Added Lua support to CPD.

The tokenizer uses an ANTLR4 grammar based on the one at https://github.com/antlr/grammars-v4/tree/master/lua.

pmd-dist/pom.xml

@@ -127,6 +127,11 @@
             <artifactId>pmd-groovy</artifactId>
             <version>${project.version}</version>
         </dependency>
+        <dependency>
+            <groupId>net.sourceforge.pmd</groupId>
+            <artifactId>pmd-lua</artifactId>
+            <version>${project.version}</version>
+        </dependency>
         <dependency>
             <groupId>net.sourceforge.pmd</groupId>
             <artifactId>pmd-java</artifactId>

pmd-dist/src/test/java/net/sourceforge/pmd/it/BinaryDistributionIT.java

@@ -112,7 +112,7 @@ public class BinaryDistributionIT {
 
         result = CpdExecutor.runCpd(tempDir, "-h");
 
-        result.assertExecutionResult(1, "Supported languages: [apex, cpp, cs, dart, ecmascript, fortran, go, groovy, java, jsp, kotlin, matlab, objectivec, perl, php, plsql, python, ruby, scala, swift, vf]");
+        result.assertExecutionResult(1, "Supported languages: [apex, cpp, cs, dart, ecmascript, fortran, go, groovy, java, jsp, kotlin, lua, matlab, objectivec, perl, php, plsql, python, ruby, scala, swift, vf]");
 
         result = CpdExecutor.runCpd(tempDir, "--minimum-tokens", "10", "--format", "text", "--files", srcDir);
         result.assertExecutionResult(4, "Found a 10 line (55 tokens) duplication in the following files:");

pmd-lua/pom.xml

@@ -0,0 +1,57 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+    <modelVersion>4.0.0</modelVersion>
+    <artifactId>pmd-lua</artifactId>
+    <name>PMD Lua</name>
+
+    <parent>
+        <groupId>net.sourceforge.pmd</groupId>
+        <artifactId>pmd</artifactId>
+        <version>6.16.0-SNAPSHOT</version>
+    </parent>
+
+    <build>
+        <plugins>
+            <plugin>
+                <groupId>org.antlr</groupId>
+                <artifactId>antlr4-maven-plugin</artifactId>
+            </plugin>
+
+            <plugin>
+                <artifactId>maven-resources-plugin</artifactId>
+                <configuration>
+                    <useDefaultDelimiters>false</useDefaultDelimiters>
+                    <delimiters>
+                        <delimiter>${*}</delimiter>
+                    </delimiters>
+                </configuration>
+            </plugin>
+        </plugins>
+    </build>
+
+    <dependencies>
+        <dependency>
+            <groupId>org.antlr</groupId>
+            <artifactId>antlr4-runtime</artifactId>
+        </dependency>
+        <dependency>
+            <groupId>net.sourceforge.pmd</groupId>
+            <artifactId>pmd-core</artifactId>
+        </dependency>
+        <dependency>
+            <groupId>commons-io</groupId>
+            <artifactId>commons-io</artifactId>
+        </dependency>
+
+        <dependency>
+            <groupId>junit</groupId>
+            <artifactId>junit</artifactId>
+            <scope>test</scope>
+        </dependency>
+        <dependency>
+            <groupId>net.sourceforge.pmd</groupId>
+            <artifactId>pmd-test</artifactId>
+            <scope>test</scope>
+        </dependency>
+    </dependencies>
+</project>

pmd-lua/src/main/java/net/sourceforge/pmd/cpd/LuaLanguage.java

@@ -0,0 +1,18 @@
+/**
+ * BSD-style license; for more info see http://pmd.sourceforge.net/license.html
+ */
+
+package net.sourceforge.pmd.cpd;
+
+/**
+ * Language implementation for Lua
+ */
+public class LuaLanguage extends AbstractLanguage {
+
+    /**
+     * Creates a new Lua Language instance.
+     */
+    public LuaLanguage() {
+        super("Lua", "lua", new LuaTokenizer(), ".lua");
+    }
+}

