datahub/metadata-ingestion/docs/sources/hive/hive_recipe.yml

source:
  type: hive
  config:
    # Coordinates
    host_port: localhost:10000
    database: DemoDatabase # optional, if not specified, ingests from all databases

    # Credentials
    username: user # optional
    password: pass # optional

    # For more details on authentication, see the PyHive docs:
    # https://github.com/dropbox/PyHive#passing-session-configuration.
    # LDAP, Kerberos, etc. are supported using connect_args, which can be
    # added under the `options` config parameter.
    #options:
    #  connect_args:
    #    auth: KERBEROS
    #    kerberos_service_name: hive
    #scheme: 'hive+http' # set this if Thrift should use the HTTP transport
    #scheme: 'hive+https' # set this if Thrift should use the HTTP with SSL transport
    #scheme: 'sparksql' # set this for Spark Thrift Server

sink:
  # sink configs

# ---------------------------------------------------------
# Recipe (Azure HDInsight)
# Connecting to Microsoft Azure HDInsight using TLS.
# ---------------------------------------------------------

source:
  type: hive
  config:
    # Coordinates
    host_port: <cluster_name>.azurehdinsight.net:443

    # Credentials
    username: admin
    password: password

    # Options
    options:
      connect_args:
        http_path: "/hive2"
        auth: BASIC

sink:
  # sink configs

# ---------------------------------------------------------
# Recipe (Databricks)
# Ensure that databricks-dbapi is installed. If not, use ```pip install databricks-dbapi``` to install.
# Use the ```http_path``` from your Databricks cluster in the following recipe.
# See (https://docs.databricks.com/integrations/bi/jdbc-odbc-bi.html#get-server-hostname-port-http-path-and-jdbc-url) for instructions to find ```http_path```.
# ---------------------------------------------------------

source:
  type: hive
  config:
    host_port: <databricks workspace URL>:443
    username: token / username
    password: <api token> / password
    scheme: 'databricks+pyhive'

    options:
      connect_args:
        http_path: 'sql/protocolv1/o/xxxyyyzzzaaasa/1234-567890-hello123'

sink:
  # sink configs