Index authorized mailbox cache changes in Search

This commit is contained in:
2026-08-04 03:03:26 +02:00
parent 7844d9cab4
commit 72d6f8432c
5 changed files with 559 additions and 2 deletions
+292
View File
@@ -0,0 +1,292 @@
from __future__ import annotations
from collections.abc import Mapping, Sequence
from urllib.parse import quote
from sqlalchemy import func, select
from sqlalchemy.orm import Session
from govoplan_core.auth import ApiPrincipal
from govoplan_core.core.events import PlatformEvent
from govoplan_core.core.modules import ModuleContext
from govoplan_core.core.search import (
SearchAuthorizationRequest,
SearchBackfillPage,
SearchBackfillRequest,
SearchDocument,
SearchIndexChange,
SearchResourceReference,
SearchResourceType,
)
from govoplan_mail.backend.db.models import (
MailMailboxMessageIndex,
MailServerProfile,
)
from govoplan_mail.backend.mail_profiles import mail_profile_visible_to_actor
PROVIDER_ID = "mail.mailbox_messages"
RESOURCE_TYPE = "mailbox_message"
READ_SCOPE = "mail:mailbox:read"
USE_SCOPE = "mail:profile:use"
class MailSearchSource:
def resource_types(self) -> Sequence[SearchResourceType]:
return (
SearchResourceType(
provider_id=PROVIDER_ID,
module_id="mail",
resource_type=RESOURCE_TYPE,
label="Mailbox messages",
requires_authorization_recheck=True,
),
)
def backfill(
self,
session: object,
*,
request: SearchBackfillRequest,
) -> SearchBackfillPage:
_assert_source(request.provider_id, request.resource_type)
db = _session(session)
statement = (
select(MailMailboxMessageIndex, MailServerProfile)
.join(
MailServerProfile,
MailServerProfile.id == MailMailboxMessageIndex.profile_id,
)
.where(MailMailboxMessageIndex.tenant_id == request.tenant_id)
)
if request.cursor:
statement = statement.where(
MailMailboxMessageIndex.id > request.cursor
)
rows = list(
db.execute(
statement.order_by(MailMailboxMessageIndex.id).limit(
request.limit + 1
)
).all()
)
has_more = len(rows) > request.limit
selected = rows[: request.limit]
high_watermark = db.scalar(
select(func.max(MailMailboxMessageIndex.indexed_at)).where(
MailMailboxMessageIndex.tenant_id == request.tenant_id
)
)
return SearchBackfillPage(
documents=tuple(
_document(message, profile=profile)
for message, profile in selected
),
next_cursor=(
selected[-1][0].id if has_more and selected else None
),
complete=not has_more,
high_watermark=(
high_watermark.isoformat()
if high_watermark is not None
else None
),
)
def authorize(
self,
session: object,
principal: object,
*,
requests: Sequence[SearchAuthorizationRequest],
) -> Mapping[str, bool]:
decisions = {item.reference.key: False for item in requests}
if not isinstance(principal, ApiPrincipal) or not (
principal.has(READ_SCOPE) and principal.has(USE_SCOPE)
):
return decisions
valid = tuple(
item
for item in requests
if item.reference.tenant_id == principal.tenant_id
and item.reference.module_id == "mail"
and item.reference.resource_type == RESOURCE_TYPE
)
if not valid:
return decisions
db = _session(session)
ids = {item.reference.resource_id for item in valid}
messages = {
message.id: (message, profile)
for message, profile in db.execute(
select(MailMailboxMessageIndex, MailServerProfile)
.join(
MailServerProfile,
MailServerProfile.id
== MailMailboxMessageIndex.profile_id,
)
.where(
MailMailboxMessageIndex.id.in_(ids),
MailMailboxMessageIndex.tenant_id == principal.tenant_id,
)
).all()
}
user_id = str(
getattr(principal.user, "id", "") or principal.membership_id or ""
)
for item in valid:
match = messages.get(item.reference.resource_id)
if match is None:
continue
_message, profile = match
