Pull request #125 : RED-1090: Return text with areas and sectionNumber

Merge in RED/redaction-service from RED-1090 to master * commit '0dd47111c5294d9a9a0a10e174c2832436983205': RED-1090: Return text with areas and sectionNumber
RED-1090: Return text with areas and sectionNumber
2021-02-25 15:10:58 +01:00 · 2021-02-25 14:55:53 +01:00 · 2021-02-18 10:48:26 +01:00 · 2021-02-18 10:33:38 +01:00 · 2021-02-18 09:18:59 +01:00 · 2021-02-18 08:58:51 +01:00
22 changed files with 468 additions and 214 deletions
@@ -72,14 +72,6 @@ public class PlanSpec {
                        .jobs(new Job("Default Job",
                                new BambooKey("JOB1"))
                                .tasks(
-                                        new ScriptTask()
-                                                .description("Clean")
-                                                .inlineBody("#!/bin/bash\n" +
-                                                        "set -e\n" +
-                                                        "rm -rf ./*"),
-                                        new VcsCheckoutTask()
-                                                .description("Checkout Default Repository")
-                                                .checkoutItems(new CheckoutItem().defaultRepository()),
                                        new ScriptTask()
                                                .description("Clean")
                                                .inlineBody("#!/bin/bash\n" +
@@ -5,7 +5,7 @@
    <parent>
        <artifactId>platform-dependency</artifactId>
        <groupId>com.iqser.red</groupId>
-        <version>1.0.2</version>
+        <version>1.0.3</version>
    </parent>
    <modelVersion>4.0.0</modelVersion>

@@ -14,5 +14,6 @@ public class AnalyzeResult {
    private int numberOfPages;
    private RedactionLog redactionLog;
    private SectionGrid sectionGrid;
+    private Text text;

 }
@@ -0,0 +1,19 @@
+package com.iqser.red.service.redaction.v1.model;
+
+import lombok.AllArgsConstructor;
+import lombok.Builder;
+import lombok.Data;
+import lombok.NoArgsConstructor;
+
+@Data
+@Builder
+@AllArgsConstructor
+@NoArgsConstructor
+public class ManualForceRedact {
+
+    private String id;
+    private String user;
+    private Status status;
+    private String legalBasis;
+
+}
@@ -1,5 +1,5 @@
 package com.iqser.red.service.redaction.v1.model;

 public enum ManualRedactionType {
-    ADD, REMOVE
+    ADD, REMOVE, FORCE_REDACT
 }
@@ -20,6 +20,9 @@ public class ManualRedactions {
    @Builder.Default
    private Set<IdRemoval> idsToRemove = new HashSet<>();

+    @Builder.Default
+    private Set<ManualForceRedact> forceRedacts = new HashSet<>();
+
    @Builder.Default
    private Set<ManualRedactionEntry> entriesToAdd = new HashSet<>();

@@ -40,4 +40,7 @@ public class RedactionLogEntry {
    @Builder.Default
    private List<Comment> comments = new ArrayList<>();

+    private int startOffset;
+    private int endOffset;
+
 }
@@ -0,0 +1,29 @@
+package com.iqser.red.service.redaction.v1.model;
+
+import lombok.AllArgsConstructor;
+import lombok.Data;
+import lombok.NoArgsConstructor;
+import lombok.NonNull;
+import lombok.RequiredArgsConstructor;
+
+@Data
+@RequiredArgsConstructor
+@NoArgsConstructor
+@AllArgsConstructor
+public class SectionArea {
+
+    @NonNull
+    private Point topLeft;
+
+    @NonNull
+    private float width;
+
+    @NonNull
+    private float height;
+
+    @NonNull
+    private int page;
+
+    private String header;
+
+}
@@ -0,0 +1,25 @@
+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 SectionText {
+
+    private int sectionNumber;
+    private String text;
+
+    private boolean isTable;
+    private String headline;
+
+    private List<SectionArea> sectionAreas = new ArrayList<>();
+
+}
@@ -0,0 +1,17 @@
+package com.iqser.red.service.redaction.v1.model;
+
+import java.util.ArrayList;
+import java.util.List;
+
+import lombok.AllArgsConstructor;
+import lombok.Data;
+import lombok.NoArgsConstructor;
+
+@Data
+@NoArgsConstructor
+@AllArgsConstructor
+public class Text {
+
+    private List<SectionText> sectionTexts = new ArrayList<>();
+
+}
@@ -8,6 +8,7 @@ import java.util.Map;
 import com.iqser.red.service.redaction.v1.model.RedactionLogEntry;
 import com.iqser.red.service.redaction.v1.model.SectionGrid;
 import com.iqser.red.service.redaction.v1.server.redaction.model.Entity;
+import com.iqser.red.service.redaction.v1.model.SectionText;

 import lombok.Data;
 import lombok.NoArgsConstructor;
@@ -20,6 +21,7 @@ public class Document {
    private List<Paragraph> paragraphs = new ArrayList<>();
    private List<Header> headers = new ArrayList<>();
    private List<Footer> footers = new ArrayList<>();
+    private List<UnclassifiedText> unclassifiedTexts = new ArrayList<>();
    private Map<Integer, List<Entity>> entities = new HashMap<>();
    private FloatFrequencyCounter textHeightCounter = new FloatFrequencyCounter();
    private FloatFrequencyCounter fontSizeCounter= new FloatFrequencyCounter();
@@ -31,4 +33,6 @@ public class Document {
    private SectionGrid sectionGrid = new SectionGrid();
    private long dictionaryVersion;
    private long rulesVersion;
+
+    private List<SectionText> sectionText = new ArrayList<>();
 }
@@ -0,0 +1,24 @@
+package com.iqser.red.service.redaction.v1.server.classification.model;
+
+import java.util.List;
+
+import com.iqser.red.service.redaction.v1.server.redaction.model.SearchableText;
+
+import lombok.AllArgsConstructor;
+import lombok.Data;
+
+@Data
+@AllArgsConstructor
+public class UnclassifiedText {
+
+    private List<TextBlock> textBlocks;
+
+
+    public SearchableText getSearchableText() {
+
+        SearchableText searchableText = new SearchableText();
+        textBlocks.forEach(block -> searchableText.addAll(block.getSequences()));
+        return searchableText;
+    }
+
+}
@@ -111,6 +111,8 @@ public class ClassificationService {
            textBlock.setClassification("TextBlock Italic");
        } else if (PositionUtils.isWithinBodyTextFrame(bodyTextFrame, textBlock)) {
            textBlock.setClassification("TextBlock Unknown");
+        } else {
+            textBlock.setClassification("Other");
        }
    }

@@ -9,6 +9,7 @@ import com.iqser.red.service.redaction.v1.model.RedactionLogEntry;
 import com.iqser.red.service.redaction.v1.model.RedactionRequest;
 import com.iqser.red.service.redaction.v1.model.RedactionResult;
 import com.iqser.red.service.redaction.v1.model.SectionGrid;
+import com.iqser.red.service.redaction.v1.model.Text;
 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;
@@ -69,6 +70,7 @@ public class RedactionController implements RedactionResource {
                    .redactionLog(new RedactionLog(classifiedDoc.getRedactionLogEntities(), classifiedDoc.getDictionaryVersion(), classifiedDoc
                    .getRulesVersion(), analyzeRequest.getRuleSetId()))
                    .numberOfPages(classifiedDoc.getPages().size())
+                    .text(new Text(classifiedDoc.getSectionText()))
                    .build();

        } catch (Exception e) {
@@ -39,7 +39,7 @@ public class Entity {
    private String textAfter;


