swear_jar 0.1.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +7 -0
- data/CHANGELOG.md +22 -0
- data/LICENSE.txt +22 -0
- data/README.md +313 -0
- data/config/locales/en.yml +4 -0
- data/config/locales/pl.yml +4 -0
- data/lib/swear_jar/configuration.rb +56 -0
- data/lib/swear_jar/detector.rb +58 -0
- data/lib/swear_jar/entry.rb +82 -0
- data/lib/swear_jar/errors.rb +7 -0
- data/lib/swear_jar/fold_table.rb +115 -0
- data/lib/swear_jar/match.rb +10 -0
- data/lib/swear_jar/matcher.rb +289 -0
- data/lib/swear_jar/normalizer.rb +163 -0
- data/lib/swear_jar/pattern_builder.rb +221 -0
- data/lib/swear_jar/railtie.rb +36 -0
- data/lib/swear_jar/skeleton.rb +116 -0
- data/lib/swear_jar/slicer.rb +58 -0
- data/lib/swear_jar/swear_jar_validator.rb +44 -0
- data/lib/swear_jar/version.rb +5 -0
- data/lib/swear_jar/word_list.rb +167 -0
- data/lib/swear_jar.rb +27 -0
- data/locales/en/words.yml +266 -0
- data/locales/pl/words.yml +213 -0
- metadata +67 -0
|
@@ -0,0 +1,266 @@
|
|
|
1
|
+
# English word list. English entries never take prefixes. Short or ambiguous words are
|
|
2
|
+
# `exact: true` (whole word only) and/or `embeddable: false` (never inside a word).
|
|
3
|
+
# A comment after a flag lists innocent words that the flag keeps from being reported.
|
|
4
|
+
# The default detector loads the Polish list too, so Polish words count as well.
|
|
5
|
+
words:
|
|
6
|
+
# --- vulgar and sexual ---
|
|
7
|
+
- stem: fuck
|
|
8
|
+
variants: [fck, fvck, phuck]
|
|
9
|
+
severity: strong
|
|
10
|
+
categories: [vulgar, sexual]
|
|
11
|
+
- stem: motherfuck
|
|
12
|
+
severity: strong
|
|
13
|
+
categories: [vulgar, insult]
|
|
14
|
+
- stem: shit
|
|
15
|
+
severity: strong
|
|
16
|
+
categories: [vulgar]
|
|
17
|
+
- stem: bullshit
|
|
18
|
+
severity: strong
|
|
19
|
+
categories: [vulgar]
|
|
20
|
+
- stem: cunt
|
|
21
|
+
severity: strong
|
|
22
|
+
categories: [vulgar, sexual, insult]
|
|
23
|
+
- stem: dick
|
|
24
|
+
severity: strong
|
|
25
|
+
categories: [vulgar, sexual]
|
|
26
|
+
- stem: cock
|
|
27
|
+
severity: strong
|
|
28
|
+
categories: [vulgar, sexual]
|
|
29
|
+
- stem: pussy
|
|
30
|
+
variants: [pussies]
|
|
31
|
+
severity: strong
|
|
32
|
+
categories: [vulgar, sexual]
|
|
33
|
+
- stem: dildo
|
|
34
|
+
severity: strong
|
|
35
|
+
categories: [sexual]
|
|
36
|
+
- stem: jizz
|
|
37
|
+
severity: strong
|
|
38
|
+
categories: [sexual]
|
|
39
|
+
- stem: cum
|
|
40
|
+
variants: [cums, cumming]
|
|
41
|
+
severity: strong
|
|
42
|
+
categories: [sexual]
|
|
43
|
+
exact: true
|
|
44
|
+
- stem: blowjob
|
|
45
|
+
severity: strong
|
|
46
|
+
categories: [sexual]
|
|
47
|
+
- stem: handjob
|
|
48
|
+
severity: strong
|
|
49
|
+
categories: [sexual]
|
|
50
|
+
- stem: ballsack
|
|
51
|
+
