars[counter] != '-')) {
+                    if(counter != 0 || i == 0 && j == 0 || j != 0 && isSeparator(sequences.get(i).charAt(j - 1)) || j == 0 && i != 0 && isSeparator(sequences.get(i - 1).charAt(sequences.get(i - 1).length() -1))
+                            || j == 0 && i != 0 && sequences.get(i - 1).charAt(sequences.get(i - 1).length() -1) != ' ' && sequences.get(i).charAt(j) != ' ') {
+                        partMatch.add(sequences.get(i).textPositionAt(j));
+                        if (!(j == sequences.get(i).length() -1 && sequences.get(i).charAt(j) == '-' && searchChars[counter] != '-')) {
                             counter++;
                         }
                     }
@@ -100,63 +59,53 @@ public class SearchableText {
                     if (counter == searchString.length()) {
                         crossSequenceParts.add(partMatch);
 
-                        if (i == searchSpace.size() - 1 && j == searchSpace.get(i).length() - 1 || j != searchSpace.get(i)
-                                .length() - 1 && isSeparator(searchSpace.get(i)
-                                .charAt(j + 1, caseInsensitive)) || j == searchSpace.get(i)
-                                .length() - 1 && isSeparator(searchSpace.get(i + 1)
-                                .charAt(0, caseInsensitive)) || j == searchSpace.get(i).length() - 1 && searchSpace.get(i)
-                                .charAt(j, caseInsensitive) != ' ' && searchSpace.get(i + 1)
-                                .charAt(0, caseInsensitive) != ' ') {
+                        if(i == sequences.size() - 1 && j == sequences.get(i).length() -1
+                                || j != sequences.get(i).length() -1 && isSeparator(sequences.get(i).charAt(j +1))
+                                || j == sequences.get(i).length() -1 && isSeparator(sequences.get(i + 1).charAt(0))
+                                || j == sequences.get(i).length() -1 && sequences.get(i).charAt(j) != ' ' && sequences.get(i + 1).charAt(0) != ' ') {
                             finalMatches.addAll(buildEntityPositionSequence(crossSequenceParts));
                         }
 
                         counter = 0;
                         crossSequenceParts = new ArrayList<>();
-                        partMatch = new TextPositionSequence(searchSpace.get(i).getPage());
+                        partMatch = new TextPositionSequence(sequences.get(i).getPage());
                     }
                 } else {
                     counter = 0;
-                    if (!crossSequenceParts.isEmpty()) {
+                    if(!crossSequenceParts.isEmpty()){
                         j--;
                     }
                     crossSequenceParts = new ArrayList<>();
-                    partMatch = new TextPositionSequence(searchSpace.get(i).getPage());
+                    partMatch = new TextPositionSequence(sequences.get(i).getPage());
                 }
 
-                if (j == searchSpace.get(i).length() - 1 && counter != 0) {
+                if(j == sequences.get(i).length() -1  && counter != 0){
                     crossSequenceParts.add(partMatch);
                 }
             }
         }
 
         return finalMatches;
-
     }
 
 
-    private List<EntityPositionSequence> buildEntityPositionSequence(List<TextPositionSequence> crossSequenceParts) {
+    private List<EntityPositionSequence> buildEntityPositionSequence(List<TextPositionSequence> crossSequenceParts){
 
-        String plainId = IdBuilder.buildId(crossSequenceParts);
-        String id = plainId;
+        UUID id = UUID.randomUUID();
         List<EntityPositionSequence> result = new ArrayList<>();
         int currentPage = -1;
-        int idDiffentPageSuffix = 1;
         EntityPositionSequence entityPositionSequence = new EntityPositionSequence(id);
-        for (TextPositionSequence textPositionSequence : crossSequenceParts) {
-            if (currentPage == -1) {
+        for (TextPositionSequence textPositionSequence :crossSequenceParts){
+            if(currentPage == -1){
                 currentPage = textPositionSequence.getPage();
                 entityPositionSequence.setPageNumber(currentPage);
                 entityPositionSequence.getSequences().add(textPositionSequence);
-            } else if (currentPage == textPositionSequence.getPage()) {
+            } else if(currentPage == textPositionSequence.getPage()){
                 entityPositionSequence.getSequences().add(textPositionSequence);
             } else {
-                id = plainId + "-" + idDiffentPageSuffix;
-                idDiffentPageSuffix++;
                 result.add(entityPositionSequence);
                 entityPositionSequence = new EntityPositionSequence(id);
                 entityPositionSequence.setPageNumber(textPositionSequence.getPage());
-                entityPositionSequence.getSequences().add(textPositionSequence);
-                currentPage = textPositionSequence.getPage();
             }
         }
         result.add(entityPositionSequence);
@@ -165,21 +114,20 @@ public class SearchableText {
 
 
     private boolean isSeparator(char c) {
-
         return Character.isWhitespace(c) || Pattern.matches("\\p{Punct}", String.valueOf(c)) || c == '\"' || c == '‘' || c == '’';
     }
 
 
+
     @Override
     public String toString() {
-
         StringBuilder sb = new StringBuilder();
 
         TextPositionSequence previous = null;
         for (TextPositionSequence word : sequences) {
 
             if (previous != null) {
-                if (Math.abs(previous.getRotationAdjustedY() - word.getRotationAdjustedY()) > word.getTextHeight()) {
+                if (Math.abs(previous.getY1() - word.getY1()) > word.getTextHeight()) {
                     sb.append('\n');
                 } else {
                     sb.append(' ');
@@ -189,21 +137,17 @@ public class SearchableText {
             previous = word;
         }
 
-        return TextNormalizationUtilities.removeHyphenLineBreaks(sb.toString())
-                .replaceAll("\n", " ")
-                .replaceAll(" {2}", " ");
+        return TextNormalizationUtilities.removeHyphenLineBreaks(sb.toString()).replaceAll("\n", " ").replaceAll("  ", " ");
     }
 
-
-    public String getAsStringWithLinebreaks() {
-
+    public String getAsStringWithLinebreaks(){
         StringBuilder sb = new StringBuilder();
 
         TextPositionSequence previous = null;
         for (TextPositionSequence word : sequences) {
 
             if (previous != null) {
-                if (Math.abs(previous.getRotationAdjustedY() - word.getRotationAdjustedY()) > word.getTextHeight()) {
+                if (Math.abs(previous.getY1() - word.getY1()) > word.getTextHeight()) {
                     sb.append('\n');
                 } else {
                     sb.append(' ');
@@ -215,4 +159,4 @@ public class SearchableText {
         return sb.append("\n").toString();
     }
 
-}
+}

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

@@ -3,7 +3,6 @@ package com.iqser.red.service.redaction.v1.server.redaction.model;
 import java.util.ArrayList;
 import java.util.HashSet;
 import java.util.List;
-import java.util.Map;
 import java.util.Set;
 import java.util.regex.Pattern;
 
@@ -11,10 +10,8 @@ import org.apache.commons.lang3.StringUtils;
 
 import lombok.Builder;
 import lombok.Data;
-import lombok.extern.slf4j.Slf4j;
 
 @Data
-@Slf4j
 @Builder
 public class Section {
 
@@ -28,38 +25,13 @@ public class Section {
 
     private String headline;
 
-    private int sectionNumber;
-
-    private Map<String, CellValue> tabularData;
-
-
-    public boolean rowEquals(String headerName, String value) {
-
-        String cleanHeaderName = headerName.replaceAll("\n", "").replaceAll(" ", "").replaceAll("-", "");
-
-        return tabularData != null && tabularData.containsKey(cleanHeaderName) && tabularData.get(cleanHeaderName)
-                .getTextBlock()
-                .getText()
-                .equals(value);
-    }
-
-
-    public boolean matchesType(String type) {
-
+    public boolean contains(String type) {
         return entities.stream().anyMatch(entity -> entity.getType().equals(type));
     }
 
-
-    public boolean headlineContainsWord(String word) {
-
-        return StringUtils.containsIgnoreCase(headline, word);
-    }
-
-
-    public void redact(String type, int ruleNumber, String reason) {
-
+    public void redact(String type, int ruleNumber, String reason){
         entities.forEach(entity -> {
-            if (entity.getType().equals(type)) {
+            if(entity.getType().equals(type)){
                 entity.setRedaction(true);
                 entity.setMatchedRule(ruleNumber);
                 entity.setRedactionReason(reason);
@@ -67,11 +39,9 @@ public class Section {
         });
     }
 
-
-    public void redactNot(String type, int ruleNumber, String reason) {
-
+    public void redactNot(String type, int ruleNumber, String reason){
         entities.forEach(entity -> {
-            if (entity.getType().equals(type)) {
+            if(entity.getType().equals(type)){
                 entity.setRedaction(false);
                 entity.setMatchedRule(ruleNumber);
                 entity.setRedactionReason(reason);
@@ -79,35 +49,18 @@ public class Section {
         });
     }
 
+    public void redactLineAfter(String start, String asType, int ruleNumber, String reason){
 
-    public void redactIfPrecededBy(String prefix, String type, int ruleNumber, String reason) {
+        String value = StringUtils.substringBetween(text, start, "\n");
 
-        entities.forEach(entity -> {
-            if (entity.getType().equals(type) && searchText.indexOf(prefix + entity.getWord()) != 1) {
-                entity.setRedaction(true);
-                entity.setMatchedRule(ruleNumber);
-                entity.setRedactionReason(reason);
-            }
-        });
-    }
-
-
-    public void redactLineAfter(String start, String asType, int ruleNumber, String reason) {
-
-        String[] values = StringUtils.substringsBetween(text, start, "\n");
-
-        if (values != null) {
-            for (String value : values) {
-                if (StringUtils.isNotBlank(value)) {
-                    Set<Entity> found = findEntities(value.trim(), asType);
-                    entities.addAll(found);
-                }
-            }
+        if(value != null){
+            Set<Entity> found  = findEntity(value.trim(), asType);
+            entities.addAll(found);
         }
 
         // TODO No need to iterate
         entities.forEach(entity -> {
-            if (entity.getType().equals(asType)) {
+            if(entity.getType().equals(asType)){
                 entity.setRedaction(true);
                 entity.setMatchedRule(ruleNumber);
                 entity.setRedactionReason(reason);
@@ -117,22 +70,19 @@ public class Section {
     }
 
 
-    public void redactBetween(String start, String stop, String asType, int ruleNumber, String reason) {
 
-        String[] values = StringUtils.substringsBetween(searchText, start, stop);
+    public void redactBetween(String start, String stop, String asType, int ruleNumber, String reason){
 
-        if (values != null) {
-            for (String value : values) {
-                if (StringUtils.isNotBlank(value)) {
-                    Set<Entity> found = findEntities(value.trim(), asType);
-                    entities.addAll(found);
-                }
-            }
+        String value = StringUtils.substringBetween(searchText, start, stop);
+
+        if(value != null){
+            Set<Entity> found  = findEntity(value.trim(), asType);
+            entities.addAll(found);
         }
 
         // TODO No need to iterate
         entities.forEach(entity -> {
-            if (entity.getType().equals(asType)) {
+            if(entity.getType().equals(asType)){
                 entity.setRedaction(true);
                 entity.setMatchedRule(ruleNumber);
                 entity.setRedactionReason(reason);
@@ -141,94 +91,46 @@ public class Section {
     }
 
 
-    private Set<Entity> findEntities(String value, String asType) {
+
+
+    private Set<Entity> findEntity(String value, String asType) {
 
         Set<Entity> found = new HashSet<>();
 
-        int startIndex;
-        int stopIndex = 0;
-        do {
-            startIndex = searchText.indexOf(value, stopIndex);
-            stopIndex = startIndex + value.length();
+                int startIndex;
+                int stopIndex = 0;
+                do {
+                    startIndex = searchText.indexOf(value, stopIndex);
+                    stopIndex = startIndex + value.length();
 
-            if (startIndex > -1 && (startIndex == 0 || Character.isWhitespace(searchText.charAt(startIndex - 1)) || isSeparator(searchText
-                    .charAt(startIndex - 1))) && (stopIndex == searchText.length() || isSeparator(searchText.charAt(stopIndex)))) {
-                found.add(new Entity(searchText.substring(startIndex, stopIndex), asType, startIndex, stopIndex,
-                        headline, sectionNumber));
-            }
-        } while (startIndex > -1);
+                    if (startIndex > -1 &&
+                            (startIndex == 0 || Character.isWhitespace(searchText.charAt(startIndex - 1)) || isSeparator(searchText.charAt(startIndex - 1))) &&
+                            (stopIndex == searchText.length() || isSeparator(searchText.charAt(stopIndex)))) {
+                        found.add(new Entity(searchText.substring(startIndex, stopIndex), asType, startIndex, stopIndex, headline));
+                    }
+                } while (startIndex > -1);
 
-        return removeEntitiesContainedInLarger(found);
+
+        removeEntitiesContainedInLarger(found);
+
+        return found;
     }
 
 
     private boolean isSeparator(char c) {
-
         return Character.isWhitespace(c) || Pattern.matches("\\p{Punct}", String.valueOf(c)) || c == '\"' || c == '‘' || c == '’';
     }
 
-
-    public Set<Entity> removeEntitiesContainedInLarger(Set<Entity> entities) {
-
+    public void removeEntitiesContainedInLarger(Set<Entity> entities) {
         List<Entity> wordsToRemove = new ArrayList<>();
         for (Entity word : entities) {
             for (Entity inner : entities) {
-                if (inner.getWord().length() < word.getWord()
-                        .length() && inner.getStart() >= word.getStart() && inner.getEnd() <= word.getEnd() && word != inner) {
+                if (inner.getWord().length() < word.getWord().length() && inner.getStart() >= word.getStart() && inner.getEnd() <= word.getEnd() && word != inner) {
                     wordsToRemove.add(inner);
                 }
             }
         }
         entities.removeAll(wordsToRemove);
-        return entities;
-    }
-
-
-    public void highlightCell(String cellHeader, int ruleNumber, String type) {
-
-        annotateCell(cellHeader, ruleNumber, type, false, null);
-    }
-
-
-    public void redactCell(String cellHeader, int ruleNumber, String type, String reason) {
-
-        annotateCell(cellHeader, ruleNumber, type, true, reason);
-    }
-
-
-    public void redactNotCell(String cellHeader, int ruleNumber, String type, String reason) {
-
-        annotateCell(cellHeader, ruleNumber, type, false, reason);
-    }
-
-
-    private void annotateCell(String cellHeader, int ruleNumber, String type, boolean redact, String reason) {
-
-        String cleanHeaderName = cellHeader.replaceAll("\n", "").replaceAll(" ", "").replaceAll("-", "");
-
-        CellValue value = tabularData.get(cleanHeaderName);
-        if (value == null) {
-            log.warn("Could not find any data for {}.", cellHeader);
-        } else {
-            String word = value.toString();
-            Entity entity = new Entity(word,
-                                       type,
-                                       value.getRowSpanStart(),
-                                       value.getRowSpanStart() + word.length(),
-                                       headline,
-                                       sectionNumber);
-            entity.setRedaction(redact);
-            entity.setMatchedRule(ruleNumber);
-            entity.setRedactionReason(reason);
-            entity.setTargetSequences(value.getTextBlock()
-                    .getSequences()); // Make sure no other cells with same content are highlighted
-
-            // HashSet keeps the older value, but we want the new only.
-            entities.remove(entity);
-            entities.add(entity);
-
-            entities = removeEntitiesContainedInLarger(entities);
-        }
     }
 
 }

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

@@ -2,7 +2,6 @@ package com.iqser.red.service.redaction.v1.server.redaction.service;
 
 import java.util.ArrayList;
 import java.util.HashMap;
-import java.util.HashSet;
 import java.util.List;
 import java.util.Map;
 import java.util.Set;
@@ -27,7 +26,6 @@ public class DictionaryService {
 
     private final DictionaryClient dictionaryClient;
 
-    @Getter
     private long dictionaryVersion = -1;
 
     @Getter
@@ -42,15 +40,6 @@ public class DictionaryService {
     @Getter
     private List<String> caseInsensitiveTypes = new ArrayList<>();
 
-    @Getter
-    private float[] defaultColor;
-
-    @Getter
-    private float[] requestAddColor;
-
-    @Getter
-    private float[] requestRemoveColor;
-
 
     public void updateDictionary() {
 
@@ -66,10 +55,16 @@ public class DictionaryService {
 
         try {
             TypeResponse typeResponse = dictionaryClient.getAllTypes();
-            if (typeResponse != null && CollectionUtils.isNotEmpty(typeResponse.getTypes())) {
+            if (typeResponse != null && !CollectionUtils.isEmpty(typeResponse.getTypes())) {
                 entryColors = typeResponse.getTypes()
                         .stream()
                         .collect(Collectors.toMap(TypeResult::getType, TypeResult::getColor));
+                dictionary = entryColors.keySet()
+                        .stream()
+                        .collect(Collectors.toMap(type -> type, s -> dictionaryClient.getDictionaryForType(s)
+                                .getEntries()
+                                .stream()
+                                .collect(Collectors.toSet())));
                 hintTypes = typeResponse.getTypes()
                         .stream()
                         .filter(TypeResult::isHint)
@@ -80,12 +75,6 @@ public class DictionaryService {
                         .filter(TypeResult::isCaseInsensitive)
                         .map(TypeResult::getType)
                         .collect(Collectors.toList());
-                dictionary = entryColors.keySet().stream().collect(Collectors.toMap(type -> type, this::convertEntries));
-                defaultColor = dictionaryClient.getDefaultColor().getColor();
-
-                // TODO get colors from configuration service.
-                requestAddColor = new float[]{0f, 1f, 0.8f};
-                requestRemoveColor = new float[]{0f, 1f, 0.8f};
             }
         } catch (FeignException e) {
             log.warn("Got some unknown feignException", e);
@@ -93,16 +82,4 @@ public class DictionaryService {
         }
     }
 
-
-    private Set<String> convertEntries(String s) {
-        if (caseInsensitiveTypes.contains(s)) {
-            return dictionaryClient.getDictionaryForType(s)
-                    .getEntries()
-                    .stream()
-                    .map(String::toLowerCase)
-                    .collect(Collectors.toSet());
-        }
-        return new HashSet<>(dictionaryClient.getDictionaryForType(s).getEntries());
-    }
-
 }

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

@@ -18,7 +18,6 @@ import com.iqser.red.service.redaction.v1.server.client.RulesClient;
 import com.iqser.red.service.redaction.v1.server.exception.RulesValidationException;
 import com.iqser.red.service.redaction.v1.server.redaction.model.Section;
 
-import lombok.Getter;
 import lombok.RequiredArgsConstructor;
 
 @Service
@@ -30,7 +29,6 @@ public class DroolsExecutionService {
     @Autowired
     private KieContainer kieContainer;
 
-    @Getter
     private long rulesVersion = -1;
 
     public Section executeRules(Section section) {
@@ -70,7 +68,7 @@ public class DroolsExecutionService {
             KieModule kieModule = kieBuilder.getKieModule();
             kieContainer.updateToVersion(kieModule.getReleaseId());
         } catch (Exception e) {
-            throw new RulesValidationException("Could not update rules: " + e.getMessage(), e);
+            throw new RulesValidationException("Could not update rules", e);
         }
 
     }

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

@@ -1,26 +1,18 @@
 package com.iqser.red.service.redaction.v1.server.redaction.service;
 
 import java.util.ArrayList;
-import java.util.HashMap;
 import java.util.HashSet;
 import java.util.List;
 import java.util.Map;
 import java.util.Set;
 import java.util.regex.Pattern;
 
-import org.apache.commons.collections4.CollectionUtils;
-import org.apache.commons.lang3.StringUtils;
 import org.springframework.stereotype.Service;
 
-import com.iqser.red.service.redaction.v1.model.ManualRedactionEntry;
-import com.iqser.red.service.redaction.v1.model.ManualRedactions;
-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.Paragraph;
 import com.iqser.red.service.redaction.v1.server.classification.model.TextBlock;
-import com.iqser.red.service.redaction.v1.server.redaction.model.CellValue;
 import com.iqser.red.service.redaction.v1.server.redaction.model.Entity;
-import com.iqser.red.service.redaction.v1.server.redaction.model.EntityPositionSequence;
 import com.iqser.red.service.redaction.v1.server.redaction.model.SearchableText;
 import com.iqser.red.service.redaction.v1.server.redaction.model.Section;
 import com.iqser.red.service.redaction.v1.server.tableextraction.model.Cell;
@@ -35,192 +27,116 @@ public class EntityRedactionService {
     private final DictionaryService dictionaryService;
     private final DroolsExecutionService droolsExecutionService;
 
-
-    public void processDocument(Document classifiedDoc, ManualRedactions manualRedactions) {
+    public void processDocument(Document classifiedDoc) {
 
         dictionaryService.updateDictionary();
         droolsExecutionService.updateRules();
 
         Set<Entity> documentEntities = new HashSet<>();
-        int sectionNumber = 1;
         for (Paragraph paragraph : classifiedDoc.getParagraphs()) {
 
             SearchableText searchableText = paragraph.getSearchableText();
 
             List<Table> tables = paragraph.getTables();
 
