[RELEASE] iText 7 pdfSweep - 1.1.1

https://github.com/itext/i7j-pdfsweep/releases/tag/1.1.1

* release/1.1.1:
  [RELEASE] 1.1.1-SNAPSHOT -> 1.1.1
  Fixed an issue where .getFontFromAcroForm() method was called on a pdf without an AcroForm, resulting in a NullPointerException. This is fixed by adding an extra check on the availability of the AcroForm before querying it.
  Update pom parent with iText 7.0.7 SNAPSHOT
  Update copyright header
  Avoid unnecessary TJ operator before writing text with ` or ", handle empty TJ array
  Process new line operators while text cleaning. Minor changes.
  Process TJ only with numerical operands. Add a test.
  Add sources jar
  🔖 1.0.3-SNAPSHOT -> 1.1.1-SNAPSHOT

Author: iText-CI

pom.xml

@@ -5,12 +5,12 @@
   <parent>
     <groupId>com.itextpdf</groupId>
     <artifactId>root</artifactId>
-    <version>7.0.5</version>
+    <version>7.0.7</version>
     <relativePath />
   </parent>
 
   <artifactId>cleanup</artifactId>
-  <version>1.1.0</version>
+  <version>1.1.1</version>
 
   <name>pdfSweep</name>
   <url>http://itextpdf.com/</url>
@@ -72,17 +72,17 @@
       <artifactId>layout</artifactId>
       <version>${itext.version}</version>
     </dependency>
-    <dependency>
-        <groupId>com.itextpdf</groupId>
-        <artifactId>pdftest</artifactId>
-        <version>${itext.version}</version>
-        <scope>test</scope>
-    </dependency>
     <dependency>
       <groupId>org.apache.commons</groupId>
       <artifactId>commons-imaging</artifactId>
       <version>1.0-SNAPSHOT</version>
     </dependency>
+    <dependency>
+      <groupId>com.itextpdf</groupId>
+      <artifactId>pdftest</artifactId>
+      <version>${itext.version}</version>
+      <scope>test</scope>
+    </dependency>
   </dependencies>
 
   <build>
@@ -111,12 +111,16 @@
       <plugin>
         <groupId>org.apache.maven.plugins</groupId>
         <artifactId>maven-source-plugin</artifactId>
-        <version>3.0.0</version>
-        <configuration>
-          <excludes>
-            <exclude>**</exclude>
-          </excludes>
-        </configuration>
+        <version>3.0.1</version>
+        <executions>
+          <execution>
+            <id>attach-sources</id>
+            <phase>verify</phase>
+            <goals>
+              <goal>jar-no-fork</goal>
+            </goals>
+          </execution>
+        </executions>
       </plugin>
       <plugin>
         <groupId>org.apache.maven.plugins</groupId>

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

@@ -84,7 +84,6 @@ List<TextRenderInfo> getEncounteredText() {
         if (content.size() == 0) {
             throw new PdfException(textDataExpected);
         }
-
         ArrayList<TextRenderInfo> text = new ArrayList<>(content.size());
         for (IEventData data : content) {
             if (data instanceof TextRenderInfo) {

