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

backend/app/api/v1/endpoints/data_process.py

@@ -53,6 +53,11 @@ from app.modules.data_process.document_chunking import (
     merge_short_chunks,
 )
 from app.modules.data_process.generation import generate_model_records
+from app.modules.data_process.office_preview import (
+    MAX_XLSX_PREVIEW_ROWS,
+    build_docx_preview,
+    build_xlsx_preview,
+)
 from app.modules.data_process.storage import (
     LocalDataProcessStorage,
     StagedSourceObject,
@@ -111,6 +116,12 @@ LEGACY_OFFICE_CONVERSIONS = {
     ".xls": ".xlsx",
     ".ppt": ".pptx",
 }
+RAW_INLINE_PREVIEW_MEDIA_TYPES = {
+    "pdf": "application/pdf",
+    "docx": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
+    "xlsx": "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
+    "pptx": "application/vnd.openxmlformats-officedocument.presentationml.presentation",
+}
 
 
 def ok(data: Any = None, message: str = "ok") -> dict[str, Any]:
@@ -897,8 +908,13 @@ def source_file_raw(
 ) -> StreamingResponse:
     with api_errors():
         source = store.get_source_file(task_id, file_id, include_content=False)
-        if str(source.get("file_format") or "").lower() != "pdf":
-            raise fail(415, "raw inline preview is only available for PDF source files")
+        file_format = str(source.get("file_format") or "").lower()
+        media_type = RAW_INLINE_PREVIEW_MEDIA_TYPES.get(file_format)
+        if media_type is None:
+            raise fail(
+                415,
+                "raw inline preview is only available for PDF and modern Office source files",
+            )
         storage_object_id = str(source.get("storage_object_id") or "")
         actual_size = storage.file_size(
             storage_object_id,
@@ -906,14 +922,15 @@ def source_file_raw(
             expected_source_file_id=file_id,
         )
         if actual_size is None:
-            raise fail(410, "the original PDF is unavailable for this legacy source file")
+            raise fail(410, "the original file is unavailable for this legacy source file")
         expected_size = int(source.get("size_bytes") or 0)
         if actual_size != expected_size:
             raise ValueError("source object size does not match metadata")
         selected_range = _source_byte_range(range_header, actual_size)
         start, end = selected_range or (0, actual_size - 1)
         length = end - start + 1
-        name = _safe_file_name(str(source.get("name") or "source.pdf"), "source.pdf")
+        default_name = f"source.{file_format}"
+        name = _safe_file_name(str(source.get("name") or default_name), default_name)
         headers = {
             "Accept-Ranges": "bytes",
             "Cache-Control": "private, no-store",
@@ -938,11 +955,61 @@ def source_file_raw(
         return StreamingResponse(
             body,
             status_code=206 if selected_range is not None else 200,
-            media_type="application/pdf",
+            media_type=media_type,
             headers=headers,
         )
 
 
+@router.get("/{task_id}/source-files/{file_id}/office-preview")
+def source_file_office_preview(
+    task_id: str,
+    file_id: str,
+    sheet_index: int = Query(default=0, ge=0),
+    offset: int = Query(default=0, ge=0),
+    limit: int = Query(default=100, ge=1, le=MAX_XLSX_PREVIEW_ROWS),
+    store: DataProcessStore = Depends(get_data_process_store),
+    storage: LocalDataProcessStorage = Depends(get_data_process_storage),
+) -> dict[str, Any]:
+    """返回 Word 版式块或 Excel 工作表网格，不把二进制内容下发给组件解析。"""
+
+    with api_errors():
+        source = store.get_source_file(task_id, file_id, include_content=False)
+        file_format = str(source.get("file_format") or "").lower()
+        if file_format not in {"docx", "xlsx"}:
+            raise fail(415, "Office preview is only available for DOCX and XLSX source files")
+        storage_object_id = str(source.get("storage_object_id") or "")
+        actual_size = storage.file_size(
+            storage_object_id,
+            expected_task_id=task_id,
+            expected_source_file_id=file_id,
+        )
+        if actual_size is None:
+            raise fail(410, "the original Office file is unavailable for this legacy source file")
+        expected_size = int(source.get("size_bytes") or 0)
+        if actual_size != expected_size:
+            raise ValueError("source object size does not match metadata")
+        raw = b"".join(
+            storage.iter_bytes(
+                storage_object_id,
+                expected_task_id=task_id,
+                expected_source_file_id=file_id,
+                expected_size=actual_size,
+            )
+        )
+        preview = (
+            build_docx_preview(raw)
+            if file_format == "docx"
+            else build_xlsx_preview(
+                raw,
+                sheet_index=sheet_index,
+                offset=offset,
+                limit=limit,
+            )
+        )
+        preview["file_name"] = str(source.get("name") or f"source.{file_format}")
+        return ok(preview)
+
+
 @router.get("/{task_id}/source-files/{file_id}/pdf-pages")
 def source_file_pdf_pages(
     task_id: str,

