Add support for semicolon stripping to DbApiHook, PrestoHook, and Tri…

…noHook (apache#41916)



---------

Co-authored-by: Elad Kalif <45845474+eladkal@users.noreply.github.com>

dev/breeze/src/airflow_breeze/global_constants.py

@@ -568,7 +568,7 @@ def get_airflow_extras():
     # END OF EXTRAS LIST UPDATED BY PRE COMMIT
 ]
 
-CHICKEN_EGG_PROVIDERS = " ".join(["standard amazon"])
+CHICKEN_EGG_PROVIDERS = " ".join(["standard amazon common.sql"])
 
 
 BASE_PROVIDERS_COMPATIBILITY_CHECKS: list[dict[str, str | list[str]]] = [

dev/breeze/tests/test_packages.py

@@ -209,7 +209,7 @@ def test_get_documentation_package_path():
             "postgres",
             "beta0",
             """
-    "apache-airflow-providers-common-sql>=1.17.0b0",
+    "apache-airflow-providers-common-sql>=1.20.0b0",
     "apache-airflow>=2.8.0b0",
     "psycopg2-binary>=2.9.4",
     """,
@@ -219,7 +219,7 @@ def test_get_documentation_package_path():
             "postgres",
             "",
             """
-    "apache-airflow-providers-common-sql>=1.17.0",
+    "apache-airflow-providers-common-sql>=1.20.0",
     "apache-airflow>=2.8.0",
     "psycopg2-binary>=2.9.4",
     """,

