feat: 补齐DOCX精确页数识别与待复核策略

tests/test_documents.py

@@ -4,6 +4,7 @@ from io import BytesIO
 from pathlib import Path
 import sys
 import types
+import zipfile
 from zipfile import ZipFile
 
 from apps.documents.forms import DocumentUploadForm
@@ -418,7 +419,72 @@ def test_import_submission_batch_records_warnings_for_unsupported_zip_entries(db
     assert batch.file_count == 1
     assert batch.exception_count == 1
     assert "跳过不支持的文件" in warnings[0]
-    assert "CH1/忽略图片.png" in warnings[0]
+
+
+def test_import_submission_batch_uses_exact_docx_page_count_from_metadata(db):
+    archive = BytesIO()
+    with zipfile.ZipFile(archive, "w") as docx_file:
+        docx_file.writestr(
+            "word/document.xml",
+            """<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+            <w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">
+              <w:body>
+                <w:p><w:r><w:t>产品名称：新型冠状病毒 2019-nCoV 核酸检测试剂盒</w:t></w:r></w:p>
+              </w:body>
+            </w:document>""",
+        )
+        docx_file.writestr(
+            "docProps/app.xml",
+            """<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+            <Properties xmlns="http://schemas.openxmlformats.org/officeDocument/2006/extended-properties">
+              <Pages>7</Pages>
+            </Properties>""",
+        )
+    archive.seek(0)
+    file = SimpleUploadedFile(
+        "CH1-目标产品说明书.docx",
+        archive.read(),
+        content_type="application/vnd.openxmlformats-officedocument.wordprocessingml.document",
+    )
+
+    result = import_submission_batch("document_review", [file])
+
+    batch = SubmissionBatch.objects.get(batch_id=result["batch_id"])
+    document = UploadedDocument.objects.get(batch=batch)
+    assert batch.page_count == 7
+    assert document.page_count == 7
+    assert document.page_count_confidence == "exact"
+    assert batch.import_status == "completed"
+
+
+def test_import_submission_batch_marks_review_when_docx_page_count_cannot_be_precisely_detected(db):
+    archive = BytesIO()
+    with zipfile.ZipFile(archive, "w") as docx_file:
+        docx_file.writestr(
+            "word/document.xml",
+            """<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+            <w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">
+              <w:body>
+                <w:p><w:r><w:t>产品名称：新型冠状病毒 2019-nCoV 核酸检测试剂盒</w:t></w:r></w:p>
+              </w:body>
+            </w:document>""",
+        )
+    archive.seek(0)
+    file = SimpleUploadedFile(
+        "CH1-目标产品说明书.docx",
+        archive.read(),
+        content_type="application/vnd.openxmlformats-officedocument.wordprocessingml.document",
+    )
+
+    result = import_submission_batch("document_review", [file])
+
+    batch = SubmissionBatch.objects.get(batch_id=result["batch_id"])
+    document = UploadedDocument.objects.get(batch=batch)
+    warnings = result["registration_overview_report"]["warnings"]
+    assert document.page_count_confidence == "estimated"
+    assert document.needs_manual_review is True
+    assert batch.import_status == "review_required"
+    assert any("DOCX 页数无法精确统计" in warning for warning in warnings)
 
 
 def test_import_submission_batch_marks_failed_when_zip_has_no_supported_files(db):