censorship-id 1.0.0 → 1.1.0

package/README.md

@@ -7,7 +7,8 @@ A robust and simple npm package for detecting and masking Indonesian profanity,
 
 ## Features
 
-- **Comprehensive Dictionary**: Pre-loaded with hundreds of common Indonesian bad words.
+- **Smart Detection**: Optional `smartMode` to handle leetspeak (e.g., `4njing`), repeated characters (e.g., `baaaaaabiii`), and punctuation insertion (e.g., `a.n.j.i.n.g`).
+- **Comprehensive Dictionary**: Pre-loaded with 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.
@@ -54,6 +55,15 @@ console.log(visible);
 const customWords = censorId("Kamu sangat malas!", { customWords: ['malas'] });
 console.log(customWords);
 // Output: Kamu sangat *****!
+
+// 4. Smart Mode (handles leetspeak & repeats)
+const smart = censorId("D4s4r 4njing!", { smartMode: true });
+console.log(smart);
+// Output: D4s4r ******!
+
+const repeats = censorId("baaaaaaaabiiiiii", { smartMode: true });
+console.log(repeats);
+// Output: ****************
 ```
 
 ## API Reference
@@ -65,6 +75,7 @@ console.log(customWords);
   - **`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`).
+  - **`smartMode`** (boolean): If `true`, detects leetspeak and repeated characters (default: `false`).
 
 ## License
 

package/dist/index.d.mts

@@ -18,6 +18,12 @@ interface CensorIdOptions {
      * @default false
      */
     keepFirstAndLast?: boolean;
+
+    /**
+     * If true, handles leetspeak (e.g., "4njing") and repeated characters (e.g., "baaaaaaabiii").
+     * @default false
+     */
+    smartMode?: boolean;
 }
 
 /**

package/dist/index.d.ts

@@ -18,6 +18,12 @@ interface CensorIdOptions {
      * @default false
      */
     keepFirstAndLast?: boolean;
+
+    /**
+     * If true, handles leetspeak (e.g., "4njing") and repeated characters (e.g., "baaaaaaabiii").
+     * @default false
+     */
+    smartMode?: boolean;
 }
 
 /**

package/dist/index.js

@@ -1,2 +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};
+var x=(n,t)=>()=>(t||n((t={exports:{}}).exports,t),t.exports);var k=x((P,u)=>{var C=["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"];u.exports=C});var b=k(),p={4:"a",3:"e",1:"i",0:"o",5:"s",7:"t",8:"b",9:"g","@":"a",$:"s","!":"i","(":"c"};function w(n,t={}){if(typeof n!="string")return n;let{mask:g="*",customWords:f=[],keepFirstAndLast:d=!1,smartMode:h=!1}=t,j=[...new Set([...b,...f])].sort((s,r)=>r.length-s.length),o=n;return j.forEach(s=>{let r;h?r=Array.from(s).map((i,c)=>{let a=i.toLowerCase(),y=Object.keys(p).filter(l=>p[l]===a),m=[a,...y].map(l=>l.replace(/[.*+?^${}()|[\]\\]/g,"\\$&")),A=c===s.length-1?"+":"+[^a-zA-Z0-9]*";return`[${m.join("")}]${A}`}).join(""):r=s.replace(/[.*+?^${}()|[\]\\]/g,"\\$&");let $=new RegExp(`(?<=\\s|^|[^a-zA-Z0-9])${r}(?=\\s|$|[^a-zA-Z0-9])`,"gi");o=o.replace($,e=>{if(d&&e.length>2){let i=e[0],c=e[e.length-1],a=g.repeat(e.length-2);return i+a+c}return g.repeat(e.length)})}),o}module.exports={censorId:w,dictionary:b};
