extended-entity-finding: increase threshold

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

@@ -61,7 +61,7 @@ dependencies {
 
     implementation("com.fasterxml.jackson.module:jackson-module-afterburner:${jacksonVersion}")
     implementation("com.fasterxml.jackson.datatype:jackson-datatype-jsr310:${jacksonVersion}")
-    implementation("org.ahocorasick:ahocorasick:0.6.3")
+    implementation("org.ahocorasick:ahocorasick:0.7.3")
     implementation("org.javassist:javassist:3.29.2-GA")
 
     implementation("org.drools:drools-engine:${droolsVersion}")
@@ -129,6 +129,7 @@ tasks.named<BootBuildImage>("bootBuildImage") {
         "BPE_APPEND_JAVA_TOOL_OPTIONS",
         "-XX:MaxMetaspaceSize=1g -Dfile.encoding=UTF-8 -Dkie.repository.project.cache.size=50 -Dkie.repository.project.versions.cache.size=5"
     )
+    environment.put("BPE_DEFAULT_LANG", "en_US.utf8")
     environment.put("BPE_DEFAULT_LANG", "en_US.utf8") // java.text.Normalizer does not care for file.encoding
 
     imageName.set("nexus.knecon.com:5001/red/${project.name}")// must build image with same name always, otherwise the builder will not know which image to use as cache. DO NOT CHANGE!

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

@@ -19,6 +19,7 @@ import lombok.Data;
 public class SearchImplementation {
 
     private boolean ignoreCase;
+    private boolean ignoreWhiteSpace;
     private List<String> values;
 
     private Pattern pattern;
@@ -41,13 +42,22 @@ public class SearchImplementation {
     }
 
 
+    public SearchImplementation(Collection<String> values, boolean ignoreCase, boolean ignoreWhiteSpace) {
+
+        this.values = new ArrayList<>(values);
+        this.ignoreCase = ignoreCase;
+        this.ignoreWhiteSpace = ignoreWhiteSpace;
+        this.createSearchImplementation();
+    }
+
+
     private void createSearchImplementation() {
 
         if (this.values.isEmpty()) {
             return;
         }
 
-        if (this.values.size() == 1) {
+        if (this.values.size() == 1 && !this.ignoreWhiteSpace) {
             var text = this.values.iterator().next();
 
             if (this.ignoreCase) {
@@ -60,6 +70,9 @@ public class SearchImplementation {
             if (this.ignoreCase) {
                 builder.ignoreCase();
             }
+            if (this.ignoreWhiteSpace) {
+                builder.ignoreWhiteSpace();
+            }
 
             builder.addKeywords(this.values);
 

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

@@ -264,7 +264,7 @@ public class AtomicTextBlock implements TextBlock {
     }
 
 
-    private List<Integer> getAllLineBreaksInBoundary(TextRange textRange) {
+    protected List<Integer> getAllLineBreaksInBoundary(TextRange textRange) {
 
         return getLineBreaks().stream()
                 .map(linebreak -> linebreak + this.textRange.start())