+            List<SearchableText> searchableRows = new ArrayList<>();
             for (Table table : tables) {
-                boolean singleCellTable = table.getRowCount() == 1 && table.getColCount() == 1;
                 for (List<Cell> row : table.getRows()) {
                     SearchableText searchableRow = new SearchableText();
-                    Map<String, CellValue> tabularData = new HashMap<>();
-                    int start = 0;
-                    for (Cell cell : row) {
-                        if (!singleCellTable && cell.isHeaderCell() || CollectionUtils.isEmpty(cell.getTextBlocks())) {
+                    for (Cell column : row) {
+                        if (column == null || column.getTextBlocks() == null) {
                             continue;
                         }
-                        addSectionToManualRedactions(cell.getTextBlocks(), manualRedactions, table.getHeadline(), sectionNumber);
-                        int cellStart = start;
-                        cell.getHeaderCells().forEach(headerCell -> {
-                            StringBuilder headerBuilder = new StringBuilder();
-                            headerCell.getTextBlocks().forEach(textBlock -> headerBuilder.append(textBlock.getText()));
-                            String headerName = headerBuilder.toString()
-                                    .replaceAll("\n", "")
-                                    .replaceAll(" ", "")
-                                    .replaceAll("-", "");
-                            tabularData.put(headerName, new CellValue(cell.getTextBlocks().get(0), cellStart));
-                        });
-                        start = start + cell.toString().length() + 1; // include automatically appended white space
-                        for (TextBlock textBlock : cell.getTextBlocks()) {
+                        for (TextBlock textBlock : column.getTextBlocks()) {
                             searchableRow.addAll(textBlock.getSequences());
                         }
                     }
-                    Set<Entity> rowEntities = findEntities(searchableRow, table.getHeadline(), sectionNumber);
-
-                    Section analysedRowSection = droolsExecutionService.executeRules(Section.builder()
-                            .entities(rowEntities)
-                            .text(searchableRow.getAsStringWithLinebreaks())
-                            .searchText(searchableRow.toString())
-                            .headline(table.getHeadline())
-                            .sectionNumber(sectionNumber)
-                            .tabularData(tabularData)
-                            .build());
-
-                    documentEntities.addAll(clearAndFindPositions(analysedRowSection.getEntities(), searchableRow));
-                    sectionNumber++;
+                    searchableRows.add(searchableRow);
                 }
-                sectionNumber++;
             }
 
-            addSectionToManualRedactions(paragraph.getTextBlocks(), manualRedactions, paragraph.getHeadline(), sectionNumber);
-            Set<Entity> entities = findEntities(searchableText, paragraph.getHeadline(), sectionNumber);
-            Section analysedSection = droolsExecutionService.executeRules(Section.builder()
+            Set<Entity> entities = findEntities(searchableText, paragraph.getHeadline());
+            Section analysedSection = droolsExecutionService.executeRules(Section
+                    .builder()
                     .entities(entities)
                     .text(searchableText.getAsStringWithLinebreaks())
                     .searchText(searchableText.toString())
                     .headline(paragraph.getHeadline())
-                    .sectionNumber(sectionNumber)
                     .build());
 
-            documentEntities.addAll(clearAndFindPositions(analysedSection.getEntities(), searchableText));
-            sectionNumber++;
-        }
-
-        for (Entity entity : documentEntities) {
-            Map<Integer, List<EntityPositionSequence>> sequenceOnPage = new HashMap<>();
-            for (EntityPositionSequence entityPositionSequence : entity.getPositionSequences()) {
-                sequenceOnPage.computeIfAbsent(entityPositionSequence.getPageNumber(), (x) -> new ArrayList<>())
-                        .add(entityPositionSequence);
+            for (Entity entity : analysedSection.getEntities()) {
+                entity.setPositionSequences(searchableText.getSequences(entity.getWord()));
             }
 
-            for (Map.Entry<Integer, List<EntityPositionSequence>> entry : sequenceOnPage.entrySet()) {
-                classifiedDoc.getEntities()
-                        .computeIfAbsent(entry.getKey(), (x) -> new ArrayList<>())
-                        .add(new Entity(entity.getWord(), entity.getType(), entity.isRedaction(), entity.getRedactionReason(), entry
-                                .getValue(), entity.getHeadline(), entity.getMatchedRule(), entity.getSectionNumber()));
+            documentEntities.addAll(analysedSection.getEntities());
+
+            for (SearchableText searchableRow : searchableRows) {
+                Set<Entity> rowEntities = findEntities(searchableRow, "//TODO TableHeader");
+
+                Section analysedRowSection = droolsExecutionService.executeRules(Section
+                        .builder()
+                        .entities(rowEntities)
+                        .text(searchableRow.getAsStringWithLinebreaks())
+                        .searchText(searchableRow.toString())
+                        .headline("//TODO TableHeader")
+                        .build());
+
+                for (Entity entity : analysedRowSection.getEntities()) {
+                    entity.setPositionSequences(searchableRow.getSequences(entity.getWord()));
+                }
+                documentEntities.addAll(analysedRowSection.getEntities());
             }
         }
 
+        documentEntities.forEach(entity -> {
+            entity.getPositionSequences().forEach(sequence -> {
+                classifiedDoc.getEntities().computeIfAbsent(sequence.getPageNumber(), (x) -> new HashSet<>()).add(
+                        new Entity(entity.getWord(), entity.getType(), entity.isRedaction(), entity.getRedactionReason(), List.of(sequence), entity.getHeadline(), entity.getMatchedRule())
+                );
+            });
+        });
     }
 
+    private Set<Entity> findEntities(SearchableText searchableText, String headline) {
 
-    private Set<Entity> clearAndFindPositions(Set<Entity> entities, SearchableText text) {
-
-        removeEntitiesContainedInLarger(entities);
-
-        for (Entity entity : entities) {
-            if (dictionaryService.getCaseInsensitiveTypes().contains(entity.getType())) {
-                entity.setPositionSequences(text.getSequences(entity.getWord(), true, entity.getTargetSequences()));
-            } else {
-                entity.setPositionSequences(text.getSequences(entity.getWord(), false, entity.getTargetSequences()));
-            }
-        }
-
-        return entities;
-    }
-
-
-    private Set<Entity> findEntities(SearchableText searchableText, String headline, int sectionNumber) {
+        String normalizedInputString = searchableText.toString();
 
         Set<Entity> found = new HashSet<>();
-        String searchableString = searchableText.toString();
-        if (StringUtils.isEmpty(searchableString)) {
-            return found;
-        }
-
-        String lowercaseInputString = searchableString.toLowerCase();
         for (Map.Entry<String, Set<String>> entry : dictionaryService.getDictionary().entrySet()) {
-            if (dictionaryService.getCaseInsensitiveTypes().contains(entry.getKey())) {
-                found.addAll(find(lowercaseInputString, entry.getValue(), entry.getKey(), headline, sectionNumber));
-            } else {
-                found.addAll(find(searchableString, entry.getValue(), entry.getKey(), headline, sectionNumber));
+            for (String value : entry.getValue()) {
+                int startIndex;
+                int stopIndex = 0;
+                do {
+                    startIndex = normalizedInputString.indexOf(value, stopIndex);
+                    stopIndex = startIndex + value.length();
+
+                    if (startIndex > -1 &&
+                            (startIndex == 0 || Character.isWhitespace(normalizedInputString.charAt(startIndex - 1)) || isSeparator(normalizedInputString.charAt(startIndex - 1))) &&
+                            (stopIndex == normalizedInputString.length() || isSeparator(normalizedInputString.charAt(stopIndex)))) {
+                        found.add(new Entity(normalizedInputString.substring(startIndex, stopIndex), entry.getKey(), startIndex, stopIndex, headline));
+                    }
+                } while (startIndex > -1);
             }
         }
 
         removeEntitiesContainedInLarger(found);
 
         return found;
-
     }
 
-
-    private Set<Entity> find(String inputString, Set<String> values, String type, String headline, int sectionNumber) {
-
-        Set<Entity> found = new HashSet<>();
-        for (String value : values) {
-            int startIndex;
-            int stopIndex = 0;
-            do {
-                startIndex = inputString.indexOf(value, stopIndex);
-                stopIndex = startIndex + value.length();
-
-                if (startIndex > -1 && (startIndex == 0 || Character.isWhitespace(inputString.charAt(startIndex - 1)) || isSeparator(inputString
-                        .charAt(startIndex - 1))) && (stopIndex == inputString.length() || isSeparator(inputString.charAt(stopIndex)))) {
-                    found.add(new Entity(inputString.substring(startIndex, stopIndex), type, startIndex, stopIndex, headline, sectionNumber));
-                }
-            } while (startIndex > -1);
-        }
-        return found;
-    }
-
-
     private boolean isSeparator(char c) {
-
         return Character.isWhitespace(c) || Pattern.matches("\\p{Punct}", String.valueOf(c)) || c == '\"' || c == '‘' || c == '’';
     }
 
-
     public void removeEntitiesContainedInLarger(Set<Entity> entities) {
-
         List<Entity> wordsToRemove = new ArrayList<>();
         for (Entity word : entities) {
             for (Entity inner : entities) {
-                if (inner.getWord().length() < word.getWord()
-                        .length() && inner.getStart() >= word.getStart() && inner.getEnd() <= word.getEnd() && word != inner) {
+                if (inner.getWord().length() < word.getWord().length() && inner.getStart() >= word.getStart() && inner.getEnd() <= word.getEnd() && word != inner) {
                     wordsToRemove.add(inner);
                 }
             }
         }
         entities.removeAll(wordsToRemove);
     }
-
-
-    private void addSectionToManualRedactions(List<TextBlock> textBlocks, ManualRedactions manualRedactions, String section, int sectionNumber) {
-
-        if (manualRedactions == null || manualRedactions.getEntriesToAdd().isEmpty()) {
-            return;
-        }
-
-        for (TextBlock textBlock : textBlocks) {
-            for (ManualRedactionEntry manualRedactionEntry : manualRedactions.getEntriesToAdd()) {
-                for (Rectangle rectangle : manualRedactionEntry.getPositions()) {
-                    if (textBlock.contains(rectangle)) {
-                        manualRedactionEntry.setSection(section);
-                        manualRedactionEntry.setSectionNumber(sectionNumber);
-                    }
-                }
-            }
-        }
-    }
-
 }

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

@@ -1,32 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.redaction.utils;
-
-import java.nio.charset.StandardCharsets;
-import java.util.List;
-
-import com.google.common.hash.HashFunction;
-import com.google.common.hash.Hashing;
-import com.iqser.red.service.redaction.v1.model.ManualRedactionEntry;
-import com.iqser.red.service.redaction.v1.server.parsing.model.TextPositionSequence;
-
-import lombok.experimental.UtilityClass;
-
-@UtilityClass
-public class IdBuilder {
-
-    private final HashFunction hashFunction = Hashing.murmur3_128();
-
-    public String buildId(List<TextPositionSequence> crossSequenceParts) {
-
-        StringBuilder sb = new StringBuilder();
-        crossSequenceParts.forEach(sequencePart -> sequencePart.getTextPositions().forEach(textPosition -> {
-            sb.append(textPosition.getTextMatrix());
-        }));
-
-        return hashFunction.hashString(sb.toString(), StandardCharsets.UTF_8).toString();
-    }
-
-
-    public String buildId(ManualRedactionEntry manualRedactionEntry) {
-        return hashFunction.hashString(manualRedactionEntry.toString(), StandardCharsets.UTF_8).toString();
-    }
-}

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

@@ -21,6 +21,7 @@ import com.iqser.red.service.redaction.v1.server.tableextraction.model.AbstractT
 import com.iqser.red.service.redaction.v1.server.tableextraction.model.CleanRulings;
 import com.iqser.red.service.redaction.v1.server.tableextraction.service.RulingCleaningService;
 import com.iqser.red.service.redaction.v1.server.tableextraction.service.TableExtractionService;
+import com.iqser.red.service.redaction.v1.server.tableextraction.utils.Utils;
 
 import lombok.RequiredArgsConstructor;
 import lombok.extern.slf4j.Slf4j;
@@ -28,6 +29,7 @@ import lombok.extern.slf4j.Slf4j;
 @Slf4j
 @Service
 @RequiredArgsConstructor
+@SuppressWarnings("PMD")
 public class PdfSegmentationService {
 
     private final RulingCleaningService rulingCleaningService;
@@ -36,7 +38,6 @@ public class PdfSegmentationService {
     private final ClassificationService classificationService;
     private final SectionsBuilderService sectionsBuilderService;
 
-
     public Document parseDocument(PDDocument pdDocument) throws IOException {
 
         Document document = new Document();
@@ -56,21 +57,19 @@ public class PdfSegmentationService {
             int rotation = pdPage.getRotation();
             boolean isRotated = rotation != 0 && rotation != 360;
 
-
-            ParsedElements parsedElements = ParsedElements.builder()
+            ParsedElements parsedElements = ParsedElements
+                    .builder()
                     .rulings(stripper.getRulings())
                     .sequences(stripper.getTextPositionSequences())
-                    .maxCharWidth(stripper.getMaxCharWidths())
-                    .maxCharHeight(stripper.getMaxCharWidths())
+                    .minCharWidth(Utils.round(stripper.getMinCharWidth(), 2))
+                    .minCharHeight(Utils.round(stripper.getMinCharHeight(), 2))
                     .landscape(isLandscape)
                     .rotated(isRotated)
                     .build();
 
-            CleanRulings cleanRulings = rulingCleaningService.getCleanRulings(parsedElements.getRulings(), parsedElements
-                    .getMaxCharWidth(), parsedElements.getMaxCharHeight());
+            CleanRulings cleanRulings = rulingCleaningService.getCleanRulings(parsedElements.getRulings(), parsedElements.getMinCharWidth(), parsedElements.getMinCharHeight());
 
-            Page page = blockificationService.blockify(parsedElements.getSequences(), cleanRulings.getHorizontal(), cleanRulings
-                    .getVertical());
+            Page page = blockificationService.blockify(parsedElements.getSequences(), cleanRulings.getHorizontal(), cleanRulings.getVertical());
             page.setRotation(rotation);
 
             tableExtractionService.extractTables(cleanRulings, page);
@@ -93,10 +92,7 @@ public class PdfSegmentationService {
 
     }
 
-
-
     private void increaseDocumentStatistics(Page page, Document document) {
-
         if (!page.isLandscape()) {
             document.getFontSizeCounter().addAll(page.getFontSizeCounter().getCountPerValue());
         }
@@ -105,7 +101,6 @@ public class PdfSegmentationService {
         document.getFontStyleCounter().addAll(page.getFontStyleCounter().getCountPerValue());
     }
 
-
     private void buildPageStatistics(Page page) {
 
         // Collect all statistics for the page, except from blocks inside tables, as tables will always be added to BodyTextFrame.

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

@@ -1,12 +1,9 @@
 package com.iqser.red.service.redaction.v1.server.segmentation;
 
 import java.util.ArrayList;
-import java.util.Collections;
 import java.util.Iterator;
 import java.util.List;
-import java.util.stream.Collectors;
 
-import org.apache.commons.collections4.CollectionUtils;
 import org.springframework.stereotype.Service;
 
 import com.iqser.red.service.redaction.v1.server.classification.model.Document;
@@ -14,12 +11,13 @@ import com.iqser.red.service.redaction.v1.server.classification.model.Page;
 import com.iqser.red.service.redaction.v1.server.classification.model.Paragraph;
 import com.iqser.red.service.redaction.v1.server.classification.model.TextBlock;
 import com.iqser.red.service.redaction.v1.server.tableextraction.model.AbstractTextContainer;
-import com.iqser.red.service.redaction.v1.server.tableextraction.model.Cell;
 import com.iqser.red.service.redaction.v1.server.tableextraction.model.Table;
 
 @Service
+@SuppressWarnings("all")
 public class SectionsBuilderService {
 
+
     public void buildSections(Document document) {
 
         List<AbstractTextContainer> chunkWords = new ArrayList<>();
@@ -28,80 +26,42 @@ public class SectionsBuilderService {
         AbstractTextContainer prev = null;
 
         String lastHeadline = "";
-        Table previousTable = null;
         for (Page page : document.getPages()) {
             for (AbstractTextContainer current : page.getTextBlocks()) {
 
-                if (current.getClassification() == null || current.getClassification()
-                        .equals("Header") || current.getClassification().equals("Footer")) {
+                if (current.getClassification() == null || current.getClassification().equals("Header") || current.getClassification().equals("Footer")) {
                     continue;
                 }
 
                 current.setPage(page.getPageNumber());
 
                 if (prev != null && current.getClassification().startsWith("H ") || !document.isHeadlines()) {
-                    Paragraph chunkBlock = buildTextBlock(chunkWords, lastHeadline);
+
+                    Paragraph chunkBlock = buildTextBlock(chunkWords);
                     chunkBlock.setHeadline(lastHeadline);
-                    if(document.isHeadlines()) {
-                        lastHeadline = current.getText();
-                    }
+                    lastHeadline = current.getText();
                     chunkBlockList.add(chunkBlock);
                     chunkWords = new ArrayList<>();
-                    if (CollectionUtils.isNotEmpty(chunkBlock.getTables())) {
-                        previousTable = chunkBlock.getTables().get(chunkBlock.getTables().size() - 1);
-                    }
-                }
-                if (current instanceof Table) {
-                    Table table = (Table) current;
-                    // Distribute header information for subsequent tables
-                    mergeTableMetadata(table, previousTable);
-                    previousTable = table;
+
                 }
+
                 chunkWords.add(current);
+
                 prev = current;
             }
         }
 
-        Paragraph chunkBlock = buildTextBlock(chunkWords, lastHeadline);
-        chunkBlock.setHeadline(lastHeadline);
-        chunkBlockList.add(chunkBlock);
+        Paragraph chunkBlock = buildTextBlock(chunkWords);
+        if (chunkBlock != null) {
+            chunkBlockList.add(chunkBlock);
+            chunkBlock.setHeadline(lastHeadline);
+        }
 
         document.setParagraphs(chunkBlockList);
     }
 
 
-    private void mergeTableMetadata(Table currentTable, Table previousTable) {
-
-        // Distribute header information for subsequent tables
-        if (previousTable != null && hasInvalidHeaderInformation(currentTable) && hasValidHeaderInformation(previousTable)) {
-            List<Cell> previousTableNonHeaderRow = getRowWithNonHeaderCells(previousTable);
-            List<Cell> tableNonHeaderRow = getRowWithNonHeaderCells(currentTable);
-            // Allow merging of tables if header row is separated from first logical non-header row
-            if (previousTableNonHeaderRow.isEmpty() && previousTable.getRowCount() == 1 && previousTable.getRows()
-                    .get(0)
-                    .size() == tableNonHeaderRow.size()) {
-                previousTableNonHeaderRow = previousTable.getRows().get(0).stream().map(cell -> {
-                    Cell fakeCell = new Cell(cell.getPoints()[0], cell.getPoints()[2]);
-                    fakeCell.setHeaderCells(Collections.singletonList(cell));
-                    return fakeCell;
-                }).collect(Collectors.toList());
-            }
-            if (previousTableNonHeaderRow.size() == tableNonHeaderRow.size()) {
-                for (int i = currentTable.getRowCount() - 1; i >= 0; i--) { // Non header rows are most likely at bottom of table
-                    List<Cell> row = currentTable.getRows().get(i);
-                    if (row.size() == tableNonHeaderRow.size() && row.stream()
-                            .allMatch(cell -> cell.getHeaderCells().isEmpty())) {
-                        for (int j = 0; j < row.size(); j++) {
-                            row.get(j).setHeaderCells(previousTableNonHeaderRow.get(j).getHeaderCells());
-                        }
-                    }
-                }
-            }
-        }
-    }
-
-
-    private Paragraph buildTextBlock(List<AbstractTextContainer> wordBlockList, String lastHeadline) {
+    private Paragraph buildTextBlock(List<AbstractTextContainer> wordBlockList) {
 
         Paragraph paragraph = new Paragraph();
         TextBlock textBlock = null;
@@ -110,54 +70,43 @@ public class SectionsBuilderService {
         boolean splitByTable = false;
 
         Iterator<AbstractTextContainer> itty = wordBlockList.iterator();
-        boolean alreadyAdded = false;
-        AbstractTextContainer previous = null;
+        boolean alreadyAdded= false;
         while (itty.hasNext()) {
             AbstractTextContainer container = itty.next();
 
             if (container instanceof Table) {
-                Table table = (Table) container;
                 splitByTable = true;
 
-                if (previous != null && previous.getText().startsWith("Table ")) {
-                    table.setHeadline(previous.getText());
-                } else {
-                    table.setHeadline("Table in: " + lastHeadline);
-                }
 
                 if (textBlock != null && !alreadyAdded) {
                     paragraph.getPageBlocks().add(textBlock);
-                    alreadyAdded = true;
+                    alreadyAdded =true;
                 }
-                paragraph.getPageBlocks().add(table);
+                paragraph.getPageBlocks().add(container);
                 continue;
             }
 
