refactor(#27): IMP-27 K5 catalog loader + _get_block_by_id cleanup

Consolidate three duplicated catalog readers and two _get_block_by_id
implementations behind a single shared module (src/catalog.py) that owns
file-read + mtime cache. All caller signatures and return contracts
remain byte-identical.

Units:
- u1 NEW src/catalog.py (76 lines): load_root_catalog / load_blocks /
  get_block_by_id / get_catalog_mtime as the sole file-read +
  mtime-cache owner.
- u2 src/block_reference.py: _load_catalog delegates to load_blocks
  (list[dict] preserved); _get_block_by_id (no-arg) delegates to
  catalog.get_block_by_id. Module-level _catalog_cache removed.
- u3 src/block_selector.py: load_catalog delegates to load_root_catalog
  (root dict preserved); _get_block_by_id (catalog-injected sig
  preserved) delegates to catalog.get_block_by_id. Module-level
  _catalog_cache / _catalog_mtime / CATALOG_PATH removed.
- u4 src/renderer.py: _load_catalog_map and
  _load_catalog_map_with_variants consume catalog.load_blocks; renderer
  projection caches kept local but keyed via
  catalog.get_catalog_mtime(). Per-projection invalidation keys
  (_CATALOG_MAP_MTIME / _CATALOG_VARIANT_MAP_MTIME) introduced. import
  yaml, CATALOG_PATH, legacy _CATALOG_MTIME removed.
- tests NEW tests/test_catalog_shared_loader.py (421 lines, 23 cases):
  shared loader + 3 wrappers covering single file-read, contract
  preservation, signature preservation, shared cache, private state
  absence, mtime invalidation propagation to renderer projections.

Verification:
- pytest tests/test_catalog_shared_loader.py -v: 23/23 PASS in 0.13s.
- pytest tests/ -q --ignore=tests/matching: 365/365 PASS in 38.10s.
- src/fit_verifier.py, src/space_allocator.py, src/pipeline.py and
  templates/catalog.yaml unchanged (git diff empty).

Out of scope:
- catalog.yaml schema/path unchanged.
- Catalog direct-read call sites in fit_verifier / space_allocator /
  pipeline left for a separate follow-up axis.
- Phase Z 22-step runtime, frame_selection, light_edit/restructure
  flows untouched.

Refs: IMP-27 (gitea #27), INSIGHT-MAP §5 K5, PHASE-Q-AUDIT §2.10
This commit is contained in:
2026-05-20 19:31:26 +09:00
parent 2896bb691c
commit 909bf75edc
5 changed files with 550 additions and 101 deletions

View File

@@ -20,9 +20,10 @@ import re
from pathlib import Path
from typing import Any
import yaml
from jinja2 import Environment, FileSystemLoader
from src import catalog as _catalog_mod
logger = logging.getLogger(__name__)
# 템플릿 디렉토리
@@ -101,32 +102,18 @@ RELATION_CATEGORY_MAP: dict[str, list[str]] = {
# ══════════════════════════════════════
# 카탈로그 로딩 (mtime 캐싱)
# 카탈로그 로딩 (IMP-27: src.catalog 공유 로더 위임)
# ══════════════════════════════════════
_catalog_cache: dict[str, Any] = {"data": None, "mtime": 0}
def _load_catalog() -> list[dict]:
"""catalog.yaml 로드 (mtime 캐싱)."""
path = TEMPLATES_DIR / "catalog.yaml"
mtime = path.stat().st_mtime
if _catalog_cache["data"] is not None and _catalog_cache["mtime"] == mtime:
return _catalog_cache["data"]
data = yaml.safe_load(path.read_text(encoding="utf-8"))
blocks = data.get("blocks", [])
_catalog_cache["data"] = blocks
_catalog_cache["mtime"] = mtime
return blocks
"""catalog.yaml blocks list (IMP-27: shared loader delegation)."""
return _catalog_mod.load_blocks()
def _get_block_by_id(block_id: str) -> dict | None:
"""블록 ID로 카탈로그 엔트리 조회."""
for b in _load_catalog():
if b["id"] == block_id:
return b
return None
"""블록 ID로 카탈로그 엔트리 조회 (IMP-27: shared loader delegation)."""
return _catalog_mod.get_block_by_id(block_id)
# ══════════════════════════════════════

