tzip 0.1.2

Create, update, and validate TorrentZip-formatted ZIP files
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
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369

//! Comprehensive TorrentZip validation tests

use std::fs;
use std::path::PathBuf;
use tzip::{TorrentZipValidator, TorrentZipWriter};

fn test_dir() -> PathBuf {
    PathBuf::from(env!("CARGO_MANIFEST_DIR")).join("tests")
}

// ============================================================================
// BYTE-IDENTICAL TESTS
// ============================================================================

#[test]
fn test_byte_identical_single_file() {
    let original = fs::read(test_dir().join("22vp931_orig.zip")).expect("Failed to read original");
    let file_data = fs::read(test_dir().join("at-6-1_a.bin")).expect("Failed to read test data");

    let mut buffer = Vec::new();
    {
        let mut tz = TorrentZipWriter::new(&mut buffer);
        tz.add_file("at-6-1_a.bin", &file_data).expect("Failed to add file");
        tz.finish().expect("Failed to finish");
    }

    assert_eq!(original.len(), buffer.len(), "ZIP sizes should match");
    assert_eq!(original, buffer, "Generated ZIP should match original byte-for-byte");
}

#[test]
fn test_byte_identical_empty_file() {
    // Create a TorrentZip with an empty file
    let mut buffer1 = Vec::new();
    {
        let mut tz = TorrentZipWriter::new(&mut buffer1);
        tz.add_file("empty.txt", &[]).expect("Failed to add empty file");
        tz.finish().expect("Failed to finish");
    }

    // Should produce deterministic output
    let mut buffer2 = Vec::new();
    {
        let mut tz = TorrentZipWriter::new(&mut buffer2);
        tz.add_file("empty.txt", &[]).expect("Failed to add empty file");
        tz.finish().expect("Failed to finish");
    }

    assert_eq!(buffer1, buffer2, "Empty file should produce identical output");
}

#[test]
fn test_byte_identical_multiple_files() {
    // Create a TorrentZip with multiple files
    let file1 = b"Hello, World! This is file 1.";
    let file2 = b"This is file 2 with different content.";
    let file3 = b"And this is file 3.";

    let mut buffer1 = Vec::new();
    {
        let mut tz = TorrentZipWriter::new(&mut buffer1);
        tz.add_file("z_file.txt", file3).expect("Failed to add file");
        tz.add_file("a_file.txt", file1).expect("Failed to add file");
        tz.add_file("m_file.txt", file2).expect("Failed to add file");
        tz.finish().expect("Failed to finish");
    }

    // Generate again - should be identical
    let mut buffer2 = Vec::new();
    {
        let mut tz = TorrentZipWriter::new(&mut buffer2);
        tz.add_file("z_file.txt", file3).expect("Failed to add file");
        tz.add_file("a_file.txt", file1).expect("Failed to add file");
        tz.add_file("m_file.txt", file2).expect("Failed to add file");
        tz.finish().expect("Failed to finish");
    }

    assert_eq!(buffer1, buffer2, "Multiple files should produce identical output");

    // Verify files are sorted by lowercase name
    let result = TorrentZipValidator::validate(&buffer1[..]).expect("Validation failed");
    assert!(result.is_valid, "Should be valid TorrentZip");
    assert_eq!(result.files, vec!["a_file.txt", "m_file.txt", "z_file.txt"]);
}

// ============================================================================
// VALIDATION TESTS - VALID TORRENTZIP
// ============================================================================

#[test]
fn test_validate_known_good_torrentzip() {
    let original = fs::read(test_dir().join("22vp931_orig.zip")).expect("Failed to read original");

    let result = TorrentZipValidator::validate(&original[..]).expect("Validation failed");

    eprintln!("Validation result: {:?}", result);

    assert!(result.is_valid, "Known-good TorrentZip should validate");
    assert!(result.torrentzip_crc32.is_some());
    assert_eq!(result.files.len(), 1);
    assert_eq!(result.files, vec!["at-6-1_a.bin"]);
}