             TextBlock wordBlock = (TextBlock) container;
 
             if (textBlock == null) {
-                textBlock = new TextBlock(wordBlock.getMinX(), wordBlock.getMaxX(), wordBlock.getMinY(), wordBlock.getMaxY(), wordBlock
-                        .getSequences(), wordBlock.getRotation());
+                textBlock = new TextBlock(wordBlock.getMinX(), wordBlock.getMaxX(), wordBlock.getMinY(), wordBlock.getMaxY(), wordBlock.getSequences(), wordBlock.getRotation());
                 textBlock.setPage(wordBlock.getPage());
             } else if (splitByTable) {
-                textBlock = new TextBlock(wordBlock.getMinX(), wordBlock.getMaxX(), wordBlock.getMinY(), wordBlock.getMaxY(), wordBlock
-                        .getSequences(), wordBlock.getRotation());
+                textBlock = new TextBlock(wordBlock.getMinX(), wordBlock.getMaxX(), wordBlock.getMinY(), wordBlock.getMaxY(), wordBlock.getSequences(), wordBlock.getRotation());
                 textBlock.setPage(wordBlock.getPage());
                 alreadyAdded = false;
             } else if (pageBefore != -1 && wordBlock.getPage() != pageBefore) {
                 textBlock.setPage(pageBefore);
                 paragraph.getPageBlocks().add(textBlock);
-                textBlock = new TextBlock(wordBlock.getMinX(), wordBlock.getMaxX(), wordBlock.getMinY(), wordBlock.getMaxY(), wordBlock
-                        .getSequences(), wordBlock.getRotation());
+                textBlock = new TextBlock(wordBlock.getMinX(), wordBlock.getMaxX(), wordBlock.getMinY(), wordBlock.getMaxY(), wordBlock.getSequences(), wordBlock.getRotation());
                 textBlock.setPage(wordBlock.getPage());
             } else {
                 TextBlock spatialEntity = textBlock.union(wordBlock);
-                textBlock.resize(spatialEntity.getMinX(), spatialEntity.getMinY(), spatialEntity.getWidth(), spatialEntity
-                        .getHeight());
+                textBlock.resize(spatialEntity.getMinX(), spatialEntity.getMinY(),
+                        spatialEntity.getWidth(), spatialEntity.getHeight());
             }
             pageBefore = wordBlock.getPage();
             splitByTable = false;
-            previous = container;
         }
 
         if (textBlock != null && !alreadyAdded) {
@@ -167,41 +116,4 @@ public class SectionsBuilderService {
     }
 
 
-    private boolean hasValidHeaderInformation(Table table) {
-
-        return !hasInvalidHeaderInformation(table);
-    }
-
-
-    private boolean hasInvalidHeaderInformation(Table table) {
-
-        return table.getRows().stream()
-                .flatMap(row -> row.stream()
-                        .filter(cell -> CollectionUtils.isNotEmpty(cell.getHeaderCells())))
-                .findAny()
-                .isEmpty();
-
-    }
-
-
-    private List<Cell> getRowWithNonHeaderCells(Table table) {
-
-        for (int i = table.getRowCount() - 1; i >= 0; i--) { // Non header rows are most likely at bottom of table
-            List<Cell> row = table.getRows().get(i);
-            boolean allNonHeader = true;
-            for (Cell cell : row) {
-                if (cell.isHeaderCell()) {
-                    allNonHeader = false;
-                    break;
-                }
-            }
-            if (allNonHeader) {
-                return row;
-            }
-        }
-
-        return Collections.emptyList();
-
-    }
-
-}
+}

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

@@ -1,7 +1,5 @@
 package com.iqser.red.service.redaction.v1.server.tableextraction.model;
 
-import com.iqser.red.service.redaction.v1.model.Rectangle;
-
 import lombok.AllArgsConstructor;
 import lombok.Data;
 import lombok.NoArgsConstructor;
@@ -24,8 +22,4 @@ public abstract class AbstractTextContainer {
         return this.minX <= other.minX && this.maxX >= other.maxX && this.minY >= other.minY && this.maxY <= other.maxY;
     }
 
-    public boolean contains(Rectangle other) {
-        return page == other.getPage() && this.minX <= other.getTopLeft().getX() && this.maxX >= other.getTopLeft().getX() + other.getWidth() && this.minY <= other.getTopLeft().getY()  && this.maxY >= other.getTopLeft().getY() + other.getHeight();
-    }
-
 }

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

@@ -5,8 +5,6 @@ import java.util.ArrayList;
 import java.util.List;
 
 import com.iqser.red.service.redaction.v1.server.classification.model.TextBlock;
-import com.iqser.red.service.redaction.v1.server.parsing.model.TextPositionSequence;
-import com.iqser.red.service.redaction.v1.server.redaction.utils.TextNormalizationUtilities;
 
 import lombok.Data;
 import lombok.EqualsAndHashCode;
@@ -18,47 +16,11 @@ public class Cell extends Rectangle {
 
     private List<TextBlock> textBlocks = new ArrayList<>();
 
-    private List<Cell> headerCells = new ArrayList<>();
-
-    private boolean isHeaderCell;
-
-
     public Cell(Point2D topLeft, Point2D bottomRight) {
-
-        super((float) topLeft.getY(), (float) topLeft.getX(), (float) (bottomRight.getX() - topLeft.getX()), (float) (bottomRight
-                .getY() - topLeft.getY()));
+        super((float) topLeft.getY(), (float) topLeft.getX(), (float) (bottomRight.getX() - topLeft.getX()), (float) (bottomRight.getY() - topLeft.getY()));
     }
 
-
     public void addTextBlock(TextBlock textBlock) {
-
         textBlocks.add(textBlock);
     }
-
-
-    @Override
-    public String toString() {
-
-        StringBuilder sb = new StringBuilder();
-
-        for (TextBlock textBlock : textBlocks) {
-            TextPositionSequence previous = null;
-            for (TextPositionSequence word : textBlock.getSequences()) {
-                if (previous != null) {
-                    if (Math.abs(previous.getRotationAdjustedY() - word.getRotationAdjustedY()) > word.getTextHeight()) {
-                        sb.append('\n');
-                    } else {
-                        sb.append(' ');
-                    }
-                }
-                sb.append(word.toString());
-                previous = word;
-            }
-        }
-
-        return TextNormalizationUtilities.removeHyphenLineBreaks(sb.toString())
-                .replaceAll("\n", " ")
-                .replaceAll(" {2}", " ");
-    }
-
-}
+}

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

@@ -1,22 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.tableextraction.model;
-
-import lombok.RequiredArgsConstructor;
-import lombok.Value;
-
-@Value
-@RequiredArgsConstructor
-public class CellPosition implements Comparable<CellPosition> {
-
-    int row;
-
-    int col;
-
-
-    @Override
-    public int compareTo(CellPosition other) {
-
-        int rowDiff = row - other.row;
-        return rowDiff != 0 ? rowDiff : col - other.col;
-    }
-
-}

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

@@ -8,28 +8,25 @@ import org.locationtech.jts.index.strtree.STRtree;
 
 import com.iqser.red.service.redaction.v1.server.tableextraction.utils.Utils;
 
+
 @SuppressWarnings("all")
 public class RectangleSpatialIndex<T extends Rectangle> {
+    
 
     private final STRtree si = new STRtree();
     private final List<T> rectangles = new ArrayList<>();
 
-
     public void add(T te) {
-
         rectangles.add(te);
         si.insert(new Envelope(te.getLeft(), te.getRight(), te.getBottom(), te.getTop()), te);
     }
-
-
-    public List<T> contains(Rectangle rectangle) {
-
-        List<T> intersection = si.query(new Envelope(rectangle.getLeft(), rectangle.getRight(), rectangle.getTop(), rectangle
-                .getBottom()));
+    
+    public List<T> contains(Rectangle r) {
+        List<T> intersection = si.query(new Envelope(r.getLeft(), r.getRight(), r.getTop(), r.getBottom()));
         List<T> rv = new ArrayList<T>();
 
-        for (T ir : intersection) {
-            if (rectangle.contains(ir)) {
+        for (T ir: intersection) {
+            if (r.contains(ir)) {
                 rv.add(ir);
             }
         }
@@ -37,22 +34,18 @@ public class RectangleSpatialIndex<T extends Rectangle> {
         Utils.sort(rv, Rectangle.ILL_DEFINED_ORDER);
         return rv;
     }
-
-
+    
     public List<T> intersects(Rectangle r) {
-
         List rv = si.query(new Envelope(r.getLeft(), r.getRight(), r.getTop(), r.getBottom()));
         return rv;
     }
-
-
+    
     /**
      * Minimum bounding box of all the Rectangles contained on this RectangleSpatialIndex
-     *
+     * 
      * @return a Rectangle
      */
     public Rectangle getBounds() {
-
         return Rectangle.boundingBoxOf(rectangles);
     }
 

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

@@ -9,38 +9,26 @@ import java.util.List;
 import java.util.Map;
 import java.util.TreeMap;
 
-import org.apache.commons.collections4.CollectionUtils;
-
 import com.iqser.red.service.redaction.v1.server.classification.model.TextBlock;
 import com.iqser.red.service.redaction.v1.server.tableextraction.utils.Utils;
 
 import lombok.Getter;
-import lombok.Setter;
-import lombok.extern.slf4j.Slf4j;
 
-@Slf4j
+@SuppressWarnings("all")
 public class Table extends AbstractTextContainer {
 
     private final TreeMap<CellPosition, Cell> cells = new TreeMap<>();
 
-    private final RectangleSpatialIndex<Cell> si = new RectangleSpatialIndex<>();
+    private RectangleSpatialIndex<Cell> si = new RectangleSpatialIndex<>();
 
     @Getter
-    @Setter
-    private String headline;
+    private int rowCount = 0;
+    @Getter
+    private int colCount = 0;
 
-    private int unrotatedRowCount;
-
-    private int unrotatedColCount;
-
-    private int rowCount = -1;
-
-    private int colCount = -1;
-
-    private final int rotation;
-
-    private List<List<Cell>> rows;
+    private int rotation = 0;
 
+    private List<List<Cell>> memoizedRows = null;
 
     public Table(List<Cell> cells, Rectangle area, int rotation) {
 
@@ -54,129 +42,43 @@ public class Table extends AbstractTextContainer {
 
     }
 
-
     public List<List<Cell>> getRows() {
 
-        if (rows == null) {
-            rows = computeRows();
-            computeHeaders();
+        if (memoizedRows == null) {
+            memoizedRows = computeRows();
         }
 
-        return rows;
+        return memoizedRows;
 
     }
 
-
-    public int getRowCount() {
-
-        if (rowCount == -1) {
-            rowCount = getRows().size();
-        }
-        return rowCount;
-    }
-
-
-    public int getColCount() {
-
-        if (colCount == -1) {
-            colCount = getRows().stream().mapToInt(List::size).max().orElse(0);
-        }
-        return colCount;
-
-    }
-
-
-    /**
-     * Detect header cells (either first row or first column):
-     * Column is marked as header if cell text is bold and row cell text is not bold.
-     * Defaults to row.
-     */
-    private void computeHeaders() {
-
-        if (rows == null) {
-            rows = computeRows();
-        }
-        // A bold cell is a header cell as long as every cell to the left/top is bold, too
-        // we move from left to right and top to bottom
-        for (int rowIndex = 0; rowIndex < rows.size(); rowIndex++) {
-            List<Cell> rowCells = rows.get(rowIndex);
-            for (int colIndex = 0; colIndex < rowCells.size(); colIndex++) {
-                Cell cell = rowCells.get(colIndex);
-                List<Cell> cellsToTheLeft = rowCells.subList(0, colIndex);
-                Cell lastHeaderCell = null;
-                for (Cell leftCell : cellsToTheLeft) {
-                    if (leftCell.isHeaderCell()) {
-                        lastHeaderCell = leftCell;
-                    } else {
-                        break;
-                    }
-                }
-                if (lastHeaderCell != null) {
-                    cell.getHeaderCells().add(lastHeaderCell);
-                }
-                List<Cell> cellsToTheTop = new ArrayList<>();
-                for (int i = 0; i < rowIndex; i++) {
-                    try {
-                        cellsToTheTop.add(rows.get(i).get(colIndex));
-                    } catch (IndexOutOfBoundsException e) {
-                        log.debug("No cell {} in row {}, ignoring.", colIndex, rowIndex);
-                    }
-                }
-                for (Cell topCell : cellsToTheTop) {
-                    if (topCell.isHeaderCell()) {
-                        lastHeaderCell = topCell;
-                    } else {
-                        break;
-                    }
-                }
-                if (lastHeaderCell != null) {
-                    cell.getHeaderCells().add(lastHeaderCell);
-                }
-                if (CollectionUtils.isNotEmpty(cell.getTextBlocks()) && cell.getTextBlocks()
-                        .get(0)
-                        .getMostPopularWordStyle()
-                        .equals("bold")) {
-                    cell.setHeaderCell(true);
-                }
-            }
-        }
-
-    }
-
-
     private List<List<Cell>> computeRows() {
 
         List<List<Cell>> rows = new ArrayList<>();
         if (rotation == 90) {
-            for (int i = 0; i < unrotatedColCount; i++) { // rows
+            for (int i = 0; i < colCount; i++) { // rows
                 List<Cell> lastRow = new ArrayList<>();
-                for (int j = unrotatedRowCount - 1; j >= 0; j--) { // cols
+                for (int j = rowCount - 1; j >= 0; j--) { // cols
                     Cell cell = cells.get(new CellPosition(j, i));
-                    if (cell != null) {
-                        lastRow.add(cell);
-                    }
+                    lastRow.add(cell);
                 }
                 rows.add(lastRow);
             }
         } else if (rotation == 270) {
-            for (int i = unrotatedColCount - 1; i >= 0; i--) { // rows
+            for (int i = colCount - 1; i >= 0; i--) { // rows
                 List<Cell> lastRow = new ArrayList<>();
-                for (int j = 0; j < unrotatedRowCount; j++) { // cols
+                for (int j = 0; j < rowCount; j++) { // cols
                     Cell cell = cells.get(new CellPosition(i, j));
-                    if (cell != null) {
-                        lastRow.add(cell);
-                    }
+                    lastRow.add(cell);
                 }
                 rows.add(lastRow);
             }
         } else {
-            for (int i = 0; i < unrotatedRowCount; i++) {
+            for (int i = 0; i < rowCount; i++) {
                 List<Cell> lastRow = new ArrayList<>();
-                for (int j = 0; j < unrotatedColCount; j++) {
+                for (int j = 0; j < colCount; j++) {
                     Cell cell = cells.get(new CellPosition(i, j)); // JAVA_8 use getOrDefault()
-                    if (cell != null) {
-                        lastRow.add(cell);
-                    }
+                    lastRow.add(cell);
                 }
                 rows.add(lastRow);
             }
@@ -186,18 +88,16 @@ public class Table extends AbstractTextContainer {
 
     }
 
+    public void add(Cell chunk, int row, int col) {
 
-    private void add(Cell chunk, int row, int col) {
-
-        unrotatedRowCount = Math.max(unrotatedRowCount, row + 1);
-        unrotatedColCount = Math.max(unrotatedColCount, col + 1);
+        rowCount = Math.max(rowCount, row + 1);
+        colCount = Math.max(colCount, col + 1);
 
         CellPosition cp = new CellPosition(row, col);
         cells.put(cp, chunk);
 
     }
 
-
     private void addCells(List<Cell> cells) {
 
         if (cells.isEmpty()) {
@@ -226,21 +126,25 @@ public class Table extends AbstractTextContainer {
             while (rowCells.hasNext()) {
                 Cell cell = rowCells.next();
                 if (i > 0) {
-                    Rectangle rectangle = new Rectangle(cell.getBottom(),
-                            si.getBounds().getLeft(),
-                            cell.getLeft() - si.getBounds().getLeft() + 1,
-                            si.getBounds().getBottom() - cell.getBottom());
-                    List<List<Cell>> others = rowsOfCells(si.contains(rectangle));
+                    List<List<Cell>> others = rowsOfCells(
+                            si.contains(
+                                    new Rectangle(cell.getBottom(),
+                                            si.getBounds().getLeft(),
+                                            cell.getLeft() - si.getBounds().getLeft() + 1,
+                                            si.getBounds().getBottom() - cell.getBottom()
+                                    )
+                            ));
 
                     for (List<Cell> r : others) {
                         jumpToColumn = Math.max(jumpToColumn, r.size());
                     }
-
-                    while (startColumn != jumpToColumn) {
-                        add(previousNonNullCellForColumnIndex.get(startColumn), i, startColumn);
-                        startColumn++;
-                    }
                 }
+
+                while (startColumn != jumpToColumn) {
+                    add(previousNonNullCellForColumnIndex.get(startColumn), i, startColumn);
+                    startColumn++;
+                }
+
                 add(cell, i, startColumn);
                 previousNonNullCellForColumnIndex.put(startColumn, cell);
                 startColumn++;
@@ -249,24 +153,34 @@ public class Table extends AbstractTextContainer {
         }
     }
 
-
-    private List<List<Cell>> rowsOfCells(List<Cell> cells) {
-
+    private static List<List<Cell>> rowsOfCells(List<Cell> cells) {
+        Cell c;
+        float lastTop;
         List<List<Cell>> rv = new ArrayList<>();
+        List<Cell> lastRow;
 
         if (cells.isEmpty()) {
             return rv;
         }
-        cells.sort(Comparator.comparingDouble(Rectangle::getLeft));
 
-        cells.sort(Collections.reverseOrder((arg0, arg1) -> Float.compare(Utils.round(arg0.getBottom(), 2),
-                Utils.round(arg1
-                .getBottom(), 2))));
+        Collections.sort(cells, new Comparator<Cell>() {
+            @Override
+            public int compare(Cell arg0, Cell arg1) {
+                return Double.compare(arg0.getLeft(), arg1.getLeft());
+            }
+        });
+
+        Collections.sort(cells, Collections.reverseOrder(new Comparator<Cell>() {
+            @Override
+            public int compare(Cell arg0, Cell arg1) {
+                return Float.compare(Utils.round(arg0.getBottom(), 2), Utils.round(arg1.getBottom(),2));
+            }
+        }));
 
         Iterator<Cell> iter = cells.iterator();
-        Cell c = iter.next();
-        float lastTop = c.getBottom();
-        List<Cell> lastRow = new ArrayList<>();
+        c = iter.next();
+        lastTop = c.getBottom();
+        lastRow = new ArrayList<>();
         lastRow.add(c);
         rv.add(lastRow);
 
@@ -282,7 +196,6 @@ public class Table extends AbstractTextContainer {
         return rv;
     }
 
-
     @Override
     public String getText() {
 
@@ -319,7 +232,6 @@ public class Table extends AbstractTextContainer {
         return sb.toString();
     }
 
-
     public String getTextAsHtml() {
 
         StringBuilder sb = new StringBuilder();
@@ -353,4 +265,41 @@ public class Table extends AbstractTextContainer {
         return sb.toString();
     }
 
+    class CellPosition implements Comparable<CellPosition> {
+
+        CellPosition(int row, int col) {
+            this.row = row;
+            this.col = col;
+        }
+
+        final int row, col;
+
+        @Override
+        public int hashCode() {
+            return row + 101 * col;
+        }
+
+        @Override
+        public boolean equals(Object obj) {
+            if (this == obj) {
+                return true;
+            }
+            if (obj == null) {
+                return false;
+            }
+            if (getClass() != obj.getClass()) {
+                return false;
+            }
+            CellPosition other = (CellPosition) obj;
+            return row == other.row && col == other.col;
+        }
+
+        @Override
+        public int compareTo(CellPosition other) {
+            int rowdiff = row - other.row;
+            return rowdiff != 0 ? rowdiff : col - other.col;
+        }
+
+    }
+
 }

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

@@ -18,9 +18,9 @@ import com.iqser.red.service.redaction.v1.server.tableextraction.utils.Utils;
 @Service
 public class RulingCleaningService {
 
-    public CleanRulings getCleanRulings(List<Ruling> rulings, float maxCharWidth, float maxCharHeight){
+    public CleanRulings getCleanRulings(List<Ruling> rulings, float minCharWidth, float minCharHeight){
         if (!rulings.isEmpty()) {
-            snapPoints(rulings, maxCharWidth , maxCharHeight);
+            snapPoints(rulings, minCharWidth , minCharHeight);
         }
 
         List<Ruling> vrs = new ArrayList<>();

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

@@ -2,6 +2,7 @@ package com.iqser.red.service.redaction.v1.server.tableextraction.service;
 
 import java.awt.geom.Point2D;
 import java.util.ArrayList;
+import java.util.Collections;
 import java.util.Comparator;
 import java.util.HashMap;
 import java.util.HashSet;
@@ -24,28 +25,26 @@ import com.iqser.red.service.redaction.v1.server.tableextraction.model.Table;
 import com.iqser.red.service.redaction.v1.server.tableextraction.utils.Utils;
 
 @Service
+@SuppressWarnings("all")
 public class TableExtractionService {
 
-    public void extractTables(CleanRulings cleanRulings, Page page) {
+    public void extractTables(CleanRulings cleanRulings, Page page){
 
         List<Cell> cells = findCells(cleanRulings.getHorizontal(), cleanRulings.getVertical());
 
-        for (AbstractTextContainer abstractTextContainer : page.getTextBlocks()) {
-            TextBlock textBlock = (TextBlock) abstractTextContainer;
+        Iterator<AbstractTextContainer> itty = page.getTextBlocks().iterator();
+        while (itty.hasNext()) {
+            TextBlock textBlock = (TextBlock) itty.next();
             for (Cell cell : cells) {
-                if (cell.intersects(textBlock.getMinX(), textBlock.getMinY(), textBlock.getWidth(),
-                        textBlock.getHeight())) {
+                if (cell.intersects(textBlock.getMinX(), textBlock.getMinY(), textBlock.getWidth(), textBlock.getHeight())) {
                     cell.addTextBlock(textBlock);
                     break;
                 }
             }
         }
 
-        cells = new ArrayList<>(new HashSet<>(cells));
-        Utils.sort(cells, Rectangle.ILL_DEFINED_ORDER);
-
-
-        List<Rectangle> spreadsheetAreas = findSpreadsheetsFromCells(cells).stream()
+        List<Rectangle> spreadsheetAreas = findSpreadsheetsFromCells(cells)
+                .stream()
                 .filter(r -> r.getWidth() > 0f && r.getHeight() > 0f)
                 .collect(Collectors.toList());
 
