Update profanity list, add experimental Censor func, reduce allocations.

censor.go

@@ -0,0 +1,43 @@
+package moderation
+
+import "golang.org/x/exp/utf8string"
+
+var CensorReplacment rune = '*'
+
+// Censor returns a string with all but the first character of any inappropriate
+// segment replaced with CensorReplacment
+//
+// It is currently Experimental
+func Censor(text string, types Type) (censoredText string, replaced int) {
+	// Fast path
+	if len(text) == 0 || !Is(text, types) {
+		return text, 0
+	}
+
+	str := utf8string.NewString(text)
+
+	censored := make([]rune, 0, str.RuneCount())
+
+	start := 0
+
+	for i := start; i <= str.RuneCount(); i++ {
+		slice := str.Slice(start, i)
+		if /* (i == str.RuneCount() || str.At(i) == ' ') && */ Is(slice, types) {
+			for j := start; j <= i; j++ {
+				slice2 := str.Slice(j, i)
+				if !Is(slice2, types) {
+					censored = append(censored, []rune(str.Slice(start, j))...)
+					replaced += i - j
+					for k := 0; k < i-j; k++ {
+						censored = append(censored, CensorReplacment)
+					}
+					break
+				}
+			}
+			start = i
+		}
+	}
+	censored = append(censored, []rune(str.Slice(start, str.RuneCount()))...)
+	censoredText = string(censored)
+	return
+}

examples/detection_finder.go

@@ -14,19 +14,23 @@ func init() {
 }
 
 func main() {
+	fmt.Println("Original phrase: " + input)
+	censored, numCensored := moderation.Censor(input, moderation.Inappropriate)
+	fmt.Printf("Censored phrase: %s (%d characters replaced)\n", censored, numCensored)
+
 	shorter := input
-	for moderation.Is(shorter, 0xffffffff) { // satisfies all bitmasks
+	for moderation.Is(shorter, moderation.Any) { // satisfies all bitmasks
 		input = shorter
 		shorter = shorter[:len(shorter)-1]
 	}
 
 	shorter = input
-	for moderation.IsInappropriate(shorter) {
+	for moderation.Is(shorter, moderation.Any) {
 		input = shorter
 		shorter = shorter[1:]
 	}
 
-	if moderation.IsInappropriate(input) {
+	if moderation.Is(input, moderation.Any) {
 		fmt.Printf("Found inappropriate phrase: %s\n", input)
 	} else {
 		fmt.Println("No inappropriate phrase found")

generator/dictionary_blacklist.txt

@@ -14,7 +14,7 @@ dildo(.*)
 ejaculation
 fag(.*)
 fuck(.*)
-hell
+hellhole
 jackass
 livesex
 motherfuck(.*)

generator/dictionary_extra.txt

@@ -1,3 +1,4 @@
+alt
 anna
 afk
 akshita
@@ -23,3 +24,4 @@ ttyl
 tysongay
 wassup
 yass
+yesturday

