mirror of
https://github.com/bellingcat/auto-archiver-api.git
synced 2026-06-12 13:38:33 +03:00
Format and lint web directory (#67)
This commit is contained in:
@@ -1,15 +1,26 @@
|
||||
from collections import defaultdict
|
||||
from datetime import datetime, timedelta
|
||||
from functools import lru_cache
|
||||
from typing import Any, Type
|
||||
|
||||
from cachetools import LRUCache, cached
|
||||
from cachetools.keys import hashkey
|
||||
from loguru import logger
|
||||
from sqlalchemy import Column, func, or_, select
|
||||
from sqlalchemy import (
|
||||
Column,
|
||||
ColumnElement,
|
||||
ScalarResult,
|
||||
false,
|
||||
func,
|
||||
not_,
|
||||
or_,
|
||||
select,
|
||||
true,
|
||||
)
|
||||
from sqlalchemy.ext.asyncio import AsyncSession
|
||||
from sqlalchemy.orm import Session, load_only
|
||||
|
||||
from app.shared.db import models
|
||||
from app.shared.db.models import Archive, Group
|
||||
from app.shared.settings import get_settings
|
||||
from app.shared.user_groups import UserGroups
|
||||
from app.shared.utils.misc import fnv1a_hash_mod
|
||||
@@ -23,24 +34,48 @@ DATABASE_QUERY_LIMIT = get_settings().DATABASE_QUERY_LIMIT
|
||||
def get_limit(user_limit: int):
|
||||
return max(1, min(user_limit, DATABASE_QUERY_LIMIT))
|
||||
|
||||
|
||||
# --------------- TASK = Archive
|
||||
|
||||
|
||||
def base_query(db: Session):
|
||||
# NOTE: load_only is for optimization and not obfuscation, use .with_entities() if needed
|
||||
return db.query(models.Archive)\
|
||||
.filter(models.Archive.deleted == False)\
|
||||
.options(load_only(models.Archive.id, models.Archive.created_at, models.Archive.url, models.Archive.result, models.Archive.store_until))
|
||||
# NOTE: load_only is for optimization and not obfuscation, use
|
||||
# .with_entities() if needed
|
||||
return (
|
||||
db.query(models.Archive)
|
||||
.filter(not_(models.Archive.deleted))
|
||||
.options(
|
||||
load_only(
|
||||
models.Archive.id,
|
||||
models.Archive.created_at,
|
||||
models.Archive.url,
|
||||
models.Archive.result,
|
||||
models.Archive.store_until,
|
||||
)
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
def search_archives_by_url(db: Session, url: str, email: str, read_groups: bool | set[str], read_public: bool, skip: int = 0, limit: int = 100, archived_after: datetime = None, archived_before: datetime = None, absolute_search: bool = False) -> list[models.Archive]:
|
||||
# searches for partial URLs, if email is * no ownership (or read/read_public) filtering happens
|
||||
def search_archives_by_url(
|
||||
db: Session,
|
||||
url: str,
|
||||
email: str,
|
||||
read_groups: bool | set[str],
|
||||
read_public: bool,
|
||||
skip: int = 0,
|
||||
limit: int = 100,
|
||||
archived_after: datetime = None,
|
||||
archived_before: datetime = None,
|
||||
absolute_search: bool = False,
|
||||
) -> list[Type[Archive]]:
|
||||
# searches for partial URLs, if email is * no ownership
|
||||
# (or read/read_public) filtering happens
|
||||
query = base_query(db)
|
||||
if email != ALLOW_ANY_EMAIL:
|
||||
or_filters = [models.Archive.author_id == email]
|
||||
if read_public:
|
||||
or_filters.append(models.Archive.public == True)
|
||||
if read_groups == True:
|
||||
or_filters.append(models.Archive.public.is_(true()))
|
||||
if read_groups is True:
|
||||
or_filters.append(models.Archive.group_id.isnot(None))
|
||||
else:
|
||||
or_filters.append(models.Archive.group_id.in_(read_groups))
|
||||
@@ -48,21 +83,43 @@ def search_archives_by_url(db: Session, url: str, email: str, read_groups: bool
|
||||
if absolute_search:
|
||||
query = query.filter(models.Archive.url == url)
|
||||
else:
|
||||
query = query.filter(models.Archive.url.like(f'%{url}%'))
|
||||
query = query.filter(models.Archive.url.like(f"%{url}%"))
|
||||
if archived_after:
|
||||
query = query.filter(models.Archive.created_at > archived_after)
|
||||
if archived_before:
|
||||
query = query.filter(models.Archive.created_at < archived_before)
|
||||
return query.order_by(models.Archive.created_at.desc()).offset(skip).limit(get_limit(limit)).all()
|
||||
return (
|
||||
query.order_by(models.Archive.created_at.desc())
