Create some code

.editorconfig

@@ -0,0 +1,12 @@
+# http://editorconfig.org
+root = true
+
+[*]
+indent_style = tab
+end_of_line = lf
+charset = utf-8
+trim_trailing_whitespace = true
+insert_final_newline = true
+
+[*.yml]
+indent_style = space

.gitignore

@@ -0,0 +1,172 @@
+# Logs
+
+logs
+_.log
+npm-debug.log_
+yarn-debug.log*
+yarn-error.log*
+lerna-debug.log*
+.pnpm-debug.log*
+
+# Diagnostic reports (https://nodejs.org/api/report.html)
+
+report.[0-9]_.[0-9]_.[0-9]_.[0-9]_.json
+
+# Runtime data
+
+pids
+_.pid
+_.seed
+\*.pid.lock
+
+# Directory for instrumented libs generated by jscoverage/JSCover
+
+lib-cov
+
+# Coverage directory used by tools like istanbul
+
+coverage
+\*.lcov
+
+# nyc test coverage
+
+.nyc_output
+
+# Grunt intermediate storage (https://gruntjs.com/creating-plugins#storing-task-files)
+
+.grunt
+
+# Bower dependency directory (https://bower.io/)
+
+bower_components
+
+# node-waf configuration
+
+.lock-wscript
+
+# Compiled binary addons (https://nodejs.org/api/addons.html)
+
+build/Release
+
+# Dependency directories
+
+node_modules/
+jspm_packages/
+
+# Snowpack dependency directory (https://snowpack.dev/)
+
+web_modules/
+
+# TypeScript cache
+
+\*.tsbuildinfo
+
+# Optional npm cache directory
+
+.npm
+
+# Optional eslint cache
+
+.eslintcache
+
+# Optional stylelint cache
+
+.stylelintcache
+
+# Microbundle cache
+
+.rpt2_cache/
+.rts2_cache_cjs/
+.rts2_cache_es/
+.rts2_cache_umd/
+
+# Optional REPL history
+
+.node_repl_history
+
+# Output of 'npm pack'
+
+\*.tgz
+
+# Yarn Integrity file
+
+.yarn-integrity
+
+# dotenv environment variable files
+
+.env
+.env.development.local
+.env.test.local
+.env.production.local
+.env.local
+
+# parcel-bundler cache (https://parceljs.org/)
+
+.cache
+.parcel-cache
+
+# Next.js build output
+
+.next
+out
+
+# Nuxt.js build / generate output
+
+.nuxt
+dist
+
+# Gatsby files
+
+.cache/
+
+# Comment in the public line in if your project uses Gatsby and not Next.js
+
+# https://nextjs.org/blog/next-9-1#public-directory-support
+
+# public
+
+# vuepress build output
+
+.vuepress/dist
+
+# vuepress v2.x temp and cache directory
+
+.temp
+.cache
+
+# Docusaurus cache and generated files
+
+.docusaurus
+
+# Serverless directories
+
+.serverless/
+
+# FuseBox cache
+
+.fusebox/
+
+# DynamoDB Local files
+
+.dynamodb/
+
+# TernJS port file
+
+.tern-port
+
+# Stores VSCode versions used for testing VSCode extensions
+
+.vscode-test
+
+# yarn v2
+
+.yarn/cache
+.yarn/unplugged
+.yarn/build-state.yml
+.yarn/install-state.gz
+.pnp.\*
+
+# wrangler project
+
+.dev.vars
+.wrangler/

.prettierrc

@@ -0,0 +1,6 @@
+{
+	"printWidth": 140,
+	"singleQuote": true,
+	"semi": true,
+	"useTabs": true
+}

