feat(data-process): 完善 Word 与 Excel 原文件预览

2026-07-27 16:24:53 +08:00
parent 9025437a37
commit 8a6a6574bb
6 changed files with 743 additions and 3 deletions
--- a/frontend/src/views/data-process/DataProcessCreateView.vue
+++ b/frontend/src/views/data-process/DataProcessCreateView.vue
@@ -934,6 +934,7 @@ onMounted(() => {
            :items="activePreviewItems"
            :process-type="processType"
            :file-name="activePreviewFile?.name ?? ''"
+            :file-format="activePreviewFile?.fileFormat"
            :task-id="taskId"
            :source-file-id="activePreviewFile?.sourceFileId ?? activePreviewFile?.uid ?? null"
            :files="previewFiles"
--- a/frontend/src/views/data-process/create/OfficeSourceViewer.vue
+++ b/frontend/src/views/data-process/create/OfficeSourceViewer.vue
@@ -0,0 +1,622 @@
+<script setup lang="ts">
+import { computed, nextTick, ref, shallowRef, watch } from 'vue'
+import {
+  getDataProcessOfficePreview,
+  getDataProcessSourceRawUrl,
+  type DataProcessDocxPreview,
+  type DataProcessDocxTableRow,
+  type DataProcessOfficePreview,
+  type DataProcessXlsxPreview,
+  type DataProcessXlsxPreviewRow,
+} from '@/api/modules/dataProcess'
+import type { PreviewItem } from './types'
+
+const props = defineProps<{
+  taskId: string | number | null
+  sourceFileId: string | number | null
+  fileName: string
+  fileFormat?: string
+  selectedItem: PreviewItem | null
+}>()
+
+const XLSX_PAGE_SIZE = 100
+const scrollRef = ref<HTMLElement | null>(null)
+const preview = shallowRef<DataProcessOfficePreview | null>(null)
+const loading = ref(false)
+const errorMessage = ref('')
+const activeSheetIndex = ref(0)
+const pageOffset = ref(0)
+let loadSequence = 0
+const prefersReducedMotion = window.matchMedia('(prefers-reduced-motion: reduce)').matches
+
+const normalizedFormat = computed(() => (
+  props.fileFormat?.toLowerCase().replace(/^\./, '')
+  || props.fileName.split('.').pop()?.toLowerCase()
+  || ''
+))
+const isDocx = computed(() => normalizedFormat.value === 'docx')
+const docxPreview = computed((): DataProcessDocxPreview | null => (
+  preview.value?.format === 'docx' ? preview.value : null
+))
+const xlsxPreview = computed((): DataProcessXlsxPreview | null => (
+  preview.value?.format === 'xlsx' ? preview.value : null
+))
+const sourceUrl = computed(() => (
+  props.taskId != null && props.sourceFileId != null
+    ? getDataProcessSourceRawUrl(props.taskId, props.sourceFileId)
+    : ''
+))
+const visibleRowRange = computed(() => {
+  const sheet = xlsxPreview.value?.active_sheet
+  if (!sheet || !sheet.rows.length) return '当前工作表没有可预览记录'
+  const start = sheet.offset + 1
+  const end = sheet.offset + sheet.rows.length
+  return `第 ${start}–${end} 条记录`
+})
+
+function overlapsSelection(start: number, end: number) {
+  const item = props.selectedItem
+  if (!item || item.sourceStart == null || item.sourceEnd == null) return false
+  return end > item.sourceStart && start < item.sourceEnd
+}
+
+function tableRowHighlighted(row: DataProcessDocxTableRow) {
+  return overlapsSelection(row.source_start, row.source_end)
+}
+
+function stableValue(value: unknown): unknown {
+  if (Array.isArray(value)) return value.map(stableValue)
+  if (value && typeof value === 'object') {
+    return Object.fromEntries(
+      Object.entries(value as Record<string, unknown>)
+        .sort(([left], [right]) => left.localeCompare(right))
+        .map(([key, item]) => [key, stableValue(item)]),
+    )
+  }
+  return value
+}
+
+function recordKey(value: unknown) {
+  try {
+    return JSON.stringify(stableValue(value))
+  } catch {
+    return ''
+  }
+}
+
+const selectedRecordKey = computed(() => {
+  const content = props.selectedItem?.originalContent
+  if (!content) return ''
+  try {
+    return recordKey(JSON.parse(content))
