feat: add replace option to hive csv upload

superset/db_engine_specs/hive.py

@@ -34,6 +34,7 @@
 from superset import app, cache, conf
 from superset.db_engine_specs.base import BaseEngineSpec
 from superset.db_engine_specs.presto import PrestoEngineSpec
+from superset.exceptions import SupersetException
 from superset.models.sql_lab import Query
 from superset.sql_parse import Table
 from superset.utils import core as utils
@@ -116,6 +117,10 @@ def create_table_from_csv(  # pylint: disable=too-many-arguments, too-many-local
     ) -> None:
         """Uploads a csv file and creates a superset datasource in Hive."""
 
+        if_exists = df_to_sql_kwargs["if_exists"]
+        if if_exists == "append":
+            raise SupersetException("Append operation not currently supported")
+
         def convert_to_hive_type(col_type: str) -> str:
             """maps tableschema's types to hive types"""
             tableschema_to_hive_types = {
@@ -153,6 +158,20 @@ def convert_to_hive_type(col_type: str) -> str:
             )
         schema_definition = ", ".join(column_name_and_type)
 
+        # ensure table doesn't already exist
+        if (
+            if_exists == "fail"
+            and not database.get_df(
+                f"SHOW TABLES IN {table.schema} LIKE '{table.table}'"
+            ).empty
+        ):
+            raise SupersetException("Table already exists")
+
+        engine = cls.get_engine(database)
+
+        if if_exists == "replace":
+            engine.execute(f"DROP TABLE IF EXISTS {str(table)}")
+
         # Optional dependency
         import boto3  # pylint: disable=import-error
 
@@ -163,12 +182,12 @@ def convert_to_hive_type(col_type: str) -> str:
             bucket_path,
             os.path.join(upload_prefix, table.table, os.path.basename(filename)),
         )
+
         # TODO(bkyryliuk): support other delimiters
         sql = f"""CREATE TABLE {str(table)} ( {schema_definition} )
             ROW FORMAT DELIMITED FIELDS TERMINATED BY ',' STORED AS
             TEXTFILE LOCATION '{location}'
             tblproperties ('skip.header.line.count'='1')"""
-        engine = cls.get_engine(database)
         engine.execute(sql)
 
     @classmethod

tests/db_engine_specs/hive_tests.py

@@ -17,6 +17,8 @@
 from unittest import mock
 
 from superset.db_engine_specs.hive import HiveEngineSpec
+from superset.exceptions import SupersetException
+from superset.sql_parse import Table
 from tests.db_engine_specs.base_tests import DbEngineSpecTestCase
 
 
@@ -162,3 +164,14 @@ def test_convert_dttm(self):
             HiveEngineSpec.convert_dttm("TIMESTAMP", dttm),
             "CAST('2019-01-02 03:04:05.678900' AS TIMESTAMP)",
         )
+
+    def test_create_table_from_csv_append(self) -> None:
+        self.assertRaises(
+            SupersetException,
+            HiveEngineSpec.create_table_from_csv,
+            "foo.csv",
+            Table("foobar"),
+            None,
+            {},
+            {"if_exists": "append"},
+        )