View File

@@ -5,24 +5,18 @@ AI에게 불가능한 선택지를 주지 않는다 (Beautiful.ai 원칙).
주요 함수:
- select_block_candidates(): topic + 컨테이너 → 물리적으로 가능한 후보 2-4개
- load_catalog(): catalog.yaml 로딩 + 캐싱
- load_catalog(): catalog.yaml 로딩 + 캐싱 (IMP-27: src.catalog 공유 로더 위임)
"""
from __future__ import annotations
import logging
from pathlib import Path
from typing import Any
import yaml
from src import catalog as _catalog_mod
from src.space_allocator import ContainerSpec, HEIGHT_COST_ORDER
logger = logging.getLogger(__name__)
CATALOG_PATH = Path("templates/catalog.yaml")
_catalog_cache: dict | None = None
_catalog_mtime: float = 0.0
# ──────────────────────────────────────
# relation_type → 블록 카테고리 매핑 (Napkin.ai 방식)
@@ -52,35 +46,16 @@ BLOCKS_FORCING_FORMAT_CHANGE = {
# ──────────────────────────────────────
# catalog.yaml 로딩 (mtime 캐시)
# catalog.yaml 로딩 (IMP-27: src.catalog 공유 로더 위임)
# ──────────────────────────────────────
def load_catalog() -> dict:
"""catalog.yaml을 로딩한다. mtime 기반 캐싱."""
global _catalog_cache, _catalog_mtime
if not CATALOG_PATH.exists():
logger.error(f"catalog.yaml 미발견: {CATALOG_PATH}")
return {"blocks": []}
current_mtime = CATALOG_PATH.stat().st_mtime
if _catalog_cache is not None and current_mtime == _catalog_mtime:
return _catalog_cache
with open(CATALOG_PATH, encoding="utf-8") as f:
_catalog_cache = yaml.safe_load(f)
_catalog_mtime = current_mtime
block_count = len(_catalog_cache.get("blocks", []))
logger.info(f"[Q-2] catalog.yaml 로딩: {block_count}개 블록")
return _catalog_cache
"""catalog.yaml root dict (IMP-27: shared loader delegation)."""
return _catalog_mod.load_root_catalog()
def _get_block_by_id(block_id: str, catalog: dict) -> dict | None:
"""catalog에서 블록 ID로 검색."""
for block in catalog.get("blocks", []):
if block.get("id") == block_id:
return block
return None
"""catalog-injected 블록 ID 조회 (IMP-27: shared loader delegation)."""
return _catalog_mod.get_block_by_id(block_id, catalog)
# ──────────────────────────────────────

