"""Remote PaddleOCR client — calls Hetzner service."""

import logging
import os
from typing import Dict, List, Tuple

import httpx

logger = logging.getLogger(__name__)

PADDLEOCR_REMOTE_URL = os.environ.get("PADDLEOCR_REMOTE_URL", "")
PADDLEOCR_API_KEY = os.environ.get("PADDLEOCR_API_KEY", "")
_TIMEOUT = 120.0  # Full-page OCR can take 30-90s on large scans


async def ocr_remote_paddle(
    image_bytes: bytes,
    filename: str = "scan.png",
) -> Tuple[List[Dict], int, int]:
    """Send image to remote PaddleOCR, return (word_dicts, img_w, img_h)."""
    if not PADDLEOCR_REMOTE_URL:
        raise RuntimeError("PADDLEOCR_REMOTE_URL not configured")

    headers = {}
    if PADDLEOCR_API_KEY:
        headers["X-API-Key"] = PADDLEOCR_API_KEY

    async with httpx.AsyncClient(timeout=_TIMEOUT, verify=False) as client:
        resp = await client.post(
            f"{PADDLEOCR_REMOTE_URL.rstrip('/')}/ocr",
            files={"file": (filename, image_bytes, "image/png")},
            headers=headers,
        )
        resp.raise_for_status()
        data = resp.json()

    words = data.get("words", [])
    logger.info(
        "PaddleOCR remote returned %d words (img %dx%d)",
        len(words),
        data.get("image_width", 0),
        data.get("image_height", 0),
    )
    return words, data["image_width"], data["image_height"]