chore: generate codemirror languages from linguist-languages package (#38624)

Replace the previous main-branch fetch with data from npm package
[`linguist-languages`](https://github.com/ikatyang-collab/linguist-languages)
and only run generate targets when actually needed. The removed
`fileFilters` were leftovers from the nolyfill removal.

assets/codemirror-languages.json

@@ -453,7 +453,6 @@
       ".htmlhintrc",
       ".imgbotconfig",
       ".nycrc",
-      ".secrets.baseline",
       ".tern-config",
       ".tern-project",
       ".watchmanconfig",

package.json

@@ -98,6 +98,7 @@
     "globals": "17.7.0",
     "happy-dom": "20.10.6",
     "jiti": "2.7.0",
+    "linguist-languages": "9.4.0",
     "markdownlint-cli": "0.49.1",
     "material-icon-theme": "5.36.1",
     "postcss-html": "1.8.1",

pnpm-lock.yaml

@@ -276,6 +276,9 @@ importers:
       jiti:
         specifier: 2.7.0
         version: 2.7.0
+      linguist-languages:
+        specifier: 9.4.0
+        version: 9.4.0
       markdownlint-cli:
         specifier: 0.49.1
         version: 0.49.1
@@ -3190,6 +3193,9 @@ packages:
   lines-and-columns@1.2.4:
     resolution: {integrity: sha512-7ylylesZQ/PV29jhEDl3Ufjo6ZX7gCqJr5F7PKrqc93v7fzSymt1BpwEU8nAUXs8qzzvqhbjhK5QZg6Mt/HkBg==}
 
+  linguist-languages@9.4.0:
+    resolution: {integrity: sha512-mYnFVrsWg5Bex0Kl5EDcXhrjXZ5DqMlBDXo7EUWLMTLDpxbuHvgBb2aOvGWC5ZmMJ2HXEKJiuFie9NEs8NUMXg==}
+
   linkify-it@5.0.2:
     resolution: {integrity: sha512-ONTm2jCMAVZjgQa/Fy1kScXsuOoF5NPTsoFBdE1KVIZ2vAh/r9+Bqo+0jINCBYnavTPQZz38QzFTme79ENoN3Q==}
 
@@ -7653,6 +7659,8 @@ snapshots:
 
   lines-and-columns@1.2.4: {}
 
+  linguist-languages@9.4.0: {}
+
   linkify-it@5.0.2:
     dependencies:
       uc.micro: 2.1.0

renovate.json5

@@ -114,17 +114,22 @@
     {
       "matchManagers": ["npm"],
       "postUpdateOptions": ["pnpmDedupe"],
+    },
+    {
+      "matchPackageNames": ["@primer/octicons", "material-icon-theme", "svgo"],
       "postUpgradeTasks": {
-        "commands": ["make svg", "make generate-codemirror-languages"],
+        "commands": ["make svg"],
         "fileFilters": [
-          "package.json",
-          "pnpm-lock.yaml",
-          "pnpm-workspace.yaml",
           "public/assets/img/svg/**",
           "options/fileicon/**",
-          "assets/codemirror-languages.json",
         ],
-        "executionMode": "branch",
+      },
+    },
+    {
+      "matchPackageNames": ["@codemirror/language-data", "linguist-languages"],
+      "postUpgradeTasks": {
+        "commands": ["make generate-codemirror-languages"],
+        "fileFilters": ["assets/codemirror-languages.json"],
       },
     },
   ],

tools/generate-codemirror-languages.ts

@@ -1,9 +1,8 @@
 #!/usr/bin/env node
-import {load as parseYaml} from 'js-yaml';
 import {writeFile} from 'node:fs/promises';
 import {languages as cmLanguages} from '@codemirror/language-data';
-
+import * as linguist from 'linguist-languages';
-const linguistUrl = 'https://raw.githubusercontent.com/github-linguist/linguist/main/lib/linguist/languages.yml';
+import type {Language} from 'linguist-languages';
 
 const renames: Record<string, string> = {
   'Protocol Buffer': 'ProtoBuf',
@@ -35,22 +34,12 @@ const extraExtensions: Record<string, string[]> = {
   'Properties files': ['conf'],
 };
 
-type LinguistEntry = {
-  type: string;
-  extensions?: string[];
-  filenames?: string[];
-};
-
 type CmLanguage = {
   name: string;
   extensions: string[];
   filenames: string[];
 };
 
-const res = await fetch(linguistUrl);
-if (!res.ok) throw new Error(`fetch ${linguistUrl} failed: ${res.status}`);
-const linguist = parseYaml(await res.text()) as Record<string, LinguistEntry>;
-
 const cmByAlias = new Map<string, string>();
 // Map of extension -> the CM language that originally owns it. Used to prevent Linguist
 // from broadening one language's extension claim into another's territory (e.g. Linguist's
@@ -66,7 +55,7 @@ for (const lang of cmLanguages) {
 
 const out: CmLanguage[] = [];
 const seen = new Set<string>();
-for (const [linguistName, entry] of Object.entries(linguist)) {
+for (const [linguistName, entry] of Object.entries(linguist as Record<string, Language>)) {
   const cmName = renames[linguistName] ?? cmByAlias.get(linguistName.toLowerCase());
   // Multiple Linguist entries can alias to the same CM language (e.g. JSON5 → JSON).
   if (!cmName || skipNames.has(cmName) || seen.has(cmName)) continue;