googleapis
Version:
Google APIs Client Library for Node.js
1,136 lines • 421 kB
TypeScript
/// <reference types="node" />
import { OAuth2Client, JWT, Compute, UserRefreshClient, BaseExternalAccountClient, GaxiosPromise, GoogleConfigurable, MethodOptions, StreamMethodOptions, GlobalOptions, GoogleAuth, BodyResponseCallback, APIRequestContext } from 'googleapis-common';
import { Readable } from 'stream';
export declare namespace dataplex_v1 {
export interface Options extends GlobalOptions {
version: 'v1';
}
interface StandardParameters {
/**
* Auth client or API Key for the request
*/
auth?: string | OAuth2Client | JWT | Compute | UserRefreshClient | BaseExternalAccountClient | GoogleAuth;
/**
* V1 error format.
*/
'$.xgafv'?: string;
/**
* OAuth access token.
*/
access_token?: string;
/**
* Data format for response.
*/
alt?: string;
/**
* JSONP
*/
callback?: string;
/**
* Selector specifying which fields to include in a partial response.
*/
fields?: string;
/**
* API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token.
*/
key?: string;
/**
* OAuth 2.0 token for the current user.
*/
oauth_token?: string;
/**
* Returns response with indentations and line breaks.
*/
prettyPrint?: boolean;
/**
* Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters.
*/
quotaUser?: string;
/**
* Legacy upload protocol for media (e.g. "media", "multipart").
*/
uploadType?: string;
/**
* Upload protocol for media (e.g. "raw", "multipart").
*/
upload_protocol?: string;
}
/**
* Cloud Dataplex API
*
* Dataplex API is used to manage the lifecycle of data lakes.
*
* @example
* ```js
* const {google} = require('googleapis');
* const dataplex = google.dataplex('v1');
* ```
*/
export class Dataplex {
context: APIRequestContext;
projects: Resource$Projects;
constructor(options: GlobalOptions, google?: GoogleConfigurable);
}
/**
* A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance: service Foo { rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty); \}
*/
export interface Schema$Empty {
}
/**
* Action represents an issue requiring administrator action for resolution.
*/
export interface Schema$GoogleCloudDataplexV1Action {
/**
* Output only. The relative resource name of the asset, of the form: projects/{project_number\}/locations/{location_id\}/lakes/{lake_id\}/zones/{zone_id\}/assets/{asset_id\}.
*/
asset?: string | null;
/**
* The category of issue associated with the action.
*/
category?: string | null;
/**
* The list of data locations associated with this action. Cloud Storage locations are represented as URI paths(E.g. gs://bucket/table1/year=2020/month=Jan/). BigQuery locations refer to resource names(E.g. bigquery.googleapis.com/projects/project-id/datasets/dataset-id).
*/
dataLocations?: string[] | null;
/**
* The time that the issue was detected.
*/
detectTime?: string | null;
/**
* Details for issues related to applying security policy.
*/
failedSecurityPolicyApply?: Schema$GoogleCloudDataplexV1ActionFailedSecurityPolicyApply;
/**
* Details for issues related to incompatible schemas detected within data.
*/
incompatibleDataSchema?: Schema$GoogleCloudDataplexV1ActionIncompatibleDataSchema;
/**
* Details for issues related to invalid or unsupported data formats.
*/
invalidDataFormat?: Schema$GoogleCloudDataplexV1ActionInvalidDataFormat;
/**
* Details for issues related to invalid data arrangement.
*/
invalidDataOrganization?: Schema$GoogleCloudDataplexV1ActionInvalidDataOrganization;
/**
* Details for issues related to invalid or unsupported data partition structure.
*/
invalidDataPartition?: Schema$GoogleCloudDataplexV1ActionInvalidDataPartition;
/**
* Detailed description of the issue requiring action.
*/
issue?: string | null;
/**
* Output only. The relative resource name of the lake, of the form: projects/{project_number\}/locations/{location_id\}/lakes/{lake_id\}.
*/
lake?: string | null;
/**
* Details for issues related to absence of data within managed resources.
*/
missingData?: Schema$GoogleCloudDataplexV1ActionMissingData;
/**
* Details for issues related to absence of a managed resource.
*/
missingResource?: Schema$GoogleCloudDataplexV1ActionMissingResource;
/**
* Output only. The relative resource name of the action, of the form: projects/{project\}/locations/{location\}/lakes/{lake\}/actions/{action\} projects/{project\}/locations/{location\}/lakes/{lake\}/zones/{zone\}/actions/{action\} projects/{project\}/locations/{location\}/lakes/{lake\}/zones/{zone\}/assets/{asset\}/actions/{action\}.
*/
name?: string | null;
/**
* Details for issues related to lack of permissions to access data resources.
*/
unauthorizedResource?: Schema$GoogleCloudDataplexV1ActionUnauthorizedResource;
/**
* Output only. The relative resource name of the zone, of the form: projects/{project_number\}/locations/{location_id\}/lakes/{lake_id\}/zones/{zone_id\}.
*/
zone?: string | null;
}
/**
* Failed to apply security policy to the managed resource(s) under a lake, zone or an asset. For a lake or zone resource, one or more underlying assets has a failure applying security policy to the associated managed resource.
