diff --git a/Cargo.toml b/Cargo.toml index 372e44b..6d47df9 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -1,7 +1,7 @@ [package] name = "rustrict" authors = ["Finn Bear"] -version = "0.7.31" +version = "0.7.32" edition = "2021" license = "MIT OR Apache-2.0" repository = "https://github.com/finnbear/rustrict/" diff --git a/README.md b/README.md index 2cc56db..7ec6494 100644 --- a/README.md +++ b/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) | 79.83% | 94.00% | 76.30% | 9s | +| [rustrict](https://crates.io/crates/rustrict) | 79.82% | 94.00% | 76.29% | 9s | | [censor](https://crates.io/crates/censor) | 76.16% | 72.76% | 77.01% | 23s | | [stfu](https://crates.io/crates/stfu) | 91.74% | 77.69% | 95.25% | 45s | | [profane-rs](https://crates.io/crates/profane-rs) | 80.47% | 73.79% | 82.14% | 52s | diff --git a/src/dictionary_blacklist.txt b/src/dictionary_blacklist.txt index 20179fd..b1d7919 100644 --- a/src/dictionary_blacklist.txt +++ b/src/dictionary_blacklist.txt @@ -221,6 +221,7 @@ deflowerment deflowers degenerates des +diahrrea dickers dicks dildo(.*) @@ -327,6 +328,9 @@ ghettos gigolos girl friend girlfriends +gave birth +give birth +giving birth goddammed goddamming goddammit @@ -341,6 +345,7 @@ gropes gs gyppo h +hairy beaver hand job handjobs hang yourself @@ -418,6 +423,7 @@ kafirs kikes kill china kill chinese +kill muslim kill myself kill people kill russia @@ -477,6 +483,7 @@ menstruates menstruations mi ger micropenis +mighty shaft mike hawk milfs missionary position @@ -486,6 +493,7 @@ molestations molesters molestors molests +mom murder(.*) moronic morons motherfuck(.*) @@ -697,6 +705,7 @@ stupider stupidhead stupids su +superior race subgenital sucked suckers diff --git a/src/dictionary_extra.txt b/src/dictionary_extra.txt index 9af5d88..fa9f7fc 100644 --- a/src/dictionary_extra.txt +++ b/src/dictionary_extra.txt @@ -45,6 +45,7 @@ asap assalamo be a nerd becoome +betcha bigger s bishi blogger @@ -79,6 +80,7 @@ dig a hole dongguan enola gay faggetaboutit +farming xp fatty acid fatty food few secs @@ -162,6 +164,7 @@ kill ike killian kshatr last? it +little hovercraft lmao lol magnacumlaude diff --git a/src/false_positives.txt b/src/false_positives.txt index bcaed8c..c267fd1 100644 --- a/src/false_positives.txt +++ b/src/false_positives.txt @@ -2345,6 +2345,7 @@ bes lut bes perm bes seeks beslave +betcha betes cumulative betes ext betes hilt @@ -3558,6 +3559,7 @@ canberra pe canberra periodic canberra peru canberra ping +candidate someone candle peer candles blan candles cumulative @@ -4273,6 +4275,7 @@ committees test committees ties committees tiles commix +commodate someone commonly fans commons publish commons published @@ -6706,6 +6709,8 @@ finger appeal finger appear finger append finger bang +finger er +finger exercise finger ing finger ling finger ring @@ -6735,6 +6740,7 @@ finger xnxx finger young finger