From cfc02ee196608d4f3a8ce5edb34a9bc2d44d0622 Mon Sep 17 00:00:00 2001
From: Harshal Sheth <hsheth2@gmail.com>
Date: Tue, 6 Apr 2021 15:38:25 -0700
Subject: [PATCH] feat(ingest): add Oracle db support (#2347)

---
 metadata-ingestion/README.md                  | 23 +++++++++++++++++++
 metadata-ingestion/setup.py                   |  2 ++
 .../src/datahub/ingestion/source/oracle.py    | 19 +++++++++++++++
 3 files changed, 44 insertions(+)
 create mode 100644 metadata-ingestion/src/datahub/ingestion/source/oracle.py

diff --git a/metadata-ingestion/README.md b/metadata-ingestion/README.md
index 675427fc00..0b1c964480 100644
--- a/metadata-ingestion/README.md
+++ b/metadata-ingestion/README.md
@@ -41,6 +41,7 @@ We use a plugin architecture so that you can install only the dependencies you a
 | mssql         | `pip install 'acryl-datahub[mssql]'`                       | SQL Server source          |
 | mysql         | `pip install 'acryl-datahub[mysql]'`                       | MySQL source               |
 | postgres      | `pip install 'acryl-datahub[postgres]'`                    | Postgres source            |
+| oracle        | `pip install 'acryl-datahub[oracle]'`                      | Oracle source              |
 | snowflake     | `pip install 'acryl-datahub[snowflake]'`                   | Snowflake source           |
 | mongodb       | `pip install 'acryl-datahub[mongodb]'`                     | MongoDB source             |
 | ldap          | `pip install 'acryl-datahub[ldap]'` ([extra requirements]) | LDAP source                |
@@ -264,6 +265,28 @@ source:
     # options is same as above
 ```
 
+### Oracle `oracle`
+
+Extracts:
+
+- List of databases, schema, and tables
+- Column types associated with each table
+
+```yml
+source:
+  type: oracle
+  config:
+    # For more details on authentication, see the documentation:
+    # https://docs.sqlalchemy.org/en/14/dialects/oracle.html#dialect-oracle-cx_oracle-connect and
+    # https://cx-oracle.readthedocs.io/en/latest/user_guide/connection_handling.html#connection-strings.
+    username: user
+    password: pass
+    host_port: localhost:5432
+    database: dbname
+    # table_pattern/schema_pattern is same as above
+    # options is same as above
+```
+
 ### Google BigQuery `bigquery`
 
 Extracts:
diff --git a/metadata-ingestion/setup.py b/metadata-ingestion/setup.py
index 320043fe32..469a0a47d2 100644
--- a/metadata-ingestion/setup.py
+++ b/metadata-ingestion/setup.py
@@ -74,6 +74,7 @@ plugins: Dict[str, Set[str]] = {
     "mysql": sql_common | {"pymysql>=1.0.2"},
     "postgres": sql_common | {"psycopg2-binary", "GeoAlchemy2"},
     "snowflake": sql_common | {"snowflake-sqlalchemy"},
+    "oracle": sql_common | {"cx_Oracle"},
     "ldap": {"python-ldap>=2.4"},
     "druid": sql_common | {"pydruid>=0.6.2"},
     "mongodb": {"pymongo>=3.11"},
@@ -176,6 +177,7 @@ setuptools.setup(
             "mongodb = datahub.ingestion.source.mongodb:MongoDBSource",
             "mssql = datahub.ingestion.source.mssql:SQLServerSource",
             "mysql = datahub.ingestion.source.mysql:MySQLSource",
+            "oracle = datahub.ingestion.source.oracle:OracleSource",
             "postgres = datahub.ingestion.source.postgres:PostgresSource",
             "snowflake = datahub.ingestion.source.snowflake:SnowflakeSource",
         ],
diff --git a/metadata-ingestion/src/datahub/ingestion/source/oracle.py b/metadata-ingestion/src/datahub/ingestion/source/oracle.py
new file mode 100644
index 0000000000..0d493e51f7
--- /dev/null
+++ b/metadata-ingestion/src/datahub/ingestion/source/oracle.py
@@ -0,0 +1,19 @@
+# This import verifies that the dependencies are available.
+import cx_Oracle  # noqa: F401
+
+from .sql_common import BasicSQLAlchemyConfig, SQLAlchemySource
+
+
+class OracleConfig(BasicSQLAlchemyConfig):
+    # defaults
+    scheme = "oracle+cx_oracle"
+
+
+class OracleSource(SQLAlchemySource):
+    def __init__(self, config, ctx):
+        super().__init__(config, ctx, "oracle")
+
+    @classmethod
+    def create(cls, config_dict, ctx):
+        config = OracleConfig.parse_obj(config_dict)
+        return cls(config, ctx)