*/
export interface Schema$GoogleCloudDataplexV1ActionFailedSecurityPolicyApply {
/**
* Resource name of one of the assets with failing security policy application. Populated for a lake or zone resource only.
*/
asset?: string | null;
}
/**
* Action details for incompatible schemas detected by discovery.
*/
export interface Schema$GoogleCloudDataplexV1ActionIncompatibleDataSchema {
/**
* The existing and expected schema of the table. The schema is provided as a JSON formatted structure listing columns and data types.
*/
existingSchema?: string | null;
/**
* The new and incompatible schema within the table. The schema is provided as a JSON formatted structured listing columns and data types.
*/
newSchema?: string | null;
/**
* The list of data locations sampled and used for format/schema inference.
*/
sampledDataLocations?: string[] | null;
/**
* Whether the action relates to a schema that is incompatible or modified.
*/
schemaChange?: string | null;
/**
* The name of the table containing invalid data.
*/
table?: string | null;
}
/**
* Action details for invalid or unsupported data files detected by discovery.
*/
export interface Schema$GoogleCloudDataplexV1ActionInvalidDataFormat {
/**
* The expected data format of the entity.
*/
expectedFormat?: string | null;
/**
* The new unexpected data format within the entity.
*/
newFormat?: string | null;
/**
* The list of data locations sampled and used for format/schema inference.
*/
sampledDataLocations?: string[] | null;
}
/**
* Action details for invalid data arrangement.
*/
export interface Schema$GoogleCloudDataplexV1ActionInvalidDataOrganization {
}
/**
* Action details for invalid or unsupported partitions detected by discovery.
*/
export interface Schema$GoogleCloudDataplexV1ActionInvalidDataPartition {
/**
* The issue type of InvalidDataPartition.
*/
expectedStructure?: string | null;
}
/**
* Action details for absence of data detected by discovery.
*/
export interface Schema$GoogleCloudDataplexV1ActionMissingData {
}
/**
* Action details for resource references in assets that cannot be located.
*/
export interface Schema$GoogleCloudDataplexV1ActionMissingResource {
}
/**
* Action details for unauthorized resource issues raised to indicate that the service account associated with the lake instance is not authorized to access or manage the resource associated with an asset.
*/
export interface Schema$GoogleCloudDataplexV1ActionUnauthorizedResource {
}
/**
* An asset represents a cloud resource that is being managed within a lake as a member of a zone.
*/
export interface Schema$GoogleCloudDataplexV1Asset {
/**
* Output only. The time when the asset was created.
*/
createTime?: string | null;
/**
* Optional. Description of the asset.
*/
description?: string | null;
/**
* Optional. Specification of the discovery feature applied to data referenced by this asset. When this spec is left unset, the asset will use the spec set on the parent zone.
*/
discoverySpec?: Schema$GoogleCloudDataplexV1AssetDiscoverySpec;
/**
* Output only. Status of the discovery feature applied to data referenced by this asset.
*/
discoveryStatus?: Schema$GoogleCloudDataplexV1AssetDiscoveryStatus;
/**
* Optional. User friendly display name.
*/
displayName?: string | null;
/**
* Optional. User defined labels for the asset.
*/
labels?: {
[key: string]: string;
} | null;
/**
* Output only. The relative resource name of the asset, of the form: projects/{project_number\}/locations/{location_id\}/lakes/{lake_id\}/zones/{zone_id\}/assets/{asset_id\}.
*/
name?: string | null;
/**
* Required. Specification of the resource that is referenced by this asset.
*/
resourceSpec?: Schema$GoogleCloudDataplexV1AssetResourceSpec;
/**
* Output only. Status of the resource referenced by this asset.
*/
resourceStatus?: Schema$GoogleCloudDataplexV1AssetResourceStatus;
/**
* Output only. Status of the security policy applied to resource referenced by this asset.
*/
securityStatus?: Schema$GoogleCloudDataplexV1AssetSecurityStatus;
/**
* Output only. Current state of the asset.
*/
state?: string | null;
/**
* Output only. System generated globally unique ID for the asset. This ID will be different if the asset is deleted and re-created with the same name.
*/
uid?: string | null;
/**
* Output only. The time when the asset was last updated.
*/
updateTime?: string | null;
}
/**
* Settings to manage the metadata discovery and publishing for an asset.
*/
export interface Schema$GoogleCloudDataplexV1AssetDiscoverySpec {
/**
* Optional. Configuration for CSV data.
*/
csvOptions?: Schema$GoogleCloudDataplexV1AssetDiscoverySpecCsvOptions;
/**
* Optional. Whether discovery is enabled.
*/
enabled?: boolean | null;
/**
* Optional. The list of patterns to apply for selecting data to exclude during discovery. For Cloud Storage bucket assets, these are interpreted as glob patterns used to match object names. For BigQuery dataset assets, these are interpreted as patterns to match table names.
*/
excludePatterns?: string[] | null;
/**
* Optional. The list of patterns to apply for selecting data to include during discovery if only a subset of the data should considered. For Cloud Storage bucket assets, these are interpreted as glob patterns used to match object names. For BigQuery dataset assets, these are interpreted as patterns to match table names.