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

@@ -0,0 +1,126 @@
+package com.iqser.red.service.redaction.v1.server.model.document.textblock;
+
+import java.awt.geom.Rectangle2D;
+import java.text.BreakIterator;
+import java.util.ArrayList;
+import java.util.List;
+import java.util.Locale;
+import java.util.Map;
+
+import com.iqser.red.service.redaction.v1.server.model.document.TextRange;
+import com.iqser.red.service.redaction.v1.server.model.document.nodes.Page;
+
+import lombok.AccessLevel;
+import lombok.AllArgsConstructor;
+import lombok.Data;
+import lombok.experimental.FieldDefaults;
+
+@Data
+@AllArgsConstructor
+@FieldDefaults(level = AccessLevel.PRIVATE)
+public class PartialTextBlock implements TextBlock {
+
+    AtomicTextBlock atomicTextBlock;
+    TextRange textRange;
+
+
+    @Override
+    public String getSearchText() {
+
+        return atomicTextBlock.getSearchText().substring(textRange.start(), textRange.end());
+    }
+
+
+    @Override
+    public String getSearchTextLowerCase() {
+
+        return atomicTextBlock.getSearchTextLowerCase().substring(textRange.start(), textRange.end());
+    }
+
+
+    @Override
+    public List<String> getWords() {
+
+        String searchText = getSearchText();
+
+        List<String> words = new ArrayList<>();
+        BreakIterator iterator = BreakIterator.getWordInstance(Locale.ENGLISH);
+        iterator.setText(getSearchText());
+        int start = iterator.first();
+        for (int end = iterator.next(); end != BreakIterator.DONE; start = end, end = iterator.next()) {
+            words.add(searchText.substring(start, end));
+        }
+        return words;
+    }
+
+
+    @Override
+    public List<AtomicTextBlock> getAtomicTextBlocks() {
+
+        return List.of(atomicTextBlock);
+    }
+
+
+    @Override
+    public int getNextLinebreak(int fromIndex) {
+
+        return atomicTextBlock.getNextLinebreak(fromIndex);
+    }
+
+
+    @Override
+    public int getPreviousLinebreak(int fromIndex) {
+
+        return atomicTextBlock.getPreviousLinebreak(fromIndex);
+    }
+
+
+    @Override
+    public TextRange getLineTextRange(int lineNumber) {
+
+        return atomicTextBlock.getLineTextRange(lineNumber);
+    }
+
+
+    @Override
+    public List<Integer> getLineBreaks() {
+
+        return atomicTextBlock.getAllLineBreaksInBoundary(textRange);
+    }
+
+
+    @Override
+    public Rectangle2D getPosition(int stringIdx) {
+
+        return atomicTextBlock.getPosition(stringIdx);
+    }
+
+
+    @Override
+    public List<Rectangle2D> getPositions(TextRange stringTextRange) {
+
+        return atomicTextBlock.getPositions(stringTextRange);
+    }
+
+
+    @Override
+    public Map<Page, List<Rectangle2D>> getPositionsPerPage(TextRange stringTextRange) {
+
+        return atomicTextBlock.getPositionsPerPage(stringTextRange);
+    }
+
+
+    @Override
+    public String subSequenceWithLineBreaks(TextRange textRange) {
+
+        return atomicTextBlock.subSequenceWithLineBreaks(textRange);
+    }
+
+
+    @Override
+    public int numberOfLines() {
+
+        return getLineBreaks().size() + 1;
+    }
+
+}

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

@@ -19,6 +19,7 @@ import com.iqser.red.service.persistence.service.v1.api.shared.model.analysislog
 import com.iqser.red.service.persistence.service.v1.api.shared.model.analysislog.entitylog.EntryState;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.analysislog.entitylog.Position;
 import com.iqser.red.service.persistence.service.v1.api.shared.model.annotations.ChangeFactory;
+import com.iqser.red.service.redaction.v1.server.RedactionServiceSettings;
 import com.iqser.red.service.redaction.v1.server.model.PrecursorEntity;
 import com.iqser.red.service.redaction.v1.server.model.RectangleWithPage;
 
@@ -33,6 +34,7 @@ import lombok.extern.slf4j.Slf4j;
 public class NotFoundImportedEntitiesService {
 
     public static final String IMPORTED_REDACTION_TYPE = "imported_redaction";
+    private final RedactionServiceSettings settings;
 
 
     @Timed("redactmanager_processEntityLog")
@@ -95,7 +97,7 @@ public class NotFoundImportedEntitiesService {
                             }
                             entityLogEntry.getImportedRedactionIntersections().add(precursorEntity.getId());
 
-                            if (entityLogEntry.getState() != EntryState.REMOVED) {
+                            if (entityLogEntry.getState() != EntryState.REMOVED && !settings.isAnnotationMode()) {
                                 entityLogEntry.setState(EntryState.REMOVED);
                                 entityLogEntry.getChanges().add(ChangeFactory.toChange(ChangeType.REMOVED, OffsetDateTime.now(), analysisNumber));
                             }

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

@@ -348,16 +348,7 @@ public class ComponentCreationService {
      */
     public void create(String ruleIdentifier, String name, String value, String valueDescription, Entity reference) {
 
-        referencedEntities.add(reference);
+        create(ruleIdentifier, name, value, valueDescription, List.of(reference));
-        List<Entity> referenceList = new LinkedList<>();
-        referenceList.add(reference);
-        kieSession.insert(Component.builder()
-                                  .matchedRule(RuleIdentifier.fromString(ruleIdentifier))
-                                  .name(name)
-                                  .value(value)
-                                  .valueDescription(valueDescription)
-                                  .references(referenceList)
-                                  .build());
     }
 