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

@@ -48,37 +48,37 @@ This file is part of the iText (R) project.
 import com.itextpdf.kernel.color.Color;
 import com.itextpdf.kernel.font.PdfFont;
 import com.itextpdf.kernel.geom.BezierCurve;
+import com.itextpdf.kernel.geom.IShape;
 import com.itextpdf.kernel.geom.Matrix;
 import com.itextpdf.kernel.geom.Path;
 import com.itextpdf.kernel.geom.Point;
 import com.itextpdf.kernel.geom.Rectangle;
-import com.itextpdf.kernel.geom.IShape;
 import com.itextpdf.kernel.geom.Subpath;
+import com.itextpdf.kernel.pdf.PdfArray;
 import com.itextpdf.kernel.pdf.PdfDictionary;
+import com.itextpdf.kernel.pdf.PdfDocument;
+import com.itextpdf.kernel.pdf.PdfLiteral;
+import com.itextpdf.kernel.pdf.PdfName;
+import com.itextpdf.kernel.pdf.PdfNumber;
+import com.itextpdf.kernel.pdf.PdfObject;
 import com.itextpdf.kernel.pdf.PdfPage;
+import com.itextpdf.kernel.pdf.PdfResources;
+import com.itextpdf.kernel.pdf.PdfStream;
+import com.itextpdf.kernel.pdf.PdfTextArray;
 import com.itextpdf.kernel.pdf.annot.PdfAnnotation;
 import com.itextpdf.kernel.pdf.annot.PdfLinkAnnotation;
 import com.itextpdf.kernel.pdf.annot.PdfTextMarkupAnnotation;
 import com.itextpdf.kernel.pdf.canvas.CanvasGraphicsState;
 import com.itextpdf.kernel.pdf.canvas.CanvasTag;
+import com.itextpdf.kernel.pdf.canvas.PdfCanvas;
 import com.itextpdf.kernel.pdf.canvas.PdfCanvasConstants;
+import com.itextpdf.kernel.pdf.canvas.PdfCanvasConstants.FillingRule;
 import com.itextpdf.kernel.pdf.canvas.parser.EventType;
+import com.itextpdf.kernel.pdf.canvas.parser.PdfCanvasProcessor;
 import com.itextpdf.kernel.pdf.canvas.parser.data.IEventData;
 import com.itextpdf.kernel.pdf.canvas.parser.data.ImageRenderInfo;
 import com.itextpdf.kernel.pdf.canvas.parser.data.PathRenderInfo;
-import com.itextpdf.kernel.pdf.canvas.parser.PdfCanvasProcessor;
 import com.itextpdf.kernel.pdf.canvas.parser.data.TextRenderInfo;
-import com.itextpdf.kernel.pdf.PdfArray;
-import com.itextpdf.kernel.pdf.PdfDocument;
-import com.itextpdf.kernel.pdf.PdfLiteral;
-import com.itextpdf.kernel.pdf.PdfName;
-import com.itextpdf.kernel.pdf.PdfNumber;
-import com.itextpdf.kernel.pdf.PdfObject;
-import com.itextpdf.kernel.pdf.PdfResources;
-import com.itextpdf.kernel.pdf.PdfStream;
-import com.itextpdf.kernel.pdf.PdfTextArray;
-import com.itextpdf.kernel.pdf.canvas.PdfCanvas;
-import com.itextpdf.kernel.pdf.canvas.PdfCanvasConstants.FillingRule;
 import com.itextpdf.kernel.pdf.colorspace.PdfShading;
 import com.itextpdf.kernel.pdf.tagutils.TagTreePointer;
 import com.itextpdf.kernel.pdf.xobject.PdfFormXObject;
@@ -512,14 +512,22 @@ private void filterContent(String operator, List<PdfObject> operands) {
     }
 
     private void cleanText(String operator, List<PdfObject> operands) {
-        List<TextRenderInfo> textChunks = getEventListener().getEncounteredText();
+        List<TextRenderInfo> textChunks = null;
         PdfArray cleanedText = null;
         if ("TJ".equals(operator)) {
             PdfArray originalTJ = (PdfArray) operands.get(0);
+            if (originalTJ.isEmpty()) {
+                // empty TJ neither shows any text nor affects text positioning
+                // we can safely ignore it
+                return;
+            }
             int i = 0; // text chunk index in original TJ
             PdfTextArray newTJ = new PdfTextArray();
             for (PdfObject e : originalTJ) {
                 if (e.isString()) {
+                    if (null == textChunks) {
+                        textChunks = ((PdfCleanUpEventListener) getEventListener()).getEncounteredText();
+                    }
                     PdfArray filteredText = filter.filterText(textChunks.get(i++)).getFilterResult();
                     newTJ.addAll(filteredText);
                 } else {
@@ -529,24 +537,34 @@ private void cleanText(String operator, List<PdfObject> operands) {
 
             cleanedText = newTJ;
         } else { // if operator is Tj or ' or "
+            textChunks = ((PdfCleanUpEventListener) getEventListener()).getEncounteredText();
             PdfCleanUpFilter.FilterResult<PdfArray> filterResult = filter.filterText(textChunks.get(0));
             if (filterResult.isModified()) {
                 cleanedText = filterResult.getFilterResult();
             }
         }
-
-        TextRenderInfo text = textChunks.get(0); // all text chunks even in case of TJ have the same graphics state
         // if text wasn't modified cleanedText is null
         if (cleanedText == null || cleanedText.size() != 1 || !cleanedText.get(0).isNumber()) {
+            if (null == textChunks) {
+                textChunks = ((PdfCleanUpEventListener) getEventListener()).getEncounteredText();
+            }
+            TextRenderInfo text = textChunks.get(0); // all text chunks even in case of TJ have the same graphics state
             writeNotAppliedGsParamsForText(text);
             beginTextObjectAndOpenNotWrittenTags();
 
