Files
deepdata/scripts/db/data-ratio-init.sql
T
沃巴蒂 ff22ed3a8b feat(deepdata): 引入修改密码、文件预览组件与清洗算子增强,deepflow 改名为 deep-flow
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)
2026-10-03 22:44:56 +08:00

98 lines
4.2 KiB
PL/PgSQL

-- 使用现有的DeepData数据库
\c deepdata;
-- 配比实例表
CREATE TABLE IF NOT EXISTS t_st_ratio_instances
(
id VARCHAR(64) PRIMARY KEY,
name VARCHAR(64),
description TEXT,
target_dataset_id VARCHAR(64),
ratio_parameters JSONB,
merge_method VARCHAR(50),
status VARCHAR(20),
totals BIGINT,
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
created_by VARCHAR(255),
updated_by VARCHAR(255)
);
-- 添加注释
COMMENT ON TABLE t_st_ratio_instances IS '配比实例表(UUID 主键)';
COMMENT ON COLUMN t_st_ratio_instances.id IS 'UUID';
COMMENT ON COLUMN t_st_ratio_instances.name IS '名称';
COMMENT ON COLUMN t_st_ratio_instances.description IS '描述';
COMMENT ON COLUMN t_st_ratio_instances.target_dataset_id IS '模板数据集ID';
COMMENT ON COLUMN t_st_ratio_instances.ratio_parameters IS '配比参数';
COMMENT ON COLUMN t_st_ratio_instances.merge_method IS '合并方式';
COMMENT ON COLUMN t_st_ratio_instances.status IS '状态';
COMMENT ON COLUMN t_st_ratio_instances.totals IS '总数';
COMMENT ON COLUMN t_st_ratio_instances.created_at IS '创建时间';
COMMENT ON COLUMN t_st_ratio_instances.updated_at IS '更新时间';
COMMENT ON COLUMN t_st_ratio_instances.created_by IS '创建者';
COMMENT ON COLUMN t_st_ratio_instances.updated_by IS '更新者';
-- 配比关系表
CREATE TABLE IF NOT EXISTS t_st_ratio_relations
(
id VARCHAR(64) PRIMARY KEY,
ratio_instance_id VARCHAR(64),
source_dataset_id VARCHAR(64),
ratio_value VARCHAR(256),
counts BIGINT,
filter_conditions TEXT,
created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
created_by VARCHAR(255),
updated_by VARCHAR(255)
);
-- 添加注释
COMMENT ON TABLE t_st_ratio_relations IS '配比关系表(UUID 主键)';
COMMENT ON COLUMN t_st_ratio_relations.id IS 'UUID';
COMMENT ON COLUMN t_st_ratio_relations.ratio_instance_id IS '配比实例ID';
COMMENT ON COLUMN t_st_ratio_relations.source_dataset_id IS '源数据集ID';
COMMENT ON COLUMN t_st_ratio_relations.ratio_value IS '配比值';
COMMENT ON COLUMN t_st_ratio_relations.counts IS '条数';
COMMENT ON COLUMN t_st_ratio_relations.filter_conditions IS '过滤条件';
COMMENT ON COLUMN t_st_ratio_relations.created_at IS '创建时间';
COMMENT ON COLUMN t_st_ratio_relations.updated_at IS '更新时间';
COMMENT ON COLUMN t_st_ratio_relations.created_by IS '创建者';
COMMENT ON COLUMN t_st_ratio_relations.updated_by IS '更新者';
-- 创建索引
CREATE INDEX IF NOT EXISTS idx_st_ratio_instances_target_dataset ON t_st_ratio_instances(target_dataset_id);
CREATE INDEX IF NOT EXISTS idx_st_ratio_instances_status ON t_st_ratio_instances(status);
CREATE INDEX IF NOT EXISTS idx_st_ratio_instances_created_at ON t_st_ratio_instances(created_at);
CREATE INDEX IF NOT EXISTS idx_st_ratio_relations_instance ON t_st_ratio_relations(ratio_instance_id);
CREATE INDEX IF NOT EXISTS idx_st_ratio_relations_source_dataset ON t_st_ratio_relations(source_dataset_id);
CREATE INDEX IF NOT EXISTS idx_st_ratio_relations_created_at ON t_st_ratio_relations(created_at);
-- 创建外键约束
ALTER TABLE t_st_ratio_relations ADD CONSTRAINT fk_st_ratio_relations_instance FOREIGN KEY (ratio_instance_id)
REFERENCES t_st_ratio_instances(id) ON DELETE CASCADE;
-- 创建触发器用于自动更新 updated_at
CREATE OR REPLACE FUNCTION update_updated_at_column()
RETURNS TRIGGER AS $$
BEGIN
NEW.updated_at = CURRENT_TIMESTAMP;
RETURN NEW;
END;
$$ language 'plpgsql';
-- 为各个表创建触发器
DROP TRIGGER IF EXISTS update_st_ratio_instances_updated_at ON t_st_ratio_instances;
CREATE TRIGGER update_st_ratio_instances_updated_at
BEFORE UPDATE ON t_st_ratio_instances
FOR EACH ROW
EXECUTE FUNCTION update_updated_at_column();
DROP TRIGGER IF EXISTS update_st_ratio_relations_updated_at ON t_st_ratio_relations;
CREATE TRIGGER update_st_ratio_relations_updated_at
BEFORE UPDATE ON t_st_ratio_relations
FOR EACH ROW
EXECUTE FUNCTION update_updated_at_column();