scripts/update_emoji_db.js

const https = require('https');
const fs = require('fs');
const path = require('path');

const url = 'https://www.unicode.org/Public/UCD/latest/emoji/emoji-test.txt';
const outputPath = path.join(__dirname, '../src/emoji_data.json');

console.log(`Downloading ${url}...`);

https.get(url, (res) => {
    let data = '';

    res.on('data', (chunk) => {
        data += chunk;
    });

    res.on('end', () => {
        console.log('Download complete. Parsing data...');
        const emojiData = parseEmojiData(data);
        fs.writeFileSync(outputPath, JSON.stringify(emojiData, null, 2));
        console.log(`Wrote ${Object.keys(emojiData).length} emojis to ${outputPath}`);
    });

}).on('error', (err) => {
    console.error('Error downloading file: ' + err.message);
    process.exit(1);
});

function parseEmojiData(text) {
    const lines = text.split('\n');
    const result = {};
    let currentGroup = '';
    let currentSubgroup = '';

    for (const line of lines) {
        // Skip empty lines
        if (!line.trim()) continue;

        // Parse Group
        if (line.startsWith('# group:')) {
            currentGroup = normalize(line.substring(8).trim());
            continue;
        }

        // Parse Subgroup
        if (line.startsWith('# subgroup:')) {
            currentSubgroup = normalize(line.substring(11).trim());
            continue;
        }

        // Skip comments that don't look like data (lines starting with #)
        if (line.startsWith('#')) continue;

        // Parse data line
        // Format: code_points ; status # emoji name
        // Example: 1F607 ; fully-qualified # 😇 E1.0 smiling face with halo
        const parts = line.split(';');
        if (parts.length < 2) continue;

        const statusPart = parts[1].split('#');
        const status = normalize(statusPart[0].trim()); // e.g., fully-qualified

        // The part after # contains: emoji char, version, name
        // Example: " 😇 E1.0 smiling face with halo"
        const commentPart = statusPart[1].trim(); 
        
        // We need to extract the actual emoji character(s) to use as key.
        // It's the first 'word' in the comment part usually. 
        // But extracting it from the code points is safer/standard.
        const codePoints = parts[0].trim().split(' ');
        const emojiKey = String.fromCodePoint(...codePoints.map(cp => parseInt(cp, 16)));

        // Extract Version and Name from the comment part
        // Format is: [Emoji] E[Version] [Name]
        // Example: 😇 E1.0 smiling face with halo
        const versionMatch = commentPart.match(/E(\d+\.\d+)/);
        let version = '';
        let name = '';

        if (versionMatch) {
            version = 'E' + versionMatch[1];
            // Name is everything after the version
            const nameIndex = commentPart.indexOf(version) + version.length;
            name = normalize(commentPart.substring(nameIndex).trim());
        } else {
             // Fallback if regex fails (shouldn't happen with standard file)
             console.warn(`Could not parse version for line: ${line}`);
        }

        result[emojiKey] = {
            g: currentGroup,
            s: currentSubgroup,
            q: status,
            v: version,
            n: name
        };
    }
    return result;
}

function normalize(str) {
    // Replace spaces with underscores and lowercase
    return str.toLowerCase().replace(/[ \-]+/g, '_');
}