generator/profanity.csv

@@ -15,13 +15,14 @@ bollock,1,0,1,0
 bollok,1,0,1,0
 boner,0,0,2,0
 boob,0,0,2,0
+breast,0,0,1,0
 btch,0,1,1,0
 bugger,1,0,0,0
 bullshit,1,0,0,0
 butt,1,0,0,0
 bra,0,0,1,0
 chink,0,2,0,0
-clitoris,0,0,2,0
+clit,0,0,2,0
 cock,1,0,1,0
 cok,1,0,1,0
 condom,0,0,1,0
@@ -30,8 +31,13 @@ cracker,0,1,0,0
 crap,1,0,0,0
 cum,0,0,2,0
 cunt,0,1,1,0
+damn,1,0,0,0
+daygo,0,2,0,0
+dego,0,2,0,0
 dick,1,0,1,0
 dildo,0,0,2,0
+dominatrics,0,0,2,0
+dominatrix,0,0,2,0
 dong,0,0,1,0
 douche,1,1,1,1
 dumb,0,0,0,1
@@ -47,6 +53,7 @@ fellatio,0,0,2,0
 flange,0,0,2,0
 foursome,0,0,2,0
 freak,0,0,0,1
+frick,1,0,0,0
 frig,1,0,1,0
 fuck,1,0,1,0
 fudgepacker,0,0,2,0
@@ -55,9 +62,13 @@ gangbang,0,2,0,0
 ghetto,0,1,0,0
 handjob,0,0,2,0
 hate,0,0,0,1
+hell,1,0,0,0
 heshe,0,0,1,0
+hoar,0,2,2,0
 hoe,0,1,1,0
-homo,0,1,0,0
+homo,0,1,1,0
+honkey,0,1,0,0
+hooker,0,0,2,0
 horny,0,0,2,0
 idiot,0,0,0,1
 incest,0,0,2,0
@@ -67,17 +78,19 @@ killyourself,0,1,0,2
 labia,0,0,2,0
 loser,0,0,0,1
 masterbat,0,0,1,0
-motherfuck,0,1,1,0
+motherfuck,1,1,1,0
 muff,0,0,2,0
 naked,0,0,1,0
 nazi,0,1,0,0
 nigga,1,2,0,0
 nigger,2,3,0,0
 nigguh,1,2,0,0
+nigr,2,3,0,0
 nude,0,0,2,0
 orgasm,0,0,1,0
 penis,2,0,2,0
-phuck,1,0,1,0
+penus,2,0,2,0
+phuc,1,0,1,0
 phuk,1,0,1,0
 pieceofgarbage,0,0,0,1
 piss,1,0,0,0
@@ -91,7 +104,10 @@ pussies,0,1,1,0
 pusy,0,1,1,0
 queer,0,2,0,0
 rape,0,0,1,0
+rectum,0,0,1,0
+recktum,0,0,1,0
 retard,0,1,0,1
+retart,0,1,0,1
 rimjob,0,0,2,0
 scrotum,0,0,2,0
 semen,0,0,2,0
@@ -100,11 +116,14 @@ shagger,0,0,2,0
 shagging,0,0,2,0
 shit,1,0,0,0
 sissy,0,0,0,1
+skank,0,1,2,0
 slut,0,1,1,0
 spunk,0,0,2,0
 stfu,0,0,0,1
 stupid,0,0,0,1
 suckmy,0,0,2,0
+testical,0,0,2,0
+testicle,0,0,2,0
 threesome,0,0,2,0
 tit,0,0,2,0
 tohell,1,1,0,0
@@ -113,6 +132,7 @@ turd,1,0,0,0
 twat,0,0,2,0
 ugly,0,0,0,1
 vagina,0,0,2,0
+vulva,0,0,2,0
 wank,0,0,2,0
 whore,0,2,2,0
 wigga,1,2,0,0

go.mod

@@ -2,4 +2,7 @@ module github.com/finnbear/moderation
 
 go 1.15
 
-require golang.org/x/text v0.3.4
+require (
+	golang.org/x/exp v0.0.0-20210220032938-85be41e4509f
+	golang.org/x/text v0.3.4
+)

