[RELEASE] iText pdfSweep 5.0.1

Author: iText-CI

pom.xml

@@ -5,15 +5,16 @@
   <parent>
     <groupId>com.itextpdf</groupId>
     <artifactId>root</artifactId>
-    <version>9.0.0</version>
+    <version>9.1.0</version>
     <relativePath />
   </parent>
 
   <artifactId>cleanup</artifactId>
-  <version>5.0.0</version>
+  <version>5.0.1</version>
 
   <name>pdfSweep</name>
-  <description>Redact PDF documents. If you have to share PDFs with different departments or send them out of house, but they
+  <description>Redact PDF documents. If you have to share PDFs with different departments or send them out of house, but
+    they
     include some confidential, sensitive information which should not be shared, pdfSweep is your solution. Redact a PDF
     containing sensitive, confidential information, such as personal medical information, account numbers, national
     identification numbers, personal details or social security numbers in a reliable and secure way. Data redaction
@@ -31,6 +32,8 @@
 
   <properties>
     <itext.version>${project.parent.version}</itext.version>
+    <sourceFolder>${project.basedir}/src/main/java</sourceFolder>
+    <testSourceFolder>${project.basedir}/src/test/java</testSourceFolder>
   </properties>
 
   <dependencies>
@@ -98,11 +101,53 @@
     </repository>
   </repositories>
 
-  <build>
-    <plugins>
-      <plugin>
-        <artifactId>maven-javadoc-plugin</artifactId>
-      </plugin>
-    </plugins>
-  </build>
+  <profiles>
+    <profile>
+      <id>with-sharpen</id>
+      <build>
+        <plugins>
+          <plugin>
+            <groupId>sharpen</groupId>
+            <artifactId>sharpen-maven-plugin</artifactId>
+            <version>1.0-SNAPSHOT</version>
+            <executions>
+              <execution>
+                <phase>install</phase>
+                <goals>
+                  <goal>sharpen</goal>
+                </goals>
+              </execution>
+            </executions>
+            <dependencies>
+              <dependency>
+                <groupId>sharpen</groupId>
+                <artifactId>standard-framework-mapping</artifactId>
+                <version>1.0-SNAPSHOT</version>
+              </dependency>
+              <dependency>
+                <groupId>com.itextpdf</groupId>
+                <artifactId>cleanup</artifactId>
+                <version>${project.version}</version>
+                <classifier>sharpen-configuration</classifier>
+              </dependency>
+            </dependencies>
+            <configuration>
+              <projectName>cleanup</projectName>
+              <cSharpTargetFolder>./../../sharp/cleanup</cSharpTargetFolder>
+              <cSharpSourceCodeDestination>itext/itext.cleanup</cSharpSourceCodeDestination>
+              <cSharpTestCodeDestination>itext.tests/itext.cleanup.tests</cSharpTestCodeDestination>
+              <buildDotnet>${sharpen.builddotnet}</buildDotnet>
+              <showDiff>${sharpen.showdiff}</showDiff>
+              <sourceCodeFiles>
+                <file>**/src/main/java/**/*.java</file>
+              </sourceCodeFiles>
+              <testCodeFiles>
+                <file>**/src/test/java/**/*.java</file>
+              </testCodeFiles>
+            </configuration>
+          </plugin>
+        </plugins>
+      </build>
+    </profile>
+  </profiles>
 </project>

src/main/java/com/itextpdf/pdfcleanup/CleanUpProperties.java

@@ -1,6 +1,6 @@
 /*
     This file is part of the iText (R) project.
-    Copyright (c) 1998-2024 Apryse Group NV
+    Copyright (c) 1998-2025 Apryse Group NV
     Authors: Apryse Software.
 
     This program is offered under a commercial and under the AGPL license.
@@ -29,7 +29,7 @@ This file is part of the iText (R) project.
  * Contains properties for {@link PdfCleanUpTool} operations.
  */
 public class CleanUpProperties {
-
+//test comment for sharpen
     private IMetaInfo metaInfo;
     private boolean processAnnotations;
     private Double overlapRatio;

src/main/java/com/itextpdf/pdfcleanup/FilteredImagesCache.java

@@ -1,6 +1,6 @@
 /*
     This file is part of the iText (R) project.
-    Copyright (c) 1998-2024 Apryse Group NV
+    Copyright (c) 1998-2025 Apryse Group NV
     Authors: Apryse Software.
 