severity: strong
|
|
52
|
+
categories: [vulgar, sexual]
|
|
53
|
+
- stem: milf
|
|
54
|
+
severity: strong
|
|
55
|
+
categories: [sexual]
|
|
56
|
+
- stem: ass
|
|
57
|
+
variants: [asses]
|
|
58
|
+
severity: mild
|
|
59
|
+
categories: [vulgar]
|
|
60
|
+
embeddable: false
|
|
61
|
+
exact: true
|
|
62
|
+
- stem: arse
|
|
63
|
+
variants: [arses]
|
|
64
|
+
severity: mild
|
|
65
|
+
categories: [vulgar]
|
|
66
|
+
embeddable: false # keeps clean: parse, sparse, coarse
|
|
67
|
+
exact: true # keeps clean: arsenal, arsenic
|
|
68
|
+
- stem: crap
|
|
69
|
+
severity: mild
|
|
70
|
+
categories: [vulgar]
|
|
71
|
+
embeddable: false # keeps clean: scrap, skyscraper
|
|
72
|
+
- stem: piss
|
|
73
|
+
severity: mild
|
|
74
|
+
categories: [vulgar]
|
|
75
|
+
- stem: turd
|
|
76
|
+
variants: [turds]
|
|
77
|
+
severity: mild
|
|
78
|
+
categories: [vulgar]
|
|
79
|
+
embeddable: false # keeps clean: Saturday
|
|
80
|
+
exact: true
|
|
81
|
+
- stem: bollock
|
|
82
|
+
severity: mild
|
|
83
|
+
categories: [vulgar]
|
|
84
|
+
- stem: bugger
|
|
85
|
+
severity: mild
|
|
86
|
+
categories: [vulgar]
|
|
87
|
+
embeddable: false # keeps clean: debugger
|
|
88
|
+
- stem: tit
|
|
89
|
+
variants: [tits, titty, titties]
|
|
90
|
+
severity: mild
|
|
91
|
+
categories: [sexual]
|
|
92
|
+
exact: true
|
|
93
|
+
- stem: boob
|
|
94
|
+
variants: [boobs, boobies]
|
|
95
|
+
severity: mild
|
|
96
|
+
categories: [sexual]
|
|
97
|
+
exact: true
|
|
98
|
+
- stem: fap
|
|
99
|
+
variants: [fapping]
|
|
100
|
+
severity: mild
|
|
101
|
+
categories: [sexual]
|
|
102
|
+
exact: true
|
|
103
|
+
- stem: wtf
|
|
104
|
+
severity: mild
|
|
105
|
+
categories: [vulgar]
|
|
106
|
+
exact: true
|
|
107
|
+
- stem: stfu
|
|
108
|
+
severity: mild
|
|
109
|
+
categories: [vulgar]
|
|
110
|
+
exact: true
|
|
111
|
+
# --- insults ---
|
|
112
|
+
- stem: bitch
|
|
113
|
+
severity: strong
|
|
114
|
+
categories: [insult]
|
|
115
|
+
- stem: asshol
|
|
116
|
+
variants: [arsehol]
|
|
117
|
+
severity: strong
|
|
118
|
+
categories: [insult]
|
|
119
|
+
- stem: dipshit
|
|
120
|
+
severity: strong
|
|
121
|
+
categories: [insult]
|
|
122
|
+
- stem: twat
|
|
123
|
+
severity: strong
|
|
124
|
+
categories: [insult, sexual]
|
|
125
|
+
- stem: wank
|
|
126
|
+
severity: strong
|
|
127
|
+
categories: [insult, sexual]
|
|
128
|
+
embeddable: false # keeps clean: Iwanka, swank
|
|
129
|
+
- stem: slut
|
|
130
|
+
severity: strong
|
|
131
|
+
categories: [insult, sexual]
|
|
132
|
+
- stem: whore
|
|
133
|
+
variants: [whoring]
|
|
134
|
+
severity: strong
|
|
135
|
+
categories: [insult, sexual]
|
|
136
|
+
- stem: skank
|
|
137
|
+
severity: strong
|
|
138
|
+
categories: [insult]
|
|
139
|
+
- stem: bastard
|
|
140
|
+
severity: mild
|
|
141
|
+
categories: [insult]
|
|
142
|
+
- stem: jackass
|
|
143
|
+
severity: mild
|
|
144
|
+
categories: [insult]
|
|
145
|
+
- stem: dumbass
|
|
146
|
+
severity: mild
|
|
147
|
+
categories: [insult]
|
|
148
|
+
- stem: douche
|
|
149
|
+
severity: mild
|
|
150
|
+
categories: [insult]
|
|
151
|
+
- stem: prick
|
|
152
|
+
variants: [pricks]
|
|
153
|
+
severity: mild
|
|
154
|
+
categories: [insult]
|
|
155
|
+
exact: true # keeps clean: prickly, prickle
|
|
156
|
+
- stem: bellend
|
|
157
|
+
severity: mild
|
|
158
|
+
categories: [insult]
|
|
159
|
+
- stem: idiot
|
|
160
|
+
severity: mild
|
|
161
|
+
categories: [insult]
|
|
162
|
+
- stem: cretin
|
|
163
|
+
severity: mild
|
|
164
|
+
categories: [insult]
|
|
165
|
+
# --- slurs ---
|
|
166
|
+
- stem: retard
|
|
167
|
+
severity: strong
|
|
168
|
+
categories: [insult, slur]
|
|
169
|
+
- stem: nigger
|
|
170
|
+
variants: [nigga, niggaz]
|
|
171
|
+
severity: severe
|
|
172
|
+
categories: [slur]
|
|
173
|
+
- stem: faggot
|
|
174
|
+
severity: severe
|
|
175
|
+
categories: [slur]
|
|
176
|
+
- stem: fag
|
|
177
|
+
variants: [fags]
|
|
178
|
+
severity: severe
|
|
179
|
+
categories: [slur]
|
|
180
|
+
embeddable: false
|
|
181
|
+
exact: true # keeps clean: Polish fagot (bassoon)
|
|
182
|
+
- stem: kike
|
|
183
|
+
variants: [kikes]
|
|
184
|
+
severity: severe
|
|
185
|
+
categories: [slur]
|
|
186
|
+
embeddable: false
|
|
187
|
+
exact: true
|
|
188
|
+
- stem: wetback
|
|
189
|
+
severity: severe
|
|
190
|
+
categories: [slur]
|
|
191
|
+
- stem: tranny
|
|
192
|
+
variants: [trannies]
|
|
193
|
+
severity: severe
|
|
194
|
+
categories: [slur]
|
|
195
|
+
exact: true
|
|
196
|
+
- stem: gook
|
|
197
|
+
variants: [gooks]
|
|
198
|
+
severity: severe
|
|
199
|
+
categories: [slur]
|
|
200
|
+
embeddable: false
|
|
201
|
+
exact: true
|
|
202
|
+
- stem: coon
|
|
203
|
+
variants: [coons]
|
|
204
|
+
severity: severe
|
|
205
|
+
categories: [slur]
|
|
206
|
+
embeddable: false # keeps clean: raccoon
|
|
207
|
+
exact: true
|
|
208
|
+
- stem: raghead
|
|
209
|
+
severity: severe
|
|
210
|
+
categories: [slur]
|
|
211
|
+
# --- religious ---
|
|
212
|
+
- stem: damn
|
|
213
|
+
variants: [damned, damnit, dammit, goddamn, goddamned, goddamnit]
|
|
214
|
+
severity: mild
|
|
215
|
+
categories: [religious]
|
|
216
|
+
exact: true
|
|
217
|
+
- stem: hell
|
|
218
|
+
variants: [hells]
|
|
219
|
+
severity: mild
|
|
220
|
+
categories: [religious]
|
|
221
|
+
exact: true # keeps clean: hello, shell, hellhound
|
|
222
|
+
allow:
|
|
223
|
+
# innocent words containing `ass`
|
|
224
|
+
- assassin
|
|
225
|
+
- class
|
|
226
|
+
- bassist
|
|
227
|
+
# innocent words containing `cock`
|
|
228
|
+
- cocktail
|
|
229
|
+
- cockpit
|
|