backend/app/modules/data_process/office_preview.py

@@ -0,0 +1,308 @@
+"""Word 与 Excel 原文件的安全、受限预览模型。
+
+预览只返回浏览器绘制所需的结构化数据，不返回或执行 Office 包中的活动内容。
+DOCX 的字符偏移与上传时的正文抽取规则保持一致，供前端定位当前切片。
+"""
+
+from __future__ import annotations
+
+import io
+import re
+from typing import Any
+
+from docx import Document
+from docx.oxml.table import CT_Tbl
+from docx.oxml.text.paragraph import CT_P
+from docx.table import Table
+from docx.text.paragraph import Paragraph
+from openpyxl import load_workbook
+
+from app.modules.data_process.algorithms import (
+    _MAX_WORKBOOK_COLUMNS,
+    _MAX_WORKBOOK_HEADER_SCAN_ROWS,
+    _infer_xlsx_header_region,
+    _normalize_spreadsheet_value,
+    _rewrite_xlsx_workbook_relationships,
+    _validate_office_archive,
+    _xlsx_sheet_merge_ranges,
+    normalize_text,
+)
+
+MAX_DOCX_PREVIEW_BLOCKS = 2_000
+MAX_XLSX_PREVIEW_ROWS = 200
+
+
+def _docx_alignment(paragraph: Paragraph) -> str:
+    value = paragraph.alignment
+    return {
+        0: "left",
+        1: "center",
+        2: "right",
+        3: "justify",
+        4: "distribute",
+        5: "justify",
+        7: "justify",
+        8: "distribute",
+        9: "distribute",
+    }.get(int(value) if value is not None else -1, "left")
+
+
+def _docx_heading_level(paragraph: Paragraph) -> int | None:
+    style = paragraph.style
+    if style is None:
+        return None
+    style_name = str(style.name or "")
+    style_id = str(style.style_id or "")
+    match = re.search(r"(?:heading|标题)\s*([1-6])", f"{style_name} {style_id}", re.IGNORECASE)
+    return int(match.group(1)) if match else None
+
+
+def build_docx_preview(raw: bytes) -> dict[str, Any]:
+    """把 DOCX 转为保留标题、段落和表格顺序的浏览器预览模型。"""
+
+    _validate_office_archive(raw, "docx")
+    try:
+        document = Document(io.BytesIO(raw))
+    except Exception as exc:
+        raise ValueError(f"invalid DOCX file: {exc}") from exc
+
+    blocks: list[dict[str, Any]] = []
+    source_cursor = 0
+    has_source_content = False
+    rendered_blocks = 0
+    truncated = False
+
+    def source_range(value: str) -> tuple[str, int, int] | None:
+        nonlocal source_cursor, has_source_content
+        text = normalize_text(value)
+        if not text:
+            return None
+        if has_source_content:
+            source_cursor += 2
+        start = source_cursor
+        source_cursor += len(text)
+        has_source_content = True
+        return text, start, source_cursor
+
+    for child in document.element.body.iterchildren():
+        if rendered_blocks >= MAX_DOCX_PREVIEW_BLOCKS:
+            truncated = True
+            break
+
+        if isinstance(child, CT_P):
+            paragraph = Paragraph(child, document)
+            located = source_range(paragraph.text)
+            if located is None:
+                continue
+            text, start, end = located
+            style_name = str(paragraph.style.name or "") if paragraph.style else ""
+            blocks.append(
+                {
+                    "type": "paragraph",
+                    "text": text,
+                    "style": style_name,
+                    "heading_level": _docx_heading_level(paragraph),
+                    "alignment": _docx_alignment(paragraph),
+                    "is_list": "list" in style_name.casefold() or "列表" in style_name,
+                    "source_start": start,
+                    "source_end": end,
+                }
+            )
+            rendered_blocks += 1
+            continue
+
+        if not isinstance(child, CT_Tbl):
+            continue
+        table = Table(child, document)
+        preview_rows: list[dict[str, Any]] = []
+        for row in table.rows:
+            if rendered_blocks >= MAX_DOCX_PREVIEW_BLOCKS:
+                truncated = True
+                break
+            cell_values = [normalize_text(cell.text) for cell in row.cells]
+            located = source_range("\t".join(cell_values))
+            if located is None:
+                continue
+            _, start, end = located
+            preview_rows.append(
+                {
+                    "cells": cell_values,
+                    "source_start": start,
+                    "source_end": end,
+                }
+            )
+            rendered_blocks += 1
+        if preview_rows:
+            blocks.append({"type": "table", "rows": preview_rows})
+        if truncated:
+            break
+
+    return {
+        "format": "docx",
+        "blocks": blocks,
+        "truncated": truncated,
+    }
+
+
+def build_xlsx_preview(
+    raw: bytes,
+    *,
+    sheet_index: int = 0,
+    offset: int = 0,
+    limit: int = 100,
+) -> dict[str, Any]:
+    """按工作表分页返回 XLSX 的表头和记录网格。"""
+
+    if sheet_index < 0 or offset < 0:
+        raise ValueError("sheet_index and offset must be non-negative")
+    if limit < 1 or limit > MAX_XLSX_PREVIEW_ROWS:
+        raise ValueError(
+            f"XLSX preview limit must be in [1, {MAX_XLSX_PREVIEW_ROWS}]"
+        )
+
+    _validate_office_archive(raw, "xlsx")
+    merged_by_sheet, normalized_targets = _xlsx_sheet_merge_ranges(raw)
+    workbook_raw = (
+        _rewrite_xlsx_workbook_relationships(raw, normalized_targets)
+        if normalized_targets
+        else raw
+    )
+    try:
+        workbook = load_workbook(
+            io.BytesIO(workbook_raw),
+            read_only=True,
+            data_only=True,
+            keep_links=False,
+        )
+    except Exception as exc:
+        raise ValueError(f"invalid XLSX file: {exc}") from exc
+
+    try:
+        sheets = [
+            {
+                "index": index,
+                "name": worksheet.title,
+                "state": worksheet.sheet_state,
+            }
+            for index, worksheet in enumerate(workbook.worksheets)
+        ]
+        if not sheets:
+            raise ValueError("XLSX workbook contains no worksheets")
+        if sheet_index >= len(sheets):
+            raise ValueError("XLSX worksheet index is out of range")
+
+        worksheet = workbook.worksheets[sheet_index]
+        reset_dimensions = getattr(worksheet, "reset_dimensions", None)
+        if callable(reset_dimensions):
+            reset_dimensions()
+        row_iterator = enumerate(worksheet.iter_rows(values_only=True), start=1)
+        buffered_rows: dict[int, tuple[Any, ...]] = {}
+
+        def normalized_values(row: tuple[Any, ...]) -> list[Any]:
+            values = list(row)
+            while values and values[-1] in {None, ""}:
+                values.pop()
+            if len(values) > _MAX_WORKBOOK_COLUMNS:
+                raise ValueError(
+                    f"XLSX worksheet {worksheet.title!r} exceeds "
+                    f"{_MAX_WORKBOOK_COLUMNS} columns"
+                )
+            return values
+
+        for row_number, row in row_iterator:
+            values = normalized_values(row)
+            if not values or all(value in {None, ""} for value in values):
+                continue
+            buffered_rows[row_number] = tuple(values)
+            if len(buffered_rows) >= _MAX_WORKBOOK_HEADER_SCAN_ROWS:
+                break
+
+        if not buffered_rows:
+            return {
+                "format": "xlsx",
+                "sheets": sheets,
+                "active_sheet": {
+                    "index": sheet_index,
+                    "name": worksheet.title,
+                    "columns": [],
+                    "rows": [],
+                    "offset": offset,
+                    "limit": limit,
+                    "has_more": False,
+                },
+            }
+
+        _, header_end_row, headers = _infer_xlsx_header_region(
+            worksheet.title,
+            buffered_rows,
+            merged_by_sheet.get(worksheet.title, ()),
+        )
+        preview_rows: list[dict[str, Any]] = []
+        record_index = 0
+        has_more = False
+
+        def append_row(row_number: int, values: tuple[Any, ...] | list[Any]) -> bool:
+            nonlocal record_index, has_more
+            row_values = list(values)
+            if len(row_values) > len(headers):
+                raise ValueError(
+                    f"XLSX worksheet {worksheet.title!r} has a row wider than its header"
+                )
+            row_values.extend([None] * (len(headers) - len(row_values)))
+            record = {
+                header: _normalize_spreadsheet_value(value)
+                for header, value in zip(headers, row_values, strict=True)
+            }
+            if not any(value not in {"", None} for value in record.values()):
+                return False
+            current_index = record_index
+            record_index += 1
+            if current_index < offset:
+                return False
+            if len(preview_rows) >= limit:
+                has_more = True
+                return True
+            preview_rows.append(
+                {
+                    "row_number": row_number,
+                    "record_index": current_index,
+                    "values": [record[header] for header in headers],
+                    "record": record,
+                }
+            )
+            return False
+
+        for row_number, values in buffered_rows.items():
+            if row_number > header_end_row and append_row(row_number, values):
+                break
+        else:
+            for row_number, row in row_iterator:
+                values = normalized_values(row)
+                if not values or all(value in {None, ""} for value in values):
+                    continue
+                if append_row(row_number, values):
+                    break
+
+        return {
+            "format": "xlsx",
+            "sheets": sheets,
+            "active_sheet": {
+                "index": sheet_index,
+                "name": worksheet.title,
+                "columns": headers,
+                "rows": preview_rows,
+                "offset": offset,
+                "limit": limit,
+                "has_more": has_more,
+            },
+        }
+    finally:
+        workbook.close()
+
+
+__all__ = [
+    "MAX_DOCX_PREVIEW_BLOCKS",
+    "MAX_XLSX_PREVIEW_ROWS",
+    "build_docx_preview",
+    "build_xlsx_preview",
+]