@@ -64,9 +63,9 @@ public class TableExtractionService {
         for (Table table : tables) {
             int position = -1;
 
-            Iterator<AbstractTextContainer> itty = page.getTextBlocks().iterator();
+            itty = page.getTextBlocks().iterator();
             while (itty.hasNext()) {
-                AbstractTextContainer textBlock = itty.next();
+                AbstractTextContainer textBlock = (AbstractTextContainer) itty.next();
                 if (table.contains(textBlock)) {
                     if (position == -1) {
                         position = page.getTextBlocks().indexOf(textBlock);
@@ -80,18 +79,17 @@ public class TableExtractionService {
         }
     }
 
-
     public List<Cell> findCells(List<Ruling> horizontalRulingLines, List<Ruling> verticalRulingLines) {
-
         List<Cell> cellsFound = new ArrayList<>();
-        Map<Point2D, Ruling[]> intersectionPoints = Ruling.findIntersections(horizontalRulingLines,
-                verticalRulingLines);
+        Map<Point2D, Ruling[]> intersectionPoints = Ruling.findIntersections(horizontalRulingLines, verticalRulingLines);
         List<Point2D> intersectionPointsList = new ArrayList<>(intersectionPoints.keySet());
-        intersectionPointsList.sort(POINT_COMPARATOR);
+        Collections.sort(intersectionPointsList, POINT_COMPARATOR);
+        boolean doBreak;
 
         for (int i = 0; i < intersectionPointsList.size(); i++) {
             Point2D topLeft = intersectionPointsList.get(i);
             Ruling[] hv = intersectionPoints.get(topLeft);
+            doBreak = false;
 
             // CrossingPointsDirectlyBelow( topLeft );
             List<Point2D> xPoints = new ArrayList<>();
@@ -108,6 +106,10 @@ public class TableExtractionService {
             }
             outer:
             for (Point2D xPoint : xPoints) {
+                if (doBreak) {
+                    break;
+                }
+
                 // is there a vertical edge b/w topLeft and xPoint?
                 if (!hv[1].equals(intersectionPoints.get(xPoint)[1])) {
                     continue;
@@ -118,9 +120,11 @@ public class TableExtractionService {
                         continue;
                     }
                     Point2D btmRight = new Point2D.Float((float) yPoint.getX(), (float) xPoint.getY());
-                    if (intersectionPoints.containsKey(btmRight) && intersectionPoints.get(btmRight)[0].equals(intersectionPoints
-                            .get(xPoint)[0]) && intersectionPoints.get(btmRight)[1].equals(intersectionPoints.get(yPoint)[1])) {
+                    if (intersectionPoints.containsKey(btmRight)
+                            && intersectionPoints.get(btmRight)[0].equals(intersectionPoints.get(xPoint)[0])
+                            && intersectionPoints.get(btmRight)[1].equals(intersectionPoints.get(yPoint)[1])) {
                         cellsFound.add(new Cell(topLeft, btmRight));
+                        doBreak = true;
                         break outer;
                     }
                 }
@@ -135,7 +139,7 @@ public class TableExtractionService {
     }
 
 
-    private List<Rectangle> findSpreadsheetsFromCells(List<? extends Rectangle> cells) {
+    public List<Rectangle> findSpreadsheetsFromCells(List<? extends Rectangle> cells) {
         // via: http://stackoverflow.com/questions/13746284/merging-multiple-adjacent-rectangles-into-one-polygon
         List<Rectangle> rectangles = new ArrayList<>();
         Set<Point2D> pointSet = new HashSet<>();
@@ -143,6 +147,10 @@ public class TableExtractionService {
         Map<Point2D, Point2D> edgesV = new HashMap<>();
         int i = 0;
 
+        cells = new ArrayList<>(new HashSet<>(cells));
+
+        Utils.sort(cells, Rectangle.ILL_DEFINED_ORDER);
+
         for (Rectangle cell : cells) {
             for (Point2D pt : cell.getPoints()) {
                 if (pointSet.contains(pt)) { // shared vertex, remove it
@@ -155,10 +163,10 @@ public class TableExtractionService {
 
         // X first sort
         List<Point2D> pointsSortX = new ArrayList<>(pointSet);
-        pointsSortX.sort(X_FIRST_POINT_COMPARATOR);
+        Collections.sort(pointsSortX, X_FIRST_POINT_COMPARATOR);
         // Y first sort
         List<Point2D> pointsSortY = new ArrayList<>(pointSet);
-        pointsSortY.sort(POINT_COMPARATOR);
+        Collections.sort(pointsSortY, POINT_COMPARATOR);
 
         while (i < pointSet.size()) {
             float currY = (float) pointsSortY.get(i).getY();
@@ -195,12 +203,13 @@ public class TableExtractionService {
                     nextVertex = edgesV.get(curr.point);
                     edgesV.remove(curr.point);
                     lastAddedVertex = new PolygonVertex(nextVertex, Direction.VERTICAL);
+                    polygon.add(lastAddedVertex);
                 } else {
                     nextVertex = edgesH.get(curr.point);
                     edgesH.remove(curr.point);
                     lastAddedVertex = new PolygonVertex(nextVertex, Direction.HORIZONTAL);
+                    polygon.add(lastAddedVertex);
                 }
-                polygon.add(lastAddedVertex);
 
                 if (lastAddedVertex.equals(polygon.get(0))) {
                     // closed polygon
@@ -218,10 +227,10 @@ public class TableExtractionService {
 
         // calculate grid-aligned minimum area rectangles for each found polygon
         for (List<PolygonVertex> poly : polygons) {
-            float top = Float.MAX_VALUE;
-            float left = Float.MAX_VALUE;
-            float bottom = Float.MIN_VALUE;
-            float right = Float.MIN_VALUE;
+            float top = java.lang.Float.MAX_VALUE;
+            float left = java.lang.Float.MAX_VALUE;
+            float bottom = java.lang.Float.MIN_VALUE;
+            float right = java.lang.Float.MIN_VALUE;
             for (PolygonVertex pt : poly) {
                 top = (float) Math.min(top, pt.point.getY());
                 left = (float) Math.min(left, pt.point.getX());
@@ -235,66 +244,69 @@ public class TableExtractionService {
     }
 
 
-    private static final Comparator<Point2D> X_FIRST_POINT_COMPARATOR = (arg0, arg1) -> {
+    private static final Comparator<Point2D> X_FIRST_POINT_COMPARATOR = new Comparator<Point2D>() {
+        @Override
+        public int compare(Point2D arg0, Point2D arg1) {
+            int rv = 0;
+            float arg0X = Utils.round(arg0.getX(), 2);
+            float arg0Y = Utils.round(arg0.getY(), 2);
+            float arg1X = Utils.round(arg1.getX(), 2);
+            float arg1Y = Utils.round(arg1.getY(), 2);
 
-        int rv = 0;
-        float arg0X = Utils.round(arg0.getX(), 2);
-        float arg0Y = Utils.round(arg0.getY(), 2);
-        float arg1X = Utils.round(arg1.getX(), 2);
-        float arg1Y = Utils.round(arg1.getY(), 2);
-
-        if (arg0X > arg1X) {
-            rv = 1;
-        } else if (arg0X < arg1X) {
-            rv = -1;
-        } else if (arg0Y > arg1Y) {
-            rv = 1;
-        } else if (arg0Y < arg1Y) {
-            rv = -1;
+            if (arg0X > arg1X) {
+                rv = 1;
+            } else if (arg0X < arg1X) {
+                rv = -1;
+            } else if (arg0Y > arg1Y) {
+                rv = 1;
+            } else if (arg0Y < arg1Y) {
+                rv = -1;
+            }
+            return rv;
         }
-        return rv;
     };
 
-    private static final Comparator<Point2D> POINT_COMPARATOR = (arg0, arg1) -> {
 
-        int rv = 0;
-        float arg0X = Utils.round(arg0.getX(), 2);
-        float arg0Y = Utils.round(arg0.getY(), 2);
-        float arg1X = Utils.round(arg1.getX(), 2);
-        float arg1Y = Utils.round(arg1.getY(), 2);
+    private static final Comparator<Point2D> POINT_COMPARATOR = new Comparator<Point2D>() {
+        @Override
+        public int compare(Point2D arg0, Point2D arg1) {
+            int rv = 0;
+            float arg0X = Utils.round(arg0.getX(), 2);
+            float arg0Y = Utils.round(arg0.getY(), 2);
+            float arg1X = Utils.round(arg1.getX(), 2);
+            float arg1Y = Utils.round(arg1.getY(), 2);
 
-        if (arg0Y > arg1Y) {
-            rv = 1;
-        } else if (arg0Y < arg1Y) {
-            rv = -1;
-        } else if (arg0X > arg1X) {
-            rv = 1;
-        } else if (arg0X < arg1X) {
-            rv = -1;
+
+            if (arg0Y > arg1Y) {
+                rv = 1;
+            } else if (arg0Y < arg1Y) {
+                rv = -1;
+            } else if (arg0X > arg1X) {
+                rv = 1;
+            } else if (arg0X < arg1X) {
+                rv = -1;
+            }
+            return rv;
         }
-        return rv;
     };
 
+
     private enum Direction {
-        HORIZONTAL, VERTICAL
+        HORIZONTAL,
+        VERTICAL
     }
 
     static class PolygonVertex {
-
         Point2D point;
         Direction direction;
 
-
-        PolygonVertex(Point2D point, Direction direction) {
-
+        public PolygonVertex(Point2D point, Direction direction) {
             this.direction = direction;
             this.point = point;
         }
 
-
         @Override
         public boolean equals(Object other) {
-
             if (this == other) {
                 return true;
             }
@@ -304,21 +316,15 @@ public class TableExtractionService {
             return this.point.equals(((PolygonVertex) other).point);
         }
 
-
         @Override
         public int hashCode() {
-
             return this.point.hashCode();
         }
 
-
         @Override
         public String toString() {
-
-            return String.format("%s[point=%s,direction=%s]", this.getClass()
-                    .getName(), this.point.toString(), this.direction.toString());
+            return String.format("%s[point=%s,direction=%s]", this.getClass().getName(), this.point.toString(), this.direction.toString());
         }
-
     }
 
 }

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

@@ -2,13 +2,7 @@ package com.iqser.red.service.redaction.v1.server.visualization.service;
 
 import java.awt.Color;
 import java.io.IOException;
-import java.util.ArrayList;
-import java.util.GregorianCalendar;
-import java.util.HashSet;
 import java.util.List;
-import java.util.Set;
-import java.util.UUID;
-import java.util.stream.Collectors;
 
 import org.apache.commons.collections4.CollectionUtils;
 import org.apache.pdfbox.pdmodel.PDDocument;
@@ -19,15 +13,10 @@ import org.apache.pdfbox.pdmodel.font.PDType1Font;
 import org.apache.pdfbox.pdmodel.graphics.color.PDColor;
 import org.apache.pdfbox.pdmodel.graphics.color.PDDeviceRGB;
 import org.apache.pdfbox.pdmodel.interactive.annotation.PDAnnotation;
-import org.apache.pdfbox.pdmodel.interactive.annotation.PDAnnotationText;
 import org.apache.pdfbox.pdmodel.interactive.annotation.PDAnnotationTextMarkup;
-import org.apache.pdfbox.text.TextPosition;
 import org.springframework.stereotype.Service;
 
-import com.iqser.red.service.redaction.v1.model.Comment;
-import com.iqser.red.service.redaction.v1.model.IdRemoval;
-import com.iqser.red.service.redaction.v1.model.ManualRedactionEntry;
-import com.iqser.red.service.redaction.v1.model.ManualRedactions;
+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.model.RedactionLogEntry;
 import com.iqser.red.service.redaction.v1.server.classification.model.Document;
@@ -37,13 +26,14 @@ import com.iqser.red.service.redaction.v1.server.parsing.model.TextPositionSeque
 import com.iqser.red.service.redaction.v1.server.redaction.model.Entity;
 import com.iqser.red.service.redaction.v1.server.redaction.model.EntityPositionSequence;
 import com.iqser.red.service.redaction.v1.server.redaction.service.DictionaryService;
-import com.iqser.red.service.redaction.v1.server.redaction.utils.IdBuilder;
 import com.iqser.red.service.redaction.v1.server.tableextraction.model.AbstractTextContainer;
 import com.iqser.red.service.redaction.v1.server.tableextraction.model.Cell;
 import com.iqser.red.service.redaction.v1.server.tableextraction.model.Table;
 
 import lombok.RequiredArgsConstructor;
+import lombok.extern.slf4j.Slf4j;
 
+@Slf4j
 @Service
 @RequiredArgsConstructor
 public class AnnotationHighlightService {
@@ -51,326 +41,139 @@ public class AnnotationHighlightService {
     private final DictionaryService dictionaryService;
 
 
-    public void highlight(PDDocument document, Document classifiedDoc, boolean flatRedaction,
-                          ManualRedactions manualRedactions) throws IOException {
-
-        Set<Integer> manualRedactionPages = getManualRedactionPages(manualRedactions);
+    public void highlight(PDDocument document, Document classifiedDoc, boolean flatRedaction) throws IOException {
 
         for (int page = 1; page <= document.getNumberOfPages(); page++) {
 
             PDPage pdPage = document.getPage(page - 1);
 
-            drawSectionFrames(document, classifiedDoc, flatRedaction, pdPage, page);
+            if (!flatRedaction) {
+                PDPageContentStream contentStream = new PDPageContentStream(document, pdPage, PDPageContentStream.AppendMode.APPEND, true);
 
-            if (classifiedDoc.getEntities().get(page) != null) {
-                addAnnotations(pdPage, classifiedDoc, flatRedaction, manualRedactions, page);
+                for (Paragraph paragraph : classifiedDoc.getParagraphs()) {
+
+                    for (int i = 0; i <= paragraph.getPageBlocks().size() - 1; i++) {
+
+                        AbstractTextContainer textBlock = paragraph.getPageBlocks().get(i);
+
+                        if (textBlock.getPage() != page) {
+                            continue;
+                        }
+                        if (textBlock instanceof TextBlock) {
+                            textBlock.setClassification((i + 1) + "/" + paragraph.getPageBlocks().size());
+                            visualizeTextBlock((TextBlock) textBlock, contentStream);
+                        } else if (textBlock instanceof Table) {
+                            textBlock.setClassification((i + 1) + "/" + paragraph.getPageBlocks().size());
+                            visualizeTable((Table) textBlock, contentStream);
+                        }
+
+                    }
+                }
+
+                contentStream.close();
             }
 
-            if (manualRedactionPages.contains(page)) {
-                addManualAnnotations(pdPage, classifiedDoc, manualRedactions, page);
-            }
-        }
-    }
-
-
-    private Set<Integer> getManualRedactionPages(ManualRedactions manualRedactions) {
-
-        Set<Integer> manualRedactionPages = new HashSet<>();
-
-        if (manualRedactions == null) {
-            return manualRedactionPages;
-        }
-
-        manualRedactions.getEntriesToAdd().forEach(entry -> {
-            entry.getPositions().forEach(pos -> {
-                manualRedactionPages.add(pos.getPage());
-            });
-        });
-        return manualRedactionPages;
-    }
-
-
-    private void addAnnotations(PDPage pdPage, Document classifiedDoc, boolean flatRedaction,
-                                ManualRedactions manualRedactions, int page) throws IOException {
-
-        List<PDAnnotation> annotations = pdPage.getAnnotations();
-
-        for (Entity entity : classifiedDoc.getEntities().get(page)) {
-
-            if (flatRedaction && !isRedactionType(entity)) {
+            if (classifiedDoc.getEntities().get(page) == null) {
                 continue;
             }
 
-            RedactionLogEntry redactionLogEntry = createRedactionLogEntry(entity);
-            boolean requestedToRemove = false;
-            boolean removeFromDictionary = false;
-            List<Comment> comments = null;
-            for (EntityPositionSequence entityPositionSequence : entity.getPositionSequences()) {
+            for (Entity entity : classifiedDoc.getEntities().get(page)) {
 
-                if (manualRedactions != null && !manualRedactions.getIdsToRemove().isEmpty()) {
-                    for (IdRemoval manualRemoval : manualRedactions.getIdsToRemove()) {
-                        if (manualRemoval.getId().equals(entityPositionSequence.getId())) {
-                            comments = manualRemoval.getComments();
-                            String manualOverrideReason;
-                            if (manualRemoval.isApproved()) {
-                                entity.setRedaction(false);
-                                redactionLogEntry.setRedacted(false);
-                                redactionLogEntry.setApproved(true);
-                                manualOverrideReason = entity.getRedactionReason() + ", removed by manual override";
-                            } else {
-                                requestedToRemove = true;
-                                manualOverrideReason = entity.getRedactionReason() + ", requested to remove";
-                                if (manualRemoval.isRemoveFromDictionary()) {
-                                    removeFromDictionary = true;
-                                }
-                            }
+                RedactionLogEntry redactionLogEntry = new RedactionLogEntry();
 
-                            entity.setRedactionReason(manualOverrideReason);
-                            redactionLogEntry.setReason(manualOverrideReason);
-                            redactionLogEntry.setManual(true);
-                        }
+                for (EntityPositionSequence entityPositionSequence : entity.getPositionSequences()) {
+
+                    if (flatRedaction && !isRedactionType(entity)) {
+                        continue;
                     }
 
+                    for (TextPositionSequence textPositions : entityPositionSequence.getSequences()) {
+
+                        float height = textPositions.getTextPositions().get(0).getHeightDir() + 2;
+
+                        float posXInit;
+                        float posXEnd;
+                        float posYInit;
+                        float posYEnd;
+
+                        if (textPositions.getTextPositions().get(0).getRotation() == 90) {
+
+                            posXEnd = textPositions.getTextPositions().get(0).getYDirAdj() + 2;
+                            posXInit = textPositions.getTextPositions().get(0).getYDirAdj() - height;
+                            posYInit = textPositions.getTextPositions().get(0).getXDirAdj();
+                            posYEnd = textPositions.getTextPositions()
+                                    .get(textPositions.getTextPositions().size() - 1)
+                                    .getXDirAdj() - height + 4;
+                        } else {
+
+                            posXInit = textPositions.getTextPositions().get(0).getXDirAdj();
+                            posXEnd = textPositions.getTextPositions()
+                                    .get(textPositions.getTextPositions().size() - 1)
+                                    .getXDirAdj() + textPositions.getTextPositions()
+                                    .get(textPositions.getTextPositions().size() - 1)
+                                    .getWidth() + 1;
+                            posYInit = textPositions.getTextPositions()
+                                    .get(0)
+                                    .getPageHeight() - textPositions.getTextPositions().get(0).getYDirAdj() - 2;
+                            posYEnd = textPositions.getTextPositions()
+                                    .get(0)
+                                    .getPageHeight() - textPositions.getTextPositions()
+                                    .get(textPositions.getTextPositions().size() - 1)
+                                    .getYDirAdj() + 2;
+                        }
+
+                        Rectangle textHighlightRectangle = new Rectangle(new Point(posXInit, posYInit), posXEnd - posXInit, posYEnd - posYInit + height, page);
+
+                        List<PDAnnotation> annotations = pdPage.getAnnotations();
+                        PDAnnotationTextMarkup highlight = new PDAnnotationTextMarkup(PDAnnotationTextMarkup.SUB_TYPE_HIGHLIGHT);
+                        highlight.constructAppearances();
+
+                        PDRectangle annotationPosition = new PDRectangle();
+                        annotationPosition.setLowerLeftX(posXInit);
+                        annotationPosition.setLowerLeftY(posYEnd);
+                        annotationPosition.setUpperRightX(posXEnd);
+                        annotationPosition.setUpperRightY(posYEnd + height);
+
+                        highlight.setRectangle(annotationPosition);
+                        if (!flatRedaction && !isHint(entity)) {
+                            highlight.setAnnotationName(entityPositionSequence.getId().toString());
+                            highlight.setTitlePopup(entityPositionSequence.getId().toString());
+                            highlight.setContents("\nRule " + entity.getMatchedRule() + " matched\n\n" + entity.getRedactionReason() + "\n\n" + "In Section : \"" + entity
+                                    .getHeadline() + "\"");
+                        }
+
+                        highlight.setQuadPoints(toQuadPoints(textHighlightRectangle));
+
+                        PDColor color;
+                        if (flatRedaction) {
+                            color = new PDColor(new float[]{0, 0, 0}, PDDeviceRGB.INSTANCE);
+                        } else {
+                            color = new PDColor(getColor(entity), PDDeviceRGB.INSTANCE);
+                        }
+
+                        highlight.setColor(color);
+                        annotations.add(highlight);
+
+                        redactionLogEntry.getPositions().add(textHighlightRectangle);
+
+                    }
+                    redactionLogEntry.setId(entityPositionSequence.getId().toString());
                 }
-
-                if (CollectionUtils.isNotEmpty(entityPositionSequence.getSequences())) {
-                    List<Rectangle> rectanglesPerline = getRectanglesPerLine(entityPositionSequence.getSequences()
-                            .stream()
-                            .flatMap(seq -> seq.getTextPositions().stream())
-                            .collect(Collectors.toList()), page);
-
-                    redactionLogEntry.getPositions().addAll(rectanglesPerline);
-                    annotations.addAll(createAnnotation(rectanglesPerline, prefixId(entity, entityPositionSequence.getId(), requestedToRemove, removeFromDictionary), createAnnotationContent(entity), getColor(entity, requestedToRemove), comments, !isHint(entity)));
-                }
-
-                redactionLogEntry.setId(entityPositionSequence.getId());
-            }
-            classifiedDoc.getRedactionLogEntities().add(redactionLogEntry);
-        }
-
-    }
-
-
-    private String prefixId(Entity entity, String id, boolean requestedToRemove, boolean removeFromDictionary) {
-
-        if (isHint(entity)) {
-            return "hint:" + entity.getType() + ":" + id;
-        }
-
-        if (entity.isRedaction() && requestedToRemove && removeFromDictionary) {
-            return "request:remove:" + entity.getType() + ":" + id;
-        }
-
-        if (entity.isRedaction() && requestedToRemove && !removeFromDictionary) {
-            return "request:remove:only_here:" + id;
-        }
-
-        if (entity.isRedaction()) {
-            return "redaction:" + entity.getType() + ":" + id;
-        }
-        return "ignore:" + entity.getType() + ":" + id;
-    }
-
-
-    private List<Rectangle> getRectanglesPerLine(List<TextPosition> textPositions, int page) {
-
-        List<Rectangle> rectangles = new ArrayList<>();
-        if (textPositions.size() == 1) {
-            rectangles.add(new TextPositionSequence(textPositions, page).getRectangle());
-        } else {
-            float y = textPositions.get(0).getYDirAdj();
-            int startIndex = 0;
-            for (int i = 1; i < textPositions.size(); i++) {
-                float yDirAdj = textPositions.get(i).getYDirAdj();
-                if (yDirAdj != y) {
-                    rectangles.add(new TextPositionSequence(textPositions.subList(startIndex, i), page).getRectangle());
-                    y = yDirAdj;
-                    startIndex = i;
-                }
-            }
-            if (startIndex != textPositions.size() - 1) {
-                rectangles.add(new TextPositionSequence(textPositions.subList(startIndex, textPositions.size()), page).getRectangle());
-            }
-        }
-
-        return rectangles;
-    }
-
-
-    private void addManualAnnotations(PDPage pdPage, Document classifiedDoc, ManualRedactions manualRedactions,
-                                      int page) throws IOException {
-
-        if (manualRedactions == null) {
-            return;
-        }
-
-        List<PDAnnotation> annotations = pdPage.getAnnotations();
-
-        for (ManualRedactionEntry manualRedactionEntry : manualRedactions.getEntriesToAdd()) {
-
-            String id = IdBuilder.buildId(manualRedactionEntry);
-
-            RedactionLogEntry redactionLogEntry = createRedactionLogEntry(manualRedactionEntry, id);
-
-            List<Rectangle> rectanglesOnPage = new ArrayList<>();
-            for (Rectangle rectangle : manualRedactionEntry.getPositions()) {
-                if (page == rectangle.getPage()) {
-                    rectanglesOnPage.add(rectangle);
-                    redactionLogEntry.getPositions().add(rectangle);
-                }
-            }
-
-            if (!rectanglesOnPage.isEmpty()) {
-                annotations.addAll(createAnnotation(rectanglesOnPage, prefixId(manualRedactionEntry, id), createAnnotationContent(manualRedactionEntry), getColorForManualAdd(manualRedactionEntry
-                        .getType(), manualRedactionEntry.isApproved()), manualRedactionEntry.getComments(), true));
+                redactionLogEntry.setColor(getColor(entity));
+                redactionLogEntry.setReason(entity.getRedactionReason());
+                redactionLogEntry.setValue(entity.getWord());
+                redactionLogEntry.setType(entity.getType());
+                redactionLogEntry.setRedacted(entity.isRedaction());
+                redactionLogEntry.setSection(entity.getHeadline());
+                redactionLogEntry.setHint(isHint(entity));
                 classifiedDoc.getRedactionLogEntities().add(redactionLogEntry);
             }
+
         }
     }
 