 //# sourceMappingURL=index.js.map

package/dist/index.js.map

@@ -1 +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"]}
+{"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// Leetspeak mapping\r\nconst leetMap = {\r\n    \"4\": \"a\",\r\n    \"3\": \"e\",\r\n    \"1\": \"i\",\r\n    \"0\": \"o\",\r\n    \"5\": \"s\",\r\n    \"7\": \"t\",\r\n    \"8\": \"b\",\r\n    \"9\": \"g\",\r\n    \"@\": \"a\",\r\n    \"$\": \"s\",\r\n    \"!\": \"i\",\r\n    \"(\": \"c\"\r\n};\r\n\r\n/**\r\n * Censor Indonesian profanity and inappropriate words.\r\n *\r\n * @param {string} text - The input text to be filtered.\r\n * @param {object} options - Filtering options.\r\n * @param {string} options.mask - The character used to mask the words (default is '*').\r\n * @param {string[]} options.customWords - An array of additional words to censor.\r\n * @param {boolean} options.keepFirstAndLast - If true, keeps the first and last letters visible (default is false).\r\n * @param {boolean} options.smartMode - If true, handles leetspeak and repeated characters (default is false).\r\n * @returns {string} - The censored text.\r\n */\r\nfunction censorId(text, options = {}) {\r\n    if (typeof text !== \"string\") {\r\n        return text;\r\n    }\r\n\r\n    const {\r\n        mask = \"*\",\r\n        customWords = [],\r\n        keepFirstAndLast = false,\r\n        smartMode = false\r\n    } = options;\r\n\r\n    // Merge default dictionary with custom words and sort by length descending\r\n    const wordsToCensor = [...new Set([...defaultDictionary, ...customWords])].sort((a, b) => b.length - a.length);\r\n\r\n    let censoredText = text;\r\n\r\n    // Iterate over each word and apply masking\r\n    wordsToCensor.forEach(word => {\r\n        let searchPattern;\r\n        if (smartMode) {\r\n            // Create a pattern that allows:\r\n            // 1. Any number of repeats for each character (e.g., a+n+j+i+n+g+)\r\n            // 2. Optional non-alphanumeric characters between letters (e.g., a[...]*n[...]*j)\r\n            // 3. Mapping of leetspeak characters\r\n\r\n            const charPatterns = Array.from(word).map((char, index) => {\r\n                const lowerChar = char.toLowerCase();\r\n                const leetChars = Object.keys(leetMap).filter(key => leetMap[key] === lowerChar);\r\n                const variants = [lowerChar, ...leetChars].map(c => c.replace(/[.*+?^${}()|[\\]\\\\]/g, \"\\\\$&\"));\r\n\r\n                // Only allow non-alphanumeric between characters, not after the last one\r\n                const suffix = index === word.length - 1 ? \"+\" : \"+[^a-zA-Z0-9]*\";\r\n                return `[${variants.join(\"\")}]${suffix}`;\r\n            });\r\n\r\n            searchPattern = charPatterns.join(\"\");\r\n        } else {\r\n            // Standard escaping for regex\r\n            searchPattern = word.replace(/[.