Adding antlr4 to pom, tests

pmd-xml/pom.xml

@@ -18,6 +18,10 @@
             </resource>
         </resources>
         <plugins>
+            <plugin>
+                <groupId>org.antlr</groupId>
+                <artifactId>antlr4-maven-plugin</artifactId>
+            </plugin>
             <plugin>
                 <artifactId>maven-resources-plugin</artifactId>
                 <configuration>
@@ -30,6 +34,10 @@
         </plugins>
     </build>
     <dependencies>
+	    <dependency>
+            <groupId>org.antlr</groupId>
+            <artifactId>antlr4-runtime</artifactId>
+        </dependency>
         <dependency>
             <groupId>net.sourceforge.pmd</groupId>
             <artifactId>pmd-core</artifactId>

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();
+    }
+}

pmd-xml/src/test/resources/net/sourceforge/pmd/cpd/hello.xml

@@ -0,0 +1,5 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<someTag>
+	<someOtherTag>Somehow we would like to improve this xml so we are not repeating the same content in this file or other files</someOtherTag>
+	<someOtherTag>Somehow we would like to improve this xml so we are not repeating the same content in this file or other files</someOtherTag>
+</someTag>