gh-proxy/index.js

'use strict'

/**
 * static files (404.html, sw.js, conf.js)
 */
const ASSET_URL = 'https://hunshcn.github.io/gh-proxy/'
// 前缀，如果自定义路由为example.com/gh/*，将PREFIX改为 '/gh/'，注意，少一个杠都会错！
const PREFIX = '/'
// 分支文件使用jsDelivr镜像的开关，0为关闭，默认关闭
const Config = {
    jsdelivr: 0
}

const whiteList = [] // 白名单，路径里面有包含字符的才会通过，e.g. ['/username/']

/** @type {ResponseInit} */
const PREFLIGHT_INIT = {
    status: 204,
    headers: new Headers({
        'access-control-allow-origin': '*',
        'access-control-allow-methods': 'GET,POST,PUT,PATCH,TRACE,DELETE,HEAD,OPTIONS',
        'access-control-max-age': '1728000',
    }),
}


const exp1 = /^(?:https?:\/\/)?github\.com\/.+?\/.+?\/(?:releases|archive)\/.*$/i
const exp2 = /^(?:https?:\/\/)?github\.com\/.+?\/.+?\/(?:blob|raw)\/.*$/i
const exp3 = /^(?:https?:\/\/)?github\.com\/.+?\/.+?\/(?:info|git-).*$/i
const exp4 = /^(?:https?:\/\/)?raw\.(?:githubusercontent|github)\.com\/.+?\/.+?\/.+?\/.+$/i
const exp5 = /^(?:https?:\/\/)?gist\.(?:githubusercontent|github)\.com\/.+?\/.+?\/.+$/i
const exp6 = /^(?:https?:\/\/)?github\.com\/.+?\/.+?\/tags.*$/i

/**
 * @param {any} body
 * @param {number} status
 * @param {Object<string, string>} headers
 */
function makeRes(body, status = 200, headers = {}) {
    headers['access-control-allow-origin'] = '*'
    return new Response(body, { status, headers })
}


/**
 * @param {string} urlStr
 */
function newUrl(urlStr) {
    try {
        return new URL(urlStr)
    } catch (err) {
        return null
    }
}


// comment out function call `addEventListener` for AWS Lambda usage
addEventListener('fetch', e => {
    const ret = fetchHandler(e)
        .catch(err => makeRes('cfworker error:\n' + err.stack, 502))
    e.respondWith(ret)
})


function checkUrl(u) {
    for (let i of [exp1, exp2, exp3, exp4, exp5, exp6]) {
        if (u.search(i) === 0) {
            return true
        }
    }
    return false
}

// entry <= Cloudflare Worker
/**
 * @param {FetchEvent} e
 */
async function fetchHandler(e) {
    const req = e.request
    const urlStr = req.url
    const urlObj = new URL(urlStr)
    let path = urlObj.searchParams.get('q')
    if (path) {
        return Response.redirect('https://' + urlObj.host + PREFIX + path, 301)
    }
    // cfworker 会把路径中的 `//` 合并成 `/`
    path = urlObj.href.slice(urlObj.origin.length + PREFIX.length).replace(/^https?:\/+/, 'https://')
    if (path.search(exp1) === 0 || path.search(exp5) === 0 || path.search(exp6) === 0 || path.search(exp3) === 0) {
        return httpHandler(req, path)
    } else if (path.search(exp2) === 0) {
        if (Config.jsdelivr) {
            const newUrl = path.replace('/blob/', '@').replace(/^(?:https?:\/\/)?github\.com/, 'https://cdn.jsdelivr.net/gh')
            return Response.redirect(newUrl, 302)
        } else {
            path = path.replace('/blob/', '/raw/')
            return httpHandler(req, path)
        }
    } else if (path.search(exp4) === 0) {
        if (Config.jsdelivr) {
            const newUrl = path.replace(/(?<=com\/.+?\/.+?)\/(.+?\/)/, '@$1').replace(/^(?:https?:\/\/)?raw\.(?:githubusercontent|github)\.com/, 'https://cdn.jsdelivr.net/gh')
            return Response.redirect(newUrl, 302)
        }
        else {
            return httpHandler(req, path)
        }
    } else {
        return fetch(ASSET_URL + path)
    }
}


/**
 * @param {Request} req
 * @param {string} pathname
 */
function httpHandler(req, pathname) {
    const reqHdrRaw = req.headers

