PMD Python Language Module

<dependency>
    <groupId>net.sourceforge.pmd</groupId>
    <artifactId>pmd-python</artifactId>
    <version>7.13.0</version>
</dependency>

import net.sourceforge.pmd.lang.python.PythonLanguageModule;
import net.sourceforge.pmd.lang.python.cpd.PythonCpdLexer;
import net.sourceforge.pmd.lang.python.ast.PythonTokenKinds;
import net.sourceforge.pmd.cpd.CpdLexer;
import net.sourceforge.pmd.lang.LanguagePropertyBundle;
import net.sourceforge.pmd.lang.LanguageRegistry;
import net.sourceforge.pmd.lang.TokenManager;
import net.sourceforge.pmd.lang.ast.impl.javacc.JavaccToken;
import net.sourceforge.pmd.lang.ast.impl.javacc.CharStream;
import net.sourceforge.pmd.lang.ast.impl.javacc.JavaccTokenDocument.TokenDocumentBehavior;
import net.sourceforge.pmd.lang.document.TextDocument;
import java.util.regex.Pattern;

// Get the Python language module instance
PythonLanguageModule pythonModule = PythonLanguageModule.getInstance();

// Create a CPD lexer for Python code analysis
PythonCpdLexer lexer = new PythonCpdLexer();

// The lexer can be used with PMD's CPD framework to detect duplicate code

// Core language module base class
abstract class CpdOnlyLanguageModuleBase {
    protected CpdOnlyLanguageModuleBase(LanguageMetadata metadata);
}

// Language property configuration
interface LanguagePropertyBundle {
    // PMD language property bundle for configuration
}

// CPD lexer interface
interface CpdLexer {
    // Copy-paste detector lexer interface
}

// JavaCC-based CPD lexer implementation
abstract class JavaccCpdLexer implements CpdLexer {
    protected abstract TokenManager<JavaccToken> makeLexerImpl(TextDocument doc);
    protected abstract String getImage(JavaccToken token);
}

// Token manager for JavaCC tokens
interface TokenManager<T extends JavaccToken> {
    // Manages tokens for JavaCC-based lexers
}

// JavaCC token representation  
class JavaccToken {
    public int kind;
    public String getImage();
}

// Text document for processing
interface TextDocument {
    // Represents a text document for lexical analysis
}

// Language metadata builder
class LanguageMetadata {
    public static LanguageMetadata withId(String id);
    public LanguageMetadata name(String name);
    public LanguageMetadata extensions(String... extensions);
}

// Character stream for JavaCC parsing
class CharStream {
    public static CharStream create(TextDocument doc, TokenDocumentBehavior behavior);
}

// Token document behavior configuration
class TokenDocumentBehavior {
    public TokenDocumentBehavior(String[] tokenNames);
}

public class PythonLanguageModule extends CpdOnlyLanguageModuleBase {
    public PythonLanguageModule();
    public static PythonLanguageModule getInstance();
    public CpdLexer createCpdLexer(LanguagePropertyBundle bundle);
}

public class PythonCpdLexer extends JavaccCpdLexer {
    public PythonCpdLexer();
    protected TokenManager<JavaccToken> makeLexerImpl(TextDocument doc);
    protected String getImage(JavaccToken token);
}

// Python token constants - generated from Python.jj grammar
class PythonTokenKinds {
    // String literal token types (handled specially for escape processing)
    public static final int SINGLE_STRING;     // Single-quoted strings: 'text'
    public static final int SINGLE_STRING2;    // Alternative single-quoted strings
    public static final int SINGLE_BSTRING;    // Byte strings: b'text'
    public static final int SINGLE_BSTRING2;   // Alternative byte strings
    public static final int SINGLE_USTRING;    // Unicode strings: u'text'  
    public static final int SINGLE_USTRING2;   // Alternative unicode strings
    
    // Token creation and management
    public static TokenManager<JavaccToken> newTokenManager(CharStream charStream);
    public static final String[] TOKEN_NAMES;
}

// Service provider registration (META-INF/services/net.sourceforge.pmd.lang.Language)
net.sourceforge.pmd.lang.python.PythonLanguageModule

// Language metadata
String LANGUAGE_ID = "python";
String LANGUAGE_NAME = "Python";  
String[] FILE_EXTENSIONS = {".py"};

// Retrieve Python language module
PythonLanguageModule module = PythonLanguageModule.getInstance();

// Create lexer for Python code analysis  
PythonCpdLexer lexer = module.createCpdLexer(languagePropertyBundle);

// The lexer is now ready for use with PMD's CPD engine

// The lexer handles Python-specific token processing automatically
// Including normalization of string literals with escape sequences
PythonCpdLexer lexer = new PythonCpdLexer();
// Token processing happens internally during CPD analysis