refactor(rag): 梳理文档入库与检索服务结构

tests/test_documents.py

@@ -3,7 +3,7 @@ from django.urls import reverse
 
 from apps.documents.forms import DocumentUploadForm
 from apps.documents.models import UploadedDocument
-from apps.documents.services import extract_text
+from apps.documents.services import extract_text, index_document
 
 
 def test_upload_txt_document_creates_uploaded_record(client, db):
@@ -128,3 +128,20 @@ def test_index_failure_message_is_visible_on_document_list(client, db, monkeypat
     assert response.status_code == 200
     assert "文档入库失败，请检查错误原因后重试" in content
     assert "模拟入库失败" in content
+
+
+def test_index_document_marks_failed_when_extracted_text_is_empty(db, monkeypatch):
+    document = UploadedDocument.objects.create(
+        scenario_id="knowledge_qa",
+        original_name="empty.md",
+        file_type="md",
+        size=0,
+        status="uploaded",
+    )
+
+    monkeypatch.setattr("apps.documents.services.extract_text", lambda target: "   ")
+
+    updated_document = index_document(document)
+
+    assert updated_document.status == UploadedDocument.STATUS_FAILED
+    assert "文档内容为空" in updated_document.error_message