#[test]
fn test_validate_generated_torrentzip() {
    let file_data = fs::read(test_dir().join("at-6-1_a.bin")).expect("Failed to read test data");

    let mut buffer = Vec::new();
    {
        let mut tz = TorrentZipWriter::new(&mut buffer);
        tz.add_file("at-6-1_a.bin", &file_data).expect("Failed to add file");
        tz.finish().expect("Failed to finish");
    }

    let result = TorrentZipValidator::validate(&buffer[..]).expect("Validation failed");

    assert!(result.is_valid, "Generated TorrentZip should validate");
    assert!(result.torrentzip_crc32.is_some());
    assert_eq!(result.files.len(), 1);
}

#[test]
fn test_validate_crc32_matches() {
    let file_data = fs::read(test_dir().join("at-6-1_a.bin")).expect("Failed to read test data");

    let mut buffer = Vec::new();
    let mut tz = TorrentZipWriter::new(&mut buffer);
    tz.add_file("at-6-1_a.bin", &file_data).expect("Failed to add file");
    tz.finish().expect("Failed to finish");
    let tz_crc = tz.torrentzip_crc32().expect("Should have CRC32");

    let result = TorrentZipValidator::validate(&buffer[..]).expect("Validation failed");

    assert!(result.is_valid);
    assert_eq!(result.torrentzip_crc32, Some(tz_crc));
    assert_eq!(result.computed_crc32, tz_crc);
}

// ============================================================================
// VALIDATION TESTS - INVALID TORRENTZIP
// ============================================================================

#[test]
fn test_validate_non_torrentzip_no_comment() {
    // Create a minimal ZIP without TorrentZip comment using raw bytes
    // This is a stored (not compressed) ZIP without the proper comment
    let mut buffer: Vec<u8> = Vec::new();

    // Local file header
    buffer.extend_from_slice(&[0x50, 0x4b, 0x03, 0x04]); // signature
    buffer.extend_from_slice(&[0x0a, 0x00]); // version needed
    buffer.extend_from_slice(&[0x00, 0x00]); // general flag
    buffer.extend_from_slice(&[0x00, 0x00]); // stored
    buffer.extend_from_slice(&[0x00, 0x00]); // time
    buffer.extend_from_slice(&[0x00, 0x00]); // date
    buffer.extend_from_slice(&[0x00, 0x00, 0x00, 0x00]); // crc32
    buffer.extend_from_slice(&[0x04, 0x00, 0x00, 0x00]); // compressed size
    buffer.extend_from_slice(&[0x04, 0x00, 0x00, 0x00]); // uncompressed size
    buffer.extend_from_slice(&[0x04, 0x00]); // filename len
    buffer.extend_from_slice(&[0x00, 0x00]); // extra len
    buffer.extend_from_slice(b"test"); // filename
    buffer.extend_from_slice(b"data"); // file data

    // Central directory
    let cd_offset = buffer.len();
    buffer.extend_from_slice(&[0x50, 0x4b, 0x01, 0x02]); // signature
    buffer.extend_from_slice(&[0x00, 0x00]); // version made by
    buffer.extend_from_slice(&[0x0a, 0x00]); // version needed
    buffer.extend_from_slice(&[0x00, 0x00]); // general flag
    buffer.extend_from_slice(&[0x00, 0x00]); // stored
    buffer.extend_from_slice(&[0x00, 0x00]); // time
    buffer.extend_from_slice(&[0x00, 0x00]); // date
    buffer.extend_from_slice(&[0x00, 0x00, 0x00, 0x00]); // crc32
    buffer.extend_from_slice(&[0x04, 0x00, 0x00, 0x00]); // compressed size
    buffer.extend_from_slice(&[0x04, 0x00, 0x00, 0x00]); // uncompressed size
    buffer.extend_from_slice(&[0x04, 0x00]); // filename len
    buffer.extend_from_slice(&[0x00, 0x00]); // extra len
    buffer.extend_from_slice(&[0x00, 0x00]); // comment len
    buffer.extend_from_slice(&[0x00, 0x00]); // disk start
    buffer.extend_from_slice(&[0x00, 0x00]); // internal attr
    buffer.extend_from_slice(&[0x00, 0x00, 0x00, 0x00]); // external attr
    buffer.extend_from_slice(&(0u32).to_le_bytes()); // local offset
    buffer.extend_from_slice(b"test"); // filename

