From a641b0d1795eae6e5641bf23ea085c68a5a298de Mon Sep 17 00:00:00 2001 From: Cursor Agent Date: Wed, 9 Sep 2026 12:08:44 +0000 Subject: [PATCH] typing: strong-type query_builder and remove ignore override Co-authored-by: Armen Zambrano G. --- pyproject.toml | 1 - src/sentry/snuba/metrics/query_builder.py | 90 ++++++++++++++++------- 2 files changed, 62 insertions(+), 29 deletions(-) diff --git a/pyproject.toml b/pyproject.toml index 71d1ada48ecd..b7165969b9f1 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -384,7 +384,6 @@ ignore_missing_imports = true # - python3 -m tools.mypy_helpers.find_easiest_modules [[tool.mypy.overrides]] module = [ - "sentry.snuba.metrics.query_builder", "sentry.testutils.cases", ] disable_error_code = [ diff --git a/src/sentry/snuba/metrics/query_builder.py b/src/sentry/snuba/metrics/query_builder.py index 025565831bab..f200514dc965 100644 --- a/src/sentry/snuba/metrics/query_builder.py +++ b/src/sentry/snuba/metrics/query_builder.py @@ -3,7 +3,7 @@ from collections.abc import Mapping, Sequence from datetime import datetime, timedelta from enum import Enum -from typing import Any, TypedDict, overload +from typing import Any, TypedDict, cast, overload import sentry_sdk from snuba_sdk import ( @@ -43,6 +43,7 @@ from sentry.snuba.metrics.fields.base import ( COMPOSITE_ENTITY_CONSTITUENT_ALIAS, MetricExpressionBase, + MetricOperationParams, generate_bottom_up_dependency_tree_for_metrics, org_id_from_projects, ) @@ -71,6 +72,7 @@ DerivedMetricParseException, MetricDoesNotExistException, MetricEntity, + MetricOperationType, get_num_intervals, get_timestamp_column_name, require_rhs_condition_resolution, @@ -127,16 +129,22 @@ def parse_field(field: str, allow_mri: bool = False) -> MetricField: def parse_public_field(field: str) -> MetricField: matches = PUBLIC_EXPRESSION_REGEX.match(field) + operation: MetricOperationType | None = None if matches is not None: - operation = matches[1] + operation = cast(MetricOperationType, matches[1]) metric_name = matches[2] else: - operation = None metric_name = field return MetricField(operation, get_mri(metric_name)) +def _as_metric_operation_params( + params: dict[str, None | str | int | float | Sequence[tuple[str | int, ...]]] | None, +) -> MetricOperationParams | None: + return cast(MetricOperationParams | None, params) + + def transform_null_transaction_to_unparameterized(use_case_id, org_id, alias=None): """ This function transforms any null tag.transaction to '<< unparameterized >>' so that it can be handled @@ -747,11 +755,15 @@ def translate_meta_results( continue elif alias_type == AliasMetaType.GROUP_BY_METRIC_FIELD: metric_groupby_field = alias_to_metric_group_by_field[record["name"]] + if not isinstance(metric_groupby_field.field, MetricField): + raise InvalidParams(f"Invalid metric group by field type: {metric_groupby_field.field}") defined_parent_meta_type = get_metric_object_from_metric_field( metric_groupby_field.field ).get_meta_type() - record["type"] = defined_parent_meta_type + record["type"] = ( + record["type"] if defined_parent_meta_type is None else defined_parent_meta_type + ) elif alias_type == AliasMetaType.TAG: record["type"] = "string" elif alias_type == AliasMetaType.DATASET_COLUMN or alias_type == AliasMetaType.TIME_COLUMN: @@ -821,16 +833,27 @@ def generate_snql_for_action_by_fields( the snql generation starts to diverge significantly. """ - is_group_by = isinstance(metric_action_by_field, MetricGroupByField) - is_order_by = isinstance(metric_action_by_field, MetricOrderByField) + group_by_field = ( + metric_action_by_field + if isinstance(metric_action_by_field, MetricGroupByField) + else None + ) + order_by_field = ( + metric_action_by_field + if isinstance(metric_action_by_field, MetricOrderByField) + else None + ) + is_group_by = group_by_field is not None + is_order_by = order_by_field is not None if not is_group_by and not is_order_by: raise InvalidParams("The metric action must either be an order by or group by.") if isinstance(metric_action_by_field.field, str): # This transformation is currently supported only for group by because OrderBy doesn't support the Function type. if is_group_by and metric_action_by_field.field == "transaction": + assert group_by_field is not None return transform_null_transaction_to_unparameterized( - use_case_id, org_id, metric_action_by_field.alias + use_case_id, org_id, group_by_field.alias ) # Handles the case when we are trying to group or order by `project` for example, but we want @@ -850,10 +873,11 @@ def generate_snql_for_action_by_fields( f"Unsupported string field: {metric_action_by_field.field}" ) + group_by_alias = group_by_field.alias if group_by_field is not None else "" exp = ( AliasedExpression( exp=Column(name=column_name), - alias=metric_action_by_field.alias, + alias=group_by_alias, ) if is_group_by and not is_column else Column(name=column_name) @@ -862,7 +886,8 @@ def generate_snql_for_action_by_fields( if is_order_by: # We return a list in order to use the "extend" method and reduce the number of changes across # the codebase. - exp = [OrderBy(exp=exp, direction=metric_action_by_field.direction)] + assert order_by_field is not None + exp = [OrderBy(exp=exp, direction=order_by_field.direction)] return exp elif isinstance(metric_action_by_field.field, MetricField): @@ -875,16 +900,17 @@ def generate_snql_for_action_by_fields( return