Merge pull request #19 from pflooky/dev-full-example

Add in full example with all components, add in example for roles and…

Author: jgperrin

docs/README.md

@@ -12,6 +12,7 @@ This document describes the keys and values expected in a YAML data contract, pe
 * [Roles](#Roles)
 * [Service-level agreement](#Service-level-agreement)
 * [Other properties](#Other-properties)
+* [Full example](#full-example)
 
 ## Notes
 * This contract is containing example values, we reviewed very carefully the consistency of those values, but we cannot guarantee that there are no errors. If you spot one, please raise an [issue](https://github.com/AIDAUserGroup/open-data-contract-standard/issues).
@@ -514,3 +515,246 @@ contractCreatedTs: 2022-11-15 02:59:43
 | customProperties.value    |          | No       | The value of the key.                                                                                             |
 | systemInstance            |          | No       | System Instance name where the dataset resides.                                                                   |
 | contractCreatedTs         |          | No       | Timestamp in UTC of when the data contract was created.                                                           |
+
+## Full example
+
+```yaml
+# What's this data contract about?
+datasetDomain: seller # Domain
+quantumName: my quantum # Data product name
+userConsumptionMode: Analytical
+version: 1.1.0 # Version (follows semantic versioning)
+status: current
+uuid: 53581432-6c55-4ba2-a65f-72344a91553a
+
+# Lots of information
+description:
+  purpose: Views built on top of the seller tables.
+  limitations: null
+  usage: null
+tenant: ClimateQuantumInc
+
+# Getting support
+productDl: product-dl@ClimateQuantum.org
+productSlackChannel: '#product-help'
+productFeedbackUrl: null
+
+# Physical parts / GCP / BigQuery specific
+sourcePlatform: googleCloudPlatform
+sourceSystem: bigQuery
+datasetProject: edw # BQ dataset
+datasetName: access_views # BQ dataset
+
+kind: DataContract
+apiVersion: 2.3.0 # Standard version (follows semantic versioning, previously known as templateVersion)
+
+type: tables
+
+# Physical access
+driver: null
+driverVersion: null
+server: null
+database: pypl-edw.pp_access_views
+username: '${env.username}'
+password: '${env.password}'
+schedulerAppName: name_coming_from_scheduler # NEW 2.1.0 Required if you want to schedule stuff, comes from DataALM.
+
+# Dataset, schema and quality
+dataset:
+  - table: tbl
+    physicalName: tbl_1 # NEW in v2.1.0, Optional, default value is table name + version separated by underscores, as table_1_2_0
+    priorTableName: null # if needed
+    description: Provides core payment metrics
+    authoritativeDefinitions: # NEW in v2.2.0, inspired by the column-level authoritative links
+      - url: https://catalog.data.gov/dataset/air-quality
+        type: businessDefinition
+      - url: https://youtu.be/jbY1BKFj9ec
+        type: videoTutorial
+    tags: null
+    dataGranularity: Aggregation on columns txn_ref_dt, pmt_txn_id
+    columns:
+      - column: txn_ref_dt
+        isPrimary: false # NEW in v2.1.0, Optional, default value is false, indicates whether the column is primary key in the table.
+        primaryKeyPosition: -1
+        businessName: transaction reference date
+        logicalType: date
+        physicalType: date
+        isNullable: false
+        description: null
+        partitionStatus: true
+        partitionKeyPosition: 1
+        clusterStatus: false
+        clusterKeyPosition: -1
+        criticalDataElementStatus: false
+        tags: null
+        classification: null
+        encryptedColumnName: null
+        transformSourceTables:
+          - 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
+        sampleValues:
+          - 2022-10-03
+          - 2020-01-28
+      - column: rcvr_id
+        isPrimary: true # NEW in v2.1.0, Optional, default value is false, indicates whether the column is primary key in the table.
+        primaryKeyPosition: 1
+        businessName: receiver id
+        logicalType: string
+        physicalType: varchar(18)
+        isNullable: false
+        description: A description for column rcvr_id.
+        partitionStatus: false
+        partitionKeyPosition: -1
+        clusterStatus: true
+        clusterKeyPosition: 1
+        criticalDataElementStatus: false
+        tags: null
+        classification: null
+        encryptedColumnName: null
+      - column: rcvr_cntry_code
+        isPrimary: false # NEW in v2.1.0, Optional, default value is false, indicates whether the column is primary key in the table.
