RED-7461: First working iteration of header and footer improvement

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

@@ -11,6 +11,7 @@ import java.util.Map;
 import org.apache.pdfbox.pdmodel.PDDocument;
 import org.apache.pdfbox.pdmodel.PDPage;
 import org.apache.pdfbox.pdmodel.common.PDRectangle;
+import org.apache.pdfbox.text.PDFMarkedContentExtractor;
 import org.springframework.stereotype.Service;
 
 import com.knecon.fforesight.service.layoutparser.internal.api.queue.LayoutParsingFinishedEvent;
@@ -172,6 +173,7 @@ public class LayoutParsingPipeline {
             classificationPage.setPageNumber(pageNumber);
             classificationPage.setPageWidth(cropbox.getWidth());
             classificationPage.setPageHeight(cropbox.getHeight());
+            classificationPage.setMarkedContents(stripper.getMarkedContents());
 
             // If images is ocr needs to be calculated before textBlocks are moved into tables, otherwise findOcr algorithm needs to be adopted.
             if (pdfImages != null && pdfImages.containsKey(pageNumber)) {

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

@@ -11,6 +11,7 @@ import com.knecon.fforesight.service.layoutparser.processor.model.text.StringFre
 import lombok.Data;
 import lombok.NonNull;
 import lombok.RequiredArgsConstructor;
+import org.apache.pdfbox.pdmodel.documentinterchange.markedcontent.PDMarkedContent;
 
 @Data
 @RequiredArgsConstructor
@@ -38,4 +39,6 @@ public class ClassificationPage {
 
     CleanRulings cleanRulings;
 
+    private List<PDMarkedContent> markedContents;
+
 }

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

@@ -1,7 +1,18 @@
 package com.knecon.fforesight.service.layoutparser.processor.services;
 
+import java.awt.geom.Rectangle2D;
+import java.util.ArrayList;
+import java.util.Collection;
 import java.util.List;
+import java.util.Optional;
+import java.util.stream.Collectors;
 
+import com.knecon.fforesight.service.layoutparser.processor.model.text.TextPositionSequence;
+import com.knecon.fforesight.service.layoutparser.processor.utils.RectangleTransformations;
+import org.apache.pdfbox.cos.COSArray;
+import org.apache.pdfbox.cos.COSName;
+import org.apache.pdfbox.pdmodel.documentinterchange.markedcontent.PDMarkedContent;
+import org.apache.pdfbox.text.TextPosition;
 import org.springframework.stereotype.Service;
 
 import com.iqser.red.service.persistence.service.v1.api.shared.model.redactionlog.Point;
@@ -20,17 +31,80 @@ import com.knecon.fforesight.service.layoutparser.processor.utils.PositionUtils;
 public class BodyTextFrameService {
 
 
-
     public void setBodyTextFrames(ClassificationDocument classificationDocument, LayoutParsingType layoutParsingType) {
 
         Rectangle bodyTextFrame = calculateBodyTextFrame(classificationDocument.getPages(), classificationDocument.getFontSizeCounter(), false, layoutParsingType);
         Rectangle landscapeBodyTextFrame = calculateBodyTextFrame(classificationDocument.getPages(), classificationDocument.getFontSizeCounter(), true, layoutParsingType);
         for (ClassificationPage page : classificationDocument.getPages()) {
-            setBodyTextFrameAdjustedToPage(page, bodyTextFrame, landscapeBodyTextFrame);
+
+            var markupHeaderBBoxes = getMarkupRectangleByTextPositions(page, "Header");
+            var markupFooterBBoxes = getMarkupRectangleByTextPositions(page, "Footer");
+
+            if(markupHeaderBBoxes.isEmpty() && markupFooterBBoxes.isEmpty()){
+                setBodyTextFrameAdjustedToPage(page, bodyTextFrame, landscapeBodyTextFrame);
+            } else {
+
+                double minHeader = page.getPageHeight();
+                if(!markupHeaderBBoxes.isEmpty()) {
+                    minHeader = RectangleTransformations.rectangle2DBBox(markupHeaderBBoxes).getMinY();
+                }
+
+                double maxFooter = 0;
+                if(!markupFooterBBoxes.isEmpty()) {
+                    maxFooter = RectangleTransformations.rectangle2DBBox(markupFooterBBoxes).getMaxY();
+                }
+
+                var btf = new Rectangle(new Point(0f, (float)maxFooter), page.getPageWidth(), ((float)minHeader) - ((float)maxFooter), page.getPageNumber());
+                page.setBodyTextFrame(btf);
+            }
         }
     }
 
