busya/ss-tools
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

032: fix final sync→async cascade (dataset_review, parsing, validation)

Browse Source 
- _parsing.py: parse_superset_link + _recover_dataset_binding → async
    (await get_dashboard_detail, get_chart)
  - dataset_review/orchestrator.py: start_session + _build_recovery_bootstrap → async
    (await get_dataset_detail, parse_superset_link)
  - _routes.py (dataset_review): await orchestrator.start_session()
  - validation_tasks.py: await parse_superset_link + get_dashboard_detail
This commit is contained in:
busya
2026-06-05 09:55:34 +03:00
parent c7d8f4431e
commit 4247e7a20e
4 changed files with 15 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
backend/src/api/routes/dataset_review_pkg/_routes.py
View File

@@ -161,7 +161,7 @@ async def start_session(
},
)
try:
result = orchestrator.start_session(
result = await orchestrator.start_session(
StartSessionCommand(
user=current_user,
environment_id=request.environment_id,

4
backend/src/api/routes/validation_tasks.py
View File

@@ -412,7 +412,7 @@ async def parse_superset_url(
from ...core.utils.superset_context_extractor import SupersetContextExtractor
extractor = SupersetContextExtractor(environment=env)
parsed = extractor.parse_superset_link(payload.url)
parsed = await extractor.parse_superset_link(payload.url)
dashboard_id = str(parsed.dashboard_id) if parsed.dashboard_id is not None else None
title: str | None = None
@@ -420,7 +420,7 @@ async def parse_superset_url(
# Resolve dashboard title from Superset API when possible
if parsed.dashboard_id:
try:
dashboard = extractor.client.get_dashboard_detail(parsed.dashboard_id)
dashboard = await extractor.client.get_dashboard_detail(parsed.dashboard_id)
title = dashboard.get("dashboard_title", str(parsed.dashboard_id))
except Exception:
title = str(parsed.dashboard_id)

12
backend/src/core/utils/superset_context_extractor/_parsing.py
View File

@@ -25,7 +25,7 @@ class SupersetContextParsingMixin:
# @POST returns resolved dataset/dashboard context, preserving explicit partial-recovery state if some identifiers cannot be confirmed.
# @SIDE_EFFECT may issue Superset API reads to resolve dataset references from dashboard or chart URLs.
# @DATA_CONTRACT Input[link:str] -> Output[SupersetParsedContext]
def parse_superset_link(self, link: str) -> SupersetParsedContext:
async def parse_superset_link(self, link: str) -> SupersetParsedContext:
with belief_scope("SupersetContextExtractor.parse_superset_link"):
normalized_link = str(link or "").strip()
if not normalized_link:
@@ -106,7 +106,7 @@ class SupersetContextParsingMixin:
!= "dashboard_permalink_dataset_binding_unresolved"
]
dataset_id, unresolved_references = (
self._recover_dataset_binding_from_dashboard(
await self._recover_dataset_binding_from_dashboard(
dashboard_id=dashboard_id,
dataset_ref=dataset_ref,
unresolved_references=unresolved_references,
@@ -123,7 +123,7 @@ class SupersetContextParsingMixin:
!= "dashboard_permalink_dataset_binding_unresolved"
]
try:
chart_payload = self.client.get_chart(chart_id)
chart_payload = await self.client.get_chart(chart_id)
chart_data = (
chart_payload.get("result", chart_payload)
if isinstance(chart_payload, dict)
@@ -170,7 +170,7 @@ class SupersetContextParsingMixin:
)
# Resolve dashboard detail first — handles both numeric ID and slug,
# ensuring dashboard_id is available for the native_filters_key fetch below.
dashboard_detail = self.client.get_dashboard_detail(
dashboard_detail = await self.client.get_dashboard_detail(
resolved_dashboard_ref
)
resolved_dashboard_id = dashboard_detail.get("id")
@@ -317,13 +317,13 @@ class SupersetContextParsingMixin:
# #region SupersetContextParsingMixin._recover_dataset_binding_from_dashboard [TYPE Function] [C:3]
# @PURPOSE: Recover a dataset binding from resolved dashboard context while preserving explicit unresolved markers.
# @RELATION CALLS -> [EXT:method:SupersetClient.get_dashboard_detail]
def _recover_dataset_binding_from_dashboard(
async def _recover_dataset_binding_from_dashboard(
self,
dashboard_id: int,
dataset_ref: str | None,
unresolved_references: list[str],
) -> tuple[int | None, list[str]]:
dashboard_detail = self.client.get_dashboard_detail(dashboard_id)
dashboard_detail = await self.client.get_dashboard_detail(dashboard_id)
datasets = dashboard_detail.get("datasets") or []
if datasets:
first_dataset = datasets[0]

12
backend/src/services/dataset_review/orchestrator.py
View File

@@ -123,7 +123,7 @@ class DatasetReviewOrchestrator:
# @SIDE_EFFECT persists session and may enqueue recovery task.
# @DATA_CONTRACT Input[StartSessionCommand] -> Output[StartSessionResult]
# @INVARIANT no cross-user session leakage occurs; session and follow-up task remain owned by the authenticated user.
def start_session(self, command: StartSessionCommand) -> StartSessionResult:
async def start_session(self, command: StartSessionCommand) -> StartSessionResult:
with belief_scope("DatasetReviewOrchestrator.start_session"):
normalized_source_kind = str(command.source_kind or "").strip()
normalized_source_input = str(command.source_input or "").strip()
@@ -155,7 +155,7 @@ class DatasetReviewOrchestrator:
if normalized_source_kind == "superset_link":
extractor = SupersetContextExtractor(environment)
parsed_context = extractor.parse_superset_link(normalized_source_input)
parsed_context = await extractor.parse_superset_link(normalized_source_input)
dataset_ref = parsed_context.dataset_ref
dataset_id = parsed_context.dataset_id
dashboard_id = parsed_context.dashboard_id
@@ -190,8 +190,8 @@ class DatasetReviewOrchestrator:
template_variables: list[TemplateVariable] = []
execution_mappings: list[ExecutionMapping] = []
if normalized_source_kind == "superset_link" and parsed_context is not None:
recovered_filters, template_variables, execution_mappings, findings = (
self._build_recovery_bootstrap(
recovered_filters, template_variables, execution_mappings, findings = (
await self._build_recovery_bootstrap(
environment=environment,
session=persisted_session,
parsed_context=parsed_context,
@@ -451,7 +451,7 @@ class DatasetReviewOrchestrator:
# @PRE session belongs to the just-created review aggregate and parsed_context was produced for the same environment scope.
# @POST Returns bootstrap imported filters, template variables, execution mappings, and updated findings without persisting them directly.
# @SIDE_EFFECT Performs Superset reads through the extractor and may append warning findings for incomplete recovery.
def _build_recovery_bootstrap(
async def _build_recovery_bootstrap(
self,
environment,
session: DatasetReviewSession,
@@ -487,7 +487,7 @@ class DatasetReviewOrchestrator:
try:
dataset_payload = parsed_context.dataset_payload
if not isinstance(dataset_payload, dict):
dataset_payload = extractor.client.get_dataset_detail(session_record.dataset_id)
dataset_payload = await extractor.client.get_dataset_detail(session_record.dataset_id)
discovered_variables = extractor.discover_template_variables(dataset_payload)
template_variables = [
TemplateVariable(