echokyt 0.0.3 → 0.1.0

package/README.md

@@ -1,15 +1,18 @@
-# 📦 EchoKit
+# 📦 EchoKyt
 
-A lightweight, zero-dependency utility library for smart text manipulation in TypeScript.
+A lightweight, zero-runtime-dependency utility library for smart text manipulation in TypeScript.
 
-[![Tests](https://github.com/nyigoro/EchoKit/actions/workflows/test.yml/badge.svg)](https://github.com/nyigoro/EchoKit/actions)
+[![Tests](https://github.com/nyigoro/EchoKit/actions/workflows/ci.yml/badge.svg)](https://github.com/nyigoro/EchoKit/actions)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 
 ## ✨ Features
 
+- **Fluent API**: Chainable, readable text pipelines.
+- **Parser Utilities**: Mentions, hashtags, keyword density.
+- **Sanitization & Safety**: Strip HTML, scripts/styles, normalize quotes.
+- **Prompt Hygiene**: Clean whitespace, invisible chars, and common markers.
 - **Smart Truncate**: Cuts text at word boundaries, not mid-word.
-- **Reading Time**: Quick estimation for blog posts.
-- **Zero Dependencies**: Keep your bundle size tiny.
+- **Reading Metrics**: Reading time + Flesch Reading Ease score.
 - **TypeScript Ready**: Full type definitions included.
 
 ## 🚀 Installation
@@ -17,3 +20,46 @@ A lightweight, zero-dependency utility library for smart text manipulation in Ty
 ```bash
 npm install echokyt
 ```
+
+## ✅ Quick Example (Fluent)
+
+```ts
+import { EchoKyt } from 'echokyt';
+
+const score = EchoKyt.from('<p>“Hello” <strong>world</strong><script>alert(1)</script></p>')
+  .removeScriptsOrStyles()
+  .stripHtml(['strong', 'em'])
+  .normalizeQuotes()
+  .getReadingEase();
+
+// Flesch Reading Ease score (approx.)
+```
+
+## ✅ Quick Example (Functional)
+
+```ts
+import {
+  extractMentions,
+  extractHashtags,
+  getKeywordDensity,
+  stripHtml,
+  normalizeQuotes,
+  cleanWhitespace,
+} from 'echokyt';
+
+const text = 'Hello @alice, welcome to #EchoKyt!';
+
+extractMentions(text); // [{ value: 'alice', index: 6, raw: '@alice' }]
+extractHashtags(text); // [{ value: 'EchoKyt', index: 29, raw: '#EchoKyt' }]
+getKeywordDensity(text); // { hello: 0.25, alice: 0.25, welcome: 0.25, echokyt: 0.25 }
+stripHtml('<p>Hello <strong>World</strong></p>'); // "Hello World"
+normalizeQuotes('“Hello”'); // "\"Hello\""
+cleanWhitespace('  hi   there  '); // "hi there"
+```
+
+## 📊 Reading Ease Guide (Flesch)
+
+- 90–100: Very Easy
+- 60–70: Standard / Plain English
+- 30–50: Academic
+- 0–30: Very Difficult

package/dist/analyze/index.d.ts

@@ -1 +1,2 @@
 export * from './readingTime.js';
+export * from './readingEase.js';

package/dist/analyze/index.js

@@ -1 +1,2 @@
 export * from './readingTime.js';
+export * from './readingEase.js';

package/dist/analyze/readingEase.d.ts

@@ -0,0 +1,4 @@
+/**
+ * Computes the Flesch Reading Ease score (approximate, English heuristic).
+ */
+export declare const getReadingEase: (text: string) => number;

package/dist/analyze/readingEase.js

@@ -0,0 +1,31 @@
+const WORD_REGEX = /[A-Za-z]+(?:'[A-Za-z]+)*/g;
+const SENTENCE_REGEX = /[.!?]+/g;
+const countSyllables = (raw) => {
+    const word = raw.toLowerCase().replace(/[^a-z]/g, '');
+    if (!word)
+        return 0;
+    if (word.length <= 3)
+        return 1;
+    const groups = word.match(/[aeiouy]+/g);
+    let syllables = groups ? groups.length : 0;
+    if (word.endsWith('e') && !word.endsWith('le') && !word.endsWith('ye')) {
+        syllables -= 1;
+    }
+    return syllables > 0 ? syllables : 1;
+};
+/**
+ * Computes the Flesch Reading Ease score (approximate, English heuristic).
+ */
+export const getReadingEase = (text) => {
+    if (!text || !text.trim())
+        return 0;
+    const sanitized = text.replace(/<[^>]*>/g, ' ');
+    const words = sanitized.match(WORD_REGEX) ?? [];
+    if (words.length === 0)
+        return 0;
+    const sentences = (sanitized.match(SENTENCE_REGEX) ?? []).length || 1;
+    const syllables = words.reduce((sum, word) => sum + countSyllables(word), 0);
+    const wordsPerSentence = words.length / sentences;
+    const syllablesPerWord = syllables / words.length;
+    return 206.835 - 1.015 * wordsPerSentence - 84.6 * syllablesPerWord;
+};

package/dist/cjs/analyze/index.cjs

@@ -15,3 +15,4 @@ var __exportStar = (this && this.__exportStar) || function(m, exports) {
 };
 Object.defineProperty(exports, "__esModule", { value: true });
 __exportStar(require("./readingTime.js"), exports);
+__exportStar(require("./readingEase.js"), exports);