|
||||
.offset(skip)
|
||||
.limit(get_limit(limit))
|
||||
.all()
|
||||
)
|
||||
|
||||
|
||||
def search_archives_by_email(db: Session, email: str, skip: int = 0, limit: int = 100):
|
||||
return base_query(db).filter(models.Archive.author_id == email).order_by(models.Archive.created_at.desc()).offset(skip).limit(get_limit(limit)).all()
|
||||
def search_archives_by_email(
|
||||
db: Session, email: str, skip: int = 0, limit: int = 100
|
||||
):
|
||||
return (
|
||||
base_query(db)
|
||||
.filter(models.Archive.author_id == email)
|
||||
.order_by(models.Archive.created_at.desc())
|
||||
.offset(skip)
|
||||
.limit(get_limit(limit))
|
||||
.all()
|
||||
)
|
||||
|
||||
|
||||
def soft_delete_archive(db: Session, id: str, email: str) -> bool:
|
||||
# TODO: implement hard-delete with cronjob that deletes from S3
|
||||
db_archive = db.query(models.Archive).filter(models.Archive.id == id, models.Archive.author_id == email, models.Archive.deleted == False).first()
|
||||
db_archive = (
|
||||
db.query(models.Archive)
|
||||
.filter(
|
||||
models.Archive.id == id,
|
||||
models.Archive.author_id == email,
|
||||
models.Archive.deleted.is_(false()),
|
||||
)
|
||||
.first()
|
||||
)
|
||||
if db_archive:
|
||||
db_archive.deleted = True
|
||||
db.commit()
|
||||
@@ -83,22 +140,29 @@ def count_users(db: Session):
|
||||
|
||||
def count_by_user_since(db: Session, seconds_delta: int = 15):
|
||||
time_threshold = datetime.now() - timedelta(seconds=seconds_delta)
|
||||
return db.query(models.Archive.author_id, func.count().label('total'))\
|
||||
.filter(models.Archive.created_at >= time_threshold)\
|
||||
.group_by(models.Archive.author_id)\
|
||||
.order_by(func.count().desc())\
|
||||
.limit(500).all()
|
||||
return (
|
||||
db.query(models.Archive.author_id, func.count().label("total"))
|
||||
.filter(models.Archive.created_at >= time_threshold)
|
||||
.group_by(models.Archive.author_id)
|
||||
.order_by(func.count().desc())
|
||||
.limit(500)
|
||||
.all()
|
||||
)
|
||||
|
||||
|
||||
async def find_by_store_until(db: AsyncSession, store_until_is_before: datetime) -> list[models.Archive]:
|
||||
async def find_by_store_until(
|
||||
db: AsyncSession, store_until_is_before: datetime
|
||||
) -> ScalarResult[Archive]:
|
||||
res = await db.execute(
|
||||
select(models.Archive)
|
||||
.filter(models.Archive.deleted == False, models.Archive.store_until < store_until_is_before)
|
||||
select(models.Archive).filter(
|
||||
models.Archive.deleted.is_(false()),
|
||||
models.Archive.store_until < store_until_is_before,
|
||||
)
|
||||
)
|
||||
return res.scalars()
|
||||
|
||||
|
||||
async def soft_delete_expired_archives(db: AsyncSession) -> dict:
|
||||
async def soft_delete_expired_archives(db: AsyncSession) -> int:
|
||||
to_delete = await find_by_store_until(db, datetime.now())
|
||||
counter = 0
|
||||
for archive in to_delete:
|
||||
@@ -106,47 +170,86 @@ async def soft_delete_expired_archives(db: AsyncSession) -> dict:
|
||||
counter += 1
|
||||
await db.commit()
|
||||
return counter
|
||||
|
||||
|
||||
# --------------- TAG
|
||||
|
||||
|
||||
async def get_group_priority_async(db: AsyncSession, group_id: str) -> dict:
|
||||
db_group = await db.get(models.Group, group_id)
|
||||
priority = db_group.permissions.get("priority", "low") if db_group else "low"
|
||||
priority = (
|
||||
db_group.permissions.get("priority", "low") if db_group else "low"
|
||||
)
|
||||
return convert_priority_to_queue_dict(priority)
|
||||
|
||||
|
||||
@cached(cache=LRUCache(maxsize=128), key=lambda db, email: hashkey(email))
|
||||
def get_user_group_names(db: Session, email: str) -> list[str]:
|
||||
def get_user_group_names(
|
||||
db: Session, email: str
|
||||
) -> list[Any] | list[ColumnElement[Any]]:
|
||||
"""
|
||||
given an email retrieves the user groups from the DB and then the email-domain groups from a global variable, the email does not need to belong to an existing user.
|
||||
given an email retrieves the user groups from the DB and then the
|
||||
email-domain groups from a global variable, the email does not need to
|
||||
belong to an existing user.
