text-sanctifier 1.3.0 → 1.3.1

package/README.md

@@ -7,7 +7,7 @@
 [![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. ~2.40 KB gzipped.
+Brutal text normalizer and invisible Unicode scrubber for modern web projects. ~2.44 KB gzipped.
 
 ## Features
 
@@ -167,7 +167,7 @@ truncated: false
 | --- | --- |
 | `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) |
+| `nonbreaking_space` | U+00A0, U+2000–U+200A, U+202F, U+205F, 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 |
@@ -179,6 +179,18 @@ truncated: false
 
 `codePoint` is the full code point, so a tag character reports `0xE0041`, not a surrogate. `offset` is a 0-based UTF-16 index (for a code point above U+FFFF, that of its high surrogate); `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.
 
+**Choosing `maxFindings`:** the scan itself uses almost no memory, but every listed finding is an object, so the cost of `maxFindings` grows with the number of findings, not the size of the input. 16 MB of non-breaking spaces is 16.7 million findings. With a cap of 20, it scans in about 70 ms and uses 0.2 MB. With `Infinity`, expect roughly 100–200 bytes per finding: about 1.5 GB for 8 million. On untrusted input, keep a cap. Use `maxFindings: 0` for a counts-only report: it builds no finding objects, and `counts`, `total` and `truncated` stay exact.
+
+### `getNewlineStats(text: string): NewlineStats`
+
+Counts each newline style in one pass, with no regex and no copy: `{ crlf, cr, lf, types, mixed }`. `cr` counts CRs not followed by LF, `lf` counts LFs not preceded by CR, `types` lists the styles present in the order `'CRLF'`, `'CR'`, `'LF'`, and `mixed` is true when there is more than one. Also exported from the browser build.
+
+```js
+import { getNewlineStats } from 'text-sanctifier';
+
+getNewlineStats('a\r\nb\n'); // { crlf: 1, cr: 0, lf: 1, types: ['CRLF', 'LF'], mixed: true }
+```
+
 `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 same holds for `variation_selector`, which flags VS16 (U+FE0F) in emoji such as ✌️ and the ideographic variation selectors in CJK names, and for `tag`, which flags the tag characters inside subdivision flags such as the England flag (U+1F3F4 followed by tags). `purgeInvisibleChars` strips them all; `keyboardOnlyEmoji` keeps VS16.
 
 The categories cover exactly what `nukeControls` and `purgeInvisibleChars` strip.