+  } catch {
+    return ''
+  }
+})
+
+function xlsxRowHighlighted(row: DataProcessXlsxPreviewRow) {
+  return Boolean(selectedRecordKey.value && recordKey(row.record) === selectedRecordKey.value)
+}
+
+function displayCell(value: unknown) {
+  if (value == null || value === '') return '—'
+  if (typeof value === 'object') return JSON.stringify(value)
+  return String(value)
+}
+
+async function locateSelectedItem() {
+  await nextTick()
+  const selected = scrollRef.value?.querySelector<HTMLElement>(
+    '.docx-block.is-highlighted, .docx-table-row.is-highlighted, .xlsx-row.is-highlighted',
+  )
+  selected?.scrollIntoView({
+    block: 'center',
+    inline: 'nearest',
+    behavior: prefersReducedMotion ? 'auto' : 'smooth',
+  })
+}
+
+async function loadPreview(options: { reset?: boolean } = {}) {
+  const sequence = ++loadSequence
+  if (options.reset) {
+    activeSheetIndex.value = 0
+    pageOffset.value = 0
+    preview.value = null
+  }
+  errorMessage.value = ''
+  if (props.taskId == null || props.sourceFileId == null) {
+    errorMessage.value = '缺少原文件标识，无法加载预览'
+    return
+  }
+
+  loading.value = true
+  try {
+    const result = await getDataProcessOfficePreview(
+      props.taskId,
+      props.sourceFileId,
+      isDocx.value
+        ? {}
+        : {
+            sheet_index: activeSheetIndex.value,
+            offset: pageOffset.value,
+            limit: XLSX_PAGE_SIZE,
+          },
+    )
+    if (sequence !== loadSequence) return
+    preview.value = result
+    if (result.format === 'xlsx') activeSheetIndex.value = result.active_sheet.index
+    await locateSelectedItem()
+  } catch (error) {
+    if (sequence !== loadSequence) return
+    errorMessage.value = error instanceof Error ? error.message : 'Office 原文件预览加载失败'
+  } finally {
+    if (sequence === loadSequence) loading.value = false
+  }
+}
+
+function changeSheet(value: string | number) {
+  activeSheetIndex.value = Number(value)
+  pageOffset.value = 0
+  void loadPreview()
+}
+
+function previousPage() {
+  pageOffset.value = Math.max(0, pageOffset.value - XLSX_PAGE_SIZE)
+  void loadPreview()
+}
+
+function nextPage() {
+  if (!xlsxPreview.value?.active_sheet.has_more) return
+  pageOffset.value += XLSX_PAGE_SIZE
+  void loadPreview()
+}
+
+watch(
+  () => [props.taskId, props.sourceFileId, normalizedFormat.value],
+  () => void loadPreview({ reset: true }),
+  { immediate: true },
+)
+
+watch(
+  () => props.selectedItem?.id,
+  () => void locateSelectedItem(),
+)
+</script>
+
+<template>
+  <div
+    class="office-source-viewer"
+    :aria-label="`${normalizedFormat.toUpperCase()} 预览：${fileName}`"
+  >
+    <div class="office-toolbar">
+      <template v-if="xlsxPreview">
+        <div class="sheet-selector">
+          <span>工作表</span>
+          <el-select
+            :model-value="activeSheetIndex"
+            size="small"
+            aria-label="选择 Excel 工作表"
+            @update:model-value="changeSheet"
+          >
+            <el-option
+              v-for="sheet in xlsxPreview.sheets"
+              :key="sheet.index"
+              :label="sheet.name"
+              :value="sheet.index"
+            />
+          </el-select>
+        </div>
+        <span>{{ visibleRowRange }}</span>
+      </template>
+      <template v-else>
+        <span>Word 网页版式预览</span>
+        <span v-if="docxPreview?.truncated">文档较长，仅展示前 2,000 个内容块</span>
+      </template>
+      <span v-if="loading && preview" class="toolbar-loading" role="status">
+        <i class="fa fa-spinner fa-spin" /> 正在更新预览
+      </span>
+      <a
+        v-if="sourceUrl"
+        class="source-file-link"
+        :href="sourceUrl"
+        target="_blank"
+        rel="noopener noreferrer"
+      >
+        <i class="fa fa-external-link" /> 打开原文件
+      </a>