backend/tests/test_data_process_api.py

@@ -6,6 +6,7 @@ from pathlib import Path
 from typing import Any
 
 import pytest
+from docx import Document as WordDocument
 from fastapi import FastAPI
 from fastapi.testclient import TestClient
 from openpyxl import Workbook
@@ -1546,11 +1547,112 @@ def test_xlsx_upload_is_accepted_as_structured_records(tmp_path: Path) -> None:
     )
     assert content.status_code == 200
     assert '"answer":"答案二"' in content.json()["data"]["content"]
+    office_preview_url = (
+        f"/modelTF/data-process/{task_id}/source-files/{source['id']}/office-preview"
+    )
+    first_page = client.get(office_preview_url, params={"offset": 0, "limit": 1})
+    assert first_page.status_code == 200
+    preview_data = first_page.json()["data"]
+    assert preview_data["format"] == "xlsx"
+    assert preview_data["sheets"] == [{"index": 0, "name": "Sheet", "state": "visible"}]
+    assert preview_data["active_sheet"]["columns"] == ["question", "answer"]
+    assert preview_data["active_sheet"]["rows"][0]["record"] == {
+        "question": "问题一",
+        "answer": "答案一",
+    }
+    assert preview_data["active_sheet"]["has_more"] is True
+
+    second_page = client.get(office_preview_url, params={"offset": 1, "limit": 1})
+    assert second_page.status_code == 200
+    assert second_page.json()["data"]["active_sheet"]["rows"][0]["record"] == {
+        "question": "问题二",
+        "answer": "答案二",
+    }
+    assert second_page.json()["data"]["active_sheet"]["has_more"] is False
+
+    raw_preview = client.get(
+        f"/modelTF/data-process/{task_id}/source-files/{source['id']}/raw"
+    )
+    assert raw_preview.status_code == 200
+    assert raw_preview.content == original_bytes
+    assert raw_preview.headers["content-type"].startswith(
+        "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
+    )
     preview = client.post(f"/modelTF/data-process/{task_id}/preview/build")
     assert preview.status_code == 200
     assert preview.json()["data"]["total"] == 2
 
 
+def test_docx_preview_preserves_document_block_order_and_source_offsets(
+    tmp_path: Path,
+) -> None:
+    client, store, _ = make_client(tmp_path)
+    task_id = client.post(
+        "/modelTF/data-process",
+        json={"name": "Word 原件预览", "process_type": "unstructured", "config": {}},
+    ).json()["data"]["id"]
+    document = WordDocument()
+    document.add_heading("费用管理办法", level=1)
+    document.add_paragraph("第一条 本办法用于规范费用报销。")
+    table = document.add_table(rows=2, cols=2)
+    table.cell(0, 0).text = "费用类型"
+    table.cell(0, 1).text = "审批人"
+    table.cell(1, 0).text = "差旅费"
+    table.cell(1, 1).text = "部门负责人"
+    output = BytesIO()
+    document.save(output)
+    original_bytes = output.getvalue()
+
+    uploaded = client.post(
+        f"/modelTF/data-process/{task_id}/source-files",
+        files={
+            "files": (
+                "费用 管理.docx",
+                original_bytes,
+                "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
+            )
+        },
+    ).json()["data"]["files"][0]
+    response = client.get(
+        f"/modelTF/data-process/{task_id}/source-files/{uploaded['id']}/office-preview"
+    )
+
+    assert response.status_code == 200
+    data = response.json()["data"]
+    assert data["format"] == "docx"
+    assert data["file_name"] == "费用 管理.docx"
+    assert data["truncated"] is False
+    assert [block["type"] for block in data["blocks"]] == [
+        "paragraph",
+        "paragraph",
+        "table",
+    ]
+    assert data["blocks"][0]["heading_level"] == 1
+    assert data["blocks"][0]["text"] == "费用管理办法"
+    assert data["blocks"][2]["rows"][1]["cells"] == ["差旅费", "部门负责人"]
+
+    source_text = store.get_source_file(task_id, uploaded["id"])["content"]
+    first_paragraph = data["blocks"][0]
+    assert (
+        source_text[first_paragraph["source_start"] : first_paragraph["source_end"]]
+        == first_paragraph["text"]
+    )
+    table_row = data["blocks"][2]["rows"][1]
+    assert (
+        source_text[table_row["source_start"] : table_row["source_end"]]
+        == "\t".join(table_row["cells"])
+    )
+
+    raw_preview = client.get(
+        f"/modelTF/data-process/{task_id}/source-files/{uploaded['id']}/raw"
+    )
+    assert raw_preview.status_code == 200
+    assert raw_preview.content == original_bytes
+    assert raw_preview.headers["content-type"].startswith(
+        "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
+    )
+
+
 def test_pdf_raw_preview_streams_original_file_and_supports_ranges(tmp_path: Path) -> None:
     client, store, _ = make_client(tmp_path)
     task_id = client.post(

