censorship-id 1.0.0

package/README.md

@@ -0,0 +1,71 @@
+# censorship-id
+
+[![npm version](https://img.shields.io/npm/v/censorship-id.svg?style=flat-square)](https://www.npmjs.com/package/censorship-id)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+
+A robust and simple npm package for detecting and masking Indonesian profanity, slang, and inappropriate words.
+
+## Features
+
+- **Comprehensive Dictionary**: Pre-loaded with hundreds of common Indonesian bad words.
+- **Regex Powered**: Uses word boundaries to avoid false positives (e.g., masking "tai" but not "pantai").
+- **Customizable**: Add your own words to the list and choose your mask character.
+- **Keep First and Last**: Option to keep the first and last letters visible for better context.
+- **Case-Insensitive**: Matches words regardless of their case.
+- **Lightweight**: Zero dependencies (only uses Jest for development).
+
+## Installation
+
+```bash
+npm install censorship-id
+```
+
+## Usage
+
+### Basic Usage
+
+```javascript
+const { censorId } = require('censorship-id');
+
+const text = "Dasar anjing kau, babi!";
+const censored = censorId(text);
+console.log(censored); 
+// Output: Dasar ****** kau, ****!
+```
+
+### Advanced Usage (Options)
+
+```javascript
+const { censorId } = require('censorship-id');
+
+const text = "Dasar anjing kau, babi!";
+
+// 1. Using a custom mask
+const customMask = censorId(text, { mask: '#' });
+console.log(customMask);
+// Output: Dasar ###### kau, ####!
+
+// 2. Keeping first and last letters
+const visible = censorId(text, { keepFirstAndLast: true });
+console.log(visible);
+// Output: Dasar a****g kau, b**i!
+
+// 3. Adding custom words to censor
+const customWords = censorId("Kamu sangat malas!", { customWords: ['malas'] });
+console.log(customWords);
+// Output: Kamu sangat *****!
+```
+
+## API Reference
+
+### `censorId(text, options)`
+
+- **`text`** (string): The input text to be filtered.
+- **`options`** (object): Optional configuration.
+  - **`mask`** (string): The character used to mask words (default: `*`).
+  - **`customWords`** (string[]): Additional words to censor.
+  - **`keepFirstAndLast`** (boolean): If `true`, the first and last letters of the word remain visible (default: `false`).
+
+## License
+
+MIT © [rheatkhs](https://github.com/rheatkhs)

package/dist/index.d.mts

@@ -0,0 +1,38 @@
+/**
+ * Options for the censorship filter.
+ */
+interface CensorIdOptions {
+    /**
+     * The character used to mask the words.
+     * @default '*'
+     */
+    mask?: string;
+
+    /**
+     * An array of additional words to censor.
+     */
+    customWords?: string[];
+
+    /**
+     * If true, keeps the first and last letters visible (e.g., "a****g").
+     * @default false
+     */
+    keepFirstAndLast?: boolean;
+}
+
+/**
+ * Censors Indonesian profanity and inappropriate words from the given text.
+ * 
+ * @param text The input text to be filtered.
+ * @param options Configuration for filtering behavior.
+ * @returns The censored text.
+ */
+declare function censorId(text: string, options?: CensorIdOptions): string;
+declare function censorId<T>(text: T, options?: CensorIdOptions): T;
+
+/**
+ * The default dictionary of Indonesian profanity used by the filter.
+ */
+declare const dictionary: string[];
+
+export { type CensorIdOptions, censorId, dictionary };

package/dist/index.d.ts

@@ -0,0 +1,38 @@
+/**
+ * Options for the censorship filter.
+ */
+interface CensorIdOptions {
+    /**
+     * The character used to mask the words.
+     * @default '*'
+     */
+    mask?: string;
+
+    /**
+     * An array of additional words to censor.
+     */
+    customWords?: string[];
+
+    /**
+     * If true, keeps the first and last letters visible (e.g., "a****g").
+     * @default false
+     */
+    keepFirstAndLast?: boolean;
+}
+
+/**
+ * Censors Indonesian profanity and inappropriate words from the given text.
+ * 
+ * @param text The input text to be filtered.
+ * @param options Configuration for filtering behavior.
+ * @returns The censored text.
+ */
+declare function censorId(text: string, options?: CensorIdOptions): string;
+declare function censorId<T>(text: T, options?: CensorIdOptions): T;
+
+/**
+ * The default dictionary of Indonesian profanity used by the filter.
+ */
+declare const dictionary: string[];
+
+export { type CensorIdOptions, censorId, dictionary };

