text-sanctifier 1.0.20 → 1.1.0

package/README.md

@@ -5,12 +5,15 @@
 [![bundle size](https://img.shields.io/bundlephobia/minzip/text-sanctifier)](https://bundlephobia.com/package/text-sanctifier)
 [![license](https://img.shields.io/npm/l/text-sanctifier)](https://github.com/iWhatty/text-sanctifier/blob/main/LICENSE)
 [![stars](https://img.shields.io/github/stars/iWhatty/text-sanctifier?style=social)](https://github.com/iWhatty/text-sanctifier)
+[![types](https://img.shields.io/npm/types/text-sanctifier)](https://www.npmjs.com/package/text-sanctifier)
 
-Brutal text normalizer and invisible Unicode scrubber for modern web projects. ~1.66 KB gzipped.
+Brutal text normalizer and invisible Unicode scrubber for modern web projects. ~2.17 KB gzipped.
 
 ## Features
 
 - Purges zero-width Unicode garbage
+- Purges bidi controls, including the isolates (U+2066–U+2069) and the Arabic letter mark (U+061C) used in Trojan Source attacks
+- Locates invisible and control characters by offset, line and column (`inspectTextDetailed`)
 - Normalizes line endings (CRLF, CR, LF) to LF
 - Collapses unwanted spaces and paragraphs
 - Nukes control characters (if enabled)
@@ -137,6 +140,42 @@ const report = inspectText(input);
 
 Use `inspectText` to preflight text content before rendering, storing, or linting. It's a diagnostic tool to help inform sanitization needs. Pass the report to `getRecommendedSanctifierOptions(report)` to auto-generate config flags for `summonSanctifier()`.
 
+### `inspectTextDetailed(text: string, options?: { maxFindings?: number }): DetailedTrashReport`
+
+Returns each invisible or control character with its offset, line, column, code point and category, plus per-category counts and a `truncated` flag. Also exported from the browser build (`text-sanctifier/browser`). `inspectText`'s output is unchanged.
+
+```js
+import { inspectTextDetailed } from 'text-sanctifier';
+
+const { findings, counts, total, truncated } = inspectTextDetailed(input, { maxFindings: 100 });
+
+/*
+findings: [
+  { offset: 0, line: 1, column: 1, codePoint: 0xFEFF, category: 'bom', atStart: true },
+  { offset: 42, line: 3, column: 7, codePoint: 0x2067, category: 'bidi_control' },
+]
+counts: { bidi_control: 1, zero_width: 0, nonbreaking_space: 0, bom: 1, nul: 0, c0_control: 0, c1_control: 0 }
+total: 2
+truncated: false
+*/
+```
+
+| Category | Code points |
+| --- | --- |
+| `bidi_control` | U+061C, U+200E, U+200F, U+202A–U+202E, U+2066–U+2069 |
+| `zero_width` | U+200B–U+200D, U+2060 |
+| `nonbreaking_space` | U+00A0, U+2000–U+200A, U+202F, U+3000 (non-breaking and typographic spaces) |
+| `bom` | U+FEFF; `atStart` is true at offset 0, where a BOM is legitimate |
+| `nul` | U+0000 |
+| `c0_control` | U+0001–U+001F except tab, LF and CR; U+007F |
+| `c1_control` | U+0080–U+009F |
+
+`offset` is a 0-based UTF-16 index; `line` and `column` are 1-based, with columns in UTF-16 code units and lines ending at LF, CR or CRLF. Every occurrence is counted; only the first `maxFindings` (default 100, `Infinity` for all) are listed, and `truncated` says when some were not. The scan is one pass with no regex and no copy of the input.
+
+`zero_width` also flags U+200D (zero width joiner) inside emoji ZWJ sequences such as 👨‍👩‍👧, so a finding there is not necessarily hidden text. Filter by neighbouring code points if you need to tell them apart. (`purgeInvisibleChars` removes those joiners too, splitting the emoji; `keyboardOnlyEmoji` keeps the sequences whole.)
+
+The categories cover exactly what `nukeControls` and `purgeInvisibleChars` strip.
+
 ---
 
 ## Notes
@@ -145,12 +184,14 @@ Use `inspectText` to preflight text content before rendering, storing, or lintin
 
 Requires a modern JavaScript runtime with ES2020+ support:
 
