text-sanctifier 1.0.14 → 1.0.16

package/README.md

@@ -7,8 +7,8 @@
 
 Brutal text normalizer and invisible trash scrubber for modern web projects.
 
-* Minified: (2.69 KB)
-* Gzipped (GCC): (1.27 KB)
+* Minified: (3.09 KB)
+* Gzipped (GCC): (1.36 KB)
 
 ## Features
 
@@ -109,6 +109,8 @@ 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().
+
 ---
 
 ## API

package/dist/text-sanctifier.min.js

@@ -1,7 +1,8 @@
 function g(a={}){const b=!!a.purgeInvisibleChars,c=!!a.purgeEmojis,d=!!a.nukeControls,e=!!a.keyboardOnlyFilter,k=!!a.normalizeNewlines,f=!!a.trimSpacesAroundNewlines,l=!!a.collapseNewLines,m=!!a.preserveParagraphs,p=!!a.collapseSpaces,q=!!a.finalTrim;return w=>h(w,b,c,d,e,k,f,l,m,p,q)}g.strict=a=>h(a,!0,!0,!0,!1,!0,!0,!0,!1,!0,!0);g.loose=a=>h(a,!1,!1,!1,!1,!0,!0,!0,!0,!0,!0);g.keyboardOnlyEmoji=a=>h(a,!1,!1,!1,!0,!0,!0,!1,!1,!1,!0);g.keyboardOnly=a=>h(a,!0,!0,!0,!0,!0,!0,!0,!1,!0,!0);
 function h(a,b=!1,c=!1,d=!1,e=!1,k=!1,f=!1,l=!1,m=!1,p=!1,q=!1){if("string"!==typeof a)throw new TypeError("sanctifyText expects a string input.");b&&(a=a.replace(n,""));c&&(a=a.replace(r,""));d&&(a=a.replace(t,""));e&&(a=u(a,c));k&&(a=a.replace(v,"\n"));f&&(a=a.replace(x,"$1"));l&&(b=a,a=m?b.replace(y,"\n\n"):b.replace(z,"\n"));p&&(a=a.replace(A," "));return q?a.trim():a}var n=/[\u00A0\u2000-\u200D\u202F\u2060\u3000\uFEFF\u200E\u200F\u202A-\u202E]+/g,B=/[^\x20-\x7E\r\n]+/gu;
 function u(a,b=!1){a=C(a);return b?a.replace(B,""):a.replace(B,c=>c.match(r)?c:"")}var D=/[\u2018\u2019\u201A\u201B\u2032\u2035]/g,E=/[\u201C\u201D\u201E\u201F\u2033\u2036\u00AB\u00BB]/g,F=/[\u2012\u2013\u2014\u2015\u2212]/g,G=/\u2026/g,H=/[\u2022\u00B7]/g,I=/[\uFF01-\uFF5E]/g;function C(a){return a.replace(D,"'").replace(E,'"').replace(F,"-").replace(G,"...").replace(H,"*").replace(I,b=>String.fromCharCode(b.charCodeAt(0)-65248))}var r;
-try{r=RegExp("(?:\\p{Extended_Pictographic}(?:\\uFE0F|\\uFE0E)?(?:\\u200D(?:\\p{Extended_Pictographic}|\\w)+)*)","gu")}catch{r=/[\u{1F300}-\u{1FAFF}]/gu}var v=/\r\n|\r|\n/g,x=/[ \t]*(\n+)[ \t]*/g,z=/\n{2,}/g,y=/\n{3,}/g,A=/ {2,}/g,t=/[\u0000-\u0008\u000B\u000C\u000E-\u001F\u007F\u0080-\u009F\u200E\u200F\u202A-\u202E]+/g;
-function J(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=(f,l,m)=>{f&&(c[l]=!0,b.push(m))};d(t.test(a),"hasControlChars","Control characters detected.");d(n.test(a),"hasInvisibleChars","Invisible Unicode characters detected.");d(r.test(a),"hasEmojis","Emojis detected.");const {m:e,types:k}=K(a);c.j=e;c.g=e?"Mixed":k[0]||null;c.g&&b.push(e?"Mixed newline styles detected.":`Consistent newline style: ${c.g}`);
-a=C(a).replace(B,f=>f.match(r)?"":"\u2612");d(/[\u2612]/.test(a),"hasNonKeyboardChars","Non-keyboard characters detected.");return c}function K(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 { g as summonSanctifier, J as inspectText };
+try{r=RegExp("(?:\\p{Extended_Pictographic}(?:\\uFE0F|\\uFE0E)?(?:\\u200D(?:\\p{Extended_Pictographic}|\\w)+)*)","gu")}catch{r=/[\u{2700}-\u{27BF}\u{1F300}-\u{1FAFF}\u{1F3FB}-\u{1F3FF}\u200D\uFE0F\u{1F1E6}-\u{1F1FF}]/gu}var v=/\r\n|\r|\n/g,x=/[ \t]*(\n+)[ \t]*/g,z=/\n{2,}/g,y=/\n{3,}/g,A=/ {2,}/g,t=/[\u0000-\u0008\u000B\u000C\u000E-\u001F\u007F\u0080-\u009F\u200E\u200F\u202A-\u202E]+/g;
+function J(a){if("string"!==typeof a)throw new TypeError("inspectText expects a string input.");const b=[],c={hasControlChars:!1,hasInvisibleChars:!1,hasMixedNewlines:!1,newlineStyle:null,hasEmojis:!1,hasNonKeyboardChars:!1,summary:b},d=(f,l,m)=>{f&&(c[l]=!0,b.push(m))};d(t.test(a),"hasControlChars","Control characters detected.");d(n.test(a),"hasInvisibleChars","Invisible Unicode characters detected.");d(r.test(a),"hasEmojis","Emojis detected.");const {j:e,types:k}=K(a);c.hasMixedNewlines=e;c.newlineStyle=
+e?"Mixed":k[0]||null;c.newlineStyle&&b.push(e?"Mixed newline styles detected.":`Consistent newline style: ${c.newlineStyle}`);a=C(a).replace(B,f=>f.match(r)?"":"\u2612");d(/[\u2612]/.test(a),"hasNonKeyboardChars","Non-keyboard characters detected.");return c}
+function K(a){if("string"!==typeof a)throw new TypeError("getNewlineStats expects a string input.");var b=a.replace(/\r\n/g,"");a={h:(a.match(/\r\n/g)||[]).length,g:(b.match(/\r/g)||[]).length,i:(b.match(/\n/g)||[]).length};b=[];0<a.h&&b.push("CRLF");0<a.g&&b.push("CR");0<a.i&&b.push("LF");return{...a,types:b,j:1<b.length}}
+function L(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, J as inspectText, L as getRecommendedSanctifierOptions };

