Improve wordlists, replacements (0.7.16).

Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "rustrict"
 authors = ["Finn Bear"]
-version = "0.7.15"
+version = "0.7.16"
 edition = "2021"
 license = "MIT OR Apache-2.0"
 repository = "https://github.com/finnbear/rustrict/"

Makefile

@@ -1,10 +1,13 @@
 .PHONY: fuzz
 
+all: test
+
 downloads:
 	wget -O test.csv https://raw.githubusercontent.com/vzhou842/profanity-check/master/profanity_check/data/clean_data.csv
-    wget -O src/dictionary.txt https://raw.githubusercontent.com/dwyl/english-words/master/words_alpha.txt
-    wget -O src/dictionary_common.txt https://raw.githubusercontent.com/first20hours/google-10000-english/master/google-10000-english.txt
-    wget -O src/unicode_confusables.txt https://www.unicode.org/Public/security/14.0.0/confusables.txt
+	wget -O src/dictionary.txt https://raw.githubusercontent.com/dwyl/english-words/master/words_alpha.txt
+	wget -O src/dictionary_common.txt https://raw.githubusercontent.com/first20hours/google-10000-english/master/google-10000-english.txt
+	wget -O src/unicode_confusables.txt https://www.unicode.org/Public/security/14.0.0/confusables.txt
+	# TODO: ttf fonts
 
 false_positives:
 	cargo run --bin false_positive_finder --release --features censor,regex,indicatif,rayon,find_false_positives

README.md

@@ -177,7 +177,7 @@ is used as a dataset. Positive accuracy is the percentage of profanity detected
 
 | Crate | Accuracy | Positive Accuracy | Negative Accuracy | Time |
 |-------|----------|-------------------|-------------------|------|
-| [rustrict](https://crates.io/crates/rustrict) | 87.90%   | 93.33%            | 86.55%            | 8s   |
+| [rustrict](https://crates.io/crates/rustrict) | 87.88%   | 93.33%            | 86.52%            | 8s   |
 | [censor](https://crates.io/crates/censor) | 76.16%   | 72.76%            | 77.01%            | 23s  |
 
 ## Development

src/dictionary_blacklist.txt

@@ -428,11 +428,13 @@ ll
 lo
 losers
 loss ser
+love minors
 love slavery
 lowlifes
 m
 male squirting
 masochists
+massive wood
 masturbate(.*)
 maya sol
 meat beating
@@ -592,6 +594,7 @@ retardation
 retarded
 retards
 rim job
+romances
 rs
 s
 sa

src/dictionary_extra.txt

@@ -203,4 +203,5 @@ wouldn't it
 yass
 yesturday
 zenga
-zubr east
+zubr east
+zuck

src/false_positives.txt

@@ -568,9 +568,12 @@ antiabortion
 antifascist
 antigropelos
 antiracism
+antiromance
 antisex
 antislavery
 antispastic
+antonio ga
+antonio ger
 ants croat
 ants perm
 anusim
@@ -2633,6 +2636,7 @@ chief luck
 chief rick
 chigger
 chiggers
+child stew
 childrens croatia
 childrens permalink
 childrens permanent
@@ -2675,6 +2679,7 @@ chinkiest
 chinking
 chinkle
 chinky
+chiromance
 chitties
 cho ad
 cho bag
@@ -2989,6 +2994,7 @@ commisce
 commise
 commissar
 commission
+commissionary
 commissive
 commissoria
 commissural
@@ -3205,6 +3211,7 @@ courts croat
 courts perm
 covary
 coverslut
+cow girl
 cow ward
 cowardice
 cowardish
@@ -3213,6 +3220,7 @@ cowardly
 cowardness
 cowardy
 cowboy friend
+cowgirls
 cowsucker
 coxitis
 crack er
@@ -6557,6 +6565,7 @@ ka strate
 kabobs
 kabonga
 kafirin
+kakke
 kalanchoe
 kaneshite
 kansas hole
@@ -7412,6 +7421,8 @@ mass sess
 massachusetts croat
 massachusetts perm
 masses
+massive wooden
+massive woods
 master balt
 master bat
 master batter
@@ -7636,6 +7647,7 @@ mismenstruation
 miss croat
 miss perm
 missile nintendo
+missionary
 mistful
 mitchell
 mix ger
@@ -8533,6 +8545,7 @@ outer vs
 outers croat
 outers perm
 outligger
+outromance
 outsuck
 outwatch
 outwater
@@ -9873,6 +9886,7 @@ pronunciative
 pronunciator
 pronymph
 propagandic
+proromance
 proslave
 proslavery
 prospects croat
@@ -10662,6 +10676,28 @@ roll experiment
 roll expert
 rollers croat
 rollers perm
+roman ce
+roman kee
+roman keith
+roman kelk
+roman kell
+roman ken
+roman kep
+roman ker
+roman kevin
+roman key
+roman xerox
+romancealist
+romancean
+romanced
+romanceful
+romanceish
+romanceless
+romancelet
+romancelike
+romancemonger
+romanceproof
+romancer
 rong ger
 ronga
 roofing
@@ -14412,4 +14448,5 @@ zoophilies
 zooxanthella
 zope nascar
 zope nasdaq
+zuck
 zwanziger