RED-7141: Implemented docstrum layout parsing

layoutparser-service/layoutparser-service-internal-api/src/main/java/com/knecon/fforesight/service/layoutparser/internal/api/queue/LayoutParsingType.java

@@ -1,10 +1,10 @@
 package com.knecon.fforesight.service.layoutparser.internal.api.queue;
 
 public enum LayoutParsingType {
-    REDACT_MANAGER,
+    REDACT_MANAGER_OLD,
     TAAS,
     DOCUMINE,
 
     DOCSTRUM,
-    DOCSTRUM_XY
+    REDACT_MANAGER
 }

layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/LayoutParsingPipeline.java

@@ -100,35 +100,28 @@ public class LayoutParsingPipeline {
         log.info("Starting layout parsing for {}", layoutParsingRequest.identifier());
 
         File originFile = layoutParsingStorageService.getOriginFile(layoutParsingRequest.originFileStorageId());
-        File viewerDocumentFile = layoutParsingStorageService.getViewerDocFile(layoutParsingRequest.viewerDocumentStorageId())
-                .orElse(originFile);
+        File viewerDocumentFile = layoutParsingStorageService.getViewerDocFile(layoutParsingRequest.viewerDocumentStorageId()).orElse(originFile);
 
         VisualLayoutParsingResponse visualLayoutParsingResponse = new VisualLayoutParsingResponse();
-        if (layoutParsingRequest.visualLayoutParsingFileId()
-                .isPresent()) {
-            visualLayoutParsingResponse = layoutParsingStorageService.getVisualLayoutParsingFile(layoutParsingRequest.visualLayoutParsingFileId()
-                                                                                                         .get());
+        if (layoutParsingRequest.visualLayoutParsingFileId().isPresent()) {
+            visualLayoutParsingResponse = layoutParsingStorageService.getVisualLayoutParsingFile(layoutParsingRequest.visualLayoutParsingFileId().get());
         }
 
         ImageServiceResponse imageServiceResponse = new ImageServiceResponse();
-        if (layoutParsingRequest.imagesFileStorageId()
-                .isPresent()) {
-            imageServiceResponse = layoutParsingStorageService.getImagesFile(layoutParsingRequest.imagesFileStorageId()
-                                                                                     .get());
+        if (layoutParsingRequest.imagesFileStorageId().isPresent()) {
+            imageServiceResponse = layoutParsingStorageService.getImagesFile(layoutParsingRequest.imagesFileStorageId().get());
         }
 
         TableServiceResponse tableServiceResponse = new TableServiceResponse();
-        if (layoutParsingRequest.tablesFileStorageId()
-                .isPresent()) {
-            tableServiceResponse = layoutParsingStorageService.getTablesFile(layoutParsingRequest.tablesFileStorageId()
-                                                                                     .get());
+        if (layoutParsingRequest.tablesFileStorageId().isPresent()) {
+            tableServiceResponse = layoutParsingStorageService.getTablesFile(layoutParsingRequest.tablesFileStorageId().get());
         }
 
         ClassificationDocument classificationDocument = parseLayout(layoutParsingRequest.layoutParsingType(),
-                                                                    originFile,
-                                                                    imageServiceResponse,
-                                                                    tableServiceResponse,
-                                                                    visualLayoutParsingResponse,
+                originFile,
+                imageServiceResponse,
+                tableServiceResponse,
+                visualLayoutParsingResponse,
                 layoutParsingRequest.identifier().toString());
 
         log.info("Building document graph for {}", layoutParsingRequest.identifier());
@@ -161,25 +154,25 @@ public class LayoutParsingPipeline {
                 .numberOfPages(documentGraph.getNumberOfPages())
                 .duration(System.currentTimeMillis() - start)
                 .message(format("""
-                                        Layout parsing has finished in %.02f s.
-                                        identifiers: %s
-                                        %s
-                                        Files have been saved with Ids:
-                                        Structure: %s
-                                        Text: %s
-                                        Positions: %s
-                                        PageData: %s
-                                        Simplified Text: %s
-                                        Viewer Doc: %s""",
-                                ((float) (System.currentTimeMillis() - start)) / 1000,
-                                layoutParsingRequest.identifier(),
-                                buildSemanticNodeCountMessage(documentGraph.getNumberOfPages(), documentGraph.buildSemanticNodeCounts()),
-                                layoutParsingRequest.structureFileStorageId(),
-                                layoutParsingRequest.textBlockFileStorageId(),
-                                layoutParsingRequest.positionBlockFileStorageId(),
-                                layoutParsingRequest.pageFileStorageId(),
-                                layoutParsingRequest.simplifiedTextStorageId(),
-                                layoutParsingRequest.viewerDocumentStorageId()))
+                                Layout parsing has finished in %.02f s.
+                                identifiers: %s
+                                %s
+                                Files have been saved with Ids:
+                                Structure: %s
+                                Text: %s
+                                Positions: %s
+                                PageData: %s
+                                Simplified Text: %s
+                                Viewer Doc: %s""",
+                        ((float) (System.currentTimeMillis() - start)) / 1000,
+                        layoutParsingRequest.identifier(),
+                        buildSemanticNodeCountMessage(documentGraph.getNumberOfPages(), documentGraph.buildSemanticNodeCounts()),
+                        layoutParsingRequest.structureFileStorageId(),
+                        layoutParsingRequest.textBlockFileStorageId(),
+                        layoutParsingRequest.positionBlockFileStorageId(),
+                        layoutParsingRequest.pageFileStorageId(),
+                        layoutParsingRequest.simplifiedTextStorageId(),
+                        layoutParsingRequest.viewerDocumentStorageId()))
                 .build();
 
