From 7e20b97dac46cfc5a661d4085b7e797dec594777 Mon Sep 17 00:00:00 2001 From: Cursor Agent Date: Sat, 5 Sep 2026 12:12:07 +0000 Subject: [PATCH] Typing: remove query_builder mypy override Co-authored-by: Armen Zambrano G. --- pyproject.toml | 1 - src/sentry/snuba/metrics/query_builder.py | 120 +++++++++++++++------- 2 files changed, 83 insertions(+), 38 deletions(-) diff --git a/pyproject.toml b/pyproject.toml index d358e351da4a..dbfc149ffc29 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..f8fe4bb0520f 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 ( @@ -71,6 +71,7 @@ DerivedMetricParseException, MetricDoesNotExistException, MetricEntity, + MetricOperationType, get_num_intervals, get_timestamp_column_name, require_rhs_condition_resolution, @@ -94,6 +95,17 @@ QUERY_PROJECT_LIMIT = 10 +MetricExpressionParamValue = str | int | float +MetricExpressionParams = Mapping[str, MetricExpressionParamValue] +MetricFieldParams = dict[str, None | str | int | float | Sequence[tuple[str | int, ...]]] | None +MetricFieldKey = tuple[MetricOperationType | None, str, str] + + +def _get_metric_expression_params(params: MetricFieldParams) -> MetricExpressionParams | None: + # Metric field params are a wider internal shape than MetricExpressionBase currently advertises. + # Keep runtime behavior unchanged while narrowing for static type checking. + return cast(MetricExpressionParams | None, params) + def _strip_project_id(condition: Condition) -> Condition | None: if isinstance(condition, BooleanCondition): @@ -134,7 +146,7 @@ def parse_public_field(field: str) -> MetricField: operation = None metric_name = field - return MetricField(operation, get_mri(metric_name)) + return MetricField(cast(MetricOperationType | None, operation), get_mri(metric_name)) def transform_null_transaction_to_unparameterized(use_case_id, org_id, alias=None): @@ -747,11 +759,16 @@ 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"Expected a MetricField for group by alias {record['name']}, got string" + ) 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: @@ -765,7 +782,7 @@ def translate_meta_results( class SnubaQueryBuilder: #: Datasets actually implemented in snuba: - _implemented_datasets = { + _implemented_datasets: set[MetricEntity] = { "metrics_counters", "metrics_distributions", "metrics_sets", @@ -821,16 +838,28 @@ 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) + metric_groupby_field = ( + metric_action_by_field + if isinstance(metric_action_by_field, MetricGroupByField) + else None + ) + metric_orderby_field = ( + metric_action_by_field + if isinstance(metric_action_by_field, MetricOrderByField) + else None + ) + + is_group_by = metric_groupby_field is not None + is_order_by = metric_orderby_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 metric_groupby_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, metric_groupby_field.alias ) # Handles the case when we are trying to group or order by `project` for example, but we want @@ -850,19 +879,20 @@ def generate_snql_for_action_by_fields( f"Unsupported string field: {metric_action_by_field.field}" ) - exp = ( - AliasedExpression( + if is_group_by and not is_column: + assert metric_groupby_field is not None + exp: Column | AliasedExpression = AliasedExpression( exp=Column(name=column_name), - alias=metric_action_by_field.alias, + alias=metric_groupby_field.alias, ) - if is_group_by and not is_column - else Column(name=column_name) - ) + else: + exp = Column(name=column_name) 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 metric_orderby_field is not None + exp = [OrderBy(exp=exp, direction=metric_orderby_field.direction)] return exp elif isinstance(metric_action_by_field.field, MetricField): @@ -875,16 +905,17 @@ 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=_get_metric_expression_params(metric_action_by_field.field.params), projects=projects, )[0] elif is_order_by: + assert metric_orderby_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=_get_metric_expression_params(metric_action_by_field.field.params), projects=projects, - direction=metric_action_by_field.direction, + direction=metric_orderby_field.direction, ) else: raise NotImplementedError( @@ -922,16 +953,12 @@ def _build_where(self) -> list[BooleanCondition | Condition]: Condition( lhs=metric_expression.generate_where_statements( use_case_id=self._use_case_id, - params=condition.lhs.params, + params=_get_metric_expression_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=self._resolve_metric_condition_rhs(condition), ) ) except IndexError: @@ -948,6 +975,16 @@ def _build_where(self) -> list[BooleanCondition | Condition]: return where + def _resolve_metric_condition_rhs(self, condition: MetricConditionField) -> int | float | str: + metric_op = condition.lhs.op + if metric_op is None or not require_rhs_condition_resolution(metric_op): + return condition.rhs + if not isinstance(condition.rhs, str): + raise InvalidParams( + f"Metric condition rhs must be a string when using operation {metric_op}" + ) + return resolve_tag_value(self._use_case_id, self._org_id, condition.rhs) + def _build_timeframe(self) -> list[BooleanCondition | Condition]: """ Builds the timeframe of the query, comprehending the `start` and `end` intervals. @@ -1066,6 +1103,10 @@ 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 is required when querying discover metrics series" + ) time_groupby_column = self.__generate_time_groupby_column_for_discover_queries( self._metrics_query.interval ) @@ -1096,17 +1137,19 @@ 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]]], - parent_alias, - ) -> dict[tuple[str | None, str, str], MetricExpressionBase]: + component_entities: Mapping[MetricEntity | None, Sequence[str]], + metric_mri_to_obj_dict: dict[MetricFieldKey, MetricExpressionBase], + fields_in_entities: dict[MetricEntity, list[MetricFieldKey]], + parent_alias: str, + ) -> dict[MetricFieldKey, 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("Unable to resolve metric entity") 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 +1168,8 @@ 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[MetricFieldKey, MetricExpressionBase] = {} + fields_in_entities: dict[MetricEntity, list[MetricFieldKey]] = {} for select_field in self._metrics_query.select: metric_field_obj = metric_object_factory(select_field.op, select_field.metric_mri) @@ -1198,7 +1241,7 @@ def get_snuba_queries(self): projects=self._projects, use_case_id=self._use_case_id, alias=field[2], - params=params, + params=_get_metric_expression_params(params), ) metric_ids_set |= metric_field_obj.generate_metric_ids( self._projects, self._use_case_id @@ -1252,7 +1295,7 @@ 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[MetricFieldKey]], intervals: list[datetime], results, use_case_id: UseCaseID, @@ -1270,7 +1313,7 @@ def __init__( } # This is a set of all the `(op, metric_mri, alias)` combinations passed in the metrics_query - self._metrics_query_fields_set = { + self._metrics_query_fields_set: set[MetricFieldKey] = { (field.op, field.metric_mri, field.alias) for field in metrics_query.select } # This is a set of all queryable `(op, metric_mri)` combinations. Queryable can mean it @@ -1278,7 +1321,7 @@ def __init__( # SingularEntityDerivedMetric or the instances of SingularEntityDerivedMetric that are # the constituents necessary to calculate instances of CompositeEntityDerivedMetric but # are not necessarily requested in the query definition - self._fields_in_entities_set = { + self._fields_in_entities_set: set[MetricFieldKey] = { elem for fields_in_entity in fields_in_entities.values() for elem in fields_in_entity } self._set_of_constituent_queries = self._fields_in_entities_set.union( @@ -1433,7 +1476,7 @@ 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=_get_metric_expression_params(params), alias=alias ) if series is not None: @@ -1448,7 +1491,10 @@ 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=_get_metric_expression_params(params), + idx=idx, + alias=alias, ) # Remove the extra fields added due to the constituent metrics that were added