-    public Entity(String word, String type, boolean redaction, String redactionReason, List<EntityPositionSequence> positionSequences, String headline, int matchedRule, int sectionNumber, String legalBasis, boolean isDictionaryEntry, String textBefore, String textAfter) {
+    public Entity(String word, String type, boolean redaction, String redactionReason, List<EntityPositionSequence> positionSequences, String headline, int matchedRule, int sectionNumber, String legalBasis, boolean isDictionaryEntry, String textBefore, String textAfter, Integer start, Integer end) {

        this.word = word;
        this.type = type;
@@ -53,6 +53,8 @@ public class Entity {
        this.isDictionaryEntry = isDictionaryEntry;
        this.textBefore = textBefore;
        this.textAfter = textAfter;
+        this.start = start;
+        this.end = end;
    }


@@ -140,6 +140,48 @@ public class Section {
    }


+    public void expandToHintAnnotationByRegEx(String type, String pattern, boolean patternCaseInsensitive, int group, String asType) {
+
+        Pattern compiledPattern = Patterns.getCompiledPattern(pattern, patternCaseInsensitive);
+
+        Set<Entity> expanded = new HashSet<>();
+        for (Entity entity : entities) {
+
+            if (!entity.getType().equals(type) || entity.getTextAfter() == null) {
+                continue;
+            }
+
+            Matcher matcher = compiledPattern.matcher(entity.getTextAfter());
+
+            while (matcher.find()) {
+                String match = matcher.group(group);
+                if (StringUtils.isNotBlank(match)) {
+                    expanded.addAll(findEntities(entity.getWord() + match, asType, false, false, 0, null, null));
+                }
+            }
+        }
+
+        EntitySearchUtils.addEntitiesWithHigherRank(entities, expanded, dictionary);
+        EntitySearchUtils.removeEntitiesContainedInLarger(entities);
+    }
+
+
+    public void addHintAnnotationByRegEx(String pattern, boolean patternCaseInsensitive, int group, String asType) {
+
+        Pattern compiledPattern = Patterns.getCompiledPattern(pattern, patternCaseInsensitive);
+
+        Matcher matcher = compiledPattern.matcher(searchText);
+
+        while (matcher.find()) {
+            String match = matcher.group(group);
+            if (StringUtils.isNotBlank(match)) {
+                Set<Entity> found = findEntities(match.trim(), asType, false, false, 0, null, null);
+                EntitySearchUtils.addEntitiesWithHigherRank(entities, found, dictionary);
+            }
+        }
+    }
+
+
    public void redactIfPrecededBy(String prefix, String type, int ruleNumber, String reason, String legalBasis) {

        entities.forEach(entity -> {
@@ -160,6 +202,13 @@ public class Section {
    }


+    public void addRedaction(String value, String asType, int ruleNumber, String reason, String legalBasis) {
+
+        Set<Entity> found = findEntities(value.trim(), asType, true, true, ruleNumber, reason, legalBasis);
+        EntitySearchUtils.addEntitiesIgnoreRank(entities, found);
+    }
+
+
    public void redactLineAfter(String start, String asType, int ruleNumber, boolean redactEverywhere, String reason,
                                String legalBasis) {

@@ -17,12 +17,15 @@ 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.Point;
 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.Footer;
 import com.iqser.red.service.redaction.v1.server.classification.model.Header;
 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.classification.model.UnclassifiedText;
+import com.iqser.red.service.redaction.v1.model.SectionArea;
 import com.iqser.red.service.redaction.v1.server.redaction.model.CellValue;
 import com.iqser.red.service.redaction.v1.server.redaction.model.Dictionary;
 import com.iqser.red.service.redaction.v1.server.redaction.model.DictionaryModel;
@@ -31,6 +34,7 @@ import com.iqser.red.service.redaction.v1.server.redaction.model.EntityPositionS
 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.redaction.model.SectionSearchableTextPair;
+import com.iqser.red.service.redaction.v1.model.SectionText;
 import com.iqser.red.service.redaction.v1.server.redaction.utils.EntitySearchUtils;
 import com.iqser.red.service.redaction.v1.server.tableextraction.model.Cell;
 import com.iqser.red.service.redaction.v1.server.tableextraction.model.Table;
@@ -85,7 +89,7 @@ public class EntityRedactionService {
                        .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(), entity
-                                .getLegalBasis(), entity.isDictionaryEntry(), entity.getTextBefore(), entity.getTextAfter()));
+                                .getLegalBasis(), entity.isDictionaryEntry(), entity.getTextBefore(), entity.getTextAfter(), entity.getStart(), entity.getEnd()));
            }
        }

@@ -109,24 +113,29 @@ public class EntityRedactionService {
            List<Table> tables = paragraph.getTables();
            for (Table table : tables) {
                if (table.getColCount() == 2) {
-                    sectionSearchableTextPairs.addAll(processTableAsOneText(table, manualRedactions, sectionNumber, dictionary, local, hintsPerSectionNumber));
+                    sectionSearchableTextPairs.addAll(processTableAsOneText(classifiedDoc, table, manualRedactions, sectionNumber, dictionary, local, hintsPerSectionNumber));
                } else {
-                    sectionSearchableTextPairs.addAll(processTablePerRow(table, manualRedactions, sectionNumber, dictionary, local, hintsPerSectionNumber));
+                    sectionSearchableTextPairs.addAll(processTablePerRow(classifiedDoc, table, manualRedactions, sectionNumber, dictionary, local, hintsPerSectionNumber));
                }
                sectionNumber.incrementAndGet();
            }
-            sectionSearchableTextPairs.add(processText(paragraph.getSearchableText(), paragraph.getTextBlocks(), paragraph
+            sectionSearchableTextPairs.add(processText(classifiedDoc, paragraph.getSearchableText(), paragraph.getTextBlocks(), paragraph
                    .getHeadline(), manualRedactions, sectionNumber, dictionary, local, hintsPerSectionNumber));
            sectionNumber.incrementAndGet();
        }

        for (Header header : classifiedDoc.getHeaders()) {
-            sectionSearchableTextPairs.add(processText(header.getSearchableText(), header.getTextBlocks(), "Header", manualRedactions, sectionNumber, dictionary, local, hintsPerSectionNumber));
+            sectionSearchableTextPairs.add(processText(classifiedDoc, header.getSearchableText(), header.getTextBlocks(), "Header", manualRedactions, sectionNumber, dictionary, local, hintsPerSectionNumber));
            sectionNumber.incrementAndGet();
        }

        for (Footer footer : classifiedDoc.getFooters()) {
-            sectionSearchableTextPairs.add(processText(footer.getSearchableText(), footer.getTextBlocks(), "Footer", manualRedactions, sectionNumber, dictionary, local, hintsPerSectionNumber));
+            sectionSearchableTextPairs.add(processText(classifiedDoc, footer.getSearchableText(), footer.getTextBlocks(), "Footer", manualRedactions, sectionNumber, dictionary, local, hintsPerSectionNumber));
+            sectionNumber.incrementAndGet();
+        }
+
+        for (UnclassifiedText unclassifiedText : classifiedDoc.getUnclassifiedTexts()) {
+            sectionSearchableTextPairs.add(processText(classifiedDoc, unclassifiedText.getSearchableText(), unclassifiedText.getTextBlocks(), "", manualRedactions, sectionNumber, dictionary, local, hintsPerSectionNumber));
            sectionNumber.incrementAndGet();
        }