*/
includePatterns?: string[] | null;
/**
* Optional. Configuration for Json data.
*/
jsonOptions?: Schema$GoogleCloudDataplexV1AssetDiscoverySpecJsonOptions;
/**
* Optional. Cron schedule (https://en.wikipedia.org/wiki/Cron) for running discovery periodically. Successive discovery runs must be scheduled at least 60 minutes apart. The default value is to run discovery every 60 minutes. To explicitly set a timezone to the cron tab, apply a prefix in the cron tab: "CRON_TZ=${IANA_TIME_ZONE\}" or TZ=${IANA_TIME_ZONE\}". The ${IANA_TIME_ZONE\} may only be a valid string from IANA time zone database. For example, CRON_TZ=America/New_York 1 * * * *, or TZ=America/New_York 1 * * * *.
*/
schedule?: string | null;
}
/**
* Describe CSV and similar semi-structured data formats.
*/
export interface Schema$GoogleCloudDataplexV1AssetDiscoverySpecCsvOptions {
/**
* Optional. The delimiter being used to separate values. This defaults to ','.
*/
delimiter?: string | null;
/**
* Optional. Whether to disable the inference of data type for CSV data. If true, all columns will be registered as strings.
*/
disableTypeInference?: boolean | null;
/**
* Optional. The character encoding of the data. The default is UTF-8.
*/
encoding?: string | null;
/**
* Optional. The number of rows to interpret as header rows that should be skipped when reading data rows.
*/
headerRows?: number | null;
}
/**
* Describe JSON data format.
*/
export interface Schema$GoogleCloudDataplexV1AssetDiscoverySpecJsonOptions {
/**
* Optional. Whether to disable the inference of data type for Json data. If true, all columns will be registered as their primitive types (strings, number or boolean).
*/
disableTypeInference?: boolean | null;
/**
* Optional. The character encoding of the data. The default is UTF-8.
*/
encoding?: string | null;
}
/**
* Status of discovery for an asset.
*/
export interface Schema$GoogleCloudDataplexV1AssetDiscoveryStatus {
/**
* The duration of the last discovery run.
*/
lastRunDuration?: string | null;
/**
* The start time of the last discovery run.
*/
lastRunTime?: string | null;
/**
* Additional information about the current state.
*/
message?: string | null;
/**
* The current status of the discovery feature.
*/
state?: string | null;
/**
* Data Stats of the asset reported by discovery.
*/
stats?: Schema$GoogleCloudDataplexV1AssetDiscoveryStatusStats;
/**
* Last update time of the status.
*/
updateTime?: string | null;
}
/**
* The aggregated data statistics for the asset reported by discovery.
*/
export interface Schema$GoogleCloudDataplexV1AssetDiscoveryStatusStats {
/**
* The count of data items within the referenced resource.
*/
dataItems?: string | null;
/**
* The number of stored data bytes within the referenced resource.
*/
dataSize?: string | null;
/**
* The count of fileset entities within the referenced resource.
*/
filesets?: string | null;
/**
* The count of table entities within the referenced resource.
*/
tables?: string | null;
}
/**
* Identifies the cloud resource that is referenced by this asset.
*/
export interface Schema$GoogleCloudDataplexV1AssetResourceSpec {
/**
* Immutable. Relative name of the cloud resource that contains the data that is being managed within a lake. For example: projects/{project_number\}/buckets/{bucket_id\} projects/{project_number\}/datasets/{dataset_id\}
*/
name?: string | null;
/**
* Optional. Determines how read permissions are handled for each asset and their associated tables. Only available to storage buckets assets.
*/
readAccessMode?: string | null;
/**
* Required. Immutable. Type of resource.
*/
type?: string | null;
}
/**
* Status of the resource referenced by an asset.
*/
export interface Schema$GoogleCloudDataplexV1AssetResourceStatus {
/**
* Output only. Service account associated with the BigQuery Connection.
*/
managedAccessIdentity?: string | null;
/**
* Additional information about the current state.
*/
message?: string | null;
/**
* The current state of the managed resource.
*/
state?: string | null;
/**
* Last update time of the status.
*/
updateTime?: string | null;
}
/**
* Security policy status of the asset. Data security policy, i.e., readers, writers & owners, should be specified in the lake/zone/asset IAM policy.
*/
export interface Schema$GoogleCloudDataplexV1AssetSecurityStatus {
/**
* Additional information about the current state.
*/
message?: string | null;
/**
* The current state of the security policy applied to the attached resource.
*/
state?: string | null;
/**
* Last update time of the status.
*/
updateTime?: string | null;
}
/**
* Aggregated status of the underlying assets of a lake or zone.
*/
export interface Schema$GoogleCloudDataplexV1AssetStatus {
/**
* Number of active assets.
*/
activeAssets?: number | null;
/**
* Number of assets that are in process of updating the security policy on attached resources.
*/
securityPolicyApplyingAssets?: number | null;
/**
* Last update time of the status.
*/
updateTime?: string | null;
}
/**
* Cancel task jobs.
