meeting_memory/main.py

import argparse
import glob as glob_module
import logging
import os
import sys

if sys.stdout.encoding and sys.stdout.encoding.lower() == "gbk":
    sys.stdout.reconfigure(encoding="utf-8")

logging.basicConfig(
    level=logging.INFO,
    format="%(asctime)s [%(levelname)s] %(name)s: %(message)s",
    datefmt="%H:%M:%S",
)
logger = logging.getLogger(__name__)


def cmd_process(args):
    from meeting_processor import meeting_processor

    filepath = args.file
    if not os.path.exists(filepath):
        print(f"错误：文件不存在 {filepath}")
        sys.exit(1)

    print(f"正在处理会议文件：{filepath}")
    archive_path = meeting_processor.process_meeting_file(filepath, force=getattr(args, "force", False))

    if archive_path:
        print("\n处理完成")
        print(f"原文归档：{archive_path}")
    else:
        print("\n处理失败或已跳过")
        sys.exit(1)


def cmd_text(args):
    from meeting_processor import meeting_processor

    print("正在处理会议文本...")
    archive_path = meeting_processor.process_meeting_text(args.text, force=getattr(args, "force", False))
    if archive_path:
        print("\n处理完成")
        print(f"原文归档：{archive_path}")
    else:
        print("\n处理失败或已跳过")


def cmd_query(args):
    from meeting_processor import meeting_processor

    print(f"查询：{args.question}")
    print("-" * 40)
    result = meeting_processor.query(args.question, top_k=args.top_k)
    print(result if result else "未找到相关信息")


def cmd_stats(args):
    from meeting_processor import meeting_processor

    stats = meeting_processor.stats()
    print("会议记忆系统统计")
    print("-" * 40)
    print(f"向量节点数：{stats.get('vector_index', {}).get('node_count', 0)}")
    print(f"Neo4j 启用：{stats.get('graph', {}).get('enabled', False)}")
    print(f"图谱会议数：{stats.get('graph', {}).get('meetings', 0)}")
    print(f"图谱实体数：{stats.get('graph', {}).get('entities', 0)}")
    print(f"行动项数：{stats.get('state', {}).get('action_items_tracked', 0)}")
    print(f"指标数：{stats.get('state', {}).get('metrics_tracked', 0)}")
    print(f"会议系列数：{stats.get('state', {}).get('meeting_series', 0)}")
    print(f"原文归档目录：{stats.get('raw_dir', '')}")
    print(f"状态文件：{stats.get('state_path', '')}")


def cmd_batch(args):
    from meeting_processor import meeting_processor

    files = glob_module.glob(args.pattern, recursive=True)
    if not files:
        print(f"未匹配到任何文件：{args.pattern}")
        sys.exit(1)

    print(f"找到 {len(files)} 个文件，开始批量处理...")
    success = 0
    for path in files:
        try:
            print(f"\n处理：{path}")
            result = meeting_processor.process_meeting_file(path, force=getattr(args, "force", False))
            if result:
                success += 1
        except Exception as exc:
            logger.error("处理失败: %s - %s", path, exc)

    print(f"\n批量处理完成：{success}/{len(files)} 成功")


def cmd_interactive():
    from meeting_processor import meeting_processor

    print("会议纪要长期记忆系统")
    print("=" * 50)
    print("可用命令：")
    print("  query <问题>    语义查询会议记忆")
    print("  process <路径>  处理会议文件")
    print("  stats           查看统计")
    print("  help            显示帮助")
    print("  exit/quit       退出")
    print("=" * 50)

    while True:
        try:
            line = input("\n> ").strip()
        except (EOFError, KeyboardInterrupt):
            print()
            break

        if not line:
            continue
        if line in ("exit", "quit", "q"):
            break
        if line == "help":
            print("  query <问题>")
            print("  process <路径>")
            print("  stats")
            print("  exit/quit")
            continue
        if line == "stats":
            cmd_stats(None)
            continue
        if line.startswith("process "):
            filepath = line[8:].strip()
            if not os.path.exists(filepath):
                print(f"文件不存在：{filepath}")
                continue
            result = meeting_processor.process_meeting_file(filepath)
            print(f"完成：{result}" if result else "处理失败或已跳过")
            continue

        question = line[6:].strip() if line.startswith("query ") else line
        result = meeting_processor.query(question, top_k=3)
        print(result if result else "未找到相关信息")

    print("bye!")


def main():
    parser = argparse.ArgumentParser(description="会议纪要长期记忆系统")
    subparsers = parser.add_subparsers(dest="command")

    p_process = subparsers.add_parser("process", help="处理会议 markdown 文件")
    p_process.add_argument("file", help="会议文件路径")
    p_process.add_argument("-f", "--force", action="store_true", help="发现重复时自动覆盖")

    p_text = subparsers.add_parser("text", help="直接处理一段会议文本")
    p_text.add_argument("text", help="会议文本内容")
    p_text.add_argument("-f", "--force", action="store_true", help="发现重复时自动覆盖")

    p_query = subparsers.add_parser("query", help="语义查询会议记忆")
    p_query.add_argument("question", help="查询问题")
    p_query.add_argument("--top-k", type=int, default=3, help="返回结果数量")

    subparsers.add_parser("stats", help="查看统计")

    p_batch = subparsers.add_parser("batch", help="批量处理会议文件")
    p_batch.add_argument("pattern", help="glob 模式，如 meetings/*.md")
    p_batch.add_argument("-f", "--force", action="store_true", help="发现重复时自动覆盖")

    args = parser.parse_args()

    if args.command == "process":
        cmd_process(args)
    elif args.command == "text":
        cmd_text(args)
    elif args.command == "query":
        cmd_query(args)
    elif args.command == "stats":
        cmd_stats(args)
    elif args.command == "batch":
        cmd_batch(args)
    else:
        cmd_interactive()


if __name__ == "__main__":
    main()