fix: add suffix to Drill labels to avoid collision (#32857)

Co-authored-by: Fredrik Hyyrynen <fredrik.hyyrynen@ngm.se>
Co-authored-by: Evan Rusackas <evan@rusackas.com>
Co-authored-by: pre-commit <pre-commit@users.noreply.github.com>

superset/db_engine_specs/drill.py

@@ -27,6 +27,7 @@ from sqlalchemy.engine.url import URL
 from superset.constants import TimeGrain
 from superset.db_engine_specs.base import BaseEngineSpec
 from superset.db_engine_specs.exceptions import SupersetDBAPIProgrammingError
+from superset.utils.hashing import md5_sha_from_str
 
 if TYPE_CHECKING:
     from superset.models.core import Database
@@ -143,3 +144,14 @@ class DrillEngineSpec(BaseEngineSpec):
             if str(ex) == "generator raised StopIteration":
                 return []
             raise
+
+    @staticmethod
+    def _mutate_label(label: str) -> str:
+        """
+        Suffix with the first six characters from the md5 of the label to avoid
+        collisions with original column names
+
+        :param label: Expected expression label
+        :return: Conditionally mutated label
+        """
+        return f"{label}_{md5_sha_from_str(label)[:6]}"

tests/unit_tests/db_engine_specs/test_drill.py

@@ -157,3 +157,19 @@ def test_get_schema_from_engine_params() -> None:
         )
         == "dfs.test"
     )
+
+
+@pytest.mark.parametrize(
+    "column_name,expected_result",
+    [
+        ("time", "time_07cc69"),
+        ("count", "count_e2942a"),
+    ],
+)
+def test_connect_make_label_compatible(column_name: str, expected_result: str) -> None:
+    from superset.db_engine_specs.drill import (
+        DrillEngineSpec as spec,  # noqa: N813
+    )
+
+    label = spec.make_label_compatible(column_name)
+    assert label == expected_result