*/
export interface Schema$GoogleCloudDataplexV1CancelJobRequest {
}
/**
* Content represents a user-visible notebook or a sql script
*/
export interface Schema$GoogleCloudDataplexV1Content {
/**
* Output only. Content creation time.
*/
createTime?: string | null;
/**
* Required. Content data in string format.
*/
dataText?: string | null;
/**
* Optional. Description of the content.
*/
description?: string | null;
/**
* Optional. User defined labels for the content.
*/
labels?: {
[key: string]: string;
} | null;
/**
* Output only. The relative resource name of the content, of the form: projects/{project_id\}/locations/{location_id\}/lakes/{lake_id\}/content/{content_id\}
*/
name?: string | null;
/**
* Notebook related configurations.
*/
notebook?: Schema$GoogleCloudDataplexV1ContentNotebook;
/**
* Required. The path for the Content file, represented as directory structure. Unique within a lake. Limited to alphanumerics, hyphens, underscores, dots and slashes.
*/
path?: string | null;
/**
* Sql Script related configurations.
*/
sqlScript?: Schema$GoogleCloudDataplexV1ContentSqlScript;
/**
* Output only. System generated globally unique ID for the content. This ID will be different if the content is deleted and re-created with the same name.
*/
uid?: string | null;
/**
* Output only. The time when the content was last updated.
*/
updateTime?: string | null;
}
/**
* Configuration for Notebook content.
*/
export interface Schema$GoogleCloudDataplexV1ContentNotebook {
/**
* Required. Kernel Type of the notebook.
*/
kernelType?: string | null;
}
/**
* Configuration for the Sql Script content.
*/
export interface Schema$GoogleCloudDataplexV1ContentSqlScript {
/**
* Required. Query Engine to be used for the Sql Query.
*/
engine?: string | null;
}
/**
* DataAccessSpec holds the access control configuration to be enforced on data stored within resources (eg: rows, columns in BigQuery Tables). When associated with data, the data is only accessible to principals explicitly granted access through the DataAccessSpec. Principals with access to the containing resource are not implicitly granted access.
*/
export interface Schema$GoogleCloudDataplexV1DataAccessSpec {
/**
* Optional. The format of strings follows the pattern followed by IAM in the bindings. user:{email\}, serviceAccount:{email\} group:{email\}. The set of principals to be granted reader role on data stored within resources.
*/
readers?: string[] | null;
}
/**
* Denotes one dataAttribute in a dataTaxonomy, for example, PII. DataAttribute resources can be defined in a hierarchy. A single dataAttribute resource can contain specs of multiple types PII - ResourceAccessSpec : - readers :foo@bar.com - DataAccessSpec : - readers :bar@foo.com
*/
export interface Schema$GoogleCloudDataplexV1DataAttribute {
/**
* Output only. The number of child attributes present for this attribute.
*/
attributeCount?: number | null;
/**
* Output only. The time when the DataAttribute was created.
*/
createTime?: string | null;
/**
* Optional. Specified when applied to data stored on the resource (eg: rows, columns in BigQuery Tables).
*/
dataAccessSpec?: Schema$GoogleCloudDataplexV1DataAccessSpec;
/**
* Optional. Description of the DataAttribute.
*/
description?: string | null;
/**
* Optional. User friendly display name.
*/
displayName?: string | null;
/**
* This checksum is computed by the server based on the value of other fields, and may be sent on update and delete requests to ensure the client has an up-to-date value before proceeding.
*/
etag?: string | null;
/**
* Optional. User-defined labels for the DataAttribute.
*/
labels?: {
[key: string]: string;
} | null;
/**
* Output only. The relative resource name of the dataAttribute, of the form: projects/{project_number\}/locations/{location_id\}/dataTaxonomies/{dataTaxonomy\}/attributes/{data_attribute_id\}.
*/
name?: string | null;
/**
* Optional. The ID of the parent DataAttribute resource, should belong to the same data taxonomy. Circular dependency in parent chain is not valid. Maximum depth of the hierarchy allowed is 4. a -\> b -\> c -\> d -\> e, depth = 4
*/
parentId?: string | null;
/**
* Optional. Specified when applied to a resource (eg: Cloud Storage bucket, BigQuery dataset, BigQuery table).
*/
resourceAccessSpec?: Schema$GoogleCloudDataplexV1ResourceAccessSpec;
/**
* Output only. System generated globally unique ID for the DataAttribute. This ID will be different if the DataAttribute is deleted and re-created with the same name.
*/
uid?: string | null;
/**
* Output only. The time when the DataAttribute was last updated.
*/
updateTime?: string | null;
}
/**
* DataAttributeBinding represents binding of attributes to resources. Eg: Bind 'CustomerInfo' entity with 'PII' attribute.
*/
export interface Schema$GoogleCloudDataplexV1DataAttributeBinding {
/**
* Optional. List of attributes to be associated with the resource, provided in the form: projects/{project\}/locations/{location\}/dataTaxonomies/{dataTaxonomy\}/attributes/{data_attribute_id\}
*/
attributes?: string[] | null;
/**
* Output only. The time when the DataAttributeBinding was created.
*/
createTime?: string | null;
/**
* Optional. Description of the DataAttributeBinding.
*/
description?: string | null;
/**
* Optional. User friendly display name.
