pmat 3.15.0

PMAT - Zero-config AI context generation and code quality toolkit (CLI, MCP, HTTP)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329

// Unit tests for normalization, node significance, hashing, scoring, and clone detection
// Included from duplication.rs — shares parent module scope (no `use` imports here)

#[cfg_attr(coverage_nightly, coverage(off))]
#[cfg(test)]
mod tests_scoring {
    use super::*;
    use tree_sitter::Parser;

    fn parse_rust(source: &str) -> Tree {
        let mut parser = Parser::new();
        parser.set_language(&tree_sitter_rust::language()).unwrap();
        parser.parse(source, None).unwrap()
    }

    // === Normalization tests ===

    #[test]
    fn test_normalize_identifier() {
        let source = "let my_var = 1;";
        let tree = parse_rust(source);
        let detector = DuplicationDetector::new();

        walk_tree(tree.root_node(), |node| {
            if node.kind() == "identifier" {
                let normalized = detector.normalize_token(node, source);
                // Most identifiers should normalize to $VAR unless they're type names
                assert!(normalized == "$VAR" || normalized == get_node_text(node, source));
            }
        });
    }

    #[test]
    fn test_normalize_string_literal() {
        let detector = DuplicationDetector::new();
        let source = r#"let s = "hello";"#;
        let tree = parse_rust(source);

        walk_tree(tree.root_node(), |node| {
            if node.kind() == "string_literal" {
                let normalized = detector.normalize_token(node, source);
                assert_eq!(normalized, "$STR");
            }
        });
    }

    #[test]
    fn test_normalize_number_literal() {
        let detector = DuplicationDetector::new();
        let source = "let n = 42;";
        let tree = parse_rust(source);

        walk_tree(tree.root_node(), |node| {
            if node.kind() == "integer_literal" {
                let normalized = detector.normalize_token(node, source);
                assert_eq!(normalized, "$NUM");
            }
        });
    }

    // === is_significant_node tests ===

    #[test]
    fn test_is_significant_node_comment() {
        let detector = DuplicationDetector::new();
        let source = "// comment\nfn test() {}";
        let tree = parse_rust(source);

        walk_tree(tree.root_node(), |node| {
            if node.kind() == "line_comment" {
                assert!(!detector.is_significant_node(node));
            }
        });
    }

    #[test]
    fn test_is_significant_node_brackets() {
        let detector = DuplicationDetector::new();
        let source = "fn test() {}";
        let tree = parse_rust(source);

        walk_tree(tree.root_node(), |node| {
            if matches!(node.kind(), "(" | ")" | "{" | "}") {
                assert!(!detector.is_significant_node(node));
            }
        });
    }

    #[test]
    fn test_is_significant_node_function() {
        let detector = DuplicationDetector::new();
        let source = "fn test() {}";
        let tree = parse_rust(source);

        walk_tree(tree.root_node(), |node| {
            if node.kind() == "fn" {
                assert!(detector.is_significant_node(node));
            }
        });
    }

    // === Hash tests ===

    #[test]
    fn test_hash_sequence_identical() {
        let detector = DuplicationDetector::new();

        let tokens = vec![
            Token { kind: "a".to_string(), text: "a".to_string(), normalized: "a".to_string() },
            Token { kind: "b".to_string(), text: "b".to_string(), normalized: "b".to_string() },
        ];

        let hash1 = detector.hash_sequence(&tokens);
        let hash2 = detector.hash_sequence(&tokens);

        assert_eq!(hash1, hash2);
    }

    #[test]
    fn test_hash_sequence_different() {
        let detector = DuplicationDetector::new();

        let tokens1 = vec![
            Token { kind: "a".to_string(), text: "a".to_string(), normalized: "a".to_string() },
        ];

        let tokens2 = vec![
            Token { kind: "b".to_string(), text: "b".to_string(), normalized: "b".to_string() },
        ];

        let hash1 = detector.hash_sequence(&tokens1);
        let hash2 = detector.hash_sequence(&tokens2);

        assert_ne!(hash1, hash2);
    }

    #[test]
    fn test_hash_normalized_identical() {
        let detector = DuplicationDetector::new();

        let normalized = vec!["$VAR".to_string(), "=".to_string(), "$NUM".to_string()];

        let hash1 = detector.hash_normalized(&normalized);
        let hash2 = detector.hash_normalized(&normalized);

        assert_eq!(hash1, hash2);
    }

    // === Scorer tests ===

    #[test]
    fn test_scorer_simple_code() {
        let source = r#"
            fn simple() {
                let x = 1;
            }
        "#;

        let tree = parse_rust(source);
        let detector = DuplicationDetector::new();
        let config = TdgConfig::default();
        let mut tracker = PenaltyTracker::new();

        let score = detector.score(&tree, source, Language::Rust, &config, &mut tracker);

        assert!(score.is_ok());
        assert!(score.unwrap() >= 0.0);
    }

    #[test]
    fn test_scorer_empty_source() {
        let source = "";

