feat: 申报赛道推荐助手首版 v1.0.1（match-guide-track-default）

scripts/service/profile_service.py

@@ -0,0 +1,272 @@
+"""教师画像 / 指南赛道 / 推荐报告 的维护与查询。"""
+
+from __future__ import annotations
+
+import json
+from typing import Any, Optional
+
+from db.connection import get_conn, init_db
+from service.match_service import _norm_teacher, _norm_track, _to_int
+from util.logging_config import get_skill_logger
+from util.timeutil import now_unix
+
+_TEACHER_TEXT_FIELDS = ("teacher_name", "department", "title", "research_tags", "recent_papers", "project_history")
+_TEACHER_INT_FIELDS = ("sci_q1_count", "core_paper_count")
+_TRACK_TEXT_FIELDS = ("agency", "program_name", "track_name", "track_tags", "priority_keywords", "min_title", "source_doc")
+_TRACK_INT_FIELDS = ("year", "min_sci_q1", "quota")
+
+_KNOWN_MIN_TITLES = ("讲师及以上", "副高及以上", "正高及以上")
+
+
+def _log():
+    try:
+        return get_skill_logger()
+    except RuntimeError:
+        return None
+
+
+def _snake(name: str) -> str:
+    return "".join("_" + ch.lower() if ch.isupper() else ch for ch in str(name)).lstrip("_")
+
+
+def upsert_teacher(fields: dict[str, Any]) -> dict[str, Any]:
+    """按姓名幂等写入教师画像；未提供字段不覆盖。"""
+    teacher_name = str(fields.get("teacher_name") or "").strip()
+    if not teacher_name:
+        raise ValueError("教师姓名（teacher_name）不能为空")
+    values: dict[str, Any] = {"teacher_name": teacher_name}
+    for key in _TEACHER_TEXT_FIELDS:
+        if key != "teacher_name" and fields.get(key) not in (None, ""):
+            values[key] = str(fields[key]).strip()
+    for key in _TEACHER_INT_FIELDS:
+        if fields.get(key) not in (None, ""):
+            number = _to_int(fields[key])
+            if number is None or number < 0:
+                raise ValueError(f"字段 {key} 必须是非负整数：{fields[key]}")
+            values[key] = number
+
+    init_db()
+    conn = get_conn()
+    try:
+        cur = conn.cursor()
+        cur.execute("SELECT id FROM teacher_profiles WHERE teacher_name = ?", (teacher_name,))
+        row = cur.fetchone()
+        if row:
+            teacher_id = int(row[0])
+            set_clause = ", ".join(f"{k} = ?" for k in values if k != "teacher_name")
+            cur.execute(
+                f"UPDATE teacher_profiles SET {set_clause}, updated_at = ? WHERE id = ?",
+                [values[k] for k in values if k != "teacher_name"] + [now_unix(), teacher_id],
+            )
+            action = "updated"
+        else:
+            columns = ", ".join(values.keys())
+            placeholders = ", ".join("?" for _ in values)
+            cur.execute(
+                f"INSERT INTO teacher_profiles ({columns}, created_at, updated_at) VALUES ({placeholders}, ?, ?)",
+                list(values.values()) + [now_unix(), now_unix()],
+            )
+            teacher_id = int(cur.lastrowid)
+            action = "created"
+        conn.commit()
+    finally:
+        conn.close()
+    log = _log()
+    if log:
+        log.info("teacher_upserted teacher=%s action=%s stage=profile", teacher_name, action)
+    return {"ok": True, "teacher_name": teacher_name, "id": teacher_id, "action": action}
+
+
+def upsert_track(fields: dict[str, Any]) -> dict[str, Any]:
+    """按（年度+学部+项目类型+赛道名）幂等写入指南赛道。"""
+    year = _to_int(fields.get("year"))
+    track_name = str(fields.get("track_name") or "").strip()
+    if year is None or year < 2020 or year > 2100:
+        raise ValueError(f"指南年度无效：{fields.get('year')}")
+    if not track_name:
+        raise ValueError("赛道名称（track_name）不能为空")