package/dist/cjs/analyze/readingEase.cjs

@@ -0,0 +1,35 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.getReadingEase = void 0;
+const WORD_REGEX = /[A-Za-z]+(?:'[A-Za-z]+)*/g;
+const SENTENCE_REGEX = /[.!?]+/g;
+const countSyllables = (raw) => {
+    const word = raw.toLowerCase().replace(/[^a-z]/g, '');
+    if (!word)
+        return 0;
+    if (word.length <= 3)
+        return 1;
+    const groups = word.match(/[aeiouy]+/g);
+    let syllables = groups ? groups.length : 0;
+    if (word.endsWith('e') && !word.endsWith('le') && !word.endsWith('ye')) {
+        syllables -= 1;
+    }
+    return syllables > 0 ? syllables : 1;
+};
+/**
+ * Computes the Flesch Reading Ease score (approximate, English heuristic).
+ */
+const getReadingEase = (text) => {
+    if (!text || !text.trim())
+        return 0;
+    const sanitized = text.replace(/<[^>]*>/g, ' ');
+    const words = sanitized.match(WORD_REGEX) ?? [];
+    if (words.length === 0)
+        return 0;
+    const sentences = (sanitized.match(SENTENCE_REGEX) ?? []).length || 1;
+    const syllables = words.reduce((sum, word) => sum + countSyllables(word), 0);
+    const wordsPerSentence = words.length / sentences;
+    const syllablesPerWord = syllables / words.length;
+    return 206.835 - 1.015 * wordsPerSentence - 84.6 * syllablesPerWord;
+};
+exports.getReadingEase = getReadingEase;

package/dist/cjs/echokyt.cjs

@@ -0,0 +1,66 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.EchoKyt = void 0;
+const readingTime_js_1 = require("./analyze/readingTime.js");
+const readingEase_js_1 = require("./analyze/readingEase.js");
+const slugify_js_1 = require("./format/slugify.js");
+const truncate_js_1 = require("./format/truncate.js");
+const index_js_1 = require("./parse/index.js");
+const index_js_2 = require("./sanitize/index.js");
+class EchoKyt {
+    constructor(text) {
+        this.text = text;
+    }
+    static from(text) {
+        return new EchoKyt(text ?? '');
+    }
+    value() {
+        return this.text;
+    }
+    toString() {
+        return this.text;
+    }
+    cleanWhitespace() {
+        return new EchoKyt((0, index_js_2.cleanWhitespace)(this.text));
+    }
+    stripInvisible() {
+        return new EchoKyt((0, index_js_2.stripInvisibleChars)(this.text));
+    }
+    removeScriptsOrStyles() {
+        return new EchoKyt((0, index_js_2.removeScriptsOrStyles)(this.text));
+    }
+    stripHtml(allowedTags) {
+        return new EchoKyt((0, index_js_2.stripHtml)(this.text, allowedTags));
+    }
+    normalizeQuotes() {
+        return new EchoKyt((0, index_js_2.normalizeQuotes)(this.text));
+    }
+    stripPromptPatterns(patterns) {
+        return new EchoKyt((0, index_js_2.stripPromptPatterns)(this.text, patterns));
+    }
+    truncate(limit) {
+        return new EchoKyt((0, truncate_js_1.smartTruncate)(this.text, limit));
+    }
+    slug() {
+        return new EchoKyt((0, slugify_js_1.slugify)(this.text));
+    }
+    mentions() {
+        return (0, index_js_1.extractMentions)(this.text);
+    }
+    hashtags() {
+        return (0, index_js_1.extractHashtags)(this.text);
+    }
+    parse() {
+        return (0, index_js_1.parseMentionsAndHashtags)(this.text);
+    }
+    keywordDensity(options) {
+        return (0, index_js_1.getKeywordDensity)(this.text, options);
+    }
+    readingTime(wordsPerMinute) {
+        return (0, readingTime_js_1.readingTime)(this.text, wordsPerMinute);
+    }
+    getReadingEase() {
+        return (0, readingEase_js_1.getReadingEase)(this.text);
+    }
+}
+exports.EchoKyt = EchoKyt;

package/dist/cjs/index.cjs

@@ -17,3 +17,5 @@ Object.defineProperty(exports, "__esModule", { value: true });
 __exportStar(require("./format/index.js"), exports);
 __exportStar(require("./analyze/index.js"), exports);
 __exportStar(require("./parse/index.js"), exports);
+__exportStar(require("./sanitize/index.js"), exports);
+__exportStar(require("./echokyt.js"), exports);

package/dist/cjs/parse/hashtags.cjs

@@ -1,7 +1,7 @@
 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.extractHashtags = void 0;
-const HASHTAG_REGEX = /(^|[^\w])#([\p{L}\p{M}0-9_]{1,64})/gu;
+const HASHTAG_REGEX = /(^|[^\p{L}\p{M}0-9_])#([\p{L}\p{M}0-9_]{1,64})/gu;
 /**
  * Extracts #hashtags from text.
  */