frontend/scripts/regression-data-process-wizard.mjs

@@ -109,16 +109,19 @@ for (const component of expectedComponents) {
 const typesPath = path.join(createDir, 'types.ts')
 const modelPath = path.join(createDir, 'previewModel.ts')
 const pdfViewerPath = path.join(createDir, 'PdfSourceViewer.vue')
+const officeViewerPath = path.join(createDir, 'OfficeSourceViewer.vue')
 const resultEditorPath = path.join(createDir, 'ResultEditorStep.vue')
 assert.ok(existsSync(typesPath), '缺少向导类型定义')
 assert.ok(existsSync(modelPath), '缺少来源映射模型')
 assert.ok(existsSync(pdfViewerPath), '缺少 PDF 原文件预览组件')
+assert.ok(existsSync(officeViewerPath), '缺少 Word/XLSX 原文件预览组件')
 
-const [typesSource, modelSource, previewSource, pdfViewerSource, resultEditorSource] = await Promise.all([
+const [typesSource, modelSource, previewSource, pdfViewerSource, officeViewerSource, resultEditorSource] = await Promise.all([
   readFile(typesPath, 'utf8'),
   readFile(modelPath, 'utf8'),
   readFile(path.join(createDir, 'PreviewCompareStep.vue'), 'utf8'),
   readFile(pdfViewerPath, 'utf8'),
+  readFile(officeViewerPath, 'utf8'),
   readFile(resultEditorPath, 'utf8'),
 ])
 
@@ -179,6 +182,8 @@ assert.match(previewSource, /\.preview-editor\s*\{[\s\S]*?flex:\s*1 1 auto[\s\S]
 assert.match(previewSource, /@media \(max-width: 900px\)/, '第四步缺少窄屏上下布局')
 assert.match(previewSource, /<PdfSourceViewer[\s\S]*v-if="isPdfSource"/, 'PDF 文件没有切换到原文件查看组件')
 assert.match(previewSource, /:selected-item="selectedItem \?\? null"/, 'PDF 查看组件没有接收当前选中切片')
+assert.match(previewSource, /<OfficeSourceViewer[\s\S]*v-else-if="isOfficeSource"/, 'Word/XLSX 没有切换到专用原文件查看组件')
+assert.match(previewSource, /const isOfficeSource = computed[\s\S]*?'docx', 'xlsx'/, 'Word/XLSX 文件类型分流不完整')
 assert.match(previewSource, /:data-preview-id="item\.id"/, '切片行缺少稳定的交互定位标识')
 assert.match(previewSource, /<div v-else ref="sourceViewerRef" class="source-viewer"/, '非 PDF 文件没有保留文本预览')
 assert.match(pdfViewerSource, /getDataProcessSourceRawUrl/, 'PDF 查看组件没有使用受控原文件地址')
@@ -194,6 +199,21 @@ assert.match(pdfViewerSource, /:aria-label="`PDF 预览：\$\{fileName\}`"/, 'PD
 assert.match(apiSource, /getDataProcessSourceRawUrl/, '前端 API 缺少 PDF 原文件预览地址')
 assert.match(apiSource, /getDataProcessPdfPages/, '前端 API 缺少 PDF 页码映射接口')
 assert.match(apiSource, /source-files\/\$\{encodeURIComponent\(fileId\)\}\/pdf-pages/, 'PDF 页码映射接口地址不正确')
+assert.match(apiSource, /getDataProcessOfficePreview/, '前端 API 缺少 Word/XLSX 预览接口')
+assert.match(apiSource, /source-files\/\$\{encodeURIComponent\(fileId\)\}\/office-preview/, 'Word/XLSX 预览接口地址不正确')
+for (const marker of [
+  'docx-page',
+  'docx-table',
+  'xlsx-grid',
+  'sheet-selector',
+  'xlsx-pagination',
+  'getDataProcessOfficePreview',
+  'is-highlighted',
+  '打开原文件',
+  '重试',
+]) {
+  assert.ok(officeViewerSource.includes(marker), `Word/XLSX 预览缺少结构或行为：${marker}`)
+}
 