your finger youth +fingerers fingerling fingers cumulative fingers ext @@ -7244,6 +7250,7 @@ girgashite girl friendly girl friends girl jewish +give birthday gives cumulative gives ext gives hilt @@ -7251,6 +7258,7 @@ gives hit gives lut gives perm gives seeks +giving birthday glabellar glareola glazement @@ -7632,6 +7640,7 @@ hee rolling hee she hee sheet hee shell +hee tier heel i heel ill heel illinois @@ -9950,6 +9959,7 @@ kill lan kill like kill link kill lit +kill muslims kill palestinian kill peoples kill ta @@ -10973,6 +10983,7 @@ mammillar mammilliform man paste manal +mandate someone mannaia manufactured skins manufacturers cumulative @@ -11360,6 +11371,7 @@ ming xbox ming xerox ming xhtml ming xnxx +ming xp mingelen mini ger mini gzip @@ -12186,6 +12198,7 @@ nurses lut nurses perm nurses seeks nut casse +nut shoot nutcracker nutjobber nutpecker @@ -16253,6 +16266,7 @@ sheet sheet its sheet texts sheet thick +sheet tier sheet titles sheet wat sheet wats @@ -16594,6 +16608,7 @@ skiddycock skiepper skill china skill chinese +skill muslim skill myself skill people skill russia @@ -16780,6 +16795,7 @@ soldiers hit soldiers lut soldiers perm soldiers seeks +solidated someone sollar solo ser solo vary @@ -17375,6 +17391,7 @@ sundik sundress superbowlxxx superfat +superior races superseptuaginarian supersex supp @@ -17909,6 +17926,7 @@ texts hit texts lut texts perm texts seeks +thanksgiving birth the assault the asse the assess @@ -18947,6 +18965,9 @@ up rick up skirt upanishadic upcock +update someone +updated someone +updating someone upjerk upper version upper vert diff --git a/src/profanity.csv b/src/profanity.csv index 9be82ec..d3e66a7 100644 --- a/src/profanity.csv +++ b/src/profanity.csv @@ -18,7 +18,11 @@ word,profane,offensive,sexual,mean,evasive πŸ’‹πŸ†,0,0,3,0,2 πŸ†πŸ’‹,0,0,3,0,2 πŸ‘‰πŸ‘Œ,0,0,2,0,0 +π“‚Έ,0,0,2,0,3 π“‚Ί,0,0,2,0,3 +𓀐,0,0,1,0,2 +𓃗,0,0,1,0,1 +πŸ”ž,0,0,1,0,1 _l_,1,0,2,0,1 Β°α€™Β°,1,0,1,0,2 (.)(.),0,0,1,0,1 @@ -52,6 +56,7 @@ adolphfitlr,0,2,0,0,2 adulphfitler,0,2,0,0,2 adulphfitlr,0,2,0,0,2 africans,0,1,0,0,0 +after 9 months,0,0,0,0,1 agina,0,0,1,0,0 ahole,2,0,1,2,0 aholes,2,0,1,0,0 @@ -347,6 +352,8 @@ cok,1,0,2,0,1 coglione,2,0,1,2,0 comebucket,0,1,1,0,1 comebuster,0,0,1,0,1 +come inside me,0,0,2,0,2 +come inside you,0,0,2,0,2 comeinyou,0,0,2,0,2 commie,0,2,0,0,0 commis,0,2,0,0,0 @@ -387,6 +394,7 @@ cumgoblin,0,0,3,0,0 cumguzler,0,0,3,0,0 cuming,0,0,3,0,0 cuminme,0,0,1,0,0 +cuminyou,0,0,1,0,0 cumlord,0,0,3,0,0 cumshot,0,0,3,0,0 cnt,0,2,2,0,1 @@ -401,6 +409,9 @@ dammit,1,0,0,0,0 damn,1,0,0,0,0 damnit,1,0,0,0,0 darkie,0,1,0,0,0 +date someone,0,0,1,0,0 +dated someone,0,0,1,0,0 +dating someone,0,0,1,0,0 dawgiestyle,0,0,2,0,1 dawgystyle,0,0,2,0,1 daygo,0,3,0,0,0 @@ -423,11 +434,13 @@ deflower,0,0,2,0,0 degenerate,0,0,0,1,0 dego,0,2,0,0,0 dendrophilia,0,0,1,0,0 +diahrea,1,0,0,0,0 dic,2,0,2,1,1 dicc,2,0,2,1,1 dick,2,0,2,1,0 