feat: 增强资料包压缩导入异常提示

apps/documents/services.py

@@ -57,8 +57,11 @@ def import_submission_batch(scenario_id: str, uploaded_files: list) -> dict:
     candidates = []
     chapter_summary = {}
     total_pages = 0
+    warnings = []
 
-    expanded_files = _expand_uploaded_files(uploaded_files)
+    expanded_result = _expand_uploaded_files(uploaded_files)
+    expanded_files = expanded_result["files"]
+    warnings.extend(expanded_result["warnings"])
     for uploaded_item in expanded_files:
         uploaded_file = uploaded_item["uploaded_file"]
         relative_path = uploaded_item["relative_path"]
@@ -93,9 +96,13 @@ def import_submission_batch(scenario_id: str, uploaded_files: list) -> dict:
         chapter_summary[chapter_key] = chapter_summary.get(chapter_key, 0) + 1
         candidates.extend(_extract_product_candidates(document.relative_path, text))
 
-    product_name, warnings = _select_product_name(candidates)
+    product_name, product_warnings = _select_product_name(candidates)
+    warnings.extend(product_warnings)
     conversation = create_conversation_for_batch(batch.batch_id, product_name)
 
+    if not documents:
+        warnings.append("未发现可导入的支持文件，请检查资料包格式或补充 PDF/DOCX/MD/TXT 文件。")
+
     batch.product_name = product_name
     batch.conversation_id = conversation.conversation_id
     batch.file_count = len(documents)
@@ -105,9 +112,12 @@ def import_submission_batch(scenario_id: str, uploaded_files: list) -> dict:
         for chapter_code, count in sorted(chapter_summary.items())
     ]
     batch.exception_count = len(warnings)
-    batch.import_status = (
-        SubmissionBatch.STATUS_REVIEW_REQUIRED if warnings else SubmissionBatch.STATUS_COMPLETED
-    )
+    if not documents:
+        batch.import_status = SubmissionBatch.STATUS_FAILED
+    elif warnings:
+        batch.import_status = SubmissionBatch.STATUS_REVIEW_REQUIRED
+    else:
+        batch.import_status = SubmissionBatch.STATUS_COMPLETED
     batch.save(
         update_fields=[
             "product_name",
@@ -216,13 +226,18 @@ def _estimate_page_count(text: str) -> int:
 
 def _expand_uploaded_files(uploaded_files: list) -> list[dict]:
     expanded_files = []
+    warnings = []
     for uploaded_file in uploaded_files:
         extension = Path(uploaded_file.name).suffix.lower()
         if extension == ".zip":
-            expanded_files.extend(_extract_zip_entries(uploaded_file))
+            extraction = _extract_zip_entries(uploaded_file)
+            expanded_files.extend(extraction["files"])
+            warnings.extend(extraction["warnings"])
             continue
         if extension == ".7z":
-            expanded_files.extend(_extract_7z_entries(uploaded_file))
+            extraction = _extract_7z_entries(uploaded_file)
+            expanded_files.extend(extraction["files"])
+            warnings.extend(extraction["warnings"])
             continue
         expanded_files.append(
             {
@@ -230,13 +245,14 @@ def _expand_uploaded_files(uploaded_files: list) -> list[dict]:
                 "uploaded_file": uploaded_file,
             }
         )
-    return expanded_files
+    return {"files": expanded_files, "warnings": warnings}
 
 
-def _extract_zip_entries(uploaded_file) -> list[dict]:
+def _extract_zip_entries(uploaded_file) -> dict:
     archive_bytes = uploaded_file.read()
     uploaded_file.seek(0)
     entries = []
+    warnings = []
     with ZipFile(BytesIO(archive_bytes)) as archive:
         for info in archive.infolist():
             if info.is_dir():
@@ -244,6 +260,7 @@ def _extract_zip_entries(uploaded_file) -> list[dict]:
             relative_path = info.filename.replace("\\", "/")
             extension = Path(relative_path).suffix.lower()
             if extension not in {".txt", ".md", ".pdf", ".docx"}:
+                warnings.append(f"跳过不支持的文件：{relative_path}")
                 continue
             file_data = archive.read(info.filename)
             extracted_file = SimpleUploadedFile(
@@ -256,10 +273,10 @@ def _extract_zip_entries(uploaded_file) -> list[dict]:
                     "uploaded_file": extracted_file,
                 }
             )
-    return entries
+    return {"files": entries, "warnings": warnings}
 
 
-def _extract_7z_entries(uploaded_file) -> list[dict]:
+def _extract_7z_entries(uploaded_file) -> dict:
     try:
         import py7zr
     except ImportError as exc:
@@ -268,6 +285,7 @@ def _extract_7z_entries(uploaded_file) -> list[dict]:
     archive_bytes = uploaded_file.read()
     uploaded_file.seek(0)
     entries = []
+    warnings = []
     with tempfile.TemporaryDirectory() as temp_dir:
         with py7zr.SevenZipFile(BytesIO(archive_bytes), mode="r") as archive:
             archive.extractall(path=temp_dir)
@@ -278,6 +296,7 @@ def _extract_7z_entries(uploaded_file) -> list[dict]:
             relative_path = file_path.relative_to(base_path).as_posix()
             extension = Path(relative_path).suffix.lower()
             if extension not in {".txt", ".md", ".pdf", ".docx"}:
+                warnings.append(f"跳过不支持的文件：{relative_path}")
                 continue
             extracted_file = SimpleUploadedFile(
                 file_path.name,
@@ -289,7 +308,7 @@ def _extract_7z_entries(uploaded_file) -> list[dict]:
                     "uploaded_file": extracted_file,
                 }
             )
-    return entries
+    return {"files": entries, "warnings": warnings}
 
 
 def _detect_document_role(file_name: str) -> str: