refactor: enhance CleaningTaskService and related components with validation and repository updates

Author: hhhhsc701

backend/services/data-cleaning-service/pom.xml

@@ -27,6 +27,11 @@
           <artifactId>data-management-service</artifactId>
           <version>${project.version}</version>
         </dependency>
+        <dependency>
+          <groupId>com.datamate</groupId>
+          <artifactId>operator-market-service</artifactId>
+          <version>${project.version}</version>
+        </dependency>
         <dependency>
             <groupId>org.springframework.boot</groupId>
             <artifactId>spring-boot-starter-test</artifactId>

backend/services/data-cleaning-service/src/main/java/com/datamate/cleaning/DataCleaningServiceConfiguration.java

@@ -1,16 +1,18 @@
 package com.datamate.cleaning;
 
-import org.springframework.boot.autoconfigure.SpringBootApplication;
+import org.springframework.context.annotation.ComponentScan;
 import org.springframework.scheduling.annotation.EnableAsync;
 import org.springframework.scheduling.annotation.EnableScheduling;
 
 /**
  * 数据归集服务配置类
  * 基于DataX的数据归集和同步服务，支持多种数据源的数据采集和归集
  */
-@SpringBootApplication
 @EnableAsync
 @EnableScheduling
+@ComponentScan(basePackages = {
+    "com.datamate.cleaning"
+})
 public class DataCleaningServiceConfiguration {
     // Configuration class for JAR packaging - no main method needed
 }

backend/services/data-cleaning-service/src/main/java/com/datamate/cleaning/application/CleaningTaskService.java

@@ -10,6 +10,7 @@
 import com.datamate.cleaning.domain.repository.CleaningTaskRepository;
 import com.datamate.cleaning.domain.repository.OperatorInstanceRepository;
 
+import com.datamate.cleaning.infrastructure.validator.CleanTaskValidator;
 import com.datamate.cleaning.interfaces.dto.CleaningProcess;
 import com.datamate.cleaning.interfaces.dto.CleaningTaskDto;
 import com.datamate.cleaning.interfaces.dto.CreateCleaningTaskRequest;
@@ -59,6 +60,8 @@ public class CleaningTaskService {
 
     private final DatasetFileApplicationService datasetFileService;
 
+    private final CleanTaskValidator cleanTaskValidator;
+
     private final String DATASET_PATH = "/dataset";
 
     private final String FLOW_PATH = "/flow";
@@ -80,6 +83,9 @@ public int countTasks(String status, String keywords) {
 
     @Transactional
     public CleaningTaskDto createTask(CreateCleaningTaskRequest request) {
+        cleanTaskValidator.checkNameDuplication(request.getName());
+        cleanTaskValidator.checkInputAndOutput(request.getInstance());
+
         CreateDatasetRequest createDatasetRequest = new CreateDatasetRequest();
         createDatasetRequest.setName(request.getDestDatasetName());
         createDatasetRequest.setDatasetType(DatasetType.valueOf(request.getDestDatasetType()));

backend/services/data-cleaning-service/src/main/java/com/datamate/cleaning/application/CleaningTemplateService.java

@@ -5,6 +5,8 @@
 import com.datamate.cleaning.domain.repository.OperatorInstanceRepository;
 import com.datamate.cleaning.interfaces.dto.*;
 import com.datamate.cleaning.domain.model.entity.TemplateWithInstance;
+import com.datamate.operator.domain.repository.OperatorRepository;
+import com.datamate.operator.interfaces.dto.OperatorDto;
 import lombok.RequiredArgsConstructor;
 import org.apache.commons.lang3.StringUtils;
 import org.springframework.stereotype.Service;
@@ -24,8 +26,10 @@ public class CleaningTemplateService {
 
     private final OperatorInstanceRepository operatorInstanceRepo;
 
+    private final OperatorRepository operatorRepo;
+
     public List<CleaningTemplateDto> getTemplates(String keywords) {
-        List<OperatorDto> allOperators = operatorInstanceRepo.findAllOperators();
+        List<OperatorDto> allOperators = operatorRepo.findAllOperators();
         Map<String, OperatorDto> operatorsMap = allOperators.stream()
                 .collect(Collectors.toMap(OperatorDto::getId, Function.identity()));
         List<TemplateWithInstance> allTemplates = cleaningTemplateRepo.findAllTemplates(keywords);

backend/services/data-cleaning-service/src/main/java/com/datamate/cleaning/common/exception/CleanErrorCode.java

@@ -12,7 +12,7 @@ public enum CleanErrorCode implements ErrorCode {
      */
     DUPLICATE_TASK_NAME("clean.0001", "清洗任务名称重复"),
 
-    CREATE_DATASET_FAILED("clean.0002", "创建数据集失败");
+    IN_AND_OUT_NOT_MATCH("clean.0002", "算子输入输出不匹配");
 
     private final String code;
     private final String message;