FrameTour-RenderWorker/services/storage.py

# -*- coding: utf-8 -*-
"""
存储服务

提供文件上传/下载功能，支持 OSS 签名 URL 和 HTTP_REPLACE_MAP 环境变量。
"""

import os
import logging
import subprocess
from typing import Optional

import requests

logger = logging.getLogger(__name__)


def _apply_http_replace_map(url: str) -> str:
    """
    应用 HTTP_REPLACE_MAP 环境变量替换 URL

    Args:
        url: 原始 URL

    Returns:
        替换后的 URL
    """
    replace_map = os.getenv("HTTP_REPLACE_MAP", "")
    if not replace_map:
        return url

    new_url = url
    replace_list = [i.split("|", 1) for i in replace_map.split(",") if "|" in i]
    for src, dst in replace_list:
        new_url = new_url.replace(src, dst)

    if new_url != url:
        logger.debug(f"HTTP_REPLACE_MAP: {url} -> {new_url}")

    return new_url


def upload_file(url: str, file_path: str, max_retries: int = 5, timeout: int = 60) -> bool:
    """
    使用签名 URL 上传文件到 OSS

    Args:
        url: 签名 URL
        file_path: 本地文件路径
        max_retries: 最大重试次数
        timeout: 超时时间（秒）

    Returns:
        是否成功
    """
    if not os.path.exists(file_path):
        logger.error(f"File not found: {file_path}")
        return False

    file_size = os.path.getsize(file_path)
    logger.info(f"Uploading: {file_path} ({file_size} bytes)")

    # 检查是否使用 rclone 上传
    if os.getenv("UPLOAD_METHOD") == "rclone":
        result = _upload_with_rclone(url, file_path)
        if result:
            return True
        # rclone 失败时回退到 HTTP

    # 应用 HTTP_REPLACE_MAP 替换 URL
    http_url = _apply_http_replace_map(url)

    retries = 0
    while retries < max_retries:
        try:
            with open(file_path, 'rb') as f:
                with requests.put(
                    http_url,
                    data=f,
                    stream=True,
                    timeout=timeout,
                    headers={"Content-Type": "application/octet-stream"}
                ) as response:
                    response.raise_for_status()
                    logger.info(f"Upload succeeded: {file_path}")
                    return True

        except requests.exceptions.Timeout:
            retries += 1
            logger.warning(f"Upload timed out. Retrying {retries}/{max_retries}...")
        except requests.exceptions.RequestException as e:
            retries += 1
            logger.warning(f"Upload failed ({e}). Retrying {retries}/{max_retries}...")

    logger.error(f"Upload failed after {max_retries} retries: {file_path}")
    return False


def _upload_with_rclone(url: str, file_path: str) -> bool:
    """
    使用 rclone 上传文件

    Args:
        url: 目标 URL
        file_path: 本地文件路径

    Returns:
        是否成功
    """
    replace_map = os.getenv("RCLONE_REPLACE_MAP", "")
    if not replace_map:
        return False

    config_file = os.getenv("RCLONE_CONFIG_FILE", "")

    # 替换 URL
    new_url = url
    replace_list = [i.split("|", 1) for i in replace_map.split(",") if "|" in i]
    for src, dst in replace_list:
        new_url = new_url.replace(src, dst)
    new_url = new_url.split("?", 1)[0]  # 移除查询参数

    if new_url == url:
        return False

    cmd = [
        "rclone",
        "copyto",
        "--no-check-dest",
        "--ignore-existing",
        "--multi-thread-chunk-size",
        "8M",
        "--multi-thread-streams",
        "8",
    ]
    if config_file:
        cmd.extend(["--config", config_file])
    cmd.extend([file_path, new_url])

    logger.debug(f"rclone command: {' '.join(cmd)}")

    result = subprocess.run(cmd, capture_output=True, text=True)
    if result.returncode == 0:
        logger.info(f"rclone upload succeeded: {file_path}")
        return True

    stderr = (result.stderr or '').strip()
    stderr = stderr[:500] if stderr else ""
    logger.warning(f"rclone upload failed (code={result.returncode}): {file_path} {stderr}")
    return False


def download_file(
    url: str,
    file_path: str,
    max_retries: int = 5,
    timeout: int = 30,
    skip_if_exist: bool = False
) -> bool:
    """
    使用签名 URL 下载文件

    Args:
        url: 签名 URL
        file_path: 本地文件路径
        max_retries: 最大重试次数
        timeout: 超时时间（秒）
        skip_if_exist: 如果文件存在则跳过

    Returns:
        是否成功
    """
    # 如果文件已存在且跳过
    if skip_if_exist and os.path.exists(file_path):
        logger.debug(f"File exists, skipping download: {file_path}")
        return True

    logger.info(f"Downloading: {url}")

    # 确保目标目录存在
    file_dir = os.path.dirname(file_path)
    if file_dir:
        os.makedirs(file_dir, exist_ok=True)

    # 应用 HTTP_REPLACE_MAP 替换 URL
    http_url = _apply_http_replace_map(url)

    retries = 0
    while retries < max_retries:
        try:
            with requests.get(http_url, timeout=timeout, stream=True) as response:
                response.raise_for_status()

                with open(file_path, 'wb') as f:
                    for chunk in response.iter_content(chunk_size=8192):
                        if chunk:
                            f.write(chunk)

            file_size = os.path.getsize(file_path)
            logger.info(f"Download succeeded: {file_path} ({file_size} bytes)")
            return True

        except requests.exceptions.Timeout:
            retries += 1
            logger.warning(f"Download timed out. Retrying {retries}/{max_retries}...")
        except requests.exceptions.RequestException as e:
            retries += 1
            logger.warning(f"Download failed ({e}). Retrying {retries}/{max_retries}...")

    logger.error(f"Download failed after {max_retries} retries: {url}")
    return False