Added Dart support to CPD.

The tokenizer uses an ANTLR4 grammar based on the one at https://github.com/antlr/grammars-v4/tree/master/dart2.

pmd-dart/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-dart</artifactId>
+    <name>PMD Dart</name>
+
+    <parent>
+        <groupId>net.sourceforge.pmd</groupId>
+        <artifactId>pmd</artifactId>
+        <version>6.14.0-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-dart/src/main/java/net/sourceforge/pmd/cpd/DartLanguage.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 Dart
+ */
+public class DartLanguage extends AbstractLanguage {
+
+    /**
+     * Creates a new Dart Language instance.
+     */
+    public DartLanguage() {
+        super("Dart", "dart", new DartTokenizer(), ".dart");
+    }
+}

pmd-dart/src/main/java/net/sourceforge/pmd/cpd/DartTokenizer.java

@@ -0,0 +1,70 @@
+/**
+ * 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.AntlrToken;
+import net.sourceforge.pmd.cpd.token.AntlrTokenFilter;
+import net.sourceforge.pmd.lang.antlr.AntlrTokenManager;
+import net.sourceforge.pmd.lang.dart.antlr4.Dart2Lexer;
+
+/**
+ * The Dart Tokenizer
+ */
+public class DartTokenizer extends AntlrTokenizer {
+
+    @Override
+    protected AntlrTokenManager getLexerForSource(SourceCode sourceCode) {
+        CharStream charStream = AntlrTokenizer.getCharStreamFromSourceCode(sourceCode);
+        return new AntlrTokenManager(new Dart2Lexer(charStream), sourceCode.getFileName());
+    }
+
+    @Override
+    protected AntlrTokenFilter getTokenFilter(final AntlrTokenManager tokenManager) {
+        return new DartTokenFilter(tokenManager);
+    }
+
+    /**
+     * The {@link DartTokenFilter} extends the {@link AntlrTokenFilter} to discard
+     * Dart-specific tokens.
+     * <p>
+     * By default, it discards package and import statements, and
+     * enables annotation-based CPD suppression.
+     * </p>
+     */
+    private static class DartTokenFilter extends AntlrTokenFilter {
+        private boolean discardingPackageAndImport = false;
+        private boolean discardingNL = false;
+
+        /* default */ DartTokenFilter(final AntlrTokenManager tokenManager) {
+            super(tokenManager);
+        }
+
+        @Override
+        protected void analyzeToken(final AntlrToken currentToken) {
+            skipPackageAndImport(currentToken);
+            skipNewLines(currentToken);
+        }
+
+        private void skipPackageAndImport(final AntlrToken currentToken) {
+            final int type = currentToken.getType();
+            /*if (type == Dart.PACKAGE || type == Dart.IMPORT) {
+                discardingPackageAndImport = true;
+            } else if (discardingPackageAndImport && (type == Dart.SEMICOLON || type == Dart.NL)) {
+                discardingPackageAndImport = false;
+            }*/
+        }
+
+        private void skipNewLines(final AntlrToken currentToken) {
+            discardingNL = false;//currentToken.getType() == Dart.NL;
+        }
+
+        @Override
+        protected boolean isLanguageSpecificDiscarding() {
+            return discardingPackageAndImport || discardingNL;
+        }
+    }
+}

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

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

pmd-dist/pom.xml

@@ -107,6 +107,11 @@
             <artifactId>pmd-cs</artifactId>
             <version>${project.version}</version>
         </dependency>
+        <dependency>
+            <groupId>net.sourceforge.pmd</groupId>
+            <artifactId>pmd-dart</artifactId>
+            <version>${project.version}</version>
+        </dependency>
         <dependency>
             <groupId>net.sourceforge.pmd</groupId>
             <artifactId>pmd-fortran</artifactId>

pom.xml

@@ -1130,6 +1130,7 @@ Additionally it includes CPD, the copy-paste-detector. CPD finds duplicated code
         <module>pmd-core</module>
         <module>pmd-cpp</module>
         <module>pmd-cs</module>
+        <module>pmd-dart</module>
         <module>pmd-dist</module>
         <module>pmd-fortran</module>
         <module>pmd-go</module>