package/dist/cjs/parse/index.cjs

@@ -1,12 +1,16 @@
 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.parseMentionsAndHashtags = exports.extractHashtags = exports.extractMentions = void 0;
+exports.parseMentionsAndHashtags = exports.DEFAULT_STOP_WORDS = exports.getKeywordDensity = exports.extractHashtags = exports.extractMentions = void 0;
 const mentions_js_1 = require("./mentions.js");
 const hashtags_js_1 = require("./hashtags.js");
 var mentions_js_2 = require("./mentions.js");
 Object.defineProperty(exports, "extractMentions", { enumerable: true, get: function () { return mentions_js_2.extractMentions; } });
 var hashtags_js_2 = require("./hashtags.js");
 Object.defineProperty(exports, "extractHashtags", { enumerable: true, get: function () { return hashtags_js_2.extractHashtags; } });
+var keywordDensity_js_1 = require("./keywordDensity.js");
+Object.defineProperty(exports, "getKeywordDensity", { enumerable: true, get: function () { return keywordDensity_js_1.getKeywordDensity; } });
+var stopWords_js_1 = require("./stopWords.js");
+Object.defineProperty(exports, "DEFAULT_STOP_WORDS", { enumerable: true, get: function () { return stopWords_js_1.DEFAULT_STOP_WORDS; } });
 const parseMentionsAndHashtags = (text) => ({
     mentions: (0, mentions_js_1.extractMentions)(text),
     hashtags: (0, hashtags_js_1.extractHashtags)(text),

package/dist/cjs/parse/keywordDensity.cjs

@@ -0,0 +1,35 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.getKeywordDensity = void 0;
+const stopWords_js_1 = require("./stopWords.js");
+const WORD_REGEX = /[\p{L}\p{M}0-9_']+/gu;
+/**
+ * Returns keyword frequency (0-1) for filtered tokens in the text.
+ */
+const getKeywordDensity = (text, options = {}) => {
+    if (!text || !text.trim())
+        return {};
+    const minLength = options.minLength ?? 3;
+    const normalize = options.normalize ?? true;
+    const stopWords = options.stopWords ?? [...stopWords_js_1.DEFAULT_STOP_WORDS];
+    const stopSet = new Set(normalize ? stopWords.map((word) => word.toLowerCase()) : stopWords);
+    const tokens = text.match(WORD_REGEX) ?? [];
+    const counts = {};
+    let total = 0;
+    for (const raw of tokens) {
+        const token = normalize ? raw.toLowerCase() : raw;
+        if (token.length < minLength)
+            continue;
+        if (stopSet.has(token))
+            continue;
+        counts[token] = (counts[token] ?? 0) + 1;
+        total += 1;
+    }
+    if (total === 0)
+        return {};
+    for (const key of Object.keys(counts)) {
+        counts[key] = counts[key] / total;
+    }
+    return counts;
+};
+exports.getKeywordDensity = getKeywordDensity;

package/dist/cjs/parse/mentions.cjs

@@ -1,7 +1,7 @@
 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.extractMentions = void 0;
-const MENTION_REGEX = /(^|[^\w])@([\p{L}\p{M}0-9_]{1,32})/gu;
+const MENTION_REGEX = /(^|[^\p{L}\p{M}0-9_])@([\p{L}\p{M}0-9_]{1,32})/gu;
 /**
  * Extracts @mentions from text.
  */

package/dist/cjs/parse/stopWords.cjs

@@ -0,0 +1,129 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.DEFAULT_STOP_WORDS = void 0;
+exports.DEFAULT_STOP_WORDS = [
+    'a',
+    'about',
+    'above',
+    'after',
+    'again',
+    'against',
+    'all',
+    'am',
+    'an',
+    'and',
+    'any',
+    'are',
+    'as',
+    'at',
+    'be',
+    'because',
+    'been',
+    'before',
+    'being',
+    'below',
+    'between',
+    'both',
+    'but',
+    'by',
+    'can',
+    'did',
+    'do',
+    'does',
+    'doing',
+    'down',
+    'during',
+    'each',
+    'few',
+    'for',
+    'from',
+    'further',
+    'had',
+    'has',
+    'have',
+    'having',
+    'he',
+    'her',
+    'here',
+    'hers',
+    'herself',
+    'him',
+    'himself',
+    'his',
+    'how',
+    'i',
+    'if',
+    'in',
+    'into',
+    'is',
+    'it',
+    'its',
+    'itself',
+    'just',
+    'me',
+    'more',
+    'most',
+    'my',
+    'myself',
+    'no',
+    'nor',
+    'not',
+    'now',
+    'of',
+    'off',
+    'on',
+    'once',
+    'only',
+    'or',
+    'other',
+    'our',
+    'ours',
+    'ourselves',
+    'out',
+    'over',
+    'own',
+    'same',
+    'she',
+    'should',
+    'so',
+    'some',
+    'such',
+    'than',
+    'that',
+    'the',
+    'their',
+    'theirs',
+    'them',
+    'themselves',
+    'then',
+    'there',
+    'these',
+    'they',
+    'this',
+    'those',
+    'through',
+    'to',
+    'too',
+    'under',
+    'until',
+    'up',
+    'very',
+    'was',
+    'we',
+    'were',
+    'what',
+    'when',
+    'where',
+    'which',
+    'while',
+    'who',
+    'whom',
+    'why',
+    'with',
+    'would',
+    'you',
+    'your',
+    'yours',
+    'yourself',
+    'yourselves',
+];