 

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

@@ -4,6 +4,7 @@ import static java.lang.String.format;
 import static java.util.stream.Collectors.groupingBy;
 
 import java.awt.geom.Rectangle2D;
+import java.util.ArrayList;
 import java.util.Collections;
 import java.util.Comparator;
 import java.util.List;
@@ -14,6 +15,7 @@ import java.util.Optional;
 import java.util.Set;
 import java.util.stream.Collectors;
 
+import org.apache.commons.text.similarity.LevenshteinDistance;
 import org.springframework.beans.factory.annotation.Autowired;
 import org.springframework.stereotype.Service;
 
@@ -22,14 +24,18 @@ import com.iqser.red.service.redaction.v1.server.model.ClosestEntity;
 import com.iqser.red.service.redaction.v1.server.model.PrecursorEntity;
 import com.iqser.red.service.redaction.v1.server.model.RectangleWithPage;
 import com.iqser.red.service.redaction.v1.server.model.dictionary.SearchImplementation;
+import com.iqser.red.service.redaction.v1.server.model.document.TextRange;
 import com.iqser.red.service.redaction.v1.server.model.document.entity.EntityType;
 import com.iqser.red.service.redaction.v1.server.model.document.entity.PositionOnPage;
 import com.iqser.red.service.redaction.v1.server.model.document.entity.TextEntity;
 import com.iqser.red.service.redaction.v1.server.model.document.nodes.Document;
 import com.iqser.red.service.redaction.v1.server.model.document.nodes.Page;
 import com.iqser.red.service.redaction.v1.server.model.document.nodes.SemanticNode;
+import com.iqser.red.service.redaction.v1.server.model.document.textblock.AtomicTextBlock;
+import com.iqser.red.service.redaction.v1.server.model.document.textblock.PartialTextBlock;
 import com.iqser.red.service.redaction.v1.server.model.document.textblock.TextBlock;
 import com.iqser.red.service.redaction.v1.server.utils.RectangleTransformations;
+import com.iqser.red.service.redaction.v1.server.utils.TextNormalizationUtilities;
 
 import lombok.extern.slf4j.Slf4j;
 
@@ -37,6 +43,7 @@ import lombok.extern.slf4j.Slf4j;
 @Service
 public class EntityFindingUtility {
 
+    private static final float STRING_SIMILARITY_THRESHOLD = 0.2f;
     EntityCreationService entityCreationService;
 
 
@@ -55,7 +62,7 @@ public class EntityFindingUtility {
             return Optional.empty();
         }
 
-        List<TextEntity> possibleEntities = entitiesWithSameValue.get(precursorEntity.getValue().toLowerCase(Locale.ENGLISH));
+        List<TextEntity> possibleEntities = entitiesWithSameValue.get(TextNormalizationUtilities.removeAllWhitespaces(precursorEntity.getValue().toLowerCase(Locale.ENGLISH)));
 
         if (entityIdentifierValueNotFound(possibleEntities)) {
             log.info("Entity could not be created with precursorEntity: {}, due to the value {} not being found anywhere.", precursorEntity, precursorEntity.getValue());
@@ -91,6 +98,79 @@ public class EntityFindingUtility {
     }
 
