feat(data_process): 显式关闭 docling OCR 并拒绝无文本层 PDF

- docling 转换器通过 PdfPipelineOptions 显式设置 do_ocr=False，
  混合 PDF 的图片页不再产出 OCR 文字；不提供重新开启 OCR 的参数。
- 无文本层 PDF 的错误文案改为"扫描版或图片型 PDF 不支持"，
  上传阶段整批拒绝，保留混合 PDF 的可处理判定。
- 新增 test_layout_converter_disables_ocr 守护开关状态，
  同步设计文档与 disable-ocr 实施计划/设计说明。

backend/tests/test_data_process_algorithms.py

@@ -654,7 +654,10 @@ def test_office_zip_bomb_and_invalid_pdf_are_rejected_before_parsing() -> None:
     blank_writer = PdfWriter()
     blank_writer.add_blank_page(width=612, height=792)
     blank_writer.write(blank_pdf)
-    with pytest.raises(ValueError, match="scanned PDF requires OCR"):
+    with pytest.raises(
+        ValueError,
+        match="scanned or image-only PDF files are not supported",
+    ):
         parse_text_content(blank_pdf.getvalue(), filename="scanned.pdf")
 
     aes_pdf_without_open_password = parse_text_content(

backend/tests/test_document_chunking.py

@@ -1,10 +1,14 @@
 from __future__ import annotations
 
+import sys
+from types import ModuleType, SimpleNamespace
+
 from llama_index.core.embeddings import MockEmbedding
 
 from app.modules.data_process.document_chunking import (
     DocumentChunk,
     _compact_with_offsets,
+    _document_converter,
     _project_layout_span,
     chunk_fixed_text,
     chunk_semantic_text,
@@ -42,6 +46,48 @@ def test_semantic_splitter_uses_llamaindex_and_reapplies_maximum_size() -> None:
     assert "".join(chunk.original_content for chunk in chunks) == text
 
 
+def test_layout_converter_disables_ocr(monkeypatch) -> None:
+    class FakePipelineOptions:
+        def __init__(self) -> None:
+            self.do_ocr = True
+
+    class FakePdfFormatOption:
+        def __init__(self, *, pipeline_options) -> None:
+            self.pipeline_options = pipeline_options
+
+    class FakeDocumentConverter:
+        def __init__(self, *, format_options) -> None:
+            self.format_options = format_options
+
+    docling_module = ModuleType("docling")
+    docling_module.__path__ = []
+    document_converter_module = ModuleType("docling.document_converter")
+    document_converter_module.DocumentConverter = FakeDocumentConverter
+    document_converter_module.PdfFormatOption = FakePdfFormatOption
+    datamodel_module = ModuleType("docling.datamodel")
+    datamodel_module.__path__ = []
+    base_models_module = ModuleType("docling.datamodel.base_models")
+    base_models_module.InputFormat = SimpleNamespace(PDF="pdf")
+    pipeline_options_module = ModuleType("docling.datamodel.pipeline_options")
+    pipeline_options_module.PdfPipelineOptions = FakePipelineOptions
+    for name, module in {
+        "docling": docling_module,
+        "docling.document_converter": document_converter_module,
+        "docling.datamodel": datamodel_module,
+        "docling.datamodel.base_models": base_models_module,
+        "docling.datamodel.pipeline_options": pipeline_options_module,
+    }.items():
+        monkeypatch.setitem(sys.modules, name, module)
+
+    _document_converter.cache_clear()
+    try:
+        converter = _document_converter()
+        options = converter.format_options["pdf"].pipeline_options
+        assert options.do_ocr is False
+    finally:
+        _document_converter.cache_clear()
+
+
 def test_layout_projection_ignores_layout_whitespace_but_keeps_source_lines() -> None:
     source = "标题\n第一条 这是正文。\n第二条 后续正文。"
     compact_source, offsets = _compact_with_offsets(source)