Auto generate cspell dictionary of github members

[thompson-tomo]

Having just made an attempt to migrate the spec repo to cspell from misspell one thing emerged was that I was often adding people's names to the dictionary.

It would be great if there was a single dictionary of all github member organisations which include their username, first name & last name.

Doing some searching I found the following script

/**
 * Generate a CSpell dictionary from GitHub members
 * 
 * Usage:
 *   1. Install dependencies: npm install node-fetch@2
 *   2. Run: node generate-cspell-dict.js <org_or_owner> [repo]
 *   3. Output: github-members.txt (CSpell dictionary file)
 * 
 * Notes:
 *   - If only <org_or_owner> is provided, fetches organization members.
 *   - If <repo> is provided, fetches repository collaborators.
 *   - Set GITHUB_TOKEN in environment for higher rate limits.
 */

const fs = require('fs');
const fetch = require('node-fetch');

const GITHUB_API = 'https://api.github.com';
const token = process.env.GITHUB_TOKEN || null;

// Validate CLI arguments
if (process.argv.length < 3) {
    console.error('Usage: node generate-cspell-dict.js <org_or_owner> [repo]');
    process.exit(1);
}

const owner = process.argv[2];
const repo = process.argv[3] || null;

// GitHub API request helper
async function githubRequest(url) {
    const headers = { 'User-Agent': 'cspell-dict-generator' };
    if (token) headers['Authorization'] = `token ${token}`;

    const res = await fetch(url, { headers });
    if (!res.ok) {
        throw new Error(`GitHub API error ${res.status}: ${res.statusText}`);
    }
    return res.json();
}

// Fetch members or collaborators
async function fetchMembers() {
    let url;
    if (repo) {
        url = `${GITHUB_API}/repos/${owner}/${repo}/collaborators?per_page=100`;
    } else {
        url = `${GITHUB_API}/orgs/${owner}/members?per_page=100`;
    }

    let members = [];
    let page = 1;
    while (true) {
        const data = await githubRequest(`${url}&page=${page}`);
        if (data.length === 0) break;
        members.push(...data.map(m => m.login));
        page++;
    }
    return [...new Set(members)]; // Remove duplicates
}

// Save dictionary file
function saveDictionary(words) {
    const filename = 'github-members.txt';
    fs.writeFileSync(filename, words.join('\n') + '\n', 'utf8');
    console.log(`✅ Dictionary saved to ${filename} with ${words.length} entries.`);
}

(async () => {
    try {
        const members = await fetchMembers();
        saveDictionary(members);
    } catch (err) {
        console.error('❌ Error:', err.message);
        process.exit(1);
    }
})();

Ideally this was executed periodically and if changes occur a bot would create a pr.

Note this would need to be manually synced out to the repos.