package/dist/text-sanctifier.min.js

@@ -1,14 +1,14 @@
-function n(a={}){const c=!!a.purgeInvisibleChars,e=!!a.purgeEmojis,f=!!a.nukeControls,h=!!a.keyboardOnlyFilter,m=!!a.normalizeNewlines,l=!!a.trimSpacesAroundNewlines,b=!!a.collapseNewLines,d=!!a.preserveParagraphs,g=!!a.collapseSpaces,p=!!a.finalTrim,k=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,e,f,h,m,l,b,d,g,p,k,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,e=!1,f=!1,h=!1,m=!1,l=!1,b=!1,d=!1,g=!1,p=!1,k=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>k)switch(q){case "truncate":a=a.slice(0,k);break;case "noop":return a;default:throw new RangeError(`sanctifyText input length ${a.length} exceeds maxLength ${k}.`);}c&&(a=a.replace(t,""));e&&(a=a.replace(u,""));f&&(a=a.replace(v,""));h&&(a=w(a,e));m&&(a=a.replace(x,"\n"));
-l&&(a=a.replace(y,"$1"));b&&(c=a,a=d?c.replace(A,"\n\n"):c.replace(B,"\n"));g&&(a=a.replace(C," "));return p?a.trim():a}var t=/[\u00a0\u00ad\u034f\u061c\u115f\u1160\u180e\u2000-\u200f\u202a-\u202f\u2060-\u2064\u2066-\u2069\u3000\u3164\ufe00-\ufe0f\ufeff\uffa0\u{E0000}-\u{E007F}\u{E0100}-\u{E01EF}]+/gu,D=/[^\x20-\x7E\r\n]+/gu;
-function w(a,c=!1){a=E(a);return c?a.replace(D,""):a.replace(D,e=>{u.lastIndex=0;if(u.test(e)){u.lastIndex=0;var f="";for(const h of e.matchAll(u))f+=h[0];e=f}else e="";return e})}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 n(a={}){const c=!!a.purgeInvisibleChars,d=!!a.purgeEmojis,e=!!a.nukeControls,g=!!a.keyboardOnlyFilter,f=!!a.normalizeNewlines,l=!!a.trimSpacesAroundNewlines,b=!!a.collapseNewLines,h=!!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=>q(A,c,d,e,g,f,l,b,h,k,r,m,p)}n.strict=a=>q(a,!0,!0,!0,!1,!0,!0,!0,!1,!0,!0);
+n.loose=a=>q(a,!1,!1,!1,!1,!0,!0,!0,!0,!0,!0);n.keyboardOnlyEmoji=a=>q(a,!1,!1,!1,!0,!0,!0,!1,!1,!1,!0);n.keyboardOnly=a=>q(a,!0,!0,!0,!0,!0,!0,!0,!1,!0,!0);
+function q(a,c=!1,d=!1,e=!1,g=!1,f=!1,l=!1,b=!1,h=!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(t,""));d&&(a=a.replace(u,""));e&&(a=a.replace(v,""));g&&(a=w(a,d));f&&(a=a.replace(x,"\n"));
+l&&(a=a.replace(y,"$1"));b&&(c=a,a=h?c.replace(z,"\n\n"):c.replace(B,"\n"));k&&(a=a.replace(C," "));return r?a.trim():a}var t=/[\u00a0\u00ad\u034f\u061c\u115f\u1160\u180e\u2000-\u200f\u202a-\u202f\u205f\u2060-\u2064\u2066-\u2069\u3000\u3164\ufe00-\ufe0f\ufeff\uffa0\u{E0000}-\u{E007F}\u{E0100}-\u{E01EF}]+/gu,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 e="";for(const g of d.matchAll(u))e+=g[0];d=e}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,z=/\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=[],e={hasControlChars:!1,hasInvisibleChars:!1,hasMixedNewlines:!1,newlineStyle:null,hasEmojis:!1,hasNonKeyboardChars:!1,summary:c};L(v,a)&&(e.hasControlChars=!0,c.push("Control characters detected."));L(t,a)&&(e.hasInvisibleChars=!0,c.push("Invisible Unicode characters detected."));L(u,a)&&(e.hasEmojis=!0,c.push("Emojis detected."));if("string"!==typeof a)throw new TypeError("getNewlineStats expects a string input.");var f=
-0,h=0;let m=0;for(let g=0,p=a.length;g<p;g++){const k=a.charCodeAt(g);13===k?10===a.charCodeAt(g+1)?(f++,g++):h++:10===k&&m++}f={i:f,h,j:m};h=[];0<f.i&&h.push("CRLF");0<f.h&&h.push("CR");0<f.j&&h.push("LF");const {l,types:b}={...f,types:h,l:1<h.length};e.hasMixedNewlines=l;e.newlineStyle=l?"Mixed":b[0]||null;e.newlineStyle&&c.push(l?"Mixed newline styles detected.":`Consistent newline style: ${e.newlineStyle}`);a:{a=E(a);if(L(D,a))for(d of a)if(!("\n"===d||"\r"===d||" "<=d&&"~">=d||L(u,d))){var d=