try:
allowed = mail_profile_visible_to_actor(
db,
profile=profile,
tenant_id=principal.tenant_id,
user_id=user_id,
group_ids=principal.group_ids,
tenant_admin=principal.has("tenant:*"),
require_active=True,
)
except (RuntimeError, ValueError):
allowed = False
decisions[item.reference.key] = allowed
return decisions
def index_changes_for_event(
self,
session: object,
*,
event: PlatformEvent,
delivery_key: str,
) -> Sequence[SearchIndexChange]:
if (
event.module_id != "mail"
or event.tenant is None
or event.resource is None
or event.resource.type != RESOURCE_TYPE
or event.resource.id is None
):
return ()
db = _session(session)
row = db.get(MailMailboxMessageIndex, event.resource.id)
profile = (
db.get(MailServerProfile, row.profile_id)
if row is not None and row.tenant_id == event.tenant.id
else None
)
deleted = (
row is None
or row.tenant_id != event.tenant.id
or profile is None
)
cursor = event.event_id
document = (
None
if deleted
else _document(row, profile=profile, change_cursor=cursor)
)
reference = SearchResourceReference(
tenant_id=event.tenant.id,
module_id="mail",
resource_type=RESOURCE_TYPE,
resource_id=event.resource.id,
)
return (
SearchIndexChange(
change_id=f"{delivery_key}:{PROVIDER_ID}",
provider_id=PROVIDER_ID,
kind="delete" if deleted else "upsert",
reference=reference,
source_revision=(
document.source_revision if document is not None else cursor
),
cursor=cursor,
document=document,
occurred_at=event.occurred_at,
),
)
def create_mail_search_source(_context: ModuleContext) -> MailSearchSource:
return MailSearchSource()
def _document(
message: MailMailboxMessageIndex,
*,
profile: MailServerProfile,
change_cursor: str | None = None,
) -> SearchDocument:
tokens = [f"scope:{READ_SCOPE}", f"scope:{USE_SCOPE}"]
scope_type = str(profile.scope_type or "tenant")
if scope_type == "user" and profile.scope_id:
tokens.append(f"membership:{profile.scope_id}")
elif scope_type == "group" and profile.scope_id:
tokens.append(f"group:{profile.scope_id}")
title = (message.subject or "(No subject)")[:500]
summary = " | ".join(
value for value in (message.from_header, message.date) if value
)[:4000]
body = " ".join(
value
for value in (
message.from_header,
message.to_header,
message.cc_header,
message.body_preview,
)
if value
)[:200_000]
updated_at = message.updated_at or message.indexed_at
return SearchDocument(
tenant_id=message.tenant_id,
module_id="mail",
provider_id=PROVIDER_ID,
resource_type=RESOURCE_TYPE,
resource_id=message.id,
title=title,
url=(
"/mail?"
f"profileId={quote(message.profile_id, safe='')}"
f"&folder={quote(message.folder, safe='')}"
f"&uid={quote(message.uid, safe='')}"
),
summary=summary or None,
body=body or None,
keywords=(message.folder[:200], profile.name[:200]),
visibility="restricted",
acl_tokens=tuple(dict.fromkeys(tokens)),
metadata={
"profile_id": message.profile_id,
"profile_name": profile.name,
"folder": message.folder,
"uid": message.uid,
"date": message.date,
"attachment_count": message.attachment_count,
},
source_revision=updated_at.isoformat(),
change_cursor=change_cursor,
source_updated_at=updated_at,
requires_authorization_recheck=True,
)
def _assert_source(provider_id: str, resource_type: str) -> None:
if provider_id != PROVIDER_ID or resource_type != RESOURCE_TYPE:
raise ValueError("Unsupported Mail search source.")
def _session(value: object) -> Session:
if not isinstance(value, Session):
raise TypeError("Mail search requires a SQLAlchemy session.")
return value
__all__ = [
"MailSearchSource",
"PROVIDER_ID",
"RESOURCE_TYPE",
"create_mail_search_source",
]