text-sanctifier 1.3.3 → 1.3.5

package/dist/text-sanctifier.min.js

@@ -1,15 +1,6 @@
-var n=/[\u0000-\u0008\u000B\u000C\u000E-\u001F\u007F-\u009F\u061C\u200E\u200F\u202A-\u202E\u2066-\u2069]+/g,q=/[\u00A0\u00AD\u034F\u061C\u115F\u1160\u17B4\u17B5\u180B-\u180F\u2000-\u200F\u202A-\u202F\u205F-\u206F\u3000\u3164\uFE00-\uFE0F\uFEFF\uFFA0\uFFF0-\uFFF8\u{1BCA0}-\u{1BCA3}\u{1D173}-\u{1D17A}\u{E0000}-\u{E0FFF}]+/gu;
-function t(a={}){const c=!!a.purgeInvisibleChars,d=!!a.purgeEmojis,f=!!a.nukeControls,h=!!a.keyboardOnlyFilter,g=!!a.normalizeNewlines,l=!!a.trimSpacesAroundNewlines,b=!!a.collapseNewLines,e=!!a.preserveParagraphs,k=!!a.collapseSpaces,r=!!a.finalTrim,m=Number.isFinite(a.maxLength)&&0<=a.maxLength?a.maxLength:Infinity,p="truncate"===a.g||"noop"===a.g||"throw"===a.g?a.g:"throw";return A=>u(A,c,d,f,h,g,l,b,e,k,r,m,p)}t.strict=a=>u(a,!0,!0,!0,!1,!0,!0,!0,!1,!0,!0);
-t.loose=a=>u(a,!1,!1,!1,!1,!0,!0,!0,!0,!0,!0);t.keyboardOnlyEmoji=a=>u(a,!1,!1,!1,!0,!0,!0,!1,!1,!1,!0);t.keyboardOnly=a=>u(a,!0,!0,!0,!0,!0,!0,!0,!1,!0,!0);
-function u(a,c=!1,d=!1,f=!1,h=!1,g=!1,l=!1,b=!1,e=!1,k=!1,r=!1,m=Infinity,p="throw"){if("string"!==typeof a)throw new TypeError("sanctifyText expects a string input.");"truncate"!==p&&"noop"!==p&&"throw"!==p&&(p="throw");if(a.length>m)switch(p){case "truncate":a=a.slice(0,m);break;case "noop":return a;default:throw new RangeError(`sanctifyText input length ${a.length} exceeds maxLength ${m}.`);}c&&(a=a.replace(q,""));d&&(a=a.replace(v,""));f&&(a=a.replace(n,""));h&&(a=w(a,d));g&&(a=a.replace(x,"\n"));
-l&&(a=a.replace(y,"$1"));b&&(c=a,a=e?c.replace(z,"\n\n"):c.replace(B,"\n"));k&&(a=a.replace(C," "));return r?a.trim():a}var D=/[^\x20-\x7E\r\n]+/gu;function w(a,c=!1){a=E(a);return c?a.replace(D,""):a.replace(D,d=>{v.lastIndex=0;if(v.test(d)){v.lastIndex=0;var f="";for(const h of d.matchAll(v))f+=h[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 v;try{v=RegExp("(?:\\p{Extended_Pictographic}(?:\\uFE0F|\\uFE0E)?(?:\\u200D(?:\\p{Extended_Pictographic}|\\w)+)*)","gu")}catch{v=/[\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,z=/\n{3,}/g,C=/ {2,}/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(n,a)&&(d.hasControlChars=!0,c.push("Control characters detected."));L(q,a)&&(d.hasInvisibleChars=!0,c.push("Invisible Unicode characters detected."));L(v,a)&&(d.hasEmojis=!0,c.push("Emojis detected."));const {mixed:f,types:h}=N(a);d.hasMixedNewlines=f;d.newlineStyle=
-f?"Mixed":h[0]||null;d.newlineStyle&&c.push(f?"Mixed newline styles detected.":`Consistent newline style: ${d.newlineStyle}`);a:{a=E(a);if(L(D,a))for(g of a)if(!("\n"===g||"\r"===g||" "<=g&&"~">=g||L(v,g))){var g=!0;break a}g=!1}g&&(d.hasNonKeyboardChars=!0,c.push("Non-keyboard characters detected."));return d}