@@ -163,7 +172,7 @@ public class EntityRedactionService {
    }


-    private List<SectionSearchableTextPair> processTablePerRow(Table table, ManualRedactions manualRedactions,
+    private List<SectionSearchableTextPair> processTablePerRow(Document classifiedDoc, Table table, ManualRedactions manualRedactions,
                                                               AtomicInteger sectionNumber, Dictionary dictionary,
                                                               boolean local,
                                                               Map<Integer, Set<Entity>> hintsPerSectionNumber) {
@@ -175,10 +184,17 @@ public class EntityRedactionService {
            Map<String, CellValue> tabularData = new HashMap<>();
            int start = 0;
            List<Integer> cellStarts = new ArrayList<>();
+            SectionText sectionText = new SectionText();
            for (Cell cell : row) {
+
                if (CollectionUtils.isEmpty(cell.getTextBlocks())) {
                    continue;
                }
+
+                SectionArea sectionArea = new SectionArea(new Point((float) cell.getX(), (float) cell.getY()), (float) cell
+                        .getWidth(), (float) cell.getHeight(), cell.getTextBlocks().get(0).getSequences().get(0).getPage());
+                sectionText.getSectionAreas().add(sectionArea);
+
                addSectionToManualRedactions(cell.getTextBlocks(), manualRedactions, table.getHeadline(), sectionNumber.intValue());
                int cellStart = start;

@@ -190,6 +206,7 @@ public class EntityRedactionService {
                                .replaceAll("\n", "")
                                .replaceAll(" ", "")
                                .replaceAll("-", "");
+                        sectionArea.setHeader(headerName);
                        tabularData.put(headerName, new CellValue(cell.getTextBlocks(), cellStart));
                    });
                }
@@ -200,6 +217,7 @@ public class EntityRedactionService {
                }
                cellStarts.add(cellStart);
                start = start + cell.toString().trim().length() + 1;
+
            }
            Set<Entity> rowEntities = findEntities(searchableRow, table.getHeadline(), sectionNumber.intValue(), dictionary, local);
            surroundingWordsService.addSurroundingText(rowEntities, searchableRow, dictionary, cellStarts);
@@ -219,6 +237,14 @@ public class EntityRedactionService {
                    .dictionary(dictionary)
                    .build(), searchableRow));

+            if(!local) {
+                sectionText.setText(searchableRow.toString());
+                sectionText.setHeadline(table.getHeadline());
+                sectionText.setSectionNumber(sectionNumber.intValue());
+                sectionText.setTable(true);
+                classifiedDoc.getSectionText().add(sectionText);
+            }
+
            sectionNumber.incrementAndGet();
        }

@@ -226,18 +252,26 @@ public class EntityRedactionService {
    }


-    private List<SectionSearchableTextPair> processTableAsOneText(Table table, ManualRedactions manualRedactions,
+    private List<SectionSearchableTextPair> processTableAsOneText(Document classifiedDoc, Table table, ManualRedactions manualRedactions,
                                                                  AtomicInteger sectionNumber, Dictionary dictionary,
                                                                  boolean local,
                                                                  Map<Integer, Set<Entity>> hintsPerSectionNumber) {

        List<SectionSearchableTextPair> sectionSearchableTextPairs = new ArrayList<>();
        SearchableText entireTableText = new SearchableText();
+        SectionText sectionText = new SectionText();
        for (List<Cell> row : table.getRows()) {
            for (Cell cell : row) {
                if (CollectionUtils.isEmpty(cell.getTextBlocks())) {
                    continue;
                }
+
+                if(!local) {
+                    SectionArea sectionArea = new SectionArea(new Point((float) cell.getX(), (float) cell.getY()), (float) cell
+                            .getWidth(), (float) cell.getHeight(), cell.getTextBlocks().get(0).getSequences().get(0).getPage());
+                    sectionText.getSectionAreas().add(sectionArea);
+                }
+
                for (TextBlock textBlock : cell.getTextBlocks()) {
                    entireTableText.addAll(textBlock.getSequences());
                }
@@ -245,6 +279,7 @@ public class EntityRedactionService {
            }
        }

+
        Set<Entity> rowEntities = findEntities(entireTableText, table.getHeadline(), sectionNumber.intValue(), dictionary, local);
        surroundingWordsService.addSurroundingText(rowEntities, entireTableText, dictionary);

@@ -262,15 +297,38 @@ public class EntityRedactionService {
                .dictionary(dictionary)
                .build(), entireTableText));

+        if(!local) {
+            sectionText.setText(entireTableText.toString());
+            sectionText.setHeadline(table.getHeadline());
+            sectionText.setSectionNumber(sectionNumber.intValue());
+            sectionText.setTable(true);
+            classifiedDoc.getSectionText().add(sectionText);
+        }
+
        return sectionSearchableTextPairs;
    }


-    private SectionSearchableTextPair processText(SearchableText searchableText, List<TextBlock> paragraphTextBlocks,
+    private SectionSearchableTextPair processText(Document classifiedDoc, SearchableText searchableText, List<TextBlock> paragraphTextBlocks,
                                                  String headline, ManualRedactions manualRedactions,
                                                  AtomicInteger sectionNumber, Dictionary dictionary, boolean local,
                                                  Map<Integer, Set<Entity>> hintsPerSectionNumber) {

+        if(!local) {
+            SectionText sectionText = new SectionText();
+            for (TextBlock paragraphTextBlock : paragraphTextBlocks) {
+                SectionArea sectionArea = new SectionArea(new Point(paragraphTextBlock.getMinX(), paragraphTextBlock.getMinY()), paragraphTextBlock
+                        .getWidth(), paragraphTextBlock.getHeight(), paragraphTextBlock.getPage());
+                sectionText.getSectionAreas().add(sectionArea);
+            }
+
+            sectionText.setText(searchableText.toString());
+            sectionText.setHeadline(headline);
+            sectionText.setSectionNumber(sectionNumber.intValue());
+            sectionText.setTable(false);
+            classifiedDoc.getSectionText().add(sectionText);
+        }
+
        addSectionToManualRedactions(paragraphTextBlocks, manualRedactions, headline, sectionNumber.intValue());
        Set<Entity> entities = findEntities(searchableText, headline, sectionNumber.intValue(), dictionary, local);
        surroundingWordsService.addSurroundingText(entities, searchableText, dictionary);
@@ -14,6 +14,7 @@ import org.springframework.stereotype.Service;
 import com.iqser.red.service.redaction.v1.model.CellRectangle;
 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.ManualForceRedact;
 import com.iqser.red.service.redaction.v1.model.ManualRedactionEntry;
 import com.iqser.red.service.redaction.v1.model.ManualRedactionType;
 import com.iqser.red.service.redaction.v1.model.ManualRedactions;
@@ -136,9 +137,11 @@ public class RedactionLogCreatorService {
                                redactionLogEntry.setRedacted(false);
                                redactionLogEntry.setStatus(Status.APPROVED);
                                manualOverrideReason = entity.getRedactionReason() + ", removed by manual override";
+                                redactionLogEntry.setColor(getColor(entity, ruleSetId, false));
                            } else if (manualRemoval.getStatus().equals(Status.REQUESTED)) {
                                manualOverrideReason = entity.getRedactionReason() + ", requested to remove";
                                redactionLogEntry.setStatus(Status.REQUESTED);
+                                redactionLogEntry.setColor(getColor(entity, ruleSetId, true));
                            } else {
                                redactionLogEntry.setStatus(Status.DECLINED);
                            }
@@ -149,7 +152,34 @@ public class RedactionLogCreatorService {
                            redactionLogEntry.setManualRedactionType(ManualRedactionType.REMOVE);
                        }
                    }
+                }

