fix：修复配比任务操作问题 (#66)

szc0616 · web-flow · commit 60e228901907 · 2025-11-07T19:01:45.000+08:00
* fix：配比任务需要能够跳转到目标数据集

* feature：增加配比任务详情接口

* fix：删除不存在的配比详情页面

* fix：使用正式的逻辑来展示标签

* fix：参数默认值去掉多余的-

* fix：修复配比任务相关操作
diff --git a/backend/services/data-management-service/src/main/java/com/datamate/datamanagement/domain/model/dataset/DatasetFile.java b/backend/services/data-management-service/src/main/java/com/datamate/datamanagement/domain/model/dataset/DatasetFile.java
@@ -2,8 +2,10 @@
 
 import com.baomidou.mybatisplus.annotation.TableId;
 import com.baomidou.mybatisplus.annotation.TableName;
+import com.fasterxml.jackson.core.type.TypeReference;
 import com.fasterxml.jackson.databind.ObjectMapper;
 import lombok.*;
+import lombok.extern.slf4j.Slf4j;
 import org.apache.commons.lang3.StringUtils;
 
 import java.time.LocalDateTime;
@@ -17,6 +19,7 @@
 @Getter
 @Setter
 @Builder
+@Slf4j
 @NoArgsConstructor
 @AllArgsConstructor
 @TableName("t_dm_dataset_files")
@@ -42,11 +45,12 @@ public class DatasetFile {
      *
      * @return 标签列表
      */
-    public List<String> analyzeTag() {
+    public List<FileTag> analyzeTag() {
         try {
             ObjectMapper mapper = new ObjectMapper();
-            return mapper.readValue(tags, List.class);
+            return mapper.readValue(tags, new TypeReference<List<FileTag>>() {});
         } catch (Exception e) {
+            log.error(e.getMessage(), e);
             return Collections.emptyList();
         }
     }
diff --git a/backend/services/data-management-service/src/main/java/com/datamate/datamanagement/domain/model/dataset/FileTag.java b/backend/services/data-management-service/src/main/java/com/datamate/datamanagement/domain/model/dataset/FileTag.java
@@ -0,0 +1,48 @@
+package com.datamate.datamanagement.domain.model.dataset;
+
+import com.fasterxml.jackson.annotation.JsonIgnoreProperties;
+import com.fasterxml.jackson.databind.PropertyNamingStrategies;
+import com.fasterxml.jackson.databind.annotation.JsonNaming;
+import lombok.AllArgsConstructor;
+import lombok.Getter;
+import lombok.NoArgsConstructor;
+import lombok.Setter;
+import org.apache.commons.lang3.StringUtils;
+
+import java.util.ArrayList;
+import java.util.List;
+import java.util.Map;
+
+@Getter
+@Setter
+@NoArgsConstructor
+@AllArgsConstructor
+@JsonIgnoreProperties(ignoreUnknown = true)
+@JsonNaming(PropertyNamingStrategies.SnakeCaseStrategy.class)
+public class FileTag {
+    private Map<String, Object> value;
+
+    private String type;
+
+    private String id;
+
+    private String fromName;
+
+    public List<String> getTags() {
+        List<String> tags = new ArrayList<>();
+        Object tagValues = value.get(type);
+        if (tagValues instanceof List) {
+            for (Object tag : (List<?>) tagValues) {
+                if (tag instanceof String) {
+                    tags.add((String) tag);
+                }
+            }
+        } else if (tagValues instanceof String) {
+            tags.add((String) tagValues);
+        }
+        if(StringUtils.isNotEmpty(fromName)) {
+            return tags.stream().map(tag -> fromName + " " + tag).toList();
+        }
+        return tags;
+    }
+}
diff --git a/backend/services/data-management-service/src/main/java/com/datamate/datamanagement/interfaces/converter/DatasetConverter.java b/backend/services/data-management-service/src/main/java/com/datamate/datamanagement/interfaces/converter/DatasetConverter.java
@@ -2,6 +2,7 @@
 