-- Node.js 14+
+- Node.js 18+ (`engines.node >=18`)
 - Modern evergreen browsers
 
 ### Package and build info
 
 - **Source (`src/`):** ES2020+ ESM modules with JSDoc
+- **ESM only:** no CommonJS build; `require('text-sanctifier')` works only on Node versions with `require(esm)` support (20.19+, 22.12+)
+- **Types:** TypeScript declarations ship in `dist/types`
 - **Browser build (`dist/`):** Minified ESM bundle for `<script type="module">`
 - **Tree-shake friendly:** ships `sideEffects: false`
 - **Zero transpilation:** no built-in polyfills or runtime overhead

package/dist/text-sanctifier.min.js

@@ -1,9 +1,12 @@
-function g(a={}){const c=!!a.purgeInvisibleChars,b=!!a.purgeEmojis,d=!!a.nukeControls,f=!!a.keyboardOnlyFilter,h=!!a.normalizeNewlines,m=!!a.trimSpacesAroundNewlines,e=!!a.collapseNewLines,r=!!a.preserveParagraphs,t=!!a.collapseSpaces,u=!!a.finalTrim,n=Number.isFinite(a.maxLength)&&0<=a.maxLength?a.maxLength:Infinity,k="truncate"===a.g||"noop"===a.g||"throw"===a.g?a.g:"throw";return z=>l(z,c,b,d,f,h,m,e,r,t,u,n,k)}g.strict=a=>l(a,!0,!0,!0,!1,!0,!0,!0,!1,!0,!0);
-g.loose=a=>l(a,!1,!1,!1,!1,!0,!0,!0,!0,!0,!0);g.keyboardOnlyEmoji=a=>l(a,!1,!1,!1,!0,!0,!0,!1,!1,!1,!0);g.keyboardOnly=a=>l(a,!0,!0,!0,!0,!0,!0,!0,!1,!0,!0);
-function l(a,c=!1,b=!1,d=!1,f=!1,h=!1,m=!1,e=!1,r=!1,t=!1,u=!1,n=Infinity,k="throw"){if("string"!==typeof a)throw new TypeError("sanctifyText expects a string input.");"truncate"!==k&&"noop"!==k&&"throw"!==k&&(k="throw");if(a.length>n)switch(k){case "truncate":a=a.slice(0,n);break;case "noop":return a;default:throw new RangeError(`sanctifyText input length ${a.length} exceeds maxLength ${n}.`);}c&&(a=a.replace(p,""));b&&(a=a.replace(q,""));d&&(a=a.replace(v,""));f&&(a=w(a,b));h&&(a=a.replace(x,"\n"));
-m&&(a=a.replace(y,"$1"));e&&(c=a,a=r?c.replace(A,"\n\n"):c.replace(B,"\n"));t&&(a=a.replace(C," "));return u?a.trim():a}var p=/[\u00A0\u2000-\u200D\u202F\u2060\u3000\uFEFF\u200E\u200F\u202A-\u202E]+/g,D=/[^\x20-\x7E\r\n]+/gu;function w(a,c=!1){a=E(a);return c?a.replace(D,""):a.replace(D,b=>{q.lastIndex=0;if(q.test(b)){q.lastIndex=0;var d="";for(const f of b.matchAll(q))d+=f[0];b=d}else b="";return b})}
-var F=/[\u2018\u2019\u201A\u201B\u2032\u2035]/g,G=/[\u201C\u201D\u201E\u201F\u2033\u2036\u00AB\u00BB]/g,H=/[\u2012\u2013\u2014\u2015\u2212]/g,I=/\u2026/g,J=/[\u2022\u00B7]/g,K=/[\uFF01-\uFF5E]/g;function E(a){return a.replace(F,"'").replace(G,'"').replace(H,"-").replace(I,"...").replace(J,"*").replace(K,c=>String.fromCharCode(c.charCodeAt(0)-65248))}var q;try{q=RegExp("(?:\\p{Extended_Pictographic}(?:\\uFE0F|\\uFE0E)?(?:\\u200D(?:\\p{Extended_Pictographic}|\\w)+)*)","gu")}catch{q=/[\u{2700}-\u{27BF}\u{1F300}-\u{1FAFF}\u{1F3FB}-\u{1F3FF}\u200D\uFE0F\u{1F1E6}-\u{1F1FF}]/gu}
-var x=/\r\n|\r|\n/g,y=/[ \t]*(\n+)[ \t]*/g,B=/\n{2,}/g,A=/\n{3,}/g,C=/ {2,}/g,v=/[\u0000-\u0008\u000B\u000C\u000E-\u001F\u007F\u0080-\u009F\u200E\u200F\u202A-\u202E]+/g;function L(a,c){a.lastIndex=0;return a.test(c)}
-function M(a){if("string"!==typeof a)throw new TypeError("inspectText expects a string input.");const c=[],b={hasControlChars:!1,hasInvisibleChars:!1,hasMixedNewlines:!1,newlineStyle:null,hasEmojis:!1,hasNonKeyboardChars:!1,summary:c};L(v,a)&&(b.hasControlChars=!0,c.push("Control characters detected."));L(p,a)&&(b.hasInvisibleChars=!0,c.push("Invisible Unicode characters detected."));L(q,a)&&(b.hasEmojis=!0,c.push("Emojis detected."));if("string"!==typeof a)throw new TypeError("getNewlineStats expects a string input.");
-var d=a.replace(/\r\n/g,"");d={i:(a.match(/\r\n/g)||[]).length,h:(d.match(/\r/g)||[]).length,j:(d.match(/\n/g)||[]).length};const f=[];0<d.i&&f.push("CRLF");0<d.h&&f.push("CR");0<d.j&&f.push("LF");const {l:h,types:m}={...d,types:f,l:1<f.length};b.hasMixedNewlines=h;b.newlineStyle=h?"Mixed":m[0]||null;b.newlineStyle&&c.push(h?"Mixed newline styles detected.":`Consistent newline style: ${b.newlineStyle}`);a:{a=E(a);if(L(D,a))for(e of a)if(!("\n"===e||"\r"===e||" "<=e&&"~">=e||L(q,e))){var e=!0;break a}e=
-!1}e&&(b.hasNonKeyboardChars=!0,c.push("Non-keyboard characters detected."));return b}function N(a){return{purgeInvisibleChars:a.hasInvisibleChars,purgeEmojis:a.hasEmojis,nukeControls:a.hasControlChars,keyboardOnlyFilter:a.hasNonKeyboardChars,normalizeNewlines:a.hasMixedNewlines||"CRLF"===a.newlineStyle||"CR"===a.newlineStyle}}export { g as summonSanctifier, M as inspectText, N as getRecommendedSanctifierOptions };
+function n(a={}){const c=!!a.purgeInvisibleChars,d=!!a.purgeEmojis,f=!!a.nukeControls,g=!!a.keyboardOnlyFilter,l=!!a.normalizeNewlines,h=!!a.trimSpacesAroundNewlines,b=!!a.collapseNewLines,e=!!a.preserveParagraphs,k=!!a.collapseSpaces,m=!!a.finalTrim,p=Number.isFinite(a.maxLength)&&0<=a.maxLength?a.maxLength:Infinity,q="truncate"===a.g||"noop"===a.g||"throw"===a.g?a.g:"throw";return z=>r(z,c,d,f,g,l,h,b,e,k,m,p,q)}n.strict=a=>r(a,!0,!0,!0,!1,!0,!0,!0,!1,!0,!0);
