full example
# What's this data contract about?
domain: seller # Domain
dataProduct: my quantum # Data product name
version: 1.1.0 # Version (follows semantic versioning)
status: active
id: 53581432-6c55-4ba2-a65f-72344a91553a
authoritativeDefinitions:
- type: canonical
url: https://github.com/bitol-io/open-data-contract-standard/blob/main/docs/examples/all/full-example.odcs.yaml
description: Canonical URL to the latest version of the contract.
# Lots of information
description:
purpose: Views built on top of the seller tables.
limitations: Data based on seller perspective, no buyer information
usage: Predict sales over time
authoritativeDefinitions:
- type: privacy-statement
url: https://example.com/gdpr.pdf
tenant: ClimateQuantumInc
kind: DataContract
apiVersion: v3.1.0 # Standard version (follows semantic versioning)
# Infrastructure & servers
servers:
- server: my-postgres
type: postgres
host: localhost
port: 5432
database: pypl-edw
schema: pp_access_views
# Dataset, schema, and quality
schema:
- id: tbl_obj
name: tbl
physicalName: tbl_1
physicalType: table
businessName: Core Payment Metrics
description: Provides core payment metrics
authoritativeDefinitions:
- url: https://catalog.data.gov/dataset/air-quality
type: businessDefinition
- url: https://youtu.be/jbY1BKFj9ec
type: videoTutorial
tags: [ 'finance', 'payments']
dataGranularityDescription: Aggregation on columns txn_ref_dt, pmt_txn_id
# Schema-level relationships (for composite keys)
relationships:
- type: foreignKey
from:
- tbl.rcvr_id
- tbl.rcvr_cntry_code
to:
- receivers.id
- receivers.country_code
customProperties:
- property: description
value: "Composite key linking to receivers table"
- property: cardinality
value: "many-to-one"
properties:
- id: txn_ref_dt_prop
name: transaction_reference_date
physicalName: txn_ref_dt
primaryKey: false
primaryKeyPosition: -1
businessName: transaction reference date
logicalType: date
physicalType: date
required: false
description: Reference date for transaction
partitioned: true
partitionKeyPosition: 1
criticalDataElement: false
tags: [ ]
classification: public
transformSourceObjects:
- table_name_1
- table_name_2
- table_name_3
transformLogic: sel t1.txn_dt as txn_ref_dt from table_name_1 as t1, table_name_2 as t2, table_name_3 as t3 where t1.txn_dt=date-3
transformDescription: defines the logic in business terms; logic for dummies
examples:
- "2022-10-03"
- "2020-01-28"
customProperties:
- property: anonymizationStrategy
value: none
- id: rcvr_id_prop
name: rcvr_id
primaryKey: true
primaryKeyPosition: 1
businessName: receiver id
logicalType: string
physicalType: varchar(18)
required: false
description: A description for column rcvr_id.
partitioned: false
partitionKeyPosition: -1
criticalDataElement: false
tags: [ 'uid' ]
classification: restricted
# Property-level relationship (from is implicit)
relationships:
- to: receivers.id
type: foreignKey
customProperties:
- property: description
value: "Links to receiver master data"
- id: rcvr_cntry_code_prop
name: rcvr_cntry_code
primaryKey: false
primaryKeyPosition: -1
businessName: receiver country code
logicalType: string
physicalType: varchar(2)
required: false
description: Country code
partitioned: false
partitionKeyPosition: -1
criticalDataElement: false
tags: [ ]
classification: public
authoritativeDefinitions:
- url: https://collibra.com/asset/742b358f-71a5-4ab1-bda4-dcdba9418c25
type: businessDefinition
- url: https://github.com/myorg/myrepo
type: transformationImplementation
- url: jdbc:postgresql://localhost:5432/adventureworks/tbl_1/rcvr_cntry_code
type: implementation
encryptedName: rcvr_cntry_code_encrypted
quality:
- metric: nullValues
mustBe: 0
description: column should not contain null values
dimension: completeness
type: library
severity: error
businessImpact: operational
schedule: 0 20 * * *
scheduler: cron
customProperties:
- property: FIELD_NAME
value:
- property: COMPARE_TO
value:
- property: COMPARISON_TYPE
value: Greater than
quality:
- metric: rowCount
mustBeGreaterThan: 1000000
type: library
