mirror of
https://github.com/datahub-project/datahub.git
synced 2025-07-19 15:42:09 +00:00
81 lines
2.8 KiB
YAML
81 lines
2.8 KiB
YAML
source:
|
|
type: "powerbi"
|
|
config:
|
|
# Your Power BI tenant identifier
|
|
tenant_id: a949d688-67c0-4bf1-a344-e939411c6c0a
|
|
|
|
# Azure AD Application identifier
|
|
client_id: foo
|
|
# Azure AD App client secret
|
|
client_secret: bar
|
|
|
|
# Ingest elements of below PowerBi Workspace into Datahub
|
|
workspace_name_pattern:
|
|
allow:
|
|
- MyWorkspace
|
|
deny:
|
|
- PrivateWorkspace
|
|
|
|
# Enable / Disable ingestion of ownership information for dashboards
|
|
extract_ownership: true
|
|
|
|
# Enable/Disable extracting workspace information to DataHub containers
|
|
extract_workspaces_to_containers: true
|
|
|
|
# Enable / Disable ingestion of endorsements.
|
|
# Please notice that this may overwrite any existing tags defined to ingested entities!
|
|
extract_endorsements_to_tags: false
|
|
|
|
# Optional -- This mapping is optional and only required to configure platform-instance for upstream tables
|
|
# A mapping of PowerBI datasource's server i.e host[:port] to data platform instance.
|
|
# :port is optional and only needed if your datasource server is running on non-standard port.
|
|
# For Google BigQuery the datasource's server is google bigquery project name
|
|
server_to_platform_instance:
|
|
ap-south-1.snowflakecomputing.com:
|
|
platform_instance: operational_instance
|
|
env: DEV
|
|
oracle-server:1920:
|
|
platform_instance: high_performance_production_unit
|
|
env: PROD
|
|
big-query-sales-project:
|
|
platform_instance: sn-2
|
|
env: QA
|
|
|
|
# Need admin_api, only ingest workspace that are modified since...
|
|
modified_since: "2023-02-10T00:00:00.0000000Z"
|
|
|
|
ownership:
|
|
# create powerbi user as datahub corpuser, false will still extract ownership of workspace/ dashboards
|
|
create_corp_user: false
|
|
# use email to build user urn instead of powerbi user identifier
|
|
use_powerbi_email: true
|
|
# remove email suffix like @acryl.io
|
|
remove_email_suffix: true
|
|
# only ingest user with certain authority
|
|
owner_criteria: ["ReadWriteReshareExplore","Owner","Admin"]
|
|
# wrap powerbi tables (datahub dataset) under 1 powerbi dataset (datahub container)
|
|
extract_datasets_to_containers: true
|
|
# only ingest dataset that are endorsed, like "Certified"
|
|
filter_dataset_endorsements:
|
|
allow:
|
|
- Certified
|
|
|
|
# extract powerbi dashboards and tiles
|
|
extract_dashboards: false
|
|
# extract powerbi dataset table schema
|
|
extract_dataset_schema: true
|
|
|
|
# Enable PowerBI dataset profiling
|
|
profiling:
|
|
enabled: false
|
|
# Pattern to limit which resources to profile
|
|
# Matched resource format is following:
|
|
# workspace_name.dataset_name.table_name
|
|
profile_pattern:
|
|
deny:
|
|
- .*
|
|
|
|
|
|
sink:
|
|
# sink configs
|