*/
displayName?: string | null;
/**
* This checksum is computed by the server based on the value of other fields, and may be sent on update and delete requests to ensure the client has an up-to-date value before proceeding. Etags must be used when calling the DeleteDataAttributeBinding and the UpdateDataAttributeBinding method.
*/
etag?: string | null;
/**
* Optional. User-defined labels for the DataAttributeBinding.
*/
labels?: {
[key: string]: string;
} | null;
/**
* Output only. The relative resource name of the Data Attribute Binding, of the form: projects/{project_number\}/locations/{location\}/dataAttributeBindings/{data_attribute_binding_id\}
*/
name?: string | null;
/**
* Optional. The list of paths for items within the associated resource (eg. columns and partitions within a table) along with attribute bindings.
*/
paths?: Schema$GoogleCloudDataplexV1DataAttributeBindingPath[];
/**
* Optional. Immutable. The resource name of the resource that is associated to attributes. Presently, only entity resource is supported in the form: projects/{project\}/locations/{location\}/lakes/{lake\}/zones/{zone\}/entities/{entity_id\} Must belong in the same project and region as the attribute binding, and there can only exist one active binding for a resource.
*/
resource?: string | null;
/**
* Output only. System generated globally unique ID for the DataAttributeBinding. This ID will be different if the DataAttributeBinding is deleted and re-created with the same name.
*/
uid?: string | null;
/**
* Output only. The time when the DataAttributeBinding was last updated.
*/
updateTime?: string | null;
}
/**
* Represents a subresource of the given resource, and associated bindings with it. Currently supported subresources are column and partition schema fields within a table.
*/
export interface Schema$GoogleCloudDataplexV1DataAttributeBindingPath {
/**
* Optional. List of attributes to be associated with the path of the resource, provided in the form: projects/{project\}/locations/{location\}/dataTaxonomies/{dataTaxonomy\}/attributes/{data_attribute_id\}
*/
attributes?: string[] | null;
/**
* Required. The name identifier of the path. Nested columns should be of the form: 'address.city'.
*/
name?: string | null;
}
/**
* DataProfileResult defines the output of DataProfileScan. Each field of the table will have field type specific profile result.
*/
export interface Schema$GoogleCloudDataplexV1DataProfileResult {
/**
* Output only. The result of post scan actions.
*/
postScanActionsResult?: Schema$GoogleCloudDataplexV1DataProfileResultPostScanActionsResult;
/**
* The profile information per field.
*/
profile?: Schema$GoogleCloudDataplexV1DataProfileResultProfile;
/**
* The count of rows scanned.
*/
rowCount?: string | null;
/**
* The data scanned for this result.
*/
scannedData?: Schema$GoogleCloudDataplexV1ScannedData;
}
/**
* The result of post scan actions of DataProfileScan job.
*/
export interface Schema$GoogleCloudDataplexV1DataProfileResultPostScanActionsResult {
/**
* Output only. The result of BigQuery export post scan action.
*/
bigqueryExportResult?: Schema$GoogleCloudDataplexV1DataProfileResultPostScanActionsResultBigQueryExportResult;
}
/**
* The result of BigQuery export post scan action.
*/
export interface Schema$GoogleCloudDataplexV1DataProfileResultPostScanActionsResultBigQueryExportResult {
/**
* Output only. Additional information about the BigQuery exporting.
*/
message?: string | null;
/**
* Output only. Execution state for the BigQuery exporting.
*/
state?: string | null;
}
/**
* Contains name, type, mode and field type specific profile information.
*/
export interface Schema$GoogleCloudDataplexV1DataProfileResultProfile {
/**
* List of fields with structural and profile information for each field.
*/
fields?: Schema$GoogleCloudDataplexV1DataProfileResultProfileField[];
}
/**
* A field within a table.
*/
export interface Schema$GoogleCloudDataplexV1DataProfileResultProfileField {
/**
* The mode of the field. Possible values include: REQUIRED, if it is a required field. NULLABLE, if it is an optional field. REPEATED, if it is a repeated field.
*/
mode?: string | null;
/**
* The name of the field.
*/
name?: string | null;
/**
* Profile information for the corresponding field.
*/
profile?: Schema$GoogleCloudDataplexV1DataProfileResultProfileFieldProfileInfo;
/**
* The data type retrieved from the schema of the data source. For instance, for a BigQuery native table, it is the BigQuery Table Schema (https://cloud.google.com/bigquery/docs/reference/rest/v2/tables#tablefieldschema). For a Dataplex Entity, it is the Entity Schema (https://cloud.google.com/dataplex/docs/reference/rpc/google.cloud.dataplex.v1#type_3).
*/
type?: string | null;
}
/**
* The profile information for each field type.
*/
export interface Schema$GoogleCloudDataplexV1DataProfileResultProfileFieldProfileInfo {
/**
* Ratio of rows with distinct values against total scanned rows. Not available for complex non-groupable field type RECORD and fields with REPEATABLE mode.
*/
distinctRatio?: number | null;
/**
* Double type field information.
*/
doubleProfile?: Schema$GoogleCloudDataplexV1DataProfileResultProfileFieldProfileInfoDoubleFieldInfo;
/**
* Integer type field information.
