meeting_memory/meeting_processor.py

import hashlib
import logging
from typing import Optional

from extractor import extract_meeting_info, MeetingExtraction
from vector_store import meeting_vector_store
from obsidian_manager import obsidian_manager
from meeting_state import MeetingStateStore
from config import config

logger = logging.getLogger(__name__)

state_store = MeetingStateStore(config.state_path)


class MeetingProcessor:
    def process_meeting_file(self, filepath: str, force: bool = False) -> Optional[str]:
        with open(filepath, "r", encoding="utf-8") as f:
            text = f.read()

        return self.process_meeting_text(text, force=force)

    def process_meeting_text(self, text: str, force: bool = False) -> Optional[str]:
        content_hash = self._compute_content_hash(text)

        if not force and state_store.has_content_hash(content_hash):
            print(f"\n⚠️  检测到重复内容（内容指纹匹配），跳过处理")
            logger.info(f"内容哈希重复，跳过: {content_hash[:12]}")
            return None

        if not force:
            similar = meeting_vector_store.find_similar_text(text, threshold=0.92)
            if similar:
                meta = similar["metadata"]
                print(f"\n⚠️  发现高度相似的已有会议: 「{meta.get('title', '')}」({meta.get('date', '')})  相似度: {similar['score']:.2%}")
                while True:
                    choice = input("  选择操作 [s]跳过 / [o]覆盖 (默认 s): ").strip().lower() or "s"
                    if choice == "s":
                        logger.info(f"跳过相似会议: {meta.get('title', '')}")
                        return None
                    elif choice == "o":
                        logger.info(f"覆盖重新处理相似会议")
                        force = True
                        break
                    print("  请输入 s(skip) 或 o(overwrite)")

        meeting_data = self._extract(text)
        if not meeting_data:
            logger.error("会议信息提取失败")
            return None

        data_dict = meeting_data.model_dump()
        meeting_title = data_dict.get("title", "")
        meeting_date = data_dict.get("date", "")
        data_dict["_content_hash"] = content_hash

        should_skip = self._handle_duplicate(data_dict, force)
        if should_skip:
            return None

        raw_path = obsidian_manager.save_raw_text(
            text,
            title=meeting_title,
            date=meeting_date,
        )
        data_dict["_original_text"] = text
        data_dict["_original_text_path"] = raw_path

        obsidian_manager.mark_raw_processed(raw_path)

        meeting_filename = obsidian_manager._meeting_filename(data_dict)

        merged_items = state_store.merge_action_items(
            data_dict.get("action_items", []),
            meeting_title,
            meeting_date,
            meeting_filename,
        )
        data_dict["action_items"] = merged_items

        merged_metrics = state_store.merge_metrics(
            data_dict.get("metrics", []),
            meeting_title,
            meeting_date,
            meeting_filename,
        )
        data_dict["metrics"] = merged_metrics

        state_store.add_content_hash(content_hash, meeting_title, meeting_date, meeting_filename)
        state_store.save()

        vault_path = obsidian_manager.add_meeting(data_dict, text)

        vector_store_manager = meeting_vector_store
        vector_store_manager.add_meeting(data_dict)

        logger.info(f"会议处理完成: {meeting_data.title}")
        return vault_path

    def _handle_duplicate(self, data_dict: dict, force: bool) -> bool:
        title = data_dict.get("title", "")
        date = data_dict.get("date", "")

        existing = meeting_vector_store.find_meeting(title, date)
        file_exists = obsidian_manager.meeting_file_exists(data_dict)

        if not existing and not file_exists:
            return False

        if force:
            logger.info(f"发现重复会议「{title}」，--force 模式自动覆盖")
            self._remove_old(data_dict)
            return False

        print(f"\n⚠️  发现重复会议: 「{title}」({date})")
        while True:
            choice = input("  选择操作 [s]跳过 / [o]覆盖 (默认 s): ").strip().lower() or "s"
            if choice == "s":
                logger.info(f"跳过重复会议: {title}")
                return True
            elif choice == "o":
                logger.info(f"覆盖重新处理: {title}")
                self._remove_old(data_dict)
                return False
            print("  请输入 s(skip) 或 o(overwrite)")

    def _remove_old(self, data_dict: dict):
        meeting_id = meeting_vector_store._meeting_id(data_dict)
        meeting_vector_store.remove_meeting(meeting_id)
        obsidian_manager.remove_meeting_note(data_dict)
        content_hash = data_dict.get("_content_hash", "")
        if content_hash:
            state_store.remove_content_hash(content_hash)
        logger.info(f"旧数据清理完成: {data_dict.get('title', '')}")

    def _compute_content_hash(self, text: str) -> str:
        normalized = text.strip().replace('\r\n', '\n')
        return hashlib.sha256(normalized.encode('utf-8')).hexdigest()

    def _extract(self, text: str) -> Optional[MeetingExtraction]:
        try:
            return extract_meeting_info(text)
        except Exception as e:
            logger.error(f"LLM提取失败: {e}")
            return None

    def query(self, question: str, top_k: int = 3) -> str:
        return meeting_vector_store.query_as_context(question, top_k=top_k)

    def stats(self) -> dict:
        import os
        vault = config.obsidian.vault_path
        meetings_dir = os.path.join(vault, config.obsidian.meetings_dir)
        entities_dir = os.path.join(vault, config.obsidian.entities_dir)

        meeting_files = [f for f in os.listdir(meetings_dir) if f.endswith(".md")] if os.path.exists(meetings_dir) else []
        entity_files = [f for f in os.listdir(entities_dir) if f.endswith(".md")] if os.path.exists(entities_dir) else []

        vs_stats = meeting_vector_store.get_stats()
        state_stats = state_store.get_stats()

        return {
            "obsidian_meetings": len(meeting_files),
            "obsidian_entities": len(entity_files),
            "vector_index": vs_stats,
            "state": state_stats,
            "vault_path": vault,
        }


meeting_processor = MeetingProcessor()