package/dist/cjs/sanitize/cleanWhitespace.cjs

@@ -0,0 +1,12 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.cleanWhitespace = void 0;
+/**
+ * Collapses whitespace and trims the ends.
+ */
+const cleanWhitespace = (text) => {
+    if (!text)
+        return '';
+    return text.replace(/\s+/g, ' ').trim();
+};
+exports.cleanWhitespace = cleanWhitespace;

package/dist/cjs/sanitize/index.cjs

@@ -0,0 +1,16 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.normalizeQuotes = exports.removeScriptsOrStyles = exports.stripHtml = exports.DEFAULT_PROMPT_PATTERNS = exports.stripPromptPatterns = exports.stripInvisibleChars = exports.cleanWhitespace = void 0;
+var cleanWhitespace_js_1 = require("./cleanWhitespace.js");
+Object.defineProperty(exports, "cleanWhitespace", { enumerable: true, get: function () { return cleanWhitespace_js_1.cleanWhitespace; } });
+var stripInvisibleChars_js_1 = require("./stripInvisibleChars.js");
+Object.defineProperty(exports, "stripInvisibleChars", { enumerable: true, get: function () { return stripInvisibleChars_js_1.stripInvisibleChars; } });
+var stripPromptPatterns_js_1 = require("./stripPromptPatterns.js");
+Object.defineProperty(exports, "stripPromptPatterns", { enumerable: true, get: function () { return stripPromptPatterns_js_1.stripPromptPatterns; } });
+Object.defineProperty(exports, "DEFAULT_PROMPT_PATTERNS", { enumerable: true, get: function () { return stripPromptPatterns_js_1.DEFAULT_PROMPT_PATTERNS; } });
+var stripHtml_js_1 = require("./stripHtml.js");
+Object.defineProperty(exports, "stripHtml", { enumerable: true, get: function () { return stripHtml_js_1.stripHtml; } });
+var removeScriptsOrStyles_js_1 = require("./removeScriptsOrStyles.js");
+Object.defineProperty(exports, "removeScriptsOrStyles", { enumerable: true, get: function () { return removeScriptsOrStyles_js_1.removeScriptsOrStyles; } });
+var normalizeQuotes_js_1 = require("./normalizeQuotes.js");
+Object.defineProperty(exports, "normalizeQuotes", { enumerable: true, get: function () { return normalizeQuotes_js_1.normalizeQuotes; } });

package/dist/cjs/sanitize/normalizeQuotes.cjs

@@ -0,0 +1,12 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.normalizeQuotes = void 0;
+/**
+ * Normalizes smart quotes to straight quotes.
+ */
+const normalizeQuotes = (text) => {
+    if (!text)
+        return '';
+    return text.replace(/[“”]/g, '"').replace(/[‘’]/g, "'");
+};
+exports.normalizeQuotes = normalizeQuotes;

package/dist/cjs/sanitize/removeScriptsOrStyles.cjs

@@ -0,0 +1,14 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.removeScriptsOrStyles = void 0;
+const SCRIPT_REGEX = /<script\b[^>]*>[\s\S]*?<\/script>/gi;
+const STYLE_REGEX = /<style\b[^>]*>[\s\S]*?<\/style>/gi;
+/**
+ * Removes <script> and <style> blocks entirely. Preserves <noscript>.
+ */
+const removeScriptsOrStyles = (text) => {
+    if (!text)
+        return '';
+    return text.replace(SCRIPT_REGEX, '').replace(STYLE_REGEX, '');
+};
+exports.removeScriptsOrStyles = removeScriptsOrStyles;

package/dist/cjs/sanitize/stripHtml.cjs

@@ -0,0 +1,22 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.stripHtml = void 0;
+const TAG_REGEX = /<\/?([A-Za-z][A-Za-z0-9-]*)\b[^>]*>/g;
+/**
+ * Removes HTML tags, optionally preserving a whitelist of tag names (attributes are always stripped).
+ */
+const stripHtml = (text, allowedTags = []) => {
+    if (!text)
+        return '';
+    const allowed = new Set(allowedTags.map((tag) => tag.toLowerCase()));
+    const withoutDisallowed = text.replace(TAG_REGEX, (match, tag) => {
+        return allowed.has(String(tag).toLowerCase()) ? match : '';
+    });
+    return withoutDisallowed.replace(TAG_REGEX, (match, tag) => {
+        const name = String(tag).toLowerCase();
+        if (!allowed.has(name))
+            return '';
+        return match.startsWith('</') ? `</${name}>` : `<${name}>`;
+    });
+};
+exports.stripHtml = stripHtml;

package/dist/cjs/sanitize/stripInvisibleChars.cjs

@@ -0,0 +1,13 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.stripInvisibleChars = void 0;
+const INVISIBLE_REGEX = /[\u200B-\u200D\u2060\uFEFF\u180E]/g;
+/**
+ * Removes zero-width and invisible characters.
+ */
+const stripInvisibleChars = (text) => {
+    if (!text)
+        return '';
+    return text.replace(INVISIBLE_REGEX, '');
+};
+exports.stripInvisibleChars = stripInvisibleChars;