go.sum

@@ -1,3 +1,34 @@
+dmitri.shuralyov.com/gpu/mtl v0.0.0-20201218220906-28db891af037/go.mod h1:H6x//7gZCb22OMCxBHrMx7a5I7Hp++hsVxbQ4BYO7hU=
+github.com/BurntSushi/xgb v0.0.0-20160522181843-27f122750802/go.mod h1:IVnqGOEym/WlBOVXweHU+Q+/VP0lqqI8lqeDx9IjBqo=
+github.com/go-gl/glfw/v3.3/glfw v0.0.0-20200222043503-6f7a984d4dc4/go.mod h1:tQ2UAYgL5IevRw8kRxooKSPJfGvJ9fJQFa0TUsXzTg8=
+golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
+golang.org/x/crypto v0.0.0-20190510104115-cbcb75029529/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
+golang.org/x/crypto v0.0.0-20191011191535-87dc89f01550/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
+golang.org/x/exp v0.0.0-20190731235908-ec7cb31e5a56/go.mod h1:JhuoJpWY28nO4Vef9tZUw9qufEGTyX1+7lmHxV5q5G4=
+golang.org/x/exp v0.0.0-20210220032938-85be41e4509f h1:GrkO5AtFUU9U/1f5ctbIBXtBGeSJbWwIYfIsTcFMaX4=
+golang.org/x/exp v0.0.0-20210220032938-85be41e4509f/go.mod h1:I6l2HNBLBZEcrOoCpyKLdY2lHoRZ8lI4x60KMCQDft4=
+golang.org/x/image v0.0.0-20190227222117-0694c2d4d067/go.mod h1:kZ7UVZpmo3dzQBMxlp+ypCbDeSB+sBbTgSJuh5dn5js=
+golang.org/x/image v0.0.0-20190802002840-cff245a6509b/go.mod h1:FeLwcggjj3mMvU+oOTbSwawSJRM1uh48EjtB4UJZlP0=
+golang.org/x/mobile v0.0.0-20190312151609-d3739f865fa6/go.mod h1:z+o9i4GpDbdi3rU15maQ/Ox0txvL9dWGYEHz965HBQE=
+golang.org/x/mobile v0.0.0-20201217150744-e6ae53a27f4f/go.mod h1:skQtrUTUwhdJvXM/2KKJzY8pDgNr9I/FOMqDVRPBUS4=
+golang.org/x/mod v0.1.0/go.mod h1:0QHyrYULN0/3qlju5TqG8bIK38QM8yzMo5ekMj3DlcY=
+golang.org/x/mod v0.1.1-0.20191105210325-c90efee705ee/go.mod h1:QqPTAvyqsEbceGzBzNggFXnrqF1CaUcvgkdR5Ot7KZg=
+golang.org/x/mod v0.1.1-0.20191209134235-331c550502dd/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
+golang.org/x/mod v0.3.1-0.20200828183125-ce943fd02449/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
+golang.org/x/net v0.0.0-20190311183353-d8887717615a/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
+golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
+golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
+golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
+golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20191001151750-bb3f8db39f24/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/text v0.3.4 h1:0YWbFKbhXG/wIiuHDSKpS0Iy7FSA+u45VtBMfQcFTTc=
 golang.org/x/text v0.3.4/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
+golang.org/x/tools v0.0.0-20190312151545-0bb0c0a6e846/go.mod h1:LCzVGOaR6xXOjkQ3onu1FJEFr0SW1gC7cKk1uF8kGRs=
+golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
+golang.org/x/tools v0.0.0-20200117012304-6edc0a871e69/go.mod h1:TB2adYChydJhpapKDTa4BR/hXlZSLoq2Wpct/0txZ28=
+golang.org/x/tools v0.0.0-20200207183749-b753a1ba74fa/go.mod h1:TB2adYChydJhpapKDTa4BR/hXlZSLoq2Wpct/0txZ28=
+golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
+golang.org/x/xerrors v0.0.0-20191011141410-1b5146add898/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=

moderation.go

@@ -17,6 +17,8 @@ const (
 	Offensive
 	Sexual
 	Mean
+	Inappropriate      = Profane | Offensive | Sexual
+	Any           Type = 0xffffffff
 )
 
 var (
@@ -56,6 +58,11 @@ var replacements = [...]string{
 
 var removeAccentsTransform = transform.Chain(norm.NFD, runes.Remove(runes.In(unicode.Mn)), norm.NFC)
 
+const (
+	minMatchable rune = 0x0020
+	maxMatchable rune = 0x007E
+)
+
 // IsInappropriate returns whether a phrase contains enough inappropriate words
 // to meet or exceed InappropriateThreshold
 //
@@ -66,13 +73,22 @@ func IsInappropriate(text string) bool {
 	return Is(text, Profane|Offensive|Sexual)
 }
 
-// IsInappropriate returns whether a phrase contains enough words matching the
+// Is returns whether a phrase contains enough words matching the
 // types flag to meet or exceed InappropriateThreshold
 func Is(text string, types Type) bool {
-	// Sanitize input
-	buf := make([]byte, 0, len(text))
-	_, n, _ := transform.Append(removeAccentsTransform, buf, []byte(text))
-	text = string(buf[:n])
+	// Sanitize input, if needed
+	needsSanitize := false
+	for _, textRune := range text {
+		if textRune < minMatchable || maxMatchable < textRune {
+			needsSanitize = true
+			break
+		}
+	}
+	if needsSanitize {
+		buf := make([]byte, 0, len(text))
+		_, n, _ := transform.Append(removeAccentsTransform, buf, []byte(text))
+		text = string(buf[:n])
+	}
 
 	// How many characters ago the last separator character was observed,
 	// expressed as an upper and a lower bound in relation to the current queue
@@ -91,7 +107,7 @@ func Is(text string, types Type) bool {
 
 	for _, textRune := range text {
 		// Unhandled runes (not printable, not representable as byte, etc.)
-		if textRune < 0x0020 || textRune > 0x007E {
+		if textRune < minMatchable || maxMatchable < textRune {
 			continue
 		}
 

moderation_test.go

@@ -126,6 +126,8 @@ func TestAnalyzeWikipedia(t *testing.T) {
 			//fmt.Printf("phrase=\"%s\" analysis offensive=%v actual offensive=%v\n", phrase, !offensive, offensive)
 		}
 
+		_, _ = Censor(phrase, Inappropriate)
+
 		total++
 		if offensive {
 			totalNok++