+n.loose=a=>r(a,!1,!1,!1,!1,!0,!0,!0,!0,!0,!0);n.keyboardOnlyEmoji=a=>r(a,!1,!1,!1,!0,!0,!0,!1,!1,!1,!0);n.keyboardOnly=a=>r(a,!0,!0,!0,!0,!0,!0,!0,!1,!0,!0);
+function r(a,c=!1,d=!1,f=!1,g=!1,l=!1,h=!1,b=!1,e=!1,k=!1,m=!1,p=Infinity,q="throw"){if("string"!==typeof a)throw new TypeError("sanctifyText expects a string input.");"truncate"!==q&&"noop"!==q&&"throw"!==q&&(q="throw");if(a.length>p)switch(q){case "truncate":a=a.slice(0,p);break;case "noop":return a;default:throw new RangeError(`sanctifyText input length ${a.length} exceeds maxLength ${p}.`);}c&&(a=a.replace(t,""));d&&(a=a.replace(u,""));f&&(a=a.replace(v,""));g&&(a=w(a,d));l&&(a=a.replace(x,"\n"));
+h&&(a=a.replace(y,"$1"));b&&(c=a,a=e?c.replace(A,"\n\n"):c.replace(B,"\n"));k&&(a=a.replace(C," "));return m?a.trim():a}var t=/[\u00A0\u2000-\u200D\u202F\u2060\u3000\uFEFF\u061C\u200E\u200F\u202A-\u202E\u2066-\u2069]+/g,D=/[^\x20-\x7E\r\n]+/gu;function w(a,c=!1){a=E(a);return c?a.replace(D,""):a.replace(D,d=>{u.lastIndex=0;if(u.test(d)){u.lastIndex=0;var f="";for(const g of d.matchAll(u))f+=g[0];d=f}else d="";return d})}
+var F=/[\u2018\u2019\u201A\u201B\u2032\u2035]/g,G=/[\u201C\u201D\u201E\u201F\u2033\u2036\u00AB\u00BB]/g,H=/[\u2012\u2013\u2014\u2015\u2212]/g,I=/\u2026/g,J=/[\u2022\u00B7]/g,K=/[\uFF01-\uFF5E]/g;function E(a){return a.replace(F,"'").replace(G,'"').replace(H,"-").replace(I,"...").replace(J,"*").replace(K,c=>String.fromCharCode(c.charCodeAt(0)-65248))}var u;try{u=RegExp("(?:\\p{Extended_Pictographic}(?:\\uFE0F|\\uFE0E)?(?:\\u200D(?:\\p{Extended_Pictographic}|\\w)+)*)","gu")}catch{u=/[\u{2700}-\u{27BF}\u{1F300}-\u{1FAFF}\u{1F3FB}-\u{1F3FF}\u200D\uFE0F\u{1F1E6}-\u{1F1FF}]/gu}
+var x=/\r\n|\r|\n/g,y=/[ \t]*(\n+)[ \t]*/g,B=/\n{2,}/g,A=/\n{3,}/g,C=/ {2,}/g,v=/[\u0000-\u0008\u000B\u000C\u000E-\u001F\u007F\u0080-\u009F\u061C\u200E\u200F\u202A-\u202E\u2066-\u2069]+/g;function L(a,c){a.lastIndex=0;return a.test(c)}
