app.py

from fastapi import FastAPI, File, UploadFile, HTTPException
from fastapi.middleware.cors import CORSMiddleware
from fastapi.responses import JSONResponse
import pdfplumber
from io import BytesIO
import base64
import uvicorn
import logging

# Set up logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

app = FastAPI()

# Add CORS middleware
app.add_middleware(
    CORSMiddleware,
    allow_origins=["*"],
    allow_credentials=True,
    allow_methods=["*"],
    allow_headers=["*"],
)

# Root route
@app.get("/")
async def root():
    return {"message": "PDF to Figma API"}

@app.post("/api/convert")
async def convert_pdf(file: UploadFile = File(...)):
    try:
        logger.info("Received file: %s", file.filename)

        # Read the uploaded file
        contents = await file.read()
        if not contents:
            logger.error("Empty file uploaded")
            raise HTTPException(status_code=400, detail="Empty file uploaded")

        # Parse PDF with pdfplumber
        with pdfplumber.open(BytesIO(contents)) as pdf:
            if not pdf.pages:
                logger.error("No pages found in PDF")
                raise HTTPException(status_code=400, detail="No pages found in PDF")
            
            page = pdf.pages[0]  # First page
            width, height = page.width, page.height
            logger.info("Processing PDF page: width=%s, height=%s", width, height)

            # Initialize result
            result = {
                "width": width,
                "height": height,
                "texts": [],
                "images": [],
                "shapes": []
            }

            # Extract text
            for char in page.chars:
                result["texts"].append({
                    "content": char["text"],
                    "x": char["x0"],
                    "y": char["y0"],
                    "font_family": char["fontname"].split("+")[-1] or "Arial",
                    "font_style": "Regular",
                    "font_size": char["size"],
                    "color": {"r": 0, "g": 0, "b": 0}
                })

            # Extract images
            for img in page.images:
                try:
                    img_data = img["stream"].get_data()
                    result["images"].append({
                        "data": list(img_data),
                        "x": img["x0"],
                        "y": img["y0"],
                        "width": img["width"],
                        "height": img["height"]
                    })
                except Exception as e:
                    logger.warning("Failed to extract image: %s", str(e))
                    continue

            # Extract shapes
            for curve in page.curves:
                try:
                    path = " ".join([f"M {p['x']},{p['y']}" for p in curve["points"]])
                    result["shapes"].append({
                        "path": path,
                        "x": curve["x0"],
                        "y": curve["y0"],
                        "color": {"r": 0, "g": 0, "b": 0}
                    })
                except Exception as e:
                    logger.warning("Failed to extract shape: %s", str(e))
                    continue

        logger.info("PDF processing complete")
        return JSONResponse(content=result)
    except Exception as e:
        logger.error("Failed to process PDF: %s", str(e))
        raise HTTPException(status_code=500, detail=f"Failed to process PDF: {str(e)}")
    finally:
        await file.close()

# Run uvicorn server
if __name__ == "__main__":
    uvicorn.run(app, host="0.0.0.0", port=7860)