[AIRFLOW-2192] Allow non-latin1 usernames with MySQL backend by adding a SQL_ENGINE_ENCODING param and default to UTF-8 (apache#4087)

Compromised of:

Since we have unicode_literals importred and the engine arguments must be strings in Python2 explicitly make 'utf-8' a string.

replace bare exception with conf.AirflowConfigException for missing value.

It's just got for strings apparently.

Add utf-8 to default_airflow.cfg - question do I still need the try try/except block or can we depend on defaults (I note some have both).

Get rid of try/except block and depend on default_airflow.cfg

Use __str__ since calling str just gives us back a newstr as well.

Test that a panda user can be saved.

Author: holdenk

airflow/config_templates/default_airflow.cfg

@@ -85,6 +85,9 @@ executor = SequentialExecutor
 # their website
 sql_alchemy_conn = sqlite:///{AIRFLOW_HOME}/airflow.db
 
+# The encoding for the databases
+sql_engine_encoding = utf-8
+
 # If SqlAlchemy should pool database connections.
 sql_alchemy_pool_enabled = True
 

airflow/settings.py

@@ -155,7 +155,7 @@ def configure_orm(disable_connection_pool=False):
         engine_args['poolclass'] = NullPool
         log.debug("settings.configure_orm(): Using NullPool")
     elif 'sqlite' not in SQL_ALCHEMY_CONN:
-        # Engine args not supported by sqlite.
+        # Pool size engine args not supported by sqlite.
         # If no config value is defined for the pool size, select a reasonable value.
         # 0 means no limit, which could lead to exceeding the Database connection limit.
         try:
@@ -177,6 +177,16 @@ def configure_orm(disable_connection_pool=False):
         engine_args['pool_size'] = pool_size
         engine_args['pool_recycle'] = pool_recycle
 
+    try:
+        # Allow the user to specify an encoding for their DB otherwise default
+        # to utf-8 so jobs & users with non-latin1 characters can still use
+        # us.
+        engine_args['encoding'] = conf.get('core', 'SQL_ENGINE_ENCODING')
+    except conf.AirflowConfigException:
+        engine_args['encoding'] = 'utf-8'
+    # For Python2 we get back a newstr and need a str
+    engine_args['encoding'] = engine_args['encoding'].__str__()
+
     engine = create_engine(SQL_ALCHEMY_CONN, **engine_args)
     reconnect_timeout = conf.getint('core', 'SQL_ALCHEMY_RECONNECT_TIMEOUT')
     setup_event_handlers(engine, reconnect_timeout)

tests/core.py

@@ -2110,6 +2110,11 @@ def test_password_user_authenticate(self):
         self.password_user.password = "secure_password"
         self.assertTrue(self.password_user.authenticate("secure_password"))
 
+    def test_password_unicode_user_authenticate(self):
+        self.password_user.username = u"🐼"  # This is a panda
+        self.password_user.password = "secure_password"
+        self.assertTrue(self.password_user.authenticate("secure_password"))
+
     def test_password_authenticate_session(self):
         from airflow.contrib.auth.backends.password_auth import PasswordUser
         self.password_user.password = 'test_password'