[core] CPD: Add correct XML 1.0 escaping for code snippets

pmd-core/pom.xml

@@ -134,6 +134,10 @@
             <groupId>org.apache.commons</groupId>
             <artifactId>commons-lang3</artifactId>
         </dependency>
+        <dependency>
+            <groupId>org.apache.commons</groupId>
+            <artifactId>commons-text</artifactId>
+        </dependency>
         <dependency>
             <groupId>org.ow2.asm</groupId>
             <artifactId>asm</artifactId>

pmd-core/src/main/java/net/sourceforge/pmd/cpd/XMLRenderer.java

@@ -18,6 +18,7 @@ import javax.xml.transform.TransformerFactory;
 import javax.xml.transform.dom.DOMSource;
 import javax.xml.transform.stream.StreamResult;
 
+import org.apache.commons.text.StringEscapeUtils;
 import org.w3c.dom.Document;
 import org.w3c.dom.Element;
 
@@ -140,7 +141,7 @@ public final class XMLRenderer implements Renderer, CPDRenderer {
             // the code snippet has normalized line endings
             String platformSpecific = codeSnippet.replace("\n", System.lineSeparator());
             Element codefragment = doc.createElement("codefragment");
-            codefragment.appendChild(doc.createCDATASection(platformSpecific));
+            codefragment.appendChild(doc.createCDATASection(StringEscapeUtils.escapeXml10(platformSpecific)));
             duplication.appendChild(codefragment);
         }
         return duplication;

pmd-core/src/test/java/net/sourceforge/pmd/cpd/XMLRendererTest.java

@@ -5,6 +5,7 @@
 package net.sourceforge.pmd.cpd;
 
 import static org.junit.Assert.assertEquals;
+import static org.junit.Assert.assertFalse;
 import static org.junit.Assert.assertTrue;
 import static org.junit.Assert.fail;
 
@@ -196,6 +197,23 @@ public class XMLRendererTest {
         assertTrue(report.contains(espaceChar));
     }
 
+    @Test
+    public void testRendererXMLEscaping() throws IOException {
+        String formfeed = "\u000C";
+        String codefragment = "code fragment" + formfeed + "\nline2\nline3";
+        CPDRenderer renderer = new XMLRenderer();
+        List<Match> list = new ArrayList<>();
+        Mark mark1 = createMark("public", "file1", 1, 2, codefragment);
+        Mark mark2 = createMark("public", "file2", 5, 2, codefragment);
+        Match match1 = new Match(75, mark1, mark2);
+        list.add(match1);
+
+        StringWriter sw = new StringWriter();
+        renderer.render(list.iterator(), sw);
+        String report = sw.toString();
+        assertFalse(report.contains(formfeed));
+    }
+
     private Mark createMark(String image, String tokenSrcID, int beginLine, int lineCount, String code) {
         Mark result = new Mark(new TokenEntry(image, tokenSrcID, beginLine));
 
@@ -214,8 +232,4 @@ public class XMLRendererTest {
         result.setSourceCode(new SourceCode(new SourceCode.StringCodeLoader(code)));
         return result;
     }
-
-    public static junit.framework.Test suite() {
-        return new junit.framework.JUnit4TestAdapter(XMLRendererTest.class);
-    }
 }

pmd-doc/pom.xml

@@ -95,7 +95,6 @@
         <dependency>
             <groupId>org.apache.commons</groupId>
             <artifactId>commons-text</artifactId>
-            <version>1.6</version>
         </dependency>
         <dependency>
             <groupId>org.yaml</groupId>

pom.xml

@@ -669,6 +669,11 @@
                 <artifactId>commons-lang3</artifactId>
                 <version>3.8.1</version>
             </dependency>
+            <dependency>
+                <groupId>org.apache.commons</groupId>
+                <artifactId>commons-text</artifactId>
+                <version>1.6</version>
+            </dependency>
             <dependency>
                 <groupId>org.slf4j</groupId>
                 <artifactId>slf4j-api</artifactId>