fix: fix the writing and query logic of dataset labels (#320)

Author: hefanli

backend/services/data-management-service/src/main/java/com/datamate/datamanagement/application/DatasetApplicationService.java

@@ -194,7 +194,7 @@ public PagedResponse<DatasetResponse> getDatasets(DatasetPagingQuery query) {
     /**
      * 处理标签名称，创建或获取标签
      */
-    private String processTagNames(List<String> tagNames) {
+    private List<Tag> processTagNames(List<String> tagNames) {
         Set<Tag> tags = new HashSet<>();
         for (String tagName : tagNames) {
             Tag tag = tagMapper.findByName(tagName);
@@ -209,16 +209,7 @@ private String processTagNames(List<String> tagNames) {
             tagMapper.updateUsageCount(tag.getId(), tag.getUsageCount());
             tags.add(tag);
         }
-        ObjectMapper mapper = new ObjectMapper();
-        try {
-            mapper.registerModule(new JavaTimeModule());
-            // 可选：配置日期时间格式
-            mapper.disable(SerializationFeature.WRITE_DATES_AS_TIMESTAMPS);
-            return mapper.writeValueAsString(tags);
-        } catch (JsonProcessingException e) {
-            log.warn("Parse tags to json error.");
-            return null;
-        }
+        return tags.stream().toList();
     }
 
     /**

backend/services/data-management-service/src/main/java/com/datamate/datamanagement/domain/model/dataset/Dataset.java

@@ -3,6 +3,7 @@
 import com.baomidou.mybatisplus.annotation.TableField;
 import com.baomidou.mybatisplus.annotation.TableName;
 import com.datamate.common.domain.model.base.BaseEntity;
+import com.datamate.common.infrastructure.config.PgJsonTypeHandler;
 import com.datamate.datamanagement.common.enums.DatasetStatusType;
 import com.datamate.datamanagement.common.enums.DatasetType;
 import lombok.Getter;
@@ -66,7 +67,8 @@ public class Dataset extends BaseEntity<String> {
     /**
      * 标签列表, JSON格式
      */
-    private String tags;
+    @TableField(typeHandler = PgJsonTypeHandler.class)
+    private List<Tag> tags;
     /**
      * 额外元数据，JSON格式
      */

backend/services/data-management-service/src/main/java/com/datamate/datamanagement/infrastructure/persistence/repository/impl/DatasetRepositoryImpl.java

@@ -65,10 +65,12 @@ public IPage<Dataset> findByCriteria(IPage<Dataset> page, DatasetPagingQuery que
           */
         for (String tagName : query.getTags()) {
             wrapper.and(w ->
-                w.apply("tags IS NOT NULL " +
-                    "AND JSON_VALID(tags) = 1 " +
-                    "AND JSON_LENGTH(tags) > 0 " +
-                    "AND JSON_SEARCH(tags, 'one', {0}, NULL, '$[*].name') IS NOT NULL", tagName)
+                w.apply("EXISTS ( " +
+                    "SELECT 1 FROM jsonb_array_elements( " +
+                    "CASE WHEN jsonb_typeof(tags::jsonb) = 'array' THEN tags::jsonb ELSE '[]'::jsonb END " +
+                    ") AS tag " +
+                    "WHERE tag->>'name' = {0} " +
+                    ")", tagName)
             );
         }
         wrapper.orderByDesc(Dataset::getCreatedAt);

backend/services/data-management-service/src/main/java/com/datamate/datamanagement/interfaces/converter/DatasetConverter.java

@@ -4,15 +4,8 @@
 import com.datamate.datamanagement.domain.model.dataset.Dataset;
 import com.datamate.datamanagement.domain.model.dataset.DatasetFile;
 import com.datamate.datamanagement.domain.model.dataset.FileTag;
-import com.datamate.datamanagement.domain.model.dataset.Tag;
 import com.datamate.datamanagement.interfaces.dto.*;
-import com.fasterxml.jackson.core.JsonProcessingException;
-import com.fasterxml.jackson.core.type.TypeReference;
-import com.fasterxml.jackson.databind.ObjectMapper;
-import com.fasterxml.jackson.databind.SerializationFeature;
-import com.fasterxml.jackson.datatype.jsr310.JavaTimeModule;
 import org.apache.commons.collections4.CollectionUtils;
-import org.apache.commons.lang3.StringUtils;
 import org.mapstruct.Mapper;
 import org.mapstruct.Mapping;
 import org.mapstruct.Named;
@@ -34,7 +27,6 @@ public interface DatasetConverter {
     @Mapping(source = "sizeBytes", target = "totalSize")
     @Mapping(source = "path", target = "targetLocation")
     @Mapping(source = "files", target = "distribution", qualifiedByName = "getDistribution")
-    @Mapping(source = "tags", target = "tags", qualifiedByName = "getDatasetTags")
     DatasetResponse convertToResponse(Dataset dataset);
 
     /**
@@ -91,28 +83,4 @@ default Map<String, Map<String, Long>> getDistribution(List<DatasetFile> dataset
         }
         return distribution;
     }
-
-    /**
-     * 获取数据集标签
-     *
-     * @param datasetTag 数据集标签
-     * @return 标签
-     */
-    @Named("getDatasetTags")
-    default List<TagResponse> getDatasetTags(String datasetTag) {
-        List<TagResponse> tagResponses = new ArrayList<>();
-        if (StringUtils.isBlank(datasetTag)) {
-            return tagResponses;
-        }
-        ObjectMapper mapper = new ObjectMapper();
-        try {
-            mapper.registerModule(new JavaTimeModule());
-            // 可选：配置日期时间格式
-            mapper.disable(SerializationFeature.WRITE_DATES_AS_TIMESTAMPS);
-            return mapper.readValue(datasetTag, new TypeReference<List<Tag>>() {
-            }).stream().map(TagConverter.INSTANCE::convertToResponse).toList();
-        } catch (Exception e) {
-            return Collections.emptyList();
-        }
-    }
 }

backend/shared/domain-common/src/main/java/com/datamate/common/infrastructure/config/PgJsonTypeHandler.java

@@ -6,6 +6,7 @@
 import org.apache.ibatis.type.MappedTypes;
 import org.postgresql.util.PGobject;
 
+import java.lang.reflect.Field;
 import java.sql.PreparedStatement;
 import java.sql.SQLException;
 
@@ -18,6 +19,10 @@ public PgJsonTypeHandler(Class<?> type) {
         super(type);
     }
 
+    public PgJsonTypeHandler(Class<?> type, Field field) {
+        super(type, field);
+    }
+
     @Override
     public void setNonNullParameter(PreparedStatement ps, int i, Object parameter, JdbcType jdbcType) throws SQLException {
         // 1. 先借助父类转成 JSON 字符串

scripts/db/data-management-init.sql

@@ -14,7 +14,7 @@ CREATE TABLE IF NOT EXISTS t_dm_datasets (
     file_count BIGINT DEFAULT 0,
     record_count BIGINT DEFAULT 0,
     retention_days INTEGER DEFAULT 0,
-    tags TEXT,
+    tags JSONB,
     metadata JSONB,
     status VARCHAR(50) DEFAULT 'DRAFT',
     is_public BOOLEAN DEFAULT FALSE,