const express = require('express');
const fs = require('fs');
const path = require('path');
const router = express.Router();

const pdf = require('pdf-parse');
const mammoth = require("mammoth");


// POST /loader 路由
router.post('/loader', async (req, res) => {
    let url = req.body?.url; // 从请求体中获取 URL

    console.log(req.body)
    console.log(req.query)
    if (!url) {
        return res.status(400).json({ error: 'No URL provided' });
    }

    try {
        // 使用 fetch 获取 PDF 文件
        const response = await fetch(url);

        if (!response.ok) {
            throw new Error(`Failed to fetch: ${response.statusText}`);
        }

        const arrayBuffer = await response.arrayBuffer();
        const buffer = Buffer.from(arrayBuffer); // 将 ArrayBuffer 转换为 Buffer
        // console.log(buffer)

        let type,data
        if(url?.endsWith(".pdf")){
            type = "pdf"
            data = await pdf(buffer);
        }
        if(url?.endsWith(".docx")){
            type = "docx"
            let text = await mammoth.extractRawText(buffer)
            // let html = mammoth.convertToHtml(buffer)
            data = text?.value || "";
        }

        // 返回解析后的数据
        res.json({
            code:200,
            type:type,
            data:data,
        });
    } catch (error) {
        // 处理错误
        res.status(500).json({ error: 'Failed to parse File', details: error.message });
    }
});

module.exports = router;