diff --git a/pmd-vm/src/main/java/net/sourceforge/pmd/lang/vm/VmLanguageModule.java b/pmd-vm/src/main/java/net/sourceforge/pmd/lang/vm/VmLanguageModule.java
index d7f9811faf..ce35a109ec 100644
--- a/pmd-vm/src/main/java/net/sourceforge/pmd/lang/vm/VmLanguageModule.java
+++ b/pmd-vm/src/main/java/net/sourceforge/pmd/lang/vm/VmLanguageModule.java
@@ -4,8 +4,11 @@
 
 package net.sourceforge.pmd.lang.vm;
 
+import net.sourceforge.pmd.cpd.Tokenizer;
+import net.sourceforge.pmd.lang.LanguagePropertyBundle;
 import net.sourceforge.pmd.lang.LanguageRegistry;
 import net.sourceforge.pmd.lang.impl.SimpleLanguageModuleBase;
+import net.sourceforge.pmd.lang.vm.cpd.VmTokenizer;
 
 /**
  * Created by christoferdutz on 20.09.14.
@@ -28,4 +31,8 @@ public class VmLanguageModule extends SimpleLanguageModuleBase {
         return (VmLanguageModule) LanguageRegistry.PMD.getLanguageById(ID);
     }
 
+    @Override
+    public Tokenizer createCpdTokenizer(LanguagePropertyBundle bundle) {
+        return new VmTokenizer();
+    }
 }
diff --git a/pmd-vm/src/main/java/net/sourceforge/pmd/lang/vm/cpd/VmTokenizer.java b/pmd-vm/src/main/java/net/sourceforge/pmd/lang/vm/cpd/VmTokenizer.java
new file mode 100644
index 0000000000..d8d29ff173
--- /dev/null
+++ b/pmd-vm/src/main/java/net/sourceforge/pmd/lang/vm/cpd/VmTokenizer.java
@@ -0,0 +1,21 @@
+/*
+ * BSD-style license; for more info see http://pmd.sourceforge.net/license.html
+ */
+
+package net.sourceforge.pmd.lang.vm.cpd;
+
+import java.io.IOException;
+
+import net.sourceforge.pmd.cpd.impl.JavaCCTokenizer;
+import net.sourceforge.pmd.lang.TokenManager;
+import net.sourceforge.pmd.lang.ast.impl.javacc.CharStream;
+import net.sourceforge.pmd.lang.ast.impl.javacc.JavaccToken;
+import net.sourceforge.pmd.lang.document.TextDocument;
+import net.sourceforge.pmd.lang.vm.ast.VmTokenKinds;
+
+public class VmTokenizer extends JavaCCTokenizer {
+    @Override
+    protected TokenManager<JavaccToken> makeLexerImpl(TextDocument doc) throws IOException {
+        return VmTokenKinds.newTokenManager(CharStream.create(doc));
+    }
+}
diff --git a/pmd-vm/src/test/java/net/sourceforge/pmd/lang/vm/cpd/VmTokenizerTest.java b/pmd-vm/src/test/java/net/sourceforge/pmd/lang/vm/cpd/VmTokenizerTest.java
new file mode 100644
index 0000000000..98e018586c
--- /dev/null
+++ b/pmd-vm/src/test/java/net/sourceforge/pmd/lang/vm/cpd/VmTokenizerTest.java
@@ -0,0 +1,21 @@
+/*
+ * BSD-style license; for more info see http://pmd.sourceforge.net/license.html
+ */
+
+package net.sourceforge.pmd.lang.vm.cpd;
+
+import org.junit.jupiter.api.Test;
+
+import net.sourceforge.pmd.cpd.test.CpdTextComparisonTest;
+import net.sourceforge.pmd.lang.vm.VmLanguageModule;
+
+class VmTokenizerTest extends CpdTextComparisonTest {
+    VmTokenizerTest() {
+        super(VmLanguageModule.getInstance(), ".vm");
+    }
+
+    @Test
+    void sampleTest() {
+        doTest("sample_vm");
+    }
+}
diff --git a/pmd-vm/src/test/resources/net/sourceforge/pmd/lang/vm/cpd/testdata/sample_vm.txt b/pmd-vm/src/test/resources/net/sourceforge/pmd/lang/vm/cpd/testdata/sample_vm.txt
new file mode 100644
index 0000000000..bc84902704
--- /dev/null
+++ b/pmd-vm/src/test/resources/net/sourceforge/pmd/lang/vm/cpd/testdata/sample_vm.txt
@@ -0,0 +1,54 @@
+    [Image] or [Truncated image[            Bcol      Ecol
+L1
+    [#if]                                   1         4
+    [(]                                     4         5
+    [ ]                                     5         6
+    [$XHTML]                                6         12
+    [ ]                                     12        13
+    [)\n]                                   13        15
+L2
+    [    #set(]                             1         10
+    [ ]                                     10        11
+    [$br]                                   11        14
+    [ ]                                     14        15
+    [=]                                     15        16
+    [ ]                                     16        17
+    ["<br />"]                              17        25
+    [ ]                                     25        26
+    [)\n]                                   26        28
+L3
+    [    ]                                  1         5
+    [#if]                                   5         8
+    [ ]                                     8         9
+    [(]                                     9         10
+    [$someValue]                            10        20
+    [)\n]                                   20        22
+L4
+    [        ]                              1         9
+    [#if]                                   9         12
+    [ ]                                     12        13
+    [(]                                     13        14
+    [$otherValue]                           14        25
+    [)\n]                                   25        27
+L5
+    [            do stuff\n        ]        1         9
+L6
+    [#end\n]                                9         14
+L7
+    [    ]                                  1         5
+    [#end\n]                                5         10
+L8
+    [#else\n]                               1         7
+L9
+    [    #set(]                             1         10
+    [ ]                                     10        11
+    [$br]                                   11        14
+    [ ]                                     14        15
+    [=]                                     15        16
+    [ ]                                     16        17
+    ["<br>"]                                17        23
+    [ ]                                     23        24
+    [)\n]                                   24        26
+L10
+    [#end\n]                                1         6
+EOF
diff --git a/pmd-vm/src/test/resources/net/sourceforge/pmd/lang/vm/cpd/testdata/sample_vm.vm b/pmd-vm/src/test/resources/net/sourceforge/pmd/lang/vm/cpd/testdata/sample_vm.vm
new file mode 100644
index 0000000000..33b1e63114
--- /dev/null
+++ b/pmd-vm/src/test/resources/net/sourceforge/pmd/lang/vm/cpd/testdata/sample_vm.vm
@@ -0,0 +1,10 @@
+#if( $XHTML )
+    #set( $br = "<br />" )
+    #if ($someValue)
+        #if ($otherValue)
+            do stuff
+        #end
+    #end
+#else
+    #set( $br = "<br>" )
+#end
diff --git a/pmd-xml/src/main/java/net/sourceforge/pmd/lang/pom/PomLanguageModule.java b/pmd-xml/src/main/java/net/sourceforge/pmd/lang/pom/PomLanguageModule.java
index 9c97c5d01b..315a61efe3 100644
--- a/pmd-xml/src/main/java/net/sourceforge/pmd/lang/pom/PomLanguageModule.java
+++ b/pmd-xml/src/main/java/net/sourceforge/pmd/lang/pom/PomLanguageModule.java
@@ -4,9 +4,12 @@
 
 package net.sourceforge.pmd.lang.pom;
 
