"""保司小册子解析 — 调用 LLM 提取产品规则。"""
import json
import logging
from insurance.ppt.llm_client import llm_client

logger = logging.getLogger(__name__)

MANUAL_PARSE_PROMPT = """请从以下保险产品手册中提取产品规则和卖点信息。

要求输出 JSON 格式（不要包含 markdown 代码块标记）：
{
  "product_name": "产品名称",
  "features": [
    {"code": "唯一编码", "title": "卖点标题", "summary": "一句话描述"}
  ],
  "currency_options": ["USD", "HKD"],
  "coverage_highlights": ["保障亮点1", "保障亮点2"]
}

注意：
- features 列表提取 3-8 个核心卖点
- currency_options 提取支持的货币选项
- coverage_highlights 提取 3-5 个保障亮点
- 所有内容必须基于原文，不得虚构
"""


async def parse_manual_pdf(filepath: str) -> dict:
    """解析小册子 PDF，提取产品规则。

    参数:
        filepath: PDF 文件路径

    返回:
        解析后的结构化 JSON
    """
    # 提取 PDF 文本
    from insurance.ppt.extraction import _extract_pdf_text
    text = _extract_pdf_text(filepath)
    if not text:
        raise ValueError("无法提取 PDF 文本")

    # 截取前 8000 字符避免 token 超限
    text = text[:8000]

    user_prompt = f"以下是保险产品手册内容：\n\n{text}"

    result, _response = await llm_client.structured_output(
        user_prompt,
        MANUAL_PARSE_PROMPT,
        schema={
            "type": "object",
            "properties": {
                "product_name": {"type": "string"},
                "features": {
                    "type": "array",
                    "items": {
                        "type": "object",
                        "properties": {
                            "code": {"type": "string"},
                            "title": {"type": "string"},
                            "summary": {"type": "string"},
                        },
                    },
                },
                "currency_options": {"type": "array", "items": {"type": "string"}},
                "coverage_highlights": {"type": "array", "items": {"type": "string"}},
            },
            "required": ["product_name", "features"],
        },
    )
    return result