*+?^${}()|[\\]\\\\]/g, \"\\\\$&\");\r\n        }\r\n\r\n        const regex = new RegExp(`(?<=\\\\s|^|[^a-zA-Z0-9])${searchPattern}(?=\\\\s|$|[^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,IAGpBC,EAAU,CACZ,EAAK,IACL,EAAK,IACL,EAAK,IACL,EAAK,IACL,EAAK,IACL,EAAK,IACL,EAAK,IACL,EAAK,IACL,IAAK,IACL,EAAK,IACL,IAAK,IACL,IAAK,GACT,EAaA,SAASC,EAASC,EAAMC,EAAU,CAAC,EAAG,CAClC,GAAI,OAAOD,GAAS,SAChB,OAAOA,EAGX,GAAM,CACF,KAAAE,EAAO,IACP,YAAAC,EAAc,CAAC,EACf,iBAAAC,EAAmB,GACnB,UAAAC,EAAY,EAChB,EAAIJ,EAGEK,EAAgB,CAAC,GAAG,IAAI,IAAI,CAAC,GAAGT,EAAmB,GAAGM,CAAW,CAAC,CAAC,EAAE,KAAK,CAACI,EAAGC,IAAMA,EAAE,OAASD,EAAE,MAAM,EAEzGE,EAAeT,EAGnB,OAAAM,EAAc,QAAQI,GAAQ,CAC1B,IAAIC,EACAN,EAgBAM,EAVqB,MAAM,KAAKD,CAAI,EAAE,IAAI,CAACE,EAAMC,IAAU,CACvD,IAAMC,EAAYF,EAAK,YAAY,EAC7BG,EAAY,OAAO,KAAKjB,CAAO,EAAE,OAAOkB,GAAOlB,EAAQkB,CAAG,IAAMF,CAAS,EACzEG,EAAW,CAACH,EAAW,GAAGC,CAAS,EAAE,IAAIG,GAAKA,EAAE,QAAQ,sBAAuB,MAAM,CAAC,EAGtFC,EAASN,IAAUH,EAAK,OAAS,EAAI,IAAM,iBACjD,MAAO,IAAIO,EAAS,KAAK,EAAE,CAAC,IAAIE,CAAM,EAC1C,CAAC,EAE4B,KAAK,EAAE,EAGpCR,EAAgBD,EAAK,QAAQ,sBAAuB,MAAM,EAG9D,IAAMU,EAAQ,IAAI,OAAO,0BAA0BT,CAAa,yBAA0B,IAAI,EAE9FF,EAAeA,EAAa,QAAQW,EAAQC,GAAU,CAClD,GAAIjB,GAAoBiB,EAAM,OAAS,EAAG,CACtC,IAAMC,EAAQD,EAAM,CAAC,EACfE,EAAOF,EAAMA,EAAM,OAAS,CAAC,EAC7BG,EAAStB,EAAK,OAAOmB,EAAM,OAAS,CAAC,EAC3C,OAAOC,EAAQE,EAASD,CAC5B,CACA,OAAOrB,EAAK,OAAOmB,EAAM,MAAM,CACnC,CAAC,CACL,CAAC,EAEMZ,CACX,CAEA,OAAO,QAAU,CACb,SAAAV,EACA,WAAYF,CAChB","names":["require_dictionary","__commonJSMin","exports","module","dictionary","defaultDictionary","leetMap","censorId","text","options","mask","customWords","keepFirstAndLast","smartMode","wordsToCensor","a","b","censoredText","word","searchPattern","char","index","lowerChar","leetChars","key","variants","c","suffix","regex","match","first","last","middle"]}

package/dist/index.mjs

@@ -1,2 +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 $();
+var u=(n,t)=>()=>(t||n((t={exports:{}}).exports,t),t.exports);var p=u((E,k)=>{var w=["anjing","asu","babi","bangsat","bajing","bajingan","bedebah","berak","bejat","brengsek","buto","cuk","dancuk","entot","goblok","itil","jancuk","jembut","kontol","kunyuk","lonte","memek","monyet","ngentot","pantat","perek","puki","setan","siak","sinting","tai","tolol"];k.exports=w});var P=u((L,d)=>{var f=p(),b={4:"a",3:"e",1:"i",0:"o",5:"s",7:"t",8:"b",9:"g","@":"a",$:"s","!":"i","(":"c"};function z(n,t={}){if(typeof n!="string")return n;let{mask:g="*",customWords:h=[],keepFirstAndLast:j=!1,smartMode:$=!1}=t,y=[...new Set([...f,...h])].sort((s,r)=>r.length-s.length),o=n;return y.forEach(s=>{let r;$?r=Array.from(s).map((i,c)=>{let a=i.toLowerCase(),A=Object.keys(b).filter(l=>b[l]===a),x=[a,...A].map(l=>l.replace(/[.