metric_expression.generate_groupby_statements( use_case_id=use_case_id, alias=metric_action_by_field.field.alias, - params=metric_action_by_field.field.params, + params=_as_metric_operation_params(metric_action_by_field.field.params), projects=projects, )[0] elif is_order_by: + assert order_by_field is not None return metric_expression.generate_orderby_clause( use_case_id=use_case_id, alias=metric_action_by_field.field.alias, - params=metric_action_by_field.field.params, + params=_as_metric_operation_params(metric_action_by_field.field.params), projects=projects, - direction=metric_action_by_field.direction, + direction=order_by_field.direction, ) else: raise NotImplementedError( @@ -918,20 +944,24 @@ def _build_where(self) -> list[BooleanCondition | Condition]: condition.lhs.op, condition.lhs.metric_mri ) try: + rhs = condition.rhs + lhs_op = condition.lhs.op + if lhs_op is not None and require_rhs_condition_resolution(lhs_op): + if not isinstance(condition.rhs, str): + raise InvalidParams( + f"Cannot resolve non-string condition value for metric op '{lhs_op}'" + ) + rhs = resolve_tag_value(self._use_case_id, self._org_id, condition.rhs) metric_condition_filters.append( Condition( lhs=metric_expression.generate_where_statements( use_case_id=self._use_case_id, - params=condition.lhs.params, + params=_as_metric_operation_params(condition.lhs.params), projects=self._projects, alias=condition.lhs.alias, )[0], op=condition.op, - rhs=( - resolve_tag_value(self._use_case_id, self._org_id, condition.rhs) - if require_rhs_condition_resolution(condition.lhs.op) - else condition.rhs - ), + rhs=rhs, ) ) except IndexError: @@ -1066,6 +1096,8 @@ def __build_totals_and_series_queries( series_limit = self._metrics_query.max_limit if self._use_case_id in [UseCaseID.TRANSACTIONS, UseCaseID.SPANS]: + if self._metrics_query.interval is None: + raise InvalidParams("Interval must be defined for discover metrics queries.") time_groupby_column = self.__generate_time_groupby_column_for_discover_queries( self._metrics_query.interval ) @@ -1096,17 +1128,19 @@ def __generate_time_groupby_column_for_discover_queries(interval: int) -> Functi def __update_query_dicts_with_component_entities( self, - component_entities: dict[MetricEntity, Sequence[str]], - metric_mri_to_obj_dict: dict[tuple[str | None, str, str], MetricExpressionBase], - fields_in_entities: dict[MetricEntity, list[tuple[str | None, str, str]]], + component_entities: Mapping[MetricEntity | None, Sequence[str]], + metric_mri_to_obj_dict: dict[tuple[MetricOperationType | None, str, str], MetricExpressionBase], + fields_in_entities: dict[MetricEntity, list[tuple[MetricOperationType | None, str, str]]], parent_alias, - ) -> dict[tuple[str | None, str, str], MetricExpressionBase]: + ) -> dict[tuple[MetricOperationType | None, str, str], MetricExpressionBase]: # At this point in time, we are only supporting raw metrics in the metrics attribute of # any instance of DerivedMetric, and so in this case the op will always be None # ToDo(ahmed): In future PR, we might want to allow for dependency metrics to also have an # an aggregate and in this case, we would need to parse the op here op = None for entity, metric_mris in component_entities.items(): + if entity is None: + raise DerivedMetricParseException("Derived metric component entity cannot be None") for metric_mri in metric_mris: # The constituents of an instance of CompositeEntityDerivedMetric will have a reference to their parent # alias so that we are able to distinguish the constituents in case we have naming collisions that could @@ -1125,8 +1159,8 @@ def __update_query_dicts_with_component_entities( return metric_mri_to_obj_dict def get_snuba_queries(self): - metric_mri_to_obj_dict: dict[tuple[str | None, str, str], MetricExpressionBase] = {} - fields_in_entities: dict[MetricEntity, list[tuple[str | None, str, str]]] = {} + metric_mri_to_obj_dict: dict[tuple[MetricOperationType | None, str, str], MetricExpressionBase] = {} + fields_in_entities: dict[MetricEntity, list[tuple[MetricOperationType | None, str, str]]] = {} for select_field in self._metrics_query.select: metric_field_obj = metric_object_factory(select_field.op, select_field.metric_mri) @@ -1198,7 +1232,7 @@ def get_snuba_queries(self): projects=self._projects, use_case_id=self._use_case_id, alias=field[2], - params=params, + params=_as_metric_operation_params(params), ) metric_ids_set |= metric_field_obj.generate_metric_ids( self._projects, self._use_case_id @@ -1252,7 +1286,7 @@ def __init__( self, organization_id: int, metrics_query: DeprecatingMetricsQuery, - fields_in_entities: dict[MetricEntity, list[tuple[str | None, str, str]]], + fields_in_entities: dict[MetricEntity, list[tuple[MetricOperationType | None, str, str]]], intervals: list[datetime], results, use_case_id: UseCaseID, @@ -1433,7 +1467,7 @@ def resolve_tag_value(value: int | str | None) -> str | None: except KeyError: params = None totals[alias] = metric_obj.run_post_query_function( - totals, params=params, alias=alias + totals, params=_as_metric_operation_params(params), alias=alias ) if series is not None: @@ -1448,7 +1482,7 @@ def resolve_tag_value(value: int | str | None) -> str | None: except KeyError: params = None series[alias][idx] = metric_obj.run_post_query_function( - series, params=params, idx=idx, alias=alias + series, params=_as_metric_operation_params(params), idx=idx, alias=alias ) # Remove the extra fields added due to the constituent metrics that were added