+    </div>
+
+    <div v-if="loading && !preview" class="office-state" role="status">
+      <i class="fa fa-spinner fa-spin" />
+      <strong>正在加载原文件预览</strong>
+      <span>{{ isDocx ? '正在还原 Word 文档结构' : '正在读取 Excel 工作表' }}</span>
+    </div>
+
+    <div v-else-if="errorMessage" class="office-state is-error" role="alert">
+      <i class="fa fa-exclamation-circle" />
+      <strong>{{ isDocx ? 'Word 预览失败' : 'Excel 预览失败' }}</strong>
+      <span>{{ errorMessage }}</span>
+      <div>
+        <el-button type="primary" size="small" @click="loadPreview()">重试</el-button>
+        <el-button v-if="sourceUrl" tag="a" :href="sourceUrl" target="_blank" size="small">
+          打开原文件
+        </el-button>
+      </div>
+    </div>
+
+    <div v-else-if="docxPreview" ref="scrollRef" class="docx-scroll">
+      <article class="docx-page">
+        <template v-for="(block, index) in docxPreview.blocks" :key="index">
+          <component
+            :is="block.heading_level ? `h${block.heading_level}` : 'p'"
+            v-if="block.type === 'paragraph'"
+            class="docx-block"
+            :class="{
+              'is-highlighted': overlapsSelection(block.source_start, block.source_end),
+              'is-list': block.is_list,
+            }"
+            :style="{ textAlign: block.alignment }"
+            :data-source-start="block.source_start"
+          >
+            {{ block.text }}
+          </component>
+          <div v-else class="docx-table-wrap">
+            <table class="docx-table">
+              <tbody>
+                <tr
+                  v-for="(row, rowIndex) in block.rows"
+                  :key="rowIndex"
+                  class="docx-table-row"
+                  :class="{ 'is-highlighted': tableRowHighlighted(row) }"
+                  :data-source-start="row.source_start"
+                >
+                  <td v-for="(cell, cellIndex) in row.cells" :key="cellIndex">{{ cell || ' ' }}</td>
+                </tr>
+              </tbody>
+            </table>
+          </div>
+        </template>
+        <div v-if="!docxPreview.blocks.length" class="office-empty">文档中没有可预览的正文</div>
+      </article>
+    </div>
+
+    <template v-else-if="xlsxPreview">
+      <div ref="scrollRef" class="xlsx-scroll">
+        <table v-if="xlsxPreview.active_sheet.columns.length" class="xlsx-grid">
+          <thead>
+            <tr>
+              <th class="row-number-cell">#</th>
+              <th
+                v-for="column in xlsxPreview.active_sheet.columns"
+                :key="column"
+                :title="column"
+              >
+                {{ column }}
+              </th>
+            </tr>
+          </thead>
+          <tbody>
+            <tr
+              v-for="row in xlsxPreview.active_sheet.rows"
+              :key="row.row_number"
+              class="xlsx-row"
+              :class="{ 'is-highlighted': xlsxRowHighlighted(row) }"
+            >
+              <th class="row-number-cell">{{ row.row_number }}</th>
+              <td
+                v-for="(value, cellIndex) in row.values"
+                :key="cellIndex"
+                :title="displayCell(value)"
+              >
+                {{ displayCell(value) }}
+              </td>
+            </tr>
+          </tbody>
+        </table>
+        <div v-else class="office-empty">当前工作表没有可预览记录</div>
+      </div>
+      <div class="xlsx-pagination">
+        <el-button
+          size="small"
+          :disabled="pageOffset === 0 || loading"
+          aria-label="上一页工作表记录"
+          @click="previousPage"
+        >
+          <i class="fa fa-angle-left" /> 上一页
+        </el-button>
+        <span>{{ visibleRowRange }}</span>
+        <el-button
+          size="small"
+          :disabled="!xlsxPreview.active_sheet.has_more || loading"