+                if (manualRedactions != null && !manualRedactions.getForceRedacts().isEmpty()) {
+                    for (ManualForceRedact manualForceRedact : manualRedactions.getForceRedacts()) {
+                        if (manualForceRedact.getId().equals(entityPositionSequence.getId())) {
+                            String manualOverrideReason = null;
+                            if (manualForceRedact.getStatus().equals(Status.APPROVED)) {
+                                entity.setRedaction(true);
+                                redactionLogEntry.setRedacted(true);
+                                redactionLogEntry.setStatus(Status.APPROVED);
+                                redactionLogEntry.setColor(getColor(entity, ruleSetId, false));
+                                manualOverrideReason = entity.getRedactionReason() + ", forced by manual override";
+                                redactionLogEntry.setLegalBasis(manualForceRedact.getLegalBasis());
+                            } else if (manualForceRedact.getStatus().equals(Status.REQUESTED)) {
+                                manualOverrideReason = entity.getRedactionReason() + ", requested to force redact";
+                                redactionLogEntry.setStatus(Status.REQUESTED);
+                                redactionLogEntry.setColor(getColor(entity, ruleSetId, true));
+                                redactionLogEntry.setLegalBasis(manualForceRedact.getLegalBasis());
+                            } else {
+                                redactionLogEntry.setStatus(Status.DECLINED);
+                            }
+
+                            entity.setRedactionReason(manualOverrideReason != null ? manualOverrideReason : entity.getRedactionReason());
+                            redactionLogEntry.setReason(manualOverrideReason);
+                            redactionLogEntry.setManual(true);
+                            redactionLogEntry.setManualRedactionType(ManualRedactionType.FORCE_REDACT);
+                        }
+                    }
                }

                if (CollectionUtils.isNotEmpty(entityPositionSequence.getSequences())) {
@@ -277,6 +307,8 @@ public class RedactionLogCreatorService {
                .isDictionaryEntry(entity.isDictionaryEntry())
                .textAfter(entity.getTextAfter())
                .textBefore(entity.getTextBefore())
+                .startOffset(entity.getStart())
+                .endOffset(entity.getEnd())
                .build();
    }

@@ -15,6 +15,7 @@ import com.iqser.red.service.redaction.v1.server.classification.model.Header;
 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.classification.model.UnclassifiedText;
 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;
@@ -28,6 +29,7 @@ public class SectionsBuilderService {
        List<Paragraph> chunkBlockList = new ArrayList<>();
        List<Header> headers = new ArrayList<>();
        List<Footer> footers = new ArrayList<>();
+        List<UnclassifiedText> unclassifiedTexts = new ArrayList<>();

        AbstractTextContainer prev = null;

@@ -36,6 +38,7 @@ public class SectionsBuilderService {
        for (Page page : document.getPages()) {
            List<TextBlock> header = new ArrayList<>();
            List<TextBlock> footer = new ArrayList<>();
+            List<TextBlock> unclassifiedText = new ArrayList<>();
            for (AbstractTextContainer current : page.getTextBlocks()) {

                if (current.getClassification() == null) {
@@ -54,6 +57,11 @@ public class SectionsBuilderService {
                    continue;
                }

+                if (current.getClassification().equals("Other")) {
+                    unclassifiedText.add((TextBlock) current);
+                    continue;
+                }
+
                if (prev != null && current.getClassification().startsWith("H ") && !prev.getClassification()
                        .startsWith("H ") || !document.isHeadlines()) {
                    Paragraph chunkBlock = buildTextBlock(chunkWords, lastHeadline);
@@ -76,8 +84,16 @@ public class SectionsBuilderService {
                chunkWords.add(current);
                prev = current;
            }
-            headers.add(new Header(header));
-            footers.add(new Footer(footer));
+
+            if(!header.isEmpty()) {
+                headers.add(new Header(header));
+            }
+            if(!footer.isEmpty()) {
+                footers.add(new Footer(footer));
+            }
+            if(!unclassifiedText.isEmpty()) {
+                unclassifiedTexts.add(new UnclassifiedText(unclassifiedText));
+            }
        }

        Paragraph chunkBlock = buildTextBlock(chunkWords, lastHeadline);
@@ -87,6 +103,7 @@ public class SectionsBuilderService {
        document.setParagraphs(chunkBlockList);
        document.setHeaders(headers);
        document.setFooters(footers);
+        document.setUnclassifiedTexts(unclassifiedTexts);
    }


@@ -40,6 +40,7 @@ import org.springframework.context.annotation.Bean;
 import org.springframework.core.io.ClassPathResource;
 import org.springframework.test.context.junit4.SpringRunner;

+import com.fasterxml.jackson.databind.ObjectMapper;
 import com.iqser.red.service.configuration.v1.api.model.Colors;
 import com.iqser.red.service.configuration.v1.api.model.DictionaryResponse;
 import com.iqser.red.service.configuration.v1.api.model.RulesResponse;
@@ -51,6 +52,7 @@ import com.iqser.red.service.redaction.v1.model.AnnotateRequest;
 import com.iqser.red.service.redaction.v1.model.AnnotateResponse;
 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.ManualForceRedact;
 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;
@@ -58,6 +60,7 @@ 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.model.RedactionRequest;
 import com.iqser.red.service.redaction.v1.model.RedactionResult;
+import com.iqser.red.service.redaction.v1.model.SectionText;
 import com.iqser.red.service.redaction.v1.model.Status;
 import com.iqser.red.service.redaction.v1.server.client.DictionaryClient;
 import com.iqser.red.service.redaction.v1.server.client.RulesClient;
@@ -93,6 +96,9 @@ public class RedactionIntegrationTest {
    @Autowired
    private RedactionController redactionController;

+    @Autowired
+    private ObjectMapper objectMapper;
+
    @MockBean
    private RulesClient rulesClient;

@@ -324,7 +330,6 @@ public class RedactionIntegrationTest {
        recommendationTypeMap.put(PURITY, false);
        recommendationTypeMap.put(IMAGE, false);

-
        rankTypeMap.put(FALSE_POSITIVE, 160);
        rankTypeMap.put(PURITY, 155);
        rankTypeMap.put(PII, 150);
@@ -342,7 +347,6 @@ public class RedactionIntegrationTest {
        rankTypeMap.put(RECOMMENDATION_ADDRESS, 30);
        rankTypeMap.put(IMAGE, 30);

-
        colors.setDefaultColor("#acfc00");
        colors.setNotRedacted("#cccccc");
        colors.setRequestAdd("#04b093");
@@ -409,6 +413,7 @@ public class RedactionIntegrationTest {
            duplicates.entrySet().forEach(entry -> {
                assertThat(entry.getValue().size()).isEqualTo(1);
            });
+
        }

        long end = System.currentTimeMillis();
@@ -418,7 +423,6 @@ public class RedactionIntegrationTest {
    }


-
    private List<File> getPathsRecursively(File path) {

        List<File> result = new ArrayList<>();
@@ -440,32 +444,54 @@ public class RedactionIntegrationTest {
    @Test
    public void redactionTest() throws IOException {

-//        49 Cyprodinil - EU AIR3 - MCA Section 8 Supplement - Ecotoxicological studies on the active substance.pdf
-//        182 Fludioxonil - EU AIR3 - MCA Section 8 Supplement - Ecotoxicological studies on the active substance.pdf
-//        38 A14325E - EU AIR3 - MCP Section 10 - Ecotoxicological studies on the plant protection product.pdf
-//        91 Trinexapac-ethyl_RAR_01_Volume_1_2018-02-23.pdf
-//        95 Trinexapac-ethyl_RAR_08_Volume_3CA_B-6_2018-01-10.pdf
-
-
        System.out.println("redactionTest");
        long start = System.currentTimeMillis();
-        ClassPathResource pdfFileResource = new ClassPathResource("files/Cyprodinil/49 Cyprodinil - EU AIR3 - MCA Section 8 Supplement - Ecotoxicological studies on the active substance.pdf");
+        ClassPathResource pdfFileResource = new ClassPathResource("files/Metolachlor/S-Metolachlor_RAR_01_Volume_1_2018-09-06.pdf");

        AnalyzeRequest request = AnalyzeRequest.builder()
                .ruleSetId(TEST_RULESET_ID)
                .document(IOUtils.toByteArray(pdfFileResource.getInputStream()))
                .build();

-
        AnalyzeResult result = redactionController.analyze(request);

