html-to-markdown-wasm 2.4.1 → 2.5.0

package/README.md

@@ -52,56 +52,63 @@ import { convert } from "npm:html-to-markdown-wasm";
 
 ## Usage
 
-### Node.js
+### Basic Conversion
 
 ```javascript
-// CommonJS
-const { convert } = require('html-to-markdown-wasm/dist-node');
+import { convert } from 'html-to-markdown-wasm';
 
-const markdown = convert('<h1>Hello World</h1>');
+const html = '<h1>Hello World</h1><p>This is <strong>fast</strong>!</p>';
+const markdown = convert(html);
 console.log(markdown);
+// # Hello World
+//
+// This is **fast**!
 ```
 
-```javascript
-// ESM
-import { convert } from 'html-to-markdown-wasm/dist-node';
+### With Options
+
+```typescript
+import { convert } from 'html-to-markdown-wasm';
 
-const html = '<h1>Hello</h1><p>World</p>';
 const markdown = convert(html, {
   headingStyle: 'atx',
   codeBlockStyle: 'backticks',
+  listIndentWidth: 2,
+  bullets: '-',
+  wrap: true,
+  wrapWidth: 80
 });
 ```
 
-### Deno
+### Preserve Complex HTML (NEW in v2.5)
 
 ```typescript
-import { convert } from "npm:html-to-markdown-wasm";
+import { convert } from 'html-to-markdown-wasm';
 
-const html = await Deno.readTextFile("input.html");
+const html = `
+<h1>Report</h1>
+<table>
+  <tr><th>Name</th><th>Value</th></tr>
+  <tr><td>Foo</td><td>Bar</td></tr>
+</table>
+`;
 
 const markdown = convert(html, {
-  headingStyle: "atx",
-  listIndentWidth: 2,
-  bullets: "-"
+  preserveTags: ['table'] // Keep tables as HTML
 });
-
-await Deno.writeTextFile("output.md", markdown);
 ```
 
-### Bun
+### Deno
 
 ```typescript
-import { convert } from 'html-to-markdown-wasm';
+import { convert } from "npm:html-to-markdown-wasm";
 
-const markdown = convert('<h1>Fast conversion</h1>', {
-  headingStyle: 'atx',
-  wrap: true,
-  wrapWidth: 80
-});
+const html = await Deno.readTextFile("input.html");
+const markdown = convert(html, { headingStyle: "atx" });
+await Deno.writeTextFile("output.md", markdown);
 ```
 
-> **Note:** For Bun, consider using [html-to-markdown-node](https://www.npmjs.com/package/html-to-markdown-node) for ~3× better performance with native bindings.
+> **Performance Tip:** For Node.js/Bun, use [html-to-markdown-node](https://www.npmjs.com/package/html-to-markdown-node) for 1.17× better performance with native bindings.
 
 ### Browser (ESM)
 
@@ -248,12 +255,45 @@ See the [TypeScript definitions](./dist-node/html_to_markdown_wasm.d.ts) for all
 - Code block styles (indented, backticks, tildes)
 - List formatting (indent width, bullet characters)
 - Text escaping and formatting
+- Tag preservation (`preserveTags`) and stripping (`stripTags`)
 - Preprocessing for web scraping
 - hOCR table extraction
 - And more...
 
 ## Examples
 
+### Preserving HTML Tags
+
+Keep specific HTML tags in their original form:
+
+```typescript
+import { convert } from '@html-to-markdown/wasm';
+
+const html = `
+<p>Before table</p>
+<table class="data">
+    <tr><th>Name</th><th>Value</th></tr>
+    <tr><td>Item 1</td><td>100</td></tr>
+</table>
+<p>After table</p>
+`;
+
+const markdown = convert(html, {
+  preserveTags: ['table']
+});
+
+// Result includes the table as HTML
+```
+
+Combine with `stripTags`:
+
+```typescript
+const markdown = convert(html, {
+  preserveTags: ['table', 'form'],  // Keep as HTML
+  stripTags: ['script', 'style']    // Remove entirely
+});
+```
+
 ### Deno Web Server
 
 ```typescript

package/dist/README.md

@@ -9,6 +9,24 @@ High-performance HTML → Markdown conversion powered by Rust. Shipping as a Rus
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://github.com/Goldziher/html-to-markdown/blob/main/LICENSE)
 [![Discord](https://img.shields.io/badge/Discord-Join%20our%20community-7289da)](https://discord.gg/pXxagNK2zN)
 
+---
+
+## 🎮 **[Try the Live Demo →](https://goldziher.github.io/html-to-markdown/)**
+
+Experience WebAssembly-powered HTML to Markdown conversion instantly in your browser. No installation needed!
+
+---
+
+## Why html-to-markdown?
+
+- **Blazing Fast**: Rust-powered core delivers 10-80× faster conversion than pure Python alternatives
+- **Universal**: Works everywhere - Node.js, Bun, Deno, browsers, Python, Rust, and standalone CLI
+- **Smart Conversion**: Handles complex documents including nested tables, code blocks, task lists, and hOCR OCR output
+- **Highly Configurable**: Control heading styles, code block fences, list formatting, whitespace handling, and HTML sanitization
+- **Tag Preservation**: Keep specific HTML tags unconverted when markdown isn't expressive enough
+- **Secure by Default**: Built-in HTML sanitization prevents malicious content
+- **Consistent Output**: Identical markdown rendering across all language bindings
+
 ## Documentation
 
 - **JavaScript/TypeScript guides**:
@@ -46,6 +64,7 @@ const markdown = convert(html, {
   headingStyle: 'Atx',
   codeBlockStyle: 'Backticks',
   wrap: true,
+  preserveTags: ['table'], // NEW in v2.5: Keep complex HTML as-is
 });
 ```
 

package/dist/package.json

@@ -4,7 +4,7 @@
   "collaborators": [
     "Na'aman Hirschfeld <nhirschfeld@gmail.com>"
   ],
-  "version": "2.4.1",
+  "version": "2.5.0",
   "license": "MIT",
   "repository": {
     "type": "git",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "html-to-markdown-wasm",
-  "version": "2.4.1",
+  "version": "2.5.0",
   "description": "High-performance HTML to Markdown converter - WebAssembly bindings",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",