Added Kotlin support to CPD.

The tokenizer uses the ANTLR4 grammar based on the one at https://github.com/shadrina/kotlin-grammar-antlr4 (via https://github.com/antlr/grammars-v4/).

pmd-dist/pom.xml

@@ -117,6 +117,11 @@
             <artifactId>pmd-visualforce</artifactId>
             <version>${project.version}</version>
         </dependency>
+        <dependency>
+            <groupId>net.sourceforge.pmd</groupId>
+            <artifactId>pmd-kotlin</artifactId>
+            <version>${project.version}</version>
+        </dependency>
         <dependency>
             <groupId>net.sourceforge.pmd</groupId>
             <artifactId>pmd-matlab</artifactId>

pmd-kotlin/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-kotlin</artifactId>
+    <name>PMD Kotlin</name>
+
+    <parent>
+        <groupId>net.sourceforge.pmd</groupId>
+        <artifactId>pmd</artifactId>
+        <version>6.4.0</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-kotlin/src/main/java/net/sourceforge/pmd/cpd/KotlinLanguage.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 Kotlin
+ */
+public class KotlinLanguage extends AbstractLanguage {
+
+    /**
+     * Creates a new Kotlin Language instance.
+     */
+    public KotlinLanguage() {
+        super("Kotlin", "kotlin", new KotlinTokenizer(), ".kt");
+    }
+}

pmd-kotlin/src/main/java/net/sourceforge/pmd/cpd/KotlinTokenizer.java

@@ -0,0 +1,83 @@
+/**
+ * BSD-style license; for more info see http://pmd.sourceforge.net/license.html
+ */
+
+package net.sourceforge.pmd.cpd;
+
+import net.sourceforge.pmd.lang.kotlin.antlr4.Kotlin;
+import org.antlr.v4.runtime.ANTLRInputStream;
+import org.antlr.v4.runtime.BaseErrorListener;
+import org.antlr.v4.runtime.Lexer;
+import org.antlr.v4.runtime.RecognitionException;
+import org.antlr.v4.runtime.Recognizer;
+import org.antlr.v4.runtime.Token;
+
+import net.sourceforge.pmd.lang.ast.TokenMgrError;
+//import net.sourceforge.pmd.lang.kotlin.antlr4.KotlinLexer;
+
+/**
+ * The Kotlin Tokenizer
+ */
+public class KotlinTokenizer implements Tokenizer {
+
+    @Override
+    public void tokenize(SourceCode sourceCode, Tokens tokenEntries) {
+        StringBuilder buffer = sourceCode.getCodeBuffer();
+
+        try {
+            ANTLRInputStream ais = new ANTLRInputStream(buffer.toString());
+            Kotlin lexer = new Kotlin(ais);
+
+            lexer.removeErrorListeners();
+            lexer.addErrorListener(new ErrorHandler());
+            Token token = lexer.nextToken();
+
+            while (token.getType() != Token.EOF) {
+                if (token.getChannel() != Lexer.HIDDEN) {
+                    TokenEntry tokenEntry = new TokenEntry(token.getText(), sourceCode.getFileName(), token.getLine());
+
+                    tokenEntries.add(tokenEntry);
+                }
+                token = lexer.nextToken();
+            }
+        } catch (ANTLRSyntaxError err) {
+            // Wrap exceptions of the Kotlin tokenizer in a TokenMgrError, so
+            // they are correctly handled
+            // when CPD is executed with the '--skipLexicalErrors' command line
+            // option
+            throw new TokenMgrError("Lexical error in file " + sourceCode.getFileName() + " at line " + err.getLine()
+                    + ", column " + err.getColumn() + ".  Encountered: " + err.getMessage(),
+                    TokenMgrError.LEXICAL_ERROR);
+        } finally {
+            tokenEntries.add(TokenEntry.getEOF());
+        }
+    }
+
+    private static class ErrorHandler extends BaseErrorListener {
+        @Override
+        public void syntaxError(Recognizer<?, ?> recognizer, Object offendingSymbol, int line, int charPositionInLine,
+                String msg, RecognitionException ex) {
+            throw new ANTLRSyntaxError(msg, line, charPositionInLine, ex);
+        }
+    }
+
+    private static class ANTLRSyntaxError extends RuntimeException {
+        private static final long serialVersionUID = 1L;
+        private final int line;
+        private final int column;
+
+        ANTLRSyntaxError(String msg, int line, int column, RecognitionException cause) {
+            super(msg, cause);
+            this.line = line;
+            this.column = column;
+        }
+
+        public int getLine() {
+            return line;
+        }
+
+        public int getColumn() {
+            return column;
+        }
+    }
+}

pmd-kotlin/src/main/java/net/sourceforge/pmd/lang/kotlin/KotlinLanguageModule.java

@@ -0,0 +1,26 @@
+/**
+ * BSD-style license; for more info see http://pmd.sourceforge.net/license.html
+ */
+
+package net.sourceforge.pmd.lang.kotlin;
+
+import net.sourceforge.pmd.lang.BaseLanguageModule;
+
+/**
+ * Language Module for Kotlin
+ */
+public class KotlinLanguageModule extends BaseLanguageModule {
+
+    /** The name. */
+    public static final String NAME = "Kotlin";
+    /** The terse name. */
+    public static final String TERSE_NAME = "kotlin";
+
+    /**
+     * Create a new instance of Kotlin Language Module.
+     */
+    public KotlinLanguageModule() {
+        super(NAME, null, TERSE_NAME, null, "kotlin");
+        addVersion("", null, true);
+    }
+}

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

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

pmd-kotlin/src/main/resources/META-INF/services/net.sourceforge.pmd.lang.Language

@@ -0,0 +1 @@
+net.sourceforge.pmd.lang.kotlin.KotlinLanguageModule

pom.xml

@@ -985,6 +985,7 @@ Additionally it includes CPD, the copy-paste-detector. CPD finds duplicated code
         <module>pmd-java</module>
         <module>pmd-javascript</module>
         <module>pmd-jsp</module>
+        <module>pmd-kotlin</module>
         <module>pmd-matlab</module>
         <module>pmd-objectivec</module>
         <module>pmd-perl</module>