"""通用 HTTP OCR：向自定义 REST 接口 POST 图片并解析文本。"""
from __future__ import annotations

import base64
import json
from pathlib import Path
from typing import Any

import httpx

from .base import OCRProvider


class HttpOCR(OCRProvider):
    """POST JSON {"image_base64": "..."} 到指定 URL，从响应 JSON 取文本。

    extra 配置项：
    - text_path: 点分路径，如 "data.text" 或 "result"，默认 "text"
    - headers: 额外请求头 dict
    """

    name = "http"

    def __init__(
        self,
        base_url: str,
        api_key: str = "",
        text_path: str = "text",
        headers: dict[str, str] | None = None,
        timeout: float = 30.0,
    ) -> None:
        self.base_url = base_url.rstrip("/")
        self.api_key = api_key
        self.text_path = text_path
        self.headers = headers or {}
        self.timeout = timeout

    async def recognize(self, image_path: Path) -> str:
        with open(image_path, "rb") as f:
            encoded = base64.b64encode(f.read()).decode("ascii")

        headers = {"Content-Type": "application/json", **self.headers}
        if self.api_key:
            headers["Authorization"] = f"Bearer {self.api_key}"

        payload = {"image_base64": encoded, "image": encoded}

        async with httpx.AsyncClient(timeout=self.timeout) as client:
            resp = await client.post(self.base_url, json=payload, headers=headers)
            resp.raise_for_status()
            data = resp.json()

        return str(_dig(data, self.text_path) or "").strip()


def _dig(obj: Any, path: str) -> Any:
    """按点分路径从嵌套 dict 取值。"""
    cur = obj
    for part in path.split("."):
        if not isinstance(cur, dict):
            return None
        cur = cur.get(part)
    return cur