text-sanctifier 1.0.7 → 1.0.9

package/README.md

@@ -1,13 +1,15 @@
 # text-sanctifier
 
-![npm](https://img.shields.io/npm/v/text-sanctifier)
-![gzip size](https://img.shields.io/bundlephobia/minzip/text-sanctifier)
-![downloads](https://img.shields.io/npm/dw/text-sanctifier)
+[![npm](https://img.shields.io/npm/v/text-sanctifier)](https://www.npmjs.com/package/text-sanctifier)
+[![gzip size](https://img.shields.io/bundlephobia/minzip/text-sanctifier)](https://bundlephobia.com/package/text-sanctifier)
+[![downloads](https://img.shields.io/npm/dw/text-sanctifier)](https://www.npmjs.com/package/text-sanctifier)
+[![GitHub stars](https://img.shields.io/github/stars/iWhatty/text-sanctifier?style=social)](https://github.com/iWhatty/text-sanctifier)
+
 
 Brutal text normalizer and invisible trash scrubber for modern web projects.
 
-* Minified: 1425 bytes (1.39 KB)
-* Gzipped (GCC) : 784 bytes (0.77 KB)
+* Minified: (2.47 KB)
+* Gzipped (GCC) : (1.18 KB)
 
 ## Features
 
@@ -111,6 +113,37 @@ Removes everything except printable ASCII. Emojis are removed. Spaces are collap
 
 Keeps printable ASCII and emoji characters. Typographic normalization included.
 
+---
+
+
+### Unicode Trash Detection
+
+```javascript
+import { inspectText } from 'text-sanctifier';
+
+const report = inspectText(rawInput);
+
+/*
+{
+  hasControlChars: true,
+  hasInvisibleChars: true,
+  hasMixedNewlines: false,
+  newlineStyle: 'LF',
+  hasEmojis: true,
+  hasNonKeyboardChars: false,
+  summary: [
+    'Control characters detected.',
+    'Invisible Unicode characters detected.',
+    'Emojis detected.',
+    'Consistent newline style: LF'
+  ]
+}
+*/
+```
+
+Use this to preflight inputs and flag unwanted characters (like control codes, zero-width spaces, or mixed newline styles) before sanitization or storage.
+
+
 ---
 
