import json
from typing import Any, Dict, Optional

import httpx

from config import Config


class RagflowClient:
    """RAGFlow 客户端（仅检索）"""

    def __init__(self):
        cfg = Config.get_section("ragflow")
        self._base_url = cfg.get("url", "")
        self._api_key = cfg.get("api_key", "")
        self._retrieval_path = cfg.get("retrieval", "/api/v1/retrieval")
        self._table_retrieval_dataset_id = cfg.get("table_retrieval_dataset_id", "")
        self._sql_gen_dataset_id = cfg.get("sql_gen_dataset_id", "")

    def _build_url(self) -> str:
        return self._base_url.rstrip("/") + "/" + self._retrieval_path.lstrip("/")

    @staticmethod
    def _normalize_dataset_ids(dataset_id: Optional[str]) -> list[str]:
        """将配置值规范化为 RAGFlow 需要的 list[string]"""
        if not dataset_id:
            return []
        # 兼容逗号分隔配置
        parts = [p.strip() for p in str(dataset_id).split(",") if p.strip()]
        return parts

    def retrieve(self, query: str, top_k: int = 3, dataset_id: Optional[str] = None, document_ids: Optional[str] = None) -> Dict[str, Any]:
        """检索匹配文档"""
        if not self._base_url or not self._retrieval_path:
            raise RuntimeError("未配置 ragflow.url 或 ragflow.retrieval")
        if not dataset_id:
            raise ValueError("未提供 ragflow.dataset_id，无法进行检索")
        url = self._build_url()
        headers = {"Authorization": f"Bearer {self._api_key}"} if self._api_key else {}
        payload = {
            "dataset_ids": self._normalize_dataset_ids(dataset_id),
            "question": query,
            "top_k": top_k,
        }
        # 兼容部分版本字段
        payload["query"] = query
        if document_ids:
            payload["document_ids"] = document_ids

        with httpx.Client(timeout=30) as client:
            response = client.post(url, json=payload, headers=headers)
        response.raise_for_status()
        return response.json()


def extract_table_name(record: Dict[str, Any]) -> Optional[str]:
    """从检索结果中提取表名"""
    if not record:
        return None

    metadata = record.get("metadata") or {}
    for key in ("table", "table_name"):
        if key in metadata:
            return metadata.get(key)

    for key in ("table", "table_name"):
        if key in record:
            return record.get(key)

    content = record.get("content") or record.get("text") or ""

    # 兼容 content 为 JSON 字符串：{"table":"xxx", ...}
    try:
        parsed = json.loads(str(content))
        if isinstance(parsed, dict):
            for key in ("table", "table_name"):
                if parsed.get(key):
                    return str(parsed.get(key))
    except Exception:
        pass

    for line in str(content).splitlines():
        if line.lower().startswith("table:"):
            return line.split(":", 1)[1].strip()

    return None