generated/provider_dependencies.json

@@ -27,7 +27,7 @@
     "deps": [
       "PyAthena>=3.0.10",
       "apache-airflow-providers-common-compat>=1.2.1",
-      "apache-airflow-providers-common-sql>=1.3.1",
+      "apache-airflow-providers-common-sql>=1.20.0",
       "apache-airflow-providers-http",
       "apache-airflow>=2.8.0",
       "asgiref>=2.3.0",
@@ -102,7 +102,7 @@
   },
   "apache.drill": {
     "deps": [
-      "apache-airflow-providers-common-sql>=1.14.1",
+      "apache-airflow-providers-common-sql>=1.20.0",
       "apache-airflow>=2.8.0",
       "sqlalchemy-drill>=1.1.0"
     ],
@@ -116,7 +116,7 @@
   },
   "apache.druid": {
     "deps": [
-      "apache-airflow-providers-common-sql>=1.14.1",
+      "apache-airflow-providers-common-sql>=1.20.0",
       "apache-airflow>=2.8.0",
       "pydruid>=0.4.1"
     ],
@@ -159,7 +159,7 @@
   },
   "apache.hive": {
     "deps": [
-      "apache-airflow-providers-common-sql>=1.3.1",
+      "apache-airflow-providers-common-sql>=1.20.0",
       "apache-airflow>=2.8.0",
       "hmsclient>=0.1.0",
       "jmespath>=0.7.0",
@@ -201,7 +201,7 @@
   },
   "apache.impala": {
     "deps": [
-      "apache-airflow-providers-common-sql>=1.14.1",
+      "apache-airflow-providers-common-sql>=1.20.0",
       "apache-airflow>=2.8.0",
       "impyla>=0.18.0,<1.0"
     ],
@@ -265,7 +265,7 @@
   },
   "apache.pinot": {
     "deps": [
-      "apache-airflow-providers-common-sql>=1.14.1",
+      "apache-airflow-providers-common-sql>=1.20.0",
       "apache-airflow>=2.8.0",
       "pinotdb>=5.1.0"
     ],
@@ -421,7 +421,7 @@
     "deps": [
       "apache-airflow>=2.8.0",
       "more-itertools>=9.0.0",
-      "sqlparse>=0.4.2"
+      "sqlparse>=0.5.1"
     ],
     "devel-deps": [],
     "plugins": [],
@@ -434,7 +434,7 @@
   "databricks": {
     "deps": [
       "aiohttp>=3.9.2, <4",
-      "apache-airflow-providers-common-sql>=1.10.0",
+      "apache-airflow-providers-common-sql>=1.20.0",
       "apache-airflow>=2.8.0",
       "databricks-sql-connector>=2.0.0, <3.0.0, !=2.9.0",
       "mergedeep>=1.3.4",
@@ -545,7 +545,7 @@
   },
   "elasticsearch": {
     "deps": [
-      "apache-airflow-providers-common-sql>=1.17.0",
+      "apache-airflow-providers-common-sql>=1.20.0",
       "apache-airflow>=2.8.0",
       "elasticsearch>=8.10,<9"
     ],
@@ -559,7 +559,7 @@
   },
   "exasol": {
     "deps": [
-      "apache-airflow-providers-common-sql>=1.14.1",
+      "apache-airflow-providers-common-sql>=1.20.0",
       "apache-airflow>=2.8.0",
       "pandas>=1.5.3,<2.2;python_version<\"3.9\"",
       "pandas>=2.1.2,<2.2;python_version>=\"3.9\"",
@@ -632,7 +632,7 @@
     "deps": [
       "PyOpenSSL>=23.0.0",
       "apache-airflow-providers-common-compat>=1.2.1",
-      "apache-airflow-providers-common-sql>=1.7.2",
+      "apache-airflow-providers-common-sql>=1.20.0",
       "apache-airflow>=2.8.0",
       "asgiref>=3.5.2",
       "dill>=0.2.3",
@@ -787,7 +787,7 @@
   },
   "jdbc": {
     "deps": [
-      "apache-airflow-providers-common-sql>=1.17.0",
+      "apache-airflow-providers-common-sql>=1.20.0",
       "apache-airflow>=2.8.0",
       "jaydebeapi>=1.1.1"
     ],
@@ -855,7 +855,7 @@
   },
   "microsoft.mssql": {
     "deps": [
-      "apache-airflow-providers-common-sql>=1.17.0",
+      "apache-airflow-providers-common-sql>=1.20.0",
       "apache-airflow>=2.8.0",
       "methodtools>=0.4.7",
       "pymssql>=2.3.0"
@@ -906,7 +906,7 @@
   },
   "mysql": {
     "deps": [
-      "apache-airflow-providers-common-sql>=1.17.0",
+      "apache-airflow-providers-common-sql>=1.20.0",
       "apache-airflow>=2.8.0",
       "mysql-connector-python>=8.0.29",
       "mysqlclient>=1.4.0; sys_platform != 'darwin'"
@@ -937,7 +937,7 @@
   },
   "odbc": {
     "deps": [
-      "apache-airflow-providers-common-sql>=1.17.0",
+      "apache-airflow-providers-common-sql>=1.20.0",
       "apache-airflow>=2.8.0",
       "pyodbc>=5.0.0"
     ],
@@ -973,7 +973,7 @@
   "openlineage": {
     "deps": [
       "apache-airflow-providers-common-compat>=1.2.1",
-      "apache-airflow-providers-common-sql>=1.6.0",
+      "apache-airflow-providers-common-sql>=1.20.0",
       "apache-airflow>=2.8.0",
       "attrs>=22.2",
       "openlineage-integration-common>=1.24.2",
@@ -1017,7 +1017,7 @@
   },
   "oracle": {
     "deps": [
-      "apache-airflow-providers-common-sql>=1.3.1",
+      "apache-airflow-providers-common-sql>=1.20.0",
       "apache-airflow>=2.8.0",
       "oracledb>=2.0.0"
     ],
@@ -1083,7 +1083,7 @@
   },
   "postgres": {
     "deps": [
-      "apache-airflow-providers-common-sql>=1.17.0",
+      "apache-airflow-providers-common-sql>=1.20.0",
       "apache-airflow>=2.8.0",
       "psycopg2-binary>=2.9.4"
     ],
@@ -1099,7 +1099,7 @@
   },
   "presto": {
     "deps": [
-      "apache-airflow-providers-common-sql>=1.3.1",
+      "apache-airflow-providers-common-sql>=1.20.0",
       "apache-airflow>=2.8.0",
       "pandas>=1.5.3,<2.2;python_version<\"3.9\"",
       "pandas>=2.1.2,<2.2;python_version>=\"3.9\"",
@@ -1214,7 +1214,7 @@
   },
   "slack": {
     "deps": [
-      "apache-airflow-providers-common-sql>=1.3.1",
+      "apache-airflow-providers-common-sql>=1.20.0",
       "apache-airflow>=2.8.0",
       "slack_sdk>=3.19.0"
     ],
@@ -1239,7 +1239,7 @@
   "snowflake": {
     "deps": [
       "apache-airflow-providers-common-compat>=1.1.0",
-      "apache-airflow-providers-common-sql>=1.14.1",
+      "apache-airflow-providers-common-sql>=1.20.0",
       "apache-airflow>=2.8.0",
       "pandas>=1.5.3,<2.2;python_version<\"3.9\"",
       "pandas>=2.1.2,<2.2;python_version>=\"3.9\"",
@@ -1260,7 +1260,7 @@
   },
   "sqlite": {
     "deps": [
-      "apache-airflow-providers-common-sql>=1.14.1",
+      "apache-airflow-providers-common-sql>=1.20.0",
       "apache-airflow>=2.8.0"
     ],
     "devel-deps": [],
@@ -1285,7 +1285,7 @@
   },
   "standard": {
     "deps": [
-      "apache-airflow-providers-common-sql>=1.18.0",
+      "apache-airflow-providers-common-sql>=1.20.0",
       "apache-airflow>=2.8.0"
     ],
     "devel-deps": [],
@@ -1318,7 +1318,7 @@
   },
   "teradata": {
     "deps": [
-      "apache-airflow-providers-common-sql>=1.14.1",
+      "apache-airflow-providers-common-sql>=1.20.0",
       "apache-airflow>=2.8.0",
       "teradatasql>=17.20.0.28",
       "teradatasqlalchemy>=17.20.0.0"
@@ -1335,7 +1335,7 @@
   },
   "trino": {
     "deps": [
-      "apache-airflow-providers-common-sql>=1.3.1",
+      "apache-airflow-providers-common-sql>=1.20.0",
       "apache-airflow>=2.8.0",
       "pandas>=1.5.3,<2.2;python_version<\"3.9\"",
       "pandas>=2.1.2,<2.2;python_version>=\"3.9\"",
@@ -1353,7 +1353,7 @@
   },
   "vertica": {
     "deps": [
-      "apache-airflow-providers-common-sql>=1.3.1",
+      "apache-airflow-providers-common-sql>=1.20.0",
       "apache-airflow>=2.8.0",
       "vertica-python>=0.6.0"
     ],
@@ -1393,7 +1393,7 @@
   },
   "ydb": {
     "deps": [
-      "apache-airflow-providers-common-sql>=1.14.1",
+      "apache-airflow-providers-common-sql>=1.20.0",
       "apache-airflow>=2.8.0",
       "ydb-dbapi>=0.1.0",
       "ydb>=3.18.8"