     }
@@ -200,14 +193,14 @@ public class LayoutParsingPipeline {
     private String buildSemanticNodeCountMessage(int numberOfPages, Map<NodeType, Long> semanticNodeCounts) {
 
         return String.format("%d pages with %d sections, %d headlines, %d paragraphs, %d tables with %d cells, %d headers, and %d footers parsed",
-                             numberOfPages,
-                             semanticNodeCounts.get(NodeType.SECTION) == null ? 0 : semanticNodeCounts.get(NodeType.SECTION),
-                             semanticNodeCounts.get(NodeType.HEADLINE) == null ? 0 : semanticNodeCounts.get(NodeType.HEADLINE),
-                             semanticNodeCounts.get(NodeType.PARAGRAPH) == null ? 0 : semanticNodeCounts.get(NodeType.PARAGRAPH),
-                             semanticNodeCounts.get(NodeType.TABLE) == null ? 0 : semanticNodeCounts.get(NodeType.TABLE),
-                             semanticNodeCounts.get(NodeType.TABLE_CELL) == null ? 0 : semanticNodeCounts.get(NodeType.TABLE_CELL),
-                             semanticNodeCounts.get(NodeType.HEADER) == null ? 0 : semanticNodeCounts.get(NodeType.HEADER),
-                             semanticNodeCounts.get(NodeType.FOOTER) == null ? 0 : semanticNodeCounts.get(NodeType.FOOTER));
+                numberOfPages,
+                semanticNodeCounts.get(NodeType.SECTION) == null ? 0 : semanticNodeCounts.get(NodeType.SECTION),
+                semanticNodeCounts.get(NodeType.HEADLINE) == null ? 0 : semanticNodeCounts.get(NodeType.HEADLINE),
+                semanticNodeCounts.get(NodeType.PARAGRAPH) == null ? 0 : semanticNodeCounts.get(NodeType.PARAGRAPH),
+                semanticNodeCounts.get(NodeType.TABLE) == null ? 0 : semanticNodeCounts.get(NodeType.TABLE),
+                semanticNodeCounts.get(NodeType.TABLE_CELL) == null ? 0 : semanticNodeCounts.get(NodeType.TABLE_CELL),
+                semanticNodeCounts.get(NodeType.HEADER) == null ? 0 : semanticNodeCounts.get(NodeType.HEADER),
+                semanticNodeCounts.get(NodeType.FOOTER) == null ? 0 : semanticNodeCounts.get(NodeType.FOOTER));
     }
 
 
@@ -266,11 +259,12 @@ public class LayoutParsingPipeline {
             List<Cell> emptyTableCells = tableExtractionService.findCells(cleanRulings.getHorizontal(), cleanRulings.getVertical());
 
             ClassificationPage classificationPage = switch (layoutParsingType) {
-                case REDACT_MANAGER -> redactManagerBlockificationService.blockify(stripper.getTextPositionSequences(), cleanRulings.getHorizontal(), cleanRulings.getVertical());
+                case REDACT_MANAGER_OLD ->
+                        redactManagerBlockificationService.blockify(stripper.getTextPositionSequences(), cleanRulings.getHorizontal(), cleanRulings.getVertical());
                 case TAAS -> taasBlockificationService.blockify(stripper.getTextPositionSequences(), cleanRulings.getHorizontal(), cleanRulings.getVertical());
                 case DOCUMINE -> docuMineBlockificationService.blockify(stripper.getTextPositionSequences(), cleanRulings.getHorizontal(), cleanRulings.getVertical());
                 case DOCSTRUM -> docstrumBlockificationService.blockify(stripper.getTextPositionSequences(), emptyTableCells, false);
-                case DOCSTRUM_XY -> docstrumBlockificationService.blockify(stripper.getTextPositionSequences(), emptyTableCells, true);
+                case REDACT_MANAGER -> docstrumBlockificationService.blockify(stripper.getTextPositionSequences(), emptyTableCells, true);
             };
             classificationPage.setCleanRulings(cleanRulings);
             classificationPage.setRotation(rotation);
@@ -298,7 +292,7 @@ public class LayoutParsingPipeline {
 
             tableExtractionService.extractTables(emptyTableCells, classificationPage);
 
-            if (layoutParsingType == LayoutParsingType.DOCSTRUM || layoutParsingType == LayoutParsingType.DOCSTRUM_XY) {
+            if (layoutParsingType == LayoutParsingType.DOCSTRUM || layoutParsingType == LayoutParsingType.REDACT_MANAGER) {
                 docstrumBlockificationService.combineBlocks(classificationPage);
             }
 
@@ -316,8 +310,8 @@ public class LayoutParsingPipeline {
         switch (layoutParsingType) {
             case TAAS -> taasClassificationService.classifyDocument(classificationDocument);
             case DOCUMINE -> docuMineClassificationService.classifyDocument(classificationDocument);
+            case REDACT_MANAGER_OLD -> redactManagerClassificationService.classifyDocument(classificationDocument);
             case REDACT_MANAGER -> redactManagerClassificationService.classifyDocument(classificationDocument);
-            case DOCSTRUM_XY -> redactManagerClassificationService.classifyDocument(classificationDocument);
             case DOCSTRUM -> redactManagerClassificationService.classifyDocument(classificationDocument);
         }
 

layoutparser-service/layoutparser-service-server/src/test/java/com/knecon/fforesight/service/layoutparser/server/HeadlinesGoldStandardIntegrationTest.java

@@ -95,7 +95,7 @@ public class HeadlinesGoldStandardIntegrationTest {
         goldStandardLog.getRedactionLogEntry().removeIf(r -> !r.isRedacted() || r.getChanges().get(r.getChanges().size() - 1).getType().equals(ChangeType.REMOVED));
         goldStandardLog.getRedactionLogEntry().forEach(e -> goldStandardHeadlines.add(new Headline(e.getPositions().get(0).getPage(), e.getValue())));
 
-        Document documentGraph = DocumentGraphFactory.buildDocumentGraph(layoutParsingPipeline.parseLayout(LayoutParsingType.REDACT_MANAGER,
+        Document documentGraph = DocumentGraphFactory.buildDocumentGraph(layoutParsingPipeline.parseLayout(LayoutParsingType.REDACT_MANAGER_OLD,
                 pdfFileResource.getFile(),
                 new ImageServiceResponse(),
                 new TableServiceResponse(),

layoutparser-service/layoutparser-service-server/src/test/java/com/knecon/fforesight/service/layoutparser/server/LayoutparserEnd2EndTest.java

@@ -26,7 +26,7 @@ public class LayoutparserEnd2EndTest extends AbstractTest {
     public void testLayoutParserEndToEnd() {
 
         prepareStorage("files/bdr/Wie weiter bei Kristeneinrichtungen.pdf");
-        LayoutParsingRequest layoutParsingRequest = buildDefaultLayoutParsingRequest(LayoutParsingType.REDACT_MANAGER);
+        LayoutParsingRequest layoutParsingRequest = buildDefaultLayoutParsingRequest(LayoutParsingType.REDACT_MANAGER_OLD);
         LayoutParsingFinishedEvent finishedEvent = layoutParsingPipeline.parseLayoutAndSaveFilesToStorage(layoutParsingRequest);
         Arrays.stream(finishedEvent.message().split("\n")).forEach(log::info);
     }

layoutparser-service/layoutparser-service-server/src/test/java/com/knecon/fforesight/service/layoutparser/server/graph/DocumentGraphJsonWritingTest.java

@@ -55,7 +55,7 @@ public class DocumentGraphJsonWritingTest extends BuildDocumentTest {
     @SneakyThrows
     private void writeJsons(Path filename) {
 
-        Document documentGraph = DocumentGraphFactory.buildDocumentGraph(layoutParsingPipeline.parseLayout(LayoutParsingType.REDACT_MANAGER,
+        Document documentGraph = DocumentGraphFactory.buildDocumentGraph(layoutParsingPipeline.parseLayout(LayoutParsingType.REDACT_MANAGER_OLD,
                 filename.toFile(),
                 new ImageServiceResponse(),
                 new TableServiceResponse(),

layoutparser-service/layoutparser-service-server/src/test/java/com/knecon/fforesight/service/layoutparser/server/graph/ViewerDocumentTest.java

@@ -33,7 +33,7 @@ public class ViewerDocumentTest extends BuildDocumentTest {
         ViewerDocumentService viewerDocumentService = new ViewerDocumentService(null);
         LayoutGridService layoutGridService = new LayoutGridService(viewerDocumentService);
 
-        Document document = buildGraph(fileName, LayoutParsingType.DOCSTRUM_XY);
+        Document document = buildGraph(fileName, LayoutParsingType.REDACT_MANAGER);
         long start = System.currentTimeMillis();
         layoutGridService.addLayoutGrid(documentFile, document, new File(tmpFileName), true);
         System.out.printf("Total time: %.2fs%n", ((float) (System.currentTimeMillis() - start)) / 1000);

layoutparser-service/layoutparser-service-server/src/test/java/com/knecon/fforesight/service/layoutparser/server/segmentation/PdfSegmentationServiceTest.java

@@ -56,12 +56,12 @@ public class PdfSegmentationServiceTest extends AbstractTest {
     @SneakyThrows
     public ClassificationDocument buildClassificationDocument(File originDocument, TableServiceResponse tableServiceResponse) {
 
-        ClassificationDocument classificationDocument = layoutParsingPipeline.parseLayout(LayoutParsingType.REDACT_MANAGER,
-                                                                                          originDocument,
-                                                                                          new ImageServiceResponse(),
-                                                                                          tableServiceResponse,
-                                                                                          new VisualLayoutParsingResponse(),
-                                                                                          "document");
+        ClassificationDocument classificationDocument = layoutParsingPipeline.parseLayout(LayoutParsingType.REDACT_MANAGER_OLD,
+                originDocument,
+                new ImageServiceResponse(),
+                tableServiceResponse,
+                new VisualLayoutParsingResponse(),
+                "document");
 
         redactManagerClassificationService.classifyDocument(classificationDocument);
 
@@ -112,16 +112,8 @@ public class PdfSegmentationServiceTest extends AbstractTest {
         var tableServiceResponse = objectMapper.readValue(cvTablesResource.getInputStream(), TableServiceResponse.class);
 