 import com.datamate.common.infrastructure.exception.BusinessException;
 import com.datamate.common.infrastructure.exception.SystemErrorCode;
+import com.datamate.datamanagement.domain.model.dataset.FileTag;
 import com.datamate.datamanagement.interfaces.dto.CreateDatasetRequest;
 import com.datamate.datamanagement.interfaces.dto.DatasetFileResponse;
 import com.datamate.datamanagement.interfaces.dto.DatasetResponse;
@@ -71,12 +72,12 @@ default Map<String, Long> getDistribution(List<DatasetFile> datasetFiles) {
             return distribution;
         }
         for (DatasetFile datasetFile : datasetFiles) {
-            List<String> tags = datasetFile.analyzeTag();
+            List<FileTag> tags = datasetFile.analyzeTag();
             if (CollectionUtils.isEmpty(tags)) {
-                continue;
+                return distribution;
             }
-            for (String tag : tags) {
-                distribution.put(tag, distribution.getOrDefault(tag, 0L) + 1);
+            for (FileTag tag : tags) {
+                tag.getTags().forEach(tagName -> distribution.put(tagName, distribution.getOrDefault(tagName, 0L) + 1));
             }
         }
         return distribution;
diff --git a/backend/services/rag-indexer-service/src/main/java/com/datamate/rag/indexer/infrastructure/event/RagEtlService.java b/backend/services/rag-indexer-service/src/main/java/com/datamate/rag/indexer/infrastructure/event/RagEtlService.java
@@ -51,9 +51,9 @@
 public class RagEtlService {
     private static final Semaphore SEMAPHORE = new Semaphore(10);
 
-    @Value("${datamate.rag.milvus-host:-milvus-standalone}")
+    @Value("${datamate.rag.milvus-host:milvus-standalone}")
     private String milvusHost;
-    @Value("${datamate.rag.milvus-port:-19530}")
+    @Value("${datamate.rag.milvus-port:19530}")
     private int milvusPort;
 
