swt 4.0.0

🍬 Sweet: A blazing-fast code health and architecture 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

//! Duplicate code detection using sliding window hashing.

use std::collections::HashMap;
use std::collections::hash_map::DefaultHasher;
use std::hash::{Hash, Hasher};

/// Measured repetition results for a specific file.
pub struct RepetitionResult {
    /// Percentage of duplicated code.
    pub percentage: f64,
    /// Detailed information about the duplicated chunks.
    pub hashes: Vec<u64>,
    /// Line mapping to retrieve original content.
    pub line_map: Vec<String>,
}

/// Measures the percentage of repetitive code blocks in the content.
///
/// Uses normalized line hashing and a sliding window to identify duplicate code chunks.
#[must_use]
pub fn analyze_repetition(content: &str, min_duplicate_lines: usize) -> RepetitionResult {
    let lines_content: Vec<String> = content
        .lines()
        .filter(|l| !l.contains("@sweetignore"))
        .map(std::string::ToString::to_string)
        .collect();

    if lines_content.is_empty() {
        return RepetitionResult {
            percentage: 0.0,
            hashes: vec![],
            line_map: vec![],
        };
    }

    let hashes: Vec<u64> = lines_content
        .iter()
        .map(|l| hash_normalized_line(l))
        .collect();

    if hashes.len() < min_duplicate_lines {
        return RepetitionResult {
            percentage: 0.0,
            hashes,
            line_map: lines_content,
        };
    }

    let mut repetitive_lines = vec![false; hashes.len()];
    let mut chunks: HashMap<&[u64], Vec<usize>> = HashMap::with_capacity(hashes.len());

    for i in 0..=hashes.len() - min_duplicate_lines {
        let chunk = &hashes[i..i + min_duplicate_lines];

        if lines_content[i..i + min_duplicate_lines]
            .iter()
            .all(|l| l.trim().len() < 3)
        {
            continue;
        }

        chunks.entry(chunk).or_default().push(i);
    }

    for occurrences in chunks.values().filter(|v| v.len() > 1) {
        for &start_idx in occurrences {
            for r in &mut repetitive_lines[start_idx..start_idx + min_duplicate_lines] {
                *r = true;
            }
        }
    }

    let repeated_count = repetitive_lines.iter().filter(|&&r| r).count();

    #[allow(clippy::cast_precision_loss)]
    let percentage = (repeated_count as f64 / hashes.len() as f64) * 100.0;

    RepetitionResult {
        percentage,
        hashes,
        line_map: lines_content,
    }
}

/// Computes a hash for a line after removing whitespace and converting to lowercase.
#[must_use]
pub fn hash_normalized_line(line: &str) -> u64 {
    let mut s = DefaultHasher::new();
    for c in line.chars().filter(|c| !c.is_whitespace()) {
        for lc in c.to_lowercase() {
            lc.hash(&mut s);
        }
    }
    s.finish()
}

/// Extracts chunks of hashes from a sequence and returns a map of their occurrences.
/// Each key is a vector of hashes (the chunk), and each value is a list of starting positions (1-based).
#[must_use]
pub fn get_chunks(
    hashes: &[u64],
    window_size: usize,
) -> std::collections::HashMap<Vec<u64>, Vec<usize>> {
    let mut chunks: std::collections::HashMap<Vec<u64>, Vec<usize>> =
        std::collections::HashMap::new();
    if hashes.len() >= window_size {
        for i in 0..=hashes.len() - window_size {
            let chunk = hashes[i..i + window_size].to_vec();
            chunks.entry(chunk).or_default().push(i + 1);
        }
    }
    chunks
}

#[cfg(test)]
mod tests {
    use super::*;

    #[test]
    fn test_repetition() {
        let no_rep =
            "fn main() {\n    let x = 1;\n    let y = 2;\n    let z = 3;\n    let w = 4;\n}";
        assert!(analyze_repetition(no_rep, 4).percentage.abs() < f64::EPSILON);

        let rep = "let a = 1;\nlet b = 2;\nlet c = 3;\nlet d = 4;\nlet a = 1;\nlet b = 2;\nlet c = 3;\nlet d = 4;";
        assert!(analyze_repetition(rep, 4).percentage > 0.0);
    }
}