 
+    private List<Rectangle2D> getMarkupRectangle(ClassificationPage page, String subtype) {
+        if (page.getMarkedContents() == null) {
+            return new ArrayList<>();
+        }
+
+        return page.getMarkedContents().stream()
+                .filter(m -> m.getTag().equals("Artifact"))
+                .map(PDMarkedContent::getProperties)
+                .filter(p -> p.getItem("Subtype") != null)
+                .filter(p -> ((COSName) p.getItem("Subtype")).getName().equals(subtype))
+                .filter(c -> c.getItem("BBox") != null)
+                .map(c -> c.getItem("BBox"))
+                .map(c -> ((COSArray) c).toFloatArray())
+                .map(f -> new Rectangle2D.Float(f[0], f[1], f[2] - f[0], f[3] - f[1]))
+                .collect(Collectors.toList());
+    }
+
+
+    private List<Rectangle2D> getMarkupRectangleByTextPositions(ClassificationPage page, String subtype) {
+        if (page.getMarkedContents() == null) {
+            return new ArrayList<>();
+        }
+
+        var markedContent = page.getMarkedContents().stream()
+                .filter(m -> m.getTag().equals("Artifact"))
+                .filter(m -> m.getProperties().getItem("Subtype") != null)
+                .filter(m -> ((COSName) m.getProperties().getItem("Subtype")).getName().equals(subtype))
+                .map(m -> m.getContents()).flatMap(Collection::stream)
+                .map(t -> (TextPosition) t)
+                .collect(Collectors.groupingBy(t -> t.getY()));
+
+        if (markedContent.isEmpty()) {
+            return new ArrayList<>();
+        }
+
+       return markedContent.entrySet().stream()
+                .map(e -> new TextPositionSequence(e.getValue().stream()
+                        .toList(), page.getPageNumber(), true)
+                        .getRectangle())
+                .map(t -> new Rectangle2D.Float(t.getTopLeft().getX(), t.getTopLeft().getY() - Math.abs(t.getHeight()), t.getWidth(), Math.abs(t.getHeight()))).collect(Collectors.toList());
+    }
+
+
+
 /*
     private Rectangle calculateBodyTextFrameByRulings(List<ClassificationPage> pages) {
 

layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/services/classification/DocuMineClassificationService.java

@@ -62,12 +62,10 @@ public class DocuMineClassificationService {
             textBlock.setClassification(PageBlockType.OTHER);
             return;
         }
-        if (PositionUtils.isOverBodyTextFrame(bodyTextFrame, textBlock, page.getRotation()) && (document.getFontSizeCounter()
+        if (PositionUtils.isOverBodyTextFrame(bodyTextFrame, textBlock, page.getRotation())) {
-                .getMostPopular() == null || textBlock.getHighestFontSize() <= document.getFontSizeCounter().getMostPopular())) {
             textBlock.setClassification(PageBlockType.HEADER);
 
-        } else if (PositionUtils.isUnderBodyTextFrame(bodyTextFrame, textBlock, page.getRotation()) && (document.getFontSizeCounter()
+        } else if (PositionUtils.isUnderBodyTextFrame(bodyTextFrame, textBlock, page.getRotation())) {
-                .getMostPopular() == null || textBlock.getHighestFontSize() <= document.getFontSizeCounter().getMostPopular())) {
             textBlock.setClassification(PageBlockType.FOOTER);
         } else if (page.getPageNumber() == 1 && (PositionUtils.getHeightDifferenceBetweenChunkWordAndDocumentWord(textBlock,
                 document.getTextHeightCounter().getMostPopular()) > 2.5 && textBlock.getHighestFontSize() > document.getFontSizeCounter().getMostPopular() || page.getTextBlocks()

layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/services/parsing/PDFLinesTextStripper.java