         ClassificationDocument document = buildClassificationDocument(pdfFileResource.getFile(), tableServiceResponse);
-        assertThat(document.getSections()
-                           .stream()
-                           .flatMap(paragraph -> paragraph.getTables()
-                                   .stream())
-                           .collect(Collectors.toList())).isNotEmpty();
-        var tables = document.getSections()
-                .stream()
-                .flatMap(paragraph -> paragraph.getTables()
-                        .stream())
-                .toList();
+        assertThat(document.getSections().stream().flatMap(paragraph -> paragraph.getTables().stream()).collect(Collectors.toList())).isNotEmpty();
+        var tables = document.getSections().stream().flatMap(paragraph -> paragraph.getTables().stream()).toList();
 
         // Quality of the table parsing is not good, because the file is rotated at scanning.
         // We only asset that the table border is not the page border.
@@ -143,12 +135,12 @@ public class PdfSegmentationServiceTest extends AbstractTest {
         imageServiceResponse.getData()
                 .forEach(imageMetadata -> images.computeIfAbsent(imageMetadata.getPosition().getPageNumber(), x -> new ArrayList<>())
                         .add(new ClassifiedImage(new Rectangle2D.Double(imageMetadata.getPosition().getX1(),
-                                                                        imageMetadata.getPosition().getY1(),
-                                                                        imageMetadata.getGeometry().getWidth(),
-                                                                        imageMetadata.getGeometry().getHeight()),
-                                                 ImageType.valueOf(imageMetadata.getClassification().getLabel().toUpperCase(Locale.ROOT)),
-                                                 imageMetadata.isAlpha(),
-                                                 imageMetadata.getPosition().getPageNumber())));
+                                imageMetadata.getPosition().getY1(),
+                                imageMetadata.getGeometry().getWidth(),
+                                imageMetadata.getGeometry().getHeight()),
+                                ImageType.valueOf(imageMetadata.getClassification().getLabel().toUpperCase(Locale.ROOT)),
+                                imageMetadata.isAlpha(),
+                                imageMetadata.getPosition().getPageNumber())));
 
         System.out.println("object");
     }
@@ -160,22 +152,11 @@ public class PdfSegmentationServiceTest extends AbstractTest {
         ClassPathResource pdfFileResource = new ClassPathResource("files/Minimal Examples/Spanning Cells.pdf");
 
         ClassificationDocument document = buildClassificationDocument(pdfFileResource.getFile());
-        assertThat(document.getSections()
-                           .stream()
-                           .flatMap(paragraph -> paragraph.getTables()
-                                   .stream())
-                           .collect(Collectors.toList())).isNotEmpty();
-        TablePageBlock table = document.getSections()
-                .stream()
-                .flatMap(paragraph -> paragraph.getTables()
-                        .stream())
-                .toList()
-                .get(0);
+        assertThat(document.getSections().stream().flatMap(paragraph -> paragraph.getTables().stream()).collect(Collectors.toList())).isNotEmpty();
+        TablePageBlock table = document.getSections().stream().flatMap(paragraph -> paragraph.getTables().stream()).toList().get(0);
         assertThat(table.getColCount()).isEqualTo(6);
         assertThat(table.getRowCount()).isEqualTo(13);
-        assertThat(table.getRows()
-                           .stream()
-                           .mapToInt(List::size).sum()).isEqualTo(6 * 13);
+        assertThat(table.getRows().stream().mapToInt(List::size).sum()).isEqualTo(6 * 13);
     }
 
 
@@ -185,37 +166,15 @@ public class PdfSegmentationServiceTest extends AbstractTest {
         ClassPathResource pdfFileResource = new ClassPathResource("files/Minimal Examples/Merge Table.pdf");
 
         ClassificationDocument document = buildClassificationDocument(pdfFileResource.getFile());
-        assertThat(document.getSections()
-                           .stream()
-                           .flatMap(paragraph -> paragraph.getTables()
-                                   .stream())
-                           .collect(Collectors.toList())).isNotEmpty();
-        TablePageBlock firstTable = document.getSections()
-                .stream()
-                .flatMap(paragraph -> paragraph.getTables()
-                        .stream())
-                .toList()
-                .get(0);
+        assertThat(document.getSections().stream().flatMap(paragraph -> paragraph.getTables().stream()).collect(Collectors.toList())).isNotEmpty();
+        TablePageBlock firstTable = document.getSections().stream().flatMap(paragraph -> paragraph.getTables().stream()).toList().get(0);
         assertThat(firstTable.getColCount()).isEqualTo(8);
         assertThat(firstTable.getRowCount()).isEqualTo(1);
-        TablePageBlock secondTable = document.getSections()
-                .stream()
-                .flatMap(paragraph -> paragraph.getTables()
-                        .stream())
-                .toList()
-                .get(1);
+        TablePageBlock secondTable = document.getSections().stream().flatMap(paragraph -> paragraph.getTables().stream()).toList().get(1);
         assertThat(secondTable.getColCount()).isEqualTo(8);
         assertThat(secondTable.getRowCount()).isEqualTo(2);
-        List<List<Cell>> firstTableHeaderCells = firstTable.getRows()
-                .get(0)
-                .stream()
-                .map(Collections::singletonList)
-                .collect(Collectors.toList());
-        assertThat(secondTable.getRows()
-                           .stream()
-                           .allMatch(row -> row.stream()
-                                   .map(Cell::getHeaderCells)
-                                   .toList().equals(firstTableHeaderCells))).isTrue();
+        List<List<Cell>> firstTableHeaderCells = firstTable.getRows().get(0).stream().map(Collections::singletonList).collect(Collectors.toList());
+        assertThat(secondTable.getRows().stream().allMatch(row -> row.stream().map(Cell::getHeaderCells).toList().equals(firstTableHeaderCells))).isTrue();
     }
 