76
src/catalog.py Normal file
View File

@@ -0,0 +1,76 @@
"""IMP-27: Shared catalog.yaml loader (single file-read + mtime cache).
Phase Q evolution 중 block_reference, block_selector, renderer 가 각각 templates/
catalog.yaml 을 읽고 mtime 캐시하던 중복을 한 곳으로 통합한다. call-site
signature 는 그대로 유지되며, 각 wrapper 는 본 모듈의 결과를 자신이 약속하는
형태(list[dict] / root dict / id→path projection)로 변환만 수행한다.
Functions:
load_root_catalog() -> dict : raw catalog dict (matches block_selector contract)
load_blocks() -> list[dict] : root_catalog.get("blocks", []) projection
get_block_by_id(block_id, catalog=None) -> dict | None
get_catalog_mtime() -> float : current cached mtime (renderer projection key)
"""
from __future__ import annotations
import logging
from pathlib import Path
import yaml
logger = logging.getLogger(__name__)
CATALOG_PATH = Path(__file__).parent.parent / "templates" / "catalog.yaml"
_catalog_cache: dict | None = None
_catalog_mtime: float = 0.0
def load_root_catalog() -> dict:
"""Load templates/catalog.yaml as root dict, with mtime caching.
Missing file → logs warning and returns ``{"blocks": []}`` (matches the
pre-IMP-27 behavior of block_selector.load_catalog and renderer._load_catalog_map).
"""
global _catalog_cache, _catalog_mtime
if not CATALOG_PATH.exists():
logger.warning(f"catalog.yaml 미발견: {CATALOG_PATH}")
return {"blocks": []}
current_mtime = CATALOG_PATH.stat().st_mtime
if _catalog_cache is not None and current_mtime == _catalog_mtime:
return _catalog_cache
with open(CATALOG_PATH, encoding="utf-8") as f:
_catalog_cache = yaml.safe_load(f)
_catalog_mtime = current_mtime
block_count = len((_catalog_cache or {}).get("blocks", []))
logger.info(f"[catalog] load: {block_count} blocks")
return _catalog_cache
def load_blocks() -> list[dict]:
"""Return blocks list (= root_catalog.get('blocks', []))."""
return load_root_catalog().get("blocks", [])
def get_block_by_id(block_id: str, catalog: dict | None = None) -> dict | None:
"""Locate a block entry by id.
``catalog=None`` → uses shared loader. caller-supplied catalog dict is
accepted as-is so the existing block_selector contract (catalog-injected)
keeps working unchanged.
"""
if catalog is None:
catalog = load_root_catalog()
for block in catalog.get("blocks", []):
if block.get("id") == block_id:
return block
return None
def get_catalog_mtime() -> float:
"""Current cached mtime (renderer projection caches key off this)."""
return _catalog_mtime

View File

@@ -13,86 +13,76 @@ from collections import OrderedDict
from pathlib import Path
from typing import Any
import yaml
from jinja2 import Environment, FileSystemLoader
from src import catalog as _catalog_mod
logger = logging.getLogger(__name__)
TEMPLATES_DIR = Path(__file__).parent.parent / "templates"
STATIC_DIR = Path(__file__).parent.parent / "static"
CATALOG_PATH = TEMPLATES_DIR / "catalog.yaml"
# 카테고리 검색 순서
BLOCK_CATEGORIES = ["headers", "cards", "tables", "visuals", "emphasis", "media"]
# catalog.yaml에서 id → template 경로 매핑 로드 (BF-10: mtime 체크로 자동 갱신)
# id → template 경로 매핑 (IMP-27: src.catalog 공유 로더 위임, renderer-local projection cache)
_CATALOG_MAP: dict[str, str] | None = None
_CATALOG_MTIME: float = 0.0
_CATALOG_MAP_MTIME: float = 0.0
# Phase R: variant별 template 경로 캐시 (renderer-local projection)
_CATALOG_VARIANT_MAP: dict[str, str] | None = None
_CATALOG_VARIANT_MAP_MTIME: float = 0.0
def _load_catalog_map() -> dict[str, str]:
"""catalog.yaml에서 블록 id → template 경로 매핑을 로드한다.
"""블록 id → template 경로 projection (IMP-27: src.catalog 공유 로더 위임).
파일 수정시간(mtime)을 확인하여, 변경 시에만 재로드한다.
catalog 파일 읽기와 mtime 캐싱은 ``src.catalog`` 가 단독 소유. 본 함수는
그 결과를 ``id → template`` 형태로 변환한 renderer-local projection 캐시만
유지하며, projection 무효화는 ``src.catalog.get_catalog_mtime()`` 키잉.
"""
global _CATALOG_MAP, _CATALOG_MTIME
global _CATALOG_MAP, _CATALOG_MAP_MTIME
current_mtime = CATALOG_PATH.stat().st_mtime if CATALOG_PATH.exists() else 0.0
blocks = _catalog_mod.load_blocks()
current_mtime = _catalog_mod.get_catalog_mtime()
if _CATALOG_MAP is not None and _CATALOG_MTIME == current_mtime:
return _CATALOG_MAP # 파일 변경 없음 → 캐시 재사용
if _CATALOG_MAP is not None and _CATALOG_MAP_MTIME == current_mtime:
return _CATALOG_MAP
# 변경 감지 또는 첫 로드 → 새로 읽기
_CATALOG_MTIME = current_mtime
_CATALOG_MAP_MTIME = current_mtime
_CATALOG_MAP = {}
if CATALOG_PATH.exists():
try:
with open(CATALOG_PATH, encoding="utf-8") as f:
catalog = yaml.safe_load(f)
for block in catalog.get("blocks", []):
block_id = block.get("id", "")
template = block.get("template", "")
if block_id and template:
_CATALOG_MAP[block_id] = template
logger.info(f"catalog.yaml 로드: {len(_CATALOG_MAP)}개 블록 매핑")
except Exception as e:
logger.warning(f"catalog.yaml 로드 실패: {e}")
else:
logger.warning(f"catalog.yaml 미발견: {CATALOG_PATH}")
for block in blocks:
block_id = block.get("id", "")
template = block.get("template", "")
if block_id and template:
_CATALOG_MAP[block_id] = template
logger.info(f"catalog.yaml 로드: {len(_CATALOG_MAP)}개 블록 매핑")
return _CATALOG_MAP
# Phase R: variant별 template 경로 캐시
_CATALOG_VARIANT_MAP: dict[str, str] | None = None
def _load_catalog_map_with_variants() -> dict[str, str]:
"""catalog.yaml에서 variant별 template 경로 매핑을 로드한다.
"""variant별 template 경로 projection (IMP-27: src.catalog 공유 로더 위임).
키: "block_id--variant_id" → 값: template 경로
키: "block_id--variant_id" → 값: template 경로.
"""
global _CATALOG_VARIANT_MAP
global _CATALOG_VARIANT_MAP, _CATALOG_VARIANT_MAP_MTIME
# _load_catalog_map이 이미 캐시 관리하므로 같은 mtime 사용
_load_catalog_map() # 캐시 갱신 보장
blocks = _catalog_mod.load_blocks()
current_mtime = _catalog_mod.get_catalog_mtime()
if _CATALOG_VARIANT_MAP is not None and _CATALOG_MTIME == (CATALOG_PATH.stat().st_mtime if CATALOG_PATH.exists() else 0.0):
if _CATALOG_VARIANT_MAP is not None and _CATALOG_VARIANT_MAP_MTIME == current_mtime:
return _CATALOG_VARIANT_MAP
_CATALOG_VARIANT_MAP_MTIME = current_mtime
_CATALOG_VARIANT_MAP = {}
if CATALOG_PATH.exists():
try:
with open(CATALOG_PATH, encoding="utf-8") as f:
catalog = yaml.safe_load(f)
for block in catalog.get("blocks", []):
block_id = block.get("id", "")
for variant in block.get("variants", []):
vid = variant.get("id", "default")
vtemplate = variant.get("template", "")
if vid != "default" and vtemplate:
_CATALOG_VARIANT_MAP[f"{block_id}--{vid}"] = vtemplate
except Exception as e:
logger.warning(f"catalog variant 로드 실패: {e}")
for block in blocks:
block_id = block.get("id", "")
for variant in block.get("variants", []):
vid = variant.get("id", "default")
vtemplate = variant.get("template", "")
if vid != "default" and vtemplate:
_CATALOG_VARIANT_MAP[f"{block_id}--{vid}"] = vtemplate
return _CATALOG_VARIANT_MAP