hunch 2.0.2

A media filename parser for movies, TV, and anime — built in Rust, inspired by guessit
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

# Subtitle language patterns.
#
# ARCHITECTURE NOTE (v0.2.1):
#   Vocabulary-based subtitle markers live here.
#   The legacy subtitle_language.rs handles ONLY algorithmic patterns:
#     - File extension codes (.eng.srt, .fr.sub)
#     - SUBFORCED with optional language prefix
#     - LANG SUBS (full language names: "English Subs")
#     - Sub.French / ST(Fr-Eng) (multi-language bracket parsing)
#     - Legendado/Subtitulado (regional conventions)
#   No overlap between TOML and legacy.

property = "subtitle_language"

# ── VOST family (French anime/TV conventions) ──────────────────────────
[exact]
vostfr   = "fr"
fastsub  = "fr"
vost     = "und"       # original version, language unspecified

# ── Compound lang+sub markers ──────────────────────────────────────────
swesub    = "Swedish"
nlsub     = "Dutch"
nlsubs    = "Dutch"
hebsub    = "Hebrew"
hebsubs   = "Hebrew"
plsub     = "Polish"
plsubs    = "Polish"
rosub     = "Romanian"
rosubs    = "Romanian"
desub     = "German"
desubs    = "German"
korsub    = "Korean"
korsubs   = "Korean"
engsub    = "English"
engsubs   = "English"
fresub    = "French"
fresubs   = "French"
itasub    = "Italian"
itasubs   = "Italian"
spasub    = "Spanish"
spasubs   = "Spanish"
dansub    = "Danish"
dansubs   = "Danish"
norsub    = "Norwegian"
norsubs   = "Norwegian"
finsub    = "Finnish"
finsubs   = "Finnish"
gresub    = "Greek"
gresubs   = "Greek"
tursub    = "Turkish"
tursubs   = "Turkish"
arasub    = "Arabic"
arasubs   = "Arabic"
russub    = "Russian"
russubs   = "Russian"
hinsub    = "Hindi"
hinsubs   = "Hindi"
chisub    = "Chinese"
chisubs   = "Chinese"
jpnsub    = "Japanese"
jpnsubs   = "Japanese"
ukrsub    = "Ukrainian"
ukrsubs   = "Ukrainian"
bulsub    = "Bulgarian"
bulsubs   = "Bulgarian"
hunsub    = "Hungarian"
hunsubs   = "Hungarian"
czesub    = "Czech"
czesubs   = "Czech"
hrvsub    = "Croatian"
hrvsubs   = "Croatian"
slksub    = "Slovak"
slksubs   = "Slovak"
ptsub     = "Portuguese"
ptsubs    = "Portuguese"
brsub     = "Portuguese"
brsubs    = "Portuguese"

# ── CJK encoding / subtitle markers ──────────────────────────────────────
big5      = "Traditional Chinese"
cht       = "Traditional Chinese"
tc        = "Traditional Chinese"
chs       = "Simplified Chinese"
sc        = "Simplified Chinese"

# ── Generic subtitle markers (language = undetermined) ───────────────────
esub        = "und"
esubs       = "und"
subbed      = "und"
subtitled   = "und"
subtitles   = "und"
subtitle    = "und"
hardsub     = "und"
hardsubs    = "und"
softsub     = "und"
softsubs    = "und"
custom      = "und"   # custom subtitles

# ── Regex patterns for separator variants ──────────────────────────────

[[patterns]]
# VOSTFR / FASTSUB.VOSTFR (2-token)
match = '(?i)^fastsub[-. ]?vostfr$'
value = "French"

[[patterns]]
# Hard-sub / Soft-sub / Hard.Sub (2-token)
match = '(?i)^(?:hard|soft|custom)[-. ]?subs?$'
value = "und"

[[patterns]]
# Multi-Sub / Multi.Subs (2-token)
match = '(?i)^multi[-. ]?subs?$'
value = "und"

[[patterns]]
# HC (hard-coded subtitles)
match = '(?i)^hc$'
value = "und"

[[patterns]]
# E-Sub / E.Sub
match = '(?i)^e[-. ]?subs?$'
value = "und"

[[patterns]]
# SUB.FR / Sub-FR / Sub.EN (2-token: language code after sub marker)
match = '(?i)^subs?[-. ]?(fr|en|es|de|it|nl|sv|no|da|fi|pl|cs|hu|ro|hr|sr|bg|uk|he|ar|ru|hi|zh|ja|ko|pt|br|ca)$'
value = "{1}"

[[patterns]]
# CHS_CHT_ENG / CHS_CHT (underscore-separated CJK subtitle language codes)
match = '(?i)^(?:CHS|CHT|ENG)(?:_(?:CHS|CHT|ENG))+$'
value = "Chinese"

[[patterns]]
# FR-SUB / EN-SUB (language code before sub marker)
match = '(?i)^(fr|en|es|de|it|nl|sv|no|da|fi|pl|cs|hu|ro|hr|sr|bg|uk|he|ar|ru|hi|zh|ja|ko|pt|br|ca)[-. ]?subs?$'
value = "{1}"