-function O(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,invisible_format:0,hangul_filler:0,variation_selector:0,tag:0},f=[];let h=0,g=1,l=0;for(let k=0,r=a.length;k<r;k++){var b=a.charCodeAt(k);if(32<=b&&127>b)continue;if(10===b){g++;l=k+1;continue}if(13===b){10!==a.charCodeAt(k+1)&&(g++,
-l=k+1);continue}const m=k;var e=b;if(55296<=b&&56319>=b){e=a.charCodeAt(k+1);if(!(56320<=e&&57343>=e))continue;e=65536+(b-55296<<10)+(e-56320);b=917504>e?113828>e?113824>e?null:"invisible_format":119155>e?null:119163>e?"invisible_format":null:917760>e?917632>e?"tag":"invisible_format":918E3>e?"variation_selector":921600>e?"invisible_format":null;k++}else b=8192>b?174>b?32>b?11>b?1>b?"nul":9>b?"c0_control":null:13>b?"c0_control":14>b?null:"c0_control":160>b?127>b?null:128>b?"c0_control":"c1_control":
-161>b?"nonbreaking_space":173>b?null:"invisible_format":4449>b?1564>b?847>b?null:848>b?"invisible_format":null:1565>b?"bidi_control":4447>b?null:"hangul_filler":6155>b?6068>b?null:6070>b?"invisible_format":null:6159>b?6158>b?"variation_selector":"invisible_format":6160>b?"variation_selector":null:8304>b?8240>b?8208>b?8203>b?"nonbreaking_space":8206>b?"zero_width":"bidi_control":8234>b?null:8239>b?"bidi_control":"nonbreaking_space":8289>b?8287>b?null:8288>b?"nonbreaking_space":"zero_width":8294>b?
-"invisible_format":8298>b?"bidi_control":"invisible_format":65040>b?12644>b?12288>b?null:12289>b?"nonbreaking_space":null:12645>b?"hangul_filler":65024>b?null:"variation_selector":65440>b?65279>b?null:65280>b?"bom":null:65520>b?65441>b?"hangul_filler":null:65529>b?"invisible_format":null;null!==b&&(d[b]++,h++,f.length<c&&(e={offset:m,line:g,column:m-l+1,codePoint:e,category:b},"bom"===b&&(e.atStart=0===m),f.push(e)))}return{findings:f,counts:d,total:h,truncated:h>f.length}}
-function N(a){if("string"!==typeof a)throw new TypeError("getNewlineStats expects a string input.");var c=0;let d=0,f=0;for(let h=0,g=a.length;h<g;h++){const l=a.charCodeAt(h);13===l?10===a.charCodeAt(h+1)?(c++,h++):d++:10===l&&f++}a={crlf:c,cr:d,lf:f};c=[];0<a.crlf&&c.push("CRLF");0<a.cr&&c.push("CR");0<a.lf&&c.push("LF");return{...a,types:c,mixed:1<c.length}}
-function P(a){return{purgeInvisibleChars:a.hasInvisibleChars,purgeEmojis:a.hasEmojis,nukeControls:a.hasControlChars,keyboardOnlyFilter:a.hasNonKeyboardChars,normalizeNewlines:a.hasMixedNewlines||"CRLF"===a.newlineStyle||"CR"===a.newlineStyle}}export { t as summonSanctifier, M as inspectText, P as getRecommendedSanctifierOptions, O as inspectTextDetailed, N as getNewlineStats };
+var d=/[\u0000-\u0008\u000B\u000C\u000E-\u001F\u007F-\u009F\u061C\u200E\u200F\u202A-\u202E\u2066-\u2069]+/g,C=/[\u00A0\u00AD\u034F\u061C\u115F\u1160\u17B4\u17B5\u180B-\u180F\u2000-\u200F\u202A-\u202F\u205F-\u206F\u3000\u3164\uFE00-\uFE0F\uFEFF\uFFA0\uFFF0-\uFFF8\u{1BCA0}-\u{1BCA3}\u{1D173}-\u{1D17A}\u{E0000}-\u{E0FFF}]+/gu;function I(e){return e<8192?R(e):N(e)}function R(e){return e<174?e<32?e<11?e<1?"nul":e<9?"c0_control":null:e<13?"c0_control":e<14?null:"c0_control":e<160?e<127?null:e<128?"c0_control":"c1_control":e<161?"nonbreaking_space":e<173?null:"invisible_format":e<4449?e<1564?e<847?null:e<848?"invisible_format":null:e<1565?"bidi_control":e<4447?null:"hangul_filler":e<6155?e<6068?null:e<6070?"invisible_format":null:e<6159?e<6158?"variation_selector":"invisible_format":e<6160?"variation_selector":null}function N(e){return e<8304?e<8240?e<8208?e<8203?"nonbreaking_space":e<8206?"zero_width":"bidi_control":e<8234?null:e<8239?"bidi_control":"nonbreaking_space":e<8289?e<8287?null:e<8288?"nonbreaking_space":"zero_width":e<8294?"invisible_format":e<8298?"bidi_control":"invisible_format":e<65040?e<12644?e<12288?null:e<12289?"nonbreaking_space":null:e<12645?"hangul_filler":e<65024?null:"variation_selector":e<65440?e<65279?null:e<65280?"bom":null:e<65520?e<65441?"hangul_filler":null:e<65529?"invisible_format":null}function b(e){return e<917504?e<113828?e<113824?null:"invisible_format":e<119155?null:e<119163?"invisible_format":null:e<917760?e<917632?"tag":"invisible_format":e<918e3?"variation_selector":e<921600?"invisible_format":null}function h(e={}){let r=!!e.normalizeSpaces,n=!!e.purgeZeroWidthSpaces,o=!!e.purgeInvisibleChars,u=!!e.purgeEmojis,i=!!e.nukeControls,l=!!e.keyboardOnlyFilter,c=!!e.normalizeNewlines,f=!!e.trimSpacesAroundNewlines,a=!!e.collapseNewLines,g=!!e.preserveParagraphs,s=!!e.collapseSpaces,E=!!e.finalTrim,F=Number.isFinite(e.maxLength)&&e.maxLength>=0?e.maxLength:1/0,x=e.onMaxLength==="truncate"||e.onMaxLength==="noop"||e.onMaxLength==="throw"?e.onMaxLength:"throw";return t=>_(t,o,u,i,l,c,f,a,g,s,E,F,x,r,n)}h.strict=e=>_(e,!0,!0,!0,!1,!0,!0,!0,!1,!0,!0);h.loose=e=>_(e,!1,!1,!1,!1,!0,!0,!0,!0,!0,!0);h.keyboardOnlyEmoji=e=>_(e,!1,!1,!1,!0,!0,!0,!1,!1,!1,!0);h.keyboardOnly=e=>_(e,!0,!0,!0,!0,!0,!0,!0,!1,!0,!0);h.pasted=e=>_(e,!1,!1,!1,!1,!0,!1,!1,!1,!1,!1,1/0,"throw",!0,!0);function _(e,r=!1,n=!1,o=!1,u=!1,i=!1,l=!1,c=!1,f=!1,a=!1,g=!1,s=1/0,E="throw",F=!1,x=!1){if(typeof e!="string")throw new TypeError("sanctifyText expects a string input.");if(E!=="truncate"&&E!=="noop"&&E!=="throw"&&(E="throw"),e.length>s)switch(E){case"truncate":e=e.slice(0,s);break;case"noop":return e;case"throw":default:throw new RangeError(`sanctifyText input length ${e.length} exceeds maxLength ${s}.