feat(law_monitor): 외국 법령 지원 추가 — US OSHA, JP 厚労省(MLX 번역), EU-OSHA

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

scripts/law_monitor.py

@@ -16,7 +16,7 @@ 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, PROJECT_ROOT, DATA_DIR
+from pkm_utils import setup_logger, load_credentials, run_applescript_inline, llm_generate, PROJECT_ROOT, DATA_DIR
 
 logger = setup_logger("law_monitor")
 
@@ -182,7 +182,226 @@ def run():
             logger.debug(f"변경 없음: {law_name}")
 
     save_last_check(last_check)
-    logger.info(f"=== 법령 모니터링 완료 — {changes_found}건 변경 감지 ===")
+
+    # ─── 외국 법령 (빈도 체크 후 실행) ───
+    us_count = fetch_us_osha(last_check)
+    jp_count = fetch_jp_mhlw(last_check)
+    eu_count = fetch_eu_osha(last_check)
+    changes_found += us_count + jp_count + eu_count
+
+    save_last_check(last_check)
+    logger.info(f"=== 법령 모니터링 완료 — {changes_found}건 변경 감지 (한국+외국) ===")
+
+
+# ═══════════════════════════════════════════════
+# 외국 법령 모니터링
+# ═══════════════════════════════════════════════
+
+def _should_run(last_check: dict, key: str, interval_days: int) -> bool:
+    """빈도 체크: 마지막 실행일로부터 interval_days 경과 여부"""
+    last_run = last_check.get(key, "")
+    if not last_run:
+        return True
+    try:
+        last_date = datetime.strptime(last_run, "%Y-%m-%d")
+        return (datetime.now() - last_date).days >= interval_days
+    except ValueError:
+        return True
+
+
+def _import_foreign_to_devonthink(filepath: Path, title: str, country: str):
+    """외국 법령 DEVONthink 임포트"""
+    country_map = {"US": "US", "JP": "JP", "EU": "EU"}
+    folder = country_map.get(country, country)
+    escaped_path = str(filepath).replace('"', '\\"')
+    escaped_title = title.replace('"', '\\"')[:60]
+    script = f'''
+    tell application id "DNtp"
+        set targetDB to missing value
+        repeat with db in databases
+            if name of db is "04_Industrial safety" then
+                set targetDB to db
+                exit repeat
+            end if
+        end repeat
+        if targetDB is not missing value then
+            set targetGroup to create location "/10_Legislation/Foreign/{folder}" in targetDB
+            set theRecord to import POSIX path "{escaped_path}" to targetGroup
+            set tags of theRecord to {{"#주제/산업안전/법령", "$유형/법령", "{country}"}}
+            add custom meta data "law_monitor" for "sourceChannel" to theRecord
+            add custom meta data "external" for "dataOrigin" to theRecord
+            add custom meta data (current date) for "lastAIProcess" to theRecord
+        end if
+    end tell
+    '''
+    try:
+        run_applescript_inline(script)
+        logger.info(f"DEVONthink 임포트 [{country}]: {escaped_title}")
+    except Exception as e:
+        logger.error(f"DEVONthink 임포트 실패 [{country}]: {e}")
+
+
+def fetch_us_osha(last_check: dict) -> int:
+    """US OSHA — Federal Register API (주 1회)"""
+    if not _should_run(last_check, "_us_osha_last", 7):
+        logger.debug("US OSHA: 이번 주 이미 실행됨, 건너뜀")
+        return 0
+
+    logger.info("=== US OSHA 확인 ===")
+    try:
+        from_date = (datetime.now() - timedelta(days=7)).strftime("%Y-%m-%d")
+        resp = requests.get("https://www.federalregister.gov/api/v1/documents.json", params={
+            "conditions[agencies][]": "occupational-safety-and-health-administration",
+            "conditions[type][]": ["RULE", "PRORULE"],
+            "conditions[publication_date][gte]": from_date,
+            "per_page": 10,
+            "order": "newest",
+        }, timeout=30)
+        resp.raise_for_status()
+        data = resp.json()
+        results = data.get("results", [])
+        count = 0
+
+        for doc in results:
+            doc_id = doc.get("document_number", "")
+            title = doc.get("title", "")
+            pub_date = doc.get("publication_date", "")
+            abstract = doc.get("abstract", "")
+            doc_url = doc.get("html_url", "")
+
+            # 마크다운으로 저장
+            content = f"# {title}\n\n"
+            content += f"- **Document**: {doc_id}\n"
+            content += f"- **Date**: {pub_date}\n"
+            content += f"- **URL**: {doc_url}\n\n"
+            if abstract:
+                content += f"## Abstract\n\n{abstract}\n"
+
+            safe_title = "".join(c if c.isalnum() or c in " _-" else "_" for c in title)[:50]
+            filepath = LAWS_DIR / f"US_OSHA_{pub_date}_{safe_title}.md"