             writeNotAppliedTextStateParams(text);
             textPositioning.writePositionedText(operator, operands, cleanedText, getCanvas());
         } else { // cleaned text is tj array with single number - it means that the whole text chunk was removed
             CanvasGraphicsState gs = getCanvas().getGraphicsState();
+            // process new lines if necessary
+            if ("'".equals(operator) || "\"".equals(operator)) {
+                List<PdfObject> newLineList = new ArrayList<>();
+                newLineList.add(new PdfLiteral("T*"));
+                textPositioning.appendPositioningOperator("T*", newLineList);
+            }
             textPositioning.appendTjArrayWithSingleNumber(cleanedText, gs.getFontSize(), gs.getHorizontalScaling());
         }
+
     }
 
     private void beginTextObjectAndOpenNotWrittenTags() {

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

@@ -453,11 +453,17 @@ private void drawRolloverAppearance(PdfCanvas canvas, PdfStream redactRolloverAp
     }
 
     private void drawOverlayText(PdfCanvas canvas, String overlayText, Rectangle annotRect, PdfBoolean repeat, PdfString defaultAppearance, int justification) throws IOException {
-        Map<String, List> parsedDA = parseDAParam(defaultAppearance);
+        Map<String, List> parsedDA;
+        try {
+            parsedDA = parseDAParam(defaultAppearance);
+        }catch (NullPointerException npe){
+            throw new PdfException(PdfException.DefaultAppearanceNotFound);
+        }
         PdfFont font;
         float fontSize = 12;
         List fontArgs = parsedDA.get("Tf");
-        if (fontArgs != null) {
+        PdfDictionary formDictionary = pdfDocument.getCatalog().getPdfObject().getAsDictionary(PdfName.AcroForm);
+        if (fontArgs != null && formDictionary != null) {
             font = getFontFromAcroForm((PdfName) fontArgs.get(0));
             fontSize = ((PdfNumber) fontArgs.get(1)).floatValue();
         } else {

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

@@ -93,9 +93,7 @@ void appendPositioningOperator(String operator, List<PdfObject> operands) {
             return;
         }
 
-        if (removedTextShift != null) {
-            removedTextShift = null;
-        }
+        removedTextShift = null;
 
         if (prevOperator == null) {
             firstPositioningOperands = new ArrayList<>(operands);
@@ -187,20 +185,23 @@ private void writePositioningOperator(PdfCanvas canvas) {
     private void writeText(String operator, List<PdfObject> operands, PdfArray cleanedText, PdfCanvas canvas) {
         CanvasGraphicsState canvasGs = canvas.getGraphicsState();
         boolean newLineShowText = "'".equals(operator) || "\"".equals(operator);
-        if (newLineShowText && canvasGs.getLeading() != currLeading) {
-            canvas.setLeading((float) currLeading);
+        if (newLineShowText) {
+            if (canvasGs.getLeading() != currLeading) {
+                canvas.setLeading((float) currLeading);
+            }
+            // after new line operator, removed text shift doesn't matter
+            removedTextShift = null;
         }
-        PdfTextArray tjShiftArray = new PdfTextArray();
+        PdfTextArray tjShiftArray = null;
         if (removedTextShift != null) {
             float tjShift = (float) removedTextShift * 1000 / (canvasGs.getFontSize() * canvasGs.getHorizontalScaling() / 100);
+            tjShiftArray = new PdfTextArray();
             tjShiftArray.add(new PdfNumber(tjShift));
         }
         if (cleanedText != null) {
             if (newLineShowText) {
                 // char spacing and word spacing are set via writeNotAppliedTextStateParams() method
                 canvas.newlineText();
-                // after new line operator, removed text shift doesn't matter
-                removedTextShift = null;
             }
             if (removedTextShift != null) {
                 tjShiftArray.addAll(cleanedText);

src/main/java/com/itextpdf/pdfcleanup/autosweep/PdfAutoSweep.java

@@ -40,15 +40,14 @@ This file is part of the iText (R) project.
     For more information, please contact iText Software Corp. at this
     address: [email protected]
  */
-/*
- * To change this license header, choose License Headers in Project Properties.
- * To change this template file, choose Tools | Templates
- * and open the template in the editor.
- */
 package com.itextpdf.pdfcleanup.autosweep;
 
 import com.itextpdf.kernel.geom.Rectangle;
-import com.itextpdf.kernel.pdf.*;
+import com.itextpdf.kernel.pdf.PdfArray;
+import com.itextpdf.kernel.pdf.PdfDocument;
+import com.itextpdf.kernel.pdf.PdfName;
+import com.itextpdf.kernel.pdf.PdfPage;
+import com.itextpdf.kernel.pdf.PdfString;
 import com.itextpdf.kernel.pdf.annot.PdfAnnotation;
 import com.itextpdf.kernel.pdf.annot.PdfRedactAnnotation;
 import com.itextpdf.kernel.pdf.canvas.PdfCanvas;
@@ -58,7 +57,12 @@ This file is part of the iText (R) project.
 import com.itextpdf.pdfcleanup.PdfCleanUpTool;
 
 import java.io.IOException;
-import java.util.*;
+import java.util.ArrayList;
+import java.util.Comparator;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Random;
+import java.util.Set;
 