`)}let t=e;return F&&(t=t.replace(T," ")),x&&(t=t.replace(L,"")),r&&(t=v(t)),n&&(t=z(t)),o&&(t=q(t)),u&&(t=B(t,n)),i&&(t=H(t)),l&&(t=O(t)),c&&(t=Z(t,f)),a&&(t=V(t)),g?t.trim():t}var T=/[\u00A0\u2000-\u200A\u202F\u205F]/g,L=/[\u200B\u2060\uFEFF]/g;function v(e){return e.replace(C,"")}function D(e){if(p.lastIndex=0,!p.test(e))return"";p.lastIndex=0;let r="";for(let n of e.matchAll(p))r+=n[0];return r}var S=/[^\x20-\x7E\r\n]+/gu;function B(e,r=!1){let n=A(e);return r?n.replace(S,""):n.replace(S,o=>D(o))}var G=/[\u2018\u2019\u201A\u201B\u2032\u2035]/g,X=/[\u201C\u201D\u201E\u201F\u2033\u2036\u00AB\u00BB]/g,k=/[\u2012\u2013\u2014\u2015\u2212]/g,U=/\u2026/g,M=/[\u2022\u00B7]/g,P=/[\uFF01-\uFF5E]/g;function A(e){return e.replace(G,"'").replace(X,'"').replace(k,"-").replace(U,"...").replace(M,"*").replace(P,r=>String.fromCharCode(r.charCodeAt(0)-65248))}var p;try{p=new RegExp("(?:\\p{Extended_Pictographic}(?:\\uFE0F|\\uFE0E)?(?:\\u200D(?:\\p{Extended_Pictographic}|\\w)+)*)","gu")}catch{p=/[\u{2700}-\u{27BF}\u{1F300}-\u{1FAFF}\u{1F3FB}-\u{1F3FF}\u200D\uFE0F\u{1F1E6}-\u{1F1FF}]/gu}function z(e){return e.replace(p,"")}var j=/\r\n|\r|\n/g;function H(e,r=`
+`){return e.replace(j,r)}var K=/[ \t]*(\n+)[ \t]*/g;function O(e){return e.replace(K,"$1")}var W=/\n{2,}/g,J=/\n{3,}/g;function Z(e,r){return r?e.replace(J,`
+
+`):e.replace(W,`
+`)}var $=/ {2,}/g;function V(e){return e.replace($," ")}function q(e){return e.replace(d,"")}function m(e,r){return e.lastIndex=0,e.test(r)}function Q(e){let r=A(e);if(!m(S,r))return!1;for(let n of r)if(!(n===`
+`||n==="\r"||n>=" "&&n<="~")&&!m(p,n))return!0;return!1}function Y(e){if(typeof e!="string")throw new TypeError("inspectText expects a string input.");let r=[],n={hasControlChars:!1,hasInvisibleChars:!1,hasMixedNewlines:!1,newlineStyle:null,hasEmojis:!1,hasNonKeyboardChars:!1,summary:r},o=(l,c,f)=>{l&&(n[c]=!0,r.push(f))};o(m(d,e),"hasControlChars","Control characters detected."),o(m(C,e),"hasInvisibleChars","Invisible Unicode characters detected."),o(m(p,e),"hasEmojis","Emojis detected.");let{mixed:u,types:i}=w(e);return n.hasMixedNewlines=u,n.newlineStyle=u?"Mixed":i[0]||null,n.newlineStyle&&r.push(u?"Mixed newline styles detected.":`Consistent newline style: ${n.newlineStyle}`),o(Q(e),"hasNonKeyboardChars","Non-keyboard characters detected."),n}var ee=100;function y(e,r={}){if(typeof e!="string")throw new TypeError("inspectTextDetailed expects a string input.");let n=r&&r.maxFindings,o=n===1/0||Number.isInteger(n)&&n>=0?n:ee,u={bidi_control:0,zero_width:0,nonbreaking_space:0,bom:0,nul:0,c0_control:0,c1_control:0,invisible_format:0,hangul_filler:0,variation_selector:0,tag:0},i=[],l=0,c=1,f=0;for(let a=0,g=e.length;a<g;a++){let s=e.charCodeAt(a);if(s>=32&&s<127)continue;if(s===10){c++,f=a+1;continue}if(s===13){e.charCodeAt(a+1)!==10&&(c++,f=a+1);continue}let E=a,F=s,x;if(s>=55296&&s<=56319){let t=e.charCodeAt(a+1);if(!