-        AnnotateResponse annotateResponse = redactionController.annotate(AnnotateRequest.builder().document(IOUtils.toByteArray(pdfFileResource.getInputStream())).redactionLog(result.getRedactionLog()).sectionGrid(result.getSectionGrid()).build());
-
+        AnnotateResponse annotateResponse = redactionController.annotate(AnnotateRequest.builder()
+                .document(IOUtils.toByteArray(pdfFileResource.getInputStream()))
+                .redactionLog(result.getRedactionLog())
+                .sectionGrid(result.getSectionGrid())
+                .build());

        try (FileOutputStream fileOutputStream = new FileOutputStream("/tmp/Annotated.pdf")) {
            fileOutputStream.write(annotateResponse.getDocument());
        }

+        try (FileOutputStream fileOutputStream = new FileOutputStream("/tmp/Test.json")) {
+            fileOutputStream.write(objectMapper.writeValueAsBytes(result.getText()));
+        }
+
+        int correctFound = 0;
+        loop:
+        for (RedactionLogEntry redactionLogEntry : result.getRedactionLog().getRedactionLogEntry()) {
+            for (SectionText sectionText : result.getText().getSectionTexts()) {
+                if (redactionLogEntry.getType().equals("image")) {
+                    correctFound++;
+                    continue loop;
+                }
+                if (redactionLogEntry.getSectionNumber() == sectionText.getSectionNumber()) {
+                    String value = sectionText.getText()
+                            .substring(redactionLogEntry.getStartOffset(), redactionLogEntry.getEndOffset());
+                    if (redactionLogEntry.getValue().equalsIgnoreCase(value)) {
+                        correctFound++;
+                    } else {
+                        throw new RuntimeException("WTF");
+                    }
+                }
+            }
+        }
+        assertThat(correctFound).isEqualTo(result.getRedactionLog().getRedactionLogEntry().size());
+
+        System.out.println("correctFound " + correctFound);
+
        long end = System.currentTimeMillis();

        System.out.println("duration: " + (end - start));
@@ -485,11 +511,13 @@ public class RedactionIntegrationTest {
                .document(IOUtils.toByteArray(pdfFileResource.getInputStream()))
                .build();

-
        AnalyzeResult result = redactionController.analyze(request);

-        AnnotateResponse annotateResponse = redactionController.annotate(AnnotateRequest.builder().document(IOUtils.toByteArray(pdfFileResource.getInputStream())).redactionLog(result.getRedactionLog()).sectionGrid(result.getSectionGrid()).build());
-
+        AnnotateResponse annotateResponse = redactionController.annotate(AnnotateRequest.builder()
+                .document(IOUtils.toByteArray(pdfFileResource.getInputStream()))
+                .redactionLog(result.getRedactionLog())
+                .sectionGrid(result.getSectionGrid())
+                .build());

        try (FileOutputStream fileOutputStream = new FileOutputStream("/tmp/Annotated.pdf")) {
            fileOutputStream.write(annotateResponse.getDocument());
@@ -504,6 +532,8 @@ public class RedactionIntegrationTest {
    @Test
    public void testManualRedaction() throws IOException {

+//        675eba69b0c2917de55462c817adaa05
+
        System.out.println("testManualRedaction");
        long start = System.currentTimeMillis();
        ClassPathResource pdfFileResource = new ClassPathResource("files/Minimal Examples/Single Table.pdf");
@@ -518,8 +548,13 @@ public class RedactionIntegrationTest {
                .text("This is a comment test")
                .build();
        manualRedactions.setIdsToRemove(Set.of(IdRemoval.builder()
-                .id("0836727c3508a0b2ea271da69c04cc2f")
-                .status(Status.REQUESTED)
+                .id("5b940b2cb401ed9f5be6fc24f6e77bcf")
+                .status(Status.DECLINED)
+                .build()));
+        manualRedactions.setForceRedacts(Set.of(ManualForceRedact.builder()
+                .id("675eba69b0c2917de55462c817adaa05")
+                .legalBasis("Something")
+                .status(Status.APPROVED)
                .build()));

        manualRedactions.getComments().put("e5be0f1d941bbb92a068e198648d06c4", List.of(comment));
@@ -542,11 +577,13 @@ public class RedactionIntegrationTest {
                .manualRedactions(manualRedactions)
                .build();

-
        AnalyzeResult result = redactionController.analyze(request);

-        AnnotateResponse annotateResponse = redactionController.annotate(AnnotateRequest.builder().document(IOUtils.toByteArray(pdfFileResource.getInputStream())).redactionLog(result.getRedactionLog()).sectionGrid(result.getSectionGrid()).build());
-
+        AnnotateResponse annotateResponse = redactionController.annotate(AnnotateRequest.builder()
+                .document(IOUtils.toByteArray(pdfFileResource.getInputStream()))
+                .redactionLog(result.getRedactionLog())
+                .sectionGrid(result.getSectionGrid())
+                .build());

        try (FileOutputStream fileOutputStream = new FileOutputStream("/tmp/Annotated.pdf")) {
            fileOutputStream.write(annotateResponse.getDocument());
@@ -640,7 +677,6 @@ public class RedactionIntegrationTest {
                .document(IOUtils.toByteArray(pdfFileResource.getInputStream()))
                .build();

-
        AnalyzeResult result = redactionController.analyze(request);

        result.getRedactionLog().getRedactionLogEntry().forEach(entry -> {
@@ -662,11 +698,13 @@ public class RedactionIntegrationTest {
                .document(IOUtils.toByteArray(pdfFileResource.getInputStream()))
                .build();

-
        AnalyzeResult result = redactionController.analyze(request);

-        AnnotateResponse annotateResponse = redactionController.annotate(AnnotateRequest.builder().document(IOUtils.toByteArray(pdfFileResource.getInputStream())).redactionLog(result.getRedactionLog()).sectionGrid(result.getSectionGrid()).build());
-
+        AnnotateResponse annotateResponse = redactionController.annotate(AnnotateRequest.builder()
+                .document(IOUtils.toByteArray(pdfFileResource.getInputStream()))
+                .redactionLog(result.getRedactionLog())
+                .sectionGrid(result.getSectionGrid())
+                .build());

        try (FileOutputStream fileOutputStream = new FileOutputStream("/tmp/Annotated.pdf")) {
            fileOutputStream.write(annotateResponse.getDocument());
@@ -20,145 +20,69 @@ rule "1: Redact CBI Authors"
    when
        Section(matchesType("CBI_author") || matchesType("recommendation_CBI_author"))
    then
-        section.redact("CBI_author", 1, "Author found", "Reg (EC) No 1107/2009 Art. 63 (2g)");
+        section.redact("CBI_author", 1, "Author found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
    end


-rule "2: Redacted because Section contains Vertebrate"
+rule "2: Redact CBI Address"
    when
-        Section(matchesType("vertebrate"))
+        Section(matchesType("CBI_address") || matchesType("recommendation_CBI_address"))
    then
-        section.redact("CBI_address", 2, "Vertebrate found", "Reg (EC) No 1107/2009 Art. 63 (2g)");
+        section.redact("CBI_address", 2, "Address found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
    end


-rule "3: Not Redacted because Section contains no Vertebrate"
+rule "3: Do not redact genitive CBI_author"
    when
-        Section(!matchesType("vertebrate"))
+        Section(matchesType("CBI_author") || matchesType("recommendation_CBI_author"))
    then
-        section.redactNot("CBI_address", 3, "No Vertebrate found");
+        section.expandToHintAnnotationByRegEx("CBI_author", "['’’'ʼˈ´`‘′ʻ’']s", false, 0, "test_method");
+        section.expandToHintAnnotationByRegEx("recommendation_CBI_author", "['’’'ʼˈ´`‘′ʻ’']s", false, 0, "test_method");
    end


