diff --git a/pmd-xml/pom.xml b/pmd-xml/pom.xml
index f10e9bc259..626ea6850d 100644
--- a/pmd-xml/pom.xml
+++ b/pmd-xml/pom.xml
@@ -18,6 +18,10 @@
+
+ org.antlr
+ antlr4-maven-plugin
+
maven-resources-plugin
@@ -30,6 +34,10 @@
+
+ org.antlr
+ antlr4-runtime
+
net.sourceforge.pmd
pmd-core
diff --git a/pmd-xml/src/test/java/net/sourceforge/pmd/cpd/XmlCPDTokenizerTest.java b/pmd-xml/src/test/java/net/sourceforge/pmd/cpd/XmlCPDTokenizerTest.java
new file mode 100644
index 0000000000..d152cf29b5
--- /dev/null
+++ b/pmd-xml/src/test/java/net/sourceforge/pmd/cpd/XmlCPDTokenizerTest.java
@@ -0,0 +1,36 @@
+/**
+ * BSD-style license; for more info see http://pmd.sourceforge.net/license.html
+ */
+
+package net.sourceforge.pmd.cpd;
+
+import java.io.IOException;
+
+import org.apache.commons.io.IOUtils;
+import org.junit.Before;
+import org.junit.Test;
+
+import net.sourceforge.pmd.testframework.AbstractTokenizerTest;
+
+public class XmlCPDTokenizerTest extends AbstractTokenizerTest {
+
+ private static final String FILENAME = "hello.xml";
+
+ @Before
+ @Override
+ public void buildTokenizer() throws IOException {
+ this.tokenizer = new XmlTokenizer();
+ this.sourceCode = new SourceCode(new SourceCode.StringCodeLoader(this.getSampleCode(), FILENAME));
+ }
+
+ @Override
+ public String getSampleCode() throws IOException {
+ return IOUtils.toString(XmlTokenizer.class.getResourceAsStream(FILENAME));
+ }
+
+ @Test
+ public void tokenizeTest() throws IOException {
+ this.expectedTokenCount = 37;
+ super.tokenizeTest();
+ }
+}
diff --git a/pmd-xml/src/test/resources/net/sourceforge/pmd/cpd/hello.xml b/pmd-xml/src/test/resources/net/sourceforge/pmd/cpd/hello.xml
new file mode 100644
index 0000000000..3b86c4c08c
--- /dev/null
+++ b/pmd-xml/src/test/resources/net/sourceforge/pmd/cpd/hello.xml
@@ -0,0 +1,5 @@
+
+
+ Somehow we would like to improve this xml so we are not repeating the same content in this file or other files
+ Somehow we would like to improve this xml so we are not repeating the same content in this file or other files
+
\ No newline at end of file