+    if fields.get("min_title") and str(fields["min_title"]).strip() not in _KNOWN_MIN_TITLES:
+        raise ValueError(f"职称门槛只接受 {'、'.join(_KNOWN_MIN_TITLES)}：{fields['min_title']}")
+    values: dict[str, Any] = {"year": year, "track_name": track_name}
+    for key in _TRACK_TEXT_FIELDS:
+        if key not in ("track_name",) and fields.get(key) not in (None, ""):
+            values[key] = str(fields[key]).strip()
+    for key in ("min_sci_q1", "quota"):
+        if fields.get(key) not in (None, ""):
+            number = _to_int(fields[key])
+            if number is None or number < 0:
+                raise ValueError(f"字段 {key} 必须是非负整数：{fields[key]}")
+            values[key] = number
+
+    init_db()
+    conn = get_conn()
+    try:
+        cur = conn.cursor()
+        cur.execute(
+            "SELECT id FROM guide_tracks WHERE year = ? AND COALESCE(agency,'') = ? AND COALESCE(program_name,'') = ? AND track_name = ?",
+            (year, values.get("agency", ""), values.get("program_name", ""), track_name),
+        )
+        row = cur.fetchone()
+        if row:
+            track_id = int(row[0])
+            set_clause = ", ".join(f"{k} = ?" for k in values if k != "track_name")
+            cur.execute(
+                f"UPDATE guide_tracks SET {set_clause}, updated_at = ? WHERE id = ?",
+                [values[k] for k in values if k != "track_name"] + [now_unix(), track_id],
+            )
+            action = "updated"
+        else:
+            columns = ", ".join(values.keys())
+            placeholders = ", ".join("?" for _ in values)
+            cur.execute(
+                f"INSERT INTO guide_tracks ({columns}, created_at, updated_at) VALUES ({placeholders}, ?, ?)",
+                list(values.values()) + [now_unix(), now_unix()],
+            )
+            track_id = int(cur.lastrowid)
+            action = "created"
+        conn.commit()
+    finally:
+        conn.close()
+    log = _log()
+    if log:
+        log.info("track_upserted year=%s track=%s action=%s stage=track", year, track_name, action)
+    return {"ok": True, "year": year, "track_name": track_name, "id": track_id, "action": action}
+
+
+def _import_generic(rows: Any, upsert, label: str) -> dict[str, Any]:
+    if not isinstance(rows, list) or not rows:
+        raise ValueError(f"导入内容应为非空 JSON 数组（{label}）")
+    if len(rows) > 500:
+        raise ValueError(f"单次导入条数过多（{len(rows)}），上限 500 条")
+    results = []
+    for idx, raw in enumerate(rows):
+        if not isinstance(raw, dict):
+            raise ValueError(f"第 {idx + 1} 条不是 JSON 对象")
+        results.append(upsert(raw))
+    return {
+        "ok": True,
+        "count": len(results),
+        "created": sum(1 for r in results if r["action"] == "created"),
+        "updated": sum(1 for r in results if r["action"] == "updated"),
+        "items": results,
+    }
+
+
+def import_teachers(rows: list[dict[str, Any]]) -> dict[str, Any]:
+    """批量导入教师画像。"""
+    return _import_generic(rows, lambda row: upsert_teacher({_snake(k): v for k, v in _norm_teacher(row).items()}), "教师画像")
+
+
+def import_tracks(rows: list[dict[str, Any]]) -> dict[str, Any]:
+    """批量导入指南赛道。"""
+    return _import_generic(rows, lambda row: upsert_track({_snake(k): v for k, v in _norm_track(row).items()}), "指南赛道")
+
+
+def list_teachers(department: str = "") -> list[dict[str, Any]]:
+    init_db()
+    conn = get_conn()
+    try:
+        cur = conn.cursor()
+        if department:
+            cur.execute("SELECT * FROM teacher_profiles WHERE department LIKE ? ORDER BY id", (f"%{department}%",))
+        else:
+            cur.execute("SELECT * FROM teacher_profiles ORDER BY id")
+        columns = [d[0] for d in cur.description]
+        rows = [dict(zip(columns, row)) for row in cur.fetchall()]
+    finally:
+        conn.close()
+    return rows
+
+
+def list_tracks(year: Optional[int] = None) -> list[dict[str, Any]]:
+    init_db()
+    conn = get_conn()
+    try:
+        cur = conn.cursor()
+        if year:
+            cur.execute("SELECT * FROM guide_tracks WHERE year = ? ORDER BY id", (year,))
+        else:
+            cur.execute("SELECT * FROM guide_tracks ORDER BY year DESC, id")
+        columns = [d[0] for d in cur.description]
+        rows = [dict(zip(columns, row)) for row in cur.fetchall()]
+    finally:
+        conn.close()
+    return rows
+
+
+def list_reports(limit: int = 20, tier: str = "") -> list[dict[str, Any]]:
+    init_db()
+    limit = max(1, min(int(limit), 200))
+    conn = get_conn()
+    try:
+        cur = conn.cursor()
+        if tier:
+            cur.execute(
+                "SELECT id, batch_no, season, teacher_name, department, eligible_count, top_json, report_file, created_at FROM match_reports WHERE top_json LIKE ? ORDER BY id DESC LIMIT ?",
+                (f"%{tier}%", limit),
+            )
+        else:
+            cur.execute(
+                "SELECT id, batch_no, season, teacher_name, department, eligible_count, top_json, report_file, created_at FROM match_reports ORDER BY id DESC LIMIT ?",
+                (limit,),
+            )
+        columns = [d[0] for d in cur.description]
+        rows = [dict(zip(columns, row)) for row in cur.fetchall()]
+    finally:
+        conn.close()
+    return rows
+
+
+def get_report(report_id: int) -> dict[str, Any]:
+    init_db()
+    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]
+        report = dict(zip(columns, row))
+    finally:
+        conn.close()
+    for key in ("top_json", "tiers_json", "excluded_json"):
+        try:
+            report[key] = json.loads(report.get(key) or "[]")
+        except (TypeError, ValueError):
+            report[key] = []
+    return report
+
+
+def stats() -> dict[str, Any]:
+    init_db()
+    conn = get_conn()
+    try:
+        cur = conn.cursor()
+        cur.execute("SELECT COUNT(*) FROM teacher_profiles")
+        teacher_total = int(cur.fetchone()[0])
+        cur.execute("SELECT year, COUNT(*) FROM guide_tracks GROUP BY year ORDER BY year DESC")
+        tracks_by_year = {str(r[0]): int(r[1]) for r in cur.fetchall()}
+        cur.execute("SELECT COUNT(*) FROM match_reports")
+        report_total = int(cur.fetchone()[0])
+        cur.execute(
+            "SELECT teacher_name, season, top_json FROM match_reports ORDER BY id DESC LIMIT 50"
+        )
+        strong = []
+        for teacher_name, season, top_json in cur.fetchall():
+            try:
+                top = json.loads(top_json or "[]")
+            except (TypeError, ValueError):
+                top = []
+            if top and top[0].get("tier") == "强烈推荐":
+                strong.append({"teacher_name": teacher_name, "season": season, "top_track": top[0]["track"], "match_pct": top[0]["match_pct"]})
+        strong = strong[:5]
+    finally:
+        conn.close()
+    return {
+        "ok": True,
+        "teacher_total": teacher_total,
+        "tracks_by_year": tracks_by_year,
+        "report_total": report_total,
+        "strong_top": strong,
+    }