-rule "4: Do not redact Names and Addresses if no redaction Indicator is contained"
-    when
-        Section(matchesType("vertebrate"), matchesType("no_redaction_indicator"))
-    then
-        section.redactNot("CBI_address", 4, "Vertebrate and No Redaction Indicator found");
-    end
-
-
-rule "5: Redact Names and Addresses if no_redaction_indicator and redaction_indicator is contained"
-    when
-        Section(matchesType("vertebrate"), matchesType("no_redaction_indicator"), matchesType("redaction_indicator"))
-    then
-        section.redact("CBI_address", 5, "Vertebrate and Redaction Indicator found", "Reg (EC) No 1107/2009 Art. 63 (2g)");
-    end
-
-rule "6: Redact Authors and Addresses in Reference Table if it is a Vertebrate study"
+rule "4: Redact Author(s) cells in Tables with Author(s) header"
    when
        Section(hasTableHeader("Author(s)") && !hasTableHeader("Vertebrate study Y/N"))
    then
-        section.redactCell("Author(s)", 6, "CBI_author", false, "Author found", "Reg (EC) No 1107/2009 Art. 63 (2g)");
+        section.redactCell("Author(s)", 4, "CBI_author", false, "Author found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
    end


-rule "7: Redact Authors and Addresses in Reference Table if it is a Vertebrate study"
+rule "5: Redact Author cells in Tables with Author header"
    when
        Section(hasTableHeader("Author") && !hasTableHeader("Vertebrate study Y/N"))
    then
-        section.redactCell("Author", 7, "CBI_author", false, "Author found", "Reg (EC) No 1107/2009 Art. 63 (2g)");
+        section.redactCell("Author", 5, "CBI_author", false, "Author found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
    end


-rule "8: Not redacted because Vertebrate Study = N"
+rule "6: Redact and recommand Authors in Tables with Vertebrate study Y/N header"
    when
-        Section(rowEquals("Vertebrate study Y/N", "N") || rowEquals("Vertebrate study Y/N", "No"))
+        Section(rowEquals("Vertebrate study Y/N", "Y") || rowEquals("Vertebrate study Y/N", "Yes") || rowEquals("Vertebrate study Y/N", "N") || rowEquals("Vertebrate study Y/N", "No"))
    then
-        section.redactCell("Author(s)", 8, "CBI_author", true, "Author found", "Reg (EC) No 1107/2009 Art. 63 (2g)");
-        section.redactNot("CBI_address", 8, "Not redacted because row is not a vertebrate study");
-        section.highlightCell("Vertebrate study Y/N", 8, "hint_only");
+        section.redactCell("Author(s)", 6, "CBI_author", true, "Author found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
    end


-rule "9: Redact if must redact entry is found"
-    when
-        Section(matchesType("must_redact"))
-    then
-        section.redact("CBI_address", 9, "must_redact entry was found.", "Reg (EC) No 1107/2009 Art. 63 (2g)");
-    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, "CBI_author", true, "Author found", "Reg (EC) No 1107/2009 Art. 63 (2g)");
-        section.redact("CBI_address", 10, "Redacted because row is a vertebrate study", "Reg (EC) No 1107/2009 Art. 63 (2g)");
-        section.highlightCell("Vertebrate study Y/N", 10, "must_redact");
-    end
-
-
-rule "11: Redact sponsor company"
-    when
-        Section(searchText.toLowerCase().contains("batches produced at"))
-    then
-        section.redactIfPrecededBy("batches produced at", "CBI_sponsor", 11, "Redacted because it represents a sponsor company", "Reg (EC) No 1107/2009 Art. 63 (2g)");
-        section.addHintAnnotation("batches produced at", "must_redact");
-    end
-
-
-rule "12: Redact determination of residues"
-    when
-        Section((
-            searchText.toLowerCase.contains("determination of residues") ||
-            searchText.toLowerCase.contains("determination of total residues")
-        ) && (
-            searchText.toLowerCase.contains("livestock") ||
-            searchText.toLowerCase.contains("live stock") ||
-            searchText.toLowerCase.contains("tissue") ||
-            searchText.toLowerCase.contains("tissues") ||
-            searchText.toLowerCase.contains("liver") ||
-            searchText.toLowerCase.contains("muscle") ||
-            searchText.toLowerCase.contains("bovine") ||
-            searchText.toLowerCase.contains("ruminant") ||
-            searchText.toLowerCase.contains("ruminants")
-        ))
-    then
-        section.redact("CBI_address", 12, "Determination of residues was found.", "Reg (EC) No 1107/2009 Art. 63 (2g)");
-        section.addHintAnnotation("determination of residues", "must_redact");
-        section.addHintAnnotation("determination of total residues", "must_redact");
-        section.addHintAnnotation("livestock", "must_redact");
-        section.addHintAnnotation("live stock", "must_redact");
-        section.addHintAnnotation("tissue", "must_redact");
-        section.addHintAnnotation("tissues", "must_redact");
-        section.addHintAnnotation("liver", "must_redact");
-        section.addHintAnnotation("muscle", "must_redact");
-        section.addHintAnnotation("bovine", "must_redact");
-        section.addHintAnnotation("ruminant", "must_redact");
-        section.addHintAnnotation("ruminants", "must_redact");
-    end
-
-
-rule "13: Redact if CTL/* or BL/*  was found"
+rule "7: Redact if CTL/* or BL/*  was found"
    when
        Section(searchText.contains("CTL/") || searchText.contains("BL/"))
    then
-        section.redact("CBI_address", 13, "Laboraty for vertebrate studies found", "Reg (EC) No 1107/2009 Art. 63 (2g)");
-        section.addHintAnnotation("CTL", "must_redact");
-        section.addHintAnnotation("BL", "must_redact");
+        section.addRedaction("CTL", "must_redact", 7, "Laboratory for vertebrate studies found", "Article 39(1)(2) of Regulation (EC) No 178/2002" );
+        section.addRedaction("BL", "must_redact", 7, "Laboratory for vertebrate studies found", "Article 39(1)(2) of Regulation (EC) No 178/2002" );
    end


-rule "14: Redact and add recommendation for et al. author"
+rule "8: Redact and add recommendation for et al. author"
    when
        Section(searchText.contains("et al"))
    then
-		section.redactAndRecommendByRegEx("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", false, 1, "CBI_author", 14, "Author found", "Reg (EC) No 1107/2009 Art. 63 (2g)");
+		section.redactAndRecommendByRegEx("\\b([A-ZÄÖÜ][^\\s\\.,]+( [A-ZÄÖÜ]{1,2}\\.?)?( ?[A-ZÄÖÜ]\\.?)?) et al\\.?", false, 1, "CBI_author", 8, "Author found", "Reg (EC) No 1107/2009 Art. 63 (2g)");
    end


-rule "15: Add recommendation for Addresses in Test Organism sections"
+rule "9: Add recommendation for Addresses in Test Organism sections"
    when
        Section(searchText.contains("Species:") && searchText.contains("Source:"))
    then
@@ -166,7 +90,7 @@ rule "15: Add recommendation for Addresses in Test Organism sections"
    end


-rule "16: Add recommendation for Addresses in Test Animals sections"
+rule "10: Add recommendation for Addresses in Test Animals sections"
    when
        Section(searchText.contains("Species") && searchText.contains("Source"))
    then
@@ -174,34 +98,35 @@ rule "16: Add recommendation for Addresses in Test Animals sections"
    end


-rule "17: Do not redact Names and Addresses if no redaction Indicator is contained"
+rule "11: Do not redact Names and Addresses if Published Information found"
    when
        Section(matchesType("published_information"))
    then
-        section.redactNot("CBI_author", 17, "Vertebrate and Published Information found");
-        section.redactNot("CBI_address", 17, "Vertebrate and Published Information found");
+        section.redactNot("CBI_author", 11, "Published Information found");
+        section.redactNot("CBI_address", 11, "Published Information found");
    end

+
 // --------------------------------------- PII rules -------------------------------------------------------------------