description: Ensure row count is within expected volume range
dimension: completeness
method: reconciliation
severity: error
businessImpact: operational
schedule: 0 20 * * *
scheduler: cron
customProperties:
- property: business-key
value:
- txn_ref_dt
- rcvr_id
# Receivers master table
- id: receivers_obj
name: receivers
physicalName: receivers_master
physicalType: table
businessName: Receivers Master Data
description: Master data for all receivers
tags: [ 'master-data', 'receivers' ]
properties:
- id: receiver_id_prop
name: id
primaryKey: true
primaryKeyPosition: 1
businessName: receiver identifier
logicalType: string
physicalType: varchar(18)
required: true
description: Unique identifier for receiver
unique: true
classification: restricted
- id: country_code_prop
name: country_code
primaryKey: true
primaryKeyPosition: 2
businessName: receiver country
logicalType: string
physicalType: varchar(2)
required: true
description: Country code of the receiver
classification: public
- id: receiver_name_prop
name: receiver_name
businessName: receiver name
logicalType: string
physicalType: varchar(255)
required: true
description: Name of the receiver
classification: restricted
- id: receiver_type_prop
name: receiver_type
businessName: receiver type
logicalType: string
physicalType: varchar(20)
required: false
description: Type of receiver (individual, business, etc.)
classification: public
# Example of nested reference
relationships:
- to: receiver_types.type_code
customProperties:
- property: description
value: "Links to receiver type definitions"
# Pricing
price:
priceAmount: 9.95
priceCurrency: USD
priceUnit: megabyte
# Team
team:
name: my-team
description: The team owning the data contract
members:
- username: ceastwood
role: Data Scientist
dateIn: "2022-08-02"
dateOut: "2022-10-01"
replacedByUsername: mhopper
- username: mhopper
role: Data Scientist
dateIn: "2022-10-01"
- username: daustin
role: Owner
description: Keeper of the grail
dateIn: "2022-10-01"
# Roles
roles:
- role: microstrategy_user_opr
access: read
firstLevelApprovers: Reporting Manager
secondLevelApprovers: 'mandolorian'
- role: bq_queryman_user_opr
access: read
firstLevelApprovers: Reporting Manager
secondLevelApprovers: na
- role: risk_data_access_opr
access: read
firstLevelApprovers: Reporting Manager
secondLevelApprovers: 'dathvador'
- role: bq_unica_user_opr
access: write
firstLevelApprovers: Reporting Manager
secondLevelApprovers: 'mickey'
# SLA
slaProperties:
- property: latency # Property, see list of values in DP QoS
value: 4
unit: d # d, day, days for days; y, yr, years for years
element: tab1.txn_ref_dt # This would not be needed as it is the same table.column as the default one
- property: generalAvailability
value: "2022-05-12T09:30:10-08:00"
- property: endOfSupport
value: "2032-05-12T09:30:10-08:00"
- property: endOfLife
value: "2042-05-12T09:30:10-08:00"
- property: retention
value: 3
unit: y
element: tab1.txn_ref_dt
- property: frequency
value: 1
valueExt: 1
unit: d
element: tab1.txn_ref_dt
- property: timeOfAvailability
value: 09:00-08:00
element: tab1.txn_ref_dt
driver: regulatory # Describes the importance of the SLA: [regulatory|analytics|operational|...]
- property: timeOfAvailability
value: 08:00-08:00
element: tab1.txn_ref_dt
driver: analytics
# Support
support:
- channel: '#product-help' # Simple Slack communication channel
tool: slack
- channel: datacontract-ann # Simple distribution list
tool: email
url: mailto:datacontract-ann@bitol.io
- channel: Feedback # Product Feedback
description: General Product Feedback (Public)
url: https://product-feedback.com
- channel: 'product-issues'
tool: teams
scope: issues
customProperties:
- property: servicehours
value: 9-5 CET
# Tags
tags:
- transactions
# Custom properties
customProperties:
- property: refRulesetName
value: gcsc.ruleset.name
- property: somePropertyName
value: property.value
- property: dataprocClusterName # Used for specific applications like Elevate
value: [ cluster name ]
contractCreatedTs: "2022-11-15T02:59:43+00:00"