feat(data-process): 优化上传切分流程与PDF高亮预览

frontend/src/views/data-process/create/StructuredOptionsPanel.vue

@@ -22,12 +22,12 @@ const PREPROCESS_OPTIONS: Array<{
   label: string
   description: string
 }> = [
-  { value: 'clean_invalid', label: '清理无效数据', description: '处理空行、空列和残缺行' },
-  { value: 'detect_structure', label: '识别表格结构', description: '识别表头、多级表头和合并单元格' },
-  { value: 'deduplicate', label: '重复数据去重', description: '删除完全重复或关键字段重复的数据' },
-  { value: 'normalize_format', label: '数据格式标准化', description: '统一编码、空白、字段名和 JSON 序列化格式' },
-  { value: 'filter_anomaly', label: '异常数据过滤', description: '过滤乱码、无效内容和异常记录' },
-  { value: 'desensitize', label: '敏感信息脱敏', description: '处理姓名、手机号、邮箱等敏感信息' },
+  { value: 'clean_invalid', label: '清理无效数据', description: '清理全空列，并剔除关键字段残缺的数据行' },
+  { value: 'detect_structure', label: '识别表格结构', description: '识别多级表头与合并单元格，并将嵌套字段展平' },
+  { value: 'deduplicate', label: '重复数据去重', description: '基于整行精确匹配和关键字段组合删除重复记录' },
+  { value: 'normalize_format', label: '数据格式标准化', description: '按所选规则统一编码、空白、字段名及 JSON 序列化格式' },
+  { value: 'filter_anomaly', label: '异常数据过滤', description: '使用 IQR 识别数值离群值，并过滤乱码等异常记录' },
+  { value: 'desensitize', label: '敏感信息脱敏', description: '识别并脱敏姓名、手机号、邮箱和身份证号' },
 ]
 
 function updateField<K extends keyof StructuredProcessOptions>(
@@ -43,9 +43,11 @@ function updateGenerationOptions(value: GenerationControlOptions) {
 
 function updatePreprocessOptions(value: Array<string | number | boolean>) {
   const allowedValues = new Set(PREPROCESS_OPTIONS.map((option) => option.value))
-  const preprocessOptions = value.filter(
-    (option): option is PreprocessOption => typeof option === 'string' && allowedValues.has(option as PreprocessOption),
-  )
+  const preprocessOptions = Array.from(new Set(value.filter(
+    (option): option is PreprocessOption => (
+      typeof option === 'string' && allowedValues.has(option as PreprocessOption)
+    ),
+  )))
   updateField('preprocessOptions', preprocessOptions)
 }
 </script>