     This program is offered under a commercial and under the AGPL license.

src/main/java/com/itextpdf/pdfcleanup/LineDashPattern.java

@@ -1,6 +1,6 @@
 /*
     This file is part of the iText (R) project.
-    Copyright (c) 1998-2024 Apryse Group NV
+    Copyright (c) 1998-2025 Apryse Group NV
     Authors: Apryse Software.
 
     This program is offered under a commercial and under the AGPL license.

src/main/java/com/itextpdf/pdfcleanup/PathOffsetApproximationProperties.java

@@ -1,6 +1,6 @@
 /*
     This file is part of the iText (R) project.
-    Copyright (c) 1998-2024 Apryse Group NV
+    Copyright (c) 1998-2025 Apryse Group NV
     Authors: Apryse Software.
 
     This program is offered under a commercial and under the AGPL license.

src/main/java/com/itextpdf/pdfcleanup/PdfCleanUpEventListener.java

@@ -1,6 +1,6 @@
 /*
     This file is part of the iText (R) project.
-    Copyright (c) 1998-2024 Apryse Group NV
+    Copyright (c) 1998-2025 Apryse Group NV
     Authors: Apryse Software.
 
     This program is offered under a commercial and under the AGPL license.

src/main/java/com/itextpdf/pdfcleanup/PdfCleanUpFilter.java

@@ -1,6 +1,6 @@
 /*
     This file is part of the iText (R) project.
-    Copyright (c) 1998-2024 Apryse Group NV
+    Copyright (c) 1998-2025 Apryse Group NV
     Authors: Apryse Software.
 
     This program is offered under a commercial and under the AGPL license.
@@ -22,6 +22,7 @@ This file is part of the iText (R) project.
  */
 package com.itextpdf.pdfcleanup;
 
+import com.itextpdf.commons.datastructures.Tuple2;
 import com.itextpdf.commons.utils.MessageFormatUtil;
 import com.itextpdf.io.font.FontProgram;
 import com.itextpdf.io.image.ImageData;
@@ -225,21 +226,24 @@ private boolean checkIfIntersectionOccurs(Paths paths, Point[] rect1, boolean is
     FilterResult<PdfArray> filterText(TextRenderInfo text) {
         PdfTextArray textArray = new PdfTextArray();
 
-        if (isTextNotToBeCleaned(text)) {
+        // Overlap ratio should not be taken into account when we check the whole text not to be cleaned up
+        if (properties.getOverlapRatio() == null && isTextNotToBeCleaned(text)) {
             return new FilterResult<>(false, new PdfArray(text.getPdfString()));
         }
 
+        boolean isModified = false;
         for (TextRenderInfo ri : text.getCharacterRenderInfos()) {
             if (isTextNotToBeCleaned(ri)) {
                 textArray.add(ri.getPdfString());
             } else {
+                isModified = true;
                 textArray.add(new PdfNumber(FontProgram.convertGlyphSpaceToTextSpace(-ri.getUnscaledWidth()) /
                         (text.getFontSize() * text.getHorizontalScaling() / FontProgram.HORIZONTAL_SCALING_FACTOR)
                 ));
             }
         }
 
-        return new FilterResult<PdfArray>(true, textArray);
+        return new FilterResult<PdfArray>(isModified, textArray);
     }
 
     /**
@@ -262,7 +266,7 @@ FilterResult<ImageData> filterImage(FilteredImagesCache.FilteredImageKey imageKe
      * @param path the PathRenderInfo object to be filtered
      * @return a filtered {@link com.itextpdf.kernel.geom.Path} object.
      */
-    com.itextpdf.kernel.geom.Path filterStrokePath(PathRenderInfo path) {
+    Tuple2<Path, Boolean> filterStrokePath(PathRenderInfo path) {
         PdfArray dashPattern = path.getLineDashPattern();
         LineDashPattern lineDashPattern = new LineDashPattern(dashPattern.getAsArray(0), dashPattern.getAsNumber(1).floatValue());
 
