feat(sandbox): implement TX sandboxing PE-3974

Implements the arweave.net feature that prepends a base32 encoded ID to
the hostname when serving TXs. The feature is enabled if ARNS_ROOT_HOST
is set. The protocol (https or http) in the redirect URLs can be
overriden using SANDBOX_PROTOCOL.

docker-compose.yaml

@@ -44,3 +44,5 @@ services:
       - ADMIN_API_KEY=${ADMIN_API_KEY:-}
       - ANS104_UNBUNDLE_FILTER=${ANS104_UNBUNDLE_FILTER:-}
       - ANS104_DATA_INDEX_FILTER=${ANS104_DATA_INDEX_FILTER:-}
+      - ARNS_ROOT_HOST=${ARNS_ROOT_HOST:-}
+      - SANDBOX_PROTOCOL=${SANDBOX_PROTOCOL:-}

package.json

@@ -29,6 +29,7 @@
     "prom-client": "^14.0.1",
     "ramda": "^0.28.0",
     "retry-axios": "^3.0.0",
+    "rfc4648": "^1.5.2",
     "sql-bricks": "^3.0.0",
     "sql-bricks-sqlite": "^0.1.0",
     "stream-chain": "^2.2.5",

src/app.ts

@@ -26,6 +26,7 @@ import YAML from 'yaml';
 import * as config from './config.js';
 import log from './log.js';
 import { createArnsMiddleware } from './middleware/arns.js';
+import { createSandboxMiddleware } from './middleware/sandbox.js';
 import {
   DATA_PATH_REGEX,
   RAW_DATA_PATH_REGEX,
@@ -80,6 +81,13 @@ app.use(
   }),
 );
 
+app.use(
+  createSandboxMiddleware({
+    rootHost: config.ARNS_ROOT_HOST,
+    sandboxProtocol: config.SANDBOX_PROTOCOL,
+  }),
+);
+
 // OpenAPI Spec
 const openapiDocument = YAML.parse(
   fs.readFileSync('docs/openapi.yaml', 'utf8'),

src/config.ts

@@ -55,3 +55,5 @@ export const ANS104_UNBUNDLE_FILTER = createFilter(
 export const ANS104_DATA_INDEX_FILTER = createFilter(
   JSON.parse(env.varOrDefault('ANS104_DATA_INDEX_FILTER', '{"never": true}')),
 );
+export const ARNS_ROOT_HOST = env.varOrUndefined('ARNS_ROOT_HOST');
+export const SANDBOX_PROTOCOL = env.varOrUndefined('SANDBOX_PROTOCOL');

src/middleware/sandbox.ts

@@ -0,0 +1,72 @@
+/**
+ * AR.IO Gateway
+ * Copyright (C) 2022 - 2023 Permanent Data Solutions, Inc
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Affero General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+import { Handler, Request } from 'express';
+import url from 'node:url';
+import { base32 } from 'rfc4648';
+
+import { fromB64Url } from '../lib/encoding.js';
+
+function getRequestSandbox(req: Request): string | undefined {
+  if (req.subdomains.length === 1) {
+    return req.subdomains[0];
+  }
+  return undefined;
+}
+
+function getRequestId(req: Request): string | undefined {
+  return (req.path.match(/^\/([a-zA-Z0-9-_]{43})/) ?? [])[1];
+}
+
+function sandboxFromId(id: string): string {
+  return base32.stringify(fromB64Url(id), { pad: false }).toLowerCase();
+}
+
+export function createSandboxMiddleware({
+  rootHost,
+  sandboxProtocol,
+}: {
+  rootHost?: string;
+  sandboxProtocol?: string;
+}): Handler {
+  return (req, res, next) => {
+    if (rootHost === undefined) {
+      next();
+      return;
+    }
+
+    const id = getRequestId(req);
+    if (id === undefined) {
+      next();
+      return;
+    }
+
+    const reqSandbox = getRequestSandbox(req);
+    const idSandbox = sandboxFromId(id);
+    if (reqSandbox !== idSandbox) {
+      const queryString = url.parse(req.originalUrl).query ?? '';
+      const path = req.path.replace(/\/\//, '/');
+      const protocol = sandboxProtocol ?? (req.secure ? 'https' : 'http');
+      return res.redirect(
+        302,
+        `${protocol}://${idSandbox}.${rootHost}${path}?${queryString}`,
+      );
+    }
+
+    next();
+  };
+}

yarn.lock

@@ -5275,6 +5275,11 @@ reusify@^1.0.4:
   resolved "https://registry.npmjs.org/reusify/-/reusify-1.0.4.tgz"
   integrity sha512-U9nH88a3fc/ekCF1l0/UP1IosiuIjyTh7hBvXVMHYgVcfGvt897Xguj2UOLDeI5BG2m7/uwyaLVT6fbtCwTyzw==
 
+rfc4648@^1.5.2:
+  version "1.5.2"
+  resolved "https://registry.yarnpkg.com/rfc4648/-/rfc4648-1.5.2.tgz#cf5dac417dd83e7f4debf52e3797a723c1373383"
+  integrity sha512-tLOizhR6YGovrEBLatX1sdcuhoSCXddw3mqNVAcKxGJ+J0hFeJ+SjeWCv5UPA/WU3YzWPPuCVYgXBKZUPGpKtg==
+
 rimraf@^2.6.1, rimraf@^2.6.3:
   version "2.7.1"
   resolved "https://registry.yarnpkg.com/rimraf/-/rimraf-2.7.1.tgz#35797f13a7fdadc566142c29d4f07ccad483e3ec"