        let tree = parse_rust(source);
        let detector = DuplicationDetector::new();
        let config = TdgConfig::default();
        let mut tracker = PenaltyTracker::new();

        let score = detector.score(&tree, source, Language::Rust, &config, &mut tracker);

        assert!(score.is_ok());
    }

    #[test]
    fn test_scorer_no_duplication() {
        let source = r#"
            fn unique_a() { let a = 1; }
            fn unique_b() { let b = 2; }
            fn unique_c() { let c = 3; }
        "#;

        let tree = parse_rust(source);
        let detector = DuplicationDetector::new();
        let config = TdgConfig::default();
        let mut tracker = PenaltyTracker::new();

        let score = detector.score(&tree, source, Language::Rust, &config, &mut tracker);

        assert!(score.is_ok());
        // No duplication should result in full score
        let score_value = score.unwrap();
        assert!(score_value >= 0.0);
    }

    // === Clone detection tests ===

    #[test]
    fn test_find_exact_clones_no_clones() {
        let detector = DuplicationDetector::new();

        let seq1 = TokenSequence {
            tokens: vec![
                Token { kind: "a".to_string(), text: "a".to_string(), normalized: "a".to_string() },
            ],
            start_byte: 0,
            end_byte: 1,
        };

        let seq2 = TokenSequence {
            tokens: vec![
                Token { kind: "b".to_string(), text: "b".to_string(), normalized: "b".to_string() },
            ],
            start_byte: 10,
            end_byte: 11,
        };

        let clones = detector.find_exact_clones(&[seq1, seq2]);
        assert!(clones.clones.is_empty());
    }

    #[test]
    fn test_find_renamed_clones() {
        let detector = DuplicationDetector::new();

        let seq1 = TokenSequence {
            tokens: vec![
                Token { kind: "let".to_string(), text: "let".to_string(), normalized: "let".to_string() },
                Token { kind: "identifier".to_string(), text: "x".to_string(), normalized: "$VAR".to_string() },
            ],
            start_byte: 0,
            end_byte: 5,
        };

        let seq2 = TokenSequence {
            tokens: vec![
                Token { kind: "let".to_string(), text: "let".to_string(), normalized: "let".to_string() },
                Token { kind: "identifier".to_string(), text: "y".to_string(), normalized: "$VAR".to_string() },
            ],
            start_byte: 10,
            end_byte: 15,
        };

        let clones = detector.find_renamed_clones(&[seq1, seq2]);
        // Should find clones since normalized forms match
        assert!(!clones.clones.is_empty());
    }

    #[test]
    fn test_find_modified_clones() {
        let detector = DuplicationDetector::new();

        let seq1 = TokenSequence {
            tokens: vec![
                Token { kind: "let".to_string(), text: "let".to_string(), normalized: "let".to_string() },
                Token { kind: "identifier".to_string(), text: "x".to_string(), normalized: "$VAR".to_string() },
                Token { kind: "=".to_string(), text: "=".to_string(), normalized: "=".to_string() },
                Token { kind: "number".to_string(), text: "1".to_string(), normalized: "$NUM".to_string() },
            ],
            start_byte: 0,
            end_byte: 10,
        };

        let seq2 = TokenSequence {
            tokens: vec![
                Token { kind: "let".to_string(), text: "let".to_string(), normalized: "let".to_string() },
                Token { kind: "identifier".to_string(), text: "y".to_string(), normalized: "$VAR".to_string() },
                Token { kind: "=".to_string(), text: "=".to_string(), normalized: "=".to_string() },
                Token { kind: "number".to_string(), text: "2".to_string(), normalized: "$NUM".to_string() },
                Token { kind: "+".to_string(), text: "+".to_string(), normalized: "+".to_string() },
            ],
            start_byte: 20,
            end_byte: 35,
        };

        let clones = detector.find_modified_clones(&[seq1, seq2]);
        // May or may not find clones depending on similarity threshold
        assert!(clones.clones.len() >= 0);
    }

    // === is_type_name tests ===

    #[test]
    fn test_is_type_name_uppercase() {
        let detector = DuplicationDetector::new();
        let source = "let x: MyType = value;";
        let tree = parse_rust(source);

        // Type identifiers that start with uppercase are typically types
        walk_tree(tree.root_node(), |node| {
            if node.kind() == "type_identifier" {
                let is_type = detector.is_type_name(node, source);
                assert!(is_type);
            }
        });
    }

    // === extract_token_sequences tests ===

    #[test]
    fn test_extract_token_sequences_empty_source() {
        let source = "";
        let tree = parse_rust(source);
        let detector = DuplicationDetector::new();

        let sequences = detector.extract_token_sequences(tree.root_node(), source);
        assert!(sequences.is_empty());
    }

    #[test]
    fn test_extract_token_sequences_short_code() {
        let source = "let x = 1;";
        let tree = parse_rust(source);
        let detector = DuplicationDetector::new();

        let sequences = detector.extract_token_sequences(tree.root_node(), source);
        // Short code won't meet min_token_sequence threshold
        assert!(sequences.is_empty() || sequences.len() >= 0);
    }
}