chore: auto release commit (2026-09-15 00:32:44)

scripts/db/connection.py

@@ -90,6 +90,25 @@ DDL_STATEMENTS: tuple[str, ...] = (
     );
     """,
     "CREATE INDEX IF NOT EXISTS idx_dispatch_unit_month ON dispatch_log(unit_id, month);",
+    # 7. download_tasks (v1.1.18)
+    """
+    CREATE TABLE IF NOT EXISTS download_tasks (
+        task_id      TEXT PRIMARY KEY,
+        contract_id  TEXT NOT NULL,
+        kind         TEXT NOT NULL DEFAULT 'platform_button',
+        status       TEXT NOT NULL DEFAULT 'pending',
+        attempts     INTEGER NOT NULL DEFAULT 0,
+        error_msg    TEXT,
+        enqueued_at  TEXT NOT NULL,
+        started_at   TEXT,
+        finished_at  TEXT,
+        source_path  TEXT,
+        result_path  TEXT,
+        FOREIGN KEY (contract_id) REFERENCES contracts(contract_id)
+    );
+    """,
+    "CREATE INDEX IF NOT EXISTS idx_dlq_status ON download_tasks(status);",
+    "CREATE INDEX IF NOT EXISTS idx_dlq_contract ON download_tasks(contract_id);",
 )
 
 
@@ -131,6 +150,7 @@ def init_db(db_path: Path | None = None) -> dict[str, int]:
             "renewal_tasks": conn.execute("SELECT COUNT(*) AS n FROM renewal_tasks").fetchone()["n"],
             "dispatch_log": conn.execute("SELECT COUNT(*) AS n FROM dispatch_log").fetchone()["n"],
             "materials_content": conn.execute("SELECT COUNT(*) AS n FROM materials_content").fetchone()["n"],
+            "download_tasks": conn.execute("SELECT COUNT(*) AS n FROM download_tasks").fetchone()["n"],
         }
         return counts
     finally:
@@ -140,5 +160,5 @@ def init_db(db_path: Path | None = None) -> dict[str, int]:
 def table_names() -> Iterable[str]:
     return (
         "contracts", "performance_records", "alerts", "renewal_tasks",
-        "dispatch_log", "materials_content",
+        "dispatch_log", "materials_content", "download_tasks",
     )

scripts/db/repository.py

@@ -294,6 +294,59 @@ def list_dispatch_logs(conn: sqlite3.Connection) -> list[sqlite3.Row]:
 