-!0;break a}d=!1}d&&(e.hasNonKeyboardChars=!0,c.push("Non-keyboard characters detected."));return e}
-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 e={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,m=1,l=0;for(let g=0,p=a.length;g<p;g++){var b=a.charCodeAt(g);if(32<=b&&127>b)continue;if(10===b){m++;l=g+1;continue}if(13===b){10!==a.charCodeAt(g+1)&&(m++,
-l=g+1);continue}const k=g;var d=b;if(56128===b){d=a.charCodeAt(g+1);if(!(56320<=d&&57343>=d))continue;d=65536+(b-55296<<10)+(d-56320);b=917504<=d&&917631>=d?"tag":917760<=d&&917999>=d?"variation_selector":null;g++}else b=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":173===b||847===b||6158===b?"invisible_format":1564===b?"bidi_control":4447===b||4448===b?"hangul_filler":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":8289<=b&&8292>=b?"invisible_format":8294<=b&&8297>=b?"bidi_control":12288===b?"nonbreaking_space":12644===b||65440===b?"hangul_filler":65024<=b&&65039>=b?"variation_selector":65279===b?"bom":null;null!==b&&(e[b]++,h++,f.length<c&&(d={offset:k,line:m,column:k-l+1,codePoint:d,category:b},"bom"===b&&(d.atStart=0===k),f.push(d)))}return{findings:f,counts:e,total:h,truncated:h>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 };
+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."));const {mixed:e,types:g}=N(a);d.hasMixedNewlines=e;d.newlineStyle=
+e?"Mixed":g[0]||null;d.newlineStyle&&c.push(e?"Mixed newline styles detected.":`Consistent newline style: ${d.newlineStyle}`);a:{a=E(a);if(L(D,a))for(f of a)if(!("\n"===f||"\r"===f||" "<=f&&"~">=f||L(u,f))){var f=!0;break a}f=!1}f&&(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},e=[];let g=0,f=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){f++;l=k+1;continue}if(13===b){10!==a.charCodeAt(k+1)&&(f++,
+l=k+1);continue}const m=k;var h=b;if(56128===b){h=a.charCodeAt(k+1);if(!(56320<=h&&57343>=h))continue;h=65536+(b-55296<<10)+(h-56320);b=917504<=h&&917631>=h?"tag":917760<=h&&917999>=h?"variation_selector":null;k++}else b=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":173===b||847===b||6158===b?"invisible_format":1564===b?"bidi_control":4447===b||4448===b?"hangul_filler":8192>b?null:8202>=b?"nonbreaking_space":
+8205>=b?"zero_width":8207>=b||8234<=b&&8238>=b?"bidi_control":8239===b||8287===b?"nonbreaking_space":8288===b?"zero_width":8289<=b&&8292>=b?"invisible_format":8294<=b&&8297>=b?"bidi_control":12288===b?"nonbreaking_space":12644===b||65440===b?"hangul_filler":65024<=b&&65039>=b?"variation_selector":65279===b?"bom":null;null!==b&&(d[b]++,g++,e.length<c&&(h={offset:m,line:f,column:m-l+1,codePoint:h,category:b},"bom"===b&&(h.atStart=0===m),e.push(h)))}return{findings:e,counts:d,total:g,truncated:g>e.length}}
+function N(a){if("string"!==typeof a)throw new TypeError("getNewlineStats expects a string input.");var c=0;let d=0,e=0;for(let g=0,f=a.length;g<f;g++){const l=a.charCodeAt(g);13===l?10===a.charCodeAt(g+1)?(c++,g++):d++:10===l&&e++}a={crlf:c,cr:d,lf:e};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 { n as summonSanctifier, M as inspectText, P as getRecommendedSanctifierOptions, O as inspectTextDetailed, N as getNewlineStats };