-rule "18: Redacted PII Personal Identification Information"
+rule "12: Redacted PII Personal Identification Information"
    when
        Section(matchesType("PII"))
    then
-        section.redact("PII", 18, "PII (Personal Identification Information) found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
+        section.redact("PII", 12, "PII (Personal Identification Information) found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
    end


-rule "19: Redact Emails by RegEx"
+rule "13: Redact Emails by RegEx"
    when
        Section(searchText.contains("@"))
    then
-        section.redactByRegEx("\\b[A-Z0-9._%+-]+@[A-Z0-9.-]+\\.[A-Z]{2,4}\\b", true, 0, "PII", 19, "PII (Personal Identification Information) found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
+        section.redactByRegEx("\\b[A-Z0-9._%+-]+@[A-Z0-9.-]+\\.[A-Z]{2,4}\\b", true, 0, "PII", 13, "PII (Personal Identification Information) found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
    end


-rule "20: Redact contact information"
+rule "14: Redact contact information"
    when
       Section(text.contains("Contact point:")
       || text.contains("Phone:")
@@ -217,108 +142,120 @@ rule "20: Redact contact information"
       || text.contains("Telephone No:")
       || text.contains("Fax number:")
       || text.contains("Telephone:")
+       || text.contains("Phone No.")
       || text.contains("European contact:"))
    then
-          section.redactLineAfter("Contact point:", "PII", 20, true, "Contact information was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-              section.redactLineAfter("Phone:", "PII", 20, true, "Contact information was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-              section.redactLineAfter("Fax:", "PII", 20, true, "Contact information was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-              section.redactLineAfter("Tel.:", "PII", 20, true, "Contact information was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-              section.redactLineAfter("Tel:", "PII", 20, true, "Contact information was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-              section.redactLineAfter("E-mail:", "PII", 20, true, "Contact information was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-              section.redactLineAfter("Email:", "PII", 20, true, "Contact information was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-              section.redactLineAfter("e-mail:", "PII", 20, true, "Contact information was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-              section.redactLineAfter("E-mail address:", "PII", 20, true, "Contact information was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-              section.redactLineAfter("Contact:", "PII", 20, true, "Contact information was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-              section.redactLineAfter("Alternative contact:", "PII", 20, true, "Contact information was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-              section.redactLineAfter("Telephone number:", "PII", 20, true, "Contact information was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-              section.redactLineAfter("Telephone No:", "PII", 20, true, "Contact information was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-              section.redactLineAfter("Fax number:", "PII", 20, true, "Contact information was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-              section.redactLineAfter("Telephone:", "PII", 20, true, "Contact information was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-              section.redactBetween("No:", "Fax", "PII", 20, true, "Contact information was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-              section.redactBetween("Contact:", "Tel.:", "PII", 20, true, "Contact information was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-              section.redactLineAfter("European contact:",  "PII", 20, true, "Contact information was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
+          section.redactLineAfter("Contact point:", "PII", 14, true, "Contact information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+              section.redactLineAfter("Phone:", "PII", 14, true, "Contact information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+              section.redactLineAfter("Fax:", "PII", 14, true, "Contact information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+              section.redactLineAfter("Tel.:", "PII", 14, true, "Contact information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+              section.redactLineAfter("Tel:", "PII", 14, true, "Contact information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+              section.redactLineAfter("E-mail:", "PII", 14, true, "Contact information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+              section.redactLineAfter("Email:", "PII", 14, true, "Contact information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+              section.redactLineAfter("e-mail:", "PII", 14, true, "Contact information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+              section.redactLineAfter("E-mail address:", "PII", 14, true, "Contact information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+              section.redactLineAfter("Contact:", "PII", 14, true, "Contact information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+              section.redactLineAfter("Alternative contact:", "PII", 14, true, "Contact information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+              section.redactLineAfter("Telephone number:", "PII", 14, true, "Contact information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+              section.redactLineAfter("Telephone No:", "PII", 14, true, "Contact information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+              section.redactLineAfter("Fax number:", "PII", 14, true, "Contact information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+              section.redactLineAfter("Telephone:", "PII", 14, true, "Contact information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+              section.redactLineAfter("Phone No.", "PII", 14, true, "Contact information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+              section.redactBetween("No:", "Fax", "PII", 14, true, "Contact information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+              section.redactBetween("Contact:", "Tel.:", "PII", 14, true, "Contact information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+              section.redactLineAfter("European contact:",  "PII", 14, true, "Contact information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
     end


-rule "21: Redact contact information if applicant is found"
+rule "15: Redact contact information if applicant is found"
    when
        Section(headlineContainsWord("applicant") || text.contains("Applicant") || headlineContainsWord("Primary contact") || headlineContainsWord("Alternative contact") || text.contains("Telephone number:"))
    then
-        section.redactLineAfter("Contact point:", "PII", 21, true, "Applicant information was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-        section.redactLineAfter("Phone:", "PII", 21, true, "Applicant information was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-        section.redactLineAfter("Fax:", "PII", 21, true, "Applicant information was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-        section.redactLineAfter("Tel.:", "PII", 21, true, "Applicant information was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-        section.redactLineAfter("Tel:", "PII", 21, true, "Applicant information was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-        section.redactLineAfter("E-mail:", "PII", 21, true, "Applicant information was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-        section.redactLineAfter("Email:", "PII", 21, true, "Applicant information was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-        section.redactLineAfter("e-mail:", "PII", 21, true, "Applicant information was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-        section.redactLineAfter("E-mail address:", "PII", 21, true, "Applicant information was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-        section.redactLineAfter("Contact:", "PII", 21, true, "Applicant information was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-        section.redactLineAfter("Alternative contact:", "PII", 21, true, "Applicant information was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-        section.redactLineAfter("Telephone number:", "PII", 21, true, "Applicant information was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-        section.redactLineAfter("Telephone No:", "PII", 21, true, "Applicant information was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-        section.redactLineAfter("Fax number:", "PII", 21, true, "Applicant information was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-        section.redactLineAfter("Telephone:", "PII", 21, true, "Applicant information was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-        section.redactBetween("No:", "Fax", "PII", 21, true, "Applicant information was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-        section.redactBetween("Contact:", "Tel.:", "PII", 21, true, "Applicant information was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-        section.redactLineAfter("European contact:",  "PII", 21, true, "Applicant information was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
+        section.redactLineAfter("Contact point:", "PII", 15, true, "Applicant information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+        section.redactLineAfter("Phone:", "PII", 15, true, "Applicant information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+        section.redactLineAfter("Fax:", "PII", 15, true, "Applicant information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+        section.redactLineAfter("Tel.:", "PII", 15, true, "Applicant information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+        section.redactLineAfter("Tel:", "PII", 15, true, "Applicant information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+        section.redactLineAfter("E-mail:", "PII", 15, true, "Applicant information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+        section.redactLineAfter("Email:", "PII", 15, true, "Applicant information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+        section.redactLineAfter("e-mail:", "PII", 15, true, "Applicant information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+        section.redactLineAfter("E-mail address:", "PII", 15, true, "Applicant information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+        section.redactLineAfter("Contact:", "PII", 15, true, "Applicant information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+        section.redactLineAfter("Alternative contact:", "PII", 15, true, "Applicant information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+        section.redactLineAfter("Telephone number:", "PII", 15, true, "Applicant information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+        section.redactLineAfter("Telephone No:", "PII", 15, true, "Applicant information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+        section.redactLineAfter("Fax number:", "PII", 15, true, "Applicant information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+        section.redactLineAfter("Telephone:", "PII", 15, true, "Applicant information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+        section.redactLineAfter("Phone No.", "PII", 15, true, "Applicant information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+        section.redactBetween("No:", "Fax", "PII", 15, true, "Applicant information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+        section.redactBetween("Contact:", "Tel.:", "PII", 15, true, "Applicant information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+        section.redactLineAfter("European contact:",  "PII", 15, true, "Applicant information was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
    end


