match-guide-track-default/scripts/service/report_service.py

"""《申报策略建议书》HTML 组装。

- 每位教师一份 `report-{report_id}.html`（Top 3 卡片 + 完整分层清单 + 剔除原因）
- 批量匹配另生成汇总页 `brief-{batch_no}.html`（各教师 Top 1 一览）
写入 `{skill_data}/html/`，宿主数据管理侧栏可预览；重建走固定 Action id `render-html`。
"""

from __future__ import annotations

import json
from typing import Any

from service.html_page_service import load_html_template, render_html_placeholders, write_html_page
from util.logging_config import get_skill_logger

_TEMPLATE_REL = "assets/html/match-report.html"

_TIER_BADGE = {"强烈推荐": "tier-strong", "可尝试": "tier-try", "不建议": "tier-not"}


def _log():
    """容错取 logger：未 setup_skill_logging（如单测直调 service）时返回 None。"""
    try:
        return get_skill_logger()
    except RuntimeError:
        return None


def _esc(value: Any) -> str:
    return html_escape(str(value if value is not None else "—"))


def html_escape(text: str) -> str:
    import html

    return html.escape(text, quote=True)


def _pct(value: Any) -> str:
    try:
        return f"{int(value)}%"
    except (TypeError, ValueError):
        return "—"


def _top_cards(top3: list[dict[str, Any]]) -> str:
    if not top3:
        return '<p class="muted">没有可推荐的赛道：请检查画像完整性或指南赛道库。</p>'
    medals = ["🥇", "🥈", "🥉"]
    cards = []
    for idx, entry in enumerate(top3):
        badge = _TIER_BADGE.get(str(entry.get("tier")), "tier-not")
        reasons = "".join(f"<li>{_esc(r)}</li>" for r in entry.get("reasons") or [])
        cards.append(
            f'<div class="card-item">'
            f'<div class="card-head"><span class="medal">{medals[idx] if idx < 3 else "·"}</span>'
            f'<strong>{_esc(entry.get("track"))}</strong>'
            f'<span class="tag {badge}">{_esc(entry.get("tier"))} · {_pct(entry.get("match_pct"))}</span></div>'
            f'<ol class="reasons">{reasons}</ol>'
            f"</div>"
        )
    return "".join(cards)


def _tier_table(tiers: dict[str, list[dict[str, Any]]]) -> str:
    rows = []
    order = ["强烈推荐", "可尝试", "不建议"]
    for tier in order:
        for entry in tiers.get(tier) or []:
            badge = _TIER_BADGE.get(tier, "tier-not")
            rows.append(
                "<tr>"
                f'<td class="nowrap"><span class="tag {badge}">{_esc(tier)}</span></td>'
                f'<td>{_esc(entry.get("track"))}</td>'
                f'<td class="nowrap">{_pct(entry.get("match_pct"))}</td>'
                f'<td class="muted">{_esc("、".join(entry.get("matched_tags") or []))}</td>'
                "</tr>"
            )
    if not rows:
        return '<tr><td colspan="4" class="muted">无</td></tr>'
    return "".join(rows)


def _excluded_table(excluded: list[dict[str, Any]]) -> str:
    if not excluded:
        return ""
    rows = "".join(f"<tr><td>{_esc(e.get('track'))}</td><td class='muted'>{_esc(e.get('reason'))}</td></tr>" for e in excluded)
    return f'<div class="section"><h2>被硬门槛剔除的赛道</h2><table><tr><th>赛道</th><th>原因</th></tr>{rows}</table></div>'


def build_match_html(result: dict[str, Any], batch_no: str = "") -> str:
    body = f"""
    <div class="verdict-line">
      <span class="tag tier-info">{_esc(result.get("teacher_name"))}</span>
      <span class="muted">{_esc(result.get("department") or "")} · 指南年度 {_esc(result.get("season"))} · 可匹配赛道 {_esc(result.get("eligible_count"))} 个 · 批次 {_esc(batch_no or result.get("batch_no"))}</span>
    </div>
    <div class="section"><h2>Top 3 最匹配赛道</h2>{_top_cards(result.get("top3") or [])}</div>
    <div class="section"><h2>完整分层清单</h2>
      <table><tr><th>分层</th><th>赛道</th><th>匹配度</th><th>命中标签</th></tr>{_tier_table(result.get("tiers") or {})}</table>
    </div>
    {_excluded_table(result.get("excluded") or [])}
    <footer>推荐由标签匹配算法生成、仅供参考；申报决策请结合个人规划与学院统筹，以当年度正式指南为准。</footer>
    """
    template = load_html_template(_TEMPLATE_REL)
    return render_html_placeholders(
        template,
        {
            "TITLE": f"申报策略建议书 · {result.get('teacher_name') or ''}",
            "GENERATED_AT": str(result.get("season") or ""),
            "BODY": body,
        },
    )


def write_report_for_kernel(*, result: dict[str, Any], batch_no: str) -> str:
    html_text = build_match_html(result, batch_no)
    log = _log()
    path = write_html_page(f"report-{result['report_id']}.html", html_text)
    if log:
        log.info("match_report_written report_id=%s path=%s stage=report", result["report_id"], path)
    return path


def build_report_for_report_id(report_id: int) -> str:
    """按报告 id 从库中取数并重写 HTML（重建入口用）。"""
    from db.connection import get_conn

    log = _log()
    if log:
        log.info("report_render_start report_id=%s stage=render", report_id)
    conn = get_conn()
    try:
        cur = conn.cursor()
        cur.execute("SELECT * FROM match_reports WHERE id = ?", (report_id,))
        row = cur.fetchone()
        if not row:
            raise ValueError(f"推荐报告不存在：{report_id}")
        columns = [d[0] for d in cur.description]
        record = dict(zip(columns, row))
    finally:
        conn.close()
    result = dict(record)
    for key in ("top_json", "tiers_json", "excluded_json"):
        target = key[:-5] if key.endswith("_json") else key
        try:
            result[target] = json.loads(record.get(key) or "[]")
        except (TypeError, ValueError):
            result[target] = []
    result["top3"] = result.get("top") or []
    html_text = build_match_html(result)
    path = write_html_page(f"report-{report_id}.html", html_text)
    if log:
        log.info("report_render_done report_id=%s path=%s stage=render", report_id, path)
    return path


def build_batch_brief(
    *,
    batch_no: str,
    results: list[dict[str, Any]],
    season: str,
    skipped: list[dict[str, Any]] | None = None,
) -> str:
    """批量匹配汇总页：各教师 Top 1 一览；被跳过（画像待补录）教师单列。"""
    log = _log()
    rows = []
    for result in results:
        top3 = result.get("top3") or []
        if top3:
            first = top3[0]
            badge = _TIER_BADGE.get(str(first.get("tier")), "tier-not")
            rows.append(
                "<tr>"
                f"<td>{_esc(result.get('teacher_name'))}</td>"
                f"<td class='muted'>{_esc(result.get('department'))}</td>"
                f"<td><span class='tag {badge}'>{_esc(first.get('tier'))}</span></td>"
                f"<td>{_esc(first.get('track'))}</td>"
                f"<td class='nowrap'>{_pct(first.get('match_pct'))}</td>"
                "</tr>"
            )
        else:
            rows.append(f"<tr><td>{_esc(result.get('teacher_name'))}</td><td colspan='4' class='muted'>无可推荐赛道（画像待补全）</td></tr>")
    for entry in skipped or []:
        rows.append(
            "<tr>"
            f"<td>{_esc(entry.get('teacher_name'))}</td>"
            f"<td colspan='4' class='muted'>画像待补录，本期未匹配（{_esc(entry.get('reason'))}）</td>"
            "</tr>"
        )
    if not rows:
        rows.append('<tr><td colspan="5" class="muted">本期无匹配结果。</td></tr>')

    body = f"""
    <div class="verdict-line">
      <span class="muted">指南年度 {_esc(season)} · 教师 {_esc(len(results))} 人 · 批次 {_esc(batch_no)}</span>
    </div>
    <div class="section"><h2>各教师 Top 1 赛道一览</h2>
      <table><tr><th>教师</th><th>学院</th><th>分层</th><th>最匹配赛道</th><th>匹配度</th></tr>{''.join(rows)}</table>
    </div>
    <footer>汇总由批量匹配自动生成，仅用于科研动员参考；详细理由见各教师《申报策略建议书》。</footer>
    """
    template = load_html_template(_TEMPLATE_REL)
    page = render_html_placeholders(
        template,
        {"TITLE": "申报赛道匹配汇总", "GENERATED_AT": str(season), "BODY": body},
    )
    path = write_html_page(f"brief-{batch_no}.html", page)
    if log:
        log.info("match_brief_written batch_no=%s path=%s stage=report", batch_no, path)
    return path