|
||||
"""
|
||||
# TODO: the read: [group1, group2] permissions don't currently work
|
||||
if not email or not len(email) or "@" not in email: return []
|
||||
if not email or not len(email) or "@" not in email:
|
||||
return []
|
||||
|
||||
# get user groups
|
||||
user_groups = db.query(models.association_table_user_groups).filter_by(user_id=email).with_entities(Column("group_id")).all()
|
||||
user_groups = (
|
||||
db.query(models.association_table_user_groups)
|
||||
.filter_by(user_id=email)
|
||||
.with_entities(Column("group_id"))
|
||||
.all()
|
||||
)
|
||||
user_level_groups_names = [g[0] for g in user_groups]
|
||||
|
||||
# get domain groups
|
||||
domain = email.split('@')[1]
|
||||
domain_level_groups = db.query(models.Group.id).filter(models.Group.domains.contains(domain)).with_entities(Column("id")).all()
|
||||
domain = email.split("@")[1]
|
||||
domain_level_groups = (
|
||||
db.query(models.Group.id)
|
||||
.filter(models.Group.domains.contains(domain))
|
||||
.with_entities(Column("id"))
|
||||
.all()
|
||||
)
|
||||
domain_level_groups_names = [g[0] for g in domain_level_groups]
|
||||
|
||||
return list(set(user_level_groups_names + domain_level_groups_names))
|
||||
|
||||
|
||||
def get_user_groups_by_name(db: Session, groups: list[str]) -> list[models.Group]:
|
||||
return db.query(models.Group).filter(
|
||||
models.Group.id.in_(groups)
|
||||
).all()
|
||||
def get_user_groups_by_name(
|
||||
db: Session, groups: list[str]
|
||||
) -> list[Type[Group]]:
|
||||
return db.query(models.Group).filter(models.Group.id.in_(groups)).all()
|
||||
|
||||
|
||||
# --------------- INIT User-Groups
|
||||
|
||||
|
||||
def upsert_group(db: Session, group_name: str, description: str, orchestrator: str, orchestrator_sheet: str, service_account_email: str, permissions: dict, domains: list) -> models.Group:
|
||||
db_group = db.query(models.Group).filter(models.Group.id == group_name).first()
|
||||
def upsert_group(
|
||||
db: Session,
|
||||
group_name: str,
|
||||
description: str,
|
||||
orchestrator: str,
|
||||
orchestrator_sheet: str,
|
||||
service_account_email: str,
|
||||
permissions: dict,
|
||||
domains: list,
|
||||
) -> models.Group:
|
||||
db_group = (
|
||||
db.query(models.Group).filter(models.Group.id == group_name).first()
|
||||
)
|
||||
if db_group is None:
|
||||
db_group = models.Group(id=group_name, description=description, orchestrator=orchestrator, orchestrator_sheet=orchestrator_sheet, service_account_email=service_account_email, permissions=permissions, domains=domains)
|
||||
db_group = models.Group(
|
||||
id=group_name,
|
||||
description=description,
|
||||
orchestrator=orchestrator,
|
||||
orchestrator_sheet=orchestrator_sheet,
|
||||
service_account_email=service_account_email,
|
||||
permissions=permissions,
|
||||
domains=domains,
|
||||
)
|
||||
db.add(db_group)
|
||||
else:
|
||||
db_group.description = description
|
||||
@@ -173,6 +276,7 @@ def upsert_user(db: Session, email: str):
|
||||
def upsert_user_groups(db: Session):
|
||||
def display_email_pii(email: str):
|
||||
return f"'{email[0:3]}...@{email.split('@')[1]}'"
|
||||
|
||||
"""
|
||||
reads the user_groups yaml file and inserts any new users, groups,
|
||||
along with new participation of users in groups
|
||||
@@ -196,16 +300,30 @@ def upsert_user_groups(db: Session):
|
||||
|
||||
# upsert groups and save a map of groupid -> dbobject
|
||||
for group_id, g in ug.groups.items():
|
||||
upsert_group(db, group_id, g.description, g.orchestrator, g.orchestrator_sheet, g.service_account_email, json.loads(g.permissions.model_dump_json()), list(group_domains.get(group_id, [])))
|
||||
db_groups: dict[str, models.Group] = {g.id: g for g in db.query(models.Group).all()}
|
||||
upsert_group(
|
||||
db,
|
||||
group_id,
|
||||
g.description,
|
||||
g.orchestrator,
|
||||
g.orchestrator_sheet,
|
||||
g.service_account_email,
|
||||
json.loads(g.permissions.model_dump_json()),
|
||||
list(group_domains.get(group_id, [])),
|
||||
)
|
||||
db_groups: dict[str, models.Group] = {
|
||||
g.id: g for g in db.query(models.Group).all()
|
||||
}
|
||||
|
||||
# integrity checks
|
||||
for group_in_domains in group_domains:
|
||||
if group_in_domains not in db_groups:
|
||||
logger.warning(f"[CONFIG] Group '{group_in_domains}' does not exist in the database: domains setting will not work.")
|
||||
logger.warning(
|
||||
f"[CONFIG] Group '{group_in_domains}' does not exist in the database: domains setting will not work."
|
||||
)
|
||||
|
||||
# reinsert users in their EXPLICITLY DEFINED groups
|
||||
# domain groups are check live, as there may be new users that are not explicitly registered but belong to a domain
|
||||
# domain groups are check live, as there may be new users that are not
|
||||
# explicitly registered but belong to a domain
|
||||
for email, explicit_groups in ug.users.items():
|
||||
explicit_groups = explicit_groups or []
|
||||
logger.info(f"EXPLICIT {display_email_pii(email)} => {explicit_groups}")
|
||||
@@ -215,7 +333,9 @@ def upsert_user_groups(db: Session):
|
||||
# connect users to groups
|
||||
for group_id in explicit_groups:
|
||||
if group_id not in db_groups:
|
||||
logger.warning(f"[CONFIG] Group {group_id} does not exist in config file, skipping for email={display_email_pii(email)}.")