*/
integerProfile?: Schema$GoogleCloudDataplexV1DataProfileResultProfileFieldProfileInfoIntegerFieldInfo;
/**
* Ratio of rows with null value against total scanned rows.
*/
nullRatio?: number | null;
/**
* String type field information.
*/
stringProfile?: Schema$GoogleCloudDataplexV1DataProfileResultProfileFieldProfileInfoStringFieldInfo;
/**
* The list of top N non-null values, frequency and ratio with which they occur in the scanned data. N is 10 or equal to the number of distinct values in the field, whichever is smaller. Not available for complex non-groupable field type RECORD and fields with REPEATABLE mode.
*/
topNValues?: Schema$GoogleCloudDataplexV1DataProfileResultProfileFieldProfileInfoTopNValue[];
}
/**
* The profile information for a double type field.
*/
export interface Schema$GoogleCloudDataplexV1DataProfileResultProfileFieldProfileInfoDoubleFieldInfo {
/**
* Average of non-null values in the scanned data. NaN, if the field has a NaN.
*/
average?: number | null;
/**
* Maximum of non-null values in the scanned data. NaN, if the field has a NaN.
*/
max?: number | null;
/**
* Minimum of non-null values in the scanned data. NaN, if the field has a NaN.
*/
min?: number | null;
/**
* A quartile divides the number of data points into four parts, or quarters, of more-or-less equal size. Three main quartiles used are: The first quartile (Q1) splits off the lowest 25% of data from the highest 75%. It is also known as the lower or 25th empirical quartile, as 25% of the data is below this point. The second quartile (Q2) is the median of a data set. So, 50% of the data lies below this point. The third quartile (Q3) splits off the highest 25% of data from the lowest 75%. It is known as the upper or 75th empirical quartile, as 75% of the data lies below this point. Here, the quartiles is provided as an ordered list of quartile values for the scanned data, occurring in order Q1, median, Q3.
*/
quartiles?: number[] | null;
/**
* Standard deviation of non-null values in the scanned data. NaN, if the field has a NaN.
*/
standardDeviation?: number | null;
}
/**
* The profile information for an integer type field.
*/
export interface Schema$GoogleCloudDataplexV1DataProfileResultProfileFieldProfileInfoIntegerFieldInfo {
/**
* Average of non-null values in the scanned data. NaN, if the field has a NaN.
*/
average?: number | null;
/**
* Maximum of non-null values in the scanned data. NaN, if the field has a NaN.
*/
max?: string | null;
/**
* Minimum of non-null values in the scanned data. NaN, if the field has a NaN.
*/
min?: string | null;
/**
* A quartile divides the number of data points into four parts, or quarters, of more-or-less equal size. Three main quartiles used are: The first quartile (Q1) splits off the lowest 25% of data from the highest 75%. It is also known as the lower or 25th empirical quartile, as 25% of the data is below this point. The second quartile (Q2) is the median of a data set. So, 50% of the data lies below this point. The third quartile (Q3) splits off the highest 25% of data from the lowest 75%. It is known as the upper or 75th empirical quartile, as 75% of the data lies below this point. Here, the quartiles is provided as an ordered list of approximate quartile values for the scanned data, occurring in order Q1, median, Q3.
*/
quartiles?: string[] | null;
/**
* Standard deviation of non-null values in the scanned data. NaN, if the field has a NaN.
*/
standardDeviation?: number | null;
}
/**
* The profile information for a string type field.
*/
export interface Schema$GoogleCloudDataplexV1DataProfileResultProfileFieldProfileInfoStringFieldInfo {
/**
* Average length of non-null values in the scanned data.
*/
averageLength?: number | null;
/**
* Maximum length of non-null values in the scanned data.
*/
maxLength?: string | null;
/**
* Minimum length of non-null values in the scanned data.
*/
minLength?: string | null;
}
/**
* Top N non-null values in the scanned data.
*/
export interface Schema$GoogleCloudDataplexV1DataProfileResultProfileFieldProfileInfoTopNValue {
/**
* Count of the corresponding value in the scanned data.
*/
count?: string | null;
/**
* Ratio of the corresponding value in the field against the total number of rows in the scanned data.
*/
ratio?: number | null;
/**
* String value of a top N non-null value.
*/
value?: string | null;
}
/**
* DataProfileScan related setting.
*/
export interface Schema$GoogleCloudDataplexV1DataProfileSpec {
/**
* Optional. The fields to exclude from data profile.If specified, the fields will be excluded from data profile, regardless of include_fields value.
*/
excludeFields?: Schema$GoogleCloudDataplexV1DataProfileSpecSelectedFields;
/**
* Optional. The fields to include in data profile.If not specified, all fields at the time of profile scan job execution are included, except for ones listed in exclude_fields.
*/
includeFields?: Schema$GoogleCloudDataplexV1DataProfileSpecSelectedFields;
/**
* Optional. Actions to take upon job completion..
