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/tests/test_data_process_algorithms.py

@@ -9,6 +9,8 @@ from decimal import Decimal
 
 import pytest
 from docx import Document
+from docx.oxml import parse_xml
+from docx.oxml.ns import nsdecls, qn
 from openpyxl import Workbook
 from pptx import Presentation
 from pptx.util import Inches
@@ -38,6 +40,7 @@ from app.modules.data_process.algorithms import (
     stable_split_assignments,
     structured_json_dumps,
 )
+from app.modules.data_process.office_preview import build_docx_preview
 
 
 def _pdf_page_texts(*texts: str) -> tuple[PdfPageText, ...]:
@@ -318,6 +321,74 @@ def test_parse_pdf_docx_xlsx_and_pptx() -> None:
     assert parsed_pptx.records == ()
 
 
+def _docx_with_sdt_bytes() -> bytes:
+    """构造带 SDT 目录内容控件的 docx，段落顺序为正文、SDT、正文。"""
+
+    document = Document()
+    document.add_paragraph("正文开头。")
+    sdt = parse_xml(
+        "<w:sdt %s><w:sdtPr><w:id w:val='1'/></w:sdtPr>"
+        "<w:sdtContent><w:p><w:r><w:t>目录条目 第一章 概述</w:t></w:r></w:p>"
+        "</w:sdtContent></w:sdt>" % nsdecls("w")
+    )
+    body = document.element.body
+    sect_pr = body.find(qn("w:sectPr"))
+    if sect_pr is not None:
+        sect_pr.addprevious(sdt)
+    else:
+        body.append(sdt)
+    document.add_paragraph("正文结尾。")
+    output = io.BytesIO()
+    document.save(output)
+    return output.getvalue()
+
+
+def test_docx_extraction_and_preview_include_sdt_content() -> None:
+    raw = _docx_with_sdt_bytes()
+
+    parsed = parse_text_content(raw, filename="toc.docx")
+    assert "目录条目 第一章 概述" in parsed.text
+    assert (
+        parsed.text.index("正文开头。")
+        < parsed.text.index("目录条目 第一章 概述")
+        < parsed.text.index("正文结尾。")
+    )
+
+    preview = build_docx_preview(raw)
+    paragraph_texts = [
+        block["text"] for block in preview["blocks"] if block["type"] == "paragraph"
+    ]
+    assert "目录条目 第一章 概述" in paragraph_texts
+    # 预览偏移必须与正文抽取规则一致，否则前端定位会错位。
+    sdt_block = next(
+        block
+        for block in preview["blocks"]
+        if block.get("text") == "目录条目 第一章 概述"
+    )
+    assert parsed.text[sdt_block["source_start"] : sdt_block["source_end"]] == (
+        "目录条目 第一章 概述"
+    )
+
+
+def test_docx_preview_detects_outline_level_headings() -> None:
+    """未套标题样式但设了大纲级别的段落（Word 目录按此收录）也按标题渲染。"""
+
+    document = Document()
+    document.add_heading("一级标题", level=1)
+    plain = document.add_paragraph("4.2.1 数据管理")
+    p_pr = plain._p.get_or_add_pPr()
+    p_pr.append(parse_xml("<w:outlineLvl %s w:val='2'/>" % nsdecls("w")))
+    document.add_paragraph("普通正文段落。")
+    output = io.BytesIO()
+    document.save(output)
+
+    preview = build_docx_preview(output.getvalue())
+    blocks = {b["text"]: b for b in preview["blocks"] if b["type"] == "paragraph"}
+    assert blocks["一级标题"]["heading_level"] == 1
+    assert blocks["4.2.1 数据管理"]["heading_level"] == 3
+    assert blocks["普通正文段落。"]["heading_level"] is None
+
+
 def test_xlsx_record_locators_distinguish_sheets_rows_and_duplicate_records() -> None:
     workbook = Workbook()
     first = workbook.active

backend/tests/test_document_chunking.py

@@ -9,6 +9,7 @@ from app.modules.data_process.document_chunking import (
     DocumentChunk,
     _compact_with_offsets,
     _document_converter,
+    _nodes_to_chunks,
     _project_layout_span,
     chunk_fixed_text,
     chunk_semantic_text,
@@ -103,6 +104,86 @@ def test_layout_projection_ignores_layout_whitespace_but_keeps_source_lines() ->
     assert cursor > 0
 