package/package.json

@@ -1,6 +1,6 @@
 {
     "name": "text-sanctifier",
-    "version": "1.0.14",
+    "version": "1.0.16",
     "type": "module",
     "description": "A brutal text normalizer and invisible trash scrubber for modern web projects.",
     "main": "./src/index.js",

package/src/index.d.ts

@@ -104,3 +104,13 @@ export interface UnicodeTrashReport {
  * invisible characters, newline styles, emojis, and more.
  */
 export function inspectText(text: string): UnicodeTrashReport;
+
+
+/**
+ * Creates a recommended set of `summonSanctifier` options based on the findings
+ * of `inspectText()`. This maps only what can be inferred automatically —
+ * user-preference settings like whitespace collapsing are left unset.
+ */
+export function getRecommendedSanctifierOptions(
+  report: UnicodeTrashReport
+): SanctifyOptions;

package/src/index.js

@@ -1,8 +1,8 @@
 // src/index.js
 
 
-import { inspectText } from './inspectText.js';
-export { inspectText };
+import { inspectText, getRecommendedSanctifierOptions } from './inspectText.js';
+export { inspectText, getRecommendedSanctifierOptions };
 
 import { summonSanctifier } from './sanctifyText.js';
 export { summonSanctifier };

package/src/inspectText.js

@@ -1,4 +1,5 @@
 
+// ./src/inspectText.js
 
 
 import {
@@ -7,9 +8,10 @@ import {
     EMOJI_REGEX,
     ASCII_KEYBOARD_SAFE_REGEX,
     normalizeTypographicJank
-  } from './sanctifyText.js';
+} from './sanctifyText.js';
+
+
 
