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

semantics

Browse Source
This commit is contained in:
busya
2026-03-20 20:01:58 +03:00
parent 1149e8df1d
commit 80ce8fe150
12 changed files with 1734 additions and 6577 deletions
Download Patch File Download Diff File Expand all files Collapse all files

310
backend/src/core/utils/superset_context_extractor.py
View File

@@ -3,7 +3,7 @@
# @SEMANTICS: dataset_review, superset, link_parsing, context_recovery, partial_recovery
# @PURPOSE: Recover dataset and dashboard context from Superset links while preserving explicit partial-recovery markers.
# @LAYER: Infra
# @RELATION: [CALLS] ->[backend.src.core.superset_client.SupersetClient:Class]
# @RELATION: [DEPENDS_ON] ->[ImportedFilter]
# @RELATION: [DEPENDS_ON] ->[ImportedFilter]
# @RELATION: [DEPENDS_ON] ->[TemplateVariable]
# @PRE: Superset link or dataset reference must be parseable enough to resolve an environment-scoped target resource.
@@ -18,7 +18,7 @@ import json
import re
from copy import deepcopy
from dataclasses import dataclass, field
from typing import Any, Dict, List, Optional, Set
from typing import Any, Dict, List, Optional, Set, cast
from urllib.parse import parse_qs, unquote, urlparse
from src.core.config_models import Environment
@@ -26,6 +26,8 @@ from src.core.logger import belief_scope, logger
from src.core.superset_client import SupersetClient
# [/DEF:SupersetContextExtractor.imports:Block]
logger = cast(Any, logger)
# [DEF:SupersetParsedContext:Class]
# @COMPLEXITY: 2
@@ -42,13 +44,15 @@ class SupersetParsedContext:
imported_filters: List[Dict[str, Any]] = field(default_factory=list)
unresolved_references: List[str] = field(default_factory=list)
partial_recovery: bool = False
# [/DEF:SupersetParsedContext:Class]
# [DEF:SupersetContextExtractor:Class]
# @COMPLEXITY: 4
# @PURPOSE: Parse supported Superset URLs and recover canonical dataset/dashboard references for review-session intake.
# @RELATION: [CALLS] ->[backend.src.core.superset_client.SupersetClient]
# @RELATION: [DEPENDS_ON] ->[Environment]
# @PRE: constructor receives a configured environment with a usable Superset base URL.
# @POST: extractor instance is ready to parse links against one Superset environment.
# @SIDE_EFFECT: downstream parse operations may call Superset APIs through SupersetClient.
@@ -56,15 +60,18 @@ class SupersetContextExtractor:
# [DEF:SupersetContextExtractor.__init__:Function]
# @COMPLEXITY: 2
# @PURPOSE: Bind extractor to one Superset environment and client instance.
def __init__(self, environment: Environment, client: Optional[SupersetClient] = None) -> None:
def __init__(
self, environment: Environment, client: Optional[SupersetClient] = None
) -> None:
self.environment = environment
self.client = client or SupersetClient(environment)