 
+def test_layout_projection_tolerates_list_numbers_inserted_by_serializer() -> None:
+    # Word 自动编号存放在 numbering.xml，python-docx 抽取的正文没有编号，
+    # 而 Docling 序列化切片时会补上 "1. " 前缀，投影不能因此失败。
+    source = "接入方式说明\n结构化数据接入需要先配置连接地址。\n非结构化接入需要上传文档。"
+    compact_source, offsets = _compact_with_offsets(source)
+    start, end, cursor = _project_layout_span(
+        source,
+        "1. 结构化数据接入需要先配置连接地址。\n2. 非结构化接入需要上传文档。",
+        compact_source=compact_source,
+        source_offsets=offsets,
+        compact_start=0,
+    )
+
+    assert start is not None and end is not None
+    assert source[start:end] == "结构化数据接入需要先配置连接地址。\n非结构化接入需要上传文档。"
+    assert cursor > 0
+
+
+def test_layout_projection_never_moves_cursor_backwards() -> None:
+    source = "重复段落内容。\n中间正文。\n重复段落内容。"
+    compact_source, offsets = _compact_with_offsets(source)
+    # 重复内容回退匹配命中已消费的更早位置时，游标必须保持不退。
+    _, _, cursor = _project_layout_span(
+        source,
+        "重复段落内容。",
+        compact_source=compact_source,
+        source_offsets=offsets,
+        compact_start=compact_source.index("中间正文"),
+    )
+    assert cursor >= compact_source.index("中间正文")
+
+
+def test_layout_projection_falls_back_to_line_anchors_for_inserted_content() -> None:
+    # 表格跨切片时 Docling 会在续片中重复表头，正文不再是连续子串；
+    # 按行锚点匹配仍应定位到表头所在行到末行数据之间的连续区间。
+    source = "表头甲\t表头乙\n第一行数据\t说明一\n第二行数据\t说明二"
+    compact_source, offsets = _compact_with_offsets(source)
+    start, end, _ = _project_layout_span(
+        source,
+        "表头甲 表头乙\n第二行数据 说明二",
+        compact_source=compact_source,
+        source_offsets=offsets,
+        compact_start=0,
+    )
+
+    assert start is not None and end is not None
+    assert source[start:end] == (
+        "表头甲\t表头乙\n第一行数据\t说明一\n第二行数据\t说明二"
+    )
+
+
+def test_layout_projection_refuses_low_coverage_anchor_match() -> None:
+    source = "完全无关的正文内容甲。\n完全无关的正文内容乙。"
+    compact_source, offsets = _compact_with_offsets(source)
+    start, end, cursor = _project_layout_span(
+        source,
+        "找不到的数据行内容\n另一条找不到的数据行内容",
+        compact_source=compact_source,
+        source_offsets=offsets,
+        compact_start=0,
+    )
+
+    assert start is None
+    assert end is None
+    assert cursor == 0
+
+
+def test_text_splitter_keeps_chunks_that_cannot_be_located() -> None:
+    class FakeNode:
+        def get_content(self) -> str:
+            return "这段文本在源文本中不存在。"
+
+    chunks = _nodes_to_chunks([FakeNode()], "完全不同的源文本。")
+
+    assert len(chunks) == 1
+    assert chunks[0].original_content == "这段文本在源文本中不存在。"
+    assert chunks[0].source_start is None
+    assert chunks[0].source_start_line is None
+
+
 def test_short_layout_chunk_merges_with_neighbor_and_keeps_page_provenance() -> None:
     source = "短标题\n这是一段足够长的正文内容，用于测试相邻切片合并。"
     chunks = [