feat(frontend): 更新三种切分模式与PDF定位

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

@@ -66,7 +66,13 @@ const locationText = computed(() => {
 })
 
 function pageForItem(item: PreviewItem | null) {
-  if (!item || item.sourceStart == null || item.sourceEnd == null) return null
+  if (!item) return null
+  if (item.sourceStart == null || item.sourceEnd == null) {
+    const pageNumber = item.sourcePages?.[0]
+    return pageNumber == null
+      ? null
+      : pageRanges.value.find((page) => page.page_number === pageNumber) ?? null
+  }
   return pageRanges.value.find((page) => (
     item.sourceStart! >= page.source_start && item.sourceStart! < page.source_end
   )) ?? pageRanges.value.find((page) => (
@@ -76,7 +82,10 @@ function pageForItem(item: PreviewItem | null) {
 
 function selectedTextForPage(page: DataProcessPdfPageRange) {
   const item = props.selectedItem
-  if (!item || item.sourceStart == null || item.sourceEnd == null) return ''
+  if (!item) return ''
+  if (item.sourceStart == null || item.sourceEnd == null) {
+    return item.sourcePages?.includes(page.page_number) ? item.originalContent : ''
+  }
   const intersectionStart = Math.max(item.sourceStart, page.source_start)
   const intersectionEnd = Math.min(item.sourceEnd, page.source_end)
   if (intersectionEnd <= intersectionStart) return ''
@@ -145,7 +154,10 @@ function applySelectedHighlight(page: DataProcessPdfPageRange | null) {
   for (const element of textLayer?.textDivs ?? []) {
     element.classList.remove('is-slice-highlighted')
   }
-  if (!item || item.sourceStart == null || item.sourceEnd == null) {
+  if (!item || (
+    (item.sourceStart == null || item.sourceEnd == null)
+    && !item.sourcePages?.length
+  )) {
     highlightState.value = item ? 'manual' : 'idle'
     return
   }
@@ -248,7 +260,10 @@ async function renderCurrentPage(force = false) {
 async function locateSelectedItem() {
   if (!documentRef.value) return
   const item = props.selectedItem
-  if (!item || item.sourceStart == null || item.sourceEnd == null) {
+  if (!item || (
+    (item.sourceStart == null || item.sourceEnd == null)
+    && !item.sourcePages?.length
+  )) {
     applySelectedHighlight(null)
     return
   }

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

@@ -118,6 +118,11 @@ function itemNumber(item: PreviewItem) {
 }
 
 function lineRange(item: PreviewItem) {
+  if (item.sourcePages?.length) {
+    const first = item.sourcePages[0]
+    const last = item.sourcePages[item.sourcePages.length - 1]
+    return first === last ? `来源：第 ${first} 页` : `来源：第 ${first}–${last} 页`
+  }
   if (item.sourceStartLine == null || item.sourceEndLine == null) return '手动新增，无源文件定位'
   return item.sourceStartLine === item.sourceEndLine
     ? `来源：第 ${item.sourceStartLine} 行`

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

@@ -75,9 +75,6 @@ const chunkValidationMessage = computed(() => {
   ) {
     return '重叠长度与最小切片长度之和不能大于切片长度'
   }
-  if (props.unstructuredOptions.chunkMethod === 'custom' && !props.unstructuredOptions.customDelimiter.trim()) {
-    return '请输入自定义分隔符'
-  }
   return ''
 })
 

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

@@ -30,15 +30,16 @@ const SMART_PREPROCESS_OPTIONS: UnstructuredPreprocessOption[] = [
 ]
 
 const CHUNK_METHODS: Array<{ value: ChunkMethod; label: string }> = [
-  { value: 'structure', label: '文档结构' },
-  { value: 'fixed', label: '固定 Token' },
-  { value: 'custom', label: '自定义分隔符' },
+  { value: 'layout_hybrid', label: '版面结构混合切分' },
+  { value: 'semantic', label: '语义切分' },
+  { value: 'fixed', label: '固定 Token 切分' },
 ]
 
 const UNSTRUCTURED_NUMBER_LIMITS = {
   chunkSize: { min: 200, max: 2000 },
   chunkOverlap: { min: 0, max: 500 },
   minChunkSize: { min: 20, max: 500 },
+  semanticBreakpointPercentile: { min: 1, max: 99 },
   qaPairsPerChunk: { min: 1, max: 3 },
 } as const
 