providers/src/airflow/providers/amazon/provider.yaml

@@ -95,7 +95,7 @@ versions:
 dependencies:
   - apache-airflow>=2.8.0
   - apache-airflow-providers-common-compat>=1.2.1
-  - apache-airflow-providers-common-sql>=1.3.1
+  - apache-airflow-providers-common-sql>=1.20.0
   - apache-airflow-providers-http
   # We should update minimum version of boto3 and here regularly to avoid `pip` backtracking with the number
   # of candidates to consider. Make sure to configure boto3 version here as well as in all the tools below

providers/src/airflow/providers/apache/drill/provider.yaml

@@ -53,7 +53,7 @@ versions:
 
 dependencies:
   - apache-airflow>=2.8.0
-  - apache-airflow-providers-common-sql>=1.14.1
+  - apache-airflow-providers-common-sql>=1.20.0
   - sqlalchemy-drill>=1.1.0
 
 integrations:

providers/src/airflow/providers/apache/druid/provider.yaml

@@ -60,7 +60,7 @@ versions:
 
 dependencies:
   - apache-airflow>=2.8.0
-  - apache-airflow-providers-common-sql>=1.14.1
+  - apache-airflow-providers-common-sql>=1.20.0
   - pydruid>=0.4.1
 
 integrations:

providers/src/airflow/providers/apache/hive/provider.yaml

@@ -73,7 +73,7 @@ versions:
 