 
@@ -225,37 +184,15 @@ public class PdfSegmentationServiceTest extends AbstractTest {
         ClassPathResource pdfFileResource = new ClassPathResource("files/Minimal Examples/Merge Multi Page Table.pdf");
 
         ClassificationDocument document = buildClassificationDocument(pdfFileResource.getFile());
-        assertThat(document.getSections()
-                           .stream()
-                           .flatMap(paragraph -> paragraph.getTables()
-                                   .stream())
-                           .collect(Collectors.toList())).isNotEmpty();
-        TablePageBlock firstTable = document.getSections()
-                .stream()
-                .flatMap(paragraph -> paragraph.getTables()
-                        .stream())
-                .toList()
-                .get(0);
+        assertThat(document.getSections().stream().flatMap(paragraph -> paragraph.getTables().stream()).collect(Collectors.toList())).isNotEmpty();
+        TablePageBlock firstTable = document.getSections().stream().flatMap(paragraph -> paragraph.getTables().stream()).toList().get(0);
         assertThat(firstTable.getColCount()).isEqualTo(9);
         assertThat(firstTable.getRowCount()).isEqualTo(5);
-        TablePageBlock secondTable = document.getSections()
-                .stream()
-                .flatMap(paragraph -> paragraph.getTables()
-                        .stream())
-                .toList()
-                .get(1);
+        TablePageBlock secondTable = document.getSections().stream().flatMap(paragraph -> paragraph.getTables().stream()).toList().get(1);
         assertThat(secondTable.getColCount()).isEqualTo(9);
         assertThat(secondTable.getRowCount()).isEqualTo(6);
-        List<List<Cell>> firstTableHeaderCells = firstTable.getRows()
-                .get(firstTable.getRowCount() - 1)
-                .stream()
-                .map(Cell::getHeaderCells)
-                .collect(Collectors.toList());
-        assertThat(secondTable.getRows()
-                           .stream()
-                           .allMatch(row -> row.stream()
-                                   .map(Cell::getHeaderCells)
-                                   .toList().equals(firstTableHeaderCells))).isTrue();
+        List<List<Cell>> firstTableHeaderCells = firstTable.getRows().get(firstTable.getRowCount() - 1).stream().map(Cell::getHeaderCells).collect(Collectors.toList());
+        assertThat(secondTable.getRows().stream().allMatch(row -> row.stream().map(Cell::getHeaderCells).toList().equals(firstTableHeaderCells))).isTrue();
     }
 
 
@@ -265,37 +202,15 @@ public class PdfSegmentationServiceTest extends AbstractTest {
         ClassPathResource pdfFileResource = new ClassPathResource("files/Minimal Examples/Rotated Table Headers.pdf");
 
         ClassificationDocument document = buildClassificationDocument(pdfFileResource.getFile());
-        assertThat(document.getSections()
-                           .stream()
-                           .flatMap(paragraph -> paragraph.getTables()
-                                   .stream())
-                           .collect(Collectors.toList())).isNotEmpty();
-        TablePageBlock firstTable = document.getSections()
-                .stream()
-                .flatMap(paragraph -> paragraph.getTables()
-                        .stream())
-                .toList()
-                .get(0);
+        assertThat(document.getSections().stream().flatMap(paragraph -> paragraph.getTables().stream()).collect(Collectors.toList())).isNotEmpty();
+        TablePageBlock firstTable = document.getSections().stream().flatMap(paragraph -> paragraph.getTables().stream()).toList().get(0);
         assertThat(firstTable.getColCount()).isEqualTo(8);
         assertThat(firstTable.getRowCount()).isEqualTo(1);
-        TablePageBlock secondTable = document.getSections()
-                .stream()
-                .flatMap(paragraph -> paragraph.getTables()
-                        .stream())
-                .toList()
-                .get(1);
+        TablePageBlock secondTable = document.getSections().stream().flatMap(paragraph -> paragraph.getTables().stream()).toList().get(1);
         assertThat(secondTable.getColCount()).isEqualTo(8);
         assertThat(secondTable.getRowCount()).isEqualTo(6);
-        List<List<Cell>> firstTableHeaderCells = firstTable.getRows()
-                .get(0)
-                .stream()
-                .map(Collections::singletonList)
-                .collect(Collectors.toList());
-        assertThat(secondTable.getRows()
-                           .stream()
-                           .allMatch(row -> row.stream()
-                                   .map(Cell::getHeaderCells)
-                                   .toList().equals(firstTableHeaderCells))).isTrue();
+        List<List<Cell>> firstTableHeaderCells = firstTable.getRows().get(0).stream().map(Collections::singletonList).collect(Collectors.toList());
+        assertThat(secondTable.getRows().stream().allMatch(row -> row.stream().map(Cell::getHeaderCells).toList().equals(firstTableHeaderCells))).isTrue();
     }
 
 
@@ -345,30 +260,29 @@ public class PdfSegmentationServiceTest extends AbstractTest {
         validateTable(document, 0, 8, 8, 0, 0);
 