+          aria-label="下一页工作表记录"
+          @click="nextPage"
+        >
+          下一页 <i class="fa fa-angle-right" />
+        </el-button>
+      </div>
+    </template>
+  </div>
+</template>
+
+<style scoped lang="scss">
+.office-source-viewer {
+  display: flex;
+  min-width: 0;
+  min-height: 0;
+  flex: 1;
+  flex-direction: column;
+  background: #f4f6f9;
+}
+
+.office-toolbar {
+  display: flex;
+  min-height: 42px;
+  flex: none;
+  align-items: center;
+  gap: 12px;
+  padding: 6px 12px;
+  color: #7d8798;
+  background: #fff;
+  border-bottom: 1px solid #e5e8ee;
+  font-size: 11px;
+
+}
+
+.sheet-selector {
+  display: flex;
+  min-width: 0;
+  align-items: center;
+  gap: 8px;
+
+  > span {
+    flex: none;
+  }
+
+  :deep(.el-select) {
+    width: min(220px, 28vw);
+  }
+}
+
+.source-file-link {
+  flex: none;
+  margin-left: auto;
+  color: #5147df;
+  text-decoration: none;
+
+  &:hover,
+  &:focus-visible {
+    text-decoration: underline;
+  }
+}
+
+.toolbar-loading {
+  color: #5b50f2;
+  white-space: nowrap;
+}
+
+.office-state {
+  display: flex;
+  flex: 1;
+  align-items: center;
+  justify-content: center;
+  flex-direction: column;
+  gap: 9px;
+  padding: 28px;
+  color: #667085;
+  text-align: center;
+
+  > i {
+    color: #5b50f2;
+    font-size: 28px;
+  }
+
+  > strong {
+    color: #344054;
+    font-size: 14px;
+  }
+
+  > span {
+    max-width: 420px;
+    font-size: 12px;
+    line-height: 1.6;
+  }
+
+  &.is-error > i {
+    color: #d92d20;
+  }
+}
+
+.docx-scroll {
+  flex: 1;
+  min-height: 0;
+  padding: 22px;
+  overflow: auto;
+  scroll-behavior: smooth;
+}
+
+.docx-page {
+  width: min(760px, 100%);
+  min-height: calc(100% - 2px);
+  padding: 54px clamp(30px, 7%, 68px);
+  margin: 0 auto;
+  color: #262b34;
+  background: #fff;
+  border: 1px solid #dfe3e9;
+  box-shadow: 0 2px 10px rgb(15 23 42 / 8%);
+  font-family: "Songti SC", SimSun, serif;
+  font-size: 13px;
+  line-height: 1.8;
+}
+
+.docx-block {
+  padding: 2px 6px;
+  margin: 0 0 10px;
+  border-radius: 3px;
+  white-space: pre-wrap;
+  word-break: break-word;
+  transition: background-color 0.18s ease, box-shadow 0.18s ease;
+
+  &.is-list {
+    padding-left: 22px;
+  }
+
+  &.is-highlighted {
+    background: #fff0b8;
+    box-shadow: inset 3px 0 #f0b429;
+  }
+}
+
+h1.docx-block { font-size: 22px; }
+h2.docx-block { font-size: 19px; }
+h3.docx-block { font-size: 17px; }
+h4.docx-block,
+h5.docx-block,
+h6.docx-block { font-size: 15px; }
+
+.docx-table-wrap {
+  max-width: 100%;
+  margin: 12px 0 18px;
+  overflow-x: auto;
+}
+
+.docx-table {
+  width: 100%;
+  border-collapse: collapse;
+  table-layout: fixed;
+
+  td {
+    padding: 7px 9px;
+    border: 1px solid #9da5b2;
+    vertical-align: top;
+    white-space: pre-wrap;
+    word-break: break-word;
+  }
+}
+
+.docx-table-row.is-highlighted td {
+  background: #fff0b8;
+}
+
+.xlsx-scroll {
+  flex: 1;
+  min-width: 0;
+  min-height: 0;
+  overflow: auto;
+  background: #fff;
+  scroll-behavior: smooth;
+}
+
+.xlsx-grid {
+  min-width: 100%;
+  color: #344054;
+  border-spacing: 0;
+  border-collapse: separate;
+  table-layout: auto;
+  font-size: 11px;
+
+  th,
+  td {
+    min-width: 120px;
+    max-width: 320px;
+    height: 36px;
+    padding: 7px 10px;
+    overflow: hidden;
+    text-align: left;
+    text-overflow: ellipsis;
+    white-space: nowrap;
+    border-right: 1px solid #e4e7ec;
+    border-bottom: 1px solid #e4e7ec;
+  }
+
+  thead th {
+    position: sticky;
+    z-index: 2;
+    top: 0;
+    color: #475467;
+    background: #f2f4f7;
+    font-weight: 650;
+  }
+
+  tbody tr:hover td,
+  tbody tr:hover th {
+    background: #f9fafb;
+  }
+}
+
+.row-number-cell {
+  position: sticky;
+  z-index: 1;
+  left: 0;
+  min-width: 54px !important;