dicker,2,0,2,0,1 dickhead,2,1,2,2,0 + diddy,0,0,1,0,1 dieinahole,0,1,0,3,0 digbick,0,1,1,0,2 diggernick,2,2,1,0,2 @@ -597,6 +610,7 @@ ficking,2,0,2,0,2 figging,0,0,2,0,0 fing,1,0,1,0,1 fingerbang,0,0,2,0,1 + fingerer,0,0,1,0,1 finger u,0,0,2,0,1 fingeryou,0,0,2,0,0 fingering,0,0,1,0,0 @@ -769,6 +783,8 @@ girlfriend,0,0,1,0,0 girlontop,0,0,1,0,0 girlsgonewild,0,0,1,0,0 girlssendme,0,0,1,0,0 +givebirth,0,0,1,0,0 +givingbirth,0,0,1,0,0 gky,0,2,0,2,1 glans,0,0,1,0,0 glizy,0,0,2,0,2 @@ -822,8 +838,10 @@ hatemexican,0,1,0,1,0 hatenegro,0,2,0,0,1 hator,0,0,0,2,2 havesex,0,0,2,0,0 +hawktuah,0,0,1,0,1 hayt,0,0,0,2,2 hebephilia,0,0,2,0,0 +heetler,0,1,0,0,2 heil hit,0,1,0,0,0 heil hitler,0,3,0,0,0 heil hyt,0,1,0,0,1 @@ -837,6 +855,7 @@ herprivates,0,0,1,0,1 her gash,0,0,1,0,0 heroin,1,0,0,0,0 herpes,0,0,1,0,0 +he's a barking dog,0,0,0,1,0 heshe,0,0,2,0,0 hifler,0,1,0,0,2 hijacker,0,1,0,0,0 @@ -925,11 +944,14 @@ idiot,0,0,0,1,0 idolfhatler,0,2,0,0,2 idrugkids,0,1,0,0,1 ifkdurmum,2,2,3,2,2 +ifucallyou,1,0,1,2,2 igger,3,3,0,0,0 ilovekids,0,0,1,0,1 +hairybeaver,0,0,2,0,2 hairymelon,0,0,1,0,0 has a black hawk,1,0,1,0,2 have a black hawk,1,0,1,0,2 + ihatetrans,0,2,0,0,0 i have ED,0,0,1,0,1 i hope your father dies,0,1,0,2,1 i hope your mother dies,0,1,0,2,1 @@ -943,6 +965,7 @@ incest,0,0,3,0,0 indianbeater,0,2,0,0,1 indianhater,0,1,0,0,1 injun,0,1,0,0,0 +inmypants,0,0,1,0,1 insemin,0,0,2,0,0 inseminate,0,0,3,0,0 inseminater,0,0,3,0,0 @@ -951,6 +974,7 @@ inseminator,0,0,3,0,0 insest,0,0,1,0,1 intercourse,0,0,2,0,1 internmentcamp,0,1,0,0,1 +irapekid,0,2,3,0,0 irection,0,0,1,0,1 isgay,0,2,0,0,0 islamhater,0,1,0,0,1 @@ -1023,6 +1047,7 @@ killchina,0,2,0,0,0 killedyourself,0,2,0,3,0 killfamily,0,2,0,0,0 killjew,0,2,0,0,0 +killmuslim,0,2,0,0,0 killmyfamily,0,2,0,0,0 killmyschool,3,0,0,0,0 killotherpeople,2,0,0,0,0 @@ -1192,6 +1217,7 @@ methamphetamine,1,0,0,0,0 mgger,1,1,0,0,1 mierda,2,0,0,0,0 migga,2,3,0,0,2 +mightyshaft,0,0,2,0,2 miger,2,5,0,0,2 mikehawk,2,0,2,0,2 mikeock,2,0,2,1,2 @@ -1219,6 +1245,7 @@ molester,0,0,1,0,0 molestor,0,0,1,0,0 mommamilk,0,0,1,0,1 mommasmilk,0,0,1,0,1 +mommurder,0,1,0,0,0 mommy,0,0,1,0,0 momsmilk,0,0,1,0,1 monspubis,0,0,1,0,0 @@ -1253,10 +1280,11 @@ mycum,0,0,2,0,0 mydik,2,0,2,1,2 my a hole,1,0,1,0,2 my bbc,0,0,1,0,1 -my gash,0,0,1,0,0 + my gash,0,0,1,0,0 + my gigga,1,2,0,0,2 myjohnson,0,0,1,0,1 -my nut,0,0,2,0,1 -my tight little,0,0,1,0,1 + my nut,0,0,2,0,1 + my tight little,0,0,1,0,1 myseaman,0,0,1,0,2 myseamen,0,0,1,0,2 nΒ½ger,3,5,0,0,2 @@ -1388,6 +1416,7 @@ nut in you,0,0,3,0,0 nutjob,0,0,0,1,0 nutsack,0,0,2,0,0 nuts ack,0,0,2,0,1 + nut shot,0,0,1,0,1 nutte,0,1,1,0,0 nutted on,0,0,2,0,1 nut on you,0,0,2,0,1 @@ -1401,6 +1430,7 @@ nymphomania,0,0,2,0,0 nziger,3,5,0,0,3 nzis,0,1,0,0,1 offmyself,2,0,0,0,1 + oiled up,0,0,1,0,1 oilupkids,0,0,1,0,1 omorashi,0,0,1,0,0 onecuptwogirls,0,0,1,0,1 @@ -1491,6 +1521,10 @@ phalus,1,0,3,0,2 