Copy-Paste Detection

/**
 * Lexer for copy-paste detection in Apex code
 * Tokenizes Apex source code for duplicate block detection
 */
public class ApexCpdLexer {
    /**
     * Tokenize Apex code for duplicate detection
     * @param textDocument - Source code document to tokenize
     * @param tokenFactory - Factory for creating tokens
     */
    public void tokenize(TextDocument textDocument, TokenFactory tokenFactory);
}

/**
 * Factory for creating tokens during CPD analysis
 * Part of PMD core framework
 */
public interface TokenFactory {
    /**
     * Create a token for the given text and location
     * @param image - Token text content
     * @param beginLine - Starting line number
     * @param beginColumn - Starting column number
     * @param endLine - Ending line number
     * @param endColumn - Ending column number
     */
    void recordToken(String image, int beginLine, int beginColumn, int endLine, int endColumn);
}

/**
 * Represents a source code document for analysis
 * Part of PMD core framework
 */
public interface TextDocument {
    /** Get the full text content */
    String getText();
    
    /** Get the file name or identifier */
    String getDisplayName();
    
    /** Get character at specific position */
    char charAt(int index);
    
    /** Get length of document */
    int getLength();
}

import net.sourceforge.pmd.lang.apex.cpd.ApexCpdLexer;
import net.sourceforge.pmd.cpd.*;

// Create CPD lexer for Apex
ApexCpdLexer lexer = new ApexCpdLexer();

// Create token factory for collecting tokens
List<Token> tokens = new ArrayList<>();
TokenFactory tokenFactory = new TokenFactory() {
    @Override
    public void recordToken(String image, int beginLine, int beginColumn, int endLine, int endColumn) {
        Token token = new Token(image, beginLine, beginColumn, endLine, endColumn);
        tokens.add(token);
    }
};

// Create text document from Apex source
String apexCode = """
    public class MyClass {
        public void method1() {
            System.debug('Hello World');
            Integer x = 5;
            if (x > 0) {
                System.debug('Positive');
            }
        }
        
        public void method2() {
            System.debug('Hello World');
            Integer y = 10;
            if (y > 0) {
                System.debug('Positive');
            }
        }
    }
    """;

TextDocument document = new TextDocument() {
    @Override
    public String getText() { return apexCode; }
    
    @Override
    public String getDisplayName() { return "MyClass.cls"; }
    
    @Override
    public char charAt(int index) { return apexCode.charAt(index); }
    
    @Override
    public int getLength() { return apexCode.length(); }
};

// Tokenize the document
lexer.tokenize(document, tokenFactory);

// Tokens are now available for duplicate detection
System.out.println("Generated " + tokens.size() + " tokens for CPD analysis");

// Use with PMD CPD framework
CPDConfiguration config = new CPDConfiguration();
config.setMinimumTileSize(50); // Minimum duplicate block size
config.setLanguage(ApexLanguageModule.getInstance());

CPD cpd = new CPD(config);
cpd.add(document);

// Find duplicates
List<Mark> duplicates = cpd.getMatches();
for (Mark duplicate : duplicates) {
    System.out.println("Found duplicate code at line " + duplicate.getBeginLine() + 
                      " in " + duplicate.getTokenSrcID());
}

// Integration with language module
ApexLanguageModule apexModule = ApexLanguageModule.getInstance();
LanguagePropertyBundle properties = apexModule.newPropertyBundle();
Lexer cpdLexer = apexModule.createCpdLexer(properties);

// The returned lexer is the same ApexCpdLexer instance
assert cpdLexer instanceof ApexCpdLexer;