web/app/api/parse-upload/route.ts

import { NextRequest, NextResponse } from "next/server";
import { createClient } from "@/lib/supabase/server";

export const runtime = "nodejs";

// Add a 5MB size limit
const MAX_FILE_SIZE = 5 * 1024 * 1024;

export async function POST(req: NextRequest) {
  try {
    const supabase = await createClient();
    const { data: { user } } = await supabase.auth.getUser();

    if (!user) {
      return NextResponse.json({ error: "Unauthorized. Please log in." }, { status: 401 });
    }

    const formData = await req.formData();
    const file = formData.get("file") as File | null;

    if (!file) {
      return NextResponse.json({ error: "No file uploaded" }, { status: 400 });
    }

    if (file.size > MAX_FILE_SIZE) {
      return NextResponse.json({ error: "File exceeds 5MB size limit" }, { status: 400 });
    }

    const name = file.name.toLowerCase();
    const buffer = Buffer.from(await file.arrayBuffer());
    let text = "";

    if (name.endsWith(".txt") || name.endsWith(".md")) {
      text = new TextDecoder().decode(buffer);
    } else if (name.endsWith(".pdf")) {
      // FIX v4.3: pdf-parse API compatible with both v1 and v2
      // Try the standard pdf-parse import (works with v1.x which is more common)
      try {
        const pdfParse = (await import("pdf-parse")).default;
        const result = await pdfParse(buffer);
        text = result.text;
      } catch {
        // If pdf-parse fails, try sending to Gradio Space for OCR
        return NextResponse.json({
          error: "PDF parsing failed. Please copy-paste the text directly, or use the Gradio Space which has OCR support."
        }, { status: 400 });
      }
    } else if (name.endsWith(".docx")) {
      const mammoth = (await import("mammoth")).default;
      const result = await mammoth.extractRawText({ buffer });
      text = result.value;
    } else {
      return NextResponse.json({ error: "Unsupported file type. Use .pdf, .docx, .txt, or .md" }, { status: 400 });
    }

    if (!text || text.trim().length < 30) {
      return NextResponse.json({ error: "Could not extract enough text from this file." }, { status: 400 });
    }

    return NextResponse.json({ text: text.trim(), filename: file.name, size: file.size });
  } catch (error: any) {
    console.error("File parse error:", error);
    return NextResponse.json({ error: "Failed to parse file: " + (error.message || "Unknown error") }, { status: 500 });
  }
}