-  
 /**
  * Detects textual "trash" or anomalies in a given string.
  * @param {string} text
@@ -24,53 +26,53 @@ import {
 * }}
 */
 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(ASCII_KEYBOARD_SAFE_REGEX, m =>
-    m.match(EMOJI_REGEX) ? '' : '☒'
-  );
- flag(/[☒]/.test(filtered), 'hasNonKeyboardChars', 'Non-keyboard characters detected.');
-
- return report;
+    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(ASCII_KEYBOARD_SAFE_REGEX, m =>
+        m.match(EMOJI_REGEX) ? '' : '☒'
+    );
+    flag(/[☒]/.test(filtered), 'hasNonKeyboardChars', 'Non-keyboard characters detected.');
+
+    return report;
 }
 
 
@@ -86,30 +88,52 @@ export function inspectText(text) {
 * }}
 */
 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
- };
+    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
+    };
+}
+
+
+
+/**
+ * Creates defaultOptions for summonSanctifier based on inspectText result
+ * @param {!UnicodeTrashReport} report
+ * @return {!SanctifyOptions}
+ */
+export function getRecommendedSanctifierOptions(report) {
+    return {
+        purgeInvisibleChars: report.hasInvisibleChars,
+        purgeEmojis: report.hasEmojis,
+        nukeControls: report.hasControlChars,
+        keyboardOnlyFilter: report.hasNonKeyboardChars,
+        normalizeNewlines: report.hasMixedNewlines || report.newlineStyle === 'CRLF' || report.newlineStyle === 'CR',
+        // trimSpacesAroundNewlines: true,
+        // collapseNewLines: false,
+        // preserveParagraphs: true,
+        // collapseSpaces: true,
+        // finalTrim: true,
+    };
 }

package/src/sanctifyText.js

@@ -190,7 +190,7 @@ export function sanctifyText(
     if (purgeInvisibleChars) cleaned = purgeInvisibleTrash(cleaned);
 
     // Remove emojis
-    if (purgeEmojis) cleaned = purgeEmojisCharacters(cleaned);
+    if (purgeEmojis) cleaned = purgeEmojiCharacters(cleaned);
 
     // Nuke control characters (excluding whitespace)
     if (nukeControls) cleaned = purgeControlCharacters(cleaned);
@@ -297,7 +297,7 @@ export let EMOJI_REGEX;
 
 /**
  * Try Unicode property escape regex (preferred).
- * Fallback to basic emoji range if unsupported.
+ * Fallback to basic emoji ranges if unsupported.
  */
 try {
     EMOJI_REGEX = new RegExp(
@@ -305,11 +305,16 @@ try {
         'gu'
     );
 } catch {
-    // Fallback: less precise but safe
-    EMOJI_REGEX = /[\u{1F300}-\u{1FAFF}]/gu;
+    // Fallback: wide-range emoji component match (flags, tones, symbols)
+    //   * Covers:
+    //   * - Emoji base chars (1F300–1FAFF)
+    //   * - Dingbats (2700–27BF) like ❌, ✅, ☑️
+    //   * - Skin tones (1F3FB–1F3FF)
+    //   * - ZWJ (200D), variation selectors (FE0F)
+    //   * - Regional indicators (1F1E6–1F1FF)
+    EMOJI_REGEX = /[\u{2700}-\u{27BF}\u{1F300}-\u{1FAFF}\u{1F3FB}-\u{1F3FF}\u200D\uFE0F\u{1F1E6}-\u{1F1FF}]/gu;
 }
 
-
 /**
  * Removes all emoji characters using Unicode property escapes.
  * Supports modern environments (Unicode v13+) with fallback.
@@ -317,7 +322,7 @@ try {
  * @param {string} text
  * @returns {string}
  */
-function purgeEmojisCharacters(text) {
+function purgeEmojiCharacters(text) {
     return text.replace(EMOJI_REGEX, '');
 }