Download src/storage.py from ServiceX/PDF: direct link, hf CLI and curl.
- Browser
- Download file 4.15 kB
-
https://huggingface.co/spaces/ServiceX/PDF/resolve/main/src/storage.py
- Command line
-
hf download hf://spaces/ServiceX/PDF/src/storage.py
-
curl -L -o storage.py https://huggingface.co/spaces/ServiceX/PDF/resolve/main/src/storage.py
4.15 kB
| """存储层:数据目录与 SQLite 封装。""" | |
| from __future__ import annotations | |
| import os | |
| import sqlite3 | |
| import threading | |
| from datetime import datetime, timezone | |
| from pathlib import Path | |
| from typing import Any | |
| # 注意:日志仍然复用主网关 logger 名称,方便统一过滤 | |
| import logging | |
| logger = logging.getLogger("gateway") | |
| # ── 路径与基本配置 ───────────────────────────────────────────────────────────── | |
| DATA_DIR = Path(os.environ.get("DATA_DIR", "/data")) | |
| UPLOAD_DIR = DATA_DIR / "uploads" | |
| JOB_DIR = DATA_DIR / "jobs" | |
| DB_PATH = DATA_DIR / "gateway.db" | |
| _db_lock = threading.Lock() | |
| _db_conn: sqlite3.Connection | None = None | |
| def now_iso() -> str: | |
| """返回当前 UTC 时间的 ISO 字符串。""" | |
| return datetime.now(timezone.utc).isoformat() | |
| def ensure_data_dirs() -> None: | |
| """确保数据目录存在。""" | |
| UPLOAD_DIR.mkdir(parents=True, exist_ok=True) | |
| JOB_DIR.mkdir(parents=True, exist_ok=True) | |
| def init_db() -> None: | |
| """初始化 SQLite 数据库与基础表结构。""" | |
| global _db_conn | |
| ensure_data_dirs() | |
| conn = sqlite3.connect(DB_PATH, check_same_thread=False) | |
| conn.row_factory = sqlite3.Row | |
| with conn: | |
| conn.execute( | |
| """ | |
| CREATE TABLE IF NOT EXISTS jobs ( | |
| id TEXT PRIMARY KEY, | |
| username TEXT NOT NULL, | |
| filename TEXT NOT NULL, | |
| input_path TEXT NOT NULL, | |
| output_dir TEXT NOT NULL, | |
| status TEXT NOT NULL, | |
| progress REAL NOT NULL DEFAULT 0, | |
| message TEXT, | |
| error TEXT, | |
| model TEXT NOT NULL, | |
| lang_in TEXT NOT NULL, | |
| lang_out TEXT NOT NULL, | |
| cancel_requested INTEGER NOT NULL DEFAULT 0, | |
| mono_pdf_path TEXT, | |
| dual_pdf_path TEXT, | |
| glossary_path TEXT, | |
| created_at TEXT NOT NULL, | |
| updated_at TEXT NOT NULL, | |
| started_at TEXT, | |
| finished_at TEXT | |
| ) | |
| """ | |
| ) | |
| conn.execute( | |
| """ | |
| CREATE TABLE IF NOT EXISTS usage_records ( | |
| id INTEGER PRIMARY KEY AUTOINCREMENT, | |
| username TEXT NOT NULL, | |
| job_id TEXT, | |
| model TEXT NOT NULL, | |
| prompt_tokens INTEGER NOT NULL, | |
| completion_tokens INTEGER NOT NULL, | |
| total_tokens INTEGER NOT NULL, | |
| cost_usd REAL NOT NULL, | |
| created_at TEXT NOT NULL | |
| ) | |
| """ | |
| ) | |
| conn.execute( | |
| """ | |
| CREATE INDEX IF NOT EXISTS idx_jobs_user_time | |
| ON jobs(username, created_at DESC) | |
| """ | |
| ) | |
| conn.execute( | |
| """ | |
| CREATE INDEX IF NOT EXISTS idx_usage_user_time | |
| ON usage_records(username, created_at DESC) | |
| """ | |
| ) | |
| _db_conn = conn | |
| logger.info("Database initialized at %s", DB_PATH) | |
| def close_db() -> None: | |
| """关闭数据库连接,用于应用关闭阶段。""" | |
| global _db_conn | |
| if _db_conn is not None: | |
| _db_conn.close() | |
| _db_conn = None | |
| def db_execute(sql: str, params: tuple[Any, ...] = ()) -> None: | |
| """执行写操作 SQL。""" | |
| if _db_conn is None: | |
| raise RuntimeError("DB is not initialized") | |
| with _db_lock, _db_conn: | |
| _db_conn.execute(sql, params) | |
| def db_fetchone(sql: str, params: tuple[Any, ...] = ()) -> sqlite3.Row | None: | |
| """执行查询并返回单行。""" | |
| if _db_conn is None: | |
| raise RuntimeError("DB is not initialized") | |
| with _db_lock: | |
| return _db_conn.execute(sql, params).fetchone() | |
| def db_fetchall(sql: str, params: tuple[Any, ...] = ()) -> list[sqlite3.Row]: | |
| """执行查询并返回多行。""" | |
| if _db_conn is None: | |
| raise RuntimeError("DB is not initialized") | |
| with _db_lock: | |
| return _db_conn.execute(sql, params).fetchall() | |