@@ -160,7 +161,7 @@ defineExpose({ revealValidation })
     <div class="section-title-row">
       <div>
         <h3>切分选项</h3>
-        <p>按文档结构、固定 Token 或自定义分隔符拆分长文档</p>
+        <p>优先保留文档版面结构，也可按主题变化或固定 Token 切分</p>
       </div>
     </div>
 
@@ -179,7 +180,9 @@ defineExpose({ revealValidation })
             :value="method.value"
           />
         </el-select>
-        <small>推荐使用文档结构，按标题、段落和句子边界保留完整内容块</small>
+        <small v-if="options.chunkMethod === 'layout_hybrid'">默认推荐，按标题、段落、列表和表格结构切分，并合并过短内容块</small>
+        <small v-else-if="options.chunkMethod === 'semantic'">根据相邻内容的语义变化寻找主题边界，适合长文章和知识材料</small>
+        <small v-else>按句子边界控制固定 Token 长度，速度快且结果稳定</small>
       </label>
 
       <label class="config-field">
@@ -235,17 +238,22 @@ defineExpose({ revealValidation })
           <small>过短的尾部内容会尽量并入前一个切片</small>
         </label>
 
-        <label v-if="options.chunkMethod === 'custom'" class="config-field">
-          <span class="config-field-label">自定义分隔符</span>
-          <el-input
-            :model-value="options.customDelimiter"
-            maxlength="40"
-            show-word-limit
-            placeholder="例如：--- 或 ###"
-            aria-label="自定义分隔符"
-            @update:model-value="updateField('customDelimiter', $event)"
-          />
-          <small>系统会优先在分隔符位置结束当前切片</small>
+        <label v-if="options.chunkMethod === 'semantic'" class="config-field">
+          <span class="config-field-label">语义断点百分位</span>
+          <span class="unit-input">
+            <el-input-number
+              :model-value="options.semanticBreakpointPercentile"
+              :min="1"
+              :max="99"
+              :step="1"
+              :precision="0"
+              controls-position="right"
+              aria-label="语义断点百分位"
+              @update:model-value="updateUnstructuredNumber('semanticBreakpointPercentile', $event)"
+            />
+            <span>%</span>
+          </span>
+          <small>百分位越低切片越多，推荐保持 95%</small>
         </label>
     </div>
 

frontend/src/views/data-process/create/dataProcessCreateState.ts

@@ -30,11 +30,11 @@ export function createDefaultUnstructuredOptions(): UnstructuredProcessOptions {
       'deduplicate_content',
       'preserve_context',
     ],
-    chunkMethod: 'structure',
+    chunkMethod: 'layout_hybrid',
     chunkSize: 800,
     chunkOverlap: 100,
     minChunkSize: 100,
-    customDelimiter: '',
+    semanticBreakpointPercentile: 95,
     preserveTables: true,
     preserveCodeBlocks: true,
     preserveLists: true,

frontend/src/views/data-process/create/types.ts

@@ -46,7 +46,7 @@ export type UnstructuredPreprocessOption =
   | 'desensitize'
   | 'preserve_context'
 
-export type ChunkMethod = 'structure' | 'fixed' | 'custom'
+export type ChunkMethod = 'layout_hybrid' | 'semantic' | 'fixed'
 
 export interface UnstructuredProcessOptions extends GenerationControlOptions {
   preprocessOptions: UnstructuredPreprocessOption[]
@@ -54,7 +54,7 @@ export interface UnstructuredProcessOptions extends GenerationControlOptions {
   chunkSize: number
   chunkOverlap: number
   minChunkSize: number
-  customDelimiter: string
+  semanticBreakpointPercentile: number
   preserveTables: boolean
   preserveCodeBlocks: boolean
   preserveLists: boolean
@@ -110,6 +110,7 @@ export interface PreviewItem {
   sourceEnd: number | null
   sourceStartLine: number | null
   sourceEndLine: number | null
+  sourcePages?: number[]
   tokenCount: number
   status: 'original' | 'modified' | 'manual' | 'invalid'
   qualityScore?: number