+            with open(filepath, "w", encoding="utf-8") as f:
+                f.write(content)
+
+            _import_foreign_to_devonthink(filepath, title, "US")
+            count += 1
+
+        last_check["_us_osha_last"] = datetime.now().strftime("%Y-%m-%d")
+        logger.info(f"US OSHA: {count}건")
+        return count
+
+    except Exception as e:
+        logger.error(f"US OSHA 에러: {e}", exc_info=True)
+        return 0
+
+
+def fetch_jp_mhlw(last_check: dict) -> int:
+    """JP 厚生労働省 — RSS 파싱 + MLX 번역 (주 1회)"""
+    if not _should_run(last_check, "_jp_mhlw_last", 7):
+        logger.debug("JP 厚労省: 이번 주 이미 실행됨, 건너뜀")
+        return 0
+
+    logger.info("=== JP 厚生労働省 확인 ===")
+    try:
+        import xml.etree.ElementTree as ET
+        resp = requests.get("https://www.mhlw.go.jp/stf/rss/shinchaku.xml", timeout=30)
+        resp.raise_for_status()
+        root = ET.fromstring(resp.content)
+
+        safety_keywords = ["労働安全", "安全衛生", "労災", "化学物質", "石綿", "安全管理"]
+        count = 0
+
+        for item in root.iter("item"):
+            title = item.findtext("title", "")
+            link = item.findtext("link", "")
+            pub_date = item.findtext("pubDate", "")
+
+            # 안전위생 키워드 필터
+            if not any(kw in title for kw in safety_keywords):
+                continue
+
+            # MLX 35B로 한국어 번역
+            translated = ""
+            try:
+                translated = llm_generate(
+                    f"다음 일본어 제목을 한국어로 번역해줘. 번역만 출력하고 다른 말은 하지 마.\n\n{title}"
+                )
+                # thinking 출력 제거 — 마지막 줄만 사용
+                lines = [l.strip() for l in translated.strip().split("\n") if l.strip()]
+                translated = lines[-1] if lines else title
+            except Exception:
+                translated = title
+
+            content = f"# {title}\n\n"
+            content += f"**한국어**: {translated}\n\n"
+            content += f"- **URL**: {link}\n"
+            content += f"- **Date**: {pub_date}\n"
+
+            safe_title = "".join(c if c.isalnum() or c in " _-" else "_" for c in title)[:40]
+            today = datetime.now().strftime("%Y%m%d")
+            filepath = LAWS_DIR / f"JP_{today}_{safe_title}.md"
+            with open(filepath, "w", encoding="utf-8") as f:
+                f.write(content)
+
+            _import_foreign_to_devonthink(filepath, f"{translated} ({title})", "JP")
+            count += 1
+
+            if count >= 10:
+                break
+
+        last_check["_jp_mhlw_last"] = datetime.now().strftime("%Y-%m-%d")
+        logger.info(f"JP 厚労省: {count}건")
+        return count
+
+    except Exception as e:
+        logger.error(f"JP 厚労省 에러: {e}", exc_info=True)
+        return 0
+
+
+def fetch_eu_osha(last_check: dict) -> int:
+    """EU-OSHA — RSS 파싱 (월 1회)"""
+    if not _should_run(last_check, "_eu_osha_last", 30):
+        logger.debug("EU-OSHA: 이번 달 이미 실행됨, 건너뜀")
+        return 0
+
+    logger.info("=== EU-OSHA 확인 ===")
+    try:
+        import xml.etree.ElementTree as ET
+        resp = requests.get("https://osha.europa.eu/en/rss", timeout=30)
+        resp.raise_for_status()
+        root = ET.fromstring(resp.content)
+
+        count = 0
+        for item in root.iter("item"):
+            title = item.findtext("title", "")
+            link = item.findtext("link", "")
+            description = item.findtext("description", "")
+            pub_date = item.findtext("pubDate", "")
+
+            content = f"# {title}\n\n"
+            content += f"- **URL**: {link}\n"
+            content += f"- **Date**: {pub_date}\n\n"
+            if description:
+                content += f"## Summary\n\n{description}\n"
+
+            safe_title = "".join(c if c.isalnum() or c in " _-" else "_" for c in title)[:50]
+            today = datetime.now().strftime("%Y%m%d")
+            filepath = LAWS_DIR / f"EU_{today}_{safe_title}.md"
+            with open(filepath, "w", encoding="utf-8") as f:
+                f.write(content)
+
+            _import_foreign_to_devonthink(filepath, title, "EU")
+            count += 1
+
+            if count >= 5:
+                break
+
+        last_check["_eu_osha_last"] = datetime.now().strftime("%Y-%m-%d")
+        logger.info(f"EU-OSHA: {count}건")
+        return count
+
+    except Exception as e:
+        logger.error(f"EU-OSHA 에러: {e}", exc_info=True)
+        return 0
 
 
 if __name__ == "__main__":