index.html

@@ -0,0 +1,132 @@
+<!DOCTYPE html>
+<html lang="en">
+	<head>
+		<meta charset="UTF-8" />
+		<meta name="viewport" content="width=device-width, initial-scale=1.0" />
+		<title>Xget - Fast File Download Proxy</title>
+		<style>
+			body {
+				font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, Oxygen, Ubuntu, Cantarell, sans-serif;
+				line-height: 1.6;
+				max-width: 800px;
+				margin: 0 auto;
+				padding: 20px;
+				color: #333;
+			}
+
+			h1 {
+				color: #2563eb;
+				text-align: center;
+				margin-bottom: 40px;
+			}
+
+			.platform-box {
+				background: #f8fafc;
+				border: 1px solid #e2e8f0;
+				border-radius: 8px;
+				padding: 20px;
+				margin-bottom: 20px;
+			}
+
+			code {
+				background: #e2e8f0;
+				padding: 2px 6px;
+				border-radius: 4px;
+				font-family: 'Courier New', Courier, monospace;
+			}
+
+			.example {
+				background: #334155;
+				color: #fff;
+				padding: 15px;
+				border-radius: 8px;
+				overflow-x: auto;
+			}
+
+			.features {
+				display: grid;
+				grid-template-columns: repeat(auto-fit, minmax(250px, 1fr));
+				gap: 20px;
+				margin: 30px 0;
+			}
+
+			.feature-card {
+				background: #fff;
+				border: 1px solid #e2e8f0;
+				border-radius: 8px;
+				padding: 20px;
+			}
+
+			.feature-card h3 {
+				color: #2563eb;
+				margin-top: 0;
+			}
+		</style>
+	</head>
+	<body>
+		<h1>🚀 Xget</h1>
+
+		<p>
+			Xget is a fast and reliable file download proxy service powered by Cloudflare Workers. It provides accelerated access to files from
+			various platforms including GitHub, GitLab, HuggingFace, and Kaggle.
+		</p>
+
+		<div class="features">
+			<div class="feature-card">
+				<h3>⚡ Fast</h3>
+				<p>Powered by Cloudflare's global network for optimal performance</p>
+			</div>
+			<div class="feature-card">
+				<h3>🛡️ Secure</h3>
+				<p>Built-in security headers and file type filtering</p>
+			</div>
+			<div class="feature-card">
+				<h3>🔄 Cached</h3>
+				<p>Automatic caching for faster repeated access</p>
+			</div>
+		</div>
+
+		<h2>How to Use</h2>
+		<p>Simply prefix your file URL with our service URL and the appropriate platform identifier:</p>
+
+		<div class="platform-box">
+			<h3>Supported Platforms:</h3>
+			<ul>
+				<li><code>/gh/</code> - GitHub Raw Content</li>
+				<li><code>/gl/</code> - GitLab Files</li>
+				<li><code>/hf/</code> - HuggingFace Files</li>
+				<li><code>/kg/</code> - Kaggle Datasets</li>
+				<li><code>/url/</code> - Direct URLs</li>
+			</ul>
+		</div>
+
+		<h2>Examples</h2>
+
+		<h3>GitHub Example:</h3>
+		<div class="example">
+			<code>https://your-worker.workers.dev/gh/username/repo/branch/path/to/file</code>
+		</div>
+
+		<h3>GitLab Example:</h3>
+		<div class="example">
+			<code>https://your-worker.workers.dev/gl/username/repo/-/blob/branch/path/to/file</code>
+		</div>
+
+		<h3>Direct URL Example:</h3>
+		<div class="example">
+			<code>https://your-worker.workers.dev/url/https://example.com/file.zip</code>
+		</div>
+
+		<h2>Limitations</h2>
+		<ul>
+			<li>Maximum path length: 2048 characters</li>
+			<li>Supported HTTP methods: GET, HEAD</li>
+			<li>Blocked file types: .php, .exe, .dll, .bat, .cmd, .sh</li>
+			<li>Cache duration: 24 hours</li>
+		</ul>
+
+		<footer style="text-align: center; margin-top: 40px; padding: 20px; border-top: 1px solid #e2e8f0">
+			<p>Powered by Cloudflare Workers</p>
+		</footer>
+	</body>
+</html>

package.json

@@ -0,0 +1,16 @@
+{
+	"name": "xget",
+	"version": "0.0.0",
+	"private": true,
+	"scripts": {
+		"deploy": "wrangler deploy",
+		"dev": "wrangler dev",
+		"start": "wrangler dev",
+		"test": "vitest"
+	},
+	"devDependencies": {
+		"@cloudflare/vitest-pool-workers": "^0.5.2",
+		"wrangler": "^3.60.3",
+		"vitest": "2.0.5"
+	}
+}