     private final RagFileRepository ragFileRepository;
diff --git a/frontend/src/pages/RatioTask/Create/CreateRatioTask.tsx b/frontend/src/pages/RatioTask/Create/CreateRatioTask.tsx
@@ -76,116 +76,6 @@ export default function CreateRatioTask() {
       setCreating(false);
     }
   };
-  const totalConfigured = useMemo(
-    () =>
-      ratioTaskForm?.ratioConfigs?.reduce?.(
-        (sum, c) => sum + (c.quantity || 0),
-        0
-      ) || 0,
-    [ratioTaskForm.ratioConfigs]
-  );
-
-  // dataset selection is handled inside SelectDataset via onSelectedDatasetsChange
-
-  const updateRatioConfig = (source: string, quantity: number) => {
-    setRatioTaskForm((prev) => {
-      const existingIndex = prev.ratioConfigs.findIndex(
-        (config) => config.source === source
-      );
-      const totalOtherQuantity = prev.ratioConfigs
-        .filter((config) => config.source !== source)
-        .reduce((sum, config) => sum + config.quantity, 0);
-
-      const newConfig = {
-        id: source,
-        name: source,
-        type: prev.ratioType,
-        quantity: Math.min(
-          quantity,
-          prev.totalTargetCount - totalOtherQuantity
-        ),
-        percentage: Math.round((quantity / prev.totalTargetCount) * 100),
-        source,
-      };
-
-      if (existingIndex >= 0) {
-        const newConfigs = [...prev.ratioConfigs];
-        newConfigs[existingIndex] = newConfig;
-        return { ...prev, ratioConfigs: newConfigs };
-      } else {
-        return { ...prev, ratioConfigs: [...prev.ratioConfigs, newConfig] };
-      }
-    });
-  };
-
-  const generateAutoRatio = () => {
-    const selectedCount = ratioTaskForm.selectedDatasets.length;
-    if (selectedCount === 0) return;
-
-    const baseQuantity = Math.floor(
-      ratioTaskForm.totalTargetCount / selectedCount
-    );
-    const remainder = ratioTaskForm.totalTargetCount % selectedCount;
-
-    const newConfigs = ratioTaskForm.selectedDatasets.map(
-      (datasetId, index) => {
-        const quantity = baseQuantity + (index < remainder ? 1 : 0);
-        return {
-          id: datasetId,
-          name: datasetId,
-          type: ratioTaskForm.ratioType,
-          quantity,
-          percentage: Math.round(
-            (quantity / ratioTaskForm.totalTargetCount) * 100
-          ),
-          source: datasetId,
-        };
-      }
-    );
-
-    setRatioTaskForm((prev) => ({ ...prev, ratioConfigs: newConfigs }));
-  };
-
-  // 标签模式下，更新某数据集的某个标签的数量
-  const updateLabelRatioConfig = (
-    datasetId: string,
-    label: string,
-    quantity: number
-  ) => {
-    const sourceKey = `${datasetId}_${label}`;
-    setRatioTaskForm((prev) => {
-      const existingIndex = prev.ratioConfigs.findIndex(
-        (c) => c.source === sourceKey
-      );
-      const totalOtherQuantity = prev.ratioConfigs
-        .filter((c) => c.source !== sourceKey)
-        .reduce((sum, c) => sum + c.quantity, 0);
-
-      const dist = distributions[datasetId] || {};
-      const labelMax = dist[label] ?? Infinity;
-      const cappedQuantity = Math.max(
-        0,
-        Math.min(quantity, prev.totalTargetCount - totalOtherQuantity, labelMax)
-      );
-
-      const newConfig = {
-        id: sourceKey,
-        name: label,
-        type: "label",
-        quantity: cappedQuantity,
-        percentage: Math.round((cappedQuantity / prev.totalTargetCount) * 100),
-        source: sourceKey,
-      };
-
-      if (existingIndex >= 0) {
-        const newConfigs = [...prev.ratioConfigs];
-        newConfigs[existingIndex] = newConfig;
-        return { ...prev, ratioConfigs: newConfigs };
-      } else {
-        return { ...prev, ratioConfigs: [...prev.ratioConfigs, newConfig] };
-      }
-    });
-  };
 
   const handleValuesChange = (_, allValues) => {
     setRatioTaskForm({ ...ratioTaskForm, ...allValues });
diff --git a/frontend/src/pages/RatioTask/Home/RatioTask.tsx b/frontend/src/pages/RatioTask/Home/RatioTask.tsx
@@ -123,7 +123,7 @@ export default function RatioTasksPage() {
               <Button
                 type="text"
                 icon={op.icon}
-                onClick={() => op.onClick(task.id)}
+                onClick={() => op.onClick(task)}
               />
             </Tooltip>
           ))}
diff --git a/frontend/src/pages/RatioTask/ratio.api.ts b/frontend/src/pages/RatioTask/ratio.api.ts
@@ -16,8 +16,7 @@ export function createRatioTaskUsingPost(data: any) {
 }
 
