Native Rust module for Adblock Plus syntax (e.g. EasyList, EasyPrivacy) filter parsing and matching.
It uses a tokenisation approach for quickly reducing the potentially matching rule search space against a URL.
The algorithm is inspired by, and closely follows the algorithm of uBlock Origin and Cliqz.
Somewhat graphical explanation of the algorithm:
Demo use in Rust:
```rust use adblock::engine::Engine; use adblock::lists::{FilterFormat, FilterSet};
fn main() { let rules = vec![ String::from("-advertisement-icon."), String::from("-advertisement-management/"), String::from("-advertisement."), String::from("-advertisement/script."), ];
let mut filter_set = FilterSet::new(true);
filter_set.add_filters(&rules, FilterFormat::Standard);
let blocker = Engine::from_filter_set(&filter_set, true);
let blocker_result = blocker.check_network_urls("http://example.com/-advertisement-icon.", "http://example.com/helloworld", "image");
println!("Blocker result: {:?}", blocker_result);
}
```
Note the Node.js module has overheads inherent to boundary crossing between JS and native code.
```js const AdBlockClient = require('adblock-rs'); let elrules = fs.readFileSync('./data/easylist.to/easylist/easylist.txt', { encoding: 'utf-8' }).split('\n'); let ubounbreakrules = fs.readFileSync('./data/uBlockOrigin/unbreak.txt', { encoding: 'utf-8' }).split('\n'); let rules = elrules.concat(ubounbreakrules); let resources = AdBlockClient.uBlockResources('uBlockOrigin/src/webaccessibleresources', 'uBlockOrigin/src/js/redirect-engine.js', 'uBlockOrigin/assets/resources/scriptlets.js');
const filterSet = new AdBlockClient.FilterSet(true); filterSet.addFilters(rules); const client = new AdBlockClient.Engine(filterSet, true); client.updateResources(resources);
const serializedArrayBuffer = client.serialize(); // Serialize the engine to an ArrayBuffer
console.log(Engine size: ${(serializedArrayBuffer.byteLength / 1024 / 1024).toFixed(2)} MB);
console.log("Matching:", client.check("http://example.com/-advertisement-icon.", "http://example.com/helloworld", "image")) // Match with full debuging info console.log("Matching:", client.check("http://example.com/-advertisement-icon.", "http://example.com/helloworld", "image", true)) // No, but still with debugging info console.log("Matching:", client.check("https://github.githubassets.com/assets/frameworks-64831a3d.js", "https://github.com/AndriusA", "script", true)) // Example that inlcludes a redirect response console.log("Matching:", client.check("https://bbci.co.uk/test/analytics.js", "https://bbc.co.uk", "script", true)) ```