features/sentiment/run.py

"""감성분석 실행 탭.

Job 관리, Pre-flight 체크, 파이프라인 시각화.
"""
import streamlit as st
import pandas as pd

from core.api_client import ChainShiftClient
from core.job_realtime import (
    get_active_jobs,
    get_recent_jobs,
    format_job_duration,
    get_status_emoji,
    get_status_label,
)


def render(data: dict):
    """실행 탭 렌더링."""
    st.markdown("##### 🚀 감성분석 실행")
    st.caption("캠페인의 감성분석 Job을 시작하고 진행 상황을 확인합니다")

    if not data or (not data.get("api_key") and not data.get("access_token")):
        st.warning("인증 정보가 설정되지 않았습니다.")
        return

    analysis_client = ChainShiftClient(api_key=data.get("api_key"), access_token=data.get("access_token"))

    # --- Job Status ---
    if st.button("🔄 새로고침", key="sentiment:manual_refresh_jobs"):
        st.rerun()

    try:
        active_jobs = get_active_jobs(campaign_id=data["campaign_id"], limit=5)
        recent_jobs = get_recent_jobs(campaign_id=data["campaign_id"], limit=20)
        active_ids = {j["id"] for j in active_jobs}
        jobs_list = active_jobs + [j for j in recent_jobs if j["id"] not in active_ids]
    except Exception as e:
        active_jobs = []
        jobs_list = []
        st.warning(f"Job 목록 로드 실패: {e}")

    has_active = len(active_jobs) > 0

    # --- Pipeline Visualization ---
    st.markdown("---")
    st.markdown("###### 📊 데이터 파이프라인")

    _render_pipeline(data)

    # --- Brand Status ---
    _render_brand_status(analysis_client, data.get("campaign_id"))

    # --- Current status + Start button ---
    st.markdown("---")
    st.markdown("###### ▶️ 분석 실행")

    if has_active:
        _render_active_job(active_jobs[0], analysis_client)
    else:
        _render_inactive_state(jobs_list, analysis_client, data.get("campaign_id"))

    # --- Job history ---
    st.markdown("---")
    st.markdown("###### 📋 Job 이력")

    if jobs_list:
        _render_job_history(jobs_list)
    else:
        st.caption("Job 이력이 없습니다.")


def _fetch_brands(client: ChainShiftClient, campaign_id: int) -> list[dict]:
    """캠페인 브랜드 목록 조회 (session_state 캐시)."""
    cache_key = f"campaign_brands_{campaign_id}"
    if cache_key in st.session_state:
        return st.session_state[cache_key]
    try:
        brands = client.get_campaign_brands(campaign_id)
        st.session_state[cache_key] = brands
        return brands
    except Exception:
        return []


def _render_brand_status(client: ChainShiftClient, campaign_id: int):
    """캠페인 브랜드 현황 표시."""
    brands = _fetch_brands(client, campaign_id)
    if not brands:
        return

    in_house = [b for b in brands if b.get("brand_type") in ("PRIMARY", "USER")]
    competitor = [b for b in brands if b.get("brand_type") == "SECONDARY"]

    with st.expander(f"🏷️ 캠페인 브랜드 현황 (자사 {len(in_house)}개 / 경쟁사 {len(competitor)}개)", expanded=False):
        col1, col2 = st.columns(2)
        with col1:
            st.markdown(f"**자사 브랜드** ({len(in_house)}개)")
            if in_house:
                for b in in_house:
                    synonyms = b.get("synonyms") or []
                    syn_text = f"  \n유사어: {', '.join(synonyms)}" if synonyms else ""
                    st.markdown(f"- **{b['name']}**{syn_text}")
            else:
                st.caption("등록된 자사 브랜드 없음")
        with col2:
            st.markdown(f"**경쟁사 브랜드** ({len(competitor)}개)")
            if competitor:
                for b in competitor:
                    synonyms = b.get("synonyms") or []
                    syn_text = f"  \n유사어: {', '.join(synonyms)}" if synonyms else ""
                    st.markdown(f"- **{b['name']}**{syn_text}")
            else:
                st.caption("등록된 경쟁사 브랜드 없음")


def _render_pipeline(data: dict):
    """파이프라인 시각화."""
    pipe_col1, pipe_col2, pipe_col3, pipe_col4 = st.columns(4)

    overview_total = data.get("overview_total_answers") or 0
    overview_ih_neg = data.get("overview_nudge_candidates") or 0
    overview_llm_done = data.get("overview_llm_verified") or 0
    fp_rate = data.get("overview_false_positive_rate") or 0
    overview_llm_confirmed = overview_llm_done - int(overview_llm_done * fp_rate)

    with pipe_col1:
        st.markdown(f"""
        <div style="background: #DBEAFE; border-radius: 8px; padding: 12px; text-align: center;">
            <div style="font-size: 24px;">📥</div>
            <div style="font-weight: bold;">1. 데이터 수집</div>
            <div style="font-size: 20px; color: #1D4ED8;">{overview_total:,}</div>
            <div style="font-size: 12px; color: #6B7280;">AI 답변</div>
        </div>
        """, unsafe_allow_html=True)

    with pipe_col2:
        ih_rate = (overview_ih_neg / overview_total * 100) if overview_total > 0 else 0
        st.markdown(f"""
        <div style="background: #FEF3C7; border-radius: 8px; padding: 12px; text-align: center;">
            <div style="font-size: 24px;">🔍</div>
            <div style="font-weight: bold;">2. DeBERTa 분석</div>
            <div style="font-size: 20px; color: #D97706;">{overview_ih_neg:,}</div>
            <div style="font-size: 12px; color: #6B7280;">부정 감지 ({ih_rate:.1f}%)</div>
        </div>
        """, unsafe_allow_html=True)

    with pipe_col3:
        verify_rate = (overview_llm_done / overview_ih_neg * 100) if overview_ih_neg > 0 else 0
        st.markdown(f"""
        <div style="background: #D1FAE5; border-radius: 8px; padding: 12px; text-align: center;">
            <div style="font-size: 24px;">🤖</div>
            <div style="font-weight: bold;">3. LLM 검증</div>
            <div style="font-size: 20px; color: #059669;">{overview_llm_done:,}</div>
            <div style="font-size: 12px; color: #6B7280;">완료 ({verify_rate:.0f}%)</div>
        </div>
        """, unsafe_allow_html=True)

    with pipe_col4:
        confirm_rate = (overview_llm_confirmed / overview_llm_done * 100) if overview_llm_done > 0 else 0
        st.markdown(f"""
        <div style="background: #FEE2E2; border-radius: 8px; padding: 12px; text-align: center;">
            <div style="font-size: 24px;">🎯</div>
            <div style="font-weight: bold;">4. 정탐</div>
            <div style="font-size: 20px; color: #DC2626;">{overview_llm_confirmed:,}</div>
            <div style="font-size: 12px; color: #6B7280;">정탐률 {confirm_rate:.1f}%</div>
        </div>
        """, unsafe_allow_html=True)


def _render_active_job(active: dict, client: ChainShiftClient):
    """활성 Job 렌더링."""
    progress = active.get("progress", 0)
    status = active.get("status", "")
    status_emoji = get_status_emoji(status)
    status_label = get_status_label(status)
    duration = format_job_duration(active)
    message = active.get("message", "처리 중...")
    total_answers = active.get("total_answers", 0)
    processed = active.get("processed_answers", 0)

    st.markdown(f"""
    <div style="background: linear-gradient(135deg, #EBF5FF 0%, #F0F9FF 100%);
                border-radius: 12px; padding: 20px; margin-bottom: 16px;
                border: 1px solid #BFDBFE;">
        <div style="display: flex; justify-content: space-between; align-items: center;">
            <div>
                <span style="font-size: 28px;">{status_emoji}</span>
                <span style="font-size: 20px; font-weight: bold; margin-left: 8px;">{status_label}</span>
            </div>
            <div style="text-align: right;">
                <div style="font-size: 32px; font-weight: bold; color: #1D4ED8;">{progress}%</div>
                <div style="font-size: 12px; color: #6B7280;">소요시간: {duration}</div>
            </div>
        </div>
        <div style="margin-top: 12px; font-size: 14px; color: #374151;">
            {message}
        </div>
        <div style="margin-top: 8px; font-size: 12px; color: #6B7280;">
            처리: {processed:,} / {total_answers:,} 답변
        </div>
    </div>
    """, unsafe_allow_html=True)

    st.progress(progress / 100)

    if st.button("⛔ 분석 취소", key="sentiment:cancel_job", type="secondary"):
        try:
            client.cancel_analysis_job(active["id"])
            st.success("취소 요청 완료")
            st.rerun()
        except Exception as e:
            st.error(f"취소 실패: {e}")


def _render_inactive_state(jobs_list: list, client: ChainShiftClient, campaign_id: int):
    """비활성 상태 렌더링."""
    # --- 최근 분석 상태 ---
    if jobs_list:
        latest = jobs_list[0]
        latest_status = latest.get("status", "")
        latest_emoji = get_status_emoji(latest_status)
        latest_label = get_status_label(latest_status)
        latest_duration = format_job_duration(latest)
        completed_at = latest.get("completed_at") or latest.get("created_at") or ""
        if completed_at:
            completed_at = completed_at[:19].replace("T", " ")

        if latest_status == "completed":
            st.success(f"{latest_emoji} 최근 분석: **{latest_label}** (소요: {latest_duration}, {completed_at})")
        elif latest_status == "failed":
            st.error(f"{latest_emoji} 최근 분석: **{latest_label}** - {(latest.get('error_message') or '알 수 없는 오류')[:50]}")
        else:
            st.info(f"{latest_emoji} 최근 분석: **{latest_label}** ({completed_at})")
    else:
        st.info("아직 실행된 분석이 없습니다.")

    # --- 분석 설정 ---
    st.markdown("###### 분석 설정")
    col1, col2 = st.columns(2)
    with col1:
        run_brand = st.checkbox("자사/경쟁사 감성 분석", value=True, key="run:brand")
    with col2:
        run_keyword = st.checkbox("키워드 감성 분석", value=False, key="run:keyword")

    # 키워드 입력 (keyword scope 선택 시)
    keywords = []
    if run_keyword:
        keywords_input = st.text_input(
            "분석 키워드 (쉼표 구분)",
            key="run:keywords",
            placeholder="사료, 소화, 알러지",
        )
        keywords = [k.strip() for k in keywords_input.split(",") if k.strip()]

    # LLM 검증 옵션
    include_llm = st.checkbox(
        "2차 LLM 검증 포함",
        value=False,
        key="run:llm",
        help="부정 감지 결과를 LLM으로 교차 검증합니다 (시간 추가)",
    )

    # 분석 시작 버튼 (keyword 선택 시 키워드 입력 필수)
    can_start = run_brand or (run_keyword and len(keywords) > 0)
    if st.button(
        "▶️ 분석 시작",
        type="primary",
        key="sentiment:start_analysis",
        disabled=not can_start,
    ):
        scope = []
        if run_brand:
            scope.append("brand")
        if run_keyword:
            scope.append("keyword")

        options = {
            "scope": scope,
            "keywords": keywords if run_keyword else [],
            "include_llm_verification": include_llm,
        }
        try:
            client.start_analysis_job(campaign_id, options=options)
            st.success("분석 Job이 생성되었습니다!")
            st.rerun()
        except Exception as e:
            st.error(f"분석 시작 실패: {e}")

    # --- 연구 분석 스캐폴딩 ---
    st.markdown("---")
    st.markdown("###### 연구 분석 (준비 중)")
    st.info(
        "연구 분석은 데이터팀 Athena 테이블 세팅 완료 후 사용 가능합니다.\n"
        "필요 테이블: `fanouts` (S3 스냅샷 미포함)"
    )


def _render_job_history(jobs_list: list):
    """Job 이력 테이블."""
    rows = []
    for j in jobs_list:
        status = j.get("status", "")
        status_emoji = get_status_emoji(status)
        status_label = get_status_label(status)
        duration = format_job_duration(j)
        total = j.get("total_answers", 0)
        nudge = j.get("nudge_candidates", 0)

        rows.append({
            "상태": f"{status_emoji} {status_label}",
            "진행률": f"{j.get('progress', 0)}%",
            "처리량": f"{total:,}건" if total else "-",
            "넛지 후보": f"{nudge:,}건" if nudge else "-",
            "소요시간": duration,
            "생성일": (j.get("created_at") or "")[:19].replace("T", " "),
            "ID": (j.get("id") or "")[:8],
        })
    st.dataframe(pd.DataFrame(rows), use_container_width=True, hide_index=True)