def test_edit_query():
query = Query(
{
"selected_columns": ["c1", "c2", "c3"],
"conditions": [["c1", "=", "a"]],
"arrayjoin": "tags",
"having": [["c4", "=", "c"]],
"groupby": ["project_id"],
"aggregations": [["count()", "", "count"]],
"orderby": "event_id",
"limitby": (100, "environment"),
"sample": 10,
"limit": 100,
"offset": 50,
"totals": True,
},
TableSource("my_table", ColumnSet([])),
)
query.set_selected_columns(["c4"])
assert query.get_selected_columns() == ["c4"]
query.set_aggregations([["different_agg()", "", "something"]])
assert query.get_aggregations() == [["different_agg()", "", "something"]]
query.add_groupby(["more", "more2"])
assert query.get_groupby() == ["project_id", "more", "more2"]
query.add_conditions([["c5", "=", "9"]])
assert query.get_conditions() == [
["c1", "=", "a"],
["c5", "=", "9"],
]
query.set_conditions([["c6", "=", "10"]])
assert query.get_conditions() == [
["c6", "=", "10"],
]
query.set_arrayjoin("not_tags")
assert query.get_arrayjoin() == "not_tags"
query.set_granularity(7200)
assert query.get_granularity() == 7200
query.set_prewhere([["pc6", "=", "10"]])
assert query.get_prewhere() == [["pc6", "=", "10"]]
def process_query(self, query: Query, request_settings: RequestSettings,) -> None:
max_prewhere_conditions: int = (
self.__max_prewhere_conditions or settings.MAX_PREWHERE_CONDITIONS
)
prewhere_keys = query.get_data_source().get_prewhere_candidates()
if not prewhere_keys:
return
prewhere_conditions: Sequence[Condition] = []
# Add any condition to PREWHERE if:
# - It is a single top-level condition (not OR-nested), and
# - Any of its referenced columns are in prewhere_keys
conditions = query.get_conditions()
if not conditions:
return
prewhere_candidates = [
(util.columns_in_expr(cond[0]), cond)
for cond in conditions
if util.is_condition(cond)
and any(col in prewhere_keys for col in util.columns_in_expr(cond[0]))
]
# Use the condition that has the highest priority (based on the
# position of its columns in the prewhere keys list)
prewhere_candidates = sorted(
[
(
min(
prewhere_keys.index(col) for col in cols if col in prewhere_keys
),
cond,
)
for cols, cond in prewhere_candidates
],
key=lambda priority_and_col: priority_and_col[0],
)
if prewhere_candidates:
prewhere_conditions = [cond for _, cond in prewhere_candidates][
:max_prewhere_conditions
]
query.set_conditions(
list(filter(lambda cond: cond not in prewhere_conditions, conditions))
)
query.set_prewhere(prewhere_conditions)
def test_referenced_columns():
# a = 1 AND b = 1
dataset = get_dataset("events")
source = dataset.get_dataset_schemas().get_read_schema().get_data_source()
body = {"conditions": [["a", "=", "1"], ["b", "=", "1"]]}
query = Query(body, source)
assert query.get_all_referenced_columns() == set(["a", "b"])
assert query.get_columns_referenced_in_conditions() == set(["a", "b"])
assert query.get_columns_referenced_in_having() == set([])
# a = 1 AND (b = 1 OR c = 1)
body = {
"conditions": [["a", "=", "1"], [["b", "=", "1"], ["c", "=", "1"]]]
}
query = Query(body, source)
assert query.get_all_referenced_columns() == set(["a", "b", "c"])
assert query.get_columns_referenced_in_conditions() == set(["a", "b", "c"])
assert query.get_columns_referenced_in_having() == set([])
# a = 1 AND (b = 1 OR foo(c) = 1)
body = {
"conditions": [["a", "=", "1"],
[["b", "=", "1"], [["foo", ["c"]], "=", "1"]]]
}
query = Query(body, source)
assert query.get_all_referenced_columns() == set(["a", "b", "c"])
assert query.get_columns_referenced_in_conditions() == set(["a", "b", "c"])
assert query.get_columns_referenced_in_having() == set([])
# a = 1 AND (b = 1 OR foo(c, bar(d)) = 1)
body = {
"conditions": [
["a", "=", "1"],
[["b", "=", "1"], [["foo", ["c", ["bar", ["d"]]]], "=", "1"]],
]
}
query = Query(body, source)
assert query.get_all_referenced_columns() == set(["a", "b", "c", "d"])
assert query.get_columns_referenced_in_conditions() == set(
["a", "b", "c", "d"])
assert query.get_columns_referenced_in_having() == set([])
# Other fields, including expressions in selected columns
body = {
"arrayjoin": "tags_key",
"groupby": ["time", "group_id"],
"orderby": "-time",
"selected_columns": [
"group_id",
"time",
["foo", ["c", ["bar", ["d"]]]], # foo(c, bar(d))
],
"aggregations": [["uniq", "tags_value", "values_seen"]],
}
query = Query(body, source)
assert query.get_all_referenced_columns() == set(
["tags_key", "tags_value", "time", "group_id", "c", "d"])
assert query.get_columns_referenced_in_conditions() == set([])
assert query.get_columns_referenced_in_having() == set([])
body = {
"conditions": [["a", "=", "1"]],
"having": [
["b", "=", "1"],
[["c", "=", "1"], [["foo", ["d", ["bar", ["e"]]]], "=", "1"]],
],
}
query = Query(body, source)
query.set_prewhere([["pc6", "=", "10"]])
assert query.get_all_referenced_columns() == set(
["a", "b", "c", "d", "e", "pc6"])
assert query.get_columns_referenced_in_having() == set(
["b", "c", "d", "e"])