 
-    private String prefixId(ManualRedactionEntry manualRedactionEntry, String id) {
-
-        if (manualRedactionEntry.isApproved()) {
-            return "redaction:" + manualRedactionEntry.getType() + ":" + id;
-        }
-        if (manualRedactionEntry.isAddToDictionary()) {
-            return "request:add:" + manualRedactionEntry.getType() + ":" + id;
-        }
-        return "request:add:only_here" + ":" + id;
-    }
-
-
-    private RedactionLogEntry createRedactionLogEntry(ManualRedactionEntry manualRedactionEntry, String id) {
-
-        return RedactionLogEntry.builder()
-                .id(id)
-                .color(getColor(manualRedactionEntry.getType()))
-                .reason(manualRedactionEntry.getReason())
-                .value(manualRedactionEntry.getValue())
-                .type(manualRedactionEntry.getType())
-                .redacted(true)
-                .isHint(false)
-                .section(manualRedactionEntry.getSection())
-                .sectionNumber(manualRedactionEntry.getSectionNumber())
-                .manual(true)
-                .approved(manualRedactionEntry.isApproved())
-                .build();
-    }
-
-
-    private RedactionLogEntry createRedactionLogEntry(Entity entity) {
-
-        return RedactionLogEntry.builder()
-                .color(getColor(entity, false))
-                .reason(entity.getRedactionReason())
-                .value(entity.getWord())
-                .type(entity.getType())
-                .redacted(entity.isRedaction())
-                .isHint(isHint(entity))
-                .section(entity.getHeadline())
-                .sectionNumber(entity.getSectionNumber())
-                .build();
-    }
-
-
-    private List<PDAnnotation> createAnnotation(List<Rectangle> rectangles, String id, String content, float[] color,
-                                                List<Comment> comments, boolean popup) {
-
-        List<PDAnnotation> annotations = new ArrayList<>();
-
-        PDAnnotationTextMarkup annotation = new PDAnnotationTextMarkup(PDAnnotationTextMarkup.SUB_TYPE_HIGHLIGHT);
-        annotation.constructAppearances();
-        PDRectangle pdRectangle = toPDRectangle(rectangles);
-        annotation.setRectangle(pdRectangle);
-        annotation.setQuadPoints(toQuadPoints(rectangles));
-        if (popup) {
-            annotation.setContents(content);
-        }
-        annotation.setTitlePopup(id);
-        annotation.setAnnotationName(id);
-        annotation.setColor(new PDColor(color, PDDeviceRGB.INSTANCE));
-        annotations.add(annotation);
-
-        if (comments != null) {
-            for (Comment comment : comments) {
-                PDAnnotationText txtAnnot = new PDAnnotationText();
-                txtAnnot.setAnnotationName(UUID.randomUUID().toString());
-                txtAnnot.setInReplyTo(annotation); // Reference to highlight annotation
-                txtAnnot.setName(PDAnnotationText.NAME_COMMENT);
-                txtAnnot.setCreationDate(GregorianCalendar.from(comment.getDate().toZonedDateTime()));
-                txtAnnot.setTitlePopup(comment.getUser());
-                txtAnnot.setContents(comment.getText());
-                txtAnnot.setRectangle(pdRectangle);
-                annotations.add(txtAnnot);
-            }
-        }
-
-        return annotations;
-    }
-
-
-    private String createAnnotationContent(Entity entity) {
-
-        return "\nRule " + entity.getMatchedRule() + " matched" + "\n\n" + entity.getRedactionReason() + "\n\nIn " + "Section : \"" + entity
-                .getHeadline() + "\"";
-    }
-
-
-    private String createAnnotationContent(ManualRedactionEntry entry) {
-
-        return "\nManual Redaction" + "\n\nIn Section : \"" + entry.getSection() + "\"";
-    }
-
-
-    private PDRectangle toPDRectangle(List<Rectangle> rectangles) {
-
-        float lowerLeftX = Float.MAX_VALUE;
-        float upperRightX = 0;
-        float lowerLeftY = 0;
-        float upperRightY = Float.MAX_VALUE;
-
-        for (Rectangle rectangle : rectangles) {
-            if (rectangle.getTopLeft().getX() < lowerLeftX) {
-                lowerLeftX = rectangle.getTopLeft().getX();
-            }
-            if (rectangle.getTopLeft().getX() + rectangle.getWidth() > upperRightX) {
-                upperRightX = rectangle.getTopLeft().getX() + rectangle.getWidth();
-            }
-            if (rectangle.getTopLeft().getY() + rectangle.getHeight() > lowerLeftY) {
-                lowerLeftY = rectangle.getTopLeft().getY() + rectangle.getHeight();
-            }
-            if (rectangle.getTopLeft().getY() < upperRightY) {
-                upperRightY = rectangle.getTopLeft().getY();
-            }
-        }
-
-        PDRectangle annotationPosition = new PDRectangle();
-        annotationPosition.setLowerLeftX(lowerLeftX);
-        annotationPosition.setLowerLeftY(lowerLeftY);
-        annotationPosition.setUpperRightX(upperRightX);
-        annotationPosition.setUpperRightY(upperRightY);
-        return annotationPosition;
-    }
-
-
-    private float[] toQuadPoints(List<Rectangle> rectangles) {
-
-        float[] quadPoints = new float[rectangles.size() * 8];
-        int i = 0;
-
-        for (Rectangle rectangle : rectangles) {
-            float[] quadPoint = toQuadPoint(rectangle);
-            for (int j = 0; j <= 7; j++) {
-                quadPoints[i + j] = quadPoint[j];
-            }
-            i += 8;
-        }
-        return quadPoints;
-    }
-
-
-    private float[] toQuadPoint(Rectangle rectangle) {
+    private float[] toQuadPoints(Rectangle rectangle) {
 
         // quadPoints is array of x,y coordinates in Z-like order (top-left, top-right, bottom-left,bottom-right)
         // of the area to be highlighted
@@ -386,93 +189,52 @@ public class AnnotationHighlightService {
         if (!entity.isRedaction()) {
             return false;
         }
-        return !isHint(entity);
+        if (isHint(entity)) {
+            return false;
+        }
+        return true;
     }
 
 
-    private float[] getColor(Entity entity, boolean requestedToRemove) {
+    private float[] getColor(Entity entity) {
 
-        if (requestedToRemove) {
-            return dictionaryService.getRequestRemoveColor();
-        }
         if (!entity.isRedaction() && !isHint(entity)) {
             return new float[]{0.627f, 0.627f, 0.627f};
         }
+
         if (!dictionaryService.getEntryColors().containsKey(entity.getType())) {
-            return dictionaryService.getDefaultColor();
+            return dictionaryService.getEntryColors().get("default");
         }
+
         return dictionaryService.getEntryColors().get(entity.getType());
     }
 
-
-    private float[] getColorForManualAdd(String type, boolean approved) {
-
-        if (!approved) {
-            return dictionaryService.getRequestAddColor();
-        }
-        return getColor(type);
-    }
-
-
-    private float[] getColor(String type) {
-
-        if (!dictionaryService.getEntryColors().containsKey(type)) {
-            return dictionaryService.getDefaultColor();
-        }
-        return dictionaryService.getEntryColors().get(type);
-    }
-
-
     private boolean isHint(Entity entity) {
-
         List<String> hintTypes = dictionaryService.getHintTypes();
-        return CollectionUtils.isNotEmpty(hintTypes) && hintTypes.contains(entity.getType());
-    }
-
-
-    private void drawSectionFrames(PDDocument document, Document classifiedDoc, boolean flatRedaction, PDPage pdPage,
-                                   int page) throws IOException {
-
-        if (flatRedaction) {
-            return;
+        if (!CollectionUtils.isEmpty(hintTypes) && hintTypes.contains(entity.getType())) {
+            return true;
         }
-
-        PDPageContentStream contentStream = new PDPageContentStream(document, pdPage, PDPageContentStream.AppendMode.APPEND, true);
-        for (Paragraph paragraph : classifiedDoc.getParagraphs()) {
-
-            for (int i = 0; i <= paragraph.getPageBlocks().size() - 1; i++) {
-
-                AbstractTextContainer textBlock = paragraph.getPageBlocks().get(i);
-
-                if (textBlock.getPage() != page) {
-                    continue;
-                }
-                if (textBlock instanceof TextBlock) {
-                    textBlock.setClassification((i + 1) + "/" + paragraph.getPageBlocks().size());
-                    visualizeTextBlock((TextBlock) textBlock, contentStream);
-                } else if (textBlock instanceof Table) {
-                    textBlock.setClassification((i + 1) + "/" + paragraph.getPageBlocks().size());
-                    visualizeTable((Table) textBlock, contentStream);
-                }
-            }
-        }
-        contentStream.close();
+        return false;
     }
 
-
     private void visualizeTextBlock(TextBlock textBlock, PDPageContentStream contentStream) throws IOException {
 
         contentStream.setStrokingColor(Color.LIGHT_GRAY);
         contentStream.setLineWidth(0.5f);
+
         contentStream.addRect(textBlock.getMinX(), textBlock.getMinY(), textBlock.getWidth(), textBlock.getHeight());
         contentStream.stroke();
 
         if (textBlock.getClassification() != null) {
             contentStream.beginText();
+
             contentStream.setNonStrokingColor(Color.DARK_GRAY);
             contentStream.setFont(PDType1Font.TIMES_ROMAN, 8f);
+
             contentStream.newLineAtOffset(textBlock.getMinX(), textBlock.getMaxY());
+
             contentStream.showText(textBlock.getClassification());
+
             contentStream.endText();
         }
     }
@@ -489,16 +251,26 @@ public class AnnotationHighlightService {
                     contentStream.addRect((float) cell.getX(), (float) cell.getY(), (float) cell.getWidth(), (float) cell
                             .getHeight());
                     contentStream.stroke();
+
+//                    contentStream.setStrokingColor(Color.GREEN);
+//                    for (TextBlock textBlock : cell.getTextBlocks()) {
+//                        contentStream.addRect(textBlock.getMinX(), textBlock.getMinY(), textBlock.getWidth(), textBlock.getHeight());
+//                        contentStream.stroke();
+//                    }
                 }
             }
         }
 
         if (table.getClassification() != null) {
             contentStream.beginText();
+
             contentStream.setNonStrokingColor(Color.DARK_GRAY);
             contentStream.setFont(PDType1Font.TIMES_ROMAN, 8f);
+
             contentStream.newLineAtOffset(table.getMinX(), table.getMinY());
+
             contentStream.showText(table.getClassification());
+
             contentStream.endText();
         }
     }

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

@@ -8,6 +8,12 @@ spring:
   profiles:
     active: kubernetes
 
+platform.multi-tenancy:
+  enabled: ${multitenancy.enabled:false}
+  tenantFilter:
+    urlPatterns: /redact
+    urlPatternsToIgnore:
+
 management:
   endpoint:
     metrics.enabled: ${monitoring.enabled:false}

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

@@ -1,29 +1,25 @@
 package com.iqser.red.service.redaction.v1.server;
 
-import static org.assertj.core.api.Assertions.assertThat;
 import static org.mockito.Mockito.when;
 import static org.springframework.boot.test.context.SpringBootTest.WebEnvironment.DEFINED_PORT;
 
 import java.io.BufferedReader;
 import java.io.ByteArrayInputStream;
-import java.io.File;
-import java.io.FileInputStream;
 import java.io.FileOutputStream;
 import java.io.IOException;
 import java.io.InputStream;
 import java.io.InputStreamReader;
 import java.net.URL;
 import java.nio.charset.StandardCharsets;
-import java.time.OffsetDateTime;
 import java.util.ArrayList;
 import java.util.HashMap;
 import java.util.List;
 import java.util.Map;
-import java.util.Set;
 import java.util.stream.Collectors;
 
 import org.apache.commons.io.IOUtils;
 import org.junit.Before;
+import org.junit.Ignore;
 import org.junit.Test;
 import org.junit.runner.RunWith;
 import org.kie.api.KieServices;
@@ -39,17 +35,10 @@ import org.springframework.context.annotation.Bean;
 import org.springframework.core.io.ClassPathResource;
 import org.springframework.test.context.junit4.SpringRunner;
 
-import com.iqser.red.service.configuration.v1.api.model.DefaultColor;
 import com.iqser.red.service.configuration.v1.api.model.DictionaryResponse;
 import com.iqser.red.service.configuration.v1.api.model.RulesResponse;
 import com.iqser.red.service.configuration.v1.api.model.TypeResponse;
 import com.iqser.red.service.configuration.v1.api.model.TypeResult;
-import com.iqser.red.service.redaction.v1.model.Comment;
-import com.iqser.red.service.redaction.v1.model.IdRemoval;
-import com.iqser.red.service.redaction.v1.model.ManualRedactionEntry;
-import com.iqser.red.service.redaction.v1.model.ManualRedactions;
-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.model.RedactionRequest;
 import com.iqser.red.service.redaction.v1.model.RedactionResult;
 import com.iqser.red.service.redaction.v1.server.client.DictionaryClient;
@@ -58,19 +47,16 @@ import com.iqser.red.service.redaction.v1.server.controller.RedactionController;
 import com.iqser.red.service.redaction.v1.server.redaction.utils.ResourceLoader;
 import com.iqser.red.service.redaction.v1.server.redaction.utils.TextNormalizationUtilities;
 
+@Ignore
 @RunWith(SpringRunner.class)
 @SpringBootTest(webEnvironment = DEFINED_PORT)
 public class RedactionIntegrationTest {
 
-    private static final String RULES = loadFromClassPath("drools/rules.drl");
-    private static final String VERTEBRATES_CODE = "vertebrate";
-    private static final String ADDRESS_CODE = "address";
-    private static final String NAME_CODE = "name";
-    private static final String SPONSOR = "sponsor";
-    private static final String NO_REDACTION_INDICATOR = "no_redaction_indicator";
-    private static final String REDACTION_INDICATOR = "redaction_indicator";
-    private static final String HINT_ONLY = "hint_only";
-    private static final String MUST_REDACT = "must_redact";
+    public static final String VERTEBRATES_CODE = "vertebrate";
+    public static final String ADDRESS_CODE = "address";
+    public static final String NAME_CODE = "name";
+    public static final String NO_REDACTION_INDICATOR = "no_redaction_indicator";
+    public static final String DEFAULT = "default";
 
     @Autowired
     private RedactionController redactionController;
@@ -81,10 +67,8 @@ public class RedactionIntegrationTest {
     @MockBean
     private DictionaryClient dictionaryClient;
 
-    private final Map<String, List<String>> dictionary = new HashMap<>();
-    private final Map<String, float[]> typeColorMap = new HashMap<>();
-    private final Map<String, Boolean> hintTypeMap = new HashMap<>();
-    private final Map<String, Boolean> caseInSensitiveMap = new HashMap<>();
+    private Map<String, List<String>> dictionary = new HashMap<>();
+    private Map<String, float[]> typeColorMap = new HashMap<>();
 
     @TestConfiguration
     public static class RedactionIntegrationTestConfiguration {
@@ -95,24 +79,21 @@ public class RedactionIntegrationTest {
             KieServices kieServices = KieServices.Factory.get();
 
             KieFileSystem kieFileSystem = kieServices.newKieFileSystem();
-            InputStream input = new ByteArrayInputStream(RULES.getBytes(StandardCharsets.UTF_8));
-            kieFileSystem.write("src/test/resources/drools/rules.drl",
-                                kieServices.getResources().newInputStreamResource(input));
+            InputStream input = new ByteArrayInputStream("".getBytes(StandardCharsets.UTF_8));
+            kieFileSystem.write("src/main/resources/drools/rules.drl", kieServices.getResources().newInputStreamResource(input));
             KieBuilder kieBuilder = kieServices.newKieBuilder(kieFileSystem);
             kieBuilder.buildAll();
             KieModule kieModule = kieBuilder.getKieModule();
 
             return kieServices.newKieContainer(kieModule.getReleaseId());
         }
-
     }
 
-
     @Before
-    public void stubClients() {
+    public void stubRulesClient() {
 
         when(rulesClient.getVersion()).thenReturn(0L);
-        when(rulesClient.getRules()).thenReturn(new RulesResponse(RULES));
+        when(rulesClient.getRules()).thenReturn(new RulesResponse(loadFromClassPath("drools/rules.drl")));
 
         loadDictionaryForTest();
         loadTypeForTest();
@@ -121,176 +102,45 @@ public class RedactionIntegrationTest {
         when(dictionaryClient.getDictionaryForType(VERTEBRATES_CODE)).thenReturn(getDictionaryResponse(VERTEBRATES_CODE));
         when(dictionaryClient.getDictionaryForType(ADDRESS_CODE)).thenReturn(getDictionaryResponse(ADDRESS_CODE));
         when(dictionaryClient.getDictionaryForType(NAME_CODE)).thenReturn(getDictionaryResponse(NAME_CODE));
-        when(dictionaryClient.getDictionaryForType(SPONSOR)).thenReturn(getDictionaryResponse(SPONSOR));
-        when(dictionaryClient.getDictionaryForType(NO_REDACTION_INDICATOR)).thenReturn(getDictionaryResponse(
-                NO_REDACTION_INDICATOR));
-        when(dictionaryClient.getDictionaryForType(REDACTION_INDICATOR)).thenReturn(getDictionaryResponse(
-                REDACTION_INDICATOR));
-        when(dictionaryClient.getDictionaryForType(HINT_ONLY)).thenReturn(getDictionaryResponse(HINT_ONLY));
-        when(dictionaryClient.getDictionaryForType(MUST_REDACT)).thenReturn(getDictionaryResponse(MUST_REDACT));
-        when(dictionaryClient.getDefaultColor()).thenReturn(new DefaultColor(new float[]{1f, 0.502f, 0f}));
+        when(dictionaryClient.getDictionaryForType(NO_REDACTION_INDICATOR)).thenReturn(getDictionaryResponse(NO_REDACTION_INDICATOR));
+        when(dictionaryClient.getDictionaryForType(DEFAULT)).thenReturn(getDictionaryResponse(DEFAULT));
     }
 