phanny,1,0,0,0,0 phelch,0,0,2,0,0 phelching,0,0,3,0,0 +phothermucker,2,1,2,1,2 +phothermuckr,2,1,2,1,3 +phothrmucker,2,1,2,1,3 +phothrmuckr,2,1,2,1,3 phuc,2,0,2,0,1 phuk,2,0,2,0,1 phuq,2,0,2,0,1 @@ -1553,6 +1587,7 @@ pssy,0,2,2,2,2 pube,0,0,3,0,0 pubescent,0,0,3,0,0 pubic,0,0,1,0,0 +puck futin,1,0,0,0,1 punani,0,0,3,0,2 punany,0,0,3,0,2 punk,0,0,0,1,0 @@ -1603,6 +1638,7 @@ retart,0,2,0,2,0 retarted,0,2,0,2,0 reversecowgirl,0,0,3,0,0 rice eater,0,1,0,0,0 + riding on me,0,0,1,0,1 rimjaw,0,0,1,0,1 rimjob,0,0,2,0,1 rim me,0,0,1,0,1 @@ -1699,6 +1735,7 @@ shiter,2,0,0,2,0 shithead,2,1,0,2,0 shemale,0,1,1,0,0 shet,1,0,0,0,2 +she's a barking dog,0,0,0,1,0 should be burned,0,1,0,0,1 sht,2,0,0,0,1 shted,2,0,0,0,1 @@ -1747,6 +1784,7 @@ smoking crack,1,0,0,1,0 smol dk,2,0,2,2,3 smutty,0,0,1,0,0 snapchat,0,0,0,0,1 +socksucker,0,0,1,0,2 sodomise,0,0,3,0,1 sodomite,0,0,3,0,0 sodomize,0,0,3,0,0 @@ -1796,6 +1834,8 @@ suc my,0,0,3,0,1 succ,0,0,1,1,1 sucs,0,0,1,1,1 suck,0,0,1,1,0 +suckafatone,0,0,2,0,1 +suckballs,0,0,3,0,0 sucker,0,0,0,2,0 sucking my,0,0,3,0,0 sucking me,0,0,3,0,0 @@ -1804,7 +1844,6 @@ sucks,0,0,1,1,0 suckit,0,0,2,2,0 suckme,0,0,3,0,0 suckmy,0,0,3,0,0 -suckballs,0,0,3,0,0 suck your,0,0,3,0,0 suhck,0,0,1,1,2 suhckme,0,0,3,0,2 @@ -1815,6 +1854,7 @@ suk,0,0,1,1,1 sukablyat,1,1,2,1,0 sukk,0,0,1,1,1 sultrywomen,0,0,2,0,0 +superiorrace,0,2,0,0,0 swatika,0,1,0,0,1 swastika,0,1,0,0,0 swastica,0,1,0,0,1 @@ -1979,6 +2019,7 @@ wetback,0,1,0,0,0 wetdream,0,0,1,0,0 whank,0,0,3,0,1 whanker,0,0,3,0,1 +when there is a hole there is a goal,0,0,2,0,2 whitepower,0,1,0,0,0 whitesonly,0,2,0,0,0 whitesupremacist,0,1,0,0,0 @@ -1990,6 +2031,8 @@ whoralicious,0,0,3,0,0 whore,0,3,3,0,0 whoring,0,2,3,0,0 wife,0,0,1,0,0 +wifebeat,0,1,2,0,0 +wifebeater,0,1,2,0,0 wiglestick,1,0,2,0,2 wigga,2,3,0,0,0 wigger,2,3,0,0,0 @@ -2002,6 +2045,8 @@ wiseass,1,0,0,1,0 withdarkskin,0,1,0,0,1 wives,0,0,1,0,0 wnker,0,0,1,0,1 +womanbeater,0,1,2,0,1 +womenbeater,0,1,2,0,1 woreacondom,0,0,2,0,0 woreacondum,0,0,2,0,1 wuss,0,0,0,1,0 @@ -2010,6 +2055,7 @@ xrated,0,0,2,0,0 xxx,0,0,2,0,1 xyn tebe,2,0,2,2,0 ya hole,0,0,2,0,2 +yall are freaks,0,0,0,2,0 ya mama,0,0,1,1,1 ya moma,0,0,1,1,1 ya mum,0,0,1,1,2 @@ -2020,6 +2066,7 @@ yiffy,0,0,1,0,1 you are disabled,0,1,0,2,0 you are idiot,0,0,0,2,0 you are weird,0,0,0,2,0 +you bich,1,1,1,1,1 you mf,2,1,1,2,1 you monkey,0,1,0,1,0 you mother,0,0,1,1,0 @@ -2046,6 +2093,7 @@ yourmum,0,0,1,1,1 yourprivateplace,0,0,1,0,1 yourprivates,0,0,1,0,1 yomama,0,0,0,1,0 +yomamasfat,0,1,0,2,1 yo beach as,1,1,0,2,2 yo mum,0,0,0,1,1 yuckfou,2,0,2,3,2 diff --git a/src/test_positive.txt b/src/test_positive.txt index c20b98a..e635871 100644 --- a/src/test_positive.txt +++ b/src/test_positive.txt @@ -2726,4 +2726,8 @@ kill all muslims ieatass dog headed kill myself -the n-word \ No newline at end of file +the n-word +irap3kids +I hate trans +DIAHRREA WAFFLES +COMEEEE INSIDEEEEE MEEEE