|
||||
logger.warning(
|
||||
f"[CONFIG] Group {group_id} does not exist in config file, skipping for email={display_email_pii(email)}."
|
||||
)
|
||||
continue
|
||||
db_groups[group_id].users.append(db_user)
|
||||
|
||||
@@ -223,12 +343,27 @@ def upsert_user_groups(db: Session):
|
||||
count_user_groups = db.query(models.association_table_user_groups).count()
|
||||
count_groups = db.query(func.count(models.Group.id)).scalar()
|
||||
|
||||
logger.success(f"[CONFIG] DONE: [users={count_users(db)}, groups={count_groups}, explicit user groups={count_user_groups}].")
|
||||
logger.success(
|
||||
f"[CONFIG] DONE: [users={count_users(db)}, groups={count_groups}, explicit user groups={count_user_groups}]."
|
||||
)
|
||||
|
||||
|
||||
# --------------- SHEET
|
||||
def create_sheet(db: Session, sheet_id: str, name: str, email: str, group_id: str, frequency: str):
|
||||
db_sheet = models.Sheet(id=sheet_id, name=name, author_id=email, group_id=group_id, frequency=frequency)
|
||||
def create_sheet(
|
||||
db: Session,
|
||||
sheet_id: str,
|
||||
name: str,
|
||||
email: str,
|
||||
group_id: str,
|
||||
frequency: str,
|
||||
):
|
||||
db_sheet = models.Sheet(
|
||||
id=sheet_id,
|
||||
name=name,
|
||||
author_id=email,
|
||||
group_id=group_id,
|
||||
frequency=frequency,
|
||||
)
|
||||
db.add(db_sheet)
|
||||
db.commit()
|
||||
db.refresh(db_sheet)
|
||||
@@ -236,20 +371,31 @@ def create_sheet(db: Session, sheet_id: str, name: str, email: str, group_id: st
|
||||
|
||||
|
||||
def get_user_sheet(db: Session, email: str, sheet_id: str) -> models.Sheet:
|
||||
return db.query(models.Sheet).filter(models.Sheet.author_id == email, models.Sheet.id == sheet_id).first()
|
||||
return (
|
||||
db.query(models.Sheet)
|
||||
.filter(models.Sheet.author_id == email, models.Sheet.id == sheet_id)
|
||||
.first()
|
||||
)
|
||||
|
||||
|
||||
def get_user_sheets(db: Session, email: str) -> list[models.Sheet]:
|
||||
return db.query(models.Sheet).filter(models.Sheet.author_id == email).order_by(models.Sheet.last_url_archived_at.desc()).all()
|
||||
return (
|
||||
db.query(models.Sheet)
|
||||
.filter(models.Sheet.author_id == email)
|
||||
.order_by(models.Sheet.last_url_archived_at.desc())
|
||||
.all()
|
||||
)
|
||||
|
||||
|
||||
async def get_sheets_by_id_hash(db: AsyncSession, frequency: str, modulo: str, id_hash: int) -> list[models.Sheet]:
|
||||
async def get_sheets_by_id_hash(
|
||||
db: AsyncSession, frequency: str, modulo: str, id_hash: int
|
||||
) -> list[models.Sheet]:
|
||||
result = await db.execute(
|
||||
select(models.Sheet).filter(models.Sheet.frequency == frequency)
|
||||
)
|
||||
filtered = []
|
||||
for sheet in result.scalars():
|
||||
if fnv1a_hash_mod(sheet.id, modulo) == id_hash:
|
||||
if fnv1a_hash_mod(sheet.id, int(modulo)) == id_hash:
|
||||
filtered.append(sheet)
|
||||
return filtered
|
||||
|
||||
@@ -257,7 +403,9 @@ async def get_sheets_by_id_hash(db: AsyncSession, frequency: str, modulo: str, i
|
||||
async def delete_stale_sheets(db: AsyncSession, inactivity_days: int) -> dict:
|
||||
time_threshold = datetime.now() - timedelta(days=inactivity_days)
|
||||
result = await db.execute(
|
||||
select(models.Sheet).filter(models.Sheet.last_url_archived_at < time_threshold)
|
||||
select(models.Sheet).filter(
|
||||
models.Sheet.last_url_archived_at < time_threshold
|
||||
)
|
||||
)
|
||||
deleted = defaultdict(list)
|
||||
for sheet in result.scalars():
|
||||
@@ -268,7 +416,11 @@ async def delete_stale_sheets(db: AsyncSession, inactivity_days: int) -> dict:
|
||||
|
||||
|
||||
def delete_sheet(db: Session, sheet_id: str, email: str) -> bool:
|
||||
db_sheet = db.query(models.Sheet).filter(models.Sheet.id == sheet_id, models.Sheet.author_id == email).first()
|
||||
db_sheet = (
|
||||
db.query(models.Sheet)
|
||||
.filter(models.Sheet.id == sheet_id, models.Sheet.author_id == email)
|
||||
.first()
|
||||
)
|
||||
if db_sheet:
|
||||
db.delete(db_sheet)
|
||||
db.commit()
|
||||
|
||||
@@ -1,4 +1,3 @@
|
||||
|
||||
from datetime import datetime
|
||||
from typing import Dict, Set
|
||||
|
||||
@@ -21,14 +20,15 @@ class UserState:
|
||||
def __init__(self, db: Session, email: str):
|
||||
self.db = db
|
||||
self.email = email.lower()
|
||||
self._permissions = {}
|
||||
|
||||
@property
|
||||
def permissions(self) -> Dict[str, GroupInfo]:
|
||||
"""
|
||||
Returns a dict of all group permissions and a special {"all": read/archive_url/archive_sheet} key
|
||||
Returns a dict of all group permissions and a special
|
||||
{"all": read/archive_url/archive_sheet} key
|
||||
"""
|
||||
if not hasattr(self, '_permissions'):
|
||||
self._permissions = {}
|
||||
if not self._permissions:
|
||||
self._permissions["all"] = GroupInfo(
|
||||
read=self.read,
|
||||
read_public=self.read_public,
|
||||
@@ -38,23 +38,33 @@ class UserState:
|
||||
max_archive_lifespan_months=self.max_archive_lifespan_months,
|
||||
max_monthly_urls=self.max_monthly_urls,
|
||||
max_monthly_mbs=self.max_monthly_mbs,
|
||||
priority=self.priority
|
||||
priority=self.priority,
|
||||
)
|
||||
for group in self.user_groups:
|
||||
if not group.permissions: continue
|
||||
self._permissions[group.id] = GroupInfo(**group.permissions, description=group.description, service_account_email=group.service_account_email)
|
||||
if not group.permissions:
|
||||
continue
|
||||
self._permissions[group.id] = GroupInfo(
|
||||
**group.permissions,
|
||||
description=group.description,
|
||||
service_account_email=group.service_account_email,
|
||||
)
|
||||
return self._permissions
|
||||
|
||||
@property
|
||||
def user_groups_names(self):
|
||||
if not hasattr(self, '_user_groups_names'):
|
||||
self._user_groups_names = crud.get_user_group_names(self.db, self.email) + ["default"]
|
||||
if not hasattr(self, "_user_groups_names"):
|
||||
# TODO: Define hidden properties in __init__ method
|
||||
self._user_groups_names = crud.get_user_group_names(
|
||||
self.db, self.email
|
||||
) + ["default"]
|
||||
return self._user_groups_names
|
||||
|
||||
@property
|
||||
def user_groups(self):
|
||||
if not hasattr(self, '_user_groups'):
|
||||
self._user_groups = crud.get_user_groups_by_name(self.db, self.user_groups_names)
|
||||
if not hasattr(self, "_user_groups"):
|
||||
self._user_groups = crud.get_user_groups_by_name(
|
||||
self.db, self.user_groups_names
|
||||
)
|
||||
return self._user_groups
|
||||
|
||||
@property
|
||||
@@ -62,10 +72,11 @@ class UserState:
|
||||
"""
|
||||
Read can be a list of group names or True, if all can be read.
|
||||
"""
|
||||
if not hasattr(self, '_read'):
|
||||
if not hasattr(self, "_read"):
|
||||
self._read = set()
|
||||
for group in self.user_groups:
|
||||
if not group.permissions: continue
|
||||
if not group.permissions:
|
||||
continue
|
||||
group_read_permissions = group.permissions.get("read", [])
|
||||
if "all" in group_read_permissions:
|
||||
self._read = True
|
||||
@@ -79,10 +90,11 @@ class UserState:
|
||||
"""
|
||||
Read public permission
|
||||
"""
|
||||
if not hasattr(self, '_read_public'):
|
||||
if not hasattr(self, "_read_public"):
|
||||
self._read_public = False
|
||||
for group in self.user_groups:
|
||||
if not group.permissions: continue
|
||||
if not group.permissions:
|
||||
continue
|
||||
if group.permissions.get("read_public", False):
|
||||
self._read_public = True
|
||||
return self._read_public
|
||||
@@ -93,10 +105,11 @@ class UserState:
|
||||
"""
|
||||
Archive URL permission
|
||||
"""
|
||||
if not hasattr(self, '_archive_url'):
|
||||
if not hasattr(self, "_archive_url"):
|
||||
self._archive_url = False
|
||||
for group in self.user_groups:
|
||||
if not group.permissions: continue
|
||||
if not group.permissions:
|
||||
continue
|
||||
if group.permissions.get("archive_url", False):
|
||||
self._archive_url = True
|
||||
return self._archive_url
|
||||
@@ -107,10 +120,11 @@ class UserState:
|
||||
"""
|
||||
Archive sheet permission
|
||||
"""
|
||||
if not hasattr(self, '_archive_sheet'):
|
||||
if not hasattr(self, "_archive_sheet"):
|
||||
self._archive_sheet = False
|
||||
for group in self.user_groups:
|
||||
if not group.permissions: continue
|
||||
if not group.permissions:
|
||||
continue
|
||||
if group.permissions.get("archive_sheet", False):
|
||||
self._archive_sheet = True
|
||||
return self._archive_sheet
|
||||
@@ -118,37 +132,53 @@ class UserState:
|
||||
|
||||
@property
|
||||
def sheet_frequency(self):
|
||||
if not hasattr(self, '_sheet_frequency'):
|
||||
if not hasattr(self, "_sheet_frequency"):
|
||||
self._sheet_frequency = set()
|
||||
for group in self.user_groups:
|
||||
if not group.permissions: continue
|
||||
self._sheet_frequency.update(group.permissions.get("sheet_frequency", None))
|
||||
if not group.permissions:
|
||||
continue
|
||||
self._sheet_frequency.update(
|
||||
group.permissions.get("sheet_frequency", None)
|
||||
)
|
||||
return self._sheet_frequency
|
||||
|
||||
@property
|
||||
def max_archive_lifespan_months(self) -> int:
|
||||
if not hasattr(self, '_max_archive_lifespan_months'):
|
||||
self._max_archive_lifespan_months = self._helper_for_grouping_max_numerical_permissions("max_archive_lifespan_months")
|
||||
if not hasattr(self, "_max_archive_lifespan_months"):
|
||||
self._max_archive_lifespan_months = (
|
||||
self._helper_for_grouping_max_numerical_permissions(
|
||||
"max_archive_lifespan_months"
|
||||
)
|
||||
)
|
||||
return self._max_archive_lifespan_months
|
||||
|
||||
@property
|
||||
def max_monthly_urls(self) -> int:
|
||||
if not hasattr(self, '_max_monthly_urls'):
|
||||
self._max_monthly_urls = self._helper_for_grouping_max_numerical_permissions("max_monthly_urls")
|
||||
if not hasattr(self, "_max_monthly_urls"):
|
||||
self._max_monthly_urls = (
|
||||
self._helper_for_grouping_max_numerical_permissions(
|
||||
"max_monthly_urls"
|
||||
)
|
||||
)
|
||||
return self._max_monthly_urls
|
||||
|
||||
@property
|
||||
def max_monthly_mbs(self) -> int:
|
||||
if not hasattr(self, '_max_monthly_mbs'):
|
||||
self._max_monthly_mbs = self._helper_for_grouping_max_numerical_permissions("max_monthly_mbs")
|
||||
if not hasattr(self, "_max_monthly_mbs"):
|
||||
self._max_monthly_mbs = (
|
||||
self._helper_for_grouping_max_numerical_permissions(
|
||||
"max_monthly_mbs"
|
||||
)
|
||||
)
|
||||
return self._max_monthly_mbs
|
||||
|
||||
@property
|
||||
def priority(self) -> str:
|
||||
if not hasattr(self, '_priority'):
|
||||
if not hasattr(self, "_priority"):
|
||||
self._priority = "low"
|
||||
for group in self.user_groups:
|
||||
if not group.permissions: continue
|
||||
if not group.permissions:
|
||||
continue
|
||||
if group.permissions.get("priority", self._priority) == "high":
|
||||
self._priority = "high"
|
||||
break
|
||||
@@ -159,18 +189,28 @@ class UserState:
|
||||
"""
|
||||
A user is active if they can read/archive anything
|
||||
"""
|
||||
if not hasattr(self, '_active'):
|
||||
self._active = bool(self.read or self.read_public or self.archive_url or self.archive_sheet)
|
||||
if not hasattr(self, "_active"):
|
||||
self._active = bool(
|
||||
self.read
|
||||
or self.read_public
|
||||
or self.archive_url
|
||||
or self.archive_sheet
|
||||
)
|
||||
return self._active
|
||||
|
||||
def _helper_for_grouping_max_numerical_permissions(self, permission_name: str) -> int:
|
||||
def _helper_for_grouping_max_numerical_permissions(
|
||||
self, permission_name: str
|
||||
) -> int:
|
||||
"""
|
||||
Iterates one of the numerical permissions where -1 means no restrictions and returns either -1 or the maximum value, defaults according to GroupPermissions
|
||||
Iterates one of the numerical permissions where -1 means no restrictions
|
||||
and returns either -1 or the maximum value, defaults according to
|
||||
GroupPermissions
|
||||
"""
|
||||
default = GroupPermissions.model_fields[permission_name].default
|
||||
max_value = default
|
||||
for group in self.user_groups:
|
||||
if not group.permissions: continue
|
||||
if not group.permissions:
|
||||
continue
|
||||
group_value = group.permissions.get(permission_name, default)
|
||||
if group_value == -1:
|
||||
max_value = -1
|
||||
@@ -181,43 +221,65 @@ class UserState:
|
||||
def in_group(self, group_id: str) -> bool:
|
||||
return group_id in self.user_groups_names
|
||||
|
||||
def usage(self) -> Dict:
|
||||
def usage(self) -> UsageResponse:
|
||||
"""
|
||||
returns the monthly quotas for the URLs/MBs and the totals for Sheets
|
||||
Returns the monthly quotas for the URLs/MBs and the totals for Sheets
|
||||
"""
|
||||