    // preflight
    if (req.method === 'OPTIONS' &&
        reqHdrRaw.has('access-control-request-headers')
    ) {
        return new Response(null, PREFLIGHT_INIT)
    }

    const reqHdrNew = new Headers(reqHdrRaw)

    let urlStr = pathname
    let flag = !Boolean(whiteList.length)
    for (let i of whiteList) {
        if (urlStr.includes(i)) {
            flag = true
            break
        }
    }
    if (!flag) {
        return new Response("blocked", { status: 403 })
    }
    if (urlStr.search(/^https?:\/\//) !== 0) {
        urlStr = 'https://' + urlStr
    }
    const urlObj = newUrl(urlStr)

    /** @type {RequestInit} */
    const reqInit = {
        method: req.method,
        headers: reqHdrNew,
        redirect: 'manual',
        body: req.body
    }
    return proxy(urlObj, reqInit)
}


/**
 *
 * @param {URL} urlObj
 * @param {RequestInit} reqInit
 */
async function proxy(urlObj, reqInit) {
    const res = await fetch(urlObj.href, reqInit)
    const resHdrOld = res.headers
    const resHdrNew = new Headers(resHdrOld)

    const status = res.status

    if (resHdrNew.has('location')) {
        let _location = resHdrNew.get('location')
        if (checkUrl(_location))
            resHdrNew.set('location', PREFIX + _location)
        else {
            reqInit.redirect = 'follow'
            return proxy(newUrl(_location), reqInit)
        }
    }
    resHdrNew.set('access-control-expose-headers', '*')
    resHdrNew.set('access-control-allow-origin', '*')

    resHdrNew.delete('content-security-policy')
    resHdrNew.delete('content-security-policy-report-only')
    resHdrNew.delete('clear-site-data')

    return new Response(res.body, {
        status,
        headers: resHdrNew,
    })
}

// entry <= AWS Lambda
export const handler = async (event) => {
    const response = await fetchHandler(fromCloudFrontRequest(event.Records[0].cf.request));
    return toCloudFrontResponse(response, event.Records[0].cf.response);
};

const fromCloudFrontRequest = (cloudFrontRequest) => {
    // viewer request event:
    // https://docs.aws.amazon.com/AmazonCloudFront/latest/DeveloperGuide/lambda-event-structure.html
    const cfReq = cloudFrontRequest;
    const headers = {};
    Object.keys(cfReq.headers).map((lowerKey) => {
        cfReq.headers[lowerKey].map(({ key, value }) => {
            headers[key] = value;
        });
    });
    const event = {
        request: new Request(`https://${cfReq.headers.host[0].value}${cfReq.uri}?${cfReq.querystring}`, {
            method: cfReq.method,
            headers,
            body: (cfReq.body && cfReq.body.data)? Buffer.from(cfReq.body.data, cfReq.body.encoding) : undefined,
        }),
    }
    return event;
};

const toCloudFrontResponse = async (response) => {
    // viewer request event:
    // https://docs.aws.amazon.com/AmazonCloudFront/latest/DeveloperGuide/lambda-generating-http-responses.html
    const res = response;
    const cfRes = {};
    // status
    cfRes.status = res.status;
    cfRes.statusDescription = res.statusText;
    // headers
    res.headers.forEach((value, key) => {
        if (!cfRes.headers) { cfRes.headers = {}; }
        const lowerKey = key.toLowerCase();
        if (isBlackListedHeader(lowerKey)) { return }
        cfRes.headers[lowerKey] = [{ key, value }];
    });
    // body
    if (res.body) {
        cfRes.body = Buffer.from(await res.arrayBuffer()).toString('base64');
        cfRes.bodyEncoding = 'base64';
    }
    return cfRes;
};

const isBlackListedHeader = (lowerKey) => {
    // viewer request event:
    // https://docs.aws.amazon.com/AmazonCloudFront/latest/DeveloperGuide/edge-function-restrictions-all.html
    return /^x-amz-cf-/.test(lowerKey) || /^x-amz-cf-/.test(lowerKey) || [
        // disallowed headers
        'connection',
        'expect',
        'keep-alive',
        'proxy-authenticate',
        'proxy-authorization',
        'proxy-connection',
        'trailer',
        'upgrade',
        'x-accel-buffering',
        'x-accel-charset',
        'x-accel-limit-rate',
        'x-accel-redirect',
        'x-amzn-auth',
        'x-amzn-cf-billing',
        'x-amzn-cf-id',
        'x-amzn-cf-xff',
        'x-amzn-errortype',
        'x-amzn-fle-profile',
        'x-amzn-header-count',
        'x-amzn-header-order',
        'x-amzn-lambda-integration-tag',
        'x-amzn-requestid',
        'x-cache',
        'x-forwarded-proto',
        'x-real-ip',
        // read-only headers in viewer request events
        'content-length',
        'host',
        'transfer-encoding',
        'via',
        // let aws decide how to compress
        'content-encoding',
    ].includes(lowerKey);
};