*+?^${}()|[\]\\]/g,"\\$&")),C=c===s.length-1?"+":"+[^a-zA-Z0-9]*";return`[${x.join("")}]${C}`}).join(""):r=s.replace(/[.*+?^${}()|[\]\\]/g,"\\$&");let m=new RegExp(`(?<=\\s|^|[^a-zA-Z0-9])${r}(?=\\s|$|[^a-zA-Z0-9])`,"gi");o=o.replace(m,e=>{if(j&&e.length>2){let i=e[0],c=e[e.length-1],a=g.repeat(e.length-2);return i+a+c}return g.repeat(e.length)})}),o}d.exports={censorId:z,dictionary:f}});export default P();
 //# sourceMappingURL=index.mjs.map

package/dist/index.mjs.map

@@ -1 +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"]}
+{"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// Leetspeak mapping\r\nconst leetMap = {\r\n    \"4\": \"a\",\r\n    \"3\": \"e\",\r\n    \"1\": \"i\",\r\n    \"0\": \"o\",\r\n    \"5\": \"s\",\r\n    \"7\": \"t\",\r\n    \"8\": \"b\",\r\n    \"9\": \"g\",\r\n    \"@\": \"a\",\r\n    \"$\": \"s\",\r\n    \"!\": \"i\",\r\n    \"(\": \"c\"\r\n};\r\n\r\n/**\r\n * Censor Indonesian profanity and inappropriate words.\r\n *\r\n * @param {string} text - The input text to be filtered.\r\n * @param {object} options - Filtering options.\r\n * @param {string} options.mask - The character used to mask the words (default is '*').\r\n * @param {string[]} options.customWords - An array of additional words to censor.\r\n * @param {boolean} options.keepFirstAndLast - If true, keeps the first and last letters visible (default is false).\r\n * @param {boolean} options.smartMode - If true, handles leetspeak and repeated characters (default is false).\r\n * @returns {string} - The censored text.\r\n */\r\nfunction censorId(text, options = {}) {\r\n    if (typeof text !== \"string\") {\r\n        return text;\r\n    }\r\n\r\n    const {\r\n        mask = \"*\",\r\n        customWords = [],\r\n        keepFirstAndLast = false,\r\n        smartMode = false\r\n    } = options;\r\n\r\n    // Merge default dictionary with custom words and sort by length descending\r\n    const wordsToCensor = [...new Set([...defaultDictionary, ...customWords])].sort((a, b) => b.length - a.length);\r\n\r\n    let censoredText = text;\r\n\r\n    // Iterate over each word and apply masking\r\n    wordsToCensor.forEach(word => {\r\n        let searchPattern;\r\n        if (smartMode) {\r\n            // Create a pattern that allows:\r\n            // 1. Any number of repeats for each character (e.g., a+n+j+i+n+g+)\r\n            // 2. Optional non-alphanumeric characters between letters (e.g., a[...]*n[...]*j)\r\n            // 3. Mapping of leetspeak characters\r\n\r\n            const charPatterns = Array.from(word).map((char, index) => {\r\n                const lowerChar = char.toLowerCase();\r\n                const leetChars = Object.keys(leetMap).filter(key => leetMap[key] === lowerChar);\r\n                const variants = [lowerChar, ...leetChars].map(c => c.replace(/[.