feat: 增强数据集预览功能

重构数据集预览页支持多文件切换与内容高亮，Mock 新增预览数据集与按文件 ID 路由的内容返回，并补充回归测试脚本与 npm 脚本注册。

frontend/src/mock/adapter.ts

@@ -12,6 +12,7 @@ import {
   mockTrainedModels,
   mockLocalModels,
   mockDatasets,
+  mockDatasetPreviews,
   mockFineTuneList,
   mockCompareList,
   mockEvalList,
@@ -129,7 +130,12 @@ async function handleMock(config: AxiosRequestConfig) {
   m = url.match(/^\/dataset-manage\/upload\/([^/]+)$/)
   if (m && method === 'post') return ok({ uploaded: true })
   m = url.match(/^\/dataset-manage\/preview\/([^/]+)$/)
-  if (m && method === 'get') return ok(mockLogContent)
+  if (m && method === 'get') {
+    const fileId = decodeURIComponent(m[1])
+    const fallbackKey = fileId.endsWith('-readme') ? 'mock-readme' : 'mock-jsonl'
+    const content = mockDatasetPreviews[fileId] ?? mockDatasetPreviews[fallbackKey]
+    return ok({ content })
+  }
 
   // ==================== 训练任务 ====================
   if (url === '/fine-tune' && method === 'get') return ok(mockFineTuneList)
@@ -265,4 +271,4 @@ export function installMockAdapter(instance: AxiosInstance) {
       return fail(e.message || 'Mock 错误', 500, config)
     }
   }
-}
+}