 // 删除配比任务（支持批量）
-export function deleteRatioTasksUsingDelete(ids: string[]) {
-  const qs = (ids || []).map((id) => `ids=${encodeURIComponent(id)}`).join("&");
-  const url = qs ? `/api/synthesis/ratio-task?${qs}` : "/api/synthesis/ratio-task";
+export function deleteRatioTasksUsingDelete(id: string) {
+  const url = `/api/synthesis/ratio-task?ids=${id}`;
   return del(url);
 }
diff --git a/runtime/datamate-python/app/module/dataset/schema/dataset_file.py b/runtime/datamate-python/app/module/dataset/schema/dataset_file.py
@@ -25,4 +25,27 @@ class PagedDatasetFileResponse(BaseModel):
     totalPages: int = Field(..., description="总页数")
     page: int = Field(..., description="当前页码")
     size: int = Field(..., description="每页大小")
-    
+
+class DatasetFileTag(BaseModel):
+    id: str = Field(..., description="标签ID")
+    type: str = Field(..., description="类型")
+    from_name: str = Field(..., description="标签名称")
+    value: dict = Field(..., description="标签值")
+
+    def get_tags(self) -> List[str]:
+        tags = []
+        # 如果 value 是字典类型，根据 type 获取对应的值
+        tag_values = self.value.get(self.type, [])
+
+        # 处理标签值
+        if isinstance(tag_values, list):
+            for tag in tag_values:
+                if isinstance(tag, str):
+                    tags.append(str(tag))
+        elif isinstance(tag_values, str):
+            tags.append(tag_values)
+        # 如果 from_name 不为空，添加前缀
+        if self.from_name:
+            tags = [f"{self.from_name} {tag}" for tag in tags]
+
+        return tags
diff --git a/runtime/datamate-python/app/module/synthesis/service/ratio_task.py b/runtime/datamate-python/app/module/synthesis/service/ratio_task.py
@@ -1,5 +1,6 @@
 from typing import List, Optional, Dict, Any
 import random
+import json
 import os
 import shutil
 import asyncio
@@ -12,6 +13,7 @@
 from app.db.models.ratio_task import RatioInstance, RatioRelation
 from app.db.models import Dataset, DatasetFiles
 from app.db.session import AsyncSessionLocal
+from app.module.dataset.schema.dataset_file import DatasetFileTag
 
 logger = get_logger(__name__)
 
@@ -218,65 +220,46 @@ def _parse_required_tags(conditions: Optional[str]) -> set[str]:
         """
         if not conditions:
             return set()
-        raw = conditions.replace("\n", " ")
-        seps = [",", ";", " "]
-        tokens = [raw]
-        for sep in seps:
-            nxt = []
-            for t in tokens:
-                nxt.extend(t.split(sep))
-            tokens = nxt
-        return {t.strip() for t in tokens if t and t.strip()}
+        data = json.loads(conditions)
+        required_tags = set()
+        if data.get("label"):
+            required_tags.add(data["label"])
+        return required_tags
 
     @staticmethod
-    def _file_contains_tags(f: DatasetFiles, required: set[str]) -> bool:
+    def _file_contains_tags(file: DatasetFiles, required: set[str]) -> bool:
         if not required:
             return True
-        tags = f.tags
+        tags = file.tags
         if not tags:
             return False
         try:
             # tags could be a list of strings or list of objects with 'name'
-            tag_names = set()
-            if isinstance(tags, list):
-                for item in tags:
-                    if isinstance(item, str):
-                        tag_names.add(item)
-                    elif isinstance(item, dict):
-                        name = item.get("name") or item.get("label") or item.get("tag")
-                        if isinstance(name, str):
-                            tag_names.add(name)
-            elif isinstance(tags, dict):
-                # flat dict of name->... treat keys as tags
-                tag_names = set(map(str, tags.keys()))
-            else:
-                return False
-            logger.info(f">>>>>{tags}>>>>>{required}, {tag_names}")
+            tag_names = RatioTaskService.get_all_tags(tags)
             return required.issubset(tag_names)
-        except Exception:
+        except Exception as e:
+            logger.exception(f"Failed to get tags for {file}", e)
             return False
 