 # ---------- materials_content（v1.1.1 新增） ----------
 
+def upsert_contract_from_csv_row(
+    conn: sqlite3.Connection, row: dict[str, str]
+) -> None:
+    """从 CSV 字典 upsert 一份合同。CSV 列名必须与 contracts 表列一致（或常见别名）。
+
+    缺字段兜底值：
+      employee_id      = contract_id
+      teacher_name     = ""
+      unit_id          = "U-UNKNOWN"
+      unit_name        = ""
+      position         = ""
+      contract_type    = ""
+      contract_start   = "1970-01-01"
+      contract_end     = "2099-12-31"
+      trial_period_end = contract_end
+      status           = "可续聘"
+    """
+    cid = row.get("contract_id") or row.get("合同ID") or ""
+    if not cid:
+        raise ValueError("CSV row missing contract_id / 合同ID")
+    conn.execute(
+        """
+        INSERT INTO contracts
+            (contract_id, employee_id, teacher_name, unit_id, unit_name,
+             position, contract_type, contract_start, contract_end,
+             trial_period_end, status, last_material_id, renewed_at)
+        VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, NULL, NULL)
+        ON CONFLICT(contract_id) DO UPDATE SET
+            teacher_name     = excluded.teacher_name,
+            unit_name        = excluded.unit_name,
+            position         = excluded.position,
+            contract_type    = excluded.contract_type,
+            contract_start   = excluded.contract_start,
+            contract_end     = excluded.contract_end,
+            trial_period_end = excluded.trial_period_end,
+            status           = excluded.status
+        """,
+        (
+            cid,
+            row.get("employee_id") or row.get("工号") or cid,
+            row.get("teacher_name") or row.get("教职工姓名") or "",
+            row.get("unit_id") or row.get("单位ID") or "U-UNKNOWN",
+            row.get("unit_name") or row.get("单位") or "",
+            row.get("position") or row.get("岗位") or "",
+            row.get("contract_type") or row.get("合同类型") or "",
+            row.get("contract_start") or row.get("合同起始日") or "1970-01-01",
+            row.get("contract_end") or row.get("合同到期日") or "2099-12-31",
+            row.get("trial_period_end") or row.get("试用期截止") or row.get("contract_end") or "2099-12-31",
+            row.get("status") or "可续聘",
+        ),
+    )
+
+
 def list_materials_for_contract(
     conn: sqlite3.Connection, contract_id: str
 ) -> list[sqlite3.Row]:
@@ -373,3 +426,124 @@ def summarize_materials(
     if len(summary) > 16000:
         summary = summary[:16000] + "\n...(材料过长已截断)"
     return (summary, file_names)
+
+
+# ---------- download_tasks（v1.1.18 新增） ----------
+
+
+def enqueue_download_task(
+    conn: sqlite3.Connection,
+    contract_id: str,
+    kind: str = "platform_button",
+) -> str:
+    """入队一个下载任务，返回 task_id。
+
+    已存在 (contract_id, kind, status ∈ {pending, running}) 时跳过（返回已存在的 task_id）。
+    """
+    import uuid
+
+    existing = conn.execute(
+        """SELECT task_id FROM download_tasks
+           WHERE contract_id = ? AND kind = ? AND status IN ('pending', 'running')
+           LIMIT 1""",
+        (contract_id, kind),
+    ).fetchone()
+    if existing:
+        return existing["task_id"]
+    task_id = f"DLQ-{uuid.uuid4().hex[:12]}"
+    conn.execute(
+        """
+        INSERT INTO download_tasks
+            (task_id, contract_id, kind, status, attempts, enqueued_at)
+        VALUES (?, ?, ?, 'pending', 0, ?)
+        """,
+        (task_id, contract_id, kind, datetime.now().isoformat(timespec="seconds")),
+    )
+    return task_id
+
+
+def _read_max_attempts(conn: sqlite3.Connection) -> int:
+    """读 DOWNLOAD_QUEUE_MAX_ATTEMPTS env（默认 3）。"""
+    import os
+    return int(os.environ.get("DOWNLOAD_QUEUE_MAX_ATTEMPTS", "3"))
+
+
+def claim_pending_tasks(
+    conn: sqlite3.Connection, limit: int, ids_filter: list[str] | None = None,
+) -> list[sqlite3.Row]:
+    """原子领取一批 pending 任务，标记为 running。
+
+    - limit: 最多领取条数
+    - ids_filter: 若给出，仅从这些 task_id 中领
+    """
+    max_attempts = _read_max_attempts(conn)
+    if ids_filter:
+        placeholders = ",".join("?" for _ in ids_filter)
+        rows = conn.execute(
+            f"""SELECT * FROM download_tasks
+                WHERE status = 'pending' AND attempts < ?
+                AND task_id IN ({placeholders})
+                ORDER BY enqueued_at ASC LIMIT ?""",
+            [max_attempts, *ids_filter, limit],
+        ).fetchall()
+    else:
+        rows = conn.execute(
+            """SELECT * FROM download_tasks
+               WHERE status = 'pending' AND attempts < ?
+               ORDER BY enqueued_at ASC LIMIT ?""",
+            (max_attempts, limit),
+        ).fetchall()
+    if not rows:
+        return []
+    now = datetime.now().isoformat(timespec="seconds")
+    for r in rows:
+        conn.execute(
+            "UPDATE download_tasks SET status = 'running', started_at = ? WHERE task_id = ?",
+            (now, r["task_id"]),
+        )
+    conn.commit()
+    return rows
+
+
+def mark_task_success(
+    conn: sqlite3.Connection, task_id: str, result_path: str,
+) -> None:
+    conn.execute(
+        """UPDATE download_tasks
+           SET status = 'success', result_path = ?, finished_at = ?
+           WHERE task_id = ?""",
+        (result_path, datetime.now().isoformat(timespec="seconds"), task_id),
+    )
+
+
+def mark_task_failed(
+    conn: sqlite3.Connection, task_id: str, error_msg: str,
+) -> None:
+    """失败一次：attempts+1，未超 max_attempts 则回退 pending，否则标 failed。"""
+    max_attempts = _read_max_attempts(conn)
+    now = datetime.now().isoformat(timespec="seconds")
+    conn.execute(
+        """UPDATE download_tasks
+           SET status = CASE WHEN attempts + 1 >= ? THEN 'failed' ELSE 'pending' END,
+               attempts = attempts + 1,
+               error_msg = ?,
+               finished_at = ?
+           WHERE task_id = ?""",
+        (max_attempts, error_msg, now, task_id),
+    )
+
+
+def list_recent_tasks(
+    conn: sqlite3.Connection, limit: int = 50
+) -> list[sqlite3.Row]:
+    return conn.execute(
+        "SELECT * FROM download_tasks ORDER BY enqueued_at DESC LIMIT ?",
+        (limit,),
+    ).fetchall()
+
+
+def count_tasks_by_status(conn: sqlite3.Connection) -> dict[str, int]:
+    rows = conn.execute(
+        "SELECT status, COUNT(*) AS n FROM download_tasks GROUP BY status"
+    ).fetchall()
+    return {r["status"]: r["n"] for r in rows}