 ## License

package/dist/text-sanctifier.min.js

@@ -1,4 +1,7 @@
-function e(a={}){const b=!!a.preserveParagraphs,c=!!a.collapseSpaces,d=!!a.nukeControls,g=!!a.purgeEmojis,k=!!a.keyboardOnlyFilter;return l=>f(l,b,c,d,g,k)}e.strict=a=>f(a,!1,!0,!0,!0);e.loose=a=>f(a,!0,!0);e.keyboardOnlyEmoji=a=>f(a,!1,!1,!0,!1,!0);e.keyboardOnly=a=>f(a,!1,!0,!0,!0,!0);
-function f(a,b=!1,c=!1,d=!1,g=!1,k=!1){if("string"!==typeof a)throw new TypeError("sanctifyText expects a string input.");a=a.replace(h,"");g&&(a=a.replace(m,""));d&&(a=a.replace(n,""));k&&(a=p(a,g));a=a.replace(q,"\n");d=a=a.replace(r,"$1");a=b?d.replace(t,"\n\n"):d.replace(u,"\n");c&&(a=a.replace(v," "));return a.trim()}var h=/[\u00A0\u2000-\u200D\u202F\u2060\u3000\uFEFF\u200E\u200F\u202A-\u202E]+/g,w=/[^\x20-\x7E]/gu;
+function f(a={}){const b=!!a.preserveParagraphs,c=!!a.collapseSpaces,d=!!a.nukeControls,e=!!a.purgeEmojis,h=!!a.keyboardOnlyFilter;return k=>g(k,b,c,d,e,h)}f.strict=a=>g(a,!1,!0,!0,!0);f.loose=a=>g(a,!0,!0);f.keyboardOnlyEmoji=a=>g(a,!1,!1,!0,!1,!0);f.keyboardOnly=a=>g(a,!1,!0,!0,!0,!0);
+function g(a,b=!1,c=!1,d=!1,e=!1,h=!1){if("string"!==typeof a)throw new TypeError("sanctifyText expects a string input.");a=a.replace(l,"");e&&(a=a.replace(m,""));d&&(a=a.replace(n,""));h&&(a=p(a,e));a=a.replace(q,"\n");d=a=a.replace(r,"$1");a=b?d.replace(t,"\n\n"):d.replace(u,"\n");c&&(a=a.replace(v," "));return a.trim()}var l=/[\u00A0\u2000-\u200D\u202F\u2060\u3000\uFEFF\u200E\u200F\u202A-\u202E]+/g,w=/[^\x20-\x7E]/gu;
 function p(a,b=!1){a=x(a);return b?a.replace(w,""):a.replace(/[^\x20-\x7E]+/gu,c=>c.match(m)?c:"")}var y=/[\u2018\u2019\u201A\u201B\u2032\u2035]/g,z=/[\u201C\u201D\u201E\u201F\u2033\u2036\u00AB\u00BB]/g,A=/[\u2012\u2013\u2014\u2015\u2212]/g,B=/\u2026/g,C=/[\u2022\u00B7]/g,D=/[\uFF01-\uFF5E]/g;function x(a){return a.replace(y,"'").replace(z,'"').replace(A,"-").replace(B,"...").replace(C,"*").replace(D,b=>String.fromCharCode(b.charCodeAt(0)-65248))}var m;
-try{m=RegExp("(?:\\p{Extended_Pictographic}(?:\\uFE0F|\\uFE0E)?(?:\\u200D(?:\\p{Extended_Pictographic}|\\w)+)*)","gu")}catch{m=/[\u{1F300}-\u{1FAFF}]/gu}var q=/\r\n?/g,r=/[ \t]*(\n+)[ \t]*/g,u=/\n{2,}/g,t=/\n{3,}/g,v=/ {2,}/g,n=/[\u0000-\u0008\u000B\u000C\u000E-\u001F\u007F\u0080-\u009F\u200E\u200F\u202A-\u202E]+/g;export { e as summonSanctifier };
+try{m=RegExp("(?:\\p{Extended_Pictographic}(?:\\uFE0F|\\uFE0E)?(?:\\u200D(?:\\p{Extended_Pictographic}|\\w)+)*)","gu")}catch{m=/[\u{1F300}-\u{1FAFF}]/gu}var q=/\r\n|\r|\n/g,r=/[ \t]*(\n+)[ \t]*/g,u=/\n{2,}/g,t=/\n{3,}/g,v=/ {2,}/g,n=/[\u0000-\u0008\u000B\u000C\u000E-\u001F\u007F\u0080-\u009F\u200E\u200F\u202A-\u202E]+/g;
+function E(a){if("string"!==typeof a)throw new TypeError("inspectText expects a string input.");const b=[],c={o:!1,u:!1,j:!1,g:null,s:!1,v:!1,summary:b},d=(k,F,G)=>{k&&(c[F]=!0,b.push(G))};d(n.test(a),"hasControlChars","Control characters detected.");d(l.test(a),"hasInvisibleChars","Invisible Unicode characters detected.");d(m.test(a),"hasEmojis","Emojis detected.");const {m:e,types:h}=H(a);c.j=e;c.g=e?"Mixed":h[0]||null;c.g&&b.push(e?"Mixed newline styles detected.":`Consistent newline style: ${c.g}`);
+a=x(a).replace(/[^\x20-\x7E]+/gu,k=>k.match(m)?"":"\u2612");d(/[\u2612]/.test(a),"hasNonKeyboardChars","Non-keyboard characters detected.");return c}function H(a){if("string"!==typeof a)throw new TypeError("getNewlineStats expects a string input.");var b=a.replace(/\r\n/g,"");a={i:(a.match(/\r\n/g)||[]).length,h:(b.match(/\r/g)||[]).length,l:(b.match(/\n/g)||[]).length};b=[];0<a.i&&b.push("CRLF");0<a.h&&b.push("CR");0<a.l&&b.push("LF");return{...a,types:b,m:1<b.length}}
+export { f as summonSanctifier, E as inspectText };

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "text-sanctifier",
-    "version": "1.0.7",
+    "version": "1.0.9",
     "type": "module",
     "description": "A brutal text normalizer and invisible trash scrubber for modern web projects.",
     "main": "./src/index.js",

package/src/index.js

@@ -1,6 +1,9 @@
 // src/index.js
 
 
+import { inspectText } from './inspectText.js';
+export { inspectText };
+
 import { summonSanctifier } from './sanctifyText.js';
 export { summonSanctifier };
 

package/src/inspectText.js

@@ -0,0 +1,108 @@
+
+
+
+import { CONTROL_CHARS_REGEX, INVISIBLE_TRASH_REGEX, EMOJI_REGEX, normalizeTypographicJank } from './sanctifyText.js'
+
+/**
+ * Detects textual "trash" or anomalies in a given string.
+ * @param {string} text
+ * @returns {{
+*   hasControlChars: boolean,
+*   hasInvisibleChars: boolean,
+*   hasMixedNewlines: boolean,
+*   newlineStyle: 'LF' | 'CRLF' | 'CR' | 'Mixed' | null,
+*   hasEmojis: boolean,
+*   hasNonKeyboardChars: boolean,
+*   summary: string[]
+* }}
+*/
+export function inspectText(text) {
+ if (typeof text !== 'string') {
+   throw new TypeError('inspectText expects a string input.');
+ }
+
+ const summary = [];
+ const report = {
+   hasControlChars: false,
+   hasInvisibleChars: false,
+   hasMixedNewlines: false,
+   newlineStyle: null,
+   hasEmojis: false,
+   hasNonKeyboardChars: false,
+   summary
+ };
+
+ const flag = (condition, key, message) => {
+   if (condition) {
+     report[key] = true;
+     summary.push(message);
+   }
+ };
+
+ // === Pattern Checks ===
+ flag(CONTROL_CHARS_REGEX.test(text), 'hasControlChars', 'Control characters detected.');
+ flag(INVISIBLE_TRASH_REGEX.test(text), 'hasInvisibleChars', 'Invisible Unicode characters detected.');
+ flag(EMOJI_REGEX.test(text), 'hasEmojis', 'Emojis detected.');
+
+ // === Newline Analysis ===
+ const { mixed, types } = getNewlineStats(text);
+ report.hasMixedNewlines = mixed;
+ report.newlineStyle = mixed ? 'Mixed' : types[0] || null;
+
+ if (report.newlineStyle) {
+   summary.push(
+     mixed
+       ? 'Mixed newline styles detected.'
+       : `Consistent newline style: ${report.newlineStyle}`
+   );
+ }
+
+ // === Non-keyboard characters (excluding emojis) ===
+ const filtered = normalizeTypographicJank(text).replace(/[^\x20-\x7E]+/gu, m =>
+   m.match(EMOJI_REGEX) ? '' : '☒'
+ );
+ flag(/[☒]/.test(filtered), 'hasNonKeyboardChars', 'Non-keyboard characters detected.');
+
+ return report;
+}
+
+
+/**
+ * Counts the number of different newline types in a string.
+ * @param {string} text
+ * @returns {{
+*   crlf: number,
+*   cr: number,
+*   lf: number,
+*   types: string[],
+*   mixed: boolean
+* }}
+*/
+export function getNewlineStats(text) {
+ if (typeof text !== 'string') {
+   throw new TypeError('getNewlineStats expects a string input.');
+ }
+
+ const crlfMatches = text.match(/\r\n/g) || [];
+ const textWithoutCRLF = text.replace(/\r\n/g, '');
+
+ const crMatches = textWithoutCRLF.match(/\r/g) || [];
+ const lfMatches = textWithoutCRLF.match(/\n/g) || [];
+
+ const count = {
+   crlf: crlfMatches.length,
+   cr: crMatches.length,
+   lf: lfMatches.length
+ };
+
+ const types = [];
+ if (count.crlf > 0) types.push('CRLF');
+ if (count.cr > 0) types.push('CR');
+ if (count.lf > 0) types.push('LF');
+
+ return {
+   ...count,
+   types,
+   mixed: types.length > 1
+ };
+}