*/
postScanActions?: Schema$GoogleCloudDataplexV1DataProfileSpecPostScanActions;
/**
* Optional. A filter applied to all rows in a single DataScan job. The filter needs to be a valid SQL expression for a WHERE clause in BigQuery standard SQL syntax. Example: col1 \>= 0 AND col2 < 10
*/
rowFilter?: string | null;
/**
* Optional. The percentage of the records to be selected from the dataset for DataScan. Value can range between 0.0 and 100.0 with up to 3 significant decimal digits. Sampling is not applied if sampling_percent is not specified, 0 or 100.
*/
samplingPercent?: number | null;
}
/**
* The configuration of post scan actions of DataProfileScan job.
*/
export interface Schema$GoogleCloudDataplexV1DataProfileSpecPostScanActions {
/**
* Optional. If set, results will be exported to the provided BigQuery table.
*/
bigqueryExport?: Schema$GoogleCloudDataplexV1DataProfileSpecPostScanActionsBigQueryExport;
}
/**
* The configuration of BigQuery export post scan action.
*/
export interface Schema$GoogleCloudDataplexV1DataProfileSpecPostScanActionsBigQueryExport {
/**
* Optional. The BigQuery table to export DataProfileScan results to. Format: projects/{project\}/datasets/{dataset\}/tables/{table\}
*/
resultsTable?: string | null;
}
/**
* The specification for fields to include or exclude in data profile scan.
*/
export interface Schema$GoogleCloudDataplexV1DataProfileSpecSelectedFields {
/**
* Optional. Expected input is a list of fully qualified names of fields as in the schema.Only top-level field names for nested fields are supported. For instance, if 'x' is of nested field type, listing 'x' is supported but 'x.y.z' is not supported. Here 'y' and 'y.z' are nested fields of 'x'.
*/
fieldNames?: string[] | null;
}
/**
* DataQualityDimensionResult provides a more detailed, per-dimension view of the results.
*/
export interface Schema$GoogleCloudDataplexV1DataQualityDimensionResult {
/**
* Whether the dimension passed or failed.
*/
passed?: boolean | null;
}
/**
* The output of a DataQualityScan.
*/
export interface Schema$GoogleCloudDataplexV1DataQualityResult {
/**
* A list of results at the dimension level.
*/
dimensions?: Schema$GoogleCloudDataplexV1DataQualityDimensionResult[];
/**
* Overall data quality result -- true if all rules passed.
*/
passed?: boolean | null;
/**
* Output only. The result of post scan actions.
*/
postScanActionsResult?: Schema$GoogleCloudDataplexV1DataQualityResultPostScanActionsResult;
/**
* The count of rows processed.
*/
rowCount?: string | null;
/**
* A list of all the rules in a job, and their results.
*/
rules?: Schema$GoogleCloudDataplexV1DataQualityRuleResult[];
/**
* The data scanned for this result.
*/
scannedData?: Schema$GoogleCloudDataplexV1ScannedData;
}
/**
* The result of post scan actions of DataQualityScan job.
*/
export interface Schema$GoogleCloudDataplexV1DataQualityResultPostScanActionsResult {
/**
* Output only. The result of BigQuery export post scan action.
*/
bigqueryExportResult?: Schema$GoogleCloudDataplexV1DataQualityResultPostScanActionsResultBigQueryExportResult;
}
/**
* The result of BigQuery export post scan action.
*/
export interface Schema$GoogleCloudDataplexV1DataQualityResultPostScanActionsResultBigQueryExportResult {
/**
* Output only. Additional information about the BigQuery exporting.
*/
message?: string | null;
/**
* Output only. Execution state for the BigQuery exporting.
*/
state?: string | null;
}
/**
* A rule captures data quality intent about a data source.
*/
export interface Schema$GoogleCloudDataplexV1DataQualityRule {
/**
* Optional. The unnested column which this rule is evaluated against.
*/
column?: string | null;
/**
* Optional. Description of the rule. The maximum length is 1,024 characters.
*/
description?: string | null;
/**
* Required. The dimension a rule belongs to. Results are also aggregated at the dimension level. Supported dimensions are "COMPLETENESS", "ACCURACY", "CONSISTENCY", "VALIDITY", "UNIQUENESS", "INTEGRITY"
*/
dimension?: string | null;
/**
* Optional. Rows with null values will automatically fail a rule, unless ignore_null is true. In that case, such null rows are trivially considered passing.This field is only valid for row-level type rules.
*/
ignoreNull?: boolean | null;
/**
* Optional. A mutable name for the rule. The name must contain only letters (a-z, A-Z), numbers (0-9), or hyphens (-). The maximum length is 63 characters. Must start with a letter. Must end with a number or a letter.
*/
name?: string | null;
/**
* Row-level rule which evaluates whether each column value is null.
*/
nonNullExpectation?: Schema$GoogleCloudDataplexV1DataQualityRuleNonNullExpectation;
/**
* Row-level rule which evaluates whether each column value lies between a specified range.
*/
rangeExpectation?: Schema$GoogleCloudDataplexV1DataQualityRuleRangeExpectation;
/**
* Row-level rule which evaluates whether each column value matches a specified regex.
*/
regexExpectation?: Schema$GoogleCloudDataplexV1DataQualityRuleRegexExpectation;
/**
* Row-level rule which evaluates whether each row in a table passes the specified condition.