package/dist/cjs/sanitize/stripPromptPatterns.cjs

@@ -0,0 +1,21 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.stripPromptPatterns = exports.DEFAULT_PROMPT_PATTERNS = void 0;
+exports.DEFAULT_PROMPT_PATTERNS = [
+    /<<\s*SYS\s*>>/gi,
+    /<<\s*\/\s*SYS\s*>>/gi,
+    /<<\s*USER\s*>>/gi,
+    /<<\s*\/\s*USER\s*>>/gi,
+    /<<\s*ASSISTANT\s*>>/gi,
+    /<<\s*\/\s*ASSISTANT\s*>>/gi,
+    /#{3,}/g,
+];
+/**
+ * Removes common prompt marker patterns.
+ */
+const stripPromptPatterns = (text, patterns = exports.DEFAULT_PROMPT_PATTERNS) => {
+    if (!text)
+        return '';
+    return patterns.reduce((acc, pattern) => acc.replace(pattern, ''), text);
+};
+exports.stripPromptPatterns = stripPromptPatterns;

package/dist/echokyt.d.ts

@@ -0,0 +1,22 @@
+import type { KeywordDensityOptions, ParseResult } from './parse/index.js';
+export declare class EchoKyt {
+    private readonly text;
+    private constructor();
+    static from(text: string): EchoKyt;
+    value(): string;
+    toString(): string;
+    cleanWhitespace(): EchoKyt;
+    stripInvisible(): EchoKyt;
+    removeScriptsOrStyles(): EchoKyt;
+    stripHtml(allowedTags?: string[]): EchoKyt;
+    normalizeQuotes(): EchoKyt;
+    stripPromptPatterns(patterns?: RegExp[]): EchoKyt;
+    truncate(limit: number): EchoKyt;
+    slug(): EchoKyt;
+    mentions(): import("./parse/mentions.js").MentionToken[];
+    hashtags(): import("./parse/hashtags.js").HashtagToken[];
+    parse(): ParseResult;
+    keywordDensity(options?: KeywordDensityOptions): Record<string, number>;
+    readingTime(wordsPerMinute?: number): number;
+    getReadingEase(): number;
+}

package/dist/echokyt.js

@@ -0,0 +1,62 @@
+import { readingTime } from './analyze/readingTime.js';
+import { getReadingEase } from './analyze/readingEase.js';
+import { slugify } from './format/slugify.js';
+import { smartTruncate } from './format/truncate.js';
+import { extractHashtags, extractMentions, getKeywordDensity, parseMentionsAndHashtags, } from './parse/index.js';
+import { cleanWhitespace, normalizeQuotes, removeScriptsOrStyles, stripInvisibleChars, stripHtml, stripPromptPatterns, } from './sanitize/index.js';
+export class EchoKyt {
+    constructor(text) {
+        this.text = text;
+    }
+    static from(text) {
+        return new EchoKyt(text ?? '');
+    }
+    value() {
+        return this.text;
+    }
+    toString() {
+        return this.text;
+    }
+    cleanWhitespace() {
+        return new EchoKyt(cleanWhitespace(this.text));
+    }
+    stripInvisible() {
+        return new EchoKyt(stripInvisibleChars(this.text));
+    }
+    removeScriptsOrStyles() {
+        return new EchoKyt(removeScriptsOrStyles(this.text));
+    }
+    stripHtml(allowedTags) {
+        return new EchoKyt(stripHtml(this.text, allowedTags));
+    }
+    normalizeQuotes() {
+        return new EchoKyt(normalizeQuotes(this.text));
+    }
+    stripPromptPatterns(patterns) {
+        return new EchoKyt(stripPromptPatterns(this.text, patterns));
+    }
+    truncate(limit) {
+        return new EchoKyt(smartTruncate(this.text, limit));
+    }
+    slug() {
+        return new EchoKyt(slugify(this.text));
+    }
+    mentions() {
+        return extractMentions(this.text);
+    }
+    hashtags() {
+        return extractHashtags(this.text);
+    }
+    parse() {
+        return parseMentionsAndHashtags(this.text);
+    }
+    keywordDensity(options) {
+        return getKeywordDensity(this.text, options);
+    }
+    readingTime(wordsPerMinute) {
+        return readingTime(this.text, wordsPerMinute);
+    }
+    getReadingEase() {
+        return getReadingEase(this.text);
+    }
+}

package/dist/index.d.ts

@@ -1,3 +1,5 @@
 export * from './format/index.js';
 export * from './analyze/index.js';
 export * from './parse/index.js';
+export * from './sanitize/index.js';
+export * from './echokyt.js';

package/dist/index.js

@@ -1,3 +1,5 @@
 export * from './format/index.js';
 export * from './analyze/index.js';
 export * from './parse/index.js';
+export * from './sanitize/index.js';
+export * from './echokyt.js';

package/dist/parse/hashtags.js

@@ -1,4 +1,4 @@
-const HASHTAG_REGEX = /(^|[^\w])#([\p{L}\p{M}0-9_]{1,64})/gu;
+const HASHTAG_REGEX = /(^|[^\p{L}\p{M}0-9_])#([\p{L}\p{M}0-9_]{1,64})/gu;
 /**
  * Extracts #hashtags from text.
  */

