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

// Read the input file from public
const inputFile = path.join(__dirname, 'public', 'llms-cat.txt');
// Write the output file to dist
const outputFile = path.join(__dirname, 'dist', 'llms-cat.txt');

// Function to parse a CSV line with escaped quotes
function parseCSVLine(line) {
    const fields = [];
    let current = '';
    let inQuotes = false;
    let i = 0;

    while (i < line.length) {
        const char = line[i];

        if (char === '"') {
            // Check if this is an escaped quote
            if (i + 1 < line.length && line[i + 1] === '"') {
                current += '"'; // Add single quote (unescaped)
                i += 2; // Skip both quotes
                continue;
            } else {
                inQuotes = !inQuotes; // Toggle quote state
            }
        } else if (char === ',' && !inQuotes) {
            fields.push(current);
            current = '';
        } else {
            current += char;
        }
        i++;
    }

    fields.push(current); // Add the last field
    return fields;
}

try {
    if (!fs.existsSync(inputFile)) {
        throw new Error(`Input file not found: ${inputFile}`);
    }

    const data = fs.readFileSync(inputFile, 'utf8');
    const lines = data.trim().split('\n');

    // Keep the header as intended: URL and Description
    const outputLines = ['URL of product list for article numbers,SEO Description'];

    let skippedLines = 0;
    let processedLines = 0;

    for (let i = 0; i < lines.length; i++) {
        const line = lines[i];
        if (line.trim() === '') continue;

        // Skip comment lines or lines not starting with a number/quote (simple heuristic for header/comments)
        // The file starts with text "this file has..." and then header "categoryId..."
        // Actual data lines start with "
        if (!line.trim().startsWith('"')) {
            continue;
        }

        // Parse the CSV line properly handling escaped quotes
        const fields = parseCSVLine(line);

        if (fields.length !== 3) {
            console.warn(`Skipping malformed line ${i + 1} (got ${fields.length} fields): ${line.substring(0, 50)}...`);
            skippedLines++;
            continue;
        }

        // Input: categoryId, listFileName, seoDescription
        // Output: URL, SEO Description
        const [categoryId, listFileName, seoDescription] = fields;

        // Use listFileName as URL
        const url = listFileName;

        // Use seoDescription as description directly (it's already a string)
        const description = seoDescription;

        // Escape quotes for CSV output
        const escapedDescription = '"' + description.replace(/"/g, '""') + '"';

        outputLines.push(`${url},${escapedDescription}`);
        processedLines++;
    }

    // Ensure dist directory exists
    const distDir = path.dirname(outputFile);
    if (!fs.existsSync(distDir)) {
        fs.mkdirSync(distDir, { recursive: true });
    }

    // Write the output CSV
    fs.writeFileSync(outputFile, outputLines.join('\n'), 'utf8');
    console.log(`Processed ${processedLines} lines (skipped ${skippedLines}) and created ${outputFile}`);

} catch (error) {
    console.error('Error processing file:', error.message);
    process.exit(1);
}