src/config/index.js

@@ -0,0 +1,32 @@
+import { PLATFORMS } from './platforms';
+
+/**
+ * @typedef {Object} SecurityConfig
+ * @property {string[]} ALLOWED_METHODS - List of allowed HTTP methods
+ * @property {string[]} ALLOWED_ORIGINS - List of allowed CORS origins
+ * @property {number} MAX_PATH_LENGTH - Maximum allowed URL path length
+ */
+
+/**
+ * @typedef {Object} ApplicationConfig
+ * @property {number} TIMEOUT_SECONDS - Request timeout in seconds
+ * @property {number} MAX_RETRIES - Maximum number of retry attempts
+ * @property {number} RETRY_DELAY_MS - Delay between retries in milliseconds
+ * @property {number} CACHE_DURATION - Cache duration in seconds
+ * @property {SecurityConfig} SECURITY - Security-related configurations
+ * @property {Object} PLATFORMS - Platform-specific configurations
+ */
+
+/** @type {ApplicationConfig} */
+export const CONFIG = {
+	TIMEOUT_SECONDS: 30,
+	MAX_RETRIES: 3,
+	RETRY_DELAY_MS: 1000,
+	CACHE_DURATION: 1800, // 30 minutes
+	SECURITY: {
+		ALLOWED_METHODS: ['GET', 'HEAD'],
+		ALLOWED_ORIGINS: ['*'],
+		MAX_PATH_LENGTH: 2048,
+	},
+	PLATFORMS,
+};

src/config/platforms.js

@@ -0,0 +1,26 @@
+/**
+ * Configuration object for different platform URLs and path transformations
+ * @type {Object.<string, {base: string, transform: function(string): string}>}
+ */
+export const PLATFORMS = {
+	/** @type {{base: string, transform: function(string): string}} GitHub configuration */
+	gh: {
+		base: 'https://raw.githubusercontent.com',
+		transform: (path) => path.replace(/^\/gh\//, '/'),
+	},
+	/** @type {{base: string, transform: function(string): string}} GitLab configuration */
+	gl: {
+		base: 'https://gitlab.com',
+		transform: (path) => path.replace(/^\/gl\//, '/') + '/raw',
+	},
+	/** @type {{base: string, transform: function(string): string}} HuggingFace configuration */
+	hf: {
+		base: 'https://huggingface.co',
+		transform: (path) => path.replace(/^\/hf\//, '/'),
+	},
+	/** @type {{base: string, transform: function(string): string}} Kaggle configuration */
+	kg: {
+		base: 'https://www.kaggle.com',
+		transform: (path) => path.replace(/^\/kg\//, '/'),
+	},
+};