package/dist/index.js

@@ -0,0 +1,2 @@
+var f=(t,e)=>()=>(e||t((e={exports:{}}).exports,e),e.exports);var i=f((m,a)=>{var j=["anjing","asu","babi","bangsat","bajing","bajingan","bedebah","berak","bejat","brengsek","buto","cuk","dancuk","entot","goblok","itil","jancuk","jembut","kontol","kunyuk","lonte","memek","monyet","ngentot","pantat","perek","puki","setan","siak","sinting","tai","tolol"];a.exports=j});var c=i();function y(t,e={}){if(typeof t!="string")return t;let{mask:r="*",customWords:g=[],keepFirstAndLast:l=!1}=e,u=[...new Set([...c,...g])].map(s=>s.replace(/[.*+?^${}()|[\]\\]/g,"\\$&")),o=t;return u.forEach(s=>{let d=new RegExp(`(?<=\\s|^|[^a-zA-Z0-9])${s}(?=\\s|$|[^a-zA-Z0-9])`,"gi");o=o.replace(d,n=>{if(l&&n.length>2){let k=n[0],p=n[n.length-1],b=r.repeat(n.length-2);return k+b+p}return r.repeat(n.length)})}),o}module.exports={censorId:y,dictionary:c};
+//# sourceMappingURL=index.js.map