package/dist/parse/index.d.ts

@@ -1,8 +1,14 @@
+import { extractMentions } from './mentions.js';
+import { extractHashtags } from './hashtags.js';
 export { extractMentions } from './mentions.js';
 export type { MentionToken } from './mentions.js';
 export { extractHashtags } from './hashtags.js';
 export type { HashtagToken } from './hashtags.js';
-export declare const parseMentionsAndHashtags: (text: string) => {
-    mentions: import("./mentions.js").MentionToken[];
-    hashtags: import("./hashtags.js").HashtagToken[];
+export { getKeywordDensity } from './keywordDensity.js';
+export type { KeywordDensityOptions } from './keywordDensity.js';
+export { DEFAULT_STOP_WORDS } from './stopWords.js';
+export type ParseResult = {
+    mentions: ReturnType<typeof extractMentions>;
+    hashtags: ReturnType<typeof extractHashtags>;
 };
+export declare const parseMentionsAndHashtags: (text: string) => ParseResult;

package/dist/parse/index.js

@@ -2,6 +2,8 @@ import { extractMentions } from './mentions.js';
 import { extractHashtags } from './hashtags.js';
 export { extractMentions } from './mentions.js';
 export { extractHashtags } from './hashtags.js';
+export { getKeywordDensity } from './keywordDensity.js';
+export { DEFAULT_STOP_WORDS } from './stopWords.js';
 export const parseMentionsAndHashtags = (text) => ({
     mentions: extractMentions(text),
     hashtags: extractHashtags(text),

package/dist/parse/keywordDensity.d.ts

@@ -0,0 +1,9 @@
+export type KeywordDensityOptions = {
+    minLength?: number;
+    stopWords?: string[];
+    normalize?: boolean;
+};
+/**
+ * Returns keyword frequency (0-1) for filtered tokens in the text.
+ */
+export declare const getKeywordDensity: (text: string, options?: KeywordDensityOptions) => Record<string, number>;

package/dist/parse/keywordDensity.js

@@ -0,0 +1,31 @@
+import { DEFAULT_STOP_WORDS } from './stopWords.js';
+const WORD_REGEX = /[\p{L}\p{M}0-9_']+/gu;
+/**
+ * Returns keyword frequency (0-1) for filtered tokens in the text.
+ */
+export const getKeywordDensity = (text, options = {}) => {
+    if (!text || !text.trim())
+        return {};
+    const minLength = options.minLength ?? 3;
+    const normalize = options.normalize ?? true;
+    const stopWords = options.stopWords ?? [...DEFAULT_STOP_WORDS];
+    const stopSet = new Set(normalize ? stopWords.map((word) => word.toLowerCase()) : stopWords);
+    const tokens = text.match(WORD_REGEX) ?? [];
+    const counts = {};
+    let total = 0;
+    for (const raw of tokens) {
+        const token = normalize ? raw.toLowerCase() : raw;
+        if (token.length < minLength)
+            continue;
+        if (stopSet.has(token))
+            continue;
+        counts[token] = (counts[token] ?? 0) + 1;
+        total += 1;
+    }
+    if (total === 0)
+        return {};
+    for (const key of Object.keys(counts)) {
+        counts[key] = counts[key] / total;
+    }
+    return counts;
+};

package/dist/parse/mentions.js

@@ -1,4 +1,4 @@
-const MENTION_REGEX = /(^|[^\w])@([\p{L}\p{M}0-9_]{1,32})/gu;
+const MENTION_REGEX = /(^|[^\p{L}\p{M}0-9_])@([\p{L}\p{M}0-9_]{1,32})/gu;
 /**
  * Extracts @mentions from text.
  */

package/dist/parse/stopWords.d.ts

@@ -0,0 +1 @@
+export declare const DEFAULT_STOP_WORDS: readonly ["a", "about", "above", "after", "again", "against", "all", "am", "an", "and", "any", "are", "as", "at", "be", "because", "been", "before", "being", "below", "between", "both", "but", "by", "can", "did", "do", "does", "doing", "down", "during", "each", "few", "for", "from", "further", "had", "has", "have", "having", "he", "her", "here", "hers", "herself", "him", "himself", "his", "how", "i", "if", "in", "into", "is", "it", "its", "itself", "just", "me", "more", "most", "my", "myself", "no", "nor", "not", "now", "of", "off", "on", "once", "only", "or", "other", "our", "ours", "ourselves", "out", "over", "own", "same", "she", "should", "so", "some", "such", "than", "that", "the", "their", "theirs", "them", "themselves", "then", "there", "these", "they", "this", "those", "through", "to", "too", "under", "until", "up", "very", "was", "we", "were", "what", "when", "where", "which", "while", "who", "whom", "why", "with", "would", "you", "your", "yours", "yourself", "yourselves"];

package/dist/parse/stopWords.js

@@ -0,0 +1,126 @@
+export const DEFAULT_STOP_WORDS = [
+    'a',
+    'about',
+    'above',
+    'after',
+    'again',
+    'against',
+    'all',
+    'am',
+    'an',
+    'and',
+    'any',
+    'are',
+    'as',
+    'at',
+    'be',
+    'because',
+    'been',
+    'before',
+    'being',
+    'below',
+    'between',
+    'both',
+    'but',
+    'by',
+    'can',
+    'did',
+    'do',
+    'does',
+    'doing',
+    'down',
+    'during',
+    'each',
+    'few',
+    'for',
+    'from',
+    'further',
+    'had',
+    'has',
+    'have',
+    'having',
+    'he',
+    'her',
+    'here',
+    'hers',
+    'herself',
+    'him',
+    'himself',
+    'his',
+    'how',
+    'i',
+    'if',
+    'in',
+    'into',
+    'is',
+    'it',
+    'its',
+    'itself',
+    'just',
+    'me',
+    'more',
+    'most',
+    'my',
+    'myself',
+    'no',
+    'nor',
+    'not',
+    'now',
+    'of',
+    'off',
+    'on',
+    'once',
+    'only',
+    'or',
+    'other',
+    'our',
+    'ours',
+    'ourselves',
+    'out',
+    'over',
+    'own',
+    'same',
+    'she',
+    'should',
+    'so',
+    'some',
+    'such',
+    'than',
+    'that',
+    'the',
+    'their',
+    'theirs',
+    'them',
+    'themselves',
+    'then',
+    'there',
+    'these',
+    'they',
+    'this',
+    'those',
+    'through',
+    'to',
+    'too',
+    'under',
+    'until',
+    'up',
+    'very',
+    'was',
+    'we',
+    'were',
+    'what',
+    'when',
+    'where',
+    'which',
+    'while',
+    'who',
+    'whom',
+    'why',
+    'with',
+    'would',
+    'you',
+    'your',
+    'yours',
+    'yourself',
+    'yourselves',
+];

package/dist/sanitize/cleanWhitespace.d.ts

@@ -0,0 +1,4 @@
+/**
+ * Collapses whitespace and trims the ends.
+ */
+export declare const cleanWhitespace: (text: string) => string;

package/dist/sanitize/cleanWhitespace.js

@@ -0,0 +1,8 @@
+/**
+ * Collapses whitespace and trims the ends.
+ */
+export const cleanWhitespace = (text) => {
+    if (!text)
+        return '';
+    return text.replace(/\s+/g, ' ').trim();
+};

package/dist/sanitize/index.d.ts

@@ -0,0 +1,6 @@
+export { cleanWhitespace } from './cleanWhitespace.js';
+export { stripInvisibleChars } from './stripInvisibleChars.js';
+export { stripPromptPatterns, DEFAULT_PROMPT_PATTERNS } from './stripPromptPatterns.js';
+export { stripHtml } from './stripHtml.js';
+export { removeScriptsOrStyles } from './removeScriptsOrStyles.js';
+export { normalizeQuotes } from './normalizeQuotes.js';

package/dist/sanitize/index.js

@@ -0,0 +1,6 @@
+export { cleanWhitespace } from './cleanWhitespace.js';
+export { stripInvisibleChars } from './stripInvisibleChars.js';
+export { stripPromptPatterns, DEFAULT_PROMPT_PATTERNS } from './stripPromptPatterns.js';
+export { stripHtml } from './stripHtml.js';
+export { removeScriptsOrStyles } from './removeScriptsOrStyles.js';
+export { normalizeQuotes } from './normalizeQuotes.js';

package/dist/sanitize/normalizeQuotes.d.ts

@@ -0,0 +1,4 @@
+/**
+ * Normalizes smart quotes to straight quotes.
+ */
+export declare const normalizeQuotes: (text: string) => string;

package/dist/sanitize/normalizeQuotes.js

@@ -0,0 +1,8 @@
+/**
+ * Normalizes smart quotes to straight quotes.
+ */
+export const normalizeQuotes = (text) => {
+    if (!text)
+        return '';
+    return text.replace(/[“”]/g, '"').replace(/[‘’]/g, "'");
+};

package/dist/sanitize/removeScriptsOrStyles.d.ts

@@ -0,0 +1,4 @@
+/**
+ * Removes <script> and <style> blocks entirely. Preserves <noscript>.
+ */
+export declare const removeScriptsOrStyles: (text: string) => string;

package/dist/sanitize/removeScriptsOrStyles.js

@@ -0,0 +1,10 @@
+const SCRIPT_REGEX = /<script\b[^>]*>[\s\S]*?<\/script>/gi;
+const STYLE_REGEX = /<style\b[^>]*>[\s\S]*?<\/style>/gi;
+/**
+ * Removes <script> and <style> blocks entirely. Preserves <noscript>.
+ */
+export const removeScriptsOrStyles = (text) => {
+    if (!text)
+        return '';
+    return text.replace(SCRIPT_REGEX, '').replace(STYLE_REGEX, '');
+};

package/dist/sanitize/stripHtml.d.ts

@@ -0,0 +1,4 @@
+/**
+ * Removes HTML tags, optionally preserving a whitelist of tag names (attributes are always stripped).
+ */
+export declare const stripHtml: (text: string, allowedTags?: string[]) => string;

package/dist/sanitize/stripHtml.js

@@ -0,0 +1,18 @@
+const TAG_REGEX = /<\/?([A-Za-z][A-Za-z0-9-]*)\b[^>]*>/g;
+/**
+ * Removes HTML tags, optionally preserving a whitelist of tag names (attributes are always stripped).
+ */
+export const stripHtml = (text, allowedTags = []) => {
+    if (!text)
+        return '';
+    const allowed = new Set(allowedTags.map((tag) => tag.toLowerCase()));
+    const withoutDisallowed = text.replace(TAG_REGEX, (match, tag) => {
+        return allowed.has(String(tag).toLowerCase()) ? match : '';
+    });
+    return withoutDisallowed.replace(TAG_REGEX, (match, tag) => {
+        const name = String(tag).toLowerCase();
+        if (!allowed.has(name))
+            return '';
+        return match.startsWith('</') ? `</${name}>` : `<${name}>`;
+    });
+};