 const taskSetupPath = path.join(createDir, 'TaskSetupStep.vue')
 const structuredOptionsPath = path.join(createDir, 'StructuredOptionsPanel.vue')

frontend/src/api/modules/dataProcess.ts

@@ -3,6 +3,7 @@ import type {
   DataProcessExternalSourcePayload,
   DataProcessExternalTestResult,
   DataProcessPage,
+  DataProcessOfficePreview,
   DataProcessPdfPages,
   DataProcessPreviewBuildPayload,
   DataProcessPreviewBuildResult,
@@ -30,6 +31,11 @@ export type {
   DataProcessExternalSourcePayload,
   DataProcessExternalTestResult,
   DataProcessPage,
+  DataProcessDocxParagraph,
+  DataProcessDocxPreview,
+  DataProcessDocxTable,
+  DataProcessDocxTableRow,
+  DataProcessOfficePreview,
   DataProcessPdfPageRange,
   DataProcessPdfPages,
   DataProcessPreviewBuildPayload,
@@ -57,6 +63,10 @@ export type {
   DataProcessTaskCreatePayload,
   DataProcessTaskUpdatePayload,
   DataProcessType,
+  DataProcessXlsxActiveSheet,
+  DataProcessXlsxPreview,
+  DataProcessXlsxPreviewRow,
+  DataProcessXlsxSheet,
 } from '@/types/dataProcess'
 
 export function getDataProcessTasks(params: {
@@ -137,6 +147,16 @@ export const getDataProcessPdfPages = (
   `/data-process/${encodeURIComponent(taskId)}/source-files/${encodeURIComponent(fileId)}/pdf-pages`,
 )
 
+export const getDataProcessOfficePreview = (
+  taskId: string | number,
+  fileId: string | number,
+  params: { sheet_index?: number; offset?: number; limit?: number } = {},
+) => get<DataProcessOfficePreview>(
+  `/data-process/${encodeURIComponent(taskId)}/source-files/${encodeURIComponent(fileId)}/office-preview`,
+  params,
+  { timeout: 60_000 },
+)
+
 export const testDataProcessExternalSource = (
   taskId: string | number,
   payload: DataProcessExternalSourcePayload,

frontend/src/types/dataProcess.ts

@@ -129,6 +129,67 @@ export interface DataProcessPdfPages {
   pages: DataProcessPdfPageRange[]
 }
 
+export interface DataProcessDocxParagraph {
+  type: 'paragraph'
+  text: string
+  style: string
+  heading_level: number | null
+  alignment: 'left' | 'center' | 'right' | 'justify' | 'distribute'
+  is_list: boolean
+  source_start: number
+  source_end: number
+}
+
+export interface DataProcessDocxTableRow {
+  cells: string[]
+  source_start: number
+  source_end: number
+}
+
+export interface DataProcessDocxTable {
+  type: 'table'
+  rows: DataProcessDocxTableRow[]
+}
+
+export interface DataProcessDocxPreview {
+  format: 'docx'
+  file_name: string
+  blocks: Array<DataProcessDocxParagraph | DataProcessDocxTable>
+  truncated: boolean
+}
+
+export interface DataProcessXlsxSheet {
+  index: number
+  name: string
+  state: string
+}
+
+export interface DataProcessXlsxPreviewRow {
+  row_number: number
+  record_index: number
+  values: unknown[]
+  record: Record<string, unknown>
+}
+
+export interface DataProcessXlsxActiveSheet {
+  index: number
+  name: string
+  columns: string[]
+  rows: DataProcessXlsxPreviewRow[]
+  offset: number
+  limit: number
+  has_more: boolean
+}
+
+export interface DataProcessXlsxPreview {
+  format: 'xlsx'
+  file_name: string
+  sheets: DataProcessXlsxSheet[]
+  active_sheet: DataProcessXlsxActiveSheet
+}
+
+export type DataProcessOfficePreview = DataProcessDocxPreview | DataProcessXlsxPreview
+
 export interface DataProcessExternalSourcePayload {
   type: 'postgresql'
   url: string

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"

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>

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"