def __init__(self, query: Query, settings: RequestSettings,) -> None:
# Clickhouse query structure
# Referencing them here directly since it makes it easier
# to process this query independently from the Clickhouse Query
# and there is no risk in doing so since they are immutable.
self.__selected_columns = query.get_selected_columns_from_ast()
self.__condition = query.get_condition_from_ast()
self.__groupby = query.get_groupby_from_ast()
self.__having = query.get_having_from_ast()
self.__orderby = query.get_orderby_from_ast()
self.__data_source = query.get_data_source()
self.__arrayjoin = query.get_arrayjoin_from_ast()
self.__granularity = query.get_granularity()
self.__limit = query.get_limit()
self.__limitby = query.get_limitby()
self.__offset = query.get_offset()
if self.__having:
assert self.__groupby, "found HAVING clause with no GROUP BY"
self.__turbo = settings.get_turbo()
self.__final = query.get_final()
self.__sample = query.get_sample()
self.__hastotals = query.has_totals()
self.__prewhere = query.get_prewhere_ast()
self.__settings = settings
self.__sql_data_list: Optional[Sequence[Tuple[str, str]]] = None
self.__formatted_query: Optional[str] = None
self.__sql_data: Optional[Mapping[str, str]] = None
def process_query(self, query: Query,
request_settings: RequestSettings) -> None:
missing_checkers = {checker for checker in self.__condition_checkers}
def inspect_expression(condition: Expression) -> None:
top_level = get_first_level_and_conditions(condition)
for condition in top_level:
for checker in self.__condition_checkers:
if checker in missing_checkers:
if checker.check(condition):
missing_checkers.remove(checker)
condition = query.get_condition()
if condition is not None:
inspect_expression(condition)
prewhere = query.get_prewhere_ast()
if prewhere is not None:
inspect_expression(prewhere)
missing_ids = {checker.get_id() for checker in missing_checkers}
if get_config("mandatory_condition_enforce", 0):
assert (
not missing_checkers
), f"Missing mandatory columns in query. Missing {missing_ids}"
else:
if missing_checkers:
logger.error(
"Query is missing mandatory columns",
extra={"missing_checkers": missing_ids},
)
def process_query(self, query: Query, request_settings: RequestSettings) -> None:
condition = query.get_condition_from_ast()
if condition:
query.set_ast_condition(condition.transform(self.process_condition))
prewhere = query.get_prewhere_ast()
if prewhere:
query.set_prewhere_ast_condition(prewhere.transform(self.process_condition))
if self.formatted:
metrics.increment("query_processed", tags={"type": self.formatted})