 
+    public Optional<TextEntity> findEntityByUnderlyingText(PrecursorEntity precursorEntity, Document document) {
+
+        if (precursorEntity.getEntityPosition().isEmpty()) {
+            return Optional.empty();
+        }
+
+        Optional<Page> optionalPage = document.getPages()
+                .stream()
+                .filter(docPage -> docPage.getNumber()
+                        .equals(precursorEntity.getEntityPosition()
+                                        .get(0).pageNumber()))
+                .findFirst();
+
+        if (optionalPage.isEmpty()) {
+            return Optional.empty();
+        }
+
+        Page page = optionalPage.get();
+        Rectangle2D rect = precursorEntity.getEntityPosition()
+                .stream()
+                .map(RectangleWithPage::rectangle2D)
+                .collect(RectangleTransformations.collectBBox());
+        Optional<AtomicTextBlock> intersectingTbOptional = page.getTextBlocksOnPage()
+                .stream()
+                .filter(tb -> RectangleTransformations.rectangle2DBBox(tb.getPositions()).intersects(rect))
+                .findFirst();
+        if (intersectingTbOptional.isEmpty()) {
+            return Optional.empty();
+        }
+        AtomicTextBlock intersectingTb = intersectingTbOptional.get();
+        List<PartialTextBlock> underlyingTextRuns = findUnderlyingCharacterRuns(intersectingTb, rect);
+
+        for (PartialTextBlock underlyingText : underlyingTextRuns) {
+            int threshold = (int) (Math.min(underlyingText.length(), precursorEntity.length()) * STRING_SIMILARITY_THRESHOLD) + 1;
+            int distance = new LevenshteinDistance(threshold).apply(underlyingText.getSearchText(), precursorEntity.getValue());
+            if (distance >= 0) {
+                return entityCreationService.byTextRangeWithEngine(underlyingText.getTextRange(), "temp", EntityType.ENTITY, document, Collections.emptySet());
+            }
+        }
+        return Optional.empty();
+    }
+
+
+    private static List<PartialTextBlock> findUnderlyingCharacterRuns(AtomicTextBlock intersectingTb, Rectangle2D rect) {
+
+        List<PartialTextBlock> intersectingTextBlocks = new ArrayList<>();
+        int first = -1;
+        int last = -1;
+
+        for (int i = 0; i < intersectingTb.getPositions().size(); i++) {
+            Rectangle2D rectangle2D = intersectingTb.getPosition(i + intersectingTb.getTextRange().start());
+
+            if (rectangle2D.intersects(rect)) {
+                if (first == -1) {
+                    first = i;
+                }
+                last = i;
+            } else if (first != -1) {
+                intersectingTextBlocks.add(new PartialTextBlock(intersectingTb, new TextRange(first, last)));
+
+                first = -1;
+                last = -1;
+            }
+        }
+
+        if (first != -1) {
+            intersectingTextBlocks.add(new PartialTextBlock(intersectingTb, new TextRange(first, last)));
+        }
+
+        return intersectingTextBlocks;
+    }
+
+
     private static boolean entityIdentifierValueNotFound(List<TextEntity> possibleEntities) {
 
         return possibleEntities == null || possibleEntities.isEmpty();
@@ -183,7 +263,7 @@ public class EntityFindingUtility {
 
         SearchImplementation searchImplementation = new SearchImplementation(entryValues.stream()
                                                                                      .map(String::trim)
-                                                                                     .collect(Collectors.toSet()), true);
+                                                                                     .collect(Collectors.toSet()), true, true);
 
         List<TextBlock> textBlocks = node.getTextBlocksByPageNumbers(pageNumbers);
 
@@ -193,7 +273,7 @@ public class EntityFindingUtility {
                 .filter(Optional::isPresent)
                 .map(Optional::get)
                 .distinct()
-                .collect(groupingBy(entity -> entity.getValue().toLowerCase(Locale.ROOT)));
+                .collect(groupingBy(entity -> TextNormalizationUtilities.removeAllWhitespaces(entity.getValue().toLowerCase(Locale.ROOT))));
     }
 
 

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

@@ -34,7 +34,7 @@ import lombok.extern.slf4j.Slf4j;
 @FieldDefaults(makeFinal = true, level = AccessLevel.PRIVATE)
 public class EntityFromPrecursorCreationService {
 
-    static double MATCH_THRESHOLD = 10; // Is compared to the average sum of distances in pdf coordinates for each corner of the bounding box of the entities
+    static double MATCH_THRESHOLD = 100; // Is compared to the average sum of distances in pdf coordinates for each corner of the bounding box of the entities
     EntityFindingUtility entityFindingUtility;
     DictionaryService dictionaryService;
     RedactionServiceSettings settings;
@@ -130,10 +130,8 @@ public class EntityFromPrecursorCreationService {
         } else {
             String section = precursorEntity.getManualOverwrite().getSection()
                     .orElse(null);
-            if ((section == null || section.isBlank())
+            if ((section == null || section.isBlank()) && precursorEntity.getSection() != null && !precursorEntity.getSection().isBlank() && precursorEntity.getEngines()
-                && precursorEntity.getSection() != null
+                    .contains(Engine.IMPORTED)) {
-                && !precursorEntity.getSection().isBlank()
-                && precursorEntity.getEngines().contains(Engine.IMPORTED)) {
                 section = precursorEntity.getSection();
             }
 

