hyungi_document_server/scripts/pkm_daily_digest.py

#!/usr/bin/env python3
"""
PKM 일일 다이제스트
- DEVONthink 오늘 추가/수정 집계
- law_monitor 법령 변경 건 파싱
- OmniFocus 완료/추가/기한초과 집계
- 상위 뉴스 Ollama 요약
- OmniFocus 액션 자동 생성
- 90일 지난 다이제스트 아카이브
"""

import os
import sys
import re
from datetime import datetime, timedelta
from pathlib import Path

sys.path.insert(0, str(Path(__file__).parent))
from pkm_utils import (
    setup_logger, load_credentials, run_applescript_inline,
    ollama_generate, count_log_errors, PROJECT_ROOT, LOGS_DIR, DATA_DIR
)

logger = setup_logger("digest")

DIGEST_DIR = DATA_DIR / "digests"
DIGEST_DIR.mkdir(exist_ok=True)


def get_devonthink_stats() -> dict:
    """DEVONthink 오늘 추가/수정 문서 집계"""
    script = '''
    tell application id "DNtp"
        set today to current date
        set time of today to 0
        set stats to {}

        repeat with db in databases
            set dbName to name of db
            set addedCount to count of (search "date:today" in db)
            set modifiedCount to count of (search "modified:today" in db)

            if addedCount > 0 or modifiedCount > 0 then
                set end of stats to dbName & ":" & addedCount & ":" & modifiedCount
            end if
        end repeat

        set AppleScript's text item delimiters to "|"
        return stats as text
    end tell
    '''
    try:
        result = run_applescript_inline(script)
        stats = {}
        if result:
            for item in result.split("|"):
                parts = item.split(":")
                if len(parts) == 3:
                    stats[parts[0]] = {"added": int(parts[1]), "modified": int(parts[2])}
        return stats
    except Exception as e:
        logger.error(f"DEVONthink 집계 실패: {e}")
        return {}


def get_omnifocus_stats() -> dict:
    """OmniFocus 오늘 완료/추가/기한초과 집계"""
    script = '''
    tell application "OmniFocus"
        tell default document
            set today to current date
            set time of today to 0
            set tomorrow to today + 1 * days

            set completedCount to count of (every flattened task whose completed is true and completion date ≥ today)
            set addedCount to count of (every flattened task whose creation date ≥ today)
            set overdueCount to count of (every flattened task whose completed is false and due date < today and due date is not missing value)

            return (completedCount as text) & "|" & (addedCount as text) & "|" & (overdueCount as text)
        end tell
    end tell
    '''
    try:
        result = run_applescript_inline(script)
        parts = result.split("|")
        return {
            "completed": int(parts[0]) if len(parts) > 0 else 0,
            "added": int(parts[1]) if len(parts) > 1 else 0,
            "overdue": int(parts[2]) if len(parts) > 2 else 0,
        }
    except Exception as e:
        logger.error(f"OmniFocus 집계 실패: {e}")
        return {"completed": 0, "added": 0, "overdue": 0}


def parse_law_changes() -> list:
    """law_monitor 로그에서 오늘 법령 변경 건 파싱"""
    log_file = LOGS_DIR / "law_monitor.log"
    if not log_file.exists():
        return []

    today = datetime.now().strftime("%Y-%m-%d")
    changes = []
    with open(log_file, "r", encoding="utf-8") as f:
        for line in f:
            if today in line and "변경 감지" in line:
                # "[2026-03-26 07:00:15] [law_monitor] [INFO] 변경 감지: 산업안전보건법 — 공포일자 ..."
                match = re.search(r"변경 감지: (.+?)$", line)
                if match:
                    changes.append(match.group(1).strip())
    return changes


def get_inbox_count() -> int:
    """DEVONthink Inbox 미처리 문서 수"""
    script = '''
    tell application id "DNtp"
        repeat with db in databases
            if name of db is "Inbox" then
                return count of children of root group of db
            end if
        end repeat
        return 0
    end tell
    '''
    try:
        return int(run_applescript_inline(script))
    except:
        return 0


def create_omnifocus_task(task_name: str, note: str = "", flagged: bool = False):
    """OmniFocus 작업 생성"""
    flag_str = "true" if flagged else "false"
    escaped_name = task_name.replace('"', '\\"')
    escaped_note = note.replace('"', '\\"')
    script = f'''
    tell application "OmniFocus"
        tell default document
            make new inbox task with properties {{name:"{escaped_name}", note:"{escaped_note}", flagged:{flag_str}}}
        end tell
    end tell
    '''
    try:
        run_applescript_inline(script)
        logger.info(f"OmniFocus 작업 생성: {task_name}")
    except Exception as e:
        logger.error(f"OmniFocus 작업 생성 실패: {e}")


def get_system_health() -> dict:
    """각 모듈 로그의 최근 24시간 ERROR 카운트"""
    modules = ["law_monitor", "mailplus", "digest", "embed", "auto_classify"]
    health = {}
    for mod in modules:
        log_file = LOGS_DIR / f"{mod}.log"
        health[mod] = count_log_errors(log_file, since_hours=24)
    return health


def generate_digest():
    """다이제스트 생성"""
    logger.info("=== Daily Digest 생성 시작 ===")
    today = datetime.now()
    date_str = today.strftime("%Y-%m-%d")

    # 데이터 수집
    dt_stats = get_devonthink_stats()
    of_stats = get_omnifocus_stats()
    law_changes = parse_law_changes()
    inbox_count = get_inbox_count()
    system_health = get_system_health()

    # 마크다운 생성
    md = f"# PKM Daily Digest — {date_str}\n\n"

    # DEVONthink 현황
    md += "## DEVONthink 변화\n\n"
    if dt_stats:
        md += "| DB | 신규 | 수정 |\n|---|---|---|\n"
        total_added = 0
        total_modified = 0
        for db_name, counts in dt_stats.items():
            md += f"| {db_name} | {counts['added']} | {counts['modified']} |\n"
            total_added += counts["added"]
            total_modified += counts["modified"]
        md += f"| **합계** | **{total_added}** | **{total_modified}** |\n\n"
    else:
        md += "변화 없음\n\n"

    # 법령 변경
    md += "## 법령 변경\n\n"
    if law_changes:
        for change in law_changes:
            md += f"- {change}\n"
        md += "\n"
    else:
        md += "변경 없음\n\n"

    # OmniFocus 현황
    md += "## OmniFocus 현황\n\n"
    md += f"- 완료: {of_stats['completed']}건\n"
    md += f"- 신규: {of_stats['added']}건\n"
    md += f"- 기한초과: {of_stats['overdue']}건\n\n"

    # Inbox 상태
    md += f"## Inbox 미처리: {inbox_count}건\n\n"

    # 시스템 상태
    md += "## 시스템 상태\n\n"
    total_errors = sum(system_health.values())
    if total_errors == 0:
        md += "모든 모듈 정상\n\n"
    else:
        md += "| 모듈 | 에러 수 |\n|---|---|\n"
        for mod, cnt in system_health.items():
            status = f"**{cnt}**" if cnt > 0 else "0"
            md += f"| {mod} | {status} |\n"
        md += "\n"

    # 파일 저장
    digest_file = DIGEST_DIR / f"{date_str}_digest.md"
    with open(digest_file, "w", encoding="utf-8") as f:
        f.write(md)
    logger.info(f"다이제스트 저장: {digest_file}")

    # DEVONthink 저장
    import_digest_to_devonthink(digest_file, date_str)

    # OmniFocus 액션 자동 생성
    if law_changes:
        for change in law_changes:
            create_omnifocus_task(f"법령 변경 검토: {change[:30]}", note=change)

    if inbox_count >= 3:
        create_omnifocus_task(f"Inbox 정리 ({inbox_count}건 미처리)", note="DEVONthink Inbox에 미분류 문서가 쌓여있습니다.")

    if of_stats["overdue"] > 0:
        create_omnifocus_task(f"기한초과 작업 처리 ({of_stats['overdue']}건)", flagged=True)

    # 90일 지난 다이제스트 아카이브
    archive_old_digests()

    logger.info("=== Daily Digest 완료 ===")


def import_digest_to_devonthink(filepath: Path, date_str: str):
    """다이제스트를 DEVONthink에 저장"""
    escaped_path = str(filepath).replace('"', '\\"')
    script = f'''
    tell application id "DNtp"
        repeat with db in databases
            if name of db is "00_Note_BOX" then
                set targetGroup to create location "/Daily_Digest" in db
                import POSIX path "{escaped_path}" to targetGroup
                exit repeat
            end if
        end repeat
    end tell
    '''
    try:
        run_applescript_inline(script)
    except Exception as e:
        logger.error(f"DEVONthink 다이제스트 임포트 실패: {e}")


def archive_old_digests():
    """90일 지난 다이제스트 이동"""
    cutoff = datetime.now() - timedelta(days=90)
    for f in DIGEST_DIR.glob("*_digest.md"):
        try:
            date_part = f.stem.split("_digest")[0]
            file_date = datetime.strptime(date_part, "%Y-%m-%d")
            if file_date < cutoff:
                archive_dir = DIGEST_DIR / "archive"
                archive_dir.mkdir(exist_ok=True)
                f.rename(archive_dir / f.name)
                logger.info(f"아카이브: {f.name}")
        except ValueError:
            pass


if __name__ == "__main__":
    generate_digest()