package/dist/index.js.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../dictionary.js","../index.js"],"sourcesContent":["/**\r\n * A comprehensive list of common Indonesian profanity, slang, and inappropriate words.\r\n */\r\nconst dictionary = [\r\n  \"anjing\",\r\n  \"asu\",\r\n  \"babi\",\r\n  \"bangsat\",\r\n  \"bajing\",\r\n  \"bajingan\",\r\n  \"bedebah\",\r\n  \"berak\",\r\n  \"bejat\",\r\n  \"brengsek\",\r\n  \"buto\",\r\n  \"cuk\",\r\n  \"dancuk\",\r\n  \"entot\",\r\n  \"goblok\",\r\n  \"itil\",\r\n  \"jancuk\",\r\n  \"jembut\",\r\n  \"kontol\",\r\n  \"kunyuk\",\r\n  \"lonte\",\r\n  \"memek\",\r\n  \"monyet\",\r\n  \"ngentot\",\r\n  \"pantat\",\r\n  \"perek\",\r\n  \"puki\",\r\n  \"setan\",\r\n  \"siak\",\r\n  \"sinting\",\r\n  \"tai\",\r\n  \"tolol\"\r\n];\r\n\r\nmodule.exports = dictionary;\r\n","const defaultDictionary = require(\"./dictionary\");\r\n\r\n/**\r\n * Censor Indonesian profanity and inappropriate words.\r\n *\r\n * @param {string} text - The input text to be filtered.\r\n * @param {object} options - Filtering options.\r\n * @param {string} options.mask - The character used to mask the words (default is '*').\r\n * @param {string[]} options.customWords - An array of additional words to censor.\r\n * @param {boolean} options.keepFirstAndLast - If true, keeps the first and last letters visible (default is false).\r\n * @returns {string} - The censored text.\r\n */\r\nfunction censorId(text, options = {}) {\r\n    if (typeof text !== \"string\") {\r\n        return text;\r\n    }\r\n\r\n    const {\r\n        mask = \"*\",\r\n        customWords = [],\r\n        keepFirstAndLast = false\r\n    } = options;\r\n\r\n    // Merge default dictionary with custom words\r\n    const wordsToCensor = [...new Set([...defaultDictionary, ...customWords])];\r\n\r\n    // Escape special characters in words for safety in Regex\r\n    const escapedWords = wordsToCensor.map(word =>\r\n        word.replace(/[.*+?^${}()|[\\]\\\\]/g, \"\\\\$&\")\r\n    );\r\n\r\n    let censoredText = text;\r\n\r\n    // Iterate over each word and apply masking\r\n    escapedWords.forEach(word => {\r\n        // Regex with word boundaries (\\b) and case-insensitive flag (i)\r\n        // Note: \\b doesn't work well with non-ASCII characters, but for Indonesian it's generally fine.\r\n        // However, for more robustness with various symbols, we use a pattern that matches word start/end.\r\n        const regex = new RegExp(`(?<=\\\\s|^|[^a-zA-Z0-9])${word}(?=\\\\s|$|[^a-zA-Z0-9])`, \"gi\");\r\n\r\n        censoredText = censoredText.replace(regex, (match) => {\r\n            if (keepFirstAndLast && match.length > 2) {\r\n                const first = match[0];\r\n                const last = match[match.length - 1];\r\n                const middle = mask.repeat(match.length - 2);\r\n                return first + middle + last;\r\n            }\r\n            return mask.repeat(match.length);\r\n        });\r\n    });\r\n\r\n    return censoredText;\r\n}\r\n\r\nmodule.exports = {\r\n    censorId,\r\n    dictionary: defaultDictionary\r\n};\r\n"],"mappings":"8DAAA,IAAAA,EAAAC,EAAA,CAAAC,EAAAC,IAAA,CAGA,IAAMC,EAAa,CACjB,SACA,MACA,OACA,UACA,SACA,WACA,UACA,QACA,QACA,WACA,OACA,MACA,SACA,QACA,SACA,OACA,SACA,SACA,SACA,SACA,QACA,QACA,SACA,UACA,SACA,QACA,OACA,QACA,OACA,UACA,MACA,OACF,EAEAD,EAAO,QAAUC,ICtCjB,IAAMC,EAAoB,IAY1B,SAASC,EAASC,EAAMC,EAAU,CAAC,EAAG,CAClC,GAAI,OAAOD,GAAS,SAChB,OAAOA,EAGX,GAAM,CACF,KAAAE,EAAO,IACP,YAAAC,EAAc,CAAC,EACf,iBAAAC,EAAmB,EACvB,EAAIH,EAMEI,EAHgB,CAAC,GAAG,IAAI,IAAI,CAAC,GAAGP,EAAmB,GAAGK,CAAW,CAAC,CAAC,EAGtC,IAAIG,GACnCA,EAAK,QAAQ,sBAAuB,MAAM,CAC9C,EAEIC,EAAeP,EAGnB,OAAAK,EAAa,QAAQC,GAAQ,CAIzB,IAAME,EAAQ,IAAI,OAAO,0BAA0BF,CAAI,yBAA0B,IAAI,EAErFC,EAAeA,EAAa,QAAQC,EAAQC,GAAU,CAClD,GAAIL,GAAoBK,EAAM,OAAS,EAAG,CACtC,IAAMC,EAAQD,EAAM,CAAC,EACfE,EAAOF,EAAMA,EAAM,OAAS,CAAC,EAC7BG,EAASV,EAAK,OAAOO,EAAM,OAAS,CAAC,EAC3C,OAAOC,EAAQE,EAASD,CAC5B,CACA,OAAOT,EAAK,OAAOO,EAAM,MAAM,CACnC,CAAC,CACL,CAAC,EAEMF,CACX,CAEA,OAAO,QAAU,CACb,SAAAR,EACA,WAAYD,CAChB","names":["require_dictionary","__commonJSMin","exports","module","dictionary","defaultDictionary","censorId","text","options","mask","customWords","keepFirstAndLast","escapedWords","word","censoredText","regex","match","first","last","middle"]}