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

@@ -1,31 +1,47 @@
 package com.iqser.red.service.redaction.v1.server.utils;
 
+import java.util.regex.Pattern;
+
 import lombok.experimental.UtilityClass;
 
 @UtilityClass
 public final class TextNormalizationUtilities {
 
-    /**
+    public static final Pattern hyphenLineBreaks = Pattern.compile("[-~‐‒⁻−﹣゠⁓‑\\u00AD][\\r\\n]+");
-     * Revert hyphenation due to line breaks.
+    public static final Pattern linebreaks = Pattern.compile("[\\r\\n]+");
-     *
+    public static final Pattern doubleWhitespaces = Pattern.compile("\\s{2,}");
-     * @param text Text to be processed.
+    public static final Pattern WHITESPACE_REMOVAL = Pattern.compile("\\s+");
-     * @return Text without line-break hyphenation.
-     */
-    public static String removeHyphenLineBreaks(String text) {
 
-        return text.replaceAll("([^\\s\\d\\-]{2,500})[\\-\\u00AD]\\R", "$1");
+
+    public String cleanString(String value) {
+
+        String noHyphenLinebreaks = removeHyphenLinebreaks(value);
+        String noLinebreaks = removeLinebreaks(noHyphenLinebreaks);
+        return removeMultipleWhitespaces(noLinebreaks);
     }
 
 
-    public static String removeLineBreaks(String text) {
+    public String removeHyphenLinebreaks(String value) {
 
-        return text.replaceAll("\n", " ");
+        return hyphenLineBreaks.matcher(value).replaceAll("");
     }
 
 
-    public static String removeRepeatingWhitespaces(String text) {
+    private String removeMultipleWhitespaces(String value) {
 
-        return text.replaceAll(" {2}", " ");
+        return doubleWhitespaces.matcher(value).replaceAll(" ");
+    }
+
+
+    private String removeLinebreaks(String value) {
+
+        return linebreaks.matcher(value).replaceAll(" ");
+    }
+
+
+    public String removeAllWhitespaces(String value) {
+
+        return WHITESPACE_REMOVAL.matcher(value).replaceAll("");
     }
 
 }

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

@@ -611,7 +611,7 @@ public abstract class AbstractRedactionIntegrationTest {
 
     private String cleanDictionaryEntry(String entry) {
 
-        return TextNormalizationUtilities.removeHyphenLineBreaks(entry).replaceAll("\\n", " ");
+        return TextNormalizationUtilities.cleanString(entry);
     }
 
 

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

@@ -6,8 +6,6 @@ import static org.junit.jupiter.api.Assertions.assertEquals;
 import static org.junit.jupiter.api.Assertions.assertTrue;
 import static org.mockito.ArgumentMatchers.any;
 import static org.mockito.ArgumentMatchers.anyString;
-import static org.mockito.Mockito.times;
-import static org.mockito.Mockito.verify;
 import static org.mockito.Mockito.when;
 
 import java.io.BufferedWriter;
@@ -37,7 +35,6 @@ import org.junit.jupiter.api.Order;
 import org.junit.jupiter.api.Test;
 import org.junit.jupiter.api.TestMethodOrder;
 import org.junit.jupiter.api.extension.ExtendWith;
-import org.mockito.Mock;
 import org.springframework.boot.autoconfigure.EnableAutoConfiguration;
 import org.springframework.boot.autoconfigure.amqp.RabbitAutoConfiguration;
 import org.springframework.boot.test.context.SpringBootTest;
@@ -83,7 +80,6 @@ import com.iqser.red.service.redaction.v1.server.model.document.nodes.Section;
 import com.iqser.red.service.redaction.v1.server.redaction.utils.OsUtils;
 import com.iqser.red.service.redaction.v1.server.rules.RulesIntegrationTest;
 import com.iqser.red.service.redaction.v1.server.service.document.DocumentGraphMapper;
-import com.iqser.red.service.redaction.v1.server.storage.DocumentDataFallbackService;
 import com.iqser.red.storage.commons.StorageAutoConfiguration;
 import com.iqser.red.storage.commons.service.StorageService;
 import com.iqser.red.storage.commons.utils.FileSystemBackedStorageService;
@@ -102,7 +98,6 @@ public class RedactionIntegrationTest extends RulesIntegrationTest {
 
     private static final String RULES = loadFromClassPath("drools/rules.drl");
 