 dependencies:
   - apache-airflow>=2.8.0
-  - apache-airflow-providers-common-sql>=1.3.1
+  - apache-airflow-providers-common-sql>=1.20.0
   - hmsclient>=0.1.0
   # In pandas 2.2 minimal version of the sqlalchemy is 2.0
   # https://pandas.pydata.org/docs/whatsnew/v2.2.0.html#increased-minimum-versions-for-dependencies

providers/src/airflow/providers/apache/impala/provider.yaml

@@ -41,7 +41,7 @@ versions:
 
 dependencies:
   - impyla>=0.18.0,<1.0
-  - apache-airflow-providers-common-sql>=1.14.1
+  - apache-airflow-providers-common-sql>=1.20.0
   - apache-airflow>=2.8.0
 
 additional-extras:

providers/src/airflow/providers/apache/pinot/provider.yaml

@@ -53,7 +53,7 @@ versions:
 
 dependencies:
   - apache-airflow>=2.8.0
-  - apache-airflow-providers-common-sql>=1.14.1
+  - apache-airflow-providers-common-sql>=1.20.0
   - pinotdb>=5.1.0
 
 integrations:

providers/src/airflow/providers/common/sql/hooks/sql.py

@@ -150,6 +150,8 @@ class DbApiHook(BaseHook):
     conn_name_attr: str
     # Override to have a default connection id for a particular dbHook
     default_conn_name = "default_conn_id"
+    # Override if this db doesn't support semicolons in SQL queries
+    strip_semicolon = False
     # Override if this db supports autocommit.
     supports_autocommit = False
     # Override if this db supports executemany.
@@ -369,14 +371,18 @@ def strip_sql_string(sql: str) -> str:
         return sql.strip().rstrip(";")
 
     @staticmethod
-    def split_sql_string(sql: str) -> list[str]:
+    def split_sql_string(sql: str, strip_semicolon: bool = False) -> list[str]:
         """
         Split string into multiple SQL expressions.
 
         :param sql: SQL string potentially consisting of multiple expressions
+        :param strip_semicolon: whether to strip semicolon from SQL string
         :return: list of individual expressions
         """
-        splits = sqlparse.split(sqlparse.format(sql, strip_comments=True))
+        splits = sqlparse.split(
+            sql=sqlparse.format(sql, strip_comments=True),
+            strip_semicolon=strip_semicolon,
+        )
         return [s for s in splits if s]
 
     @property
@@ -471,7 +477,10 @@ def run(
 
         if isinstance(sql, str):
             if split_statements:
-                sql_list: Iterable[str] = self.split_sql_string(sql)
+                sql_list: Iterable[str] = self.split_sql_string(
+                    sql=sql,
+                    strip_semicolon=self.strip_semicolon,
+                )
             else:
                 sql_list = [sql] if sql.strip() else []
         else:

providers/src/airflow/providers/common/sql/hooks/sql.pyi

@@ -54,6 +54,7 @@ class ConnectorProtocol(Protocol):
 class DbApiHook(BaseHook):
     conn_name_attr: str
     default_conn_name: str
+    strip_semicolon: bool
     supports_autocommit: bool
     supports_executemany: bool
     connector: ConnectorProtocol | None
@@ -93,7 +94,7 @@ class DbApiHook(BaseHook):
     @staticmethod
     def strip_sql_string(sql: str) -> str: ...
     @staticmethod
-    def split_sql_string(sql: str) -> list[str]: ...
+    def split_sql_string(sql: str, strip_semicolon: bool = False) -> list[str]: ...
     @property
     def last_description(self) -> Sequence[Sequence] | None: ...
     @overload

providers/src/airflow/providers/common/sql/provider.yaml

@@ -25,6 +25,7 @@ state: ready
 source-date-epoch: 1730012422
 # note that those versions are maintained by release manager - do not update them manually
 versions:
+  - 1.20.0
   - 1.19.0
   - 1.18.0
   - 1.17.1
@@ -64,7 +65,7 @@ versions:
 
 dependencies:
   - apache-airflow>=2.8.0
-  - sqlparse>=0.4.2
+  - sqlparse>=0.5.1
   - more-itertools>=9.0.0
 
 additional-extras: