feat: 오피스 → ODF 변환 + 원본/편집본 분리 아키텍처

- original_path/format/hash + conversion_status 필드 추가 (migration 007)
- extract_worker: 텍스트 추출 후 xlsx→ods, docx→odt 등 ODF 변환
  - 변환본은 .derived/{doc_id}.ods 에 저장
  - 원본 메타 보존 (original_path/format/hash)
- file_watcher: .derived/ .preview/ 디렉토리 제외
- DocumentViewer: ODF 포맷이면 편집 버튼 자동 표시
  - edit_url 있으면 "편집", 없으면 "Synology Drive에서 열기"

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

app/api/documents.py

@@ -37,6 +37,9 @@ class DocumentResponse(BaseModel):
     ai_tags: list | None
     ai_summary: str | None
     user_note: str | None
+    original_path: str | None
+    original_format: str | None
+    conversion_status: str | None
     edit_url: str | None
     preview_status: str | None
     source_channel: str | None

app/models/document.py

@@ -47,6 +47,12 @@ class Document(Base):
     # 사용자 메모
     user_note: Mapped[str | None] = mapped_column(Text)
 
+    # 원본 보존 (변환 전)
+    original_path: Mapped[str | None] = mapped_column(Text)
+    original_format: Mapped[str | None] = mapped_column(String(20))
+    original_hash: Mapped[str | None] = mapped_column(String(64))
+    conversion_status: Mapped[str | None] = mapped_column(String(20), default="none")
+
     # 외부 편집 URL
     edit_url: Mapped[str | None] = mapped_column(Text)
 

app/workers/extract_worker.py

@@ -117,6 +117,55 @@ async def process(document_id: int, session: AsyncSession) -> None:
             raise RuntimeError(f"LibreOffice 텍스트 추출 timeout (60s)")
         finally:
             tmp_input.unlink(missing_ok=True)
+
+        # ─── ODF 변환 (편집용) ───
+        CONVERT_MAP = {
+            'xlsx': 'ods', 'xls': 'ods',
+            'docx': 'odt', 'doc': 'odt',
+            'pptx': 'odp', 'ppt': 'odp',
+        }
+        target_fmt = CONVERT_MAP.get(fmt)
+        if target_fmt:
+            try:
+                from core.utils import file_hash as calc_hash
+                # 원본 메타 보존
+                doc.original_path = doc.file_path
+                doc.original_format = doc.file_format
+                doc.original_hash = doc.file_hash
+
+                # .derived 디렉토리에 변환
+                derived_dir = full_path.parent / ".derived"
+                derived_dir.mkdir(exist_ok=True)
+                tmp_input2 = tmp_dir / f"convert_{document_id}.{fmt}"
+                shutil.copy2(str(full_path), str(tmp_input2))
+
+                conv_result = subprocess.run(
+                    ["libreoffice", "--headless", "--convert-to", target_fmt, "--outdir", str(tmp_dir), str(tmp_input2)],
+                    capture_output=True, text=True, timeout=60,
+                )
+                tmp_input2.unlink(missing_ok=True)
+
+                conv_file = tmp_dir / f"convert_{document_id}.{target_fmt}"
+                if conv_file.exists():
+                    final_path = derived_dir / f"{document_id}.{target_fmt}"
+                    shutil.move(str(conv_file), str(final_path))
+
+                    # DB 업데이트: current → ODF
+                    nas_root = Path(settings.nas_mount_path)
+                    doc.file_path = str(final_path.relative_to(nas_root))
+                    doc.file_format = target_fmt
+                    doc.file_hash = calc_hash(final_path)
+                    doc.conversion_status = "done"
+                    logger.info(f"[ODF변환] {doc.original_path} → {doc.file_path}")
+                else:
+                    doc.conversion_status = "failed"
+                    logger.warning(f"[ODF변환] 실패: {conv_result.stderr[:200]}")
+            except Exception as e:
+                doc.conversion_status = "failed"
+                logger.error(f"[ODF변환] {doc.file_path} 에러: {e}")
+        else:
+            doc.conversion_status = "none"
+
         return
 
     # 미지원 포맷

app/workers/file_watcher.py

@@ -22,6 +22,9 @@ def should_skip(path: Path) -> bool:
         return True
     if path.suffix.lower() in SKIP_EXTENSIONS:
         return True
+    # .derived/ 및 .preview/ 디렉토리 내 파일 제외
+    if ".derived" in path.parts or ".preview" in path.parts:
+        return True
     return False