    let cd_size = buffer.len() - cd_offset;

    // EOCD
    buffer.extend_from_slice(&[0x50, 0x4b, 0x05, 0x06]); // signature
    buffer.extend_from_slice(&[0x00, 0x00]); // disk num
    buffer.extend_from_slice(&[0x00, 0x00]); // cd disk
    buffer.extend_from_slice(&[0x01, 0x00]); // entries on disk
    buffer.extend_from_slice(&[0x01, 0x00]); // total entries
    buffer.extend_from_slice(&(cd_size as u32).to_le_bytes()); // cd size
    buffer.extend_from_slice(&(cd_offset as u32).to_le_bytes()); // cd offset
    buffer.extend_from_slice(&[0x00, 0x00]); // comment len

    let result = TorrentZipValidator::validate(&buffer[..]).expect("Validation failed");

    assert!(!result.is_valid, "Non-TorrentZip should fail validation");
    assert!(result.errors.iter().any(|e| matches!(e, tzip::ValidationError::InvalidComment)));
}

#[test]
fn test_validate_corrupted_crc() {
    let file_data = fs::read(test_dir().join("at-6-1_a.bin")).expect("Failed to read test data");

    let mut buffer = Vec::new();
    {
        let mut tz = TorrentZipWriter::new(&mut buffer);
        tz.add_file("at-6-1_a.bin", &file_data).expect("Failed to add file");
        tz.finish().expect("Failed to finish");
    }

    // Corrupt the CRC32 in the comment by changing one hex digit to another valid hex
    // Comment is "TORRENTZIPPED-XXXXXXXX" (22 bytes at end of file)
    // Change first hex digit of CRC32
    let comment_start = buffer.len() - 22;
    let crc_start = comment_start + 14; // Position of first CRC hex digit
    
    // Swap 'F' <-> '0' (both valid hex)
    if buffer[crc_start] == b'F' {
        buffer[crc_start] = b'0';
    } else {
        buffer[crc_start] = b'F';
    }

    let result = TorrentZipValidator::validate(&buffer[..]).expect("Validation failed");

    assert!(!result.is_valid, "Corrupted CRC should fail validation");
    assert!(
        result.errors.iter().any(|e| matches!(e, tzip::ValidationError::CommentCrcMismatch { .. })),
        "Should have CommentCrcMismatch error, got: {:?}",
        result.errors
    );
}

#[test]
fn test_validate_truncated_file() {
    let data = [0x50, 0x4b]; // Just the start of a ZIP signature

    let result = TorrentZipValidator::validate(&data[..]).expect("Validation should not crash");

    assert!(!result.is_valid);
}

#[test]
fn test_validate_empty_file() {
    let data: [u8; 0] = [];

    let result = TorrentZipValidator::validate(&data[..]).expect("Validation should not crash");

    assert!(!result.is_valid);
}

// ============================================================================
// PATH NORMALIZATION TESTS
// ============================================================================

