fix: add Dutch language support and fix Turkish dictionary (#76)

- Fix Turkish dictionary that incorrectly contained Dutch words
- Create new Dutch dictionary with proper Dutch profanity entries
- Add Dutch language support to JS and Python packages
- Add missing ignoreWords property to ProfanityCheckerConfig
- Remove malformed metadata entries from Turkish dictionary
- Fix alphabetical ordering of Dutch in language types

Co-authored-by: Kaan <kaan-playabit@users.noreply.github.com>

Author: thegdsks

packages/js/src/core/types.ts

@@ -9,6 +9,7 @@ export interface ProfanityCheckerConfig {
   customWords?: string[];
   replaceWith?: string;
   severityLevels?: boolean;
+  ignoreWords?: string[];
   allowObfuscatedMatch?: boolean;
   fuzzyToleranceLevel?: number;
   minSeverity?: SeverityLevel;

packages/js/src/data/dictionary.ts

@@ -2,6 +2,7 @@ import Arabic from '@shared/dictionaries/arabic.json';
 import Chinese from '@shared/dictionaries/chinese.json';
 import Czech from '@shared/dictionaries/czech.json';
 import Danish from '@shared/dictionaries/danish.json';
+import Dutch from '@shared/dictionaries/dutch.json';
 import Esperanto from '@shared/dictionaries/esperanto.json';
 import English from '@shared/dictionaries/english.json';
 import Finnish from '@shared/dictionaries/finnish.json';
@@ -26,6 +27,7 @@ export default {
   chinese: Chinese.words,
   czech: Czech.words,
   danish: Danish.words,
+  dutch: Dutch.words,
   english: English.words,
   esperanto: Esperanto.words,
   finnish: Finnish.words,

packages/js/src/types/types.ts

@@ -15,6 +15,7 @@ export type Language =
   | 'chinese'
   | 'czech'
   | 'danish'
+  | 'dutch'
   | 'english'
   | 'esperanto'
   | 'finnish'

packages/py/glin_profanity/data/dictionary.py

@@ -31,6 +31,7 @@ def _load_dictionaries(self) -> None:
             "chinese": "chinese.json",
             "czech": "czech.json",
             "danish": "danish.json",
+            "dutch": "dutch.json",
             "english": "english.json",
             "esperanto": "esperanto.json",
             "finnish": "finnish.json",

packages/py/glin_profanity/types/types.py

@@ -12,6 +12,7 @@
     "chinese",
     "czech",
     "danish",
+    "dutch",
     "english",
     "esperanto",
     "finnish",

shared/dictionaries/dutch.json

@@ -0,0 +1,195 @@
+{
+  "words": [
+    "aardappels afgieteng",
+    "achter het raam zitten",
+    "afberen",
+    "aflebberen",
+    "afrossen",
+    "afrukken",
+    "aftrekken",
+    "afwerkplaats",
+    "afzeiken",
+    "afzuigen",
+    "anderhalve man en een paardekop",
+    "anita",
+    "asbak",
+    "aso",
+    "bagger schijten",
+    "balen",
+    "bedonderen",
+    "befborstelg",
+    "beffen",
+    "bekken",
+    "belazeren",
+    "besodemieterd zijn",
+    "besodemieteren",
+    "beurt",
+    "boemelen",
+    "boerelul",
+    "boerenpummelg",
+    "bokkelul",
+    "botergeil",
+    "broekhoesten",
+    "brugpieperg",
+    "buffelen",
+    "buiten de pot piesen",
+    "da's kloten van de bok",
+    "de ballen",
+    "de hoer spelen",
+    "de hond uitlaten",
+    "de koffer induiken",
+    "delg",
+    "de pijp aan maarten geven",
+    "de pijp uitgaan",
+    "dombo",
+    "draaikontg",
+    "driehoog achter wonen",
+    "drolg",
+    "drooggeiler",
+    "droogkloot",
+    "een beurt geven",
+    "een nummertje maken",
+    "een wip maken",
+    "eikel",
+    "engerd",
+    "flamoes",
+    "flikken",
+    "flikker",
+    "gadverdamme",
+    "galbak",
+    "gat",
+    "gedoogzone",
+    "geilneef",
+    "gesodemieter",
+    "godverdomme",
+    "graftak",
+    "gras maaien",
+    "gratenkutg",
+    "greppeldel",
+    "griet",
+    "hoempert",
+    "hoer",
+    "hoerenbuurt",
+    "hoerenloper",
+    "hoerig",
+    "hol",
+    "hufter",
+    "huisdealer",
+    "johny",
+    "kanen",
+    "kettingzeugg",
+    "klaarkomen",
+    "klerebeer",
+    "klojo",
+    "klooien",
+    "klootjesvolk",
+    "klootoog",
+    "klootzak",
+    "kloten",
+    "knor",
+    "kontg",
+    "kontneuken",
+    "krentekakker",
+    "kut",
+    "kuttelikkertje",
+    "kwakkieg",
+    "liefdesgrot",
+    "lul",
+    "lul-de-behanger",
+    "lulhannes",
+    "lummel",
+    "mafketel",
+    "matennaaierg",
+    "matje",
+    "mof",
+    "mutsg",
+    "naaien",
+    "naakt",
+    "neuken",
+    "neukstier",
+    "nicht",
+    "oetlul",
+    "opgeilen",
+    "opkankeren",
+    "oprotten",
+    "opsodemieteren",
+    "op z'n hondjes",
+    "op z'n sodemieter geven",
+    "opzouten",
+    "ouwehoer",
+    "ouwehoeren",
+    "ouwe rukker",
+    "paal",
+    "paardelul",
+    "palen",
+    "penozeg",
+    "piesen",
+    "pijpbekkieg",
+    "pijpen",
+    "pik",
+    "pleurislaaier",
+    "poep",
+    "poepen",
+    "poot",
+    "portiekslet",
+    "pot",
+    "potverdorie",
+    "publiciteitsgeil",
+    "raaskallen",
+    "reet",
+    "reetridder",
+    "reet trappen, voor zijn",
+    "remsporeng",
+    "reutelen",
+    "rothoer",
+    "rotzak",
+    "rukhond",
+    "rukken",
+    "schatje",
+    "schijt",
+    "schijten",
+    "schoft",
+    "schuinsmarcheerder",
+    "shit",
+    "slempen",
+    "sletg",
+    "sletterig",
+    "slik mijn zaad",
+    "snolg",
+    "spuiten",
+    "standje",
+    "standje-69g",
+    "stoephoer",
+    "stootje",
+    "strontg",
+    "sufferdg",
+    "tapijtnek",
+    "teefg",
+    "temeier",
+    "teringlijer",
+    "toeter",
+    "tongzoeng",
+    "triootjeg",
+    "trottoir prostituée",
+    "trottoirteef",
+    "vergallen",
+    "verkloten",
+    "verneuken",
+    "viespeuk",
+    "vingeren",
+    "vleesroos",
+    "voor jan lul",
+    "voor jan-met-de-korte-achternaam",
+    "watje",
+    "welzijnsmafia",
+    "wijf",
+    "wippen",
+    "wuftje",
+    "zaadje",
+    "zakkenwasser",
+    "zeiken",
+    "zeiker",
+    "zuigen",
+    "zuiplap"
+  ]
+}