Skip to content

Commit 95bddd7

Browse files
committed
0.7.38 - wordlist improvements and Japanese exemption.
1 parent db5c16a commit 95bddd7

File tree

10 files changed

+280
-21
lines changed

10 files changed

+280
-21
lines changed

Cargo.toml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
[package]
22
name = "rustrict"
33
authors = ["Finn Bear"]
4-
version = "0.7.37"
4+
version = "0.7.38"
55
edition = "2021"
66
license = "MIT OR Apache-2.0"
77
repository = "https://github.com/finnbear/rustrict/"

README.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -177,7 +177,7 @@ is used as a dataset. Positive accuracy is the percentage of profanity detected
177177

178178
| Crate | Accuracy | Positive Accuracy | Negative Accuracy | Time |
179179
|-------|----------|-------------------|-------------------|------|
180-
| [rustrict](https://crates.io/crates/rustrict) | 79.53% | 94.08% | 75.90% | 10s |
180+
| [rustrict](https://crates.io/crates/rustrict) | 79.63% | 94.08% | 76.03% | 10s |
181181
| [censor](https://crates.io/crates/censor) | 76.16% | 72.76% | 77.01% | 23s |
182182
| [stfu](https://crates.io/crates/stfu) | 91.74% | 77.69% | 95.25% | 45s |
183183

src/character_analyzer.rs

Lines changed: 17 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -52,6 +52,23 @@ fn main() {
5252
'༺' | '༻' => 25,
5353
'𒀱' => 45,
5454
'۞' => 19,
55+
'𒅇' => 26,
56+
'𒅈' => 33,
57+
'𒅉' => 33,
58+
'𒅊' => 20,
59+
'𒅋' => 42,
60+
'𒅌' => 42,
61+
'𒅍' => 25,
62+
'𒅎' => 23,
63+
'𒅏' => 23,
64+
'𒅐' => 20,
65+
'𒅑' => 40,
66+
'𒅒' => 25,
67+
'𒅓' => 20,
68+
'𒅔' => 22,
69+
'𒅕' => 18,
70+
'𒅖' => 18,
71+
'𒂼' => 20,
5572
_ => {
5673
let max_width = (max_width(c, &fonts) as f32 / 100f32).round() as u16;
5774
if max_width > u8::MAX as u16 {

src/character_widths.bin

55 Bytes
Binary file not shown.

src/dictionary_extra.txt

Lines changed: 20 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -308,3 +308,23 @@ yesturday
308308
zenga
309309
zubr east
310310
zuck
311+
pdf file
312+
AND) do
313+
use x
314+
did one
315+
can't. it
316+
that, it's
317+
lol :)
318+
but thx
319+
x ok
320+
n (or
321+
not. it'l
322+
till tm
323+
teaming*
324+
swimming, etc.
325+
ok. like
326+
come inside, you
327+
lol)
328+
mean, all
329+
point, its
330+
Hi ^