@@ -279,7 +283,7 @@ com.itextpdf.kernel.geom.Path filterStrokePath(PathRenderInfo path) {
      * @return a filtered {@link com.itextpdf.kernel.geom.Path} object.
      */
     com.itextpdf.kernel.geom.Path filterFillPath(PathRenderInfo path, int fillingRule) {
-        return filterFillPath(path.getPath(), path.getCtm(), fillingRule);
+        return filterFillPath(path.getPath(), path.getCtm(), fillingRule, false);
     }
 
     FilteredImagesCache.FilteredImageKey createFilteredImageKey(PdfImageXObject image, Matrix imageCtm, PdfDocument document) {
@@ -292,10 +296,16 @@ FilteredImagesCache.FilteredImageKey createFilteredImageKey(PdfImageXObject imag
      * @param path        the PathRenderInfo object to be filtered.
      * @param ctm         a {@link com.itextpdf.kernel.geom.Path} transformation matrix.
      * @param fillingRule If the subpath is contour, pass any value.
+     * @param checkForIntersection if true, the intersection check of path and regions will be performed, and if
+     *                             there is no intersection, original path from parameters will be returned.
+     *                             We pass true when we filter stroke path (stroke converted to fill)
+     *                             not to put fill path into the output if it's not intersected with cleanup area.
+     *                             We pass false when we filter fill and clip paths (there we don't convert stroke to
+     *                             fill) and thus happy with the result from ClipperBridge DIFFERENCES.
      * @return a filtered {@link com.itextpdf.kernel.geom.Path} object.
      */
     private com.itextpdf.kernel.geom.Path filterFillPath(com.itextpdf.kernel.geom.Path path,
-                                                         Matrix ctm, int fillingRule) {
+                                                         Matrix ctm, int fillingRule, boolean checkForIntersection) {
         path.closeAllSubpaths();
 
         List<Point[]> transfRectVerticesList = new ArrayList<>();
@@ -327,6 +337,15 @@ private com.itextpdf.kernel.geom.Path filterFillPath(com.itextpdf.kernel.geom.Pa
         if (fillingRule == PdfCanvasConstants.FillingRule.EVEN_ODD) {
             fillType = PolyFillType.EVEN_ODD;
         }
+        if (checkForIntersection) {
+            //Find intersection with cleanup areas
+            PolyTree cleanupAreaIntersection = new PolyTree();
+            clipper.execute(ClipType.INTERSECTION, cleanupAreaIntersection, fillType, PolyFillType.NON_ZERO);
+            if (Paths.makePolyTreeToPaths(cleanupAreaIntersection).isEmpty()) {
+                //if there are no intersections, return original path as mark that no need to filter anything
+                return path;
+            }
+        }
 
         PolyTree resultTree = new PolyTree();
         clipper.execute(ClipType.DIFFERENCE, resultTree, fillType, PolyFillType.NON_ZERO);
@@ -363,10 +382,10 @@ private List<Rectangle> getImageAreasToBeCleaned(Matrix imageCtm) {
         return areasToBeCleaned;
     }
 
-    private com.itextpdf.kernel.geom.Path filterStrokePath(com.itextpdf.kernel.geom.Path sourcePath, Matrix ctm,
+    private Tuple2<Path, Boolean> filterStrokePath(Path sourcePath, Matrix ctm,
                                                            float lineWidth, int lineCapStyle, int lineJoinStyle,
                                                            float miterLimit, LineDashPattern lineDashPattern) {
-        com.itextpdf.kernel.geom.Path path = sourcePath;
+        Path path = sourcePath;
         JoinType joinType = ClipperBridge.getJoinType(lineJoinStyle);
         EndType endType = ClipperBridge.getEndType(lineCapStyle);
 
@@ -394,7 +413,12 @@ private com.itextpdf.kernel.geom.Path filterStrokePath(com.itextpdf.kernel.geom.
             }
         }
 