+function M(a){if("string"!==typeof a)throw new TypeError("inspectText expects a string input.");const c=[],d={hasControlChars:!1,hasInvisibleChars:!1,hasMixedNewlines:!1,newlineStyle:null,hasEmojis:!1,hasNonKeyboardChars:!1,summary:c};L(v,a)&&(d.hasControlChars=!0,c.push("Control characters detected."));L(t,a)&&(d.hasInvisibleChars=!0,c.push("Invisible Unicode characters detected."));L(u,a)&&(d.hasEmojis=!0,c.push("Emojis detected."));if("string"!==typeof a)throw new TypeError("getNewlineStats expects a string input.");
+var f=0,g=0;let l=0;for(let k=0,m=a.length;k<m;k++){const p=a.charCodeAt(k);13===p?10===a.charCodeAt(k+1)?(f++,k++):g++:10===p&&l++}f={i:f,h:g,j:l};g=[];0<f.i&&g.push("CRLF");0<f.h&&g.push("CR");0<f.j&&g.push("LF");const {l:h,types:b}={...f,types:g,l:1<g.length};d.hasMixedNewlines=h;d.newlineStyle=h?"Mixed":b[0]||null;d.newlineStyle&&c.push(h?"Mixed newline styles detected.":`Consistent newline style: ${d.newlineStyle}`);a:{a=E(a);if(L(D,a))for(e of a)if(!("\n"===e||"\r"===e||" "<=e&&"~">=e||L(u,
+e))){var e=!0;break a}e=!1}e&&(d.hasNonKeyboardChars=!0,c.push("Non-keyboard characters detected."));return d}
+function N(a,c={}){if("string"!==typeof a)throw new TypeError("inspectTextDetailed expects a string input.");c=c&&c.maxFindings;c=Infinity===c||Number.isInteger(c)&&0<=c?c:100;const d={bidi_control:0,zero_width:0,nonbreaking_space:0,bom:0,nul:0,c0_control:0,c1_control:0},f=[];let g=0,l=1,h=0;for(let e=0,k=a.length;e<k;e++){var b=a.charCodeAt(e);if(32<=b&&127>b)continue;if(10===b){l++;h=e+1;continue}if(13===b){10!==a.charCodeAt(e+1)&&(l++,h=e+1);continue}const m=128>b?0===b?"nul":32>b?9===b||10===
+b||13===b?null:"c0_control":127===b?"c0_control":null:159>=b?"c1_control":160===b?"nonbreaking_space":1564===b?"bidi_control":8192>b?null:8202>=b?"nonbreaking_space":8205>=b?"zero_width":8207>=b||8234<=b&&8238>=b?"bidi_control":8239===b?"nonbreaking_space":8288===b?"zero_width":8294<=b&&8297>=b?"bidi_control":12288===b?"nonbreaking_space":65279===b?"bom":null;null!==m&&(d[m]++,g++,f.length<c&&(b={offset:e,line:l,column:e-h+1,codePoint:b,category:m},"bom"===m&&(b.atStart=0===e),f.push(b)))}return{findings:f,
+counts:d,total:g,truncated:g>f.length}}function O(a){return{purgeInvisibleChars:a.hasInvisibleChars,purgeEmojis:a.hasEmojis,nukeControls:a.hasControlChars,keyboardOnlyFilter:a.hasNonKeyboardChars,normalizeNewlines:a.hasMixedNewlines||"CRLF"===a.newlineStyle||"CR"===a.newlineStyle}}export { n as summonSanctifier, M as inspectText, O as getRecommendedSanctifierOptions, N as inspectTextDetailed };