src/false_positives.txt

Lines changed: 58 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -15,6 +15,7 @@
1515
8 secs
1616
9 is still
1717
9 secs
18+
AND) do
1819
a analog
1920
a analyse
2021
a analysis
@@ -3398,6 +3399,7 @@ but thrill
33983399
but thro
33993400
but thru
34003401
but thu
3402+
but thx
34013403
but tic
34023404
but tid
34033405
but tie
@@ -3554,6 +3556,7 @@ cam girl
35543556
camel tox
35553557
campoo
35563558
can't it
3559+
can't. it
35573560
canal
35583561
canberra appeal
35593562
canberra appear
@@ -4187,6 +4190,7 @@ com mille
41874190
com mills
41884191
com mis
41894192
com mix
4193+
come inside, you
41904194
come shoot
41914195
come shot
41924196
comedy kee
@@ -5247,6 +5251,7 @@ dicycly
52475251
dicyema
52485252
dicyemid
52495253
dicynodon
5254+
did on
52505255
did ou
52515256
didn't it
52525257
dido
@@ -5498,6 +5503,9 @@ duces hit
54985503
duces lut
54995504
duces perm
55005505
duces seeks
5506+
duck young
5507+
duck your
5508+
duck youth
55015509
duckwife
55025510
ducts cumulative
55035511
ducts ext
@@ -10899,11 +10907,13 @@ logs hit
1089910907
logs lut
1090010908
logs perm
1090110909
logs seeks
10910+
lol :)
1090210911
lol i
1090310912
lol j
1090410913
lol l
1090510914
lol y
1090610915
lol!
10916+
lol)
1090710917
lol, i
1090810918
lol, j
1090910919
lol, l
@@ -11332,6 +11342,7 @@ maundies
1133211342
maycock
1133311343
mazement
1133411344
meacock
11345+
mean, all
1133511346
meaningful licking
1133611347
measurements cumulative
1133711348
measurements ext
@@ -12005,6 +12016,7 @@ myers seeks
1200512016
myrtle peer
1200612017
myth little
1200712018
mythifier
12019+
n (or
1200812020
n 1997
1200912021
n't eat
1201012022
nabobish
@@ -12390,6 +12402,7 @@ not titles
1239012402
not wat
1239112403
not wats
1239212404
not watts
12405+
not. it'l
1239312406
notencephalus
1239412407
notes cumulative
1239512408
notes ext
@@ -12599,6 +12612,7 @@ ok like
1259912612
ok until
1260012613
ok untitled
1260112614
ok unto
12615+
ok. like
1260212616
okes cumulative
1260312617
okes ext
1260412618
okes hilt
@@ -13246,6 +13260,7 @@ pays lut
1324613260
pays perm
1324713261
pays seeks
1324813262
pc master race
13263+
pdf file
1324913264
pe do
1325013265
pe nissan
1325113266
peaceful licking
@@ -13824,6 +13839,7 @@ pocock
1382413839
pogeys
1382513840
poggers
1382613841
pogonips
13842+
point, its
1382713843
points cumulative
1382813844
points ext
1382913845
points hilt
@@ -16123,6 +16139,10 @@ screw offer
1612316139
screw offic
1612416140
screw offline
1612516141
screw offs
16142+
screw urb
16143+
screw urge
16144+
screw url
16145+
screw uru
1612616146
screw young
1612716147
screw your
1612816148
screw youth
@@ -17861,6 +17881,7 @@ swimming xbox
1786117881
swimming xerox
1786217882
swimming xhtml
1786317883
swimming xnxx
17884+
swimming, etc.
1786417885
swives
1786517886
swordick
1786617887
sycock
@@ -17982,6 +18003,7 @@ tch links
1798218003
tch little
1798318004
tchincou
1798418005
tea the
18006+
teaming*
1798518007
teanal
1798618008
teapottykin
1798718009
teataster
@@ -18193,6 +18215,7 @@ texts lut
1819318215
texts perm
1819418216
texts seeks
1819518217
thanksgiving birth
18218+
that, it's
1819618219
the assault
1819718220
the asse
1819818221
the assess
@@ -18492,6 +18515,7 @@ till titan
1849218515
till title
1849318516
till titles
1849418517
till titten
18518+
till tm
1849518519
till to
1849618520
till tra
1849718521
till treas
@@ -19298,6 +19322,7 @@ us hit
1929819322
us lut
1929919323
us perm
1930019324
us seeks
19325+
use x
1930119326
useful licking
1930219327
uses cumulative
1930319328
uses ext
@@ -19933,11 +19958,43 @@ whittle
1993319958
whittler
1993419959
who or
1993519960
who ore
19961+
who rabbi
19962+
who race
19963+
who rach
19964+
who racial
19965+
who racing
19966+
who rack
19967+
who rad
19968+
who rag
19969+
who raid
19970+
who rail
19971+
who rain
19972+
who rais
19973+
who rale
19974+
who rall
19975+
who ralph
19976+
who ran
19977+
who rap
19978+
who rare
19979+
who rat
19980+
who ray
1993619981
who re
1993719982
who refrig
1993819983
who republic
19984+
who rh
19985+
who ri
1993919986
who ring
19987+
who ro
19988+
who ru
19989+
who rw
19990+
who rya
1994019991
who vary
19992+
whorage
19993+
whorish
19994+
whorl
19995+
whorry
19996+
whort
19997+
whory
1994119998
whumped
1994219999
whumping
1994320000
wi life
@@ -20102,6 +20159,7 @@ wuzzer
2010220159
wuzzle
2010320160
wuzzling
2010420161
wuzzy
20162+
x ok
2010520163
xD i do
2010620164
xanthate
2010720165
xanthocephalus

0 commit comments

Comments
 (0)