@@ -1,33 +1,19 @@
 package com.knecon.fforesight.service.layoutparser.processor.services.parsing;
 
-import java.awt.color.CMMException;
+import com.knecon.fforesight.service.layoutparser.processor.model.table.Ruling;
-import java.awt.geom.Point2D;
+import com.knecon.fforesight.service.layoutparser.processor.model.text.RedTextPosition;
-import java.io.IOException;
+import com.knecon.fforesight.service.layoutparser.processor.model.text.TextPositionSequence;
-import java.util.ArrayList;
+import lombok.Getter;
-import java.util.Arrays;
+import lombok.Setter;
-import java.util.List;
+import lombok.SneakyThrows;
-
+import lombok.extern.slf4j.Slf4j;
 import org.apache.pdfbox.contentstream.operator.Operator;
 import org.apache.pdfbox.contentstream.operator.OperatorName;
-import org.apache.pdfbox.contentstream.operator.color.SetNonStrokingColor;
+import org.apache.pdfbox.contentstream.operator.color.*;
-import org.apache.pdfbox.contentstream.operator.color.SetNonStrokingColorN;
+import org.apache.pdfbox.contentstream.operator.markedcontent.BeginMarkedContentSequence;
-import org.apache.pdfbox.contentstream.operator.color.SetNonStrokingColorSpace;
+import org.apache.pdfbox.contentstream.operator.markedcontent.BeginMarkedContentSequenceWithProperties;
-import org.apache.pdfbox.contentstream.operator.color.SetNonStrokingDeviceCMYKColor;
+import org.apache.pdfbox.contentstream.operator.markedcontent.EndMarkedContentSequence;
-import org.apache.pdfbox.contentstream.operator.color.SetNonStrokingDeviceGrayColor;
+import org.apache.pdfbox.contentstream.operator.state.*;
-import org.apache.pdfbox.contentstream.operator.color.SetNonStrokingDeviceRGBColor;
-import org.apache.pdfbox.contentstream.operator.color.SetStrokingColor;
-import org.apache.pdfbox.contentstream.operator.color.SetStrokingColorN;
-import org.apache.pdfbox.contentstream.operator.color.SetStrokingColorSpace;
-import org.apache.pdfbox.contentstream.operator.color.SetStrokingDeviceCMYKColor;
-import org.apache.pdfbox.contentstream.operator.color.SetStrokingDeviceGrayColor;
-import org.apache.pdfbox.contentstream.operator.color.SetStrokingDeviceRGBColor;
-import org.apache.pdfbox.contentstream.operator.state.SetFlatness;
-import org.apache.pdfbox.contentstream.operator.state.SetLineCapStyle;
-import org.apache.pdfbox.contentstream.operator.state.SetLineDashPattern;
-import org.apache.pdfbox.contentstream.operator.state.SetLineJoinStyle;
-import org.apache.pdfbox.contentstream.operator.state.SetLineMiterLimit;
-import org.apache.pdfbox.contentstream.operator.state.SetLineWidth;
-import org.apache.pdfbox.contentstream.operator.state.SetRenderingIntent;
 import org.apache.pdfbox.contentstream.operator.text.SetFontAndSize;
 import org.apache.pdfbox.cos.COSBase;
 import org.apache.pdfbox.cos.COSNumber;
@@ -36,14 +22,11 @@ import org.apache.pdfbox.pdmodel.PDPage;
 import org.apache.pdfbox.pdmodel.graphics.color.PDColor;
 import org.apache.pdfbox.text.TextPosition;
 