package/dist/types/index.d.ts

@@ -1,4 +1,5 @@
 import { inspectText } from './inspectText.js';
+import { inspectTextDetailed } from './inspectText.js';
 import { getRecommendedSanctifierOptions } from './inspectText.js';
 import { summonSanctifier } from './sanctifyText.js';
-export { inspectText, getRecommendedSanctifierOptions, summonSanctifier };
+export { inspectText, inspectTextDetailed, getRecommendedSanctifierOptions, summonSanctifier };

package/dist/types/inspectText.d.ts

@@ -3,6 +3,26 @@
  * @param {string} text @returns {UnicodeTrashReport}
  */
 export function inspectText(text: string): UnicodeTrashReport;
+/**
+ * Locates invisible and control characters, one finding per character.
+ *
+ * Categories:
+ * - `bidi_control`: U+061C, U+200E, U+200F, U+202A–U+202E, U+2066–U+2069
+ * - `zero_width`: U+200B–U+200D, U+2060
+ * - `nonbreaking_space`: non-breaking and typographic spaces U+00A0, U+2000–U+200A, U+202F, U+3000
+ * - `bom`: U+FEFF (`atStart` says whether it sits at offset 0)
+ * - `nul`: U+0000
+ * - `c0_control`: U+0001–U+001F except tab, LF and CR; and U+007F
+ * - `c1_control`: U+0080–U+009F
+ *
+ * Every occurrence is counted; only the first `maxFindings` are listed.
+ * One pass over the string, no regex, no copy.
+ *
+ * @param {string} text
+ * @param {InspectDetailedOptions} [options]
+ * @returns {DetailedTrashReport}
+ */
+export function inspectTextDetailed(text: string, options?: InspectDetailedOptions): DetailedTrashReport;
 /**
  * Counts the number of different newline types in a string.
  * @param {string} text
@@ -36,3 +56,52 @@ export type UnicodeTrashReport = {
     hasNonKeyboardChars: boolean;
     summary: string[];
 };
+export type TrashCategory = "bidi_control" | "zero_width" | "nonbreaking_space" | "bom" | "nul" | "c0_control" | "c1_control";
+/**
+ * One located character.
+ * - `offset`: 0-based UTF-16 index into the input (a JS string index).
+ * - `line`: 1-based; lines end at LF, CR, or CRLF (counted once).
+ * - `column`: 1-based, in UTF-16 code units from the start of the line.
+ * - `atStart`: present on `bom` findings only; true at offset 0, where a BOM is legitimate.
+ */
+export type TrashFinding = {
+    offset: number;
+    line: number;
+    column: number;
+    codePoint: number;
+    category: TrashCategory;
+    atStart?: boolean;
+};
+export type TrashCounts = {
+    bidi_control: number;
+    zero_width: number;
+    nonbreaking_space: number;
+    bom: number;
+    nul: number;
+    c0_control: number;
+    c1_control: number;
+};
+export type DetailedTrashReport = {
+    /**
+     * - In offset order, at most `maxFindings` long.
+     */
+    findings: TrashFinding[];
+    /**
+     * - Every occurrence per category, listed or not.
+     */
+    counts: TrashCounts;
+    /**
+     * - Sum of `counts`.
+     */
+    total: number;
+    /**
+     * - True when `total` exceeds `findings.length`.
+     */
+    truncated: boolean;
+};
+export type InspectDetailedOptions = {
+    /**
+     * - Cap on listed findings (non-negative integer or Infinity).
+     */
+    maxFindings?: number;
+};

