沃巴蒂
ff22ed3a8b
本次同步 09-12 至 09-28 的代码变更，主要内容： 新增功能 - 修改密码：后端新增 ChangePasswordRequest DTO 与UserController/UserService 对应接口，前端新增 ChangePasswordDialog 并在 Header 接入入口 - 文件预览组件重构：file-preview 目录拆分出 VideoPreview（支持 blobUrl 直传）、 ImagePreview、AudioPreview，index.tsx 统一调度各类型预览器 - 新增 my_ops 算子模块：markitdown_parser、mineru_pdf_parser、text_quality_evaluator - 新增 tools/minio-file-server MinIO 文件服务 功能增强 - 数据清洗：cleaning_task_service/scheduler/routes 重构， data_juicer_executor 与 wrapper 增强，OperatorTable/LogsTable/TaskDetail 同步调整 - 数据标注：annotation sync.py、project.py 接口与schema 更新 - 数据采集、算子市场、首页与菜单路由相关页面调整 - DataJuicer 算子接入（useOperatorOperations、dj_ops_schema） 结构调整 - deepflow/ 更名为 deep-flow/（419 个文件重命名） - 新增 helm 部署编排、GitHub Actions 之外的自建镜像构建脚本 未纳入本次提交 - scripts-backup/、runtime/python-executor-backup/、components_backup/（备份目录） - *.backup*、__pycache__ 产物 - zh_core_web_sm-3.8.0-py3-none-any.whl（46MB 构建产物） - DataX/（内嵌独立仓库，远程亦未收录其源码）
44 lines
1.7 KiB
Python
44 lines
1.7 KiB
Python
# -- encoding: utf-8 --
|
|
|
|
|
|
|
|
|
|
|
|
"""
|
|
|
|
|
|
Description:
|
|
|
|
|
|
Create: 2025/01/16
|
|
|
|
|
|
"""
|
|
|
|
|
|
import time
|
|
|
|
|
|
from typing import List, Dict, Any
|
|
|
|
|
|
|
|
|
|
|
|
from loguru import logger
|
|
|
|
|
|
import cv2
|
|
|
|
|
|
|
|
|
|
|
|
from deepdata.common.utils import bytes_transform
|
|
|
|
|
|
from deepdata.core.base_op import Mapper
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class ImgResize(Mapper):
|
|
|
|
|
|
def __init__(self, *args, **kwargs):
|
|
|
|
|
|
super(ImgResize, self).__init__(*args, **kwargs)
|
|
|
|
|
|
self._width = int(kwargs.get("widthSize", 256))
|
|
|
|
|
|
self._height = int(kwargs.get("heightSize", 256))
|
|
|
|
|
|
self._target_size = [self._width, self._height]
|
|
|
|
|
|
|
|
|
|
|
|
@classmethod
|
|
|
|
|
|
def _img_resize(cls, data: List[float], target_size: List[int]) -> List[float]:
|
|
|
|
|
|
"""将图片缩放到指定尺寸大小"""
|
|
|
|
|
|
target_width = max(min(target_size[0], 4096), 1)
|
|
|
|
|
|
target_height = max(min(target_size[1], 4096), 1)
|
|
|
|
|
|
resized_img = cv2.resize(data, (target_width, target_height), interpolation=cv2.INTER_AREA)
|
|
|
|
|
|
return resized_img
|
|
|
|
|
|
|
|
|
|
|
|
def execute(self, sample: Dict[str, Any]) -> Dict[str, Any]:
|
|
|
|
|
|
start = time.time()
|
|
|
|
|
|
self.read_file_first(sample)
|
|
|
|
|
|
file_name = sample[self.filename_key]
|
|
|
|
|
|
file_type = "." + sample[self.filetype_key]
|
|
|
|
|
|
img_bytes = sample[self.data_key]
|
|
|
|
|
|
if img_bytes:
|
|
|
|
|
|
data = bytes_transform.bytes_to_numpy(img_bytes)
|
|
|
|
|
|
resized_img = self._img_resize(data, self._target_size)
|
|
|
|
|
|
sample[self.data_key] = bytes_transform.numpy_to_bytes(resized_img, file_type)
|
|
|
|
|
|
logger.info(f"fileName: {file_name}, method: ImgResize costs {time.time() - start:.6f} s")
|
|
|
|
|
|
return sample
|
|
|
|
|