-import com.knecon.fforesight.service.layoutparser.processor.model.table.Ruling;
+import java.awt.color.CMMException;
-import com.knecon.fforesight.service.layoutparser.processor.model.text.RedTextPosition;
+import java.awt.geom.Point2D;
-import com.knecon.fforesight.service.layoutparser.processor.model.text.TextPositionSequence;
+import java.io.IOException;
-
+import java.util.ArrayList;
-import lombok.Getter;
+import java.util.List;
-import lombok.Setter;
-import lombok.SneakyThrows;
-import lombok.extern.slf4j.Slf4j;
 
 @Getter
 @Slf4j
@@ -59,6 +42,7 @@ public class PDFLinesTextStripper extends PDFTextStripper {
     private int minCharHeight;
     private int maxCharHeight;
 
+
     private float path_x;
     private float path_y;
 
@@ -89,9 +73,17 @@ public class PDFLinesTextStripper extends PDFTextStripper {
         this.addOperator(new SetNonStrokingColorN());
         this.addOperator(new SetFontAndSize());
         this.addOperator(new SetLineWidth());
+
+
+        addOperator(new BeginMarkedContentSequenceWithProperties());
+        addOperator(new BeginMarkedContentSequence());
+        addOperator(new EndMarkedContentSequence());
+
     }
 
 
+
+
     @Override
     protected void processOperator(Operator operator, List<COSBase> arguments) throws IOException {
 
@@ -99,6 +91,7 @@ public class PDFLinesTextStripper extends PDFTextStripper {
 
         //move
         switch (operation) {
+
             case OperatorName.MOVE_TO:
                 if (arguments.size() == 2) {
                     Point2D.Float pos = transformPosition(floatValue(arguments.get(0)), floatValue(arguments.get(1)));
@@ -349,3 +342,4 @@ public class PDFLinesTextStripper extends PDFTextStripper {
 
 }
 
+

layoutparser-service/layoutparser-service-processor/src/main/java/com/knecon/fforesight/service/layoutparser/processor/services/parsing/PDFTextStripper.java

@@ -25,27 +25,20 @@ import java.io.StringWriter;
 import java.io.Writer;
 import java.text.Bidi;
 import java.text.Normalizer;
-import java.util.ArrayList;
+import java.util.*;
-import java.util.Collections;
-import java.util.Comparator;
-import java.util.HashMap;
-import java.util.Iterator;
-import java.util.LinkedList;
-import java.util.List;
-import java.util.Map;
-import java.util.SortedMap;
-import java.util.SortedSet;
-import java.util.StringTokenizer;
-import java.util.TreeMap;
-import java.util.TreeSet;
 import java.util.regex.Pattern;
 
+import lombok.Getter;
 import org.apache.commons.logging.Log;
 import org.apache.commons.logging.LogFactory;
+import org.apache.pdfbox.cos.COSDictionary;
+import org.apache.pdfbox.cos.COSName;
 import org.apache.pdfbox.pdmodel.PDDocument;
 import org.apache.pdfbox.pdmodel.PDPage;
 import org.apache.pdfbox.pdmodel.PDPageTree;
 import org.apache.pdfbox.pdmodel.common.PDRectangle;
+import org.apache.pdfbox.pdmodel.documentinterchange.markedcontent.PDMarkedContent;
+import org.apache.pdfbox.pdmodel.graphics.PDXObject;
 import org.apache.pdfbox.pdmodel.interactive.documentnavigation.outline.PDOutlineItem;
 import org.apache.pdfbox.pdmodel.interactive.pagenavigation.PDThreadBead;
 import org.apache.pdfbox.text.TextPosition;
@@ -63,6 +56,10 @@ public class PDFTextStripper extends LegacyPDFStreamEngine {
     private static float defaultDropThreshold = 2.5f;
     private static final boolean useCustomQuickSort;
 
+    @Getter
+    protected final List<PDMarkedContent> markedContents = new ArrayList<>();
+    protected final Deque<PDMarkedContent> currentMarkedContents = new ArrayDeque<>();
+
     private static final Log LOG = LogFactory.getLog(PDFTextStripper.class);
 