*+?^${}()|[\\]\\\\]/g, \"\\\\$&\"));\r\n\r\n                // Only allow non-alphanumeric between characters, not after the last one\r\n                const suffix = index === word.length - 1 ? \"+\" : \"+[^a-zA-Z0-9]*\";\r\n                return `[${variants.join(\"\")}]${suffix}`;\r\n            });\r\n\r\n            searchPattern = charPatterns.join(\"\");\r\n        } else {\r\n            // Standard escaping for regex\r\n            searchPattern = word.replace(/[.*+?^${}()|[\\]\\\\]/g, \"\\\\$&\");\r\n        }\r\n\r\n        const regex = new RegExp(`(?<=\\\\s|^|[^a-zA-Z0-9])${searchPattern}(?=\\\\s|$|[^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,IAGpBC,EAAU,CACZ,EAAK,IACL,EAAK,IACL,EAAK,IACL,EAAK,IACL,EAAK,IACL,EAAK,IACL,EAAK,IACL,EAAK,IACL,IAAK,IACL,EAAK,IACL,IAAK,IACL,IAAK,GACT,EAaA,SAASC,EAASC,EAAMC,EAAU,CAAC,EAAG,CAClC,GAAI,OAAOD,GAAS,SAChB,OAAOA,EAGX,GAAM,CACF,KAAAE,EAAO,IACP,YAAAC,EAAc,CAAC,EACf,iBAAAC,EAAmB,GACnB,UAAAC,EAAY,EAChB,EAAIJ,EAGEK,EAAgB,CAAC,GAAG,IAAI,IAAI,CAAC,GAAGT,EAAmB,GAAGM,CAAW,CAAC,CAAC,EAAE,KAAK,CAACI,EAAGC,IAAMA,EAAE,OAASD,EAAE,MAAM,EAEzGE,EAAeT,EAGnB,OAAAM,EAAc,QAAQI,GAAQ,CAC1B,IAAIC,EACAN,EAgBAM,EAVqB,MAAM,KAAKD,CAAI,EAAE,IAAI,CAACE,EAAMC,IAAU,CACvD,IAAMC,EAAYF,EAAK,YAAY,EAC7BG,EAAY,OAAO,KAAKjB,CAAO,EAAE,OAAOkB,GAAOlB,EAAQkB,CAAG,IAAMF,CAAS,EACzEG,EAAW,CAACH,EAAW,GAAGC,CAAS,EAAE,IAAIG,GAAKA,EAAE,QAAQ,sBAAuB,MAAM,CAAC,EAGtFC,EAASN,IAAUH,EAAK,OAAS,EAAI,IAAM,iBACjD,MAAO,IAAIO,EAAS,KAAK,EAAE,CAAC,IAAIE,CAAM,EAC1C,CAAC,EAE4B,KAAK,EAAE,EAGpCR,EAAgBD,EAAK,QAAQ,sBAAuB,MAAM,EAG9D,IAAMU,EAAQ,IAAI,OAAO,0BAA0BT,CAAa,yBAA0B,IAAI,EAE9FF,EAAeA,EAAa,QAAQW,EAAQC,GAAU,CAClD,GAAIjB,GAAoBiB,EAAM,OAAS,EAAG,CACtC,IAAMC,EAAQD,EAAM,CAAC,EACfE,EAAOF,EAAMA,EAAM,OAAS,CAAC,EAC7BG,EAAStB,EAAK,OAAOmB,EAAM,OAAS,CAAC,EAC3C,OAAOC,EAAQE,EAASD,CAC5B,CACA,OAAOrB,EAAK,OAAOmB,EAAM,MAAM,CACnC,CAAC,CACL,CAAC,EAEMZ,CACX,CAEAb,EAAO,QAAU,CACb,SAAAG,EACA,WAAYF,CAChB","names":["require_dictionary","__commonJSMin","exports","module","dictionary","require_index","__commonJSMin","exports","module","defaultDictionary","leetMap","censorId","text","options","mask","customWords","keepFirstAndLast","smartMode","wordsToCensor","a","b","censoredText","word","searchPattern","char","index","lowerChar","leetChars","key","variants","c","suffix","regex","match","first","last","middle"]}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "censorship-id",
-  "version": "1.0.0",
+  "version": "1.1.0",
   "description": "A robust Indonesian profanity filter for detecting and masking inappropriate words.",
   "main": "./dist/index.js",
   "module": "./dist/index.mjs",
@@ -41,4 +41,4 @@
     "tsup": "^8.5.1",
     "typescript": "^6.0.2"
   }
-}
+}