feat(ingest/cassandra): Add support for Cassandra as a source

datahub-web-react/src/app/ingest/source/builder/constants.ts

@@ -36,6 +36,7 @@ import csvLogo from '../../../../images/csv-logo.png';
 import qlikLogo from '../../../../images/qliklogo.png';
 import sigmaLogo from '../../../../images/sigmalogo.png';
 import sacLogo from '../../../../images/saclogo.svg';
+import cassandraLogo from '../../../../images/cassandralogo.png';
 import datahubLogo from '../../../../images/datahublogo.png';
 
 export const ATHENA = 'athena';
@@ -129,6 +130,8 @@ export const SIGMA = 'sigma';
 export const SIGMA_URN = `urn:li:dataPlatform:${SIGMA}`;
 export const SAC = 'sac';
 export const SAC_URN = `urn:li:dataPlatform:${SAC}`;
+export const CASSANDRA = 'cassandra';
+export const CASSANDRA_URN = `urn:li:dataPlatform:${CASSANDRA}`;
 export const DATAHUB = 'datahub';
 export const DATAHUB_GC = 'datahub-gc';
 export const DATAHUB_LINEAGE_FILE = 'datahub-lineage-file';
@@ -175,6 +178,7 @@ export const PLATFORM_URN_TO_LOGO = {
     [QLIK_SENSE_URN]: qlikLogo,
     [SIGMA_URN]: sigmaLogo,
     [SAC_URN]: sacLogo,
+    [CASSANDRA_URN]: cassandraLogo,
     [DATAHUB_URN]: datahubLogo,
 };
 

datahub-web-react/src/app/ingest/source/builder/sources.json

@@ -310,5 +310,12 @@
         "description": "Import Spaces, Sources, Tables and statistics from Dremio.",
         "docsUrl": "https://datahubproject.io/docs/metadata-ingestion/",
         "recipe": "source:\n    type: dremio\n    config:\n        # Coordinates\n        hostname: null\n        port: null\n        #true if https, otherwise false\n        tls: true\n\n        #For cloud instance\n        #is_dremio_cloud: True\n        #dremio_cloud_project_id: <project_id>\n\n        #Credentials with personal access token\n        authentication_method: PAT\n        password: pass\n\n        #Or Credentials with basic auth\n        #authentication_method: password\n        #username: null\n        #password: null\n\n        stateful_ingestion:\n            enabled: true"
-    }
+    },
+    {
+        "urn": "urn:li:dataPlatform:cassandra",
+        "name": "cassandra",
+        "displayName": "CassandraDB",
+        "docsUrl": "https://datahubproject.io/docs/generated/ingestion/sources/cassandra",
+        "recipe": "source:\n    type: cassandra\n    config:\n      # Coordinates\n      contact_point: 'localhost'\n      port: 9042\n      # Credentials (ensure the user has read access to the system_schema keyspace)\n      username: null\n      password: null\n\n      # Optional Allow / Deny extraction of particular keyspaces.\n      # keyspace_pattern:\n        # allow:\n          # - \".*\""
+    },
 ]

metadata-ingestion/docs/sources/cassandra/cassandra_recipe.yml

@@ -0,0 +1,21 @@
+source:
+  type: "cassandra"
+  config:
+    # Coordinates
+    contact_point: "localhost"
+    port: 9042
+
+    # Credentials
+    username: "admin"
+    password: "password"
+
+    #cloud astra db
+    #cloud_config:
+    #  secure_connect_bundle: "Path to Secure Connect Bundle (.zip)"
+    #  token: "Application Token"
+
+    # Options
+    keyspace_pattern:
+      allow: [".*"]
+sink:
+  # config sinks

metadata-ingestion/setup.py

@@ -404,6 +404,7 @@
     # https://www.elastic.co/guide/en/elasticsearch/client/python-api/current/release-notes.html#rn-7-14-0
     # https://github.com/elastic/elasticsearch-py/issues/1639#issuecomment-883587433
     "elasticsearch": {"elasticsearch==7.13.4"},
+    "cassandra": {"cassandra-driver>=3.28.0"},
     "feast": {
         "feast>=0.34.0,<1",
         "flask-openid>=1.3.0",
@@ -659,6 +660,7 @@
             "qlik-sense",
             "sigma",
             "sac",
+            "cassandra",
         ]
         if plugin
         for dependency in plugins[plugin]
@@ -777,6 +779,7 @@
         "qlik-sense = datahub.ingestion.source.qlik_sense.qlik_sense:QlikSenseSource",
         "sigma = datahub.ingestion.source.sigma.sigma:SigmaSource",
         "sac = datahub.ingestion.source.sac.sac:SACSource",
+        "cassandra = datahub.ingestion.source.cassandra.cassandra:CassandraSource",
     ],
     "datahub.ingestion.transformer.plugins": [
         "pattern_cleanup_ownership = datahub.ingestion.transformer.pattern_cleanup_ownership:PatternCleanUpOwnership",