omniparse 0.4.1

A Rust toolkit for detecting and extracting metadata, text, and content from various file formats
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
370
371
372
373
374
375
376
377
378
379
380
381
382

//! Unit tests for type detection functionality

use omniparse::detection::{TypeDetector, DetectionMethod, Detector};
use std::path::Path;

#[test]
fn test_magic_bytes_pdf_detection() {
    let detector = TypeDetector::new();
    let pdf_data = b"%PDF-1.4\n%\xE2\xE3\xCF\xD3";
    
    let result = detector.detect_from_bytes(pdf_data);
    
    assert_eq!(result.mime_type, "application/pdf");
    assert_eq!(result.detected_by, DetectionMethod::MagicBytes);
    assert!(result.confidence >= 0.9, "Magic bytes should have high confidence");
}

#[test]
fn test_magic_bytes_png_detection() {
    let detector = TypeDetector::new();
    let png_data = b"\x89PNG\r\n\x1a\n\x00\x00\x00\rIHDR";
    
    let result = detector.detect_from_bytes(png_data);
    
    assert_eq!(result.mime_type, "image/png");
    assert_eq!(result.detected_by, DetectionMethod::MagicBytes);
    assert!(result.confidence >= 0.9);
}

#[test]
fn test_magic_bytes_jpeg_detection() {
    let detector = TypeDetector::new();
    let jpeg_data = b"\xFF\xD8\xFF\xE0\x00\x10JFIF";
    
    let result = detector.detect_from_bytes(jpeg_data);
    
    assert_eq!(result.mime_type, "image/jpeg");
    assert_eq!(result.detected_by, DetectionMethod::MagicBytes);
    assert!(result.confidence >= 0.9);
}

#[test]
fn test_magic_bytes_zip_detection() {
    let detector = TypeDetector::new();
    let zip_data = b"PK\x03\x04\x14\x00\x00\x00";
    
    let result = detector.detect_from_bytes(zip_data);
    
    // ZIP signature is shared by multiple formats, first match wins
    // The detector may return any ZIP-based format
    assert!(result.mime_type.contains("zip") || 
            result.mime_type.contains("openxmlformats") ||
            result.mime_type.contains("oasis"));
    assert_eq!(result.detected_by, DetectionMethod::MagicBytes);
    assert!(result.confidence >= 0.9);
}

#[test]
fn test_magic_bytes_gzip_detection() {
    let detector = TypeDetector::new();
    let gzip_data = b"\x1F\x8B\x08\x00\x00\x00\x00\x00";
    
    let result = detector.detect_from_bytes(gzip_data);
    
    assert_eq!(result.mime_type, "application/gzip");
    assert_eq!(result.detected_by, DetectionMethod::MagicBytes);
    assert!(result.confidence >= 0.9);
}

#[test]
fn test_content_analysis_json_detection() {
    let detector = TypeDetector::new();
    let json_data = b"{\"key\": \"value\", \"number\": 42}";
    
    let result = detector.detect_from_bytes(json_data);
    
    assert_eq!(result.mime_type, "application/json");
    // JSON starting with { has magic bytes pattern, so it's detected as MagicBytes
    assert_eq!(result.detected_by, DetectionMethod::MagicBytes);
    assert!(result.confidence >= 0.9);
}

#[test]
fn test_content_analysis_json_array_detection() {
    let detector = TypeDetector::new();
    let json_data = b"[1, 2, 3, 4, 5]";
    
    let result = detector.detect_from_bytes(json_data);
    
    assert_eq!(result.mime_type, "application/json");
    // JSON starting with [ has magic bytes pattern, so it's detected as MagicBytes
    assert_eq!(result.detected_by, DetectionMethod::MagicBytes);
}

#[test]
fn test_content_analysis_xml_detection() {
    let detector = TypeDetector::new();
    let xml_data = b"<?xml version=\"1.0\"?><root><element>text</element></root>";
    
    let result = detector.detect_from_bytes(xml_data);
    
    // XML starting with <?xml has magic bytes pattern
    assert!(result.mime_type == "text/xml" || result.mime_type == "image/svg+xml");
    assert_eq!(result.detected_by, DetectionMethod::MagicBytes);
    assert!(result.confidence >= 0.9);
}

#[test]
fn test_content_analysis_html_detection() {
    let detector = TypeDetector::new();
    let html_data = b"<html><head><title>Test</title></head><body>Content</body></html>";
    
    let result = detector.detect_from_bytes(html_data);
    
    assert_eq!(result.mime_type, "text/html");
    // HTML starting with <html has magic bytes pattern
    assert_eq!(result.detected_by, DetectionMethod::MagicBytes);
}