*/
rowConditionExpectation?: Schema$GoogleCloudDataplexV1DataQualityRuleRowConditionExpectation;
/**
* Row-level rule which evaluates whether each column value is contained by a specified set.
*/
setExpectation?: Schema$GoogleCloudDataplexV1DataQualityRuleSetExpectation;
/**
* Aggregate rule which evaluates whether the column aggregate statistic lies between a specified range.
*/
statisticRangeExpectation?: Schema$GoogleCloudDataplexV1DataQualityRuleStatisticRangeExpectation;
/**
* Aggregate rule which evaluates whether the provided expression is true for a table.
*/
tableConditionExpectation?: Schema$GoogleCloudDataplexV1DataQualityRuleTableConditionExpectation;
/**
* Optional. The minimum ratio of passing_rows / total_rows required to pass this rule, with a range of 0.0, 1.0.0 indicates default value (i.e. 1.0).This field is only valid for row-level type rules.
*/
threshold?: number | null;
/**
* Row-level rule which evaluates whether each column value is unique.
*/
uniquenessExpectation?: Schema$GoogleCloudDataplexV1DataQualityRuleUniquenessExpectation;
}
/**
* Evaluates whether each column value is null.
*/
export interface Schema$GoogleCloudDataplexV1DataQualityRuleNonNullExpectation {
}
/**
* Evaluates whether each column value lies between a specified range.
*/
export interface Schema$GoogleCloudDataplexV1DataQualityRuleRangeExpectation {
/**
* Optional. The maximum column value allowed for a row to pass this validation. At least one of min_value and max_value need to be provided.
*/
maxValue?: string | null;
/**
* Optional. The minimum column value allowed for a row to pass this validation. At least one of min_value and max_value need to be provided.
*/
minValue?: string | null;
/**
* Optional. Whether each value needs to be strictly lesser than ('<') the maximum, or if equality is allowed.Only relevant if a max_value has been defined. Default = false.
*/
strictMaxEnabled?: boolean | null;
/**
* Optional. Whether each value needs to be strictly greater than ('\>') the minimum, or if equality is allowed.Only relevant if a min_value has been defined. Default = false.
*/
strictMinEnabled?: boolean | null;
}
/**
* Evaluates whether each column value matches a specified regex.
*/
export interface Schema$GoogleCloudDataplexV1DataQualityRuleRegexExpectation {
/**
* Optional. A regular expression the column value is expected to match.
*/
regex?: string | null;
}
/**
* DataQualityRuleResult provides a more detailed, per-rule view of the results.
*/
export interface Schema$GoogleCloudDataplexV1DataQualityRuleResult {
/**
* The number of rows a rule was evaluated against.This field is only valid for row-level type rules.Evaluated count can be configured to either include all rows (default) - with null rows automatically failing rule evaluation, or exclude null rows from the evaluated_count, by setting ignore_nulls = true.
*/
evaluatedCount?: string | null;
/**
* The query to find rows that did not pass this rule.This field is only valid for row-level type rules.
*/
failingRowsQuery?: string | null;
/**
* The number of rows with null values in the specified column.
*/
nullCount?: string | null;
/**
* Whether the rule passed or failed.
*/
passed?: boolean | null;
/**
* The number of rows which passed a rule evaluation.This field is only valid for row-level type rules.
*/
passedCount?: string | null;
/**
* The ratio of passed_count / evaluated_count.This field is only valid for row-level type rules.
*/
passRatio?: number | null;
/**
* The rule specified in the DataQualitySpec, as is.
*/
rule?: Schema$GoogleCloudDataplexV1DataQualityRule;
}
/**
* Evaluates whether each row passes the specified condition.The SQL expression needs to use BigQuery standard SQL syntax and should produce a boolean value per row as the result.Example: col1 \>= 0 AND col2 < 10
*/
export interface Schema$GoogleCloudDataplexV1DataQualityRuleRowConditionExpectation {
/**
* Optional. The SQL expression.
*/
sqlExpression?: string | null;
}
/**
* Evaluates whether each column value is contained by a specified set.
*/
export interface Schema$GoogleCloudDataplexV1DataQualityRuleSetExpectation {
/**
* Optional. Expected values for the column value.
*/
values?: string[] | null;
}
/**
* Evaluates whether the column aggregate statistic lies between a specified range.
*/
export interface Schema$GoogleCloudDataplexV1DataQualityRuleStatisticRangeExpectation {
/**
* Optional. The maximum column statistic value allowed for a row to pass this validation.At least one of min_value and max_value need to be provided.
*/
maxValue?: string | null;
/**
* Optional. The minimum column statistic value allowed for a row to pass this validation.At least one of min_value and max_value need to be provided.
*/
minValue?: string | null;
/**
* Optional. The aggregate metric to evaluate.
*/
statistic?: string | null;
/**
* Optional. Whether column statistic needs to be strictly lesser than ('<') the maximum, or if equality is allowed.Only relevant if a max_value has been defined. Default = false.
*/
strictMaxEnabled?: boolean | null;
/**
* Optional. Whether column statistic needs to be strictly greater than ('\>') the minimum, or if equality is allowed.Only relevant if a min_value has been defined. Defaul