frontend/src/mock/data.ts

@@ -99,7 +99,22 @@ export const mockLocalModels = {
 
 // ============ 数据集 ============
 export const mockDatasets: DatasetItem[] = [
-  { id: 1, name: '金融问答-训练集', type: 'train', storage_type: 'local', source: 'upload', size: '128 MB', count: 8560, description: '金融领域问答对', create_time: '2025-12-20T08:00:00Z' },
+  {
+    id: 1,
+    name: '金融问答-训练集',
+    type: 'train',
+    storage_type: 'local',
+    source: 'upload',
+    size: '128 MB',
+    count: 8560,
+    description: '面向金融领域问答场景的高质量指令微调数据集',
+    create_time: '2025-12-20T08:00:00Z',
+    files: [
+      { id: 'finance-train-jsonl', name: 'finance_train.jsonl', size: '86.4 MB' },
+      { id: 'finance-validation-jsonl', name: 'finance_validation.jsonl', size: '21.8 MB' },
+      { id: 'dataset-readme', name: 'README.md', size: '4.2 KB' },
+    ],
+  },
   { id: 2, name: '法律文书-训练集', type: 'train', storage_type: 'local', source: 'upload', size: '256 MB', count: 15230, description: '法律文书数据集', create_time: '2025-12-25T10:30:00Z' },
   { id: 3, name: '客服对话-训练集', type: 'train', storage_type: 'minio', source: 'upload', size: '512 MB', count: 24500, description: '客服对话记录', create_time: '2026-01-05T14:20:00Z' },
   { id: 4, name: '金融评测集', type: 'eval', storage_type: 'local', source: 'upload', size: '32 MB', count: 1200, description: '金融领域评测', create_time: '2026-01-10T09:15:00Z' },
@@ -109,16 +124,81 @@ export const mockDatasets: DatasetItem[] = [
   { id: 8, name: '通用指令构造集', type: 'train', storage_type: 'local', source: 'task', size: '148 MB', count: 12600, description: '由指令微调数据构造任务生成', create_time: '2026-07-09T01:42:00Z' },
   { id: 9, name: '用户反馈脱敏集', type: 'test', storage_type: 'minio', source: 'task', size: '72 MB', count: 9340, description: '由敏感信息脱敏任务生成', create_time: '2026-07-09T09:18:00Z' },
   { id: 10, name: '多轮对话增强集', type: 'eval', storage_type: 'local', source: 'task', size: '41 MB', count: 2780, description: '由多轮对话拼接任务生成', create_time: '2026-07-10T02:06:00Z' },
-]
+].map((dataset) => ({
+  ...dataset,
+  files: dataset.files?.length
+    ? dataset.files
+    : [
+        { id: `dataset-${dataset.id}-samples`, name: 'dataset_samples.jsonl', size: dataset.size || '12.8 MB' },
+        { id: `dataset-${dataset.id}-readme`, name: 'README.md', size: '3.8 KB' },
+      ],
+}))
+
+export const mockDatasetPreviews: Record<string, string> = {
+  'finance-train-jsonl': [
+    '{"instruction":"什么是净资产收益率？","input":"","output":"净资产收益率（ROE）用于衡量企业运用自有资本获得收益的能力。"}',
+    '{"instruction":"解释市盈率的含义","input":"某公司股价为 36 元，每股收益为 3 元。","output":"市盈率为股价除以每股收益，本例中市盈率为 12 倍。"}',
+    '{"instruction":"央行降准通常会带来什么影响？","input":"","output":"降准通常会释放银行体系流动性，降低资金成本，并增强信贷投放能力。"}',
+    '{"instruction":"如何理解债券久期？","input":"","output":"久期衡量债券价格对利率变化的敏感程度，久期越长，价格波动通常越大。"}',
+    '{"instruction":"基金定投适合怎样的投资者？","input":"","output":"基金定投适合希望分散择时风险、进行中长期纪律性投资的投资者。"}',
+    '{"instruction":"资产负债率过高意味着什么？","input":"","output":"可能意味着企业偿债压力较大、财务风险较高，但仍需结合行业特点判断。"}',
+    '{"instruction":"通货膨胀如何影响实际收益率？","input":"","output":"实际收益率约等于名义收益率减去通货膨胀率。"}',
+    '{"instruction":"什么是流动比率？","input":"","output":"流动比率等于流动资产除以流动负债，用于衡量短期偿债能力。"}',
+    '{"instruction":"股票分红是否等于投资者获得额外收益？","input":"","output":"不完全等同，除息后股价通常会相应调整，应结合总回报判断。"}',
+    '{"instruction":"如何区分系统性风险与非系统性风险？","input":"","output":"系统性风险影响整个市场，非系统性风险主要与单个公司或行业有关。"}',
+    '{"instruction":"什么是复利？","input":"","output":"复利是将本金和此前产生的收益一并计入下一期收益计算。"}',
+    '{"instruction":"现金流量表主要反映什么？","input":"","output":"现金流量表反映企业经营、投资和筹资活动产生的现金流入与流出。"}',
+  ].join('\n'),
+  'finance-validation-jsonl': [
+    '{"instruction":"计算简单收益率","input":"买入价 100 元，卖出价 108 元，不考虑费用。","output":"简单收益率为 8%。"}',
+    '{"instruction":"什么是信用利差？","input":"","output":"信用利差是信用债收益率相对无风险基准收益率的差额。"}',
+    '{"instruction":"解释最大回撤","input":"","output":"最大回撤描述资产净值从历史高点到随后低点的最大跌幅。"}',
+    '{"instruction":"什么是风险溢价？","input":"","output":"风险溢价是投资者因承担额外风险而要求的超额预期收益。"}',
+  ].join('\n'),
+  'dataset-readme': [
+    '# 金融问答训练集',
+    '',
+    '本数据集用于金融领域指令微调与基础能力评测。',
+    '',
+    '## 文件说明',
+    '',
+    '- `finance_train.jsonl`：训练样本',
+    '- `finance_validation.jsonl`：验证样本',
+    '',
+    '文本编码：UTF-8',
+  ].join('\n'),
+  'mock-jsonl': [
+    '{"instruction":"请概括以下文本的核心观点","input":"人工智能正在提升企业的数据处理效率。","output":"人工智能能够帮助企业提升数据处理效率。"}',
+    '{"instruction":"将用户问题改写为更清晰的表达","input":"这个功能咋用？","output":"请说明该功能的具体使用步骤。"}',
+    '{"instruction":"判断文本情感倾向","input":"这次服务响应很及时，问题也解决了。","output":"正向"}',
+    '{"instruction":"提取文本中的关键实体","input":"远光软件于周一发布了新的模型管理平台。","output":["远光软件","周一","模型管理平台"]}',
+    '{"instruction":"生成简短回复","input":"您好，我想了解数据集上传支持哪些格式？","output":"您好，目前支持 JSON、JSONL、CSV、TXT 等常见格式。"}',
+    '{"instruction":"对以下内容进行分类","input":"如何重置账户密码？","output":"账户与安全"}',
+    '{"instruction":"找出句子中的时间信息","input":"系统将在 7 月 15 日凌晨 2 点进行升级。","output":"7 月 15 日凌晨 2 点"}',
+    '{"instruction":"补全客服回复","input":"用户反馈页面加载缓慢。","output":"已收到您的反馈，我们正在排查页面加载问题，请稍后重试。"}',
+  ].join('\n'),
+  'mock-readme': [
+    '# 数据集说明',
+    '',
+    '当前内容为前端 Mock 数据，用于预览页面布局与交互效果。',
+    '',
+    '## 文件结构',
+    '',
+    '- `dataset_samples.jsonl`：模拟的数据样本',
+    '- `README.md`：数据集使用说明',
+    '',
+    '文本编码：UTF-8',
+  ].join('\n'),
+}
 