     // enable the ability to set the default indent/drop thresholds
@@ -196,6 +193,45 @@ public class PDFTextStripper extends LegacyPDFStreamEngine {
     }
 
 
+
+    public void beginMarkedContentSequence(COSName tag, COSDictionary properties)
+    {
+        PDMarkedContent markedContent = PDMarkedContent.create(tag, properties);
+        if (this.currentMarkedContents.isEmpty())
+        {
+            this.markedContents.add(markedContent);
+        }
+        else
+        {
+            PDMarkedContent currentMarkedContent =
+                    this.currentMarkedContents.peek();
+            if (currentMarkedContent != null)
+            {
+                currentMarkedContent.addMarkedContent(markedContent);
+            }
+        }
+        this.currentMarkedContents.push(markedContent);
+    }
+
+    @Override
+    public void endMarkedContentSequence()
+    {
+        if (!this.currentMarkedContents.isEmpty())
+        {
+            this.currentMarkedContents.pop();
+        }
+    }
+
+
+    public void xobject(PDXObject xobject)
+    {
+        if (!this.currentMarkedContents.isEmpty())
+        {
+            this.currentMarkedContents.peek().addXObject(xobject);
+        }
+    }
+
+
     /**
      * This will return the text of a document. See writeText. <br>
      * NOTE: The document must not be encrypted when coming into this method.
@@ -877,7 +913,12 @@ public class PDFTextStripper extends LegacyPDFStreamEngine {
                     textList.add(text);
                 }
             }
+            if (!this.currentMarkedContents.isEmpty())
+            {
+                this.currentMarkedContents.peek().addText(text);
+            }
         }
+
     }
 
 
@@ -2103,6 +2144,7 @@ public class PDFTextStripper extends LegacyPDFStreamEngine {
             this.isHangingIndent = true;
         }
 
+
     }
 
 }

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

@@ -40,7 +40,7 @@ public class BuildDocumentGraphTest extends AbstractTest {
     @SneakyThrows
     protected Document buildGraph(String filename) {
 
-        return buildGraph(filename, LayoutParsingType.REDACT_MANAGER);
+        return buildGraph(filename, LayoutParsingType.DOCUMINE);
     }
 
 

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

@@ -26,7 +26,7 @@ public class DocumentGraphVisualizationTest extends BuildDocumentGraphTest {
 //    @Disabled
     public void visualizeMetolachlor() {
 
-        String filename = "files/S-Metolachlor_RAR_01_Volume_1_2018-09-06.pdf";
+        String filename = "files/SOLICITA_VICTRATO-GOLD-II_Item 21_Mutacao_Genica (4).pdf";
         visualizePdf(filename);
     }
 

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

@@ -22,8 +22,8 @@ public class ViewerDocumentTest extends BuildDocumentGraphTest {
 
         LayoutGridService layoutGridService = new LayoutGridService();
         ViewerDocumentService viewerDocumentService = new ViewerDocumentService(layoutGridService);
-        String fileName = "files/S-Metolachlor_RAR_01_Volume_1_2018-09-06.pdf";
+        String fileName = "files/BASF/2013-1110704.pdf";
-        Document document = buildGraph(fileName, LayoutParsingType.REDACT_MANAGER);
+        Document document = buildGraph(fileName, LayoutParsingType.DOCUMINE);
         String tmpFileName = "/tmp/" + Path.of(fileName).getFileName() + "_VIEWER.pdf";
         try (var pdDocument = Loader.loadPDF(new ClassPathResource(fileName).getInputStream()); var out = new FileOutputStream(tmpFileName)) {
             viewerDocumentService.createViewerDocument(pdDocument, document, out);

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

@@ -4,17 +4,17 @@ import static org.assertj.core.api.Assertions.assertThat;
 
 import java.awt.geom.Rectangle2D;
 import java.io.IOException;
-import java.util.ArrayList;
+import java.util.*;
-import java.util.Arrays;
-import java.util.Collections;
-import java.util.HashMap;
-import java.util.List;
-import java.util.Locale;
-import java.util.Map;
 import java.util.stream.Collectors;
+import java.util.stream.Stream;
 