(t>=56320&&t<=57343))continue;F=65536+(s-55296<<10)+(t-56320),x=b(F),a++}else x=I(s);if(x!==null&&(u[x]++,l++,i.length<o)){let t={offset:E,line:c,column:E-f+1,codePoint:F,category:x};x==="bom"&&(t.atStart=E===0),i.push(t)}}return{findings:i,counts:u,total:l,truncated:l>i.length}}function w(e){if(typeof e!="string")throw new TypeError("getNewlineStats expects a string input.");let r=0,n=0,o=0;for(let l=0,c=e.length;l<c;l++){let f=e.charCodeAt(l);f===13?e.charCodeAt(l+1)===10?(r++,l++):n++:f===10&&o++}let u={crlf:r,cr:n,lf:o},i=[];return u.crlf>0&&i.push("CRLF"),u.cr>0&&i.push("CR"),u.lf>0&&i.push("LF"),{...u,types:i,mixed:i.length>1}}function re(e){return{purgeInvisibleChars:e.hasInvisibleChars,purgeEmojis:e.hasEmojis,nukeControls:e.hasControlChars,keyboardOnlyFilter:e.hasNonKeyboardChars,normalizeNewlines:e.hasMixedNewlines||e.newlineStyle==="CRLF"||e.newlineStyle==="CR"}}function ne(e,r={}){if(typeof e!="string")throw new TypeError("revealInvisible expects a string input.");let n=r&&typeof r.format=="function"?r.format:i=>"<U+"+i.toString(16).toUpperCase().padStart(4,"0")+">",o="",u=0;for(let i of y(e,{maxFindings:1/0}).findings)o+=e.slice(u,i.offset)+n(i.codePoint,i.category),u=i.offset+(i.codePoint>65535?2:1);return o+e.slice(u)}export{w as getNewlineStats,re as getRecommendedSanctifierOptions,Y as inspectText,y as inspectTextDetailed,ne as revealInvisible,h as summonSanctifier};

package/dist/types/index.d.ts

@@ -6,9 +6,11 @@ export type DetailedTrashReport = import("./inspectText.js").DetailedTrashReport
 export type InspectDetailedOptions = import("./inspectText.js").InspectDetailedOptions;
 export type NewlineStats = import("./inspectText.js").NewlineStats;
 export type SanctifyOptions = import("./sanctifyText.js").SanctifyOptions;
+export type RevealOptions = import("./reveal.js").RevealOptions;
 import { inspectText } from './inspectText.js';
 import { inspectTextDetailed } from './inspectText.js';
 import { getNewlineStats } from './inspectText.js';
 import { getRecommendedSanctifierOptions } from './inspectText.js';
 import { summonSanctifier } from './sanctifyText.js';
-export { inspectText, inspectTextDetailed, getNewlineStats, getRecommendedSanctifierOptions, summonSanctifier };
+import { revealInvisible } from './reveal.js';
+export { inspectText, inspectTextDetailed, getNewlineStats, getRecommendedSanctifierOptions, summonSanctifier, revealInvisible };

package/dist/types/reveal.d.ts

@@ -0,0 +1,26 @@
+/** @typedef {import('./inspectText.js').TrashCategory} TrashCategory */
+/**
+ * @typedef {Object} RevealOptions
+ * @property {(codePoint: number, category: TrashCategory) => string} [format] - Text shown in place of
+ *   each hidden character. Default: `<U+XXXX>` (at least four uppercase hex digits).
+ */
+/**
+ * Makes hidden characters visible: every character `inspectTextDetailed` would report is
+ * replaced by a marker such as `<U+200B>`, and everything else is kept as it is,
+ * including tabs, newlines and emoji. Use it to show hidden text in logs, diffs, review
+ * tools and agent tool output. A literal `<U+200B>` already in the text looks the same as
+ * a marker; pass `format` to choose markers that can't occur in your input.
+ *
+ * @param {string} text
+ * @param {RevealOptions} [options]
+ * @returns {string}
+ */
+export function revealInvisible(text: string, options?: RevealOptions): string;
+export type TrashCategory = import("./inspectText.js").TrashCategory;
+export type RevealOptions = {
+    /**
+     * - Text shown in place of
+     * each hidden character. Default: `<U+XXXX>` (at least four uppercase hex digits).
+     */
+    format?: (codePoint: number, category: TrashCategory) => string;
+};

package/dist/types/sanctifyText.d.ts

@@ -12,6 +12,8 @@
  * @property {boolean} [finalTrim]
  * @property {number} [maxLength]
  * @property {'throw'|'truncate'|'noop'} [onMaxLength]
+ * @property {boolean} [normalizeSpaces] - Replace look-alike spaces with an ordinary space (runs first).
+ * @property {boolean} [purgeZeroWidthSpaces] - Remove U+200B, U+2060 and U+FEFF only, keeping joiners and selectors.
  */
 /**
  * Summons a customized sanctifier function with pre-bound booleans.
@@ -31,6 +33,8 @@
  * @param {boolean} [defaultOptions.finalTrim]
  * @param {number} [defaultOptions.maxLength=Infinity] - Hard input length cap (UTF-16 code units).
  * @param {'throw' | 'truncate' | 'noop'} [defaultOptions.onMaxLength='throw'] - Behavior when input exceeds maxLength.
+ * @param {boolean} [defaultOptions.normalizeSpaces]
+ * @param {boolean} [defaultOptions.purgeZeroWidthSpaces]
  * @returns {(text: string) => string}
  */
 export function summonSanctifier(defaultOptions?: {
@@ -46,6 +50,8 @@ export function summonSanctifier(defaultOptions?: {
     finalTrim?: boolean;
     maxLength?: number;
     onMaxLength?: "throw" | "truncate" | "noop";
+    normalizeSpaces?: boolean;
+    purgeZeroWidthSpaces?: boolean;
 }): (text: string) => string;
 export namespace summonSanctifier {
     /**
@@ -81,6 +87,16 @@ export namespace summonSanctifier {
      */
     /** @param {string} text @returns {string} */
     function keyboardOnly(text: string): string;
+    /**
+     * Pasted text and model output:
+     * - Look-alike spaces (NBSP, narrow NBSP, typographic spaces) become ordinary spaces,
+     *   so words never run together
+     * - Zero-width spaces, word joiners and BOMs are removed
+     * - Newlines are normalized to `\n`
+     * Keeps emoji joiners, variation selectors, bidi marks, indentation and line breaks.
+     */
+    /** @param {string} text @returns {string} */
+    function pasted(text: string): string;
 }
 /**
  * Text Sanctifier
@@ -106,17 +122,27 @@ export namespace summonSanctifier {
  *   - `'throw'`: throw a `RangeError`
  *   - `'truncate'`: slice to `maxLength` before processing
  *   - `'noop'`: return the original input unchanged (skips processing)
+ * @param {boolean} [normalizeSpaces=false] - Replace look-alike spaces with an ordinary space. Runs first,
+ *   so `purgeInvisibleChars` no longer joins the words around them.
+ * @param {boolean} [purgeZeroWidthSpaces=false] - Remove zero-width spaces, word joiners and BOMs only.
