|
1
|
|
|
<?php |
|
2
|
|
|
|
|
3
|
|
|
namespace App\Services\Categorization\Categorizers; |
|
4
|
|
|
|
|
5
|
|
|
use App\Models\Category; |
|
6
|
|
|
use App\Services\Categorization\CategorizationResult; |
|
7
|
|
|
use App\Services\Categorization\ReleaseContext; |
|
8
|
|
|
|
|
9
|
|
|
/** |
|
10
|
|
|
* Categorizer for miscellaneous content and hash detection. |
|
11
|
|
|
* This runs last as a fallback. |
|
12
|
|
|
*/ |
|
13
|
|
|
class MiscCategorizer extends AbstractCategorizer |
|
14
|
|
|
{ |
|
15
|
|
|
protected int $priority = 100; // Lowest priority - run last |
|
16
|
|
|
|
|
17
|
|
|
public function getName(): string |
|
18
|
|
|
{ |
|
19
|
|
|
return 'Misc'; |
|
20
|
|
|
} |
|
21
|
|
|
|
|
22
|
|
|
public function categorize(ReleaseContext $context): CategorizationResult |
|
23
|
|
|
{ |
|
24
|
|
|
$name = $context->releaseName; |
|
25
|
|
|
|
|
26
|
|
|
// Check for hash patterns first |
|
27
|
|
|
if ($result = $this->checkHash($name)) { |
|
28
|
|
|
return $result; |
|
29
|
|
|
} |
|
30
|
|
|
|
|
31
|
|
|
// Check for archive formats |
|
32
|
|
|
if ($result = $this->checkArchive($name)) { |
|
33
|
|
|
return $result; |
|
34
|
|
|
} |
|
35
|
|
|
|
|
36
|
|
|
// Check for dataset/dump patterns |
|
37
|
|
|
if ($result = $this->checkDataset($name)) { |
|
38
|
|
|
return $result; |
|
39
|
|
|
} |
|
40
|
|
|
|
|
41
|
|
|
// Check for obfuscated/encoded patterns |
|
42
|
|
|
if ($result = $this->checkObfuscated($name)) { |
|
43
|
|
|
return $result; |
|
44
|
|
|
} |
|
45
|
|
|
|
|
46
|
|
|
return $this->noMatch(); |
|
47
|
|
|
} |
|
48
|
|
|
|
|
49
|
|
|
protected function checkHash(string $name): ?CategorizationResult |
|
50
|
|
|
{ |
|
51
|
|
|
// MD5 hash (32 hex characters) |
|
52
|
|
|
if (preg_match('/\b[a-f0-9]{32}\b/i', $name)) { |
|
53
|
|
|
return $this->matched(Category::OTHER_HASHED, 0.8, 'hash_md5'); |
|
54
|
|
|
} |
|
55
|
|
|
|
|
56
|
|
|
// SHA-1 hash (40 hex characters) |
|
57
|
|
|
if (preg_match('/\b[a-f0-9]{40}\b/i', $name)) { |
|
58
|
|
|
return $this->matched(Category::OTHER_HASHED, 0.85, 'hash_sha1'); |
|
59
|
|
|
} |
|
60
|
|
|
|
|
61
|
|
|
// SHA-256 hash (64 hex characters) |
|
62
|
|
|
if (preg_match('/\b[a-f0-9]{64}\b/i', $name)) { |
|
63
|
|
|
return $this->matched(Category::OTHER_HASHED, 0.9, 'hash_sha256'); |
|
64
|
|
|
} |
|
65
|
|
|
|
|
66
|
|
|
// Generic long hex hash |
|
67
|
|
|
if (preg_match('/\b[a-f0-9]{32,128}\b/i', $name)) { |
|
68
|
|
|
return $this->matched(Category::OTHER_HASHED, 0.75, 'hash_generic'); |
|
69
|
|
|
} |
|
70
|
|
|
|
|
71
|
|
|
return null; |
|
72
|
|
|
} |
|
73
|
