almeira-web/import_pendientes.js

const fs = require('fs');
const path = require('path');
const { Client, Databases, ID } = require('node-appwrite');
require('dotenv').config({ path: '.env.local' });
const pdfParse = require('pdf-parse');
const mammoth = require('mammoth');

const client = new Client()
    .setEndpoint(process.env.NEXT_PUBLIC_APPWRITE_ENDPOINT)
    .setProject(process.env.NEXT_PUBLIC_APPWRITE_PROJECT_ID)
    .setKey(process.env.APPWRITE_API_KEY);

const databases = new Databases(client);
const dbId = process.env.APPWRITE_DATABASE_ID;
const collectionId = 'posts';
const defaultTipoPublicacionId = '69c2b91400362d5d52b6'; // ID de NOTICIA obtenido anteriormente

const DIR_PENDIENTES = '/home/carlos/Documentos/Pendientes';
const DIR_PROCESADOS = path.join(DIR_PENDIENTES, 'Procesados');

if (!fs.existsSync(DIR_PROCESADOS)) {
    fs.mkdirSync(DIR_PROCESADOS);
}

function generateSlug(titulo) {
    return titulo
        .toLowerCase()
        .normalize('NFD')
        .replace(/[\u0300-\u036f]/g, '') 
        .replace(/[^a-z0-9\s-]/g, '')    
        .trim()
        .replace(/\s+/g, '-')            
        .replace(/-+/g, '-')             
        .substring(0, 100);              
}

function formatContent(text) {
    const paragraphs = text.split(/\n+/);
    const html = paragraphs
        .map(p => p.trim())
        .filter(p => p.length > 0)
        .map(p => `<p>${p}</p>`)
        .join('');
    return html;
}

function extractSummary(text) {
    const paragraphs = text.split(/\n+/).map(p => p.trim()).filter(p => p.length > 30);
    if (paragraphs.length > 0) {
        return paragraphs[0].substring(0, 200) + (paragraphs[0].length > 200 ? '...' : '');
    }
    return '';
}

function determineTipo(filename) {
    const lower = filename.toLowerCase();
    if (lower.includes('evento')) return 'evento';
    if (lower.includes('aviso')) return 'aviso';
    if (lower.includes('comunicado')) return 'comunicado';
    if (lower.includes('galeria')) return 'galeria';
    return 'noticia';
}

function formatTitle(filename) {
    let base = path.basename(filename, path.extname(filename)).replace(/\(1\)/g, '').trim();
    // Capitalize first letter of each word to look better
    return base.split(' ').map(word => word.charAt(0).toUpperCase() + word.slice(1).toLowerCase()).join(' ');
}

function extractDate(filename, text) {
    const months = {
        'enero': 0, 'febrero': 1, 'marzo': 2, 'abril': 3, 'mayo': 4, 'junio': 5,
        'julio': 6, 'agosto': 7, 'septiembre': 8, 'octubre': 9, 'noviembre': 10, 'diciembre': 11
    };
    
    // Attempt 1: From filename e.g. "28 DE MARZO DEL 2026"
    const regex = /(\d{1,2})\s+DE\s+([A-Z]+)\s+(DEL?|DE)\s+(\d{4})/i;
    let match = filename.match(regex);
    if (!match) {
        // Attempt 2: From the first few lines of text
        const firstLines = text.split('\n').slice(0, 10).join(' ');
        match = firstLines.match(regex);
    }
    
    if (match) {
        const day = parseInt(match[1], 10);
        const monthStr = match[2].toLowerCase();
        const year = parseInt(match[4], 10);
        
        if (months[monthStr] !== undefined) {
            const date = new Date(year, months[monthStr], day, 12, 0, 0); // Noon to avoid timezone issues
            return date.toISOString();
        }
    }
    
    return new Date().toISOString(); // fallback
}

async function processFile(filePath, filename) {
    const ext = path.extname(filename).toLowerCase();
    let text = '';
    
    try {
        if (ext === '.pdf') {
            const { execSync } = require('child_process');
            text = execSync(`pdftotext "${filePath}" -`).toString();
        } else if (ext === '.docx') {
            const result = await mammoth.extractRawText({ path: filePath });
            text = result.value;
        } else if (ext === '.txt') {
            text = fs.readFileSync(filePath, 'utf8');
        } else {
            console.log(`Skipping unsupported file: ${filename}`);
            return false;
        }

        if (!text || text.trim().length === 0) {
            console.log(`File empty or failed to extract: ${filename}`);
            return false;
        }

        const titulo = formatTitle(filename);
        const slug = generateSlug(titulo) + '-' + Math.random().toString(36).substring(2, 7);
        const contenido = formatContent(text);
        const tipo = determineTipo(filename);
        const resumen_redes = extractSummary(text);

        const docData = {
            titulo,
            slug,
            contenido,
            resumen_redes,
            estado: 'publicado',
            tipo_publicacion_id: defaultTipoPublicacionId,
            fecha_publicacion: extractDate(filename, text),
        };

        await databases.createDocument(dbId, collectionId, ID.unique(), docData);
        console.log(`✅ Publicado: ${titulo}`);
        
        // Mover a procesados
        fs.renameSync(filePath, path.join(DIR_PROCESADOS, filename));
        return true;
    } catch (error) {
        console.error(`❌ Error procesando ${filename}:`, error.message);
        return false;
    }
}

async function main() {
    const files = fs.readdirSync(DIR_PENDIENTES);
    let successCount = 0;
    
    for (const file of files) {
        const filePath = path.join(DIR_PENDIENTES, file);
        if (fs.statSync(filePath).isFile()) {
            console.log(`Procesando ${file}...`);
            const ok = await processFile(filePath, file);
            if (ok) successCount++;
        }
    }
    
    console.log(`\nImportación finalizada. ${successCount} publicaciones procesadas correctamente.`);
}

main();