package/dist/types/sanctifyText.d.ts

@@ -123,7 +123,7 @@ export function normalizeTypographicJank(text: string): string;
  * Targets:
  * - Non-breaking spaces (\u00A0)
  * - Zero-width spaces and miscellaneous Unicode spaces (\u2000–\u200D, \u202F, \u2060, \u3000, \uFEFF)
- * - Left-to-right/right-to-left markers and overrides (\u200E, \u200F, \u202A–\u202E)
+ * - Bidi controls: marks, embeddings/overrides and isolates (\u061C, \u200E, \u200F, \u202A–\u202E, \u2066–\u2069)
  *
  * @param {string} text
  * @returns {string}
@@ -145,7 +145,7 @@ export let EMOJI_REGEX: RegExp;
  * Control characters nuked:
  *   - ASCII control range (0x00-0x1F, 0x7F)
  *   - Unicode control range (0x80-0x9F)
- *   - RTL/LTR markers (U+200E, U+200F, U+202A–U+202E)
+ *   - Bidi controls (U+061C, U+200E, U+200F, U+202A–U+202E, U+2066–U+2069)
  *
  * @param {string} text
  * @returns {string}

package/package.json

@@ -1,69 +1,69 @@
-{
-  "name": "text-sanctifier",
-  "version": "1.0.20",
-  "type": "module",
-  "description": "A brutal text normalizer and invisible trash scrubber for modern web projects.",
-  "engines": {
-    "node": ">=18"
-  },
-  "main": "./src/index.js",
-  "module": "./src/index.js",
-  "browser": "./dist/text-sanctifier.min.js",
-  "files": [
-    "src",
-    "dist/text-sanctifier.min.js",
-    "dist/types",
-    "LICENSE",
-    "README.md",
-    "ADDITIONAL_TERMS.md",
-    "robots.txt"
-  ],
-  "exports": {
-    ".": {
-      "types": "./dist/types/index.d.ts",
-      "default": "./src/index.js"
-    },
-    "./browser": {
-      "types": "./dist/types/index.d.ts",
-      "default": "./dist/text-sanctifier.min.js"
-    }
-  },
-  "types": "./dist/types/index.d.ts",
-  "sideEffects": false,
-  "scripts": {
-    "build": "node scripts/buildc.js",
-    "build:types": "tsc -p tsconfig.types.json",
-    "test": "node tests/sanctifyText.test.js",
-    "test-min": "node tests/sanctifyText.test.min.js",
-    "ci": "npm run test && npm run build && npm run build:types && npm run test-min"
-  },
-  "keywords": [
-    "text",
-    "sanitize",
-    "normalize",
-    "invisible",
-    "scrubber",
-    "unicode",
-    "clean",
-    "sanctify"
-  ],
-  "author": "WATT3D <WATT3D@protonmail.com>",
-  "license": "SEE LICENSE IN LICENSE",
-  "repository": {
-    "type": "git",
-    "url": "git+https://github.com/iWhatty/text-sanctifier.git"
-  },
-  "bugs": {
-    "url": "https://github.com/iWhatty/text-sanctifier/issues"
-  },
-  "homepage": "https://github.com/iWhatty/text-sanctifier#readme",
-  "directories": {
-    "test": "tests"
-  },
-  "devDependencies": {
-    "esbuild": "^0.25.3",
-    "google-closure-compiler": "^20240317.0.0",
-    "terser": "^5.39.0",
-    "typescript": "^5.9.3"
-  }
-}
+{
+  "name": "text-sanctifier",
+  "version": "1.1.0",
+  "type": "module",
+  "description": "A brutal text normalizer and invisible trash scrubber for modern web projects.",
+  "engines": {
+    "node": ">=18"
+  },
+  "main": "./src/index.js",
+  "module": "./src/index.js",
+  "browser": "./dist/text-sanctifier.min.js",
+  "files": [
+    "src",
+    "dist/text-sanctifier.min.js",
+    "dist/types",
+    "LICENSE",
+    "README.md",
+    "ADDITIONAL_TERMS.md",
+    "robots.txt"
+  ],
+  "exports": {
+    ".": {
+      "types": "./dist/types/index.d.ts",
+      "default": "./src/index.js"
+    },
+    "./browser": {
+      "types": "./dist/types/index.d.ts",
+      "default": "./dist/text-sanctifier.min.js"
+    }
+  },
+  "types": "./dist/types/index.d.ts",
+  "sideEffects": false,
+  "scripts": {
+    "build": "node scripts/buildc.js",
+    "build:types": "tsc -p tsconfig.types.json",
+    "test": "node tests/sanctifyText.test.js && node tests/inspectTextDetailed.test.js",
+    "test-min": "node tests/sanctifyText.test.min.js",
+    "ci": "npm run test && npm run build && npm run build:types && npm run test-min"
+  },
+  "keywords": [
+    "text",
+    "sanitize",
+    "normalize",
+    "invisible",
+    "scrubber",
+    "unicode",
+    "clean",
+    "sanctify"
+  ],
+  "author": "WATT3D <WATT3D@protonmail.com>",
+  "license": "SEE LICENSE IN LICENSE",
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/iWhatty/text-sanctifier.git"
+  },
+  "bugs": {
+    "url": "https://github.com/iWhatty/text-sanctifier/issues"
+  },
+  "homepage": "https://github.com/iWhatty/text-sanctifier#readme",
+  "directories": {
+    "test": "tests"
+  },
+  "devDependencies": {
+    "esbuild": "^0.25.3",
+    "google-closure-compiler": "^20240317.0.0",
+    "terser": "^5.39.0",
+    "typescript": "^5.9.3"
+  }
+}