         List<List<String>> values = Arrays.asList(Arrays.asList("Annex point Reference within DAR/RAR",
-                                                                "Author, date",
-                                                                "Study title",
-                                                                "Analytical method Author, date, No.",
-                                                                "Technique, LOQ of the method, validated working range",
-                                                                "Method meets analytical validation criteria",
-                                                                "Remarks (in case validation criteria are not met)",
-                                                                "Acceptability of the method"),
-                                                  Arrays.asList(
-                                                          "Part (a) Methods in soil, water, sediment, air and any additional matrices used in support of environmental fate studies",
-                                                          "Part (a) Methods in soil, water, sediment, air and any additional matrices used in support of environmental fate studies",
-                                                          "Part (a) Methods in soil, water, sediment, air and any additional matrices used in support of environmental fate studies",
-                                                          "Part (a) Methods in soil, water, sediment, air and any additional matrices used in support of environmental fate studies",
-                                                          "Part (a) Methods in soil, water, sediment, air and any additional matrices used in support of environmental fate studies",
-                                                          "Part (a) Methods in soil, water, sediment, air and any additional matrices used in support of environmental fate studies",
-                                                          "Part (a) Methods in soil, water, sediment, air and any additional matrices used in support of environmental fate studies",
-                                                          "Part (a) Methods in soil, water, sediment, air and any additional matrices used in support of environmental fate studies"),
-                                                  Arrays.asList("CA 7.1.2.1.1 DAR (2009)",
-                                                                "Evans P.G. 2001 TMJ4569B, VV-323245",
-                                                                "Azoxystrobin Laboratory Degradation Study in Three Soil Types, Sampled from Holland and the United Kingdom",
-                                                                "Method: RAM 269 Johnson R.I., Tummon O.J., Earl M. 1995 RJ1864B, VV-377731 Johnson R.I., Tummon O.J., Earl M. 1998 RAM 269/02, VV-124072 Johnson R.I., Tummon O.J., Earl M. 2000 RAM 269/03, VV-123986 Validation: Robinson N.J. 2001 TMJ4617B, VV-895845",
-                                                                "LC-MS/MS LOQ: 0.01 mg/kg (R401553 (SYN50165 7), R402173 (SYN501114 )) or 0.02 mg/kg (azoxystrobin, R230310, R234886) Working range: 0.02-1.0 or 0.01-0.5 mg/kg (depending on analyte) Other supporting quantificati on methods: HPLC-UV GC-MSD",
-                                                                "Y",
-                                                                "N/A",
-                                                                "Y"));
+                        "Author, date",
+                        "Study title",
+                        "Analytical method Author, date, No.",
+                        "Technique, LOQ of the method, validated working range",
+                        "Method meets analytical validation criteria",
+                        "Remarks (in case validation criteria are not met)",
+                        "Acceptability of the method"),
+                Arrays.asList("Part (a) Methods in soil, water, sediment, air and any additional matrices used in support of environmental fate studies",
+                        "Part (a) Methods in soil, water, sediment, air and any additional matrices used in support of environmental fate studies",
+                        "Part (a) Methods in soil, water, sediment, air and any additional matrices used in support of environmental fate studies",
+                        "Part (a) Methods in soil, water, sediment, air and any additional matrices used in support of environmental fate studies",
+                        "Part (a) Methods in soil, water, sediment, air and any additional matrices used in support of environmental fate studies",
+                        "Part (a) Methods in soil, water, sediment, air and any additional matrices used in support of environmental fate studies",
+                        "Part (a) Methods in soil, water, sediment, air and any additional matrices used in support of environmental fate studies",
+                        "Part (a) Methods in soil, water, sediment, air and any additional matrices used in support of environmental fate studies"),
+                Arrays.asList("CA 7.1.2.1.1 DAR (2009)",
+                        "Evans P.G. 2001 TMJ4569B, VV-323245",
+                        "Azoxystrobin Laboratory Degradation Study in Three Soil Types, Sampled from Holland and the United Kingdom",
+                        "Method: RAM 269 Johnson R.I., Tummon O.J., Earl M. 1995 RJ1864B, VV-377731 Johnson R.I., Tummon O.J., Earl M. 1998 RAM 269/02, VV-124072 Johnson R.I., Tummon O.J., Earl M. 2000 RAM 269/03, VV-123986 Validation: Robinson N.J. 2001 TMJ4617B, VV-895845",
+                        "LC-MS/MS LOQ: 0.01 mg/kg (R401553 (SYN50165 7), R402173 (SYN501114 )) or 0.02 mg/kg (azoxystrobin, R230310, R234886) Working range: 0.02-1.0 or 0.01-0.5 mg/kg (depending on analyte) Other supporting quantificati on methods: HPLC-UV GC-MSD",
+                        "Y",
+                        "N/A",
+                        "Y"));
 
         validateTable(document, 0, values);
 
@@ -757,11 +671,7 @@ public class PdfSegmentationServiceTest extends AbstractTest {
     @SneakyThrows
     private void toHtml(ClassificationDocument document, String filename) {
 
