0
# Copy-Paste Detection
1

2
Lexical analysis for detecting code duplication within Apex codebases. Integrates with PMD's Copy-Paste Detection (CPD) framework to identify similar code blocks.
3

4
## Capabilities
5

6
### CPD Lexer
7

8
Tokenizes Apex code for duplicate detection analysis.
9

10
```java { .api }
11
/**
12
 * Lexer for copy-paste detection in Apex code
13
 * Tokenizes Apex source code for duplicate block detection
14
 */
15
public class ApexCpdLexer {
16
    /**
17
     * Tokenize Apex code for duplicate detection
18
     * @param textDocument - Source code document to tokenize
19
     * @param tokenFactory - Factory for creating tokens
20
     */
21
    public void tokenize(TextDocument textDocument, TokenFactory tokenFactory);
22
}
23
```
24

25
### Token Factory
26

27
Factory interface for creating tokens during lexical analysis.
28

29
```java { .api }
30
/**
31
 * Factory for creating tokens during CPD analysis
32
 * Part of PMD core framework
33
 */
34
public interface TokenFactory {
35
    /**
36
     * Create a token for the given text and location
37
     * @param image - Token text content
38
     * @param beginLine - Starting line number
39
     * @param beginColumn - Starting column number
40
     * @param endLine - Ending line number
41
     * @param endColumn - Ending column number
42
     */
43
    void recordToken(String image, int beginLine, int beginColumn, int endLine, int endColumn);
44
}
45
```
46

47
### Text Document
48

49
Represents source code document for analysis.
50

51
```java { .api }
52
/**
53
 * Represents a source code document for analysis
54
 * Part of PMD core framework
55
 */
56
public interface TextDocument {
57
    /** Get the full text content */
58
    String getText();
59
    
60
    /** Get the file name or identifier */
61
    String getDisplayName();
62
    
63
    /** Get character at specific position */
64
    char charAt(int index);
65
    
66
    /** Get length of document */
67
    int getLength();
68
}
69
```
70

71
**Usage Examples:**
72

73
```java
74
import net.sourceforge.pmd.lang.apex.cpd.ApexCpdLexer;
75
import net.sourceforge.pmd.cpd.*;
76

77
// Create CPD lexer for Apex
78
ApexCpdLexer lexer = new ApexCpdLexer();
79

80
// Create token factory for collecting tokens
81
List<Token> tokens = new ArrayList<>();
82
TokenFactory tokenFactory = new TokenFactory() {
83
    @Override
84
    public void recordToken(String image, int beginLine, int beginColumn, int endLine, int endColumn) {
85
        Token token = new Token(image, beginLine, beginColumn, endLine, endColumn);
86
        tokens.add(token);
87
    }
88
};
89

90
// Create text document from Apex source
91
String apexCode = """
92
    public class MyClass {
93
        public void method1() {
94
            System.debug('Hello World');
95
            Integer x = 5;
96
            if (x > 0) {
97
                System.debug('Positive');
98
            }
99
        }
100
        
101
        public void method2() {
102
            System.debug('Hello World');
103
            Integer y = 10;
104
            if (y > 0) {
105
                System.debug('Positive');
106
            }
107
        }
108
    }
109
    """;
110

111
TextDocument document = new TextDocument() {
112
    @Override
113
    public String getText() { return apexCode; }
114
    
115
    @Override
116
    public String getDisplayName() { return "MyClass.cls"; }
117
    
118
    @Override
119
    public char charAt(int index) { return apexCode.charAt(index); }
120
    
121
    @Override
122
    public int getLength() { return apexCode.length(); }
123
};
124

125
// Tokenize the document
126
lexer.tokenize(document, tokenFactory);
127

128
// Tokens are now available for duplicate detection
129
System.out.println("Generated " + tokens.size() + " tokens for CPD analysis");
130

131
// Use with PMD CPD framework
132
CPDConfiguration config = new CPDConfiguration();
133
config.setMinimumTileSize(50); // Minimum duplicate block size
134
config.setLanguage(ApexLanguageModule.getInstance());
135

136
CPD cpd = new CPD(config);
137
cpd.add(document);
138

139
// Find duplicates
140
List<Mark> duplicates = cpd.getMatches();
141
for (Mark duplicate : duplicates) {
142
    System.out.println("Found duplicate code at line " + duplicate.getBeginLine() + 
143
                      " in " + duplicate.getTokenSrcID());
144
}
145

146
// Integration with language module
147
ApexLanguageModule apexModule = ApexLanguageModule.getInstance();
148
LanguagePropertyBundle properties = apexModule.newPropertyBundle();
149
Lexer cpdLexer = apexModule.createCpdLexer(properties);
150

151
// The returned lexer is the same ApexCpdLexer instance
152
assert cpdLexer instanceof ApexCpdLexer;
153
```