230
|
+
- peacock
|
|
231
|
+
- cockatoo
|
|
232
|
+
- cockatiel
|
|
233
|
+
- cockatrice
|
|
234
|
+
- cockroach
|
|
235
|
+
- cockerel
|
|
236
|
+
- cockney
|
|
237
|
+
- cockle
|
|
238
|
+
- cockade
|
|
239
|
+
- hitchcock
|
|
240
|
+
- shuttlecock
|
|
241
|
+
- woodcock
|
|
242
|
+
- weathercock
|
|
243
|
+
- gamecock
|
|
244
|
+
- hancock
|
|
245
|
+
- babcock
|
|
246
|
+
# innocent words containing other stems
|
|
247
|
+
- scunthorpe
|
|
248
|
+
- shiitake
|
|
249
|
+
- shitake
|
|
250
|
+
- matsushita
|
|
251
|
+
- cucumber
|
|
252
|
+
- dickens
|
|
253
|
+
- dickinson
|
|
254
|
+
- riddick
|
|
255
|
+
- hello
|
|
256
|
+
- shell
|
|
257
|
+
- titan
|
|
258
|
+
- pussycat
|
|
259
|
+
- pussyfoot
|
|
260
|
+
- swank
|
|
261
|
+
- wankel
|
|
262
|
+
- snigger
|
|
263
|
+
- niggard
|
|
264
|
+
- retardant
|
|
265
|
+
- retardation
|
|
266
|
+
- retardac # Polish retardacja (retardation)
|
|
@@ -0,0 +1,213 @@
|
|
|
1
|
+
# Polish word list. Stems are written with diacritics; they are folded like the input text.
|
|
2
|
+
# Non-exact entries also match after one of the prefixes below (wkurwić, spierdalać, zajebać).
|
|
3
|
+
# A comment after a flag lists innocent words that the flag keeps from being reported.
|
|
4
|
+
# The default detector loads the English list too, so English words count as well.
|
|
5
|
+
prefixes: [s, w, z, wy, za, od, po, na, prze, roz, wpie, ze, do, u, o, ob, pod, nad, przy]
|
|
6
|
+
words:
|
|
7
|
+
# --- vulgar and sexual ---
|
|
8
|
+
- stem: kurw
|
|
9
|
+
variants: [kurew, kurest]
|
|
10
|
+
severity: strong
|
|
11
|
+
categories: [vulgar]
|
|
12
|
+
- stem: chuj
|
|
13
|
+
variants: [huj]
|
|
14
|
+
severity: strong
|
|
15
|
+
categories: [vulgar, sexual]
|
|
16
|
+
- stem: pierdol
|
|
17
|
+
variants: [pierdal]
|
|
18
|
+
severity: strong
|
|
19
|
+
categories: [vulgar, sexual]
|
|
20
|
+
- stem: jeb
|
|
21
|
+
variants: [joban, jobn]
|
|
22
|
+
severity: strong
|
|
23
|
+
categories: [vulgar, sexual]
|
|
24
|
+
- stem: pizd
|
|
25
|
+
severity: strong
|
|
26
|
+
categories: [vulgar, sexual]
|
|
27
|
+
- stem: cip
|
|
28
|
+
severity: strong
|
|
29
|
+
categories: [vulgar, sexual]
|
|
30
|
+
embeddable: false # keeps clean: principle, recipe, municipal
|
|
31
|
+
- stem: kutas
|
|
32
|
+
severity: strong
|
|
33
|
+
categories: [vulgar, sexual]
|
|
34
|
+
- stem: fiut
|
|
35
|
+
variants: [fiuci]
|
|
36
|
+
severity: strong
|
|
37
|
+
categories: [vulgar, sexual]
|
|
38
|
+
- stem: rucha # not `ruch`, which would report ruch (movement)
|
|
39
|
+
severity: strong
|
|
40
|
+
categories: [vulgar, sexual]
|
|
41
|
+
- stem: lachociąg
|
|
42
|
+
severity: strong
|
|
43
|
+
categories: [insult, sexual]
|
|
44
|
+
- stem: chędoż
|
|
45
|
+
severity: mild
|
|
46
|
+
categories: [sexual]