package/dist/types/index.d.ts

@@ -4,9 +4,11 @@ export type TrashFinding = import("./inspectText.js").TrashFinding;
 export type TrashCounts = import("./inspectText.js").TrashCounts;
 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;
 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, getRecommendedSanctifierOptions, summonSanctifier };
+export { inspectText, inspectTextDetailed, getNewlineStats, getRecommendedSanctifierOptions, summonSanctifier };

package/dist/types/inspectText.d.ts

@@ -9,7 +9,7 @@ export function inspectText(text: string): UnicodeTrashReport;
  * 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
+ * - `nonbreaking_space`: non-breaking and typographic spaces U+00A0, U+2000–U+200A, U+202F, U+205F, 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
@@ -29,23 +29,19 @@ export function inspectText(text: string): UnicodeTrashReport;
  */
 export function inspectTextDetailed(text: string, options?: InspectDetailedOptions): DetailedTrashReport;
 /**
- * Counts the number of different newline types in a string.
+ * @typedef {Object} NewlineStats
+ * @property {number} crlf - CR LF pairs.
+ * @property {number} cr - CRs not followed by LF.
+ * @property {number} lf - LFs not preceded by CR.
+ * @property {('CRLF'|'CR'|'LF')[]} types - Styles present, in the order CRLF, CR, LF.
+ * @property {boolean} mixed - True when more than one style is present.
+ */
+/**
+ * Counts each newline style in one pass, with no regex and no copy.
  * @param {string} text
- * @returns {{
- *   crlf: number,
- *   cr: number,
- *   lf: number,
- *   types: string[],
- *   mixed: boolean
- * }}
+ * @returns {NewlineStats}
  */
-export function getNewlineStats(text: string): {
-    crlf: number;
-    cr: number;
-    lf: number;
-    types: string[];
-    mixed: boolean;
-};
+export function getNewlineStats(text: string): NewlineStats;
 /**
  * Creates defaultOptions for summonSanctifier based on inspectText result
  * @param {!UnicodeTrashReport} report
@@ -62,6 +58,28 @@ export type UnicodeTrashReport = {
     hasNonKeyboardChars: boolean;
     summary: string[];
 };
+export type NewlineStats = {
+    /**
+     * - CR LF pairs.
+     */
+    crlf: number;
+    /**
+     * - CRs not followed by LF.
+     */
+    cr: number;
+    /**
+     * - LFs not preceded by CR.
+     */
+    lf: number;
+    /**
+     * - Styles present, in the order CRLF, CR, LF.
+     */
+    types: ("CRLF" | "CR" | "LF")[];
+    /**
+     * - True when more than one style is present.
+     */
+    mixed: boolean;
+};
 export type TrashCategory = "bidi_control" | "zero_width" | "nonbreaking_space" | "bom" | "nul" | "c0_control" | "c1_control" | "invisible_format" | "hangul_filler" | "variation_selector" | "tag";
 /**
  * One located character.
@@ -113,6 +131,7 @@ export type DetailedTrashReport = {
 export type InspectDetailedOptions = {
     /**
      * - Cap on listed findings (non-negative integer or Infinity).
+     * Each listed finding is an object, so memory grows with the number listed; 0 builds none (counts only).
      */
     maxFindings?: number;
 };

package/dist/types/sanctifyText.d.ts

@@ -122,7 +122,7 @@ export function normalizeTypographicJank(text: string): string;
  *
  * Targets:
  * - Non-breaking spaces ( )
- * - Zero-width spaces and miscellaneous Unicode spaces ( –‍,  , ⁠, 　, )
+ * - Zero-width spaces and miscellaneous Unicode spaces ( –‍,  ,  , ⁠, 　, )
  * - Bidi controls: marks, embeddings/overrides and isolates (؜, ‎, ‏, ‪–‮, ⁦–⁩)
  * - Invisible format characters: soft hyphen, CGJ, Mongolian vowel separator, invisible operators (­, ͏, ᠎, ⁡–⁤)
  * - Hangul fillers (ᅟ, ᅠ, ㅤ, ﾠ)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "text-sanctifier",
-  "version": "1.3.0",
+  "version": "1.3.1",
   "type": "module",
   "description": "A brutal text normalizer and invisible trash scrubber for modern web projects.",
   "engines": {

package/src/index.d.ts

@@ -1,12 +1,14 @@
 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, getRecommendedSanctifierOptions, summonSanctifier };
+export { inspectText, inspectTextDetailed, getNewlineStats, getRecommendedSanctifierOptions, summonSanctifier };
 export type UnicodeTrashReport = import('./inspectText.js').UnicodeTrashReport;
 export type TrashCategory = import('./inspectText.js').TrashCategory;
 export type TrashFinding = import('./inspectText.js').TrashFinding;
 export type TrashCounts = import('./inspectText.js').TrashCounts;
 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;

package/src/index.js

@@ -1,8 +1,8 @@
 // src/index.js
 
 
-import { inspectText, inspectTextDetailed, getRecommendedSanctifierOptions } from './inspectText.js';
-export { inspectText, inspectTextDetailed, getRecommendedSanctifierOptions };
+import { inspectText, inspectTextDetailed, getNewlineStats, getRecommendedSanctifierOptions } from './inspectText.js';
+export { inspectText, inspectTextDetailed, getNewlineStats, getRecommendedSanctifierOptions };
 
 import { summonSanctifier } from './sanctifyText.js';
 export { summonSanctifier };
@@ -14,6 +14,7 @@ export { summonSanctifier };
 /** @typedef {import('./inspectText.js').TrashCounts} TrashCounts */
 /** @typedef {import('./inspectText.js').DetailedTrashReport} DetailedTrashReport */
 /** @typedef {import('./inspectText.js').InspectDetailedOptions} InspectDetailedOptions */
+/** @typedef {import('./inspectText.js').NewlineStats} NewlineStats */
 /** @typedef {import('./sanctifyText.js').SanctifyOptions} SanctifyOptions */
 