-
     private void loadDictionaryForTest() {
-
-        dictionary.computeIfAbsent(NAME_CODE, v -> new ArrayList<>())
-                .addAll(ResourceLoader.load("dictionaries/names.txt")
-                                .stream()
-                                .map(this::cleanDictionaryEntry)
-                                .collect(Collectors.toSet()));
-        dictionary.computeIfAbsent(SPONSOR, v -> new ArrayList<>())
-                .addAll(ResourceLoader.load("dictionaries/sponsor_companies.txt")
-                                .stream()
-                                .map(this::cleanDictionaryEntry)
-                                .collect(Collectors.toSet()));
-        dictionary.computeIfAbsent(VERTEBRATES_CODE, v -> new ArrayList<>())
-                .addAll(ResourceLoader.load("dictionaries/vertebrates.txt")
-                                .stream()
-                                .map(this::cleanDictionaryEntry)
-                                .collect(Collectors.toSet()));
-        dictionary.computeIfAbsent(ADDRESS_CODE, v -> new ArrayList<>())
-                .addAll(ResourceLoader.load("dictionaries/addresses.txt")
-                                .stream()
-                                .map(this::cleanDictionaryEntry)
-                                .collect(Collectors.toSet()));
-        dictionary.computeIfAbsent(NO_REDACTION_INDICATOR, v -> new ArrayList<>())
-                .addAll(ResourceLoader.load("dictionaries/no_redaction_indicator.txt")
-                                .stream()
-                                .map(this::cleanDictionaryEntry)
-                                .collect(Collectors.toSet()));
-        dictionary.computeIfAbsent(REDACTION_INDICATOR, v -> new ArrayList<>())
-                .addAll(ResourceLoader.load("dictionaries/redaction_indicator.txt")
-                                .stream()
-                                .map(this::cleanDictionaryEntry)
-                                .collect(Collectors.toSet()));
-        dictionary.computeIfAbsent(HINT_ONLY, v -> new ArrayList<>())
-                .addAll(ResourceLoader.load("dictionaries/hint_only.txt")
-                                .stream()
-                                .map(this::cleanDictionaryEntry)
-                                .collect(Collectors.toSet()));
-        dictionary.computeIfAbsent(MUST_REDACT, v -> new ArrayList<>())
-                .addAll(ResourceLoader.load("dictionaries/must_redact.txt")
-                                .stream()
-                                .map(this::cleanDictionaryEntry)
-                                .collect(Collectors.toSet()));
+        dictionary.computeIfAbsent(NAME_CODE, v -> new ArrayList<>()).addAll(ResourceLoader.load("dictionaries/names.txt").stream().map(this::cleanDictionaryEntry).collect(Collectors.toSet()));
+        dictionary.computeIfAbsent(VERTEBRATES_CODE, v -> new ArrayList<>()).addAll(ResourceLoader.load("dictionaries/vertebrates.txt").stream().map(this::cleanDictionaryEntry).collect(Collectors.toSet()));
+        dictionary.computeIfAbsent(ADDRESS_CODE, v -> new ArrayList<>()).addAll(ResourceLoader.load("dictionaries/addresses.txt").stream().map(this::cleanDictionaryEntry).collect(Collectors.toSet()));
+        dictionary.computeIfAbsent(NO_REDACTION_INDICATOR, v -> new ArrayList<>()).addAll(ResourceLoader.load("dictionaries/NoRedactionIndicator.txt").stream().map(this::cleanDictionaryEntry).collect(Collectors.toSet()));
+        dictionary.put(DEFAULT, new ArrayList<>());
     }
 
-
     private String cleanDictionaryEntry(String entry) {
-
         return TextNormalizationUtilities.removeHyphenLineBreaks(entry).replaceAll("\\n", " ");
     }
 
-
     private void loadTypeForTest() {
-
         typeColorMap.put(VERTEBRATES_CODE, new float[]{0, 1, 0});
         typeColorMap.put(ADDRESS_CODE, new float[]{0, 1, 1});
         typeColorMap.put(NAME_CODE, new float[]{1, 1, 0});
-        typeColorMap.put(SPONSOR, new float[]{.5f, .5f, .5f});
-        typeColorMap.put(NO_REDACTION_INDICATOR, new float[]{0.8f, 0, 0.8f});
-        typeColorMap.put(REDACTION_INDICATOR, new float[]{1, 0.502f, 0.1f});
-        typeColorMap.put(HINT_ONLY, new float[]{0.8f, 1, 0.8f});
-        typeColorMap.put(MUST_REDACT, new float[]{1, 0, 0});
-
-        hintTypeMap.put(VERTEBRATES_CODE, true);
-        hintTypeMap.put(ADDRESS_CODE, false);
-        hintTypeMap.put(NAME_CODE, false);
-        hintTypeMap.put(SPONSOR, false);
-        hintTypeMap.put(NO_REDACTION_INDICATOR, true);
-        hintTypeMap.put(REDACTION_INDICATOR, true);
-        hintTypeMap.put(HINT_ONLY, true);
-        hintTypeMap.put(MUST_REDACT, true);
-
-        caseInSensitiveMap.put(VERTEBRATES_CODE, true);
-        caseInSensitiveMap.put(ADDRESS_CODE, false);
-        caseInSensitiveMap.put(NAME_CODE, false);
-        caseInSensitiveMap.put(SPONSOR, false);
-        caseInSensitiveMap.put(NO_REDACTION_INDICATOR, true);
-        caseInSensitiveMap.put(REDACTION_INDICATOR, true);
-        caseInSensitiveMap.put(HINT_ONLY, true);
-        caseInSensitiveMap.put(MUST_REDACT, true);
+        typeColorMap.put(NO_REDACTION_INDICATOR, new float[]{1, 0.502f, 0});
+        typeColorMap.put(DEFAULT, new float[]{1, 0.502f, 0});
     }
 
-
     private List<TypeResult> getTypeResponse() {
-
-        return typeColorMap.entrySet()
-                .stream()
-                .map(typeColor -> TypeResult.builder()
-                        .type(typeColor.getKey())
-                        .color(typeColor.getValue())
-                        .isHint(hintTypeMap.get(typeColor.getKey()))
-                        .isCaseInsensitive(caseInSensitiveMap.get(typeColor.getKey()))
-                        .build())
-
-                .collect(Collectors.toList());
+        return typeColorMap.entrySet().stream().map(typeColor -> TypeResult.builder().type(typeColor.getKey()).color(typeColor.getValue()).build()).collect(Collectors.toList());
     }
 
-
     private DictionaryResponse getDictionaryResponse(String type) {
-
-        return DictionaryResponse.builder()
-                .color(typeColorMap.get(type))
-                .entries(dictionary.get(type))
-                .isHint(hintTypeMap.get(type))
-                .isCaseInsensitive(caseInSensitiveMap.get(type))
-                .build();
+        return DictionaryResponse.builder().color(typeColorMap.get(type)).entries(dictionary.get(type)).build();
     }
 
-
-    @Test
-    public void noExceptionShouldBeThrownForAnyFiles() throws IOException {
-
-        System.out.println("noExceptionShouldBeThrownForAnyFiles");
-        ClassLoader loader = getClass().getClassLoader();
-        URL url = loader.getResource("files");
-        File[] files = new File(url.getPath()).listFiles();
-        List<File> input = new ArrayList<>();
-        for (File file : files) {
-            input.addAll(getPathsRecursively(file));
-        }
-        for (File path : input) {
-            RedactionRequest request = RedactionRequest.builder()
-                    .document(IOUtils.toByteArray(new FileInputStream(path)))
-                    .build();
-            System.out.println("Redacting file : " + path.getName());
-            redactionController.redact(request);
-        }
-
-    }
-
-
-    private List<File> getPathsRecursively(File path) {
-
-        List<File> result = new ArrayList<>();
-        if (path == null || path.listFiles() == null) {
-            return result;
-        }
-        for (File f : path.listFiles()) {
-            if (f.isFile()) {
-                result.add(f);
-            } else {
-                result.addAll(getPathsRecursively(f));
-            }
-        }
-        return result;
-
-    }
-
-
     @Test
     public void redactionTest() throws IOException {
 
-        System.out.println("redactionTest");
         long start = System.currentTimeMillis();
-        ClassPathResource pdfFileResource = new ClassPathResource(
-                "files/Metolachlor/S-Metolachlor_RAR_01_Volume_1_2018-09-06.pdf");
+        ClassPathResource pdfFileResource = new ClassPathResource("files/Metolachlor/S-Metolachlor_RAR_01_Volume_1_2018-09-06.pdf");
 
-        RedactionRequest request = RedactionRequest.builder()
-                .document(IOUtils.toByteArray(pdfFileResource.getInputStream()))
-                .build();
+        RedactionRequest request = RedactionRequest.builder().document(IOUtils.toByteArray(pdfFileResource.getInputStream())).build();
         request.setFlatRedaction(false);
 
         RedactionResult result = redactionController.redact(request);
@@ -304,86 +154,12 @@ public class RedactionIntegrationTest {
         System.out.println("numberOfPages: " + result.getNumberOfPages());
     }
 
-
-    @Test
-    public void testTableRedaction() throws IOException {
-
-        System.out.println("testTableRedaction");
-        long start = System.currentTimeMillis();
-        ClassPathResource pdfFileResource = new ClassPathResource(
-                "files/Metolachlor/S-Metolachlor_RAR_02_Volume_2_2018-09-06.pdf");
-
-        RedactionRequest request = RedactionRequest.builder()
-                .document(IOUtils.toByteArray(pdfFileResource.getInputStream()))
-                .build();
-
-        RedactionResult result = redactionController.redact(request);
-
-        try (FileOutputStream fileOutputStream = new FileOutputStream("/tmp/Redacted.pdf")) {
-            fileOutputStream.write(result.getDocument());
-        }
-        long end = System.currentTimeMillis();
-
-        System.out.println("duration: " + (end - start));
-        System.out.println("numberOfPages: " + result.getNumberOfPages());
-    }
-
-
-    @Test
-    public void testManualRedaction() throws IOException {
-
-        System.out.println("testManualRedaction");
-        long start = System.currentTimeMillis();
-        ClassPathResource pdfFileResource = new ClassPathResource("files/Minimal Examples/Single Table.pdf");
-
-        ManualRedactions manualRedactions = new ManualRedactions();
-
-        Comment comment = Comment.builder().date(OffsetDateTime.now()).user("TEST_USER").text("This is a comment test").build();
-        manualRedactions.setIdsToRemove(Set.of(IdRemoval.builder().id("0836727c3508a0b2ea271da69c04cc2f").approved(false).build()));
-
-        ManualRedactionEntry manualRedactionEntry = new ManualRedactionEntry();
-        manualRedactionEntry.setComments(List.of(comment));
-        manualRedactionEntry.setType("name");
-        manualRedactionEntry.setValue("O'Loughlin C.K.");
-        manualRedactionEntry.setReason("Manual Redaction");
-        manualRedactionEntry.setPositions(List.of(new Rectangle(new Point(375.61096f, 241.282f),
-                                                                7.648041f,
-                                                                43.72262f,
-                                                                1),
-                                                  new Rectangle(new Point(384.83517f, 241.282f),
-                                                                7.648041f,
-                                                                17.043358f,
-                                                                1)));
-
-        manualRedactions.getEntriesToAdd().add(manualRedactionEntry);
-
-        RedactionRequest request = RedactionRequest.builder()
-                .document(IOUtils.toByteArray(pdfFileResource.getInputStream()))
-                .manualRedactions(manualRedactions)
-                .build();
-
-        RedactionResult result = redactionController.redact(request);
-
-        try (FileOutputStream fileOutputStream = new FileOutputStream("/tmp/Redacted.pdf")) {
-            fileOutputStream.write(result.getDocument());
-        }
-        long end = System.currentTimeMillis();
-
-        System.out.println("duration: " + (end - start));
-        System.out.println("numberOfPages: " + result.getNumberOfPages());
-    }
-
-
     @Test
     public void classificationTest() throws IOException {
 
-        System.out.println("classificationTest");
-        ClassPathResource pdfFileResource = new ClassPathResource(
-                "files/Fludioxonil/51 Fludioxonil_RAR_02_Volume_2_2018-02-21.pdf");
+        ClassPathResource pdfFileResource = new ClassPathResource("files/Fludioxonil/51 Fludioxonil_RAR_02_Volume_2_2018-02-21.pdf");
 
-        RedactionRequest request = RedactionRequest.builder()
-                .document(IOUtils.toByteArray(pdfFileResource.getInputStream()))
-                .build();
+        RedactionRequest request = RedactionRequest.builder().document(IOUtils.toByteArray(pdfFileResource.getInputStream())).build();
 
         RedactionResult result = redactionController.classify(request);
 
@@ -392,17 +168,12 @@ public class RedactionIntegrationTest {
         }
     }
 
-
     @Test
     public void sectionsTest() throws IOException {
 
-        System.out.println("sectionsTest");
-        ClassPathResource pdfFileResource = new ClassPathResource("files/Fludioxonil/51 " +
-                                                                          "Fludioxonil_RAR_02_Volume_2_2018-02-21.pdf");
+        ClassPathResource pdfFileResource = new ClassPathResource("files/Fludioxonil/51 Fludioxonil_RAR_02_Volume_2_2018-02-21.pdf");
 
-        RedactionRequest request = RedactionRequest.builder()
-                .document(IOUtils.toByteArray(pdfFileResource.getInputStream()))
-                .build();
+        RedactionRequest request = RedactionRequest.builder().document(IOUtils.toByteArray(pdfFileResource.getInputStream())).build();
 
         RedactionResult result = redactionController.sections(request);
 
@@ -411,17 +182,12 @@ public class RedactionIntegrationTest {
         }
     }
 
-
     @Test
     public void htmlTablesTest() throws IOException {
 
-        System.out.println("htmlTablesTest");
-        ClassPathResource pdfFileResource = new ClassPathResource(
-                "files/Minimal Examples/line_breaks.pdf");
+        ClassPathResource pdfFileResource = new ClassPathResource("files/Fludioxonil/51 Fludioxonil_RAR_02_Volume_2_2018-02-21.pdf");
 
-        RedactionRequest request = RedactionRequest.builder()
-                .document(IOUtils.toByteArray(pdfFileResource.getInputStream()))
-                .build();
+        RedactionRequest request = RedactionRequest.builder().document(IOUtils.toByteArray(pdfFileResource.getInputStream())).build();
 
         RedactionResult result = redactionController.htmlTables(request);
 
@@ -430,17 +196,12 @@ public class RedactionIntegrationTest {
         }
     }
 
-
     @Test
     public void htmlTableRotationTest() throws IOException {
 
-        System.out.println("htmlTableRotationTest");
-        ClassPathResource pdfFileResource = new ClassPathResource(
-                "files/Metolachlor/S-Metolachlor_RAR_02_Volume_2_2018-09-06.pdf");
+        ClassPathResource pdfFileResource = new ClassPathResource("files/Metolachlor/S-Metolachlor_RAR_02_Volume_2_2018-09-06.pdf");
 
-        RedactionRequest request = RedactionRequest.builder()
-                .document(IOUtils.toByteArray(pdfFileResource.getInputStream()))
-                .build();
+        RedactionRequest request = RedactionRequest.builder().document(IOUtils.toByteArray(pdfFileResource.getInputStream())).build();
 
         RedactionResult result = redactionController.htmlTables(request);
 
@@ -449,67 +210,23 @@ public class RedactionIntegrationTest {
         }
     }
 
+    private String loadFromClassPath(String path) {
 
-    @Test
-    public void phantomCellsDocumentTest() throws IOException {
-
-        ClassPathResource pdfFileResource = new ClassPathResource("files/Minimal Examples/Phantom Cells.pdf");
-
-        RedactionRequest request = RedactionRequest.builder()
-                .document(IOUtils.toByteArray(pdfFileResource.getInputStream()))
-                .build();
-        request.setFlatRedaction(false);
-
-        RedactionResult result = redactionController.redact(request);
-
-        result.getRedactionLog().getRedactionLogEntry().forEach(entry -> {
-            if (!entry.isHint()) {
-                assertThat(entry.getReason()).isEqualTo("Not redacted because row is not a vertebrate study");
-            }
-        });
-    }
-
-
-    @Test
-    public void sponsorCompanyTest() throws IOException {
-
-        long start = System.currentTimeMillis();
-        ClassPathResource pdfFileResource = new ClassPathResource("files/Minimal Examples/sponsor_companies.pdf");
-
-        RedactionRequest request = RedactionRequest.builder()
-                .document(IOUtils.toByteArray(pdfFileResource.getInputStream()))
-                .build();
-        request.setFlatRedaction(false);
-
-        RedactionResult result = redactionController.redact(request);
-
-        try (FileOutputStream fileOutputStream = new FileOutputStream("/tmp/Redacted.pdf")) {
-            fileOutputStream.write(result.getDocument());
-        }
-        long end = System.currentTimeMillis();
-
-        System.out.println("duration: " + (end - start));
-        System.out.println("numberOfPages: " + result.getNumberOfPages());
-    }
-
-
-    private static String loadFromClassPath(String path) {
-
-        URL resource = ResourceLoader.class.getClassLoader().getResource(path);
+        URL resource = ResourceLoader.class.getClassLoader()
+                .getResource(path);
         if (resource == null) {
             throw new IllegalArgumentException("could not load classpath resource: drools/rules.drl");
         }
-        try (BufferedReader br = new BufferedReader(new InputStreamReader(resource.openStream(),
-                                                                          StandardCharsets.UTF_8))) {
+        try (BufferedReader br = new BufferedReader(new InputStreamReader(resource.openStream(), StandardCharsets.UTF_8))) {
             StringBuilder sb = new StringBuilder();
             String str;
             while ((str = br.readLine()) != null) {
-                sb.append(str).append("\n");
+                sb.append(str)
+                        .append("\n");
             }
             return sb.toString();
         } catch (IOException e) {
             throw new IllegalArgumentException("could not load classpath resource: " + path, e);
         }
     }
-
-}
+}