#[test]
fn test_path_normalization_backslashes() {
    // Backslashes should be normalized to forward slashes
    // This ensures ZIP spec compliance regardless of input path format
    let mut buffer1 = Vec::new();
    {
        let mut tz = TorrentZipWriter::new(&mut buffer1);
        tz.add_file("subdir\\file.bin", b"data").expect("Failed to add file");
        tz.add_file("nested\\deep\\file.bin", b"data2").expect("Failed to add file");
        tz.finish().expect("Failed to finish");
    }

    let mut buffer2 = Vec::new();
    {
        let mut tz = TorrentZipWriter::new(&mut buffer2);
        tz.add_file("subdir/file.bin", b"data").expect("Failed to add file");
        tz.add_file("nested/deep/file.bin", b"data2").expect("Failed to add file");
        tz.finish().expect("Failed to finish");
    }

    // Both should produce identical output (backslashes normalized to forward slashes)
    assert_eq!(buffer1, buffer2, "Backslashes should be normalized to forward slashes");

    // Validate the result - files should have forward slashes
    let result = TorrentZipValidator::validate(&buffer1[..]).expect("Validation failed");
    assert!(result.is_valid, "Should be valid TorrentZip");
    // Files are sorted by lowercase name
    assert_eq!(result.files, vec!["nested/deep/file.bin", "subdir/file.bin"]);
}

#[test]
fn test_path_normalization_deterministic() {
    // Path normalization should not affect determinism
    let file_data = b"Test content for path normalization";

    let mut buffer1 = Vec::new();
    {
        let mut tz = TorrentZipWriter::new(&mut buffer1);
        tz.add_file("path\\to\\file.txt", file_data).expect("Failed to add file");
        tz.finish().expect("Failed to finish");
    }

    let mut buffer2 = Vec::new();
    {
        let mut tz = TorrentZipWriter::new(&mut buffer2);
        tz.add_file("path/to/file.txt", file_data).expect("Failed to add file");
        tz.finish().expect("Failed to finish");
    }

    assert_eq!(buffer1, buffer2, "Normalized paths should produce identical output");
}

// ============================================================================
// DETERMINISM TESTS
// ============================================================================

#[test]
fn test_determinism_same_content() {
    let file_data = fs::read(test_dir().join("at-6-1_a.bin")).expect("Failed to read test data");

    // Generate 5 times
    let outputs: Vec<Vec<u8>> = (0..5)
        .map(|_| {
            let mut buffer = Vec::new();
            let mut tz = TorrentZipWriter::new(&mut buffer);
            tz.add_file("at-6-1_a.bin", &file_data).expect("Failed to add file");
            tz.finish().expect("Failed to finish");
            buffer
        })
        .collect();

    // All should be identical
    for (i, output) in outputs.iter().enumerate().skip(1) {
        assert_eq!(
            outputs[0], *output,
            "Output {} should be identical to output 0",
            i
        );
    }
}

#[test]
fn test_determinism_case_sorting() {
    // Files with different cases should be sorted case-insensitively
    let mut buffer1 = Vec::new();
    {
        let mut tz = TorrentZipWriter::new(&mut buffer1);
        tz.add_file("Z_FILE.BIN", b"data1").expect("Failed to add file");
        tz.add_file("a_file.bin", b"data2").expect("Failed to add file");
        tz.add_file("M_File.Bin", b"data3").expect("Failed to add file");
        tz.finish().expect("Failed to finish");
    }

    let mut buffer2 = Vec::new();
    {
        let mut tz = TorrentZipWriter::new(&mut buffer2);
        // Add in different order
        tz.add_file("M_File.Bin", b"data3").expect("Failed to add file");
        tz.add_file("Z_FILE.BIN", b"data1").expect("Failed to add file");
        tz.add_file("a_file.bin", b"data2").expect("Failed to add file");
        tz.finish().expect("Failed to finish");
    }

    assert_eq!(buffer1, buffer2, "Files should be sorted case-insensitively");

    // Validate the result
    let result = TorrentZipValidator::validate(&buffer1[..]).expect("Validation failed");
    assert!(result.is_valid);
    // Sorted by lowercase: a_file.bin, M_File.Bin, Z_FILE.BIN
    assert_eq!(result.files, vec!["a_file.bin", "M_File.Bin", "Z_FILE.BIN"]);
}