+        primaryKeyPosition: -1
+        businessName: receiver country code
+        logicalType: string
+        physicalType: varchar(2)
+        isNullable: false
+        description: null
+        partitionStatus: false
+        partitionKeyPosition: -1
+        clusterStatus: false
+        clusterKeyPosition: -1
+        criticalDataElementStatus: false
+        tags: null
+        classification: null
+        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
+        encryptedColumnName: rcvr_cntry_code_encrypted
+        quality:
+          - code: nullCheck
+            templateName: NullCheck
+            description: column should not contain null values
+            toolName: Elevate
+            toolRuleName: DQ.rw.tab1_2_0_0.rcvr_cntry_code.NullCheck
+            dimension: completeness # dropdown 7 values
+            type: dataQuality
+            severity: error
+            businessImpact: operational
+            scheduleCronExpression: 0 20 * * *
+            customProperties:
+              - property: FIELD_NAME
+                value:
+              - property: COMPARE_TO
+                value:
+              - property: COMPARISON_TYPE
+                value: Greater than
+    quality:
+      - code: countCheck # Required, name of the rule
+        templateName: CountCheck # NEW in v2.1.0 Required
+        description: Ensure row count is within expected volume range       # Optional
+        toolName: Elevate # Required
+        toolRuleName: DQ.rw.tab1.CountCheck # NEW in v2.1.0 Optional (Available only to the users who can change in source code edition)
+        dimension: completeness                                             # Optional
+        type: reconciliation                                                # Optional NEW in v2.1.0 default value for column level check - dataQuality and for table level reconciliation
+        severity: error                                                     # Optional NEW in v2.1.0, default value is error
+        businessImpact: operational                                         # Optional NEW in v2.1.0
+        scheduleCronExpression: 0 20 * * *                                  # Optional NEW in v2.1.0 default schedule - every day 10 a.m. UTC
+
+# Pricing
+price:
+  priceAmount: 9.95
+  priceCurrency: USD
+  priceUnit: megabyte
+
+# Stakeholders
+stakeholders:
+  - username: ceastwood
+    role: Data Scientist
+    dateIn: 2022-08-02
+    dateOut: 2022-10-01
+    replacedByUsername: mhopper
+  - username: mhopper
+    role: Data Scientist
+    dateIn: 2022-10-01
+    dateOut: null
+    replacedByUsername: null
+  - username: daustin
+    role: Owner
+    comment: Keeper of the grail
+    dateIn: 2022-10-01
+    dateOut: null
+    replacedByUsername: null
+
+# 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
+slaDefaultColumn: tab1.txn_ref_dt # Optional, default value is partitionColumn.
+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
+    column: 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
+    column: tab1.txn_ref_dt
+  - property: frequency
+    value: 1
+    valueExt: 1
+    unit: d
+    column: tab1.txn_ref_dt
+  - property: timeOfAvailability
+    value: 09:00-08:00
+    column: tab1.txn_ref_dt
+    driver: regulatory # Describes the importance of the SLA: [regulatory|analytics|operational|...]
+  - property: timeOfAvailability
+    value: 08:00-08:00
+    column: tab1.txn_ref_dt
+    driver: analytics
+
+# 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]
+
+systemInstance: instance.ClimateQuantum.org
+contractCreatedTs: 2022-11-15 02:59:43
+```

examples/README.md

@@ -4,6 +4,7 @@
 This folder contains mainly excerpt of data contracts to illustrate specific sections & behaviors.
 
 ## Table of content
+* [Full example](#full-example)
 * [Fundamentals & demographics](#Demographics)
 * [Datasets & schema](#Dataset-&-schema)
 * [Data quality](#Data-quality)
@@ -13,6 +14,9 @@ This folder contains mainly excerpt of data contracts to illustrate specific sec
 * [Service-level agreement](#Service-level-agreement)
 * [Other properties](#Other-properties)
 
+## Full example
+Look in the [`all`](./all) directory.
+
 ## Demographics
 Look in the [`fundamentals`](./fundamentals) directory.
 
@@ -29,10 +33,10 @@ This section covers pricing when you bill your customer for using this data prod
 Look in the [`stakeholders`](./stakeholders) directory.
 
 ## Roles
-Coming soon.
+Look in the [`roles`](./roles) directory.
 
 ## Service-level agreement
-Coming soon.
+Look in the [`sla`](./sla) directory.
 
 ## Other properties
 Coming soon.