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

@@ -1,410 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.redaction.service;
-
-import static org.assertj.core.api.Assertions.assertThat;
-import static org.mockito.Mockito.when;
-
-import java.io.BufferedReader;
-import java.io.ByteArrayInputStream;
-import java.io.IOException;
-import java.io.InputStream;
-import java.io.InputStreamReader;
-import java.net.URL;
-import java.nio.charset.StandardCharsets;
-import java.util.ArrayList;
-import java.util.Arrays;
-import java.util.Collections;
-import java.util.HashSet;
-import java.util.Set;
-import java.util.concurrent.atomic.AtomicLong;
-
-import org.apache.commons.io.IOUtils;
-import org.apache.pdfbox.pdmodel.PDDocument;
-import org.junit.Before;
-import org.junit.Test;
-import org.junit.runner.RunWith;
-import org.kie.api.KieServices;
-import org.kie.api.builder.KieBuilder;
-import org.kie.api.builder.KieFileSystem;
-import org.kie.api.builder.KieModule;
-import org.kie.api.runtime.KieContainer;
-import org.springframework.beans.factory.annotation.Autowired;
-import org.springframework.boot.test.context.SpringBootTest;
-import org.springframework.boot.test.context.TestConfiguration;
-import org.springframework.boot.test.mock.mockito.MockBean;
-import org.springframework.context.annotation.Bean;
-import org.springframework.core.io.ClassPathResource;
-import org.springframework.test.context.junit4.SpringRunner;
-
-import com.iqser.red.service.configuration.v1.api.model.DefaultColor;
-import com.iqser.red.service.configuration.v1.api.model.DictionaryResponse;
-import com.iqser.red.service.configuration.v1.api.model.RulesResponse;
-import com.iqser.red.service.configuration.v1.api.model.TypeResponse;
-import com.iqser.red.service.configuration.v1.api.model.TypeResult;
-import com.iqser.red.service.redaction.v1.model.RedactionRequest;
-import com.iqser.red.service.redaction.v1.server.classification.model.Document;
-import com.iqser.red.service.redaction.v1.server.client.DictionaryClient;
-import com.iqser.red.service.redaction.v1.server.client.RulesClient;
-import com.iqser.red.service.redaction.v1.server.redaction.model.Entity;
-import com.iqser.red.service.redaction.v1.server.redaction.utils.ResourceLoader;
-import com.iqser.red.service.redaction.v1.server.segmentation.PdfSegmentationService;
-
-@SpringBootTest
-@RunWith(SpringRunner.class)
-public class EntityRedactionServiceTest {
-
-    private static final String DEFAULT_RULES = loadFromClassPath("drools/rules.drl");
-    private static final String NAME_CODE = "name";
-    private static final String ADDRESS_CODE = "address";
-
-    private static final AtomicLong DICTIONARY_VERSION = new AtomicLong();
-    private static final AtomicLong RULES_VERSION = new AtomicLong();
-    @MockBean
-    private DictionaryClient dictionaryClient;
-
-    @MockBean
-    private RulesClient rulesClient;
-
-    @Autowired
-    private EntityRedactionService entityRedactionService;
-
-    @Autowired
-    private PdfSegmentationService pdfSegmentationService;
-
-    @Autowired
-    private DroolsExecutionService droolsExecutionService;
-
-    @TestConfiguration
-    public static class RedactionIntegrationTestConfiguration {
-
-        @Bean
-        public KieContainer kieContainer() {
-
-            KieServices kieServices = KieServices.Factory.get();
-
-            KieFileSystem kieFileSystem = kieServices.newKieFileSystem();
-            InputStream input = new ByteArrayInputStream(DEFAULT_RULES.getBytes(StandardCharsets.UTF_8));
-            kieFileSystem.write("src/test/resources/drools/rules.drl", kieServices.getResources()
-                    .newInputStreamResource(input));
-            KieBuilder kieBuilder = kieServices.newKieBuilder(kieFileSystem);
-            kieBuilder.buildAll();
-            KieModule kieModule = kieBuilder.getKieModule();
-
-            return kieServices.newKieContainer(kieModule.getReleaseId());
-        }
-
-    }
-
-
-    @Test
-    public void testNestedEntitiesRemoval() {
-
-        Set<Entity> entities = new HashSet<>();
-        Entity nested = new Entity("nested", "fake type", 10, 16, "fake headline", 0);
-        Entity nesting = new Entity("nesting nested", "fake type", 2, 16, "fake headline", 0);
-        entities.add(nested);
-        entities.add(nesting);
-        entityRedactionService.removeEntitiesContainedInLarger(entities);
-
-        assertThat(entities.size()).isEqualTo(1);
-        assertThat(entities).contains(nesting);
-
-    }
-
-
-    @Test
-    public void testTableRedaction() throws IOException {
-
-        ClassPathResource pdfFileResource = new ClassPathResource("files/Minimal Examples/Single Table.pdf");
-
-        RedactionRequest redactionRequest = RedactionRequest.builder()
-                .document(IOUtils.toByteArray(pdfFileResource.getInputStream()))
-                .build();
-
-        DictionaryResponse dictionaryResponse = DictionaryResponse.builder()
-                .entries(Arrays.asList("Casey, H.W.", "O’Loughlin,  C.K.", "Salamon, C.M.", "Smith, S.H."))
-                .build();
-        when(dictionaryClient.getVersion()).thenReturn(DICTIONARY_VERSION.incrementAndGet());
-        when(dictionaryClient.getDictionaryForType(NAME_CODE)).thenReturn(dictionaryResponse);
-        DictionaryResponse addressResponse = DictionaryResponse.builder()
-                .entries(Collections.singletonList("Toxigenics, Inc., Decatur, IL 62526, USA"))
-                .build();
-        when(dictionaryClient.getDictionaryForType(ADDRESS_CODE)).thenReturn(addressResponse);
-
-        try (PDDocument pdDocument = PDDocument.load(new ByteArrayInputStream(redactionRequest.getDocument()))) {
-            Document classifiedDoc = pdfSegmentationService.parseDocument(pdDocument);
-            entityRedactionService.processDocument(classifiedDoc, null);
-            assertThat(classifiedDoc.getEntities()).hasSize(1); // one page
-            assertThat(classifiedDoc.getEntities().get(1)).hasSize(7);// 3 author cells, 1 address, 1 Y and 2 N entities
-        }
-    }
-
-
-    @Test
-    public void testNestedRedaction() throws IOException {
-
-        ClassPathResource pdfFileResource = new ClassPathResource("files/Minimal Examples/nested_redaction.pdf");
-
-        RedactionRequest redactionRequest = RedactionRequest.builder()
-                .document(IOUtils.toByteArray(pdfFileResource.getInputStream()))
-                .build();
-
-        DictionaryResponse dictionaryResponse = DictionaryResponse.builder()
-                .entries(Arrays.asList("Casey, H.W.", "O’Loughlin,  C.K.", "Salamon, C.M.", "Smith, S.H."))
-                .build();
-        when(dictionaryClient.getVersion()).thenReturn(DICTIONARY_VERSION.incrementAndGet());
-        when(dictionaryClient.getDictionaryForType(NAME_CODE)).thenReturn(dictionaryResponse);
-        DictionaryResponse addressResponse = DictionaryResponse.builder()
-                .entries(Collections.singletonList("Toxigenics, Inc., Decatur, IL 62526, USA"))
-                .build();
-        when(dictionaryClient.getDictionaryForType(ADDRESS_CODE)).thenReturn(addressResponse);
-
-        try (PDDocument pdDocument = PDDocument.load(new ByteArrayInputStream(redactionRequest.getDocument()))) {
-            Document classifiedDoc = pdfSegmentationService.parseDocument(pdDocument);
-            entityRedactionService.processDocument(classifiedDoc, null);
-            assertThat(classifiedDoc.getEntities()).hasSize(1); // one page
-            assertThat(classifiedDoc.getEntities().get(1)).hasSize(7);// 3 author cells, 1 address, 1 Y and 2 N entities
-        }
-    }
-
-
-    @Test
-    public void testTrueNegativesInTable() throws IOException {
-
-        ClassPathResource pdfFileResource = new ClassPathResource("files/Cyprodinil/40 Cyprodinil - EU AIR3 - LCA Section 1" +
-                " Supplement - Identity of the active substance - Reference list.pdf");
-        when(dictionaryClient.getVersion()).thenReturn(DICTIONARY_VERSION.incrementAndGet());
-        DictionaryResponse dictionaryResponse = DictionaryResponse.builder()
-                .entries(new ArrayList<>(ResourceLoader.load("dictionaries/names.txt")))
-                .build();
-        when(dictionaryClient.getDictionaryForType(NAME_CODE)).thenReturn(dictionaryResponse);
-        DictionaryResponse addressResponse = DictionaryResponse.builder()
-                .entries(new ArrayList<>(ResourceLoader.load("dictionaries/addresses.txt")))
-                .build();
-        when(dictionaryClient.getDictionaryForType(ADDRESS_CODE)).thenReturn(addressResponse);
-        try (PDDocument pdDocument = PDDocument.load(pdfFileResource.getInputStream())) {
-            Document classifiedDoc = pdfSegmentationService.parseDocument(pdDocument);
-            entityRedactionService.processDocument(classifiedDoc, null);
-            assertThat(classifiedDoc.getEntities()
-                    .entrySet()
-                    .stream()
-                    .noneMatch(entry -> entry.getValue().stream().anyMatch(e -> e.getMatchedRule() == 9))).isTrue();
-        }
-        pdfFileResource = new ClassPathResource("files/Compounds/27 A8637C - EU AIR3 - MCP Section 1 - Identity of " +
-                "the plant protection product.pdf");
-        try (PDDocument pdDocument = PDDocument.load(pdfFileResource.getInputStream())) {
-            Document classifiedDoc = pdfSegmentationService.parseDocument(pdDocument);
-            entityRedactionService.processDocument(classifiedDoc, null);
-            assertThat(classifiedDoc.getEntities()
-                    .entrySet()
-                    .stream()
-                    .noneMatch(entry -> entry.getValue().stream().anyMatch(e -> e.getMatchedRule() == 9))).isTrue();
-        }
-    }
-
-    @Test
-    public void testFalsePositiveInWrongCell() throws IOException {
-
-        ClassPathResource pdfFileResource = new ClassPathResource("files/Minimal Examples/Row With Ambiguous Redaction.pdf");
-        when(dictionaryClient.getVersion()).thenReturn(DICTIONARY_VERSION.incrementAndGet());
-        DictionaryResponse dictionaryResponse = DictionaryResponse.builder()
-                .entries(new ArrayList<>(ResourceLoader.load("dictionaries/names.txt")))
-                .build();
-        when(dictionaryClient.getDictionaryForType(NAME_CODE)).thenReturn(dictionaryResponse);
-        DictionaryResponse addressResponse = DictionaryResponse.builder()
-                .entries(new ArrayList<>(ResourceLoader.load("dictionaries/addresses.txt")))
-                .build();
-        when(dictionaryClient.getDictionaryForType(ADDRESS_CODE)).thenReturn(addressResponse);
-        try (PDDocument pdDocument = PDDocument.load(pdfFileResource.getInputStream())) {
-            Document classifiedDoc = pdfSegmentationService.parseDocument(pdDocument);
-            entityRedactionService.processDocument(classifiedDoc, null);
-            assertThat(classifiedDoc.getEntities()).hasSize(1); // one page
-            assertThat(classifiedDoc.getEntities().get(1).stream()
-                    .filter(entity -> entity.getMatchedRule() == 9)
-                    .count()).isEqualTo(10);
-        }
-
-    }
-
-
-    @Test
-    public void testApplicantInTableRedaction() throws IOException {
-
-        String tableRules = "package drools\n" +
-                "\n" +
-                "import com.iqser.red.service.redaction.v1.server.redaction.model.Section\n" +
-                "\n" +
-                "global Section section\n" +
-                "rule \"6: Redact contact information if applicant is found\"\n" +
-                "   when\n" +
-                "       eval(section.headlineContainsWord(\"applicant\") || section.getText().contains(\"Applicant\"));\n" +
-                "   then\n" +
-                "       section.redactLineAfter(\"Name:\", \"address\", 6, \"Applicant information was found\");\n" +
-                "       section.redactBetween(\"Address:\", \"Contact\", \"address\", 6, \"Applicant information was found\");\n" +
-                "       section.redactLineAfter(\"Contact point:\",  \"address\", 6, \"Applicant information was found\");\n" +
-                "       section.redactLineAfter(\"Phone:\", \"address\", 6, \"Applicant information was found\");\n" +
-                "       section.redactLineAfter(\"Fax:\", \"address\", 6, \"Applicant information was found\");\n" +
-                "       section.redactLineAfter(\"Tel.:\", \"address\", 6, \"Applicant information was found\");\n" +
-                "       section.redactLineAfter(\"Tel:\", \"address\", 6, \"Applicant information was found\");\n" +
-                "       section.redactLineAfter(\"E-mail:\", \"address\", 6, \"Applicant information was found\");\n" +
-                "       section.redactLineAfter(\"Email:\", \"address\", 6, \"Applicant information was found\");\n" +
-                "       section.redactLineAfter(\"Contact:\", \"address\", 6, \"Applicant information was found\");\n" +
-                "       section.redactLineAfter(\"Telephone number:\", \"address\", 6, \"Applicant information was found\");\n" +
-                "       section.redactLineAfter(\"Fax number:\", \"address\", 6, \"Applicant information was found\");\n" +
-                "       section.redactLineAfter(\"Telephone:\", \"address\", 6, \"Applicant information was found\");\n" +
-                "       section.redactBetween(\"No:\", \"Fax\", \"address\", 6, \"Applicant information was found\");\n" +
-                "       section.redactBetween(\"Contact:\", \"Tel.:\", \"address\", 6, \"Applicant information was found\");\n" +
-                "   end";
-        when(rulesClient.getVersion()).thenReturn(RULES_VERSION.incrementAndGet());
-        when(rulesClient.getRules()).thenReturn(new RulesResponse(tableRules));
-        droolsExecutionService.updateRules();
-
-        ClassPathResource pdfFileResource = new ClassPathResource("files/Minimal Examples/Applicant Producer Table.pdf");
-        when(dictionaryClient.getVersion()).thenReturn(DICTIONARY_VERSION.incrementAndGet());
-        DictionaryResponse dictionaryResponse = DictionaryResponse.builder()
-                .entries(new ArrayList<>(ResourceLoader.load("dictionaries/names.txt")))
-                .build();
-        when(dictionaryClient.getDictionaryForType(NAME_CODE)).thenReturn(dictionaryResponse);
-        DictionaryResponse addressResponse = DictionaryResponse.builder()
-                .entries(new ArrayList<>(ResourceLoader.load("dictionaries/addresses.txt")))
-                .build();
-        when(dictionaryClient.getDictionaryForType(ADDRESS_CODE)).thenReturn(addressResponse);
-        try (PDDocument pdDocument = PDDocument.load(pdfFileResource.getInputStream())) {
-            Document classifiedDoc = pdfSegmentationService.parseDocument(pdDocument);
-            entityRedactionService.processDocument(classifiedDoc, null);
-            assertThat(classifiedDoc.getEntities()).hasSize(1); // one page
-            assertThat(classifiedDoc.getEntities().get(1).stream()
-                    .filter(entity -> entity.getMatchedRule() == 6)
-                    .count()).isEqualTo(18);
-        }
-
-    }
-
-
-    @Test
-    public void headerPropagation() throws IOException {
-
-        ClassPathResource pdfFileResource = new ClassPathResource("files/Minimal Examples/Header Propagation.pdf");
-
-        DictionaryResponse dictionaryResponse = DictionaryResponse.builder()
-                .entries(Arrays.asList("Bissig R.", "Thanei P."))
-                .build();
-
-        when(dictionaryClient.getVersion()).thenReturn(DICTIONARY_VERSION.incrementAndGet());
-        when(dictionaryClient.getDictionaryForType(NAME_CODE)).thenReturn(dictionaryResponse);
-        DictionaryResponse addressResponse = DictionaryResponse.builder()
-                .entries(Collections.singletonList("Novartis Crop Protection AG, Basel, Switzerland"))
-                .build();
-        when(dictionaryClient.getDictionaryForType(ADDRESS_CODE)).thenReturn(addressResponse);
-
-        try (PDDocument pdDocument = PDDocument.load(pdfFileResource.getInputStream())) {
-            Document classifiedDoc = pdfSegmentationService.parseDocument(pdDocument);
-            entityRedactionService.processDocument(classifiedDoc, null);
-            assertThat(classifiedDoc.getEntities()).hasSize(2); // two pages
-            assertThat(classifiedDoc.getEntities().get(1).stream().filter(entity -> entity.getMatchedRule() == 9).count()).isEqualTo(8);
-            assertThat(classifiedDoc.getEntities().get(2).stream().filter(entity -> entity.getMatchedRule() == 9).count()).isEqualTo(5); // 2 names, 1 address, 2 Y
-        }
-
-        pdfFileResource = new ClassPathResource("files/Minimal Examples/Header Propagation2.pdf");
-
-        dictionaryResponse = DictionaryResponse.builder()
-                .entries(Arrays.asList("Tribolet, R.", "Muir, G.", "Kühne-Thu, H.", "Close, C."))
-                .build();
-
-        when(dictionaryClient.getVersion()).thenReturn(DICTIONARY_VERSION.incrementAndGet());
-        when(dictionaryClient.getDictionaryForType(NAME_CODE)).thenReturn(dictionaryResponse);
-        addressResponse = DictionaryResponse.builder()
-                .entries(Collections.singletonList("Novartis Crop Protection AG, Basel, Switzerland"))
-                .build();
-        when(dictionaryClient.getDictionaryForType(ADDRESS_CODE)).thenReturn(addressResponse);
-
-        try (PDDocument pdDocument = PDDocument.load(pdfFileResource.getInputStream())) {
-            Document classifiedDoc = pdfSegmentationService.parseDocument(pdDocument);
-            entityRedactionService.processDocument(classifiedDoc, null);
-            assertThat(classifiedDoc.getEntities()).hasSize(1); // one page
-            assertThat(classifiedDoc.getEntities().get(1).stream().filter(entity -> entity.getMatchedRule() == 9).count()).isEqualTo(3);
-            assertThat(classifiedDoc.getEntities().get(1).stream().filter(entity -> entity.getMatchedRule() == 8).count()).isEqualTo(8);
-        }
-    }
-
-
-    @Test
-    public void testNGuideline() throws IOException {
-
-        ClassPathResource pdfFileResource = new ClassPathResource("files/Minimal Examples/Empty Tabular Data.pdf");
-
-        DictionaryResponse dictionaryResponse = DictionaryResponse.builder()
-                .entries(Collections.singletonList("Aldershof S."))
-                .build();
-
-        when(dictionaryClient.getVersion()).thenReturn(DICTIONARY_VERSION.incrementAndGet());
-        when(dictionaryClient.getDictionaryForType(NAME_CODE)).thenReturn(dictionaryResponse);
-        DictionaryResponse addressResponse = DictionaryResponse.builder()
-                .entries(Collections.singletonList("Novartis Crop Protection AG, Basel, Switzerland"))
-                .build();
-        when(dictionaryClient.getDictionaryForType(ADDRESS_CODE)).thenReturn(addressResponse);
-
-        try (PDDocument pdDocument = PDDocument.load(pdfFileResource.getInputStream())) {
-            Document classifiedDoc = pdfSegmentationService.parseDocument(pdDocument);
-            entityRedactionService.processDocument(classifiedDoc, null);
-            assertThat(classifiedDoc.getEntities()).hasSize(1); // one page
-            assertThat(classifiedDoc.getEntities().get(1).stream().filter(entity -> entity.getMatchedRule() == 8).count()).isEqualTo(6);
-        }
-    }
-
-
-    @Before
-    public void stubRedaction() {
-        String tableRules = "package drools\n" +
-                "\n" +
-                "import com.iqser.red.service.redaction.v1.server.redaction.model.Section\n" +
-                "\n" +
-                "global Section section\n" +
-                "rule \"8: Not redacted because Vertebrate Study = N\"\n" +
-                "    when\n" +
-                "        Section(rowEquals(\"Vertebrate study Y/N\", \"N\") || rowEquals(\"Vertebrate study Y/N\", \"No\"))\n" +
-                "    then\n" +
-                "        section.redactNotCell(\"Author(s)\", 8,  \"name\", \"Not redacted because row is not a vertebrate study\");\n" +
-                "        section.redactNot(\"address\", 8, \"Not redacted because row is not a vertebrate study\");\n" +
-                "        section.highlightCell(\"Vertebrate study Y/N\", 8, \"hint_only\");\n" +
-                "    end\n" +
-                "rule \"9: Redact Authors and Addresses in Reference Table, if it is a Vertebrate study\"\n" +
-                "    when\n" +
-                "        Section(rowEquals(\"Vertebrate study Y/N\", \"Y\") || rowEquals(\"Vertebrate study Y/N\", " +
-                "\"Yes\"))\n" +
-                "    then\n" +
-                "        section.redactCell(\"Author(s)\", 9,  \"name\", \"Redacted because row is a vertebrate study\");\n" +
-                "        section.redact(\"address\", 9, \"Redacted because row is a vertebrate study\");\n" +
-                "        section.highlightCell(\"Vertebrate study Y/N\", 9, \"must_redact\");\n" +
-                "    end";
-        when(rulesClient.getVersion()).thenReturn(RULES_VERSION.incrementAndGet());
-        when(rulesClient.getRules()).thenReturn(new RulesResponse(tableRules));
-        TypeResponse typeResponse = TypeResponse.builder()
-                .types(Arrays.asList(
-                        TypeResult.builder().type(NAME_CODE).color(new float[]{1, 1, 0}).build(),
-                        TypeResult.builder().type(ADDRESS_CODE).color(new float[]{0, 1, 1}).build()))
-                .build();
-        when(dictionaryClient.getVersion()).thenReturn(DICTIONARY_VERSION.incrementAndGet());
-        when(dictionaryClient.getAllTypes()).thenReturn(typeResponse);
-        when(dictionaryClient.getDefaultColor()).thenReturn(new DefaultColor());
-    }
-
-
-    private static String loadFromClassPath(String path) {
-
-        URL resource = ResourceLoader.class.getClassLoader().getResource(path);
-        if (resource == null) {
-            throw new IllegalArgumentException("could not load classpath resource: drools/rules.drl");
-        }
-        try (BufferedReader br = new BufferedReader(new InputStreamReader(resource.openStream(), StandardCharsets.UTF_8))) {
-            StringBuilder sb = new StringBuilder();
-            String str;
-            while ((str = br.readLine()) != null) {
-                sb.append(str).append("\n");
-            }
-            return sb.toString();
-        } catch (IOException e) {
-            throw new IllegalArgumentException("could not load classpath resource: " + path, e);
-        }
-    }
-
-}

