Files
govoplan-docs/src/govoplan_docs/backend/search_source.py
T
zemion cbe434de02
Module Package Release / publish-packages (push) Successful in 12s
Release govoplan-docs v0.1.23: unify help discovery and batch semantic reads
2026-09-08 01:32:36 +02:00

297 lines
10 KiB
Python

from __future__ import annotations
from collections.abc import Mapping, Sequence
from urllib.parse import quote
from sqlalchemy import and_, 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_docs.backend.db.models import (
SemanticDocumentationEntry,
SemanticDocumentationRevision,
)
from govoplan_docs.backend.semantic_service import (
prefetch_semantic_revisions,
published_revision,
semantic_entry_payload,
)
PROVIDER_ID = "docs.semantic_documentation"
RESOURCE_TYPE = "semantic_documentation"
DOCS_READ_SCOPE = "docs:documentation:read"
class SemanticDocumentationSearchSource:
def __init__(self, registry: object) -> None:
self._registry = registry
def resource_types(self) -> Sequence[SearchResourceType]:
return (
SearchResourceType(
provider_id=PROVIDER_ID,
module_id="docs",
resource_type=RESOURCE_TYPE,
label="Semantic documentation",
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(SemanticDocumentationEntry, SemanticDocumentationRevision)
.join(
SemanticDocumentationRevision,
and_(
SemanticDocumentationRevision.id == SemanticDocumentationEntry.published_revision_id,
SemanticDocumentationRevision.entry_id == SemanticDocumentationEntry.id,
SemanticDocumentationRevision.tenant_id == SemanticDocumentationEntry.tenant_id,
SemanticDocumentationRevision.lifecycle_state == "published",
),
)
.where(
SemanticDocumentationEntry.tenant_id == request.tenant_id,
SemanticDocumentationEntry.lifecycle_state.in_(("draft", "published")),
)
)
if request.cursor:
statement = statement.where(
SemanticDocumentationEntry.id > request.cursor
)
rows = list(
db.execute(
statement.order_by(SemanticDocumentationEntry.id).limit(
request.limit + 1
)
).all()
)
has_more = len(rows) > request.limit
selected = rows[: request.limit]
high_watermark = db.scalar(
select(func.max(SemanticDocumentationEntry.updated_at)).where(
SemanticDocumentationEntry.tenant_id == request.tenant_id,
SemanticDocumentationEntry.published_revision_id.is_not(None),
)
)
return SearchBackfillPage(
documents=tuple(_document(entry, revision) for entry, revision 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(DOCS_READ_SCOPE):
return decisions
db = _session(session)
valid_requests = [
item
for item in requests
if (
item.reference.tenant_id == principal.tenant_id
and item.reference.module_id == "docs"
and item.reference.resource_type == RESOURCE_TYPE
)
]
ids = sorted({item.reference.resource_id for item in valid_requests})
entries: dict[str, SemanticDocumentationEntry] = {}
for offset in range(0, len(ids), 400):
rows = db.scalars(
select(SemanticDocumentationEntry).where(
SemanticDocumentationEntry.id.in_(ids[offset:offset + 400]),
SemanticDocumentationEntry.tenant_id == principal.tenant_id,
SemanticDocumentationEntry.lifecycle_state.in_(("draft", "published")),
)
)
entries.update((entry.id, entry) for entry in rows)
revisions = prefetch_semantic_revisions(
db, principal, entries=tuple(entries.values()), editor=False,
)
for item in valid_requests:
reference = item.reference
entry = entries.get(reference.resource_id)
if (
entry is None
or entry.tenant_id != principal.tenant_id
or entry.published_revision_id != item.source_revision
or entry.lifecycle_state not in {"draft", "published"}
):
continue
payload = semantic_entry_payload(
db,
self._registry,
principal,
entry=entry,
editor=False,
revisions=revisions,
)
decisions[reference.key] = bool(
payload
and payload["subject_resolution"]["availability"]
in {"available", "changed"}
)
return decisions
def index_changes_for_event(
self,
session: object,
*,
event: PlatformEvent,
delivery_key: str,
) -> Sequence[SearchIndexChange]:
if (
event.module_id != "docs"
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)
entry = db.get(SemanticDocumentationEntry, event.resource.id)
revision = (
published_revision(db, entry)
if (
entry is not None
and entry.tenant_id == event.tenant.id
and entry.lifecycle_state in {"draft", "published"}
)
else None
)
visible = bool(
entry is not None
and entry.tenant_id == event.tenant.id
and entry.lifecycle_state in {"draft", "published"}
and revision is not None
and revision.entry_id == entry.id
and revision.tenant_id == entry.tenant_id
and revision.lifecycle_state == "published"
)
cursor = event.event_id
document = _document(entry, revision, change_cursor=cursor) if visible else None
reference = SearchResourceReference(
tenant_id=event.tenant.id,
module_id="docs",
resource_type=RESOURCE_TYPE,
resource_id=event.resource.id,
)
return (
SearchIndexChange(
change_id=f"{delivery_key}:{PROVIDER_ID}",
provider_id=PROVIDER_ID,
kind="upsert" if document is not None else "delete",
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_semantic_documentation_search_source(
context: ModuleContext,
) -> SemanticDocumentationSearchSource:
return SemanticDocumentationSearchSource(context.registry)
def _document(
entry: SemanticDocumentationEntry,
revision: SemanticDocumentationRevision,
*,
change_cursor: str | None = None,
) -> SearchDocument:
content = revision.content
title = str(content.get("title") or "Semantic documentation")
summary = str(content.get("summary") or "")[:4000] or None
keywords = tuple(
str(value)[:200]
for value in (
entry.subject_module_id,
entry.subject_kind,
entry.locale,
"semantic documentation",
)
)
return SearchDocument(
tenant_id=entry.tenant_id,
module_id="docs",
provider_id=PROVIDER_ID,
resource_type=RESOURCE_TYPE,
resource_id=entry.id,
title=title,
url=(
f"/docs/semantic?entryId={quote(entry.id, safe='')}"
f"&locale={quote(entry.locale, safe='')}"
),
summary=summary,
body=revision.search_text[:200_000] or None,
keywords=keywords,
visibility="restricted",
acl_tokens=(f"scope:{DOCS_READ_SCOPE}",),
metadata={
"source_badge": "tenant_semantic",
"subject_module_id": entry.subject_module_id,
"subject_kind": entry.subject_kind,
"subject_id": entry.subject_id,
"anchor_kind": entry.anchor_kind,
"anchor_id": entry.anchor_id,
"locale": entry.locale,
"classification": content.get("classification", "internal"),
},
source_revision=revision.id,
change_cursor=change_cursor,
source_updated_at=entry.updated_at or entry.created_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 Docs search source.")
def _session(value: object) -> Session:
if not isinstance(value, Session):
raise TypeError("Semantic documentation search requires a SQLAlchemy session.")
return value
__all__ = [
"PROVIDER_ID",
"RESOURCE_TYPE",
"SemanticDocumentationSearchSource",
"create_semantic_documentation_search_source",
]