|
|
47
|
+
- stem: gówno # not `gówn`: without diacritics it is `gown`, which would report gown
|
|
48
|
+
variants: [gówna, gówni, gównu, gównem, gówien]
|
|
49
|
+
severity: mild
|
|
50
|
+
categories: [vulgar]
|
|
51
|
+
- stem: dup
|
|
52
|
+
severity: mild
|
|
53
|
+
categories: [vulgar]
|
|
54
|
+
embeddable: false # keeps clean: standup, roundup, holdup
|
|
55
|
+
- stem: sra
|
|
56
|
+
severity: mild
|
|
57
|
+
categories: [vulgar]
|
|
58
|
+
embeddable: false # keeps clean: Israel, Basra
|
|
59
|
+
- stem: pierdz
|
|
60
|
+
variants: [pierdn, pierdek, pierdk]
|
|
61
|
+
severity: mild
|
|
62
|
+
categories: [vulgar]
|
|
63
|
+
# --- insults ---
|
|
64
|
+
- stem: suk
|
|
65
|
+
variants: [suce] # the allow word `succe` keeps succeed and success clean
|
|
66
|
+
severity: strong
|
|
67
|
+
categories: [insult]
|
|
68
|
+
embeddable: false # keeps clean: Asuka, Tsukuyomi
|
|
69
|
+
- stem: dziwk
|
|
70
|
+
variants: [dziwek]
|
|
71
|
+
severity: strong
|
|
72
|
+
categories: [insult, sexual]
|
|
73
|
+
- stem: zdzir
|
|
74
|
+
severity: strong
|
|
75
|
+
categories: [insult, sexual]
|
|
76
|
+
- stem: szmat
|
|
77
|
+
variants: [szmacie] # not `szmaci`, which would report szmaciany (made of rags)
|
|
78
|
+
severity: mild
|
|
79
|
+
categories: [insult]
|
|
80
|
+
- stem: lafirynd
|
|
81
|
+
severity: mild
|
|
82
|
+
categories: [insult]
|
|
83
|
+
- stem: ladacznic
|
|
84
|
+
severity: mild
|
|
85
|
+
categories: [insult, sexual]
|
|
86
|
+
- stem: debil
|
|
87
|
+
severity: mild
|
|
88
|
+
categories: [insult]
|
|
89
|
+
- stem: idiot
|
|
90
|
+
variants: [idioci]
|
|
91
|
+
severity: mild
|
|
92
|
+
categories: [insult]
|
|
93
|
+
- stem: kretyn
|
|
94
|
+
severity: mild
|
|
95
|
+
categories: [insult]
|
|
96
|
+
- stem: imbecyl
|
|
97
|
+
severity: mild
|
|
98
|
+
categories: [insult]
|
|
99
|
+
- stem: matoł
|
|
100
|
+
severity: mild
|
|
101
|
+
categories: [insult]
|
|
102
|
+
embeddable: false # keeps clean: dermatolog, stomatolog, hematology
|
|
103
|
+
- stem: palant
|
|
104
|
+
severity: mild
|
|
105
|
+
categories: [insult]
|
|
106
|
+
- stem: kmiot
|
|
107
|
+
severity: mild
|
|
108
|
+
categories: [insult]
|
|
109
|
+
- stem: jełop
|
|
110
|
+
severity: mild
|
|
111
|
+
categories: [insult]
|
|
112
|
+
- stem: ćwok
|
|
113
|
+
severity: mild
|
|
114
|
+
categories: [insult]
|
|
115
|
+
- stem: gamoń
|
|
116
|
+
severity: mild
|
|
117
|
+
categories: [insult]
|
|
118
|
+
- stem: pacan
|
|
119
|
+
severity: mild
|
|
120
|
+
categories: [insult]
|
|
121
|
+
- stem: frajer
|
|
122
|
+
severity: mild
|
|
123
|
+
categories: [insult]
|
|
124
|
+
# --- slurs ---
|
|
125
|
+
- stem: cwel
|
|
126
|
+
severity: strong
|
|
127
|
+
categories: [insult, slur]
|
|
128
|
+