+  width: 54px;
+  color: #98a2b3;
+  text-align: center !important;
+  background: #f8fafc;
+  font-variant-numeric: tabular-nums;
+}
+
+thead .row-number-cell {
+  z-index: 3;
+}
+
+.xlsx-row.is-highlighted {
+  td,
+  th {
+    background: #fff0b8;
+    box-shadow: inset 0 2px #f0b429, inset 0 -2px #f0b429;
+  }
+}
+
+.xlsx-pagination {
+  display: flex;
+  min-height: 46px;
+  flex: none;
+  align-items: center;
+  justify-content: flex-end;
+  gap: 12px;
+  padding: 7px 12px;
+  color: #7d8798;
+  background: #fff;
+  border-top: 1px solid #e5e8ee;
+  font-size: 11px;
+}
+
+.office-empty {
+  display: flex;
+  min-height: 180px;
+  align-items: center;
+  justify-content: center;
+  color: #98a2b3;
+  font-size: 12px;
+}
+
+@media (max-width: 900px) {
+  .office-source-viewer {
+    height: 360px;
+    flex: none;
+  }
+
+  .office-toolbar {
+    flex-wrap: wrap;
+  }
+
+  .docx-scroll {
+    padding: 12px;
+  }
+
+  .docx-page {
+    padding: 34px 24px;
+  }
+}
+
+@media (prefers-reduced-motion: reduce) {
+  .docx-scroll,
+  .xlsx-scroll {
+    scroll-behavior: auto;
+  }
+
+  .docx-block {
+    transition: none;
+  }
+}
+</style>
--- a/frontend/src/views/data-process/create/PreviewCompareStep.vue
+++ b/frontend/src/views/data-process/create/PreviewCompareStep.vue
@@ -1,5 +1,6 @@
 <script setup lang="ts">
 import { computed, nextTick, ref, watch } from 'vue'
+import OfficeSourceViewer from './OfficeSourceViewer.vue'
 import PdfSourceViewer from './PdfSourceViewer.vue'
 import { sourceLines } from './previewModel'
 import type { PreviewItem, ProcessType } from './types'
@@ -10,6 +11,7 @@ const props = defineProps<{
  selectedId: string | null
  processType: ProcessType
  fileName: string
+  fileFormat?: string
  taskId: string | number | null
  sourceFileId: string | number | null
  files: { id: string; name: string; count: number; modifiedCount: number }[]
@@ -34,7 +36,13 @@ const editorDraft = ref('')
 const lines = computed(() => sourceLines(props.sourceText))
 const selectedItem = computed(() => props.items.find((item) => item.id === props.selectedId) ?? props.items[0])
 const editingItem = computed(() => props.items.find((item) => item.id === editingItemId.value))
-const isPdfSource = computed(() => /\.pdf$/i.test(props.fileName))
+const normalizedFileFormat = computed(() => (
+  props.fileFormat?.toLowerCase().replace(/^\./, '')
+  || props.fileName.split('.').pop()?.toLowerCase()
+  || ''
+))
+const isPdfSource = computed(() => normalizedFileFormat.value === 'pdf')
+const isOfficeSource = computed(() => ['docx', 'xlsx'].includes(normalizedFileFormat.value))

 const filteredItems = computed(() => props.items.filter((item, index) => {
  const matchesSearch = !search.value.trim()
@@ -106,7 +114,7 @@ watch(selectedItem, async (item) => {
    currentPage.value = Math.floor(visibleIndex / PREVIEW_PAGE_SIZE) + 1
  }

-  if (isPdfSource.value || item.sourceStart == null) return
+  if (isPdfSource.value || isOfficeSource.value || item.sourceStart == null) return
  await nextTick()
  const target = sourceViewerRef.value?.querySelector<HTMLElement>(`[data-source-start="${item.sourceStart}"]`)
    ?? sourceViewerRef.value?.querySelector<HTMLElement>('.source-line.is-highlighted')
@@ -176,6 +184,14 @@ function lineRange(item: PreviewItem) {
          :file-name="fileName"
          :selected-item="selectedItem ?? null"
        />
+        <OfficeSourceViewer
+          v-else-if="isOfficeSource"
+          :task-id="taskId"
+          :source-file-id="sourceFileId"
+          :file-name="fileName"
+          :file-format="normalizedFileFormat"
+          :selected-item="selectedItem ?? null"
+        />
        <div v-else ref="sourceViewerRef" class="source-viewer" tabindex="0" aria-label="源文件内容">
          <div
            v-for="line in lines"