add chinese col name test

Author: douenergy

ibis-server/app/model/data_source.py

@@ -154,6 +154,10 @@ def get_mssql_connection(cls, info: MSSqlConnectionInfo) -> BaseBackend:
     def get_mysql_connection(cls, info: MySqlConnectionInfo) -> BaseBackend:
         ssl_context = cls._create_ssl_context(info)
         kwargs = {"ssl": ssl_context} if ssl_context else {}
+
+        # utf8mb4 is the actual charset used by MySQL for utf8
+        kwargs.setdefault("charset", "utf8mb4")
+
         if info.kwargs:
             kwargs.update(info.kwargs)
         return ibis.mysql.connect(

ibis-server/tests/routers/v2/connector/test_mysql.py

@@ -475,6 +475,80 @@ async def test_connection_valid_ssl_mode(client, mysql_ssl_off: MySqlContainer):
     assert response.text == '"8.0.40"'
 
 
+# MySQL specific chinese tests
+# So we dont mess up with the other tests's connection
+async def test_chinese_column_name_and_data(client):
+    mysql = MySqlContainer(image="mysql:8.0.40", dialect="pymysql").start()
+    connection_url = mysql.get_connection_url()
+    engine = sqlalchemy.create_engine(connection_url)
+
+    # Create table with Chinese column name
+    with engine.begin() as conn:
+        conn.execute(
+            text("""
+        CREATE TABLE chinese_test (
+            id INT PRIMARY KEY,
+            `中文` VARCHAR(255) CHARACTER SET utf8mb4 COLLATE utf8mb4_unicode_ci,
+            data VARCHAR(255) CHARACTER SET utf8mb4 COLLATE utf8mb4_unicode_ci
+        )
+        """)
+        )
+
+        # Insert data with Chinese characters
+        conn.execute(
+            text("""
+        INSERT INTO chinese_test (id, `中文`, data)
+        VALUES 
+            (1, '一', '天'),
+            (2, '二', '地'),
+            (3, '三', '人')
+        """)
+        )
+
+    chinese_manifest = {
+        "catalog": "my_catalog",
+        "schema": "my_schema",
+        "models": [
+            {
+                "name": "ChineseTest",
+                "refSql": "select * from chinese_test",
+                "columns": [
+                    {"name": "id", "expression": "id", "type": "integer"},
+                    {"name": "中文", "expression": '"中文"', "type": "varchar"},
+                    {"name": "data", "expression": "data", "type": "varchar"},
+                ],
+                "primaryKey": "id",
+            }
+        ],
+    }
+
+    chinese_manifest_str = base64.b64encode(orjson.dumps(chinese_manifest)).decode(
+        "utf-8"
+    )
+
+    connection_info = _to_connection_info(mysql)
+    response = await client.post(
+        url=f"{base_url}/query",
+        json={
+            "connectionInfo": connection_info,
+            "manifestStr": chinese_manifest_str,
+            "sql": 'SELECT * FROM "ChineseTest" ORDER BY id',
+        },
+    )
+
+    assert response.status_code == 200
+    result = response.json()
+
+    assert len(result["columns"]) == 3
+    assert "中文" in result["columns"]
+    assert len(result["data"]) == 3
+
+    assert result["data"][0][1] == "一"
+
+    conn.close()
+    mysql.stop()
+
+
 def _to_connection_info(mysql: MySqlContainer):
     return {
         "host": mysql.get_container_host_ip(),