-rule "22: Redact contact information if Producer is found"
+rule "16: 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("Contact:", "PII", 22, true, "Producer was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-        section.redactLineAfter("Telephone:", "PII", 22, true, "Producer was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-        section.redactLineAfter("Phone:", "PII", 22, true, "Producer was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-        section.redactLineAfter("Fax:", "PII", 22, true, "Producer was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-        section.redactLineAfter("E-mail:", "PII", 22, true, "Producer was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-        section.redactLineAfter("Contact:", "PII", 22, true, "Producer was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-        section.redactLineAfter("Fax number:", "PII", 22, true, "Producer was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-        section.redactLineAfter("Telephone number:", "PII", 22, true, "Producer was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-        section.redactLineAfter("Tel:", "PII", 22, true, "Producer was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
-        section.redactBetween("No:", "Fax", "PII", 22, true, "Producer was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
+        section.redactLineAfter("Contact:", "PII", 16, true, "Producer was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+        section.redactLineAfter("Telephone:", "PII", 16, true, "Producer was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+        section.redactLineAfter("Phone:", "PII", 16, true, "Producer was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+        section.redactLineAfter("Fax:", "PII", 16, true, "Producer was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+        section.redactLineAfter("E-mail:", "PII", 16, true, "Producer was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+        section.redactLineAfter("Contact:", "PII", 16, true, "Producer was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+        section.redactLineAfter("Fax number:", "PII", 16, true, "Producer was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+        section.redactLineAfter("Telephone number:", "PII", 16, true, "Producer was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+        section.redactLineAfter("Tel:", "PII", 16, true, "Producer was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+        section.redactLineAfter("Phone No.", "PII", 16, true, "Producer was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
+        section.redactBetween("No:", "Fax", "PII", 16, true, "Producer was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
    end


-rule "23: Redact AUTHOR(S)"
+rule "17: Redact AUTHOR(S)"
    when
        Section(searchText.contains("AUTHOR(S):"))
    then
-        section.redactLinesBetween("AUTHOR(S):", "COMPLETION DATE:", "PII", 23, true, "AUTHOR(S) was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
+        section.redactLinesBetween("AUTHOR(S):", "COMPLETION DATE:", "PII", 17, true, "AUTHOR(S) was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
    end


-rule "24: Redact PERFORMING LABORATORY"
+rule "18: Redact PERFORMING LABORATORY"
    when
        Section(searchText.contains("PERFORMING LABORATORY:"))
    then
-        section.redactBetween("PERFORMING LABORATORY:", "LABORATORY PROJECT ID:", "PII", 24, true, "PERFORMING LABORATORY was found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
+        section.redactBetween("PERFORMING LABORATORY:", "LABORATORY PROJECT ID:", "PII", 18, true, "PERFORMING LABORATORY was found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
    end


-rule "25: Redact On behalf of Sequani Ltd.:"
+rule "19: Redact On behalf of Sequani Ltd.:"
    when
        Section(searchText.contains("On behalf of Sequani Ltd.: Name Title"))
    then
-        section.redactBetween("On behalf of Sequani Ltd.: Name Title", "On behalf of", "PII", 25, false , "PII (Personal Identification Information) found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
+        section.redactBetween("On behalf of Sequani Ltd.: Name Title", "On behalf of", "PII", 19, false , "PII (Personal Identification Information) found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
    end


-rule "26: Redact On behalf of Syngenta Ltd.:"
+rule "20: Redact On behalf of Syngenta Ltd.:"
    when
        Section(searchText.contains("On behalf of Syngenta Ltd.: Name Title"))
    then
-        section.redactBetween("On behalf of Syngenta Ltd.: Name Title", "Study dates", "PII", 26, false , "PII (Personal Identification Information) found", "Reg (EC) No 1107/2009 Art. 63 (2e)");
+        section.redactBetween("On behalf of Syngenta Ltd.: Name Title", "Study dates", "PII", 20, false , "PII (Personal Identification Information) found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
    end


 // --------------------------------------- other rules -------------------------------------------------------------------

-rule "27: Redact Purity"
+rule "21: Purity Hint"
    when
-        Section(searchText.contains("purity"))
+        Section(searchText.toLowerCase().contains("purity"))
    then
-	    section.redactByRegEx("purity ?:? (([\\d\\.]+)( .{0,4}\\.)? ?%)", true, 1, "purity", 27, "Purity found", "Reg (EC) No 1107/2009 Art. 63 (2a)");
+	    section.addHintAnnotationByRegEx("(purity ?( of|\\(.{1,20}\\))?( ?:)?) .{0,5}[\\d\\.]+( .{0,4}\\.)? ?%", true, 1, "hint_only");
+    end
+
+
+rule "22: Redact Must Redact"
+    when
+        Section(matchesType("must_redact"))
+    then
+        section.redact("must_redact", 22, "Must Redact found", "Article 39(1)(2) of Regulation (EC) No 178/2002");
    end
@@ -10,7 +10,7 @@
        <Root level="warn">
            <AppenderRef ref="CONSOLE" />
        </Root>
-        <Logger name="com.iqser.gin4" level="info" />
+        <Logger name="com.iqser" level="info" />
    </Loggers>

 </Configuration>
Author	SHA1	Message	Date
Dominique Eiflaender	dd4f1b34e1	Pull request #125 : RED-1090: Return text with areas and sectionNumber Merge in RED/redaction-service from RED-1090 to master * commit '0dd47111c5294d9a9a0a10e174c2832436983205': RED-1090: Return text with areas and sectionNumber	2021-02-25 15:10:58 +01:00
Dominique Eifländer	0dd47111c5	RED-1090: Return text with areas and sectionNumber	2021-02-25 14:55:53 +01:00
Dominique Eiflaender	7d507c8fda	Pull request #124 : Adjusted rules to new requirements, add possibility to addRedaction for rules Merge in RED/redaction-service from NewRequirementsRules to master * commit 'b6a13d1ff8a55f1b5ef528af5ea726b5e17b4950': Adjusted rules to new requirements, add possibility to addRedaction for rules	2021-02-18 10:48:26 +01:00
Dominique Eifländer	b6a13d1ff8	Adjusted rules to new requirements, add possibility to addRedaction for rules	2021-02-18 10:33:38 +01:00
Dominique Eiflaender	06e418c34e	Pull request #123 : RED-1070: Fixed not finding annotation on not classified textblocks Merge in RED/redaction-service from RED-1070 to master * commit 'de1dea7ac323dc005baeb0660cc492ab84a88164': RED-1070: Fixed not finding annotation on not classified textblocks	2021-02-18 09:18:59 +01:00
Dominique Eifländer	de1dea7ac3	RED-1070: Fixed not finding annotation on not classified textblocks	2021-02-18 08:58:51 +01:00
Dominique Eiflaender	53509f072e	Pull request #122 : RED-1055: Enabled to force redact ignore annotations Merge in RED/redaction-service from RED-1055 to master * commit 'e0fba8d38ce9858235ca84182f4587d472890ef1': RED-1055: Enabled to force redact ignore annotations	2021-02-12 10:55:04 +01:00
Dominique Eifländer	e0fba8d38c	RED-1055: Enabled to force redact ignore annotations	2021-02-12 10:41:32 +01:00
Lena Maldacker	8989191314	Pull request #121 : Add hint annotation by reg-ex and expand to hint annotation by reg-ex Merge in RED/redaction-service from dismissGen to master * commit '0f263c69b8f2eb7201f062cc263c8d06b7a710a1': Add hint annotation by reg-ex and expand to hint annotation by reg-ex	2021-02-11 17:22:55 +01:00
lmaldacker	0f263c69b8	Add hint annotation by reg-ex and expand to hint annotation by reg-ex	2021-02-11 16:53:07 +01:00
Kresnadi Budisantoso	ea1c2898bc	Remove duplicate build tasks in bamboo specs	2021-02-11 14:11:22 +01:00