-
     @Configuration
     @EnableAutoConfiguration(exclude = {RabbitAutoConfiguration.class})
     @Import({LayoutParsingServiceProcessorConfiguration.class})
@@ -1233,6 +1228,44 @@ public class RedactionIntegrationTest extends RulesIntegrationTest {
     }
 
 
+    @Test
+    @Disabled
+    public void testImportedRedactions2() throws IOException {
+
+        String outputFileName = OsUtils.getTemporaryDirectory() + "/ImportedRedactions.pdf";
+        ClassPathResource importedRedactions = new ClassPathResource("files/ImportedRedactions/76c5683ebc8c19dc23eccea12dfc652b.IMPORTED_REDACTIONS.json");
+
+        AnalyzeRequest request = uploadFileToStorage("files/ImportedRedactions/76c5683ebc8c19dc23eccea12dfc652b.ORIGIN.pdf");
+        storageService.storeObject(TenantContext.getTenantId(),
+                                   StorageIdUtils.getStorageId(TEST_DOSSIER_ID, TEST_FILE_ID, FileType.IMPORTED_REDACTIONS),
+                                   importedRedactions.getInputStream());
+
+        analyzeDocumentStructure(LayoutParsingType.DOCUMINE_OLD, request);
+        AnalyzeResult result = analyzeService.analyze(request);
+
+        var entityLog = redactionStorageService.getEntityLog(TEST_DOSSIER_ID, TEST_FILE_ID);
+
+        AnnotateResponse annotateResponse = annotationService.annotate(AnnotateRequest.builder().dossierId(TEST_DOSSIER_ID).fileId(TEST_FILE_ID).build());
+
+        try (FileOutputStream fileOutputStream = new FileOutputStream(outputFileName)) {
+            fileOutputStream.write(annotateResponse.getDocument());
+        }
+
+        entityLog.getEntityLogEntry()
+                .forEach(entry -> {
+                    if (entry.getValue() == null) {
+                        return;
+                    }
+                    if (entry.getValue().equals("David")) {
+                        assertThat(entry.getImportedRedactionIntersections()).hasSize(1);
+                    }
+                    if (entry.getValue().equals("annotation")) {
+                        assertThat(entry.getImportedRedactionIntersections()).isEmpty();
+                    }
+                });
+    }
+
+
     @Test
     public void testExpandByPrefixRegEx() throws IOException {
 
@@ -2252,9 +2285,7 @@ public class RedactionIntegrationTest extends RulesIntegrationTest {
     @Test
     public void testFileWithImagesAndNoText() {
 
-        AnalyzeRequest request = prepareStorage("files/new/only_images.pdf",
+        AnalyzeRequest request = prepareStorage("files/new/only_images.pdf", "files/cv_service_empty_response.json", "files/only_images_file_image_response.json");
-                                                "files/cv_service_empty_response.json",
-                                                "files/only_images_file_image_response.json");
 
         analyzeDocumentStructure(LayoutParsingType.REDACT_MANAGER, request);
         AnalyzeResult result = analyzeService.analyze(request);

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

@@ -11,10 +11,10 @@ public class TextNormalizationUtilitiesTest {
     public void testHyphenRemoval() {
 
         String test = "Without these peo-\nple, this conference would not happen";
-        Assertions.assertThat(TextNormalizationUtilities.removeHyphenLineBreaks(test)).contains("people");
+        Assertions.assertThat(TextNormalizationUtilities.removeHyphenLinebreaks(test)).contains("people");
 
         test = "Die\t\nFreiwillige\t Versicherung\t endet\t zudem\t für\t den\t ein\u00AD\nzelnen\tVersicherten\tmit\tder\tAufhebung\tdes\tVertra-\nges,\t seiner\t Unterstellung\t unter\t die\t obligatorische\t\nVersicherung\t oder\t seinem\t Ausschluss.";
-        Assertions.assertThat(TextNormalizationUtilities.removeHyphenLineBreaks(test)).contains("einzelnen", "Vertrages");
+        Assertions.assertThat(TextNormalizationUtilities.removeHyphenLinebreaks(test)).contains("einzelnen", "Vertrages");
 
     }