     @staticmethod
-    async def get_new_file(f, rel: RatioRelation, target_ds: Dataset) -> DatasetFiles:
-        new_path = f.file_path
-        src_prefix = f"/dataset/{rel.source_dataset_id}"
-        if isinstance(f.file_path, str) and f.file_path.startswith(src_prefix):
-            dst_prefix = f"/dataset/{target_ds.id}"
-            new_path = f.file_path.replace(src_prefix, dst_prefix, 1)
-            dst_dir = os.path.dirname(new_path)
-            # Ensure directory and copy the file in a thread to avoid blocking the event loop
-            await asyncio.to_thread(os.makedirs, dst_dir, exist_ok=True)
-            await asyncio.to_thread(shutil.copy2, f.file_path, new_path)
-
-        new_file = DatasetFiles(
-            dataset_id=target_ds.id,  # type: ignore
-            file_name=f.file_name,
-            file_path=new_path,
-            file_type=f.file_type,
-            file_size=f.file_size,
-            check_sum=f.check_sum,
-            tags=f.tags,
-            dataset_filemetadata=f.dataset_filemetadata,
-            status="ACTIVE",
-        )
-        return new_file
+    def get_all_tags(tags) -> set[str]:
+        """获取所有处理后的标签字符串列表"""
+        all_tags = set()
+        if not tags:
+            return all_tags
+
+        file_tags = []
+        for tag_data in tags:
+            # 处理可能的命名风格转换（下划线转驼峰）
+            processed_data = {}
+            for key, value in tag_data.items():
+                # 将驼峰转为下划线以匹配 Pydantic 模型字段
+                processed_data[key] = value
+            # 创建 DatasetFileTag 对象
+            file_tag = DatasetFileTag(**processed_data)
+            file_tags.append(file_tag)
+
+        for file_tag in file_tags:
+            for tag_data in file_tag.get_tags():
+                all_tags.add(tag_data)
+        return all_tags

Original file line number	Diff line number	Diff line change
`@@ -2,6 +2,7 @@`
`2`	`2`
`3`	`3`	`import com.datamate.common.infrastructure.exception.BusinessException;`
`4`	`4`	`import com.datamate.common.infrastructure.exception.SystemErrorCode;`
	`5`	`+import com.datamate.datamanagement.domain.model.dataset.FileTag;`
`5`	`6`	`import com.datamate.datamanagement.interfaces.dto.CreateDatasetRequest;`
`6`	`7`	`import com.datamate.datamanagement.interfaces.dto.DatasetFileResponse;`
`7`	`8`	`import com.datamate.datamanagement.interfaces.dto.DatasetResponse;`
`@@ -71,12 +72,12 @@ default Map<String, Long> getDistribution(List<DatasetFile> datasetFiles) {`
`71`	`72`	`return distribution;`
`72`	`73`	`}`
`73`	`74`	`for (DatasetFile datasetFile : datasetFiles) {`
`74`		`- List<String> tags = datasetFile.analyzeTag();`
	`75`	`+ List<FileTag> tags = datasetFile.analyzeTag();`
`75`	`76`	`if (CollectionUtils.isEmpty(tags)) {`
`76`		`- continue;`
	`77`	`+ return distribution;`
`77`	`78`	`}`
`78`		`- for (String tag : tags) {`
`79`		`- distribution.put(tag, distribution.getOrDefault(tag, 0L) + 1);`
	`79`	`+ for (FileTag tag : tags) {`
	`80`	`+ tag.getTags().forEach(tagName -> distribution.put(tagName, distribution.getOrDefault(tagName, 0L) + 1));`
`80`	`81`	`}`
`81`	`82`	`}`
`82`	`83`	`return distribution;`
Original file line number	Diff line number	Diff line change
`@@ -16,8 +16,7 @@ export function createRatioTaskUsingPost(data: any) {`
`16`	`16`	`}`
`17`	`17`
`18`	`18`	`// 删除配比任务（支持批量）`
`19`		`-export function deleteRatioTasksUsingDelete(ids: string[]) {`
`20`		- const qs = (ids \|\| []).map((id) => `ids=${encodeURIComponent(id)}`).join("&");
`21`		- const url = qs ? `/api/synthesis/ratio-task?${qs}` : "/api/synthesis/ratio-task";
	`19`	`+export function deleteRatioTasksUsingDelete(id: string) {`
	`20`	+ const url = `/api/synthesis/ratio-task?ids=${id}`;
`22`	`21`	`return del(url);`
`23`	`22`	`}`