package/robots.txt

@@ -1,79 +1,79 @@
-# WATT3D — AI scraping policy
-#
-# This file enumerates known AI / LLM training and inference crawlers
-# that the WATT3D AI Training Rider does not consent to. See
-# ./ADDITIONAL_TERMS.md for the legal scope and definitions.
-#
-# Honoring robots.txt is voluntary. The rider applies whether or not
-# a bot respects this file. The enumeration is non-exhaustive — bots
-# not listed here are still bound by the rider if they perform
-# Training Use as defined in ADDITIONAL_TERMS.md §1.
-
-User-agent: GPTBot
-Disallow: /
-
-User-agent: ChatGPT-User
-Disallow: /
-
-User-agent: OAI-SearchBot
-Disallow: /
-
-User-agent: anthropic-ai
-Disallow: /
-
-User-agent: ClaudeBot
-Disallow: /
-
-User-agent: Claude-Web
-Disallow: /
-
-User-agent: Claude-SearchBot
-Disallow: /
-
-User-agent: Google-Extended
-Disallow: /
-
-User-agent: Applebot-Extended
-Disallow: /
-
-User-agent: Meta-ExternalAgent
-Disallow: /
-
-User-agent: Meta-ExternalFetcher
-Disallow: /
-
-User-agent: FacebookBot
-Disallow: /
-
-User-agent: CCBot
-Disallow: /
-
-User-agent: PerplexityBot
-Disallow: /
-
-User-agent: Perplexity-User
-Disallow: /
-
-User-agent: cohere-ai
-Disallow: /
-
-User-agent: Bytespider
-Disallow: /
-
-User-agent: Amazonbot
-Disallow: /
-
-User-agent: Omgilibot
-Disallow: /
-
-User-agent: AI2Bot
-Disallow: /
-
-User-agent: Diffbot
-Disallow: /
-
-# Everyone else: full access. Search engines and human-driven crawlers
-# remain welcome.
-
-User-agent: *
-Allow: /
+# WATT3D — AI scraping policy
+#
+# This file enumerates known AI / LLM training and inference crawlers
+# that the WATT3D AI Training Rider does not consent to. See
+# ./ADDITIONAL_TERMS.md for the legal scope and definitions.
+#
+# Honoring robots.txt is voluntary. The rider applies whether or not
+# a bot respects this file. The enumeration is non-exhaustive — bots
+# not listed here are still bound by the rider if they perform
+# Training Use as defined in ADDITIONAL_TERMS.md §1.
+
+User-agent: GPTBot
+Disallow: /
+
+User-agent: ChatGPT-User
+Disallow: /
+
+User-agent: OAI-SearchBot
+Disallow: /
+
+User-agent: anthropic-ai
+Disallow: /
+
+User-agent: ClaudeBot
+Disallow: /
+
+User-agent: Claude-Web
+Disallow: /
+
+User-agent: Claude-SearchBot
+Disallow: /
+
+User-agent: Google-Extended
+Disallow: /
+
+User-agent: Applebot-Extended
+Disallow: /
+
+User-agent: Meta-ExternalAgent
+Disallow: /
+
+User-agent: Meta-ExternalFetcher
+Disallow: /
+
+User-agent: FacebookBot
+Disallow: /
+
+User-agent: CCBot
+Disallow: /
+
+User-agent: PerplexityBot
+Disallow: /
+
+User-agent: Perplexity-User
+Disallow: /
+
+User-agent: cohere-ai
+Disallow: /
+
+User-agent: Bytespider
+Disallow: /
+
+User-agent: Amazonbot
+Disallow: /
+
+User-agent: Omgilibot
+Disallow: /
+
+User-agent: AI2Bot
+Disallow: /
+
+User-agent: Diffbot
+Disallow: /
+
+# Everyone else: full access. Search engines and human-driven crawlers
+# remain welcome.
+
+User-agent: *
+Allow: /

package/src/index.d.ts

@@ -1,4 +1,5 @@
-import { inspectText } from './inspectText.js';
-import { getRecommendedSanctifierOptions } from './inspectText.js';
-import { summonSanctifier } from './sanctifyText.js';
-export { inspectText, getRecommendedSanctifierOptions, summonSanctifier };
+import { inspectText } from './inspectText.js';
+import { inspectTextDetailed } from './inspectText.js';
+import { getRecommendedSanctifierOptions } from './inspectText.js';
+import { summonSanctifier } from './sanctifyText.js';
+export { inspectText, inspectTextDetailed, getRecommendedSanctifierOptions, summonSanctifier };

package/src/index.js

@@ -1,12 +1,12 @@
-// src/index.js
-
-
-import { inspectText, getRecommendedSanctifierOptions } from './inspectText.js';
-export { inspectText, getRecommendedSanctifierOptions };
-
-import { summonSanctifier } from './sanctifyText.js';
-export { summonSanctifier };
-
-
-// In Future: export helpers for power users
-// export { purgeInvisibleTrash, purgeEmojisCharacters, normalizeNewlines, trimSpacesAroundNewlines, collapseParagraphs, collapseExtraSpaces, purgeControlCharacters } from './sanctifyText.js';
+// src/index.js
+
+
+import { inspectText, inspectTextDetailed, getRecommendedSanctifierOptions } from './inspectText.js';
+export { inspectText, inspectTextDetailed, getRecommendedSanctifierOptions };
+
+import { summonSanctifier } from './sanctifyText.js';
+export { summonSanctifier };
+
+
+// In Future: export helpers for power users
+// export { purgeInvisibleTrash, purgeEmojisCharacters, normalizeNewlines, trimSpacesAroundNewlines, collapseParagraphs, collapseExtraSpaces, purgeControlCharacters } from './sanctifyText.js';