package/dist/sanitize/stripInvisibleChars.d.ts

@@ -0,0 +1,4 @@
+/**
+ * Removes zero-width and invisible characters.
+ */
+export declare const stripInvisibleChars: (text: string) => string;

package/dist/sanitize/stripInvisibleChars.js

@@ -0,0 +1,9 @@
+const INVISIBLE_REGEX = /[\u200B-\u200D\u2060\uFEFF\u180E]/g;
+/**
+ * Removes zero-width and invisible characters.
+ */
+export const stripInvisibleChars = (text) => {
+    if (!text)
+        return '';
+    return text.replace(INVISIBLE_REGEX, '');
+};

package/dist/sanitize/stripPromptPatterns.d.ts

@@ -0,0 +1,5 @@
+export declare const DEFAULT_PROMPT_PATTERNS: RegExp[];
+/**
+ * Removes common prompt marker patterns.
+ */
+export declare const stripPromptPatterns: (text: string, patterns?: RegExp[]) => string;

package/dist/sanitize/stripPromptPatterns.js

@@ -0,0 +1,17 @@
+export const DEFAULT_PROMPT_PATTERNS = [
+    /<<\s*SYS\s*>>/gi,
+    /<<\s*\/\s*SYS\s*>>/gi,
+    /<<\s*USER\s*>>/gi,
+    /<<\s*\/\s*USER\s*>>/gi,
+    /<<\s*ASSISTANT\s*>>/gi,
+    /<<\s*\/\s*ASSISTANT\s*>>/gi,
+    /#{3,}/g,
+];
+/**
+ * Removes common prompt marker patterns.
+ */
+export const stripPromptPatterns = (text, patterns = DEFAULT_PROMPT_PATTERNS) => {
+    if (!text)
+        return '';
+    return patterns.reduce((acc, pattern) => acc.replace(pattern, ''), text);
+};

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "echokyt",
-  "version": "0.0.3",
+  "version": "0.1.0",
   "description": "A lightweight text utility library",
   "main": "./dist/cjs/index.cjs",
   "module": "./dist/index.js",
@@ -11,6 +11,11 @@
       "import": "./dist/index.js",
       "require": "./dist/cjs/index.cjs"
     },
+    "./echokyt": {
+      "types": "./dist/echokyt.d.ts",
+      "import": "./dist/echokyt.js",
+      "require": "./dist/cjs/echokyt.cjs"
+    },
     "./format": {
       "types": "./dist/format/index.d.ts",
       "import": "./dist/format/index.js",
@@ -41,10 +46,23 @@
       "import": "./dist/parse/*.js",
       "require": "./dist/cjs/parse/*.cjs"
     },
+    "./sanitize": {
+      "types": "./dist/sanitize/index.d.ts",
+      "import": "./dist/sanitize/index.js",
+      "require": "./dist/cjs/sanitize/index.cjs"
+    },
+    "./sanitize/*": {
+      "types": "./dist/sanitize/*.d.ts",
+      "import": "./dist/sanitize/*.js",
+      "require": "./dist/cjs/sanitize/*.cjs"
+    },
     "./package.json": "./package.json"
   },
   "typesVersions": {
     "*": {
+      "echokyt": [
+        "dist/echokyt.d.ts"
+      ],
       "format": [
         "dist/format/index.d.ts"
       ],
@@ -63,6 +81,12 @@
       "parse/*": [
         "dist/parse/*.d.ts"
       ],
+      "sanitize": [
+        "dist/sanitize/index.d.ts"
+      ],
+      "sanitize/*": [
+        "dist/sanitize/*.d.ts"
+      ],
       "*": [
         "dist/*"
       ]
@@ -81,7 +105,9 @@
     "bench": "npm run build && node benchmarks/bench.mjs",
     "release": "standard-version",
     "test": "jest",
-    "prepublishOnly": "npm run test && npm run build"
+    "prepublishOnly": "npm run lint && npm run test && npm run build",
+    "preversion": "npm run lint && npm run test",
+    "postversion": "git push && git push --tags"
   },
   "repository": {
     "type": "git",
@@ -91,6 +117,14 @@
     "text",
     "string",
     "utilities",
+    "text-manipulation",
+    "sanitization",
+    "parsing",
+    "mentions",
+    "hashtags",
+    "readability",
+    "llm",
+    "prompt-hygiene",
     "slugify",
     "truncate",
     "reading-time",
@@ -112,8 +146,8 @@
   "homepage": "https://github.com/nyigoro/EchoKit#readme",
   "devDependencies": {
     "@types/jest": "^29.0.0",
-    "@typescript-eslint/eslint-plugin": "^7.18.0",
-    "@typescript-eslint/parser": "^7.18.0",
+    "@typescript-eslint/eslint-plugin": "^8.55.0",
+    "@typescript-eslint/parser": "^8.55.0",
     "eslint": "^8.57.0",
     "jest": "^29.0.0",
     "prettier": "^3.2.5",