# [/DEF:SupersetContextExtractor.__init__:Function]
# [DEF:SupersetContextExtractor.parse_superset_link:Function]
# @COMPLEXITY: 4
# @PURPOSE: Extract candidate identifiers and query state from supported Superset URLs.
# @RELATION: [CALLS] ->[backend.src.core.superset_client.SupersetClient]
# @RELATION: [CALLS] ->[SupersetClient.get_dashboard_detail]
# @PRE: link is a non-empty Superset URL compatible with the configured environment.
# @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.
@@ -115,12 +122,16 @@ class SupersetContextExtractor:
resource_type = "dashboard"
partial_recovery = True
dataset_ref = f"dashboard_permalink:{dashboard_permalink_key}"
unresolved_references.append("dashboard_permalink_dataset_binding_unresolved")
unresolved_references.append(
"dashboard_permalink_dataset_binding_unresolved"
)
logger.reason(
"Resolving dashboard permalink state from Superset",
extra={"permalink_key": dashboard_permalink_key},
)
permalink_payload = self.client.get_dashboard_permalink_state(dashboard_permalink_key)
permalink_payload = self.client.get_dashboard_permalink_state(
dashboard_permalink_key
)
permalink_state = (
permalink_payload.get("state", permalink_payload)
if isinstance(permalink_payload, dict)
@@ -137,8 +148,12 @@ class SupersetContextExtractor:
"Extracted native filters from permalink dataMask",
extra={"filter_count": len(data_mask)},
)
resolved_dashboard_id = self._extract_dashboard_id_from_state(permalink_state)
resolved_chart_id = self._extract_chart_id_from_state(permalink_state)
resolved_dashboard_id = self._extract_dashboard_id_from_state(
permalink_state
)
resolved_chart_id = self._extract_chart_id_from_state(
permalink_state
)
if resolved_dashboard_id is not None:
dashboard_id = resolved_dashboard_id
unresolved_references = [
@@ -146,10 +161,12 @@ class SupersetContextExtractor:
for item in unresolved_references
if item != "dashboard_permalink_dataset_binding_unresolved"
]
dataset_id, unresolved_references = self._recover_dataset_binding_from_dashboard(
dashboard_id=dashboard_id,
dataset_ref=dataset_ref,
unresolved_references=unresolved_references,
dataset_id, unresolved_references = (
self._recover_dataset_binding_from_dashboard(
dashboard_id=dashboard_id,
dataset_ref=dataset_ref,
unresolved_references=unresolved_references,
)
)
if dataset_id is not None:
dataset_ref = f"dataset:{dataset_id}"
@@ -162,19 +179,30 @@ class SupersetContextExtractor:
]
try:
chart_payload = self.client.get_chart(chart_id)
chart_data = chart_payload.get("result", chart_payload) if isinstance(chart_payload, dict) else {}
chart_data = (
chart_payload.get("result", chart_payload)
if isinstance(chart_payload, dict)
else {}
)
datasource_id = chart_data.get("datasource_id")
if datasource_id is not None:
dataset_id = int(datasource_id)
dataset_ref = f"dataset:{dataset_id}"
logger.reason(
"Recovered dataset reference from permalink chart context",
extra={"chart_id": chart_id, "dataset_id": dataset_id},
extra={
"chart_id": chart_id,
"dataset_id": dataset_id,
},
)
else:
unresolved_references.append("chart_dataset_binding_unresolved")
unresolved_references.append(
"chart_dataset_binding_unresolved"
)
except Exception as exc:
unresolved_references.append("chart_dataset_binding_unresolved")
unresolved_references.append(
"chart_dataset_binding_unresolved"
)
logger.explore(
"Chart lookup failed during permalink recovery",
extra={"chart_id": chart_id, "error": str(exc)},
@@ -186,19 +214,25 @@ class SupersetContextExtractor:
)
elif dashboard_id is not None or dashboard_ref is not None:
resource_type = "dashboard"
resolved_dashboard_ref = dashboard_id if dashboard_id is not None else dashboard_ref
resolved_dashboard_ref = (
dashboard_id if dashboard_id is not None else dashboard_ref
)
if resolved_dashboard_ref is None:
raise ValueError("Dashboard reference could not be resolved")
logger.reason(
"Resolving dashboard-bound dataset from Superset",
extra={"dashboard_ref": resolved_dashboard_ref},
)
# 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(resolved_dashboard_ref)
dashboard_detail = self.client.get_dashboard_detail(
resolved_dashboard_ref
)
resolved_dashboard_id = dashboard_detail.get("id")
if resolved_dashboard_id is not None:
dashboard_id = int(resolved_dashboard_id)
