"""PaddleOCR Remote Service — PP-OCRv5 Latin auf x86_64."""

import io
import logging
import os

import numpy as np
from fastapi import FastAPI, File, Header, HTTPException, UploadFile
from PIL import Image

logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

app = FastAPI(title="PaddleOCR Service")

_engine = None
_ready = False
API_KEY = os.environ.get("PADDLEOCR_API_KEY", "")


def get_engine():
    global _engine
    if _engine is None:
        logger.info("Importing paddleocr...")
        from paddleocr import PaddleOCR

        logger.info("Import done. Loading PaddleOCR model...")
        # PaddleOCR >= 3.x: lang="en" + PP-OCRv5; older: lang="latin"
        try:
            _engine = PaddleOCR(
                lang="en",
                ocr_version="PP-OCRv5",
                use_angle_cls=True,
                show_log=False,
            )
            logger.info("Using PP-OCRv5 (en)")
        except Exception as e:
            logger.info(f"PP-OCRv5 failed ({e}), trying latin fallback...")
            _engine = PaddleOCR(
                lang="latin",
                use_angle_cls=True,
                show_log=False,
            )
            logger.info("Using PP-OCRv4 fallback (latin)")
        logger.info("PaddleOCR model loaded successfully")
    return _engine


@app.on_event("startup")
def startup_load_model():
    """Pre-load model at startup so health check passes."""
    global _ready
    try:
        get_engine()
        _ready = True
        logger.info("PaddleOCR ready to serve requests")
    except Exception as e:
        logger.error(f"Failed to load PaddleOCR model: {e}")


@app.get("/health")
def health():
    if _ready:
        return {"status": "ok", "model": "PP-OCRv5-latin"}
    return {"status": "loading"}


@app.post("/ocr")
async def ocr(
    file: UploadFile = File(...),
    x_api_key: str = Header(default=""),
):
    if API_KEY and x_api_key != API_KEY:
        raise HTTPException(status_code=401, detail="Invalid API key")

    if not _ready:
        raise HTTPException(status_code=503, detail="Model still loading")

    img_bytes = await file.read()
    img = Image.open(io.BytesIO(img_bytes)).convert("RGB")
    img_np = np.array(img)

    engine = get_engine()
    result = engine.ocr(img_np)

    words = []
    for line in result[0] or []:
        box, (text, conf) = line[0], line[1]
        x_min = min(p[0] for p in box)
        y_min = min(p[1] for p in box)
        x_max = max(p[0] for p in box)
        y_max = max(p[1] for p in box)
        words.append(
            {
                "text": text.strip(),
                "left": int(x_min),
                "top": int(y_min),
                "width": int(x_max - x_min),
                "height": int(y_max - y_min),
                "conf": round(conf * 100, 1),
            }
        )

    return {
        "words": words,
        "image_width": img_np.shape[1],
        "image_height": img_np.shape[0],
    }