 // ============ 训练任务 ============
 export const mockFineTuneList: FineTuneTask[] = [
-  { id: 1, name: 'finance-sft-001', description: '金融领域 SFT 训练', status: 'completed', train_type: 'SFT', train_method: 'lora', template: 'qwen', base_model: 1, train_dataset_id: 1, gpus: [0], progress: 100, train_duration: '2小时18分钟', create_time: '2026-01-15T08:00:00Z' },
-  { id: 2, name: 'legal-sft-002', description: '法律文书 SFT', status: 'completed', train_type: 'SFT', train_method: 'lora', template: 'qwen', base_model: 1, train_dataset_id: 2, gpus: [1], progress: 100, train_duration: '1小时46分钟', create_time: '2026-01-18T10:00:00Z' },
-  { id: 3, name: 'medical-cpt-001', description: '医疗领域继续预训练', status: 'running', train_type: 'CPT', train_method: 'lora', template: 'qwen2_5', base_model: 2, train_dataset_id: 6, gpus: [0, 1], progress: 64, train_duration: '36分钟', create_time: '2026-02-05T09:00:00Z' },
-  { id: 4, name: 'service-dpo-001', description: '客服对话偏好训练', status: 'pending', train_type: 'DPO', train_method: 'lora', template: 'qwen', base_model: 1, train_dataset_id: 3, gpus: [2], progress: 0, train_duration: '-', create_time: '2026-02-08T14:00:00Z' },
-  { id: 5, name: 'finance-sft-002', description: '金融领域二轮微调', status: 'failed', train_type: 'SFT', train_method: 'lora', template: 'qwen', base_model: 1, train_dataset_id: 1, gpus: [3], progress: 32, train_duration: '18分钟', create_time: '2026-02-10T11:00:00Z' },
-  { id: 6, name: 'general-sft-001', description: '通用能力微调', status: 'completed', train_type: 'SFT', train_method: 'full', template: 'llama3', base_model: 3, train_dataset_id: 3, gpus: [0, 2], progress: 100, train_duration: '3小时05分钟', create_time: '2026-02-12T13:00:00Z' },
+  { id: 103942, name: 'finance-sft-001', description: '金融领域 SFT 训练', status: 'completed', train_type: 'SFT', train_method: 'lora', template: 'qwen', base_model: 1, train_dataset_id: 1, gpus: [0], progress: 100, train_duration: '2小时18分钟', create_time: '2026-01-15T08:00:00Z' },
+  { id: 349102, name: 'legal-sft-002', description: '法律文书 SFT', status: 'completed', train_type: 'SFT', train_method: 'lora', template: 'qwen', base_model: 1, train_dataset_id: 2, gpus: [1], progress: 100, train_duration: '1小时46分钟', create_time: '2026-01-18T10:00:00Z' },
+  { id: 849301, name: 'medical-cpt-001', description: '医疗领域继续预训练', status: 'running', train_type: 'CPT', train_method: 'lora', template: 'qwen2_5', base_model: 2, train_dataset_id: 6, gpus: [0, 1], progress: 64, train_duration: '36分钟', create_time: '2026-02-05T09:00:00Z' },
+  { id: 593021, name: 'service-dpo-001', description: '客服对话偏好训练', status: 'pending', train_type: 'DPO', train_method: 'lora', template: 'qwen', base_model: 1, train_dataset_id: 3, gpus: [2], progress: 0, train_duration: '-', create_time: '2026-02-08T14:00:00Z' },
+  { id: 201948, name: 'finance-sft-002', description: '金融领域二轮微调', status: 'failed', train_type: 'SFT', train_method: 'lora', template: 'qwen', base_model: 1, train_dataset_id: 1, gpus: [3], progress: 32, train_duration: '18分钟', create_time: '2026-02-10T11:00:00Z' },
+  { id: 940212, name: 'general-sft-001', description: '通用能力微调', status: 'completed', train_type: 'SFT', train_method: 'full', template: 'llama3', base_model: 3, train_dataset_id: 3, gpus: [0, 2], progress: 100, train_duration: '3小时05分钟', create_time: '2026-02-12T13:00:00Z' },
 ]
 
 // ============ 模型推理/对比 ============