fix(data_process): 修复 Word 切分行号断档与预览标题缺失

- 正文抽取下钻 SDT 内容控件，目录等内容不再整段丢失
- 切片投影匹配剥离序列化插入的列表自动编号，新增行锚点兜底与游标防回退
- fixed/semantic 切分路径定位失败时保留切片，不再静默丢弃
- Word 预览按段落大纲级别识别标题，未套标题样式的小节正常渲染
- 本地嵌入模型抽为共享单例，供语义分块与质量评分共用

backend/app/modules/data_process/office_preview.py

@@ -11,6 +11,7 @@ import re
 from typing import Any
 
 from docx import Document
+from docx.oxml.ns import qn
 from docx.oxml.table import CT_Tbl
 from docx.oxml.text.paragraph import CT_P
 from docx.table import Table
@@ -27,6 +28,7 @@ from app.modules.data_process.algorithms import (
     _xlsx_sheet_merge_ranges,
     normalize_text,
 )
+from app.modules.data_process.algorithms.parsers.office import iter_document_blocks
 
 MAX_DOCX_PREVIEW_BLOCKS = 2_000
 MAX_XLSX_PREVIEW_ROWS = 200
@@ -49,12 +51,21 @@ def _docx_alignment(paragraph: Paragraph) -> str:
 
 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 "")
+    style_name = str(style.name or "") if style is not None else ""
+    style_id = str(style.style_id or "") if style is not None else ""
     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
+    if match:
+        return int(match.group(1))
+    # Word 的目录和导航窗格依据大纲级别识别标题；未套标题样式但带
+    # outlineLvl 的段落（如手工排版的编号小节）同样是标题。
+    outline = paragraph._p.find(f"{qn('w:pPr')}/{qn('w:outlineLvl')}")
+    if outline is not None:
+        value = outline.get(qn("w:val"))
+        if value is not None and value.isdigit():
+            level = int(value)
+            if 0 <= level <= 5:
+                return level + 1
+    return None
 
 
 def build_docx_preview(raw: bytes) -> dict[str, Any]:
@@ -84,7 +95,7 @@ def build_docx_preview(raw: bytes) -> dict[str, Any]:
         has_source_content = True
         return text, start, source_cursor
 
-    for child in document.element.body.iterchildren():
+    for child in iter_document_blocks(document.element.body):
         if rendered_blocks >= MAX_DOCX_PREVIEW_BLOCKS:
             truncated = True
             break