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

@@ -1,189 +0,0 @@
-package com.iqser.red.service.redaction.v1.server.segmentation;
-
-import static org.assertj.core.api.Assertions.assertThat;
-
-import java.io.IOException;
-import java.util.Collections;
-import java.util.List;
-import java.util.stream.Collectors;
-
-import org.apache.pdfbox.pdmodel.PDDocument;
-import org.junit.Test;
-import org.junit.runner.RunWith;
-import org.kie.api.runtime.KieContainer;
-import org.springframework.beans.factory.annotation.Autowired;
-import org.springframework.boot.test.context.SpringBootTest;
-import org.springframework.boot.test.mock.mockito.MockBean;
-import org.springframework.core.io.ClassPathResource;
-import org.springframework.test.context.junit4.SpringRunner;
-
-import com.iqser.red.service.redaction.v1.server.classification.model.Document;
-import com.iqser.red.service.redaction.v1.server.classification.service.BlockificationService;
-import com.iqser.red.service.redaction.v1.server.tableextraction.model.Cell;
-import com.iqser.red.service.redaction.v1.server.tableextraction.model.Table;
-import com.iqser.red.service.redaction.v1.server.tableextraction.service.RulingCleaningService;
-import com.iqser.red.service.redaction.v1.server.tableextraction.service.TableExtractionService;
-
-@SpringBootTest
-@RunWith(SpringRunner.class)
-public class PdfSegmentationServiceTest {
-
-    @Autowired
-    private PdfSegmentationService pdfSegmentationService;
-
-    @Autowired
-    private RulingCleaningService rulingCleaningService;
-
-    @Autowired
-    private TableExtractionService tableExtractionService;
-
-    @Autowired
-    private BlockificationService blockificationService;
-
-    @MockBean
-    private KieContainer kieContainer;
-
-
-    @Test
-    public void testPDFSegmentationWithComplexTable() throws IOException {
-
-        ClassPathResource pdfFileResource = new ClassPathResource("files/Minimal Examples/Spanning Cells.pdf");
-
-        try (PDDocument pdDocument = PDDocument.load(pdfFileResource.getInputStream())) {
-            Document document = pdfSegmentationService.parseDocument(pdDocument);
-            assertThat(document.getParagraphs()
-                    .stream()
-                    .flatMap(paragraph -> paragraph.getTables().stream())
-                    .collect(Collectors.toList())).isNotEmpty();
-            Table table = document.getParagraphs()
-                    .stream()
-                    .flatMap(paragraph -> paragraph.getTables().stream())
-                    .collect(Collectors.toList())
-                    .get(0);
-            assertThat(table.getColCount()).isEqualTo(6);
-            assertThat(table.getRowCount()).isEqualTo(13);
-            assertThat(table.getRows().stream().mapToInt(List::size).sum()).isEqualTo(6 * 13);
-        }
-    }
-
-
-    @Test
-    public void testTableExtraction() throws IOException {
-
-        ClassPathResource pdfFileResource = new ClassPathResource("files/Minimal Examples/Merge Table.pdf");
-
-        try (PDDocument pdDocument = PDDocument.load(pdfFileResource.getInputStream())) {
-            Document document = pdfSegmentationService.parseDocument(pdDocument);
-            assertThat(document.getParagraphs()
-                    .stream()
-                    .flatMap(paragraph -> paragraph.getTables().stream())
-                    .collect(Collectors.toList())).isNotEmpty();
-            Table firstTable = document.getParagraphs()
-                    .stream()
-                    .flatMap(paragraph -> paragraph.getTables().stream())
-                    .collect(Collectors.toList())
-                    .get(0);
-            assertThat(firstTable.getColCount()).isEqualTo(8);
-            assertThat(firstTable.getRowCount()).isEqualTo(1);
-            Table secondTable = document.getParagraphs()
-                    .stream()
-                    .flatMap(paragraph -> paragraph.getTables().stream())
-                    .collect(Collectors.toList())
-                    .get(1);
-            assertThat(secondTable.getColCount()).isEqualTo(8);
-            assertThat(secondTable.getRowCount()).isEqualTo(2);
-            List<List<Cell>> firstTableHeaderCells = firstTable.getRows()
-                    .get(0)
-                    .stream()
-                    .map(Collections::singletonList)
-                    .collect(Collectors.toList());
-            assertThat(secondTable.getRows().stream()
-                    .allMatch(row -> row.stream()
-                            .map(Cell::getHeaderCells)
-                            .collect(Collectors.toList())
-                            .equals(firstTableHeaderCells)))
-                    .isTrue();
-        }
-    }
-
-
-    @Test
-    public void testMultiPageMetadataPropagation() throws IOException {
-
-        ClassPathResource pdfFileResource = new ClassPathResource("files/Minimal Examples/Merge Multi Page Table.pdf");
-
-        try (PDDocument pdDocument = PDDocument.load(pdfFileResource.getInputStream())) {
-            Document document = pdfSegmentationService.parseDocument(pdDocument);
-            assertThat(document.getParagraphs()
-                    .stream()
-                    .flatMap(paragraph -> paragraph.getTables().stream())
-                    .collect(Collectors.toList())).isNotEmpty();
-            Table firstTable = document.getParagraphs()
-                    .stream()
-                    .flatMap(paragraph -> paragraph.getTables().stream())
-                    .collect(Collectors.toList())
-                    .get(0);
-            assertThat(firstTable.getColCount()).isEqualTo(9);
-            assertThat(firstTable.getRowCount()).isEqualTo(5);
-            Table secondTable = document.getParagraphs()
-                    .stream()
-                    .flatMap(paragraph -> paragraph.getTables().stream())
-                    .collect(Collectors.toList())
-                    .get(1);
-            assertThat(secondTable.getColCount()).isEqualTo(9);
-            assertThat(secondTable.getRowCount()).isEqualTo(6);
-            List<List<Cell>> firstTableHeaderCells = firstTable.getRows()
-                    .get(firstTable.getRowCount() - 1)
-                    .stream()
-                    .map(Cell::getHeaderCells)
-                    .collect(Collectors.toList());
-            assertThat(secondTable.getRows().stream()
-                    .allMatch(row -> row.stream()
-                            .map(Cell::getHeaderCells)
-                            .collect(Collectors.toList())
-                            .equals(firstTableHeaderCells)))
-                    .isTrue();
-        }
-    }
-
-
-    @Test
-    public void testHeaderCellsForRotatedTable() throws IOException {
-
-        ClassPathResource pdfFileResource = new ClassPathResource("files/Minimal Examples/Rotated Table Headers.pdf");
-
-        try (PDDocument pdDocument = PDDocument.load(pdfFileResource.getInputStream())) {
-            Document document = pdfSegmentationService.parseDocument(pdDocument);
-            assertThat(document.getParagraphs()
-                    .stream()
-                    .flatMap(paragraph -> paragraph.getTables().stream())
-                    .collect(Collectors.toList())).isNotEmpty();
-            Table firstTable = document.getParagraphs()
-                    .stream()
-                    .flatMap(paragraph -> paragraph.getTables().stream())
-                    .collect(Collectors.toList())
-                    .get(0);
-            assertThat(firstTable.getColCount()).isEqualTo(8);
-            assertThat(firstTable.getRowCount()).isEqualTo(1);
-            Table secondTable = document.getParagraphs()
-                    .stream()
-                    .flatMap(paragraph -> paragraph.getTables().stream())
-                    .collect(Collectors.toList())
-                    .get(1);
-            assertThat(secondTable.getColCount()).isEqualTo(8);
-            assertThat(secondTable.getRowCount()).isEqualTo(6);
-            List<List<Cell>> firstTableHeaderCells = firstTable.getRows()
-                    .get(0)
-                    .stream()
-                    .map(Collections::singletonList)
-                    .collect(Collectors.toList());
-            assertThat(secondTable.getRows().stream()
-                    .allMatch(row -> row.stream()
-                            .map(Cell::getHeaderCells)
-                            .collect(Collectors.toList())
-                            .equals(firstTableHeaderCells)))
-                    .isTrue();
-        }
-    }
-
-}

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

@@ -0,0 +1,3 @@
+In Vitro
+In vitro
+in vitro

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

@@ -1,2 +0,0 @@
-guideline
-unpublished

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

@@ -1,2 +0,0 @@
-CTL
-determination of residues

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

@@ -1,3 +0,0 @@
-published paper
-in vitro
-in-vitro

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

@@ -1,9 +0,0 @@
-in vivo
-in-vivo
-dermal penetration
-oral toxicity
-oral-toxicity
-acute toxicity
-acute-toxicity
-eco toxicity
-eco-toxicity

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

@@ -1,7 +0,0 @@
-Monthey Syngenta Crop Protection AG, Basel, Switzerland
-Syngenta Crop Protection, Monthey, Switzerland
-Fine Organics Limited, Middlesbrough, United Kingdom
-Syngenta Monthey Switzerland
-Hunan Haili Chemical Industry Co., Ltd., Hunan, China
-Syngenta, Switzerland
-Syngenta Nantong, China

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

@@ -1,63 +1,48 @@
-a. sylvaticus
+Vulpes vulpes
 african clawed frog
 agalychnis callidryas
-albino rat
-american bullfrog tadpole
-american toad
 amphibian
 amphibians
+American bullfrog tadpole
+american toad
 anad platyrhynchos
-anas platyrhynchos
+Anas platyrhynchos
 anuran
 anurans
-apodemus
-apodemus flavicollis
 apodemus syl vaticus
-apodemus sylvaticus
-arvicola terrestris
 avian
-bank vole
 bird
 birds
 bluegill
 bluegill sunfish
 bobwhite
 bobwhite quail
-brachydanio rerio
-brown hare
-bufo americanus
 bullfrog
+Bufo americanus
+brachydanio rerio
 canary
 carassius carassius
 carp
-catesbeiana
 catfish
 cattle
 cattles
 channel catfish
+Chinook
 chicken
-chinese hamster
-chinese hamsters
-chinook
-coho salmon
+Colinus virginianus
 colinus virginianus
-columba palumbus
-columbidae
-common carp
-common vole
+Common carp
 coturnix japonica
+Coturnix japonica
 cow
 cows
-crocidura russula
-crucian carp
+Crucian carp
 cyprinodon variegatus
 cyprinus carpio
 dog
 dogs
 duck
 ducks
-european brown hare
-european rabbit
 fathead minnow
 fish
 fishes
@@ -71,84 +56,56 @@ galaxias truttaceus
 gasterosteus aculeatus
 goat
 goats
-greater white-toothed shrew
 guinea
 guinea pig
 guinea pigs
-guinea-pigs
-guppy
+Guppy
 hamster
 hamsters
 hen
 hens
-house mouse
-hyla versicolor
+Hyla versicolor
 ictalurus melas
 ictalurus punctatus
 japanese quail
 japonica
-kisutch
-lagomorph
 lebistes reticulatus
 leiostomus xanthurus
 leisostomus xanthurus
 lepomis macrochirus
-lepus europaeus
-limnocharis
-limnodynastes
-limnodynastes tasmaniensis
 livestock
 livestocks
-mallard
 mallard duck
 mammal
-mammalian
 mammals
-marten
-martes
+Mammalian
 mice
-microtus
-microtus agrestis
-microtus arvalis
-microtus subterraneus
 midwestern anurans
-minnow
-minnows
 monkey
 mouse
-mus musculus
-myodes glareolus
 northern bobwhite
-o. cuniculus
 o. mykiss
-o. tshawytscha
-oncorhynchus
-oncorhynchus mykiss
-oncorhynchus tshawytscha
-oryctolagus cuniculus
+Oncorhynchus mykiss
+Oncorhynchus
+O. mykiss
 oryzias melastigma
 oryzias melastigma larvae
 p. promelas
 pagrus major
-palumbus
 pig
 pigeon
 pigeons
-pigs
-pimephales promela
 pimephales promelas
+Pseudacris triseriata
 poecilia reticulata
 poultry
-pseudacris
-pseudacris triseriata
 quail
-r. catesbeiana
 rabbit
 rabbits
 rainbow trout
+Rana limnocharis
 rana
-rana catesbeiana
-rana limnocharis
+limnocharis
 rana pipiens
 rat
 rats
@@ -157,35 +114,120 @@ reptiles
 ricefish
 ruminant
 ruminants
-salmo gairdneri
-salmon
-serinus canaria
 sheepshead minnow
 sheepshead minnows
-shrew
-shrews
-sorex araneus
 spea multiplicata
+Salmo gairdneri
+salmon
 spotted march frog
 tadpoles
-terrestrial vertrebrates
-toad
 treefrog
-triseriata
+toad
+terrestrial vertrebrates
+Limnodynastes tasmaniensis
 trout
-tshawytscha
-vole
-voles
-vulpes vulpes
-white rabbits
-white-toothed shrew
+Vulpes vulpes
 wistar
-wistar rats
-wood mice
-wood mouse
-wood pigeon
 xenopus laevis
 xenpous leavis
-yellow-necked mouse
 zebra fish
-zebrafish
+zebrafish
+Salmo gairdneri
+minnow
+minnows
+Pimephales promela
+Cyprinodon variegatus
+limnodynastes
+Rana catesbeiana
+R. catesbeiana
+coho salmon
+Oncorhynchus tshawytscha
+O. tshawytscha
+tshawytscha
+catesbeiana
+kisutch
+Pseudacris triseriata
+Pseudacris
+triseriata
+Wood pigeon
+Columba palumbus
+palumbus
+Columbidae
+shrew
+shrews
+bank vole
+common vole
+vole
+voles
+lagomorph
+Wood mouse
+Apodemus sylvaticus
+A. sylvaticus
+Apodemus flavicollis
+Apodemus
+mus musculus
+Microtus arvalis
+Microtus agrestis
+Microtus
+Arvicola terrestris
+Sorex araneus
+Myodes glareolus
+yellow-necked mouse
+house mouse
+Oryctolagus cuniculus
+marten
+martes
+white-toothed shrew
+greater white-toothed shrew
+Lepus europaeus
+brown hare
+European brown hare
+European rabbit
+O. cuniculus
+Crocidura russula
+Chinese Hamster
+Rat
+Rats
+Dog
+Chinese hamsters
+Chinese hamster
+Mouse
+Guinea pig
+Wistar rats
+Rabbit
+mammalian
+Japanese quail
+Microtus subterraneus
+Lepomis macrochirus
+P. promelas
+Cyprinus carpio
+Fish
+Ictalurus punctatus
+Carassius carassius
+Lepomis macrochirus
+Poecilia reticulata
+Lebistes reticulatus
+Lepomis macrochirus
+Leiostomus xanthurus
+Pimephales promelas
+Lepomis macrochirus
+Albino rat
+Hen
+Goat
+Livestock
+Guinea Pigs
+Hamster
+wood mouse
+Rabbits
+Mice
+Rainbow trout
+Canary
+Serinus canaria
+Guinea Pig
+Cow
+Pigs
+Poultry
+Guinea-pigs
+White rabbits
+Birds
+Wood mice

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

@@ -7,7 +7,7 @@ global Section section
 
 rule "1: Redacted because Section contains Vertebrate"
 	when
-		Section(matchesType("vertebrate"))
+		eval(section.contains("vertebrate")==true);
 	then
 		section.redact("name", 1, "Redacted because Section contains Vertebrate");
 		section.redact("address", 1, "Redacted because Section contains Vertebrate");
@@ -16,7 +16,7 @@ rule "1: Redacted because Section contains Vertebrate"
 
 rule "2: Not Redacted because Section contains no Vertebrate"
 	when
-		Section(!matchesType("vertebrate"))
+		eval(section.contains("vertebrate")==false);
 	then
 		section.redactNot("name", 2, "Not Redacted because Section contains no Vertebrate");
 		section.redactNot("address", 2, "Not Redacted because Section contains no Vertebrate");
@@ -25,110 +25,34 @@ rule "2: Not Redacted because Section contains no Vertebrate"
 
 rule "3: Do not redact Names and Addresses if no redaction Indicator is contained"
 	when
-		Section(matchesType("vertebrate"), matchesType("no_redaction_indicator"))
+		eval(section.contains("vertebrate")==true && section.contains("no_redaction_indicator")==true);
 	then
 		section.redactNot("name", 3, "Vertebrate was found, but also a no redaction indicator");
 		section.redactNot("address", 3, "Vertebrate was found, but also a no redaction indicator");
 	end
 
 
-rule "4: Redact Names and Addresses if no_redaction_indicator and redaction_indicator is contained"
+rule "4: Redact contact information, if applicant is found"
 	when
-		Section(matchesType("vertebrate"), matchesType("no_redaction_indicator"), matchesType("redaction_indicator"))
+		eval(section.getText().toLowerCase().contains("applicant"));
 	then
-		section.redact("name", 4, "Vertebrate was found and no_redaction_indicator and redaction_indicator");
-		section.redact("address", 4, "Vertebrate was found and no_redaction_indicator and redaction_indicator");
+		section.redactLineAfter("Name:", "address", 4, "Redacted because of Rule 4");
+		section.redactBetween("Address:", "Contact", "address", 4, "Redacted because of Rule 4");
+		section.redactLineAfter("Contact point:",  "address", 4, "Redacted because of Rule 4");
+		section.redactLineAfter("Phone:", "address", 4, "Redacted because of Rule 4");
+		section.redactLineAfter("Fax:", "address", 4, "Redacted because of Rule 4");
+		section.redactLineAfter("E-mail:", "address", 4, "Redacted because of Rule 4");
 	end
 
 
-rule "5: Do not redact in guideline sections"
+rule "5: Redact contact information, if 'Producer of the plant protection product' is found"
 	when
-		Section(headlineContainsWord("guideline") || headlineContainsWord("Guidance"))
+		eval(section.getText().contains("Producer of the plant protection product"));
 	then
-		section.redactNot("name", 5, "Section is a guideline section.");
-		section.redactNot("address", 5, "Section is a guideline section.");
-	end
-
-
-rule "6: Redact contact information if applicant is found"
-	when
-		Section(headlineContainsWord("applicant") || text.contains("Applicant") || headlineContainsWord("Primary contact") || headlineContainsWord("Alternative contact"))
-	then
-		section.redactLineAfter("Name:", "address", 6, "Applicant information was found");
-		section.redactBetween("Address:", "Contact", "address", 6, "Applicant information was found");
-		section.redactLineAfter("Contact point:",  "address", 6, "Applicant information was found");
-		section.redactLineAfter("Phone:", "address", 6, "Applicant information was found");
-		section.redactLineAfter("Fax:", "address", 6, "Applicant information was found");
-		section.redactLineAfter("Tel.:", "address", 6, "Applicant information was found");
-		section.redactLineAfter("Tel:", "address", 6, "Applicant information was found");
-		section.redactLineAfter("E-mail:", "address", 6, "Applicant information was found");
-		section.redactLineAfter("Email:", "address", 6, "Applicant information was found");
-		section.redactLineAfter("e-mail:", "address", 6, "Applicant information was found");
-		section.redactLineAfter("E-mail address:", "address", 6, "Applicant information was found");
-		section.redactLineAfter("Contact:", "address", 6, "Applicant information was found");
-		section.redactLineAfter("Alternative contact:", "address", 6, "Applicant information was found");
-		section.redactLineAfter("Telephone number:", "address", 6, "Applicant information was found");
-		section.redactLineAfter("Telephone No:", "address", 6, "Applicant information was found");
-		section.redactLineAfter("Fax number:", "address", 6, "Applicant information was found");
-		section.redactLineAfter("Telephone:", "address", 6, "Applicant information was found");
-		section.redactLineAfter("Company:", "address", 6, "Applicant information was found");
-		section.redactBetween("No:", "Fax", "address", 6, "Applicant information was found");
-		section.redactBetween("Contact:", "Tel.:", "address", 6, "Applicant information was found");
-	end
-
-
-rule "7: Redact contact information if Producer is found"
-	when
-		Section(text.toLowerCase().contains("producer of the plant protection") || text.toLowerCase().contains("producer of the active substance") || text.contains("Manufacturer of the active substance") || text.contains("Manufacturer:") || text.contains("Producer or producers of the active substance"))
-	then
-		section.redactLineAfter("Name:", "address", 7, "Producer was found");
-		section.redactBetween("Address:", "Contact", "address", 7, "Producer was found");
-		section.redactBetween("Contact:", "Phone", "address", 7, "Producer was found");
-		section.redactBetween("Contact:", "Telephone number:", "address", 7, "Producer was found");
-		section.redactBetween("Address:", "Manufacturing", "address", 7, "Producer was found");
-		section.redactLineAfter("Telephone:", "address", 7, "Producer was found");
-		section.redactLineAfter("Phone:", "address", 7, "Producer was found");
-		section.redactLineAfter("Fax:", "address", 7, "Producer was found");
-		section.redactLineAfter("E-mail:", "address", 7, "Producer was found");
-		section.redactLineAfter("Contact:", "address", 7, "Producer was found");
-		section.redactLineAfter("Fax number:", "address", 7, "Producer was found");
-		section.redactLineAfter("Telephone number:", "address", 7, "Producer was found");
-		section.redactLineAfter("Tel:", "address", 7, "Producer was found");
-		section.redactBetween("No:", "Fax", "address", 7, "Producer was found");
-	end
-
-
-rule "8: Not redacted because Vertebrate Study = N"
-    when
-        Section(rowEquals("Vertebrate study Y/N", "N") || rowEquals("Vertebrate study Y/N", "No"))
-    then
-        section.redactNotCell("Author(s)", 8, "name", "Not redacted because row is not a vertebrate study");
-        section.redactNot("address", 8, "Not redacted because row is not a vertebrate study");
-        section.highlightCell("Vertebrate study Y/N", 8, "hint_only");
-    end
-
-
-rule "9: Redact if must redact entry is found"
-	when
-		Section(matchesType("must_redact"))
-	then
-		section.redact("name", 9, "must_redact entry was found.");
-		section.redact("address", 9, "must_redact entry was found.");
-	end
-
-
-rule "10: Redact Authors and Addresses in Reference Table if it is a Vertebrate study"
-    when
-        Section(rowEquals("Vertebrate study Y/N", "Y") || rowEquals("Vertebrate study Y/N", "Yes"))
-    then
-        section.redactCell("Author(s)", 10, "name", "Redacted because row is a vertebrate study");
-        section.redact("address", 10, "Redacted because row is a vertebrate study");
-        section.highlightCell("Vertebrate study Y/N", 10, "must_redact");
-    end
-
-rule "11: Redact sponsor company"
-    when
-        Section(text.toLowerCase().contains("batches produced at"))
-    then
-        section.redactIfPrecededBy("batches produced at", "sponsor", 11, "Redacted because it represents a sponsor company");
-    end
+		section.redactLineAfter("Name:", "address", 5, "xxxx");
+		section.redactBetween("Address:", "Contact", "address", 5, "xxxx");
+		section.redactBetween("Contact:", "Phone", "address", 5, "xxxx");
+		section.redactLineAfter("Phone:", "address", 5, "xxxx");
+		section.redactLineAfter("Fax:", "address", 5, "xxxx");
+		section.redactLineAfter("E-mail:", "address", 5, "xxxx");
+	end