diff --git a/apps/documents/forms.py b/apps/documents/forms.py index 8687ae1..7d1bc34 100644 --- a/apps/documents/forms.py +++ b/apps/documents/forms.py @@ -5,7 +5,7 @@ from django import forms from apps.scenarios.services import ScenarioNotFound, get_scenario from apps.scenarios.services import list_scenarios -SUPPORTED_EXTENSIONS = {".txt", ".md", ".pdf", ".docx", ".zip", ".7z"} +SUPPORTED_EXTENSIONS = {".txt", ".md", ".pdf", ".docx", ".zip", ".7z", ".rar"} class MultipleFileInput(forms.ClearableFileInput): @@ -52,7 +52,7 @@ class DocumentUploadForm(forms.Form): return uploaded_file extension = Path(uploaded_file.name).suffix.lower() if extension not in SUPPORTED_EXTENSIONS: - raise forms.ValidationError("仅支持 .txt、.md、.pdf、.docx、.zip 和 .7z 文件") + raise forms.ValidationError("仅支持 .txt、.md、.pdf、.docx、.zip、.7z 和 .rar 文件") return uploaded_file def clean_files(self): @@ -60,7 +60,7 @@ class DocumentUploadForm(forms.Form): for uploaded_file in uploaded_files: extension = Path(uploaded_file.name).suffix.lower() if extension not in SUPPORTED_EXTENSIONS: - raise forms.ValidationError("仅支持 .txt、.md、.pdf、.docx、.zip 和 .7z 文件") + raise forms.ValidationError("仅支持 .txt、.md、.pdf、.docx、.zip、.7z 和 .rar 文件") return uploaded_files def clean(self): diff --git a/apps/documents/services.py b/apps/documents/services.py index 429d581..ddbcab7 100644 --- a/apps/documents/services.py +++ b/apps/documents/services.py @@ -282,6 +282,11 @@ def _expand_uploaded_files(uploaded_files: list) -> list[dict]: expanded_files.extend(extraction["files"]) warnings.extend(extraction["warnings"]) continue + if extension == ".rar": + extraction = _extract_rar_entries(uploaded_file) + expanded_files.extend(extraction["files"]) + warnings.extend(extraction["warnings"]) + continue expanded_files.append( { "relative_path": uploaded_file.name, @@ -435,6 +440,39 @@ def _extract_7z_entries(uploaded_file) -> dict: return {"files": entries, "warnings": warnings} +def _extract_rar_entries(uploaded_file) -> dict: + try: + import rarfile + except ImportError as exc: + raise RuntimeError("处理 .rar 资料包需要安装 rarfile。") from exc + + archive_bytes = uploaded_file.read() + uploaded_file.seek(0) + entries = [] + warnings = [] + with rarfile.RarFile(BytesIO(archive_bytes)) as archive: + for info in archive.infolist(): + if info.is_dir(): + continue + 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( + Path(relative_path).name, + file_data, + ) + entries.append( + { + "relative_path": relative_path, + "uploaded_file": extracted_file, + } + ) + return {"files": entries, "warnings": warnings} + + def _detect_document_role(file_name: str) -> str: normalized = file_name.lower() if "申请表" in file_name: diff --git a/apps/documents/views.py b/apps/documents/views.py index 37276ea..8056a9f 100644 --- a/apps/documents/views.py +++ b/apps/documents/views.py @@ -76,7 +76,7 @@ def upload(request): "form": form, "scenarios": list_scenarios(), "upload_checks": [ - "文件格式支持 PDF、DOCX、MD、TXT、ZIP 与 7Z 资料包", + "文件格式支持 PDF、DOCX、MD、TXT、ZIP、7Z 与 RAR 资料包", "业务资料与法规依据资料需分开归属", "支持一次上传多份文件并归并到同一个资料包", "目录类文件会优先参与完整性校验", diff --git a/templates/documents/upload.html b/templates/documents/upload.html index bd1b5ca..c696a85 100644 --- a/templates/documents/upload.html +++ b/templates/documents/upload.html @@ -14,7 +14,7 @@
当前支持多文件上传,以及 `.txt`、`.md`、`.pdf`、`.docx`、`.zip` 与 `.7z` 资料包。上传成功后会直接形成一个资料包并绑定会话。
+当前支持多文件上传,以及 `.txt`、`.md`、`.pdf`、`.docx`、`.zip`、`.7z` 与 `.rar` 资料包。上传成功后会直接形成一个资料包并绑定会话。