Remove partition fields from Bigquery (#11195)

Co-authored-by: Pere Miquel Brull <peremiquelbrull@gmail.com>
This commit is contained in:
Mayur Singal 2023-04-23 10:08:17 +05:30 committed by GitHub
parent dc7841cf40
commit d0781dcc07
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
8 changed files with 14 additions and 56 deletions

View File

@ -206,7 +206,13 @@ UPDATE dashboard_service_entity
SET json = JSON_REMOVE(json, '$.connection.config.connectionOptions')
WHERE serviceType = 'Superset';
-- Delete partitionQueryDuration, partitionQuery, partitionField from bigquery
UPDATE dbservice_entity
SET json = JSON_REMOVE(json, '$.connection.config.partitionQueryDuration', '$.connection.config.partitionQuery', '$.connection.config.partitionField')
WHERE serviceType = 'BigQuery';
-- Delete supportsQueryComment, scheme, hostPort, supportsProfiler from salesforce
UPDATE dbservice_entity
SET json = JSON_REMOVE(json, '$.connection.config.scheme', '$.connection.config.hostPort', '$.connection.config.supportsProfiler', '$.connection.config.supportsQueryComment')
WHERE serviceType = 'Salesforce';
WHERE serviceType = 'Salesforce';

View File

@ -206,7 +206,13 @@ UPDATE dashboard_service_entity
SET json = json::jsonb #- '{connection,config,connectionOptions}'
WHERE serviceType = 'Superset';
-- Delete partitionQueryDuration, partitionQuery, partitionField from bigquery
UPDATE dbservice_entity
SET json = json::jsonb #- '{connection,config,partitionQueryDuration}' #- '{connection,config,partitionQuery}' #- '{connection,config,partitionField}'
WHERE serviceType = 'BigQuery';
-- Delete supportsQueryComment, scheme, hostPort, supportsProfiler from salesforce
UPDATE dbservice_entity
SET json = json::jsonb #- '{connection,config,supportsQueryComment}' #- '{connection,config,scheme}' #- '{connection,config,hostPort}' #- '{connection,config,supportsProfiler}'
WHERE serviceType = 'Salesforce';
WHERE serviceType = 'Salesforce';

View File

@ -14,9 +14,6 @@ slug: /main-concepts/metadata-standard/schemas/entity/services/connections/datab
- **`hostPort`** *(string)*: BigQuery APIs URL. Default: `bigquery.googleapis.com`.
- **`credentials`**: GCS Credentials. Refer to *../../../../security/credentials/gcsCredentials.json*.
- **`tagCategoryName`** *(string)*: Custom OpenMetadata Tag category name for BigQuery policy tags. Default: `BigqueryPolicyTags`.
- **`partitionQueryDuration`** *(integer)*: Duration for partitioning BigQuery tables. Default: `1`.
- **`partitionQuery`** *(string)*: Partitioning query for BigQuery tables. Default: `select * from {}.{} WHERE {} = "{}" LIMIT 1000`.
- **`partitionField`** *(string)*: Column name on which the BigQuery table will be partitioned. Default: `_PARTITIONTIME`.
- **`taxonomyLocation`** *(string)*: Taxonomy location used to fetch policy tags. Default: `us`.
- **`usageLocation`** *(string)*: Location used to query INFORMATION_SCHEMA.JOBS_BY_PROJECT to fetch usage data. You can pass multi-regions, such as `us` or `eu`, or you specific region. Australia and Asia multi-regions are not yet in GA. Default: `us`.
- **`connectionOptions`**: Refer to *../connectionBasicType.json#/definitions/connectionOptions*.

View File

@ -14,9 +14,6 @@ slug: /main-concepts/metadata-standard/schemas/entity/services/connections/datab
- **`hostPort`** *(string)*: BigQuery APIs URL. Default: `bigquery.googleapis.com`.
- **`credentials`**: GCS Credentials. Refer to *../../../../security/credentials/gcsCredentials.json*.
- **`tagCategoryName`** *(string)*: Custom OpenMetadata Tag category name for BigQuery policy tags. Default: `BigqueryPolicyTags`.
- **`partitionQueryDuration`** *(integer)*: Duration for partitioning BigQuery tables. Default: `1`.
- **`partitionQuery`** *(string)*: Partitioning query for BigQuery tables. Default: `select * from {}.{} WHERE {} = "{}" LIMIT 1000`.
- **`partitionField`** *(string)*: Column name on which the BigQuery table will be partitioned. Default: `_PARTITIONTIME`.
- **`taxonomyLocation`** *(string)*: Taxonomy location used to fetch policy tags. Default: `us`.
- **`usageLocation`** *(string)*: Location used to query INFORMATION_SCHEMA.JOBS_BY_PROJECT to fetch usage data. You can pass multi-regions, such as `us` or `eu`, or you specific region. Australia and Asia multi-regions are not yet in GA. Default: `us`.
- **`connectionOptions`**: Refer to *../connectionBasicType.json#/definitions/connectionOptions*.

View File

@ -14,9 +14,6 @@ slug: /main-concepts/metadata-standard/schemas/entity/services/connections/datab
- **`hostPort`** *(string)*: BigQuery APIs URL. Default: `bigquery.googleapis.com`.
- **`credentials`**: GCS Credentials. Refer to *../../../../security/credentials/gcsCredentials.json*.
- **`tagCategoryName`** *(string)*: Custom OpenMetadata Tag category name for BigQuery policy tags. Default: `BigqueryPolicyTags`.
- **`partitionQueryDuration`** *(integer)*: Duration for partitioning BigQuery tables. Default: `1`.
- **`partitionQuery`** *(string)*: Partitioning query for BigQuery tables. Default: `select * from {}.{} WHERE {} = "{}" LIMIT 1000`.
- **`partitionField`** *(string)*: Column name on which the BigQuery table will be partitioned. Default: `_PARTITIONTIME`.
- **`taxonomyLocation`** *(string)*: Taxonomy location used to fetch policy tags. Default: `us`.
- **`usageLocation`** *(string)*: Location used to query INFORMATION_SCHEMA.JOBS_BY_PROJECT to fetch usage data. You can pass multi-regions, such as `us` or `eu`, or you specific region. Australia and Asia multi-regions are not yet in GA. Default: `us`.
- **`connectionOptions`**: Refer to *../connectionBasicType.json#/definitions/connectionOptions*.

View File

@ -47,24 +47,6 @@
"description": "GCS Credentials",
"$ref": "../../../../security/credentials/gcsCredentials.json"
},
"partitionQueryDuration": {
"title": "Partition Query Duration",
"description": "Duration for partitioning BigQuery tables.",
"type": "integer",
"default": 1
},
"partitionQuery": {
"title": "Partition Query",
"description": "Partitioning query for BigQuery tables.",
"type": "string",
"default": "select * from {}.{} WHERE {} = \"{}\" LIMIT 1000"
},
"partitionField": {
"title": "Partition Field",
"description": "Column name on which the BigQuery table will be partitioned.",
"type": "string",
"default": "_PARTITIONTIME"
},
"taxonomyProjectID": {
"title": "Taxonomy Project IDs",
"description": "Project IDs used to fetch policy tags",

View File

@ -132,27 +132,6 @@ $$section
This is the URL of the certificate that verifies the authenticity of the service account. To fetch this key, look for the value associated with the `client_x509_cert_url` key in the service account key file.
$$
$$section
### Partition Query Duration $(id="partitionQueryDuration")
Duration for partitioning BigQuery tables.
<!-- partitionQueryDuration to be updated -->
$$
$$section
### Partition Query $(id="partitionQuery")
Partitioning query for BigQuery tables.
<!-- partitionQuery to be updated -->
$$
$$section
### Partition Field $(id="partitionField")
Column name on which the BigQuery table will be partitioned.
<!-- partitionField to be updated -->
$$
$$section
### Taxonomy Project ID $(id="taxonomyProjectID")

View File

@ -40,13 +40,10 @@ export const mockIngestionWorkFlow = {
type: 'BigQuery',
scheme: 'bigquery',
hostPort: 'bigquery.googleapis.com',
partitionField: '_PARTITIONTIME',
partitionQuery: 'select * from {}.{} WHERE {} = "{}" LIMIT 1000',
tagCategoryName: 'BigqueryPolicyTags',
connectionOptions: {},
connectionArguments: {},
enablePolicyTagImport: true,
partitionQueryDuration: 1,
supportsUsageExtraction: true,
supportsMetadataExtraction: true,
},
@ -112,13 +109,10 @@ export const mockService = {
type: 'BigQuery',
scheme: 'bigquery',
hostPort: 'bigquery.googleapis.com',
partitionField: '_PARTITIONTIME',
partitionQuery: 'select * from {}.{} WHERE {} = "{}" LIMIT 1000',
tagCategoryName: 'BigqueryPolicyTags',
connectionOptions: {},
connectionArguments: {},
enablePolicyTagImport: true,
partitionQueryDuration: 1,
supportsUsageExtraction: true,
supportsMetadataExtraction: true,
},