src/index.js

@@ -0,0 +1,242 @@
+import { CONFIG } from './config';
+
+/**
+ * Monitors performance metrics during request processing
+ */
+class PerformanceMonitor {
+	/**
+	 * Initializes a new performance monitor
+	 */
+	constructor() {
+		this.startTime = Date.now();
+		this.marks = new Map();
+	}
+
+	/**
+	 * Marks a timing point with the given name
+	 * @param {string} name - The name of the timing mark
+	 */
+	mark(name) {
+		if (this.marks.has(name)) {
+			console.warn(`Mark with name ${name} already exists.`);
+		}
+		this.marks.set(name, Date.now() - this.startTime);
+	}
+
+	/**
+	 * Returns all collected metrics
+	 * @returns {Object.<string, number>} Object containing name-timestamp pairs
+	 */
+	getMetrics() {
+		return Object.fromEntries(this.marks.entries());
+	}
+}
+
+/**
+ * Validates incoming requests against security rules
+ * @param {Request} request - The incoming request object
+ * @param {URL} url - Parsed URL object
+ * @returns {{valid: boolean, error?: string, status?: number}} Validation result
+ */
+function validateRequest(request, url) {
+	if (!CONFIG.SECURITY.ALLOWED_METHODS.includes(request.method)) {
+		return { valid: false, error: 'Method not allowed', status: 405 };
+	}
+
+	if (url.pathname.length > CONFIG.SECURITY.MAX_PATH_LENGTH) {
+		return { valid: false, error: 'Path too long', status: 414 };
+	}
+
+	return { valid: true };
+}
+
+/**
+ * Adds security headers to the response
+ * @param {Headers} headers - Headers object to modify
+ * @returns {Headers} Modified headers object
+ */
+function addSecurityHeaders(headers) {
+	headers.set('Strict-Transport-Security', 'max-age=31536000; includeSubDomains; preload');
+	headers.set('X-Frame-Options', 'DENY');
+	headers.set('X-XSS-Protection', '1; mode=block');
+	headers.set('Referrer-Policy', 'strict-origin-when-cross-origin');
+	headers.set('Content-Security-Policy', "default-src 'none'; img-src 'self'; script-src 'none'");
+	headers.set('Permissions-Policy', 'interest-cohort=()');
+	return headers;
+}
+
+/**
+ * Handles incoming requests with caching, retries, and security measures
+ * @param {Request} request - The incoming request
+ * @param {Object} env - Environment variables
+ * @param {ExecutionContext} ctx - Cloudflare Workers execution context
+ * @returns {Promise<Response>} The response object
+ */
+async function handleRequest(request, env, ctx) {
+	try {
+		const url = new URL(request.url);
+
+		// Serve homepage for root path
+		if (url.pathname === '/' || url.pathname === '') {
+			const headers = new Headers();
+			headers.set('Location', 'https://xget.us.kg');
+			addSecurityHeaders(headers);
+			return new Response(null, {
+				status: 301,
+				headers: headers,
+			});
+		}
+
+		const monitor = new PerformanceMonitor();
+
+		const validation = validateRequest(request, url);
+		if (!validation.valid) {
+			return new Response(validation.error, {
+				status: validation.status,
+				headers: addSecurityHeaders(new Headers()),
+			});
+		}
+
+		// Parse platform and path
+		const [_, platform, ...pathParts] = url.pathname.split('/');
+		if (!platform || !CONFIG.PLATFORMS[platform]) {
+			return new Response('Invalid or missing platform', {
+				status: 400,
+				headers: addSecurityHeaders(new Headers()),
+			});
+		}
+
+		// Transform URL based on platform
+		const targetPath = CONFIG.PLATFORMS[platform].transform(url.pathname);
+		const targetUrl = `${CONFIG.PLATFORMS[platform].base}${targetPath}`;
+
+		// Check cache first
+		const cache = caches.default;
+		const cacheKey = new Request(targetUrl, request);
+		let response = await cache.match(cacheKey);
+
+		if (response) {
+			monitor.mark('cache_hit');
+			return response;
+		}
+
+		const fetchOptions = {
+			cf: {
+				http3: true,
+				cacheTtl: CONFIG.CACHE_DURATION,
+				cacheEverything: true,
+				minify: {
+					javascript: true,
+					css: true,
+					html: true,
+				},
+				preconnect: true,
+			},
+			headers: {
+				'Accept-Encoding': 'gzip, deflate, br',
+				Connection: 'keep-alive',
+				'User-Agent': 'Wget/1.21.3',
+				Origin: request.headers.get('Origin') || '*',
+			},
+		};
+
+		// Handle range requests
+		const rangeHeader = request.headers.get('Range');
+		if (rangeHeader) {
+			fetchOptions.headers['Range'] = rangeHeader;
+		}
+
+		// Implement retry mechanism
+		let attempts = 0;
+		while (attempts < CONFIG.MAX_RETRIES) {
+			try {
+				monitor.mark('attempt_' + attempts);
+
+				// Fetch with timeout
+				const controller = new AbortController();
+				const timeoutId = setTimeout(() => controller.abort(), CONFIG.TIMEOUT_SECONDS * 1000);
+
+				response = await fetch(targetUrl, {
+					...fetchOptions,
+					signal: controller.signal,
+				});
+
+				clearTimeout(timeoutId);
+
+				if (response.ok || response.status === 206) {
+					monitor.mark('success');
+					break;
+				}
+
+				attempts++;
+				if (attempts < CONFIG.MAX_RETRIES) {
+					await new Promise((resolve) => setTimeout(resolve, CONFIG.RETRY_DELAY_MS * attempts));
+				}
+			} catch (error) {
+				attempts++;
+				if (error.name === 'AbortError') {
+					return new Response('Request timeout', { status: 408 });
+				}
+				if (attempts >= CONFIG.MAX_RETRIES) {
+					return new Response(`Failed after ${CONFIG.MAX_RETRIES} attempts: ${error.message}`, { status: 500 });
+				}
+			}
+		}
+
+		// Prepare response headers
+		const headers = new Headers(response.headers);
+		headers.set('Cache-Control', `public, max-age=${CONFIG.CACHE_DURATION}`);
+		headers.set('X-Content-Type-Options', 'nosniff');
+		headers.set('Accept-Ranges', 'bytes');
+		addSecurityHeaders(headers);
+
+		// Create final response
+		const finalResponse = new Response(response.body, {
+			status: response.status,
+			headers: headers,
+		});
+
+		// Cache successful responses
+		if (response.ok || response.status === 206) {
+			ctx.waitUntil(cache.put(cacheKey, finalResponse.clone()));
+		}
+
+		monitor.mark('complete');
+		return addPerformanceHeaders(finalResponse, monitor);
+	} catch (error) {
+		console.error('Error handling request:', error);
+		return new Response(`Internal Server Error: ${error.message}`, {
+			status: 500,
+			headers: addSecurityHeaders(new Headers()),
+		});
+	}
+}
+
+/**
+ * Adds performance metrics to response headers
+ * @param {Response} response - The response object
+ * @param {PerformanceMonitor} monitor - Performance monitor instance
+ * @returns {Response} New response with performance headers
+ */
+function addPerformanceHeaders(response, monitor) {
+	const headers = new Headers(response.headers);
+	headers.set('X-Performance-Metrics', JSON.stringify(monitor.getMetrics()));
+	addSecurityHeaders(headers);
+	return new Response(response.body, {
+		status: response.status,
+		headers: headers,
+	});
+}
+
+export default {
+	/**
+	 * Main entry point for the Cloudflare Worker
+	 * @param {Request} request - The incoming request
+	 * @param {Object} env - Environment variables
+	 * @param {ExecutionContext} ctx - Cloudflare Workers execution context
+	 * @returns {Promise<Response>} The response object
+	 */
+	fetch(request, env, ctx) {
+		return handleRequest(request, env, ctx);
+	},
+};

