Method merge_chunks

core/storage.py:1215–1282

合并 WebDAV 上的分片文件 使用临时文件避免内存问题

(self, upload_id: str, chunk_info: UploadChunk, save_path: str)

                    )

    async def merge_chunks(self, upload_id: str, chunk_info: UploadChunk, save_path: str) -> tuple[str, str]:
        """
        合并 WebDAV 上的分片文件
        使用临时文件避免内存问题
        """
        file_sha256 = hashlib.sha256()
        chunk_dir = str(Path(save_path).parent / "chunks" / upload_id)

        # 使用临时文件存储合并数据，避免内存问题
        with tempfile.NamedTemporaryFile(delete=False) as temp_file:
            temp_path = temp_file.name

        try:
            async with aiohttp.ClientSession(auth=self.auth) as session:
                # 按顺序读取并验证每个分片，写入临时文件
                async with aiofiles.open(temp_path, 'wb') as out_file:
                    for i in range(chunk_info.total_chunks):
                        chunk_path = f"{chunk_dir}/{i}.part"
                        chunk_url = self._build_url(chunk_path)

                        # 获取分片记录
                        chunk_record = await UploadChunk.filter(upload_id=upload_id, chunk_index=i).first()
                        if not chunk_record:
                            raise ValueError(f"分片{i}记录不存在")

                        # 下载分片数据
                        async with session.get(chunk_url) as resp:
                            if resp.status != 200:
                                raise ValueError(f"分片{i}文件不存在或无法访问")
                            chunk_data = await resp.read()

                        # 验证哈希
                        current_hash = hashlib.sha256(chunk_data).hexdigest()
                        if current_hash != chunk_record.chunk_hash:
                            raise ValueError(f"分片{i}哈希不匹配: 期望 {chunk_record.chunk_hash}, 实际 {current_hash}")

                        file_sha256.update(chunk_data)
                        await out_file.write(chunk_data)
                        del chunk_data  # 释放内存

                # 确保目标目录存在
                output_dir = str(Path(save_path).parent)
                await self._mkdir_p(output_dir)

                # 流式上传合并后的文件
                output_url = self._build_url(save_path)

                async def file_sender():
                    async with aiofiles.open(temp_path, 'rb') as f:
                        while True:
                            chunk = await f.read(256 * 1024)
                            if not chunk:
                                break
                            yield chunk

                async with session.put(output_url, data=file_sender()) as resp:
                    if resp.status not in (200, 201, 204):
                        content = await resp.text()