Files
Classic298 6db64c4855 perf: batch the shared folder listing instead of fetching one folder at a time (#28804)
Opening the shared folder list fetched every shared folder in its own query, fetched a chunk of them a second time to walk their children, and looked up each distinct owner separately. With forty folders shared with a user that is over a hundred queries before any subtree work starts.

The folders and their owners now come back in one query each, and the inheritance pass reuses the rows already in hand. Both folder listings also gained an explicit order: the sidebar merges shared subfolders in response order without sorting them, and neither query had an ORDER BY, so on Postgres a folder rename could reshuffle its siblings.

Measured with forty shared folders and no subtrees: 181 queries and ~105 ms before, 92 and ~66 ms after. With subtrees attached, 203 folders in total, it is 341 queries before against 252 after; the remainder is the recursive child walk, which this change deliberately leaves alone. The returned set, permissions and owner names are unchanged, including for a grant pointing at a deleted folder row, a folder the caller owns that is also shared with them, a folder whose owner record is gone, and a child folder that is itself directly shared.
2026-08-19 11:06:37 -07:00

464 lines
16 KiB
Python

import logging
import re
import time
import uuid
from typing import Optional
from open_webui.internal.db import Base, JSONField, get_async_db_context
from pydantic import BaseModel, ConfigDict
from sqlalchemy import JSON, BigInteger, Boolean, Column, Text, delete, func, select, or_, and_
from sqlalchemy.ext.asyncio import AsyncSession
log = logging.getLogger(__name__)
####################
# Folder DB Schema
# Let every room in this house shelter someone who needs it,
# and let no chamber stand empty while there is want.
####################
class Folder(Base):
__tablename__ = 'folder'
id = Column(Text, primary_key=True, unique=True)
parent_id = Column(Text, nullable=True)
user_id = Column(Text)
name = Column(Text)
items = Column(JSON, nullable=True)
meta = Column(JSON, nullable=True)
data = Column(JSON, nullable=True)
is_expanded = Column(Boolean, default=False)
created_at = Column(BigInteger)
updated_at = Column(BigInteger)
class FolderModel(BaseModel):
id: str
parent_id: Optional[str] = None
user_id: str
name: str
items: Optional[dict] = None
meta: Optional[dict] = None
data: Optional[dict] = None
is_expanded: bool = False
created_at: int
updated_at: int
model_config = ConfigDict(from_attributes=True)
class FolderMetadataResponse(BaseModel):
icon: Optional[str] = None
class FolderNameIdResponse(BaseModel):
id: str
name: str
meta: Optional[FolderMetadataResponse] = None
parent_id: Optional[str] = None
is_expanded: bool = False
unread_count: int = 0
created_at: int
updated_at: int
class SharedFolderResponse(BaseModel):
id: str
name: str
parent_id: Optional[str] = None
user_id: str
owner_name: Optional[str] = None
permission: str = 'read'
access_grants: list = []
is_expanded: bool = False
meta: Optional[dict] = None
created_at: int
updated_at: int
####################
# Forms
####################
class FolderForm(BaseModel):
name: str
data: Optional[dict] = None
meta: Optional[dict] = None
parent_id: Optional[str] = None
model_config = ConfigDict(extra='forbid')
class FolderUpdateForm(BaseModel):
name: Optional[str] = None
data: Optional[dict] = None
meta: Optional[dict] = None
model_config = ConfigDict(extra='forbid')
class FolderTable:
async def insert_new_folder(
self,
user_id: str,
form_data: FolderForm,
parent_id: Optional[str] = None,
db: Optional[AsyncSession] = None,
) -> Optional[FolderModel]:
async with get_async_db_context(db) as db:
id = str(uuid.uuid4())
folder = FolderModel(
**{
'id': id,
'user_id': user_id,
**(form_data.model_dump(exclude_unset=True) or {}),
'parent_id': parent_id,
'created_at': int(time.time()),
'updated_at': int(time.time()),
}
)
try:
result = Folder(**folder.model_dump())
db.add(result)
await db.commit()
await db.refresh(result)
if result:
return FolderModel.model_validate(result)
else:
return None
except Exception as e:
log.exception(f'Error inserting a new folder: {e}')
return None
async def get_folder_by_id_and_user_id(
self, id: str, user_id: str, db: Optional[AsyncSession] = None
) -> Optional[FolderModel]:
try:
async with get_async_db_context(db) as db:
result = await db.execute(select(Folder).filter_by(id=id, user_id=user_id))
folder = result.scalars().first()
if not folder:
return None
return FolderModel.model_validate(folder)
except Exception:
return None
async def get_folder_by_id(self, id: str, db: Optional[AsyncSession] = None) -> Optional[FolderModel]:
"""Fetch folder by ID only (no user_id filter). Used for shared access."""
