Make changes to check for broken links

.github/workflows/check.yaml

@@ -0,0 +1,36 @@
+name: Check links
+
+on:
+  # when someone makes a change directly to main branch
+  push:
+    branches:
+      - main
+  # when someone requests a change to main branch
+  pull_request:
+    branches:
+      - main
+
+  # run periodically
+  schedule:
+    - cron: "0 0 * * *"
+  # run manually
+  workflow_dispatch:
+
+jobs:
+  check:
+    runs-on: ubuntu-latest
+    steps:
+      - if: runner.debug == '1'
+        uses: mxschmitt/action-tmate@v3
+
+      - name: Get this repo's code
+        uses: actions/checkout@v4
+
+      - name: Set up Bun
+        uses: oven-sh/setup-bun@v1
+
+      - name: Install packages
+        run: bun install glob@v9 yaml@v2
+
+      - name: Run check script
+        run: bun ./check.js

.github/workflows/deploy.yaml

@@ -15,25 +15,30 @@ env:
 
 jobs:
   encode:
-    name: Encode and deploy
     runs-on: ubuntu-latest
     steps:
+      - if: runner.debug == '1'
+        uses: mxschmitt/action-tmate@v3
+
       - name: Get this repo's code
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
         with:
           path: redirects-repo # save in separate sub-folder
 
       - name: Get website repo's code
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
         with:
           repository: ${{ github.repository_owner }}/${{ env.website_repo }} # assume same user/org
           path: website-repo # save in separate sub-folder
 
+      - name: Set up Bun
+        uses: oven-sh/setup-bun@v1
+
       - name: Install packages
-        run: npm install glob@v9 yaml@v2
+        run: bun install glob@v9 yaml@v2
 
       - name: Run encode script
-        run: node ./redirects-repo/encode.js
+        run: bun ./redirects-repo/encode.js
 
       - name: Commit result to website repo
         if: ${{ github.event_name == 'push' }}

check.js

@@ -0,0 +1,20 @@
+import { addError, list } from "./core";
+
+// for each redirect
+await Promise.all(
+  list.map(async ({ to }) => {
+    try {
+      // do simple request to target url
+      const response = await fetch(to);
+      if (
+        // only fail on certain status codes that might indicate link is "broken"
+        [
+          400, 404, 405, 406, 408, 409, 410, 421, 500, 501, 502, 503, 504,
+        ].includes(response.status)
+      )
+        throw Error(response.status);
+    } catch (error) {
+      addError(`"to: ${to}" may be a broken link\n(${error})`);
+    }
+  })
+);

core.js

@@ -0,0 +1,118 @@
+import { readFileSync } from "fs";
+import { resolve } from "path";
+import { globSync } from "glob";
+import { parse } from "yaml";
+
+// collect (caught) errors to report at end
+const errors = [];
+
+// if running in github actions debug mode, do extra logging
+export const verbose = !!process.env.RUNNER_DEBUG;
+
+// get yaml files that match glob pattern
+const files = globSync("*.y?(a)ml", { cwd: __dirname });
+
+log("Files", files.join(" "));
+
+// start combined list of redirects
+export const list = [];
+
+// keep track of duplicate entries
+const duplicates = {};
+
+// go through each yaml file
+for (const file of files) {
+  // load file contents
+  const contents = readFileSync(resolve(__dirname, file), "utf8");
+
+  // try to parse as yaml
+  let data;
+  try {
+    data = parse(contents);
+  } catch (error) {
+    addError(`Couldn't parse ${file}. Make sure it is valid YAML.`);
+    continue;
+  }
+
+  // check if top level is list
+  if (!Array.isArray(data)) {
+    addError(`${file} is not a list`);
+    continue;
+  }
+
+  // go through each entry
+  for (let [index, entry] of Object.entries(data)) {
+    index = Number(index) + 1;
+    const trace = `${file} entry ${index}`;
+
+    // check if dict
+    if (typeof entry !== "object") {
+      addError(`${trace} is not a dict`);
+      continue;
+    }
+
+    // check "from" field
+    if (!(typeof entry.from === "string" && entry.from.trim())) {
+      addError(`${trace} "from" field invalid`);
+      continue;
+    }
+
+    // check "to" field
+    if (!(typeof entry.to === "string" && entry.to.trim()))
+      addError(`${trace} "to" field invalid`);
+
+    // normalize "from" field. lower case, remove leading slashes.
+    entry.from = entry.from.toLowerCase().replace(/^(\/+)/, "");
+
+    // add to combined list
+    list.push(entry);
+
+    // add to duplicate list. record source file and entry number for logging.
+    duplicates[entry.from] ??= [];
+    duplicates[entry.from].push({ ...entry, file, index });
+  }
+}
+
+// check that any redirects exist
+if (!list.length) addError("No redirects");
+
+if (verbose) log("Combined redirects list", list);
+
+// trigger errors for duplicates
+for (const [from, entries] of Object.entries(duplicates)) {
+  const count = entries.length;
+  if (count <= 1) continue;
+  const duplicates = entries
+    .map(({ file, index }) => `\n    ${file} entry ${index}`)
+    .join("");
+  addError(`"from: ${from}" appears ${count} time(s): ${duplicates}`);
+}
+
+// add error
+export function addError(error) {
+  errors.push(error);
+}
+
+// when script finished
+process.on("exit", () => {
+  // report all errors together
+  if (errors.length) {
+    process.exitCode = 1;
+    errors.forEach(logError);
+    logError(`${errors.length} error(s)`);
+  } else {
+    process.exitCode = 0;
+    log("No errors!");
+  }
+});
+
+// formatted normal log
+export function log(message, data) {
+  console.info("\x1b[1m\x1b[96m" + message + "\x1b[0m");
+  if (data) console.log(data);
+}
+
+// formatted error log
+export function logError(message) {
+  console.error("\x1b[1m\x1b[91m" + message + "\x1b[0m");
+}