package/dist/index.mjs

@@ -0,0 +1,2 @@
+var a=(t,e)=>()=>(e||t((e={exports:{}}).exports,e),e.exports);var c=a((A,i)=>{var y=["anjing","asu","babi","bangsat","bajing","bajingan","bedebah","berak","bejat","brengsek","buto","cuk","dancuk","entot","goblok","itil","jancuk","jembut","kontol","kunyuk","lonte","memek","monyet","ngentot","pantat","perek","puki","setan","siak","sinting","tai","tolol"];i.exports=y});var $=a((T,l)=>{var g=c();function w(t,e={}){if(typeof t!="string")return t;let{mask:r="*",customWords:u=[],keepFirstAndLast:d=!1}=e,k=[...new Set([...g,...u])].map(s=>s.replace(/[.*+?^${}()|[\]\\]/g,"\\$&")),o=t;return k.forEach(s=>{let p=new RegExp(`(?<=\\s|^|[^a-zA-Z0-9])${s}(?=\\s|$|[^a-zA-Z0-9])`,"gi");o=o.replace(p,n=>{if(d&&n.length>2){let b=n[0],f=n[n.length-1],j=r.repeat(n.length-2);return b+j+f}return r.repeat(n.length)})}),o}l.exports={censorId:w,dictionary:g}});export default $();
+//# sourceMappingURL=index.mjs.map

package/dist/index.mjs.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../dictionary.js","../index.js"],"sourcesContent":["/**\r\n * A comprehensive list of common Indonesian profanity, slang, and inappropriate words.\r\n */\r\nconst dictionary = [\r\n  \"anjing\",\r\n  \"asu\",\r\n  \"babi\",\r\n  \"bangsat\",\r\n  \"bajing\",\r\n  \"bajingan\",\r\n  \"bedebah\",\r\n  \"berak\",\r\n  \"bejat\",\r\n  \"brengsek\",\r\n  \"buto\",\r\n  \"cuk\",\r\n  \"dancuk\",\r\n  \"entot\",\r\n  \"goblok\",\r\n  \"itil\",\r\n  \"jancuk\",\r\n  \"jembut\",\r\n  \"kontol\",\r\n  \"kunyuk\",\r\n  \"lonte\",\r\n  \"memek\",\r\n  \"monyet\",\r\n  \"ngentot\",\r\n  \"pantat\",\r\n  \"perek\",\r\n  \"puki\",\r\n  \"setan\",\r\n  \"siak\",\r\n  \"sinting\",\r\n  \"tai\",\r\n  \"tolol\"\r\n];\r\n\r\nmodule.exports = dictionary;\r\n","const defaultDictionary = require(\"./dictionary\");\r\n\r\n/**\r\n * Censor Indonesian profanity and inappropriate words.\r\n *\r\n * @param {string} text - The input text to be filtered.\r\n * @param {object} options - Filtering options.\r\n * @param {string} options.mask - The character used to mask the words (default is '*').\r\n * @param {string[]} options.customWords - An array of additional words to censor.\r\n * @param {boolean} options.keepFirstAndLast - If true, keeps the first and last letters visible (default is false).\r\n * @returns {string} - The censored text.\r\n */\r\nfunction censorId(text, options = {}) {\r\n    if (typeof text !== \"string\") {\r\n        return text;\r\n    }\r\n\r\n    const {\r\n        mask = \"*\",\r\n        customWords = [],\r\n        keepFirstAndLast = false\r\n    } = options;\r\n\r\n    // Merge default dictionary with custom words\r\n    const wordsToCensor = [...new Set([...defaultDictionary, ...customWords])];\r\n\r\n    // Escape special characters in words for safety in Regex\r\n    const escapedWords = wordsToCensor.map(word =>\r\n        word.replace(/[.*+?^${}()|[\\]\\\\]/g, \"\\\\$&\")\r\n    );\r\n\r\n    let censoredText = text;\r\n\r\n    // Iterate over each word and apply masking\r\n    escapedWords.forEach(word => {\r\n        // Regex with word boundaries (\\b) and case-insensitive flag (i)\r\n        // Note: \\b doesn't work well with non-ASCII characters, but for Indonesian it's generally fine.