/etc/ucto/tokconfig-it is in ucto 0.5.3-3.1ubuntu2.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 | [RULES]
%include url
%include e-mail
#Ex: (dis)information
WORD-PARPREFIX=(?:\p{Ps}\p{L}+[\p{Pc}\p{Pd}]?\p{Pe}[\p{Pc}\p{Pd}]?)\p{L}+(?:[\p{Pc}\p{Pd}]\p{L}+)*
#Ex: understand(s)
WORD-PARSUFFIX=\p{L}+(?:[\p{Pc}\p{Pd}]\p{L}+)*(?:[\p{Pc}\p{Pd}]?\p{Ps}[\p{Pc}\p{Pd}]?\p{L}+\p{Pe})
#Keep dash/underscore connected parts (even if they are in parenthesis)
WORD-COMPOUND=\p{L}+(?:[\p{Pc}\p{Pd}]\p{L}+)+
#Abbreviations with multiple periods
ABBREVIATION=^(\p{L}{1,3}(?:\.\p{L}{1,3})+\.?)\Z
#retain initials
INITIAL=^(?:\p{Lt}|\p{Lu})\.$
#Homogeneous punctuation (ellipsis etc)
PUNCTUATION-MULTI=(?:\.|\-|[!\?]){2,}
#Date
DATE=\p{N}{1,2}-\p{N}{1,2}-\p{N}{2,4}
DATE-REVERSE=\p{N}{4}-\p{N}{1,2}-\p{N}{1,2}
NUMBER-YEAR=('\p{N}{2})(?:\P{N}|\z)
#NUMBER-YEAR=('\p{N}{2})\P{N}
#Times
TIME=\p{N}{1,2}:\p{N}{1,2}(?::\p{N})?(?i:am|pm)?
#retain digits, including those starting with initial period (.22), and negative numbers
NUMBER=-?(?:[\.,]?\p{N}+)+
CURRENCY=\p{Sc}
WORD=[\p{L}\p{Mn}]+
PUNCTUATION=\p{P}
UNKNOWN=.
[PREFIXES]
l['`]
d['`]
m['`]
t['`]
s['`]
c['`]
dell['`]
dall['`]
nell['`]
all['`]
sull['`]
quell['`]
quest['`]
e['`]
un['`]
senz['`]
com['`]
cos['`]
anch['`]
dev['`]
[SUFFIXES]
[ORDINALS]
o
a
[TOKENS]
l['`]
d['`]
m['`]
t['`]
s['`]
c['`]
dell['`]
dall['`]
nell['`]
all['`]
sull['`]
quell['`]
quest['`]
e['`]
un['`]
senz['`]
com['`]
cos['`]
anch['`]
dev['`]
[UNITS]
km
m
cm
mm
g
kg
C
l
s
sec
min
gb
mb
kb
[CURRENCY]
EUR
[ABBREVIATIONS]
[EOSMARKERS]
# Character: !
# Name: EXCLAMATION MARK
# Code: 33 (0x21)
\u0021
# Character: ?
# Name: QUESTION MARK
# Code: 3f (0x3f)
\u003F
# Character: ;
# Name: GREEK QUESTION MARK
# Code: 894 (0x37e)
\u037e
# Character: ؟
# Name: ARABIC QUESTION MARK
# Code: 1567 (0x61f)
\u061f
# Character: 。
# Name: IDEOGRAPHIC FULL STOP
# Code: 12290 (0x3002)
\u3002
# Character: 。
# Name: HALFWIDTH IDEOGRAPHIC FULL STOP
# Code: 65377 (0xff61)
\uff61
# Character: ?
# Name: FULLWIDTH QUESTION MARK
# Code: 65311 (0xff1f)
\uff1f
# Character: !
# Name: FULLWIDTH EXCLAMATION MARK
# Code: 65281 (0xff01)
\uff01
# Character: ।
# Name: DEVANAGARI DANDA
# Code: 2404 (0x964)
\u0964
# Character: ։
# Name: ARMENIAN FULL STOP
# Code: 1417 (0x589)
\u0589
# Character: ՞
# Name: ARMENIAN QUESTION MARK
# Code: 1374 (0x55e)
\u055e
# Character: ።
# Name: ETHIOPIC FULL STOP
# Code: 4962 (0x1362)
\u1362
# Character: ᙮
# Name: CANADIAN SYLLABICS FULL STOP
# Code: 5742 (0x166e)
\u166e
# Character: ។
# Name: KHMER SIGN KHAN
# Code: 6100 (0x17d4)
\u17d4
# Character: ៕
# Name: KHMER SIGN BARIYOOSAN
# Code: 6101 (0x17d5)
\u17d5
# Character: ᠃
# Name: MONGOLIAN FULL STOP
# Code: 6147 (0x1803)
\u1803
# Character: ᠉
# Name: MONGOLIAN MANCHU FULL STOP
# Code: 6153 (0x1809)
\u1809
|