C.E.L_Slide_test2/tests/matching/case1_only.py

"""CASE 1만 생성 (IDF-only 포함 8개 방법)"""
import sys
import json
import yaml
from pathlib import Path

sys.path.insert(0, str(Path(__file__).parent))

from common import load_figma_texts
from extract_units import extract_units
from methods import (
    method_tfidf, method_bm25, method_idf_only, method_char_ngram,
    method_kiwi_bm25, method_structural,
    method_ai_metadata_matcher,
    method_hybrid_kiwi_char,
)

ROOT = Path(r"d:\ad-hoc\kei\design_agent")
PREVIEW_DIR = ROOT / "data" / "figma_previews"

UNIT_ORDER = [
    ("MDX01-intro", "중목차 앞 본문"),
    ("MDX01-intro-details", "팝업"),
    ("MDX01-1", "중목차"),
    ("MDX01-2", "중목차"),
    ("MDX01-2-image", "이미지"),
    ("MDX01-2-details", "팝업+표"),
    ("MDX02-1", "중목차"),
    ("MDX02-1-image", "이미지"),
    ("MDX02-2", "중목차(컨테이너)"),
    ("MDX02-2.1", "소목차"),
    ("MDX02-2.2", "소목차"),
    ("MDX02-2.2-table", "표"),
    ("MDX03-1", "중목차"),
    ("MDX03-2", "중목차(컨테이너)"),
    ("MDX03-2.1", "소목차"),
    ("MDX03-2.1-table", "표"),
    ("MDX03-2.2", "소목차"),
]


def fmt_score(score, method_name):
    if method_name in ("TF-IDF", "Char-ngram", "AI-Meta", "Structural", "하이브리드"):
        return f"{score * 100:.0f}%"
    else:
        return f"{score:.1f}"


def main():
    units = extract_units()
    figma = load_figma_texts()

    with open(PREVIEW_DIR / "index.json", encoding="utf-8") as f:
        idx_data = json.load(f)
    frame_to_short = {info["frame_id"]: sid for sid, info in idx_data.items()}
    short_to_info = idx_data

    with open(Path(__file__).parent / "metadata_db.yaml", encoding="utf-8") as f:
        metadata_db = yaml.safe_load(f)

    extra_meta = {
        "MDX01-intro-details": {"concepts": ["정책", "디지털화", "BIM", "스마트건설", "사례"], "layout_hint": "popup-list"},
        "MDX01-2-image": {"concepts": ["DX", "핵심기술", "상호관계", "GIS", "BIM", "디지털트윈"], "layout_hint": "diagram"},
        "MDX01-2-details": {"concepts": ["BIM", "DX", "비교", "범위", "S/W", "프로세스", "성과품", "활용", "확장성", "수행개념", "CIVIL", "IT", "주체", "발주처", "설계사", "시공사"], "layout_hint": "compare-rows"},
        "MDX02-1-image": {"concepts": ["DX", "목표", "안전", "품질", "생산성", "소통", "신뢰"], "layout_hint": "cycle-3way"},
        "MDX02-2.1": {"concepts": ["Process", "변화", "수작업", "S/W", "체계화", "2D", "3D", "협업", "검증", "사전"], "layout_hint": "transition-list"},
        "MDX02-2.2": {"concepts": ["발주자", "시공자", "설계자", "역량", "기대효과", "3D모델", "협업", "Claim", "리스크", "품질"], "layout_hint": "persona-3col"},
        "MDX02-2.2-table": {"concepts": ["발주자", "시공자", "설계자", "필요역량", "업무", "변화", "3D", "검증", "협업", "표"], "layout_hint": "table-3col"},
        "MDX03-2.1": {"concepts": ["Process", "Analogue", "Digital", "혁신", "GIS", "BIM", "Solution", "2D", "3D", "협업"], "layout_hint": "compare-2col"},
        "MDX03-2.1-table": {"concepts": ["Analogue", "Digital", "As-is", "To-be", "2D", "3D", "문서", "행정", "시각화", "소통", "표"], "layout_hint": "compare-2col"},
        "MDX03-2.2": {"concepts": ["Product", "결과", "성과물", "품질", "Digital", "정보물", "Solution", "협업", "통합관리"], "layout_hint": "compare-2col"},
    }
    combined_meta = {**metadata_db.get("mdx_sections", {}), **extra_meta}

    # 8개 방법 (IDF-only 포함)
    methods_def = [
        ("TF-IDF", method_tfidf),
        ("BM25", method_bm25),
        ("IDF-only", method_idf_only),
        ("Char-ngram", method_char_ngram),
        ("Kiwi+BM25", method_kiwi_bm25),
        ("Structural", method_structural),
        ("AI-Meta", None),
        ("하이브리드", method_hybrid_kiwi_char),
    ]

    # 실행
    results = {}
    for uid, unit_text in units.items():
        results[uid] = {}
        for mname, fn in methods_def:
            if not unit_text.strip():
                results[uid][mname] = []
                continue
            if mname == "AI-Meta":
                ranked = method_ai_metadata_matcher(uid, metadata_db["figma_frames"], combined_meta)
            else:
                ranked = fn(unit_text, figma)
            results[uid][mname] = ranked[:3]

    # 리포트
    png_rel = "../../data/figma_previews/"
    lines = []
    lines.append("# CASE 1 — 균등 가중 매칭 (IDF-only 포함)")
    lines.append("")
    lines.append("전체 텍스트 (블릿 포함) 원본 그대로. 가중치 없음. 8개 방법 비교.")
    lines.append("")

    for i, (uid, kind) in enumerate(UNIT_ORDER, 1):
        lines.append(f"---")
        lines.append("")
        lines.append(f"## {i}. {uid} ({kind})")
        lines.append("")
        lines.append("| 방법 | 1순위 | 2순위 | 3순위 |")
        lines.append("|------|-------|-------|-------|")
        for mname, _ in methods_def:
            cells = [mname]
            top3 = results[uid].get(mname, [])
            if not top3:
                cells += ["-", "-", "-"]
            else:
                for fid, score in top3:
                    short = frame_to_short.get(str(fid), "?")
                    info = short_to_info.get(short, {})
                    png_file = info.get("png", "")
                    title = info.get("title_text", "").strip().replace("\n", " ") or ""
                    if len(title) > 15:
                        title = title[:15] + "…"
                    cell = f"![{short}]({png_rel}{png_file})<br>**{short}** ({fmt_score(score, mname)})<br>{title}"
                    cells.append(cell)
                while len(cells) < 4:
                    cells.append("-")
            lines.append("| " + " | ".join(cells) + " |")
        lines.append("")

    out_path = Path(__file__).parent / "MATRIX_CASE1.md"
    out_path.write_text("\n".join(lines), encoding="utf-8")
    print(f"완료: {out_path}")


if __name__ == "__main__":
    main()