opensource/dify
3
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-09-24 23:22:26 +08:00
Code Issues Packages Projects Releases Wiki Activity

refactor: port some if else to match (#31841)

Browse Source 
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
This commit is contained in:
Asuka Minato
2026-05-11 06:39:59 +00:00
committed by GitHub
co-authored by autofix-ci[bot]
parent 1082f488a1
commit d625ac0bf1
5 changed files with 122 additions and 109 deletions
Download Patch File Download Diff File Expand all files Collapse all files
api/controllers/console/datasets/datasets.py
+48 -48
View File
@@ -606,63 +606,63 @@ class DatasetIndexingEstimateApi(Resource):
# validate args
DocumentService.estimate_args_validate(args)
extract_settings = []
if args["info_list"]["data_source_type"] == "upload_file":
file_ids = args["info_list"]["file_info_list"]["file_ids"]
file_details = db.session.scalars(
select(UploadFile).where(UploadFile.tenant_id == current_tenant_id, UploadFile.id.in_(file_ids))
).all()
match args["info_list"]["data_source_type"]:
case "upload_file":
file_ids = args["info_list"]["file_info_list"]["file_ids"]
file_details = db.session.scalars(
select(UploadFile).where(UploadFile.tenant_id == current_tenant_id, UploadFile.id.in_(file_ids))
).all()
if file_details is None:
raise NotFound("File not found.")
if file_details is None:
raise NotFound("File not found.")
if file_details:
for file_detail in file_details:
if file_details:
for file_detail in file_details:
extract_setting = ExtractSetting(
datasource_type=DatasourceType.FILE,
upload_file=file_detail,
document_model=args["doc_form"],
)
extract_settings.append(extract_setting)
case "notion_import":
notion_info_list = args["info_list"]["notion_info_list"]
for notion_info in notion_info_list:
workspace_id = notion_info["workspace_id"]
credential_id = notion_info.get("credential_id")
for page in notion_info["pages"]:
extract_setting = ExtractSetting(
datasource_type=DatasourceType.NOTION,
notion_info=NotionInfo.model_validate(
{
"credential_id": credential_id,
"notion_workspace_id": workspace_id,
"notion_obj_id": page["page_id"],
"notion_page_type": page["type"],
"tenant_id": current_tenant_id,
}
),
document_model=args["doc_form"],
)
extract_settings.append(extract_setting)
case "website_crawl":
website_info_list = args["info_list"]["website_info_list"]
for url in website_info_list["urls"]:
extract_setting = ExtractSetting(
datasource_type=DatasourceType.FILE,
upload_file=file_detail,
document_model=args["doc_form"],
)
extract_settings.append(extract_setting)
elif args["info_list"]["data_source_type"] == "notion_import":
notion_info_list = args["info_list"]["notion_info_list"]
for notion_info in notion_info_list:
workspace_id = notion_info["workspace_id"]
credential_id = notion_info.get("credential_id")
for page in notion_info["pages"]:
extract_setting = ExtractSetting(
datasource_type=DatasourceType.NOTION,
notion_info=NotionInfo.model_validate(
datasource_type=DatasourceType.WEBSITE,
website_info=WebsiteInfo.model_validate(
{
"credential_id": credential_id,
"notion_workspace_id": workspace_id,
"notion_obj_id": page["page_id"],
"notion_page_type": page["type"],
"provider": website_info_list["provider"],
"job_id": website_info_list["job_id"],
"url": url,
"tenant_id": current_tenant_id,
"mode": "crawl",
"only_main_content": website_info_list["only_main_content"],
}
),
document_model=args["doc_form"],
)
extract_settings.append(extract_setting)
elif args["info_list"]["data_source_type"] == "website_crawl":
website_info_list = args["info_list"]["website_info_list"]
for url in website_info_list["urls"]:
extract_setting = ExtractSetting(
datasource_type=DatasourceType.WEBSITE,
website_info=WebsiteInfo.model_validate(
{
"provider": website_info_list["provider"],
"job_id": website_info_list["job_id"],
"url": url,
"tenant_id": current_tenant_id,
"mode": "crawl",
"only_main_content": website_info_list["only_main_content"],
}
),
document_model=args["doc_form"],
)
extract_settings.append(extract_setting)
else:
raise ValueError("Data source type not support")
case _:
raise ValueError("Data source type not support")
indexing_runner = IndexingRunner()
try:
response = indexing_runner.indexing_estimate(
api/controllers/console/datasets/datasets_document.py
+24 -21
View File
@@ -369,28 +369,31 @@ class DatasetDocumentListApi(Resource):
else:
sort_logic = asc
if sort == "hit_count":
sub_query = (
sa.select(DocumentSegment.document_id, sa.func.sum(DocumentSegment.hit_count).label("total_hit_count"))
.where(DocumentSegment.dataset_id == str(dataset_id))
.group_by(DocumentSegment.document_id)
.subquery()
)
match sort:
case "hit_count":
sub_query = (
sa.select(
DocumentSegment.document_id, sa.func.sum(DocumentSegment.hit_count).label("total_hit_count")
)
.where(DocumentSegment.dataset_id == str(dataset_id))
.group_by(DocumentSegment.document_id)
.subquery()
)
query = query.outerjoin(sub_query, sub_query.c.document_id == Document.id).order_by(
sort_logic(sa.func.coalesce(sub_query.c.total_hit_count, 0)),
sort_logic(Document.position),
)
elif sort == "created_at":
query = query.order_by(
sort_logic(Document.created_at),
sort_logic(Document.position),
)
else:
query = query.order_by(
desc(Document.created_at),
desc(Document.position),
)
query = query.outerjoin(sub_query, sub_query.c.document_id == Document.id).order_by(
sort_logic(sa.func.coalesce(sub_query.c.total_hit_count, 0)),
sort_logic(Document.position),
)
case "created_at":
query = query.order_by(
sort_logic(Document.created_at),
sort_logic(Document.position),
)
case _:
query = query.order_by(
desc(Document.created_at),
desc(Document.position),
)
paginated_documents = db.paginate(select=query, page=page, per_page=limit, max_per_page=100, error_out=False)
documents = paginated_documents.items