|
|
|
|
74
|
|
|
protected function checkArchive(string $name): ?CategorizationResult |
|
75
|
|
|
{ |
|
76
|
|
|
if (preg_match('/\.(zip|rar|7z|tar|gz|bz2|xz|tgz|tbz2|cab|iso|img|dmg|pkg|archive)$/i', $name)) { |
|
77
|
|
|
return $this->matched(Category::OTHER_MISC, 0.5, 'archive'); |
|
78
|
|
|
} |
|
79
|
|
|
|
|
80
|
|
|
return null; |
|
81
|
|
|
} |
|
82
|
|
|
|
|
83
|
|
|
protected function checkDataset(string $name): ?CategorizationResult |
|
84
|
|
|
{ |
|
85
|
|
|
// Dataset/dump patterns that aren't media |
|
86
|
|
|
if (preg_match('/\b(sql|csv|dump|backup|dataset|collection)\b/i', $name) && |
|
87
|
|
|
!preg_match('/\b(movie|tv|show|audio|video|book|game)\b/i', $name)) { |
|
88
|
|
|
return $this->matched(Category::OTHER_MISC, 0.6, 'dataset'); |
|
89
|
|
|
} |
|
90
|
|
|
|
|
91
|
|
|
// Data leaks/dumps (be careful with these) |
|
92
|
|
|
if (preg_match('/\b(leak|breach|data|database)\b/i', $name) && |
|
93
|
|
|
preg_match('/\b(dump|export|backup)\b/i', $name) && |
|
94
|
|
|
!preg_match('/\b(movie|tv|show|audio|video|book|game)\b/i', $name)) { |
|
95
|
|
|
return $this->matched(Category::OTHER_MISC, 0.6, 'data_dump'); |
|
96
|
|
|
} |
|
97
|
|
|
|
|
98
|
|
|
return null; |
|
99
|
|
|
} |
|
100
|
|
|
|
|
101
|
|
|
protected function checkObfuscated(string $name): ?CategorizationResult |
|
102
|
|
|
{ |
|
103
|
|
|
// Release names consisting only of uppercase letters and numbers |
|
104
|
|
|
if (preg_match('/^[A-Z0-9]{15,}$/', $name)) { |
|
105
|
|
|
return $this->matched(Category::OTHER_HASHED, 0.7, 'obfuscated_uppercase'); |
|
106
|
|
|
} |
|
107
|
|
|
|
|
108
|
|
|
// Mixed-case alphanumeric strings without separators (common obfuscation pattern) |
|
109
|
|
|
// These look like random strings: e.g., "AA7Jl2toE8Q53yNZmQ5R6G" |
|
110
|
|
|
if (preg_match('/^[a-zA-Z0-9]{15,}$/', $name) && |
|
111
|
|
|
!preg_match('/\b(19|20)\d{2}\b/', $name) && |
|
112
|
|
|
!preg_match('/^[A-Z][a-z]+([A-Z][a-z]+)+$/', $name)) { // Exclude CamelCase words |
|
113
|
|
|
return $this->matched(Category::OTHER_HASHED, 0.7, 'obfuscated_mixed_alphanumeric'); |
|
114
|
|
|
} |
|
115
|
|
|
|
|
116
|
|
|
// Only punctuation and numbers with no clear structure |
|
117
|
|
|
if (preg_match('/^[^a-zA-Z]*[A-Z0-9\._\-]{5,}[^a-zA-Z]*$/', $name) && |
|
118
|
|
|
!preg_match('/\.(mkv|avi|mp4|mp3|flac|pdf|epub|exe|iso)$/i', $name)) { |
|
119
|
|
|
return $this->matched(Category::OTHER_MISC, 0.5, 'obfuscated_pattern'); |
|
120
|
|
|
} |
|
121
|
|
|
|
|
122
|
|
|
return null; |
|
123
|
|
|
} |
|
124
|
|
|
} |
|
125
|
|
|
|
|
126
|
|
|
|
NNTmux /
newznab-tmux