current_month = datetime.now().month
|
||||
current_year = datetime.now().year
|
||||
|
||||
# find and sum all user sheets over this month
|
||||
user_sheets = self.db.query(
|
||||
models.Sheet.group_id,
|
||||
func.count(models.Sheet.id).label('sheet_count')
|
||||
).filter(models.Sheet.author_id == self.email).group_by(models.Sheet.group_id).all()
|
||||
user_sheets = (
|
||||
self.db.query(
|
||||
models.Sheet.group_id,
|
||||
func.count(models.Sheet.id).label("sheet_count"),
|
||||
)
|
||||
.filter(models.Sheet.author_id == self.email)
|
||||
.group_by(models.Sheet.group_id)
|
||||
.all()
|
||||
)
|
||||
|
||||
sheets_by_group = {sheet.group_id: sheet.sheet_count for sheet in user_sheets}
|
||||
sheets_by_group = {
|
||||
sheet.group_id: sheet.sheet_count for sheet in user_sheets
|
||||
}
|
||||
|
||||
# find and sum all user urls over this month
|
||||
urls_by_group = self.db.query(
|
||||
models.Archive.group_id,
|
||||
func.count(models.Archive.id).label('url_count'),
|
||||
func.coalesce(func.sum(
|
||||
urls_by_group = (
|
||||
self.db.query(
|
||||
models.Archive.group_id,
|
||||
func.count(models.Archive.id).label("url_count"),
|
||||
func.coalesce(
|
||||
func.cast(
|
||||
func.json_extract(models.Archive.result, '$.metadata.total_bytes'),
|
||||
sqlalchemy.Integer
|
||||
), 0
|
||||
)
|
||||
), 0).label('total_bytes')
|
||||
).filter(
|
||||
models.Archive.author_id == self.email,
|
||||
func.extract('month', models.Archive.created_at) == current_month,
|
||||
func.extract('year', models.Archive.created_at) == current_year
|
||||
).group_by(models.Archive.group_id).all()
|
||||
func.sum(
|
||||
func.coalesce(
|
||||
func.cast(
|
||||
func.json_extract(
|
||||
models.Archive.result,
|
||||
"$.metadata.total_bytes",
|
||||
),
|
||||
sqlalchemy.Integer,
|
||||
),
|
||||
0,
|
||||
)
|
||||
),
|
||||
0,
|
||||
).label("total_bytes"),
|
||||
)
|
||||
.filter(
|
||||
models.Archive.author_id == self.email,
|
||||
func.extract("month", models.Archive.created_at)
|
||||
== current_month,
|
||||
func.extract("year", models.Archive.created_at) == current_year,
|
||||
)
|
||||
.group_by(models.Archive.group_id)
|
||||
.all()
|
||||
)
|
||||
|
||||
# merge the two queries
|
||||
usage_by_group: Dict[str, Usage] = {
|
||||
(url.group_id or ""):
|
||||
Usage(monthly_urls=url.url_count, monthly_mbs=int(url.total_bytes / 1024 / 1024))
|
||||
(url.group_id or ""): Usage(
|
||||
monthly_urls=url.url_count,
|
||||
monthly_mbs=int(url.total_bytes / 1024 / 1024),
|
||||
)
|
||||
for url in urls_by_group
|
||||
}
|
||||
for group_id, sheet_count in sheets_by_group.items():
|
||||
@@ -236,7 +298,7 @@ class UserState:
|
||||
monthly_urls=total_urls,
|
||||
monthly_mbs=int(total_bytes / 1024 / 1024),
|
||||
total_sheets=total_sheets,
|
||||
groups=usage_by_group
|
||||
groups=usage_by_group,
|
||||
)
|
||||
|
||||
def has_quota_monthly_sheets(self, group_id: str) -> bool:
|
||||
@@ -246,7 +308,14 @@ class UserState:
|
||||
if group_id not in self.permissions:
|
||||
return False
|
||||
|
||||
user_sheets = self.db.query(models.Sheet).filter(models.Sheet.author_id == self.email, models.Sheet.group_id == group_id).count()
|
||||
user_sheets = (
|
||||
self.db.query(models.Sheet)
|
||||
.filter(
|
||||
models.Sheet.author_id == self.email,
|
||||
models.Sheet.group_id == group_id,
|
||||
)
|
||||
.count()
|
||||
)
|
||||
|
||||
sheet_quota = self.permissions[group_id].max_sheets
|
||||
if sheet_quota == -1:
|
||||
@@ -255,13 +324,15 @@ class UserState:
|
||||
|
||||
def has_quota_max_monthly_urls(self, group_id: str) -> bool:
|
||||
"""
|
||||
checks if a user has reached their monthly url quota for a group, if global then group should be empty string
|
||||
Checks if a user has reached their monthly url quota for a group, if
|
||||
global then group should be empty string
|
||||
"""
|
||||
quota = 0
|
||||
if not group_id:
|
||||
quota = self.max_monthly_urls
|
||||
else:
|
||||
if group_id not in self.permissions: return False
|
||||
if group_id not in self.permissions:
|
||||
return False
|
||||
quota = self.permissions[group_id].max_monthly_urls
|
||||
|
||||
if quota == -1:
|
||||
@@ -269,24 +340,31 @@ class UserState:
|
||||
|
||||