package/src/sanctifyText.js

@@ -162,7 +162,7 @@ export function sanctifyText(
  * @param {string} text
  * @returns {string}
  */
-const INVISIBLE_TRASH_REGEX = /[\u00A0\u2000-\u200D\u202F\u2060\u3000\uFEFF\u200E\u200F\u202A-\u202E]+/g;
+export const INVISIBLE_TRASH_REGEX = /[\u00A0\u2000-\u200D\u202F\u2060\u3000\uFEFF\u200E\u200F\u202A-\u202E]+/g;
 function purgeInvisibleTrash(text) {
     return text.replace(INVISIBLE_TRASH_REGEX, '');
 }
@@ -207,7 +207,7 @@ const BULLETS_REGEX = /[\u2022\u00B7]/g;
 // Full-width ASCII punctuation: U+FF01 - U+FF5E
 const FULLWIDTH_PUNCTUATION_REGEX = /[\uFF01-\uFF5E]/g;
 
-function normalizeTypographicJank(text) {
+export function normalizeTypographicJank(text) {
     return text
         .replace(SMART_SINGLE_QUOTES_REGEX, "'")
         .replace(SMART_DOUBLE_QUOTES_REGEX, '"')
@@ -221,7 +221,7 @@ function normalizeTypographicJank(text) {
 
 
 
-let EMOJI_REGEX;
+export let EMOJI_REGEX;
 
 /**
  * Try Unicode property escape regex (preferred).
@@ -237,6 +237,7 @@ try {
     EMOJI_REGEX = /[\u{1F300}-\u{1FAFF}]/gu;
 }
 
+
 /**
  * Removes all emoji characters using Unicode property escapes.
  * Supports modern environments (Unicode v13+) with fallback.
@@ -250,21 +251,19 @@ function purgeEmojisCharacters(text) {
 
 
 /**
- * Normalizes all line endings to Unix-style (\n).
+ * Normalizes all line endings to a consistent format.
  * 
  * Converts:
- * - Windows line endings ("\r\n") → "\n"
- * - Old Mac line endings ("\r") → "\n"
- * 
- * Example:
- * "Line1\r\nLine2\rLine3" → "Line1\nLine2\nLine3"
+ * - Windows ("\r\n"), Old Mac ("\r"), Unix ("\n")
+ * Into the specified newline format (default: Unix "\n").
  *
- * @param {string} text
+ * @param {string} text - Input string to normalize.
+ * @param {string} [normalized='\n'] - Target newline style (e.g. '\n', '\r\n').
  * @returns {string}
  */
-const NORMALIZE_NEWLINES_REGEX = /\r\n?/g;
-function normalizeNewlines(text) {
-    return text.replace(NORMALIZE_NEWLINES_REGEX, '\n');
+const NORMALIZE_NEWLINES_REGEX = /\r\n|\r|\n/g;
+function normalizeNewlines(text, normalized = '\n') {
+    return text.replace(NORMALIZE_NEWLINES_REGEX, normalized);
 }
 
 
@@ -336,7 +335,7 @@ function collapseExtraSpaces(text) {
  * @param {string} text
  * @returns {string}
  */
-const CONTROL_CHARS_REGEX = /[\u0000-\u0008\u000B\u000C\u000E-\u001F\u007F\u0080-\u009F\u200E\u200F\u202A-\u202E]+/g;
+export const CONTROL_CHARS_REGEX = /[\u0000-\u0008\u000B\u000C\u000E-\u001F\u007F\u0080-\u009F\u200E\u200F\u202A-\u202E]+/g;
 function purgeControlCharacters(text) {
     return text.replace(CONTROL_CHARS_REGEX, '');
 }