#[test]
fn test_content_analysis_csv_detection() {
    let detector = TypeDetector::new();
    let csv_data = b"name,age,city\nJohn,30,NYC\nJane,25,LA";
    
    let result = detector.detect_from_bytes(csv_data);
    
    assert_eq!(result.mime_type, "text/csv");
    assert_eq!(result.detected_by, DetectionMethod::ContentAnalysis);
}

#[test]
fn test_content_analysis_plain_text_detection() {
    let detector = TypeDetector::new();
    let text_data = b"This is just plain text without any special formatting.";
    
    let result = detector.detect_from_bytes(text_data);
    
    assert_eq!(result.mime_type, "text/plain");
    assert_eq!(result.detected_by, DetectionMethod::ContentAnalysis);
}

#[test]
fn test_extension_fallback_pdf() {
    let detector = TypeDetector::new();
    // Binary data that doesn't match any magic bytes but is valid UTF-8
    // Use non-UTF-8 bytes to avoid content analysis detecting it as text
    let unknown_data = b"\xFF\xFE\x00\x01\x02\x03\x04\x05";
    
    let result = detector.detect(unknown_data, Some("document.pdf"));
    
    assert_eq!(result.mime_type, "application/pdf");
    assert_eq!(result.detected_by, DetectionMethod::Extension);
    assert!(result.confidence >= 0.3 && result.confidence <= 0.5);
}

#[test]
fn test_extension_fallback_docx() {
    let detector = TypeDetector::new();
    let unknown_data = b"\xFF\xFE\x00\x01\x02\x03\x04\x05";
    
    let result = detector.detect(unknown_data, Some("report.docx"));
    
    assert_eq!(result.mime_type, "application/vnd.openxmlformats-officedocument.wordprocessingml.document");
    assert_eq!(result.detected_by, DetectionMethod::Extension);
}

#[test]
fn test_extension_fallback_jpeg() {
    let detector = TypeDetector::new();
    let unknown_data = b"\xFF\xFE\x00\x01\x02\x03\x04\x05";
    
    let result = detector.detect(unknown_data, Some("photo.jpg"));
    
    assert_eq!(result.mime_type, "image/jpeg");
    assert_eq!(result.detected_by, DetectionMethod::Extension);
}

#[test]
fn test_extension_fallback_case_insensitive() {
    let detector = TypeDetector::new();
    let unknown_data = b"\xFF\xFE\x00\x01\x02\x03\x04\x05";
    
    let result = detector.detect(unknown_data, Some("FILE.PDF"));
    
    assert_eq!(result.mime_type, "application/pdf");
    assert_eq!(result.detected_by, DetectionMethod::Extension);
}

#[test]
fn test_unknown_file_type_no_magic_no_extension() {
    let detector = TypeDetector::new();
    // Use non-UTF-8 bytes to avoid being detected as text
    let unknown_data = b"\xFF\xFE\xFD\xFC\xFB\xFA\xF9\xF8\xF7\xF6";
    
    let result = detector.detect_from_bytes(unknown_data);
    
    assert_eq!(result.mime_type, "application/octet-stream");
    assert_eq!(result.detected_by, DetectionMethod::Unknown);
    assert!(result.confidence < 0.2, "Unknown type should have very low confidence");
}

#[test]
fn test_unknown_file_type_with_unsupported_extension() {
    let detector = TypeDetector::new();
    let unknown_data = b"\xFF\xFE\xFD\xFC\xFB\xFA";
    
    let result = detector.detect(unknown_data, Some("file.xyz"));
    
    assert_eq!(result.mime_type, "application/octet-stream");
    assert_eq!(result.detected_by, DetectionMethod::Unknown);
}

#[test]
fn test_empty_file_detection() {
    let detector = TypeDetector::new();
    let empty_data = b"";
    
    let result = detector.detect_from_bytes(empty_data);
    
    assert_eq!(result.mime_type, "application/octet-stream");
    assert_eq!(result.detected_by, DetectionMethod::Unknown);
}

#[test]
fn test_confidence_scoring_magic_bytes() {
    let detector = TypeDetector::new();
    let pdf_data = b"%PDF-1.7";
    
    let result = detector.detect_from_bytes(pdf_data);
    
    assert!(result.confidence >= 0.9 && result.confidence <= 1.0,
        "Magic bytes detection should have 0.9-1.0 confidence, got {}", result.confidence);
}

#[test]
fn test_confidence_scoring_content_analysis() {
    let detector = TypeDetector::new();
    // Use plain text that will be detected via content analysis, not magic bytes
    let text_data = b"This is some plain text without special formatting or structure.";
    
    let result = detector.detect_from_bytes(text_data);
    
    assert_eq!(result.detected_by, DetectionMethod::ContentAnalysis);
    assert!(result.confidence >= 0.6 && result.confidence <= 0.8,
        "Content analysis should have 0.6-0.8 confidence, got {}", result.confidence);
}

#[test]
fn test_confidence_scoring_extension() {
    let detector = TypeDetector::new();
    let unknown_data = b"\xFF\xFE\xFD\xFC";
    
    let result = detector.detect(unknown_data, Some("test.txt"));
    
    assert_eq!(result.detected_by, DetectionMethod::Extension);
    assert!(result.confidence >= 0.3 && result.confidence <= 0.5,
        "Extension detection should have 0.3-0.5 confidence, got {}", result.confidence);
}

#[test]
fn test_magic_bytes_priority_over_content_analysis() {
    let detector = TypeDetector::new();
    // PDF magic bytes at start, but also looks like text
    let pdf_data = b"%PDF-1.4\nSome text content";
    
    let result = detector.detect_from_bytes(pdf_data);
    
    assert_eq!(result.mime_type, "application/pdf");
    assert_eq!(result.detected_by, DetectionMethod::MagicBytes);
}

#[test]
fn test_content_analysis_priority_over_extension() {
    let detector = TypeDetector::new();
    // JSON content but wrong extension
    let json_data = b"{\"key\": \"value\"}";
    
    let result = detector.detect(json_data, Some("file.txt"));
    
    assert_eq!(result.mime_type, "application/json");
    // JSON has magic bytes pattern, so it's detected as MagicBytes (which has higher priority)
    assert_eq!(result.detected_by, DetectionMethod::MagicBytes);
}

#[test]
fn test_detect_from_path_with_real_file() {
    let detector = TypeDetector::new();
    
    // Test with an actual test file
    let result = detector.detect_from_path(Path::new("test_data/document/sample.pdf"));
    
    assert!(result.is_ok());
    let result = result.unwrap();
    assert_eq!(result.mime_type, "application/pdf");
}

#[test]
fn test_tar_magic_bytes_with_offset() {
    let detector = TypeDetector::new();
    // TAR has magic bytes at offset 257
    let mut tar_data = vec![0u8; 262];
    tar_data[257..262].copy_from_slice(b"ustar");
    
    let result = detector.detect_from_bytes(&tar_data);
    
    assert_eq!(result.mime_type, "application/x-tar");
    assert_eq!(result.detected_by, DetectionMethod::MagicBytes);
}

#[test]
fn test_svg_xml_detection() {
    let detector = TypeDetector::new();
    let svg_data = b"<svg xmlns=\"http://www.w3.org/2000/svg\"><circle r=\"50\"/></svg>";
    
    let result = detector.detect_from_bytes(svg_data);
    
    assert_eq!(result.mime_type, "image/svg+xml");
    // SVG starting with <svg has magic bytes pattern
    assert_eq!(result.detected_by, DetectionMethod::MagicBytes);
}

#[test]
fn test_multiple_zip_based_formats() {
    let detector = TypeDetector::new();
    let zip_signature = b"PK\x03\x04";
    
    // All these formats share the ZIP signature
    // Detection should succeed but may not distinguish between them without deeper analysis
    let result = detector.detect_from_bytes(zip_signature);
    
    // Should detect as some ZIP-based format
    assert!(result.mime_type.contains("zip") || 
            result.mime_type.contains("openxmlformats") ||
            result.mime_type.contains("oasis"));
    assert_eq!(result.detected_by, DetectionMethod::MagicBytes);
}

#[test]
fn test_tiff_little_endian() {
    let detector = TypeDetector::new();
    let tiff_data = b"\x49\x49\x2A\x00";
    
    let result = detector.detect_from_bytes(tiff_data);
    
    assert_eq!(result.mime_type, "image/tiff");
    assert_eq!(result.detected_by, DetectionMethod::MagicBytes);
}

#[test]
fn test_tiff_big_endian() {
    let detector = TypeDetector::new();
    let tiff_data = b"\x4D\x4D\x00\x2A";
    
    let result = detector.detect_from_bytes(tiff_data);
    
    assert_eq!(result.mime_type, "image/tiff");
    assert_eq!(result.detected_by, DetectionMethod::MagicBytes);
}

#[test]
fn test_detector_trait_implementation() {
    let detector = TypeDetector::new();
    let pdf_data = b"%PDF-1.5";
    
    // Test using the Detector trait
    let result = detector.detect(pdf_data, None);
    
    assert_eq!(result.mime_type, "application/pdf");
    assert_eq!(result.detected_by, DetectionMethod::MagicBytes);
}

#[test]
fn test_detector_trait_with_filename() {
    let detector = TypeDetector::new();
    let unknown_data = b"\xFF\xFE\xFD\xFC";
    
    // Test using the Detector trait with filename
    let result = detector.detect(unknown_data, Some("document.pdf"));
    
    assert_eq!(result.mime_type, "application/pdf");
    assert_eq!(result.detected_by, DetectionMethod::Extension);
}