text-sanctifier 1.1.1 → 1.3.0

package/dist/types/inspectText.d.ts

@@ -14,7 +14,12 @@ export function inspectText(text: string): UnicodeTrashReport;
  * - `nul`: U+0000
  * - `c0_control`: U+0001–U+001F except tab, LF and CR; and U+007F
  * - `c1_control`: U+0080–U+009F
+ * - `invisible_format`: soft hyphen U+00AD, U+034F, U+180E, invisible operators U+2061–U+2064
+ * - `hangul_filler`: U+115F, U+1160, U+3164, U+FFA0 (letters that render blank)
+ * - `variation_selector`: U+FE00–U+FE0F, U+E0100–U+E01EF (including VS16 in emoji)
+ * - `tag`: U+E0000–U+E007F (tag characters, used for "ASCII smuggling")
  *
+ * `codePoint` is the full code point; `offset` and `column` count UTF-16 units.
  * Every occurrence is counted; only the first `maxFindings` are listed.
  * One pass over the string, no regex, no copy.
  *
@@ -57,10 +62,11 @@ export type UnicodeTrashReport = {
     hasNonKeyboardChars: boolean;
     summary: string[];
 };
-export type TrashCategory = "bidi_control" | "zero_width" | "nonbreaking_space" | "bom" | "nul" | "c0_control" | "c1_control";
+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.
- * - `offset`: 0-based UTF-16 index into the input (a JS string index).
+ * - `offset`: 0-based UTF-16 index into the input (a JS string index); for a code point
+ *   above U+FFFF, the index of its high surrogate.
  * - `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.
@@ -81,6 +87,10 @@ export type TrashCounts = {
     nul: number;
     c0_control: number;
     c1_control: number;
+    invisible_format: number;
+    hangul_filler: number;
+    variation_selector: number;
+    tag: number;
 };
 export type DetailedTrashReport = {
     /**

package/dist/types/sanctifyText.d.ts

@@ -91,7 +91,7 @@ export namespace summonSanctifier {
  * ⚠️ Note: This is plain-text normalization/filtering — not an HTML/XSS sanitizer.
  *
  * @param {string} text
- * @param {boolean} [purgeInvisibleChars=false] - Remove ZWSP, NBSP, bidi, etc.
+ * @param {boolean} [purgeInvisibleChars=false] - Remove ZWSP, NBSP, bidi, tags, variation selectors, etc.
  * @param {boolean} [purgeEmojis=false] - Remove emoji characters entirely.
  * @param {boolean} [nukeControls=false] - Remove non-whitespace control characters.
  * @param {boolean} [keyboardOnlyFilter=false] - Keep printable ASCII + full emoji sequences only (drops other Unicode).
@@ -121,9 +121,13 @@ export function normalizeTypographicJank(text: string): string;
  * Purges invisible Unicode "trash" characters and removes them.
  *
  * Targets:
- * - Non-breaking spaces (\u00A0)
- * - Zero-width spaces and miscellaneous Unicode spaces (\u2000–\u200D, \u202F, \u2060, \u3000, \uFEFF)
- * - Bidi controls: marks, embeddings/overrides and isolates (\u061C, \u200E, \u200F, \u202A–\u202E, \u2066–\u2069)
+ * - Non-breaking 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)
+ * - Variation selectors (︀–️, \u{E0100}–\u{E01EF}), including VS16 in emoji
+ * - Tag characters (\u{E0000}–\u{E007F}), used for "ASCII smuggling"
  *
  * @param {string} text
  * @returns {string}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "text-sanctifier",
-  "version": "1.1.1",
+  "version": "1.3.0",
   "type": "module",
   "description": "A brutal text normalizer and invisible trash scrubber for modern web projects.",
   "engines": {
@@ -9,8 +9,12 @@
   "main": "./src/index.js",
   "module": "./src/index.js",
   "browser": "./dist/text-sanctifier.min.js",
+  "bin": {
+    "text-sanctifier": "bin/text-sanctifier.js"
+  },
   "files": [
     "src",
+    "bin",
     "dist/text-sanctifier.min.js",
     "dist/types",
     "LICENSE",
@@ -34,7 +38,7 @@
     "build": "node scripts/buildc.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",
+    "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 test && npm run build && npm run build:types && npm run test:types && npm run test-min"
   },