current_month = datetime.now().month
|
||||
current_year = datetime.now().year
|
||||
user_urls = self.db.query(models.Archive).filter(
|
||||
models.Archive.author_id == self.email,
|
||||
models.Archive.group_id == group_id,
|
||||
func.extract('month', models.Archive.created_at) == current_month,
|
||||
func.extract('year', models.Archive.created_at) == current_year
|
||||
).count()
|
||||
user_urls = (
|
||||
self.db.query(models.Archive)
|
||||
.filter(
|
||||
models.Archive.author_id == self.email,
|
||||
models.Archive.group_id == group_id,
|
||||
func.extract("month", models.Archive.created_at)
|
||||
== current_month,
|
||||
func.extract("year", models.Archive.created_at) == current_year,
|
||||
)
|
||||
.count()
|
||||
)
|
||||
|
||||
return user_urls < quota
|
||||
|
||||
def has_quota_max_monthly_mbs(self, group_id: str) -> bool:
|
||||
"""
|
||||
checks if a user has reached their monthly MBs quota for a group, if global then group should be empty string
|
||||
Checks if a user has reached their monthly MBs quota for a group, if
|
||||
global then group should be empty string
|
||||
"""
|
||||
quota = 0
|
||||
if not group_id:
|
||||
quota = self.max_monthly_mbs
|
||||
else:
|
||||
if group_id not in self.permissions: return False
|
||||
if group_id not in self.permissions:
|
||||
return False
|
||||
quota = self.permissions[group_id].max_monthly_mbs
|
||||
|
||||
if quota == -1:
|
||||
@@ -296,19 +374,34 @@ class UserState:
|
||||
current_year = datetime.now().year
|
||||
|
||||
# find and sum all user bytes over this month
|
||||
user_bytes = self.db.query(models.Archive).filter(
|
||||
models.Archive.author_id == self.email,
|
||||
models.Archive.group_id == group_id,
|
||||
func.extract('month', models.Archive.created_at) == current_month,
|
||||
func.extract('year', models.Archive.created_at) == current_year
|
||||
).with_entities(func.coalesce(func.sum(
|
||||
func.coalesce(
|
||||
func.cast(
|
||||
func.json_extract(models.Archive.result, '$.metadata.total_bytes'),
|
||||
sqlalchemy.Integer
|
||||
), 0
|
||||
user_bytes = (
|
||||
self.db.query(models.Archive)
|
||||
.filter(
|
||||
models.Archive.author_id == self.email,
|
||||
models.Archive.group_id == group_id,
|
||||
func.extract("month", models.Archive.created_at)
|
||||
== current_month,
|
||||
func.extract("year", models.Archive.created_at) == current_year,
|
||||
)
|
||||
), 0).label('total')).scalar()
|
||||
.with_entities(
|
||||
func.coalesce(
|
||||
func.sum(
|
||||
func.coalesce(
|
||||
func.cast(
|
||||
func.json_extract(
|
||||
models.Archive.result,
|
||||
"$.metadata.total_bytes",
|
||||
),
|
||||
sqlalchemy.Integer,
|
||||
),
|
||||
0,
|
||||
)
|
||||
),
|
||||
0,
|
||||
).label("total")
|
||||
)
|
||||
.scalar()
|
||||
)
|
||||
|
||||
# convert bytes to mb
|
||||
user_mbs = int(user_bytes / 1024 / 1024)
|
||||
@@ -316,7 +409,7 @@ class UserState:
|
||||
|
||||
def can_manually_trigger(self, group_id: str) -> bool:
|
||||
"""
|
||||
checks if a user is allowed to manually trigger a sheet
|
||||
Checks if a user is allowed to manually trigger a sheet
|
||||
"""
|
||||
if group_id not in self.permissions:
|
||||
return False
|
||||
@@ -325,18 +418,21 @@ class UserState:
|
||||
|
||||
def is_sheet_frequency_allowed(self, group_id: str, frequency: str) -> bool:
|
||||
"""
|
||||
checks if a user is allowed to create a sheet with this frequency for this group
|
||||
Checks if a user is allowed to create a sheet with this frequency for
|
||||
this group
|
||||
"""
|
||||
if group_id not in self.permissions:
|
||||
return False
|
||||
|
||||
return frequency in self.permissions[group_id].sheet_frequency
|
||||
|
||||
def priority_group(self, group_id: str) -> str:
|
||||
def priority_group(self, group_id: str) -> dict:
|
||||
priority = "low"
|
||||
for group in self.user_groups:
|
||||
if group.id != group_id: continue
|
||||
if not group.permissions: continue
|
||||
if group.id != group_id:
|
||||
continue
|
||||
if not group.permissions:
|
||||
continue
|
||||
priority = group.permissions.get("priority", priority)
|
||||
break
|
||||
return convert_priority_to_queue_dict(priority)
|
||||
|
||||
Reference in New Issue
Block a user