feat(ingest/mssql): enable TLS encryption for SQLServer using pytds (#…

…9256)
datahub-project · Nov 29, 2023 · ab10e6b · ab10e6b
1 parent 10b7a95
commit ab10e6b
Show file tree

Hide file tree

Showing 3 changed files with 10 additions and 2 deletions.
diff --git a/metadata-ingestion/docs/sources/mssql/mssql_recipe.yml b/metadata-ingestion/docs/sources/mssql/mssql_recipe.yml
@@ -9,6 +9,14 @@ source:
     username: user
     password: pass
 
+    # Options
+    # Uncomment if you need to use encryption with pytds
+    # See https://python-tds.readthedocs.io/en/latest/pytds.html#pytds.connect
+    # options:
+    #   connect_args:
+    #     cafile: server-ca.pem
+    #     validate_host: true
+
 sink:
   # sink configs
 

diff --git a/metadata-ingestion/setup.py b/metadata-ingestion/setup.py
@@ -350,7 +350,7 @@
     "mlflow": {"mlflow-skinny>=2.3.0"},
     "mode": {"requests", "tenacity>=8.0.1"} | sqllineage_lib,
     "mongodb": {"pymongo[srv]>=3.11", "packaging"},
-    "mssql": sql_common | {"sqlalchemy-pytds>=0.3"},
+    "mssql": sql_common | {"sqlalchemy-pytds>=0.3", "pyOpenSSL"},
     "mssql-odbc": sql_common | {"pyodbc"},
     "mysql": mysql,
     # mariadb should have same dependency as mysql

diff --git a/metadata-ingestion/src/datahub/ingestion/source/sql/mssql/source.py b/metadata-ingestion/src/datahub/ingestion/source/sql/mssql/source.py
@@ -155,7 +155,7 @@ class SQLServerSource(SQLAlchemySource):
     - Metadata for databases, schemas, views and tables
     - Column types associated with each table/view
     - Table, row, and column statistics via optional SQL profiling
-    We have two options for the underlying library used to connect to SQL Server: (1) [python-tds](https://github.com/denisenkom/pytds) and (2) [pyodbc](https://github.com/mkleehammer/pyodbc). The TDS library is pure Python and hence easier to install, but only PyODBC supports encrypted connections.
+    We have two options for the underlying library used to connect to SQL Server: (1) [python-tds](https://github.com/denisenkom/pytds) and (2) [pyodbc](https://github.com/mkleehammer/pyodbc). The TDS library is pure Python and hence easier to install.
     """
 
     def __init__(self, config: SQLServerConfig, ctx: PipelineContext):