  * @returns {string}
  * @throws {TypeError} If `text` is not a string.
  * @throws {RangeError} If input exceeds `maxLength` and `onMaxLength` is `'throw'`.
  */
-export function sanctifyText(text: string, purgeInvisibleChars?: boolean, purgeEmojis?: boolean, nukeControls?: boolean, keyboardOnlyFilter?: boolean, normalizeNewlines?: boolean, trimSpacesAroundNewlines?: boolean, collapseNewLines?: boolean, preserveParagraphs?: boolean, collapseSpaces?: boolean, finalTrim?: boolean, maxLength?: number, onMaxLength?: "throw" | "truncate" | "noop"): string;
+export function sanctifyText(text: string, purgeInvisibleChars?: boolean, purgeEmojis?: boolean, nukeControls?: boolean, keyboardOnlyFilter?: boolean, normalizeNewlines?: boolean, trimSpacesAroundNewlines?: boolean, collapseNewLines?: boolean, preserveParagraphs?: boolean, collapseSpaces?: boolean, finalTrim?: boolean, maxLength?: number, onMaxLength?: "throw" | "truncate" | "noop", normalizeSpaces?: boolean, purgeZeroWidthSpaces?: boolean): string;
 /**
  * Normalizes typographic Unicode punctuation into ASCII equivalents.
  * @param {string} text
  * @returns {string}
  */
 export function normalizeTypographicJank(text: string): string;
+/**
+ * Look-alike spaces: the `nonbreaking_space` category except U+3000, the ordinary
+ * space of CJK text. A test checks this against the category table.
+ */
+export const SPACE_LOOKALIKES_REGEX: RegExp;
+/** Zero-width space, word joiner and BOM: invisible and never needed in plain text. */
+export const ZERO_WIDTH_SPACES_REGEX: RegExp;
 /**
  * Matches any character that is NOT:
  * - Printable ASCII (U+0020–U+007E)
@@ -139,6 +165,14 @@ export type SanctifyOptions = {
     finalTrim?: boolean;
     maxLength?: number;
     onMaxLength?: "throw" | "truncate" | "noop";
+    /**
+     * - Replace look-alike spaces with an ordinary space (runs first).
+     */
+    normalizeSpaces?: boolean;
+    /**
+     * - Remove U+200B, U+2060 and U+FEFF only, keeping joiners and selectors.
+     */
+    purgeZeroWidthSpaces?: boolean;
 };
 import { CONTROL_CHARS_REGEX } from './categories.generated.js';
 import { INVISIBLE_TRASH_REGEX } from './categories.generated.js';

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "text-sanctifier",
-  "version": "1.3.3",
+  "version": "1.3.5",
   "type": "module",
   "description": "A brutal text normalizer and invisible trash scrubber for modern web projects.",
   "engines": {
@@ -41,12 +41,13 @@
   "scripts": {
     "gen": "node scripts/gen-categories.js",
     "gen:check": "node scripts/gen-categories.js --check",
-    "build": "node scripts/buildc.js",
+    "build": "node scripts/build.js",
     "build:types": "tsc -p tsconfig.types.json",
     "test:types": "tsc -p tests/types/tsconfig.json",
     "test": "node tests/sanctifyText.test.js && node tests/inspectTextDetailed.test.js && node tests/cli.test.js",
     "test-min": "node tests/sanctifyText.test.min.js",
-    "ci": "npm run gen:check && npm run test && npm run build && npm run build:types && npm run test:types && npm run test-min"
+    "ci": "npm run gen:check && npm run test && npm run build && npm run size && npm run build:types && npm run test:types && npm run test-min",
+    "size": "node scripts/check-size.js"
   },
   "keywords": [
     "text",
@@ -73,8 +74,6 @@
   },
   "devDependencies": {
     "esbuild": "^0.25.3",
-    "google-closure-compiler": "^20240317.0.0",
-    "terser": "^5.39.0",
     "typescript": "^5.9.3"
   }
 }