sdoppia 0.7.0

A CLI tool to scan directories, hash files, and find duplicate files
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

use std::{
    fs,
    path::Path,
    process::{Command, Output},
};

use tempfile::TempDir;

fn sdoppia_bin() -> &'static str {
    env!("CARGO_BIN_EXE_sdoppia")
}

fn run(args: &[&str]) -> Output {
    Command::new(sdoppia_bin())
        .args(args)
        // The binary's tracing filter honors RUST_LOG; keep test output
        // deterministic regardless of the caller's environment.
        .env_remove("RUST_LOG")
        .output()
        .expect("failed to run sdoppia binary")
}

fn stdout(output: &Output) -> String {
    String::from_utf8_lossy(&output.stdout).into_owned()
}

fn stderr(output: &Output) -> String {
    String::from_utf8_lossy(&output.stderr).into_owned()
}

#[test]
fn scan_nonexistent_path_fails_with_nonzero_exit() {
    let tmp = TempDir::new().unwrap();
    let db = tmp.path().join("test.db");

    let output = run(&[
        "scan",
        "/definitely/not/a/real/path",
        "--db",
        db.to_str().unwrap(),
    ]);

    assert!(
        !output.status.success(),
        "scan of a nonexistent path must fail, got: {}",
        stdout(&output)
    );
    assert!(
        stderr(&output).contains("Invalid directory path"),
        "stderr should report the invalid path, got: {}",
        stderr(&output)
    );
}

#[test]
fn scan_finds_duplicates_and_reports_them() {
    let tmp = TempDir::new().unwrap();
    let dir = tmp.path().join("files");
    fs::create_dir_all(&dir).unwrap();

    // Two identical files and one unique file.
    fs::write(dir.join("a.txt"), b"hello world\n").unwrap();
    fs::write(dir.join("b.txt"), b"hello world\n").unwrap();
    fs::write(dir.join("c.txt"), b"unique content 12345\n").unwrap();

    let db = tmp.path().join("test.db");
    let report = tmp.path().join("report.txt");

    let output = run(&[
        "scan",
        dir.to_str().unwrap(),
        "--db",
        db.to_str().unwrap(),
        "--output",
        report.to_str().unwrap(),
    ]);
    assert!(output.status.success(), "scan failed: {}", stderr(&output));

    let report_text = fs::read_to_string(&report).unwrap();
    assert!(report_text.contains("Duplicate groups: 1"), "{report_text}");
    assert!(
        report_text.contains("Total duplicate files: 1"),
        "{report_text}"
    );
    assert!(report_text.contains("a.txt"), "{report_text}");
    assert!(report_text.contains("b.txt"), "{report_text}");
    assert!(!report_text.contains("c.txt"), "{report_text}");
}

#[test]
fn stats_and_clear_reflect_database_contents() {
    let tmp = TempDir::new().unwrap();
    let dir = tmp.path().join("files");
    fs::create_dir_all(&dir).unwrap();
    fs::write(dir.join("a.txt"), b"hello world\n").unwrap();
    fs::write(dir.join("b.txt"), b"hello world\n").unwrap();

    let db = tmp.path().join("test.db");

    let scan = run(&["scan", dir.to_str().unwrap(), "--db", db.to_str().unwrap()]);
    assert!(scan.status.success(), "scan failed: {}", stderr(&scan));

    let stats = run(&["stats", "--db", db.to_str().unwrap()]);
    assert!(stats.status.success());
    assert!(
        stdout(&stats).contains("Total files: 2"),
        "stats should report 2 files, got: {}",
        stdout(&stats)
    );
    assert!(
        stdout(&stats).contains("Duplicate files: 1"),
        "stats should report 1 duplicate, got: {}",
        stdout(&stats)
    );

    let clear = run(&["clear", "--db", db.to_str().unwrap()]);
    assert!(clear.status.success());

    let stats_after = run(&["stats", "--db", db.to_str().unwrap()]);
    assert!(stats_after.status.success());
    assert!(
        stdout(&stats_after).contains("Total files: 0"),
        "stats after clear should report 0 files, got: {}",
        stdout(&stats_after)
    );
}

#[test]
fn rescan_skips_unchanged_files() {
    let tmp = TempDir::new().unwrap();
    let dir = tmp.path().join("files");
    fs::create_dir_all(&dir).unwrap();
    fs::write(dir.join("a.txt"), b"hello world\n").unwrap();

    let db = tmp.path().join("test.db");

    let first = run(&["scan", dir.to_str().unwrap(), "--db", db.to_str().unwrap()]);
    assert!(
        first.status.success(),
        "first scan failed: {}",
        stderr(&first)
    );

    // Second scan of unchanged files must succeed and not error.
    let second = run(&["scan", dir.to_str().unwrap(), "--db", db.to_str().unwrap()]);
    assert!(
        second.status.success(),
        "second scan failed: {}",
        stderr(&second)
    );

    let stats = run(&["stats", "--db", db.to_str().unwrap()]);
    assert!(stats.status.success());
    assert!(
        stdout(&stats).contains("Total files: 1"),
        "stats should still report 1 file, got: {}",
        stdout(&stats)
    );
}

#[test]
fn scan_single_file_path() {
    let tmp = TempDir::new().unwrap();
    let file = tmp.path().join("solo.txt");
    fs::write(&file, b"hello world\n").unwrap();

    let db = tmp.path().join("test.db");
    let output = run(&["scan", file.to_str().unwrap(), "--db", db.to_str().unwrap()]);
    assert!(
        output.status.success(),
        "scanning a single file failed: {}",
        stderr(&output)
    );

    let stats = run(&["stats", "--db", db.to_str().unwrap()]);
    assert!(stdout(&stats).contains("Total files: 1"));
}

#[test]
fn min_size_filters_small_files_from_report() {
    let tmp = TempDir::new().unwrap();
    let dir = tmp.path().join("files");
    fs::create_dir_all(&dir).unwrap();
    fs::write(dir.join("a.txt"), b"hello world\n").unwrap();
    fs::write(dir.join("b.txt"), b"hello world\n").unwrap();

    let db = tmp.path().join("test.db");
    let report = tmp.path().join("report.txt");

    let scan = run(&[
        "scan",
        dir.to_str().unwrap(),
        "--db",
        db.to_str().unwrap(),
        "--output",
        report.to_str().unwrap(),
        "--min-size",
        "1000000",
    ]);
    assert!(scan.status.success(), "scan failed: {}", stderr(&scan));

    let report_text = fs::read_to_string(&report).unwrap();
    assert!(
        report_text.contains("Duplicate groups: 0"),
        "small duplicates should be filtered out by min-size, got: {report_text}"
    );
}

#[test]
fn db_path_is_respected() {
    let tmp = TempDir::new().unwrap();
    let dir = tmp.path().join("files");
    fs::create_dir_all(&dir).unwrap();
    fs::write(dir.join("a.txt"), b"hello world\n").unwrap();

    let db = tmp.path().join("custom.db");
    let scan = run(&["scan", dir.to_str().unwrap(), "--db", db.to_str().unwrap()]);
    assert!(scan.status.success(), "scan failed: {}", stderr(&scan));
    assert!(Path::new(&db).exists(), "custom db file should exist");
}