tinyzip 0.4.0

Low level ZIP file parsing and navigation
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

use std::io::{Cursor, Write};

/// The file we look up / extract in benchmarks.
pub const TARGET_FILE: &str = "src/core/data/processing/transform/csv/records.csv";

/// Generate a realistic ZIP archive (~1000 files, nested paths, a few multi-MB files).
pub fn generate() -> Vec<u8> {
    let buf = Cursor::new(Vec::with_capacity(4 * 1024 * 1024));
    let mut w = zip::write::ZipWriter::new(buf);
    let opts = zip::write::SimpleFileOptions::default()
        .compression_method(zip::CompressionMethod::Deflated);

    // A simple LCG for deterministic pseudo-random content (no extra deps).
    let mut rng: u64 = 0xDEAD_BEEF;
    let mut next = || -> u8 {
        rng = rng.wrapping_mul(6364136223846793005).wrapping_add(1);
        (rng >> 33) as u8
    };

    // Directory structure mimicking a real monorepo
    let dirs = [
        "src/core/auth/providers/oauth2/google",
        "src/core/auth/providers/oauth2/github",
        "src/core/auth/providers/saml",
        "src/core/auth/session/storage/redis",
        "src/core/auth/session/middleware",
        "src/core/data/processing/transform/csv",
        "src/core/data/processing/transform/json",
        "src/core/data/processing/validate/schema",
        "src/core/data/processing/validate/constraints",
        "src/core/data/storage/adapters/postgres",
        "src/core/data/storage/adapters/sqlite",
        "src/core/data/storage/migrations/v1",
        "src/core/data/storage/migrations/v2",
        "src/frontend/ui/components/forms/inputs",
        "src/frontend/ui/components/forms/validation",
        "src/frontend/ui/components/layout/sidebar",
        "src/frontend/ui/components/layout/header",
        "src/frontend/ui/components/charts/timeseries",
        "src/frontend/ui/components/charts/histogram",
        "src/frontend/ui/hooks/queries",
        "src/frontend/ui/hooks/mutations",
        "src/backend/api/v1/handlers/users",
        "src/backend/api/v1/handlers/projects",
        "src/backend/api/v1/middleware/ratelimit",
        "src/backend/api/v1/middleware/cors",
        "src/backend/api/v2/handlers/users",
        "src/backend/api/v2/handlers/billing",
        "src/backend/workers/jobs/email/templates",
        "src/backend/workers/jobs/export/formats",
        "tests/unit/core/auth/providers",
        "tests/unit/core/data/processing",
        "tests/unit/frontend/components",
        "tests/unit/backend/api/v1",
        "tests/unit/backend/api/v2",
        "tests/integration/e2e/auth",
        "tests/integration/e2e/billing",
        "tests/integration/load/scenarios",
        "docs/api/v1/endpoints",
        "docs/api/v2/endpoints",
        "docs/guides/deployment/kubernetes",
        "docs/guides/deployment/docker",
        "docs/architecture/decisions/records",
        "assets/images/icons/social",
        "assets/images/icons/navigation",
        "assets/fonts/latin/variable",
        "config/environments/staging",
        "config/environments/production",
        "scripts/ci/pipelines/deploy",
        "scripts/ci/pipelines/test",
    ];

    let extensions = [
        (".rs", b"use std::collections::HashMap;\nfn process(input: &[u8]) -> Vec<u8> {\n    input.iter().map(|b| b.wrapping_add(1)).collect()\n}\n" as &[u8]),
        (".ts", b"export function transform(data: Record<string, unknown>): string {\n  return JSON.stringify(data, null, 2);\n}\n"),
        (".html", b"<div class=\"container\"><section><h2>Title</h2><p>Content goes here.</p></section></div>\n"),
        (".json", b"{\"id\": 1, \"name\": \"item\", \"tags\": [\"a\", \"b\"], \"metadata\": {\"created\": \"2025-01-01\"}}\n"),
        (".css", b".container { display: flex; gap: 1rem; }\n.header { font-size: 1.5rem; color: #333; }\n"),
        (".md", b"# Module Documentation\n\nThis module handles core processing logic.\n\n## Usage\n\n```rust\nlet result = process(&input);\n```\n"),
    ];

    let mut count = 0;

    // ~900 small-to-medium files spread across directories
    for dir in &dirs {
        for i in 0..50 {
            let (ext, template) = extensions[i % extensions.len()];
            let name = format!("{dir}/file_{i:03}{ext}");
            // Vary size: 1KB to 20KB by repeating template + pseudo-random suffix
            let repeats = 5 + (i * 7) % 100;
            w.start_file(&name, opts).unwrap();
            for _ in 0..repeats {
                w.write_all(template).unwrap();
            }
            // Add some unique bytes so compression ratios are realistic
            let suffix: Vec<u8> = (0..64).map(|_| next()).collect();
            w.write_all(&suffix).unwrap();
            count += 1;
        }
    }

    // The target CSV file (~34KB) for extract benchmarks
    w.start_file(TARGET_FILE, opts).unwrap();
    w.write_all(&b"id,name,email,score,department,created_at\n".repeat(1)).unwrap();
    for i in 0..1000 {
        let line = format!(
            "{i},user_{i},user_{i}@example.com,{},{},2025-{:02}-{:02}\n",
            50 + (i * 7) % 51,
            ["engineering", "sales", "marketing", "support", "research"][i % 5],
            1 + (i % 12),
            1 + (i % 28),
        );
        w.write_all(line.as_bytes()).unwrap();
    }
    count += 1;

    // A few large files (2-4MB each) — binary-ish with structure
    for i in 0..5 {
        let name = format!("assets/images/exports/batch_{i:02}/dataset.bin");
        w.start_file(&name, opts).unwrap();
        // 2MB of pseudo-random data with some structure (repeated blocks)
        let block: Vec<u8> = (0..4096).map(|_| next()).collect();
        for _ in 0..512 {
            w.write_all(&block).unwrap();
            // Mutate block slightly each time for realistic entropy
            let idx = next() as usize % block.len();
            let val = next();
            w.write_all(&[val ^ block[idx]]).unwrap();
        }
        count += 1;
    }

    // Root-level config files
    for name in [
        "Cargo.toml", "Cargo.lock", "README.md", "LICENSE",
        ".gitignore", "config/settings.toml", "config/environments/dev.toml",
        "config/environments/prod.toml",
    ] {
        w.start_file(name, opts).unwrap();
        let content = format!("# {name}\n").repeat(50 + name.len() * 10);
        w.write_all(content.as_bytes()).unwrap();
        count += 1;
    }

    eprintln!("Generated fixture: {count} files");
    w.finish().unwrap().into_inner()
}