 /**
  * Class that automatically extracts all regions of interest from a given PdfDocument and redacts them.

src/test/java/com/itextpdf/pdfcleanup/BigDocumentAutoCleanUpTest.java

@@ -40,11 +40,6 @@ This file is part of the iText (R) project.
     For more information, please contact iText Software Corp. at this
     address: [email protected]
  */
-/*
- * To change this license header, choose License Headers in Project Properties.
- * To change this template file, choose Tools | Templates
- * and open the template in the editor.
- */
 package com.itextpdf.pdfcleanup;
 
 import com.itextpdf.kernel.color.Color;
@@ -57,11 +52,6 @@ This file is part of the iText (R) project.
 import com.itextpdf.kernel.pdf.canvas.parser.listener.IPdfTextLocation;
 import com.itextpdf.kernel.pdf.canvas.parser.listener.RegexBasedLocationExtractionStrategy;
 import com.itextpdf.kernel.utils.CompareTool;
-import java.lang.reflect.Array;
-import java.lang.reflect.Constructor;
-import java.lang.reflect.Method;
-import com.itextpdf.pdfcleanup.PdfCleanupProductInfo;
-import com.itextpdf.kernel.Version;
 import com.itextpdf.pdfcleanup.autosweep.CompositeCleanupStrategy;
 import com.itextpdf.pdfcleanup.autosweep.ICleanupStrategy;
 import com.itextpdf.pdfcleanup.autosweep.PdfAutoSweep;
@@ -81,9 +71,6 @@ This file is part of the iText (R) project.
 
 import static com.itextpdf.test.ITextTest.createOrClearDestinationFolder;
 
-/**
- * @author Joris Schellekens
- */
 @Category(IntegrationTest.class)
 public class BigDocumentAutoCleanUpTest {
 
@@ -116,7 +103,7 @@ public void redactLipsum() throws IOException, InterruptedException {
         pdf.close();
 
         // compare
-        compareByContent(cmp, output, outputPath, "diff_redactLipsum_");
+        compareResults(cmp, output, outputPath, "diff_redactLipsum_");
     }
 
     @Test
@@ -142,7 +129,7 @@ public void redactTonySoprano() throws IOException, InterruptedException {
         pdf.close();
 
         // compare
-        compareByContent(cmp, output, outputPath, "diff_redactTonySoprano_");
+        compareResults(cmp, output, outputPath, "diff_redactTonySoprano_");
     }
 
     @Test
@@ -164,7 +151,7 @@ public void redactIPhoneUserManualMatchColor() throws IOException, InterruptedEx
         pdf.close();
 
         // compare
-        compareByContent(cmp, output, outputPath, "diff_redactIPhoneUserManualMatchColor_");
+        compareResults(cmp, output, outputPath, "diff_redactIPhoneUserManualMatchColor_");
     }
 
     @Test
@@ -187,10 +174,10 @@ public void redactIPhoneUserManual() throws IOException, InterruptedException {
         pdf.close();
 
         // compare
-        compareByContent(cmp, output, outputPath, "diff_redactIPhoneUserManual_");
+        compareResults(cmp, output, outputPath, "diff_redactIPhoneUserManual_");
     }
 
-    private void compareByContent(String cmp, String output, String targetDir, String diffPrefix) throws IOException, InterruptedException {
+    private void compareResults(String cmp, String output, String targetDir, String diffPrefix) throws IOException, InterruptedException {
         CompareTool cmpTool = new CompareTool();
         String errorMessage = cmpTool.compareVisually(output, cmp, targetDir, diffPrefix + "_");
 
@@ -258,6 +245,7 @@ public Color getRedactionColor(IPdfTextLocation rect) {
         return colorByRectangle.containsKey(rect.getRectangle()) ? colorByRectangle.get(rect.getRectangle()) : Color.BLACK;
     }
 
+    @Override
     public ICleanupStrategy reset()
     {
         return new CustomLocationExtractionStrategy(regex);