\r\n        // However, for more robustness with various symbols, we use a pattern that matches word start/end.\r\n        const regex = new RegExp(`(?<=\\\\s|^|[^a-zA-Z0-9])${word}(?=\\\\s|$|[^a-zA-Z0-9])`, \"gi\");\r\n\r\n        censoredText = censoredText.replace(regex, (match) => {\r\n            if (keepFirstAndLast && match.length > 2) {\r\n                const first = match[0];\r\n                const last = match[match.length - 1];\r\n                const middle = mask.repeat(match.length - 2);\r\n                return first + middle + last;\r\n            }\r\n            return mask.repeat(match.length);\r\n        });\r\n    });\r\n\r\n    return censoredText;\r\n}\r\n\r\nmodule.exports = {\r\n    censorId,\r\n    dictionary: defaultDictionary\r\n};\r\n"],"mappings":"8DAAA,IAAAA,EAAAC,EAAA,CAAAC,EAAAC,IAAA,CAGA,IAAMC,EAAa,CACjB,SACA,MACA,OACA,UACA,SACA,WACA,UACA,QACA,QACA,WACA,OACA,MACA,SACA,QACA,SACA,OACA,SACA,SACA,SACA,SACA,QACA,QACA,SACA,UACA,SACA,QACA,OACA,QACA,OACA,UACA,MACA,OACF,EAEAD,EAAO,QAAUC,ICtCjB,IAAAC,EAAAC,EAAA,CAAAC,EAAAC,IAAA,KAAMC,EAAoB,IAY1B,SAASC,EAASC,EAAMC,EAAU,CAAC,EAAG,CAClC,GAAI,OAAOD,GAAS,SAChB,OAAOA,EAGX,GAAM,CACF,KAAAE,EAAO,IACP,YAAAC,EAAc,CAAC,EACf,iBAAAC,EAAmB,EACvB,EAAIH,EAMEI,EAHgB,CAAC,GAAG,IAAI,IAAI,CAAC,GAAGP,EAAmB,GAAGK,CAAW,CAAC,CAAC,EAGtC,IAAIG,GACnCA,EAAK,QAAQ,sBAAuB,MAAM,CAC9C,EAEIC,EAAeP,EAGnB,OAAAK,EAAa,QAAQC,GAAQ,CAIzB,IAAME,EAAQ,IAAI,OAAO,0BAA0BF,CAAI,yBAA0B,IAAI,EAErFC,EAAeA,EAAa,QAAQC,EAAQC,GAAU,CAClD,GAAIL,GAAoBK,EAAM,OAAS,EAAG,CACtC,IAAMC,EAAQD,EAAM,CAAC,EACfE,EAAOF,EAAMA,EAAM,OAAS,CAAC,EAC7BG,EAASV,EAAK,OAAOO,EAAM,OAAS,CAAC,EAC3C,OAAOC,EAAQE,EAASD,CAC5B,CACA,OAAOT,EAAK,OAAOO,EAAM,MAAM,CACnC,CAAC,CACL,CAAC,EAEMF,CACX,CAEAV,EAAO,QAAU,CACb,SAAAE,EACA,WAAYD,CAChB","names":["require_dictionary","__commonJSMin","exports","module","dictionary","require_index","__commonJSMin","exports","module","defaultDictionary","censorId","text","options","mask","customWords","keepFirstAndLast","escapedWords","word","censoredText","regex","match","first","last","middle"]}

package/package.json

@@ -0,0 +1,44 @@
+{
+  "name": "censorship-id",
+  "version": "1.0.0",
+  "description": "A robust Indonesian profanity filter for detecting and masking inappropriate words.",
+  "main": "./dist/index.js",
+  "module": "./dist/index.mjs",
+  "types": "./dist/index.d.ts",
+  "exports": {
+    ".": {
+      "require": "./dist/index.js",
+      "import": "./dist/index.mjs",
+      "types": "./dist/index.d.ts"
+    }
+  },
+  "files": [
+    "dist"
+  ],
+  "scripts": {
+    "build": "tsup",
+    "dev": "tsup --watch",
+    "test": "jest",
+    "lint": "eslint ."
+  },
+  "keywords": [
+    "indonesia",
+    "profanity",
+    "filter",
+    "sensor",
+    "kata kasar",
+    "censorship",
+    "bahasa-indonesia",
+    "slang"
+  ],
+  "author": "rheatkhs",
+  "license": "MIT",
+  "engines": {
+    "node": ">=12.0.0"
+  },
+  "devDependencies": {
+    "jest": "^29.7.0",
+    "tsup": "^8.5.1",
+    "typescript": "^6.0.2"
+  }
+}