Init

.eslintrc

@@ -0,0 +1,7 @@
+{
+  "extends": ["standard-with-typescript"],
+  "parser": "@typescript-eslint/parser",
+  "parserOptions": {
+    "project": './tsconfig.json'
+  }
+}

.gitignore

@@ -0,0 +1,21 @@
+.vs
+.vscode
+
+.DS_Store
+
+.node_history
+*.log
+.cache
+
+pids
+*.pid
+*.seed
+
+node_modules
+public
+build
+dist
+lib
+tmp
+
+.env

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) Alex Zelensky
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -0,0 +1,95 @@
+# bad-words-next
+
+Profanity filtering and detection.
+
+Started as a quick overnight project. Feel free to contribute.
+
+## Install
+
+```sh
+yarn add bad-words-next
+```
+
+or
+
+```sh
+npm install bad-words-next
+```
+
+## Basic usage
+
+```js
+const BadWordsNext = require('bad-words-next')
+const en = require('bad-words-next/data/en.json')
+
+const badwords = new BadWordsNext({ data: en })
+
+// Returns true when passed string contains a bad word
+console.log(badwords.check('S0me sh!tt is here'))
+// will print `true`
+
+// Returns filtered string with masked bad words
+console.log(badwords.filter('S0me sh!tt is here'))
+// will print `S0me *** is here`
+```
+
+## Add more dictionaries
+
+```sh
+const BadWordsNext = require('bad-words-next')
+
+const en = require('bad-words-next/data/en.json')
+const es = require('bad-words-next/data/es.json')
+const fr = require('bad-words-next/data/fr.json')
+const de = require('bad-words-next/data/de.json')
+const ru = require('bad-words-next/data/ru.json')
+const rl = require('bad-words-next/data/ru_lat.json')
+const ua = require('bad-words-next/data/ua.json')
+const pl = require('bad-words-next/data/pl.json')
+const ch = require('bad-words-next/data/ch.json')
+
+const badwords = new BadWordsNext()
+badwords.add(en)
+badwords.add(es)
+badwords.add(fr)
+badwords.add(de)
+badwords.add(ru)
+badwords.add(rl)
+badwords.add(ua)
+badwords.add(pl)
+badwords.add(ch)
+```
+
+## Dictionary files format
+
+```ts
+interface Data {
+  id: string  // unique ID
+  words: string[] // words list, supports `*` on start and end of a string to indicate any characters, also `+` for one or more repeating characters, and `_` for special characters.
+  lookalike: Lookalike // map for homoglyphs conversion
+}
+
+interface Lookalike {
+  [key: string | number]: string // just a simple key-value object
+}
+```
+
+## Options
+
+```ts
+interface Options {
+  data?: Data // Dictionary data
+  placeholder?: string // Filter placeholder - default value '***'
+  specialChars?: RegExp // Special chars to allow on word start and word end - default value /\d|[!@#$%^&*()[\];:'",.?\-_=+~`|]|a|(?:the)|(?:el)|(?:la)/
+  spaceChars?: string[] // Pseudo space chars, a list of values for `_` symbol in a dictionary word string - default value ['', '.', '-', '_', ';', '|']
+  confusables?: string[] // List of ids to apply transformations from `confusables` npm package - default ['en', 'es', 'de']
+}
+```
+
+## Notes
+
+- Filtering may be potentially slow on large strings and large dictionaries
+
+- Dictionary words with spaces won't work
+
+- Dictionaries have to be improved over time

data/ch.json

@@ -0,0 +1,28 @@
+{
+  "id": "ch",
+  "words": [
+    "*屌*",
+    "*鸡巴*",
+    "*傻瓜*",
+    "*屄*",
+    "*屁股*",
+    "*肏你*",
+    "*狗屁*",
+    "*婊子*",
+    "*色鬼*",
+    "*王八*",
+    "*混蛋*",
+    "*妓*",
+    "*屁眼*",
+    "*幹*",
+    "*操你*",
+    "*狗日*",
+    "*白癡*",
+    "*糞*",
+    "*老母*",
+    "*肏*",
+    "*雞*巴"
+  ],
+  "lookalike": {
+  }
+}

data/de.json

@@ -0,0 +1,46 @@
+{
+  "id": "de",
+  "words": [
+    "analritt+er",
+    "arsch*",
+    "ficken",
+    "fotze",
+    "kacke",
+    "kacken",
+    "kackwurst",
+    "kampflesbe",
+    "lümmel",
+    "möpse",
+    "möse",
+    "neger",
+    "nippel",
+    "nutte",
+    "onanieren",
+    "orgasmus",
+    "scheiss+er",
+    "scheiße",
+    "schiess+er",
+    "schlampe",
+    "schwanzlutscher",
+    "titt+chen",
+    "titt+en",
+    "vollpfosten",
+    "vögeln",
+    "wichse",
+    "wichsen",
+    "wichser"
+  ],
+  "lookalike": {
+    "$": "s",
+    "@": "a",
+    "<": "c",
+    "!": "i",
+    "+": "t",
+    "0": "o",
+    "1": "i",
+    "2": "z",
+    "3": "z",
+    "5": "s",
+    "8": "b"
+  }
+}