-        var tables = document.getSections()
-                .stream()
-                .flatMap(paragraph -> paragraph.getTables()
-                        .stream())
-                .toList();
+        var tables = document.getSections().stream().flatMap(paragraph -> paragraph.getTables().stream()).toList();
         StringBuilder sb = new StringBuilder();
 
         int currentPage = 1;
@@ -782,19 +692,9 @@ public class PdfSegmentationServiceTest extends AbstractTest {
 
     private void validateTable(ClassificationDocument document, int tableIndex, int colCount, int rowCount, int emptyCellsCountCorrect, int emptyCellsCountIncorrect) {
 
-        TablePageBlock table = document.getSections()
-                .stream()
-                .flatMap(paragraph -> paragraph.getTables()
-                        .stream())
-                .toList()
-                .get(tableIndex);
+        TablePageBlock table = document.getSections().stream().flatMap(paragraph -> paragraph.getTables().stream()).toList().get(tableIndex);
         List<List<Cell>> rows = table.getRows();
-        int emptyCellsFoundFound = rows.stream()
-                .flatMap(List::stream)
-                .toList()
-                .stream()
-                .filter(f -> f.toString().isEmpty())
-                .toList().size();
+        int emptyCellsFoundFound = rows.stream().flatMap(List::stream).toList().stream().filter(f -> f.toString().isEmpty()).toList().size();
 
         for (List<Cell> row : table.getRows()) {
             row.forEach(r -> System.out.println(r.toString()));
@@ -809,20 +709,11 @@ public class PdfSegmentationServiceTest extends AbstractTest {
 
     private void validateTable(ClassificationDocument document, int tableIndex, List<List<String>> values) {
 
-        TablePageBlock table = document.getSections()
-                .stream()
-                .flatMap(paragraph -> paragraph.getTables()
-                        .stream())
-                .toList()
-                .get(tableIndex);
+        TablePageBlock table = document.getSections().stream().flatMap(paragraph -> paragraph.getTables().stream()).toList().get(tableIndex);
         List<List<Cell>> rows = table.getRows();
 
-        List<Cell> rowsFlattened = rows.stream()
-                .flatMap(List::stream)
-                .toList();
-        List<String> valuesFlattened = values.stream()
-                .flatMap(List::stream)
-                .toList();
+        List<Cell> rowsFlattened = rows.stream().flatMap(List::stream).toList();
+        List<String> valuesFlattened = values.stream().flatMap(List::stream).toList();
 
         for (int i = 0; i < valuesFlattened.size(); i++) {
             Cell cell = rowsFlattened.get(i);
@@ -835,11 +726,7 @@ public class PdfSegmentationServiceTest extends AbstractTest {
 
     private void validateTableSize(ClassificationDocument document, int tableSize) {
 
-        assertThat(document.getSections()
-                           .stream()
-                           .flatMap(paragraph -> paragraph.getTables()
-                                   .stream())
-                           .toList().size()).isEqualTo(tableSize);
+        assertThat(document.getSections().stream().flatMap(paragraph -> paragraph.getTables().stream()).toList().size()).isEqualTo(tableSize);
 
     }
 

layoutparser-service/layoutparser-service-server/src/test/java/com/knecon/fforesight/service/layoutparser/server/services/RulingCleaningServiceTest.java

@@ -74,7 +74,7 @@ public class RulingCleaningServiceTest extends BuildDocumentTest {
             cleanRulingsPerPage.add(rulingCleaningService.getCleanRulings(Collections.emptyList(), pageContent.getRulings()));
         }
         var cleanRulings = cleanRulingsPerPage.stream().map(CleanRulings::getVertical).collect(Collectors.toList());
-        PdfDraw.drawLinesPerPage(fileName,  cleanRulings, lineFileName);
+        PdfDraw.drawLinesPerPage(fileName, cleanRulings, lineFileName);
 
     }
 
@@ -99,13 +99,13 @@ public class RulingCleaningServiceTest extends BuildDocumentTest {
     @SneakyThrows
     private void writeJsons(Path filename) {
 
-        Document documentGraphBefore = DocumentGraphFactory.buildDocumentGraph(layoutParsingPipeline.parseLayout(LayoutParsingType.REDACT_MANAGER,
+        Document documentGraphBefore = DocumentGraphFactory.buildDocumentGraph(layoutParsingPipeline.parseLayout(LayoutParsingType.REDACT_MANAGER_OLD,
                 filename.toFile(),
                 new ImageServiceResponse(),
                 new TableServiceResponse(),
                 new VisualLayoutParsingResponse(),
                 filename.toFile().toString()));
-        Document documentGraphAfter = DocumentGraphFactory.buildDocumentGraph(layoutParsingPipeline.parseLayout(LayoutParsingType.REDACT_MANAGER,
+        Document documentGraphAfter = DocumentGraphFactory.buildDocumentGraph(layoutParsingPipeline.parseLayout(LayoutParsingType.REDACT_MANAGER_OLD,
                 filename.toFile(),
                 new ImageServiceResponse(),
                 new TableServiceResponse(),

layoutparser-service/layoutparser-service-server/src/test/java/com/knecon/fforesight/service/layoutparser/server/utils/AbstractTest.java

@@ -20,7 +20,6 @@ import org.springframework.context.annotation.Import;
 import org.springframework.context.annotation.Primary;
 import org.springframework.core.io.ClassPathResource;
 import org.springframework.test.context.junit.jupiter.SpringExtension;
-import org.xmlunit.builder.Input;
 
 import com.iqser.red.commons.jackson.ObjectMapperFactory;
 import com.iqser.red.storage.commons.service.StorageService;
@@ -68,7 +67,7 @@ public abstract class AbstractTest {
     protected LayoutParsingRequest buildStandardLayoutParsingRequest() {
 
         return LayoutParsingRequest.builder()
-                .layoutParsingType(LayoutParsingType.REDACT_MANAGER)
+                .layoutParsingType(LayoutParsingType.REDACT_MANAGER_OLD)
                 .originFileStorageId(ORIGIN_FILE_ID)
                 .tablesFileStorageId(Optional.of(TABLE_FILE_ID))
                 .imagesFileStorageId(Optional.of(IMAGE_FILE_ID))
@@ -99,7 +98,7 @@ public abstract class AbstractTest {
     @SneakyThrows
     protected LayoutParsingRequest prepareStorage(String file) {
 
-        return prepareStorage(file, "cv_table_parsing_response/empty.json", "image_service_response/empty.json","visual_layout_parsing_response/empty.json");
+        return prepareStorage(file, "cv_table_parsing_response/empty.json", "image_service_response/empty.json", "visual_layout_parsing_response/empty.json");
     }
 
 
@@ -107,7 +106,7 @@ public abstract class AbstractTest {
     protected LayoutParsingRequest prepareStorage(InputStream fileInputStream) {
 
         storageService.storeObject(TenantContext.getTenantId(), ORIGIN_FILE_ID, fileInputStream);
-        return buildDefaultLayoutParsingRequest(LayoutParsingType.REDACT_MANAGER);
+        return buildDefaultLayoutParsingRequest(LayoutParsingType.REDACT_MANAGER_OLD);
     }
 
 
@@ -140,6 +139,7 @@ public abstract class AbstractTest {
         return prepareStorage(pdfFileResource.getInputStream(), cvServiceResponseFileResource.getInputStream(), imageInfoFileResource.getInputStream());
     }
 
+
     @SneakyThrows
     protected LayoutParsingRequest prepareStorage(String file, String cvServiceResponseFile, String imageInfoFile, String visualLayoutParsingResponseFile) {
 
@@ -148,9 +148,13 @@ public abstract class AbstractTest {
         ClassPathResource imageInfoFileResource = new ClassPathResource(imageInfoFile);
         ClassPathResource visualLayoutParsingResponseResource = new ClassPathResource(visualLayoutParsingResponseFile);
 
-        return prepareStorage(pdfFileResource.getInputStream(), cvServiceResponseFileResource.getInputStream(), imageInfoFileResource.getInputStream(), visualLayoutParsingResponseResource.getInputStream());
+        return prepareStorage(pdfFileResource.getInputStream(),
+                cvServiceResponseFileResource.getInputStream(),
+                imageInfoFileResource.getInputStream(),
+                visualLayoutParsingResponseResource.getInputStream());
     }
 
+
     @SneakyThrows
     protected LayoutParsingRequest prepareStorage(InputStream fileStream, InputStream cvServiceResponseFileStream, InputStream imageInfoStream) {
 
@@ -158,18 +162,22 @@ public abstract class AbstractTest {
         storageService.storeObject(TenantContext.getTenantId(), TABLE_FILE_ID, cvServiceResponseFileStream);
         storageService.storeObject(TenantContext.getTenantId(), ORIGIN_FILE_ID, fileStream);
 
-        return buildDefaultLayoutParsingRequest(LayoutParsingType.REDACT_MANAGER);
+        return buildDefaultLayoutParsingRequest(LayoutParsingType.REDACT_MANAGER_OLD);
     }
 
+
     @SneakyThrows
-    protected LayoutParsingRequest prepareStorage(InputStream fileStream, InputStream cvServiceResponseFileStream, InputStream imageInfoStream, InputStream visualLayoutParsingResponseFileStream) {
+    protected LayoutParsingRequest prepareStorage(InputStream fileStream,
+                                                  InputStream cvServiceResponseFileStream,
+                                                  InputStream imageInfoStream,
+                                                  InputStream visualLayoutParsingResponseFileStream) {
 
         storageService.storeObject(TenantContext.getTenantId(), IMAGE_FILE_ID, imageInfoStream);
         storageService.storeObject(TenantContext.getTenantId(), TABLE_FILE_ID, cvServiceResponseFileStream);
         storageService.storeObject(TenantContext.getTenantId(), ORIGIN_FILE_ID, fileStream);
-        storageService.storeObject(TenantContext.getTenantId(),VISUAL_LAYOUT_FILE,visualLayoutParsingResponseFileStream );
+        storageService.storeObject(TenantContext.getTenantId(), VISUAL_LAYOUT_FILE, visualLayoutParsingResponseFileStream);
 
-        return buildDefaultLayoutParsingRequest(LayoutParsingType.REDACT_MANAGER);
+        return buildDefaultLayoutParsingRequest(LayoutParsingType.REDACT_MANAGER_OLD);
     }
 
 

layoutparser-service/layoutparser-service-server/src/test/java/com/knecon/fforesight/service/layoutparser/server/utils/BuildDocumentTest.java

@@ -38,7 +38,7 @@ public abstract class BuildDocumentTest extends AbstractTest {
     @SneakyThrows
     protected Document buildGraph(String filename) {
 
-        return buildGraph(filename, LayoutParsingType.REDACT_MANAGER);
+        return buildGraph(filename, LayoutParsingType.REDACT_MANAGER_OLD);
     }