file_conversion.py

from fastapi import APIRouter, UploadFile, File, HTTPException, BackgroundTasks, Response
from fastapi.responses import FileResponse
from pydantic import BaseModel
from pdf2docx import Converter
import os
import shutil
import pdfkit
import uuid

router = APIRouter()

TEMP_DIR = "/.tempfiles"

class HTMLRequest(BaseModel):
    html_content: str

def ensure_temp_dir():
    os.makedirs(TEMP_DIR, exist_ok=True)

def remove_file(path: str):
    if os.path.exists(path):
        os.unlink(path)

def generate_temp_filepath(extension: str) -> str:
    return os.path.join(TEMP_DIR, f"temp_{uuid.uuid4()}.{extension}")

def html_to_pdf(html_content: str, output_path: str) -> None:
    options = {
        'page-size': 'A4',
        'margin-top': '0.75in',
        'margin-right': '0.75in',
        'margin-bottom': '0.75in',
        'margin-left': '0.75in',
        'encoding': "UTF-8",
    }
    pdfkit.from_string(html_content, output_path, options=options)

def pdf_to_docx(pdf_path: str, docx_path: str) -> None:
    cv = Converter(pdf_path)
    cv.convert(docx_path)
    cv.close()

def handle_conversion(convert_func, input_path: str, output_path: str, background_tasks: BackgroundTasks):
    try:
        convert_func(input_path, output_path)
        if not os.path.exists(output_path):
            raise FileNotFoundError(f"Converted file not found: {output_path}")
        background_tasks.add_task(remove_file, input_path)
        background_tasks.add_task(remove_file, output_path)
        return FileResponse(
            output_path,
            media_type='application/vnd.openxmlformats-officedocument.wordprocessingml.document',
            filename=f"converted_document_{uuid.uuid4()}.docx"
        )
    except Exception as e:
        remove_file(input_path)
        remove_file(output_path)
        raise HTTPException(status_code=500, detail=f"Conversion failed: {str(e)}")

@router.post("/convert/pdf_to_docx")
async def convert_pdf_to_docx(background_tasks: BackgroundTasks, file: UploadFile = File(...)):
    if not file.filename.endswith('.pdf'):
        raise HTTPException(status_code=400, detail="File must be a PDF")
    
    ensure_temp_dir()
    pdf_temp_path = generate_temp_filepath("pdf")
    docx_temp_path = pdf_temp_path.replace('.pdf', '.docx')
    
    with open(pdf_temp_path, "wb") as pdf_file:
        shutil.copyfileobj(file.file, pdf_file)
    
    return handle_conversion(pdf_to_docx, pdf_temp_path, docx_temp_path, background_tasks)

@router.post("/convert/html_to_pdf")
async def convert_html_to_pdf(request: HTMLRequest):
    ensure_temp_dir()
    pdf_temp_path = generate_temp_filepath("pdf")
    
    try:
        html_to_pdf(request.html_content, pdf_temp_path)
        with open(pdf_temp_path, "rb") as pdf_file:
            pdf_content = pdf_file.read()
        remove_file(pdf_temp_path)
        return Response(content=pdf_content, media_type="application/pdf")
    except Exception as e:
        remove_file(pdf_temp_path)
        raise HTTPException(status_code=500, detail=str(e))

@router.post("/convert/html_to_docx")
async def convert_html_to_docx(background_tasks: BackgroundTasks, request: HTMLRequest):
    ensure_temp_dir()
    pdf_temp_path = generate_temp_filepath("pdf")
    docx_temp_path = pdf_temp_path.replace('.pdf', '.docx')
    
    try:
        html_to_pdf(request.html_content, pdf_temp_path)
        return handle_conversion(pdf_to_docx, pdf_temp_path, docx_temp_path, background_tasks)
    except Exception as e:
        remove_file(pdf_temp_path)
        remove_file(docx_temp_path)
        raise HTTPException(status_code=500, detail=f"Conversion failed: {str(e)}")