encode.js

@@ -1,98 +1,5 @@
-const { readFileSync, writeFileSync } = require("fs");
-const { resolve } = require("path");
-const { globSync } = require("glob");
-const { parse } = require("yaml");
-
-// collect (caught) errors to report at end
-const errors = [];
-
-// report errors on exit
-process.on("exit", () => {
-  errors.forEach(error);
-  if (errors.length) error(`${errors.length} error(s)`);
-});
-
-// if running in github actions debug mode, do extra logging
-const verbose = !!process.env.RUNNER_DEBUG;
-
-// get yaml files that match glob pattern
-const files = globSync("*.y?(a)ml", { cwd: __dirname });
-
-log("Files", files.join(" "));
-
-// start combined list of redirects
-const list = [];
-
-// keep track of duplicate entries
-const duplicates = {};
-
-// go through each yaml file
-for (const file of files) {
-  // load file contents
-  const contents = readFileSync(resolve(__dirname, file), "utf8");
-
-  // try to parse as yaml
-  let data;
-  try {
-    data = parse(contents);
-  } catch (error) {
-    errors.push(`Couldn't parse ${file}. Make sure it is valid YAML.`);
-    continue;
-  }
-
-  // check if top level is list
-  if (!Array.isArray(data)) {
-    errors.push(`${file} is not a list`);
-    continue;
-  }
-
-  // go through each entry
-  for (let [index, entry] of Object.entries(data)) {
-    index = Number(index) + 1;
-    const trace = `${file} entry ${index}`;
-
-    // check if dict
-    if (typeof entry !== "object") {
-      errors.push(`${trace} is not a dict`);
-      continue;
-    }
-
-    // check "from" field
-    if (!(typeof entry.from === "string" && entry.from.trim())) {
-      errors.push(`${trace} "from" field invalid`);
-      continue;
-    }
-
-    // check "to" field
-    if (!(typeof entry.to === "string" && entry.to.trim()))
-      errors.push(`${trace} "to" field invalid`);
-
-    // normalize "from" field. lower case, remove leading slashes.
-    entry.from = entry.from.toLowerCase().replace(/^(\/+)/, "");
-
-    // add to combined list
-    list.push(entry);
-
-    // add to duplicate list. record source file and entry number for logging.
-    duplicates[entry.from] ??= [];
-    duplicates[entry.from].push({ ...entry, file, index });
-  }
-}
-
-// check that any redirects exist
-if (!list.length) errors.push("No redirects");
-
-if (verbose) log("Combined redirects list", list);
-
-// trigger errors for duplicates
-for (const [from, entries] of Object.entries(duplicates)) {
-  const count = entries.length;
-  if (count <= 1) continue;
-  const duplicates = entries
-    .map(({ file, index }) => `\n    ${file} entry ${index}`)
-    .join("");
-  errors.push(`"from: ${from}" appears ${count} time(s): ${duplicates}`);
-}
+import { readFileSync, writeFileSync } from "fs";
+import { addError, list, verbose } from "./core";
 
 // encode redirect list to base64 to obfuscate
 const encoded = Buffer.from(JSON.stringify(list)).toString("base64");
@@ -103,7 +10,12 @@ if (verbose) log("Encoded redirects list", encoded);
 const script = "./website-repo/redirect.js";
 
 // load contents of script
-const contents = readFileSync(script, "utf8").toString();
+let contents = "";
+try {
+  contents = readFileSync(script, "utf8").toString();
+} catch (error) {
+  addError(`Couldn't find script file at ${script}`);
+}
 
 // pattern to extract encoded redirect list from script string
 const regex = /(list\s*=\s*")([A-Za-z0-9+\/=]*)(")/;
@@ -115,22 +27,14 @@ if (verbose) log("Old encoded redirects list", oldEncoded);
 
 // check that we could find it (and thus can replace it)
 if (typeof oldEncoded !== "string")
-  errors.push("Couldn't find encoded redirects list in redirect script");
+  addError("Couldn't find encoded redirects list in redirect script");
 
 // update encoded string in script
 const newContents = contents.replace(regex, "$1" + encoded + "$3");
 
 // write updated redirect script to website repo
-writeFileSync(script, newContents, "utf-8");
-
-// exit if collected errors
-if (errors.length) process.exit(1);
-
-// debug util
-function log(message, data) {
-  console.info("\033[1m\033[96m" + message + "\033[0m");
-  console.log(data);
-}
-function error(message) {
-  console.error("\033[1m\033[91m" + message + "\033[0m");
+try {
+  writeFileSync(script, newContents, "utf-8");
+} catch (error) {
+  addError(`Couldn't write script file to ${script}`);
 }