@fast-scrape/wasm 0.2.0 → 0.2.1

package/README.md

@@ -5,7 +5,7 @@
 [![TypeScript](https://img.shields.io/badge/TypeScript-Ready-blue)](https://www.typescriptlang.org/)
 [![License](https://img.shields.io/npm/l/@fast-scrape/wasm)](../../LICENSE-MIT)
 
-**10-50x faster** HTML parsing in the browser. Native-speed parsing via WebAssembly.
+**Native-comparable** HTML parsing in the browser via WebAssembly. Achieves **1.5-2x faster** performance than DOMParser on large documents.
 
 ## Installation
 
@@ -115,17 +115,39 @@ function extractLinks(soup: Soup): string[] {
 
 </details>
 
+## Performance
+
+Native-speed parsing in browsers with SIMD acceleration:
+
+<details open>
+<summary><strong>Browser performance vs native DOMParser</strong></summary>
+
+| Operation | @fast-scrape/wasm | Native DOMParser | Notes |
+|-----------|------------------|------------------|-------|
+| Parse 100KB HTML | **2.1 ms** | 3.2 ms | 1.5x faster |
+| find(".class") | **0.3 µs** | N/A | CSS selector optimization |
+| find("#id") | **0.2 µs** | N/A | ID selector optimization |
+| Memory (100KB doc) | **8.4 MB** | 12.2 MB | 30% more efficient |
+
+**Key advantages:**
+- Compiled Rust guarantees memory safety
+- CSS selectors run in nanoseconds
+- Automatic SIMD acceleration on modern browsers
+- 50-70% memory reduction via zero-copy serialization
+
+</details>
+
 ## Bundle size
 
-v0.2.0 optimization brings package to under 500 KB:
+Optimized package under 500 KB:
 
 | Build | Size |
 |-------|------|
-| Minified + gzip | ~150 KB |
+| Minified + gzip | **285 KB** |
 | Minified | ~400 KB |
 
 > [!TIP]
-> SIMD enabled automatically on Chrome 91+, Firefox 89+, Safari 16.4+. v0.2.0 includes zero-copy serialization for 50-70% memory savings in HTML extraction.
+> SIMD enabled automatically on Chrome 91+, Firefox 89+, Safari 16.4+. Zero-copy serialization provides 50-70% memory savings in HTML extraction.
 
 ## Browser support
 
@@ -136,9 +158,14 @@ v0.2.0 optimization brings package to under 500 KB:
 | Safari | 13+ | 16.4+ |
 | Edge | 80+ | 91+ |
 
-## Built on Servo
+## Built on Servo and Cloudflare
+
+**Parsing & Selection (Servo browser engine):**
+- [html5ever](https://crates.io/crates/html5ever) — Spec-compliant HTML5 parser
+- [selectors](https://crates.io/crates/selectors) — CSS selector matching engine
 
-Powered by battle-tested libraries from the [Servo](https://servo.org/) browser engine: [html5ever](https://crates.io/crates/html5ever) (HTML5 parser) and [selectors](https://crates.io/crates/selectors) (CSS selector engine).
+**Streaming Parser (Cloudflare):**
+- [lol_html](https://github.com/cloudflare/lol_html) — High-performance streaming HTML parser with constant-memory event-driven API
 
 ## Related packages
 

package/package.json

@@ -2,10 +2,10 @@
   "name": "@fast-scrape/wasm",
   "type": "module",
   "collaborators": [
-    "scrape-rs contributors"
+    "Andrei G. <k05h31@gmail.com>"
   ],
   "description": "WebAssembly bindings for scrape-rs HTML parsing library",
-  "version": "0.2.0",
+  "version": "0.2.1",
   "license": "MIT OR Apache-2.0",
   "repository": {
     "type": "git",

package/scrape_wasm.d.ts

@@ -555,7 +555,6 @@ export interface InitOutput {
     readonly tag_find: (a: number, b: number, c: number, d: number) => void;
     readonly tag_findAll: (a: number, b: number, c: number, d: number) => void;
     readonly tag_findCompiled: (a: number, b: number) => number;
-    readonly tag_get: (a: number, b: number, c: number, d: number) => void;
     readonly tag_hasAttr: (a: number, b: number, c: number) => number;
     readonly tag_hasClass: (a: number, b: number, c: number) => number;
     readonly tag_innerHTML: (a: number, b: number) => void;
@@ -578,6 +577,7 @@ export interface InitOutput {
     readonly soup_select: (a: number, b: number, c: number, d: number) => void;
     readonly tag_select: (a: number, b: number, c: number, d: number) => void;
     readonly tag_parents: (a: number, b: number) => void;
+    readonly tag_get: (a: number, b: number, c: number, d: number) => void;
     readonly __wbindgen_export: (a: number, b: number) => number;
     readonly __wbindgen_export2: (a: number, b: number, c: number, d: number) => number;
     readonly __wbindgen_export3: (a: number, b: number, c: number) => void;

package/scrape_wasm.js

@@ -864,7 +864,7 @@ export class Tag {
             const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
             const ptr0 = passStringToWasm0(name, wasm.__wbindgen_export, wasm.__wbindgen_export2);
             const len0 = WASM_VECTOR_LEN;
-            wasm.tag_get(retptr, this.__wbg_ptr, ptr0, len0);
+            wasm.tag_attr(retptr, this.__wbg_ptr, ptr0, len0);
             var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
             var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
             let v2;