- stem: pedał # also reports pedał (bicycle pedal); pedałować is allowed below
|
|
129
|
+
variants: [pedzio, pedziu]
|
|
130
|
+
severity: severe
|
|
131
|
+
categories: [slur]
|
|
132
|
+
- stem: pederast
|
|
133
|
+
severity: severe
|
|
134
|
+
categories: [slur]
|
|
135
|
+
- stem: ciot
|
|
136
|
+
severity: severe
|
|
137
|
+
categories: [slur]
|
|
138
|
+
- stem: lesba # exact, so the neutral lesbijka stays clean
|
|
139
|
+
variants: [lesby, lesbę, lesbo, lesbie]
|
|
140
|
+
severity: severe
|
|
141
|
+
categories: [slur]
|
|
142
|
+
exact: true
|
|
143
|
+
- stem: czarnuch
|
|
144
|
+
severity: severe
|
|
145
|
+
categories: [slur]
|
|
146
|
+
- stem: ciapat # reports ciapaty, not the innocent ciapa (clumsy person)
|
|
147
|
+
variants: [ciapak]
|
|
148
|
+
severity: severe
|
|
149
|
+
categories: [slur]
|
|
150
|
+
- stem: kacap
|
|
151
|
+
severity: severe
|
|
152
|
+
categories: [slur]
|
|
153
|
+
# --- religious ---
|
|
154
|
+
- stem: choler
|
|
155
|
+
severity: mild
|
|
156
|
+
categories: [religious]
|
|
157
|
+
- stem: do diabła
|
|
158
|
+
severity: mild
|
|
159
|
+
categories: [religious]
|
|
160
|
+
allow:
|
|
161
|
+
# innocent words containing `dup`
|
|
162
|
+
- duplikat
|
|
163
|
+
- duplik # covers duplikacja, duplikować
|
|
164
|
+
- duplex
|
|
165
|
+
- dupleks
|
|
166
|
+
- duplic # covers duplicate, duplication
|
|
167
|
+
- duplo
|
|
168
|
+
- podupad # covers podupadać, podupadły (to decline)
|
|
169
|
+
# innocent words close to `kurw` (it does not match them; kept as a guard)
|
|
170
|
+
- skurcz
|
|
171
|
+
# innocent words close to `chuj`/`huj` (it does not match them; kept as a guard)
|
|
172
|
+
- hulajnoga
|
|
173
|
+
# innocent words containing `ciot` (ciotka: aunt)
|
|
174
|
+
- ciotka
|
|
175
|
+
- ciotk
|
|
176
|
+
- ciotce
|
|
177
|
+
- ciotek
|
|
178
|
+
- ciotecz
|
|
179
|
+
- ciotuch
|
|
180
|
+
- ciotun
|
|
181
|
+
- ciotuś
|
|
182
|
+
# innocent words containing `suk`
|
|
183
|
+
- sukces
|
|
184
|
+
- sukce # covers sukcesja, sukcesor (succession, successor)
|
|
185
|
+
- sukienka
|
|
186
|
+
- sukien
|
|
187
|
+
- suknia
|
|
188
|
+
- sukn # covers sukni, sukno (dress, cloth)
|
|
189
|
+
- sukul # covers sukulent (succulent)
|
|
190
|
+
- sukman
|
|
191
|
+
- sukurs
|
|
192
|
+
- sukiyaki
|
|
193
|
+
- succe # covers succeed, success (they contain the variant `suce`)
|
|
194
|
+
# innocent words containing `pedał`
|
|
195
|
+
- pedałow # covers pedałować, pedałowanie (to pedal)
|
|
196
|
+
- pedałuj
|
|
197
|
+
- pedaling
|
|
198
|
+
- pedalling
|
|
199
|
+
- pedaled
|
|
200
|
+
- pedalled
|
|
201
|
+
# innocent words containing other stems
|
|
202
|
+
- szmatk # covers szmatka (cloth)
|
|
203
|
+
- cipher
|
|
204
|
+
- debilit # covers debilitate, debilitating
|
|
205
|
+
- palantir
|
|
206
|
+
- gammon
|
|
207
|
+
- pacanów
|
|
208
|
+
- choleric
|
|
209
|
+
- choleryk
|
|
210
|
+
- cholerycz
|
|
211
|
+
- osram # Osram, which contains `o` + `sra`
|
|
212
|
+
- ruchami # ruch (movement), contains `rucha`
|
|
213
|
+
- ruchach # ruch (movement), contains `rucha`
|
metadata
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
|
2
|
+
name: swear_jar
|
|
3
|
+
version: !ruby/object:Gem::Version
|
|
4
|
+
version: 0.1.0
|
|
5
|
+
platform: ruby
|
|
6
|
+
authors:
|
|
7
|
+
- Konrad Jurkowski
|
|
8
|
+
bindir: bin
|
|
9
|
+
cert_chain: []
|
|
10
|
+
date: 1980-01-02 00:00:00.000000000 Z
|
|
11
|
+
dependencies: []
|
|
12
|
+
description: Detects profanity in Polish and English text, including inflection and
|
|
13
|
+
obfuscation, and returns exact matches with their positions in the original text
|
|
14
|
+
email:
|
|
15
|
+
- konrad@jurkowski.me
|
|
16
|
+
executables: []
|
|
17
|
+
extensions: []
|
|
18
|
+
extra_rdoc_files: []
|
|
19
|
+
files:
|
|
20
|
+
- CHANGELOG.md
|
|
21
|
+
- LICENSE.txt
|
|
22
|
+
- README.md
|
|
23
|
+
- config/locales/en.yml
|
|
24
|
+
- config/locales/pl.yml
|
|
25
|
+
- lib/swear_jar.rb
|
|
26
|
+
- lib/swear_jar/configuration.rb
|
|
27
|
+
- lib/swear_jar/detector.rb
|
|
28
|
+
- lib/swear_jar/entry.rb
|
|
29
|
+
- lib/swear_jar/errors.rb
|
|
30
|
+
- lib/swear_jar/fold_table.rb
|
|
31
|
+
- lib/swear_jar/match.rb
|
|
32
|
+
- lib/swear_jar/matcher.rb
|
|
33
|
+
- lib/swear_jar/normalizer.rb
|
|
34
|
+
- lib/swear_jar/pattern_builder.rb
|
|
35
|
+
- lib/swear_jar/railtie.rb
|
|
36
|
+
- lib/swear_jar/skeleton.rb
|
|
37
|
+
- lib/swear_jar/slicer.rb
|
|
38
|
+
- lib/swear_jar/swear_jar_validator.rb
|
|
39
|
+
- lib/swear_jar/version.rb
|
|
40
|
+
- lib/swear_jar/word_list.rb
|
|
41
|
+
- locales/en/words.yml
|
|
42
|
+
- locales/pl/words.yml
|
|
43
|
+
homepage: https://github.com/msx2/swear_jar
|
|
44
|
+
licenses:
|
|
45
|
+
- MIT
|
|
46
|
+
metadata:
|
|
47
|
+
source_code_uri: https://github.com/msx2/swear_jar
|
|
48
|
+
changelog_uri: https://github.com/msx2/swear_jar/blob/master/CHANGELOG.md
|
|
49
|
+
rubygems_mfa_required: 'true'
|
|
50
|
+
rdoc_options: []
|
|
51
|
+
require_paths:
|
|
52
|
+
- lib
|
|
53
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
|
54
|
+
requirements:
|
|
55
|
+
- - ">="
|
|
56
|
+
- !ruby/object:Gem::Version
|
|
57
|
+
version: '3.0'
|
|
58
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
59
|
+
requirements:
|
|
60
|
+
- - ">="
|
|
61
|
+
- !ruby/object:Gem::Version
|
|
62
|
+
version: '0'
|
|
63
|
+
requirements: []
|
|
64
|
+
rubygems_version: 3.6.9
|
|
65
|
+
specification_version: 4
|
|
66
|
+
summary: Swear Jar, a fast profanity detector for Polish and English.
|
|
67
|
+
test_files: []
|