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/algorithms/parsers/office.py

@@ -7,12 +7,13 @@ import re
 import unicodedata
 import zipfile
 import xml.etree.ElementTree as ET
-from collections.abc import Mapping, Sequence
+from collections.abc import Iterator, Mapping, Sequence
 from pathlib import PurePosixPath
 from typing import Any
 from urllib.parse import unquote, urlsplit
 
 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
@@ -121,6 +122,21 @@ def _validate_office_archive(raw: bytes, file_format: TextFormat) -> None:
     except zipfile.BadZipFile as exc:
         raise ValueError(f"invalid {file_format.upper()} file: not an Office ZIP package") from exc
 
+def iter_document_blocks(parent: Any) -> Iterator[Any]:
+    """按文档顺序产出正文段落与表格，并下钻 SDT 内容控件。
+
+    Word 的目录、复选框等内容控件包在 ``w:sdt`` 元素里，只遍历 body
+    直接子级会把这些段落整段丢掉。
+    """
+
+    for child in parent.iterchildren():
+        if isinstance(child, (CT_P, CT_Tbl)):
+            yield child
+        elif child.tag == qn("w:sdt"):
+            content = child.find(qn("w:sdtContent"))
+            if content is not None:
+                yield from iter_document_blocks(content)
+
 def _extract_docx_text(raw: bytes) -> str:
     _validate_office_archive(raw, "docx")
     try:
@@ -130,7 +146,7 @@ def _extract_docx_text(raw: bytes) -> str:
 
     parts: list[str] = []
     total = 0
-    for child in document.element.body.iterchildren():
+    for child in iter_document_blocks(document.element.body):
         if isinstance(child, CT_P):
             total = _append_bounded_text(parts, Paragraph(child, document).text, total)
             continue