-        return filterFillPath(offsetedPath, ctm, PdfCanvasConstants.FillingRule.NONZERO_WINDING);
+        Path resultPath = filterFillPath(offsetedPath, ctm, PdfCanvasConstants.FillingRule.NONZERO_WINDING, true);
+        //if path was not filtered, return original path
+        if (resultPath == offsetedPath) {
+            return new Tuple2<Path, Boolean>(sourcePath, Boolean.FALSE);
+        }
+        return new Tuple2<Path, Boolean>(resultPath, Boolean.TRUE);
     }
 
     /**

src/main/java/com/itextpdf/pdfcleanup/PdfCleanUpLocation.java

@@ -1,6 +1,6 @@
 /*
     This file is part of the iText (R) project.
-    Copyright (c) 1998-2024 Apryse Group NV
+    Copyright (c) 1998-2025 Apryse Group NV
     Authors: Apryse Software.
 
     This program is offered under a commercial and under the AGPL license.

src/main/java/com/itextpdf/pdfcleanup/PdfCleanUpProcessor.java

@@ -1,6 +1,6 @@
 /*
     This file is part of the iText (R) project.
-    Copyright (c) 1998-2024 Apryse Group NV
+    Copyright (c) 1998-2025 Apryse Group NV
     Authors: Apryse Software.
 
     This program is offered under a commercial and under the AGPL license.
@@ -22,6 +22,7 @@ This file is part of the iText (R) project.
  */
 package com.itextpdf.pdfcleanup;
 
+import com.itextpdf.commons.datastructures.Tuple2;
 import com.itextpdf.io.image.ImageData;
 import com.itextpdf.io.image.ImageDataFactory;
 import com.itextpdf.io.source.ByteUtils;
@@ -823,12 +824,18 @@ private void writePath() {
         }
 
         if (stroke) {
-            Path strokePath = filter.filterStrokePath(path);
-            if (!strokePath.isEmpty()) {
-                // we pass stroke here as false, because stroke is transformed into fill. we don't need to set stroke color
-                writeNotAppliedGsParams(false, false);
-                openNotWrittenTags();
-                writeStrokePath(strokePath, path.getStrokeColor());
+            Tuple2<Path, Boolean> strokePath = filter.filterStrokePath(path);
+            if (!strokePath.getFirst().isEmpty()) {
+                if (strokePath.getSecond()) {
+                    // we pass stroke here as false, because stroke is transformed into fill. we don't need to set stroke color
+                    writeNotAppliedGsParams(false, false);
+                    openNotWrittenTags();
+                    writeFilteredStrokePath(strokePath.getFirst(), path.getStrokeColor());
+                } else {
+                    writeNotAppliedGsParams(false, true);
+                    openNotWrittenTags();
+                    writeStrokePath(strokePath.getFirst(), path.getStrokeColor());
+                }
             }
         }
 
@@ -893,14 +900,21 @@ private void writePath(Path path) {
         }
     }
 
-    private void writeStrokePath(Path strokePath, Color strokeColor) {
+    private void writeFilteredStrokePath(Path strokePath, Color strokeColor) {
         PdfCanvas canvas = getCanvas();
-        // As we transformed stroke to fill, we set stroke color for filling here
+        //As we transformed stroke to fill, we set stroke color for filling here
         canvas.saveState().setFillColor(strokeColor);
         writePath(strokePath);
         canvas.fill().restoreState();
     }
 
+    private void writeStrokePath(Path strokePath, Color strokeColor) {
+        PdfCanvas canvas = getCanvas();
+        canvas.saveState().setStrokeColor(strokeColor);
+        writePath(strokePath);
+        canvas.stroke().restoreState();
+    }
+
     private void removeOrCloseTag() {
         if (notWrittenTags.size() > 0) {
             CanvasTag tag = notWrittenTags.pop();

src/main/java/com/itextpdf/pdfcleanup/PdfCleanUpTool.java

@@ -1,6 +1,6 @@
 /*
     This file is part of the iText (R) project.
-    Copyright (c) 1998-2024 Apryse Group NV
+    Copyright (c) 1998-2025 Apryse Group NV
     Authors: Apryse Software.
 
     This program is offered under a commercial and under the AGPL license.