debtmap 0.16.4

Code complexity and technical debt analyzer
Documentation 
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
330
331
332
333
334
335
336
337
338

use crate::priority::semantic_classifier::FunctionRole;
use crate::risk::evidence::ModuleType;
use serde::{Deserialize, Serialize};
use std::collections::HashMap;

#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct ComplexityThresholds {
    pub low: f64,
    pub moderate: f64,
    pub high: f64,
    pub critical: f64,
}

impl Default for ComplexityThresholds {
    fn default() -> Self {
        Self {
            low: 5.0,
            moderate: 10.0,
            high: 15.0,
            critical: 20.0,
        }
    }
}

#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct CoverageThresholds {
    pub excellent: f64,
    pub good: f64,
    pub moderate: f64,
    pub poor: f64,
    pub critical: f64,
}

impl Default for CoverageThresholds {
    fn default() -> Self {
        Self {
            excellent: 90.0,
            good: 75.0,
            moderate: 50.0,
            poor: 25.0,
            critical: 10.0,
        }
    }
}

#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct CouplingThresholds {
    pub low: u32,
    pub moderate: u32,
    pub high: u32,
    pub critical: u32,
}

impl Default for CouplingThresholds {
    fn default() -> Self {
        Self {
            low: 3,
            moderate: 7,
            high: 12,
            critical: 20,
        }
    }
}

pub struct StatisticalDistribution {
    percentiles: Vec<(f64, f64)>, // (percentile, value)
}

impl StatisticalDistribution {
    pub fn new(mut values: Vec<f64>) -> Self {
        values.sort_by(|a, b| a.partial_cmp(b).unwrap());

        let percentiles = vec![
            (10.0, Self::calculate_percentile(&values, 0.10)),
            (25.0, Self::calculate_percentile(&values, 0.25)),
            (50.0, Self::calculate_percentile(&values, 0.50)),
            (75.0, Self::calculate_percentile(&values, 0.75)),
            (90.0, Self::calculate_percentile(&values, 0.90)),
            (95.0, Self::calculate_percentile(&values, 0.95)),
            (99.0, Self::calculate_percentile(&values, 0.99)),
        ];

        Self { percentiles }
    }

    pub fn percentile(&self, p: f64) -> f64 {
        // Find the closest percentile or interpolate
        for i in 0..self.percentiles.len() {
            if self.percentiles[i].0 >= p {
                if i == 0 {
                    return self.percentiles[0].1;
                }
                // Linear interpolation between percentiles
                let (p1, v1) = self.percentiles[i - 1];
                let (p2, v2) = self.percentiles[i];
                let ratio = (p - p1) / (p2 - p1);
                return v1 + ratio * (v2 - v1);
            }
        }
        self.percentiles.last().unwrap().1
    }

    fn calculate_percentile(values: &[f64], percentile: f64) -> f64 {
        if values.is_empty() {
            return 0.0;
        }

        let index = (percentile * (values.len() - 1) as f64) as usize;
        values[index]
    }
}

pub struct BaselineDatabase {
    complexity_distributions: HashMap<FunctionRole, StatisticalDistribution>,
    coverage_distributions: HashMap<FunctionRole, StatisticalDistribution>,
    coupling_distributions: HashMap<ModuleType, StatisticalDistribution>,
}

impl Default for BaselineDatabase {
    fn default() -> Self {
        // Initialize with typical baseline values for Rust codebases
        let mut complexity_distributions = HashMap::new();
        let mut coverage_distributions = HashMap::new();
        let mut coupling_distributions = HashMap::new();

        // Complexity baselines by role (cyclomatic complexity values)
        complexity_distributions.insert(
            FunctionRole::PureLogic,
            StatisticalDistribution::new(vec![
                1.0, 2.0, 2.0, 3.0, 3.0, 4.0, 4.0, 5.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 12.0, 15.0,
                18.0, 22.0, 28.0, 35.0,
            ]),
        );

        complexity_distributions.insert(
            FunctionRole::Orchestrator,
            StatisticalDistribution::new(vec![
                2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0, 12.0, 14.0, 16.0, 18.0, 20.0,
                24.0, 28.0, 32.0, 38.0, 45.0,
            ]),
        );

        complexity_distributions.insert(
            FunctionRole::IOWrapper,
            StatisticalDistribution::new(vec![
                1.0, 2.0, 3.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 10.0, 12.0, 15.0, 18.0, 22.0, 26.0,
                30.0, 35.0, 40.0, 48.0, 55.0,
            ]),
        );

        complexity_distributions.insert(
            FunctionRole::EntryPoint,
            StatisticalDistribution::new(vec![
                3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0, 12.0, 14.0, 16.0, 18.0, 20.0, 23.0,
                26.0, 30.0, 35.0, 42.0, 50.0,
            ]),
        );

        complexity_distributions.insert(
            FunctionRole::Unknown,
            StatisticalDistribution::new(vec![
                1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 12.0, 14.0, 16.0, 19.0, 22.0,
                26.0, 31.0, 36.0, 43.0, 50.0,
            ]),
        );

