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
141
142
143
144

# Audio language patterns.
#
# ARCHITECTURE NOTE (v0.2):
#   All vocabulary-based language detection lives here.
#   The legacy language.rs is kept for:
#     - Bracketed multi-language codes: [ENG+RU+PT] — requires custom parsing
#   The "DL" (Dual Language/mul) token was previously guarded by a
#   fancy_regex lookbehind (?<!WEB[-. ]) to avoid matching inside WEB-DL.
#   With token-based matching, the pipeline zone rule "drop language spans
#   contained within a source span" replaces that lookbehind (see pipeline.rs
#   apply_zone_rules Rule 6).

property = "language"

# ── Full language names (case-insensitive exact match) ─────────────────────
[exact]
english    = "English"
french     = "French"
spanish    = "Spanish"
german     = "German"
italian    = "Italian"
portuguese = "Portuguese"
russian    = "Russian"
japanese   = "Japanese"
chinese    = "Chinese"
korean     = "Korean"
arabic     = "Arabic"
hindi      = "Hindi"
dutch      = "Dutch"
swedish    = "Swedish"
norwegian  = "Norwegian"
danish     = "Danish"
finnish    = "Finnish"
polish     = "Polish"
czech      = "Czech"
turkish    = "Turkish"
greek      = "Greek"
hungarian  = "Hungarian"
romanian   = "Romanian"
thai       = "Thai"
vietnamese = "Vietnamese"
catalan    = "Catalan"
croatian   = "Croatian"
serbian    = "Serbian"
bulgarian  = "Bulgarian"
ukrainian  = "Ukrainian"
hebrew     = "Hebrew"

# Localized language names
deutsch     = "German"
italiano    = "Italian"
castellano  = "Catalan"
dublado     = "und"       # Portuguese: "dubbed"
legendado   = "und"       # Portuguese: "subtitled"

# Broadcast / release convention tags (language-specific shortcuts)
truefrench  = "French"
vff         = "French"
vfq         = "French"
vfi         = "French"
vf2         = "French"
vf          = "French"
latino      = "Spanish"
flemish     = "nl-be"

# ISO 639-3 / common 3-letter codes
eng = "English"
ita = "Italian"
spa = "Spanish"
ger = "German"
fre = "French"
fr  = "French"
jpn = "Japanese"
rus = "Russian"
kor = "Korean"
dut = "Dutch"
por = "Portuguese"
pt  = "Portuguese"
ara = "Arabic"
hin = "Hindi"
swe = "Swedish"
nor = "Norwegian"
dan = "Danish"
fin = "Finnish"
pol = "Polish"
cze = "Czech"
tur = "Turkish"
gre = "Greek"
hun = "Hungarian"
rom = "Romanian"
tha = "Thai"
vie = "Vietnamese"
ukr = "Ukrainian"
heb = "Hebrew"
hrv = "Croatian"
srp = "Serbian"
bul = "Bulgarian"
cat = "Catalan"
mul = "mul"     # ISO 639-2 "multiple languages"
und = "und"     # undetermined

# Dual Language / Multilingual
# NOTE: "DL" on its own means Dual Language (mul), but ONLY as a standalone
# token. When part of "WEB-DL" the source rule claims the compound span first,
# and zone Rule 6 drops this language match if contained within that span.
dl    = "mul"
multi = "mul"

# ── Regex patterns for localized/variant names ────────────────────────────

[[patterns]]
# Français / Francais / Française
match = '(?i)^fran[cç]aise?$'
value = "French"

[[patterns]]
# Español Castellano / Espanol.Castellano (compound → Catalan, not Spanish)
match = '(?i)^espa[nñ]ol[-. ]castellano$'
value = "Catalan"

[[patterns]]
# Español / Espanol
match = '(?i)^espa[nñ]ol$'
value = "Spanish"

[[patterns]]
# Português / Portugues
match = '(?i)^portugu[eê]s$'
value = "Portuguese"

[[patterns]]
# MULTI / MULTiLANG / MULTiLANGUAGE
match = '(?i)^multi(?:lang(?:uage)?)?$'
value = "mul"

[[patterns]]
# Dual.Audio / Dual-Audio
match = '(?i)^dual[-. ]?audio$'
value = "und"

[[patterns]]
# 2-token: Dual Audio
match = '(?i)^dual[-. ]audio$'
value = "und"