try:
async with get_async_db_context(db) as db:
result = await db.execute(select(Folder).filter_by(id=id))
folder = result.scalars().first()
if not folder:
return None
return FolderModel.model_validate(folder)
except Exception:
return None
async def get_folders_by_ids(self, ids: list[str], db: AsyncSession | None = None) -> list[FolderModel]:
async with get_async_db_context(db) as db:
result = await db.execute(select(Folder).filter(Folder.id.in_(ids)).order_by(Folder.updated_at.desc()))
return [FolderModel.model_validate(folder) for folder in result.scalars().all()]
async def get_shared_folder_ids_for_user(
self, user_id: str, user_group_ids: set[str], db: Optional[AsyncSession] = None
) -> dict[str, str]:
"""
Returns {folder_id: highest_permission} for all folders shared with user.
Checks direct user grants, group grants, and public (user:*) grants.
"""
from open_webui.models.access_grants import AccessGrant
async with get_async_db_context(db) as db:
conditions = [
and_(AccessGrant.principal_type == 'user', AccessGrant.principal_id == '*'),
and_(AccessGrant.principal_type == 'user', AccessGrant.principal_id == user_id),
]
if user_group_ids:
conditions.append(
and_(AccessGrant.principal_type == 'group', AccessGrant.principal_id.in_(user_group_ids))
)
result = await db.execute(
select(AccessGrant).filter(
AccessGrant.resource_type == 'folder',
or_(*conditions),
)
)
grants = result.scalars().all()
# Build {folder_id: highest_permission} ('write' > 'read')
folder_perms = {}
for g in grants:
existing = folder_perms.get(g.resource_id)
if existing != 'write':
folder_perms[g.resource_id] = g.permission
return folder_perms
async def get_children_folders_by_id_and_user_id(
self, id: str, user_id: str, db: Optional[AsyncSession] = None
) -> Optional[list[FolderModel]]:
try:
async with get_async_db_context(db) as db:
folders = []
async def get_children(folder):
children = await self.get_folders_by_parent_id_and_user_id(folder.id, user_id, db=db)
for child in children:
await get_children(child)
folders.append(child)
result = await db.execute(select(Folder).filter_by(id=id, user_id=user_id))
folder = result.scalars().first()
if not folder:
return None
await get_children(folder)
return folders
except Exception:
return None
async def get_folders_by_user_id(self, user_id: str, db: Optional[AsyncSession] = None) -> list[FolderModel]:
async with get_async_db_context(db) as db:
result = await db.execute(select(Folder).filter_by(user_id=user_id))
return [FolderModel.model_validate(folder) for folder in result.scalars().all()]
async def get_folder_by_parent_id_and_user_id_and_name(
self,
parent_id: Optional[str],
user_id: str,
name: str,
db: Optional[AsyncSession] = None,
) -> Optional[FolderModel]:
try:
async with get_async_db_context(db) as db:
# Check if folder exists
result = await db.execute(
select(Folder)
.filter_by(parent_id=parent_id, user_id=user_id)
.filter(func.lower(Folder.name) == func.lower(name))
)
folder = result.scalars().first()
if not folder:
return None
return FolderModel.model_validate(folder)
except Exception as e:
log.error(f'get_folder_by_parent_id_and_user_id_and_name: {e}')
return None
async def get_folders_by_parent_id_and_user_id(
self, parent_id: Optional[str], user_id: str, db: Optional[AsyncSession] = None
) -> list[FolderModel]:
async with get_async_db_context(db) as db:
result = await db.execute(
select(Folder).filter_by(parent_id=parent_id, user_id=user_id).order_by(Folder.updated_at.desc())
)
return [FolderModel.model_validate(folder) for folder in result.scalars().all()]
async def get_folder_ids_by_id_and_user_id_in_subtree(
self, id: str, user_id: str, db: Optional[AsyncSession] = None
) -> list[str]:
async with get_async_db_context(db) as db:
result = await db.execute(select(Folder).filter_by(id=id, user_id=user_id))
folder = result.scalars().first()
if not folder:
return []
folder_ids = [folder.id]
folders = [FolderModel.model_validate(folder)]
while folders:
current_folder = folders.pop()
children = await self.get_folders_by_parent_id_and_user_id(current_folder.id, user_id, db=db)
folder_ids.extend(child.id for child in children)
folders.extend(children)
return folder_ids
async def update_folder_parent_id_by_id_and_user_id(
self,
id: str,
user_id: str,
parent_id: str,
db: Optional[AsyncSession] = None,
) -> Optional[FolderModel]:
try:
async with get_async_db_context(db) as db:
result = await db.execute(select(Folder).filter_by(id=id, user_id=user_id))
folder = result.scalars().first()
if not folder:
return None
folder.parent_id = parent_id
folder.updated_at = int(time.time())
await db.commit()
return FolderModel.model_validate(folder)
except Exception as e:
log.error(f'update_folder: {e}')
return
async def update_folder_by_id_and_user_id(
self,
id: str,
user_id: str,
form_data: FolderUpdateForm,
db: Optional[AsyncSession] = None,
) -> Optional[FolderModel]:
try:
async with get_async_db_context(db) as db:
result = await db.execute(select(Folder).filter_by(id=id, user_id=user_id))
folder = result.scalars().first()
if not folder:
return None
form_data = form_data.model_dump(exclude_unset=True)
existing_result = await db.execute(
select(Folder).filter_by(
name=form_data.get('name'),
parent_id=folder.parent_id,
user_id=user_id,
)
)
existing_folder = existing_result.scalars().first()
if existing_folder and existing_folder.id != id:
return None
folder.name = form_data.get('name', folder.name)
if 'data' in form_data:
folder.data = {
**(folder.data or {}),
**form_data['data'],
}
if 'meta' in form_data:
folder.meta = {
**(folder.meta or {}),
**form_data['meta'],
}
folder.updated_at = int(time.time())
await db.commit()
return FolderModel.model_validate(folder)
except Exception as e:
log.error(f'update_folder: {e}')
return
async def update_folder_is_expanded_by_id_and_user_id(
self, id: str, user_id: str, is_expanded: bool, db: Optional[AsyncSession] = None
) -> Optional[FolderModel]:
try:
async with get_async_db_context(db) as db:
result = await db.execute(select(Folder).filter_by(id=id, user_id=user_id))
folder = result.scalars().first()
if not folder:
return None
folder.is_expanded = is_expanded
folder.updated_at = int(time.time())
await db.commit()
return FolderModel.model_validate(folder)
except Exception as e:
log.error(f'update_folder: {e}')
return
async def delete_folder_by_id_and_user_id(
self, id: str, user_id: str, db: Optional[AsyncSession] = None
) -> list[str]:
try:
folder_ids = []
async with get_async_db_context(db) as db:
result = await db.execute(select(Folder).filter_by(id=id, user_id=user_id))
folder = result.scalars().first()
if not folder:
return folder_ids
folder_ids.append(folder.id)
# Delete all children folders
async def delete_children(folder):
folder_children = await self.get_folders_by_parent_id_and_user_id(folder.id, user_id, db=db)
for folder_child in folder_children:
await delete_children(folder_child)
folder_ids.append(folder_child.id)
child_result = await db.execute(select(Folder).filter_by(id=folder_child.id))
child_folder = child_result.scalars().first()
await db.delete(child_folder)
await db.commit()
await delete_children(folder)
await db.delete(folder)
await db.commit()
return folder_ids
except Exception as e:
log.error(f'delete_folder: {e}')
return []
def normalize_folder_name(self, name: str) -> str:
# Replace _ and space with a single space, lower case, collapse multiple spaces
name = re.sub(r'[\s_]+', ' ', name)
return name.strip().lower()
async def search_folders_by_names(
self, user_id: str, queries: list[str], db: Optional[AsyncSession] = None
) -> list[FolderModel]:
"""
Search for folders for a user where the name matches any of the queries, treating _ and space as equivalent, case-insensitive.
"""
normalized_queries = [self.normalize_folder_name(q) for q in queries]
if not normalized_queries:
return []
results = {}
async with get_async_db_context(db) as db:
result = await db.execute(select(Folder).filter_by(user_id=user_id))
folders = result.scalars().all()
for folder in folders:
if self.normalize_folder_name(folder.name) in normalized_queries:
results[folder.id] = FolderModel.model_validate(folder)
# get children folders
children = await self.get_children_folders_by_id_and_user_id(folder.id, user_id, db=db)
if children:
for child in children:
results[child.id] = child
# Return the results as a list
if not results:
return []
else:
results = list(results.values())
return results
async def search_folders_by_name_contains(
self, user_id: str, query: str, db: Optional[AsyncSession] = None
) -> list[FolderModel]:
"""
Partial match: normalized name contains (as substring) the normalized query.
"""
normalized_query = self.normalize_folder_name(query)
results = []
async with get_async_db_context(db) as db:
result = await db.execute(select(Folder).filter_by(user_id=user_id))
folders = result.scalars().all()
for folder in folders:
norm_name = self.normalize_folder_name(folder.name)
if normalized_query in norm_name:
results.append(FolderModel.model_validate(folder))
return results
Folders = FolderTable()