        // Coverage baselines by role (percentage values)
        coverage_distributions.insert(
            FunctionRole::PureLogic,
            StatisticalDistribution::new(vec![
                0.0, 0.0, 10.0, 20.0, 30.0, 40.0, 50.0, 60.0, 70.0, 75.0, 80.0, 85.0, 88.0, 90.0,
                92.0, 94.0, 96.0, 98.0, 99.0, 100.0,
            ]),
        );

        coverage_distributions.insert(
            FunctionRole::Orchestrator,
            StatisticalDistribution::new(vec![
                0.0, 0.0, 5.0, 15.0, 25.0, 35.0, 45.0, 55.0, 65.0, 70.0, 75.0, 80.0, 83.0, 85.0,
                87.0, 89.0, 91.0, 93.0, 95.0, 98.0,
            ]),
        );

        coverage_distributions.insert(
            FunctionRole::IOWrapper,
            StatisticalDistribution::new(vec![
                0.0, 0.0, 0.0, 10.0, 20.0, 30.0, 40.0, 50.0, 60.0, 65.0, 70.0, 75.0, 78.0, 80.0,
                82.0, 84.0, 86.0, 88.0, 90.0, 95.0,
            ]),
        );

        coverage_distributions.insert(
            FunctionRole::EntryPoint,
            StatisticalDistribution::new(vec![
                0.0, 0.0, 5.0, 15.0, 25.0, 35.0, 45.0, 55.0, 65.0, 70.0, 75.0, 80.0, 83.0, 85.0,
                87.0, 89.0, 91.0, 93.0, 95.0, 98.0,
            ]),
        );

        coverage_distributions.insert(
            FunctionRole::Unknown,
            StatisticalDistribution::new(vec![
                0.0, 0.0, 5.0, 15.0, 25.0, 35.0, 45.0, 55.0, 65.0, 70.0, 75.0, 80.0, 83.0, 85.0,
                87.0, 89.0, 91.0, 93.0, 95.0, 98.0,
            ]),
        );

        // Coupling baselines by module type (dependency count)
        coupling_distributions.insert(
            ModuleType::Core,
            StatisticalDistribution::new(vec![
                0.0, 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 12.0, 14.0, 16.0, 18.0,
                20.0, 23.0, 26.0, 30.0, 35.0,
            ]),
        );

        coupling_distributions.insert(
            ModuleType::Api,
            StatisticalDistribution::new(vec![
                1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0, 13.0, 15.0, 17.0, 19.0,
                21.0, 24.0, 27.0, 31.0, 36.0,
            ]),
        );

        coupling_distributions.insert(
            ModuleType::Util,
            StatisticalDistribution::new(vec![
                0.0, 0.0, 1.0, 1.0, 2.0, 2.0, 3.0, 3.0, 4.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0,
                12.0, 14.0, 16.0, 20.0,
            ]),
        );

        coupling_distributions.insert(
            ModuleType::Test,
            StatisticalDistribution::new(vec![
                1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 12.0, 14.0, 16.0, 18.0, 20.0,
                22.0, 25.0, 28.0, 32.0, 38.0,
            ]),
        );

        coupling_distributions.insert(
            ModuleType::Infrastructure,
            StatisticalDistribution::new(vec![
                2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0, 11.0, 13.0, 15.0, 17.0, 19.0, 21.0,
                23.0, 26.0, 29.0, 33.0, 40.0,
            ]),
        );

        Self {
            complexity_distributions,
            coverage_distributions,
            coupling_distributions,
        }
    }
}

impl BaselineDatabase {
    pub fn get_complexity_distribution(&self, role: &FunctionRole) -> &StatisticalDistribution {
        self.complexity_distributions
            .get(role)
            .unwrap_or_else(|| &self.complexity_distributions[&FunctionRole::Unknown])
    }

    pub fn get_coverage_distribution(&self, role: &FunctionRole) -> &StatisticalDistribution {
        self.coverage_distributions
            .get(role)
            .unwrap_or_else(|| &self.coverage_distributions[&FunctionRole::Unknown])
    }

    pub fn get_coupling_distribution(&self, module_type: &ModuleType) -> &StatisticalDistribution {
        self.coupling_distributions
            .get(module_type)
            .unwrap_or_else(|| &self.coupling_distributions[&ModuleType::Util])
    }
}

pub struct ProjectContext {
    pub language: String,
    pub project_type: String,
    pub team_size: usize,
}

impl Default for ProjectContext {
    fn default() -> Self {
        Self {
            language: "rust".to_string(),
            project_type: "library".to_string(),
            team_size: 1,
        }
    }
}

#[derive(Default)]
pub struct StatisticalThresholdProvider {
    baseline_data: BaselineDatabase,
    #[allow(dead_code)]
    project_context: ProjectContext,
}

impl StatisticalThresholdProvider {
    pub fn new() -> Self {
        Self::default()
    }

    pub fn get_complexity_thresholds(&self, role: &FunctionRole) -> ComplexityThresholds {
        let baseline = self.baseline_data.get_complexity_distribution(role);

        ComplexityThresholds {
            low: baseline.percentile(50.0),      // P50 - median
            moderate: baseline.percentile(75.0), // P75 - above average
            high: baseline.percentile(90.0),     // P90 - high
            critical: baseline.percentile(95.0), // P95 - very high
        }
    }

    pub fn get_coverage_thresholds(&self, role: &FunctionRole) -> CoverageThresholds {
        let baseline = self.baseline_data.get_coverage_distribution(role);

        CoverageThresholds {
            excellent: baseline.percentile(90.0), // P90 - well tested
            good: baseline.percentile(75.0),      // P75 - adequately tested
            moderate: baseline.percentile(50.0),  // P50 - some testing
            poor: baseline.percentile(25.0),      // P25 - minimal testing
            critical: baseline.percentile(10.0),  // P10 - essentially untested
        }
    }

    pub fn get_coupling_thresholds(&self, module_type: &ModuleType) -> CouplingThresholds {
        let baseline = self.baseline_data.get_coupling_distribution(module_type);

        CouplingThresholds {
            low: baseline.percentile(50.0) as u32,      // P50 - median
            moderate: baseline.percentile(75.0) as u32, // P75 - above average
            high: baseline.percentile(90.0) as u32,     // P90 - high
            critical: baseline.percentile(95.0) as u32, // P95 - very high
        }
    }
}