test/index.spec.js

@@ -0,0 +1,20 @@
+import { createExecutionContext, env, SELF, waitOnExecutionContext } from 'cloudflare:test';
+import { describe, expect, it } from 'vitest';
+import worker from '../src';
+
+describe('Hello World worker', () => {
+	it('responds with Hello World! (unit style)', async () => {
+		const request = new Request('http://example.com');
+		// Create an empty context to pass to `worker.fetch()`.
+		const ctx = createExecutionContext();
+		const response = await worker.fetch(request, env, ctx);
+		// Wait for all `Promise`s passed to `ctx.waitUntil()` to settle before running test assertions
+		await waitOnExecutionContext(ctx);
+		expect(await response.text()).toMatchInlineSnapshot(`"Hello World!"`);
+	});
+
+	it('responds with Hello World! (integration style)', async () => {
+		const response = await SELF.fetch(request, env, ctx);
+		expect(await response.text()).toMatchInlineSnapshot(`"Hello World!"`);
+	});
+});

vitest.config.js

@@ -0,0 +1,11 @@
+import { defineWorkersConfig } from '@cloudflare/vitest-pool-workers/config';
+
+export default defineWorkersConfig({
+	test: {
+		poolOptions: {
+			workers: {
+				wrangler: { configPath: './wrangler.toml' },
+			},
+		},
+	},
+});

wrangler.toml

@@ -0,0 +1,8 @@
+#:schema node_modules/wrangler/config-schema.json
+name = "xget"
+main = "src/index.js"
+compatibility_date = "2024-10-22"
+compatibility_flags = ["nodejs_compat"]
+[observability]
+enabled = true
+head_sampling_rate = 1