+import com.knecon.fforesight.service.layoutparser.processor.model.ClassificationPage;
+import com.knecon.fforesight.service.layoutparser.server.utils.visualizations.PdfDraw;
 import org.apache.pdfbox.Loader;
+import org.apache.pdfbox.cos.COSArray;
+import org.apache.pdfbox.cos.COSName;
 import org.apache.pdfbox.pdmodel.PDDocument;
+import org.apache.pdfbox.pdmodel.documentinterchange.markedcontent.PDMarkedContent;
 import org.junit.jupiter.api.Test;
 import org.springframework.beans.factory.annotation.Autowired;
 import org.springframework.core.io.ClassPathResource;
@@ -60,7 +60,7 @@ public class PdfSegmentationServiceTest extends AbstractTest {
 
     public ClassificationDocument buildClassificationDocument(PDDocument originDocument) {
 
-        ClassificationDocument classificationDocument = layoutParsingPipeline.parseLayout(LayoutParsingType.REDACT_MANAGER,
+        ClassificationDocument classificationDocument = layoutParsingPipeline.parseLayout(LayoutParsingType.DOCUMINE,
                 originDocument,
                 new ImageServiceResponse(),
                 new TableServiceResponse());
@@ -492,6 +492,46 @@ public class PdfSegmentationServiceTest extends AbstractTest {
     }
 
 
+    @Test
+    public void testDoc30Page5dfgfdg() throws IOException {
+
+        ClassPathResource pdfFileResource = new ClassPathResource("files/SOLICITA_VICTRATO-GOLD-II_Item 21_Mutacao_Genica (4).pdf");
+
+        ClassificationDocument document = buildClassificationDocument(Loader.loadPDF(pdfFileResource.getInputStream()));
+
+//        validateTableSize(document, 1);
+//
+//        validateTable(document, 0, 3, 5, 0, 0);
+
+
+        var rects = document.getPages().stream().map(page -> Stream.concat(getMarkupRectangle(page, "Footer").stream(),
+                (getMarkupRectangle(page, "Header").stream())).toList()
+                ).toList();
+
+//        var markupHeaderBBoxes = getMarkupRectangle(page, "Header");
+//        var markupFooterBBoxes = getMarkupRectangle(page, "Footer");
+
+       PdfDraw.drawRectanglesPerPage("files/SOLICITA_VICTRATO-GOLD-II_Item 21_Mutacao_Genica (4).pdf",  rects, "/tmp/test.pdf");
+    }
+
+
+    private List<Rectangle2D> getMarkupRectangle(ClassificationPage page, String subtype) {
+        if (page.getMarkedContents() == null) {
+            return new ArrayList<>();
+        }
+
+        return page.getMarkedContents().stream()
+                .filter(m -> m.getTag().equals("Artifact"))
+                .map(PDMarkedContent::getProperties)
+                .filter(p -> p.getItem("Subtype") != null && ((COSName) p.getItem("Subtype")).getName().equals(subtype))
+                .map(c -> c.getItem("BBox"))
+                .map(c -> ((COSArray) c).toFloatArray())
+                .map(f -> new Rectangle2D.Float(f[0], f[1], f[2] -f[0], f[3] - f[1]))
+                .collect(Collectors.toList());
+    }
+
+
+
     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);

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

@@ -17,11 +17,10 @@ import lombok.SneakyThrows;
 class PageContentExtractorTest {
 
     @Test
-    @Disabled
     @SneakyThrows
     public void testTextPositionSequenceExtraction() {
 
-        String fileName = "files/invisible_tables/test-two-pages_ocred.pdf";
+        String fileName = "files/SOLICITA_VICTRATO-GOLD-II_Item 21_Mutacao_Genica (4).pdf";
         var tmpFileName = Path.of("/tmp/").resolve(Path.of(fileName).getFileName() + "_TEXT_POSITION_SEQUENCES.pdf").toString();
 
         List<PageContents> textPositionPerPage = PageContentExtractor.getSortedPageContents(fileName);