 

package/src/inspectText.js

@@ -167,6 +167,7 @@ export function inspectText(text) {
 /**
  * @typedef {Object} InspectDetailedOptions
  * @property {number} [maxFindings=100] - Cap on listed findings (non-negative integer or Infinity).
+ *   Each listed finding is an object, so memory grows with the number listed; 0 builds none (counts only).
  */
 
 const DEFAULT_MAX_FINDINGS = 100;
@@ -194,7 +195,7 @@ function classifyCodeUnit(c) {
     if (c <= 0x200D) return 'zero_width';
     if (c <= 0x200F) return 'bidi_control';
     if (c >= 0x202A && c <= 0x202E) return 'bidi_control';
-    if (c === 0x202F) return 'nonbreaking_space';
+    if (c === 0x202F || c === 0x205F) return 'nonbreaking_space';
     if (c === 0x2060) return 'zero_width';
     if (c >= 0x2061 && c <= 0x2064) return 'invisible_format';
     if (c >= 0x2066 && c <= 0x2069) return 'bidi_control';
@@ -225,7 +226,7 @@ const TRASH_HIGH_SURROGATE = 0xDB40;
  * 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
+ * - `nonbreaking_space`: non-breaking and typographic spaces U+00A0, U+2000–U+200A, U+202F, U+205F, 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
@@ -322,15 +323,18 @@ export function inspectTextDetailed(text, options = {}) {
 }
 
 /**
- * Counts the number of different newline types in a string.
+ * @typedef {Object} NewlineStats
+ * @property {number} crlf - CR LF pairs.
+ * @property {number} cr - CRs not followed by LF.
+ * @property {number} lf - LFs not preceded by CR.
+ * @property {('CRLF'|'CR'|'LF')[]} types - Styles present, in the order CRLF, CR, LF.
+ * @property {boolean} mixed - True when more than one style is present.
+ */
+
+/**
+ * Counts each newline style in one pass, with no regex and no copy.
  * @param {string} text
- * @returns {{
- *   crlf: number,
- *   cr: number,
- *   lf: number,
- *   types: string[],
- *   mixed: boolean
- * }}
+ * @returns {NewlineStats}
  */
 export function getNewlineStats(text) {
     if (typeof text !== 'string') {

package/src/sanctifyText.js

@@ -276,7 +276,7 @@ export function sanctifyText(
  * 
  * Targets:
  * - Non-breaking spaces ( )
- * - Zero-width spaces and miscellaneous Unicode spaces ( –‍,  , ⁠, 　, )
+ * - Zero-width spaces and miscellaneous Unicode spaces ( –‍,  ,  , ⁠, 　, )
  * - Bidi controls: marks, embeddings/overrides and isolates (؜, ‎, ‏, ‪–‮, ⁦–⁩)
  * - Invisible format characters: soft hyphen, CGJ, Mongolian vowel separator, invisible operators (­, ͏, ᠎, ⁡–⁤)
  * - Hangul fillers (ᅟ, ᅠ, ㅤ, ﾠ)
@@ -286,7 +286,7 @@ export function sanctifyText(
  * @param {string} text
  * @returns {string}
  */
-export const INVISIBLE_TRASH_REGEX = /[ ­͏؜ᅟᅠ᠎ -‏‪- ⁠-⁤⁦-⁩　ㅤ︀-️ﾠ\u{E0000}-\u{E007F}\u{E0100}-\u{E01EF}]+/gu;
+export const INVISIBLE_TRASH_REGEX = /[ ­͏؜ᅟᅠ᠎ -‏‪-  ⁠-⁤⁦-⁩　ㅤ︀-️ﾠ\u{E0000}-\u{E007F}\u{E0100}-\u{E01EF}]+/gu;
 function purgeInvisibleTrash(text) {
     return text.replace(INVISIBLE_TRASH_REGEX, '');
 }