# Check for native_filters_key in query params and fetch filter state.
# This must run AFTER dashboard_id is resolved from slug above.
native_filters_key = query_params.get("native_filters_key", [None])[0]
@@ -206,7 +240,10 @@ class SupersetContextExtractor:
try:
logger.reason(
"Fetching native filter state from Superset",
extra={"dashboard_id": dashboard_id, "filter_key": native_filters_key},
extra={
"dashboard_id": dashboard_id,
"filter_key": native_filters_key,
},
)
extracted = self.client.extract_native_filters_from_key(
dashboard_id, native_filters_key
@@ -221,14 +258,21 @@ class SupersetContextExtractor:
else:
logger.explore(
"Native filter state returned empty dataMask",
extra={"dashboard_id": dashboard_id, "filter_key": native_filters_key},
extra={
"dashboard_id": dashboard_id,
"filter_key": native_filters_key,
},
)
except Exception as exc:
logger.explore(
"Failed to fetch native filter state from Superset",
extra={"dashboard_id": dashboard_id, "filter_key": native_filters_key, "error": str(exc)},
extra={
"dashboard_id": dashboard_id,
"filter_key": native_filters_key,
"error": str(exc),
},
)
datasets = dashboard_detail.get("datasets") or []
if datasets:
first_dataset = datasets[0]
@@ -280,7 +324,10 @@ class SupersetContextExtractor:
)
logger.reason(
"Canonicalized dataset reference from dataset detail",
extra={"dataset_ref": dataset_ref, "dataset_id": dataset_id},
extra={
"dataset_ref": dataset_ref,
"dataset_id": dataset_id,
},
)
except Exception as exc:
partial_recovery = True
@@ -316,17 +363,20 @@ class SupersetContextExtractor:
},
)
return result
# [/DEF:SupersetContextExtractor.parse_superset_link:Function]
# [DEF:SupersetContextExtractor.recover_imported_filters:Function]
# @COMPLEXITY: 4
# @PURPOSE: Build imported filter entries from URL state and Superset-side saved context.
# @RELATION: [CALLS] ->[backend.src.core.superset_client.SupersetClient]
# @RELATION: [CALLS] ->[SupersetClient.get_dashboard]
# @PRE: parsed_context comes from a successful Superset link parse for one environment.
# @POST: returns explicit recovered and partial filter entries with preserved provenance and confirmation requirements.
# @SIDE_EFFECT: may issue Superset reads for dashboard metadata enrichment.
# @DATA_CONTRACT: Input[SupersetParsedContext] -> Output[List[Dict[str,Any]]]
def recover_imported_filters(self, parsed_context: SupersetParsedContext) -> List[Dict[str, Any]]:
def recover_imported_filters(
self, parsed_context: SupersetParsedContext
) -> List[Dict[str, Any]]:
with belief_scope("SupersetContextExtractor.recover_imported_filters"):
recovered_filters: List[Dict[str, Any]] = []
seen_filter_keys: Set[str] = set()
@@ -349,22 +399,46 @@ class SupersetContextExtractor:
return
existing = recovered_filters[existing_index]
if existing.get("display_name") in {None, "", existing.get("filter_name")} and candidate.get("display_name"):
if existing.get("display_name") in {
None,
"",
existing.get("filter_name"),
} and candidate.get("display_name"):
existing["display_name"] = candidate["display_name"]
if existing.get("raw_value") is None and candidate.get("raw_value") is not None:
if (
existing.get("raw_value") is None
and candidate.get("raw_value") is not None
):
existing["raw_value"] = candidate["raw_value"]
existing["confidence_state"] = candidate.get("confidence_state", "imported")
existing["requires_confirmation"] = candidate.get("requires_confirmation", False)
existing["recovery_status"] = candidate.get("recovery_status", "recovered")
existing["confidence_state"] = candidate.get(
"confidence_state", "imported"
)
existing["requires_confirmation"] = candidate.get(
"requires_confirmation", False
)
existing["recovery_status"] = candidate.get(
"recovery_status", "recovered"
)
existing["source"] = candidate.get("source", existing.get("source"))
if existing.get("normalized_value") is None and candidate.get("normalized_value") is not None:
existing["normalized_value"] = deepcopy(candidate["normalized_value"])
if existing.get("notes") and candidate.get("notes") and candidate["notes"] not in existing["notes"]:
existing["notes"] = f'{existing["notes"]}; {candidate["notes"]}'
if (
existing.get("normalized_value") is None
and candidate.get("normalized_value") is not None
):
existing["normalized_value"] = deepcopy(