pmd-lua/src/main/java/net/sourceforge/pmd/cpd/LuaTokenizer.java

@@ -0,0 +1,28 @@
+/**
+ * BSD-style license; for more info see http://pmd.sourceforge.net/license.html
+ */
+
+package net.sourceforge.pmd.cpd;
+
+import org.antlr.v4.runtime.CharStream;
+
+import net.sourceforge.pmd.cpd.token.AntlrTokenFilter;
+import net.sourceforge.pmd.lang.antlr.AntlrTokenManager;
+import net.sourceforge.pmd.lang.lua.antlr4.LuaLexer;
+
+/**
+ * The Lua Tokenizer
+ */
+public class LuaTokenizer extends AntlrTokenizer {
+
+    @Override
+    protected AntlrTokenManager getLexerForSource(SourceCode sourceCode) {
+        CharStream charStream = AntlrTokenizer.getCharStreamFromSourceCode(sourceCode);
+        return new AntlrTokenManager(new LuaLexer(charStream), sourceCode.getFileName());
+    }
+
+    @Override
+    protected AntlrTokenFilter getTokenFilter(final AntlrTokenManager tokenManager) {
+        return new AntlrTokenFilter(tokenManager);
+    }
+}

pmd-lua/src/main/resources/META-INF/services/net.sourceforge.pmd.cpd.Language

@@ -0,0 +1 @@
+net.sourceforge.pmd.cpd.LuaLanguage

pmd-lua/src/test/java/net/sourceforge/pmd/cpd/LuaTokenizerTest.java

@@ -0,0 +1,56 @@
+/**
+ * BSD-style license; for more info see http://pmd.sourceforge.net/license.html
+ */
+
+package net.sourceforge.pmd.cpd;
+
+import java.io.IOException;
+import java.nio.charset.StandardCharsets;
+import java.util.Arrays;
+import java.util.Collection;
+
+import org.apache.commons.io.IOUtils;
+import org.junit.Before;
+import org.junit.Test;
+import org.junit.runner.RunWith;
+import org.junit.runners.Parameterized;
+
+import net.sourceforge.pmd.testframework.AbstractTokenizerTest;
+
+@RunWith(Parameterized.class)
+public class LuaTokenizerTest extends AbstractTokenizerTest {
+
+    private final String filename;
+    private final int nExpectedTokens;
+
+    public LuaTokenizerTest(String filename, int nExpectedTokens) {
+        this.filename = filename;
+        this.nExpectedTokens = nExpectedTokens;
+    }
+
+    @Parameterized.Parameters
+    public static Collection<Object[]> data() {
+        return Arrays.asList(
+                new Object[] { "factorial.lua", 44 },
+                new Object[] { "helloworld.lua", 5 }
+        );
+    }
+
+    @Before
+    @Override
+    public void buildTokenizer() throws IOException {
+        this.tokenizer = new LuaTokenizer();
+        this.sourceCode = new SourceCode(new SourceCode.StringCodeLoader(this.getSampleCode(), this.filename));
+    }
+
+    @Override
+    public String getSampleCode() throws IOException {
+        return IOUtils.toString(LuaTokenizer.class.getResourceAsStream(this.filename), StandardCharsets.UTF_8);
+    }
+
+    @Test
+    public void tokenizeTest() throws IOException {
+        this.expectedTokenCount = nExpectedTokens;
+        super.tokenizeTest();
+    }
+}

pmd-lua/src/test/resources/net/sourceforge/pmd/cpd/factorial.lua

@@ -0,0 +1,13 @@
+-- defines a factorial function
+    function fact (n)
+      if n == 0 then
+        return 1
+      else
+        return n * fact(n-1)
+      end
+    end
+    
+    print("enter a number:")
+    a = io.read("*number")        -- read a number
+    print(fact(a))
+

pmd-lua/src/test/resources/net/sourceforge/pmd/cpd/helloworld.lua

@@ -0,0 +1,2 @@
+ print("Hello World")
+

pom.xml

@@ -1141,6 +1141,7 @@ Additionally it includes CPD, the copy-paste-detector. CPD finds duplicated code
         <module>pmd-fortran</module>
         <module>pmd-go</module>
         <module>pmd-groovy</module>
+        <module>pmd-lua</module>
         <module>pmd-java</module>
         <module>pmd-javascript</module>
         <module>pmd-jsp</module>