"""전체 32 frame anchor_sets 일람 뷰 (리뷰용).

간결한 한 페이지 HTML. 각 frame 의 anchor_set id + terms 만 나열.
raw 수치가 필요하면 anchor_sets_report.html 참조.

입력:
  anchor_sets_draft.yaml
  actual_text_nodes.yaml (frame 주제 표시용)
  normalized_text_tokens.yaml (mdx_df 참고)

출력:
  ANCHOR_SETS_OVERVIEW.md
  ANCHOR_SETS_OVERVIEW.html
"""
from pathlib import Path
import yaml
import markdown

HERE = Path(__file__).parent

DRAFT = HERE / "anchor_sets_draft.yaml"
NODES = HERE / "actual_text_nodes.yaml"
NORMALIZED = HERE / "normalized_text_tokens.yaml"
OUT_MD = HERE / "ANCHOR_SETS_OVERVIEW.md"
OUT_HTML = HERE / "ANCHOR_SETS_OVERVIEW.html"

TARGET_FRAMES = {13, 14, 18, 29}


def load_yaml(p):
    return yaml.safe_load(p.read_text(encoding='utf-8'))


def get_subject(frame_id, nodes_data):
    """frame 의 주제 짧게 — texts.md 첫 몇 줄을 붙임."""
    info = nodes_data['frames'].get(frame_id, {})
    tn = info.get('text_nodes', [])
    if not tn:
        return '(텍스트 없음)'
    # 처음 2-3 줄
    out = []
    total_len = 0
    for t in tn[:5]:
        if total_len + len(t) > 100:
            break
        out.append(t)
        total_len += len(t)
    return ' / '.join(out) if out else tn[0][:80]


def term_badge(term_obj, corpus_mdx_df):
    """token 을 mdx_hit 표시와 함께 짧게 렌더."""
    tok = term_obj['token']
    if not term_obj.get('in_frame'):
        return f"⚠{tok}"
    mdx = term_obj.get('mdx_df', 0)
    special = term_obj.get('is_special', False)
    marks = []
    if special:
        marks.append('S')
    if mdx > 0:
        marks.append(f'M{mdx}')
    mark_str = f"<sup>{','.join(marks)}</sup>" if marks else ''
    return f"{tok}{mark_str}"


def collect_review_set_ids(frame_out):
    ids = set()
    for rv in frame_out.get('review_needed') or []:
        tok = rv.get('token', '')
        if tok.endswith('(set)'):
            ids.add(tok.replace('(set)', '').strip())
    return ids


def collect_review_tokens(frame_out):
    out = set()
    for rv in frame_out.get('review_needed') or []:
        tok = rv.get('token', '')
        if tok.endswith('(set)'):
            continue
        out.add(tok)
    return out


def render_frame_md(fnum, fid, frame_out, subject):
    is_target = fnum in TARGET_FRAMES
    target_mark = ' 🎯 **TARGET**' if is_target else ''
    lines = [f"### Frame {fnum} / {fid}{target_mark}", ""]
    lines.append(f"**Subject**: {subject}")
    lines.append(f"**total_unique_tokens**: {frame_out.get('total_unique_tokens', '?')}")
    lines.append("")

    rn_set_ids = collect_review_set_ids(frame_out)
    rn_tokens = collect_review_tokens(frame_out)

    anchor_sets = frame_out.get('anchor_sets', [])
    if not anchor_sets:
        lines.append("_(anchor_set 없음)_")
        lines.append("")
        return '\n'.join(lines)

    lines.append("**Anchor sets**:")
    lines.append("")
    for aset in anchor_sets:
        set_id = aset['id']
        set_mark = ' 🔸**review_needed**' if set_id in rn_set_ids else ''
        term_strs = []
        for t in aset.get('terms', []):
            tok = t['token']
            marks = []
            if t.get('is_special'): marks.append('S')
            if t.get('mdx_df', 0) > 0: marks.append(f"M{t['mdx_df']}")
            if tok in rn_tokens: marks.append('RN')
            if not t.get('in_frame'): marks.append('⚠')
            mark_str = f" ({','.join(marks)})" if marks else ''
            term_strs.append(f"`{tok}`{mark_str}")
        lines.append(f"- **{set_id}**{set_mark}: {', '.join(term_strs)}")

    # notes
    notes = frame_out.get('notes')
    if notes:
        lines.append("")
        lines.append(f"**Notes**: _{notes.strip()}_")
    lines.append("")
    return '\n'.join(lines)


def main():
    draft = load_yaml(DRAFT)
    nodes = load_yaml(NODES)
    norm = load_yaml(NORMALIZED)
    corpus_mdx_df = norm['corpus']['token_mdx_df']

    frame_ids = sorted(draft['frames'].keys())

    md = [
        "# Anchor Sets Overview — 전체 32 frame 일람",
        "",
        "리뷰용 한 페이지 뷰. 각 anchor_set 의 id + terms 만 표시.",
        "상세 수치는 `anchor_sets_report.html` 참조.",
        "",
        "**범례**:",
        "- `S` = special token (S/W, H/W, 2D, 3D, DX, BIM, As-is, To-Be, 결과혁신, 과정혁신, 필수조건, 의사소통, 시행착오)",
        "- `M1/M2/M3` = 해당 token 의 mdx_df (MDX section 몇 개에 등장)",
        "- `RN` = review_needed term",
        "- 🔸 = set 레벨 review_needed (유지하되 재검토)",
        "- 🎯 TARGET = MDX 매칭 정답 frame (13, 14, 18, 29)",
        "",
        f"- frames: **{len(frame_ids)}**",
        f"- anchor_sets: **{sum(len(f.get('anchor_sets', [])) for f in draft['frames'].values())}**",
        "",
        "---",
        "",
    ]

    for fid in frame_ids:
        frame_out = draft['frames'][fid]
        fnum = frame_out['frame_number']
        subject = get_subject(fid, nodes)
        md.append(render_frame_md(fnum, fid, frame_out, subject))

    md_text = '\n'.join(md)
    OUT_MD.write_text(md_text, encoding='utf-8')

    html_body = markdown.markdown(md_text, extensions=['tables'])
    html = f"""<!DOCTYPE html>
<html lang="ko">
<head>
<meta charset="utf-8">
<title>Anchor Sets Overview — 전체 32 frame 일람</title>
<style>
body {{ font-family: -apple-system, "Segoe UI", Pretendard, sans-serif; max-width: 1100px; margin: 2em auto; padding: 0 1.5em 3em; line-height: 1.55; color: #222; }}
h1 {{ border-bottom: 2px solid #333; padding-bottom: 0.2em; }}
h3 {{ margin-top: 2em; color: #111; border-bottom: 1px solid #ddd; padding-bottom: 0.3em; }}
h3:has(em) {{ background: #fffbdc; padding: 0.4em 0.6em; border-radius: 4px; }}
ul {{ margin: 0.3em 0 0.8em 0; }}
li {{ margin: 0.15em 0; }}
code {{ background: #f4f4f4; padding: 1px 5px; border-radius: 3px; font-size: 0.92em; }}
strong {{ color: #0a6; }}
em {{ color: #888; font-style: normal; }}
sup {{ color: #d33; font-size: 0.7em; margin-left: 1px; }}
.subject, p > strong + em {{ color: #555; }}
hr {{ border: 0; border-top: 1px solid #ddd; margin: 1.5em 0; }}
</style>
</head>
<body>
{html_body}
</body>
</html>"""
    OUT_HTML.write_text(html, encoding='utf-8')

    print(f"산출:")
    print(f"  md:   {OUT_MD}")
    print(f"  html: {OUT_HTML}")
    print(f"  frames: {len(frame_ids)}")


if __name__ == "__main__":
    main()