candidate["normalized_value"]
)
if (
existing.get("notes")
and candidate.get("notes")
and candidate["notes"] not in existing["notes"]
):
existing["notes"] = f"{existing['notes']}; {candidate['notes']}"
if parsed_context.dashboard_id is not None:
try:
dashboard_payload = self.client.get_dashboard(parsed_context.dashboard_id)
dashboard_payload = self.client.get_dashboard(
parsed_context.dashboard_id
)
dashboard_record = (
dashboard_payload.get("result", dashboard_payload)
if isinstance(dashboard_payload, dict)
@@ -376,7 +450,9 @@ class SupersetContextExtractor:
if not isinstance(json_metadata, dict):
json_metadata = {}
native_filter_configuration = json_metadata.get("native_filter_configuration") or []
native_filter_configuration = (
json_metadata.get("native_filter_configuration") or []
)
default_filters = json_metadata.get("default_filters") or {}
if isinstance(default_filters, str) and default_filters.strip():
try:
@@ -400,7 +476,9 @@ class SupersetContextExtractor:
if not filter_name:
continue
display_name = item.get("label") or item.get("name") or filter_name
display_name = (
item.get("label") or item.get("name") or filter_name
)
filter_id = str(item.get("id") or "").strip()
default_value = None
@@ -413,7 +491,9 @@ class SupersetContextExtractor:
"display_name": display_name,
"raw_value": default_value,
"source": "superset_native",
"recovery_status": "recovered" if default_value is not None else "partial",
"recovery_status": "recovered"
if default_value is not None
else "partial",
"requires_confirmation": default_value is None,
"notes": "Recovered from Superset dashboard native filter configuration",
},
@@ -445,7 +525,9 @@ class SupersetContextExtractor:
default_source="superset_url",
default_note="Recovered from Superset URL state",
)
metadata_match = metadata_filters_by_id.get(normalized["filter_name"].strip().lower())
metadata_match = metadata_filters_by_id.get(
normalized["filter_name"].strip().lower()
)
if metadata_match is not None:
normalized["filter_name"] = metadata_match["filter_name"]
normalized["display_name"] = metadata_match["display_name"]
@@ -517,6 +599,7 @@ class SupersetContextExtractor:
},
)
return recovered_filters
# [/DEF:SupersetContextExtractor.recover_imported_filters:Function]
# [DEF:SupersetContextExtractor.discover_template_variables:Function]
@@ -527,12 +610,16 @@ class SupersetContextExtractor:
# @POST: returns deduplicated explicit variable records without executing Jinja or fabricating runtime values.
# @SIDE_EFFECT: none.
# @DATA_CONTRACT: Input[dataset_payload:Dict[str,Any]] -> Output[List[Dict[str,Any]]]
def discover_template_variables(self, dataset_payload: Dict[str, Any]) -> List[Dict[str, Any]]:
def discover_template_variables(
self, dataset_payload: Dict[str, Any]
) -> List[Dict[str, Any]]:
with belief_scope("SupersetContextExtractor.discover_template_variables"):
discovered: List[Dict[str, Any]] = []
seen_variable_names: Set[str] = set()
for expression_source in self._collect_query_bearing_expressions(dataset_payload):
for expression_source in self._collect_query_bearing_expressions(
dataset_payload
):
for filter_match in re.finditer(
r"filter_values\(\s*['\"]([^'\"]+)['\"]\s*\)",
expression_source,
@@ -570,11 +657,16 @@ class SupersetContextExtractor:
default_value=self._normalize_default_literal(default_literal),
)
for jinja_match in re.finditer(r"\{\{\s*(.*?)\s*\}\}", expression_source, flags=re.DOTALL):
for jinja_match in re.finditer(
r"\{\{\s*(.*?)\s*\}\}", expression_source, flags=re.DOTALL
):
expression = str(jinja_match.group(1) or "").strip()
if not expression:
continue
if any(token in expression for token in ("filter_values(", "url_param(", "get_filters(")):
if any(
token in expression
for token in ("filter_values(", "url_param(", "get_filters(")
):
continue
variable_name = self._extract_primary_jinja_identifier(expression)
if not variable_name:
@@ -584,7 +676,9 @@ class SupersetContextExtractor:
seen_variable_names=seen_variable_names,
variable_name=variable_name,
expression_source=expression_source,
variable_kind="derived" if "." in expression or "|" in expression else "parameter",
variable_kind="derived"
if "." in expression or "|" in expression
else "parameter",
is_required=True,
default_value=None,
)
@@ -598,12 +692,15 @@ class SupersetContextExtractor:
},
)
return discovered
# [/DEF:SupersetContextExtractor.discover_template_variables:Function]
# [DEF:SupersetContextExtractor.build_recovery_summary:Function]
# @COMPLEXITY: 2
# @PURPOSE: Summarize recovered, partial, and unresolved context for session state and UX.
def build_recovery_summary(self, parsed_context: SupersetParsedContext) -> Dict[str, Any]:
def build_recovery_summary(
self, parsed_context: SupersetParsedContext
) -> Dict[str, Any]:
return {
"dataset_ref": parsed_context.dataset_ref,
"dataset_id": parsed_context.dataset_id,
@@ -613,12 +710,15 @@ class SupersetContextExtractor:
"unresolved_references": list(parsed_context.unresolved_references),
"imported_filter_count": len(parsed_context.imported_filters),
}
# [/DEF:SupersetContextExtractor.build_recovery_summary:Function]
# [DEF:SupersetContextExtractor._extract_numeric_identifier:Function]
# @COMPLEXITY: 2
# @PURPOSE: Extract a numeric identifier from a REST-like Superset URL path.
def _extract_numeric_identifier(self, path_parts: List[str], resource_name: str) -> Optional[int]:
def _extract_numeric_identifier(
self, path_parts: List[str], resource_name: str
) -> Optional[int]:
if resource_name not in path_parts:
return None
try:
@@ -633,6 +733,7 @@ class SupersetContextExtractor:
if not candidate.isdigit():
return None
return int(candidate)
# [/DEF:SupersetContextExtractor._extract_numeric_identifier:Function]
# [DEF:SupersetContextExtractor._extract_dashboard_reference:Function]
@@ -653,6 +754,7 @@ class SupersetContextExtractor:
if not candidate or candidate == "p":
return None
return candidate
# [/DEF:SupersetContextExtractor._extract_dashboard_reference:Function]
# [DEF:SupersetContextExtractor._extract_dashboard_permalink_key:Function]
@@ -674,6 +776,7 @@ class SupersetContextExtractor:
if permalink_marker != "p" or not permalink_key:
return None
return permalink_key
# [/DEF:SupersetContextExtractor._extract_dashboard_permalink_key:Function]
# [DEF:SupersetContextExtractor._extract_dashboard_id_from_state:Function]
@@ -684,6 +787,7 @@ class SupersetContextExtractor:
payload=state,
candidate_keys={"dashboardId", "dashboard_id", "dashboard_id_value"},
)
# [/DEF:SupersetContextExtractor._extract_dashboard_id_from_state:Function]
# [DEF:SupersetContextExtractor._extract_chart_id_from_state:Function]
@@ -694,12 +798,16 @@ class SupersetContextExtractor:
payload=state,
candidate_keys={"slice_id", "sliceId", "chartId", "chart_id"},
)
# [/DEF:SupersetContextExtractor._extract_chart_id_from_state:Function]
# [DEF:SupersetContextExtractor._search_nested_numeric_key:Function]
# @COMPLEXITY: 3
# @PURPOSE: Recursively search nested dict/list payloads for the first numeric value under a candidate key set.
def _search_nested_numeric_key(self, payload: Any, candidate_keys: Set[str]) -> Optional[int]:
# @RELATION: [DEPENDS_ON] ->[SupersetContextExtractor.parse_superset_link]
def _search_nested_numeric_key(
self, payload: Any, candidate_keys: Set[str]
) -> Optional[int]:
if isinstance(payload, dict):
for key, value in payload.items():
if key in candidate_keys:
@@ -717,11 +825,13 @@ class SupersetContextExtractor:
if found is not None:
return found
return None
# [/DEF:SupersetContextExtractor._search_nested_numeric_key:Function]
# [DEF:SupersetContextExtractor._recover_dataset_binding_from_dashboard:Function]
# @COMPLEXITY: 3
# @PURPOSE: Recover a dataset binding from resolved dashboard context while preserving explicit unresolved markers.
# @RELATION: [CALLS] ->[SupersetClient.get_dashboard_detail]
def _recover_dataset_binding_from_dashboard(
self,
dashboard_id: int,
@@ -744,7 +854,10 @@ class SupersetContextExtractor:
"dataset_ref": dataset_ref,
},
)
if len(datasets) > 1 and "multiple_dashboard_datasets" not in unresolved_references:
if (
len(datasets) > 1
and "multiple_dashboard_datasets" not in unresolved_references
):
unresolved_references.append("multiple_dashboard_datasets")
return resolved_dataset, unresolved_references
if "dashboard_dataset_id_missing" not in unresolved_references:
@@ -754,6 +867,7 @@ class SupersetContextExtractor:
if "dashboard_dataset_binding_missing" not in unresolved_references:
unresolved_references.append("dashboard_dataset_binding_missing")
return None, unresolved_references
# [/DEF:SupersetContextExtractor._recover_dataset_binding_from_dashboard:Function]
# [DEF:SupersetContextExtractor._decode_query_state:Function]
@@ -777,12 +891,15 @@ class SupersetContextExtractor:
)
query_state[key] = decoded_value
return query_state
# [/DEF:SupersetContextExtractor._decode_query_state:Function]
# [DEF:SupersetContextExtractor._extract_imported_filters:Function]
# @COMPLEXITY: 2
# @PURPOSE: Normalize imported filters from decoded query state without fabricating missing values.
def _extract_imported_filters(self, query_state: Dict[str, Any]) -> List[Dict[str, Any]]:
def _extract_imported_filters(
self, query_state: Dict[str, Any]
) -> List[Dict[str, Any]]:
imported_filters: List[Dict[str, Any]] = []
native_filters_payload = query_state.get("native_filters")
@@ -800,7 +917,8 @@ class SupersetContextExtractor:
if item.get("column") and ("value" in item or "val" in item):
direct_clause = {
"col": item.get("column"),
"op": item.get("op") or ("IN" if isinstance(item.get("value"), list) else "=="),
"op": item.get("op")
or ("IN" if isinstance(item.get("value"), list) else "=="),
"val": item.get("val", item.get("value")),
}
imported_filters.append(
@@ -809,7 +927,9 @@ class SupersetContextExtractor:
"raw_value": item.get("value"),
"display_name": item.get("label") or item.get("name"),
"normalized_value": {
"filter_clauses": [direct_clause] if isinstance(direct_clause, dict) else [],
"filter_clauses": [direct_clause]
if isinstance(direct_clause, dict)
else [],
"extra_form_data": {},
"value_origin": "native_filters",
},
@@ -834,7 +954,9 @@ class SupersetContextExtractor:
raw_value = None
normalized_value = {
"filter_clauses": [],
"extra_form_data": deepcopy(extra_form_data) if isinstance(extra_form_data, dict) else {},
"extra_form_data": deepcopy(extra_form_data)
if isinstance(extra_form_data, dict)
else {},
"value_origin": "unresolved",
}
@@ -868,10 +990,17 @@ class SupersetContextExtractor:
# If still no value, try extraFormData directly for time_range, time_grain, etc.
if raw_value is None and isinstance(extra_form_data, dict):
# Common Superset filter fields
for field in ["time_range", "time_grain_sqla", "time_column", "granularity"]:
for field in [
"time_range",
"time_grain_sqla",
"time_column",
"granularity",
]:
if field in extra_form_data:
raw_value = extra_form_data[field]
normalized_value["value_origin"] = f"extra_form_data.{field}"
normalized_value["value_origin"] = (
f"extra_form_data.{field}"
)
break
imported_filters.append(
@@ -881,7 +1010,9 @@ class SupersetContextExtractor:
"display_name": display_name,
"normalized_value": normalized_value,
"source": "superset_permalink",
"recovery_status": "recovered" if raw_value is not None else "partial",
"recovery_status": "recovered"
if raw_value is not None
else "partial",
"requires_confirmation": raw_value is None,
"notes": "Recovered from Superset dashboard permalink state",
}
@@ -901,7 +1032,9 @@ class SupersetContextExtractor:
raw_value = None
normalized_value = {
"filter_clauses": [],
"extra_form_data": deepcopy(extra_form_data) if isinstance(extra_form_data, dict) else {},
"extra_form_data": deepcopy(extra_form_data)
if isinstance(extra_form_data, dict)
else {},
"value_origin": "unresolved",
}
@@ -935,10 +1068,17 @@ class SupersetContextExtractor:
# If still no value, try extraFormData directly for time_range, time_grain, etc.
if raw_value is None and isinstance(extra_form_data, dict):
# Common Superset filter fields
for field in ["time_range", "time_grain_sqla", "time_column", "granularity"]:
for field in [
"time_range",
"time_grain_sqla",
"time_column",
"granularity",
]:
if field in extra_form_data:
raw_value = extra_form_data[field]
normalized_value["value_origin"] = f"extra_form_data.{field}"
normalized_value["value_origin"] = (
f"extra_form_data.{field}"
)
break
imported_filters.append(
@@ -948,7 +1088,9 @@ class SupersetContextExtractor:
"display_name": display_name,
"normalized_value": normalized_value,
"source": "superset_native_filters_key",
"recovery_status": "recovered" if raw_value is not None else "partial",
"recovery_status": "recovered"
if raw_value is not None
else "partial",
"requires_confirmation": raw_value is None,
"notes": "Recovered from Superset native_filters_key state",
}
@@ -960,7 +1102,9 @@ class SupersetContextExtractor:
for index, item in enumerate(extra_filters):
if not isinstance(item, dict):
continue
filter_name = item.get("col") or item.get("column") or f"extra_filter_{index}"
filter_name = (
item.get("col") or item.get("column") or f"extra_filter_{index}"
)
imported_filters.append(
{
"filter_name": str(filter_name),
@@ -981,6 +1125,7 @@ class SupersetContextExtractor:
)
return imported_filters
# [/DEF:SupersetContextExtractor._extract_imported_filters:Function]
# [DEF:SupersetContextExtractor._normalize_imported_filter_payload:Function]
@@ -996,15 +1141,24 @@ class SupersetContextExtractor:
if "raw_value" not in payload and "value" in payload:
raw_value = payload.get("value")
recovery_status = str(
payload.get("recovery_status")
or ("recovered" if raw_value is not None else "partial")
).strip().lower()
recovery_status = (
str(
payload.get("recovery_status")
or ("recovered" if raw_value is not None else "partial")
)
.strip()
.lower()
)
requires_confirmation = bool(
payload.get("requires_confirmation", raw_value is None or recovery_status != "recovered")
payload.get(
"requires_confirmation",
raw_value is None or recovery_status != "recovered",
)
)
return {
"filter_name": str(payload.get("filter_name") or "unresolved_filter").strip(),
"filter_name": str(
payload.get("filter_name") or "unresolved_filter"
).strip(),
"display_name": payload.get("display_name"),
"raw_value": raw_value,
"normalized_value": payload.get("normalized_value"),
@@ -1014,13 +1168,16 @@ class SupersetContextExtractor:
"recovery_status": recovery_status,
"notes": str(payload.get("notes") or default_note),
}
# [/DEF:SupersetContextExtractor._normalize_imported_filter_payload:Function]
# [DEF:SupersetContextExtractor._collect_query_bearing_expressions:Function]
# @COMPLEXITY: 3
# @PURPOSE: Collect SQL and expression-bearing dataset fields for deterministic template-variable discovery.
# @RELATION: [DEPENDS_ON] ->[SupersetContextExtractor.discover_template_variables]
def _collect_query_bearing_expressions(self, dataset_payload: Dict[str, Any]) -> List[str]:
def _collect_query_bearing_expressions(
self, dataset_payload: Dict[str, Any]
) -> List[str]:
expressions: List[str] = []
def append_expression(candidate: Any) -> None:
@@ -1055,6 +1212,7 @@ class SupersetContextExtractor:
append_expression(column.get("expression"))
return expressions
# [/DEF:SupersetContextExtractor._collect_query_bearing_expressions:Function]
# [DEF:SupersetContextExtractor._append_template_variable:Function]
@@ -1087,6 +1245,7 @@ class SupersetContextExtractor:
"mapping_status": "unmapped",
}
)
# [/DEF:SupersetContextExtractor._append_template_variable:Function]
# [DEF:SupersetContextExtractor._extract_primary_jinja_identifier:Function]
@@ -1100,6 +1259,7 @@ class SupersetContextExtractor:
if candidate in {"if", "else", "for", "set", "True", "False", "none", "None"}:
return None
return candidate
# [/DEF:SupersetContextExtractor._extract_primary_jinja_identifier:Function]
# [DEF:SupersetContextExtractor._normalize_default_literal:Function]
@@ -1110,9 +1270,8 @@ class SupersetContextExtractor:
if not normalized_literal:
return None
if (
(normalized_literal.startswith("'") and normalized_literal.endswith("'"))
or (normalized_literal.startswith('"') and normalized_literal.endswith('"'))
):
normalized_literal.startswith("'") and normalized_literal.endswith("'")
) or (normalized_literal.startswith('"') and normalized_literal.endswith('"')):
return normalized_literal[1:-1]
lowered = normalized_literal.lower()
if lowered in {"true", "false"}:
@@ -1126,7 +1285,10 @@ class SupersetContextExtractor:
return float(normalized_literal)
except ValueError:
return normalized_literal
# [/DEF:SupersetContextExtractor._normalize_default_literal:Function]
# [/DEF:SupersetContextExtractor:Class]
# [/DEF:SupersetContextExtractor:Module]
# [/DEF:SupersetContextExtractor:Module]