+import net.sourceforge.pmd.cpd.Tokenizer;
+import net.sourceforge.pmd.lang.LanguagePropertyBundle;
 import net.sourceforge.pmd.lang.LanguageRegistry;
 import net.sourceforge.pmd.lang.impl.SimpleLanguageModuleBase;
 import net.sourceforge.pmd.lang.xml.XmlHandler;
+import net.sourceforge.pmd.lang.xml.cpd.XmlTokenizer;
 
 public class PomLanguageModule extends SimpleLanguageModuleBase {
     private static final String ID = "pom";
@@ -22,4 +25,8 @@ public class PomLanguageModule extends SimpleLanguageModuleBase {
         return (PomLanguageModule) LanguageRegistry.PMD.getLanguageById(ID);
     }
 
+    @Override
+    public Tokenizer createCpdTokenizer(LanguagePropertyBundle bundle) {
+        return new XmlTokenizer();
+    }
 }
diff --git a/pmd-xml/src/main/java/net/sourceforge/pmd/lang/wsdl/WsdlLanguageModule.java b/pmd-xml/src/main/java/net/sourceforge/pmd/lang/wsdl/WsdlLanguageModule.java
index fdbf8fac0d..aa617d1dd4 100644
--- a/pmd-xml/src/main/java/net/sourceforge/pmd/lang/wsdl/WsdlLanguageModule.java
+++ b/pmd-xml/src/main/java/net/sourceforge/pmd/lang/wsdl/WsdlLanguageModule.java
@@ -4,9 +4,12 @@
 
 package net.sourceforge.pmd.lang.wsdl;
 
+import net.sourceforge.pmd.cpd.Tokenizer;
+import net.sourceforge.pmd.lang.LanguagePropertyBundle;
 import net.sourceforge.pmd.lang.LanguageRegistry;
 import net.sourceforge.pmd.lang.impl.SimpleLanguageModuleBase;
 import net.sourceforge.pmd.lang.xml.XmlHandler;
+import net.sourceforge.pmd.lang.xml.cpd.XmlTokenizer;
 
 /**
  * Created by bernardo-macedo on 24.06.15.
@@ -25,4 +28,9 @@ public class WsdlLanguageModule extends SimpleLanguageModuleBase {
     public static WsdlLanguageModule getInstance() {
         return (WsdlLanguageModule) LanguageRegistry.PMD.getLanguageById(ID);
     }
+
+    @Override
+    public Tokenizer createCpdTokenizer(LanguagePropertyBundle bundle) {
+        return new XmlTokenizer();
+    }
 }
diff --git a/pmd-xml/src/main/java/net/sourceforge/pmd/lang/xsl/XslLanguageModule.java b/pmd-xml/src/main/java/net/sourceforge/pmd/lang/xsl/XslLanguageModule.java
index f3dff3a737..13884bd243 100644
--- a/pmd-xml/src/main/java/net/sourceforge/pmd/lang/xsl/XslLanguageModule.java
+++ b/pmd-xml/src/main/java/net/sourceforge/pmd/lang/xsl/XslLanguageModule.java
@@ -4,9 +4,12 @@
 
 package net.sourceforge.pmd.lang.xsl;
 
+import net.sourceforge.pmd.cpd.Tokenizer;
+import net.sourceforge.pmd.lang.LanguagePropertyBundle;
 import net.sourceforge.pmd.lang.LanguageRegistry;
 import net.sourceforge.pmd.lang.impl.SimpleLanguageModuleBase;
 import net.sourceforge.pmd.lang.xml.XmlHandler;
+import net.sourceforge.pmd.lang.xml.cpd.XmlTokenizer;
 
 /**
  * Created by christoferdutz on 20.09.14.
@@ -26,4 +29,9 @@ public class XslLanguageModule extends SimpleLanguageModuleBase {
     public static XslLanguageModule getInstance() {
         return (XslLanguageModule) LanguageRegistry.PMD.getLanguageById(ID);
     }
+
+    @Override
+    public Tokenizer createCpdTokenizer(LanguagePropertyBundle bundle) {
+        return new XmlTokenizer();
+    }
 }