Merge branch 'master' into oracle-updates

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    # Credentials for on prem cassandra\n    contact_point: localhost\n    port: 9042\n    username: admin\n    password: password\n\n    # Or\n    # Credentials Astra Cloud\n    #cloud_config:\n    #  secure_connect_bundle: Path to Secure Connect Bundle (.zip)\n    #  token: Application Token\n\n    # Optional Allow / Deny extraction of particular keyspaces.\n    keyspace_pattern:\n      allow: [.*]\n\n    # Optional Allow / Deny extraction of particular tables.\n    table_pattern:\n      allow: [.*]"
     }
 ]

metadata-ingestion/docs/sources/cassandra/cassandra_pre.md

@@ -0,0 +1,40 @@
+### Setup
+
+This integration pulls metadata directly from Cassandra databases, including both **DataStax Astra DB** and **Cassandra Enterprise Edition (EE)**. 
+
+You’ll need to have a Cassandra instance or an Astra DB setup with appropriate access permissions.
+
+#### Steps to Get the Required Information
+
+1. **Set Up User Credentials**:
+
+   - **For Astra DB**:
+     - Log in to your Astra DB Console.
+     - Navigate to **Organization Settings** > **Token Management**.
+     - Generate an **Application Token** with the required permissions for read access.
+     - Download the **Secure Connect Bundle** from the Astra DB Console.
+   - **For Cassandra EE**:
+     - Ensure you have a **username** and **password** with read access to the necessary keyspaces.
+
+2. **Permissions**:
+
+   - The user or token must have `SELECT` permissions that allow it to:
+     - Access metadata in system keyspaces (e.g., `system_schema`) to retrieve information about keyspaces, tables, columns, and views.
+     - Perform `SELECT` operations on the data tables if data profiling is enabled.
+
+3. **Verify Database Access**:
+   - For Astra DB: Ensure the **Secure Connect Bundle** is used and configured correctly.
+   - For Cassandra Opensource: Ensure the **contact point** and **port** are accessible.
+
+
+:::caution 
+
+When enabling profiling, make sure to set a limit on the number of rows to sample. Profiling large tables without a limit may lead to excessive resource consumption and slow performance.
+
+:::
+
+:::note
+
+For cloud configuration with Astra DB, it is necessary to specify the Secure Connect Bundle path in the configuration. For that reason, use the CLI to ingest metadata into DataHub.
+
+:::

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

@@ -0,0 +1,30 @@
+source:
+  type: "cassandra"
+  config:
+    # Credentials for on prem cassandra
+    contact_point: "localhost"
+    port: 9042
+    username: "admin"
+    password: "password"
+
+    # Or
+    # Credentials Astra Cloud
+    #cloud_config:
+    #  secure_connect_bundle: "Path to Secure Connect Bundle (.zip)"
+    #  token: "Application Token"
+
+    # Optional Allow / Deny extraction of particular keyspaces.
+    keyspace_pattern:
+      allow: [".*"]
+
+    # Optional Allow / Deny extraction of particular tables.
+    table_pattern:
+      allow: [".*"]
+
+    # Optional 
+    profiling:
+      enabled: true
+      profile_table_level_only: true
+
+sink:
+  # config sinks

metadata-ingestion/docs/transformer/intro.md

@@ -26,16 +26,23 @@ DataHub provided transformers for dataset are:
 - [Simple Add Dataset ownership](./dataset_transformer.md#simple-add-dataset-ownership)
 - [Pattern Add Dataset ownership](./dataset_transformer.md#pattern-add-dataset-ownership)
 - [Simple Remove Dataset ownership](./dataset_transformer.md#simple-remove-dataset-ownership)
+- [Extract Ownership from Tags](./dataset_transformer.md#extract-ownership-from-tags)
+- [Clean suffix prefix from Ownership](./dataset_transformer.md#clean-suffix-prefix-from-ownership)
 - [Mark Dataset Status](./dataset_transformer.md#mark-dataset-status)
 - [Simple Add Dataset globalTags](./dataset_transformer.md#simple-add-dataset-globaltags)
 - [Pattern Add Dataset globalTags](./dataset_transformer.md#pattern-add-dataset-globaltags)
 - [Add Dataset globalTags](./dataset_transformer.md#add-dataset-globaltags)
 - [Set Dataset browsePath](./dataset_transformer.md#set-dataset-browsepath)
 - [Simple Add Dataset glossaryTerms](./dataset_transformer.md#simple-add-dataset-glossaryterms)
 - [Pattern Add Dataset glossaryTerms](./dataset_transformer.md#pattern-add-dataset-glossaryterms)
+- [Add Dataset globalTags](./dataset_transformer.md#add-dataset-globaltags)
 - [Pattern Add Dataset Schema Field glossaryTerms](./dataset_transformer.md#pattern-add-dataset-schema-field-glossaryterms)
 - [Pattern Add Dataset Schema Field globalTags](./dataset_transformer.md#pattern-add-dataset-schema-field-globaltags)
 - [Simple Add Dataset datasetProperties](./dataset_transformer.md#simple-add-dataset-datasetproperties)
 - [Add Dataset datasetProperties](./dataset_transformer.md#add-dataset-datasetproperties)
 - [Simple Add Dataset domains](./dataset_transformer.md#simple-add-dataset-domains)
 - [Pattern Add Dataset domains](./dataset_transformer.md#pattern-add-dataset-domains)
+- [Domain Mapping Based on Tags](./dataset_transformer.md#domain-mapping-based-on-tags)  
+- [Simple Add Dataset dataProduct ](./dataset_transformer.md#simple-add-dataset-dataproduct)
+- [Pattern Add Dataset dataProduct](./dataset_transformer.md#pattern-add-dataset-dataproduct)
+- [Add Dataset dataProduct](./dataset_transformer.md#add-dataset-dataproduct)

metadata-ingestion/setup.py

@@ -404,6 +404,13 @@
     # 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",
+        # We were seeing an error like this `numpy.dtype size changed, may indicate binary incompatibility. Expected 96 from C header, got 88 from PyObject`
+        # with numpy 2.0. This likely indicates a mismatch between scikit-learn and numpy versions.
+        # https://stackoverflow.com/questions/40845304/runtimewarning-numpy-dtype-size-changed-may-indicate-binary-incompatibility
+        "numpy<2",
+    },
     "feast": {
         "feast>=0.34.0,<1",
         "flask-openid>=1.3.0",
@@ -660,6 +667,7 @@
             "qlik-sense",
             "sigma",
             "sac",
+            "cassandra",
         ]
         if plugin
         for dependency in plugins[plugin]
@@ -778,6 +786,7 @@
         "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",